Merge branch 'v3.10/topic/arm64-errata' into linux-linaro-lsk-v3.10
* v3.10/topic/arm64-errata:
arm64: errata: add workaround for cortex-a53 erratum #845719
arm64: Remove unused cpu_name ascii in arch/arm64/mm/proc.S
diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram
index ec93fe3..0c7f4f9 100644
--- a/Documentation/ABI/testing/sysfs-block-zram
+++ b/Documentation/ABI/testing/sysfs-block-zram
@@ -42,15 +42,48 @@
The invalid_io file is read-only and specifies the number of
non-page-size-aligned I/O requests issued to this device.
+What: /sys/block/zram<id>/failed_reads
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_reads file is read-only and specifies the number of
+ failed reads happened on this device.
+
+What: /sys/block/zram<id>/failed_writes
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The failed_writes file is read-only and specifies the number of
+ failed writes happened on this device.
+
+What: /sys/block/zram<id>/max_comp_streams
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The max_comp_streams file is read-write and specifies the
+ number of backend's zcomp_strm compression streams (number of
+ concurrent compress operations).
+
+What: /sys/block/zram<id>/comp_algorithm
+Date: February 2014
+Contact: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
+Description:
+ The comp_algorithm file is read-write and lets to show
+ available and selected compression algorithms, change
+ compression algorithm selection.
+
What: /sys/block/zram<id>/notify_free
Date: August 2010
Contact: Nitin Gupta <ngupta@vflare.org>
Description:
- The notify_free file is read-only and specifies the number of
- swap slot free notifications received by this device. These
- notifications are send to a swap block device when a swap slot
- is freed. This statistic is applicable only when this disk is
- being used as a swap disk.
+ The notify_free file is read-only. Depending on device usage
+ scenario it may account a) the number of pages freed because
+ of swap slot free notifications or b) the number of pages freed
+ because of REQ_DISCARD requests sent by bio. The former ones
+ are sent to a swap block device when a swap slot is freed, which
+ implies that this disk is being used as a swap disk. The latter
+ ones are sent by filesystem mounted with discard option,
+ whenever some data blocks are getting discarded.
What: /sys/block/zram<id>/discard
Date: August 2010
@@ -97,3 +130,22 @@
efficiency can be calculated using compr_data_size and this
statistic.
Unit: bytes
+
+What: /sys/block/zram<id>/mem_used_max
+Date: August 2014
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The mem_used_max file is read/write and specifies the amount
+ of maximum memory zram have consumed to store compressed data.
+ For resetting the value, you should write "0". Otherwise,
+ you could see -EINVAL.
+ Unit: bytes
+
+What: /sys/block/zram<id>/mem_limit
+Date: August 2014
+Contact: Minchan Kim <minchan@kernel.org>
+Description:
+ The mem_limit file is read/write and specifies the maximum
+ amount of memory ZRAM can use to store the compressed data. The
+ limit could be changed in run time and "0" means disable the
+ limit. No limit is the initial state. Unit: bytes
diff --git a/Documentation/ABI/testing/sysfs-firmware-ofw b/Documentation/ABI/testing/sysfs-firmware-ofw
new file mode 100644
index 0000000..f562b18
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-ofw
@@ -0,0 +1,28 @@
+What: /sys/firmware/devicetree/*
+Date: November 2013
+Contact: Grant Likely <grant.likely@linaro.org>
+Description:
+ When using OpenFirmware or a Flattened Device Tree to enumerate
+ hardware, the device tree structure will be exposed in this
+ directory.
+
+ It is possible for multiple device-tree directories to exist.
+ Some device drivers use a separate detached device tree which
+ have no attachment to the system tree and will appear in a
+ different subdirectory under /sys/firmware/devicetree.
+
+ Userspace must not use the /sys/firmware/devicetree/base
+ path directly, but instead should follow /proc/device-tree
+ symlink. It is possible that the absolute path will change
+ in the future, but the symlink is the stable ABI.
+
+ The /proc/device-tree symlink replaces the devicetree /proc
+ filesystem support, and has largely the same semantics and
+ should be compatible with existing userspace.
+
+ The contents of /sys/firmware/devicetree/ is a
+ hierarchy of directories, one per device tree node. The
+ directory name is the resolved path component name (node
+ name plus address). Properties are represented as files
+ in the directory. The contents of each file is the exact
+ binary data from the device tree.
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 14129f1..5e98303 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -101,14 +101,23 @@
because this shows that you did think about these issues wrt. your
device.
-The query is performed via a call to dma_set_mask():
+The query is performed via a call to dma_set_mask_and_coherent():
- int dma_set_mask(struct device *dev, u64 mask);
+ int dma_set_mask_and_coherent(struct device *dev, u64 mask);
-The query for consistent allocations is performed via a call to
-dma_set_coherent_mask():
+which will query the mask for both streaming and coherent APIs together.
+If you have some special requirements, then the following two separate
+queries can be used instead:
- int dma_set_coherent_mask(struct device *dev, u64 mask);
+ The query for streaming mappings is performed via a call to
+ dma_set_mask():
+
+ int dma_set_mask(struct device *dev, u64 mask);
+
+ The query for consistent allocations is performed via a call
+ to dma_set_coherent_mask():
+
+ int dma_set_coherent_mask(struct device *dev, u64 mask);
Here, dev is a pointer to the device struct of your device, and mask
is a bit mask describing which bits of an address your device
@@ -137,7 +146,7 @@
The standard 32-bit addressing device would do something like this:
- if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
+ if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
printk(KERN_WARNING
"mydev: No suitable DMA available.\n");
goto ignore_this_device;
@@ -171,22 +180,20 @@
int using_dac, consistent_using_dac;
- if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
+ if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
using_dac = 1;
consistent_using_dac = 1;
- dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
- } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
+ } else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
using_dac = 0;
consistent_using_dac = 0;
- dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
} else {
printk(KERN_WARNING
"mydev: No suitable DMA available.\n");
goto ignore_this_device;
}
-dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as dma_set_mask(). However for the rare case that a
+The coherent coherent mask will always be able to set the same or a
+smaller mask as the streaming mask. However for the rare case that a
device driver only uses consistent allocations, one would have to
check the return value from dma_set_coherent_mask().
@@ -199,9 +206,9 @@
goto ignore_this_device;
}
-When dma_set_mask() is successful, and returns zero, the kernel saves
-away this mask you have provided. The kernel will use this
-information later when you make DMA mappings.
+When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
+returns zero, the kernel saves away this mask you have provided. The
+kernel will use this information later when you make DMA mappings.
There is a case which we are aware of at this time, which is worth
mentioning in this documentation. If your device supports multiple
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 78a6c56..e865279 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -142,6 +142,14 @@
driver writers.
int
+dma_set_mask_and_coherent(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+streaming and coherent DMA mask parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
+int
dma_set_mask(struct device *dev, u64 mask)
Checks to see if the mask is possible and updates the device
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index f9fd615..1d27f0a 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -195,7 +195,7 @@
#
install_media_images = \
- $(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+ $(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
$(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
$(Q)base64 -d $< >$@
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 6a8b715..9c92bb8 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -1,6 +1,6 @@
<?xml version="1.0"?>
-<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
- "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" [
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.2//EN"
+ "http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd" [
<!ENTITY % media-entities SYSTEM "./media-entities.tmpl"> %media-entities;
<!ENTITY media-indices SYSTEM "./media-indices.tmpl">
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 6e97e73..4dbba7e 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -131,6 +131,20 @@
then only post say 15 or so at a time and wait for review and integration.
+If your patch fixes a bug in a specific commit, e.g. you found an issue using
+git-bisect, please use the 'Fixes:' tag with the first 12 characters of the
+SHA-1 ID, and the one line summary.
+Example:
+
+ Fixes: e21d2170f366 ("video: remove unnecessary platform_set_drvdata()")
+
+The following git-config settings can be used to add a pretty format for
+outputting the above style in the git log or git show commands
+
+ [core]
+ abbrev = 12
+ [pretty]
+ fixes = Fixes: %h (\"%s\")
4) Style check your changes.
@@ -420,7 +434,7 @@
have been included in the discussion
-14) Using Reported-by:, Tested-by:, Reviewed-by: and Suggested-by:
+14) Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes:
If this patch fixes a problem reported by somebody else, consider adding a
Reported-by: tag to credit the reporter for their contribution. Please
@@ -475,6 +489,12 @@
idea reporters, they will, hopefully, be inspired to help us again in the
future.
+A Fixes: tag indicates that the patch fixes an issue in a previous commit. It
+is used to make it easy to determine where a bug originated, which can help
+review a bug fix. This tag also assists the stable kernel team in determining
+which stable kernel versions should receive your fix. This is the preferred
+method for indicating a bug fixed by the patch. See #2 above for more details.
+
15) The canonical patch format
diff --git a/Documentation/arm/small_task_packing.txt b/Documentation/arm/small_task_packing.txt
new file mode 100644
index 0000000..43f0a8b8
--- /dev/null
+++ b/Documentation/arm/small_task_packing.txt
@@ -0,0 +1,136 @@
+Small Task Packing in the big.LITTLE MP Reference Patch Set
+
+What is small task packing?
+----
+Simply that the scheduler will fit as many small tasks on a single CPU
+as possible before using other CPUs. A small task is defined as one
+whose tracked load is less than 90% of a NICE_0 task. This is a change
+from the usual behavior since the scheduler will normally use an idle
+CPU for a waking task unless that task is considered cache hot.
+
+
+How is it implemented?
+----
+Since all small tasks must wake up relatively frequently, the main
+requirement for packing small tasks is to select a partly-busy CPU when
+waking rather than looking for an idle CPU. We use the tracked load of
+the CPU runqueue to determine how heavily loaded each CPU is and the
+tracked load of the task to determine if it will fit on the CPU. We
+always start with the lowest-numbered CPU in a sched domain and stop
+looking when we find a CPU with enough space for the task.
+
+Some further tweaks are necessary to suppress load balancing when the
+CPU is not fully loaded, otherwise the scheduler attempts to spread
+tasks evenly across the domain.
+
+
+How does it interact with the HMP patches?
+----
+Firstly, we only enable packing on the little domain. The intent is that
+the big domain is intended to spread tasks amongst the available CPUs
+one-task-per-CPU. The little domain however is attempting to use as
+little power as possible while servicing its tasks.
+
+Secondly, since we offload big tasks onto little CPUs in order to try
+to devote one CPU to each task, we have a threshold above which we do
+not try to pack a task and instead will select an idle CPU if possible.
+This maintains maximum forward progress for busy tasks temporarily
+demoted from big CPUs.
+
+
+Can the behaviour be tuned?
+----
+Yes, the load level of a 'full' CPU can be easily modified in the source
+and is exposed through sysfs as /sys/kernel/hmp/packing_limit to be
+changed at runtime. The presence of the packing behaviour is controlled
+by CONFIG_SCHED_HMP_LITTLE_PACKING and can be disabled at run-time
+using /sys/kernel/hmp/packing_enable.
+The definition of a small task is hard coded as 90% of NICE_0_LOAD
+and cannot be modified at run time.
+
+
+Why do I need to tune it?
+----
+The optimal configuration is likely to be different depending upon the
+design and manufacturing of your SoC.
+
+In the main, there are two system effects from enabling small task
+packing.
+
+1. CPU operating point may increase
+2. wakeup latency of tasks may be increased
+
+There are also likely to be secondary effects from loading one CPU
+rather than spreading tasks.
+
+Note that all of these system effects are dependent upon the workload
+under consideration.
+
+
+CPU Operating Point
+----
+The primary impact of loading one CPU with a number of light tasks is to
+increase the compute requirement of that CPU since it is no longer idle
+as often. Increased compute requirement causes an increase in the
+frequency of the CPU through CPUfreq.
+
+Consider this example:
+We have a system with 3 CPUs which can operate at any frequency between
+350MHz and 1GHz. The system has 6 tasks which would each produce 10%
+load at 1GHz. The scheduler has frequency-invariant load scaling
+enabled. Our DVFS governor aims for 80% utilization at the chosen
+frequency.
+
+Without task packing, these tasks will be spread out amongst all CPUs
+such that each has 2. This will produce roughly 20% system load, and
+the frequency of the package will remain at 350MHz.
+
+With task packing set to the default packing_limit, all of these tasks
+will sit on one CPU and require a package frequency of ~750MHz to reach
+80% utilization. (0.75 = 0.6 * 0.8).
+
+When a package operates on a single frequency domain, all CPUs in that
+package share frequency and voltage.
+
+Depending upon the SoC implementation there can be a significant amount
+of energy lost to leakage from idle CPUs. The decision about how
+loaded a CPU must be to be considered 'full' is therefore controllable
+through sysfs (sys/kernel/hmp/packing_limit) and directly in the code.
+
+Continuing the example, lets set packing_limit to 450 which means we
+will pack tasks until the total load of all running tasks >= 450. In
+practise, this is very similar to a 55% idle 1Ghz CPU.
+
+Now we are only able to place 4 tasks on CPU0, and two will overflow
+onto CPU1. CPU0 will have a load of 40% and CPU1 will have a load of
+20%. In order to still hit 80% utilization, CPU0 now only needs to
+operate at (0.4*0.8=0.32) 320MHz, which means that the lowest operating
+point will be selected, the same as in the non-packing case, except that
+now CPU2 is no longer needed and can be power-gated.
+
+In order to use less energy, the saving from power-gating CPU2 must be
+more than the energy spent running CPU0 for the extra cycles. This
+depends upon the SoC implementation.
+
+This is obviously a contrived example requiring all the tasks to
+be runnable at the same time, but it illustrates the point.
+
+
+Wakeup Latency
+----
+This is an unavoidable consequence of trying to pack tasks together
+rather than giving them a CPU each. If you cannot find an acceptable
+level of wakeup latency, you should turn packing off.
+
+Cyclictest is a good test application for determining the added latency
+when configuring packing.
+
+
+Why is it turned off for the VersatileExpress V2P_CA15A7 CoreTile?
+----
+Simply, this core tile only has power gating for the whole A7 package.
+When small task packing is enabled, all our low-energy use cases
+normally fit onto one A7 CPU. We therefore end up with 2 mostly-idle
+CPUs and one mostly-busy CPU. This decreases the amount of time
+available where the whole package is idle and can be turned off.
+
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 9c4d388..1b0c968 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -68,13 +68,23 @@
Requirement: MANDATORY
-The decompressed kernel image contains a 32-byte header as follows:
+The decompressed kernel image contains a 64-byte header as follows:
- u32 magic = 0x14000008; /* branch to stext, little-endian */
- u32 res0 = 0; /* reserved */
+ u32 code0; /* Executable code */
+ u32 code1; /* Executable code */
u64 text_offset; /* Image load offset */
+ u64 res0 = 0; /* reserved */
u64 res1 = 0; /* reserved */
u64 res2 = 0; /* reserved */
+ u64 res3 = 0; /* reserved */
+ u64 res4 = 0; /* reserved */
+ u32 magic = 0x644d5241; /* Magic number, little endian, "ARM\x64" */
+ u32 res5 = 0; /* reserved */
+
+
+Header notes:
+
+- code0/code1 are responsible for branching to stext.
The image must be placed at the specified offset (currently 0x80000)
from the start of the system RAM and called there. The start of the
@@ -101,8 +111,14 @@
- Caches, MMUs
The MMU must be off.
Instruction cache may be on or off.
- Data cache must be off and invalidated.
- External caches (if present) must be configured and disabled.
+ The address range corresponding to the loaded kernel image must be
+ cleaned to the PoC. In the presence of a system cache or other
+ coherent masters with caches enabled, this will typically require
+ cache maintenance by VA rather than set/way operations.
+ System caches which respect the architected cache maintenance by VA
+ operations must be configured and may be enabled.
+ System caches which do not respect architected cache maintenance by VA
+ operations (not recommended) must be configured and disabled.
- Architected timers
CNTFRQ must be programmed with the timer frequency.
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 5f583af..d50fa61 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -21,7 +21,7 @@
TTBR0.
-AArch64 Linux memory layout:
+AArch64 Linux memory layout with 4KB pages:
Start End Size Use
-----------------------------------------------------------------------
@@ -35,17 +35,46 @@
ffffffbe00000000 ffffffbffbbfffff ~8GB [guard, future vmmemap]
-ffffffbffbc00000 ffffffbffbdfffff 2MB earlyprintk device
+ffffffbffa000000 ffffffbffaffffff 16MB PCI I/O space
-ffffffbffbe00000 ffffffbffbe0ffff 64KB PCI I/O space
+ffffffbffb000000 ffffffbffbbfffff 12MB [guard]
-ffffffbbffff0000 ffffffbcffffffff ~2MB [guard]
+ffffffbffbc00000 ffffffbffbdfffff 2MB fixed mappings
+
+ffffffbffbe00000 ffffffbffbffffff 2MB [guard]
ffffffbffc000000 ffffffbfffffffff 64MB modules
ffffffc000000000 ffffffffffffffff 256GB kernel logical memory map
+AArch64 Linux memory layout with 64KB pages:
+
+Start End Size Use
+-----------------------------------------------------------------------
+0000000000000000 000003ffffffffff 4TB user
+
+fffffc0000000000 fffffdfbfffeffff ~2TB vmalloc
+
+fffffdfbffff0000 fffffdfbffffffff 64KB [guard page]
+
+fffffdfc00000000 fffffdfdffffffff 8GB vmemmap
+
+fffffdfe00000000 fffffdfffbbfffff ~8GB [guard, future vmmemap]
+
+fffffdfffa000000 fffffdfffaffffff 16MB PCI I/O space
+
+fffffdfffb000000 fffffdfffbbfffff 12MB [guard]
+
+fffffdfffbc00000 fffffdfffbdfffff 2MB fixed mappings
+
+fffffdfffbe00000 fffffdfffbffffff 2MB [guard]
+
+fffffdfffc000000 fffffdffffffffff 64MB modules
+
+fffffe0000000000 ffffffffffffffff 2TB kernel logical memory map
+
+
Translation table lookup with 4KB pages:
+--------+--------+--------+--------+--------+--------+--------+--------+
@@ -73,3 +102,10 @@
| | +--------------------------> [41:29] L2 index (only 38:29 used)
| +-------------------------------> [47:42] L1 index (not used)
+-------------------------------------------------> [63] TTBR0/1
+
+When using KVM, the hypervisor maps kernel pages in EL2, at a fixed
+offset from the kernel VA (top 24bits of the kernel VA set to zero):
+
+Start End Size Use
+-----------------------------------------------------------------------
+0000004000000000 0000007fffffffff 256GB kernel objects mapped in HYP
diff --git a/Documentation/arm64/tagged-pointers.txt b/Documentation/arm64/tagged-pointers.txt
new file mode 100644
index 0000000..d9995f1
--- /dev/null
+++ b/Documentation/arm64/tagged-pointers.txt
@@ -0,0 +1,34 @@
+ Tagged virtual addresses in AArch64 Linux
+ =========================================
+
+Author: Will Deacon <will.deacon@arm.com>
+Date : 12 June 2013
+
+This document briefly describes the provision of tagged virtual
+addresses in the AArch64 translation system and their potential uses
+in AArch64 Linux.
+
+The kernel configures the translation tables so that translations made
+via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
+the virtual address ignored by the translation hardware. This frees up
+this byte for application use, with the following caveats:
+
+ (1) The kernel requires that all user addresses passed to EL1
+ are tagged with tag 0x00. This means that any syscall
+ parameters containing user virtual addresses *must* have
+ their top byte cleared before trapping to the kernel.
+
+ (2) Non-zero tags are not preserved when delivering signals.
+ This means that signal handlers in applications making use
+ of tags cannot rely on the tag information for user virtual
+ addresses being maintained for fields inside siginfo_t.
+ One exception to this rule is for signals raised in response
+ to watchpoint debug exceptions, where the tag information
+ will be preserved.
+
+ (3) Special care should be taken when using tagged pointers,
+ since it is likely that C compilers will not hazard two
+ virtual addresses differing only in the upper byte.
+
+The architecture prevents the use of a tagged PC, so the upper byte will
+be set to a sign-extension of bit 55 on exception return.
diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt
new file mode 100644
index 0000000..5cd0bd9
--- /dev/null
+++ b/Documentation/blockdev/zram.txt
@@ -0,0 +1,129 @@
+zram: Compressed RAM based block devices
+----------------------------------------
+
+* Introduction
+
+The zram module creates RAM based block devices named /dev/zram<id>
+(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
+in memory itself. These disks allow very fast I/O and compression provides
+good amounts of memory savings. Some of the usecases include /tmp storage,
+use as swap disks, various caches under /var and maybe many more :)
+
+Statistics for individual zram devices are exported through sysfs nodes at
+/sys/block/zram<id>/
+
+* Usage
+
+Following shows a typical sequence of steps for using zram.
+
+1) Load Module:
+ modprobe zram num_devices=4
+ This creates 4 devices: /dev/zram{0,1,2,3}
+ (num_devices parameter is optional. Default: 1)
+
+2) Set max number of compression streams
+ Compression backend may use up to max_comp_streams compression streams,
+ thus allowing up to max_comp_streams concurrent compression operations.
+ By default, compression backend uses single compression stream.
+
+ Examples:
+ #show max compression streams number
+ cat /sys/block/zram0/max_comp_streams
+
+ #set max compression streams number to 3
+ echo 3 > /sys/block/zram0/max_comp_streams
+
+Note:
+In order to enable compression backend's multi stream support max_comp_streams
+must be initially set to desired concurrency level before ZRAM device
+initialisation. Once the device initialised as a single stream compression
+backend (max_comp_streams equals to 1), you will see error if you try to change
+the value of max_comp_streams because single stream compression backend
+implemented as a special case by lock overhead issue and does not support
+dynamic max_comp_streams. Only multi stream backend supports dynamic
+max_comp_streams adjustment.
+
+3) Select compression algorithm
+ Using comp_algorithm device attribute one can see available and
+ currently selected (shown in square brackets) compression algortithms,
+ change selected compression algorithm (once the device is initialised
+ there is no way to change compression algorithm).
+
+ Examples:
+ #show supported compression algorithms
+ cat /sys/block/zram0/comp_algorithm
+ lzo [lz4]
+
+ #select lzo compression algorithm
+ echo lzo > /sys/block/zram0/comp_algorithm
+
+4) Set Disksize
+ Set disk size by writing the value to sysfs node 'disksize'.
+ The value can be either in bytes or you can use mem suffixes.
+ Examples:
+ # Initialize /dev/zram0 with 50MB disksize
+ echo $((50*1024*1024)) > /sys/block/zram0/disksize
+
+ # Using mem suffixes
+ echo 256K > /sys/block/zram0/disksize
+ echo 512M > /sys/block/zram0/disksize
+ echo 1G > /sys/block/zram0/disksize
+
+Note:
+There is little point creating a zram of greater than twice the size of memory
+since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the
+size of the disk when not in use so a huge zram is wasteful.
+
+5) Set memory limit: Optional
+ Set memory limit by writing the value to sysfs node 'mem_limit'.
+ The value can be either in bytes or you can use mem suffixes.
+ In addition, you could change the value in runtime.
+ Examples:
+ # limit /dev/zram0 with 50MB memory
+ echo $((50*1024*1024)) > /sys/block/zram0/mem_limit
+
+ # Using mem suffixes
+ echo 256K > /sys/block/zram0/mem_limit
+ echo 512M > /sys/block/zram0/mem_limit
+ echo 1G > /sys/block/zram0/mem_limit
+
+ # To disable memory limit
+ echo 0 > /sys/block/zram0/mem_limit
+
+6) Activate:
+ mkswap /dev/zram0
+ swapon /dev/zram0
+
+ mkfs.ext4 /dev/zram1
+ mount /dev/zram1 /tmp
+
+7) Stats:
+ Per-device statistics are exported as various nodes under
+ /sys/block/zram<id>/
+ disksize
+ num_reads
+ num_writes
+ invalid_io
+ notify_free
+ discard
+ zero_pages
+ orig_data_size
+ compr_data_size
+ mem_used_total
+ mem_used_max
+
+8) Deactivate:
+ swapoff /dev/zram0
+ umount /dev/zram1
+
+9) Reset:
+ Write any positive value to 'reset' sysfs node
+ echo 1 > /sys/block/zram0/reset
+ echo 1 > /sys/block/zram1/reset
+
+ This frees all the memory allocated for the given device and
+ resets the disksize to zero. You must set the disksize again
+ before reusing the device.
+
+Nitin Gupta
+ngupta@vflare.org
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index 20746e5..06fc760 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -1,10 +1,14 @@
* ARM architected timer
-ARM cores may have a per-core architected timer, which provides per-cpu timers.
+ARM cores may have a per-core architected timer, which provides per-cpu timers,
+or a memory mapped architected timer, which provides up to 8 frames with a
+physical and optional virtual timer per frame.
-The timer is attached to a GIC to deliver its per-processor interrupts.
+The per-core architected timer is attached to a GIC to deliver its
+per-processor interrupts via PPIs. The memory mapped timer is attached to a GIC
+to deliver its interrupts via SPIs.
-** Timer node properties:
+** CP15 Timer node properties:
- compatible : Should at least contain one of
"arm,armv7-timer"
@@ -26,3 +30,52 @@
<1 10 0xf08>;
clock-frequency = <100000000>;
};
+
+** Memory mapped timer node properties:
+
+- compatible : Should at least contain "arm,armv7-timer-mem".
+
+- clock-frequency : The frequency of the main counter, in Hz. Optional.
+
+- reg : The control frame base address.
+
+Note that #address-cells, #size-cells, and ranges shall be present to ensure
+the CPU can address a frame's registers.
+
+A timer node has up to 8 frame sub-nodes, each with the following properties:
+
+- frame-number: 0 to 7.
+
+- interrupts : Interrupt list for physical and virtual timers in that order.
+ The virtual timer interrupt is optional.
+
+- reg : The first and second view base addresses in that order. The second view
+ base address is optional.
+
+- status : "disabled" indicates the frame is not available for use. Optional.
+
+Example:
+
+ timer@f0000000 {
+ compatible = "arm,armv7-timer-mem";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges;
+ reg = <0xf0000000 0x1000>;
+ clock-frequency = <50000000>;
+
+ frame@f0001000 {
+ frame-number = <0>
+ interrupts = <0 13 0x8>,
+ <0 14 0x8>;
+ reg = <0xf0001000 0x1000>,
+ <0xf0002000 0x1000>;
+ };
+
+ frame@f0003000 {
+ frame-number = <1>
+ interrupts = <0 15 0x8>;
+ reg = <0xf0003000 0x1000>;
+ status = "disabled";
+ };
+ };
diff --git a/Documentation/devicetree/bindings/arm/cci.txt b/Documentation/devicetree/bindings/arm/cci.txt
new file mode 100644
index 0000000..92d36e2
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/cci.txt
@@ -0,0 +1,172 @@
+=======================================================
+ARM CCI cache coherent interconnect binding description
+=======================================================
+
+ARM multi-cluster systems maintain intra-cluster coherency through a
+cache coherent interconnect (CCI) that is capable of monitoring bus
+transactions and manage coherency, TLB invalidations and memory barriers.
+
+It allows snooping and distributed virtual memory message broadcast across
+clusters, through memory mapped interface, with a global control register
+space and multiple sets of interface control registers, one per slave
+interface.
+
+Bindings for the CCI node follow the ePAPR standard, available from:
+
+www.power.org/documentation/epapr-version-1-1/
+
+with the addition of the bindings described in this document which are
+specific to ARM.
+
+* CCI interconnect node
+
+ Description: Describes a CCI cache coherent Interconnect component
+
+ Node name must be "cci".
+ Node's parent must be the root node /, and the address space visible
+ through the CCI interconnect is the same as the one seen from the
+ root node (ie from CPUs perspective as per DT standard).
+ Every CCI node has to define the following properties:
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: must be set to
+ "arm,cci-400"
+
+ - reg
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. Specifies base physical
+ address of CCI control registers common to all
+ interfaces.
+
+ - ranges:
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: A standard property. Follow rules in the ePAPR for
+ hierarchical bus addressing. CCI interfaces
+ addresses refer to the parent node addressing
+ scheme to declare their register bases.
+
+ CCI interconnect node can define the following child nodes:
+
+ - CCI control interface nodes
+
+ Node name must be "slave-if".
+ Parent node must be CCI interconnect node.
+
+ A CCI control interface node must contain the following
+ properties:
+
+ - compatible
+ Usage: required
+ Value type: <string>
+ Definition: must be set to
+ "arm,cci-400-ctrl-if"
+
+ - interface-type:
+ Usage: required
+ Value type: <string>
+ Definition: must be set to one of {"ace", "ace-lite"}
+ depending on the interface type the node
+ represents.
+
+ - reg:
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: the base address and size of the
+ corresponding interface programming
+ registers.
+
+* CCI interconnect bus masters
+
+ Description: masters in the device tree connected to a CCI port
+ (inclusive of CPUs and their cpu nodes).
+
+ A CCI interconnect bus master node must contain the following
+ properties:
+
+ - cci-control-port:
+ Usage: required
+ Value type: <phandle>
+ Definition: a phandle containing the CCI control interface node
+ the master is connected to.
+
+Example:
+
+ cpus {
+ #size-cells = <0>;
+ #address-cells = <1>;
+
+ CPU0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ cci-control-port = <&cci_control1>;
+ reg = <0x0>;
+ };
+
+ CPU1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ cci-control-port = <&cci_control1>;
+ reg = <0x1>;
+ };
+
+ CPU2: cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ cci-control-port = <&cci_control2>;
+ reg = <0x100>;
+ };
+
+ CPU3: cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ cci-control-port = <&cci_control2>;
+ reg = <0x101>;
+ };
+
+ };
+
+ dma0: dma@3000000 {
+ compatible = "arm,pl330", "arm,primecell";
+ cci-control-port = <&cci_control0>;
+ reg = <0x0 0x3000000 0x0 0x1000>;
+ interrupts = <10>;
+ #dma-cells = <1>;
+ #dma-channels = <8>;
+ #dma-requests = <32>;
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0x0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x6000>;
+
+ cci_control0: slave-if@1000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace-lite";
+ reg = <0x1000 0x1000>;
+ };
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+This CCI node corresponds to a CCI component whose control registers sits
+at address 0x000000002c090000.
+CCI slave interface @0x000000002c091000 is connected to dma controller dma0.
+CCI slave interface @0x000000002c094000 is connected to CPUs {CPU0, CPU1};
+CCI slave interface @0x000000002c095000 is connected to CPUs {CPU2, CPU3};
diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt
new file mode 100644
index 0000000..a308935
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/coresight.txt
@@ -0,0 +1,200 @@
+* CoreSight Components:
+
+CoreSight components are compliant with the ARM CoreSight architecture
+specification and can be connected in various topologies to suit a particular
+SoCs tracing needs. These trace components can generally be classified as
+sinks, links and sources. Trace data produced by one or more sources flows
+through the intermediate links connecting the source to the currently selected
+sink. Each CoreSight component device should use these properties to describe
+its hardware characteristcs.
+
+* Required properties for all components *except* non-configurable replicators:
+
+ * compatible: These have to be supplemented with "arm,primecell" as
+ drivers are using the AMBA bus interface. Possible values include:
+ - "arm,coresight-etb10", "arm,primecell";
+ - "arm,coresight-tpiu", "arm,primecell";
+ - "arm,coresight-tmc", "arm,primecell";
+ - "arm,coresight-funnel", "arm,primecell";
+ - "arm,coresight-etm3x", "arm,primecell";
+
+ * reg: physical base address and length of the register
+ set(s) of the component.
+
+ * clocks: the clock associated to this component.
+
+ * clock-names: the name of the clock as referenced by the code.
+ Since we are using the AMBA framework, the name should be
+ "apb_pclk".
+
+ * port or ports: The representation of the component's port
+ layout using the generic DT graph presentation found in
+ "bindings/graph.txt".
+
+* Required properties for devices that don't show up on the AMBA bus, such as
+ non-configurable replicators:
+
+ * compatible: Currently supported value is (note the absence of the
+ AMBA markee):
+ - "arm,coresight-replicator"
+
+ * port or ports: same as above.
+
+* Optional properties for ETM/PTMs:
+
+ * arm,cp14: must be present if the system accesses ETM/PTM management
+ registers via co-processor 14.
+
+ * cpu: the cpu phandle this ETM/PTM is affined to. When omitted the
+ source is considered to belong to CPU0.
+
+* Optional property for TMC:
+
+ * arm,buffer-size: size of contiguous buffer space for TMC ETR
+ (embedded trace router)
+
+
+Example:
+
+1. Sinks
+ etb@20010000 {
+ compatible = "arm,coresight-etb10", "arm,primecell";
+ reg = <0 0x20010000 0 0x1000>;
+
+ coresight-default-sink;
+ clocks = <&oscclk6a>;
+ clock-names = "apb_pclk";
+ port {
+ etb_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator_out_port0>;
+ };
+ };
+ };
+
+ tpiu@20030000 {
+ compatible = "arm,coresight-tpiu", "arm,primecell";
+ reg = <0 0x20030000 0 0x1000>;
+
+ clocks = <&oscclk6a>;
+ clock-names = "apb_pclk";
+ port {
+ tpiu_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator_out_port1>;
+ };
+ };
+ };
+
+2. Links
+ replicator {
+ /* non-configurable replicators don't show up on the
+ * AMBA bus. As such no need to add "arm,primecell".
+ */
+ compatible = "arm,coresight-replicator";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* replicator output ports */
+ port@0 {
+ reg = <0>;
+ replicator_out_port0: endpoint {
+ remote-endpoint = <&etb_in_port>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+ replicator_out_port1: endpoint {
+ remote-endpoint = <&tpiu_in_port>;
+ };
+ };
+
+ /* replicator input port */
+ port@2 {
+ reg = <0>;
+ replicator_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&funnel_out_port0>;
+ };
+ };
+ };
+ };
+
+ funnel@20040000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0x20040000 0 0x1000>;
+
+ clocks = <&oscclk6a>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel_out_port0: endpoint {
+ remote-endpoint =
+ <&replicator_in_port0>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm0_out_port>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm1_out_port>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint = <&etm0_out_port>;
+ };
+ };
+
+ };
+ };
+
+3. Sources
+ ptm@2201c000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0x2201c000 0 0x1000>;
+
+ cpu = <&cpu0>;
+ clocks = <&oscclk6a>;
+ clock-names = "apb_pclk";
+ port {
+ ptm0_out_port: endpoint {
+ remote-endpoint = <&funnel_in_port0>;
+ };
+ };
+ };
+
+ ptm@2201d000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0x2201d000 0 0x1000>;
+
+ cpu = <&cpu1>;
+ clocks = <&oscclk6a>;
+ clock-names = "apb_pclk";
+ port {
+ ptm1_out_port: endpoint {
+ remote-endpoint = <&funnel_in_port1>;
+ };
+ };
+ };
diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
index 3dfb0c0..5357745 100644
--- a/Documentation/devicetree/bindings/arm/gic.txt
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -49,6 +49,11 @@
regions, used when the GIC doesn't have banked registers. The offset is
cpu-offset * cpu-nr.
+- arm,routable-irqs : Total number of gic irq inputs which are not directly
+ connected from the peripherals, but are routed dynamically
+ by a crossbar/multiplexer preceding the GIC. The GIC irq
+ input line is assigned dynamically when the corresponding
+ peripheral's crossbar line is mapped.
Example:
intc: interrupt-controller@fff11000 {
@@ -56,6 +61,7 @@
#interrupt-cells = <3>;
#address-cells = <1>;
interrupt-controller;
+ arm,routable-irqs = <160>;
reg = <0xfff11000 0x1000>,
<0xfff10100 0x100>;
};
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 343781b..4ce82d0 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -16,6 +16,9 @@
"arm,arm1176-pmu"
"arm,arm1136-pmu"
- interrupts : 1 combined interrupt or 1 per core.
+- cluster : a phandle to the cluster to which it belongs
+ If there are more than one cluster with same CPU type
+ then there should be separate PMU nodes per cluster.
Example:
diff --git a/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt b/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt
new file mode 100644
index 0000000..3b8fbf3
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/rtsm-dcscb.txt
@@ -0,0 +1,19 @@
+ARM Dual Cluster System Configuration Block
+-------------------------------------------
+
+The Dual Cluster System Configuration Block (DCSCB) provides basic
+functionality for controlling clocks, resets and configuration pins in
+the Dual Cluster System implemented by the Real-Time System Model (RTSM).
+
+Required properties:
+
+- compatible : should be "arm,rtsm,dcscb"
+
+- reg : physical base address and the size of the registers window
+
+Example:
+
+ dcscb@60000000 {
+ compatible = "arm,rtsm,dcscb";
+ reg = <0x60000000 0x1000>;
+ };
diff --git a/Documentation/devicetree/bindings/ata/marvell.txt b/Documentation/devicetree/bindings/ata/marvell.txt
index b5cdd20..1c83516 100644
--- a/Documentation/devicetree/bindings/ata/marvell.txt
+++ b/Documentation/devicetree/bindings/ata/marvell.txt
@@ -1,7 +1,7 @@
* Marvell Orion SATA
Required Properties:
-- compatibility : "marvell,orion-sata"
+- compatibility : "marvell,orion-sata" or "marvell,armada-370-sata"
- reg : Address range of controller
- interrupts : Interrupt controller is using
- nr-ports : Number of SATA ports in use.
diff --git a/Documentation/devicetree/bindings/mailbox/mailbox.txt b/Documentation/devicetree/bindings/mailbox/mailbox.txt
new file mode 100644
index 0000000..1a2cd3d
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/mailbox.txt
@@ -0,0 +1,38 @@
+* Generic Mailbox Controller and client driver bindings
+
+Generic binding to provide a way for Mailbox controller drivers to
+assign appropriate mailbox channel to client drivers.
+
+* Mailbox Controller
+
+Required property:
+- #mbox-cells: Must be at least 1. Number of cells in a mailbox
+ specifier.
+
+Example:
+ mailbox: mailbox {
+ ...
+ #mbox-cells = <1>;
+ };
+
+
+* Mailbox Client
+
+Required property:
+- mboxes: List of phandle and mailbox channel specifiers.
+
+Optional property:
+- mbox-names: List of identifier strings for each mailbox channel
+ required by the client. The use of this property
+ is discouraged in favor of using index in list of
+ 'mboxes' while requesting a mailbox. Instead the
+ platforms may define channel indices, in DT headers,
+ to something legible.
+
+Example:
+ pwr_cntrl: power {
+ ...
+ mbox-names = "pwr-ctrl", "rpc";
+ mboxes = <&mailbox 0
+ &mailbox 1>;
+ };
diff --git a/Documentation/devicetree/bindings/mfd/vexpress-spc.txt b/Documentation/devicetree/bindings/mfd/vexpress-spc.txt
new file mode 100644
index 0000000..1d71dc2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/vexpress-spc.txt
@@ -0,0 +1,35 @@
+* ARM Versatile Express Serial Power Controller device tree bindings
+
+Latest ARM development boards implement a power management interface (serial
+power controller - SPC) that is capable of managing power/voltage and
+operating point transitions, through memory mapped registers interface.
+
+On testchips like TC2 it also provides a configuration interface that can
+be used to read/write values which cannot be read/written through simple
+memory mapped reads/writes.
+
+- spc node
+
+ - compatible:
+ Usage: required
+ Value type: <stringlist>
+ Definition: must be
+ "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc"
+ - reg:
+ Usage: required
+ Value type: <prop-encode-array>
+ Definition: A standard property that specifies the base address
+ and the size of the SPC address space
+ - interrupts:
+ Usage: required
+ Value type: <prop-encoded-array>
+ Definition: SPC interrupt configuration. A standard property
+ that follows ePAPR interrupts specifications
+
+Example:
+
+spc: spc@7fff0000 {
+ compatible = "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc";
+ reg = <0 0x7FFF0000 0 0x1000>;
+ interrupts = <0 95 4>;
+};
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
index c95ea82..b275be4 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
@@ -126,3 +126,55 @@
whether there is any interaction between the child and intermediate parent
nodes, is again defined entirely by the binding for the individual pin
controller device.
+
+== Using generic pinconfig options ==
+
+Generic pinconfig parameters can be used by defining a separate node containing
+the applicable parameters (and optional values), like:
+
+pcfg_pull_up: pcfg_pull_up {
+ bias-pull-up;
+ drive-strength = <20>;
+};
+
+This node should then be referenced in the appropriate pinctrl node as a phandle
+and parsed in the driver using the pinconf_generic_parse_dt_config function.
+
+Supported configuration parameters are:
+
+bias-disable - disable any pin bias
+bias-high-impedance - high impedance mode ("third-state", "floating")
+bias-bus-hold - latch weakly
+bias-pull-up - pull up the pin
+bias-pull-down - pull down the pin
+bias-pull-pin-default - use pin-default pull state
+drive-push-pull - drive actively high and low
+drive-open-drain - drive with open drain
+drive-open-source - drive with open source
+drive-strength - sink or source at most X mA
+input-enable - enable input on pin (no effect on output)
+input-disable - disable input on pin (no effect on output)
+input-schmitt-enable - enable schmitt-trigger mode
+input-schmitt-disable - disable schmitt-trigger mode
+input-debounce - debounce mode with debound time X
+low-power-enable - enable low power mode
+low-power-disable - disable low power mode
+output-low - set the pin to output mode with low level
+output-high - set the pin to output mode with high level
+slew-rate - set the slew rate
+
+Arguments for parameters:
+
+- bias-pull-up, -down and -pin-default take as optional argument 0 to disable
+ the pull, on hardware supporting it the pull strength in Ohm. bias-disable
+ will also disable any active pull.
+
+- drive-strength takes as argument the target strength in mA.
+
+- input-debounce takes the debounce time in usec as argument
+ or 0 to disable debouncing
+
+All parameters not listed here, do not take an argument.
+
+More in-depth documentation on these parameters can be found in
+<include/linux/pinctrl/pinconfig-generic.h>
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
new file mode 100644
index 0000000..98c1667
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -0,0 +1,49 @@
+* Generic PM domains
+
+System on chip designs are often divided into multiple PM domains that can be
+used for power gating of selected IP blocks for power saving by reduced leakage
+current.
+
+This device tree binding can be used to bind PM domain consumer devices with
+their PM domains provided by PM domain providers. A PM domain provider can be
+represented by any node in the device tree and can provide one or more PM
+domains. A consumer node can refer to the provider by a phandle and a set of
+phandle arguments (so called PM domain specifiers) of length specified by the
+#power-domain-cells property in the PM domain provider node.
+
+==PM domain providers==
+
+Required properties:
+ - #power-domain-cells : Number of cells in a PM domain specifier;
+ Typically 0 for nodes representing a single PM domain and 1 for nodes
+ providing multiple PM domains (e.g. power controllers), but can be any value
+ as specified by device tree binding documentation of particular provider.
+
+Example:
+
+ power: power-controller@12340000 {
+ compatible = "foo,power-controller";
+ reg = <0x12340000 0x1000>;
+ #power-domain-cells = <1>;
+ };
+
+The node above defines a power controller that is a PM domain provider and
+expects one cell as its phandle argument.
+
+==PM domain consumers==
+
+Required properties:
+ - power-domains : A phandle and PM domain specifier as defined by bindings of
+ the power controller specified by phandle.
+
+Example:
+
+ leaky-device@12350000 {
+ compatible = "foo,i-leak-current";
+ reg = <0x12350000 0x1000>;
+ power-domains = <&power 0>;
+ };
+
+The node above defines a typical PM domain consumer device, which is located
+inside a PM domain with index 0 of a power controller represented by a node
+with the label "power".
diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt
new file mode 100644
index 0000000..f5db6b7
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -0,0 +1,595 @@
+* Thermal Framework Device Tree descriptor
+
+This file describes a generic binding to provide a way of
+defining hardware thermal structure using device tree.
+A thermal structure includes thermal zones and their components,
+such as trip points, polling intervals, sensors and cooling devices
+binding descriptors.
+
+The target of device tree thermal descriptors is to describe only
+the hardware thermal aspects. The thermal device tree bindings are
+not about how the system must control or which algorithm or policy
+must be taken in place.
+
+There are five types of nodes involved to describe thermal bindings:
+- thermal sensors: devices which may be used to take temperature
+ measurements.
+- cooling devices: devices which may be used to dissipate heat.
+- trip points: describe key temperatures at which cooling is recommended. The
+ set of points should be chosen based on hardware limits.
+- cooling maps: used to describe links between trip points and cooling devices;
+- thermal zones: used to describe thermal data within the hardware;
+
+The following is a description of each of these node types.
+
+* Thermal sensor devices
+
+Thermal sensor devices are nodes providing temperature sensing capabilities on
+thermal zones. Typical devices are I2C ADC converters and bandgaps. These are
+nodes providing temperature data to thermal zones. Thermal sensor devices may
+control one or more internal sensors.
+
+Required property:
+- #thermal-sensor-cells: Used to provide sensor device specific information
+ Type: unsigned while referring to it. Typically 0 on thermal sensor
+ Size: one cell nodes with only one sensor, and at least 1 on nodes
+ with several internal sensors, in order
+ to identify uniquely the sensor instances within
+ the IC. See thermal zone binding for more details
+ on how consumers refer to sensor devices.
+
+* Cooling device nodes
+
+Cooling devices are nodes providing control on power dissipation. There
+are essentially two ways to provide control on power dissipation. First
+is by means of regulating device performance, which is known as passive
+cooling. A typical passive cooling is a CPU that has dynamic voltage and
+frequency scaling (DVFS), and uses lower frequencies as cooling states.
+Second is by means of activating devices in order to remove
+the dissipated heat, which is known as active cooling, e.g. regulating
+fan speeds. In both cases, cooling devices shall have a way to determine
+the state of cooling in which the device is.
+
+Any cooling device has a range of cooling states (i.e. different levels
+of heat dissipation). For example a fan's cooling states correspond to
+the different fan speeds possible. Cooling states are referred to by
+single unsigned integers, where larger numbers mean greater heat
+dissipation. The precise set of cooling states associated with a device
+(as referred to be the cooling-min-state and cooling-max-state
+properties) should be defined in a particular device's binding.
+For more examples of cooling devices, refer to the example sections below.
+
+Required properties:
+- cooling-min-state: An integer indicating the smallest
+ Type: unsigned cooling state accepted. Typically 0.
+ Size: one cell
+
+- cooling-max-state: An integer indicating the largest
+ Type: unsigned cooling state accepted.
+ Size: one cell
+
+- #cooling-cells: Used to provide cooling device specific information
+ Type: unsigned while referring to it. Must be at least 2, in order
+ Size: one cell to specify minimum and maximum cooling state used
+ in the reference. The first cell is the minimum
+ cooling state requested and the second cell is
+ the maximum cooling state requested in the reference.
+ See Cooling device maps section below for more details
+ on how consumers refer to cooling devices.
+
+* Trip points
+
+The trip node is a node to describe a point in the temperature domain
+in which the system takes an action. This node describes just the point,
+not the action.
+
+Required properties:
+- temperature: An integer indicating the trip temperature level,
+ Type: signed in millicelsius.
+ Size: one cell
+
+- hysteresis: A low hysteresis value on temperature property (above).
+ Type: unsigned This is a relative value, in millicelsius.
+ Size: one cell
+
+- type: a string containing the trip type. Expected values are:
+ "active": A trip point to enable active cooling
+ "passive": A trip point to enable passive cooling
+ "hot": A trip point to notify emergency
+ "critical": Hardware not reliable.
+ Type: string
+
+* Cooling device maps
+
+The cooling device maps node is a node to describe how cooling devices
+get assigned to trip points of the zone. The cooling devices are expected
+to be loaded in the target system.
+
+Required properties:
+- cooling-device: A phandle of a cooling device with its specifier,
+ Type: phandle + referring to which cooling device is used in this
+ cooling specifier binding. In the cooling specifier, the first cell
+ is the minimum cooling state and the second cell
+ is the maximum cooling state used in this map.
+- trip: A phandle of a trip point node within the same thermal
+ Type: phandle of zone.
+ trip point node
+
+Optional property:
+- contribution: The cooling contribution to the thermal zone of the
+ Type: unsigned referred cooling device at the referred trip point.
+ Size: one cell The contribution is a ratio of the sum
+ of all cooling contributions within a thermal zone.
+
+Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
+limit specifier means:
+(i) - minimum state allowed for minimum cooling state used in the reference.
+(ii) - maximum state allowed for maximum cooling state used in the reference.
+Refer to include/dt-bindings/thermal/thermal.h for definition of this constant.
+
+* Thermal zone nodes
+
+The thermal zone node is the node containing all the required info
+for describing a thermal zone, including its cooling device bindings. The
+thermal zone node must contain, apart from its own properties, one sub-node
+containing trip nodes and one sub-node containing all the zone cooling maps.
+
+Required properties:
+- polling-delay: The maximum number of milliseconds to wait between polls
+ Type: unsigned when checking this thermal zone.
+ Size: one cell
+
+- polling-delay-passive: The maximum number of milliseconds to wait
+ Type: unsigned between polls when performing passive cooling.
+ Size: one cell
+
+- thermal-sensors: A list of thermal sensor phandles and sensor specifier
+ Type: list of used while monitoring the thermal zone.
+ phandles + sensor
+ specifier
+
+- trips: A sub-node which is a container of only trip point nodes
+ Type: sub-node required to describe the thermal zone.
+
+- cooling-maps: A sub-node which is a container of only cooling device
+ Type: sub-node map nodes, used to describe the relation between trips
+ and cooling devices.
+
+Optional property:
+- coefficients: An array of integers (one signed cell) containing
+ Type: array coefficients to compose a linear relation between
+ Elem size: one cell the sensors listed in the thermal-sensors property.
+ Elem type: signed Coefficients defaults to 1, in case this property
+ is not specified. A simple linear polynomial is used:
+ Z = c0 * x0 + c1 + x1 + ... + c(n-1) * x(n-1) + cn.
+
+ The coefficients are ordered and they match with sensors
+ by means of sensor ID. Additional coefficients are
+ interpreted as constant offset.
+
+Note: The delay properties are bound to the maximum dT/dt (temperature
+derivative over time) in two situations for a thermal zone:
+(i) - when passive cooling is activated (polling-delay-passive); and
+(ii) - when the zone just needs to be monitored (polling-delay) or
+when active cooling is activated.
+
+The maximum dT/dt is highly bound to hardware power consumption and dissipation
+capability. The delays should be chosen to account for said max dT/dt,
+such that a device does not cross several trip boundaries unexpectedly
+between polls. Choosing the right polling delays shall avoid having the
+device in temperature ranges that may damage the silicon structures and
+reduce silicon lifetime.
+
+* The thermal-zones node
+
+The "thermal-zones" node is a container for all thermal zone nodes. It shall
+contain only sub-nodes describing thermal zones as in the section
+"Thermal zone nodes". The "thermal-zones" node appears under "/".
+
+* Examples
+
+Below are several examples on how to use thermal data descriptors
+using device tree bindings:
+
+(a) - CPU thermal zone
+
+The CPU thermal zone example below describes how to setup one thermal zone
+using one single sensor as temperature source and many cooling devices and
+power dissipation control sources.
+
+#include <dt-bindings/thermal/thermal.h>
+
+cpus {
+ /*
+ * Here is an example of describing a cooling device for a DVFS
+ * capable CPU. The CPU node describes its four OPPs.
+ * The cooling states possible are 0..3, and they are
+ * used as OPP indexes. The minimum cooling state is 0, which means
+ * all four OPPs can be available to the system. The maximum
+ * cooling state is 3, which means only the lowest OPPs (198MHz@0.85V)
+ * can be available in the system.
+ */
+ cpu0: cpu@0 {
+ ...
+ operating-points = <
+ /* kHz uV */
+ 970000 1200000
+ 792000 1100000
+ 396000 950000
+ 198000 850000
+ >;
+ cooling-min-state = <0>;
+ cooling-max-state = <3>;
+ #cooling-cells = <2>; /* min followed by max */
+ };
+ ...
+};
+
+&i2c1 {
+ ...
+ /*
+ * A simple fan controller which supports 10 speeds of operation
+ * (represented as 0-9).
+ */
+ fan0: fan@0x48 {
+ ...
+ cooling-min-state = <0>;
+ cooling-max-state = <9>;
+ #cooling-cells = <2>; /* min followed by max */
+ };
+};
+
+ocp {
+ ...
+ /*
+ * A simple IC with a single bandgap temperature sensor.
+ */
+ bandgap0: bandgap@0x0000ED00 {
+ ...
+ #thermal-sensor-cells = <0>;
+ };
+};
+
+thermal-zones {
+ cpu-thermal: cpu-thermal {
+ polling-delay-passive = <250>; /* milliseconds */
+ polling-delay = <1000>; /* milliseconds */
+
+ thermal-sensors = <&bandgap0>;
+
+ trips {
+ cpu-alert0: cpu-alert {
+ temperature = <90000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "active";
+ };
+ cpu-alert1: cpu-alert {
+ temperature = <100000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ cpu-crit: cpu-crit {
+ temperature = <125000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ map0 {
+ trip = <&cpu-alert0>;
+ cooling-device = <&fan0 THERMAL_NO_LIMITS 4>;
+ };
+ map1 {
+ trip = <&cpu-alert1>;
+ cooling-device = <&fan0 5 THERMAL_NO_LIMITS>;
+ };
+ map2 {
+ trip = <&cpu-alert1>;
+ cooling-device =
+ <&cpu0 THERMAL_NO_LIMITS THERMAL_NO_LIMITS>;
+ };
+ };
+ };
+};
+
+In the example above, the ADC sensor (bandgap0) at address 0x0000ED00 is
+used to monitor the zone 'cpu-thermal' using its sole sensor. A fan
+device (fan0) is controlled via I2C bus 1, at address 0x48, and has ten
+different cooling states 0-9. It is used to remove the heat out of
+the thermal zone 'cpu-thermal' using its cooling states
+from its minimum to 4, when it reaches trip point 'cpu-alert0'
+at 90C, as an example of active cooling. The same cooling device is used at
+'cpu-alert1', but from 5 to its maximum state. The cpu@0 device is also
+linked to the same thermal zone, 'cpu-thermal', as a passive cooling device,
+using all its cooling states at trip point 'cpu-alert1',
+which is a trip point at 100C. On the thermal zone 'cpu-thermal', at the
+temperature of 125C, represented by the trip point 'cpu-crit', the silicon
+is not reliable anymore.
+
+(b) - IC with several internal sensors
+
+The example below describes how to deploy several thermal zones based off a
+single sensor IC, assuming it has several internal sensors. This is a common
+case on SoC designs with several internal IPs that may need different thermal
+requirements, and thus may have their own sensor to monitor or detect internal
+hotspots in their silicon.
+
+#include <dt-bindings/thermal/thermal.h>
+
+ocp {
+ ...
+ /*
+ * A simple IC with several bandgap temperature sensors.
+ */
+ bandgap0: bandgap@0x0000ED00 {
+ ...
+ #thermal-sensor-cells = <1>;
+ };
+};
+
+thermal-zones {
+ cpu-thermal: cpu-thermal {
+ polling-delay-passive = <250>; /* milliseconds */
+ polling-delay = <1000>; /* milliseconds */
+
+ /* sensor ID */
+ thermal-sensors = <&bandgap0 0>;
+
+ trips {
+ /* each zone within the SoC may have its own trips */
+ cpu-alert: cpu-alert {
+ temperature = <100000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ cpu-crit: cpu-crit {
+ temperature = <125000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ /* each zone within the SoC may have its own cooling */
+ ...
+ };
+ };
+
+ gpu-thermal: gpu-thermal {
+ polling-delay-passive = <120>; /* milliseconds */
+ polling-delay = <1000>; /* milliseconds */
+
+ /* sensor ID */
+ thermal-sensors = <&bandgap0 1>;
+
+ trips {
+ /* each zone within the SoC may have its own trips */
+ gpu-alert: gpu-alert {
+ temperature = <90000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ gpu-crit: gpu-crit {
+ temperature = <105000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ /* each zone within the SoC may have its own cooling */
+ ...
+ };
+ };
+
+ dsp-thermal: dsp-thermal {
+ polling-delay-passive = <50>; /* milliseconds */
+ polling-delay = <1000>; /* milliseconds */
+
+ /* sensor ID */
+ thermal-sensors = <&bandgap0 2>;
+
+ trips {
+ /* each zone within the SoC may have its own trips */
+ dsp-alert: gpu-alert {
+ temperature = <90000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ dsp-crit: gpu-crit {
+ temperature = <135000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ /* each zone within the SoC may have its own cooling */
+ ...
+ };
+ };
+};
+
+In the example above, there is one bandgap IC which has the capability to
+monitor three sensors. The hardware has been designed so that sensors are
+placed on different places in the DIE to monitor different temperature
+hotspots: one for CPU thermal zone, one for GPU thermal zone and the
+other to monitor a DSP thermal zone.
+
+Thus, there is a need to assign each sensor provided by the bandgap IC
+to different thermal zones. This is achieved by means of using the
+#thermal-sensor-cells property and using the first cell of the sensor
+specifier as sensor ID. In the example, then, <bandgap 0> is used to
+monitor CPU thermal zone, <bandgap 1> is used to monitor GPU thermal
+zone and <bandgap 2> is used to monitor DSP thermal zone. Each zone
+may be uncorrelated, having its own dT/dt requirements, trips
+and cooling maps.
+
+
+(c) - Several sensors within one single thermal zone
+
+The example below illustrates how to use more than one sensor within
+one thermal zone.
+
+#include <dt-bindings/thermal/thermal.h>
+
+&i2c1 {
+ ...
+ /*
+ * A simple IC with a single temperature sensor.
+ */
+ adc: sensor@0x49 {
+ ...
+ #thermal-sensor-cells = <0>;
+ };
+};
+
+ocp {
+ ...
+ /*
+ * A simple IC with a single bandgap temperature sensor.
+ */
+ bandgap0: bandgap@0x0000ED00 {
+ ...
+ #thermal-sensor-cells = <0>;
+ };
+};
+
+thermal-zones {
+ cpu-thermal: cpu-thermal {
+ polling-delay-passive = <250>; /* milliseconds */
+ polling-delay = <1000>; /* milliseconds */
+
+ thermal-sensors = <&bandgap0>, /* cpu */
+ <&adc>; /* pcb north */
+
+ /* hotspot = 100 * bandgap - 120 * adc + 484 */
+ coefficients = <100 -120 484>;
+
+ trips {
+ ...
+ };
+
+ cooling-maps {
+ ...
+ };
+ };
+};
+
+In some cases, there is a need to use more than one sensor to extrapolate
+a thermal hotspot in the silicon. The above example illustrates this situation.
+For instance, it may be the case that a sensor external to CPU IP may be placed
+close to CPU hotspot and together with internal CPU sensor, it is used
+to determine the hotspot. Assuming this is the case for the above example,
+the hypothetical extrapolation rule would be:
+ hotspot = 100 * bandgap - 120 * adc + 484
+
+In other context, the same idea can be used to add fixed offset. For instance,
+consider the hotspot extrapolation rule below:
+ hotspot = 1 * adc + 6000
+
+In the above equation, the hotspot is always 6C higher than what is read
+from the ADC sensor. The binding would be then:
+ thermal-sensors = <&adc>;
+
+ /* hotspot = 1 * adc + 6000 */
+ coefficients = <1 6000>;
+
+(d) - Board thermal
+
+The board thermal example below illustrates how to setup one thermal zone
+with many sensors and many cooling devices.
+
+#include <dt-bindings/thermal/thermal.h>
+
+&i2c1 {
+ ...
+ /*
+ * An IC with several temperature sensor.
+ */
+ adc-dummy: sensor@0x50 {
+ ...
+ #thermal-sensor-cells = <1>; /* sensor internal ID */
+ };
+};
+
+thermal-zones {
+ batt-thermal {
+ polling-delay-passive = <500>; /* milliseconds */
+ polling-delay = <2500>; /* milliseconds */
+
+ /* sensor ID */
+ thermal-sensors = <&adc-dummy 4>;
+
+ trips {
+ ...
+ };
+
+ cooling-maps {
+ ...
+ };
+ };
+
+ board-thermal: board-thermal {
+ polling-delay-passive = <1000>; /* milliseconds */
+ polling-delay = <2500>; /* milliseconds */
+
+ /* sensor ID */
+ thermal-sensors = <&adc-dummy 0>, /* pcb top edge */
+ <&adc-dummy 1>, /* lcd */
+ <&adc-dymmy 2>; /* back cover */
+ /*
+ * An array of coefficients describing the sensor
+ * linear relation. E.g.:
+ * z = c1*x1 + c2*x2 + c3*x3
+ */
+ coefficients = <1200 -345 890>;
+
+ trips {
+ /* Trips are based on resulting linear equation */
+ cpu-trip: cpu-trip {
+ temperature = <60000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ gpu-trip: gpu-trip {
+ temperature = <55000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ }
+ lcd-trip: lcp-trip {
+ temperature = <53000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "passive";
+ };
+ crit-trip: crit-trip {
+ temperature = <68000>; /* millicelsius */
+ hysteresis = <2000>; /* millicelsius */
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ map0 {
+ trip = <&cpu-trip>;
+ cooling-device = <&cpu0 0 2>;
+ contribution = <55>;
+ };
+ map1 {
+ trip = <&gpu-trip>;
+ cooling-device = <&gpu0 0 2>;
+ contribution = <20>;
+ };
+ map2 {
+ trip = <&lcd-trip>;
+ cooling-device = <&lcd0 5 10>;
+ contribution = <15>;
+ };
+ };
+ };
+};
+
+The above example is a mix of previous examples, a sensor IP with several internal
+sensors used to monitor different zones, one of them is composed by several sensors and
+with different cooling devices.
diff --git a/Documentation/devicetree/changesets.txt b/Documentation/devicetree/changesets.txt
new file mode 100644
index 0000000..935ba5a
--- /dev/null
+++ b/Documentation/devicetree/changesets.txt
@@ -0,0 +1,40 @@
+A DT changeset is a method which allows one to apply changes
+in the live tree in such a way that either the full set of changes
+will be applied, or none of them will be. If an error occurs partway
+through applying the changeset, then the tree will be rolled back to the
+previous state. A changeset can also be removed after it has been
+applied.
+
+When a changeset is applied, all of the changes get applied to the tree
+at once before emitting OF_RECONFIG notifiers. This is so that the
+receiver sees a complete and consistent state of the tree when it
+receives the notifier.
+
+The sequence of a changeset is as follows.
+
+1. of_changeset_init() - initializes a changeset
+
+2. A number of DT tree change calls, of_changeset_attach_node(),
+of_changeset_detach_node(), of_changeset_add_property(),
+of_changeset_remove_property, of_changeset_update_property() to prepare
+a set of changes. No changes to the active tree are made at this point.
+All the change operations are recorded in the of_changeset 'entries'
+list.
+
+3. mutex_lock(of_mutex) - starts a changeset; The global of_mutex
+ensures there can only be one editor at a time.
+
+4. of_changeset_apply() - Apply the changes to the tree. Either the
+entire changeset will get applied, or if there is an error the tree will
+be restored to the previous state
+
+5. mutex_unlock(of_mutex) - All operations complete, release the mutex
+
+If a successfully applied changeset needs to be removed, it can be done
+with the following sequence.
+
+1. mutex_lock(of_mutex)
+
+2. of_changeset_revert()
+
+3. mutex_unlock(of_mutex)
diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt
new file mode 100644
index 0000000..083d232
--- /dev/null
+++ b/Documentation/devicetree/dynamic-resolution-notes.txt
@@ -0,0 +1,25 @@
+Device Tree Dynamic Resolver Notes
+----------------------------------
+
+This document describes the implementation of the in-kernel
+Device Tree resolver, residing in drivers/of/resolver.c and is a
+companion document to Documentation/devicetree/dt-object-internal.txt[1]
+
+How the resolver works
+----------------------
+
+The resolver is given as an input an arbitrary tree compiled with the
+proper dtc option and having a /plugin/ tag. This generates the
+appropriate __fixups__ & __local_fixups__ nodes as described in [1].
+
+In sequence the resolver works by the following steps:
+
+1. Get the maximum device tree phandle value from the live tree + 1.
+2. Adjust all the local phandles of the tree to resolve by that amount.
+3. Using the __local__fixups__ node information adjust all local references
+ by the same amount.
+4. For each property in the __fixups__ node locate the node it references
+ in the live tree. This is the label used to tag the node.
+5. Retrieve the phandle of the target of the fixup.
+6. For each fixup in the property locate the node:property:offset location
+ and replace it with the phandle value.
diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt
new file mode 100644
index 0000000..30ae758
--- /dev/null
+++ b/Documentation/devicetree/overlay-notes.txt
@@ -0,0 +1,133 @@
+Device Tree Overlay Notes
+-------------------------
+
+This document describes the implementation of the in-kernel
+device tree overlay functionality residing in drivers/of/overlay.c and is a
+companion document to Documentation/devicetree/dt-object-internal.txt[1] &
+Documentation/devicetree/dynamic-resolution-notes.txt[2]
+
+How overlays work
+-----------------
+
+A Device Tree's overlay purpose is to modify the kernel's live tree, and
+have the modification affecting the state of the the kernel in a way that
+is reflecting the changes.
+Since the kernel mainly deals with devices, any new device node that result
+in an active device should have it created while if the device node is either
+disabled or removed all together, the affected device should be deregistered.
+
+Lets take an example where we have a foo board with the following base tree
+which is taken from [1].
+
+---- foo.dts -----------------------------------------------------------------
+ /* FOO platform */
+ / {
+ compatible = "corp,foo";
+
+ /* shared resources */
+ res: res {
+ };
+
+ /* On chip peripherals */
+ ocp: ocp {
+ /* peripherals that are always instantiated */
+ peripheral1 { ... };
+ }
+ };
+---- foo.dts -----------------------------------------------------------------
+
+The overlay bar.dts, when loaded (and resolved as described in [2]) should
+
+---- bar.dts -----------------------------------------------------------------
+/plugin/; /* allow undefined label references and record them */
+/ {
+ .... /* various properties for loader use; i.e. part id etc. */
+ fragment@0 {
+ target = <&ocp>;
+ __overlay__ {
+ /* bar peripheral */
+ bar {
+ compatible = "corp,bar";
+ ... /* various properties and child nodes */
+ }
+ };
+ };
+};
+---- bar.dts -----------------------------------------------------------------
+
+result in foo+bar.dts
+
+---- foo+bar.dts -------------------------------------------------------------
+ /* FOO platform + bar peripheral */
+ / {
+ compatible = "corp,foo";
+
+ /* shared resources */
+ res: res {
+ };
+
+ /* On chip peripherals */
+ ocp: ocp {
+ /* peripherals that are always instantiated */
+ peripheral1 { ... };
+
+ /* bar peripheral */
+ bar {
+ compatible = "corp,bar";
+ ... /* various properties and child nodes */
+ }
+ }
+ };
+---- foo+bar.dts -------------------------------------------------------------
+
+As a result of the the overlay, a new device node (bar) has been created
+so a bar platform device will be registered and if a matching device driver
+is loaded the device will be created as expected.
+
+Overlay in-kernel API
+--------------------------------
+
+The API is quite easy to use.
+
+1. Call of_overlay_create() to create and apply an overlay. The return value
+is a cookie identifying this overlay.
+
+2. Call of_overlay_destroy() to remove and cleanup the overlay previously
+created via the call to of_overlay_create(). Removal of an overlay that
+is stacked by another will not be permitted.
+
+Finally, if you need to remove all overlays in one-go, just call
+of_overlay_destroy_all() which will remove every single one in the correct
+order.
+
+Overlay DTS Format
+------------------
+
+The DTS of an overlay should have the following format:
+
+{
+ /* ignored properties by the overlay */
+
+ fragment@0 { /* first child node */
+
+ target=<phandle>; /* phandle target of the overlay */
+ or
+ target-path="/path"; /* target path of the overlay */
+
+ __overlay__ {
+ property-a; /* add property-a to the target */
+ node-a { /* add to an existing, or create a node-a */
+ ...
+ };
+ };
+ }
+ fragment@1 { /* second child node */
+ ...
+ };
+ /* more fragments follow */
+}
+
+Using the non-phandle based target method allows one to use a base DT which does
+not contain a __symbols__ node, i.e. it was not compiled with the -@ option.
+The __symbols__ node is only required for the target=<phandle> method, since it
+contains the information required to map from a phandle to a tree location.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index fd8d0d5..954eab8 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1372,8 +1372,8 @@
For example, if a task is using all allowed memory, its badness score will be
1000. If it is using half of its allowed memory, its score will be 500.
-There is an additional factor included in the badness score: root
-processes are given 3% extra memory over other tasks.
+There is an additional factor included in the badness score: the current memory
+and swap usage is discounted by 3% for root processes.
The amount of "allowed" memory depends on the context in which the oom killer
was called. If it is due to the memory assigned to the allocating task's cpuset
diff --git a/Documentation/gcov.txt b/Documentation/gcov.txt
index e7ca647..7b72778 100644
--- a/Documentation/gcov.txt
+++ b/Documentation/gcov.txt
@@ -50,6 +50,10 @@
CONFIG_DEBUG_FS=y
CONFIG_GCOV_KERNEL=y
+select the gcc's gcov format, default is autodetect based on gcc version:
+
+ CONFIG_GCOV_FORMAT_AUTODETECT=y
+
and to get coverage data for the entire kernel:
CONFIG_GCOV_PROFILE_ALL=y
diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp
index 90956b6..4dfdc8f 100644
--- a/Documentation/hwmon/k10temp
+++ b/Documentation/hwmon/k10temp
@@ -12,6 +12,7 @@
* AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
* AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity"
+* AMD Family 16h processors: "Kabini"
Prefix: 'k10temp'
Addresses scanned: PCI space
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index d55b8ab..babe2ef 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -24,6 +24,9 @@
* Intel Lynx Point-LP (PCH)
* Intel Avoton (SOC)
* Intel Wellsburg (PCH)
+ * Intel Coleto Creek (PCH)
+ * Intel Wildcat Point-LP (PCH)
+ * Intel BayTrail (SOC)
Datasheets: Publicly available at the Intel website
On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/i2c/busses/i2c-piix4 b/Documentation/i2c/busses/i2c-piix4
index 1e6634f..a370b20 100644
--- a/Documentation/i2c/busses/i2c-piix4
+++ b/Documentation/i2c/busses/i2c-piix4
@@ -13,7 +13,7 @@
* AMD SP5100 (SB700 derivative found on some server mainboards)
Datasheet: Publicly available at the AMD website
http://support.amd.com/us/Embedded_TechDocs/44413.pdf
- * AMD Hudson-2
+ * AMD Hudson-2, CZ
Datasheet: Not publicly available
* Standard Microsystems (SMSC) SLC90E66 (Victory66) southbridge
Datasheet: Publicly available at the SMSC website http://www.smsc.com
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index 5602eb7..e1ae127 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -504,9 +504,12 @@
* reg_10
bit 7 6 5 4 3 2 1 0
- 0 0 0 0 0 0 0 A
+ 0 0 0 0 R F T A
A: 1 = enable absolute tracking
+ T: 1 = enable two finger mode auto correct
+ F: 1 = disable ABS Position Filter
+ R: 1 = enable real hardware resolution
6.2 Native absolute mode 6 byte packet format
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 050d37f..46ed735 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -315,7 +315,7 @@
もし、2.6.x.y カーネルが存在しない場合には、番号が一番大きい 2.6.x が
最新の安定版カーネルです。
-2.6.x.y は "stable" チーム <stable@kernel.org> でメンテされており、必
+2.6.x.y は "stable" チーム <stable@vger.kernel.org> でメンテされており、必
要に応じてリリースされます。通常のリリース期間は 2週間毎ですが、差し迫っ
た問題がなければもう少し長くなることもあります。セキュリティ関連の問題
の場合はこれに対してだいたいの場合、すぐにリリースがされます。
diff --git a/Documentation/ja_JP/stable_kernel_rules.txt b/Documentation/ja_JP/stable_kernel_rules.txt
index 1426583..9dbda9b 100644
--- a/Documentation/ja_JP/stable_kernel_rules.txt
+++ b/Documentation/ja_JP/stable_kernel_rules.txt
@@ -50,16 +50,16 @@
-stable ツリーにパッチを送付する手続き-
- - 上記の規則に従っているかを確認した後に、stable@kernel.org にパッチ
+ - 上記の規則に従っているかを確認した後に、stable@vger.kernel.org にパッチ
を送る。
- 送信者はパッチがキューに受け付けられた際には ACK を、却下された場合
には NAK を受け取る。この反応は開発者たちのスケジュールによって、数
日かかる場合がある。
- もし受け取られたら、パッチは他の開発者たちと関連するサブシステムの
メンテナーによるレビューのために -stable キューに追加される。
- - パッチに stable@kernel.org のアドレスが付加されているときには、それ
+ - パッチに stable@vger.kernel.org のアドレスが付加されているときには、それ
が Linus のツリーに入る時に自動的に stable チームに email される。
- - セキュリティパッチはこのエイリアス (stable@kernel.org) に送られるべ
+ - セキュリティパッチはこのエイリアス (stable@vger.kernel.org) に送られるべ
きではなく、代わりに security@kernel.org のアドレスに送られる。
レビューサイクル-
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 2fe6e76..d592974 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1061,6 +1061,7 @@
i8042.notimeout [HW] Ignore timeout condition signalled by controller
i8042.reset [HW] Reset the controller during init and cleanup
i8042.unlock [HW] Unlock (ignore) the keylock
+ i8042.kbdreset [HW] Reset device connected to KBD port
i810= [HW,DRM]
@@ -1240,6 +1241,15 @@
See comment before ip2_setup() in
drivers/char/ip2/ip2base.c.
+ irqaffinity= [SMP] Set the default irq affinity mask
+ Format:
+ <cpu number>,...,<cpu number>
+ or
+ <cpu number>-<cpu number>
+ (must be a positive range in ascending order)
+ or a mixture
+ <cpu number>,...,<cpu number>-<cpu number>
+
irqfixup [HW]
When an interrupt is not handled search all handlers
for it. Intended to get systems with badly broken
@@ -1456,6 +1466,10 @@
* dump_id: dump IDENTIFY data.
+ * atapi_dmadir: Enable ATAPI DMADIR bridge support
+
+ * disable: Disable this device.
+
If there are multiple matching configurations changing
the same attribute, the last one is used.
@@ -3341,6 +3355,21 @@
that this also can be controlled per-workqueue for
workqueues visible under /sys/bus/workqueue/.
+ workqueue.power_efficient
+ Per-cpu workqueues are generally preferred because
+ they show better performance thanks to cache
+ locality; unfortunately, per-cpu workqueues tend to
+ be more power hungry than unbound workqueues.
+
+ Enabling this makes the per-cpu workqueues which
+ were observed to contribute significantly to power
+ consumption unbound, leading to measurably lower
+ power usage at the cost of small performance
+ overhead.
+
+ The default value of this parameter is determined by
+ the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
+
x2apic_phys [X86-64,APIC] Use x2apic physical mode instead of
default x2apic cluster mode on platforms
supporting x2apic.
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
new file mode 100644
index 0000000..ea45dd3
--- /dev/null
+++ b/Documentation/lzo.txt
@@ -0,0 +1,164 @@
+
+LZO stream format as understood by Linux's LZO decompressor
+===========================================================
+
+Introduction
+
+ This is not a specification. No specification seems to be publicly available
+ for the LZO stream format. This document describes what input format the LZO
+ decompressor as implemented in the Linux kernel understands. The file subject
+ of this analysis is lib/lzo/lzo1x_decompress_safe.c. No analysis was made on
+ the compressor nor on any other implementations though it seems likely that
+ the format matches the standard one. The purpose of this document is to
+ better understand what the code does in order to propose more efficient fixes
+ for future bug reports.
+
+Description
+
+ The stream is composed of a series of instructions, operands, and data. The
+ instructions consist in a few bits representing an opcode, and bits forming
+ the operands for the instruction, whose size and position depend on the
+ opcode and on the number of literals copied by previous instruction. The
+ operands are used to indicate :
+
+ - a distance when copying data from the dictionary (past output buffer)
+ - a length (number of bytes to copy from dictionary)
+ - the number of literals to copy, which is retained in variable "state"
+ as a piece of information for next instructions.
+
+ Optionally depending on the opcode and operands, extra data may follow. These
+ extra data can be a complement for the operand (eg: a length or a distance
+ encoded on larger values), or a literal to be copied to the output buffer.
+
+ The first byte of the block follows a different encoding from other bytes, it
+ seems to be optimized for literal use only, since there is no dictionary yet
+ prior to that byte.
+
+ Lengths are always encoded on a variable size starting with a small number
+ of bits in the operand. If the number of bits isn't enough to represent the
+ length, up to 255 may be added in increments by consuming more bytes with a
+ rate of at most 255 per extra byte (thus the compression ratio cannot exceed
+ around 255:1). The variable length encoding using #bits is always the same :
+
+ length = byte & ((1 << #bits) - 1)
+ if (!length) {
+ length = ((1 << #bits) - 1)
+ length += 255*(number of zero bytes)
+ length += first-non-zero-byte
+ }
+ length += constant (generally 2 or 3)
+
+ For references to the dictionary, distances are relative to the output
+ pointer. Distances are encoded using very few bits belonging to certain
+ ranges, resulting in multiple copy instructions using different encodings.
+ Certain encodings involve one extra byte, others involve two extra bytes
+ forming a little-endian 16-bit quantity (marked LE16 below).
+
+ After any instruction except the large literal copy, 0, 1, 2 or 3 literals
+ are copied before starting the next instruction. The number of literals that
+ were copied may change the meaning and behaviour of the next instruction. In
+ practice, only one instruction needs to know whether 0, less than 4, or more
+ literals were copied. This is the information stored in the <state> variable
+ in this implementation. This number of immediate literals to be copied is
+ generally encoded in the last two bits of the instruction but may also be
+ taken from the last two bits of an extra operand (eg: distance).
+
+ End of stream is declared when a block copy of distance 0 is seen. Only one
+ instruction may encode this distance (0001HLLL), it takes one LE16 operand
+ for the distance, thus requiring 3 bytes.
+
+ IMPORTANT NOTE : in the code some length checks are missing because certain
+ instructions are called under the assumption that a certain number of bytes
+ follow because it has already been garanteed before parsing the instructions.
+ They just have to "refill" this credit if they consume extra bytes. This is
+ an implementation design choice independant on the algorithm or encoding.
+
+Byte sequences
+
+ First byte encoding :
+
+ 0..17 : follow regular instruction encoding, see below. It is worth
+ noting that codes 16 and 17 will represent a block copy from
+ the dictionary which is empty, and that they will always be
+ invalid at this place.
+
+ 18..21 : copy 0..3 literals
+ state = (byte - 17) = 0..3 [ copy <state> literals ]
+ skip byte
+
+ 22..255 : copy literal string
+ length = (byte - 17) = 4..238
+ state = 4 [ don't copy extra literals ]
+ skip byte
+
+ Instruction encoding :
+
+ 0 0 0 0 X X X X (0..15)
+ Depends on the number of literals copied by the last instruction.
+ If last instruction did not copy any literal (state == 0), this
+ encoding will be a copy of 4 or more literal, and must be interpreted
+ like this :
+
+ 0 0 0 0 L L L L (0..15) : copy long literal string
+ length = 3 + (L ?: 15 + (zero_bytes * 255) + non_zero_byte)
+ state = 4 (no extra literals are copied)
+
+ If last instruction used to copy between 1 to 3 literals (encoded in
+ the instruction's opcode or distance), the instruction is a copy of a
+ 2-byte block from the dictionary within a 1kB distance. It is worth
+ noting that this instruction provides little savings since it uses 2
+ bytes to encode a copy of 2 other bytes but it encodes the number of
+ following literals for free. It must be interpreted like this :
+
+ 0 0 0 0 D D S S (0..15) : copy 2 bytes from <= 1kB distance
+ length = 2
+ state = S (copy S literals after this block)
+ Always followed by exactly one byte : H H H H H H H H
+ distance = (H << 2) + D + 1
+
+ If last instruction used to copy 4 or more literals (as detected by
+ state == 4), the instruction becomes a copy of a 3-byte block from the
+ dictionary from a 2..3kB distance, and must be interpreted like this :
+
+ 0 0 0 0 D D S S (0..15) : copy 3 bytes from 2..3 kB distance
+ length = 3
+ state = S (copy S literals after this block)
+ Always followed by exactly one byte : H H H H H H H H
+ distance = (H << 2) + D + 2049
+
+ 0 0 0 1 H L L L (16..31)
+ Copy of a block within 16..48kB distance (preferably less than 10B)
+ length = 2 + (L ?: 7 + (zero_bytes * 255) + non_zero_byte)
+ Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S
+ distance = 16384 + (H << 14) + D
+ state = S (copy S literals after this block)
+ End of stream is reached if distance == 16384
+
+ 0 0 1 L L L L L (32..63)
+ Copy of small block within 16kB distance (preferably less than 34B)
+ length = 2 + (L ?: 31 + (zero_bytes * 255) + non_zero_byte)
+ Always followed by exactly one LE16 : D D D D D D D D : D D D D D D S S
+ distance = D + 1
+ state = S (copy S literals after this block)
+
+ 0 1 L D D D S S (64..127)
+ Copy 3-4 bytes from block within 2kB distance
+ state = S (copy S literals after this block)
+ length = 3 + L
+ Always followed by exactly one byte : H H H H H H H H
+ distance = (H << 3) + D + 1
+
+ 1 L L D D D S S (128..255)
+ Copy 5-8 bytes from block within 2kB distance
+ state = S (copy S literals after this block)
+ length = 5 + L
+ Always followed by exactly one byte : H H H H H H H H
+ distance = (H << 3) + D + 1
+
+Authors
+
+ This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
+ analysis of the decompression code available in Linux 3.16-rc5. The code is
+ tricky, it is possible that this document contains mistakes or that a few
+ corner cases were overlooked. In any case, please report any doubt, fix, or
+ proposed updates to the author(s) so that the document can be updated.
diff --git a/Documentation/mailbox.txt b/Documentation/mailbox.txt
new file mode 100644
index 0000000..60f43ff
--- /dev/null
+++ b/Documentation/mailbox.txt
@@ -0,0 +1,122 @@
+ The Common Mailbox Framework
+ Jassi Brar <jaswinder.singh@linaro.org>
+
+ This document aims to help developers write client and controller
+drivers for the API. But before we start, let us note that the
+client (especially) and controller drivers are likely going to be
+very platform specific because the remote firmware is likely to be
+proprietary and implement non-standard protocol. So even if two
+platforms employ, say, PL320 controller, the client drivers can't
+be shared across them. Even the PL320 driver might need to accommodate
+some platform specific quirks. So the API is meant mainly to avoid
+similar copies of code written for each platform. Having said that,
+nothing prevents the remote f/w to also be Linux based and use the
+same api there. However none of that helps us locally because we only
+ever deal at client's protocol level.
+ Some of the choices made during implementation are the result of this
+peculiarity of this "common" framework.
+
+
+
+ Part 1 - Controller Driver (See include/linux/mailbox_controller.h)
+
+ Allocate mbox_controller and the array of mbox_chan.
+Populate mbox_chan_ops, except peek_data() all are mandatory.
+The controller driver might know a message has been consumed
+by the remote by getting an IRQ or polling some hardware flag
+or it can never know (the client knows by way of the protocol).
+The method in order of preference is IRQ -> Poll -> None, which
+the controller driver should set via 'txdone_irq' or 'txdone_poll'
+or neither.
+
+
+ Part 2 - Client Driver (See include/linux/mailbox_client.h)
+
+ The client might want to operate in blocking mode (synchronously
+send a message through before returning) or non-blocking/async mode (submit
+a message and a callback function to the API and return immediately).
+
+
+struct demo_client {
+ struct mbox_client cl;
+ struct mbox_chan *mbox;
+ struct completion c;
+ bool async;
+ /* ... */
+};
+
+/*
+ * This is the handler for data received from remote. The behaviour is purely
+ * dependent upon the protocol. This is just an example.
+ */
+static void message_from_remote(struct mbox_client *cl, void *mssg)
+{
+ struct demo_client *dc = container_of(mbox_client,
+ struct demo_client, cl);
+ if (dc->aysnc) {
+ if (is_an_ack(mssg)) {
+ /* An ACK to our last sample sent */
+ return; /* Or do something else here */
+ } else { /* A new message from remote */
+ queue_req(mssg);
+ }
+ } else {
+ /* Remote f/w sends only ACK packets on this channel */
+ return;
+ }
+}
+
+static void sample_sent(struct mbox_client *cl, void *mssg, int r)
+{
+ struct demo_client *dc = container_of(mbox_client,
+ struct demo_client, cl);
+ complete(&dc->c);
+}
+
+static void client_demo(struct platform_device *pdev)
+{
+ struct demo_client *dc_sync, *dc_async;
+ /* The controller already knows async_pkt and sync_pkt */
+ struct async_pkt ap;
+ struct sync_pkt sp;
+
+ dc_sync = kzalloc(sizeof(*dc_sync), GFP_KERNEL);
+ dc_async = kzalloc(sizeof(*dc_async), GFP_KERNEL);
+
+ /* Populate non-blocking mode client */
+ dc_async->cl.dev = &pdev->dev;
+ dc_async->cl.rx_callback = message_from_remote;
+ dc_async->cl.tx_done = sample_sent;
+ dc_async->cl.tx_block = false;
+ dc_async->cl.tx_tout = 0; /* doesn't matter here */
+ dc_async->cl.knows_txdone = false; /* depending upon protocol */
+ dc_async->async = true;
+ init_completion(&dc_async->c);
+
+ /* Populate blocking mode client */
+ dc_sync->cl.dev = &pdev->dev;
+ dc_sync->cl.rx_callback = message_from_remote;
+ dc_sync->cl.tx_done = NULL; /* operate in blocking mode */
+ dc_sync->cl.tx_block = true;
+ dc_sync->cl.tx_tout = 500; /* by half a second */
+ dc_sync->cl.knows_txdone = false; /* depending upon protocol */
+ dc_sync->async = false;
+
+ /* ASync mailbox is listed second in 'mboxes' property */
+ dc_async->mbox = mbox_request_channel(&dc_async->cl, 1);
+ /* Populate data packet */
+ /* ap.xxx = 123; etc */
+ /* Send async message to remote */
+ mbox_send_message(dc_async->mbox, &ap);
+
+ /* Sync mailbox is listed first in 'mboxes' property */
+ dc_sync->mbox = mbox_request_channel(&dc_sync->cl, 0);
+ /* Populate data packet */
+ /* sp.abc = 123; etc */
+ /* Send message to remote in blocking mode */
+ mbox_send_message(dc_sync->mbox, &sp);
+ /* At this point 'sp' has been sent */
+
+ /* Now wait for async chan to be done */
+ wait_for_completion(&dc_async->c);
+}
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 3458d63..a59ee43 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -478,6 +478,15 @@
tcp_timestamps - BOOLEAN
Enable timestamps as defined in RFC1323.
+tcp_min_tso_segs - INTEGER
+ Minimal number of segments per TSO frame.
+ Since linux-3.12, TCP does an automatic sizing of TSO frames,
+ depending on flow rate, instead of filling 64Kbytes packets.
+ For specific usages, it's possible to force TCP to build big
+ TSO frames. Note that TCP stack might split too big TSO packets
+ if available window is too small.
+ Default: 2
+
tcp_tso_win_divisor - INTEGER
This allows control over what percentage of the congestion window
can be consumed by a single TSO frame.
@@ -562,9 +571,6 @@
typical pfifo_fast qdiscs.
tcp_limit_output_bytes limits the number of bytes on qdisc
or device to reduce artificial RTT/cwnd and reduce bufferbloat.
- Note: For GSO/TSO enabled flows, we try to have at least two
- packets in flight. Reducing tcp_limit_output_bytes might also
- reduce the size of individual GSO packet (64KB being the max)
Default: 131072
tcp_challenge_ack_limit - INTEGER
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 23dd80e..0f4376e 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -123,6 +123,16 @@
[shutdown] close() --------> destruction of the transmission socket and
deallocation of all associated resources.
+Socket creation and destruction is also straight forward, and is done
+the same way as in capturing described in the previous paragraph:
+
+ int fd = socket(PF_PACKET, mode, 0);
+
+The protocol can optionally be 0 in case we only want to transmit
+via this socket, which avoids an expensive call to packet_rcv().
+In this case, you also need to bind(2) the TX_RING with sll_protocol = 0
+set. Otherwise, htons(ETH_P_ALL) or any other protocol, for example.
+
Binding the socket to your network interface is mandatory (with zero copy) to
know the header size of frames used in the circular buffer.
diff --git a/Documentation/parisc/registers b/Documentation/parisc/registers
index dd3cadd..10c7d17 100644
--- a/Documentation/parisc/registers
+++ b/Documentation/parisc/registers
@@ -78,6 +78,14 @@
TOC enable bit 1
=========================================================================
+
+The PA-RISC architecture defines 7 registers as "shadow registers".
+Those are used in RETURN FROM INTERRUPTION AND RESTORE instruction to reduce
+the state save and restore time by eliminating the need for general register
+(GR) saves and restores in interruption handlers.
+Shadow registers are the GRs 1, 8, 9, 16, 17, 24, and 25.
+
+=========================================================================
Register usage notes, originally from John Marvin, with some additional
notes from Randolph Chung.
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index 447fd4c..c876380 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -203,15 +203,8 @@
stable value when nothing is driving the rail it is connected to, or when it's
unconnected.
-Pin configuration can be programmed either using the explicit APIs described
-immediately below, or by adding configuration entries into the mapping table;
-see section "Board/machine configuration" below.
-
-For example, a platform may do the following to pull up a pin to VDD:
-
-#include <linux/pinctrl/consumer.h>
-
-ret = pin_config_set("foo-dev", "FOO_GPIO_PIN", PLATFORM_X_PULL_UP);
+Pin configuration can be programmed by adding configuration entries into the
+mapping table; see section "Board/machine configuration" below.
The format and meaning of the configuration parameter, PLATFORM_X_PULL_UP
above, is entirely defined by the pin controller driver.
diff --git a/Documentation/ramoops.txt b/Documentation/ramoops.txt
index 69b3cac..5d86756 100644
--- a/Documentation/ramoops.txt
+++ b/Documentation/ramoops.txt
@@ -14,11 +14,19 @@
1. Ramoops concepts
-Ramoops uses a predefined memory area to store the dump. The start and size of
-the memory area are set using two variables:
+Ramoops uses a predefined memory area to store the dump. The start and size
+and type of the memory area are set using three variables:
* "mem_address" for the start
* "mem_size" for the size. The memory size will be rounded down to a
power of two.
+ * "mem_type" to specifiy if the memory type (default is pgprot_writecombine).
+
+Typically the default value of mem_type=0 should be used as that sets the pstore
+mapping to pgprot_writecombine. Setting mem_type=1 attempts to use
+pgprot_noncached, which only works on some platforms. This is because pstore
+depends on atomic operations. At least on ARM, pgprot_noncached causes the
+memory to be mapped strongly ordered, and atomic operations on strongly ordered
+memory are implementation defined, and won't work on many ARMs such as omaps.
The memory area is divided into "record_size" chunks (also rounded down to
power of two) and each oops/panic writes a "record_size" chunk of
@@ -55,6 +63,7 @@
static struct ramoops_platform_data ramoops_data = {
.mem_size = <...>,
.mem_address = <...>,
+ .mem_type = <...>,
.record_size = <...>,
.dump_oops = <...>,
.ecc = <...>,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 95731a0..8f08b2a 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@
-------------------
Module for sound cards based on the Asus AV66/AV100/AV200 chips,
- i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
- HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+ i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+ Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
This module supports autoprobe and multiple cards.
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index b0714d8..8dfb6a5 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -29,6 +29,9 @@
Procedure for submitting patches to the -stable tree:
+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+ submission guidelines as described in
+ Documentation/networking/netdev-FAQ.txt
- Send the patch, after verifying that it follows the above rules, to
stable@vger.kernel.org. You must note the upstream commit ID in the
changelog of your submission, as well as the kernel version you wish
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index ccd4258..8d90c42 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -289,13 +289,24 @@
kptr_restrict:
This toggle indicates whether restrictions are placed on
-exposing kernel addresses via /proc and other interfaces. When
-kptr_restrict is set to (0), there are no restrictions. When
-kptr_restrict is set to (1), the default, kernel pointers
-printed using the %pK format specifier will be replaced with 0's
-unless the user has CAP_SYSLOG. When kptr_restrict is set to
-(2), kernel pointers printed using %pK will be replaced with 0's
-regardless of privileges.
+exposing kernel addresses via /proc and other interfaces.
+
+When kptr_restrict is set to (0), the default, there are no restrictions.
+
+When kptr_restrict is set to (1), kernel pointers printed using the %pK
+format specifier will be replaced with 0's unless the user has CAP_SYSLOG
+and effective user and group ids are equal to the real ids. This is
+because %pK checks are done at read() time rather than open() time, so
+if permissions are elevated between the open() and the read() (e.g via
+a setuid binary) then %pK will not leak kernel pointers to unprivileged
+users. Note, this is a temporary solution only. The correct long-term
+solution is to do the permission checks at open() time. Consider removing
+world read permissions from files that use %pK, and using dmesg_restrict
+to protect against uses of %pK in dmesg(8) if leaking kernel pointer
+values to unprivileged users is a concern.
+
+When kptr_restrict is set to (2), kernel pointers printed using
+%pK will be replaced with 0's regardless of privileges.
==============================================================
@@ -427,6 +438,32 @@
==============================================================
+perf_cpu_time_max_percent:
+
+Hints to the kernel how much CPU time it should be allowed to
+use to handle perf sampling events. If the perf subsystem
+is informed that its samples are exceeding this limit, it
+will drop its sampling frequency to attempt to reduce its CPU
+usage.
+
+Some perf sampling happens in NMIs. If these samples
+unexpectedly take too long to execute, the NMIs can become
+stacked up next to each other so much that nothing else is
+allowed to execute.
+
+0: disable the mechanism. Do not monitor or correct perf's
+ sampling rate no matter how CPU time it takes.
+
+1-100: attempt to throttle perf's sample rate to this
+ percentage of CPU. Note: the kernel calculates an
+ "expected" length of each sample event. 100 here means
+ 100% of that expected length. Even if this is set to
+ 100, you may still see sample throttling if this
+ length is exceeded. Set to 0 if you truly do not care
+ how much CPU is consumed.
+
+==============================================================
+
pid_max:
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index a71bd5b..37c5486 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -142,6 +142,11 @@
This is an optional feature where some platforms can choose not to
provide this data.
.governor_name: Name of the thermal governor used for this zone
+ .no_hwmon: a boolean to indicate if the thermal to hwmon sysfs interface
+ is required. when no_hwmon == false, a hwmon sysfs interface
+ will be created. when no_hwmon == true, nothing will be done.
+ In case the thermal_zone_params is NULL, the hwmon interface
+ will be created (for backward compatibility).
.num_tbps: Number of thermal_bind_params entries for this zone
.tbp: thermal_bind_params entries
diff --git a/Documentation/trace/coresight.txt b/Documentation/trace/coresight.txt
new file mode 100644
index 0000000..0236155
--- /dev/null
+++ b/Documentation/trace/coresight.txt
@@ -0,0 +1,299 @@
+ Coresight - HW Assisted Tracing on ARM
+ ======================================
+
+ Author: Mathieu Poirier <mathieu.poirier@linaro.org>
+ Date: September 11th, 2014
+
+Introduction
+------------
+
+Coresight is an umbrella of technologies allowing for the debugging of ARM
+based SoC. It includes solutions for JTAG and HW assisted tracing. This
+document is concerned with the latter.
+
+HW assisted tracing is becoming increasingly useful when dealing with systems
+that have many SoCs and other components like GPU and DMA engines. ARM has
+developed a HW assisted tracing solution by means of different components, each
+being added to a design at systhesis time to cater to specific tracing needs.
+Compoments are generally categorised as source, link and sinks and are
+(usually) discovered using the AMBA bus.
+
+"Sources" generate a compressed stream representing the processor instruction
+path based on tracing scenarios as configured by users. From there the stream
+flows through the coresight system (via ATB bus) using links that are connecting
+the emanating source to a sink(s). Sinks serve as endpoints to the coresight
+implementation, either storing the compressed stream in a memory buffer or
+creating an interface to the outside world where data can be transferred to a
+host without fear of filling up the onboard coresight memory buffer.
+
+At typical coresight system would look like this:
+
+ *****************************************************************
+ **************************** AMBA AXI ****************************===||
+ ***************************************************************** ||
+ ^ ^ | ||
+ | | * **
+ 0000000 ::::: 0000000 ::::: ::::: @@@@@@@ ||||||||||||
+ 0 CPU 0<-->: C : 0 CPU 0<-->: C : : C : @ STM @ || System ||
+ |->0000000 : T : |->0000000 : T : : T :<--->@@@@@ || Memory ||
+ | #######<-->: I : | #######<-->: I : : I : @@@<-| ||||||||||||
+ | # ETM # ::::: | # PTM # ::::: ::::: @ |
+ | ##### ^ ^ | ##### ^ ! ^ ! . | |||||||||
+ | |->### | ! | |->### | ! | ! . | || DAP ||
+ | | # | ! | | # | ! | ! . | |||||||||
+ | | . | ! | | . | ! | ! . | | |
+ | | . | ! | | . | ! | ! . | | *
+ | | . | ! | | . | ! | ! . | | SWD/
+ | | . | ! | | . | ! | ! . | | JTAG
+ *****************************************************************<-|
+ *************************** AMBA Debug APB ************************
+ *****************************************************************
+ | . ! . ! ! . |
+ | . * . * * . |
+ *****************************************************************
+ ******************** Cross Trigger Matrix (CTM) *******************
+ *****************************************************************
+ | . ^ . . |
+ | * ! * * |
+ *****************************************************************
+ ****************** AMBA Advanced Trace Bus (ATB) ******************
+ *****************************************************************
+ | ! =============== |
+ | * ===== F =====<---------|
+ | ::::::::: ==== U ====
+ |-->:: CTI ::<!! === N ===
+ | ::::::::: ! == N ==
+ | ^ * == E ==
+ | ! &&&&&&&&& IIIIIII == L ==
+ |------>&& ETB &&<......II I =======
+ | ! &&&&&&&&& II I .
+ | ! I I .
+ | ! I REP I<..........
+ | ! I I
+ | !!>&&&&&&&&& II I *Source: ARM ltd.
+ |------>& TPIU &<......II I DAP = Debug Access Port
+ &&&&&&&&& IIIIIII ETM = Embedded Trace Macrocell
+ ; PTM = Program Trace Macrocell
+ ; CTI = Cross Trigger Interface
+ * ETB = Embedded Trace Buffer
+ To trace port TPIU= Trace Port Interface Unit
+ SWD = Serial Wire Debug
+
+While on target configuration of the components is done via the APB bus,
+all trace data are carried out-of-band on the ATB bus. The CTM provides
+a way to aggregate and distribute signals between CoreSight components.
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform. This first implementation centers on
+the basic tracing functionality, enabling components such ETM/PTM, funnel,
+replicator, TMC, TPIU and ETB. Future work will enable more
+intricate IP blocks such as STM and CTI.
+
+
+Acronyms and Classification
+---------------------------
+
+Acronyms:
+
+PTM: Program Trace Macrocell
+ETM: Embedded Trace Macrocell
+STM: System trace Macrocell
+ETB: Embedded Trace Buffer
+ITM: Instrumentation Trace Macrocell
+TPIU: Trace Port Interface Unit
+TMC-ETR: Trace Memory Controller, configured as Embedded Trace Router
+TMC-ETF: Trace Memory Controller, configured as Embedded Trace FIFO
+CTI: Cross Trigger Interface
+
+Classification:
+
+Source:
+ ETMv3.x ETMv4, PTMv1.0, PTMv1.1, STM, STM500, ITM
+Link:
+ Funnel, replicator (intelligent or not), TMC-ETR
+Sinks:
+ ETBv1.0, ETB1.1, TPIU, TMC-ETF
+Misc:
+ CTI
+
+
+Device Tree Bindings
+----------------------
+
+See Documentation/devicetree/bindings/arm/coresight.txt for details.
+
+As of this writing drivers for ITM, STMs and CTIs are not provided but are
+expected to be added as the solution matures.
+
+
+Framework and implementation
+----------------------------
+
+The coresight framework provides a central point to represent, configure and
+manage coresight devices on a platform. Any coresight compliant device can
+register with the framework for as long as they use the right APIs:
+
+struct coresight_device *coresight_register(struct coresight_desc *desc);
+void coresight_unregister(struct coresight_device *csdev);
+
+The registering function is taking a "struct coresight_device *csdev" and
+register the device with the core framework. The unregister function takes
+a reference to a "strut coresight_device", obtained at registration time.
+
+If everything goes well during the registration process the new devices will
+show up under /sys/bus/coresight/devices, as showns here for a TC2 platform:
+
+root:~# ls /sys/bus/coresight/devices/
+replicator 20030000.tpiu 2201c000.ptm 2203c000.etm 2203e000.etm
+20010000.etb 20040000.funnel 2201d000.ptm 2203d000.etm
+root:~#
+
+The functions take a "struct coresight_device", which looks like this:
+
+struct coresight_desc {
+ enum coresight_dev_type type;
+ struct coresight_dev_subtype subtype;
+ const struct coresight_ops *ops;
+ struct coresight_platform_data *pdata;
+ struct device *dev;
+ const struct attribute_group **groups;
+};
+
+
+The "coresight_dev_type" identifies what the device is, i.e, source link or
+sink while the "coresight_dev_subtype" will characterise that type further.
+
+The "struct coresight_ops" is mandatory and will tell the framework how to
+perform base operations related to the components, each component having
+a different set of requirement. For that "struct coresight_ops_sink",
+"struct coresight_ops_link" and "struct coresight_ops_source" have been
+provided.
+
+The next field, "struct coresight_platform_data *pdata" is acquired by calling
+"of_get_coresight_platform_data()", as part of the driver's _probe routine and
+"struct device *dev" gets the device reference embedded in the "amba_device":
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ ...
+ ...
+ drvdata->dev = &adev->dev;
+ ...
+}
+
+Specific class of device (source, link, or sink) have generic operations
+that can be performed on them (see "struct coresight_ops"). The
+"**groups" is a list of sysfs entries pertaining to operations
+specific to that component only. "Implementation defined" customisations are
+expected to be accessed and controlled using those entries.
+
+Last but not least, "struct module *owner" is expected to be set to reflect
+the information carried in "THIS_MODULE".
+
+How to use
+----------
+
+Before trace collection can start, a coresight sink needs to be identify.
+There is no limit on the amount of sinks (nor sources) that can be enabled at
+any given moment. As a generic operation, all device pertaining to the sink
+class will have an "active" entry in sysfs:
+
+root:/sys/bus/coresight/devices# ls
+replicator 20030000.tpiu 2201c000.ptm 2203c000.etm 2203e000.etm
+20010000.etb 20040000.funnel 2201d000.ptm 2203d000.etm
+root:/sys/bus/coresight/devices# ls 20010000.etb
+enable_sink status trigger_cntr
+root:/sys/bus/coresight/devices# echo 1 > 20010000.etb/enable_sink
+root:/sys/bus/coresight/devices# cat 20010000.etb/enable_sink
+1
+root:/sys/bus/coresight/devices#
+
+At boot time the current etm3x driver will configure the first address
+comparator with "_stext" and "_etext", essentially tracing any instruction
+that falls within that range. As such "enabling" a source will immediately
+trigger a trace capture:
+
+root:/sys/bus/coresight/devices# echo 1 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices# cat 2201c000.ptm/enable_source
+1
+root:/sys/bus/coresight/devices# cat 20010000.etb/status
+Depth: 0x2000
+Status: 0x1
+RAM read ptr: 0x0
+RAM wrt ptr: 0x19d3 <----- The write pointer is moving
+Trigger cnt: 0x0
+Control: 0x1
+Flush status: 0x0
+Flush ctrl: 0x2001
+root:/sys/bus/coresight/devices#
+
+Trace collection is stopped the same way:
+
+root:/sys/bus/coresight/devices# echo 0 > 2201c000.ptm/enable_source
+root:/sys/bus/coresight/devices#
+
+The content of the ETB buffer can be harvested directly from /dev:
+
+root:/sys/bus/coresight/devices# dd if=/dev/20010000.etb \
+of=~/cstrace.bin
+
+64+0 records in
+64+0 records out
+32768 bytes (33 kB) copied, 0.00125258 s, 26.2 MB/s
+root:/sys/bus/coresight/devices#
+
+The file cstrace.bin can be decompressed using "ptm2human", DS-5 or Trace32.
+
+Following is a DS-5 output of an experimental loop that increments a variable up
+to a certain value. The example is simple and yet provides a glimpse of the
+wealth of possibilities that coresight provides.
+
+Info Tracing enabled
+Instruction 106378866 0x8026B53C E52DE004 false PUSH {lr}
+Instruction 0 0x8026B540 E24DD00C false SUB sp,sp,#0xc
+Instruction 0 0x8026B544 E3A03000 false MOV r3,#0
+Instruction 0 0x8026B548 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Timestamp Timestamp: 17106715833
+Instruction 319 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Instruction 9 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Instruction 7 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Instruction 7 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Instruction 10 0x8026B54C E59D3004 false LDR r3,[sp,#4]
+Instruction 0 0x8026B550 E3530004 false CMP r3,#4
+Instruction 0 0x8026B554 E2833001 false ADD r3,r3,#1
+Instruction 0 0x8026B558 E58D3004 false STR r3,[sp,#4]
+Instruction 0 0x8026B55C DAFFFFFA true BLE {pc}-0x10 ; 0x8026b54c
+Instruction 6 0x8026B560 EE1D3F30 false MRC p15,#0x0,r3,c13,c0,#1
+Instruction 0 0x8026B564 E1A0100D false MOV r1,sp
+Instruction 0 0x8026B568 E3C12D7F false BIC r2,r1,#0x1fc0
+Instruction 0 0x8026B56C E3C2203F false BIC r2,r2,#0x3f
+Instruction 0 0x8026B570 E59D1004 false LDR r1,[sp,#4]
+Instruction 0 0x8026B574 E59F0010 false LDR r0,[pc,#16] ; [0x8026B58C] = 0x80550368
+Instruction 0 0x8026B578 E592200C false LDR r2,[r2,#0xc]
+Instruction 0 0x8026B57C E59221D0 false LDR r2,[r2,#0x1d0]
+Instruction 0 0x8026B580 EB07A4CF true BL {pc}+0x1e9344 ; 0x804548c4
+Info Tracing enabled
+Instruction 13570831 0x8026B584 E28DD00C false ADD sp,sp,#0xc
+Instruction 0 0x8026B588 E8BD8000 true LDM sp!,{pc}
+Timestamp Timestamp: 17107041535
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1e6b653..d2ba80b 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -55,6 +55,7 @@
sonixj 0458:7025 Genius Eye 311Q
sn9c20x 0458:7029 Genius Look 320s
sonixj 0458:702e Genius Slim 310 NB
+sn9c20x 0458:7045 Genius Look 1320 V2
sn9c20x 0458:704a Genius Slim 1320
sn9c20x 0458:704c Genius i-Look 1321
sn9c20x 045e:00f4 LifeCam VX-6000 (SN9C20x + OV9650)
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 5f91eda..257a1f1 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -148,9 +148,9 @@
4.4 KVM_CHECK_EXTENSION
-Capability: basic
+Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
Architectures: all
-Type: system ioctl
+Type: system ioctl, vm ioctl
Parameters: extension identifier (KVM_CAP_*)
Returns: 0 if unsupported; 1 (or some other positive integer) if supported
@@ -160,6 +160,9 @@
Generally 0 means no and 1 means yes, but some extensions may report
additional information in the integer return value.
+Based on their initialization different VMs may have different capabilities.
+It is thus encouraged to use the vm ioctl to query for capabilities (available
+with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
4.5 KVM_GET_VCPU_MMAP_SIZE
@@ -280,7 +283,7 @@
4.11 KVM_GET_REGS
Capability: basic
-Architectures: all except ARM
+Architectures: all except ARM, arm64
Type: vcpu ioctl
Parameters: struct kvm_regs (out)
Returns: 0 on success, -1 on error
@@ -301,7 +304,7 @@
4.12 KVM_SET_REGS
Capability: basic
-Architectures: all except ARM
+Architectures: all except ARM, arm64
Type: vcpu ioctl
Parameters: struct kvm_regs (in)
Returns: 0 on success, -1 on error
@@ -587,7 +590,7 @@
4.24 KVM_CREATE_IRQCHIP
Capability: KVM_CAP_IRQCHIP
-Architectures: x86, ia64, ARM
+Architectures: x86, ia64, ARM, arm64
Type: vm ioctl
Parameters: none
Returns: 0 on success, -1 on error
@@ -595,14 +598,14 @@
Creates an interrupt controller model in the kernel. On x86, creates a virtual
ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
local APIC. IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
-only go to the IOAPIC. On ia64, a IOSAPIC is created. On ARM, a GIC is
+only go to the IOAPIC. On ia64, a IOSAPIC is created. On ARM/arm64, a GIC is
created.
4.25 KVM_IRQ_LINE
Capability: KVM_CAP_IRQCHIP
-Architectures: x86, ia64, arm
+Architectures: x86, ia64, arm, arm64
Type: vm ioctl
Parameters: struct kvm_irq_level
Returns: 0 on success, -1 on error
@@ -612,9 +615,10 @@
been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
interrupts require the level to be set to 1 and then back to 0.
-ARM can signal an interrupt either at the CPU level, or at the in-kernel irqchip
-(GIC), and for in-kernel irqchip can tell the GIC to use PPIs designated for
-specific cpus. The irq field is interpreted like this:
+ARM/arm64 can signal an interrupt either at the CPU level, or at the
+in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
+use PPIs designated for specific cpus. The irq field is interpreted
+like this:
bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 |
field: | irq_type | vcpu_index | irq_id |
@@ -968,18 +972,20 @@
Possible values are:
- - KVM_MP_STATE_RUNNABLE: the vcpu is currently running
+ - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86, ia64]
- KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP)
- which has not yet received an INIT signal
+ which has not yet received an INIT signal [x86,
+ ia64]
- KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is
- now ready for a SIPI
+ now ready for a SIPI [x86, ia64]
- KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and
- is waiting for an interrupt
+ is waiting for an interrupt [x86, ia64]
- KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector
- accessible via KVM_GET_VCPU_EVENTS)
+ accessible via KVM_GET_VCPU_EVENTS) [x86, ia64]
-This ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
4.39 KVM_SET_MP_STATE
@@ -993,8 +999,9 @@
Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
arguments.
-This ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
4.40 KVM_SET_IDENTITY_MAP_ADDR
@@ -1121,9 +1128,9 @@
struct kvm_cpuid_entry2 entries[0];
};
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC 2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT 4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
struct kvm_cpuid_entry2 {
__u32 function;
@@ -1831,6 +1838,22 @@
ARM 64-bit FP registers have the following id bit patterns:
0x4030 0000 0012 0 <regno:12>
+
+arm64 registers are mapped using the lower 32 bits. The upper 16 of
+that is the register group type, or coprocessor number:
+
+arm64 core/FP-SIMD registers have the following id bit patterns. Note
+that the size of the access is variable, as the kvm_regs structure
+contains elements ranging from 32 to 128 bits. The index is a 32bit
+value in the kvm_regs structure seen as a 32bit array.
+ 0x60x0 0000 0010 <index into the kvm_regs struct:16>
+
+arm64 CCSIDR registers are demultiplexed by CSSELR value:
+ 0x6020 0000 0011 00 <csselr:8>
+
+arm64 system registers have the following id bit patterns:
+ 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
+
4.69 KVM_GET_ONE_REG
Capability: KVM_CAP_ONE_REG
@@ -2264,7 +2287,7 @@
4.77 KVM_ARM_VCPU_INIT
Capability: basic
-Architectures: arm
+Architectures: arm, arm64
Type: vcpu ioctl
Parameters: struct struct kvm_vcpu_init (in)
Returns: 0 on success; -1 on error
@@ -2283,12 +2306,14 @@
Possible features:
- KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
Depends on KVM_CAP_ARM_PSCI.
+ - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
+ Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
4.78 KVM_GET_REG_LIST
Capability: basic
-Architectures: arm
+Architectures: arm, arm64
Type: vcpu ioctl
Parameters: struct kvm_reg_list (in/out)
Returns: 0 on success; -1 on error
@@ -2305,10 +2330,10 @@
KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
-4.80 KVM_ARM_SET_DEVICE_ADDR
+4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
-Architectures: arm
+Architectures: arm, arm64
Type: vm ioctl
Parameters: struct kvm_arm_device_address (in)
Returns: 0 on success, -1 on error
@@ -2329,20 +2354,25 @@
to know about. The id field is an architecture specific identifier for a
specific device.
-ARM divides the id field into two parts, a device id and an address type id
-specific to the individual device.
+ARM/arm64 divides the id field into two parts, a device id and an
+address type id specific to the individual device.
bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
field: | 0x00000000 | device id | addr type id |
-ARM currently only require this when using the in-kernel GIC support for the
-hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2 as the device id. When
-setting the base address for the guest's mapping of the VGIC virtual CPU
-and distributor interface, the ioctl must be called after calling
-KVM_CREATE_IRQCHIP, but before calling KVM_RUN on any of the VCPUs. Calling
-this ioctl twice for any of the base addresses will return -EEXIST.
+ARM/arm64 currently only require this when using the in-kernel GIC
+support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
+as the device id. When setting the base address for the guest's
+mapping of the VGIC virtual CPU and distributor interface, the ioctl
+must be called after calling KVM_CREATE_IRQCHIP, but before calling
+KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
+base addresses will return -EEXIST.
-4.82 KVM_PPC_RTAS_DEFINE_TOKEN
+Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
+should be used instead.
+
+
+4.86 KVM_PPC_RTAS_DEFINE_TOKEN
Capability: KVM_CAP_PPC_RTAS
Architectures: ppc
@@ -2612,6 +2642,21 @@
external interrupt has just been delivered into the guest. User space
should put the acknowledged interrupt vector into the 'epr' field.
+ /* KVM_EXIT_SYSTEM_EVENT */
+ struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN 1
+#define KVM_SYSTEM_EVENT_RESET 2
+ __u32 type;
+ __u64 flags;
+ } system_event;
+
+If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
+a system-level event using some architecture specific mechanism (hypercall
+or some special instruction). In case of ARM/ARM64, this is triggered using
+HVC instruction based PSCI call from the vcpu. The 'type' field describes
+the system-level event type. The 'flags' field describes architecture
+specific flags for the system-level event.
+
/* Fix the size of the union. */
char padding[256];
};
@@ -2641,6 +2686,77 @@
};
+4.81 KVM_GET_EMULATED_CPUID
+
+Capability: KVM_CAP_EXT_EMUL_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+ __u32 nent;
+ __u32 flags;
+ struct kvm_cpuid_entry2 entries[0];
+};
+
+The member 'flags' is used for passing flags from userspace.
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
+
+struct kvm_cpuid_entry2 {
+ __u32 function;
+ __u32 index;
+ __u32 flags;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are emulated by
+kvm.Userspace can use the information returned by this ioctl to query
+which features are emulated by kvm instead of being present natively.
+
+Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
+structure with the 'nent' field indicating the number of entries in
+the variable-size array 'entries'. If the number of entries is too low
+to describe the cpu capabilities, an error (E2BIG) is returned. If the
+number is too high, the 'nent' field is adjusted and an error (ENOMEM)
+is returned. If the number is just right, the 'nent' field is adjusted
+to the number of valid entries in the 'entries' array, which is then
+filled.
+
+The entries returned are the set CPUID bits of the respective features
+which kvm emulates, as returned by the CPUID instruction, with unknown
+or unsupported feature bits cleared.
+
+Features like x2apic, for example, may not be present in the host cpu
+but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
+emulated efficiently and thus not included here.
+
+The fields in each entry are defined as follows:
+
+ function: the eax value used to obtain the entry
+ index: the ecx value used to obtain the entry (for entries that are
+ affected by ecx)
+ flags: an OR of zero or more of the following:
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+ if the index field is valid
+ KVM_CPUID_FLAG_STATEFUL_FUNC:
+ if cpuid for this function returns different values for successive
+ invocations; there will be several entries with the same function,
+ all with this flag set
+ KVM_CPUID_FLAG_STATE_READ_NEXT:
+ for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+ the first entry to be read by a cpu
+ eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+ this function/index combination
+
+
6. Capabilities that can be enabled
-----------------------------------
diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt
new file mode 100644
index 0000000..df8b0c7
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/arm-vgic.txt
@@ -0,0 +1,83 @@
+ARM Virtual Generic Interrupt Controller (VGIC)
+===============================================
+
+Device types supported:
+ KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0
+
+Only one VGIC instance may be instantiated through either this API or the
+legacy KVM_CREATE_IRQCHIP api. The created VGIC will act as the VM interrupt
+controller, requiring emulated user-space devices to inject interrupts to the
+VGIC instead of directly to CPUs.
+
+Groups:
+ KVM_DEV_ARM_VGIC_GRP_ADDR
+ Attributes:
+ KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit)
+ Base address in the guest physical address space of the GIC distributor
+ register mappings.
+
+ KVM_VGIC_V2_ADDR_TYPE_CPU (rw, 64-bit)
+ Base address in the guest physical address space of the GIC virtual cpu
+ interface register mappings.
+
+ KVM_DEV_ARM_VGIC_GRP_DIST_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
+ values: | reserved | cpu id | offset |
+
+ All distributor regs are (rw, 32-bit)
+
+ The offset is relative to the "Distributor base address" as defined in the
+ GICv2 specs. Getting or setting such a register has the same effect as
+ reading or writing the register on the actual hardware from the cpu
+ specified with cpu id field. Note that most distributor fields are not
+ banked, but return the same value regardless of the cpu id used to access
+ the register.
+ Limitations:
+ - Priorities are not implemented, and registers are RAZ/WI
+ Errors:
+ -ENODEV: Getting or setting this register is not yet supported
+ -EBUSY: One or more VCPUs are running
+
+ KVM_DEV_ARM_VGIC_GRP_CPU_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
+ values: | reserved | cpu id | offset |
+
+ All CPU interface regs are (rw, 32-bit)
+
+ The offset specifies the offset from the "CPU interface base address" as
+ defined in the GICv2 specs. Getting or setting such a register has the
+ same effect as reading or writing the register on the actual hardware.
+
+ The Active Priorities Registers APRn are implementation defined, so we set a
+ fixed format for our implementation that fits with the model of a "GICv2
+ implementation without the security extensions" which we present to the
+ guest. This interface always exposes four register APR[0-3] describing the
+ maximum possible 128 preemption levels. The semantics of the register
+ indicate if any interrupts in a given preemption level are in the active
+ state by setting the corresponding bit.
+
+ Thus, preemption level X has one or more active interrupts if and only if:
+
+ APRn[X mod 32] == 0b1, where n = X / 32
+
+ Bits for undefined preemption levels are RAZ/WI.
+
+ Limitations:
+ - Priorities are not implemented, and registers are RAZ/WI
+ Errors:
+ -ENODEV: Getting or setting this register is not yet supported
+ -EBUSY: One or more VCPUs are running
+
+ KVM_DEV_ARM_VGIC_GRP_NR_IRQS
+ Attributes:
+ A value describing the number of interrupts (SGI, PPI and SPI) for
+ this GIC instance, ranging from 64 to 1024, in increments of 32.
+
+ Errors:
+ -EINVAL: Value set is out of the expected range
+ -EBUSY: Value has already be set, or GIC has already been initialized
+ with default values.
diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
new file mode 100644
index 0000000..ef51740
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -0,0 +1,22 @@
+VFIO virtual device
+===================
+
+Device types supported:
+ KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM. The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM. As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence. When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+ KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+ KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+ KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+
+For each, kvm_device_attr.addr points to an int32_t file descriptor
+for the VFIO group.
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 41b7ac9..ba035c3 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -132,10 +132,14 @@
------------
Name: kvm_lock
-Type: raw_spinlock
+Type: spinlock_t
Arch: any
Protects: - vm_list
- - hardware virtualization enable/disable
+
+Name: kvm_count_lock
+Type: raw_spinlock_t
+Arch: any
+Protects: - hardware virtualization enable/disable
Comment: 'raw' because hardware enabling/disabling must be atomic /wrt
migration.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..bd43704 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,8 @@
ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0
ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO
index 7fba5aa..7599eb3 100644
--- a/Documentation/zh_CN/HOWTO
+++ b/Documentation/zh_CN/HOWTO
@@ -237,7 +237,7 @@
如果没有2.6.x.y版本内核存在，那么最新的2.6.x版本内核就相当于是当前的稳定
版内核。
-2.6.x.y版本由“稳定版”小组（邮件地址<stable@kernel.org>）维护，一般隔周发
+2.6.x.y版本由“稳定版”小组（邮件地址<stable@vger.kernel.org>）维护，一般隔周发
布新版本。
内核源码中的Documentation/stable_kernel_rules.txt文件具体描述了可被稳定
diff --git a/Documentation/zh_CN/stable_kernel_rules.txt b/Documentation/zh_CN/stable_kernel_rules.txt
index b5b9b0a..26ea5ed 100644
--- a/Documentation/zh_CN/stable_kernel_rules.txt
+++ b/Documentation/zh_CN/stable_kernel_rules.txt
@@ -42,7 +42,7 @@
向稳定版代码树提交补丁的过程：
- - 在确认了补丁符合以上的规则后，将补丁发送到stable@kernel.org。
+ - 在确认了补丁符合以上的规则后，将补丁发送到stable@vger.kernel.org。
- 如果补丁被接受到队列里，发送者会收到一个ACK回复，如果没有被接受，收
到的是NAK回复。回复需要几天的时间，这取决于开发者的时间安排。
- 被接受的补丁会被加到稳定版本队列里，等待其他开发者的审查。
diff --git a/MAINTAINERS b/MAINTAINERS
index ad7e322..8a8a48b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -783,6 +783,14 @@
S: Maintained
F: arch/arm/mach-ep93xx/micro9.c
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M: Mathieu Poirier <mathieu.poirier@linaro.org>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: drivers/coresight/*
+F: Documentation/trace/coresight.txt
+F: Documentation/devicetree/bindings/arm/coresight.txt
+
ARM/CORGI MACHINE SUPPORT
M: Richard Purdie <rpurdie@rpsys.net>
S: Maintained
@@ -4719,6 +4727,15 @@
F: arch/arm/include/asm/kvm*
F: arch/arm/kvm/
+KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
+M: Marc Zyngier <marc.zyngier@arm.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: kvmarm@lists.cs.columbia.edu
+S: Maintained
+F: arch/arm64/include/uapi/asm/kvm*
+F: arch/arm64/include/asm/kvm*
+F: arch/arm64/kvm/
+
KEXEC
M: Eric Biederman <ebiederm@xmission.com>
W: http://kernel.org/pub/linux/utils/kernel/kexec/
@@ -5152,6 +5169,14 @@
F: drivers/net/macvlan.c
F: include/linux/if_macvlan.h
+MAILBOX API
+M: Jassi Brar <jassisinghbrar@gmail.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: drivers/mailbox/
+F: include/linux/mailbox_client.h
+F: include/linux/mailbox_controller.h
+
MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7
M: Michael Kerrisk <mtk.manpages@gmail.com>
W: http://www.kernel.org/doc/man-pages
@@ -7667,6 +7692,7 @@
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
L: stable@vger.kernel.org
S: Supported
+F: Documentation/stable_kernel_rules.txt
STAGING SUBSYSTEM
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
@@ -8072,6 +8098,7 @@
F: drivers/thermal/
F: include/linux/thermal.h
F: include/linux/cpu_cooling.h
+F: Documentation/devicetree/bindings/thermal/
THINGM BLINK(1) USB RGB LED DRIVER
M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
diff --git a/Makefile b/Makefile
index e5e3ba0..923ad8a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
VERSION = 3
PATCHLEVEL = 10
-SUBLEVEL = 0
+SUBLEVEL = 77
EXTRAVERSION =
-NAME = Unicycling Gorilla
+NAME = TOSSUG Baby Fish
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
@@ -614,6 +614,8 @@
endif
endif
+KBUILD_CFLAGS += $(call cc-option, -fno-var-tracking-assignments)
+
ifdef CONFIG_DEBUG_INFO
KBUILD_CFLAGS += -g
KBUILD_AFLAGS += -gdwarf-2
diff --git a/arch/Kconfig b/arch/Kconfig
index a4429bc..00e3702 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -404,6 +404,12 @@
help
Architecture has the first two arguments of clone(2) swapped.
+config CLONE_BACKWARDS3
+ bool
+ help
+ Architecture has tls passed as the 3rd argument of clone(2),
+ not the 5th one.
+
config ODD_RT_SIGACTION
bool
help
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 0c4132d..9d0ac09 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -89,8 +89,7 @@
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
@@ -115,7 +114,8 @@
if (address >= TASK_SIZE)
goto vmalloc_fault;
#endif
-
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -142,6 +142,7 @@
} else {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
}
/* If for any reason at all we couldn't handle the fault,
@@ -155,6 +156,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
index ea16d78..4c169d8 100644
--- a/arch/arc/boot/dts/nsimosci.dts
+++ b/arch/arc/boot/dts/nsimosci.dts
@@ -11,13 +11,16 @@
/ {
compatible = "snps,nsimosci";
- clock-frequency = <80000000>; /* 80 MHZ */
+ clock-frequency = <20000000>; /* 20 MHZ */
#address-cells = <1>;
#size-cells = <1>;
interrupt-parent = <&intc>;
chosen {
- bootargs = "console=tty0 consoleblank=0";
+ /* this is for console on PGU */
+ /* bootargs = "console=tty0 consoleblank=0"; */
+ /* this is for console on serial */
+ bootargs = "earlycon=uart8250,mmio32,0xf0000000,115200n8 console=tty0 console=ttyS0,115200n8 consoleblank=0 debug";
};
aliases {
@@ -43,33 +46,32 @@
#interrupt-cells = <1>;
};
- uart0: serial@c0000000 {
- compatible = "snps,dw-apb-uart";
- reg = <0xc0000000 0x2000>;
+ uart0: serial@f0000000 {
+ compatible = "ns8250";
+ reg = <0xf0000000 0x2000>;
interrupts = <11>;
- #clock-frequency = <80000000>;
clock-frequency = <3686400>;
baud = <115200>;
reg-shift = <2>;
reg-io-width = <4>;
- status = "okay";
+ no-loopback-test = <1>;
};
- pgu0: pgu@c9000000 {
+ pgu0: pgu@f9000000 {
compatible = "snps,arcpgufb";
- reg = <0xc9000000 0x400>;
+ reg = <0xf9000000 0x400>;
};
- ps2: ps2@c9001000 {
+ ps2: ps2@f9001000 {
compatible = "snps,arc_ps2";
- reg = <0xc9000400 0x14>;
+ reg = <0xf9000400 0x14>;
interrupts = <13>;
interrupt-names = "arc_ps2_irq";
};
- eth0: ethernet@c0003000 {
+ eth0: ethernet@f0003000 {
compatible = "snps,oscilan";
- reg = <0xc0003000 0x44>;
+ reg = <0xf0003000 0x44>;
interrupts = <7>, <8>;
interrupt-names = "rx", "tx";
};
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 446c96c..00788e7 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -54,6 +54,7 @@
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DW=y
+CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_ARC=y
CONFIG_SERIAL_ARC_CONSOLE=y
# CONFIG_HW_RANDOM is not set
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index 442ce5d..43de302 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -53,11 +53,10 @@
{
unsigned long loops;
- /* (long long) cast ensures 64 bit MPY - real or emulated
+ /* (u64) cast ensures 64 bit MPY - real or emulated
* HZ * 4295 is pre-evaluated by gcc - hence only 2 mpy ops
*/
- loops = ((long long)(usecs * 4295 * HZ) *
- (long long)(loops_per_jiffy)) >> 32;
+ loops = ((u64) usecs * 4295 * HZ * loops_per_jiffy) >> 32;
__delay(loops);
}
diff --git a/arch/arc/include/asm/irqflags.h b/arch/arc/include/asm/irqflags.h
index eac0716..c29d565 100644
--- a/arch/arc/include/asm/irqflags.h
+++ b/arch/arc/include/asm/irqflags.h
@@ -137,13 +137,6 @@
flag \scratch
.endm
-.macro IRQ_DISABLE_SAVE scratch, save
- lr \scratch, [status32]
- mov \save, \scratch /* Make a copy */
- bic \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
- flag \scratch
-.endm
-
.macro IRQ_ENABLE scratch
lr \scratch, [status32]
or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
diff --git a/arch/arc/include/asm/kgdb.h b/arch/arc/include/asm/kgdb.h
index 4930957..e897610 100644
--- a/arch/arc/include/asm/kgdb.h
+++ b/arch/arc/include/asm/kgdb.h
@@ -19,7 +19,7 @@
* register API yet */
#undef DBG_MAX_REG_NUM
-#define GDB_MAX_REGS 39
+#define GDB_MAX_REGS 87
#define BREAK_INSTR_SIZE 2
#define CACHE_FLUSH_IS_SAFE 1
@@ -33,23 +33,27 @@
extern void kgdb_trap(struct pt_regs *regs, int param);
-enum arc700_linux_regnums {
+/* This is the numbering of registers according to the GDB. See GDB's
+ * arc-tdep.h for details.
+ *
+ * Registers are ordered for GDB 7.5. It is incompatible with GDB 6.8. */
+enum arc_linux_regnums {
_R0 = 0,
_R1, _R2, _R3, _R4, _R5, _R6, _R7, _R8, _R9, _R10, _R11, _R12, _R13,
_R14, _R15, _R16, _R17, _R18, _R19, _R20, _R21, _R22, _R23, _R24,
_R25, _R26,
- _BTA = 27,
- _LP_START = 28,
- _LP_END = 29,
- _LP_COUNT = 30,
- _STATUS32 = 31,
- _BLINK = 32,
- _FP = 33,
- __SP = 34,
- _EFA = 35,
- _RET = 36,
- _ORIG_R8 = 37,
- _STOP_PC = 38
+ _FP = 27,
+ __SP = 28,
+ _R30 = 30,
+ _BLINK = 31,
+ _LP_COUNT = 60,
+ _STOP_PC = 64,
+ _RET = 64,
+ _LP_START = 65,
+ _LP_END = 66,
+ _STATUS32 = 67,
+ _ECR = 76,
+ _BTA = 82,
};
#else
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 95b1522..ecf23ea 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -270,7 +270,8 @@
#define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0)
#define pte_page(x) (mem_map + \
- (unsigned long)(((pte_val(x) - PAGE_OFFSET) >> PAGE_SHIFT)))
+ (unsigned long)(((pte_val(x) - CONFIG_LINUX_LINK_BASE) >> \
+ PAGE_SHIFT)))
#define mk_pte(page, pgprot) \
({ \
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 6179de7..2046a89 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -52,12 +52,14 @@
/*to distinguish bet excp, syscall, irq */
union {
+ struct {
#ifdef CONFIG_CPU_BIG_ENDIAN
/* so that assembly code is same for LE/BE */
unsigned long orig_r8:16, event:16;
#else
unsigned long event:16, orig_r8:16;
#endif
+ };
long orig_r8_word;
};
};
diff --git a/arch/arc/include/asm/sections.h b/arch/arc/include/asm/sections.h
index 6fc1159..764f1e3 100644
--- a/arch/arc/include/asm/sections.h
+++ b/arch/arc/include/asm/sections.h
@@ -11,7 +11,6 @@
#include <asm-generic/sections.h>
-extern char _int_vec_base_lds[];
extern char __arc_dccm_base[];
extern char __dtb_start[];
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index f158197..b6a8c2d 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -45,7 +45,14 @@
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
- lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+ unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+ __asm__ __volatile__(
+ " ex %0, [%1] \n"
+ : "+r" (tmp)
+ : "r"(&(lock->slock))
+ : "memory");
+
smp_mb();
}
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index 33ab304..29de098 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -18,7 +18,7 @@
syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
{
if (user_mode(regs) && in_syscall(regs))
- return regs->orig_r8;
+ return regs->r8;
else
return -1;
}
@@ -26,8 +26,7 @@
static inline void
syscall_rollback(struct task_struct *task, struct pt_regs *regs)
{
- /* XXX: I can't fathom how pt_regs->r8 will be clobbered ? */
- regs->r8 = regs->orig_r8;
+ regs->r0 = regs->orig_r0;
}
static inline long
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index 3242082..30c9baf 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -43,7 +43,7 @@
* Because it essentially checks if buffer end is within limit and @len is
* non-ngeative, which implies that buffer start will be within limit too.
*
- * The reason for rewriting being, for majorit yof cases, @len is generally
+ * The reason for rewriting being, for majority of cases, @len is generally
* compile time constant, causing first sub-expression to be compile time
* subsumed.
*
@@ -53,7 +53,7 @@
*
*/
#define __user_ok(addr, sz) (((sz) <= TASK_SIZE) && \
- (((addr)+(sz)) <= get_fs()))
+ ((addr) <= (get_fs() - (sz))))
#define __access_ok(addr, sz) (unlikely(__kernel_ok) || \
likely(__user_ok((addr), (sz))))
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 30333ce..ef9d79a 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -11,6 +11,7 @@
#ifndef _UAPI__ASM_ARC_PTRACE_H
#define _UAPI__ASM_ARC_PTRACE_H
+#define PTRACE_GET_THREAD_AREA 25
#ifndef __ASSEMBLY__
/*
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index bdee3a8..afdd13c 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -40,7 +40,7 @@
const char *model, *compat;
void *clk;
char manufacturer[16];
- unsigned long len;
+ int len;
/* check device tree validity */
if (be32_to_cpu(devtree->magic) != OF_DT_HEADER)
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 0c6d664..6f3cd0f 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -498,7 +498,7 @@
trap_with_param:
; stop_pc info by gdb needs this info
- stw orig_r8_IS_BRKPT, [sp, PT_orig_r8]
+ st orig_r8_IS_BRKPT, [sp, PT_orig_r8]
mov r0, r12
lr r1, [efa]
@@ -589,11 +589,7 @@
; Pre-{IRQ,Trap,Exception} K/U mode from pt_regs->status32
ld r8, [sp, PT_status32] ; returning to User/Kernel Mode
-#ifdef CONFIG_PREEMPT
bbit0 r8, STATUS_U_BIT, resume_kernel_mode
-#else
- bbit0 r8, STATUS_U_BIT, restore_regs
-#endif
; Before returning to User mode check-for-and-complete any pending work
; such as rescheduling/signal-delivery etc.
@@ -653,10 +649,15 @@
b resume_user_mode_begin ; unconditionally back to U mode ret chks
; for single exit point from this block
-#ifdef CONFIG_PREEMPT
-
resume_kernel_mode:
+ ; Disable Interrupts from this point on
+ ; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
+ ; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
+ IRQ_DISABLE r9
+
+#ifdef CONFIG_PREEMPT
+
; Can't preempt if preemption disabled
GET_CURR_THR_INFO_FROM_SP r10
ld r8, [r10, THREAD_INFO_PREEMPT_COUNT]
@@ -666,8 +667,6 @@
ld r9, [r10, THREAD_INFO_FLAGS]
bbit0 r9, TIF_NEED_RESCHED, restore_regs
- IRQ_DISABLE r9
-
; Invoke PREEMPTION
bl preempt_schedule_irq
@@ -680,12 +679,11 @@
;
; Restore the saved sys context (common exit-path for EXCPN/IRQ/Trap)
; IRQ shd definitely not happen between now and rtie
+; All 2 entry points to here already disable interrupts
restore_regs :
- ; Disable Interrupts while restoring reg-file back
- ; XXX can this be optimised out
- IRQ_DISABLE_SAVE r9, r10 ;@r10 has prisitine (pre-disable) copy
+ lr r10, [status32]
#ifdef CONFIG_ARC_CURR_IN_REG
; Restore User R25
@@ -723,7 +721,7 @@
; things to what they were, before returning from L2 context
;----------------------------------------------------------------
- ldw r9, [sp, PT_orig_r8] ; get orig_r8 to make sure it is
+ ld r9, [sp, PT_orig_r8] ; get orig_r8 to make sure it is
brne r9, orig_r8_IS_IRQ2, 149f ; infact a L2 ISR ret path
ld r9, [sp, PT_status32] ; get statu32_l2 (saved in pt_regs)
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 006dec3..0f944f0 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -27,11 +27,16 @@
; Don't clobber r0-r4 yet. It might have bootloader provided info
;-------------------------------------------------------------------
+ sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
#ifdef CONFIG_SMP
; Only Boot (Master) proceeds. Others wait in platform dependent way
; IDENTITY Reg [ 3 2 1 0 ]
; (cpu-id) ^^^ => Zero for UP ARC700
; => #Core-ID if SMP (Master 0)
+ ; Note that non-boot CPUs might not land here if halt-on-reset and
+ ; instead breath life from @first_lines_of_secondary, but we still
+ ; need to make sure only boot cpu takes this path.
GET_CPU_ID r5
cmp r5, 0
jnz arc_platform_smp_wait_to_boot
@@ -96,6 +101,8 @@
first_lines_of_secondary:
+ sr @_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
; setup per-cpu idle task as "current" on this CPU
ld r0, [@secondary_idle_tsk]
SET_CURR_TASK_ON_CPU r0, r1
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 8115fa5..a199471 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -24,7 +24,6 @@
* -Needed for each CPU (hence not foldable into init_IRQ)
*
* what it does ?
- * -setup Vector Table Base Reg - in case Linux not linked at 0x8000_0000
* -Disable all IRQs (on CPU side)
* -Optionally, setup the High priority Interrupts as Level 2 IRQs
*/
@@ -32,8 +31,6 @@
{
int level_mask = 0;
- write_aux_reg(AUX_INTR_VEC_BASE, _int_vec_base_lds);
-
/* Disable all IRQs: enable them as devices request */
write_aux_reg(AUX_IENABLE, 0);
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index c6a81c5..f8a36ed 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -92,7 +92,7 @@
REG_IN_CHUNK(scratch, callee, ptregs); /* pt_regs[bta..orig_r8] */
REG_IN_CHUNK(callee, efa, cregs); /* callee_regs[r25..r13] */
REG_IGNORE_ONE(efa); /* efa update invalid */
- REG_IN_ONE(stop_pc, &ptregs->ret); /* stop_pc: PC update */
+ REG_IGNORE_ONE(stop_pc); /* PC updated via @ret */
return ret;
}
@@ -136,6 +136,10 @@
pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
switch (request) {
+ case PTRACE_GET_THREAD_AREA:
+ ret = put_user(task_thread_info(child)->thr_ptr,
+ (unsigned long __user *)data);
+ break;
default:
ret = ptrace_request(child, request, addr, data);
break;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index b2b3731..2d7786b 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,10 +47,7 @@
READ_BCR(AUX_IDENTITY, cpu->core);
cpu->timers = read_aux_reg(ARC_REG_TIMERS_BCR);
-
cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
- if (cpu->vec_base == 0)
- cpu->vec_base = (unsigned int)_int_vec_base_lds;
READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
cpu->uncached_base = uncached_space.start << 24;
diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c
index ee6ef2f..7e95e1a 100644
--- a/arch/arc/kernel/signal.c
+++ b/arch/arc/kernel/signal.c
@@ -101,7 +101,6 @@
{
struct rt_sigframe __user *sf;
unsigned int magic;
- int err;
struct pt_regs *regs = current_pt_regs();
/* Always make any pending restarted system calls return -EINTR */
@@ -119,15 +118,16 @@
if (!access_ok(VERIFY_READ, sf, sizeof(*sf)))
goto badframe;
- err = restore_usr_regs(regs, sf);
- err |= __get_user(magic, &sf->sigret_magic);
- if (err)
+ if (__get_user(magic, &sf->sigret_magic))
goto badframe;
if (unlikely(is_do_ss_needed(magic)))
if (restore_altstack(&sf->uc.uc_stack))
goto badframe;
+ if (restore_usr_regs(regs, sf))
+ goto badframe;
+
/* Don't restart from sigreturn */
syscall_wont_restart(regs);
@@ -191,6 +191,15 @@
return 1;
/*
+ * w/o SA_SIGINFO, struct ucontext is partially populated (only
+ * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
+ * during signal handler execution. This works for SA_SIGINFO as well
+ * although the semantics are now overloaded (the same reg state can be
+ * inspected by userland: but are they allowed to fiddle with it ?
+ */
+ err |= stash_usr_regs(sf, regs, set);
+
+ /*
* SA_SIGINFO requires 3 args to signal handler:
* #1: sig-no (common to any handler)
* #2: struct siginfo
@@ -213,14 +222,6 @@
magic = MAGIC_SIGALTSTK;
}
- /*
- * w/o SA_SIGINFO, struct ucontext is partially populated (only
- * uc_mcontext/uc_sigmask) for kernel's normal user state preservation
- * during signal handler execution. This works for SA_SIGINFO as well
- * although the semantics are now overloaded (the same reg state can be
- * inspected by userland: but are they allowed to fiddle with it ?
- */
- err |= stash_usr_regs(sf, regs, set);
err |= __put_user(magic, &sf->sigret_magic);
if (err)
return err;
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index 4cd8163..116d3e0 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -233,6 +233,12 @@
regs->status32 &= ~STATUS_DE_MASK;
} else {
regs->ret += state.instr_len;
+
+ /* handle zero-overhead-loop */
+ if ((regs->ret == regs->lp_end) && (regs->lp_count)) {
+ regs->ret = regs->lp_start;
+ regs->lp_count--;
+ }
}
return 0;
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S
index 99c1047..9c548c7 100644
--- a/arch/arc/lib/strchr-700.S
+++ b/arch/arc/lib/strchr-700.S
@@ -39,9 +39,18 @@
ld.a r2,[r0,4]
sub r12,r6,r7
bic r12,r12,r6
+#ifdef __LITTLE_ENDIAN__
and r7,r12,r4
breq r7,0,.Loop ; For speed, we want this branch to be unaligned.
b .Lfound_char ; Likewise this one.
+#else
+ and r12,r12,r4
+ breq r12,0,.Loop ; For speed, we want this branch to be unaligned.
+ lsr_s r12,r12,7
+ bic r2,r7,r6
+ b.d .Lfound_char_b
+ and_s r2,r2,r12
+#endif
; /* We require this code address to be unaligned for speed... */
.Laligned:
ld_s r2,[r0]
@@ -95,6 +104,7 @@
lsr r7,r7,7
bic r2,r7,r6
+.Lfound_char_b:
norm r2,r2
sub_s r0,r0,4
asr_s r2,r2,3
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 689ffd8..08f65bc 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -16,7 +16,7 @@
#include <linux/kdebug.h>
#include <asm/pgalloc.h>
-static int handle_vmalloc_fault(struct mm_struct *mm, unsigned long address)
+static int handle_vmalloc_fault(unsigned long address)
{
/*
* Synchronize this task's top level page-table
@@ -26,7 +26,7 @@
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
- pgd = pgd_offset_fast(mm, address);
+ pgd = pgd_offset_fast(current->active_mm, address);
pgd_k = pgd_offset_k(address);
if (!pgd_present(*pgd_k))
@@ -59,8 +59,7 @@
struct mm_struct *mm = tsk->mm;
siginfo_t info;
int fault, ret;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/*
* We fault-in kernel-space virtual memory on-demand. The
@@ -72,7 +71,7 @@
* nothing more.
*/
if (address >= VMALLOC_START && address <= VMALLOC_END) {
- ret = handle_vmalloc_fault(mm, address);
+ ret = handle_vmalloc_fault(address);
if (unlikely(ret))
goto bad_area_nosemaphore;
else
@@ -88,6 +87,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -115,12 +116,12 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -159,6 +160,8 @@
/* TBD: switch to pagefault_out_of_memory() */
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
@@ -200,14 +203,12 @@
die("Oops", regs, address, cause_code);
out_of_memory:
- if (is_global_init(tsk)) {
- yield();
- goto survive;
- }
up_read(&mm->mmap_sem);
- if (user_mode(regs))
- do_group_exit(SIGKILL); /* This will never return */
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return;
+ }
goto no_context;
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 4a17736..7991e08 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -157,9 +157,8 @@
#endif
#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
- pr_err("%s(%lx, %lx)\n", __func__, start, end);
+ pr_err("%s(%llx, %llx)\n", __func__, start, end);
}
#endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 136f263..9422f29 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -4,7 +4,9 @@
select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAVE_CUSTOM_GPIO_H
+ select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_WANT_IPC_PARSE_VERSION
select BUILDTIME_EXTABLE_SORT if MMU
select CPU_PM if (SUSPEND || CPU_IDLE)
@@ -19,7 +21,6 @@
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
select HARDIRQS_SW_RESEND
- select HAVE_AOUT
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
select HAVE_ARCH_KGDB
select HAVE_ARCH_SECCOMP_FILTER
@@ -213,7 +214,8 @@
default DRAM_BASE if REMAP_VECTORS_TO_RAM
default 0x00000000
help
- The base address of exception vectors.
+ The base address of exception vectors. This must be two pages
+ in size.
config ARM_PATCH_PHYS_VIRT
bool "Patch physical to virtual translations at runtime" if EMBEDDED
@@ -474,6 +476,7 @@
bool "IXP4xx-based"
depends on MMU
select ARCH_HAS_DMA_SET_COHERENT_MASK
+ select ARCH_SUPPORTS_BIG_ENDIAN
select ARCH_REQUIRE_GPIOLIB
select CLKSRC_MMIO
select CPU_XSCALE
@@ -1494,6 +1497,109 @@
MultiThreading at a cost of slightly increased overhead in some
places. If unsure say N here.
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+ bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+ help
+ Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+ bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+ depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+ help
+ Experimental scheduler optimizations for heterogeneous platforms.
+ Attempts to introspectively select task affinity to optimize power
+ and performance. Basic support for multiple (>2) cpu types is in place,
+ but it has only been tested with two types of cpus.
+ There is currently no support for migration of task groups, hence
+ !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+ between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+ When turned on, this option adds sys/kernel/hmp directory which
+ contains the following files:
+ up_threshold - the load average threshold used for up migration
+ (0 - 1023)
+ down_threshold - the load average threshold used for down migration
+ (0 - 1023)
+ hmp_domains - a list of cpumasks for the present HMP domains,
+ starting with the 'biggest' and ending with the
+ 'smallest'.
+ Note that both the threshold files can be written at runtime to
+ control scheduler behaviour.
+
+config SCHED_HMP_PRIO_FILTER
+ bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+ depends on SCHED_HMP
+ help
+ Enables task priority based HMP migration filter. Any task with
+ a NICE value above the threshold will always be on low-power cpus
+ with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+ int "NICE priority threshold"
+ default 5
+ depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+ string "HMP scheduler fast CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the fast CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+ string "HMP scheduler slow CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the slow CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+ bool "Allows changing the load tracking scale through sysfs"
+ depends on SCHED_HMP
+ help
+ When turned on, this option exports the load average period value
+ for the load tracking patches through sysfs.
+ The values can be modified to change the rate of load accumulation
+ used for HMP migration. 'load_avg_period_ms' is the time in ms to
+ reach a load average of 0.5 for an idle task of 0 load average
+ ratio which becomes 100% busy.
+ For example, with load_avg_period_ms = 128 and up_threshold = 512,
+ a running task with a load of 0 will be migrated to a bigger CPU after
+ 128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+ up_threshold is 0.5.
+ This patch has the same behavior as changing the Y of the load
+ average computation to
+ (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+ but removes intermediate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+ bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+ depends on SCHED_HMP && CPU_FREQ
+ help
+ Scales the current load contribution in line with the frequency
+ of the CPU that the task was executed on.
+ In this version, we use a simple linear scale derived from the
+ maximum frequency reported by CPUFreq.
+ Restricting tracked load to be scaled by the CPU's frequency
+ represents the consumption of possible compute capacity
+ (rather than consumption of actual instantaneous capacity as
+ normal) and allows the HMP migration's simple threshold
+ migration strategy to interact more predictably with CPUFreq's
+ asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+ bool "Small task packing for HMP"
+ depends on SCHED_HMP
+ default n
+ help
+ Allows the HMP Scheduler to pack small tasks into CPUs in the
+ smallest HMP domain.
+ Controlled by two sysfs files in sys/kernel/hmp.
+ packing_enable: 1 to enable, 0 to disable packing. Default 1.
+ packing_limit: runqueue load ratio where a RQ is considered
+ to be full. Default is NICE_0_LOAD * 9/8.
+
config HAVE_ARM_SCU
bool
help
@@ -1521,6 +1627,31 @@
for (multi-)cluster based systems, such as big.LITTLE based
systems.
+config BIG_LITTLE
+ bool "big.LITTLE support (Experimental)"
+ depends on CPU_V7 && SMP
+ select MCPM
+ help
+ This option enables support for the big.LITTLE architecture.
+
+config BL_SWITCHER
+ bool "big.LITTLE switcher support"
+ depends on BIG_LITTLE && MCPM && HOTPLUG_CPU
+ select CPU_PM
+ select ARM_CPU_SUSPEND
+ help
+ The big.LITTLE "switcher" provides the core functionality to
+ transparently handle transition between a cluster of A15's
+ and a cluster of A7's in a big.LITTLE system.
+
+config BL_SWITCHER_DUMMY_IF
+ tristate "Simple big.LITTLE switcher user interface"
+ depends on BL_SWITCHER && DEBUG_KERNEL
+ help
+ This is a simple and dummy char dev interface to control
+ the big.LITTLE switcher core code. It is meant for
+ debugging purposes only.
+
choice
prompt "Memory split"
default VMSPLIT_3G
@@ -1731,6 +1862,14 @@
Enable hardware performance counter support for perf events. If
disabled, perf events will use software events only.
+config SYS_SUPPORTS_HUGETLBFS
+ def_bool y
+ depends on ARM_LPAE
+
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ def_bool y
+ depends on ARM_LPAE
+
source "mm/Kconfig"
config FORCE_MAX_ZONEORDER
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 1d41908..5fdb6db 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -669,14 +669,6 @@
kernel low-level debugging functions. Add earlyprintk to your
kernel parameters to enable this console.
-config OC_ETM
- bool "On-chip ETM and ETB"
- depends on ARM_AMBA
- help
- Enables the on-chip embedded trace macrocell and embedded trace
- buffer driver that will allow you to collect traces of the
- kernel code.
-
config ARM_KPROBES_TEST
tristate "Kprobes test module"
depends on KPROBES && MODULES
@@ -692,4 +684,70 @@
additional instructions during context switch. Say Y here only if you
are planning to use hardware trace tools with this kernel.
+config DEBUG_SET_MODULE_RONX
+ bool "Set loadable kernel module data as NX and text as RO"
+ depends on MODULES
+ ---help---
+ This option helps catch unintended modifications to loadable
+ kernel module's text and read-only data. It also prevents execution
+ of module data. Such protection may interfere with run-time code
+ patching and dynamic kernel tracing - and they might also protect
+ against certain classes of kernel exploits.
+ If in doubt, say "N".
+
+menuconfig CORESIGHT
+ bool "CoreSight Tracing Support"
+ select ARM_AMBA
+ help
+ This framework provides a kernel interface for the CoreSight debug
+ and trace drivers to register themselves with. It's intended to build
+ a topological view of the CoreSight components based on a DT
+ specification and configure the right serie of components when a
+ trace source gets enabled.
+
+if CORESIGHT
+config CORESIGHT_LINKS_AND_SINKS
+ bool "CoreSight Link and Sink drivers"
+ help
+ This enables support for CoreSight link and sink drivers that are
+ responsible for transporting and collecting the trace data
+ respectively. Link and sinks are dynamically aggregated with a trace
+ entity at run time to form a complete trace path.
+
+config CORESIGHT_LINK_AND_SINK_TMC
+ bool "Coresight generic TMC driver"
+ depends on CORESIGHT_LINKS_AND_SINKS
+ help
+ This enables support for the Trace Memory Controller driver. Depending
+ on its configuration the device can act as a link (embedded trace router
+ - ETR) or sink (embedded trace FIFO). The driver complies with the
+ generic implementation of the component without special enhancement or
+ added features.
+
+config CORESIGHT_SINK_TPIU
+ bool "Coresight generic TPIU driver"
+ depends on CORESIGHT_LINKS_AND_SINKS
+ help
+ This enables support for the Trace Port Interface Unit driver, responsible
+ for bridging the gap between the on-chip coresight components and a trace
+ port collection engine, typically connected to an external host for use
+ case capturing more traces than the on-board coresight memory can handle.
+
+config CORESIGHT_SINK_ETBV10
+ bool "Coresight ETBv1.0 driver"
+ depends on CORESIGHT_LINKS_AND_SINKS
+ help
+ This enables support for the Embedded Trace Buffer version 1.0 driver
+ that complies with the generic implementation of the component without
+ special enhancement or added features.
+
+config CORESIGHT_SOURCE_ETM3X
+ bool "CoreSight Embedded Trace Macrocell 3.x driver"
+ select CORESIGHT_LINKS_AND_SINKS
+ help
+ This driver provides support for processor ETM3.x and PTM1.x modules,
+ which allows tracing the instructions that a processor is executing
+ This is primarily useful for instruction level tracing. Depending
+ the ETM version data tracing may also be available.
+endif
endmenu
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 1ba358b..70bc19e 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -16,6 +16,7 @@
LDFLAGS_vmlinux :=-p --no-undefined -X
ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
LDFLAGS_vmlinux += --be8
+LDFLAGS_MODULE += --be8
endif
OBJCOPYFLAGS :=-O binary -R .comment -S
diff --git a/arch/arm/boot/bootp/Makefile b/arch/arm/boot/bootp/Makefile
index c394e30..5761f00 100644
--- a/arch/arm/boot/bootp/Makefile
+++ b/arch/arm/boot/bootp/Makefile
@@ -5,6 +5,8 @@
# architecture-specific flags and dependencies.
#
+GCOV_PROFILE := n
+
LDFLAGS_bootp :=-p --no-undefined -X \
--defsym initrd_phys=$(INITRD_PHYS) \
--defsym params_phys=$(PARAMS_PHYS) -T
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 120b83b..e1fc76e 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -37,6 +37,8 @@
OBJS += hyp-stub.o
endif
+GCOV_PROFILE := n
+
#
# Architecture dependencies
#
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index aabc02a..d1153c8 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -53,6 +53,17 @@
return fdt_getprop(fdt, offset, property, len);
}
+static uint32_t get_cell_size(const void *fdt)
+{
+ int len;
+ uint32_t cell_size = 1;
+ const uint32_t *size_len = getprop(fdt, "/", "#size-cells", &len);
+
+ if (size_len)
+ cell_size = fdt32_to_cpu(*size_len);
+ return cell_size;
+}
+
static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
{
char cmdline[COMMAND_LINE_SIZE];
@@ -95,9 +106,11 @@
int atags_to_fdt(void *atag_list, void *fdt, int total_space)
{
struct tag *atag = atag_list;
- uint32_t mem_reg_property[2 * NR_BANKS];
+ /* In the case of 64 bits memory size, need to reserve 2 cells for
+ * address and size for each bank */
+ uint32_t mem_reg_property[2 * 2 * NR_BANKS];
int memcount = 0;
- int ret;
+ int ret, memsize;
/* make sure we've got an aligned pointer */
if ((u32)atag_list & 0x3)
@@ -137,8 +150,25 @@
continue;
if (!atag->u.mem.size)
continue;
- mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
- mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+ memsize = get_cell_size(fdt);
+
+ if (memsize == 2) {
+ /* if memsize is 2, that means that
+ * each data needs 2 cells of 32 bits,
+ * so the data are 64 bits */
+ uint64_t *mem_reg_prop64 =
+ (uint64_t *)mem_reg_property;
+ mem_reg_prop64[memcount++] =
+ cpu_to_fdt64(atag->u.mem.start);
+ mem_reg_prop64[memcount++] =
+ cpu_to_fdt64(atag->u.mem.size);
+ } else {
+ mem_reg_property[memcount++] =
+ cpu_to_fdt32(atag->u.mem.start);
+ mem_reg_property[memcount++] =
+ cpu_to_fdt32(atag->u.mem.size);
+ }
+
} else if (atag->hdr.tag == ATAG_INITRD2) {
uint32_t initrd_start, initrd_size;
initrd_start = atag->u.initrd.start;
@@ -150,8 +180,10 @@
}
}
- if (memcount)
- setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+ if (memcount) {
+ setprop(fdt, "/memory", "reg", mem_reg_property,
+ 4 * memcount * memsize);
+ }
return fdt_pack(fdt);
}
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 032a8d9..f6e34be 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -135,6 +135,7 @@
.word _edata @ zImage end address
THUMB( .thumb )
1:
+ ARM_BE8( setend be ) @ go BE8 if compiled for BE8
mrs r9, cpsr
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install @ get into SVC mode, reversibly
@@ -679,9 +680,7 @@
mrc p15, 0, r0, c1, c0, 0 @ read control reg
orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
orr r0, r0, #0x0030
-#ifdef CONFIG_CPU_ENDIAN_BE8
- orr r0, r0, #1 << 25 @ big-endian page tables
-#endif
+ ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables
bl __common_mmu_cache_on
mov r0, #0
mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
@@ -708,9 +707,7 @@
orr r0, r0, #1 << 22 @ U (v6 unaligned access model)
@ (needed for ARM1176)
#ifdef CONFIG_MMU
-#ifdef CONFIG_CPU_ENDIAN_BE8
- orr r0, r0, #1 << 25 @ big-endian page tables
-#endif
+ ARM_BE8( orr r0, r0, #1 << 25 ) @ big-endian page tables
mrcne p15, 0, r6, c2, c0, 2 @ read ttb control reg
orrne r0, r0, #1 @ MMU enabled
movne r1, #0xfffffffd @ domain 0 = client
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index f0895c5..00baf9f 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -202,7 +202,14 @@
dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2p-ca5s.dtb \
vexpress-v2p-ca9.dtb \
vexpress-v2p-ca15-tc1.dtb \
- vexpress-v2p-ca15_a7.dtb
+ vexpress-v2p-ca15_a7.dtb \
+ rtsm_ve-cortex_a9x2.dtb \
+ rtsm_ve-cortex_a9x4.dtb \
+ rtsm_ve-cortex_a15x1.dtb \
+ rtsm_ve-cortex_a15x2.dtb \
+ rtsm_ve-cortex_a15x4.dtb \
+ rtsm_ve-v2p-ca15x1-ca7x1.dtb \
+ rtsm_ve-v2p-ca15x4-ca7x4.dtb
dtb-$(CONFIG_ARCH_VIRT) += xenvm-4.2.dtb
dtb-$(CONFIG_ARCH_VT8500) += vt8500-bv07.dtb \
wm8505-ref.dtb \
diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
index 550eb77..ddd068b 100644
--- a/arch/arm/boot/dts/armada-370-xp.dtsi
+++ b/arch/arm/boot/dts/armada-370-xp.dtsi
@@ -51,7 +51,7 @@
coherency-fabric@20200 {
compatible = "marvell,coherency-fabric";
- reg = <0x20200 0xb0>, <0x21810 0x1c>;
+ reg = <0x20200 0xb0>, <0x21010 0x1c>;
};
serial@12000 {
@@ -92,6 +92,7 @@
#size-cells = <0>;
compatible = "marvell,orion-mdio";
reg = <0x72004 0x4>;
+ clocks = <&gateclk 4>;
};
ethernet@70000 {
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 76db557..f975504 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -124,7 +124,7 @@
/* Device Bus parameters are required */
/* Read parameters */
- devbus,bus-width = <8>;
+ devbus,bus-width = <16>;
devbus,turn-off-ps = <60000>;
devbus,badr-skew-ps = <0>;
devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/armada-xp-mv78230.dtsi b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
index f8eaa383..f94cdbc 100644
--- a/arch/arm/boot/dts/armada-xp-mv78230.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78230.dtsi
@@ -81,7 +81,7 @@
/*
* MV78230 has 2 PCIe units Gen2.0: One unit can be
* configured as x4 or quad x1 lanes. One unit is
- * x4/x1.
+ * x1 only.
*/
pcie-controller {
compatible = "marvell,armada-xp-pcie";
@@ -94,10 +94,10 @@
bus-range = <0x00 0xff>;
ranges = <0x82000000 0 0x40000 0x40000 0 0x00002000 /* Port 0.0 registers */
- 0x82000000 0 0x42000 0x42000 0 0x00002000 /* Port 2.0 registers */
0x82000000 0 0x44000 0x44000 0 0x00002000 /* Port 0.1 registers */
0x82000000 0 0x48000 0x48000 0 0x00002000 /* Port 0.2 registers */
0x82000000 0 0x4c000 0x4c000 0 0x00002000 /* Port 0.3 registers */
+ 0x82000000 0 0x80000 0x80000 0 0x00002000 /* Port 1.0 registers */
0x82000000 0 0xe0000000 0xe0000000 0 0x08000000 /* non-prefetchable memory */
0x81000000 0 0 0xe8000000 0 0x00100000>; /* downstream I/O */
@@ -165,19 +165,19 @@
status = "disabled";
};
- pcie@9,0 {
+ pcie@5,0 {
device_type = "pci";
- assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
- reg = <0x4800 0 0 0 0>;
+ assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+ reg = <0x2800 0 0 0 0>;
#address-cells = <3>;
#size-cells = <2>;
#interrupt-cells = <1>;
ranges;
interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &mpic 99>;
- marvell,pcie-port = <2>;
+ interrupt-map = <0 0 0 0 &mpic 62>;
+ marvell,pcie-port = <1>;
marvell,pcie-lane = <0>;
- clocks = <&gateclk 26>;
+ clocks = <&gateclk 9>;
status = "disabled";
};
};
diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
index f4029f0..55cdd58 100644
--- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi
+++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi
@@ -101,7 +101,7 @@
/*
* MV78260 has 3 PCIe units Gen2.0: Two units can be
* configured as x4 or quad x1 lanes. One unit is
- * x4/x1.
+ * x4 only.
*/
pcie-controller {
compatible = "marvell,armada-xp-pcie";
@@ -119,7 +119,9 @@
0x82000000 0 0x48000 0x48000 0 0x00002000 /* Port 0.2 registers */
0x82000000 0 0x4c000 0x4c000 0 0x00002000 /* Port 0.3 registers */
0x82000000 0 0x80000 0x80000 0 0x00002000 /* Port 1.0 registers */
- 0x82000000 0 0x82000 0x82000 0 0x00002000 /* Port 3.0 registers */
+ 0x82000000 0 0x84000 0x84000 0 0x00002000 /* Port 1.1 registers */
+ 0x82000000 0 0x88000 0x88000 0 0x00002000 /* Port 1.2 registers */
+ 0x82000000 0 0x8c000 0x8c000 0 0x00002000 /* Port 1.3 registers */
0x82000000 0 0xe0000000 0xe0000000 0 0x08000000 /* non-prefetchable memory */
0x81000000 0 0 0xe8000000 0 0x00100000>; /* downstream I/O */
@@ -187,6 +189,70 @@
status = "disabled";
};
+ pcie@5,0 {
+ device_type = "pci";
+ assigned-addresses = <0x82000800 0 0x80000 0 0x2000>;
+ reg = <0x2800 0 0 0 0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+ ranges;
+ interrupt-map-mask = <0 0 0 0>;
+ interrupt-map = <0 0 0 0 &mpic 62>;
+ marvell,pcie-port = <1>;
+ marvell,pcie-lane = <0>;
+ clocks = <&gateclk 9>;
+ status = "disabled";
+ };
+
+ pcie@6,0 {
+ device_type = "pci";
+ assigned-addresses = <0x82000800 0 0x84000 0 0x2000>;
+ reg = <0x3000 0 0 0 0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+ ranges;
+ interrupt-map-mask = <0 0 0 0>;
+ interrupt-map = <0 0 0 0 &mpic 63>;
+ marvell,pcie-port = <1>;
+ marvell,pcie-lane = <1>;
+ clocks = <&gateclk 10>;
+ status = "disabled";
+ };
+
+ pcie@7,0 {
+ device_type = "pci";
+ assigned-addresses = <0x82000800 0 0x88000 0 0x2000>;
+ reg = <0x3800 0 0 0 0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+ ranges;
+ interrupt-map-mask = <0 0 0 0>;
+ interrupt-map = <0 0 0 0 &mpic 64>;
+ marvell,pcie-port = <1>;
+ marvell,pcie-lane = <2>;
+ clocks = <&gateclk 11>;
+ status = "disabled";
+ };
+
+ pcie@8,0 {
+ device_type = "pci";
+ assigned-addresses = <0x82000800 0 0x8c000 0 0x2000>;
+ reg = <0x4000 0 0 0 0>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ #interrupt-cells = <1>;
+ ranges;
+ interrupt-map-mask = <0 0 0 0>;
+ interrupt-map = <0 0 0 0 &mpic 65>;
+ marvell,pcie-port = <1>;
+ marvell,pcie-lane = <3>;
+ clocks = <&gateclk 12>;
+ status = "disabled";
+ };
+
pcie@9,0 {
device_type = "pci";
assigned-addresses = <0x82000800 0 0x42000 0 0x2000>;
@@ -202,22 +268,6 @@
clocks = <&gateclk 26>;
status = "disabled";
};
-
- pcie@10,0 {
- device_type = "pci";
- assigned-addresses = <0x82000800 0 0x82000 0 0x2000>;
- reg = <0x5000 0 0 0 0>;
- #address-cells = <3>;
- #size-cells = <2>;
- #interrupt-cells = <1>;
- ranges;
- interrupt-map-mask = <0 0 0 0>;
- interrupt-map = <0 0 0 0 &mpic 103>;
- marvell,pcie-port = <3>;
- marvell,pcie-lane = <0>;
- clocks = <&gateclk 27>;
- status = "disabled";
- };
};
};
};
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index fdea75c..9746d0e 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -152,7 +152,7 @@
/* Device Bus parameters are required */
/* Read parameters */
- devbus,bus-width = <8>;
+ devbus,bus-width = <16>;
devbus,turn-off-ps = <60000>;
devbus,badr-skew-ps = <0>;
devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/at91rm9200.dtsi b/arch/arm/boot/dts/at91rm9200.dtsi
index 5d3ed5a..0af879a 100644
--- a/arch/arm/boot/dts/at91rm9200.dtsi
+++ b/arch/arm/boot/dts/at91rm9200.dtsi
@@ -35,8 +35,12 @@
ssc2 = &ssc2;
};
cpus {
- cpu@0 {
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
compatible = "arm,arm920t";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index 84c4bef..0dbdb84 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -32,8 +32,12 @@
ssc0 = &ssc0;
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
@@ -340,6 +344,14 @@
};
};
+ i2c_gpio0 {
+ pinctrl_i2c_gpio0: i2c_gpio0-0 {
+ atmel,pins =
+ <0 23 0x0 0x3 /* PA23 gpio I2C_SDA pin */
+ 0 24 0x0 0x3>; /* PA24 gpio I2C_SCL pin */
+ };
+ };
+
pioA: gpio@fffff400 {
compatible = "atmel,at91rm9200-gpio";
reg = <0xfffff400 0x200>;
@@ -592,6 +604,8 @@
i2c-gpio,delay-us = <2>; /* ~100 kHz */
#address-cells = <1>;
#size-cells = <0>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_i2c_gpio0>;
status = "disabled";
};
};
diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi
index 94b58ab..fcd38f8 100644
--- a/arch/arm/boot/dts/at91sam9263.dtsi
+++ b/arch/arm/boot/dts/at91sam9263.dtsi
@@ -29,8 +29,12 @@
ssc1 = &ssc1;
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/at91sam9g45.dtsi b/arch/arm/boot/dts/at91sam9g45.dtsi
index bf18a73..479a062 100644
--- a/arch/arm/boot/dts/at91sam9g45.dtsi
+++ b/arch/arm/boot/dts/at91sam9g45.dtsi
@@ -35,8 +35,12 @@
ssc1 = &ssc1;
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index 8d25f88..a92ec78 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -31,8 +31,12 @@
ssc0 = &ssc0;
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index d30e48b..28ba798 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -14,11 +14,11 @@
compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9";
chosen {
- bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
+ bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2";
};
memory {
- reg = <0x20000000 0x10000000>;
+ reg = <0x20000000 0x8000000>;
};
clocks {
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 1145ac3..2b2b692 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -33,8 +33,12 @@
ssc0 = &ssc0;
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
@@ -643,7 +647,7 @@
};
rtc@fffffeb0 {
- compatible = "atmel,at91rm9200-rtc";
+ compatible = "atmel,at91sam9x5-rtc";
reg = <0xfffffeb0 0x40>;
interrupts = <1 4 7>;
status = "disabled";
diff --git a/arch/arm/boot/dts/bcm2835.dtsi b/arch/arm/boot/dts/bcm2835.dtsi
index 1e12aef..aa537ed 100644
--- a/arch/arm/boot/dts/bcm2835.dtsi
+++ b/arch/arm/boot/dts/bcm2835.dtsi
@@ -85,6 +85,8 @@
reg = <0x7e205000 0x1000>;
interrupts = <2 21>;
clocks = <&clk_i2c>;
+ #address-cells = <1>;
+ #size-cells = <0>;
status = "disabled";
};
@@ -93,6 +95,8 @@
reg = <0x7e804000 0x1000>;
interrupts = <2 21>;
clocks = <&clk_i2c>;
+ #address-cells = <1>;
+ #size-cells = <0>;
status = "disabled";
};
diff --git a/arch/arm/boot/dts/clcd-panels.dtsi b/arch/arm/boot/dts/clcd-panels.dtsi
new file mode 100644
index 0000000..0b0ff6e
--- /dev/null
+++ b/arch/arm/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+ panels {
+ panel@0 {
+ compatible = "panel";
+ mode = "VGA";
+ refresh = <60>;
+ xres = <640>;
+ yres = <480>;
+ pixclock = <39721>;
+ left_margin = <40>;
+ right_margin = <24>;
+ upper_margin = <32>;
+ lower_margin = <11>;
+ hsync_len = <96>;
+ vsync_len = <2>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+
+ panel@1 {
+ compatible = "panel";
+ mode = "XVGA";
+ refresh = <60>;
+ xres = <1024>;
+ yres = <768>;
+ pixclock = <15748>;
+ left_margin = <152>;
+ right_margin = <48>;
+ upper_margin = <23>;
+ lower_margin = <3>;
+ hsync_len = <104>;
+ vsync_len = <4>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/cros5250-common.dtsi b/arch/arm/boot/dts/cros5250-common.dtsi
index 3f0239e..49d8da2 100644
--- a/arch/arm/boot/dts/cros5250-common.dtsi
+++ b/arch/arm/boot/dts/cros5250-common.dtsi
@@ -27,6 +27,13 @@
i2c2_bus: i2c2-bus {
samsung,pin-pud = <0>;
};
+
+ max77686_irq: max77686-irq {
+ samsung,pins = "gpx3-2";
+ samsung,pin-function = <0>;
+ samsung,pin-pud = <0>;
+ samsung,pin-drv = <0>;
+ };
};
i2c@12C60000 {
@@ -35,6 +42,11 @@
max77686@09 {
compatible = "maxim,max77686";
+ interrupt-parent = <&gpx3>;
+ interrupts = <2 0>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&max77686_irq>;
+ wakeup-source;
reg = <0x09>;
voltage-regulators {
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index 02cfc76..b64cb43 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -263,6 +263,7 @@
regulator-name = "vdd_g3d";
regulator-min-microvolt = <1000000>;
regulator-max-microvolt = <1000000>;
+ regulator-always-on;
regulator-boot-on;
op_mode = <1>;
};
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index fc9fb3d..19b9109 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -89,6 +89,11 @@
<1 14 0xf08>,
<1 11 0xf08>,
<1 10 0xf08>;
+ /* Unfortunately we need this since some versions of U-Boot
+ * on Exynos don't set the CNTFRQ register, so we need the
+ * value from DT.
+ */
+ clock-frequency = <24000000>;
};
combiner:interrupt-controller@10440000 {
@@ -545,7 +550,7 @@
compatible = "arm,pl330", "arm,primecell";
reg = <0x10800000 0x1000>;
interrupts = <0 33 0>;
- clocks = <&clock 271>;
+ clocks = <&clock 346>;
clock-names = "apb_pclk";
#dma-cells = <1>;
#dma-channels = <8>;
diff --git a/arch/arm/boot/dts/hip04.dtsi b/arch/arm/boot/dts/hip04.dtsi
new file mode 100644
index 0000000..2388145
--- /dev/null
+++ b/arch/arm/boot/dts/hip04.dtsi
@@ -0,0 +1,984 @@
+/*
+ * Hisilicon Ltd. HiP04 SoC
+ *
+ * Copyright (C) 2013-2014 Hisilicon Ltd.
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ *
+ * Author: Haojian Zhuang <haojian.zhuang@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/ {
+ /* memory bus is 64-bit */
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ aliases {
+ serial0 = &uart0;
+ };
+
+ bootwrapper {
+ compatible = "hisilicon,hip04-bootwrapper";
+ boot-method = <0x10c00000 0x10000>, <0xe0000100 0x1000>;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&CPU0>;
+ };
+ core1 {
+ cpu = <&CPU1>;
+ };
+ core2 {
+ cpu = <&CPU2>;
+ };
+ core3 {
+ cpu = <&CPU3>;
+ };
+ };
+ cluster1 {
+ core0 {
+ cpu = <&CPU4>;
+ };
+ core1 {
+ cpu = <&CPU5>;
+ };
+ core2 {
+ cpu = <&CPU6>;
+ };
+ core3 {
+ cpu = <&CPU7>;
+ };
+ };
+ cluster2 {
+ core0 {
+ cpu = <&CPU8>;
+ };
+ core1 {
+ cpu = <&CPU9>;
+ };
+ core2 {
+ cpu = <&CPU10>;
+ };
+ core3 {
+ cpu = <&CPU11>;
+ };
+ };
+ cluster3 {
+ core0 {
+ cpu = <&CPU12>;
+ };
+ core1 {
+ cpu = <&CPU13>;
+ };
+ core2 {
+ cpu = <&CPU14>;
+ };
+ core3 {
+ cpu = <&CPU15>;
+ };
+ };
+ };
+ CPU0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+ CPU1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ };
+ CPU2: cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <2>;
+ };
+ CPU3: cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <3>;
+ };
+ CPU4: cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x100>;
+ };
+ CPU5: cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x101>;
+ };
+ CPU6: cpu@102 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x102>;
+ };
+ CPU7: cpu@103 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x103>;
+ };
+ CPU8: cpu@200 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x200>;
+ };
+ CPU9: cpu@201 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x201>;
+ };
+ CPU10: cpu@202 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x202>;
+ };
+ CPU11: cpu@203 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x203>;
+ };
+ CPU12: cpu@300 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x300>;
+ };
+ CPU13: cpu@301 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x301>;
+ };
+ CPU14: cpu@302 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x302>;
+ };
+ CPU15: cpu@303 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0x303>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupt-parent = <&gic>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ clk_50m: clk_50m {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ clock-frequency = <50000000>;
+ };
+
+ clk_168m: clk_168m {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ clock-frequency = <168000000>;
+ };
+
+ clk_375m: clk_375m {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ clock-frequency = <375000000>;
+ };
+
+ soc {
+ /* It's a 32-bit SoC. */
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "simple-bus";
+ interrupt-parent = <&gic>;
+ ranges = <0 0 0xe0000000 0x10000000>;
+
+ gic: interrupt-controller@c01000 {
+ compatible = "hisilicon,hip04-intc";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ interrupts = <1 9 0xf04>;
+
+ reg = <0xc01000 0x1000>, <0xc02000 0x1000>,
+ <0xc04000 0x2000>, <0xc06000 0x2000>;
+ };
+
+ sysctrl: sysctrl {
+ compatible = "hisilicon,sysctrl";
+ reg = <0x3e00000 0x00100000>;
+ };
+
+ fabric: fabric {
+ compatible = "hisilicon,hip04-fabric";
+ reg = <0x302a000 0x1000>;
+ };
+
+ dual_timer0: dual_timer@3000000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x3000000 0x1000>;
+ interrupts = <0 224 4>;
+ clocks = <&clk_50m>, <&clk_50m>;
+ clock-names = "apb_pclk";
+ };
+
+ arm-pmu {
+ compatible = "arm,cortex-a15-pmu";
+ interrupts = <0 64 4>,
+ <0 65 4>,
+ <0 66 4>,
+ <0 67 4>,
+ <0 68 4>,
+ <0 69 4>,
+ <0 70 4>,
+ <0 71 4>,
+ <0 72 4>,
+ <0 73 4>,
+ <0 74 4>,
+ <0 75 4>,
+ <0 76 4>,
+ <0 77 4>,
+ <0 78 4>,
+ <0 79 4>;
+ };
+
+ uart0: uart@4007000 {
+ compatible = "snps,dw-apb-uart";
+ reg = <0x4007000 0x1000>;
+ interrupts = <0 381 4>;
+ clocks = <&clk_168m>;
+ clock-names = "uartclk";
+ reg-shift = <2>;
+ status = "disabled";
+ };
+
+ sata0: sata@a000000 {
+ compatible = "hisilicon,hisi-ahci";
+ reg = <0xa000000 0x1000000>;
+ interrupts = <0 372 4>;
+ };
+
+ };
+
+ etb@0,e3c42000 {
+ compatible = "arm,coresight-etb10", "arm,primecell";
+ reg = <0 0xe3c42000 0 0x1000>;
+
+ coresight-default-sink;
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ port {
+ etb0_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator0_out_port0>;
+ };
+ };
+ };
+
+ etb@0,e3c82000 {
+ compatible = "arm,coresight-etb10", "arm,primecell";
+ reg = <0 0xe3c82000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ port {
+ etb1_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator1_out_port0>;
+ };
+ };
+ };
+
+ etb@0,e3cc2000 {
+ compatible = "arm,coresight-etb10", "arm,primecell";
+ reg = <0 0xe3cc2000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ port {
+ etb2_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator2_out_port0>;
+ };
+ };
+ };
+
+ etb@0,e3d02000 {
+ compatible = "arm,coresight-etb10", "arm,primecell";
+ reg = <0 0xe3d02000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ port {
+ etb3_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&replicator3_out_port0>;
+ };
+ };
+ };
+
+ tpiu@0,e3c05000 {
+ compatible = "arm,coresight-tpiu", "arm,primecell";
+ reg = <0 0xe3c05000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ port {
+ tpiu_in_port: endpoint@0 {
+ slave-mode;
+ remote-endpoint = <&funnel4_out_port0>;
+ };
+ };
+ };
+
+ replicator0 {
+ /* non-configurable replicators don't show up on the
+ * AMBA bus. As such no need to add "arm,primecell".
+ */
+ compatible = "arm,coresight-replicator";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* replicator output ports */
+ port@0 {
+ reg = <0>;
+ replicator0_out_port0: endpoint {
+ remote-endpoint = <&etb0_in_port>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+ replicator0_out_port1: endpoint {
+ remote-endpoint = <&funnel4_in_port0>;
+ };
+ };
+
+ /* replicator input port */
+ port@2 {
+ reg = <0>;
+ replicator0_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&funnel0_out_port0>;
+ };
+ };
+ };
+ };
+
+ replicator1 {
+ /* non-configurable replicators don't show up on the
+ * AMBA bus. As such no need to add "arm,primecell".
+ */
+ compatible = "arm,coresight-replicator";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* replicator output ports */
+ port@0 {
+ reg = <0>;
+ replicator1_out_port0: endpoint {
+ remote-endpoint = <&etb1_in_port>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+ replicator1_out_port1: endpoint {
+ remote-endpoint = <&funnel4_in_port1>;
+ };
+ };
+
+ /* replicator input port */
+ port@2 {
+ reg = <0>;
+ replicator1_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&funnel1_out_port0>;
+ };
+ };
+ };
+ };
+
+ replicator2 {
+ /* non-configurable replicators don't show up on the
+ * AMBA bus. As such no need to add "arm,primecell".
+ */
+ compatible = "arm,coresight-replicator";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* replicator output ports */
+ port@0 {
+ reg = <0>;
+ replicator2_out_port0: endpoint {
+ remote-endpoint = <&etb2_in_port>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+ replicator2_out_port1: endpoint {
+ remote-endpoint = <&funnel4_in_port2>;
+ };
+ };
+
+ /* replicator input port */
+ port@2 {
+ reg = <0>;
+ replicator2_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&funnel2_out_port0>;
+ };
+ };
+ };
+ };
+
+ replicator3 {
+ /* non-configurable replicators don't show up on the
+ * AMBA bus. As such no need to add "arm,primecell".
+ */
+ compatible = "arm,coresight-replicator";
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* replicator output ports */
+ port@0 {
+ reg = <0>;
+ replicator3_out_port0: endpoint {
+ remote-endpoint = <&etb3_in_port>;
+ };
+ };
+
+ port@1 {
+ reg = <1>;
+ replicator3_out_port1: endpoint {
+ remote-endpoint = <&funnel4_in_port3>;
+ };
+ };
+
+ /* replicator input port */
+ port@2 {
+ reg = <0>;
+ replicator3_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&funnel3_out_port0>;
+ };
+ };
+ };
+ };
+
+ funnel@0,e3c41000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0xe3c41000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel0_out_port0: endpoint {
+ remote-endpoint =
+ <&replicator0_in_port0>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel0_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm0_out_port>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel0_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm1_out_port>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel0_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm2_out_port>;
+ };
+ };
+
+ port@4 {
+ reg = <3>;
+ funnel0_in_port3: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm3_out_port>;
+ };
+ };
+ };
+ };
+
+ funnel@0,e3c81000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0xe3c81000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel1_out_port0: endpoint {
+ remote-endpoint =
+ <&replicator1_in_port0>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel1_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm4_out_port>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel1_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm5_out_port>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel1_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm6_out_port>;
+ };
+ };
+
+ port@4 {
+ reg = <3>;
+ funnel1_in_port3: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm7_out_port>;
+ };
+ };
+ };
+ };
+
+ funnel@0,e3cc1000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0xe3cc1000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel2_out_port0: endpoint {
+ remote-endpoint =
+ <&replicator2_in_port0>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel2_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm8_out_port>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel2_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm9_out_port>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel2_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm10_out_port>;
+ };
+ };
+
+ port@4 {
+ reg = <3>;
+ funnel2_in_port3: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm11_out_port>;
+ };
+ };
+ };
+ };
+
+ funnel@0,e3d01000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0xe3d01000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel3_out_port0: endpoint {
+ remote-endpoint =
+ <&replicator3_in_port0>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel3_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm12_out_port>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel3_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm13_out_port>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel3_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm14_out_port>;
+ };
+ };
+
+ port@4 {
+ reg = <3>;
+ funnel3_in_port3: endpoint {
+ slave-mode;
+ remote-endpoint = <&ptm15_out_port>;
+ };
+ };
+ };
+ };
+
+ funnel@0,e3c04000 {
+ compatible = "arm,coresight-funnel", "arm,primecell";
+ reg = <0 0xe3c04000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ /* funnel output port */
+ port@0 {
+ reg = <0>;
+ funnel4_out_port0: endpoint {
+ remote-endpoint = <&tpiu_in_port>;
+ };
+ };
+
+ /* funnel input ports */
+ port@1 {
+ reg = <0>;
+ funnel4_in_port0: endpoint {
+ slave-mode;
+ remote-endpoint =
+ <&replicator0_out_port1>;
+ };
+ };
+
+ port@2 {
+ reg = <1>;
+ funnel4_in_port1: endpoint {
+ slave-mode;
+ remote-endpoint =
+ <&replicator1_out_port1>;
+ };
+ };
+
+ port@3 {
+ reg = <2>;
+ funnel4_in_port2: endpoint {
+ slave-mode;
+ remote-endpoint =
+ <&replicator2_out_port1>;
+ };
+ };
+
+ port@4 {
+ reg = <3>;
+ funnel4_in_port3: endpoint {
+ slave-mode;
+ remote-endpoint =
+ <&replicator3_out_port1>;
+ };
+ };
+ };
+ };
+
+ ptm@0,e3c7c000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3c7c000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU0>;
+ port {
+ ptm0_out_port: endpoint {
+ remote-endpoint = <&funnel0_in_port0>;
+ };
+ };
+ };
+
+ ptm@0,e3c7d000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3c7d000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU1>;
+ port {
+ ptm1_out_port: endpoint {
+ remote-endpoint = <&funnel0_in_port1>;
+ };
+ };
+ };
+
+ ptm@0,e3c7e000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3c7e000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU2>;
+ port {
+ ptm2_out_port: endpoint {
+ remote-endpoint = <&funnel0_in_port2>;
+ };
+ };
+ };
+
+ ptm@0,e3c7f000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3c7f000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU3>;
+ port {
+ ptm3_out_port: endpoint {
+ remote-endpoint = <&funnel0_in_port3>;
+ };
+ };
+ };
+
+ ptm@0,e3cbc000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cbc000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU4>;
+ port {
+ ptm4_out_port: endpoint {
+ remote-endpoint = <&funnel1_in_port0>;
+ };
+ };
+ };
+
+ ptm@0,e3cbd000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cbd000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU5>;
+ port {
+ ptm5_out_port: endpoint {
+ remote-endpoint = <&funnel1_in_port1>;
+ };
+ };
+ };
+
+ ptm@0,e3cbe000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cbe000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU6>;
+ port {
+ ptm6_out_port: endpoint {
+ remote-endpoint = <&funnel1_in_port2>;
+ };
+ };
+ };
+
+ ptm@0,e3cbf000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cbf000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU7>;
+ port {
+ ptm7_out_port: endpoint {
+ remote-endpoint = <&funnel1_in_port3>;
+ };
+ };
+ };
+
+ ptm@0,e3cfc000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cfc000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU8>;
+ port {
+ ptm8_out_port: endpoint {
+ remote-endpoint = <&funnel2_in_port0>;
+ };
+ };
+ };
+
+ ptm@0,e3cfd000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cfd000 0 0x1000>;
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU9>;
+ port {
+ ptm9_out_port: endpoint {
+ remote-endpoint = <&funnel2_in_port1>;
+ };
+ };
+ };
+
+ ptm@0,e3cfe000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cfe000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU10>;
+ port {
+ ptm10_out_port: endpoint {
+ remote-endpoint = <&funnel2_in_port2>;
+ };
+ };
+ };
+
+ ptm@0,e3cff000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3cff000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU11>;
+ port {
+ ptm11_out_port: endpoint {
+ remote-endpoint = <&funnel2_in_port3>;
+ };
+ };
+ };
+
+ ptm@0,e3d3c000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3d3c000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU12>;
+ port {
+ ptm12_out_port: endpoint {
+ remote-endpoint = <&funnel3_in_port0>;
+ };
+ };
+ };
+
+ ptm@0,e3d3d000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3d3d000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU13>;
+ port {
+ ptm13_out_port: endpoint {
+ remote-endpoint = <&funnel3_in_port1>;
+ };
+ };
+ };
+
+ ptm@0,e3d3e000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3d3e000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU14>;
+ port {
+ ptm14_out_port: endpoint {
+ remote-endpoint = <&funnel3_in_port2>;
+ };
+ };
+ };
+
+ ptm@0,e3d3f000 {
+ compatible = "arm,coresight-etm3x", "arm,primecell";
+ reg = <0 0xe3d3f000 0 0x1000>;
+
+ clocks = <&clk_375m>;
+ clock-names = "apb_pclk";
+ cpu = <&CPU15>;
+ port {
+ ptm15_out_port: endpoint {
+ remote-endpoint = <&funnel3_in_port3>;
+ };
+ };
+ };
+};
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index 73fd7d0..587ceef 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -23,8 +23,12 @@
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 7011539..97d1a55 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -141,7 +141,7 @@
#size-cells = <0>;
compatible = "fsl,imx25-cspi", "fsl,imx35-cspi";
reg = <0x43fa4000 0x4000>;
- clocks = <&clks 62>, <&clks 62>;
+ clocks = <&clks 78>, <&clks 78>;
clock-names = "ipg", "per";
interrupts = <14>;
status = "disabled";
@@ -335,7 +335,7 @@
compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
#pwm-cells = <2>;
reg = <0x53fa0000 0x4000>;
- clocks = <&clks 106>, <&clks 36>;
+ clocks = <&clks 106>, <&clks 52>;
clock-names = "ipg", "per";
interrupts = <36>;
};
@@ -354,7 +354,7 @@
compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
#pwm-cells = <2>;
reg = <0x53fa8000 0x4000>;
- clocks = <&clks 107>, <&clks 36>;
+ clocks = <&clks 107>, <&clks 52>;
clock-names = "ipg", "per";
interrupts = <41>;
};
@@ -394,7 +394,7 @@
pwm4: pwm@53fc8000 {
compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
reg = <0x53fc8000 0x4000>;
- clocks = <&clks 108>, <&clks 36>;
+ clocks = <&clks 108>, <&clks 52>;
clock-names = "ipg", "per";
interrupts = <42>;
};
@@ -439,7 +439,7 @@
compatible = "fsl,imx25-pwm", "fsl,imx27-pwm";
#pwm-cells = <2>;
reg = <0x53fe0000 0x4000>;
- clocks = <&clks 105>, <&clks 36>;
+ clocks = <&clks 105>, <&clks 52>;
clock-names = "ipg", "per";
interrupts = <26>;
};
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 600f7cb..4c10a19 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -32,8 +32,12 @@
};
cpus {
- cpu@0 {
- compatible = "arm,arm926ejs";
+ #address-cells = <0>;
+ #size-cells = <0>;
+
+ cpu {
+ compatible = "arm,arm926ej-s";
+ device_type = "cpu";
};
};
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index eb83aa0..e524316 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -71,7 +71,7 @@
ipu: ipu@18000000 {
#crtc-cells = <1>;
compatible = "fsl,imx53-ipu";
- reg = <0x18000000 0x080000000>;
+ reg = <0x18000000 0x08000000>;
interrupts = <11 10>;
clocks = <&clks 59>, <&clks 110>, <&clks 61>;
clock-names = "bus", "di0", "di1";
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 5bcdf3a..62dc781 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -18,12 +18,14 @@
cpu@0 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <0>;
next-level-cache = <&L2>;
};
cpu@1 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <1>;
next-level-cache = <&L2>;
};
diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi
index 21e6758..dc54a72 100644
--- a/arch/arm/boot/dts/imx6q.dtsi
+++ b/arch/arm/boot/dts/imx6q.dtsi
@@ -18,6 +18,7 @@
cpu@0 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <0>;
next-level-cache = <&L2>;
operating-points = <
@@ -39,18 +40,21 @@
cpu@1 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <1>;
next-level-cache = <&L2>;
};
cpu@2 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <2>;
next-level-cache = <&L2>;
};
cpu@3 {
compatible = "arm,cortex-a9";
+ device_type = "cpu";
reg = <3>;
next-level-cache = <&L2>;
};
diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts
index ff1aea0..72693a6 100644
--- a/arch/arm/boot/dts/integratorcp.dts
+++ b/arch/arm/boot/dts/integratorcp.dts
@@ -9,11 +9,6 @@
model = "ARM Integrator/CP";
compatible = "arm,integrator-cp";
- aliases {
- arm,timer-primary = &timer2;
- arm,timer-secondary = &timer1;
- };
-
chosen {
bootargs = "root=/dev/ram0 console=ttyAMA0,38400n8 earlyprintk";
};
@@ -24,14 +19,18 @@
};
timer0: timer@13000000 {
+ /* TIMER0 runs @ 25MHz */
compatible = "arm,integrator-cp-timer";
+ status = "disabled";
};
timer1: timer@13000100 {
+ /* TIMER1 runs @ 1MHz */
compatible = "arm,integrator-cp-timer";
};
timer2: timer@13000200 {
+ /* TIMER2 runs @ 1MHz */
compatible = "arm,integrator-cp-timer";
};
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
new file mode 100644
index 0000000..c9eee91
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x1.dts
@@ -0,0 +1,159 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x1CT
+ *
+ * RTSM_VE_Cortex_A15x1.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x1";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x1", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
new file mode 100644
index 0000000..853a166
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x2.dts
@@ -0,0 +1,165 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x2CT
+ *
+ * RTSM_VE_Cortex_A15x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x2";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x2", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
new file mode 100644
index 0000000..c1947a3
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a15x4.dts
@@ -0,0 +1,177 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ *
+ * RTSM_VE_Cortex_A15x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA15x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ };
+
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <2>;
+ };
+
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <3>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
new file mode 100644
index 0000000..fca6b2f
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x2.dts
@@ -0,0 +1,171 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx2CT
+ *
+ * RTSM_VE_Cortex_A9x2.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA9x2";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a9x2", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <1>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x80000000 0x80000000>;
+ };
+
+ scu@2c000000 {
+ compatible = "arm,cortex-a9-scu";
+ reg = <0x2c000000 0x58>;
+ };
+
+ timer@2c000600 {
+ compatible = "arm,cortex-a9-twd-timer";
+ reg = <0x2c000600 0x20>;
+ interrupts = <1 13 0xf04>;
+ };
+
+ watchdog@2c000620 {
+ compatible = "arm,cortex-a9-twd-wdt";
+ reg = <0x2c000620 0x20>;
+ interrupts = <1 14 0xf04>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x2c001000 0x1000>,
+ <0x2c000100 0x100>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0x08000000 0x04000000>,
+ <1 0 0x14000000 0x04000000>,
+ <2 0 0x18000000 0x04000000>,
+ <3 0 0x1c000000 0x04000000>,
+ <4 0 0x0c000000 0x04000000>,
+ <5 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
new file mode 100644
index 0000000..fd8a6ed
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-cortex_a9x4.dts
@@ -0,0 +1,183 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA9MPx4CT
+ *
+ * RTSM_VE_Cortex_A9x4.lisa
+ */
+
+/dts-v1/;
+
+/ {
+ model = "RTSM_VE_CortexA9x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a9x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <0>;
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <1>;
+ };
+
+ cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <2>;
+ };
+
+ cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a9";
+ reg = <3>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x80000000 0x80000000>;
+ };
+
+ scu@2c000000 {
+ compatible = "arm,cortex-a9-scu";
+ reg = <0x2c000000 0x58>;
+ };
+
+ timer@2c000600 {
+ compatible = "arm,cortex-a9-twd-timer";
+ reg = <0x2c000600 0x20>;
+ interrupts = <1 13 0xf04>;
+ };
+
+ watchdog@2c000620 {
+ compatible = "arm,cortex-a9-twd-wdt";
+ reg = <0x2c000620 0x20>;
+ interrupts = <1 14 0xf04>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x2c001000 0x1000>,
+ <0x2c000100 0x100>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0x08000000 0x04000000>,
+ <1 0 0x14000000 0x04000000>,
+ <2 0 0x18000000 0x04000000>,
+ <3 0 0x1c000000 0x04000000>,
+ <4 0 0x0c000000 0x04000000>,
+ <5 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
new file mode 100644
index 0000000..a2d895e
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-motherboard.dtsi
@@ -0,0 +1,231 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * Motherboard component
+ *
+ * VEMotherBoard.lisa
+ */
+
+ motherboard {
+ compatible = "arm,vexpress,v2m-p1", "simple-bus";
+ arm,hbi = <0x190>;
+ arm,vexpress,site = <0>;
+ arm,v2m-memory-map = "rs1";
+ #address-cells = <2>; /* SMB chipselect number and offset */
+ #size-cells = <1>;
+ #interrupt-cells = <1>;
+ ranges;
+
+ flash@0,00000000 {
+ compatible = "arm,vexpress-flash", "cfi-flash";
+ reg = <0 0x00000000 0x04000000>,
+ <4 0x00000000 0x04000000>;
+ bank-width = <4>;
+ };
+
+ vram@2,00000000 {
+ compatible = "arm,vexpress-vram";
+ reg = <2 0x00000000 0x00800000>;
+ };
+
+ ethernet@2,02000000 {
+ compatible = "smsc,lan91c111";
+ reg = <2 0x02000000 0x10000>;
+ interrupts = <15>;
+ };
+
+ iofpga@3,00000000 {
+ compatible = "arm,amba-bus", "simple-bus";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0 3 0 0x200000>;
+
+ v2m_sysreg: sysreg@010000 {
+ compatible = "arm,vexpress-sysreg";
+ reg = <0x010000 0x1000>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ };
+
+ v2m_sysctl: sysctl@020000 {
+ compatible = "arm,sp810", "arm,primecell";
+ reg = <0x020000 0x1000>;
+ clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&smbclk>;
+ clock-names = "refclk", "timclk", "apb_pclk";
+ #clock-cells = <1>;
+ clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3";
+ };
+
+ aaci@040000 {
+ compatible = "arm,pl041", "arm,primecell";
+ reg = <0x040000 0x1000>;
+ interrupts = <11>;
+ clocks = <&smbclk>;
+ clock-names = "apb_pclk";
+ };
+
+ mmci@050000 {
+ compatible = "arm,pl180", "arm,primecell";
+ reg = <0x050000 0x1000>;
+ interrupts = <9 10>;
+ cd-gpios = <&v2m_sysreg 0 0>;
+ wp-gpios = <&v2m_sysreg 1 0>;
+ max-frequency = <12000000>;
+ vmmc-supply = <&v2m_fixed_3v3>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "mclk", "apb_pclk";
+ };
+
+ kmi@060000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x060000 0x1000>;
+ interrupts = <12>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ kmi@070000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x070000 0x1000>;
+ interrupts = <13>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ v2m_serial0: uart@090000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x090000 0x1000>;
+ interrupts = <5>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial1: uart@0a0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0a0000 0x1000>;
+ interrupts = <6>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial2: uart@0b0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0b0000 0x1000>;
+ interrupts = <7>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ v2m_serial3: uart@0c0000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0c0000 0x1000>;
+ interrupts = <8>;
+ clocks = <&v2m_clk24mhz>, <&smbclk>;
+ clock-names = "uartclk", "apb_pclk";
+ };
+
+ wdt@0f0000 {
+ compatible = "arm,sp805", "arm,primecell";
+ reg = <0x0f0000 0x1000>;
+ interrupts = <0>;
+ clocks = <&v2m_refclk32khz>, <&smbclk>;
+ clock-names = "wdogclk", "apb_pclk";
+ };
+
+ v2m_timer01: timer@110000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x110000 0x1000>;
+ interrupts = <2>;
+ clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&smbclk>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
+ };
+
+ v2m_timer23: timer@120000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x120000 0x1000>;
+ interrupts = <3>;
+ clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&smbclk>;
+ clock-names = "timclken1", "timclken2", "apb_pclk";
+ };
+
+ rtc@170000 {
+ compatible = "arm,pl031", "arm,primecell";
+ reg = <0x170000 0x1000>;
+ interrupts = <4>;
+ clocks = <&smbclk>;
+ clock-names = "apb_pclk";
+ };
+
+ clcd@1f0000 {
+ compatible = "arm,pl111", "arm,primecell";
+ reg = <0x1f0000 0x1000>;
+ interrupts = <14>;
+ clocks = <&v2m_oscclk1>, <&smbclk>;
+ clock-names = "v2m:oscclk1", "apb_pclk";
+ mode = "VGA";
+ use_dma = <0>;
+ framebuffer = <0x18000000 0x00180000>;
+ };
+
+ virtio_block@0130000 {
+ compatible = "virtio,mmio";
+ reg = <0x130000 0x200>;
+ interrupts = <42>;
+ };
+
+ };
+
+ v2m_fixed_3v3: fixedregulator@0 {
+ compatible = "regulator-fixed";
+ regulator-name = "3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ v2m_clk24mhz: clk24mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <24000000>;
+ clock-output-names = "v2m:clk24mhz";
+ };
+
+ v2m_refclk1mhz: refclk1mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <1000000>;
+ clock-output-names = "v2m:refclk1mhz";
+ };
+
+ v2m_refclk32khz: refclk32khz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "v2m:refclk32khz";
+ };
+
+ mcc {
+ compatible = "simple-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ v2m_oscclk1: osc@1 {
+ /* CLCD clock */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <23750000 63500000>;
+ #clock-cells = <0>;
+ clock-output-names = "v2m:oscclk1";
+ };
+
+ muxfpga@0 {
+ compatible = "arm,vexpress-muxfpga";
+ arm,vexpress-sysreg,func = <7 0>;
+ };
+
+ shutdown@0 {
+ compatible = "arm,vexpress-shutdown";
+ arm,vexpress-sysreg,func = <8 0>;
+ };
+ };
+ };
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
new file mode 100644
index 0000000..fe8cf5d
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x1-ca7x1.dts
@@ -0,0 +1,244 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x1_A7x1.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+ model = "RTSM_VE_CortexA15x1-A7x1";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x1_a7x1", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ clusters {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cluster0: cluster@0 {
+ reg = <0>;
+// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ };
+ };
+
+ cluster1: cluster@1 {
+ reg = <1>;
+// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core1: core@0 {
+ reg = <0>;
+ };
+
+ };
+ };
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core1>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400", "arm,cci";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ dcscb@60000000 {
+ compatible = "arm,rtsm,dcscb";
+ reg = <0 0x60000000 0 0x1000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
new file mode 100644
index 0000000..f715285
--- /dev/null
+++ b/arch/arm/boot/dts/rtsm_ve-v2p-ca15x4-ca7x4.dts
@@ -0,0 +1,358 @@
+/*
+ * ARM Ltd. Fast Models
+ *
+ * Versatile Express (VE) system model
+ * ARMCortexA15x4CT
+ * ARMCortexA7x4CT
+ * RTSM_VE_Cortex_A15x4_A7x4.lisa
+ */
+
+/dts-v1/;
+
+/memreserve/ 0xff000000 0x01000000;
+
+/ {
+ model = "RTSM_VE_CortexA15x4-A7x4";
+ arm,vexpress,site = <0xf>;
+ compatible = "arm,rtsm_ve,cortex_a15x4_a7x4", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ clusters {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cluster0: cluster@0 {
+ reg = <0>;
+// freqs = <500000000 600000000 700000000 800000000 900000000 1000000000 1100000000 1200000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ core1: core@1 {
+ reg = <1>;
+ };
+
+ core2: core@2 {
+ reg = <2>;
+ };
+
+ core3: core@3 {
+ reg = <3>;
+ };
+
+ };
+ };
+
+ cluster1: cluster@1 {
+ reg = <1>;
+// freqs = <350000000 400000000 500000000 600000000 700000000 800000000 900000000 1000000000>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core4: core@0 {
+ reg = <0>;
+ };
+
+ core5: core@1 {
+ reg = <1>;
+ };
+
+ core6: core@2 {
+ reg = <2>;
+ };
+
+ core7: core@3 {
+ reg = <3>;
+ };
+
+ };
+ };
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ cluster = <&cluster0>;
+ core = <&core1>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu2: cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <2>;
+ cluster = <&cluster0>;
+ core = <&core2>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu3: cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <3>;
+ cluster = <&cluster0>;
+ core = <&core3>;
+// clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu4: cpu@4 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core4>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu5: cpu@5 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x101>;
+ cluster = <&cluster1>;
+ core = <&core5>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu6: cpu@6 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x102>;
+ cluster = <&cluster1>;
+ core = <&core6>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu7: cpu@7 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a7";
+ reg = <0x103>;
+ cluster = <&cluster1>;
+ core = <&core7>;
+// clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0 0x80000000 0 0x80000000>;
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400", "arm,cci";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ dcscb@60000000 {
+ compatible = "arm,rtsm,dcscb";
+ reg = <0 0x60000000 0 0x1000>;
+ };
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0 0x2c001000 0 0x1000>,
+ <0 0x2c002000 0 0x1000>,
+ <0 0x2c004000 0 0x2000>,
+ <0 0x2c006000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ gic-cpuif@2 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <2>;
+ cpu = <&cpu2>;
+ };
+ gic-cpuif@3 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <3>;
+ cpu = <&cpu3>;
+ };
+ gic-cpuif@4 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <4>;
+ cpu = <&cpu4>;
+ };
+ gic-cpuif@5 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <5>;
+ cpu = <&cpu5>;
+ };
+ gic-cpuif@6 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <6>;
+ cpu = <&cpu6>;
+ };
+ gic-cpuif@7 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <7>;
+ cpu = <&cpu7>;
+ };
+ };
+
+ timer {
+ compatible = "arm,armv7-timer";
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
+ };
+
+ dcc {
+ compatible = "arm,vexpress,config-bus";
+ arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+ osc@0 {
+ /* ACLK clock to the AXI master port on the test chip */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 0>;
+ freq-range = <30000000 50000000>;
+ #clock-cells = <0>;
+ clock-output-names = "extsaxiclk";
+ };
+
+ oscclk1: osc@1 {
+ /* Reference clock for the CLCD */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 1>;
+ freq-range = <10000000 80000000>;
+ #clock-cells = <0>;
+ clock-output-names = "clcdclk";
+ };
+
+ smbclk: oscclk2: osc@2 {
+ /* Reference clock for the test chip internal PLLs */
+ compatible = "arm,vexpress-osc";
+ arm,vexpress-sysreg,func = <1 2>;
+ freq-range = <33000000 100000000>;
+ #clock-cells = <0>;
+ clock-output-names = "tcrefclk";
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index 5000e0d..642775d 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -35,8 +35,12 @@
ssc1 = &ssc1;
};
cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
cpu@0 {
+ device_type = "cpu";
compatible = "arm,cortex-a5";
+ reg = <0x0>;
};
};
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index e7ef619..06ef8b6 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -16,8 +16,12 @@
interrupt-parent = <&intc>;
cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
cpu@0 {
+ device_type = "cpu";
compatible = "arm,cortex-a8";
+ reg = <0x0>;
};
};
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 31fa38f..d285254 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -17,8 +17,12 @@
interrupt-parent = <&intc>;
cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
cpu@0 {
+ device_type = "cpu";
compatible = "arm,cortex-a8";
+ reg = <0x0>;
};
};
diff --git a/arch/arm/boot/dts/testcases/tests-phandle.dtsi b/arch/arm/boot/dts/testcases/tests-phandle.dtsi
index 0007d3c..788a4c2 100644
--- a/arch/arm/boot/dts/testcases/tests-phandle.dtsi
+++ b/arch/arm/boot/dts/testcases/tests-phandle.dtsi
@@ -1,6 +1,9 @@
/ {
testcase-data {
+ security-password = "password";
+ duplicate-name = "duplicate";
+ duplicate-name { };
phandle-tests {
provider0: provider0 {
#phandle-cells = <0>;
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index ac870fb..9584232e 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -228,6 +228,7 @@
};
clcd@1f0000 {
+ status = "disabled";
compatible = "arm,pl111", "arm,primecell";
reg = <0x1f0000 0x1000>;
interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi
index f142036..6593398 100644
--- a/arch/arm/boot/dts/vexpress-v2m.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m.dtsi
@@ -227,6 +227,7 @@
};
clcd@1f000 {
+ status = "disabled";
compatible = "arm,pl111", "arm,primecell";
reg = <0x1f000 0x1000>;
interrupts = <14>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 9420053..cc6a8c0 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/memreserve/ 0xbf000000 0x01000000;
+
/ {
model = "V2P-CA15";
arm,hbi = <0x237>;
@@ -57,6 +59,8 @@
interrupts = <0 85 4>;
clocks = <&oscclk5>;
clock-names = "pxlclk";
+ mode = "1024x768-16@60";
+ framebuffer = <0 0xff000000 0 0x01000000>;
};
memory-controller@2b0a0000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index d2803be..f1dc620 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -9,11 +9,13 @@
/dts-v1/;
+/memreserve/ 0xff000000 0x01000000;
+
/ {
model = "V2P-CA15_CA7";
arm,hbi = <0x249>;
arm,vexpress,site = <0xf>;
- compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress";
+ compatible = "arm,vexpress,v2p-ca15_a7", "arm,vexpress", "arm,generic";
interrupt-parent = <&gic>;
#address-cells = <2>;
#size-cells = <2>;
@@ -29,44 +31,106 @@
i2c1 = &v2m_i2c_pcie;
};
- cpus {
+ clusters {
#address-cells = <1>;
#size-cells = <0>;
- cpu0: cpu@0 {
- device_type = "cpu";
- compatible = "arm,cortex-a15";
+ cluster0: cluster@0 {
reg = <0>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core0: core@0 {
+ reg = <0>;
+ };
+
+ core1: core@1 {
+ reg = <1>;
+ };
+
+ };
};
- cpu1: cpu@1 {
- device_type = "cpu";
- compatible = "arm,cortex-a15";
+ cluster1: cluster@1 {
reg = <1>;
+ cores {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ core2: core@0 {
+ reg = <0>;
+ };
+
+ core3: core@1 {
+ reg = <1>;
+ };
+
+ core4: core@2 {
+ reg = <2>;
+ };
+ };
};
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
cpu2: cpu@2 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x100>;
+ cluster = <&cluster1>;
+ core = <&core2>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
};
cpu3: cpu@3 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x101>;
+ cluster = <&cluster1>;
+ core = <&core3>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
};
cpu4: cpu@4 {
device_type = "cpu";
compatible = "arm,cortex-a7";
reg = <0x102>;
+ cluster = <&cluster1>;
+ core = <&core4>;
+ clock-frequency = <800000000>;
+ cci-control-port = <&cci_control2>;
+ };
+
+ cpu0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <0>;
+ cluster = <&cluster0>;
+ core = <&core0>;
+ clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
+ };
+
+ cpu1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a15";
+ reg = <1>;
+ cluster = <&cluster0>;
+ core = <&core1>;
+ clock-frequency = <1000000000>;
+ cci-control-port = <&cci_control1>;
};
};
memory@80000000 {
device_type = "memory";
- reg = <0 0x80000000 0 0x40000000>;
+ reg = <0 0x80000000 0 0x80000000>;
};
wdt@2a490000 {
@@ -81,6 +145,8 @@
compatible = "arm,hdlcd";
reg = <0 0x2b000000 0 0x1000>;
interrupts = <0 85 4>;
+ mode = "1024x768-16@60";
+ framebuffer = <0 0xff000000 0 0x01000000>;
clocks = <&oscclk5>;
clock-names = "pxlclk";
};
@@ -102,6 +168,64 @@
<0 0x2c004000 0 0x2000>,
<0 0x2c006000 0 0x2000>;
interrupts = <1 9 0xf04>;
+
+ gic-cpuif@0 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <0>;
+ cpu = <&cpu0>;
+ };
+ gic-cpuif@1 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <1>;
+ cpu = <&cpu1>;
+ };
+ gic-cpuif@2 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <2>;
+ cpu = <&cpu2>;
+ };
+
+ gic-cpuif@3 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <3>;
+ cpu = <&cpu3>;
+ };
+
+ gic-cpuif@4 {
+ compatible = "arm,gic-cpuif";
+ cpuif-id = <4>;
+ cpu = <&cpu4>;
+ };
+ };
+
+ cci@2c090000 {
+ compatible = "arm,cci-400";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0 0x2c090000 0 0x1000>;
+ ranges = <0x0 0x0 0x2c090000 0x10000>;
+
+ cci_control1: slave-if@4000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x4000 0x1000>;
+ };
+
+ cci_control2: slave-if@5000 {
+ compatible = "arm,cci-400-ctrl-if";
+ interface-type = "ace";
+ reg = <0x5000 0x1000>;
+ };
+ };
+
+ cci-pmu@2c099000 {
+ compatible = "arm,cci-400-pmu";
+ reg = <0 0x2c099000 0 0x6000>;
+ interrupts = <0 101 4>,
+ <0 102 4>,
+ <0 103 4>,
+ <0 104 4>,
+ <0 105 4>;
};
memory-controller@7ffd0000 {
@@ -125,6 +249,12 @@
clock-names = "apb_pclk";
};
+ spc@7fff0000 {
+ compatible = "arm,vexpress-spc,v2p-ca15_a7","arm,vexpress-spc";
+ reg = <0 0x7fff0000 0 0x1000>;
+ interrupts = <0 95 4>;
+ };
+
timer {
compatible = "arm,armv7-timer";
interrupts = <1 13 0xf08>,
@@ -133,12 +263,21 @@
<1 10 0xf08>;
};
- pmu {
+ pmu_a15 {
compatible = "arm,cortex-a15-pmu";
+ cluster = <&cluster0>;
interrupts = <0 68 4>,
<0 69 4>;
};
+ pmu_a7 {
+ compatible = "arm,cortex-a7-pmu";
+ cluster = <&cluster1>;
+ interrupts = <0 128 4>,
+ <0 129 4>,
+ <0 130 4>;
+ };
+
oscclk6a: oscclk6a {
/* Reference 24MHz clock */
compatible = "fixed-clock";
@@ -147,6 +286,15 @@
clock-output-names = "oscclk6a";
};
+ psci {
+ compatible = "arm,psci";
+ method = "smc";
+ cpu_suspend = <0x80100001>;
+ cpu_off = <0x80100002>;
+ cpu_on = <0x80100003>;
+ migrate = <0x80100004>;
+ };
+
dcc {
compatible = "arm,vexpress,config-bus";
arm,vexpress,config-bridge = <&v2m_sysreg>;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index c544a55..cf633ed 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/memreserve/ 0xbf000000 0x01000000;
+
/ {
model = "V2P-CA5s";
arm,hbi = <0x225>;
@@ -59,6 +61,8 @@
interrupts = <0 85 4>;
clocks = <&oscclk3>;
clock-names = "pxlclk";
+ mode = "640x480-16@60";
+ framebuffer = <0xbf000000 0x01000000>;
};
memory-controller@2a150000 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index 62d9b22..f83706b 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -9,6 +9,8 @@
/dts-v1/;
+/include/ "clcd-panels.dtsi"
+
/ {
model = "V2P-CA9";
arm,hbi = <0x191>;
@@ -73,6 +75,8 @@
interrupts = <0 44 4>;
clocks = <&oscclk1>, <&oscclk2>;
clock-names = "clcdclk", "apb_pclk";
+ mode = "XVGA";
+ use_dma = <1>;
};
memory-controller@100e0000 {
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 48434cbe..462cd58 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -14,5 +14,9 @@
obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o
obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o
obj-$(CONFIG_MCPM) += mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+obj-$(CONFIG_BL_SWITCHER) += bL_switcher.o
+obj-$(CONFIG_BL_SWITCHER_DUMMY_IF) += bL_switcher_dummy_if.o
+
AFLAGS_mcpm_head.o := -march=armv7-a
AFLAGS_vlock.o := -march=armv7-a
+CFLAGS_REMOVE_mcpm_entry.o = -pg
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
new file mode 100644
index 0000000..8fee70d
--- /dev/null
+++ b/arch/arm/common/bL_switcher.c
@@ -0,0 +1,864 @@
+/*
+ * arch/arm/common/bL_switcher.c -- big.LITTLE cluster switcher core driver
+ *
+ * Created by: Nicolas Pitre, March 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/atomic.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/cpu_pm.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kthread.h>
+#include <linux/wait.h>
+#include <linux/time.h>
+#include <linux/clockchips.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/notifier.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/moduleparam.h>
+
+#include <asm/smp_plat.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/suspend.h>
+#include <asm/mcpm.h>
+#include <asm/bL_switcher.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power_cpu_migrate.h>
+
+
+/*
+ * Use our own MPIDR accessors as the generic ones in asm/cputype.h have
+ * __attribute_const__ and we don't want the compiler to assume any
+ * constness here as the value _does_ change along some code paths.
+ */
+
+static int read_mpidr(void)
+{
+ unsigned int id;
+ asm volatile ("mrc\tp15, 0, %0, c0, c0, 5" : "=r" (id));
+ return id & MPIDR_HWID_BITMASK;
+}
+
+/*
+ * Get a global nanosecond time stamp for tracing.
+ */
+static s64 get_ns(void)
+{
+ struct timespec ts;
+ getnstimeofday(&ts);
+ return timespec_to_ns(&ts);
+}
+
+/*
+ * bL switcher core code.
+ */
+
+static void bL_do_switch(void *_arg)
+{
+ unsigned ib_mpidr, ib_cpu, ib_cluster;
+ long volatile handshake, **handshake_ptr = _arg;
+
+ pr_debug("%s\n", __func__);
+
+ ib_mpidr = cpu_logical_map(smp_processor_id());
+ ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+ ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+ /* Advertise our handshake location */
+ if (handshake_ptr) {
+ handshake = 0;
+ *handshake_ptr = &handshake;
+ } else
+ handshake = -1;
+
+ /*
+ * Our state has been saved at this point. Let's release our
+ * inbound CPU.
+ */
+ mcpm_set_entry_vector(ib_cpu, ib_cluster, cpu_resume);
+ sev();
+
+ /*
+ * From this point, we must assume that our counterpart CPU might
+ * have taken over in its parallel world already, as if execution
+ * just returned from cpu_suspend(). It is therefore important to
+ * be very careful not to make any change the other guy is not
+ * expecting. This is why we need stack isolation.
+ *
+ * Fancy under cover tasks could be performed here. For now
+ * we have none.
+ */
+
+ /*
+ * Let's wait until our inbound is alive.
+ */
+ while (!handshake) {
+ wfe();
+ smp_mb();
+ }
+
+ /* Let's put ourself down. */
+ mcpm_cpu_power_down();
+
+ /* should never get here */
+ BUG();
+}
+
+/*
+ * Stack isolation. To ensure 'current' remains valid, we just use another
+ * piece of our thread's stack space which should be fairly lightly used.
+ * The selected area starts just above the thread_info structure located
+ * at the very bottom of the stack, aligned to a cache line, and indexed
+ * with the cluster number.
+ */
+#define STACK_SIZE 512
+extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+static int bL_switchpoint(unsigned long _arg)
+{
+ unsigned int mpidr = read_mpidr();
+ unsigned int clusterid = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ void *stack = current_thread_info() + 1;
+ stack = PTR_ALIGN(stack, L1_CACHE_BYTES);
+ stack += clusterid * STACK_SIZE + STACK_SIZE;
+ call_with_stack(bL_do_switch, (void *)_arg, stack);
+ BUG();
+}
+
+/*
+ * Generic switcher interface
+ */
+
+static unsigned int bL_gic_id[MAX_CPUS_PER_CLUSTER][MAX_NR_CLUSTERS];
+static int bL_switcher_cpu_pairing[NR_CPUS];
+
+/*
+ * bL_switch_to - Switch to a specific cluster for the current CPU
+ * @new_cluster_id: the ID of the cluster to switch to.
+ *
+ * This function must be called on the CPU to be switched.
+ * Returns 0 on success, else a negative status code.
+ */
+static int bL_switch_to(unsigned int new_cluster_id)
+{
+ unsigned int mpidr, this_cpu, that_cpu;
+ unsigned int ob_mpidr, ob_cpu, ob_cluster, ib_mpidr, ib_cpu, ib_cluster;
+ struct completion inbound_alive;
+ struct tick_device *tdev;
+ enum clock_event_mode tdev_mode;
+ long volatile *handshake_ptr;
+ int ipi_nr, ret;
+
+ this_cpu = smp_processor_id();
+ ob_mpidr = read_mpidr();
+ ob_cpu = MPIDR_AFFINITY_LEVEL(ob_mpidr, 0);
+ ob_cluster = MPIDR_AFFINITY_LEVEL(ob_mpidr, 1);
+ BUG_ON(cpu_logical_map(this_cpu) != ob_mpidr);
+
+ if (new_cluster_id == ob_cluster)
+ return 0;
+
+ that_cpu = bL_switcher_cpu_pairing[this_cpu];
+ ib_mpidr = cpu_logical_map(that_cpu);
+ ib_cpu = MPIDR_AFFINITY_LEVEL(ib_mpidr, 0);
+ ib_cluster = MPIDR_AFFINITY_LEVEL(ib_mpidr, 1);
+
+ pr_debug("before switch: CPU %d MPIDR %#x -> %#x\n",
+ this_cpu, ob_mpidr, ib_mpidr);
+
+ this_cpu = smp_processor_id();
+
+ /* Close the gate for our entry vectors */
+ mcpm_set_entry_vector(ob_cpu, ob_cluster, NULL);
+ mcpm_set_entry_vector(ib_cpu, ib_cluster, NULL);
+
+ /* Install our "inbound alive" notifier. */
+ init_completion(&inbound_alive);
+ ipi_nr = register_ipi_completion(&inbound_alive, this_cpu);
+ ipi_nr |= ((1 << 16) << bL_gic_id[ob_cpu][ob_cluster]);
+ mcpm_set_early_poke(ib_cpu, ib_cluster, gic_get_sgir_physaddr(), ipi_nr);
+
+ /*
+ * Let's wake up the inbound CPU now in case it requires some delay
+ * to come online, but leave it gated in our entry vector code.
+ */
+ ret = mcpm_cpu_power_up(ib_cpu, ib_cluster);
+ if (ret) {
+ pr_err("%s: mcpm_cpu_power_up() returned %d\n", __func__, ret);
+ return ret;
+ }
+
+ /*
+ * Raise a SGI on the inbound CPU to make sure it doesn't stall
+ * in a possible WFI, such as in bL_power_down().
+ */
+ gic_send_sgi(bL_gic_id[ib_cpu][ib_cluster], 0);
+
+ /*
+ * Wait for the inbound to come up. This allows for other
+ * tasks to be scheduled in the mean time.
+ */
+ wait_for_completion(&inbound_alive);
+ mcpm_set_early_poke(ib_cpu, ib_cluster, 0, 0);
+
+ /*
+ * From this point we are entering the switch critical zone
+ * and can't sleep/schedule anymore.
+ */
+ local_irq_disable();
+ local_fiq_disable();
+ trace_cpu_migrate_begin(get_ns(), ob_mpidr);
+
+ /* redirect GIC's SGIs to our counterpart */
+ gic_migrate_target(bL_gic_id[ib_cpu][ib_cluster]);
+
+ tdev = tick_get_device(this_cpu);
+ if (tdev && !cpumask_equal(tdev->evtdev->cpumask, cpumask_of(this_cpu)))
+ tdev = NULL;
+ if (tdev) {
+ tdev_mode = tdev->evtdev->mode;
+ clockevents_set_mode(tdev->evtdev, CLOCK_EVT_MODE_SHUTDOWN);
+ }
+
+ ret = cpu_pm_enter();
+
+ /* we can not tolerate errors at this point */
+ if (ret)
+ panic("%s: cpu_pm_enter() returned %d\n", __func__, ret);
+
+ /*
+ * Swap the physical CPUs in the logical map for this logical CPU.
+ * This must be flushed to RAM as the resume code
+ * needs to access it while the caches are still disabled.
+ */
+ cpu_logical_map(this_cpu) = ib_mpidr;
+ cpu_logical_map(that_cpu) = ob_mpidr;
+ sync_cache_w(&cpu_logical_map(this_cpu));
+
+ /* Let's do the actual CPU switch. */
+ ret = cpu_suspend((unsigned long)&handshake_ptr, bL_switchpoint);
+ if (ret > 0)
+ panic("%s: cpu_suspend() returned %d\n", __func__, ret);
+
+ /* We are executing on the inbound CPU at this point */
+ mpidr = read_mpidr();
+ pr_debug("after switch: CPU %d MPIDR %#x\n", this_cpu, mpidr);
+ BUG_ON(mpidr != ib_mpidr);
+
+ mcpm_cpu_powered_up();
+
+ ret = cpu_pm_exit();
+
+ if (tdev) {
+ clockevents_set_mode(tdev->evtdev, tdev_mode);
+ clockevents_program_event(tdev->evtdev,
+ tdev->evtdev->next_event, 1);
+ }
+
+ trace_cpu_migrate_finish(get_ns(), ib_mpidr);
+ local_fiq_enable();
+ local_irq_enable();
+
+ *handshake_ptr = 1;
+ dsb_sev();
+
+ if (ret)
+ pr_err("%s exiting with error %d\n", __func__, ret);
+ return ret;
+}
+
+struct bL_thread {
+ spinlock_t lock;
+ struct task_struct *task;
+ wait_queue_head_t wq;
+ int wanted_cluster;
+ struct completion started;
+ bL_switch_completion_handler completer;
+ void *completer_cookie;
+};
+
+static struct bL_thread bL_threads[NR_CPUS];
+
+static int bL_switcher_thread(void *arg)
+{
+ struct bL_thread *t = arg;
+ struct sched_param param = { .sched_priority = 1 };
+ int cluster;
+ bL_switch_completion_handler completer;
+ void *completer_cookie;
+
+ sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m);
+ complete(&t->started);
+
+ do {
+ if (signal_pending(current))
+ flush_signals(current);
+ wait_event_interruptible(t->wq,
+ t->wanted_cluster != -1 ||
+ kthread_should_stop());
+
+ spin_lock(&t->lock);
+ cluster = t->wanted_cluster;
+ completer = t->completer;
+ completer_cookie = t->completer_cookie;
+ t->wanted_cluster = -1;
+ t->completer = NULL;
+ spin_unlock(&t->lock);
+
+ if (cluster != -1) {
+ bL_switch_to(cluster);
+
+ if (completer)
+ completer(completer_cookie);
+ }
+ } while (!kthread_should_stop());
+
+ return 0;
+}
+
+static struct task_struct * bL_switcher_thread_create(int cpu, void *arg)
+{
+ struct task_struct *task;
+
+ task = kthread_create_on_node(bL_switcher_thread, arg,
+ cpu_to_node(cpu), "kswitcher_%d", cpu);
+ if (!IS_ERR(task)) {
+ kthread_bind(task, cpu);
+ wake_up_process(task);
+ } else
+ pr_err("%s failed for CPU %d\n", __func__, cpu);
+ return task;
+}
+
+/*
+ * bL_switch_request_cb - Switch to a specific cluster for the given CPU,
+ * with completion notification via a callback
+ *
+ * @cpu: the CPU to switch
+ * @new_cluster_id: the ID of the cluster to switch to.
+ * @completer: switch completion callback. if non-NULL,
+ * @completer(@completer_cookie) will be called on completion of
+ * the switch, in non-atomic context.
+ * @completer_cookie: opaque context argument for @completer.
+ *
+ * This function causes a cluster switch on the given CPU by waking up
+ * the appropriate switcher thread. This function may or may not return
+ * before the switch has occurred.
+ *
+ * If a @completer callback function is supplied, it will be called when
+ * the switch is complete. This can be used to determine asynchronously
+ * when the switch is complete, regardless of when bL_switch_request()
+ * returns. When @completer is supplied, no new switch request is permitted
+ * for the affected CPU until after the switch is complete, and @completer
+ * has returned.
+ */
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+ bL_switch_completion_handler completer,
+ void *completer_cookie)
+{
+ struct bL_thread *t;
+
+ if (cpu >= ARRAY_SIZE(bL_threads)) {
+ pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+ return -EINVAL;
+ }
+
+ t = &bL_threads[cpu];
+
+ if (IS_ERR(t->task))
+ return PTR_ERR(t->task);
+ if (!t->task)
+ return -ESRCH;
+
+ spin_lock(&t->lock);
+ if (t->completer) {
+ spin_unlock(&t->lock);
+ return -EBUSY;
+ }
+ t->completer = completer;
+ t->completer_cookie = completer_cookie;
+ t->wanted_cluster = new_cluster_id;
+ spin_unlock(&t->lock);
+ wake_up(&t->wq);
+ return 0;
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_cb);
+
+/*
+ * Detach an outstanding switch request.
+ *
+ * The switcher will continue with the switch request in the background,
+ * but the completer function will not be called.
+ *
+ * This may be necessary if the completer is in a kernel module which is
+ * about to be unloaded.
+ */
+void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer)
+{
+ struct bL_thread *t;
+
+ if (cpu >= ARRAY_SIZE(bL_threads)) {
+ pr_err("%s: cpu %d out of bounds\n", __func__, cpu);
+ return;
+ }
+
+ t = &bL_threads[cpu];
+
+ if (IS_ERR(t->task) || !t->task)
+ return;
+
+ spin_lock(&t->lock);
+ if (t->completer == completer)
+ t->completer = NULL;
+ spin_unlock(&t->lock);
+}
+
+EXPORT_SYMBOL_GPL(bL_switch_request_detach);
+
+/*
+ * Activation and configuration code.
+ */
+
+static DEFINE_MUTEX(bL_switcher_activation_lock);
+static BLOCKING_NOTIFIER_HEAD(bL_activation_notifier);
+static unsigned int bL_switcher_active;
+static unsigned int bL_switcher_cpu_original_cluster[NR_CPUS];
+static cpumask_t bL_switcher_removed_logical_cpus;
+
+int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_register_notifier);
+
+int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&bL_activation_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_unregister_notifier);
+
+static int bL_activation_notify(unsigned long val)
+{
+ int ret;
+
+ ret = blocking_notifier_call_chain(&bL_activation_notifier, val, NULL);
+ if (ret & NOTIFY_STOP_MASK)
+ pr_err("%s: notifier chain failed with status 0x%x\n",
+ __func__, ret);
+ return notifier_to_errno(ret);
+}
+
+static void bL_switcher_restore_cpus(void)
+{
+ int i;
+
+ for_each_cpu(i, &bL_switcher_removed_logical_cpus)
+ cpu_up(i);
+}
+
+static int bL_switcher_halve_cpus(void)
+{
+ int i, j, cluster_0, gic_id, ret;
+ unsigned int cpu, cluster, mask;
+ cpumask_t available_cpus;
+
+ /* First pass to validate what we have */
+ mask = 0;
+ for_each_online_cpu(i) {
+ cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+ if (cluster >= 2) {
+ pr_err("%s: only dual cluster systems are supported\n", __func__);
+ return -EINVAL;
+ }
+ if (WARN_ON(cpu >= MAX_CPUS_PER_CLUSTER))
+ return -EINVAL;
+ mask |= (1 << cluster);
+ }
+ if (mask != 3) {
+ pr_err("%s: no CPU pairing possible\n", __func__);
+ return -EINVAL;
+ }
+
+ /*
+ * Now let's do the pairing. We match each CPU with another CPU
+ * from a different cluster. To get a uniform scheduling behavior
+ * without fiddling with CPU topology and compute capacity data,
+ * we'll use logical CPUs initially belonging to the same cluster.
+ */
+ memset(bL_switcher_cpu_pairing, -1, sizeof(bL_switcher_cpu_pairing));
+ cpumask_copy(&available_cpus, cpu_online_mask);
+ cluster_0 = -1;
+ for_each_cpu(i, &available_cpus) {
+ int match = -1;
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+ if (cluster_0 == -1)
+ cluster_0 = cluster;
+ if (cluster != cluster_0)
+ continue;
+ cpumask_clear_cpu(i, &available_cpus);
+ for_each_cpu(j, &available_cpus) {
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(j), 1);
+ /*
+ * Let's remember the last match to create "odd"
+ * pairing on purpose in order for other code not
+ * to assume any relation between physical and
+ * logical CPU numbers.
+ */
+ if (cluster != cluster_0)
+ match = j;
+ }
+ if (match != -1) {
+ bL_switcher_cpu_pairing[i] = match;
+ cpumask_clear_cpu(match, &available_cpus);
+ pr_info("CPU%d paired with CPU%d\n", i, match);
+ }
+ }
+
+ /*
+ * Now we disable the unwanted CPUs i.e. everything that has no
+ * pairing information (that includes the pairing counterparts).
+ */
+ cpumask_clear(&bL_switcher_removed_logical_cpus);
+ for_each_online_cpu(i) {
+ cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 1);
+
+ /* Let's take note of the GIC ID for this CPU */
+ gic_id = gic_get_cpu_id(i);
+ if (gic_id < 0) {
+ pr_err("%s: bad GIC ID for CPU %d\n", __func__, i);
+ bL_switcher_restore_cpus();
+ return -EINVAL;
+ }
+ bL_gic_id[cpu][cluster] = gic_id;
+ pr_info("GIC ID for CPU %u cluster %u is %u\n",
+ cpu, cluster, gic_id);
+
+ if (bL_switcher_cpu_pairing[i] != -1) {
+ bL_switcher_cpu_original_cluster[i] = cluster;
+ continue;
+ }
+
+ ret = cpu_down(i);
+ if (ret) {
+ bL_switcher_restore_cpus();
+ return ret;
+ }
+ cpumask_set_cpu(i, &bL_switcher_removed_logical_cpus);
+ }
+
+ return 0;
+}
+
+/* Determine the logical CPU a given physical CPU is grouped on. */
+int bL_switcher_get_logical_index(u32 mpidr)
+{
+ int cpu;
+
+ if (!bL_switcher_active)
+ return -EUNATCH;
+
+ mpidr &= MPIDR_HWID_BITMASK;
+ for_each_online_cpu(cpu) {
+ int pairing = bL_switcher_cpu_pairing[cpu];
+ if (pairing == -1)
+ continue;
+ if ((mpidr == cpu_logical_map(cpu)) ||
+ (mpidr == cpu_logical_map(pairing)))
+ return cpu;
+ }
+ return -EINVAL;
+}
+
+static void bL_switcher_trace_trigger_cpu(void *__always_unused info)
+{
+ trace_cpu_migrate_current(get_ns(), read_mpidr());
+}
+
+int bL_switcher_trace_trigger(void)
+{
+ int ret;
+
+ preempt_disable();
+
+ bL_switcher_trace_trigger_cpu(NULL);
+ ret = smp_call_function(bL_switcher_trace_trigger_cpu, NULL, true);
+
+ preempt_enable();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_trace_trigger);
+
+static int bL_switcher_enable(void)
+{
+ int cpu, ret;
+
+ mutex_lock(&bL_switcher_activation_lock);
+ cpu_hotplug_driver_lock();
+ if (bL_switcher_active) {
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+ return 0;
+ }
+
+ pr_info("big.LITTLE switcher initializing\n");
+
+ ret = bL_activation_notify(BL_NOTIFY_PRE_ENABLE);
+ if (ret)
+ goto error;
+
+ ret = bL_switcher_halve_cpus();
+ if (ret)
+ goto error;
+
+ bL_switcher_trace_trigger();
+
+ for_each_online_cpu(cpu) {
+ struct bL_thread *t = &bL_threads[cpu];
+ spin_lock_init(&t->lock);
+ init_waitqueue_head(&t->wq);
+ init_completion(&t->started);
+ t->wanted_cluster = -1;
+ t->task = bL_switcher_thread_create(cpu, t);
+ }
+
+ bL_switcher_active = 1;
+ bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+ pr_info("big.LITTLE switcher initialized\n");
+ goto out;
+
+error:
+ pr_warning("big.LITTLE switcher initialization failed\n");
+ bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+ return ret;
+}
+
+#ifdef CONFIG_SYSFS
+
+static void bL_switcher_disable(void)
+{
+ unsigned int cpu, cluster;
+ struct bL_thread *t;
+ struct task_struct *task;
+
+ mutex_lock(&bL_switcher_activation_lock);
+ cpu_hotplug_driver_lock();
+
+ if (!bL_switcher_active)
+ goto out;
+
+ if (bL_activation_notify(BL_NOTIFY_PRE_DISABLE) != 0) {
+ bL_activation_notify(BL_NOTIFY_POST_ENABLE);
+ goto out;
+ }
+
+ bL_switcher_active = 0;
+
+ /*
+ * To deactivate the switcher, we must shut down the switcher
+ * threads to prevent any other requests from being accepted.
+ * Then, if the final cluster for given logical CPU is not the
+ * same as the original one, we'll recreate a switcher thread
+ * just for the purpose of switching the CPU back without any
+ * possibility for interference from external requests.
+ */
+ for_each_online_cpu(cpu) {
+ t = &bL_threads[cpu];
+ task = t->task;
+ t->task = NULL;
+ if (!task || IS_ERR(task))
+ continue;
+ kthread_stop(task);
+ /* no more switch may happen on this CPU at this point */
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+ if (cluster == bL_switcher_cpu_original_cluster[cpu])
+ continue;
+ init_completion(&t->started);
+ t->wanted_cluster = bL_switcher_cpu_original_cluster[cpu];
+ task = bL_switcher_thread_create(cpu, t);
+ if (!IS_ERR(task)) {
+ wait_for_completion(&t->started);
+ kthread_stop(task);
+ cluster = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+ if (cluster == bL_switcher_cpu_original_cluster[cpu])
+ continue;
+ }
+ /* If execution gets here, we're in trouble. */
+ pr_crit("%s: unable to restore original cluster for CPU %d\n",
+ __func__, cpu);
+ pr_crit("%s: CPU %d can't be restored\n",
+ __func__, bL_switcher_cpu_pairing[cpu]);
+ cpumask_clear_cpu(bL_switcher_cpu_pairing[cpu],
+ &bL_switcher_removed_logical_cpus);
+ }
+
+ bL_switcher_restore_cpus();
+ bL_switcher_trace_trigger();
+
+ bL_activation_notify(BL_NOTIFY_POST_DISABLE);
+
+out:
+ cpu_hotplug_driver_unlock();
+ mutex_unlock(&bL_switcher_activation_lock);
+}
+
+static ssize_t bL_switcher_active_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", bL_switcher_active);
+}
+
+static ssize_t bL_switcher_active_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int ret;
+
+ switch (buf[0]) {
+ case '0':
+ bL_switcher_disable();
+ ret = 0;
+ break;
+ case '1':
+ ret = bL_switcher_enable();
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return (ret >= 0) ? count : ret;
+}
+
+static ssize_t bL_switcher_trace_trigger_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int ret = bL_switcher_trace_trigger();
+
+ return ret ? ret : count;
+}
+
+static struct kobj_attribute bL_switcher_active_attr =
+ __ATTR(active, 0644, bL_switcher_active_show, bL_switcher_active_store);
+
+static struct kobj_attribute bL_switcher_trace_trigger_attr =
+ __ATTR(trace_trigger, 0200, NULL, bL_switcher_trace_trigger_store);
+
+static struct attribute *bL_switcher_attrs[] = {
+ &bL_switcher_active_attr.attr,
+ &bL_switcher_trace_trigger_attr.attr,
+ NULL,
+};
+
+static struct attribute_group bL_switcher_attr_group = {
+ .attrs = bL_switcher_attrs,
+};
+
+static struct kobject *bL_switcher_kobj;
+
+static int __init bL_switcher_sysfs_init(void)
+{
+ int ret;
+
+ bL_switcher_kobj = kobject_create_and_add("bL_switcher", kernel_kobj);
+ if (!bL_switcher_kobj)
+ return -ENOMEM;
+ ret = sysfs_create_group(bL_switcher_kobj, &bL_switcher_attr_group);
+ if (ret)
+ kobject_put(bL_switcher_kobj);
+ return ret;
+}
+
+#endif /* CONFIG_SYSFS */
+
+bool bL_switcher_get_enabled(void)
+{
+ mutex_lock(&bL_switcher_activation_lock);
+
+ return bL_switcher_active;
+}
+EXPORT_SYMBOL_GPL(bL_switcher_get_enabled);
+
+void bL_switcher_put_enabled(void)
+{
+ mutex_unlock(&bL_switcher_activation_lock);
+}
+EXPORT_SYMBOL_GPL(bL_switcher_put_enabled);
+
+/*
+ * Veto any CPU hotplug operation while the switcher is active.
+ * We're just not ready to deal with that given the trickery involved.
+ */
+static int bL_switcher_hotplug_callback(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_DOWN_PREPARE:
+ if (bL_switcher_active)
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block bL_switcher_hotplug_notifier =
+ { &bL_switcher_hotplug_callback, NULL, 0 };
+
+#ifdef CONFIG_SCHED_HMP
+static bool no_bL_switcher = true;
+#else
+static bool no_bL_switcher;
+#endif
+core_param(no_bL_switcher, no_bL_switcher, bool, 0644);
+
+static int __init bL_switcher_init(void)
+{
+ int ret;
+
+ if (MAX_NR_CLUSTERS != 2) {
+ pr_err("%s: only dual cluster systems are supported\n", __func__);
+ return -EINVAL;
+ }
+
+ register_cpu_notifier(&bL_switcher_hotplug_notifier);
+
+ if (!no_bL_switcher) {
+ ret = bL_switcher_enable();
+ if (ret)
+ return ret;
+ }
+
+#ifdef CONFIG_SYSFS
+ ret = bL_switcher_sysfs_init();
+ if (ret)
+ pr_err("%s: unable to create sysfs entry\n", __func__);
+#endif
+
+ return 0;
+}
+
+late_initcall(bL_switcher_init);
diff --git a/arch/arm/common/bL_switcher_dummy_if.c b/arch/arm/common/bL_switcher_dummy_if.c
new file mode 100644
index 0000000..5e2dd19
--- /dev/null
+++ b/arch/arm/common/bL_switcher_dummy_if.c
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/common/bL_switcher_dummy_if.c -- b.L switcher dummy interface
+ *
+ * Created by: Nicolas Pitre, November 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * Dummy interface to user space for debugging purpose only.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <asm/uaccess.h>
+#include <asm/bL_switcher.h>
+
+static ssize_t bL_switcher_write(struct file *file, const char __user *buf,
+ size_t len, loff_t *pos)
+{
+ unsigned char val[3];
+ unsigned int cpu, cluster;
+ int ret;
+
+ pr_debug("%s\n", __func__);
+
+ if (len < 3)
+ return -EINVAL;
+
+ if (copy_from_user(val, buf, 3))
+ return -EFAULT;
+
+ /* format: <cpu#>,<cluster#> */
+ if (val[0] < '0' || val[0] > '4' ||
+ val[1] != ',' ||
+ val[2] < '0' || val[2] > '1')
+ return -EINVAL;
+
+ cpu = val[0] - '0';
+ cluster = val[2] - '0';
+ ret = bL_switch_request(cpu, cluster);
+
+ return ret ? : len;
+}
+
+static const struct file_operations bL_switcher_fops = {
+ .write = bL_switcher_write,
+ .owner = THIS_MODULE,
+};
+
+static struct miscdevice bL_switcher_device = {
+ MISC_DYNAMIC_MINOR,
+ "b.L_switcher",
+ &bL_switcher_fops
+};
+
+static int __init bL_switcher_dummy_if_init(void)
+{
+ return misc_register(&bL_switcher_device);
+}
+
+static void __exit bL_switcher_dummy_if_exit(void)
+{
+ misc_deregister(&bL_switcher_device);
+}
+
+module_init(bL_switcher_dummy_if_init);
+module_exit(bL_switcher_dummy_if_exit);
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 370236d..4a2b32f 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -27,6 +27,18 @@
sync_cache_w(&mcpm_entry_vectors[cluster][cpu]);
}
+extern unsigned long mcpm_entry_early_pokes[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER][2];
+
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+ unsigned long poke_phys_addr, unsigned long poke_val)
+{
+ unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
+ poke[0] = poke_phys_addr;
+ poke[1] = poke_val;
+ __cpuc_flush_dcache_area((void *)poke, 8);
+ outer_clean_range(__pa(poke), __pa(poke + 2));
+}
+
static const struct mcpm_platform_ops *platform_ops;
int __init mcpm_platform_register(const struct mcpm_platform_ops *ops)
diff --git a/arch/arm/common/mcpm_head.S b/arch/arm/common/mcpm_head.S
index 8178705..0decb3c 100644
--- a/arch/arm/common/mcpm_head.S
+++ b/arch/arm/common/mcpm_head.S
@@ -15,6 +15,7 @@
#include <linux/linkage.h>
#include <asm/mcpm.h>
+#include <asm/assembler.h>
#include "vlock.h"
@@ -47,6 +48,7 @@
ENTRY(mcpm_entry_point)
+ ARM_BE8(setend be)
THUMB( adr r12, BSYM(1f) )
THUMB( bx r12 )
THUMB( .thumb )
@@ -71,12 +73,19 @@
* position independent way.
*/
adr r5, 3f
- ldmia r5, {r6, r7, r8, r11}
+ ldmia r5, {r0, r6, r7, r8, r11}
+ add r0, r5, r0 @ r0 = mcpm_entry_early_pokes
add r6, r5, r6 @ r6 = mcpm_entry_vectors
ldr r7, [r5, r7] @ r7 = mcpm_power_up_setup_phys
add r8, r5, r8 @ r8 = mcpm_sync
add r11, r5, r11 @ r11 = first_man_locks
+ @ Perform an early poke, if any
+ add r0, r0, r4, lsl #3
+ ldmia r0, {r0, r1}
+ teq r0, #0
+ strne r1, [r0]
+
mov r0, #MCPM_SYNC_CLUSTER_SIZE
mla r8, r0, r10, r8 @ r8 = sync cluster base
@@ -195,7 +204,8 @@
.align 2
-3: .word mcpm_entry_vectors - .
+3: .word mcpm_entry_early_pokes - .
+ .word mcpm_entry_vectors - 3b
.word mcpm_power_up_setup_phys - 3b
.word mcpm_sync - 3b
.word first_man_locks - 3b
@@ -214,6 +224,10 @@
ENTRY(mcpm_entry_vectors)
.space 4 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+ .type mcpm_entry_early_pokes, #object
+ENTRY(mcpm_entry_early_pokes)
+ .space 8 * MAX_NR_CLUSTERS * MAX_CPUS_PER_CLUSTER
+
.type mcpm_power_up_setup_phys, #object
ENTRY(mcpm_power_up_setup_phys)
.space 4 @ set by mcpm_sync_init()
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 2e67a27..adb9aa5 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -1,6 +1,7 @@
CONFIG_EXPERIMENTAL=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BLK_DEV_INITRD=y
CONFIG_ARCH_MVEBU=y
CONFIG_MACH_ARMADA_370=y
CONFIG_ARCH_SIRF=y
@@ -22,6 +23,7 @@
CONFIG_HIGHMEM=y
CONFIG_HIGHPTE=y
CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_VFP=y
CONFIG_NEON=y
CONFIG_NET=y
@@ -46,6 +48,8 @@
CONFIG_SERIAL_SIRFSOC_CONSOLE=y
CONFIG_SERIAL_VT8500=y
CONFIG_SERIAL_VT8500_CONSOLE=y
+CONFIG_SERIAL_XILINX_PS_UART=y
+CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
CONFIG_IPMI_HANDLER=y
CONFIG_IPMI_SI=y
CONFIG_I2C=y
diff --git a/arch/arm/crypto/aes-armv4.S b/arch/arm/crypto/aes-armv4.S
index 19d6cd6..3a14ea8 100644
--- a/arch/arm/crypto/aes-armv4.S
+++ b/arch/arm/crypto/aes-armv4.S
@@ -148,7 +148,7 @@
@ const AES_KEY *key) {
.align 5
ENTRY(AES_encrypt)
- sub r3,pc,#8 @ AES_encrypt
+ adr r3,AES_encrypt
stmdb sp!,{r1,r4-r12,lr}
mov r12,r0 @ inp
mov r11,r2
@@ -381,7 +381,7 @@
.align 5
ENTRY(private_AES_set_encrypt_key)
_armv4_AES_set_encrypt_key:
- sub r3,pc,#8 @ AES_set_encrypt_key
+ adr r3,_armv4_AES_set_encrypt_key
teq r0,#0
moveq r0,#-1
beq .Labrt
@@ -843,7 +843,7 @@
@ const AES_KEY *key) {
.align 5
ENTRY(AES_decrypt)
- sub r3,pc,#8 @ AES_decrypt
+ adr r3,AES_decrypt
stmdb sp!,{r1,r4-r12,lr}
mov r12,r0 @ inp
mov r11,r2
diff --git a/arch/arm/crypto/aes_glue.c b/arch/arm/crypto/aes_glue.c
index 59f7877..e73ec2a 100644
--- a/arch/arm/crypto/aes_glue.c
+++ b/arch/arm/crypto/aes_glue.c
@@ -103,6 +103,6 @@
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm (ASM)");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 76cd976..ace4cd6 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -175,5 +175,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm (ARM)");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
MODULE_AUTHOR("David McCullough <ucdevel@gmail.com>");
diff --git a/arch/arm/include/asm/a.out-core.h b/arch/arm/include/asm/a.out-core.h
deleted file mode 100644
index 92f10cb..0000000
--- a/arch/arm/include/asm/a.out-core.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/* a.out coredump register dumper
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#ifndef _ASM_A_OUT_CORE_H
-#define _ASM_A_OUT_CORE_H
-
-#ifdef __KERNEL__
-
-#include <linux/user.h>
-#include <linux/elfcore.h>
-
-/*
- * fill in the user structure for an a.out core dump
- */
-static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
-{
- struct task_struct *tsk = current;
-
- dump->magic = CMAGIC;
- dump->start_code = tsk->mm->start_code;
- dump->start_stack = regs->ARM_sp & ~(PAGE_SIZE - 1);
-
- dump->u_tsize = (tsk->mm->end_code - tsk->mm->start_code) >> PAGE_SHIFT;
- dump->u_dsize = (tsk->mm->brk - tsk->mm->start_data + PAGE_SIZE - 1) >> PAGE_SHIFT;
- dump->u_ssize = 0;
-
- memset(dump->u_debugreg, 0, sizeof(dump->u_debugreg));
-
- if (dump->start_stack < 0x04000000)
- dump->u_ssize = (0x04000000 - dump->start_stack) >> PAGE_SHIFT;
-
- dump->regs = *regs;
- dump->u_fpvalid = dump_fpu (regs, &dump->u_fp);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_A_OUT_CORE_H */
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 7c1bfc0..4b26d14 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -17,7 +17,8 @@
* nicely work out which register we want, and chuck away the rest of
* the code. At least it does so with a recent GCC (4.6.3).
*/
-static inline void arch_timer_reg_write(const int access, const int reg, u32 val)
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
{
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
@@ -28,9 +29,7 @@
asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val));
break;
}
- }
-
- if (access == ARCH_TIMER_VIRT_ACCESS) {
+ } else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val));
@@ -44,7 +43,8 @@
isb();
}
-static inline u32 arch_timer_reg_read(const int access, const int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
{
u32 val = 0;
@@ -57,9 +57,7 @@
asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val));
break;
}
- }
-
- if (access == ARCH_TIMER_VIRT_ACCESS) {
+ } else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
case ARCH_TIMER_REG_CTRL:
asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val));
@@ -80,15 +78,6 @@
return val;
}
-static inline u64 arch_counter_get_cntpct(void)
-{
- u64 cval;
-
- isb();
- asm volatile("mrrc p15, 0, %Q0, %R0, c14" : "=r" (cval));
- return cval;
-}
-
static inline u64 arch_counter_get_cntvct(void)
{
u64 cval;
@@ -98,17 +87,43 @@
return cval;
}
-static inline void __cpuinit arch_counter_set_user_access(void)
+static inline u32 arch_timer_get_cntkctl(void)
{
u32 cntkctl;
-
asm volatile("mrc p15, 0, %0, c14, c1, 0" : "=r" (cntkctl));
+ return cntkctl;
+}
- /* disable user access to everything */
- cntkctl &= ~((3 << 8) | (7 << 0));
-
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
asm volatile("mcr p15, 0, %0, c14, c1, 0" : : "r" (cntkctl));
}
+
+static inline void __cpuinit arch_counter_set_user_access(void)
+{
+ u32 cntkctl = arch_timer_get_cntkctl();
+
+ /* Disable user access to both physical/virtual counters/timers */
+ /* Also disable virtual event stream */
+ cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+ | ARCH_TIMER_USR_VT_ACCESS_EN
+ | ARCH_TIMER_VIRT_EVT_EN
+ | ARCH_TIMER_USR_VCT_ACCESS_EN
+ | ARCH_TIMER_USR_PCT_ACCESS_EN);
+ arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+ u32 cntkctl = arch_timer_get_cntkctl();
+ cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+ /* Set the divider and enable virtual event stream */
+ cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+ | ARCH_TIMER_VIRT_EVT_EN;
+ arch_timer_set_cntkctl(cntkctl);
+ elf_hwcap |= HWCAP_EVTSTRM;
+}
+
#endif
#endif
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 05ee9ee..f0963bb 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -30,8 +30,8 @@
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
-#define pull lsr
-#define push lsl
+#define lspull lsr
+#define lspush lsl
#define get_byte_0 lsl #0
#define get_byte_1 lsr #8
#define get_byte_2 lsr #16
@@ -41,8 +41,8 @@
#define put_byte_2 lsl #16
#define put_byte_3 lsl #24
#else
-#define pull lsl
-#define push lsr
+#define lspull lsl
+#define lspush lsr
#define get_byte_0 lsr #24
#define get_byte_1 lsr #16
#define get_byte_2 lsr #8
@@ -53,6 +53,13 @@
#define put_byte_3 lsl #0
#endif
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
/*
* Data preload for architectures that support it
*/
@@ -212,9 +219,9 @@
#ifdef CONFIG_SMP
#if __LINUX_ARM_ARCH__ >= 7
.ifeqs "\mode","arm"
- ALT_SMP(dmb)
+ ALT_SMP(dmb ish)
.else
- ALT_SMP(W(dmb))
+ ALT_SMP(W(dmb) ish)
.endif
#elif __LINUX_ARM_ARCH__ == 6
ALT_SMP(mcr p15, 0, r0, c7, c10, 5) @ dmb
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index da1c77d..bccea39 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -114,7 +114,8 @@
static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
{
- unsigned long oldval, res;
+ int oldval;
+ unsigned long res;
smp_mb();
@@ -238,15 +239,15 @@
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
- u64 __aligned(8) counter;
+ long long counter;
} atomic64_t;
#define ATOMIC64_INIT(i) { (i) }
#ifdef CONFIG_ARM_LPAE
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
{
- u64 result;
+ long long result;
__asm__ __volatile__("@ atomic64_read\n"
" ldrd %0, %H0, [%1]"
@@ -257,7 +258,7 @@
return result;
}
-static inline void atomic64_set(atomic64_t *v, u64 i)
+static inline void atomic64_set(atomic64_t *v, long long i)
{
__asm__ __volatile__("@ atomic64_set\n"
" strd %2, %H2, [%1]"
@@ -266,9 +267,9 @@
);
}
#else
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
{
- u64 result;
+ long long result;
__asm__ __volatile__("@ atomic64_read\n"
" ldrexd %0, %H0, [%1]"
@@ -279,9 +280,9 @@
return result;
}
-static inline void atomic64_set(atomic64_t *v, u64 i)
+static inline void atomic64_set(atomic64_t *v, long long i)
{
- u64 tmp;
+ long long tmp;
__asm__ __volatile__("@ atomic64_set\n"
"1: ldrexd %0, %H0, [%2]\n"
@@ -294,15 +295,15 @@
}
#endif
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
{
- u64 result;
+ long long result;
unsigned long tmp;
__asm__ __volatile__("@ atomic64_add\n"
"1: ldrexd %0, %H0, [%3]\n"
-" adds %0, %0, %4\n"
-" adc %H0, %H0, %H4\n"
+" adds %Q0, %Q0, %Q4\n"
+" adc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@@ -311,17 +312,17 @@
: "cc");
}
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
{
- u64 result;
+ long long result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_add_return\n"
"1: ldrexd %0, %H0, [%3]\n"
-" adds %0, %0, %4\n"
-" adc %H0, %H0, %H4\n"
+" adds %Q0, %Q0, %Q4\n"
+" adc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@@ -334,15 +335,15 @@
return result;
}
-static inline void atomic64_sub(u64 i, atomic64_t *v)
+static inline void atomic64_sub(long long i, atomic64_t *v)
{
- u64 result;
+ long long result;
unsigned long tmp;
__asm__ __volatile__("@ atomic64_sub\n"
"1: ldrexd %0, %H0, [%3]\n"
-" subs %0, %0, %4\n"
-" sbc %H0, %H0, %H4\n"
+" subs %Q0, %Q0, %Q4\n"
+" sbc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@@ -351,17 +352,17 @@
: "cc");
}
-static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
{
- u64 result;
+ long long result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_sub_return\n"
"1: ldrexd %0, %H0, [%3]\n"
-" subs %0, %0, %4\n"
-" sbc %H0, %H0, %H4\n"
+" subs %Q0, %Q0, %Q4\n"
+" sbc %R0, %R0, %R4\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
" bne 1b"
@@ -374,9 +375,10 @@
return result;
}
-static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
+static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
+ long long new)
{
- u64 oldval;
+ long long oldval;
unsigned long res;
smp_mb();
@@ -398,9 +400,9 @@
return oldval;
}
-static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
{
- u64 result;
+ long long result;
unsigned long tmp;
smp_mb();
@@ -419,18 +421,18 @@
return result;
}
-static inline u64 atomic64_dec_if_positive(atomic64_t *v)
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
{
- u64 result;
+ long long result;
unsigned long tmp;
smp_mb();
__asm__ __volatile__("@ atomic64_dec_if_positive\n"
"1: ldrexd %0, %H0, [%3]\n"
-" subs %0, %0, #1\n"
-" sbc %H0, %H0, #0\n"
-" teq %H0, #0\n"
+" subs %Q0, %Q0, #1\n"
+" sbc %R0, %R0, #0\n"
+" teq %R0, #0\n"
" bmi 2f\n"
" strexd %1, %0, %H0, [%3]\n"
" teq %1, #0\n"
@@ -445,9 +447,9 @@
return result;
}
-static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
{
- u64 val;
+ long long val;
unsigned long tmp;
int ret = 1;
@@ -459,8 +461,8 @@
" teqeq %H0, %H5\n"
" moveq %1, #0\n"
" beq 2f\n"
-" adds %0, %0, %6\n"
-" adc %H0, %H0, %H6\n"
+" adds %Q0, %Q0, %Q6\n"
+" adc %R0, %R0, %R6\n"
" strexd %2, %0, %H0, [%4]\n"
" teq %2, #0\n"
" bne 1b\n"
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 0000000..482383b
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,83 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by: Nicolas Pitre, April 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+ bL_switch_completion_handler completer,
+ void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+ return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE 0
+#define BL_NOTIFY_POST_ENABLE 1
+#define BL_NOTIFY_PRE_DISABLE 2
+#define BL_NOTIFY_POST_DISABLE 3
+
+#ifdef CONFIG_BL_SWITCHER
+
+void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer);
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled. Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled(). These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static void bL_switch_request_detach(unsigned int cpu,
+ bL_switch_completion_handler completer) { }
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 8dcd9c7..60f15e2 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -14,27 +14,27 @@
#endif
#if __LINUX_ARM_ARCH__ >= 7
-#define isb() __asm__ __volatile__ ("isb" : : : "memory")
-#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
-#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
+#define isb(option) __asm__ __volatile__ ("isb " #option : : : "memory")
+#define dsb(option) __asm__ __volatile__ ("dsb " #option : : : "memory")
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
: : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
: : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
: : "r" (0) : "memory")
#elif defined(CONFIG_CPU_FA526)
-#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
+#define isb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
: : "r" (0) : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
: : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
#else
-#define isb() __asm__ __volatile__ ("" : : : "memory")
-#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
+#define isb(x) __asm__ __volatile__ ("" : : : "memory")
+#define dsb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
: : "r" (0) : "memory")
-#define dmb() __asm__ __volatile__ ("" : : : "memory")
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
#endif
#ifdef CONFIG_ARCH_HAS_BARRIERS
@@ -42,7 +42,7 @@
#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
#define mb() do { dsb(); outer_sync(); } while (0)
#define rmb() dsb()
-#define wmb() mb()
+#define wmb() do { dsb(st); outer_sync(); } while (0)
#else
#define mb() barrier()
#define rmb() barrier()
@@ -54,9 +54,9 @@
#define smp_rmb() barrier()
#define smp_wmb() barrier()
#else
-#define smp_mb() dmb()
-#define smp_rmb() dmb()
-#define smp_wmb() dmb()
+#define smp_mb() dmb(ish)
+#define smp_rmb() smp_mb()
+#define smp_wmb() dmb(ishst)
#endif
#define read_barrier_depends() do { } while(0)
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 7af5c6c..b274bde 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -2,6 +2,8 @@
#define _ASMARM_BUG_H
#include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
#ifdef CONFIG_BUG
@@ -12,10 +14,10 @@
*/
#ifdef CONFIG_THUMB2_KERNEL
#define BUG_INSTR_VALUE 0xde02
-#define BUG_INSTR_TYPE ".hword "
+#define BUG_INSTR(__value) __inst_thumb16(__value)
#else
#define BUG_INSTR_VALUE 0xe7f001f2
-#define BUG_INSTR_TYPE ".word "
+#define BUG_INSTR(__value) __inst_arm(__value)
#endif
@@ -33,7 +35,7 @@
#define __BUG(__file, __line, __value) \
do { \
- asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n" \
+ asm volatile("1:\t" BUG_INSTR(__value) "\n" \
".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
"2:\t.asciz " #__file "\n" \
".popsection\n" \
@@ -48,7 +50,7 @@
#define __BUG(__file, __line, __value) \
do { \
- asm volatile(BUG_INSTR_TYPE #__value); \
+ asm volatile(BUG_INSTR(__value) "\n"); \
unreachable(); \
} while (0)
#endif /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 17d0ae8..2059f01 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -212,6 +212,7 @@
static inline void __flush_icache_all(void)
{
__flush_icache_preferred();
+ dsb();
}
/*
@@ -436,4 +437,50 @@
#define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
#define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ * however some exceptions may exist. Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ * fp is preserved to the stack explicitly prior disabling the cache
+ * since adding it to the clobber list is incompatible with having
+ * CONFIG_FRAME_POINTER=y. ip is saved as well if ever r12-clobbering
+ * trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+ asm volatile( \
+ "stmfd sp!, {fp, ip} \n\t" \
+ "mrc p15, 0, r0, c1, c0, 0 @ get SCTLR \n\t" \
+ "bic r0, r0, #"__stringify(CR_C)" \n\t" \
+ "mcr p15, 0, r0, c1, c0, 0 @ set SCTLR \n\t" \
+ "isb \n\t" \
+ "bl v7_flush_dcache_"__stringify(level)" \n\t" \
+ "clrex \n\t" \
+ "mrc p15, 0, r0, c1, c0, 1 @ get ACTLR \n\t" \
+ "bic r0, r0, #(1 << 6) @ disable local coherency \n\t" \
+ "mcr p15, 0, r0, c1, c0, 1 @ set ACTLR \n\t" \
+ "isb \n\t" \
+ "dsb \n\t" \
+ "ldmfd sp!, {fp, ip}" \
+ : : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+ "r9","r10","lr","memory" )
+
#endif
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 1f3262e..cedd372 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -61,6 +61,20 @@
isb();
}
+static inline unsigned int get_auxcr(void)
+{
+ unsigned int val;
+ asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val));
+ return val;
+}
+
+static inline void set_auxcr(unsigned int val)
+{
+ asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR"
+ : : "r" (val));
+ isb();
+}
+
#ifndef CONFIG_SMP
extern void adjust_cr(unsigned long mask, unsigned long set);
#endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index dba62cb..3392fe2 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -43,15 +43,18 @@
#define ARM_CPU_IMP_ARM 0x41
#define ARM_CPU_IMP_INTEL 0x69
-#define ARM_CPU_PART_ARM1136 0xB360
-#define ARM_CPU_PART_ARM1156 0xB560
-#define ARM_CPU_PART_ARM1176 0xB760
-#define ARM_CPU_PART_ARM11MPCORE 0xB020
-#define ARM_CPU_PART_CORTEX_A8 0xC080
-#define ARM_CPU_PART_CORTEX_A9 0xC090
-#define ARM_CPU_PART_CORTEX_A5 0xC050
-#define ARM_CPU_PART_CORTEX_A15 0xC0F0
-#define ARM_CPU_PART_CORTEX_A7 0xC070
+/* ARM implemented processors */
+#define ARM_CPU_PART_ARM1136 0x4100b360
+#define ARM_CPU_PART_ARM1156 0x4100b560
+#define ARM_CPU_PART_ARM1176 0x4100b760
+#define ARM_CPU_PART_ARM11MPCORE 0x4100b020
+#define ARM_CPU_PART_CORTEX_A8 0x4100c080
+#define ARM_CPU_PART_CORTEX_A9 0x4100c090
+#define ARM_CPU_PART_CORTEX_A5 0x4100c050
+#define ARM_CPU_PART_CORTEX_A7 0x4100c070
+#define ARM_CPU_PART_CORTEX_A12 0x4100c0d0
+#define ARM_CPU_PART_CORTEX_A17 0x4100c0e0
+#define ARM_CPU_PART_CORTEX_A15 0x4100c0f0
#define ARM_CPU_XSCALE_ARCH_MASK 0xe000
#define ARM_CPU_XSCALE_ARCH_V1 0x2000
@@ -122,14 +125,24 @@
return (read_cpuid_id() & 0xFF000000) >> 24;
}
-static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
+/*
+ * The CPU part number is meaningless without referring to the CPU
+ * implementer: implementers are free to define their own part numbers
+ * which are permitted to clash with other implementer part numbers.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_part(void)
+{
+ return read_cpuid_id() & 0xff00fff0;
+}
+
+static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)
{
return read_cpuid_id() & 0xFFF0;
}
static inline unsigned int __attribute_const__ xscale_cpu_arch_version(void)
{
- return read_cpuid_part_number() & ARM_CPU_XSCALE_ARCH_MASK;
+ return read_cpuid_id() & ARM_CPU_XSCALE_ARCH_MASK;
}
static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index fe92ccf..a66061a 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -156,7 +156,7 @@
/* Select the best insn combination to perform the */ \
/* actual __m * __n / (__p << 64) operation. */ \
if (!__c) { \
- asm ( "umull %Q0, %R0, %1, %Q2\n\t" \
+ asm ( "umull %Q0, %R0, %Q1, %Q2\n\t" \
"mov %Q0, #0" \
: "=&r" (__res) \
: "r" (__m), "r" (__n) \
diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h
index 3ed37b4..4f8e9e5 100644
--- a/arch/arm/include/asm/dma-contiguous.h
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -2,10 +2,9 @@
#define ASMARM_DMA_CONTIGUOUS_H
#ifdef __KERNEL__
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
#include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 38050b1..051b726 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -19,8 +19,6 @@
typedef struct user_fp elf_fpregset_t;
-#define EM_ARM 40
-
#define EF_ARM_EABI_MASK 0xff000000
#define EF_ARM_EABI_UNKNOWN 0x00000000
#define EF_ARM_EABI_VER1 0x01000000
@@ -116,7 +114,7 @@
the loader. We need to make sure that it is out of the way of the program
that it will "exec", and that there is sufficient room for the brk. */
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
/* When the program starts, a1 contains a pointer to a function to be
registered with atexit, as per the SVR4 ABI. A value of 0 means we
@@ -130,4 +128,10 @@
extern unsigned long arch_randomize_brk(struct mm_struct *mm);
#define arch_randomize_brk arch_randomize_brk
+#ifdef CONFIG_MMU
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+struct linux_binprm;
+int arch_setup_additional_pages(struct linux_binprm *, int);
+#endif
+
#endif
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index f89515a..39eb16b 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,15 +52,7 @@
#endif
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
#endif /* ifndef __ASSEMBLY__ */
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index e42cf59..2aff798 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -3,11 +3,6 @@
#ifdef __KERNEL__
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
#include <linux/futex.h>
#include <linux/uaccess.h>
#include <asm/errno.h>
@@ -164,6 +159,5 @@
return ret;
}
-#endif /* !(CPU_USE_DOMAINS && SMP) */
#endif /* __KERNEL__ */
#endif /* _ASM_ARM_FUTEX_H */
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 2740c2a..3d7351c 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
-#define NR_IPI 6
+#define NR_IPI 7
typedef struct {
unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
deleted file mode 100644
index 0cf7a6b..0000000
--- a/arch/arm/include/asm/hardware/coresight.h
+++ /dev/null
@@ -1,157 +0,0 @@
-/*
- * linux/arch/arm/include/asm/hardware/coresight.h
- *
- * CoreSight components' registers
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_HARDWARE_CORESIGHT_H
-#define __ASM_HARDWARE_CORESIGHT_H
-
-#define TRACER_ACCESSED_BIT 0
-#define TRACER_RUNNING_BIT 1
-#define TRACER_CYCLE_ACC_BIT 2
-#define TRACER_ACCESSED BIT(TRACER_ACCESSED_BIT)
-#define TRACER_RUNNING BIT(TRACER_RUNNING_BIT)
-#define TRACER_CYCLE_ACC BIT(TRACER_CYCLE_ACC_BIT)
-
-#define TRACER_TIMEOUT 10000
-
-#define etm_writel(t, v, x) \
- (__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
-
-/* CoreSight Management Registers */
-#define CSMR_LOCKACCESS 0xfb0
-#define CSMR_LOCKSTATUS 0xfb4
-#define CSMR_AUTHSTATUS 0xfb8
-#define CSMR_DEVID 0xfc8
-#define CSMR_DEVTYPE 0xfcc
-/* CoreSight Component Registers */
-#define CSCR_CLASS 0xff4
-
-#define CS_LAR_KEY 0xc5acce55
-
-/* ETM control register, "ETM Architecture", 3.3.1 */
-#define ETMR_CTRL 0
-#define ETMCTRL_POWERDOWN 1
-#define ETMCTRL_PROGRAM (1 << 10)
-#define ETMCTRL_PORTSEL (1 << 11)
-#define ETMCTRL_DO_CONTEXTID (3 << 14)
-#define ETMCTRL_PORTMASK1 (7 << 4)
-#define ETMCTRL_PORTMASK2 (1 << 21)
-#define ETMCTRL_PORTMASK (ETMCTRL_PORTMASK1 | ETMCTRL_PORTMASK2)
-#define ETMCTRL_PORTSIZE(x) ((((x) & 7) << 4) | (!!((x) & 8)) << 21)
-#define ETMCTRL_DO_CPRT (1 << 1)
-#define ETMCTRL_DATAMASK (3 << 2)
-#define ETMCTRL_DATA_DO_DATA (1 << 2)
-#define ETMCTRL_DATA_DO_ADDR (1 << 3)
-#define ETMCTRL_DATA_DO_BOTH (ETMCTRL_DATA_DO_DATA | ETMCTRL_DATA_DO_ADDR)
-#define ETMCTRL_BRANCH_OUTPUT (1 << 8)
-#define ETMCTRL_CYCLEACCURATE (1 << 12)
-
-/* ETM configuration code register */
-#define ETMR_CONFCODE (0x04)
-
-/* ETM trace start/stop resource control register */
-#define ETMR_TRACESSCTRL (0x18)
-
-/* ETM trigger event register */
-#define ETMR_TRIGEVT (0x08)
-
-/* address access type register bits, "ETM architecture",
- * table 3-27 */
-/* - access type */
-#define ETMAAT_IFETCH 0
-#define ETMAAT_IEXEC 1
-#define ETMAAT_IEXECPASS 2
-#define ETMAAT_IEXECFAIL 3
-#define ETMAAT_DLOADSTORE 4
-#define ETMAAT_DLOAD 5
-#define ETMAAT_DSTORE 6
-/* - comparison access size */
-#define ETMAAT_JAVA (0 << 3)
-#define ETMAAT_THUMB (1 << 3)
-#define ETMAAT_ARM (3 << 3)
-/* - data value comparison control */
-#define ETMAAT_NOVALCMP (0 << 5)
-#define ETMAAT_VALMATCH (1 << 5)
-#define ETMAAT_VALNOMATCH (3 << 5)
-/* - exact match */
-#define ETMAAT_EXACTMATCH (1 << 7)
-/* - context id comparator control */
-#define ETMAAT_IGNCONTEXTID (0 << 8)
-#define ETMAAT_VALUE1 (1 << 8)
-#define ETMAAT_VALUE2 (2 << 8)
-#define ETMAAT_VALUE3 (3 << 8)
-/* - security level control */
-#define ETMAAT_IGNSECURITY (0 << 10)
-#define ETMAAT_NSONLY (1 << 10)
-#define ETMAAT_SONLY (2 << 10)
-
-#define ETMR_COMP_VAL(x) (0x40 + (x) * 4)
-#define ETMR_COMP_ACC_TYPE(x) (0x80 + (x) * 4)
-
-/* ETM status register, "ETM Architecture", 3.3.2 */
-#define ETMR_STATUS (0x10)
-#define ETMST_OVERFLOW BIT(0)
-#define ETMST_PROGBIT BIT(1)
-#define ETMST_STARTSTOP BIT(2)
-#define ETMST_TRIGGER BIT(3)
-
-#define etm_progbit(t) (etm_readl((t), ETMR_STATUS) & ETMST_PROGBIT)
-#define etm_started(t) (etm_readl((t), ETMR_STATUS) & ETMST_STARTSTOP)
-#define etm_triggered(t) (etm_readl((t), ETMR_STATUS) & ETMST_TRIGGER)
-
-#define ETMR_TRACEENCTRL2 0x1c
-#define ETMR_TRACEENCTRL 0x24
-#define ETMTE_INCLEXCL BIT(24)
-#define ETMR_TRACEENEVT 0x20
-#define ETMCTRL_OPTS (ETMCTRL_DO_CPRT | \
- ETMCTRL_DATA_DO_ADDR | \
- ETMCTRL_BRANCH_OUTPUT | \
- ETMCTRL_DO_CONTEXTID)
-
-/* ETM management registers, "ETM Architecture", 3.5.24 */
-#define ETMMR_OSLAR 0x300
-#define ETMMR_OSLSR 0x304
-#define ETMMR_OSSRR 0x308
-#define ETMMR_PDSR 0x314
-
-/* ETB registers, "CoreSight Components TRM", 9.3 */
-#define ETBR_DEPTH 0x04
-#define ETBR_STATUS 0x0c
-#define ETBR_READMEM 0x10
-#define ETBR_READADDR 0x14
-#define ETBR_WRITEADDR 0x18
-#define ETBR_TRIGGERCOUNT 0x1c
-#define ETBR_CTRL 0x20
-#define ETBR_FORMATTERCTRL 0x304
-#define ETBFF_ENFTC 1
-#define ETBFF_ENFCONT BIT(1)
-#define ETBFF_FONFLIN BIT(4)
-#define ETBFF_MANUAL_FLUSH BIT(6)
-#define ETBFF_TRIGIN BIT(8)
-#define ETBFF_TRIGEVT BIT(9)
-#define ETBFF_TRIGFL BIT(10)
-
-#define etb_writel(t, v, x) \
- (__raw_writel((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
-
-#define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etm_unlock(t) \
- do { etm_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#define etb_lock(t) do { etb_writel((t), 0, CSMR_LOCKACCESS); } while (0)
-#define etb_unlock(t) \
- do { etb_writel((t), CS_LAR_KEY, CSMR_LOCKACCESS); } while (0)
-
-#endif /* __ASM_HARDWARE_CORESIGHT_H */
-
diff --git a/arch/arm/include/asm/hardware/cp14.h b/arch/arm/include/asm/hardware/cp14.h
new file mode 100644
index 0000000..61576dc
--- /dev/null
+++ b/arch/arm/include/asm/hardware/cp14.h
@@ -0,0 +1,542 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __ASM_HARDWARE_CP14_H
+#define __ASM_HARDWARE_CP14_H
+
+#include <linux/types.h>
+
+/* Accessors for CP14 registers */
+#define dbg_read(reg) RCP14_##reg()
+#define dbg_write(val, reg) WCP14_##reg(val)
+#define etm_read(reg) RCP14_##reg()
+#define etm_write(val, reg) WCP14_##reg(val)
+
+/* MRC14 and MCR14 */
+#define MRC14(op1, crn, crm, op2) \
+({ \
+u32 val; \
+asm volatile("mrc p14, "#op1", %0, "#crn", "#crm", "#op2 : "=r" (val)); \
+val; \
+})
+
+#define MCR14(val, op1, crn, crm, op2) \
+({ \
+asm volatile("mcr p14, "#op1", %0, "#crn", "#crm", "#op2 : : "r" (val));\
+})
+
+/*
+ * Debug Registers
+ *
+ * Available only in DBGv7
+ * DBGECR, DBGDSCCR, DBGDSMCR, DBGDRCR
+ *
+ * Available only in DBGv7.1
+ * DBGBXVRm, DBGOSDLR, DBGDEVID2, DBGDEVID1
+ *
+ * Read only
+ * DBGDIDR, DBGDSCRint, DBGDTRRXint, DBGDRAR, DBGOSLSR, DBGOSSRR, DBGPRSR,
+ * DBGPRSR, DBGDSAR, DBGAUTHSTATUS, DBGDEVID2, DBGDEVID1, DBGDEVID
+ *
+ * Write only
+ * DBGDTRTXint, DBGOSLAR
+ */
+#define RCP14_DBGDIDR() MRC14(0, c0, c0, 0)
+#define RCP14_DBGDSCRint() MRC14(0, c0, c1, 0)
+#define RCP14_DBGDTRRXint() MRC14(0, c0, c5, 0)
+#define RCP14_DBGWFAR() MRC14(0, c0, c6, 0)
+#define RCP14_DBGVCR() MRC14(0, c0, c7, 0)
+#define RCP14_DBGECR() MRC14(0, c0, c9, 0)
+#define RCP14_DBGDSCCR() MRC14(0, c0, c10, 0)
+#define RCP14_DBGDSMCR() MRC14(0, c0, c11, 0)
+#define RCP14_DBGDTRRXext() MRC14(0, c0, c0, 2)
+#define RCP14_DBGDSCRext() MRC14(0, c0, c2, 2)
+#define RCP14_DBGDTRTXext() MRC14(0, c0, c3, 2)
+#define RCP14_DBGDRCR() MRC14(0, c0, c4, 2)
+#define RCP14_DBGBVR0() MRC14(0, c0, c0, 4)
+#define RCP14_DBGBVR1() MRC14(0, c0, c1, 4)
+#define RCP14_DBGBVR2() MRC14(0, c0, c2, 4)
+#define RCP14_DBGBVR3() MRC14(0, c0, c3, 4)
+#define RCP14_DBGBVR4() MRC14(0, c0, c4, 4)
+#define RCP14_DBGBVR5() MRC14(0, c0, c5, 4)
+#define RCP14_DBGBVR6() MRC14(0, c0, c6, 4)
+#define RCP14_DBGBVR7() MRC14(0, c0, c7, 4)
+#define RCP14_DBGBVR8() MRC14(0, c0, c8, 4)
+#define RCP14_DBGBVR9() MRC14(0, c0, c9, 4)
+#define RCP14_DBGBVR10() MRC14(0, c0, c10, 4)
+#define RCP14_DBGBVR11() MRC14(0, c0, c11, 4)
+#define RCP14_DBGBVR12() MRC14(0, c0, c12, 4)
+#define RCP14_DBGBVR13() MRC14(0, c0, c13, 4)
+#define RCP14_DBGBVR14() MRC14(0, c0, c14, 4)
+#define RCP14_DBGBVR15() MRC14(0, c0, c15, 4)
+#define RCP14_DBGBCR0() MRC14(0, c0, c0, 5)
+#define RCP14_DBGBCR1() MRC14(0, c0, c1, 5)
+#define RCP14_DBGBCR2() MRC14(0, c0, c2, 5)
+#define RCP14_DBGBCR3() MRC14(0, c0, c3, 5)
+#define RCP14_DBGBCR4() MRC14(0, c0, c4, 5)
+#define RCP14_DBGBCR5() MRC14(0, c0, c5, 5)
+#define RCP14_DBGBCR6() MRC14(0, c0, c6, 5)
+#define RCP14_DBGBCR7() MRC14(0, c0, c7, 5)
+#define RCP14_DBGBCR8() MRC14(0, c0, c8, 5)
+#define RCP14_DBGBCR9() MRC14(0, c0, c9, 5)
+#define RCP14_DBGBCR10() MRC14(0, c0, c10, 5)
+#define RCP14_DBGBCR11() MRC14(0, c0, c11, 5)
+#define RCP14_DBGBCR12() MRC14(0, c0, c12, 5)
+#define RCP14_DBGBCR13() MRC14(0, c0, c13, 5)
+#define RCP14_DBGBCR14() MRC14(0, c0, c14, 5)
+#define RCP14_DBGBCR15() MRC14(0, c0, c15, 5)
+#define RCP14_DBGWVR0() MRC14(0, c0, c0, 6)
+#define RCP14_DBGWVR1() MRC14(0, c0, c1, 6)
+#define RCP14_DBGWVR2() MRC14(0, c0, c2, 6)
+#define RCP14_DBGWVR3() MRC14(0, c0, c3, 6)
+#define RCP14_DBGWVR4() MRC14(0, c0, c4, 6)
+#define RCP14_DBGWVR5() MRC14(0, c0, c5, 6)
+#define RCP14_DBGWVR6() MRC14(0, c0, c6, 6)
+#define RCP14_DBGWVR7() MRC14(0, c0, c7, 6)
+#define RCP14_DBGWVR8() MRC14(0, c0, c8, 6)
+#define RCP14_DBGWVR9() MRC14(0, c0, c9, 6)
+#define RCP14_DBGWVR10() MRC14(0, c0, c10, 6)
+#define RCP14_DBGWVR11() MRC14(0, c0, c11, 6)
+#define RCP14_DBGWVR12() MRC14(0, c0, c12, 6)
+#define RCP14_DBGWVR13() MRC14(0, c0, c13, 6)
+#define RCP14_DBGWVR14() MRC14(0, c0, c14, 6)
+#define RCP14_DBGWVR15() MRC14(0, c0, c15, 6)
+#define RCP14_DBGWCR0() MRC14(0, c0, c0, 7)
+#define RCP14_DBGWCR1() MRC14(0, c0, c1, 7)
+#define RCP14_DBGWCR2() MRC14(0, c0, c2, 7)
+#define RCP14_DBGWCR3() MRC14(0, c0, c3, 7)
+#define RCP14_DBGWCR4() MRC14(0, c0, c4, 7)
+#define RCP14_DBGWCR5() MRC14(0, c0, c5, 7)
+#define RCP14_DBGWCR6() MRC14(0, c0, c6, 7)
+#define RCP14_DBGWCR7() MRC14(0, c0, c7, 7)
+#define RCP14_DBGWCR8() MRC14(0, c0, c8, 7)
+#define RCP14_DBGWCR9() MRC14(0, c0, c9, 7)
+#define RCP14_DBGWCR10() MRC14(0, c0, c10, 7)
+#define RCP14_DBGWCR11() MRC14(0, c0, c11, 7)
+#define RCP14_DBGWCR12() MRC14(0, c0, c12, 7)
+#define RCP14_DBGWCR13() MRC14(0, c0, c13, 7)
+#define RCP14_DBGWCR14() MRC14(0, c0, c14, 7)
+#define RCP14_DBGWCR15() MRC14(0, c0, c15, 7)
+#define RCP14_DBGDRAR() MRC14(0, c1, c0, 0)
+#define RCP14_DBGBXVR0() MRC14(0, c1, c0, 1)
+#define RCP14_DBGBXVR1() MRC14(0, c1, c1, 1)
+#define RCP14_DBGBXVR2() MRC14(0, c1, c2, 1)
+#define RCP14_DBGBXVR3() MRC14(0, c1, c3, 1)
+#define RCP14_DBGBXVR4() MRC14(0, c1, c4, 1)
+#define RCP14_DBGBXVR5() MRC14(0, c1, c5, 1)
+#define RCP14_DBGBXVR6() MRC14(0, c1, c6, 1)
+#define RCP14_DBGBXVR7() MRC14(0, c1, c7, 1)
+#define RCP14_DBGBXVR8() MRC14(0, c1, c8, 1)
+#define RCP14_DBGBXVR9() MRC14(0, c1, c9, 1)
+#define RCP14_DBGBXVR10() MRC14(0, c1, c10, 1)
+#define RCP14_DBGBXVR11() MRC14(0, c1, c11, 1)
+#define RCP14_DBGBXVR12() MRC14(0, c1, c12, 1)
+#define RCP14_DBGBXVR13() MRC14(0, c1, c13, 1)
+#define RCP14_DBGBXVR14() MRC14(0, c1, c14, 1)
+#define RCP14_DBGBXVR15() MRC14(0, c1, c15, 1)
+#define RCP14_DBGOSLSR() MRC14(0, c1, c1, 4)
+#define RCP14_DBGOSSRR() MRC14(0, c1, c2, 4)
+#define RCP14_DBGOSDLR() MRC14(0, c1, c3, 4)
+#define RCP14_DBGPRCR() MRC14(0, c1, c4, 4)
+#define RCP14_DBGPRSR() MRC14(0, c1, c5, 4)
+#define RCP14_DBGDSAR() MRC14(0, c2, c0, 0)
+#define RCP14_DBGITCTRL() MRC14(0, c7, c0, 4)
+#define RCP14_DBGCLAIMSET() MRC14(0, c7, c8, 6)
+#define RCP14_DBGCLAIMCLR() MRC14(0, c7, c9, 6)
+#define RCP14_DBGAUTHSTATUS() MRC14(0, c7, c14, 6)
+#define RCP14_DBGDEVID2() MRC14(0, c7, c0, 7)
+#define RCP14_DBGDEVID1() MRC14(0, c7, c1, 7)
+#define RCP14_DBGDEVID() MRC14(0, c7, c2, 7)
+
+#define WCP14_DBGDTRTXint(val) MCR14(val, 0, c0, c5, 0)
+#define WCP14_DBGWFAR(val) MCR14(val, 0, c0, c6, 0)
+#define WCP14_DBGVCR(val) MCR14(val, 0, c0, c7, 0)
+#define WCP14_DBGECR(val) MCR14(val, 0, c0, c9, 0)
+#define WCP14_DBGDSCCR(val) MCR14(val, 0, c0, c10, 0)
+#define WCP14_DBGDSMCR(val) MCR14(val, 0, c0, c11, 0)
+#define WCP14_DBGDTRRXext(val) MCR14(val, 0, c0, c0, 2)
+#define WCP14_DBGDSCRext(val) MCR14(val, 0, c0, c2, 2)
+#define WCP14_DBGDTRTXext(val) MCR14(val, 0, c0, c3, 2)
+#define WCP14_DBGDRCR(val) MCR14(val, 0, c0, c4, 2)
+#define WCP14_DBGBVR0(val) MCR14(val, 0, c0, c0, 4)
+#define WCP14_DBGBVR1(val) MCR14(val, 0, c0, c1, 4)
+#define WCP14_DBGBVR2(val) MCR14(val, 0, c0, c2, 4)
+#define WCP14_DBGBVR3(val) MCR14(val, 0, c0, c3, 4)
+#define WCP14_DBGBVR4(val) MCR14(val, 0, c0, c4, 4)
+#define WCP14_DBGBVR5(val) MCR14(val, 0, c0, c5, 4)
+#define WCP14_DBGBVR6(val) MCR14(val, 0, c0, c6, 4)
+#define WCP14_DBGBVR7(val) MCR14(val, 0, c0, c7, 4)
+#define WCP14_DBGBVR8(val) MCR14(val, 0, c0, c8, 4)
+#define WCP14_DBGBVR9(val) MCR14(val, 0, c0, c9, 4)
+#define WCP14_DBGBVR10(val) MCR14(val, 0, c0, c10, 4)
+#define WCP14_DBGBVR11(val) MCR14(val, 0, c0, c11, 4)
+#define WCP14_DBGBVR12(val) MCR14(val, 0, c0, c12, 4)
+#define WCP14_DBGBVR13(val) MCR14(val, 0, c0, c13, 4)
+#define WCP14_DBGBVR14(val) MCR14(val, 0, c0, c14, 4)
+#define WCP14_DBGBVR15(val) MCR14(val, 0, c0, c15, 4)
+#define WCP14_DBGBCR0(val) MCR14(val, 0, c0, c0, 5)
+#define WCP14_DBGBCR1(val) MCR14(val, 0, c0, c1, 5)
+#define WCP14_DBGBCR2(val) MCR14(val, 0, c0, c2, 5)
+#define WCP14_DBGBCR3(val) MCR14(val, 0, c0, c3, 5)
+#define WCP14_DBGBCR4(val) MCR14(val, 0, c0, c4, 5)
+#define WCP14_DBGBCR5(val) MCR14(val, 0, c0, c5, 5)
+#define WCP14_DBGBCR6(val) MCR14(val, 0, c0, c6, 5)
+#define WCP14_DBGBCR7(val) MCR14(val, 0, c0, c7, 5)
+#define WCP14_DBGBCR8(val) MCR14(val, 0, c0, c8, 5)
+#define WCP14_DBGBCR9(val) MCR14(val, 0, c0, c9, 5)
+#define WCP14_DBGBCR10(val) MCR14(val, 0, c0, c10, 5)
+#define WCP14_DBGBCR11(val) MCR14(val, 0, c0, c11, 5)
+#define WCP14_DBGBCR12(val) MCR14(val, 0, c0, c12, 5)
+#define WCP14_DBGBCR13(val) MCR14(val, 0, c0, c13, 5)
+#define WCP14_DBGBCR14(val) MCR14(val, 0, c0, c14, 5)
+#define WCP14_DBGBCR15(val) MCR14(val, 0, c0, c15, 5)
+#define WCP14_DBGWVR0(val) MCR14(val, 0, c0, c0, 6)
+#define WCP14_DBGWVR1(val) MCR14(val, 0, c0, c1, 6)
+#define WCP14_DBGWVR2(val) MCR14(val, 0, c0, c2, 6)
+#define WCP14_DBGWVR3(val) MCR14(val, 0, c0, c3, 6)
+#define WCP14_DBGWVR4(val) MCR14(val, 0, c0, c4, 6)
+#define WCP14_DBGWVR5(val) MCR14(val, 0, c0, c5, 6)
+#define WCP14_DBGWVR6(val) MCR14(val, 0, c0, c6, 6)
+#define WCP14_DBGWVR7(val) MCR14(val, 0, c0, c7, 6)
+#define WCP14_DBGWVR8(val) MCR14(val, 0, c0, c8, 6)
+#define WCP14_DBGWVR9(val) MCR14(val, 0, c0, c9, 6)
+#define WCP14_DBGWVR10(val) MCR14(val, 0, c0, c10, 6)
+#define WCP14_DBGWVR11(val) MCR14(val, 0, c0, c11, 6)
+#define WCP14_DBGWVR12(val) MCR14(val, 0, c0, c12, 6)
+#define WCP14_DBGWVR13(val) MCR14(val, 0, c0, c13, 6)
+#define WCP14_DBGWVR14(val) MCR14(val, 0, c0, c14, 6)
+#define WCP14_DBGWVR15(val) MCR14(val, 0, c0, c15, 6)
+#define WCP14_DBGWCR0(val) MCR14(val, 0, c0, c0, 7)
+#define WCP14_DBGWCR1(val) MCR14(val, 0, c0, c1, 7)
+#define WCP14_DBGWCR2(val) MCR14(val, 0, c0, c2, 7)
+#define WCP14_DBGWCR3(val) MCR14(val, 0, c0, c3, 7)
+#define WCP14_DBGWCR4(val) MCR14(val, 0, c0, c4, 7)
+#define WCP14_DBGWCR5(val) MCR14(val, 0, c0, c5, 7)
+#define WCP14_DBGWCR6(val) MCR14(val, 0, c0, c6, 7)
+#define WCP14_DBGWCR7(val) MCR14(val, 0, c0, c7, 7)
+#define WCP14_DBGWCR8(val) MCR14(val, 0, c0, c8, 7)
+#define WCP14_DBGWCR9(val) MCR14(val, 0, c0, c9, 7)
+#define WCP14_DBGWCR10(val) MCR14(val, 0, c0, c10, 7)
+#define WCP14_DBGWCR11(val) MCR14(val, 0, c0, c11, 7)
+#define WCP14_DBGWCR12(val) MCR14(val, 0, c0, c12, 7)
+#define WCP14_DBGWCR13(val) MCR14(val, 0, c0, c13, 7)
+#define WCP14_DBGWCR14(val) MCR14(val, 0, c0, c14, 7)
+#define WCP14_DBGWCR15(val) MCR14(val, 0, c0, c15, 7)
+#define WCP14_DBGBXVR0(val) MCR14(val, 0, c1, c0, 1)
+#define WCP14_DBGBXVR1(val) MCR14(val, 0, c1, c1, 1)
+#define WCP14_DBGBXVR2(val) MCR14(val, 0, c1, c2, 1)
+#define WCP14_DBGBXVR3(val) MCR14(val, 0, c1, c3, 1)
+#define WCP14_DBGBXVR4(val) MCR14(val, 0, c1, c4, 1)
+#define WCP14_DBGBXVR5(val) MCR14(val, 0, c1, c5, 1)
+#define WCP14_DBGBXVR6(val) MCR14(val, 0, c1, c6, 1)
+#define WCP14_DBGBXVR7(val) MCR14(val, 0, c1, c7, 1)
+#define WCP14_DBGBXVR8(val) MCR14(val, 0, c1, c8, 1)
+#define WCP14_DBGBXVR9(val) MCR14(val, 0, c1, c9, 1)
+#define WCP14_DBGBXVR10(val) MCR14(val, 0, c1, c10, 1)
+#define WCP14_DBGBXVR11(val) MCR14(val, 0, c1, c11, 1)
+#define WCP14_DBGBXVR12(val) MCR14(val, 0, c1, c12, 1)
+#define WCP14_DBGBXVR13(val) MCR14(val, 0, c1, c13, 1)
+#define WCP14_DBGBXVR14(val) MCR14(val, 0, c1, c14, 1)
+#define WCP14_DBGBXVR15(val) MCR14(val, 0, c1, c15, 1)
+#define WCP14_DBGOSLAR(val) MCR14(val, 0, c1, c0, 4)
+#define WCP14_DBGOSSRR(val) MCR14(val, 0, c1, c2, 4)
+#define WCP14_DBGOSDLR(val) MCR14(val, 0, c1, c3, 4)
+#define WCP14_DBGPRCR(val) MCR14(val, 0, c1, c4, 4)
+#define WCP14_DBGITCTRL(val) MCR14(val, 0, c7, c0, 4)
+#define WCP14_DBGCLAIMSET(val) MCR14(val, 0, c7, c8, 6)
+#define WCP14_DBGCLAIMCLR(val) MCR14(val, 0, c7, c9, 6)
+
+/*
+ * ETM Registers
+ *
+ * Available only in ETMv3.3, 3.4, 3.5
+ * ETMASICCR, ETMTECR2, ETMFFRR, ETMVDEVR, ETMVDCR1, ETMVDCR2, ETMVDCR3,
+ * ETMDCVRn, ETMDCMRn
+ *
+ * Available only in ETMv3.5 as read only
+ * ETMIDR2
+ *
+ * Available only in ETMv3.5, PFTv1.0, 1.1
+ * ETMTSEVR, ETMVMIDCVR, ETMPDCR
+ *
+ * Read only
+ * ETMCCR, ETMSCR, ETMIDR, ETMCCER, ETMOSLSR
+ * ETMLSR, ETMAUTHSTATUS, ETMDEVID, ETMDEVTYPE, ETMPIDR4, ETMPIDR5, ETMPIDR6,
+ * ETMPIDR7, ETMPIDR0, ETMPIDR1, ETMPIDR2, ETMPIDR2, ETMPIDR3, ETMCIDR0,
+ * ETMCIDR1, ETMCIDR2, ETMCIDR3
+ *
+ * Write only
+ * ETMOSLAR, ETMLAR
+ * Note: ETMCCER[11] controls WO nature of certain regs. Refer ETM arch spec.
+ */
+#define RCP14_ETMCR() MRC14(1, c0, c0, 0)
+#define RCP14_ETMCCR() MRC14(1, c0, c1, 0)
+#define RCP14_ETMTRIGGER() MRC14(1, c0, c2, 0)
+#define RCP14_ETMASICCR() MRC14(1, c0, c3, 0)
+#define RCP14_ETMSR() MRC14(1, c0, c4, 0)
+#define RCP14_ETMSCR() MRC14(1, c0, c5, 0)
+#define RCP14_ETMTSSCR() MRC14(1, c0, c6, 0)
+#define RCP14_ETMTECR2() MRC14(1, c0, c7, 0)
+#define RCP14_ETMTEEVR() MRC14(1, c0, c8, 0)
+#define RCP14_ETMTECR1() MRC14(1, c0, c9, 0)
+#define RCP14_ETMFFRR() MRC14(1, c0, c10, 0)
+#define RCP14_ETMFFLR() MRC14(1, c0, c11, 0)
+#define RCP14_ETMVDEVR() MRC14(1, c0, c12, 0)
+#define RCP14_ETMVDCR1() MRC14(1, c0, c13, 0)
+#define RCP14_ETMVDCR2() MRC14(1, c0, c14, 0)
+#define RCP14_ETMVDCR3() MRC14(1, c0, c15, 0)
+#define RCP14_ETMACVR0() MRC14(1, c0, c0, 1)
+#define RCP14_ETMACVR1() MRC14(1, c0, c1, 1)
+#define RCP14_ETMACVR2() MRC14(1, c0, c2, 1)
+#define RCP14_ETMACVR3() MRC14(1, c0, c3, 1)
+#define RCP14_ETMACVR4() MRC14(1, c0, c4, 1)
+#define RCP14_ETMACVR5() MRC14(1, c0, c5, 1)
+#define RCP14_ETMACVR6() MRC14(1, c0, c6, 1)
+#define RCP14_ETMACVR7() MRC14(1, c0, c7, 1)
+#define RCP14_ETMACVR8() MRC14(1, c0, c8, 1)
+#define RCP14_ETMACVR9() MRC14(1, c0, c9, 1)
+#define RCP14_ETMACVR10() MRC14(1, c0, c10, 1)
+#define RCP14_ETMACVR11() MRC14(1, c0, c11, 1)
+#define RCP14_ETMACVR12() MRC14(1, c0, c12, 1)
+#define RCP14_ETMACVR13() MRC14(1, c0, c13, 1)
+#define RCP14_ETMACVR14() MRC14(1, c0, c14, 1)
+#define RCP14_ETMACVR15() MRC14(1, c0, c15, 1)
+#define RCP14_ETMACTR0() MRC14(1, c0, c0, 2)
+#define RCP14_ETMACTR1() MRC14(1, c0, c1, 2)
+#define RCP14_ETMACTR2() MRC14(1, c0, c2, 2)
+#define RCP14_ETMACTR3() MRC14(1, c0, c3, 2)
+#define RCP14_ETMACTR4() MRC14(1, c0, c4, 2)
+#define RCP14_ETMACTR5() MRC14(1, c0, c5, 2)
+#define RCP14_ETMACTR6() MRC14(1, c0, c6, 2)
+#define RCP14_ETMACTR7() MRC14(1, c0, c7, 2)
+#define RCP14_ETMACTR8() MRC14(1, c0, c8, 2)
+#define RCP14_ETMACTR9() MRC14(1, c0, c9, 2)
+#define RCP14_ETMACTR10() MRC14(1, c0, c10, 2)
+#define RCP14_ETMACTR11() MRC14(1, c0, c11, 2)
+#define RCP14_ETMACTR12() MRC14(1, c0, c12, 2)
+#define RCP14_ETMACTR13() MRC14(1, c0, c13, 2)
+#define RCP14_ETMACTR14() MRC14(1, c0, c14, 2)
+#define RCP14_ETMACTR15() MRC14(1, c0, c15, 2)
+#define RCP14_ETMDCVR0() MRC14(1, c0, c0, 3)
+#define RCP14_ETMDCVR2() MRC14(1, c0, c2, 3)
+#define RCP14_ETMDCVR4() MRC14(1, c0, c4, 3)
+#define RCP14_ETMDCVR6() MRC14(1, c0, c6, 3)
+#define RCP14_ETMDCVR8() MRC14(1, c0, c8, 3)
+#define RCP14_ETMDCVR10() MRC14(1, c0, c10, 3)
+#define RCP14_ETMDCVR12() MRC14(1, c0, c12, 3)
+#define RCP14_ETMDCVR14() MRC14(1, c0, c14, 3)
+#define RCP14_ETMDCMR0() MRC14(1, c0, c0, 4)
+#define RCP14_ETMDCMR2() MRC14(1, c0, c2, 4)
+#define RCP14_ETMDCMR4() MRC14(1, c0, c4, 4)
+#define RCP14_ETMDCMR6() MRC14(1, c0, c6, 4)
+#define RCP14_ETMDCMR8() MRC14(1, c0, c8, 4)
+#define RCP14_ETMDCMR10() MRC14(1, c0, c10, 4)
+#define RCP14_ETMDCMR12() MRC14(1, c0, c12, 4)
+#define RCP14_ETMDCMR14() MRC14(1, c0, c14, 4)
+#define RCP14_ETMCNTRLDVR0() MRC14(1, c0, c0, 5)
+#define RCP14_ETMCNTRLDVR1() MRC14(1, c0, c1, 5)
+#define RCP14_ETMCNTRLDVR2() MRC14(1, c0, c2, 5)
+#define RCP14_ETMCNTRLDVR3() MRC14(1, c0, c3, 5)
+#define RCP14_ETMCNTENR0() MRC14(1, c0, c4, 5)
+#define RCP14_ETMCNTENR1() MRC14(1, c0, c5, 5)
+#define RCP14_ETMCNTENR2() MRC14(1, c0, c6, 5)
+#define RCP14_ETMCNTENR3() MRC14(1, c0, c7, 5)
+#define RCP14_ETMCNTRLDEVR0() MRC14(1, c0, c8, 5)
+#define RCP14_ETMCNTRLDEVR1() MRC14(1, c0, c9, 5)
+#define RCP14_ETMCNTRLDEVR2() MRC14(1, c0, c10, 5)
+#define RCP14_ETMCNTRLDEVR3() MRC14(1, c0, c11, 5)
+#define RCP14_ETMCNTVR0() MRC14(1, c0, c12, 5)
+#define RCP14_ETMCNTVR1() MRC14(1, c0, c13, 5)
+#define RCP14_ETMCNTVR2() MRC14(1, c0, c14, 5)
+#define RCP14_ETMCNTVR3() MRC14(1, c0, c15, 5)
+#define RCP14_ETMSQ12EVR() MRC14(1, c0, c0, 6)
+#define RCP14_ETMSQ21EVR() MRC14(1, c0, c1, 6)
+#define RCP14_ETMSQ23EVR() MRC14(1, c0, c2, 6)
+#define RCP14_ETMSQ31EVR() MRC14(1, c0, c3, 6)
+#define RCP14_ETMSQ32EVR() MRC14(1, c0, c4, 6)
+#define RCP14_ETMSQ13EVR() MRC14(1, c0, c5, 6)
+#define RCP14_ETMSQR() MRC14(1, c0, c7, 6)
+#define RCP14_ETMEXTOUTEVR0() MRC14(1, c0, c8, 6)
+#define RCP14_ETMEXTOUTEVR1() MRC14(1, c0, c9, 6)
+#define RCP14_ETMEXTOUTEVR2() MRC14(1, c0, c10, 6)
+#define RCP14_ETMEXTOUTEVR3() MRC14(1, c0, c11, 6)
+#define RCP14_ETMCIDCVR0() MRC14(1, c0, c12, 6)
+#define RCP14_ETMCIDCVR1() MRC14(1, c0, c13, 6)
+#define RCP14_ETMCIDCVR2() MRC14(1, c0, c14, 6)
+#define RCP14_ETMCIDCMR() MRC14(1, c0, c15, 6)
+#define RCP14_ETMIMPSPEC0() MRC14(1, c0, c0, 7)
+#define RCP14_ETMIMPSPEC1() MRC14(1, c0, c1, 7)
+#define RCP14_ETMIMPSPEC2() MRC14(1, c0, c2, 7)
+#define RCP14_ETMIMPSPEC3() MRC14(1, c0, c3, 7)
+#define RCP14_ETMIMPSPEC4() MRC14(1, c0, c4, 7)
+#define RCP14_ETMIMPSPEC5() MRC14(1, c0, c5, 7)
+#define RCP14_ETMIMPSPEC6() MRC14(1, c0, c6, 7)
+#define RCP14_ETMIMPSPEC7() MRC14(1, c0, c7, 7)
+#define RCP14_ETMSYNCFR() MRC14(1, c0, c8, 7)
+#define RCP14_ETMIDR() MRC14(1, c0, c9, 7)
+#define RCP14_ETMCCER() MRC14(1, c0, c10, 7)
+#define RCP14_ETMEXTINSELR() MRC14(1, c0, c11, 7)
+#define RCP14_ETMTESSEICR() MRC14(1, c0, c12, 7)
+#define RCP14_ETMEIBCR() MRC14(1, c0, c13, 7)
+#define RCP14_ETMTSEVR() MRC14(1, c0, c14, 7)
+#define RCP14_ETMAUXCR() MRC14(1, c0, c15, 7)
+#define RCP14_ETMTRACEIDR() MRC14(1, c1, c0, 0)
+#define RCP14_ETMIDR2() MRC14(1, c1, c2, 0)
+#define RCP14_ETMVMIDCVR() MRC14(1, c1, c0, 1)
+#define RCP14_ETMOSLSR() MRC14(1, c1, c1, 4)
+/* Not available in PFTv1.1 */
+#define RCP14_ETMOSSRR() MRC14(1, c1, c2, 4)
+#define RCP14_ETMPDCR() MRC14(1, c1, c4, 4)
+#define RCP14_ETMPDSR() MRC14(1, c1, c5, 4)
+#define RCP14_ETMITCTRL() MRC14(1, c7, c0, 4)
+#define RCP14_ETMCLAIMSET() MRC14(1, c7, c8, 6)
+#define RCP14_ETMCLAIMCLR() MRC14(1, c7, c9, 6)
+#define RCP14_ETMLSR() MRC14(1, c7, c13, 6)
+#define RCP14_ETMAUTHSTATUS() MRC14(1, c7, c14, 6)
+#define RCP14_ETMDEVID() MRC14(1, c7, c2, 7)
+#define RCP14_ETMDEVTYPE() MRC14(1, c7, c3, 7)
+#define RCP14_ETMPIDR4() MRC14(1, c7, c4, 7)
+#define RCP14_ETMPIDR5() MRC14(1, c7, c5, 7)
+#define RCP14_ETMPIDR6() MRC14(1, c7, c6, 7)
+#define RCP14_ETMPIDR7() MRC14(1, c7, c7, 7)
+#define RCP14_ETMPIDR0() MRC14(1, c7, c8, 7)
+#define RCP14_ETMPIDR1() MRC14(1, c7, c9, 7)
+#define RCP14_ETMPIDR2() MRC14(1, c7, c10, 7)
+#define RCP14_ETMPIDR3() MRC14(1, c7, c11, 7)
+#define RCP14_ETMCIDR0() MRC14(1, c7, c12, 7)
+#define RCP14_ETMCIDR1() MRC14(1, c7, c13, 7)
+#define RCP14_ETMCIDR2() MRC14(1, c7, c14, 7)
+#define RCP14_ETMCIDR3() MRC14(1, c7, c15, 7)
+
+#define WCP14_ETMCR(val) MCR14(val, 1, c0, c0, 0)
+#define WCP14_ETMTRIGGER(val) MCR14(val, 1, c0, c2, 0)
+#define WCP14_ETMASICCR(val) MCR14(val, 1, c0, c3, 0)
+#define WCP14_ETMSR(val) MCR14(val, 1, c0, c4, 0)
+#define WCP14_ETMTSSCR(val) MCR14(val, 1, c0, c6, 0)
+#define WCP14_ETMTECR2(val) MCR14(val, 1, c0, c7, 0)
+#define WCP14_ETMTEEVR(val) MCR14(val, 1, c0, c8, 0)
+#define WCP14_ETMTECR1(val) MCR14(val, 1, c0, c9, 0)
+#define WCP14_ETMFFRR(val) MCR14(val, 1, c0, c10, 0)
+#define WCP14_ETMFFLR(val) MCR14(val, 1, c0, c11, 0)
+#define WCP14_ETMVDEVR(val) MCR14(val, 1, c0, c12, 0)
+#define WCP14_ETMVDCR1(val) MCR14(val, 1, c0, c13, 0)
+#define WCP14_ETMVDCR2(val) MCR14(val, 1, c0, c14, 0)
+#define WCP14_ETMVDCR3(val) MCR14(val, 1, c0, c15, 0)
+#define WCP14_ETMACVR0(val) MCR14(val, 1, c0, c0, 1)
+#define WCP14_ETMACVR1(val) MCR14(val, 1, c0, c1, 1)
+#define WCP14_ETMACVR2(val) MCR14(val, 1, c0, c2, 1)
+#define WCP14_ETMACVR3(val) MCR14(val, 1, c0, c3, 1)
+#define WCP14_ETMACVR4(val) MCR14(val, 1, c0, c4, 1)
+#define WCP14_ETMACVR5(val) MCR14(val, 1, c0, c5, 1)
+#define WCP14_ETMACVR6(val) MCR14(val, 1, c0, c6, 1)
+#define WCP14_ETMACVR7(val) MCR14(val, 1, c0, c7, 1)
+#define WCP14_ETMACVR8(val) MCR14(val, 1, c0, c8, 1)
+#define WCP14_ETMACVR9(val) MCR14(val, 1, c0, c9, 1)
+#define WCP14_ETMACVR10(val) MCR14(val, 1, c0, c10, 1)
+#define WCP14_ETMACVR11(val) MCR14(val, 1, c0, c11, 1)
+#define WCP14_ETMACVR12(val) MCR14(val, 1, c0, c12, 1)
+#define WCP14_ETMACVR13(val) MCR14(val, 1, c0, c13, 1)
+#define WCP14_ETMACVR14(val) MCR14(val, 1, c0, c14, 1)
+#define WCP14_ETMACVR15(val) MCR14(val, 1, c0, c15, 1)
+#define WCP14_ETMACTR0(val) MCR14(val, 1, c0, c0, 2)
+#define WCP14_ETMACTR1(val) MCR14(val, 1, c0, c1, 2)
+#define WCP14_ETMACTR2(val) MCR14(val, 1, c0, c2, 2)
+#define WCP14_ETMACTR3(val) MCR14(val, 1, c0, c3, 2)
+#define WCP14_ETMACTR4(val) MCR14(val, 1, c0, c4, 2)
+#define WCP14_ETMACTR5(val) MCR14(val, 1, c0, c5, 2)
+#define WCP14_ETMACTR6(val) MCR14(val, 1, c0, c6, 2)
+#define WCP14_ETMACTR7(val) MCR14(val, 1, c0, c7, 2)
+#define WCP14_ETMACTR8(val) MCR14(val, 1, c0, c8, 2)
+#define WCP14_ETMACTR9(val) MCR14(val, 1, c0, c9, 2)
+#define WCP14_ETMACTR10(val) MCR14(val, 1, c0, c10, 2)
+#define WCP14_ETMACTR11(val) MCR14(val, 1, c0, c11, 2)
+#define WCP14_ETMACTR12(val) MCR14(val, 1, c0, c12, 2)
+#define WCP14_ETMACTR13(val) MCR14(val, 1, c0, c13, 2)
+#define WCP14_ETMACTR14(val) MCR14(val, 1, c0, c14, 2)
+#define WCP14_ETMACTR15(val) MCR14(val, 1, c0, c15, 2)
+#define WCP14_ETMDCVR0(val) MCR14(val, 1, c0, c0, 3)
+#define WCP14_ETMDCVR2(val) MCR14(val, 1, c0, c2, 3)
+#define WCP14_ETMDCVR4(val) MCR14(val, 1, c0, c4, 3)
+#define WCP14_ETMDCVR6(val) MCR14(val, 1, c0, c6, 3)
+#define WCP14_ETMDCVR8(val) MCR14(val, 1, c0, c8, 3)
+#define WCP14_ETMDCVR10(val) MCR14(val, 1, c0, c10, 3)
+#define WCP14_ETMDCVR12(val) MCR14(val, 1, c0, c12, 3)
+#define WCP14_ETMDCVR14(val) MCR14(val, 1, c0, c14, 3)
+#define WCP14_ETMDCMR0(val) MCR14(val, 1, c0, c0, 4)
+#define WCP14_ETMDCMR2(val) MCR14(val, 1, c0, c2, 4)
+#define WCP14_ETMDCMR4(val) MCR14(val, 1, c0, c4, 4)
+#define WCP14_ETMDCMR6(val) MCR14(val, 1, c0, c6, 4)
+#define WCP14_ETMDCMR8(val) MCR14(val, 1, c0, c8, 4)
+#define WCP14_ETMDCMR10(val) MCR14(val, 1, c0, c10, 4)
+#define WCP14_ETMDCMR12(val) MCR14(val, 1, c0, c12, 4)
+#define WCP14_ETMDCMR14(val) MCR14(val, 1, c0, c14, 4)
+#define WCP14_ETMCNTRLDVR0(val) MCR14(val, 1, c0, c0, 5)
+#define WCP14_ETMCNTRLDVR1(val) MCR14(val, 1, c0, c1, 5)
+#define WCP14_ETMCNTRLDVR2(val) MCR14(val, 1, c0, c2, 5)
+#define WCP14_ETMCNTRLDVR3(val) MCR14(val, 1, c0, c3, 5)
+#define WCP14_ETMCNTENR0(val) MCR14(val, 1, c0, c4, 5)
+#define WCP14_ETMCNTENR1(val) MCR14(val, 1, c0, c5, 5)
+#define WCP14_ETMCNTENR2(val) MCR14(val, 1, c0, c6, 5)
+#define WCP14_ETMCNTENR3(val) MCR14(val, 1, c0, c7, 5)
+#define WCP14_ETMCNTRLDEVR0(val) MCR14(val, 1, c0, c8, 5)
+#define WCP14_ETMCNTRLDEVR1(val) MCR14(val, 1, c0, c9, 5)
+#define WCP14_ETMCNTRLDEVR2(val) MCR14(val, 1, c0, c10, 5)
+#define WCP14_ETMCNTRLDEVR3(val) MCR14(val, 1, c0, c11, 5)
+#define WCP14_ETMCNTVR0(val) MCR14(val, 1, c0, c12, 5)
+#define WCP14_ETMCNTVR1(val) MCR14(val, 1, c0, c13, 5)
+#define WCP14_ETMCNTVR2(val) MCR14(val, 1, c0, c14, 5)
+#define WCP14_ETMCNTVR3(val) MCR14(val, 1, c0, c15, 5)
+#define WCP14_ETMSQ12EVR(val) MCR14(val, 1, c0, c0, 6)
+#define WCP14_ETMSQ21EVR(val) MCR14(val, 1, c0, c1, 6)
+#define WCP14_ETMSQ23EVR(val) MCR14(val, 1, c0, c2, 6)
+#define WCP14_ETMSQ31EVR(val) MCR14(val, 1, c0, c3, 6)
+#define WCP14_ETMSQ32EVR(val) MCR14(val, 1, c0, c4, 6)
+#define WCP14_ETMSQ13EVR(val) MCR14(val, 1, c0, c5, 6)
+#define WCP14_ETMSQR(val) MCR14(val, 1, c0, c7, 6)
+#define WCP14_ETMEXTOUTEVR0(val) MCR14(val, 1, c0, c8, 6)
+#define WCP14_ETMEXTOUTEVR1(val) MCR14(val, 1, c0, c9, 6)
+#define WCP14_ETMEXTOUTEVR2(val) MCR14(val, 1, c0, c10, 6)
+#define WCP14_ETMEXTOUTEVR3(val) MCR14(val, 1, c0, c11, 6)
+#define WCP14_ETMCIDCVR0(val) MCR14(val, 1, c0, c12, 6)
+#define WCP14_ETMCIDCVR1(val) MCR14(val, 1, c0, c13, 6)
+#define WCP14_ETMCIDCVR2(val) MCR14(val, 1, c0, c14, 6)
+#define WCP14_ETMCIDCMR(val) MCR14(val, 1, c0, c15, 6)
+#define WCP14_ETMIMPSPEC0(val) MCR14(val, 1, c0, c0, 7)
+#define WCP14_ETMIMPSPEC1(val) MCR14(val, 1, c0, c1, 7)
+#define WCP14_ETMIMPSPEC2(val) MCR14(val, 1, c0, c2, 7)
+#define WCP14_ETMIMPSPEC3(val) MCR14(val, 1, c0, c3, 7)
+#define WCP14_ETMIMPSPEC4(val) MCR14(val, 1, c0, c4, 7)
+#define WCP14_ETMIMPSPEC5(val) MCR14(val, 1, c0, c5, 7)
+#define WCP14_ETMIMPSPEC6(val) MCR14(val, 1, c0, c6, 7)
+#define WCP14_ETMIMPSPEC7(val) MCR14(val, 1, c0, c7, 7)
+/* Can be read only in ETMv3.4, ETMv3.5 */
+#define WCP14_ETMSYNCFR(val) MCR14(val, 1, c0, c8, 7)
+#define WCP14_ETMEXTINSELR(val) MCR14(val, 1, c0, c11, 7)
+#define WCP14_ETMTESSEICR(val) MCR14(val, 1, c0, c12, 7)
+#define WCP14_ETMEIBCR(val) MCR14(val, 1, c0, c13, 7)
+#define WCP14_ETMTSEVR(val) MCR14(val, 1, c0, c14, 7)
+#define WCP14_ETMAUXCR(val) MCR14(val, 1, c0, c15, 7)
+#define WCP14_ETMTRACEIDR(val) MCR14(val, 1, c1, c0, 0)
+#define WCP14_ETMIDR2(val) MCR14(val, 1, c1, c2, 0)
+#define WCP14_ETMVMIDCVR(val) MCR14(val, 1, c1, c0, 1)
+#define WCP14_ETMOSLAR(val) MCR14(val, 1, c1, c0, 4)
+/* Not available in PFTv1.1 */
+#define WCP14_ETMOSSRR(val) MCR14(val, 1, c1, c2, 4)
+#define WCP14_ETMPDCR(val) MCR14(val, 1, c1, c4, 4)
+#define WCP14_ETMPDSR(val) MCR14(val, 1, c1, c5, 4)
+#define WCP14_ETMITCTRL(val) MCR14(val, 1, c7, c0, 4)
+#define WCP14_ETMCLAIMSET(val) MCR14(val, 1, c7, c8, 6)
+#define WCP14_ETMCLAIMCLR(val) MCR14(val, 1, c7, c9, 6)
+/* Writes to this from CP14 interface are ignored */
+#define WCP14_ETMLAR(val) MCR14(val, 1, c7, c12, 6)
+
+#endif
diff --git a/arch/arm/include/asm/hardware/debug-pl01x.S b/arch/arm/include/asm/hardware/debug-pl01x.S
index f9fd083..6489d1f 100644
--- a/arch/arm/include/asm/hardware/debug-pl01x.S
+++ b/arch/arm/include/asm/hardware/debug-pl01x.S
@@ -18,12 +18,14 @@
.macro waituart,rd,rx
1001: ldr \rd, [\rx, #UART01x_FR]
+ ARM_BE8( rev \rd, \rd )
tst \rd, #UART01x_FR_TXFF
bne 1001b
.endm
.macro busyuart,rd,rx
1001: ldr \rd, [\rx, #UART01x_FR]
+ ARM_BE8( rev \rd, \rd )
tst \rd, #UART01x_FR_BUSY
bne 1001b
.endm
diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
new file mode 100644
index 0000000..d4014fb
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/include/asm/hugetlb-3level.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_3LEVEL_H
+#define _ASM_ARM_HUGETLB_3LEVEL_H
+
+
+/*
+ * If our huge pte is non-zero then mark the valid bit.
+ * This allows pte_present(huge_ptep_get(ptep)) to return true for non-zero
+ * ptes.
+ * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
+ */
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+ pte_t retval = *ptep;
+ if (pte_val(retval))
+ pte_val(retval) |= L_PTE_VALID;
+ return retval;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
+{
+ ptep_clear_flush(vma, addr, ptep);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty)
+{
+ return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+#endif /* _ASM_ARM_HUGETLB_3LEVEL_H */
diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
new file mode 100644
index 0000000..1f1b1cd
--- /dev/null
+++ b/arch/arm/include/asm/hugetlb.h
@@ -0,0 +1,84 @@
+/*
+ * arch/arm/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _ASM_ARM_HUGETLB_H
+#define _ASM_ARM_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+#include <asm/hugetlb-3level.h>
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor,
+ unsigned long ceiling)
+{
+ free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+ unsigned long addr, unsigned long len)
+{
+ return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+ unsigned long addr, unsigned long len)
+{
+ struct hstate *h = hstate_file(file);
+ if (len & ~huge_page_mask(h))
+ return -EINVAL;
+ if (addr & ~huge_page_mask(h))
+ return -EINVAL;
+ return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+ return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+ return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+ return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+ clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* _ASM_ARM_HUGETLB_H */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 652b560..d070741 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -130,16 +130,16 @@
*/
extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
size_t, unsigned int, void *);
-extern void __iomem *__arm_ioremap_caller(unsigned long, size_t, unsigned int,
+extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
void *);
extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap_exec(unsigned long, size_t, bool cached);
+extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
+extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
extern void __iounmap(volatile void __iomem *addr);
extern void __arm_iounmap(volatile void __iomem *addr);
-extern void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
unsigned int, void *);
extern void (*arch_iounmap)(volatile void __iomem *);
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index bfc198c..863c892 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -16,7 +16,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:\n\t"
+ asm_volatile_goto("1:\n\t"
JUMP_LABEL_NOP "\n\t"
".pushsection __jump_table, \"aw\"\n\t"
".word 1b, %l[l_yes], %c0\n\t"
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 48066ce..0a9d5dd 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -11,6 +11,7 @@
#define __ARM_KGDB_H__
#include <linux/ptrace.h>
+#include <asm/opcodes.h>
/*
* GDB assumes that we're a user process being debugged, so
@@ -41,7 +42,7 @@
static inline void arch_kgdb_breakpoint(void)
{
- asm(".word 0xe7ffdeff");
+ asm(__inst_arm(0xe7ffdeff));
}
extern void kgdb_handle_bus_error(void);
diff --git a/arch/arm/include/asm/kvm_arch_timer.h b/arch/arm/include/asm/kvm_arch_timer.h
deleted file mode 100644
index 68cb9e1..0000000
--- a/arch/arm/include/asm/kvm_arch_timer.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef __ASM_ARM_KVM_ARCH_TIMER_H
-#define __ASM_ARM_KVM_ARCH_TIMER_H
-
-#include <linux/clocksource.h>
-#include <linux/hrtimer.h>
-#include <linux/workqueue.h>
-
-struct arch_timer_kvm {
-#ifdef CONFIG_KVM_ARM_TIMER
- /* Is the timer enabled */
- bool enabled;
-
- /* Virtual offset */
- cycle_t cntvoff;
-#endif
-};
-
-struct arch_timer_cpu {
-#ifdef CONFIG_KVM_ARM_TIMER
- /* Registers: control register, timer value */
- u32 cntv_ctl; /* Saved/restored */
- cycle_t cntv_cval; /* Saved/restored */
-
- /*
- * Anything that is not used directly from assembly code goes
- * here.
- */
-
- /* Background timer used when the guest is not running */
- struct hrtimer timer;
-
- /* Work queued with the above timer expires */
- struct work_struct expired;
-
- /* Background timer active */
- bool armed;
-
- /* Timer IRQ */
- const struct kvm_irq_level *irq;
-#endif
-};
-
-#ifdef CONFIG_KVM_ARM_TIMER
-int kvm_timer_hyp_init(void);
-int kvm_timer_init(struct kvm *kvm);
-void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
-void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
-#else
-static inline int kvm_timer_hyp_init(void)
-{
- return 0;
-};
-
-static inline int kvm_timer_init(struct kvm *kvm)
-{
- return 0;
-}
-
-static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
-static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {}
-static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {}
-static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {}
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index 124623e..816db0b 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -55,8 +55,10 @@
* The bits we set in HCR:
* TAC: Trap ACTLR
* TSC: Trap SMC
+ * TVM: Trap VM ops (until MMU and caches are on)
* TSW: Trap cache operations by set/way
* TWI: Trap WFI
+ * TWE: Trap WFE
* TIDCP: Trap L2CTLR/L2ECTLR
* BSU_IS: Upgrade barriers to the inner shareable domain
* FB: Force broadcast of all maintainance operations
@@ -67,8 +69,7 @@
*/
#define HCR_GUEST_MASK (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \
HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \
- HCR_SWIO | HCR_TIDCP)
-#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+ HCR_TVM | HCR_TWE | HCR_SWIO | HCR_TIDCP)
/* System Control Register (SCTLR) bits */
#define SCTLR_TE (1 << 30)
@@ -95,12 +96,12 @@
#define TTBCR_IRGN1 (3 << 24)
#define TTBCR_EPD1 (1 << 23)
#define TTBCR_A1 (1 << 22)
-#define TTBCR_T1SZ (3 << 16)
+#define TTBCR_T1SZ (7 << 16)
#define TTBCR_SH0 (3 << 12)
#define TTBCR_ORGN0 (3 << 10)
#define TTBCR_IRGN0 (3 << 8)
#define TTBCR_EPD0 (1 << 7)
-#define TTBCR_T0SZ 3
+#define TTBCR_T0SZ (7 << 0)
#define HTCR_MASK (TTBCR_T0SZ | TTBCR_IRGN0 | TTBCR_ORGN0 | TTBCR_SH0)
/* Hyp System Trap Register */
@@ -135,7 +136,6 @@
#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1ULL)
#define PTRS_PER_S2_PGD (1ULL << (KVM_PHYS_SHIFT - 30))
#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
-#define S2_PGD_SIZE (1 << S2_PGD_ORDER)
/* Virtualization Translation Control Register (VTCR) bits */
#define VTCR_SH0 (3 << 12)
@@ -209,6 +209,8 @@
#define HSR_EC_DABT (0x24)
#define HSR_EC_DABT_HYP (0x25)
+#define HSR_WFI_IS_WFE (1U << 0)
+
#define HSR_HVC_IMM_MASK ((1UL << 16) - 1)
#define HSR_DABT_S1PTW (1U << 7)
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 18d5032..3a67bec 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -37,16 +37,20 @@
#define c5_AIFSR 15 /* Auxilary Instrunction Fault Status R */
#define c6_DFAR 16 /* Data Fault Address Register */
#define c6_IFAR 17 /* Instruction Fault Address Register */
-#define c9_L2CTLR 18 /* Cortex A15 L2 Control Register */
-#define c10_PRRR 19 /* Primary Region Remap Register */
-#define c10_NMRR 20 /* Normal Memory Remap Register */
-#define c12_VBAR 21 /* Vector Base Address Register */
-#define c13_CID 22 /* Context ID Register */
-#define c13_TID_URW 23 /* Thread ID, User R/W */
-#define c13_TID_URO 24 /* Thread ID, User R/O */
-#define c13_TID_PRIV 25 /* Thread ID, Privileged */
-#define c14_CNTKCTL 26 /* Timer Control Register (PL1) */
-#define NR_CP15_REGS 27 /* Number of regs (incl. invalid) */
+#define c7_PAR 18 /* Physical Address Register */
+#define c7_PAR_high 19 /* PAR top 32 bits */
+#define c9_L2CTLR 20 /* Cortex A15/A7 L2 Control Register */
+#define c10_PRRR 21 /* Primary Region Remap Register */
+#define c10_NMRR 22 /* Normal Memory Remap Register */
+#define c12_VBAR 23 /* Vector Base Address Register */
+#define c13_CID 24 /* Context ID Register */
+#define c13_TID_URW 25 /* Thread ID, User R/W */
+#define c13_TID_URO 26 /* Thread ID, User R/O */
+#define c13_TID_PRIV 27 /* Thread ID, Privileged */
+#define c14_CNTKCTL 28 /* Timer Control Register (PL1) */
+#define c10_AMAIR0 29 /* Auxilary Memory Attribute Indirection Reg0 */
+#define c10_AMAIR1 30 /* Auxilary Memory Attribute Indirection Reg1 */
+#define NR_CP15_REGS 31 /* Number of regs (incl. invalid) */
#define ARM_EXCEPTION_RESET 0
#define ARM_EXCEPTION_UNDEFINED 1
@@ -57,6 +61,24 @@
#define ARM_EXCEPTION_FIQ 6
#define ARM_EXCEPTION_HVC 7
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
#ifndef __ASSEMBLY__
struct kvm;
struct kvm_vcpu;
@@ -72,8 +94,6 @@
extern char __kvm_hyp_code_start[];
extern char __kvm_hyp_code_end[];
-extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
-
extern void __kvm_flush_vm_context(void);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 82b4bab..b9db269 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -65,11 +65,6 @@
return cpsr_mode > USR_MODE;;
}
-static inline bool kvm_vcpu_reg_is_pc(struct kvm_vcpu *vcpu, int reg)
-{
- return reg == 15;
-}
-
static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu)
{
return vcpu->arch.fault.hsr;
@@ -154,6 +149,11 @@
static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
{
+ return kvm_vcpu_get_hsr(vcpu) & HSR_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu)
+{
return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
}
@@ -162,4 +162,69 @@
return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK;
}
+static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.cp15[c0_MPIDR];
+}
+
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+ *vcpu_cpsr(vcpu) |= PSR_E_BIT;
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+ return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT);
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+ unsigned long data,
+ unsigned int len)
+{
+ if (kvm_vcpu_is_be(vcpu)) {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return be16_to_cpu(data & 0xffff);
+ default:
+ return be32_to_cpu(data);
+ }
+ } else {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return le16_to_cpu(data & 0xffff);
+ default:
+ return le32_to_cpu(data);
+ }
+ }
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+ unsigned long data,
+ unsigned int len)
+{
+ if (kvm_vcpu_is_be(vcpu)) {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return cpu_to_be16(data & 0xffff);
+ default:
+ return cpu_to_be32(data);
+ }
+ } else {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return cpu_to_le16(data & 0xffff);
+ default:
+ return cpu_to_le32(data);
+ }
+ }
+}
+
#endif /* __ARM_KVM_EMULATE_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 57cb786..46e5d4d 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -19,30 +19,31 @@
#ifndef __ARM_KVM_HOST_H__
#define __ARM_KVM_HOST_H__
+#include <linux/types.h>
+#include <linux/kvm_types.h>
#include <asm/kvm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmio.h>
#include <asm/fpstate.h>
-#include <asm/kvm_arch_timer.h>
+#include <kvm/arm_arch_timer.h>
+#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
+#else
+#define KVM_MAX_VCPUS 0
+#endif
+
#define KVM_USER_MEM_SLOTS 32
#define KVM_PRIVATE_MEM_SLOTS 4
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
#define KVM_HAVE_ONE_REG
-#define KVM_VCPU_MAX_FEATURES 1
+#define KVM_VCPU_MAX_FEATURES 2
-/* We don't currently support large pages. */
-#define KVM_HPAGE_GFN_SHIFT(x) 0
-#define KVM_NR_PAGE_SIZES 1
-#define KVM_PAGES_PER_HPAGE(x) (1UL<<31)
+#include <kvm/arm_vgic.h>
-#include <asm/kvm_vgic.h>
-
-struct kvm_vcpu;
u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
@@ -101,6 +102,12 @@
/* The CPU type we expose to the VM */
u32 midr;
+ /* HYP trapping configuration */
+ u32 hcr;
+
+ /* Interrupt related fields */
+ u32 irq_lines; /* IRQ and FIQ levels */
+
/* Exception Information */
struct kvm_vcpu_fault_info fault;
@@ -128,9 +135,6 @@
/* IO related fields */
struct kvm_decode mmio_decode;
- /* Interrupt related fields */
- u32 irq_lines; /* IRQ and FIQ levels */
-
/* Cache some mmu pages needed inside spinlock regions */
struct kvm_mmu_memory_cache mmu_page_cache;
@@ -146,19 +150,17 @@
u32 halt_wakeup;
};
-struct kvm_vcpu_init;
int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
const struct kvm_vcpu_init *init);
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
-struct kvm_one_reg;
int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
u64 kvm_call_hyp(void *hypfn, ...);
void force_vm_exit(const cpumask_t *mask);
#define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm,
unsigned long start, unsigned long end);
@@ -183,15 +185,14 @@
int kvm_arm_copy_coproc_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
unsigned long kvm_arm_num_coproc_regs(struct kvm_vcpu *vcpu);
-struct kvm_one_reg;
int kvm_arm_coproc_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
int exception_index);
-static inline void __cpu_init_hyp_mode(unsigned long long boot_pgd_ptr,
- unsigned long long pgd_ptr,
+static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
+ phys_addr_t pgd_ptr,
unsigned long hyp_stack_ptr,
unsigned long vector_ptr)
{
@@ -221,7 +222,18 @@
return 0;
}
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+ BUG_ON(vgic->type != VGIC_V2);
+}
+
int kvm_perf_init(void);
int kvm_perf_teardown(void);
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
#endif /* __ARM_KVM_HOST_H__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 472ac70..3f688b4 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -62,9 +62,15 @@
int kvm_mmu_init(void);
void kvm_clear_hyp_idmap(void);
+static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd)
+{
+ *pmd = new_pmd;
+ flush_pmd_entry(pmd);
+}
+
static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
{
- pte_val(*pte) = new_pte;
+ *pte = new_pte;
/*
* flush_pmd_entry just takes a void pointer and cleans the necessary
* cache entries, so we can reuse the function for ptes.
@@ -72,17 +78,6 @@
flush_pmd_entry(pte);
}
-static inline bool kvm_is_write_fault(unsigned long hsr)
-{
- unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
- if (hsr_ec == HSR_EC_IABT)
- return false;
- else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR))
- return false;
- else
- return true;
-}
-
static inline void kvm_clean_pgd(pgd_t *pgd)
{
clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
@@ -103,10 +98,51 @@
pte_val(*pte) |= L_PTE_S2_RDWR;
}
+static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
+{
+ pmd_val(*pmd) |= L_PMD_S2_RDWR;
+}
+
+/* Open coded p*d_addr_end that can deal with 64bit addresses */
+#define kvm_pgd_addr_end(addr, end) \
+({ u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \
+ (__boundary - 1 < (end) - 1)? __boundary: (end); \
+})
+
+#define kvm_pud_addr_end(addr,end) (end)
+
+#define kvm_pmd_addr_end(addr, end) \
+({ u64 __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \
+ (__boundary - 1 < (end) - 1)? __boundary: (end); \
+})
+
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
+
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(pudp) (0)
+
+
struct kvm;
-static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
+#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
{
+ return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+ unsigned long size)
+{
+ if (!vcpu_has_cache_enabled(vcpu))
+ kvm_flush_dcache_to_poc((void *)hva, size);
+
/*
* If we are going to insert an instruction page and the icache is
* either VIPT or PIPT, there is a potential problem where the host
@@ -120,15 +156,16 @@
* need any kind of flushing (DDI 0406C.b - Page B3-1392).
*/
if (icache_is_pipt()) {
- unsigned long hva = gfn_to_hva(kvm, gfn);
- __cpuc_coherent_user_range(hva, hva + PAGE_SIZE);
+ __cpuc_coherent_user_range(hva, hva + size);
} else if (!icache_is_vivt_asid_tagged()) {
/* any kind of VIPT cache */
__flush_icache_all();
}
}
-#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l))
+#define kvm_virt_to_phys(x) virt_to_idmap((unsigned long)(x))
+
+void stage2_flush_vm(struct kvm *kvm);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arm/include/asm/kvm_psci.h b/arch/arm/include/asm/kvm_psci.h
index 9a83d98..6bda945 100644
--- a/arch/arm/include/asm/kvm_psci.h
+++ b/arch/arm/include/asm/kvm_psci.h
@@ -18,6 +18,10 @@
#ifndef __ARM_KVM_PSCI_H__
#define __ARM_KVM_PSCI_H__
-bool kvm_psci_call(struct kvm_vcpu *vcpu);
+#define KVM_ARM_PSCI_0_1 1
+#define KVM_ARM_PSCI_0_2 2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
#endif /* __ARM_KVM_PSCI_H__ */
diff --git a/arch/arm/include/asm/kvm_vgic.h b/arch/arm/include/asm/kvm_vgic.h
deleted file mode 100644
index 343744e..0000000
--- a/arch/arm/include/asm/kvm_vgic.h
+++ /dev/null
@@ -1,220 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef __ASM_ARM_KVM_VGIC_H
-#define __ASM_ARM_KVM_VGIC_H
-
-#include <linux/kernel.h>
-#include <linux/kvm.h>
-#include <linux/irqreturn.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/irqchip/arm-gic.h>
-
-#define VGIC_NR_IRQS 128
-#define VGIC_NR_SGIS 16
-#define VGIC_NR_PPIS 16
-#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
-#define VGIC_NR_SHARED_IRQS (VGIC_NR_IRQS - VGIC_NR_PRIVATE_IRQS)
-#define VGIC_MAX_CPUS KVM_MAX_VCPUS
-#define VGIC_MAX_LRS (1 << 6)
-
-/* Sanity checks... */
-#if (VGIC_MAX_CPUS > 8)
-#error Invalid number of CPU interfaces
-#endif
-
-#if (VGIC_NR_IRQS & 31)
-#error "VGIC_NR_IRQS must be a multiple of 32"
-#endif
-
-#if (VGIC_NR_IRQS > 1024)
-#error "VGIC_NR_IRQS must be <= 1024"
-#endif
-
-/*
- * The GIC distributor registers describing interrupts have two parts:
- * - 32 per-CPU interrupts (SGI + PPI)
- * - a bunch of shared interrupts (SPI)
- */
-struct vgic_bitmap {
- union {
- u32 reg[VGIC_NR_PRIVATE_IRQS / 32];
- DECLARE_BITMAP(reg_ul, VGIC_NR_PRIVATE_IRQS);
- } percpu[VGIC_MAX_CPUS];
- union {
- u32 reg[VGIC_NR_SHARED_IRQS / 32];
- DECLARE_BITMAP(reg_ul, VGIC_NR_SHARED_IRQS);
- } shared;
-};
-
-struct vgic_bytemap {
- u32 percpu[VGIC_MAX_CPUS][VGIC_NR_PRIVATE_IRQS / 4];
- u32 shared[VGIC_NR_SHARED_IRQS / 4];
-};
-
-struct vgic_dist {
-#ifdef CONFIG_KVM_ARM_VGIC
- spinlock_t lock;
- bool ready;
-
- /* Virtual control interface mapping */
- void __iomem *vctrl_base;
-
- /* Distributor and vcpu interface mapping in the guest */
- phys_addr_t vgic_dist_base;
- phys_addr_t vgic_cpu_base;
-
- /* Distributor enabled */
- u32 enabled;
-
- /* Interrupt enabled (one bit per IRQ) */
- struct vgic_bitmap irq_enabled;
-
- /* Interrupt 'pin' level */
- struct vgic_bitmap irq_state;
-
- /* Level-triggered interrupt in progress */
- struct vgic_bitmap irq_active;
-
- /* Interrupt priority. Not used yet. */
- struct vgic_bytemap irq_priority;
-
- /* Level/edge triggered */
- struct vgic_bitmap irq_cfg;
-
- /* Source CPU per SGI and target CPU */
- u8 irq_sgi_sources[VGIC_MAX_CPUS][VGIC_NR_SGIS];
-
- /* Target CPU for each IRQ */
- u8 irq_spi_cpu[VGIC_NR_SHARED_IRQS];
- struct vgic_bitmap irq_spi_target[VGIC_MAX_CPUS];
-
- /* Bitmap indicating which CPU has something pending */
- unsigned long irq_pending_on_cpu;
-#endif
-};
-
-struct vgic_cpu {
-#ifdef CONFIG_KVM_ARM_VGIC
- /* per IRQ to LR mapping */
- u8 vgic_irq_lr_map[VGIC_NR_IRQS];
-
- /* Pending interrupts on this VCPU */
- DECLARE_BITMAP( pending_percpu, VGIC_NR_PRIVATE_IRQS);
- DECLARE_BITMAP( pending_shared, VGIC_NR_SHARED_IRQS);
-
- /* Bitmap of used/free list registers */
- DECLARE_BITMAP( lr_used, VGIC_MAX_LRS);
-
- /* Number of list registers on this CPU */
- int nr_lr;
-
- /* CPU vif control registers for world switch */
- u32 vgic_hcr;
- u32 vgic_vmcr;
- u32 vgic_misr; /* Saved only */
- u32 vgic_eisr[2]; /* Saved only */
- u32 vgic_elrsr[2]; /* Saved only */
- u32 vgic_apr;
- u32 vgic_lr[VGIC_MAX_LRS];
-#endif
-};
-
-#define LR_EMPTY 0xff
-
-struct kvm;
-struct kvm_vcpu;
-struct kvm_run;
-struct kvm_exit_mmio;
-
-#ifdef CONFIG_KVM_ARM_VGIC
-int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr);
-int kvm_vgic_hyp_init(void);
-int kvm_vgic_init(struct kvm *kvm);
-int kvm_vgic_create(struct kvm *kvm);
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
- bool level);
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
- struct kvm_exit_mmio *mmio);
-
-#define irqchip_in_kernel(k) (!!((k)->arch.vgic.vctrl_base))
-#define vgic_initialized(k) ((k)->arch.vgic.ready)
-
-#else
-static inline int kvm_vgic_hyp_init(void)
-{
- return 0;
-}
-
-static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
-{
- return 0;
-}
-
-static inline int kvm_vgic_init(struct kvm *kvm)
-{
- return 0;
-}
-
-static inline int kvm_vgic_create(struct kvm *kvm)
-{
- return 0;
-}
-
-static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
-static inline void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) {}
-static inline void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) {}
-
-static inline int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid,
- unsigned int irq_num, bool level)
-{
- return 0;
-}
-
-static inline int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
-static inline bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
- struct kvm_exit_mmio *mmio)
-{
- return false;
-}
-
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
- return 0;
-}
-
-static inline bool vgic_initialized(struct kvm *kvm)
-{
- return true;
-}
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 308ad7d..75bf079 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -8,6 +8,8 @@
* published by the Free Software Foundation.
*/
+#include <linux/types.h>
+
#ifndef __ASSEMBLY__
struct tag;
@@ -16,8 +18,10 @@
struct smp_operations;
#ifdef CONFIG_SMP
#define smp_ops(ops) (&(ops))
+#define smp_init_ops(ops) (&(ops))
#else
#define smp_ops(ops) (struct smp_operations *)NULL
+#define smp_init_ops(ops) (bool (*)(void))NULL
#endif
struct machine_desc {
@@ -41,6 +45,7 @@
unsigned char reserve_lp2 :1; /* never has lp2 */
char restart_mode; /* default restart mode */
struct smp_operations *smp; /* SMP operations */
+ bool (*smp_init)(void);
void (*fixup)(struct tag *, char **,
struct meminfo *);
void (*reserve)(void);/* reserve mem blocks */
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index 0f7b762..7626a7f 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -42,6 +42,14 @@
void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
/*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated. The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+ unsigned long poke_phys_addr, unsigned long poke_val);
+
+/*
* CPU/cluster power operations API for higher subsystems to use.
*/
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 57870ab..d5acecb 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -98,23 +98,19 @@
#define TASK_UNMAPPED_BASE UL(0x00000000)
#endif
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET UL(CONFIG_DRAM_BASE)
-#endif
-
#ifndef END_MEM
#define END_MEM (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
#endif
#ifndef PAGE_OFFSET
-#define PAGE_OFFSET (PHYS_OFFSET)
+#define PAGE_OFFSET PLAT_PHYS_OFFSET
#endif
/*
* The module can be at any place in ram in nommu mode.
*/
#define MODULES_END (END_MEM)
-#define MODULES_VADDR (PHYS_OFFSET)
+#define MODULES_VADDR PAGE_OFFSET
#define XIP_VIRT_ADDR(physaddr) (physaddr)
@@ -141,6 +137,16 @@
#define page_to_phys(page) (__pfn_to_phys(page_to_pfn(page)))
#define phys_to_page(phys) (pfn_to_page(__phys_to_pfn(phys)))
+/*
+ * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
+ * memory. This is used for XIP and NoMMU kernels, or by kernels which
+ * have their own mach/memory.h. Assembly code must always use
+ * PLAT_PHYS_OFFSET and not PHYS_OFFSET.
+ */
+#ifndef PLAT_PHYS_OFFSET
+#define PLAT_PHYS_OFFSET UL(CONFIG_PHYS_OFFSET)
+#endif
+
#ifndef __ASSEMBLY__
/*
@@ -157,6 +163,7 @@
*/
#define __PV_BITS_31_24 0x81000000
+extern phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
extern unsigned long __pv_phys_offset;
#define PHYS_OFFSET __pv_phys_offset
@@ -183,22 +190,15 @@
return t;
}
#else
+
+#define PHYS_OFFSET PLAT_PHYS_OFFSET
+
#define __virt_to_phys(x) ((x) - PAGE_OFFSET + PHYS_OFFSET)
#define __phys_to_virt(x) ((x) - PHYS_OFFSET + PAGE_OFFSET)
-#endif
-#endif
-#endif /* __ASSEMBLY__ */
-#ifndef PHYS_OFFSET
-#ifdef PLAT_PHYS_OFFSET
-#define PHYS_OFFSET PLAT_PHYS_OFFSET
-#else
-#define PHYS_OFFSET UL(CONFIG_PHYS_OFFSET)
#endif
#endif
-#ifndef __ASSEMBLY__
-
/*
* PFNs are used to describe any physical page; this means
* PFN 0 == physical address 0.
@@ -207,7 +207,7 @@
* direct-mapped view. We assume this is the first page
* of RAM in the mem_map as well.
*/
-#define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT)
+#define PHYS_PFN_OFFSET ((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
/*
* These are *only* valid on the kernel direct mapped RAM memory.
@@ -233,6 +233,21 @@
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
/*
+ * These are for systems that have a hardware interconnect supported alias of
+ * physical memory for idmap purposes. Most cases should leave these
+ * untouched.
+ */
+static inline phys_addr_t __virt_to_idmap(unsigned long x)
+{
+ if (arch_virt_to_idmap)
+ return arch_virt_to_idmap(x);
+ else
+ return __virt_to_phys(x);
+}
+
+#define virt_to_idmap(x) __virt_to_idmap((unsigned long)(x))
+
+/*
* Virtual <-> DMA view memory address translations
* Again, these are *only* valid on the kernel direct mapped RAM
* memory. Use of these is *deprecated* (and that doesn't mean
@@ -275,7 +290,8 @@
#define ARCH_PFN_OFFSET PHYS_PFN_OFFSET
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
+#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \
+ && pfn_valid(__pa(kaddr) >> PAGE_SHIFT) )
#endif
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index e3d5554..64fd151 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -6,14 +6,17 @@
typedef struct {
#ifdef CONFIG_CPU_HAS_ASID
atomic64_t id;
+#else
+ int switch_pending;
#endif
unsigned int vmalloc_seq;
+ unsigned long sigpage;
} mm_context_t;
#ifdef CONFIG_CPU_HAS_ASID
#define ASID_BITS 8
#define ASID_MASK ((~0ULL) << ASID_BITS)
-#define ASID(mm) ((mm)->context.id.counter & ~ASID_MASK)
+#define ASID(mm) ((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
#else
#define ASID(mm) (0)
#endif
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index a7b85e0..e0b10f1 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -27,7 +27,15 @@
void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; })
-DECLARE_PER_CPU(atomic64_t, active_asids);
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+ cpumask_t *mask);
+#else /* !CONFIG_ARM_ERRATA_798181 */
+static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+ cpumask_t *mask)
+{
+}
+#endif /* CONFIG_ARM_ERRATA_798181 */
#else /* !CONFIG_CPU_HAS_ASID */
@@ -47,7 +55,7 @@
* on non-ASID CPUs, the old mm will remain valid until the
* finish_arch_post_lock_switch() call.
*/
- set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
+ mm->context.switch_pending = 1;
else
cpu_switch_mm(mm->pgd, mm);
}
@@ -56,9 +64,21 @@
finish_arch_post_lock_switch
static inline void finish_arch_post_lock_switch(void)
{
- if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
- struct mm_struct *mm = current->mm;
- cpu_switch_mm(mm->pgd, mm);
+ struct mm_struct *mm = current->mm;
+
+ if (mm && mm->context.switch_pending) {
+ /*
+ * Preemption must be disabled during cpu_switch_mm() as we
+ * have some stateful cache flush implementations. Check
+ * switch_pending again in case we were preempted and the
+ * switch to this mm was already done.
+ */
+ preempt_disable();
+ if (mm->context.switch_pending) {
+ mm->context.switch_pending = 0;
+ cpu_switch_mm(mm->pgd, mm);
+ }
+ preempt_enable_no_resched();
}
}
diff --git a/arch/arm/include/asm/module.h b/arch/arm/include/asm/module.h
index 0d3a28d..ed690c4 100644
--- a/arch/arm/include/asm/module.h
+++ b/arch/arm/include/asm/module.h
@@ -12,6 +12,8 @@
ARM_SEC_CORE,
ARM_SEC_EXIT,
ARM_SEC_DEVEXIT,
+ ARM_SEC_HOT,
+ ARM_SEC_UNLIKELY,
ARM_SEC_MAX,
};
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 12f71a1..f94784f 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -37,10 +37,10 @@
void (*resume)(void);
};
-#ifdef CONFIG_OUTER_CACHE
-
extern struct outer_cache_fns outer_cache;
+#ifdef CONFIG_OUTER_CACHE
+
static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
{
if (outer_cache.inv_range)
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 812a494..4355f0e 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -13,7 +13,7 @@
/* PAGE_SHIFT determines the page size */
#define PAGE_SHIFT 12
#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
+#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1))
#ifndef __ASSEMBLY__
@@ -142,7 +142,9 @@
#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE)
extern void copy_page(void *to, const void *from);
+#ifdef CONFIG_KUSER_HELPERS
#define __HAVE_ARCH_GATE_AREA 1
+#endif
#ifdef CONFIG_ARM_LPAE
#include <asm/pgtable-3level-types.h>
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index f97ee02..c98c9c8 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -140,6 +140,7 @@
#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */
#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */
#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */
+#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */
#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2)
#ifndef __ASSEMBLY__
diff --git a/arch/arm/include/asm/pgtable-3level-hwdef.h b/arch/arm/include/asm/pgtable-3level-hwdef.h
index 18f5cef..5d9f086 100644
--- a/arch/arm/include/asm/pgtable-3level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-3level-hwdef.h
@@ -30,6 +30,7 @@
#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0)
#define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0)
#define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1)
#define PMD_BIT4 (_AT(pmdval_t, 0))
#define PMD_DOMAIN(x) (_AT(pmdval_t, 0))
#define PMD_APTABLE_SHIFT (61)
@@ -41,6 +42,8 @@
*/
#define PMD_SECT_BUFFERABLE (_AT(pmdval_t, 1) << 2)
#define PMD_SECT_CACHEABLE (_AT(pmdval_t, 1) << 3)
+#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */
+#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
#define PMD_SECT_AF (_AT(pmdval_t, 1) << 10)
#define PMD_SECT_nG (_AT(pmdval_t, 1) << 11)
@@ -66,8 +69,10 @@
#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0)
#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0)
#define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1)
#define PTE_BUFFERABLE (_AT(pteval_t, 1) << 2) /* AttrIndx[0] */
#define PTE_CACHEABLE (_AT(pteval_t, 1) << 3) /* AttrIndx[1] */
+#define PTE_AP2 (_AT(pteval_t, 1) << 7) /* AP[2] */
#define PTE_EXT_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
#define PTE_EXT_AF (_AT(pteval_t, 1) << 10) /* Access Flag */
#define PTE_EXT_NG (_AT(pteval_t, 1) << 11) /* nG */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 86b8fe3..0ea7f99 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -33,7 +33,7 @@
#define PTRS_PER_PMD 512
#define PTRS_PER_PGD 4
-#define PTE_HWTABLE_PTRS (PTRS_PER_PTE)
+#define PTE_HWTABLE_PTRS (0)
#define PTE_HWTABLE_OFF (0)
#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u64))
@@ -48,20 +48,28 @@
#define PMD_SHIFT 21
#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
+#define PMD_MASK (~((1 << PMD_SHIFT) - 1))
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
+#define PGDIR_MASK (~((1 << PGDIR_SHIFT) - 1))
/*
* section address mask and size definitions.
*/
#define SECTION_SHIFT 21
#define SECTION_SIZE (1UL << SECTION_SHIFT)
-#define SECTION_MASK (~(SECTION_SIZE-1))
+#define SECTION_MASK (~((1 << SECTION_SHIFT) - 1))
#define USER_PTRS_PER_PGD (PAGE_OFFSET / PGDIR_SIZE)
/*
+ * Hugetlb definitions.
+ */
+#define HPAGE_SHIFT PMD_SHIFT
+#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
+
+/*
* "Linux" PTE definitions for LPAE.
*
* These bits overlap with the hardware bits but the naming is preserved for
@@ -71,13 +79,18 @@
#define L_PTE_PRESENT (_AT(pteval_t, 3) << 0) /* Present */
#define L_PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !PRESENT */
#define L_PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */
-#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */
#define L_PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
#define L_PTE_YOUNG (_AT(pteval_t, 1) << 10) /* AF */
#define L_PTE_XN (_AT(pteval_t, 1) << 54) /* XN */
-#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55) /* unused */
-#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56) /* unused */
+#define L_PTE_DIRTY (_AT(pteval_t, 1) << 55)
+#define L_PTE_SPECIAL (_AT(pteval_t, 1) << 56)
#define L_PTE_NONE (_AT(pteval_t, 1) << 57) /* PROT_NONE */
+#define L_PTE_RDONLY (_AT(pteval_t, 1) << 58) /* READ ONLY */
+
+#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55)
+#define PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56)
+#define PMD_SECT_NONE (_AT(pmdval_t, 1) << 57)
/*
* To be used in assembly code with the upper page attributes.
@@ -113,6 +126,8 @@
#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */
#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
+#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
+
/*
* Hyp-mode PL2 PTE definitions for LPAE.
*/
@@ -166,8 +181,83 @@
clean_pmd_entry(pmdp); \
} while (0)
+/*
+ * For 3 levels of paging the PTE_EXT_NG bit will be set for user address ptes
+ * that are written to a page table but not for ptes created with mk_pte.
+ *
+ * In hugetlb_no_page, a new huge pte (new_pte) is generated and passed to
+ * hugetlb_cow, where it is compared with an entry in a page table.
+ * This comparison test fails erroneously leading ultimately to a memory leak.
+ *
+ * To correct this behaviour, we mask off PTE_EXT_NG for any pte that is
+ * present before running the comparison.
+ */
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(pte_a,pte_b) ((pte_present(pte_a) ? pte_val(pte_a) & ~PTE_EXT_NG \
+ : pte_val(pte_a)) \
+ == (pte_present(pte_b) ? pte_val(pte_b) & ~PTE_EXT_NG \
+ : pte_val(pte_b)))
+
#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,__pte(pte_val(pte)|(ext)))
+#define pte_huge(pte) (pte_val(pte) && !(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+#define pmd_young(pmd) (pmd_val(pmd) & PMD_SECT_AF)
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd) (!(pmd_val(pmd) & PMD_SECT_RDONLY))
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#endif
+
+#define PMD_BIT_FUNC(fn,op) \
+static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+
+PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF);
+PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
+PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY);
+PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
+
+#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
+
+/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */
+#define pmd_mknotpresent(pmd) (__pmd(0))
+
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+ const pmdval_t mask = PMD_SECT_USER | PMD_SECT_XN | PMD_SECT_RDONLY |
+ PMD_SECT_VALID | PMD_SECT_NONE;
+ pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
+ return pmd;
+}
+
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp, pmd_t pmd)
+{
+ BUG_ON(addr >= TASK_SIZE);
+
+ /* create a faulting entry if PROT_NONE protected */
+ if (pmd_val(pmd) & PMD_SECT_NONE)
+ pmd_val(pmd) &= ~PMD_SECT_VALID;
+
+ *pmdp = __pmd(pmd_val(pmd) | PMD_SECT_nG);
+ flush_pmd_entry(pmdp);
+}
+
+static inline int has_transparent_hugepage(void)
+{
+ return 1;
+}
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_PGTABLE_3LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 9bcd262..c312a72 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -24,6 +24,9 @@
#include <asm/memory.h>
#include <asm/pgtable-hwdef.h>
+
+#include <asm/tlbflush.h>
+
#ifdef CONFIG_ARM_LPAE
#include <asm/pgtable-3level.h>
#else
@@ -58,7 +61,7 @@
* mapping to be mapped at. This is particularly important for
* non-high vector CPUs.
*/
-#define FIRST_USER_ADDRESS PAGE_SIZE
+#define FIRST_USER_ADDRESS (PAGE_SIZE * 2)
/*
* Use TASK_SIZE as the ceiling argument for free_pgtables() and
@@ -97,7 +100,7 @@
#define PAGE_HYP _MOD_PROT(pgprot_kernel, L_PTE_HYP)
#define PAGE_HYP_DEVICE _MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
#define PAGE_S2 _MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
-#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_USER | L_PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE _MOD_PROT(pgprot_s2_device, L_PTE_S2_RDWR)
#define __PAGE_NONE __pgprot(_L_PTE_DEFAULT | L_PTE_RDONLY | L_PTE_XN | L_PTE_NONE)
#define __PAGE_SHARED __pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_XN)
@@ -211,12 +214,16 @@
#define pte_clear(mm,addr,ptep) set_pte_ext(ptep, __pte(0), 0)
+#define pte_isset(pte, val) ((u32)(val) == (val) ? pte_val(pte) & (val) \
+ : !!(pte_val(pte) & (val)))
+#define pte_isclear(pte, val) (!(pte_val(pte) & (val)))
+
#define pte_none(pte) (!pte_val(pte))
-#define pte_present(pte) (pte_val(pte) & L_PTE_PRESENT)
-#define pte_write(pte) (!(pte_val(pte) & L_PTE_RDONLY))
-#define pte_dirty(pte) (pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte) (pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte) (!(pte_val(pte) & L_PTE_XN))
+#define pte_present(pte) (pte_isset((pte), L_PTE_PRESENT))
+#define pte_write(pte) (pte_isclear((pte), L_PTE_RDONLY))
+#define pte_dirty(pte) (pte_isset((pte), L_PTE_DIRTY))
+#define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG))
+#define pte_exec(pte) (pte_isclear((pte), L_PTE_XN))
#define pte_special(pte) (0)
#define pte_present_user(pte) (pte_present(pte) && (pte_val(pte) & L_PTE_USER))
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad..0cd7824 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -62,9 +62,19 @@
raw_spinlock_t pmu_lock;
};
+struct cpupmu_regs {
+ u32 pmc;
+ u32 pmcntenset;
+ u32 pmuseren;
+ u32 pmintenset;
+ u32 pmxevttype[8];
+ u32 pmxevtcnt[8];
+};
+
struct arm_pmu {
struct pmu pmu;
cpumask_t active_irqs;
+ cpumask_t valid_cpus;
char *name;
irqreturn_t (*handle_irq)(int irq_num, void *dev);
void (*enable)(struct perf_event *event);
@@ -81,6 +91,8 @@
int (*request_irq)(struct arm_pmu *, irq_handler_t handler);
void (*free_irq)(struct arm_pmu *);
int (*map_event)(struct perf_event *event);
+ void (*save_regs)(struct arm_pmu *, struct cpupmu_regs *);
+ void (*restore_regs)(struct arm_pmu *, struct cpupmu_regs *);
int num_events;
atomic_t active_events;
struct mutex reserve_mutex;
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 06e7d50..413f387 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -54,7 +54,6 @@
#define start_thread(regs,pc,sp) \
({ \
- unsigned long *stack = (unsigned long *)sp; \
memset(regs->uregs, 0, sizeof(regs->uregs)); \
if (current->personality & ADDR_LIMIT_32BIT) \
regs->ARM_cpsr = USR_MODE; \
@@ -65,9 +64,6 @@
regs->ARM_cpsr |= PSR_ENDSTATE; \
regs->ARM_pc = pc & ~1; /* pc */ \
regs->ARM_sp = sp; /* sp */ \
- regs->ARM_r2 = stack[2]; /* r2 (envp) */ \
- regs->ARM_r1 = stack[1]; /* r1 (argv) */ \
- regs->ARM_r0 = stack[0]; /* r0 (argc) */ \
nommu_start_thread(regs); \
})
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index ce0dbe7..f0a8627 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -16,6 +16,10 @@
#define PSCI_POWER_STATE_TYPE_STANDBY 0
#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL0 0
+#define PSCI_POWER_STATE_AFFINITY_LEVEL1 1
+#define PSCI_POWER_STATE_AFFINITY_LEVEL2 2
+#define PSCI_POWER_STATE_AFFINITY_LEVEL3 3
struct psci_power_state {
u16 id;
@@ -32,5 +36,22 @@
};
extern struct psci_operations psci_ops;
+extern struct smp_operations psci_smp_ops;
+#ifdef CONFIG_ARM_PSCI
+void psci_init(void);
+bool psci_smp_available(void);
+#else
+static inline void psci_init(void) { }
+static inline bool psci_smp_available(void) { return false; }
+#endif
+
+#ifdef CONFIG_ARM_PSCI
+extern int __init psci_probe(void);
+#else
+static inline int psci_probe(void)
+{
+ return -ENODEV;
+}
+#endif
#endif /* __ASM_ARM_PSCI_H */
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index d3a22be..610ccf3 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -81,6 +81,8 @@
extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
struct smp_operations {
#ifdef CONFIG_SMP
/*
diff --git a/arch/arm/include/asm/smp_scu.h b/arch/arm/include/asm/smp_scu.h
index 18d1693..1a292d8 100644
--- a/arch/arm/include/asm/smp_scu.h
+++ b/arch/arm/include/asm/smp_scu.h
@@ -11,7 +11,7 @@
static inline bool scu_a9_has_base(void)
{
- return read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
+ return read_cpuid_part() == ARM_CPU_PART_CORTEX_A9;
}
static inline unsigned long scu_a9_get_base(void)
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 6220e9f..b07c09e 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -97,19 +97,22 @@
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
- unsigned long tmp;
+ unsigned long contended, res;
u32 slock;
- __asm__ __volatile__(
-" ldrex %0, [%2]\n"
-" subs %1, %0, %0, ror #16\n"
-" addeq %0, %0, %3\n"
-" strexeq %1, %0, [%2]"
- : "=&r" (slock), "=&r" (tmp)
- : "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
- : "cc");
+ do {
+ __asm__ __volatile__(
+ " ldrex %0, [%3]\n"
+ " mov %2, #0\n"
+ " subs %1, %0, %0, ror #16\n"
+ " addeq %0, %0, %4\n"
+ " strexeq %2, %0, [%3]"
+ : "=&r" (slock), "=&r" (contended), "=&r" (res)
+ : "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
+ : "cc");
+ } while (res);
- if (tmp == 0) {
+ if (!contended) {
smp_mb();
return 1;
} else {
@@ -165,17 +168,20 @@
static inline int arch_write_trylock(arch_rwlock_t *rw)
{
- unsigned long tmp;
+ unsigned long contended, res;
- __asm__ __volatile__(
-" ldrex %0, [%1]\n"
-" teq %0, #0\n"
-" strexeq %0, %2, [%1]"
- : "=&r" (tmp)
- : "r" (&rw->lock), "r" (0x80000000)
- : "cc");
+ do {
+ __asm__ __volatile__(
+ " ldrex %0, [%2]\n"
+ " mov %1, #0\n"
+ " teq %0, #0\n"
+ " strexeq %1, %3, [%2]"
+ : "=&r" (contended), "=&r" (res)
+ : "r" (&rw->lock), "r" (0x80000000)
+ : "cc");
+ } while (res);
- if (tmp == 0) {
+ if (!contended) {
smp_mb();
return 1;
} else {
@@ -251,18 +257,26 @@
static inline int arch_read_trylock(arch_rwlock_t *rw)
{
- unsigned long tmp, tmp2 = 1;
+ unsigned long contended, res;
- __asm__ __volatile__(
-" ldrex %0, [%2]\n"
-" adds %0, %0, #1\n"
-" strexpl %1, %0, [%2]\n"
- : "=&r" (tmp), "+r" (tmp2)
- : "r" (&rw->lock)
- : "cc");
+ do {
+ __asm__ __volatile__(
+ " ldrex %0, [%2]\n"
+ " mov %1, #0\n"
+ " adds %0, %0, #1\n"
+ " strexpl %1, %0, [%2]"
+ : "=&r" (contended), "=&r" (res)
+ : "r" (&rw->lock)
+ : "cc");
+ } while (res);
- smp_mb();
- return tmp2 == 0;
+ /* If the lock is negative, then it is already held for write. */
+ if (contended < 0x80000000) {
+ smp_mb();
+ return 1;
+ } else {
+ return 0;
+ }
}
/* read_can_lock - would read_trylock() succeed? */
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index f1d96d4..73ddd723 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -57,6 +57,9 @@
unsigned int i, unsigned int n,
unsigned long *args)
{
+ if (n == 0)
+ return;
+
if (i + n > SYSCALL_MAX_ARGS) {
unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -81,6 +84,9 @@
unsigned int i, unsigned int n,
const unsigned long *args)
{
+ if (n == 0)
+ return;
+
if (i + n > SYSCALL_MAX_ARGS) {
pr_warning("%s called with max args %d, handling only %d\n",
__func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 1995d1a..f00b569 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -156,7 +156,6 @@
#define TIF_USING_IWMMXT 17
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_RESTORE_SIGMASK 20
-#define TIF_SWITCH_MM 22 /* deferred switch_mm */
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index bdf2b84..0baf7f0 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
@@ -107,10 +108,12 @@
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
@@ -204,6 +207,12 @@
#endif
}
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+ tlb_add_flush(tlb, addr);
+}
+
#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
#define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index a3625d1..c374592 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -535,6 +535,8 @@
}
#endif
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
#endif
#endif /* CONFIG_MMU */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84..983fa7c 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -26,11 +26,45 @@
void init_cpu_topology(void);
void store_cpu_topology(unsigned int cpuid);
const struct cpumask *cpu_coregroup_mask(int cpu);
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 2, \
+ .idle_idx = 1, \
+ .newidle_idx = 0, \
+ .wake_idx = 0, \
+ .forkexec_idx = 0, \
+ \
+ .flags = 0*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 0*SD_BALANCE_WAKE \
+ | 1*SD_WAKE_AFFINE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
#else
static inline void init_cpu_topology(void) { }
static inline void store_cpu_topology(unsigned int cpuid) { }
+static inline int cluster_to_logical_mask(unsigned int socket_id,
+ cpumask_t *cluster_mask) { return -EINVAL; }
#endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7e1f760..20e1c99 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -164,8 +164,9 @@
#define __put_user_check(x,p) \
({ \
unsigned long __limit = current_thread_info()->addr_limit - 1; \
+ const typeof(*(p)) __user *__tmp_p = (p); \
register const typeof(*(p)) __r2 asm("r2") = (x); \
- register const typeof(*(p)) __user *__p asm("r0") = (p);\
+ register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
switch (sizeof(*(__p))) { \
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 141baa3..cbd6197 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -48,6 +48,5 @@
*/
#define __IGNORE_fadvise64_64
#define __IGNORE_migrate_pages
-#define __IGNORE_kcmp
#endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 47bcb2d..18d76fd 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -1,7 +1,6 @@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += a.out.h
header-y += byteorder.h
header-y += fcntl.h
header-y += hwcap.h
diff --git a/arch/arm/include/uapi/asm/a.out.h b/arch/arm/include/uapi/asm/a.out.h
deleted file mode 100644
index 083894b..0000000
--- a/arch/arm/include/uapi/asm/a.out.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ARM_A_OUT_H__
-#define __ARM_A_OUT_H__
-
-#include <linux/personality.h>
-#include <linux/types.h>
-
-struct exec
-{
- __u32 a_info; /* Use macros N_MAGIC, etc for access */
- __u32 a_text; /* length of text, in bytes */
- __u32 a_data; /* length of data, in bytes */
- __u32 a_bss; /* length of uninitialized data area for file, in bytes */
- __u32 a_syms; /* length of symbol table data in file, in bytes */
- __u32 a_entry; /* start address */
- __u32 a_trsize; /* length of relocation info for text, in bytes */
- __u32 a_drsize; /* length of relocation info for data, in bytes */
-};
-
-/*
- * This is always the same
- */
-#define N_TXTADDR(a) (0x00008000)
-
-#define N_TRSIZE(a) ((a).a_trsize)
-#define N_DRSIZE(a) ((a).a_drsize)
-#define N_SYMSIZE(a) ((a).a_syms)
-
-#define M_ARM 103
-
-#ifndef LIBRARY_START_TEXT
-#define LIBRARY_START_TEXT (0x00c00000)
-#endif
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/arch/arm/include/uapi/asm/hwcap.h b/arch/arm/include/uapi/asm/hwcap.h
index 3688fd1..7dcc10d 100644
--- a/arch/arm/include/uapi/asm/hwcap.h
+++ b/arch/arm/include/uapi/asm/hwcap.h
@@ -25,6 +25,7 @@
#define HWCAP_IDIVT (1 << 18)
#define HWCAP_VFPD32 (1 << 19) /* set if VFP has 32 regs (not 16) */
#define HWCAP_IDIV (HWCAP_IDIVA | HWCAP_IDIVT)
-
+#define HWCAP_LPAE (1 << 20)
+#define HWCAP_EVTSTRM (1 << 21)
#endif /* _UAPI__ASMARM_HWCAP_H */
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index c1ee007..09ee408 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -20,10 +20,12 @@
#define __ARM_KVM_H__
#include <linux/types.h>
+#include <linux/psci.h>
#include <asm/ptrace.h>
#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -63,7 +65,8 @@
/* Supported Processor Types */
#define KVM_ARM_TARGET_CORTEX_A15 0
-#define KVM_ARM_NUM_TARGETS 1
+#define KVM_ARM_TARGET_CORTEX_A7 1
+#define KVM_ARM_NUM_TARGETS 2
/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
#define KVM_ARM_DEVICE_TYPE_SHIFT 0
@@ -82,6 +85,7 @@
#define KVM_VGIC_V2_CPU_SIZE 0x2000
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */
struct kvm_vcpu_init {
__u32 target;
@@ -118,6 +122,26 @@
#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800
#define KVM_REG_ARM_32_CRN_SHIFT 11
+#define ARM_CP15_REG_SHIFT_MASK(x,n) \
+ (((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
+
+#define __ARM_CP15_REG(op1,crn,crm,op2) \
+ (KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \
+ ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \
+ ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \
+ ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \
+ ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2))
+
+#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32)
+
+#define __ARM_CP15_REG64(op1,crm) \
+ (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
+#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
+
+#define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14)
+
/* Normal registers are mapped as coprocessor 16. */
#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT)
#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / 4)
@@ -142,6 +166,15 @@
#define KVM_REG_ARM_VFP_FPINST 0x1009
#define KVM_REG_ARM_VFP_FPINST2 0x100A
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
+#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
+#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
+#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_TYPE_SHIFT 24
@@ -172,9 +205,9 @@
#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2)
#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3)
-#define KVM_PSCI_RET_SUCCESS 0
-#define KVM_PSCI_RET_NI ((unsigned long)-1)
-#define KVM_PSCI_RET_INVAL ((unsigned long)-2)
-#define KVM_PSCI_RET_DENIED ((unsigned long)-3)
+#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
#endif /* __ARM_KVM_H__ */
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5f3338e..65160d5 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,13 +17,13 @@
obj-y := elf.o entry-armv.o entry-common.o irq.o opcodes.o \
process.o ptrace.o return_address.o sched_clock.o \
- setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
+ setup.o signal.o sigreturn_codes.o \
+ stacktrace.o sys_arm.o time.o traps.o
obj-$(CONFIG_ATAGS) += atags_parse.o
obj-$(CONFIG_ATAGS_PROC) += atags_proc.o
obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
-obj-$(CONFIG_OC_ETM) += etm.o
obj-$(CONFIG_CPU_IDLE) += cpuidle.o
obj-$(CONFIG_ISA_DMA_API) += dma.o
obj-$(CONFIG_FIQ) += fiq.o fiqasm.o
@@ -82,6 +82,9 @@
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o
-obj-$(CONFIG_ARM_PSCI) += psci.o
+ifeq ($(CONFIG_ARM_PSCI),y)
+obj-y += psci.o
+obj-$(CONFIG_SMP) += psci_smp.o
+endif
extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index ee68cce..776d918 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -168,6 +168,7 @@
DEFINE(VCPU_FIQ_REGS, offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
DEFINE(VCPU_CPSR, offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
+ DEFINE(VCPU_HCR, offsetof(struct kvm_vcpu, arch.hcr));
DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines));
DEFINE(VCPU_HSR, offsetof(struct kvm_vcpu, arch.fault.hsr));
DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar));
@@ -175,13 +176,13 @@
DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
#ifdef CONFIG_KVM_ARM_VGIC
DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu));
- DEFINE(VGIC_CPU_HCR, offsetof(struct vgic_cpu, vgic_hcr));
- DEFINE(VGIC_CPU_VMCR, offsetof(struct vgic_cpu, vgic_vmcr));
- DEFINE(VGIC_CPU_MISR, offsetof(struct vgic_cpu, vgic_misr));
- DEFINE(VGIC_CPU_EISR, offsetof(struct vgic_cpu, vgic_eisr));
- DEFINE(VGIC_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_elrsr));
- DEFINE(VGIC_CPU_APR, offsetof(struct vgic_cpu, vgic_apr));
- DEFINE(VGIC_CPU_LR, offsetof(struct vgic_cpu, vgic_lr));
+ DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+ DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+ DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+ DEFINE(VGIC_V2_CPU_EISR, offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+ DEFINE(VGIC_V2_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+ DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+ DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr));
#ifdef CONFIG_KVM_ARM_TIMER
DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c
index 90c50d4..5d1286d 100644
--- a/arch/arm/kernel/crash_dump.c
+++ b/arch/arm/kernel/crash_dump.c
@@ -39,7 +39,7 @@
if (!csize)
return 0;
- vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+ vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE);
if (!vaddr)
return -ENOMEM;
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 5859c8b..a44e7d1 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -212,7 +212,7 @@
}
if (!mdesc_best) {
const char *prop;
- long size;
+ int size;
early_print("\nError: unrecognized/unsupported "
"device tree compatible list:\n[ ");
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 582b405..45a68d6 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -192,6 +192,7 @@
svc_entry
mov r2, sp
dabt_helper
+ THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR
svc_exit r5 @ return from exception
UNWIND(.fnend )
ENDPROC(__dabt_svc)
@@ -415,9 +416,8 @@
bne __und_usr_thumb
sub r4, r2, #4 @ ARM instr at LR - 4
1: ldrt r0, [r4]
-#ifdef CONFIG_CPU_ENDIAN_BE8
- rev r0, r0 @ little endian instruction
-#endif
+ ARM_BE8(rev r0, r0) @ little endian instruction
+
@ r0 = 32-bit ARM instruction which caused the exception
@ r2 = PC value for the following instruction (:= regs->ARM_pc)
@ r4 = PC value for the faulting instruction
@@ -741,6 +741,18 @@
#endif
.endm
+ .macro kuser_pad, sym, size
+ .if (. - \sym) & 3
+ .rept 4 - (. - \sym) & 3
+ .byte 0
+ .endr
+ .endif
+ .rept (\size - (. - \sym)) / 4
+ .word 0xe7fddef1
+ .endr
+ .endm
+
+#ifdef CONFIG_KUSER_HELPERS
.align 5
.globl __kuser_helper_start
__kuser_helper_start:
@@ -831,18 +843,13 @@
#error "incoherent kernel configuration"
#endif
- /* pad to next slot */
- .rept (16 - (. - __kuser_cmpxchg64)/4)
- .word 0
- .endr
-
- .align 5
+ kuser_pad __kuser_cmpxchg64, 64
__kuser_memory_barrier: @ 0xffff0fa0
smp_dmb arm
usr_ret lr
- .align 5
+ kuser_pad __kuser_memory_barrier, 32
__kuser_cmpxchg: @ 0xffff0fc0
@@ -915,13 +922,14 @@
#endif
- .align 5
+ kuser_pad __kuser_cmpxchg, 32
__kuser_get_tls: @ 0xffff0fe0
ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init
usr_ret lr
mrc p15, 0, r0, c13, c0, 3 @ 0xffff0fe8 hardware TLS code
- .rep 4
+ kuser_pad __kuser_get_tls, 16
+ .rep 3
.word 0 @ 0xffff0ff0 software TLS value, then
.endr @ pad up to __kuser_helper_version
@@ -931,14 +939,16 @@
.globl __kuser_helper_end
__kuser_helper_end:
+#endif
+
THUMB( .thumb )
/*
* Vector stubs.
*
- * This code is copied to 0xffff0200 so we can use branches in the
- * vectors, rather than ldr's. Note that this code must not
- * exceed 0x300 bytes.
+ * This code is copied to 0xffff1000 so we can use branches in the
+ * vectors, rather than ldr's. Note that this code must not exceed
+ * a page size.
*
* Common stub entry macro:
* Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC
@@ -985,8 +995,17 @@
1:
.endm
- .globl __stubs_start
+ .section .stubs, "ax", %progbits
__stubs_start:
+ @ This must be the first word
+ .word vector_swi
+
+vector_rst:
+ ARM( swi SYS_ERROR0 )
+ THUMB( svc #0 )
+ THUMB( nop )
+ b vector_und
+
/*
* Interrupt dispatcher
*/
@@ -1081,6 +1100,16 @@
.align 5
/*=============================================================================
+ * Address exception handler
+ *-----------------------------------------------------------------------------
+ * These aren't too critical.
+ * (they're not supposed to happen, and won't happen in 32-bit data mode).
+ */
+
+vector_addrexcptn:
+ b vector_addrexcptn
+
+/*=============================================================================
* Undefined FIQs
*-----------------------------------------------------------------------------
* Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC
@@ -1093,45 +1122,19 @@
vector_fiq:
subs pc, lr, #4
-/*=============================================================================
- * Address exception handler
- *-----------------------------------------------------------------------------
- * These aren't too critical.
- * (they're not supposed to happen, and won't happen in 32-bit data mode).
- */
+ .globl vector_fiq_offset
+ .equ vector_fiq_offset, vector_fiq
-vector_addrexcptn:
- b vector_addrexcptn
-
-/*
- * We group all the following data together to optimise
- * for CPUs with separate I & D caches.
- */
- .align 5
-
-.LCvswi:
- .word vector_swi
-
- .globl __stubs_end
-__stubs_end:
-
- .equ stubs_offset, __vectors_start + 0x200 - __stubs_start
-
- .globl __vectors_start
+ .section .vectors, "ax", %progbits
__vectors_start:
- ARM( swi SYS_ERROR0 )
- THUMB( svc #0 )
- THUMB( nop )
- W(b) vector_und + stubs_offset
- W(ldr) pc, .LCvswi + stubs_offset
- W(b) vector_pabt + stubs_offset
- W(b) vector_dabt + stubs_offset
- W(b) vector_addrexcptn + stubs_offset
- W(b) vector_irq + stubs_offset
- W(b) vector_fiq + stubs_offset
-
- .globl __vectors_end
-__vectors_end:
+ W(b) vector_rst
+ W(b) vector_und
+ W(ldr) pc, __vectors_start + 0x1000
+ W(b) vector_pabt
+ W(b) vector_dabt
+ W(b) vector_addrexcptn
+ W(b) vector_irq
+ W(b) vector_fiq
.data
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index bc5bc0a..11d6891 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -362,6 +362,16 @@
str r0, [sp, #S_OLD_R0] @ Save OLD_R0
zero_fp
+#ifdef CONFIG_ALIGNMENT_TRAP
+ ldr ip, __cr_alignment
+ ldr ip, [ip]
+ mcr p15, 0, ip, c1, c0 @ update control register
+#endif
+
+ enable_irq
+ ct_user_exit
+ get_thread_info tsk
+
/*
* Get the system call number.
*/
@@ -375,13 +385,11 @@
#ifdef CONFIG_ARM_THUMB
tst r8, #PSR_T_BIT
movne r10, #0 @ no thumb OABI emulation
- ldreq r10, [lr, #-4] @ get SWI instruction
+ USER( ldreq r10, [lr, #-4] ) @ get SWI instruction
#else
- ldr r10, [lr, #-4] @ get SWI instruction
+ USER( ldr r10, [lr, #-4] ) @ get SWI instruction
#endif
-#ifdef CONFIG_CPU_ENDIAN_BE8
- rev r10, r10 @ little endian instruction
-#endif
+ ARM_BE8(rev r10, r10) @ little endian instruction
#elif defined(CONFIG_AEABI)
@@ -392,22 +400,13 @@
/* Legacy ABI only, possibly thumb mode. */
tst r8, #PSR_T_BIT @ this is SPSR from save_user_regs
addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in
- ldreq scno, [lr, #-4]
+ USER( ldreq scno, [lr, #-4] )
#else
/* Legacy ABI only. */
- ldr scno, [lr, #-4] @ get SWI instruction
+ USER( ldr scno, [lr, #-4] ) @ get SWI instruction
#endif
-#ifdef CONFIG_ALIGNMENT_TRAP
- ldr ip, __cr_alignment
- ldr ip, [ip]
- mcr p15, 0, ip, c1, c0 @ update control register
-#endif
- enable_irq
- ct_user_exit
-
- get_thread_info tsk
adr tbl, sys_call_table @ load syscall table pointer
#if defined(CONFIG_OABI_COMPAT)
@@ -442,6 +441,21 @@
eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back
bcs arm_syscall
b sys_ni_syscall @ not private func
+
+#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
+ /*
+ * We failed to handle a fault trying to access the page
+ * containing the swi instruction, but we're not really in a
+ * position to return -EFAULT. Instead, return back to the
+ * instruction and re-enter the user fault handling path trying
+ * to page it in. This will likely result in sending SEGV to the
+ * current task.
+ */
+9001:
+ sub lr, lr, #4
+ str lr, [sp, #S_PC]
+ b ret_fast_syscall
+#endif
ENDPROC(vector_swi)
/*
diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c
deleted file mode 100644
index 8ff0ecd..0000000
--- a/arch/arm/kernel/etm.c
+++ /dev/null
@@ -1,660 +0,0 @@
-/*
- * linux/arch/arm/kernel/etm.c
- *
- * Driver for ARM's Embedded Trace Macrocell and Embedded Trace Buffer.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/sysrq.h>
-#include <linux/device.h>
-#include <linux/clk.h>
-#include <linux/amba/bus.h>
-#include <linux/fs.h>
-#include <linux/uaccess.h>
-#include <linux/miscdevice.h>
-#include <linux/vmalloc.h>
-#include <linux/mutex.h>
-#include <linux/module.h>
-#include <asm/hardware/coresight.h>
-#include <asm/sections.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/*
- * ETM tracer state
- */
-struct tracectx {
- unsigned int etb_bufsz;
- void __iomem *etb_regs;
- void __iomem *etm_regs;
- unsigned long flags;
- int ncmppairs;
- int etm_portsz;
- struct device *dev;
- struct clk *emu_clk;
- struct mutex mutex;
-};
-
-static struct tracectx tracer;
-
-static inline bool trace_isrunning(struct tracectx *t)
-{
- return !!(t->flags & TRACER_RUNNING);
-}
-
-static int etm_setup_address_range(struct tracectx *t, int n,
- unsigned long start, unsigned long end, int exclude, int data)
-{
- u32 flags = ETMAAT_ARM | ETMAAT_IGNCONTEXTID | ETMAAT_NSONLY | \
- ETMAAT_NOVALCMP;
-
- if (n < 1 || n > t->ncmppairs)
- return -EINVAL;
-
- /* comparators and ranges are numbered starting with 1 as opposed
- * to bits in a word */
- n--;
-
- if (data)
- flags |= ETMAAT_DLOADSTORE;
- else
- flags |= ETMAAT_IEXEC;
-
- /* first comparator for the range */
- etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2));
- etm_writel(t, start, ETMR_COMP_VAL(n * 2));
-
- /* second comparator is right next to it */
- etm_writel(t, flags, ETMR_COMP_ACC_TYPE(n * 2 + 1));
- etm_writel(t, end, ETMR_COMP_VAL(n * 2 + 1));
-
- flags = exclude ? ETMTE_INCLEXCL : 0;
- etm_writel(t, flags | (1 << n), ETMR_TRACEENCTRL);
-
- return 0;
-}
-
-static int trace_start(struct tracectx *t)
-{
- u32 v;
- unsigned long timeout = TRACER_TIMEOUT;
-
- etb_unlock(t);
-
- etb_writel(t, 0, ETBR_FORMATTERCTRL);
- etb_writel(t, 1, ETBR_CTRL);
-
- etb_lock(t);
-
- /* configure etm */
- v = ETMCTRL_OPTS | ETMCTRL_PROGRAM | ETMCTRL_PORTSIZE(t->etm_portsz);
-
- if (t->flags & TRACER_CYCLE_ACC)
- v |= ETMCTRL_CYCLEACCURATE;
-
- etm_unlock(t);
-
- etm_writel(t, v, ETMR_CTRL);
-
- while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
- etm_lock(t);
- return -EFAULT;
- }
-
- etm_setup_address_range(t, 1, (unsigned long)_stext,
- (unsigned long)_etext, 0, 0);
- etm_writel(t, 0, ETMR_TRACEENCTRL2);
- etm_writel(t, 0, ETMR_TRACESSCTRL);
- etm_writel(t, 0x6f, ETMR_TRACEENEVT);
-
- v &= ~ETMCTRL_PROGRAM;
- v |= ETMCTRL_PORTSEL;
-
- etm_writel(t, v, ETMR_CTRL);
-
- timeout = TRACER_TIMEOUT;
- while (etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to deassert timed out\n");
- etm_lock(t);
- return -EFAULT;
- }
-
- etm_lock(t);
-
- t->flags |= TRACER_RUNNING;
-
- return 0;
-}
-
-static int trace_stop(struct tracectx *t)
-{
- unsigned long timeout = TRACER_TIMEOUT;
-
- etm_unlock(t);
-
- etm_writel(t, 0x440, ETMR_CTRL);
- while (!(etm_readl(t, ETMR_CTRL) & ETMCTRL_PROGRAM) && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for progbit to assert timed out\n");
- etm_lock(t);
- return -EFAULT;
- }
-
- etm_lock(t);
-
- etb_unlock(t);
- etb_writel(t, ETBFF_MANUAL_FLUSH, ETBR_FORMATTERCTRL);
-
- timeout = TRACER_TIMEOUT;
- while (etb_readl(t, ETBR_FORMATTERCTRL) &
- ETBFF_MANUAL_FLUSH && --timeout)
- ;
- if (!timeout) {
- dev_dbg(t->dev, "Waiting for formatter flush to commence "
- "timed out\n");
- etb_lock(t);
- return -EFAULT;
- }
-
- etb_writel(t, 0, ETBR_CTRL);
-
- etb_lock(t);
-
- t->flags &= ~TRACER_RUNNING;
-
- return 0;
-}
-
-static int etb_getdatalen(struct tracectx *t)
-{
- u32 v;
- int rp, wp;
-
- v = etb_readl(t, ETBR_STATUS);
-
- if (v & 1)
- return t->etb_bufsz;
-
- rp = etb_readl(t, ETBR_READADDR);
- wp = etb_readl(t, ETBR_WRITEADDR);
-
- if (rp > wp) {
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_WRITEADDR);
-
- return 0;
- }
-
- return wp - rp;
-}
-
-/* sysrq+v will always stop the running trace and leave it at that */
-static void etm_dump(void)
-{
- struct tracectx *t = &tracer;
- u32 first = 0;
- int length;
-
- if (!t->etb_regs) {
- printk(KERN_INFO "No tracing hardware found\n");
- return;
- }
-
- if (trace_isrunning(t))
- trace_stop(t);
-
- etb_unlock(t);
-
- length = etb_getdatalen(t);
-
- if (length == t->etb_bufsz)
- first = etb_readl(t, ETBR_WRITEADDR);
-
- etb_writel(t, first, ETBR_READADDR);
-
- printk(KERN_INFO "Trace buffer contents length: %d\n", length);
- printk(KERN_INFO "--- ETB buffer begin ---\n");
- for (; length; length--)
- printk("%08x", cpu_to_be32(etb_readl(t, ETBR_READMEM)));
- printk(KERN_INFO "\n--- ETB buffer end ---\n");
-
- /* deassert the overflow bit */
- etb_writel(t, 1, ETBR_CTRL);
- etb_writel(t, 0, ETBR_CTRL);
-
- etb_writel(t, 0, ETBR_TRIGGERCOUNT);
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_WRITEADDR);
-
- etb_lock(t);
-}
-
-static void sysrq_etm_dump(int key)
-{
- dev_dbg(tracer.dev, "Dumping ETB buffer\n");
- etm_dump();
-}
-
-static struct sysrq_key_op sysrq_etm_op = {
- .handler = sysrq_etm_dump,
- .help_msg = "etm-buffer-dump(v)",
- .action_msg = "etm",
-};
-
-static int etb_open(struct inode *inode, struct file *file)
-{
- if (!tracer.etb_regs)
- return -ENODEV;
-
- file->private_data = &tracer;
-
- return nonseekable_open(inode, file);
-}
-
-static ssize_t etb_read(struct file *file, char __user *data,
- size_t len, loff_t *ppos)
-{
- int total, i;
- long length;
- struct tracectx *t = file->private_data;
- u32 first = 0;
- u32 *buf;
-
- mutex_lock(&t->mutex);
-
- if (trace_isrunning(t)) {
- length = 0;
- goto out;
- }
-
- etb_unlock(t);
-
- total = etb_getdatalen(t);
- if (total == t->etb_bufsz)
- first = etb_readl(t, ETBR_WRITEADDR);
-
- etb_writel(t, first, ETBR_READADDR);
-
- length = min(total * 4, (int)len);
- buf = vmalloc(length);
-
- dev_dbg(t->dev, "ETB buffer length: %d\n", total);
- dev_dbg(t->dev, "ETB status reg: %x\n", etb_readl(t, ETBR_STATUS));
- for (i = 0; i < length / 4; i++)
- buf[i] = etb_readl(t, ETBR_READMEM);
-
- /* the only way to deassert overflow bit in ETB status is this */
- etb_writel(t, 1, ETBR_CTRL);
- etb_writel(t, 0, ETBR_CTRL);
-
- etb_writel(t, 0, ETBR_WRITEADDR);
- etb_writel(t, 0, ETBR_READADDR);
- etb_writel(t, 0, ETBR_TRIGGERCOUNT);
-
- etb_lock(t);
-
- length -= copy_to_user(data, buf, length);
- vfree(buf);
-
-out:
- mutex_unlock(&t->mutex);
-
- return length;
-}
-
-static int etb_release(struct inode *inode, struct file *file)
-{
- /* there's nothing to do here, actually */
- return 0;
-}
-
-static const struct file_operations etb_fops = {
- .owner = THIS_MODULE,
- .read = etb_read,
- .open = etb_open,
- .release = etb_release,
- .llseek = no_llseek,
-};
-
-static struct miscdevice etb_miscdev = {
- .name = "tracebuf",
- .minor = 0,
- .fops = &etb_fops,
-};
-
-static int etb_probe(struct amba_device *dev, const struct amba_id *id)
-{
- struct tracectx *t = &tracer;
- int ret = 0;
-
- ret = amba_request_regions(dev, NULL);
- if (ret)
- goto out;
-
- t->etb_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
- if (!t->etb_regs) {
- ret = -ENOMEM;
- goto out_release;
- }
-
- amba_set_drvdata(dev, t);
-
- etb_miscdev.parent = &dev->dev;
-
- ret = misc_register(&etb_miscdev);
- if (ret)
- goto out_unmap;
-
- t->emu_clk = clk_get(&dev->dev, "emu_src_ck");
- if (IS_ERR(t->emu_clk)) {
- dev_dbg(&dev->dev, "Failed to obtain emu_src_ck.\n");
- return -EFAULT;
- }
-
- clk_enable(t->emu_clk);
-
- etb_unlock(t);
- t->etb_bufsz = etb_readl(t, ETBR_DEPTH);
- dev_dbg(&dev->dev, "Size: %x\n", t->etb_bufsz);
-
- /* make sure trace capture is disabled */
- etb_writel(t, 0, ETBR_CTRL);
- etb_writel(t, 0x1000, ETBR_FORMATTERCTRL);
- etb_lock(t);
-
- dev_dbg(&dev->dev, "ETB AMBA driver initialized.\n");
-
-out:
- return ret;
-
-out_unmap:
- amba_set_drvdata(dev, NULL);
- iounmap(t->etb_regs);
-
-out_release:
- amba_release_regions(dev);
-
- return ret;
-}
-
-static int etb_remove(struct amba_device *dev)
-{
- struct tracectx *t = amba_get_drvdata(dev);
-
- amba_set_drvdata(dev, NULL);
-
- iounmap(t->etb_regs);
- t->etb_regs = NULL;
-
- clk_disable(t->emu_clk);
- clk_put(t->emu_clk);
-
- amba_release_regions(dev);
-
- return 0;
-}
-
-static struct amba_id etb_ids[] = {
- {
- .id = 0x0003b907,
- .mask = 0x0007ffff,
- },
- { 0, 0 },
-};
-
-static struct amba_driver etb_driver = {
- .drv = {
- .name = "etb",
- .owner = THIS_MODULE,
- },
- .probe = etb_probe,
- .remove = etb_remove,
- .id_table = etb_ids,
-};
-
-/* use a sysfs file "trace_running" to start/stop tracing */
-static ssize_t trace_running_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
-{
- return sprintf(buf, "%x\n", trace_isrunning(&tracer));
-}
-
-static ssize_t trace_running_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t n)
-{
- unsigned int value;
- int ret;
-
- if (sscanf(buf, "%u", &value) != 1)
- return -EINVAL;
-
- mutex_lock(&tracer.mutex);
- ret = value ? trace_start(&tracer) : trace_stop(&tracer);
- mutex_unlock(&tracer.mutex);
-
- return ret ? : n;
-}
-
-static struct kobj_attribute trace_running_attr =
- __ATTR(trace_running, 0644, trace_running_show, trace_running_store);
-
-static ssize_t trace_info_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
-{
- u32 etb_wa, etb_ra, etb_st, etb_fc, etm_ctrl, etm_st;
- int datalen;
-
- etb_unlock(&tracer);
- datalen = etb_getdatalen(&tracer);
- etb_wa = etb_readl(&tracer, ETBR_WRITEADDR);
- etb_ra = etb_readl(&tracer, ETBR_READADDR);
- etb_st = etb_readl(&tracer, ETBR_STATUS);
- etb_fc = etb_readl(&tracer, ETBR_FORMATTERCTRL);
- etb_lock(&tracer);
-
- etm_unlock(&tracer);
- etm_ctrl = etm_readl(&tracer, ETMR_CTRL);
- etm_st = etm_readl(&tracer, ETMR_STATUS);
- etm_lock(&tracer);
-
- return sprintf(buf, "Trace buffer len: %d\nComparator pairs: %d\n"
- "ETBR_WRITEADDR:\t%08x\n"
- "ETBR_READADDR:\t%08x\n"
- "ETBR_STATUS:\t%08x\n"
- "ETBR_FORMATTERCTRL:\t%08x\n"
- "ETMR_CTRL:\t%08x\n"
- "ETMR_STATUS:\t%08x\n",
- datalen,
- tracer.ncmppairs,
- etb_wa,
- etb_ra,
- etb_st,
- etb_fc,
- etm_ctrl,
- etm_st
- );
-}
-
-static struct kobj_attribute trace_info_attr =
- __ATTR(trace_info, 0444, trace_info_show, NULL);
-
-static ssize_t trace_mode_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
-{
- return sprintf(buf, "%d %d\n",
- !!(tracer.flags & TRACER_CYCLE_ACC),
- tracer.etm_portsz);
-}
-
-static ssize_t trace_mode_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t n)
-{
- unsigned int cycacc, portsz;
-
- if (sscanf(buf, "%u %u", &cycacc, &portsz) != 2)
- return -EINVAL;
-
- mutex_lock(&tracer.mutex);
- if (cycacc)
- tracer.flags |= TRACER_CYCLE_ACC;
- else
- tracer.flags &= ~TRACER_CYCLE_ACC;
-
- tracer.etm_portsz = portsz & 0x0f;
- mutex_unlock(&tracer.mutex);
-
- return n;
-}
-
-static struct kobj_attribute trace_mode_attr =
- __ATTR(trace_mode, 0644, trace_mode_show, trace_mode_store);
-
-static int etm_probe(struct amba_device *dev, const struct amba_id *id)
-{
- struct tracectx *t = &tracer;
- int ret = 0;
-
- if (t->etm_regs) {
- dev_dbg(&dev->dev, "ETM already initialized\n");
- ret = -EBUSY;
- goto out;
- }
-
- ret = amba_request_regions(dev, NULL);
- if (ret)
- goto out;
-
- t->etm_regs = ioremap_nocache(dev->res.start, resource_size(&dev->res));
- if (!t->etm_regs) {
- ret = -ENOMEM;
- goto out_release;
- }
-
- amba_set_drvdata(dev, t);
-
- mutex_init(&t->mutex);
- t->dev = &dev->dev;
- t->flags = TRACER_CYCLE_ACC;
- t->etm_portsz = 1;
-
- etm_unlock(t);
- (void)etm_readl(t, ETMMR_PDSR);
- /* dummy first read */
- (void)etm_readl(&tracer, ETMMR_OSSRR);
-
- t->ncmppairs = etm_readl(t, ETMR_CONFCODE) & 0xf;
- etm_writel(t, 0x440, ETMR_CTRL);
- etm_lock(t);
-
- ret = sysfs_create_file(&dev->dev.kobj,
- &trace_running_attr.attr);
- if (ret)
- goto out_unmap;
-
- /* failing to create any of these two is not fatal */
- ret = sysfs_create_file(&dev->dev.kobj, &trace_info_attr.attr);
- if (ret)
- dev_dbg(&dev->dev, "Failed to create trace_info in sysfs\n");
-
- ret = sysfs_create_file(&dev->dev.kobj, &trace_mode_attr.attr);
- if (ret)
- dev_dbg(&dev->dev, "Failed to create trace_mode in sysfs\n");
-
- dev_dbg(t->dev, "ETM AMBA driver initialized.\n");
-
-out:
- return ret;
-
-out_unmap:
- amba_set_drvdata(dev, NULL);
- iounmap(t->etm_regs);
-
-out_release:
- amba_release_regions(dev);
-
- return ret;
-}
-
-static int etm_remove(struct amba_device *dev)
-{
- struct tracectx *t = amba_get_drvdata(dev);
-
- amba_set_drvdata(dev, NULL);
-
- iounmap(t->etm_regs);
- t->etm_regs = NULL;
-
- amba_release_regions(dev);
-
- sysfs_remove_file(&dev->dev.kobj, &trace_running_attr.attr);
- sysfs_remove_file(&dev->dev.kobj, &trace_info_attr.attr);
- sysfs_remove_file(&dev->dev.kobj, &trace_mode_attr.attr);
-
- return 0;
-}
-
-static struct amba_id etm_ids[] = {
- {
- .id = 0x0003b921,
- .mask = 0x0007ffff,
- },
- { 0, 0 },
-};
-
-static struct amba_driver etm_driver = {
- .drv = {
- .name = "etm",
- .owner = THIS_MODULE,
- },
- .probe = etm_probe,
- .remove = etm_remove,
- .id_table = etm_ids,
-};
-
-static int __init etm_init(void)
-{
- int retval;
-
- retval = amba_driver_register(&etb_driver);
- if (retval) {
- printk(KERN_ERR "Failed to register etb\n");
- return retval;
- }
-
- retval = amba_driver_register(&etm_driver);
- if (retval) {
- amba_driver_unregister(&etb_driver);
- printk(KERN_ERR "Failed to probe etm\n");
- return retval;
- }
-
- /* not being able to install this handler is not fatal */
- (void)register_sysrq_key('v', &sysrq_etm_op);
-
- return 0;
-}
-
-device_initcall(etm_init);
-
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 2adda11..25442f4 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -47,6 +47,11 @@
#include <asm/irq.h>
#include <asm/traps.h>
+#define FIQ_OFFSET ({ \
+ extern void *vector_fiq_offset; \
+ (unsigned)&vector_fiq_offset; \
+ })
+
static unsigned long no_fiq_insn;
/* Default reacquire function
@@ -80,13 +85,16 @@
void set_fiq_handler(void *start, unsigned int length)
{
#if defined(CONFIG_CPU_USE_DOMAINS)
- memcpy((void *)0xffff001c, start, length);
+ void *base = (void *)0xffff0000;
#else
- memcpy(vectors_page + 0x1c, start, length);
+ void *base = vectors_page;
#endif
- flush_icache_range(0xffff001c, 0xffff001c + length);
+ unsigned offset = FIQ_OFFSET;
+
+ memcpy(base + offset, start, length);
+ flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
if (!vectors_high())
- flush_icache_range(0x1c, 0x1c + length);
+ flush_icache_range(offset, offset + length);
}
int claim_fiq(struct fiq_handler *f)
@@ -144,6 +152,7 @@
void __init init_FIQ(int start)
{
- no_fiq_insn = *(unsigned long *)0xffff001c;
+ unsigned offset = FIQ_OFFSET;
+ no_fiq_insn = *(unsigned long *)(0xffff0000 + offset);
fiq_start = start;
}
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 8bac553..2d1bf8c 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -77,6 +77,7 @@
__HEAD
ENTRY(stext)
+ ARM_BE8(setend be ) @ ensure we are in BE8 mode
THUMB( adr r9, BSYM(1f) ) @ Kernel is always entered in ARM.
THUMB( bx r9 ) @ If this is a Thumb-2 kernel,
@@ -109,7 +110,7 @@
sub r4, r3, r4 @ (PHYS_OFFSET - PAGE_OFFSET)
add r8, r8, r4 @ PHYS_OFFSET
#else
- ldr r8, =PHYS_OFFSET @ always constant in this case
+ ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case
#endif
/*
@@ -342,7 +343,6 @@
.long __turn_mmu_on_end
#if defined(CONFIG_SMP)
- __CPUINIT
ENTRY(secondary_startup)
/*
* Common entry point for secondary CPUs.
@@ -351,6 +351,9 @@
* the processor type - there is no need to check the machine type
* as it has already been validated by the primary processor.
*/
+
+ ARM_BE8(setend be) @ ensure we are in BE8 mode
+
#ifdef CONFIG_ARM_VIRT_EXT
bl __hyp_stub_install_secondary
#endif
@@ -584,8 +587,10 @@
b 2f
1: add r7, r3
ldrh ip, [r7, #2]
+ARM_BE8(rev16 ip, ip)
and ip, 0x8f00
orr ip, r6 @ mask in offset bits 31-24
+ARM_BE8(rev16 ip, ip)
strh ip, [r7, #2]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
@@ -594,8 +599,14 @@
#else
b 2f
1: ldr ip, [r7, r3]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ @ in BE8, we load data in BE, but instructions still in LE
+ bic ip, ip, #0xff000000
+ orr ip, ip, r6, lsl#24
+#else
bic ip, ip, #0x000000ff
orr ip, ip, r6 @ mask in offset bits 31-24
+#endif
str ip, [r7, r3]
2: cmp r4, r5
ldrcc r7, [r4], #4 @ use branch for delay slot
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 1fd749e..7eee611 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -29,6 +29,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/smp.h>
#include <linux/cpu_pm.h>
+#include <linux/coresight.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
@@ -36,7 +37,6 @@
#include <asm/hw_breakpoint.h>
#include <asm/kdebug.h>
#include <asm/traps.h>
-#include <asm/hardware/coresight.h>
/* Breakpoint currently in use for each BRP. */
static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
@@ -975,7 +975,7 @@
* Unconditionally clear the OS lock by writing a value
* other than CS_LAR_KEY to the access register.
*/
- ARM_DBG_WRITE(c1, c0, 4, ~CS_LAR_KEY);
+ ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK);
isb();
/*
@@ -1049,7 +1049,8 @@
static void __init pm_init(void)
{
- cpu_pm_register_notifier(&dbg_cpu_pm_nb);
+ if (has_ossr)
+ cpu_pm_register_notifier(&dbg_cpu_pm_nb);
}
#else
static inline void pm_init(void)
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 1315c4c..dbe2110 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -153,6 +153,8 @@
mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL
orr r7, r7, #3 @ PL1PCEN | PL1PCTEN
mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL
+ mov r7, #0
+ mcrr p15, 4, r7, r7, c14 @ CNTVOFF
1:
#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17..1e782bd 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -163,7 +163,7 @@
c = irq_data_get_irq_chip(d);
if (!c->irq_set_affinity)
pr_debug("IRQ%u: unable to set affinity\n", d->irq);
- else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+ else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
cpumask_copy(d->affinity, affinity);
return ret;
diff --git a/arch/arm/kernel/kprobes-common.c b/arch/arm/kernel/kprobes-common.c
index 18a7628..380c20f 100644
--- a/arch/arm/kernel/kprobes-common.c
+++ b/arch/arm/kernel/kprobes-common.c
@@ -14,6 +14,7 @@
#include <linux/kernel.h>
#include <linux/kprobes.h>
#include <asm/system_info.h>
+#include <asm/opcodes.h>
#include "kprobes.h"
@@ -305,7 +306,8 @@
if (handler) {
/* We can emulate the instruction in (possibly) modified form */
- asi->insn[0] = (insn & 0xfff00000) | (rn << 16) | reglist;
+ asi->insn[0] = __opcode_to_mem_arm((insn & 0xfff00000) |
+ (rn << 16) | reglist);
asi->insn_handler = handler;
return INSN_GOOD;
}
@@ -334,13 +336,14 @@
#ifdef CONFIG_THUMB2_KERNEL
if (thumb) {
u16 *thumb_insn = (u16 *)asi->insn;
- thumb_insn[1] = 0x4770; /* Thumb bx lr */
- thumb_insn[2] = 0x4770; /* Thumb bx lr */
+ /* Thumb bx lr */
+ thumb_insn[1] = __opcode_to_mem_thumb16(0x4770);
+ thumb_insn[2] = __opcode_to_mem_thumb16(0x4770);
return insn;
}
- asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+ asi->insn[1] = __opcode_to_mem_arm(0xe12fff1e); /* ARM bx lr */
#else
- asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+ asi->insn[1] = __opcode_to_mem_arm(0xe1a0f00e); /* mov pc, lr */
#endif
/* Make an ARM instruction unconditional */
if (insn < 0xe0000000)
@@ -360,12 +363,12 @@
if (thumb) {
u16 *ip = (u16 *)asi->insn;
if (is_wide_instruction(insn))
- *ip++ = insn >> 16;
- *ip++ = insn;
+ *ip++ = __opcode_to_mem_thumb16(insn >> 16);
+ *ip++ = __opcode_to_mem_thumb16(insn);
return;
}
#endif
- asi->insn[0] = insn;
+ asi->insn[0] = __opcode_to_mem_arm(insn);
}
/*
diff --git a/arch/arm/kernel/kprobes-thumb.c b/arch/arm/kernel/kprobes-thumb.c
index 6123daf..b82e798 100644
--- a/arch/arm/kernel/kprobes-thumb.c
+++ b/arch/arm/kernel/kprobes-thumb.c
@@ -163,9 +163,9 @@
enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi);
/* Fixup modified instruction to have halfwords in correct order...*/
- insn = asi->insn[0];
- ((u16 *)asi->insn)[0] = insn >> 16;
- ((u16 *)asi->insn)[1] = insn & 0xffff;
+ insn = __mem_to_opcode_arm(asi->insn[0]);
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn >> 16);
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0xffff);
return ret;
}
@@ -1153,7 +1153,7 @@
{
insn &= ~0x00ff;
insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
- ((u16 *)asi->insn)[0] = insn;
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(insn);
asi->insn_handler = t16_emulate_hiregs;
return INSN_GOOD;
}
@@ -1182,8 +1182,10 @@
* and call it with R9=SP and LR in the register list represented
* by R8.
*/
- ((u16 *)asi->insn)[0] = 0xe929; /* 1st half STMDB R9!,{} */
- ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */
+ /* 1st half STMDB R9!,{} */
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe929);
+ /* 2nd half (register list) */
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
asi->insn_handler = t16_emulate_push;
return INSN_GOOD;
}
@@ -1232,8 +1234,10 @@
* and call it with R9=SP and PC in the register list represented
* by R8.
*/
- ((u16 *)asi->insn)[0] = 0xe8b9; /* 1st half LDMIA R9!,{} */
- ((u16 *)asi->insn)[1] = insn & 0x1ff; /* 2nd half (register list) */
+ /* 1st half LDMIA R9!,{} */
+ ((u16 *)asi->insn)[0] = __opcode_to_mem_thumb16(0xe8b9);
+ /* 2nd half (register list) */
+ ((u16 *)asi->insn)[1] = __opcode_to_mem_thumb16(insn & 0x1ff);
asi->insn_handler = insn & 0x100 ? t16_emulate_pop_pc
: t16_emulate_pop_nopc;
return INSN_GOOD;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 170e9f3..1c6ece5 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -26,6 +26,7 @@
#include <linux/stop_machine.h>
#include <linux/stringify.h>
#include <asm/traps.h>
+#include <asm/opcodes.h>
#include <asm/cacheflush.h>
#include "kprobes.h"
@@ -62,10 +63,10 @@
#ifdef CONFIG_THUMB2_KERNEL
thumb = true;
addr &= ~1; /* Bit 0 would normally be set to indicate Thumb code */
- insn = ((u16 *)addr)[0];
+ insn = __mem_to_opcode_thumb16(((u16 *)addr)[0]);
if (is_wide_instruction(insn)) {
- insn <<= 16;
- insn |= ((u16 *)addr)[1];
+ u16 inst2 = __mem_to_opcode_thumb16(((u16 *)addr)[1]);
+ insn = __opcode_thumb32_compose(insn, inst2);
decode_insn = thumb32_kprobe_decode_insn;
} else
decode_insn = thumb16_kprobe_decode_insn;
@@ -73,7 +74,7 @@
thumb = false;
if (addr & 0x3)
return -EINVAL;
- insn = *p->addr;
+ insn = __mem_to_opcode_arm(*p->addr);
decode_insn = arm_kprobe_decode_insn;
#endif
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 4fb074c..70ae735 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -14,10 +14,11 @@
#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
+#include <asm/fncpy.h>
#include <asm/mach-types.h>
#include <asm/system_misc.h>
-extern const unsigned char relocate_new_kernel[];
+extern void relocate_new_kernel(void);
extern const unsigned int relocate_new_kernel_size;
extern unsigned long kexec_start_address;
@@ -73,6 +74,7 @@
crash_save_cpu(®s, smp_processor_id());
flush_cache_all();
+ set_cpu_online(smp_processor_id(), false);
atomic_dec(&waiting_for_crash_ipi);
while (1)
cpu_relax();
@@ -132,6 +134,8 @@
{
unsigned long page_list;
unsigned long reboot_code_buffer_phys;
+ unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
+ unsigned long reboot_entry_phys;
void *reboot_code_buffer;
if (num_online_cpus() > 1) {
@@ -155,16 +159,23 @@
/* copy our kernel relocation code to the control code page */
- memcpy(reboot_code_buffer,
- relocate_new_kernel, relocate_new_kernel_size);
+ reboot_entry = fncpy(reboot_code_buffer,
+ reboot_entry,
+ relocate_new_kernel_size);
+ reboot_entry_phys = (unsigned long)reboot_entry +
+ (reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
-
- flush_icache_range((unsigned long) reboot_code_buffer,
- (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
printk(KERN_INFO "Bye!\n");
if (kexec_reinit)
kexec_reinit();
- soft_restart(reboot_code_buffer_phys);
+ soft_restart(reboot_entry_phys);
+}
+
+void arch_crash_save_vmcoreinfo(void)
+{
+#ifdef CONFIG_ARM_LPAE
+ VMCOREINFO_CONFIG(ARM_LPAE);
+#endif
}
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 1e9be5d..1705ee8 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -24,6 +24,7 @@
#include <asm/sections.h>
#include <asm/smp_plat.h>
#include <asm/unwind.h>
+#include <asm/opcodes.h>
#ifdef CONFIG_XIP_KERNEL
/*
@@ -60,6 +61,7 @@
Elf32_Sym *sym;
const char *symname;
s32 offset;
+ u32 tmp;
#ifdef CONFIG_THUMB2_KERNEL
u32 upper, lower, sign, j1, j2;
#endif
@@ -95,7 +97,8 @@
case R_ARM_PC24:
case R_ARM_CALL:
case R_ARM_JUMP24:
- offset = (*(u32 *)loc & 0x00ffffff) << 2;
+ offset = __mem_to_opcode_arm(*(u32 *)loc);
+ offset = (offset & 0x00ffffff) << 2;
if (offset & 0x02000000)
offset -= 0x04000000;
@@ -111,9 +114,10 @@
}
offset >>= 2;
+ offset &= 0x00ffffff;
- *(u32 *)loc &= 0xff000000;
- *(u32 *)loc |= offset & 0x00ffffff;
+ *(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
+ *(u32 *)loc |= __opcode_to_mem_arm(offset);
break;
case R_ARM_V4BX:
@@ -121,8 +125,8 @@
* other bits to re-code instruction as
* MOV PC,Rm.
*/
- *(u32 *)loc &= 0xf000000f;
- *(u32 *)loc |= 0x01a0f000;
+ *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
+ *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
break;
case R_ARM_PREL31:
@@ -132,7 +136,7 @@
case R_ARM_MOVW_ABS_NC:
case R_ARM_MOVT_ABS:
- offset = *(u32 *)loc;
+ offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
offset = (offset ^ 0x8000) - 0x8000;
@@ -140,16 +144,18 @@
if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
offset >>= 16;
- *(u32 *)loc &= 0xfff0f000;
- *(u32 *)loc |= ((offset & 0xf000) << 4) |
- (offset & 0x0fff);
+ tmp &= 0xfff0f000;
+ tmp |= ((offset & 0xf000) << 4) |
+ (offset & 0x0fff);
+
+ *(u32 *)loc = __opcode_to_mem_arm(tmp);
break;
#ifdef CONFIG_THUMB2_KERNEL
case R_ARM_THM_CALL:
case R_ARM_THM_JUMP24:
- upper = *(u16 *)loc;
- lower = *(u16 *)(loc + 2);
+ upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+ lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* 25 bit signed address range (Thumb-2 BL and B.W
@@ -198,17 +204,20 @@
sign = (offset >> 24) & 1;
j1 = sign ^ (~(offset >> 23) & 1);
j2 = sign ^ (~(offset >> 22) & 1);
- *(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+ upper = (u16)((upper & 0xf800) | (sign << 10) |
((offset >> 12) & 0x03ff));
- *(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
- (j1 << 13) | (j2 << 11) |
- ((offset >> 1) & 0x07ff));
+ lower = (u16)((lower & 0xd000) |
+ (j1 << 13) | (j2 << 11) |
+ ((offset >> 1) & 0x07ff));
+
+ *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+ *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
case R_ARM_THM_MOVW_ABS_NC:
case R_ARM_THM_MOVT_ABS:
- upper = *(u16 *)loc;
- lower = *(u16 *)(loc + 2);
+ upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+ lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
/*
* MOVT/MOVW instructions encoding in Thumb-2:
@@ -229,12 +238,14 @@
if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
offset >>= 16;
- *(u16 *)loc = (u16)((upper & 0xfbf0) |
- ((offset & 0xf000) >> 12) |
- ((offset & 0x0800) >> 1));
- *(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
- ((offset & 0x0700) << 4) |
- (offset & 0x00ff));
+ upper = (u16)((upper & 0xfbf0) |
+ ((offset & 0xf000) >> 12) |
+ ((offset & 0x0800) >> 1));
+ lower = (u16)((lower & 0x8f00) |
+ ((offset & 0x0700) << 4) |
+ (offset & 0x00ff));
+ *(u16 *)loc = __opcode_to_mem_thumb16(upper);
+ *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
break;
#endif
@@ -296,6 +307,10 @@
maps[ARM_SEC_EXIT].unw_sec = s;
else if (strcmp(".ARM.exidx.devexit.text", secname) == 0)
maps[ARM_SEC_DEVEXIT].unw_sec = s;
+ else if (strcmp(".ARM.exidx.text.unlikely", secname) == 0)
+ maps[ARM_SEC_UNLIKELY].unw_sec = s;
+ else if (strcmp(".ARM.exidx.text.hot", secname) == 0)
+ maps[ARM_SEC_HOT].unw_sec = s;
else if (strcmp(".init.text", secname) == 0)
maps[ARM_SEC_INIT].txt_sec = s;
else if (strcmp(".devinit.text", secname) == 0)
@@ -306,6 +321,10 @@
maps[ARM_SEC_EXIT].txt_sec = s;
else if (strcmp(".devexit.text", secname) == 0)
maps[ARM_SEC_DEVEXIT].txt_sec = s;
+ else if (strcmp(".text.unlikely", secname) == 0)
+ maps[ARM_SEC_UNLIKELY].txt_sec = s;
+ else if (strcmp(".text.hot", secname) == 0)
+ maps[ARM_SEC_HOT].txt_sec = s;
}
for (i = 0; i < ARM_SEC_MAX; i++)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 8c3094d..b41749f 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
*/
#define pr_fmt(fmt) "hw perfevents: " fmt
+#include <linux/cpumask.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
@@ -53,7 +54,12 @@
static int
armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
{
- int mapping = (*event_map)[config];
+ int mapping;
+
+ if (config >= PERF_COUNT_HW_MAX)
+ return -ENOENT;
+
+ mapping = (*event_map)[config];
return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
}
@@ -81,6 +87,9 @@
return armpmu_map_cache_event(cache_map, config);
case PERF_TYPE_RAW:
return armpmu_map_raw_event(raw_event_mask, config);
+ default:
+ if (event->attr.type >= PERF_TYPE_MAX)
+ return armpmu_map_raw_event(raw_event_mask, config);
}
return -ENOENT;
@@ -158,6 +167,8 @@
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
/*
* ARM pmu always has to update the counter, so ignore
* PERF_EF_UPDATE, see comments in armpmu_start().
@@ -174,6 +185,8 @@
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
/*
* ARM pmu always has to reprogram the period, so ignore
* PERF_EF_RELOAD, see the comment below.
@@ -201,6 +214,9 @@
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return;
+
armpmu_stop(event, PERF_EF_UPDATE);
hw_events->events[idx] = NULL;
clear_bit(idx, hw_events->used_mask);
@@ -217,6 +233,10 @@
int idx;
int err = 0;
+ /* An event following a process won't be stopped earlier */
+ if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+ return 0;
+
perf_pmu_disable(event->pmu);
/* If we don't have a space for the counter then finish early. */
@@ -253,6 +273,9 @@
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
struct pmu *leader_pmu = event->group_leader->pmu;
+ if (is_software_event(event))
+ return 1;
+
if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
return 1;
@@ -295,11 +318,18 @@
struct arm_pmu *armpmu = (struct arm_pmu *) dev;
struct platform_device *plat_device = armpmu->plat_device;
struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
+ int ret;
+ u64 start_clock, finish_clock;
+ start_clock = sched_clock();
if (plat && plat->handle_irq)
- return plat->handle_irq(irq, dev, armpmu->handle_irq);
+ ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
else
- return armpmu->handle_irq(irq, dev);
+ ret = armpmu->handle_irq(irq, dev);
+ finish_clock = sched_clock();
+
+ perf_sample_event_took(finish_clock - start_clock);
+ return ret;
}
static void
@@ -416,6 +446,10 @@
int err = 0;
atomic_t *active_events = &armpmu->active_events;
+ if (event->cpu != -1 &&
+ !cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+ return -ENOENT;
+
/* does not support taken branch sampling */
if (has_branch_stack(event))
return -EOPNOTSUPP;
@@ -569,6 +603,7 @@
return;
}
+ perf_callchain_store(entry, regs->ARM_pc);
tail = (struct frame_tail __user *)regs->ARM_fp - 1;
while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 1f2740e..e0665b8 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -19,6 +19,7 @@
#define pr_fmt(fmt) "CPU PMU: " fmt
#include <linux/bitmap.h>
+#include <linux/cpu_pm.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/of.h>
@@ -31,33 +32,36 @@
#include <asm/pmu.h>
/* Set at runtime when we know what CPU type we are. */
-static struct arm_pmu *cpu_pmu;
+static DEFINE_PER_CPU(struct arm_pmu *, cpu_pmu);
static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
+static DEFINE_PER_CPU(struct cpupmu_regs, cpu_pmu_regs);
+
/*
* Despite the names, these two functions are CPU-specific and are used
* by the OProfile/perf code.
*/
const char *perf_pmu_name(void)
{
- if (!cpu_pmu)
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
+ if (!pmu)
return NULL;
- return cpu_pmu->name;
+ return pmu->name;
}
EXPORT_SYMBOL_GPL(perf_pmu_name);
int perf_num_counters(void)
{
- int max_events = 0;
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, 0);
- if (cpu_pmu != NULL)
- max_events = cpu_pmu->num_events;
+ if (!pmu)
+ return 0;
- return max_events;
+ return pmu->num_events;
}
EXPORT_SYMBOL_GPL(perf_num_counters);
@@ -75,11 +79,13 @@
{
int i, irq, irqs;
struct platform_device *pmu_device = cpu_pmu->plat_device;
+ int cpu = -1;
irqs = min(pmu_device->num_resources, num_possible_cpus());
for (i = 0; i < irqs; ++i) {
- if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+ cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
+ if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
continue;
irq = platform_get_irq(pmu_device, i);
if (irq >= 0)
@@ -91,6 +97,7 @@
{
int i, err, irq, irqs;
struct platform_device *pmu_device = cpu_pmu->plat_device;
+ int cpu = -1;
if (!pmu_device)
return -ENODEV;
@@ -103,6 +110,7 @@
for (i = 0; i < irqs; ++i) {
err = 0;
+ cpu = cpumask_next(cpu, &cpu_pmu->valid_cpus);
irq = platform_get_irq(pmu_device, i);
if (irq < 0)
continue;
@@ -112,7 +120,7 @@
* assume that we're running on a uniprocessor machine and
* continue. Otherwise, continue without this interrupt.
*/
- if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+ if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
irq, i);
continue;
@@ -126,7 +134,7 @@
return err;
}
- cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+ cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
}
return 0;
@@ -135,7 +143,7 @@
static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
{
int cpu;
- for_each_possible_cpu(cpu) {
+ for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
events->events = per_cpu(hw_events, cpu);
events->used_mask = per_cpu(used_mask, cpu);
@@ -148,7 +156,7 @@
/* Ensure the PMU has sane values out of reset. */
if (cpu_pmu->reset)
- on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+ on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
}
/*
@@ -160,21 +168,46 @@
static int __cpuinit cpu_pmu_notify(struct notifier_block *b,
unsigned long action, void *hcpu)
{
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, (long)hcpu);
+
if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
return NOTIFY_DONE;
- if (cpu_pmu && cpu_pmu->reset)
- cpu_pmu->reset(cpu_pmu);
+ if (pmu && pmu->reset)
+ pmu->reset(pmu);
else
return NOTIFY_DONE;
return NOTIFY_OK;
}
+static int cpu_pmu_pm_notify(struct notifier_block *b,
+ unsigned long action, void *hcpu)
+{
+ int cpu = smp_processor_id();
+ struct arm_pmu *pmu = per_cpu(cpu_pmu, cpu);
+ struct cpupmu_regs *pmuregs = &per_cpu(cpu_pmu_regs, cpu);
+
+ if (!pmu)
+ return NOTIFY_DONE;
+
+ if (action == CPU_PM_ENTER && pmu->save_regs) {
+ pmu->save_regs(pmu, pmuregs);
+ } else if (action == CPU_PM_EXIT && pmu->restore_regs) {
+ pmu->restore_regs(pmu, pmuregs);
+ }
+
+ return NOTIFY_OK;
+}
+
static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = {
.notifier_call = cpu_pmu_notify,
};
+static struct notifier_block __cpuinitdata cpu_pmu_pm_notifier = {
+ .notifier_call = cpu_pmu_pm_notify,
+};
+
/*
* PMU platform driver and devicetree bindings.
*/
@@ -201,51 +234,44 @@
static int probe_current_pmu(struct arm_pmu *pmu)
{
int cpu = get_cpu();
- unsigned long implementor = read_cpuid_implementor();
- unsigned long part_number = read_cpuid_part_number();
int ret = -ENODEV;
pr_info("probing PMU on CPU %d\n", cpu);
+ switch (read_cpuid_part()) {
/* ARM Ltd CPUs. */
- if (implementor == ARM_CPU_IMP_ARM) {
- switch (part_number) {
- case ARM_CPU_PART_ARM1136:
- case ARM_CPU_PART_ARM1156:
- case ARM_CPU_PART_ARM1176:
- ret = armv6pmu_init(pmu);
- break;
- case ARM_CPU_PART_ARM11MPCORE:
- ret = armv6mpcore_pmu_init(pmu);
- break;
- case ARM_CPU_PART_CORTEX_A8:
- ret = armv7_a8_pmu_init(pmu);
- break;
- case ARM_CPU_PART_CORTEX_A9:
- ret = armv7_a9_pmu_init(pmu);
- break;
- case ARM_CPU_PART_CORTEX_A5:
- ret = armv7_a5_pmu_init(pmu);
- break;
- case ARM_CPU_PART_CORTEX_A15:
- ret = armv7_a15_pmu_init(pmu);
- break;
- case ARM_CPU_PART_CORTEX_A7:
- ret = armv7_a7_pmu_init(pmu);
- break;
+ case ARM_CPU_PART_ARM1136:
+ case ARM_CPU_PART_ARM1156:
+ case ARM_CPU_PART_ARM1176:
+ ret = armv6pmu_init(pmu);
+ break;
+ case ARM_CPU_PART_ARM11MPCORE:
+ ret = armv6mpcore_pmu_init(pmu);
+ break;
+ case ARM_CPU_PART_CORTEX_A8:
+ ret = armv7_a8_pmu_init(pmu);
+ break;
+ case ARM_CPU_PART_CORTEX_A9:
+ ret = armv7_a9_pmu_init(pmu);
+ break;
+
+ default:
+ if (read_cpuid_implementor() == ARM_CPU_IMP_INTEL) {
+ switch (xscale_cpu_arch_version()) {
+ case ARM_CPU_XSCALE_ARCH_V1:
+ ret = xscale1pmu_init(pmu);
+ break;
+ case ARM_CPU_XSCALE_ARCH_V2:
+ ret = xscale2pmu_init(pmu);
+ break;
+ }
}
- /* Intel CPUs [xscale]. */
- } else if (implementor == ARM_CPU_IMP_INTEL) {
- switch (xscale_cpu_arch_version()) {
- case ARM_CPU_XSCALE_ARCH_V1:
- ret = xscale1pmu_init(pmu);
- break;
- case ARM_CPU_XSCALE_ARCH_V2:
- ret = xscale2pmu_init(pmu);
- break;
- }
+ break;
}
+ /* assume PMU support all the CPUs in this case */
+ cpumask_setall(&pmu->valid_cpus);
+
put_cpu();
return ret;
}
@@ -253,15 +279,10 @@
static int cpu_pmu_device_probe(struct platform_device *pdev)
{
const struct of_device_id *of_id;
- int (*init_fn)(struct arm_pmu *);
struct device_node *node = pdev->dev.of_node;
struct arm_pmu *pmu;
- int ret = -ENODEV;
-
- if (cpu_pmu) {
- pr_info("attempt to register multiple PMU devices!");
- return -ENOSPC;
- }
+ int ret = 0;
+ int cpu;
pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
if (!pmu) {
@@ -270,8 +291,28 @@
}
if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
- init_fn = of_id->data;
- ret = init_fn(pmu);
+ smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+ struct device_node *ncluster;
+ int cluster = -1;
+ cpumask_t sibling_mask;
+
+ ncluster = of_parse_phandle(node, "cluster", 0);
+ if (ncluster) {
+ int len;
+ const u32 *hwid;
+ hwid = of_get_property(ncluster, "reg", &len);
+ if (hwid && len == 4)
+ cluster = be32_to_cpup(hwid);
+ }
+ /* set sibling mask to all cpu mask if socket is not specified */
+ if (cluster == -1 ||
+ cluster_to_logical_mask(cluster, &sibling_mask))
+ cpumask_setall(&sibling_mask);
+
+ smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+ /* now set the valid_cpus after init */
+ cpumask_copy(&pmu->valid_cpus, &sibling_mask);
} else {
ret = probe_current_pmu(pmu);
}
@@ -281,10 +322,12 @@
goto out_free;
}
- cpu_pmu = pmu;
- cpu_pmu->plat_device = pdev;
- cpu_pmu_init(cpu_pmu);
- ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
+ for_each_cpu_mask(cpu, pmu->valid_cpus)
+ per_cpu(cpu_pmu, cpu) = pmu;
+
+ pmu->plat_device = pdev;
+ cpu_pmu_init(pmu);
+ ret = armpmu_register(pmu, -1);
if (!ret)
return 0;
@@ -313,9 +356,17 @@
if (err)
return err;
- err = platform_driver_register(&cpu_pmu_driver);
- if (err)
+ err = cpu_pm_register_notifier(&cpu_pmu_pm_notifier);
+ if (err) {
unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+ return err;
+ }
+
+ err = platform_driver_register(&cpu_pmu_driver);
+ if (err) {
+ cpu_pm_unregister_notifier(&cpu_pmu_pm_notifier);
+ unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+ }
return err;
}
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 039cffb..654db50 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -950,6 +950,51 @@
}
#endif
+static void armv7pmu_save_regs(struct arm_pmu *cpu_pmu,
+ struct cpupmu_regs *regs)
+{
+ unsigned int cnt;
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (regs->pmc));
+ if (!(regs->pmc & ARMV7_PMNC_E))
+ return;
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (regs->pmcntenset));
+ asm volatile("mrc p15, 0, %0, c9, c14, 0" : "=r" (regs->pmuseren));
+ asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (regs->pmintenset));
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (regs->pmxevtcnt[0]));
+ for (cnt = ARMV7_IDX_COUNTER0;
+ cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+ armv7_pmnc_select_counter(cnt);
+ asm volatile("mrc p15, 0, %0, c9, c13, 1"
+ : "=r"(regs->pmxevttype[cnt]));
+ asm volatile("mrc p15, 0, %0, c9, c13, 2"
+ : "=r"(regs->pmxevtcnt[cnt]));
+ }
+ return;
+}
+
+static void armv7pmu_restore_regs(struct arm_pmu *cpu_pmu,
+ struct cpupmu_regs *regs)
+{
+ unsigned int cnt;
+ if (!(regs->pmc & ARMV7_PMNC_E))
+ return;
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (regs->pmcntenset));
+ asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r" (regs->pmuseren));
+ asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (regs->pmintenset));
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (regs->pmxevtcnt[0]));
+ for (cnt = ARMV7_IDX_COUNTER0;
+ cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) {
+ armv7_pmnc_select_counter(cnt);
+ asm volatile("mcr p15, 0, %0, c9, c13, 1"
+ : : "r"(regs->pmxevttype[cnt]));
+ asm volatile("mcr p15, 0, %0, c9, c13, 2"
+ : : "r"(regs->pmxevtcnt[cnt]));
+ }
+ asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (regs->pmc));
+}
+
static void armv7pmu_enable_event(struct perf_event *event)
{
unsigned long flags;
@@ -1223,6 +1268,8 @@
cpu_pmu->start = armv7pmu_start;
cpu_pmu->stop = armv7pmu_stop;
cpu_pmu->reset = armv7pmu_reset;
+ cpu_pmu->save_regs = armv7pmu_save_regs;
+ cpu_pmu->restore_regs = armv7pmu_restore_regs;
cpu_pmu->max_period = (1LLU << 32) - 1;
};
@@ -1240,7 +1287,7 @@
static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A8";
+ cpu_pmu->name = "ARMv7_Cortex_A8";
cpu_pmu->map_event = armv7_a8_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1249,7 +1296,7 @@
static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A9";
+ cpu_pmu->name = "ARMv7_Cortex_A9";
cpu_pmu->map_event = armv7_a9_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1258,7 +1305,7 @@
static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A5";
+ cpu_pmu->name = "ARMv7_Cortex_A5";
cpu_pmu->map_event = armv7_a5_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
return 0;
@@ -1267,7 +1314,7 @@
static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A15";
+ cpu_pmu->name = "ARMv7_Cortex_A15";
cpu_pmu->map_event = armv7_a15_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1277,7 +1324,7 @@
static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
{
armv7pmu_init(cpu_pmu);
- cpu_pmu->name = "ARMv7 Cortex-A7";
+ cpu_pmu->name = "ARMv7_Cortex_A7";
cpu_pmu->map_event = armv7_a7_map_event;
cpu_pmu->num_events = armv7_read_num_pmnc_events();
cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 6e8931c..ac4c2e5 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -408,6 +408,7 @@
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
+ unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
@@ -416,9 +417,11 @@
frame.sp = thread_saved_sp(p);
frame.lr = 0; /* recovered from the stack */
frame.pc = thread_saved_pc(p);
+ stack_page = (unsigned long)task_stack_page(p);
do {
- int ret = unwind_frame(&frame);
- if (ret < 0)
+ if (frame.sp < stack_page ||
+ frame.sp >= stack_page + THREAD_SIZE ||
+ unwind_frame(&frame) < 0)
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
@@ -433,10 +436,11 @@
}
#ifdef CONFIG_MMU
+#ifdef CONFIG_KUSER_HELPERS
/*
* The vectors page is always readable from user space for the
- * atomic helpers and the signal restart code. Insert it into the
- * gate_vma so that it is visible through ptrace and /proc/<pid>/mem.
+ * atomic helpers. Insert it into the gate_vma so that it is visible
+ * through ptrace and /proc/<pid>/mem.
*/
static struct vm_area_struct gate_vma = {
.vm_start = 0xffff0000,
@@ -465,9 +469,48 @@
{
return in_gate_area(NULL, addr);
}
+#define is_gate_vma(vma) ((vma) == &gate_vma)
+#else
+#define is_gate_vma(vma) 0
+#endif
const char *arch_vma_name(struct vm_area_struct *vma)
{
- return (vma == &gate_vma) ? "[vectors]" : NULL;
+ return is_gate_vma(vma) ? "[vectors]" :
+ (vma->vm_mm && vma->vm_start == vma->vm_mm->context.sigpage) ?
+ "[sigpage]" : NULL;
+}
+
+static struct page *signal_page;
+extern struct page *get_signal_page(void);
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long addr;
+ int ret;
+
+ if (!signal_page)
+ signal_page = get_signal_page();
+ if (!signal_page)
+ return -ENOMEM;
+
+ down_write(&mm->mmap_sem);
+ addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
+ }
+
+ ret = install_special_mapping(mm, addr, PAGE_SIZE,
+ VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
+ &signal_page);
+
+ if (ret == 0)
+ mm->context.sigpage = addr;
+
+ up_fail:
+ up_write(&mm->mmap_sem);
+ return ret;
}
#endif
diff --git a/arch/arm/kernel/psci.c b/arch/arm/kernel/psci.c
index 3653164..0daf4f2 100644
--- a/arch/arm/kernel/psci.c
+++ b/arch/arm/kernel/psci.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/of.h>
+#include <linux/string.h>
#include <asm/compiler.h>
#include <asm/errno.h>
@@ -26,6 +27,11 @@
struct psci_operations psci_ops;
+/* Type of psci support. Currently can only be enabled or disabled */
+#define PSCI_SUP_DISABLED 0
+#define PSCI_SUP_ENABLED 1
+
+static unsigned int psci;
static int (*invoke_psci_fn)(u32, u32, u32, u32);
enum psci_function {
@@ -42,6 +48,7 @@
#define PSCI_RET_EOPNOTSUPP -1
#define PSCI_RET_EINVAL -2
#define PSCI_RET_EPERM -3
+#define PSCI_RET_EALREADYON -4
static int psci_to_linux_errno(int errno)
{
@@ -54,6 +61,8 @@
return -EINVAL;
case PSCI_RET_EPERM:
return -EPERM;
+ case PSCI_RET_EALREADYON:
+ return -EAGAIN;
};
return -EINVAL;
@@ -158,15 +167,18 @@
{},
};
-static int __init psci_init(void)
+void __init psci_init(void)
{
struct device_node *np;
const char *method;
u32 id;
+ if (psci == PSCI_SUP_DISABLED)
+ return;
+
np = of_find_matching_node(NULL, psci_of_match);
if (!np)
- return 0;
+ return;
pr_info("probing function IDs from device-tree\n");
@@ -206,6 +218,35 @@
out_put_node:
of_node_put(np);
- return 0;
+ return;
}
-early_initcall(psci_init);
+
+int __init psci_probe(void)
+{
+ struct device_node *np;
+ int ret = -ENODEV;
+
+ if (psci == PSCI_SUP_ENABLED) {
+ np = of_find_matching_node(NULL, psci_of_match);
+ if (np)
+ ret = 0;
+ }
+
+ of_node_put(np);
+ return ret;
+}
+
+static int __init early_psci(char *val)
+{
+ int ret = 0;
+
+ if (strcmp(val, "enable") == 0)
+ psci = PSCI_SUP_ENABLED;
+ else if (strcmp(val, "disable") == 0)
+ psci = PSCI_SUP_DISABLED;
+ else
+ ret = -EINVAL;
+
+ return ret;
+}
+early_param("psci", early_psci);
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
new file mode 100644
index 0000000..23a1142
--- /dev/null
+++ b/arch/arm/kernel/psci_smp.c
@@ -0,0 +1,84 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/init.h>
+#include <linux/irqchip/arm-gic.h>
+#include <linux/smp.h>
+#include <linux/of.h>
+
+#include <asm/psci.h>
+#include <asm/smp_plat.h>
+
+/*
+ * psci_smp assumes that the following is true about PSCI:
+ *
+ * cpu_suspend Suspend the execution on a CPU
+ * @state we don't currently describe affinity levels, so just pass 0.
+ * @entry_point the first instruction to be executed on return
+ * returns 0 success, < 0 on failure
+ *
+ * cpu_off Power down a CPU
+ * @state we don't currently describe affinity levels, so just pass 0.
+ * no return on successful call
+ *
+ * cpu_on Power up a CPU
+ * @cpuid cpuid of target CPU, as from MPIDR
+ * @entry_point the first instruction to be executed on return
+ * returns 0 success, < 0 on failure
+ *
+ * migrate Migrate the context to a different CPU
+ * @cpuid cpuid of target CPU, as from MPIDR
+ * returns 0 success, < 0 on failure
+ *
+ */
+
+extern void secondary_startup(void);
+
+static int __cpuinit psci_boot_secondary(unsigned int cpu,
+ struct task_struct *idle)
+{
+ if (psci_ops.cpu_on)
+ return psci_ops.cpu_on(cpu_logical_map(cpu),
+ __pa(secondary_startup));
+ return -ENODEV;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void __ref psci_cpu_die(unsigned int cpu)
+{
+ const struct psci_power_state ps = {
+ .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+ };
+
+ if (psci_ops.cpu_off)
+ psci_ops.cpu_off(ps);
+
+ /* We should never return */
+ panic("psci: cpu %d failed to shutdown\n", cpu);
+}
+#else
+#define psci_cpu_die NULL
+#endif
+
+bool __init psci_smp_available(void)
+{
+ /* is cpu_on available at least? */
+ return (psci_ops.cpu_on != NULL);
+}
+
+struct smp_operations __initdata psci_smp_ops = {
+ .smp_boot_secondary = psci_boot_secondary,
+ .cpu_die = psci_cpu_die,
+};
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index d0cdedf..9585896 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -2,10 +2,12 @@
* relocate_kernel.S - put the kernel image in place to boot
*/
+#include <linux/linkage.h>
#include <asm/kexec.h>
- .globl relocate_new_kernel
-relocate_new_kernel:
+ .align 3 /* not needed for this code, but keeps fncpy() happy */
+
+ENTRY(relocate_new_kernel)
ldr r0,kexec_indirection_page
ldr r1,kexec_start_address
@@ -79,6 +81,8 @@
kexec_boot_atags:
.long 0x0
+ENDPROC(relocate_new_kernel)
+
relocate_new_kernel_end:
.globl relocate_new_kernel_size
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index e8edcaa..a57cc5d 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -51,10 +51,11 @@
return (cyc * mult) >> shift;
}
-static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace sched_clock_32(void)
{
u64 epoch_ns;
u32 epoch_cyc;
+ u32 cyc;
if (cd.suspended)
return cd.epoch_ns;
@@ -73,7 +74,9 @@
smp_rmb();
} while (epoch_cyc != cd.epoch_cyc_copy);
- return epoch_ns + cyc_to_ns((cyc - epoch_cyc) & mask, cd.mult, cd.shift);
+ cyc = read_sched_clock();
+ cyc = (cyc - epoch_cyc) & sched_clock_mask;
+ return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift);
}
/*
@@ -165,12 +168,6 @@
pr_debug("Registered %pF as sched_clock source\n", read);
}
-static unsigned long long notrace sched_clock_32(void)
-{
- u32 cyc = read_sched_clock();
- return cyc_to_sched_clock(cyc, sched_clock_mask);
-}
-
unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32;
unsigned long long notrace sched_clock(void)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index b4b1d39..29beb8c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -37,6 +37,7 @@
#include <asm/cputype.h>
#include <asm/elf.h>
#include <asm/procinfo.h>
+#include <asm/psci.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -261,6 +262,19 @@
int aliasing_icache;
unsigned int id_reg, num_sets, line_size;
+#ifdef CONFIG_BIG_LITTLE
+ /*
+ * We expect a combination of Cortex-A15 and Cortex-A7 cores.
+ * A7 = VIPT aliasing I-cache
+ * A15 = PIPT (non-aliasing) I-cache
+ * To cater for this discrepancy, let's assume aliasing I-cache
+ * all the time. This means unneeded extra work on the A15 but
+ * only ptrace is affected which is not performance critical.
+ */
+ if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc0f0)
+ return 1;
+#endif
+
/* PIPT caches never alias. */
if (icache_is_pipt())
return 0;
@@ -530,6 +544,7 @@
int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
{
struct membank *bank = &meminfo.bank[meminfo.nr_banks];
+ u64 aligned_start;
if (meminfo.nr_banks >= NR_BANKS) {
printk(KERN_CRIT "NR_BANKS too low, "
@@ -542,10 +557,16 @@
* Size is appropriately rounded down, start is rounded up.
*/
size -= start & ~PAGE_MASK;
- bank->start = PAGE_ALIGN(start);
+ aligned_start = PAGE_ALIGN(start);
-#ifndef CONFIG_ARM_LPAE
- if (bank->start + size < bank->start) {
+#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+ if (aligned_start > ULONG_MAX) {
+ printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
+ "32-bit physical address space\n", (long long)start);
+ return -EINVAL;
+ }
+
+ if (aligned_start + size > ULONG_MAX) {
printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
"32-bit physical address space\n", (long long)start);
/*
@@ -553,10 +574,25 @@
* 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
* This means we lose a page after masking.
*/
- size = ULONG_MAX - bank->start;
+ size = ULONG_MAX - aligned_start;
}
#endif
+ if (aligned_start < PHYS_OFFSET) {
+ if (aligned_start + size <= PHYS_OFFSET) {
+ pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+ aligned_start, aligned_start + size);
+ return -EINVAL;
+ }
+
+ pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n",
+ aligned_start, (u64)PHYS_OFFSET);
+
+ size -= PHYS_OFFSET - aligned_start;
+ aligned_start = PHYS_OFFSET;
+ }
+
+ bank->start = aligned_start;
bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
/*
@@ -796,9 +832,15 @@
unflatten_device_tree();
arm_dt_init_cpu_maps();
+ psci_init();
#ifdef CONFIG_SMP
if (is_smp()) {
- smp_set_ops(mdesc->smp);
+ if (!mdesc->smp_init || !mdesc->smp_init()) {
+ if (psci_smp_available())
+ smp_set_ops(&psci_smp_ops);
+ else if (mdesc->smp)
+ smp_set_ops(mdesc->smp);
+ }
smp_init_cpus();
}
#endif
@@ -872,6 +914,9 @@
"vfpv4",
"idiva",
"idivt",
+ "vfpd32",
+ "lpae",
+ "evtstrm",
NULL
};
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 296786b..3c23086 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -8,6 +8,7 @@
* published by the Free Software Foundation.
*/
#include <linux/errno.h>
+#include <linux/random.h>
#include <linux/signal.h>
#include <linux/personality.h>
#include <linux/uaccess.h>
@@ -15,35 +16,14 @@
#include <asm/elf.h>
#include <asm/cacheflush.h>
+#include <asm/traps.h>
#include <asm/ucontext.h>
#include <asm/unistd.h>
#include <asm/vfp.h>
-#include "signal.h"
+extern const unsigned long sigreturn_codes[7];
-/*
- * For ARM syscalls, we encode the syscall number into the instruction.
- */
-#define SWI_SYS_SIGRETURN (0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-#define SWI_SYS_RT_SIGRETURN (0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-
-/*
- * With EABI, the syscall number has to be loaded into r7.
- */
-#define MOV_R7_NR_SIGRETURN (0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-/*
- * For Thumb syscalls, we pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-#define SWI_THUMB_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define SWI_THUMB_RT_SIGRETURN (0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-const unsigned long sigreturn_codes[7] = {
- MOV_R7_NR_SIGRETURN, SWI_SYS_SIGRETURN, SWI_THUMB_SIGRETURN,
- MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
-};
+static unsigned long signal_return_offset;
#ifdef CONFIG_CRUNCH
static int preserve_crunch_context(struct crunch_sigframe __user *frame)
@@ -396,13 +376,19 @@
__put_user(sigreturn_codes[idx+1], rc+1))
return 1;
+#ifdef CONFIG_MMU
if (cpsr & MODE32_BIT) {
+ struct mm_struct *mm = current->mm;
/*
- * 32-bit code can use the new high-page
- * signal return code support.
+ * 32-bit code can use the signal return page
+ * except when the MPU has protected the vectors
+ * page from PL0
*/
- retcode = KERN_SIGRETURN_CODE + (idx << 2) + thumb;
- } else {
+ retcode = mm->context.sigpage + signal_return_offset +
+ (idx << 2) + thumb;
+ } else
+#endif
+ {
/*
* Ensure that the instruction cache sees
* the return code written onto the stack.
@@ -603,3 +589,33 @@
} while (thread_flags & _TIF_WORK_MASK);
return 0;
}
+
+struct page *get_signal_page(void)
+{
+ unsigned long ptr;
+ unsigned offset;
+ struct page *page;
+ void *addr;
+
+ page = alloc_pages(GFP_KERNEL, 0);
+
+ if (!page)
+ return NULL;
+
+ addr = page_address(page);
+
+ /* Give the signal return code some randomness */
+ offset = 0x200 + (get_random_int() & 0x7fc);
+ signal_return_offset = offset;
+
+ /*
+ * Copy signal return handlers into the vector page, and
+ * set sigreturn to be a pointer to these.
+ */
+ memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes));
+
+ ptr = (unsigned long)addr + offset;
+ flush_icache_range(ptr, ptr + sizeof(sigreturn_codes));
+
+ return page;
+}
diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h
deleted file mode 100644
index 5ff067b7..0000000
--- a/arch/arm/kernel/signal.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * linux/arch/arm/kernel/signal.h
- *
- * Copyright (C) 2005-2009 Russell King.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define KERN_SIGRETURN_CODE (CONFIG_VECTORS_BASE + 0x00000500)
-
-extern const unsigned long sigreturn_codes[7];
diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S
new file mode 100644
index 0000000..3c5d0f2
--- /dev/null
+++ b/arch/arm/kernel/sigreturn_codes.S
@@ -0,0 +1,80 @@
+/*
+ * sigreturn_codes.S - code sinpets for sigreturn syscalls
+ *
+ * Created by: Victor Kamensky, 2013-08-13
+ * Copyright: (C) 2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <asm/unistd.h>
+
+/*
+ * For ARM syscalls, we encode the syscall number into the instruction.
+ * With EABI, the syscall number has to be loaded into r7. As result
+ * ARM syscall sequence snippet will have move and svc in .arm encoding
+ *
+ * For Thumb syscalls, we pass the syscall number via r7. We therefore
+ * need two 16-bit instructions in .thumb encoding
+ *
+ * Please note sigreturn_codes code are not executed in place. Instead
+ * they just copied by kernel into appropriate places. Code inside of
+ * arch/arm/kernel/signal.c is very sensitive to layout of these code
+ * snippets.
+ */
+
+#if __LINUX_ARM_ARCH__ <= 4
+ /*
+ * Note we manually set minimally required arch that supports
+ * required thumb opcodes for early arch versions. It is OK
+ * for this file to be used in combination with other
+ * lower arch variants, since these code snippets are only
+ * used as input data.
+ */
+ .arch armv4t
+#endif
+
+ .section .rodata
+ .global sigreturn_codes
+ .type sigreturn_codes, #object
+
+ .arm
+
+sigreturn_codes:
+
+ /* ARM sigreturn syscall code snippet */
+ mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+ swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+ /* Thumb sigreturn syscall code snippet */
+ .thumb
+ movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+ swi #0
+
+ /* ARM sigreturn_rt syscall code snippet */
+ .arm
+ mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+ swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+ /* Thumb sigreturn_rt syscall code snippet */
+ .thumb
+ movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+ swi #0
+
+ /*
+ * Note on addtional space: setup_return in signal.c
+ * algorithm uses two words copy regardless whether
+ * it is thumb case or not, so we need additional
+ * word after real last entry.
+ */
+ .arm
+ .space 4
+
+ .size sigreturn_codes, . - sigreturn_codes
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 987dcf3..baf4d28 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -4,6 +4,7 @@
#include <asm/assembler.h>
#include <asm/glue-cache.h>
#include <asm/glue-proc.h>
+#include "entry-header.S"
.text
/*
@@ -30,9 +31,8 @@
mov r2, r5 @ virtual SP
ldr r3, =sleep_save_sp
#ifdef CONFIG_SMP
- ALT_SMP(mrc p15, 0, lr, c0, c0, 5)
- ALT_UP(mov lr, #0)
- and lr, lr, #15
+ get_thread_info r5
+ ldr lr, [r5, #TI_CPU] @ cpu logical index
add r3, r3, lr, lsl #2
#endif
bl __cpu_suspend_save
@@ -81,11 +81,15 @@
.data
.align
ENTRY(cpu_resume)
+ARM_BE8(setend be) @ ensure we are in BE mode
#ifdef CONFIG_SMP
+ mov r1, #0 @ fall-back logical index for UP
+ ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
+ ALT_UP_B(1f)
+ bic r0, #0xff000000
+ bl cpu_logical_index @ return logical index in r1
+1:
adr r0, sleep_save_sp
- ALT_SMP(mrc p15, 0, r1, c0, c0, 5)
- ALT_UP(mov r1, #0)
- and r1, r1, #15
ldr r0, [r0, r1, lsl #2] @ stack phys addr
#else
ldr r0, sleep_save_sp @ stack phys addr
@@ -102,3 +106,20 @@
.rept CONFIG_NR_CPUS
.long 0 @ preserve stack phys ptr here
.endr
+
+#ifdef CONFIG_SMP
+cpu_logical_index:
+ adr r3, cpu_map_ptr
+ ldr r2, [r3]
+ add r3, r3, r2 @ virt_to_phys(__cpu_logical_map)
+ mov r1, #0
+1:
+ ldr r2, [r3, r1, lsl #2]
+ cmp r2, r0
+ moveq pc, lr
+ add r1, r1, #1
+ b 1b
+
+cpu_map_ptr:
+ .long __cpu_logical_map - .
+#endif
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 5919eb4..d6e3d1c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -46,6 +46,9 @@
#include <asm/virt.h>
#include <asm/mach/arch.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/arm-ipi.h>
+
/*
* as from 2.5, kernels no longer have an init_tasks structure
* so we need some other way of telling a new secondary core
@@ -57,7 +60,7 @@
* control for which core is the next to come out of the secondary
* boot "holding pen"
*/
-volatile int __cpuinitdata pen_release = -1;
+volatile int pen_release = -1;
enum ipi_msg_type {
IPI_WAKEUP,
@@ -66,6 +69,7 @@
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
+ IPI_COMPLETION,
};
static DECLARE_COMPLETION(cpu_running);
@@ -87,8 +91,8 @@
* its stack and the page tables.
*/
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
- secondary_data.pgdir = virt_to_phys(idmap_pgd);
- secondary_data.swapper_pg_dir = virt_to_phys(swapper_pg_dir);
+ secondary_data.pgdir = virt_to_idmap(idmap_pgd);
+ secondary_data.swapper_pg_dir = virt_to_idmap(swapper_pg_dir);
__cpuc_flush_dcache_area(&secondary_data, sizeof(secondary_data));
outer_clean_range(__pa(&secondary_data), __pa(&secondary_data + 1));
@@ -463,6 +467,7 @@
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_COMPLETION, "completion interrupts"),
};
void show_ipi_list(struct seq_file *p, int prec)
@@ -588,6 +593,19 @@
cpu_relax();
}
+static DEFINE_PER_CPU(struct completion *, cpu_completion);
+
+int register_ipi_completion(struct completion *completion, int cpu)
+{
+ per_cpu(cpu_completion, cpu) = completion;
+ return IPI_COMPLETION;
+}
+
+static void ipi_complete(unsigned int cpu)
+{
+ complete(per_cpu(cpu_completion, cpu));
+}
+
/*
* Main handler for inter-processor interrupts
*/
@@ -604,6 +622,7 @@
if (ipinr < NR_IPI)
__inc_irq_stat(cpu, ipi_irqs[ipinr]);
+ trace_arm_ipi_entry(ipinr);
switch (ipinr) {
case IPI_WAKEUP:
break;
@@ -638,11 +657,18 @@
irq_exit();
break;
+ case IPI_COMPLETION:
+ irq_enter();
+ ipi_complete(cpu);
+ irq_exit();
+ break;
+
default:
printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
cpu, ipinr);
break;
}
+ trace_arm_ipi_exit(ipinr);
set_irq_regs(old_regs);
}
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 5bc1a63..1aafa0d 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -28,7 +28,7 @@
*/
unsigned int __init scu_get_core_count(void __iomem *scu_base)
{
- unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG);
+ unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG);
return (ncores & 0x03) + 1;
}
@@ -42,19 +42,19 @@
#ifdef CONFIG_ARM_ERRATA_764369
/* Cortex-A9 only */
if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
- scu_ctrl = __raw_readl(scu_base + 0x30);
+ scu_ctrl = readl_relaxed(scu_base + 0x30);
if (!(scu_ctrl & 1))
- __raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+ writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30);
}
#endif
- scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
+ scu_ctrl = readl_relaxed(scu_base + SCU_CTRL);
/* already enabled? */
if (scu_ctrl & 1)
return;
scu_ctrl |= 1;
- __raw_writel(scu_ctrl, scu_base + SCU_CTRL);
+ writel_relaxed(scu_ctrl, scu_base + SCU_CTRL);
/*
* Ensure that the data accessed by CPU0 before the SCU was
@@ -80,9 +80,9 @@
if (mode > 3 || mode == 1 || cpu > 3)
return -EINVAL;
- val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
+ val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
val |= mode;
- __raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu);
+ writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu);
return 0;
}
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 9a52a07..a98b62d 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -103,7 +103,7 @@
static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
{
- int cpu, this_cpu;
+ int this_cpu;
cpumask_t mask = { CPU_BITS_NONE };
if (!erratum_a15_798181())
@@ -111,21 +111,7 @@
dummy_flush_tlb_a15_erratum();
this_cpu = get_cpu();
- for_each_online_cpu(cpu) {
- if (cpu == this_cpu)
- continue;
- /*
- * We only need to send an IPI if the other CPUs are running
- * the same ASID as the one being invalidated. There is no
- * need for locking around the active_asids check since the
- * switch_mm() function has at least one dmb() (as required by
- * this workaround) in case a context switch happens on
- * another CPU after the condition below.
- */
- if (atomic64_read(&mm->context.id) ==
- atomic64_read(&per_cpu(active_asids, cpu)))
- cpumask_set_cpu(cpu, &mask);
- }
+ a15_erratum_get_cpumask(this_cpu, mm, &mask);
smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
put_cpu();
}
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 90525d9..4971ccf 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -45,7 +45,7 @@
case CLOCK_EVT_MODE_PERIODIC:
ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
| TWD_TIMER_CONTROL_PERIODIC;
- __raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
+ writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
twd_base + TWD_TIMER_LOAD);
break;
case CLOCK_EVT_MODE_ONESHOT:
@@ -58,18 +58,18 @@
ctrl = 0;
}
- __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+ writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
}
static int twd_set_next_event(unsigned long evt,
struct clock_event_device *unused)
{
- unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
+ unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL);
ctrl |= TWD_TIMER_CONTROL_ENABLE;
- __raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
- __raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+ writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER);
+ writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
return 0;
}
@@ -82,8 +82,8 @@
*/
static int twd_timer_ack(void)
{
- if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
- __raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
+ if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) {
+ writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT);
return 1;
}
@@ -120,7 +120,7 @@
* changing cpu.
*/
if (flags == POST_RATE_CHANGE)
- smp_call_function(twd_update_frequency,
+ on_each_cpu(twd_update_frequency,
(void *)&cnd->new_rate, 1);
return NOTIFY_OK;
@@ -209,15 +209,15 @@
waitjiffies += 5;
/* enable, no interrupt or reload */
- __raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
+ writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL);
/* maximum value */
- __raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
+ writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
while (get_jiffies_64() < waitjiffies)
udelay(10);
- count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
+ count = readl_relaxed(twd_base + TWD_TIMER_COUNTER);
twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
@@ -275,7 +275,7 @@
* bother with the below.
*/
if (per_cpu(percpu_setup_called, cpu)) {
- __raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+ writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
clockevents_register_device(*__this_cpu_ptr(twd_evt));
enable_percpu_irq(clk->irq, 0);
return 0;
@@ -288,7 +288,7 @@
* The following is done once per CPU the first time .setup() is
* called.
*/
- __raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+ writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
clk->name = "local_timer";
clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 00f79e5..6582c4adc 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -31,7 +31,7 @@
high = ALIGN(low, THREAD_SIZE);
/* check current frame pointer is within bounds */
- if (fp < (low + 12) || fp + 4 >= high)
+ if (fp < low + 12 || fp > high - 4)
return -EINVAL;
/* restore the registers from the stack frame */
@@ -83,13 +83,16 @@
return trace->nr_entries >= trace->max_entries;
}
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+ struct stack_trace *trace, unsigned int nosched)
{
struct stack_trace_data data;
struct stackframe frame;
data.trace = trace;
data.skip = trace->skip;
+ data.no_sched_functions = nosched;
if (tsk != current) {
#ifdef CONFIG_SMP
@@ -102,7 +105,6 @@
trace->entries[trace->nr_entries++] = ULONG_MAX;
return;
#else
- data.no_sched_functions = 1;
frame.fp = thread_saved_fp(tsk);
frame.sp = thread_saved_sp(tsk);
frame.lr = 0; /* recovered from the stack */
@@ -111,11 +113,12 @@
} else {
register unsigned long current_sp asm ("sp");
- data.no_sched_functions = 0;
+ /* We don't want this function nor the caller */
+ data.skip += 2;
frame.fp = (unsigned long)__builtin_frame_address(0);
frame.sp = current_sp;
frame.lr = (unsigned long)__builtin_return_address(0);
- frame.pc = (unsigned long)save_stack_trace_tsk;
+ frame.pc = (unsigned long)__save_stack_trace;
}
walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +126,14 @@
trace->entries[trace->nr_entries++] = ULONG_MAX;
}
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+ __save_stack_trace(tsk, trace, 1);
+}
+
void save_stack_trace(struct stack_trace *trace)
{
- save_stack_trace_tsk(current, trace);
+ __save_stack_trace(current, trace, 0);
}
EXPORT_SYMBOL_GPL(save_stack_trace);
#endif
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index c5a5954..677da58d 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <asm/cputype.h>
+#include <asm/smp_plat.h>
#include <asm/topology.h>
/*
@@ -289,6 +290,140 @@
cpu_topology[cpuid].socket_id, mpidr);
}
+
+#ifdef CONFIG_SCHED_HMP
+
+static const char * const little_cores[] = {
+ "arm,cortex-a7",
+ NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+ const char * const *lc;
+ for (lc = little_cores; *lc; lc++)
+ if (of_device_is_compatible(cn, *lc))
+ return true;
+ return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+ struct cpumask *slow)
+{
+ struct device_node *cn = NULL;
+ int cpu;
+
+ cpumask_clear(fast);
+ cpumask_clear(slow);
+
+ /*
+ * Use the config options if they are given. This helps testing
+ * HMP scheduling on systems without a big.LITTLE architecture.
+ */
+ if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+ if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+ WARN(1, "Failed to parse HMP fast cpu mask!\n");
+ if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+ WARN(1, "Failed to parse HMP slow cpu mask!\n");
+ return;
+ }
+
+ /*
+ * Else, parse device tree for little cores.
+ */
+ while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+ const u32 *mpidr;
+ int len;
+
+ mpidr = of_get_property(cn, "reg", &len);
+ if (!mpidr || len != 4) {
+ pr_err("* %s missing reg property\n", cn->full_name);
+ continue;
+ }
+
+ cpu = get_logical_index(be32_to_cpup(mpidr));
+ if (cpu == -EINVAL) {
+ pr_err("couldn't get logical index for mpidr %x\n",
+ be32_to_cpup(mpidr));
+ break;
+ }
+
+ if (is_little_cpu(cn))
+ cpumask_set_cpu(cpu, slow);
+ else
+ cpumask_set_cpu(cpu, fast);
+ }
+
+ if (!cpumask_empty(fast) && !cpumask_empty(slow))
+ return;
+
+ /*
+ * We didn't find both big and little cores so let's call all cores
+ * fast as this will keep the system running, with all cores being
+ * treated equal.
+ */
+ cpumask_setall(fast);
+ cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+ struct cpumask hmp_fast_cpu_mask;
+ struct hmp_domain *domain;
+
+ arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+ /*
+ * Initialize hmp_domains
+ * Must be ordered with respect to compute capacity.
+ * Fastest domain at head of list.
+ */
+ if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+ }
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id: cluster HW identifier
+ * @cluster_mask: the cpumask location to be initialized, modified by the
+ * function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+ int cpu;
+
+ if (!cluster_mask)
+ return -EINVAL;
+
+ for_each_online_cpu(cpu)
+ if (socket_id == topology_physical_package_id(cpu)) {
+ cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
/*
* init_cpu_topology is called at boot when only one cpu is running
* which prevent simultaneous write access to cpu_topology array
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 18b32e8..b4fd850 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -34,10 +34,15 @@
#include <asm/unwind.h>
#include <asm/tls.h>
#include <asm/system_misc.h>
+#include <asm/opcodes.h>
-#include "signal.h"
-
-static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
+static const char *handler[]= {
+ "prefetch abort",
+ "data abort",
+ "address exception",
+ "interrupt",
+ "undefined instruction",
+};
void *vectors_page;
@@ -343,15 +348,17 @@
int is_valid_bugaddr(unsigned long pc)
{
#ifdef CONFIG_THUMB2_KERNEL
- unsigned short bkpt;
+ u16 bkpt;
+ u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE);
#else
- unsigned long bkpt;
+ u32 bkpt;
+ u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
#endif
if (probe_kernel_address((unsigned *)pc, bkpt))
return 0;
- return bkpt == BUG_INSTR_VALUE;
+ return bkpt == insn;
}
#endif
@@ -404,25 +411,28 @@
if (processor_mode(regs) == SVC_MODE) {
#ifdef CONFIG_THUMB2_KERNEL
if (thumb_mode(regs)) {
- instr = ((u16 *)pc)[0];
+ instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]);
if (is_wide_instruction(instr)) {
- instr <<= 16;
- instr |= ((u16 *)pc)[1];
+ u16 inst2;
+ inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]);
+ instr = __opcode_thumb32_compose(instr, inst2);
}
} else
#endif
- instr = *(u32 *) pc;
+ instr = __mem_to_opcode_arm(*(u32 *) pc);
} else if (thumb_mode(regs)) {
if (get_user(instr, (u16 __user *)pc))
goto die_sig;
+ instr = __mem_to_opcode_thumb16(instr);
if (is_wide_instruction(instr)) {
unsigned int instr2;
if (get_user(instr2, (u16 __user *)pc+1))
goto die_sig;
- instr <<= 16;
- instr |= instr2;
+ instr2 = __mem_to_opcode_thumb16(instr2);
+ instr = __opcode_thumb32_compose(instr, instr2);
}
} else if (get_user(instr, (u32 __user *)pc)) {
+ instr = __mem_to_opcode_arm(instr);
goto die_sig;
}
@@ -800,47 +810,55 @@
return;
}
-static void __init kuser_get_tls_init(unsigned long vectors)
+#ifdef CONFIG_KUSER_HELPERS
+static void __init kuser_init(void *vectors)
{
+ extern char __kuser_helper_start[], __kuser_helper_end[];
+ int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+
+ memcpy(vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz);
+
/*
* vectors + 0xfe0 = __kuser_get_tls
* vectors + 0xfe8 = hardware TLS instruction at 0xffff0fe8
*/
if (tls_emu || has_tls_reg)
- memcpy((void *)vectors + 0xfe0, (void *)vectors + 0xfe8, 4);
+ memcpy(vectors + 0xfe0, vectors + 0xfe8, 4);
}
+#else
+static void __init kuser_init(void *vectors)
+{
+}
+#endif
void __init early_trap_init(void *vectors_base)
{
unsigned long vectors = (unsigned long)vectors_base;
extern char __stubs_start[], __stubs_end[];
extern char __vectors_start[], __vectors_end[];
- extern char __kuser_helper_start[], __kuser_helper_end[];
- int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+ unsigned i;
vectors_page = vectors_base;
/*
+ * Poison the vectors page with an undefined instruction. This
+ * instruction is chosen to be undefined for both ARM and Thumb
+ * ISAs. The Thumb version is an undefined instruction with a
+ * branch back to the undefined instruction.
+ */
+ for (i = 0; i < PAGE_SIZE / sizeof(u32); i++)
+ ((u32 *)vectors_base)[i] = 0xe7fddef1;
+
+ /*
* Copy the vectors, stubs and kuser helpers (in entry-armv.S)
* into the vector page, mapped at 0xffff0000, and ensure these
* are visible to the instruction stream.
*/
memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start);
- memcpy((void *)vectors + 0x200, __stubs_start, __stubs_end - __stubs_start);
- memcpy((void *)vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz);
+ memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start);
- /*
- * Do processor specific fixups for the kuser helpers
- */
- kuser_get_tls_init(vectors);
+ kuser_init(vectors_base);
- /*
- * Copy signal return handlers into the vector page, and
- * set sigreturn to be a pointer to these.
- */
- memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
- sigreturn_codes, sizeof(sigreturn_codes));
-
- flush_icache_range(vectors, vectors + PAGE_SIZE);
+ flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
}
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index a871b8e..33f2ea3 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -152,6 +152,23 @@
. = ALIGN(PAGE_SIZE);
__init_begin = .;
#endif
+ /*
+ * The vectors and stubs are relocatable code, and the
+ * only thing that matters is their relative offsets
+ */
+ __vectors_start = .;
+ .vectors 0 : AT(__vectors_start) {
+ *(.vectors)
+ }
+ . = __vectors_start + SIZEOF(.vectors);
+ __vectors_end = .;
+
+ __stubs_start = .;
+ .stubs 0x1000 : AT(__stubs_start) {
+ *(.stubs)
+ }
+ . = __stubs_start + SIZEOF(.stubs);
+ __stubs_end = .;
INIT_TEXT_SECTION(8)
.exit.text : {
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 370e1a8..466bd29 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -20,6 +20,7 @@
bool "Kernel-based Virtual Machine (KVM) support"
select PREEMPT_NOTIFIERS
select ANON_INODES
+ select HAVE_KVM_CPU_RELAX_INTERCEPT
select KVM_MMIO
select KVM_ARM_HOST
depends on ARM_VIRT_EXT && ARM_LPAE
@@ -41,9 +42,9 @@
Provides host support for ARM processors.
config KVM_ARM_MAX_VCPUS
- int "Number maximum supported virtual CPUs per VM" if KVM_ARM_HOST
- default 4 if KVM_ARM_HOST
- default 0
+ int "Number maximum supported virtual CPUs per VM"
+ depends on KVM_ARM_HOST
+ default 4
help
Static number of max supported virtual CPUs per VM.
@@ -67,6 +68,4 @@
---help---
Adds support for the Architected Timers in virtual machines
-source drivers/virtio/Kconfig
-
endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 53c5ed8..f7057ed 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -14,10 +14,12 @@
AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt)
AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt)
-kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
+KVM := ../../../virt/kvm
+kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o
obj-y += kvm-arm.o init.o interrupts.o
obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
-obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o
-obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o
-obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o
+obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arch_timer.c b/arch/arm/kvm/arch_timer.c
deleted file mode 100644
index c55b608..0000000
--- a/arch/arm/kvm/arch_timer.c
+++ /dev/null
@@ -1,272 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#include <linux/cpu.h>
-#include <linux/of_irq.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-
-#include <clocksource/arm_arch_timer.h>
-#include <asm/arch_timer.h>
-
-#include <asm/kvm_vgic.h>
-#include <asm/kvm_arch_timer.h>
-
-static struct timecounter *timecounter;
-static struct workqueue_struct *wqueue;
-static struct kvm_irq_level timer_irq = {
- .level = 1,
-};
-
-static cycle_t kvm_phys_timer_read(void)
-{
- return timecounter->cc->read(timecounter->cc);
-}
-
-static bool timer_is_armed(struct arch_timer_cpu *timer)
-{
- return timer->armed;
-}
-
-/* timer_arm: as in "arm the timer", not as in ARM the company */
-static void timer_arm(struct arch_timer_cpu *timer, u64 ns)
-{
- timer->armed = true;
- hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns),
- HRTIMER_MODE_ABS);
-}
-
-static void timer_disarm(struct arch_timer_cpu *timer)
-{
- if (timer_is_armed(timer)) {
- hrtimer_cancel(&timer->timer);
- cancel_work_sync(&timer->expired);
- timer->armed = false;
- }
-}
-
-static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
-{
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-
- timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
- kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
- vcpu->arch.timer_cpu.irq->irq,
- vcpu->arch.timer_cpu.irq->level);
-}
-
-static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
-{
- struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
-
- /*
- * We disable the timer in the world switch and let it be
- * handled by kvm_timer_sync_hwstate(). Getting a timer
- * interrupt at this point is a sure sign of some major
- * breakage.
- */
- pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu);
- return IRQ_HANDLED;
-}
-
-static void kvm_timer_inject_irq_work(struct work_struct *work)
-{
- struct kvm_vcpu *vcpu;
-
- vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
- vcpu->arch.timer_cpu.armed = false;
- kvm_timer_inject_irq(vcpu);
-}
-
-static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
-{
- struct arch_timer_cpu *timer;
- timer = container_of(hrt, struct arch_timer_cpu, timer);
- queue_work(wqueue, &timer->expired);
- return HRTIMER_NORESTART;
-}
-
-/**
- * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
- * @vcpu: The vcpu pointer
- *
- * Disarm any pending soft timers, since the world-switch code will write the
- * virtual timer state back to the physical CPU.
- */
-void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
-{
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-
- /*
- * We're about to run this vcpu again, so there is no need to
- * keep the background timer running, as we're about to
- * populate the CPU timer again.
- */
- timer_disarm(timer);
-}
-
-/**
- * kvm_timer_sync_hwstate - sync timer state from cpu
- * @vcpu: The vcpu pointer
- *
- * Check if the virtual timer was armed and either schedule a corresponding
- * soft timer or inject directly if already expired.
- */
-void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
-{
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
- cycle_t cval, now;
- u64 ns;
-
- if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
- !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE))
- return;
-
- cval = timer->cntv_cval;
- now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
- BUG_ON(timer_is_armed(timer));
-
- if (cval <= now) {
- /*
- * Timer has already expired while we were not
- * looking. Inject the interrupt and carry on.
- */
- kvm_timer_inject_irq(vcpu);
- return;
- }
-
- ns = cyclecounter_cyc2ns(timecounter->cc, cval - now);
- timer_arm(timer, ns);
-}
-
-void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
-{
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-
- INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
- hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
- timer->timer.function = kvm_timer_expire;
- timer->irq = &timer_irq;
-}
-
-static void kvm_timer_init_interrupt(void *info)
-{
- enable_percpu_irq(timer_irq.irq, 0);
-}
-
-
-static int kvm_timer_cpu_notify(struct notifier_block *self,
- unsigned long action, void *cpu)
-{
- switch (action) {
- case CPU_STARTING:
- case CPU_STARTING_FROZEN:
- kvm_timer_init_interrupt(NULL);
- break;
- case CPU_DYING:
- case CPU_DYING_FROZEN:
- disable_percpu_irq(timer_irq.irq);
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block kvm_timer_cpu_nb = {
- .notifier_call = kvm_timer_cpu_notify,
-};
-
-static const struct of_device_id arch_timer_of_match[] = {
- { .compatible = "arm,armv7-timer", },
- {},
-};
-
-int kvm_timer_hyp_init(void)
-{
- struct device_node *np;
- unsigned int ppi;
- int err;
-
- timecounter = arch_timer_get_timecounter();
- if (!timecounter)
- return -ENODEV;
-
- np = of_find_matching_node(NULL, arch_timer_of_match);
- if (!np) {
- kvm_err("kvm_arch_timer: can't find DT node\n");
- return -ENODEV;
- }
-
- ppi = irq_of_parse_and_map(np, 2);
- if (!ppi) {
- kvm_err("kvm_arch_timer: no virtual timer interrupt\n");
- err = -EINVAL;
- goto out;
- }
-
- err = request_percpu_irq(ppi, kvm_arch_timer_handler,
- "kvm guest timer", kvm_get_running_vcpus());
- if (err) {
- kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n",
- ppi, err);
- goto out;
- }
-
- timer_irq.irq = ppi;
-
- err = register_cpu_notifier(&kvm_timer_cpu_nb);
- if (err) {
- kvm_err("Cannot register timer CPU notifier\n");
- goto out_free;
- }
-
- wqueue = create_singlethread_workqueue("kvm_arch_timer");
- if (!wqueue) {
- err = -ENOMEM;
- goto out_free;
- }
-
- kvm_info("%s IRQ%d\n", np->name, ppi);
- on_each_cpu(kvm_timer_init_interrupt, NULL, 1);
-
- goto out;
-out_free:
- free_percpu_irq(ppi, kvm_get_running_vcpus());
-out:
- of_node_put(np);
- return err;
-}
-
-void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
-{
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-
- timer_disarm(timer);
-}
-
-int kvm_timer_init(struct kvm *kvm)
-{
- if (timecounter && wqueue) {
- kvm->arch.timer.cntvoff = kvm_phys_timer_read();
- kvm->arch.timer.enabled = 1;
- }
-
- return 0;
-}
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index ef1703b..d0c8ee6 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -17,6 +17,7 @@
*/
#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
@@ -81,12 +82,12 @@
/**
* kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
*/
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
{
return &kvm_arm_running_vcpu;
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
return 0;
}
@@ -96,27 +97,16 @@
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
int kvm_arch_hardware_setup(void)
{
return 0;
}
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
void kvm_arch_check_processor_compat(void *rtn)
{
*(int *)rtn = 0;
}
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
/**
* kvm_arch_init_vm - initializes a VM data structure
@@ -137,6 +127,8 @@
if (ret)
goto out_free_stage2_pgd;
+ kvm_timer_init(kvm);
+
/* Mark the initial VMID generation invalid */
kvm->arch.vmid_gen = 0;
@@ -152,15 +144,6 @@
return VM_FAULT_SIGBUS;
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
- struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
-{
- return 0;
-}
/**
* kvm_arch_destroy_vm - destroy the VM data structure
@@ -178,20 +161,25 @@
kvm->vcpus[i] = NULL;
}
}
+
+ kvm_vgic_destroy(kvm);
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
switch (ext) {
case KVM_CAP_IRQCHIP:
r = vgic_present;
break;
+ case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_USER_MEMORY:
case KVM_CAP_SYNC_MMU:
case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
case KVM_CAP_ONE_REG:
case KVM_CAP_ARM_PSCI:
+ case KVM_CAP_ARM_PSCI_0_2:
+ case KVM_CAP_READONLY_MEM:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -219,29 +207,6 @@
return -EINVAL;
}
-int kvm_arch_prepare_memory_region(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
- struct kvm_userspace_memory_region *mem,
- enum kvm_mr_change change)
-{
- return 0;
-}
-
-void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old,
- enum kvm_mr_change change)
-{
-}
-
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot)
-{
-}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
@@ -280,6 +245,7 @@
{
kvm_mmu_free_memory_caches(vcpu);
kvm_timer_vcpu_terminate(vcpu);
+ kvm_vgic_vcpu_destroy(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
@@ -295,26 +261,15 @@
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
- int ret;
-
/* Force users to call KVM_ARM_VCPU_INIT */
vcpu->arch.target = -1;
- /* Set up VGIC */
- ret = kvm_vgic_vcpu_init(vcpu);
- if (ret)
- return ret;
-
/* Set up the timer */
kvm_timer_vcpu_init(vcpu);
return 0;
}
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-}
-
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
vcpu->cpu = cpu;
@@ -334,6 +289,13 @@
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ /*
+ * The arch-generic KVM code expects the cpu field of a vcpu to be -1
+ * if the vcpu is no longer assigned to a cpu. This is used for the
+ * optimized make_all_cpus_request path.
+ */
+ vcpu->cpu = -1;
+
kvm_arm_set_running_vcpu(NULL);
}
@@ -448,15 +410,17 @@
/* update vttbr to be used with the new vmid */
pgd_phys = virt_to_phys(kvm->arch.pgd);
+ BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
- kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
- kvm->arch.vttbr |= vmid;
+ kvm->arch.vttbr = pgd_phys | vmid;
spin_unlock(&kvm_vmid_lock);
}
static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
{
+ int ret;
+
if (likely(vcpu->arch.has_run_once))
return 0;
@@ -466,22 +430,12 @@
* Initialize the VGIC before running a vcpu the first time on
* this VM.
*/
- if (irqchip_in_kernel(vcpu->kvm) &&
- unlikely(!vgic_initialized(vcpu->kvm))) {
- int ret = kvm_vgic_init(vcpu->kvm);
+ if (unlikely(!vgic_initialized(vcpu->kvm))) {
+ ret = kvm_vgic_init(vcpu->kvm);
if (ret)
return ret;
}
- /*
- * Handle the "start in power-off" case by calling into the
- * PSCI code.
- */
- if (test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) {
- *vcpu_reg(vcpu, 0) = KVM_PSCI_FN_CPU_OFF;
- kvm_psci_call(vcpu);
- }
-
return 0;
}
@@ -695,6 +649,24 @@
return -EINVAL;
}
+static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu_init *init)
+{
+ int ret;
+
+ ret = kvm_vcpu_set_target(vcpu, init);
+ if (ret)
+ return ret;
+
+ /*
+ * Handle the "start in power-off" case by marking the VCPU as paused.
+ */
+ if (__test_and_clear_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
+ vcpu->arch.pause = true;
+
+ return 0;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -708,8 +680,7 @@
if (copy_from_user(&init, argp, sizeof(init)))
return -EFAULT;
- return kvm_vcpu_set_target(vcpu, &init);
-
+ return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
}
case KVM_SET_ONE_REG:
case KVM_GET_ONE_REG: {
@@ -767,7 +738,7 @@
case KVM_ARM_DEVICE_VGIC_V2:
if (!vgic_present)
return -ENXIO;
- return kvm_vgic_set_addr(kvm, type, dev_addr->addr);
+ return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
default:
return -ENODEV;
}
@@ -793,6 +764,19 @@
return -EFAULT;
return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
}
+ case KVM_ARM_PREFERRED_TARGET: {
+ int err;
+ struct kvm_vcpu_init init;
+
+ err = kvm_vcpu_preferred_target(&init);
+ if (err)
+ return err;
+
+ if (copy_to_user(argp, &init, sizeof(init)))
+ return -EFAULT;
+
+ return 0;
+ }
default:
return -EINVAL;
}
@@ -800,8 +784,8 @@
static void cpu_init_hyp_mode(void *dummy)
{
- unsigned long long boot_pgd_ptr;
- unsigned long long pgd_ptr;
+ phys_addr_t boot_pgd_ptr;
+ phys_addr_t pgd_ptr;
unsigned long hyp_stack_ptr;
unsigned long stack_page;
unsigned long vector_ptr;
@@ -809,8 +793,8 @@
/* Switch from the HYP stub to our own HYP init vector */
__hyp_set_vectors(kvm_get_idmap_vector());
- boot_pgd_ptr = (unsigned long long)kvm_mmu_get_boot_httbr();
- pgd_ptr = (unsigned long long)kvm_mmu_get_httbr();
+ boot_pgd_ptr = kvm_mmu_get_boot_httbr();
+ pgd_ptr = kvm_mmu_get_httbr();
stack_page = __get_cpu_var(kvm_arm_hyp_stack_page);
hyp_stack_ptr = stack_page + PAGE_SIZE;
vector_ptr = (unsigned long)__kvm_hyp_vector;
@@ -824,7 +808,8 @@
switch (action) {
case CPU_STARTING:
case CPU_STARTING_FROZEN:
- cpu_init_hyp_mode(NULL);
+ if (__hyp_get_vectors() == hyp_default_vectors)
+ cpu_init_hyp_mode(NULL);
break;
}
@@ -835,6 +820,34 @@
.notifier_call = hyp_init_cpu_notify,
};
+#ifdef CONFIG_CPU_PM
+static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
+ unsigned long cmd,
+ void *v)
+{
+ if (cmd == CPU_PM_EXIT &&
+ __hyp_get_vectors() == hyp_default_vectors) {
+ cpu_init_hyp_mode(NULL);
+ return NOTIFY_OK;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block hyp_init_cpu_pm_nb = {
+ .notifier_call = hyp_init_cpu_pm_notifier,
+};
+
+static void __init hyp_cpu_pm_init(void)
+{
+ cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
+}
+#else
+static inline void hyp_cpu_pm_init(void)
+{
+}
+#endif
+
/**
* Inits Hyp-mode on all online CPUs
*/
@@ -995,6 +1008,8 @@
goto out_err;
}
+ hyp_cpu_pm_init();
+
kvm_coproc_table_init();
return 0;
out_err:
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 8eea97b..7928dbd 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -23,6 +23,7 @@
#include <asm/kvm_host.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <trace/events/kvm.h>
@@ -43,6 +44,31 @@
/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
#define CSSELR_MAX 12
+/*
+ * kvm_vcpu_arch.cp15 holds cp15 registers as an array of u32, but some
+ * of cp15 registers can be viewed either as couple of two u32 registers
+ * or one u64 register. Current u64 register encoding is that least
+ * significant u32 word is followed by most significant u32 word.
+ */
+static inline void vcpu_cp15_reg64_set(struct kvm_vcpu *vcpu,
+ const struct coproc_reg *r,
+ u64 val)
+{
+ vcpu->arch.cp15[r->reg] = val & 0xffffffff;
+ vcpu->arch.cp15[r->reg + 1] = val >> 32;
+}
+
+static inline u64 vcpu_cp15_reg64_get(struct kvm_vcpu *vcpu,
+ const struct coproc_reg *r)
+{
+ u64 val;
+
+ val = vcpu->arch.cp15[r->reg + 1];
+ val = val << 32;
+ val = val | vcpu->arch.cp15[r->reg];
+ return val;
+}
+
int kvm_handle_cp10_id(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
kvm_inject_undefined(vcpu);
@@ -71,6 +97,98 @@
return 1;
}
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+ /*
+ * Compute guest MPIDR. We build a virtual cluster out of the
+ * vcpu_id, but we read the 'U' bit from the underlying
+ * hardware directly.
+ */
+ vcpu->arch.cp15[c0_MPIDR] = ((read_cpuid_mpidr() & MPIDR_SMP_BITMASK) |
+ ((vcpu->vcpu_id >> 2) << MPIDR_LEVEL_BITS) |
+ (vcpu->vcpu_id & 3));
+}
+
+/* TRM entries A7:4.3.31 A15:4.3.28 - RO WI */
+static bool access_actlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+
+ *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
+ return true;
+}
+
+/* TRM entries A7:4.3.56, A15:4.3.60 - R/O. */
+static bool access_cbar(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ if (p->is_write)
+ return write_to_read_only(vcpu, p);
+ return read_zero(vcpu, p);
+}
+
+/* TRM entries A7:4.3.49, A15:4.3.48 - R/O WI */
+static bool access_l2ctlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+
+ *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
+ return true;
+}
+
+static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+ u32 l2ctlr, ncores;
+
+ asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
+ l2ctlr &= ~(3 << 24);
+ ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
+ /* How many cores in the current cluster and the next ones */
+ ncores -= (vcpu->vcpu_id & ~3);
+ /* Cap it to the maximum number of cores in a single cluster */
+ ncores = min(ncores, 3U);
+ l2ctlr |= (ncores & 3) << 24;
+
+ vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
+}
+
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
+{
+ u32 actlr;
+
+ /* ACTLR contains SMP bit: make sure you create all cpus first! */
+ asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr));
+ /* Make the SMP bit consistent with the guest configuration */
+ if (atomic_read(&vcpu->kvm->online_vcpus) > 1)
+ actlr |= 1U << 6;
+ else
+ actlr &= ~(1U << 6);
+
+ vcpu->arch.cp15[c1_ACTLR] = actlr;
+}
+
+/*
+ * TRM entries: A7:4.3.50, A15:4.3.49
+ * R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored).
+ */
+static bool access_l2ectlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+
+ *vcpu_reg(vcpu, p->Rt1) = 0;
+ return true;
+}
+
/* See note at ARM ARM B1.14.4 */
static bool access_dcsw(struct kvm_vcpu *vcpu,
const struct coproc_params *p,
@@ -113,6 +231,44 @@
}
/*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ BUG_ON(!p->is_write);
+
+ vcpu->arch.cp15[r->reg] = *vcpu_reg(vcpu, p->Rt1);
+ if (p->is_64bit)
+ vcpu->arch.cp15[r->reg + 1] = *vcpu_reg(vcpu, p->Rt2);
+
+ return true;
+}
+
+/*
+ * SCTLR accessor. Only called as long as HCR_TVM is set. If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ *
+ * Used by the cpu-specific code.
+ */
+bool access_sctlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r)
+{
+ access_vm_reg(vcpu, p, r);
+
+ if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */
+ vcpu->arch.hcr &= ~HCR_TVM;
+ stage2_flush_vm(vcpu->kvm);
+ }
+
+ return true;
+}
+
+/*
* We could trap ID_DFR0 and tell the guest we don't support performance
* monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
* NAKed, so it will read the PMCR anyway.
@@ -146,40 +302,63 @@
#define access_pmintenclr pm_fake
/* Architected CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ * registers preceding 32-bit ones.
*/
static const struct coproc_reg cp15_regs[] = {
+ /* MPIDR: we use VMPIDR for guest access. */
+ { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32,
+ NULL, reset_mpidr, c0_MPIDR },
+
/* CSSELR: swapped by interrupt.S. */
{ CRn( 0), CRm( 0), Op1( 2), Op2( 0), is32,
NULL, reset_unknown, c0_CSSELR },
- /* TTBR0/TTBR1: swapped by interrupt.S. */
- { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 },
- { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 },
+ /* ACTLR: trapped by HCR.TAC bit. */
+ { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
+ access_actlr, reset_actlr, c1_ACTLR },
- /* TTBCR: swapped by interrupt.S. */
+ /* CPACR: swapped by interrupt.S. */
+ { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
+ NULL, reset_val, c1_CPACR, 0x00000000 },
+
+ /* TTBR0/TTBR1/TTBCR: swapped by interrupt.S. */
+ { CRm64( 2), Op1( 0), is64, access_vm_reg, reset_unknown64, c2_TTBR0 },
+ { CRn(2), CRm( 0), Op1( 0), Op2( 0), is32,
+ access_vm_reg, reset_unknown, c2_TTBR0 },
+ { CRn(2), CRm( 0), Op1( 0), Op2( 1), is32,
+ access_vm_reg, reset_unknown, c2_TTBR1 },
{ CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32,
- NULL, reset_val, c2_TTBCR, 0x00000000 },
+ access_vm_reg, reset_val, c2_TTBCR, 0x00000000 },
+ { CRm64( 2), Op1( 1), is64, access_vm_reg, reset_unknown64, c2_TTBR1 },
+
/* DACR: swapped by interrupt.S. */
{ CRn( 3), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c3_DACR },
+ access_vm_reg, reset_unknown, c3_DACR },
/* DFSR/IFSR/ADFSR/AIFSR: swapped by interrupt.S. */
{ CRn( 5), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c5_DFSR },
+ access_vm_reg, reset_unknown, c5_DFSR },
{ CRn( 5), CRm( 0), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c5_IFSR },
+ access_vm_reg, reset_unknown, c5_IFSR },
{ CRn( 5), CRm( 1), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c5_ADFSR },
+ access_vm_reg, reset_unknown, c5_ADFSR },
{ CRn( 5), CRm( 1), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c5_AIFSR },
+ access_vm_reg, reset_unknown, c5_AIFSR },
/* DFAR/IFAR: swapped by interrupt.S. */
{ CRn( 6), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c6_DFAR },
+ access_vm_reg, reset_unknown, c6_DFAR },
{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
- NULL, reset_unknown, c6_IFAR },
+ access_vm_reg, reset_unknown, c6_IFAR },
+
+ /* PAR swapped by interrupt.S */
+ { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
+
/*
* DC{C,I,CI}SW operations:
*/
@@ -187,6 +366,13 @@
{ CRn( 7), CRm(10), Op1( 0), Op2( 2), is32, access_dcsw},
{ CRn( 7), CRm(14), Op1( 0), Op2( 2), is32, access_dcsw},
/*
+ * L2CTLR access (guest wants to know #CPUs).
+ */
+ { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32,
+ access_l2ctlr, reset_l2ctlr, c9_L2CTLR },
+ { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr},
+
+ /*
* Dummy performance monitor implementation.
*/
{ CRn( 9), CRm(12), Op1( 0), Op2( 0), is32, access_pmcr},
@@ -205,9 +391,15 @@
/* PRRR/NMRR (aka MAIR0/MAIR1): swapped by interrupt.S. */
{ CRn(10), CRm( 2), Op1( 0), Op2( 0), is32,
- NULL, reset_unknown, c10_PRRR},
+ access_vm_reg, reset_unknown, c10_PRRR},
{ CRn(10), CRm( 2), Op1( 0), Op2( 1), is32,
- NULL, reset_unknown, c10_NMRR},
+ access_vm_reg, reset_unknown, c10_NMRR},
+
+ /* AMAIR0/AMAIR1: swapped by interrupt.S. */
+ { CRn(10), CRm( 3), Op1( 0), Op2( 0), is32,
+ access_vm_reg, reset_unknown, c10_AMAIR0},
+ { CRn(10), CRm( 3), Op1( 0), Op2( 1), is32,
+ access_vm_reg, reset_unknown, c10_AMAIR1},
/* VBAR: swapped by interrupt.S. */
{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
@@ -215,7 +407,7 @@
/* CONTEXTIDR/TPIDRURW/TPIDRURO/TPIDRPRW: swapped by interrupt.S. */
{ CRn(13), CRm( 0), Op1( 0), Op2( 1), is32,
- NULL, reset_val, c13_CID, 0x00000000 },
+ access_vm_reg, reset_val, c13_CID, 0x00000000 },
{ CRn(13), CRm( 0), Op1( 0), Op2( 2), is32,
NULL, reset_unknown, c13_TID_URW },
{ CRn(13), CRm( 0), Op1( 0), Op2( 3), is32,
@@ -226,6 +418,9 @@
/* CNTKCTL: swapped by interrupt.S. */
{ CRn(14), CRm( 1), Op1( 0), Op2( 0), is32,
NULL, reset_val, c14_CNTKCTL, 0x00000000 },
+
+ /* The Configuration Base Address Register. */
+ { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
};
/* Target specific emulation tables */
@@ -233,6 +428,12 @@
void kvm_register_target_coproc_table(struct kvm_coproc_target_table *table)
{
+ unsigned int i;
+
+ for (i = 1; i < table->num; i++)
+ BUG_ON(cmp_reg(&table->table[i-1],
+ &table->table[i]) >= 0);
+
target_tables[table->target] = table;
}
@@ -315,7 +516,7 @@
{
struct coproc_params params;
- params.CRm = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
+ params.CRn = (kvm_vcpu_get_hsr(vcpu) >> 1) & 0xf;
params.Rt1 = (kvm_vcpu_get_hsr(vcpu) >> 5) & 0xf;
params.is_write = ((kvm_vcpu_get_hsr(vcpu) & 1) == 0);
params.is_64bit = true;
@@ -323,7 +524,7 @@
params.Op1 = (kvm_vcpu_get_hsr(vcpu) >> 16) & 0xf;
params.Op2 = 0;
params.Rt2 = (kvm_vcpu_get_hsr(vcpu) >> 10) & 0xf;
- params.CRn = 0;
+ params.CRm = 0;
return emulate_cp15(vcpu, ¶ms);
}
@@ -395,12 +596,13 @@
| KVM_REG_ARM_OPC1_MASK))
return false;
params->is_64bit = true;
- params->CRm = ((id & KVM_REG_ARM_CRM_MASK)
+ /* CRm to CRn: see cp15_to_index for details */
+ params->CRn = ((id & KVM_REG_ARM_CRM_MASK)
>> KVM_REG_ARM_CRM_SHIFT);
params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK)
>> KVM_REG_ARM_OPC1_SHIFT);
params->Op2 = 0;
- params->CRn = 0;
+ params->CRm = 0;
return true;
default:
return false;
@@ -505,17 +707,23 @@
{ CRn( 0), CRm( 0), Op1( 1), Op2( 7), is32, NULL, get_AIDR },
};
+/*
+ * Reads a register value from a userspace address to a kernel
+ * variable. Make sure that register size matches sizeof(*__val).
+ */
static int reg_from_user(void *val, const void __user *uaddr, u64 id)
{
- /* This Just Works because we are little endian. */
if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
return -EFAULT;
return 0;
}
+/*
+ * Writes a register value to a userspace address from a kernel variable.
+ * Make sure that register size matches sizeof(*__val).
+ */
static int reg_to_user(void __user *uaddr, const void *val, u64 id)
{
- /* This Just Works because we are little endian. */
if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
return -EFAULT;
return 0;
@@ -525,6 +733,7 @@
{
struct coproc_params params;
const struct coproc_reg *r;
+ int ret;
if (!index_to_params(id, ¶ms))
return -ENOENT;
@@ -533,7 +742,15 @@
if (!r)
return -ENOENT;
- return reg_to_user(uaddr, &r->val, id);
+ ret = -ENOENT;
+ if (KVM_REG_SIZE(id) == 4) {
+ u32 val = r->val;
+
+ ret = reg_to_user(uaddr, &val, id);
+ } else if (KVM_REG_SIZE(id) == 8) {
+ ret = reg_to_user(uaddr, &r->val, id);
+ }
+ return ret;
}
static int set_invariant_cp15(u64 id, void __user *uaddr)
@@ -541,7 +758,7 @@
struct coproc_params params;
const struct coproc_reg *r;
int err;
- u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */
+ u64 val;
if (!index_to_params(id, ¶ms))
return -ENOENT;
@@ -549,7 +766,16 @@
if (!r)
return -ENOENT;
- err = reg_from_user(&val, uaddr, id);
+ err = -ENOENT;
+ if (KVM_REG_SIZE(id) == 4) {
+ u32 val32;
+
+ err = reg_from_user(&val32, uaddr, id);
+ if (!err)
+ val = val32;
+ } else if (KVM_REG_SIZE(id) == 8) {
+ err = reg_from_user(&val, uaddr, id);
+ }
if (err)
return err;
@@ -565,7 +791,7 @@
u32 level, ctype;
if (val >= CSSELR_MAX)
- return -ENOENT;
+ return false;
/* Bottom bit is Instruction or Data bit. Next 3 bits are level. */
level = (val >> 1);
@@ -827,6 +1053,7 @@
{
const struct coproc_reg *r;
void __user *uaddr = (void __user *)(long)reg->addr;
+ int ret;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
return demux_c15_get(reg->id, uaddr);
@@ -838,14 +1065,24 @@
if (!r)
return get_invariant_cp15(reg->id, uaddr);
- /* Note: copies two regs if size is 64 bit. */
- return reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+ ret = -ENOENT;
+ if (KVM_REG_SIZE(reg->id) == 8) {
+ u64 val;
+
+ val = vcpu_cp15_reg64_get(vcpu, r);
+ ret = reg_to_user(uaddr, &val, reg->id);
+ } else if (KVM_REG_SIZE(reg->id) == 4) {
+ ret = reg_to_user(uaddr, &vcpu->arch.cp15[r->reg], reg->id);
+ }
+
+ return ret;
}
int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
const struct coproc_reg *r;
void __user *uaddr = (void __user *)(long)reg->addr;
+ int ret;
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
return demux_c15_set(reg->id, uaddr);
@@ -857,8 +1094,18 @@
if (!r)
return set_invariant_cp15(reg->id, uaddr);
- /* Note: copies two regs if size is 64 bit */
- return reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+ ret = -ENOENT;
+ if (KVM_REG_SIZE(reg->id) == 8) {
+ u64 val;
+
+ ret = reg_from_user(&val, uaddr, reg->id);
+ if (!ret)
+ vcpu_cp15_reg64_set(vcpu, r, val);
+ } else if (KVM_REG_SIZE(reg->id) == 4) {
+ ret = reg_from_user(&vcpu->arch.cp15[r->reg], uaddr, reg->id);
+ }
+
+ return ret;
}
static unsigned int num_demux_regs(void)
@@ -894,7 +1141,14 @@
if (reg->is_64) {
val |= KVM_REG_SIZE_U64;
val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
- val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT);
+ /*
+ * CRn always denotes the primary coproc. reg. nr. for the
+ * in-kernel representation, but the user space API uses the
+ * CRm for the encoding, because it is modelled after the
+ * MRRC/MCRR instructions: see the ARM ARM rev. c page
+ * B3-1445
+ */
+ val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT);
} else {
val |= KVM_REG_SIZE_U32;
val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT);
diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h
index b7301d3..1a44bbe 100644
--- a/arch/arm/kvm/coproc.h
+++ b/arch/arm/kvm/coproc.h
@@ -58,8 +58,8 @@
{
/* Look, we even formatted it for you to paste into the table! */
if (p->is_64bit) {
- kvm_pr_unimpl(" { CRm(%2lu), Op1(%2lu), is64, func_%s },\n",
- p->CRm, p->Op1, p->is_write ? "write" : "read");
+ kvm_pr_unimpl(" { CRm64(%2lu), Op1(%2lu), is64, func_%s },\n",
+ p->CRn, p->Op1, p->is_write ? "write" : "read");
} else {
kvm_pr_unimpl(" { CRn(%2lu), CRm(%2lu), Op1(%2lu), Op2(%2lu), is32,"
" func_%s },\n",
@@ -139,15 +139,22 @@
return i1->CRm - i2->CRm;
if (i1->Op1 != i2->Op1)
return i1->Op1 - i2->Op1;
- return i1->Op2 - i2->Op2;
+ if (i1->Op2 != i2->Op2)
+ return i1->Op2 - i2->Op2;
+ return i2->is_64 - i1->is_64;
}
#define CRn(_x) .CRn = _x
#define CRm(_x) .CRm = _x
+#define CRm64(_x) .CRn = _x, .CRm = 0
#define Op1(_x) .Op1 = _x
#define Op2(_x) .Op2 = _x
#define is64 .is_64 = true
#define is32 .is_64 = false
+bool access_sctlr(struct kvm_vcpu *vcpu,
+ const struct coproc_params *p,
+ const struct coproc_reg *r);
+
#endif /* __ARM_KVM_COPROC_LOCAL_H__ */
diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c
index 685063a..e6f4ae4 100644
--- a/arch/arm/kvm/coproc_a15.c
+++ b/arch/arm/kvm/coproc_a15.c
@@ -17,129 +17,24 @@
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
#include <linux/kvm_host.h>
-#include <asm/cputype.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_host.h>
-#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
#include <linux/init.h>
-static void reset_mpidr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
- /*
- * Compute guest MPIDR:
- * (Even if we present only one VCPU to the guest on an SMP
- * host we don't set the U bit in the MPIDR, or vice versa, as
- * revealing the underlying hardware properties is likely to
- * be the best choice).
- */
- vcpu->arch.cp15[c0_MPIDR] = (read_cpuid_mpidr() & ~MPIDR_LEVEL_MASK)
- | (vcpu->vcpu_id & MPIDR_LEVEL_MASK);
-}
-
#include "coproc.h"
-/* A15 TRM 4.3.28: RO WI */
-static bool access_actlr(struct kvm_vcpu *vcpu,
- const struct coproc_params *p,
- const struct coproc_reg *r)
-{
- if (p->is_write)
- return ignore_write(vcpu, p);
-
- *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c1_ACTLR];
- return true;
-}
-
-/* A15 TRM 4.3.60: R/O. */
-static bool access_cbar(struct kvm_vcpu *vcpu,
- const struct coproc_params *p,
- const struct coproc_reg *r)
-{
- if (p->is_write)
- return write_to_read_only(vcpu, p);
- return read_zero(vcpu, p);
-}
-
-/* A15 TRM 4.3.48: R/O WI. */
-static bool access_l2ctlr(struct kvm_vcpu *vcpu,
- const struct coproc_params *p,
- const struct coproc_reg *r)
-{
- if (p->is_write)
- return ignore_write(vcpu, p);
-
- *vcpu_reg(vcpu, p->Rt1) = vcpu->arch.cp15[c9_L2CTLR];
- return true;
-}
-
-static void reset_l2ctlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
- u32 l2ctlr, ncores;
-
- asm volatile("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
- l2ctlr &= ~(3 << 24);
- ncores = atomic_read(&vcpu->kvm->online_vcpus) - 1;
- l2ctlr |= (ncores & 3) << 24;
-
- vcpu->arch.cp15[c9_L2CTLR] = l2ctlr;
-}
-
-static void reset_actlr(struct kvm_vcpu *vcpu, const struct coproc_reg *r)
-{
- u32 actlr;
-
- /* ACTLR contains SMP bit: make sure you create all cpus first! */
- asm volatile("mrc p15, 0, %0, c1, c0, 1\n" : "=r" (actlr));
- /* Make the SMP bit consistent with the guest configuration */
- if (atomic_read(&vcpu->kvm->online_vcpus) > 1)
- actlr |= 1U << 6;
- else
- actlr &= ~(1U << 6);
-
- vcpu->arch.cp15[c1_ACTLR] = actlr;
-}
-
-/* A15 TRM 4.3.49: R/O WI (even if NSACR.NS_L2ERR, a write of 1 is ignored). */
-static bool access_l2ectlr(struct kvm_vcpu *vcpu,
- const struct coproc_params *p,
- const struct coproc_reg *r)
-{
- if (p->is_write)
- return ignore_write(vcpu, p);
-
- *vcpu_reg(vcpu, p->Rt1) = 0;
- return true;
-}
-
/*
* A15-specific CP15 registers.
- * Important: Must be sorted ascending by CRn, CRM, Op1, Op2
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ * registers preceding 32-bit ones.
*/
static const struct coproc_reg a15_regs[] = {
- /* MPIDR: we use VMPIDR for guest access. */
- { CRn( 0), CRm( 0), Op1( 0), Op2( 5), is32,
- NULL, reset_mpidr, c0_MPIDR },
-
/* SCTLR: swapped by interrupt.S. */
{ CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
- NULL, reset_val, c1_SCTLR, 0x00C50078 },
- /* ACTLR: trapped by HCR.TAC bit. */
- { CRn( 1), CRm( 0), Op1( 0), Op2( 1), is32,
- access_actlr, reset_actlr, c1_ACTLR },
- /* CPACR: swapped by interrupt.S. */
- { CRn( 1), CRm( 0), Op1( 0), Op2( 2), is32,
- NULL, reset_val, c1_CPACR, 0x00000000 },
-
- /*
- * L2CTLR access (guest wants to know #CPUs).
- */
- { CRn( 9), CRm( 0), Op1( 1), Op2( 2), is32,
- access_l2ctlr, reset_l2ctlr, c9_L2CTLR },
- { CRn( 9), CRm( 0), Op1( 1), Op2( 3), is32, access_l2ectlr},
-
- /* The Configuration Base Address Register. */
- { CRn(15), CRm( 0), Op1( 4), Op2( 0), is32, access_cbar},
+ access_sctlr, reset_val, c1_SCTLR, 0x00C50078 },
};
static struct kvm_coproc_target_table a15_target_table = {
@@ -150,12 +45,6 @@
static int __init coproc_a15_init(void)
{
- unsigned int i;
-
- for (i = 1; i < ARRAY_SIZE(a15_regs); i++)
- BUG_ON(cmp_reg(&a15_regs[i-1],
- &a15_regs[i]) >= 0);
-
kvm_register_target_coproc_table(&a15_target_table);
return 0;
}
diff --git a/arch/arm/kvm/coproc_a7.c b/arch/arm/kvm/coproc_a7.c
new file mode 100644
index 0000000..17fc7cd
--- /dev/null
+++ b/arch/arm/kvm/coproc_a7.c
@@ -0,0 +1,54 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Copyright (C) 2013 - ARM Ltd
+ *
+ * Authors: Rusty Russell <rusty@rustcorp.au>
+ * Christoffer Dall <c.dall@virtualopensystems.com>
+ * Jonathan Austin <jonathan.austin@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+#include <linux/kvm_host.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_emulate.h>
+#include <linux/init.h>
+
+#include "coproc.h"
+
+/*
+ * Cortex-A7 specific CP15 registers.
+ * CRn denotes the primary register number, but is copied to the CRm in the
+ * user space API for 64-bit register access in line with the terminology used
+ * in the ARM ARM.
+ * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit
+ * registers preceding 32-bit ones.
+ */
+static const struct coproc_reg a7_regs[] = {
+ /* SCTLR: swapped by interrupt.S. */
+ { CRn( 1), CRm( 0), Op1( 0), Op2( 0), is32,
+ access_sctlr, reset_val, c1_SCTLR, 0x00C50878 },
+};
+
+static struct kvm_coproc_target_table a7_target_table = {
+ .target = KVM_ARM_TARGET_CORTEX_A7,
+ .table = a7_regs,
+ .num = ARRAY_SIZE(a7_regs),
+};
+
+static int __init coproc_a7_init(void)
+{
+ kvm_register_target_coproc_table(&a7_target_table);
+ return 0;
+}
+late_initcall(coproc_a7_init);
diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c
index bdede9e..d6c0052 100644
--- a/arch/arm/kvm/emulate.c
+++ b/arch/arm/kvm/emulate.c
@@ -354,7 +354,7 @@
*vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset;
if (is_pabt) {
- /* Set DFAR and DFSR */
+ /* Set IFAR and IFSR */
vcpu->arch.cp15[c6_IFAR] = addr;
is_lpae = (vcpu->arch.cp15[c2_TTBCR] >> 31);
/* Always give debug fault for now - should give guest a clue */
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 152d036..cc0b787 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -38,6 +38,7 @@
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.hcr = HCR_GUEST_MASK;
return 0;
}
@@ -109,6 +110,73 @@
return -EINVAL;
}
+#ifndef CONFIG_KVM_ARM_TIMER
+
+#define NUM_TIMER_REGS 0
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ return 0;
+}
+
+static bool is_timer_reg(u64 index)
+{
+ return false;
+}
+
+#else
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+ switch (index) {
+ case KVM_REG_ARM_TIMER_CTL:
+ case KVM_REG_ARM_TIMER_CNT:
+ case KVM_REG_ARM_TIMER_CVAL:
+ return true;
+ }
+ return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+ return -EFAULT;
+ uindices++;
+ if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+ return -EFAULT;
+ uindices++;
+ if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+ return -EFAULT;
+
+ return 0;
+}
+
+#endif
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+ int ret;
+
+ ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+ if (ret != 0)
+ return -EFAULT;
+
+ return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+
+ val = kvm_arm_timer_get_reg(vcpu, reg->id);
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
static unsigned long num_core_regs(void)
{
return sizeof(struct kvm_regs) / sizeof(u32);
@@ -121,7 +189,8 @@
*/
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
- return num_core_regs() + kvm_arm_num_coproc_regs(vcpu);
+ return num_core_regs() + kvm_arm_num_coproc_regs(vcpu)
+ + NUM_TIMER_REGS;
}
/**
@@ -133,6 +202,7 @@
{
unsigned int i;
const u64 core_reg = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE;
+ int ret;
for (i = 0; i < sizeof(struct kvm_regs)/sizeof(u32); i++) {
if (put_user(core_reg | i, uindices))
@@ -140,6 +210,11 @@
uindices++;
}
+ ret = copy_timer_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += NUM_TIMER_REGS;
+
return kvm_arm_copy_coproc_indices(vcpu, uindices);
}
@@ -153,6 +228,9 @@
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if (is_timer_reg(reg->id))
+ return get_timer_reg(vcpu, reg);
+
return kvm_arm_coproc_get_reg(vcpu, reg);
}
@@ -166,6 +244,9 @@
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if (is_timer_reg(reg->id))
+ return set_timer_reg(vcpu, reg);
+
return kvm_arm_coproc_set_reg(vcpu, reg);
}
@@ -183,13 +264,9 @@
int __attribute_const__ kvm_target_cpu(void)
{
- unsigned long implementor = read_cpuid_implementor();
- unsigned long part_number = read_cpuid_part_number();
-
- if (implementor != ARM_CPU_IMP_ARM)
- return -EINVAL;
-
- switch (part_number) {
+ switch (read_cpuid_part()) {
+ case ARM_CPU_PART_CORTEX_A7:
+ return KVM_ARM_TARGET_CORTEX_A7;
case ARM_CPU_PART_CORTEX_A15:
return KVM_ARM_TARGET_CORTEX_A15;
default:
@@ -202,7 +279,7 @@
{
unsigned int i;
- /* We can only do a cortex A15 for now. */
+ /* We can only cope with guest==host and only on A15/A7 (for now). */
if (init->target != kvm_target_cpu())
return -EINVAL;
@@ -222,6 +299,26 @@
return kvm_reset_vcpu(vcpu);
}
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
+{
+ int target = kvm_target_cpu();
+
+ if (target < 0)
+ return -ENODEV;
+
+ memset(init, 0, sizeof(*init));
+
+ /*
+ * For now, we don't return any features.
+ * In future, we might use features to return target
+ * specific features available for the preferred
+ * target type.
+ */
+ init->target = (__u32)target;
+
+ return 0;
+}
+
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
return -EINVAL;
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 3d74a0b..4c979d4 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -26,8 +26,6 @@
#include "trace.h"
-#include "trace.h"
-
typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
static int handle_svc_hyp(struct kvm_vcpu *vcpu, struct kvm_run *run)
@@ -40,21 +38,22 @@
static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
+ int ret;
+
trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
kvm_vcpu_hvc_get_imm(vcpu));
- if (kvm_psci_call(vcpu))
+ ret = kvm_psci_call(vcpu);
+ if (ret < 0) {
+ kvm_inject_undefined(vcpu);
return 1;
+ }
- kvm_inject_undefined(vcpu);
- return 1;
+ return ret;
}
static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- if (kvm_psci_call(vcpu))
- return 1;
-
kvm_inject_undefined(vcpu);
return 1;
}
@@ -76,23 +75,29 @@
}
/**
- * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest
+ * kvm_handle_wfx - handle a WFI or WFE instructions trapped in guests
* @vcpu: the vcpu pointer
* @run: the kvm_run structure pointer
*
- * Simply sets the wait_for_interrupts flag on the vcpu structure, which will
- * halt execution of world-switches and schedule other host processes until
- * there is an incoming IRQ or FIQ to the VM.
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
+ * world-switches and schedule other host processes until there is an
+ * incoming IRQ or FIQ to the VM.
*/
-static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run)
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
trace_kvm_wfi(*vcpu_pc(vcpu));
- kvm_vcpu_block(vcpu);
+ if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE)
+ kvm_vcpu_on_spin(vcpu);
+ else
+ kvm_vcpu_block(vcpu);
+
return 1;
}
static exit_handle_fn arm_exit_handlers[] = {
- [HSR_EC_WFI] = kvm_handle_wfi,
+ [HSR_EC_WFI] = kvm_handle_wfx,
[HSR_EC_CP15_32] = kvm_handle_cp15_32,
[HSR_EC_CP15_64] = kvm_handle_cp15_64,
[HSR_EC_CP14_MR] = kvm_handle_cp14_access,
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index f048338..2cc14df 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -71,7 +71,7 @@
bne phase2 @ Yes, second stage init
@ Set the HTTBR to point to the hypervisor PGD pointer passed
- mcrr p15, 4, r2, r3, c2
+ mcrr p15, 4, rr_lo_hi(r2, r3), c2
@ Set the HTCR and VTCR to the same shareability and cacheability
@ settings as the non-secure TTBCR and with T0SZ == 0.
@@ -137,12 +137,12 @@
mov pc, r0
target: @ We're now in the trampoline code, switch page tables
- mcrr p15, 4, r2, r3, c2
+ mcrr p15, 4, rr_lo_hi(r2, r3), c2
isb
@ Invalidate the old TLBs
mcr p15, 4, r0, c8, c7, 0 @ TLBIALLH
- dsb
+ dsb ish
eret
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index f7793df..01dcb0e 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -49,12 +49,13 @@
ENTRY(__kvm_tlb_flush_vmid_ipa)
push {r2, r3}
+ dsb ishst
add r0, r0, #KVM_VTTBR
ldrd r2, r3, [r0]
- mcrr p15, 6, r2, r3, c2 @ Write VTTBR
+ mcrr p15, 6, rr_lo_hi(r2, r3), c2 @ Write VTTBR
isb
mcr p15, 0, r0, c8, c3, 0 @ TLBIALLIS (rt ignored)
- dsb
+ dsb ish
isb
mov r2, #0
mov r3, #0
@@ -78,7 +79,7 @@
mcr p15, 4, r0, c8, c3, 4
/* Invalidate instruction caches Inner Shareable (ICIALLUIS) */
mcr p15, 0, r0, c7, c1, 0
- dsb
+ dsb ish
isb @ Not necessary if followed by eret
bx lr
@@ -134,7 +135,7 @@
ldr r1, [vcpu, #VCPU_KVM]
add r1, r1, #KVM_VTTBR
ldrd r2, r3, [r1]
- mcrr p15, 6, r2, r3, c2 @ Write VTTBR
+ mcrr p15, 6, rr_lo_hi(r2, r3), c2 @ Write VTTBR
@ We're all done, just restore the GPRs and go to the guest
restore_guest_regs
@@ -198,8 +199,13 @@
restore_host_regs
clrex @ Clear exclusive monitor
+#ifndef CONFIG_CPU_ENDIAN_BE8
mov r0, r1 @ Return the return code
mov r1, #0 @ Clear upper bits in return value
+#else
+ @ r1 already has return code
+ mov r0, #0 @ Clear upper bits in return value
+#endif /* CONFIG_CPU_ENDIAN_BE8 */
bx lr @ return to IOCTL
/********************************************************************
@@ -219,6 +225,10 @@
* in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
* passed in r0 and r1.
*
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
* The calling convention follows the standard AAPCS:
* r0 - r3: caller save
* r12: caller save
@@ -291,6 +301,7 @@
ldr r2, =BSYM(panic)
msr ELR_hyp, r2
ldr r0, =\panic_str
+ clrex @ Clear exclusive monitor
eret
.endm
@@ -361,6 +372,11 @@
host_switch_to_hyp:
pop {r0, r1, r2}
+ /* Check for __hyp_get_vectors */
+ cmp r0, #-1
+ mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR
+ beq 1f
+
push {lr}
mrs lr, SPSR
push {lr}
@@ -376,7 +392,7 @@
pop {lr}
msr SPSR_csxf, lr
pop {lr}
- eret
+1: eret
guest_trap:
load_vcpu @ Load VCPU pointer to r0
@@ -414,6 +430,10 @@
mrcne p15, 4, r2, c6, c0, 4 @ HPFAR
bne 3f
+ /* Preserve PAR */
+ mrrc p15, 0, r0, r1, c7 @ PAR
+ push {r0, r1}
+
/* Resolve IPA using the xFAR */
mcr p15, 0, r2, c7, c8, 0 @ ATS1CPR
isb
@@ -424,13 +444,20 @@
lsl r2, r2, #4
orr r2, r2, r1, lsl #24
+ /* Restore PAR */
+ pop {r0, r1}
+ mcrr p15, 0, r0, r1, c7 @ PAR
+
3: load_vcpu @ Load VCPU pointer to r0
str r2, [r0, #VCPU_HPFAR]
1: mov r1, #ARM_EXCEPTION_HVC
b __kvm_vcpu_return
-4: pop {r0, r1, r2} @ Failed translation, return to guest
+4: pop {r0, r1} @ Failed translation, return to guest
+ mcrr p15, 0, r0, r1, c7 @ PAR
+ clrex
+ pop {r0, r1, r2}
eret
/*
@@ -456,6 +483,7 @@
pop {r3-r7}
pop {r0-r2}
+ clrex
eret
#endif
@@ -478,10 +506,10 @@
.section ".rodata"
und_die_str:
- .ascii "unexpected undefined exception in Hyp mode at: %#08x"
+ .ascii "unexpected undefined exception in Hyp mode at: %#08x\n"
pabt_die_str:
- .ascii "unexpected prefetch abort in Hyp mode at: %#08x"
+ .ascii "unexpected prefetch abort in Hyp mode at: %#08x\n"
dabt_die_str:
- .ascii "unexpected data abort in Hyp mode at: %#08x"
+ .ascii "unexpected data abort in Hyp mode at: %#08x\n"
svc_die_str:
- .ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x"
+ .ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x\n"
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 3c8f2f0..98c8c5b 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -1,4 +1,5 @@
#include <linux/irqchip/arm-gic.h>
+#include <asm/assembler.h>
#define VCPU_USR_REG(_reg_nr) (VCPU_USR_REGS + (_reg_nr * 4))
#define VCPU_USR_SP (VCPU_USR_REG(13))
@@ -302,11 +303,18 @@
.endif
mrc p15, 0, r2, c14, c1, 0 @ CNTKCTL
+ mrrc p15, 0, r4, r5, c7 @ PAR
+ mrc p15, 0, r6, c10, c3, 0 @ AMAIR0
+ mrc p15, 0, r7, c10, c3, 1 @ AMAIR1
.if \store_to_vcpu == 0
- push {r2}
+ push {r2,r4-r7}
.else
str r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+ add r12, vcpu, #CP15_OFFSET(c7_PAR)
+ strd r4, r5, [r12]
+ str r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+ str r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
.endif
.endm
@@ -319,12 +327,19 @@
*/
.macro write_cp15_state read_from_vcpu
.if \read_from_vcpu == 0
- pop {r2}
+ pop {r2,r4-r7}
.else
ldr r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+ add r12, vcpu, #CP15_OFFSET(c7_PAR)
+ ldrd r4, r5, [r12]
+ ldr r6, [vcpu, #CP15_OFFSET(c10_AMAIR0)]
+ ldr r7, [vcpu, #CP15_OFFSET(c10_AMAIR1)]
.endif
mcr p15, 0, r2, c14, c1, 0 @ CNTKCTL
+ mcrr p15, 0, r4, r5, c7 @ PAR
+ mcr p15, 0, r6, c10, c3, 0 @ AMAIR0
+ mcr p15, 0, r7, c10, c3, 1 @ AMAIR1
.if \read_from_vcpu == 0
pop {r2-r12}
@@ -406,15 +421,23 @@
ldr r8, [r2, #GICH_ELRSR0]
ldr r9, [r2, #GICH_ELRSR1]
ldr r10, [r2, #GICH_APR]
+ARM_BE8(rev r3, r3 )
+ARM_BE8(rev r4, r4 )
+ARM_BE8(rev r5, r5 )
+ARM_BE8(rev r6, r6 )
+ARM_BE8(rev r7, r7 )
+ARM_BE8(rev r8, r8 )
+ARM_BE8(rev r9, r9 )
+ARM_BE8(rev r10, r10 )
- str r3, [r11, #VGIC_CPU_HCR]
- str r4, [r11, #VGIC_CPU_VMCR]
- str r5, [r11, #VGIC_CPU_MISR]
- str r6, [r11, #VGIC_CPU_EISR]
- str r7, [r11, #(VGIC_CPU_EISR + 4)]
- str r8, [r11, #VGIC_CPU_ELRSR]
- str r9, [r11, #(VGIC_CPU_ELRSR + 4)]
- str r10, [r11, #VGIC_CPU_APR]
+ str r3, [r11, #VGIC_V2_CPU_HCR]
+ str r4, [r11, #VGIC_V2_CPU_VMCR]
+ str r5, [r11, #VGIC_V2_CPU_MISR]
+ str r6, [r11, #VGIC_V2_CPU_EISR]
+ str r7, [r11, #(VGIC_V2_CPU_EISR + 4)]
+ str r8, [r11, #VGIC_V2_CPU_ELRSR]
+ str r9, [r11, #(VGIC_V2_CPU_ELRSR + 4)]
+ str r10, [r11, #VGIC_V2_CPU_APR]
/* Clear GICH_HCR */
mov r5, #0
@@ -422,9 +445,10 @@
/* Save list registers */
add r2, r2, #GICH_LR0
- add r3, r11, #VGIC_CPU_LR
+ add r3, r11, #VGIC_V2_CPU_LR
ldr r4, [r11, #VGIC_CPU_NR_LR]
1: ldr r6, [r2], #4
+ARM_BE8(rev r6, r6 )
str r6, [r3], #4
subs r4, r4, #1
bne 1b
@@ -449,9 +473,12 @@
add r11, vcpu, #VCPU_VGIC_CPU
/* We only restore a minimal set of registers */
- ldr r3, [r11, #VGIC_CPU_HCR]
- ldr r4, [r11, #VGIC_CPU_VMCR]
- ldr r8, [r11, #VGIC_CPU_APR]
+ ldr r3, [r11, #VGIC_V2_CPU_HCR]
+ ldr r4, [r11, #VGIC_V2_CPU_VMCR]
+ ldr r8, [r11, #VGIC_V2_CPU_APR]
+ARM_BE8(rev r3, r3 )
+ARM_BE8(rev r4, r4 )
+ARM_BE8(rev r8, r8 )
str r3, [r2, #GICH_HCR]
str r4, [r2, #GICH_VMCR]
@@ -459,9 +486,10 @@
/* Restore list registers */
add r2, r2, #GICH_LR0
- add r3, r11, #VGIC_CPU_LR
+ add r3, r11, #VGIC_V2_CPU_LR
ldr r4, [r11, #VGIC_CPU_NR_LR]
1: ldr r6, [r3], #4
+ARM_BE8(rev r6, r6 )
str r6, [r2], #4
subs r4, r4, #1
bne 1b
@@ -492,11 +520,15 @@
mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL
isb
- mrrc p15, 3, r2, r3, c14 @ CNTV_CVAL
+ mrrc p15, 3, rr_lo_hi(r2, r3), c14 @ CNTV_CVAL
ldr r4, =VCPU_TIMER_CNTV_CVAL
add r5, vcpu, r4
strd r2, r3, [r5]
+ @ Ensure host CNTVCT == CNTPCT
+ mov r2, #0
+ mcrr p15, 4, r2, r2, c14 @ CNTVOFF
+
1:
#endif
@ Allow physical timer/counter access for the host
@@ -528,12 +560,12 @@
ldr r2, [r4, #KVM_TIMER_CNTVOFF]
ldr r3, [r4, #(KVM_TIMER_CNTVOFF + 4)]
- mcrr p15, 4, r2, r3, c14 @ CNTVOFF
+ mcrr p15, 4, rr_lo_hi(r2, r3), c14 @ CNTVOFF
ldr r4, =VCPU_TIMER_CNTV_CVAL
add r5, vcpu, r4
ldrd r2, r3, [r5]
- mcrr p15, 3, r2, r3, c14 @ CNTV_CVAL
+ mcrr p15, 3, rr_lo_hi(r2, r3), c14 @ CNTV_CVAL
isb
ldr r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
@@ -587,17 +619,14 @@
/* Enable/Disable: stage-2 trans., trap interrupts, trap wfi, trap smc */
.macro configure_hyp_role operation
- mrc p15, 4, r2, c1, c1, 0 @ HCR
- bic r2, r2, #HCR_VIRT_EXCP_MASK
- ldr r3, =HCR_GUEST_MASK
.if \operation == vmentry
- orr r2, r2, r3
+ ldr r2, [vcpu, #VCPU_HCR]
ldr r3, [vcpu, #VCPU_IRQ_LINES]
orr r2, r2, r3
.else
- bic r2, r2, r3
+ mov r2, #0
.endif
- mcr p15, 4, r2, c1, c1, 0
+ mcr p15, 4, r2, c1, c1, 0 @ HCR
.endm
.macro load_vcpu
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 72a12f2..4cb5a93 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -23,6 +23,68 @@
#include "trace.h"
+static void mmio_write_buf(char *buf, unsigned int len, unsigned long data)
+{
+ void *datap = NULL;
+ union {
+ u8 byte;
+ u16 hword;
+ u32 word;
+ u64 dword;
+ } tmp;
+
+ switch (len) {
+ case 1:
+ tmp.byte = data;
+ datap = &tmp.byte;
+ break;
+ case 2:
+ tmp.hword = data;
+ datap = &tmp.hword;
+ break;
+ case 4:
+ tmp.word = data;
+ datap = &tmp.word;
+ break;
+ case 8:
+ tmp.dword = data;
+ datap = &tmp.dword;
+ break;
+ }
+
+ memcpy(buf, datap, len);
+}
+
+static unsigned long mmio_read_buf(char *buf, unsigned int len)
+{
+ unsigned long data = 0;
+ union {
+ u16 hword;
+ u32 word;
+ u64 dword;
+ } tmp;
+
+ switch (len) {
+ case 1:
+ data = buf[0];
+ break;
+ case 2:
+ memcpy(&tmp.hword, buf, len);
+ data = tmp.hword;
+ break;
+ case 4:
+ memcpy(&tmp.word, buf, len);
+ data = tmp.word;
+ break;
+ case 8:
+ memcpy(&tmp.dword, buf, len);
+ data = tmp.dword;
+ break;
+ }
+
+ return data;
+}
+
/**
* kvm_handle_mmio_return -- Handle MMIO loads after user space emulation
* @vcpu: The VCPU pointer
@@ -33,28 +95,27 @@
*/
int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
- unsigned long *dest;
+ unsigned long data;
unsigned int len;
int mask;
if (!run->mmio.is_write) {
- dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt);
- *dest = 0;
-
len = run->mmio.len;
if (len > sizeof(unsigned long))
return -EINVAL;
- memcpy(dest, run->mmio.data, len);
-
- trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
- *((u64 *)run->mmio.data));
+ data = mmio_read_buf(run->mmio.data, len);
if (vcpu->arch.mmio_decode.sign_extend &&
len < sizeof(unsigned long)) {
mask = 1U << ((len * 8) - 1);
- *dest = (*dest ^ mask) - mask;
+ data = (data ^ mask) - mask;
}
+
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
+ data);
+ data = vcpu_data_host_to_guest(vcpu, data, len);
+ *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
}
return 0;
@@ -63,7 +124,8 @@
static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_exit_mmio *mmio)
{
- unsigned long rt, len;
+ unsigned long rt;
+ int len;
bool is_write, sign_extend;
if (kvm_vcpu_dabt_isextabt(vcpu)) {
@@ -86,12 +148,6 @@
sign_extend = kvm_vcpu_dabt_issext(vcpu);
rt = kvm_vcpu_dabt_get_rd(vcpu);
- if (kvm_vcpu_reg_is_pc(vcpu, rt)) {
- /* IO memory trying to read/write pc */
- kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
- return 1;
- }
-
mmio->is_write = is_write;
mmio->phys_addr = fault_ipa;
mmio->len = len;
@@ -110,6 +166,7 @@
phys_addr_t fault_ipa)
{
struct kvm_exit_mmio mmio;
+ unsigned long data;
unsigned long rt;
int ret;
@@ -130,13 +187,15 @@
}
rt = vcpu->arch.mmio_decode.rt;
+ data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len);
+
trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE :
KVM_TRACE_MMIO_READ_UNSATISFIED,
mmio.len, fault_ipa,
- (mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0);
+ (mmio.is_write) ? data : 0);
if (mmio.is_write)
- memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len);
+ mmio_write_buf(mmio.data, mmio.len, data);
if (vgic_handle_mmio(vcpu, run, &mmio))
return 1;
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 84ba67b..eea0306 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -19,6 +19,7 @@
#include <linux/mman.h>
#include <linux/kvm_host.h>
#include <linux/io.h>
+#include <linux/hugetlb.h>
#include <trace/events/kvm.h>
#include <asm/pgalloc.h>
#include <asm/cacheflush.h>
@@ -41,6 +42,10 @@
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
+#define kvm_pmd_huge(_x) (pmd_huge(_x) || pmd_trans_huge(_x))
+
static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
/*
@@ -85,9 +90,19 @@
return p;
}
+static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
+{
+ pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
+ pgd_clear(pgd);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ pud_free(NULL, pud_table);
+ put_page(virt_to_page(pgd));
+}
+
static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
pmd_t *pmd_table = pmd_offset(pud, 0);
+ VM_BUG_ON(pud_huge(*pud));
pud_clear(pud);
kvm_tlb_flush_vmid_ipa(kvm, addr);
pmd_free(NULL, pmd_table);
@@ -97,73 +112,186 @@
static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
{
pte_t *pte_table = pte_offset_kernel(pmd, 0);
+ VM_BUG_ON(kvm_pmd_huge(*pmd));
pmd_clear(pmd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
pte_free_kernel(NULL, pte_table);
put_page(virt_to_page(pmd));
}
-static bool pmd_empty(pmd_t *pmd)
+static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+ phys_addr_t addr, phys_addr_t end)
{
- struct page *pmd_page = virt_to_page(pmd);
- return page_count(pmd_page) == 1;
-}
+ phys_addr_t start_addr = addr;
+ pte_t *pte, *start_pte;
-static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
-{
- if (pte_present(*pte)) {
- kvm_set_pte(pte, __pte(0));
- put_page(virt_to_page(pte));
- kvm_tlb_flush_vmid_ipa(kvm, addr);
- }
-}
-
-static bool pte_empty(pte_t *pte)
-{
- struct page *pte_page = virt_to_page(pte);
- return page_count(pte_page) == 1;
-}
-
-static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
- unsigned long long start, u64 size)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
- unsigned long long addr = start, end = start + size;
- u64 range;
-
- while (addr < end) {
- pgd = pgdp + pgd_index(addr);
- pud = pud_offset(pgd, addr);
- if (pud_none(*pud)) {
- addr += PUD_SIZE;
- continue;
+ start_pte = pte = pte_offset_kernel(pmd, addr);
+ do {
+ if (!pte_none(*pte)) {
+ kvm_set_pte(pte, __pte(0));
+ put_page(virt_to_page(pte));
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
}
+ } while (pte++, addr += PAGE_SIZE, addr != end);
- pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd)) {
- addr += PMD_SIZE;
- continue;
- }
+ if (kvm_pte_table_empty(start_pte))
+ clear_pmd_entry(kvm, pmd, start_addr);
+}
- pte = pte_offset_kernel(pmd, addr);
- clear_pte_entry(kvm, pte, addr);
- range = PAGE_SIZE;
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+ phys_addr_t addr, phys_addr_t end)
+{
+ phys_addr_t next, start_addr = addr;
+ pmd_t *pmd, *start_pmd;
- /* If we emptied the pte, walk back up the ladder */
- if (pte_empty(pte)) {
- clear_pmd_entry(kvm, pmd, addr);
- range = PMD_SIZE;
- if (pmd_empty(pmd)) {
- clear_pud_entry(kvm, pud, addr);
- range = PUD_SIZE;
+ start_pmd = pmd = pmd_offset(pud, addr);
+ do {
+ next = kvm_pmd_addr_end(addr, end);
+ if (!pmd_none(*pmd)) {
+ if (kvm_pmd_huge(*pmd)) {
+ pmd_clear(pmd);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ put_page(virt_to_page(pmd));
+ } else {
+ unmap_ptes(kvm, pmd, addr, next);
}
}
+ } while (pmd++, addr = next, addr != end);
- addr += range;
- }
+ if (kvm_pmd_table_empty(start_pmd))
+ clear_pud_entry(kvm, pud, start_addr);
+}
+
+static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ phys_addr_t next, start_addr = addr;
+ pud_t *pud, *start_pud;
+
+ start_pud = pud = pud_offset(pgd, addr);
+ do {
+ next = kvm_pud_addr_end(addr, end);
+ if (!pud_none(*pud)) {
+ if (pud_huge(*pud)) {
+ pud_clear(pud);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ put_page(virt_to_page(pud));
+ } else {
+ unmap_pmds(kvm, pud, addr, next);
+ }
+ }
+ } while (pud++, addr = next, addr != end);
+
+ if (kvm_pud_table_empty(start_pud))
+ clear_pgd_entry(kvm, pgd, start_addr);
+}
+
+
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+ phys_addr_t start, u64 size)
+{
+ pgd_t *pgd;
+ phys_addr_t addr = start, end = start + size;
+ phys_addr_t next;
+
+ pgd = pgdp + pgd_index(addr);
+ do {
+ next = kvm_pgd_addr_end(addr, end);
+ unmap_puds(kvm, pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
+}
+
+static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pte_t *pte;
+
+ pte = pte_offset_kernel(pmd, addr);
+ do {
+ if (!pte_none(*pte)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PAGE_SIZE);
+ }
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pmd_t *pmd;
+ phys_addr_t next;
+
+ pmd = pmd_offset(pud, addr);
+ do {
+ next = kvm_pmd_addr_end(addr, end);
+ if (!pmd_none(*pmd)) {
+ if (kvm_pmd_huge(*pmd)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PMD_SIZE);
+ } else {
+ stage2_flush_ptes(kvm, pmd, addr, next);
+ }
+ }
+ } while (pmd++, addr = next, addr != end);
+}
+
+static void stage2_flush_puds(struct kvm *kvm, pgd_t *pgd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ pud_t *pud;
+ phys_addr_t next;
+
+ pud = pud_offset(pgd, addr);
+ do {
+ next = kvm_pud_addr_end(addr, end);
+ if (!pud_none(*pud)) {
+ if (pud_huge(*pud)) {
+ hva_t hva = gfn_to_hva(kvm, addr >> PAGE_SHIFT);
+ kvm_flush_dcache_to_poc((void*)hva, PUD_SIZE);
+ } else {
+ stage2_flush_pmds(kvm, pud, addr, next);
+ }
+ }
+ } while (pud++, addr = next, addr != end);
+}
+
+static void stage2_flush_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+{
+ phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+ phys_addr_t end = addr + PAGE_SIZE * memslot->npages;
+ phys_addr_t next;
+ pgd_t *pgd;
+
+ pgd = kvm->arch.pgd + pgd_index(addr);
+ do {
+ next = kvm_pgd_addr_end(addr, end);
+ stage2_flush_puds(kvm, pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_flush_vm - Invalidate cache for pages mapped in stage 2
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the stage 2 page tables and invalidate any cache lines
+ * backing memory already mapped to the VM.
+ */
+void stage2_flush_vm(struct kvm *kvm)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(memslot, slots)
+ stage2_flush_memslot(kvm, memslot);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
}
/**
@@ -178,14 +306,14 @@
if (boot_hyp_pgd) {
unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
- kfree(boot_hyp_pgd);
+ free_pages((unsigned long)boot_hyp_pgd, pgd_order);
boot_hyp_pgd = NULL;
}
if (hyp_pgd)
unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
- kfree(init_bounce_page);
+ free_page((unsigned long)init_bounce_page);
init_bounce_page = NULL;
mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -215,7 +343,7 @@
for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
- kfree(hyp_pgd);
+ free_pages((unsigned long)hyp_pgd, pgd_order);
hyp_pgd = NULL;
}
@@ -313,6 +441,17 @@
return err;
}
+static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
+{
+ if (!is_vmalloc_addr(kaddr)) {
+ BUG_ON(!virt_addr_valid(kaddr));
+ return __pa(kaddr);
+ } else {
+ return page_to_phys(vmalloc_to_page(kaddr)) +
+ offset_in_page(kaddr);
+ }
+}
+
/**
* create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
* @from: The virtual kernel start address of the range
@@ -324,16 +463,27 @@
*/
int create_hyp_mappings(void *from, void *to)
{
- unsigned long phys_addr = virt_to_phys(from);
+ phys_addr_t phys_addr;
+ unsigned long virt_addr;
unsigned long start = KERN_TO_HYP((unsigned long)from);
unsigned long end = KERN_TO_HYP((unsigned long)to);
- /* Check for a valid kernel memory mapping */
- if (!virt_addr_valid(from) || !virt_addr_valid(to - 1))
- return -EINVAL;
+ start = start & PAGE_MASK;
+ end = PAGE_ALIGN(end);
- return __create_hyp_mappings(hyp_pgd, start, end,
- __phys_to_pfn(phys_addr), PAGE_HYP);
+ for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) {
+ int err;
+
+ phys_addr = kvm_kaddr_to_phys(from + virt_addr - start);
+ err = __create_hyp_mappings(hyp_pgd, virt_addr,
+ virt_addr + PAGE_SIZE,
+ __phys_to_pfn(phys_addr),
+ PAGE_HYP);
+ if (err)
+ return err;
+ }
+
+ return 0;
}
/**
@@ -382,9 +532,6 @@
if (!pgd)
return -ENOMEM;
- /* stage-2 pgd must be aligned to its size */
- VM_BUG_ON((unsigned long)pgd & (S2_PGD_SIZE - 1));
-
memset(pgd, 0, PTRS_PER_S2_PGD * sizeof(pgd_t));
kvm_clean_pgd(pgd);
kvm->arch.pgd = pgd;
@@ -429,29 +576,71 @@
kvm->arch.pgd = NULL;
}
-
-static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
- phys_addr_t addr, const pte_t *new_pte, bool iomap)
+static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+ phys_addr_t addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
- pte_t *pte, old_pte;
- /* Create 2nd stage page table mapping - Level 1 */
pgd = kvm->arch.pgd + pgd_index(addr);
pud = pud_offset(pgd, addr);
if (pud_none(*pud)) {
if (!cache)
- return 0; /* ignore calls from kvm_set_spte_hva */
+ return NULL;
pmd = mmu_memory_cache_alloc(cache);
pud_populate(NULL, pud, pmd);
get_page(virt_to_page(pud));
}
- pmd = pmd_offset(pud, addr);
+ return pmd_offset(pud, addr);
+}
- /* Create 2nd stage page table mapping - Level 2 */
+static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
+ *cache, phys_addr_t addr, const pmd_t *new_pmd)
+{
+ pmd_t *pmd, old_pmd;
+
+ pmd = stage2_get_pmd(kvm, cache, addr);
+ VM_BUG_ON(!pmd);
+
+ /*
+ * Mapping in huge pages should only happen through a fault. If a
+ * page is merged into a transparent huge page, the individual
+ * subpages of that huge page should be unmapped through MMU
+ * notifiers before we get here.
+ *
+ * Merging of CompoundPages is not supported; they should become
+ * splitting first, unmapped, merged, and mapped back in on-demand.
+ */
+ VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd));
+
+ old_pmd = *pmd;
+ kvm_set_pmd(pmd, *new_pmd);
+ if (pmd_present(old_pmd))
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ else
+ get_page(virt_to_page(pmd));
+ return 0;
+}
+
+static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+ phys_addr_t addr, const pte_t *new_pte, bool iomap)
+{
+ pmd_t *pmd;
+ pte_t *pte, old_pte;
+
+ /* Create stage-2 page table mapping - Level 1 */
+ pmd = stage2_get_pmd(kvm, cache, addr);
+ if (!pmd) {
+ /*
+ * Ignore calls from kvm_set_spte_hva for unallocated
+ * address ranges.
+ */
+ return 0;
+ }
+
+ /* Create stage-2 page mappings - Level 2 */
if (pmd_none(*pmd)) {
if (!cache)
return 0; /* ignore calls from kvm_set_spte_hva */
@@ -498,7 +687,6 @@
for (addr = guest_ipa; addr < end; addr += PAGE_SIZE) {
pte_t pte = pfn_pte(pfn, PAGE_S2_DEVICE);
- kvm_set_s2pte_writable(&pte);
ret = mmu_topup_memory_cache(&cache, 2, 2);
if (ret)
@@ -517,23 +705,97 @@
return ret;
}
+static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
+{
+ pfn_t pfn = *pfnp;
+ gfn_t gfn = *ipap >> PAGE_SHIFT;
+
+ if (PageTransCompound(pfn_to_page(pfn))) {
+ unsigned long mask;
+ /*
+ * The address we faulted on is backed by a transparent huge
+ * page. However, because we map the compound huge page and
+ * not the individual tail page, we need to transfer the
+ * refcount to the head page. We have to be careful that the
+ * THP doesn't start to split while we are adjusting the
+ * refcounts.
+ *
+ * We are sure this doesn't happen, because mmu_notifier_retry
+ * was successful and we are holding the mmu_lock, so if this
+ * THP is trying to split, it will be blocked in the mmu
+ * notifier before touching any of the pages, specifically
+ * before being able to call __split_huge_page_refcount().
+ *
+ * We can therefore safely transfer the refcount from PG_tail
+ * to PG_head and switch the pfn from a tail page to the head
+ * page accordingly.
+ */
+ mask = PTRS_PER_PMD - 1;
+ VM_BUG_ON((gfn & mask) != (pfn & mask));
+ if (pfn & mask) {
+ *ipap &= PMD_MASK;
+ kvm_release_pfn_clean(pfn);
+ pfn &= ~mask;
+ kvm_get_pfn(pfn);
+ *pfnp = pfn;
+ }
+
+ return true;
+ }
+
+ return false;
+}
+
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+ if (kvm_vcpu_trap_is_iabt(vcpu))
+ return false;
+
+ return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
- gfn_t gfn, struct kvm_memory_slot *memslot,
+ struct kvm_memory_slot *memslot, unsigned long hva,
unsigned long fault_status)
{
- pte_t new_pte;
- pfn_t pfn;
int ret;
- bool write_fault, writable;
+ bool write_fault, writable, hugetlb = false, force_pte = false;
unsigned long mmu_seq;
+ gfn_t gfn = fault_ipa >> PAGE_SHIFT;
+ struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
+ struct vm_area_struct *vma;
+ pfn_t pfn;
+ pgprot_t mem_type = PAGE_S2;
- write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+ write_fault = kvm_is_write_fault(vcpu);
if (fault_status == FSC_PERM && !write_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
+ /* Let's check if we will get back a huge page backed by hugetlbfs */
+ down_read(¤t->mm->mmap_sem);
+ vma = find_vma_intersection(current->mm, hva, hva + 1);
+ if (is_vm_hugetlb_page(vma)) {
+ hugetlb = true;
+ gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
+ } else {
+ /*
+ * Pages belonging to memslots that don't have the same
+ * alignment for userspace and IPA cannot be mapped using
+ * block descriptors even if the pages belong to a THP for
+ * the process, because the stage-2 block descriptor will
+ * cover more than a single THP and we loose atomicity for
+ * unmapping, updates, and splits of the THP or other pages
+ * in the stage-2 block range.
+ */
+ if ((memslot->userspace_addr & ~PMD_MASK) !=
+ ((memslot->base_gfn << PAGE_SHIFT) & ~PMD_MASK))
+ force_pte = true;
+ }
+ up_read(¤t->mm->mmap_sem);
+
/* We need minimum second+third level pages */
ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
if (ret)
@@ -551,26 +813,44 @@
*/
smp_rmb();
- pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write_fault, &writable);
+ pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
if (is_error_pfn(pfn))
return -EFAULT;
- new_pte = pfn_pte(pfn, PAGE_S2);
- coherent_icache_guest_page(vcpu->kvm, gfn);
+ if (kvm_is_mmio_pfn(pfn))
+ mem_type = PAGE_S2_DEVICE;
- spin_lock(&vcpu->kvm->mmu_lock);
- if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+ spin_lock(&kvm->mmu_lock);
+ if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
- if (writable) {
- kvm_set_s2pte_writable(&new_pte);
- kvm_set_pfn_dirty(pfn);
+ if (!hugetlb && !force_pte)
+ hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
+
+ if (hugetlb) {
+ pmd_t new_pmd = pfn_pmd(pfn, mem_type);
+ new_pmd = pmd_mkhuge(new_pmd);
+ if (writable) {
+ kvm_set_s2pmd_writable(&new_pmd);
+ kvm_set_pfn_dirty(pfn);
+ }
+ coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
+ ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
+ } else {
+ pte_t new_pte = pfn_pte(pfn, mem_type);
+ if (writable) {
+ kvm_set_s2pte_writable(&new_pte);
+ kvm_set_pfn_dirty(pfn);
+ }
+ coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
+ ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
+ mem_type == PAGE_S2_DEVICE);
}
- stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte, false);
+
out_unlock:
- spin_unlock(&vcpu->kvm->mmu_lock);
+ spin_unlock(&kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
- return 0;
+ return ret;
}
/**
@@ -590,7 +870,8 @@
unsigned long fault_status;
phys_addr_t fault_ipa;
struct kvm_memory_slot *memslot;
- bool is_iabt;
+ unsigned long hva;
+ bool is_iabt, write_fault, writable;
gfn_t gfn;
int ret, idx;
@@ -601,17 +882,22 @@
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
- fault_status = kvm_vcpu_trap_get_fault(vcpu);
+ fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
- kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n",
- kvm_vcpu_trap_get_class(vcpu), fault_status);
+ kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+ kvm_vcpu_trap_get_class(vcpu),
+ (unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+ (unsigned long)kvm_vcpu_get_hsr(vcpu));
return -EFAULT;
}
idx = srcu_read_lock(&vcpu->kvm->srcu);
gfn = fault_ipa >> PAGE_SHIFT;
- if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+ memslot = gfn_to_memslot(vcpu->kvm, gfn);
+ hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+ write_fault = kvm_is_write_fault(vcpu);
+ if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
if (is_iabt) {
/* Prefetch Abort on I/O address */
kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
@@ -619,13 +905,6 @@
goto out_unlock;
}
- if (fault_status != FSC_FAULT) {
- kvm_err("Unsupported fault status on io memory: %#lx\n",
- fault_status);
- ret = -EFAULT;
- goto out_unlock;
- }
-
/*
* The IPA is reported as [MAX:12], so we need to
* complement it with the bottom 12 bits from the
@@ -637,9 +916,7 @@
goto out_unlock;
}
- memslot = gfn_to_memslot(vcpu->kvm, gfn);
-
- ret = user_mem_abort(vcpu, fault_ipa, gfn, memslot, fault_status);
+ ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
if (ret == 0)
ret = 1;
out_unlock:
@@ -757,9 +1034,9 @@
{
int err;
- hyp_idmap_start = virt_to_phys(__hyp_idmap_text_start);
- hyp_idmap_end = virt_to_phys(__hyp_idmap_text_end);
- hyp_idmap_vector = virt_to_phys(__kvm_hyp_init);
+ hyp_idmap_start = kvm_virt_to_phys(__hyp_idmap_text_start);
+ hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
+ hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);
if ((hyp_idmap_start ^ hyp_idmap_end) & PAGE_MASK) {
/*
@@ -769,7 +1046,7 @@
size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
phys_addr_t phys_base;
- init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
if (!init_bounce_page) {
kvm_err("Couldn't allocate HYP init bounce page\n");
err = -ENOMEM;
@@ -786,7 +1063,7 @@
*/
kvm_flush_dcache_to_poc(init_bounce_page, len);
- phys_base = virt_to_phys(init_bounce_page);
+ phys_base = kvm_virt_to_phys(init_bounce_page);
hyp_idmap_vector += phys_base - hyp_idmap_start;
hyp_idmap_start = phys_base;
hyp_idmap_end = phys_base + len;
@@ -795,8 +1072,9 @@
(unsigned long)phys_base);
}
- hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
- boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+ hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+ boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
if (!hyp_pgd || !boot_hyp_pgd) {
kvm_err("Hyp mode PGD not allocated\n");
err = -ENOMEM;
@@ -842,3 +1120,49 @@
free_hyp_pgds();
return err;
}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ enum kvm_mr_change change)
+{
+ gpa_t gpa = old->base_gfn << PAGE_SHIFT;
+ phys_addr_t size = old->npages << PAGE_SHIFT;
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ spin_lock(&kvm->mmu_lock);
+ unmap_stage2_range(kvm, gpa, size);
+ spin_unlock(&kvm->mmu_lock);
+ }
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ struct kvm_userspace_memory_region *mem,
+ enum kvm_mr_change change)
+{
+ return 0;
+}
+
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
+{
+ return 0;
+}
+
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot)
+{
+}
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 7ee5bb7..09cf377 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -18,6 +18,7 @@
#include <linux/kvm_host.h>
#include <linux/wait.h>
+#include <asm/cputype.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_psci.h>
@@ -26,6 +27,36 @@
* as described in ARM document number ARM DEN 0022A.
*/
+#define AFFINITY_MASK(level) ~((0x1UL << ((level) * MPIDR_LEVEL_BITS)) - 1)
+
+static unsigned long psci_affinity_mask(unsigned long affinity_level)
+{
+ if (affinity_level <= 3)
+ return MPIDR_HWID_BITMASK & AFFINITY_MASK(affinity_level);
+
+ return 0;
+}
+
+static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
+{
+ /*
+ * NOTE: For simplicity, we make VCPU suspend emulation to be
+ * same-as WFI (Wait-for-interrupt) emulation.
+ *
+ * This means for KVM the wakeup events are interrupts and
+ * this is consistent with intended use of StateID as described
+ * in section 5.4.1 of PSCI v0.2 specification (ARM DEN 0022A).
+ *
+ * Further, we also treat power-down request to be same as
+ * stand-by request as-per section 5.4.2 clause 3 of PSCI v0.2
+ * specification (ARM DEN 0022A). This means all suspend states
+ * for KVM will preserve the register state.
+ */
+ kvm_vcpu_block(vcpu);
+
+ return PSCI_RET_SUCCESS;
+}
+
static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
{
vcpu->arch.pause = true;
@@ -34,25 +65,41 @@
static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
{
struct kvm *kvm = source_vcpu->kvm;
- struct kvm_vcpu *vcpu;
+ struct kvm_vcpu *vcpu = NULL, *tmp;
wait_queue_head_t *wq;
unsigned long cpu_id;
+ unsigned long context_id;
+ unsigned long mpidr;
phys_addr_t target_pc;
+ int i;
cpu_id = *vcpu_reg(source_vcpu, 1);
if (vcpu_mode_is_32bit(source_vcpu))
cpu_id &= ~((u32) 0);
- if (cpu_id >= atomic_read(&kvm->online_vcpus))
- return KVM_PSCI_RET_INVAL;
+ kvm_for_each_vcpu(i, tmp, kvm) {
+ mpidr = kvm_vcpu_get_mpidr(tmp);
+ if ((mpidr & MPIDR_HWID_BITMASK) == (cpu_id & MPIDR_HWID_BITMASK)) {
+ vcpu = tmp;
+ break;
+ }
+ }
+
+ /*
+ * Make sure the caller requested a valid CPU and that the CPU is
+ * turned off.
+ */
+ if (!vcpu)
+ return PSCI_RET_INVALID_PARAMS;
+ if (!vcpu->arch.pause) {
+ if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
+ return PSCI_RET_ALREADY_ON;
+ else
+ return PSCI_RET_INVALID_PARAMS;
+ }
target_pc = *vcpu_reg(source_vcpu, 2);
-
- vcpu = kvm_get_vcpu(kvm, cpu_id);
-
- wq = kvm_arch_vcpu_wq(vcpu);
- if (!waitqueue_active(wq))
- return KVM_PSCI_RET_INVAL;
+ context_id = *vcpu_reg(source_vcpu, 3);
kvm_reset_vcpu(vcpu);
@@ -62,26 +109,165 @@
vcpu_set_thumb(vcpu);
}
+ /* Propagate caller endianness */
+ if (kvm_vcpu_is_be(source_vcpu))
+ kvm_vcpu_set_be(vcpu);
+
*vcpu_pc(vcpu) = target_pc;
+ /*
+ * NOTE: We always update r0 (or x0) because for PSCI v0.1
+ * the general puspose registers are undefined upon CPU_ON.
+ */
+ *vcpu_reg(vcpu, 0) = context_id;
vcpu->arch.pause = false;
smp_mb(); /* Make sure the above is visible */
+ wq = kvm_arch_vcpu_wq(vcpu);
wake_up_interruptible(wq);
- return KVM_PSCI_RET_SUCCESS;
+ return PSCI_RET_SUCCESS;
}
-/**
- * kvm_psci_call - handle PSCI call if r0 value is in range
- * @vcpu: Pointer to the VCPU struct
- *
- * Handle PSCI calls from guests through traps from HVC or SMC instructions.
- * The calling convention is similar to SMC calls to the secure world where
- * the function number is placed in r0 and this function returns true if the
- * function number specified in r0 is withing the PSCI range, and false
- * otherwise.
- */
-bool kvm_psci_call(struct kvm_vcpu *vcpu)
+static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
+{
+ int i;
+ unsigned long mpidr;
+ unsigned long target_affinity;
+ unsigned long target_affinity_mask;
+ unsigned long lowest_affinity_level;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_vcpu *tmp;
+
+ target_affinity = *vcpu_reg(vcpu, 1);
+ lowest_affinity_level = *vcpu_reg(vcpu, 2);
+
+ /* Determine target affinity mask */
+ target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
+ if (!target_affinity_mask)
+ return PSCI_RET_INVALID_PARAMS;
+
+ /* Ignore other bits of target affinity */
+ target_affinity &= target_affinity_mask;
+
+ /*
+ * If one or more VCPU matching target affinity are running
+ * then ON else OFF
+ */
+ kvm_for_each_vcpu(i, tmp, kvm) {
+ mpidr = kvm_vcpu_get_mpidr(tmp);
+ if (((mpidr & target_affinity_mask) == target_affinity) &&
+ !tmp->arch.pause) {
+ return PSCI_0_2_AFFINITY_LEVEL_ON;
+ }
+ }
+
+ return PSCI_0_2_AFFINITY_LEVEL_OFF;
+}
+
+static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
+{
+ memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
+ vcpu->run->system_event.type = type;
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+}
+
+static void kvm_psci_system_off(struct kvm_vcpu *vcpu)
+{
+ kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_SHUTDOWN);
+}
+
+static void kvm_psci_system_reset(struct kvm_vcpu *vcpu)
+{
+ kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET);
+}
+
+int kvm_psci_version(struct kvm_vcpu *vcpu)
+{
+ if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features))
+ return KVM_ARM_PSCI_0_2;
+
+ return KVM_ARM_PSCI_0_1;
+}
+
+static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
+{
+ int ret = 1;
+ unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+ unsigned long val;
+
+ switch (psci_fn) {
+ case PSCI_0_2_FN_PSCI_VERSION:
+ /*
+ * Bits[31:16] = Major Version = 0
+ * Bits[15:0] = Minor Version = 2
+ */
+ val = 2;
+ break;
+ case PSCI_0_2_FN_CPU_SUSPEND:
+ case PSCI_0_2_FN64_CPU_SUSPEND:
+ val = kvm_psci_vcpu_suspend(vcpu);
+ break;
+ case PSCI_0_2_FN_CPU_OFF:
+ kvm_psci_vcpu_off(vcpu);
+ val = PSCI_RET_SUCCESS;
+ break;
+ case PSCI_0_2_FN_CPU_ON:
+ case PSCI_0_2_FN64_CPU_ON:
+ val = kvm_psci_vcpu_on(vcpu);
+ break;
+ case PSCI_0_2_FN_AFFINITY_INFO:
+ case PSCI_0_2_FN64_AFFINITY_INFO:
+ val = kvm_psci_vcpu_affinity_info(vcpu);
+ break;
+ case PSCI_0_2_FN_MIGRATE:
+ case PSCI_0_2_FN64_MIGRATE:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
+ /*
+ * Trusted OS is MP hence does not require migration
+ * or
+ * Trusted OS is not present
+ */
+ val = PSCI_0_2_TOS_MP;
+ break;
+ case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU:
+ case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
+ val = PSCI_RET_NOT_SUPPORTED;
+ break;
+ case PSCI_0_2_FN_SYSTEM_OFF:
+ kvm_psci_system_off(vcpu);
+ /*
+ * We should'nt be going back to guest VCPU after
+ * receiving SYSTEM_OFF request.
+ *
+ * If user space accidently/deliberately resumes
+ * guest VCPU after SYSTEM_OFF request then guest
+ * VCPU should see internal failure from PSCI return
+ * value. To achieve this, we preload r0 (or x0) with
+ * PSCI return value INTERNAL_FAILURE.
+ */
+ val = PSCI_RET_INTERNAL_FAILURE;
+ ret = 0;
+ break;
+ case PSCI_0_2_FN_SYSTEM_RESET:
+ kvm_psci_system_reset(vcpu);
+ /*
+ * Same reason as SYSTEM_OFF for preloading r0 (or x0)
+ * with PSCI return value INTERNAL_FAILURE.
+ */
+ val = PSCI_RET_INTERNAL_FAILURE;
+ ret = 0;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ *vcpu_reg(vcpu, 0) = val;
+ return ret;
+}
+
+static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
{
unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
unsigned long val;
@@ -89,20 +275,45 @@
switch (psci_fn) {
case KVM_PSCI_FN_CPU_OFF:
kvm_psci_vcpu_off(vcpu);
- val = KVM_PSCI_RET_SUCCESS;
+ val = PSCI_RET_SUCCESS;
break;
case KVM_PSCI_FN_CPU_ON:
val = kvm_psci_vcpu_on(vcpu);
break;
case KVM_PSCI_FN_CPU_SUSPEND:
case KVM_PSCI_FN_MIGRATE:
- val = KVM_PSCI_RET_NI;
+ val = PSCI_RET_NOT_SUPPORTED;
break;
-
default:
- return false;
+ return -EINVAL;
}
*vcpu_reg(vcpu, 0) = val;
- return true;
+ return 1;
+}
+
+/**
+ * kvm_psci_call - handle PSCI call if r0 value is in range
+ * @vcpu: Pointer to the VCPU struct
+ *
+ * Handle PSCI calls from guests through traps from HVC instructions.
+ * The calling convention is similar to SMC calls to the secure world
+ * where the function number is placed in r0.
+ *
+ * This function returns: > 0 (success), 0 (success but exit to user
+ * space), and < 0 (errors)
+ *
+ * Errors:
+ * -EINVAL: Unrecognized PSCI function
+ */
+int kvm_psci_call(struct kvm_vcpu *vcpu)
+{
+ switch (kvm_psci_version(vcpu)) {
+ case KVM_ARM_PSCI_0_2:
+ return kvm_psci_0_2_call(vcpu);
+ case KVM_ARM_PSCI_0_1:
+ return kvm_psci_0_1_call(vcpu);
+ default:
+ return -EINVAL;
+ };
}
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index b80256b..f558c07 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -27,16 +27,21 @@
#include <asm/kvm_arm.h>
#include <asm/kvm_coproc.h>
+#include <kvm/arm_arch_timer.h>
+
/******************************************************************************
- * Cortex-A15 Reset Values
+ * Cortex-A15 and Cortex-A7 Reset Values
*/
-static const int a15_max_cpu_idx = 3;
-
-static struct kvm_regs a15_regs_reset = {
+static struct kvm_regs cortexa_regs_reset = {
.usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT,
};
+static const struct kvm_irq_level cortexa_vtimer_irq = {
+ { .irq = 27 },
+ .level = 1,
+};
+
/*******************************************************************************
* Exported reset function
@@ -51,24 +56,28 @@
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
- struct kvm_regs *cpu_reset;
+ struct kvm_regs *reset_regs;
+ const struct kvm_irq_level *cpu_vtimer_irq;
switch (vcpu->arch.target) {
+ case KVM_ARM_TARGET_CORTEX_A7:
case KVM_ARM_TARGET_CORTEX_A15:
- if (vcpu->vcpu_id > a15_max_cpu_idx)
- return -EINVAL;
- cpu_reset = &a15_regs_reset;
+ reset_regs = &cortexa_regs_reset;
vcpu->arch.midr = read_cpuid_id();
+ cpu_vtimer_irq = &cortexa_vtimer_irq;
break;
default:
return -ENODEV;
}
/* Reset core registers */
- memcpy(&vcpu->arch.regs, cpu_reset, sizeof(vcpu->arch.regs));
+ memcpy(&vcpu->arch.regs, reset_regs, sizeof(vcpu->arch.regs));
/* Reset CP15 registers */
kvm_reset_coprocs(vcpu);
+ /* Reset arch_timer context */
+ kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
+
return 0;
}
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index a8e73ed..b1d640f 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -59,10 +59,9 @@
__entry->ipa = ipa;
),
- TP_printk("guest fault at PC %#08lx (hxfar %#08lx, "
- "ipa %#16llx, hsr %#08lx",
- __entry->vcpu_pc, __entry->hxfar,
- __entry->ipa, __entry->hsr)
+ TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+ __entry->ipa, __entry->hsr,
+ __entry->hxfar, __entry->vcpu_pc)
);
TRACE_EVENT(kvm_irq_line,
diff --git a/arch/arm/kvm/vgic.c b/arch/arm/kvm/vgic.c
deleted file mode 100644
index 17c5ac7..0000000
--- a/arch/arm/kvm/vgic.c
+++ /dev/null
@@ -1,1499 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#include <linux/cpu.h>
-#include <linux/kvm.h>
-#include <linux/kvm_host.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include <linux/irqchip/arm-gic.h>
-
-#include <asm/kvm_emulate.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_mmu.h>
-
-/*
- * How the whole thing works (courtesy of Christoffer Dall):
- *
- * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
- * something is pending
- * - VGIC pending interrupts are stored on the vgic.irq_state vgic
- * bitmap (this bitmap is updated by both user land ioctls and guest
- * mmio ops, and other in-kernel peripherals such as the
- * arch. timers) and indicate the 'wire' state.
- * - Every time the bitmap changes, the irq_pending_on_cpu oracle is
- * recalculated
- * - To calculate the oracle, we need info for each cpu from
- * compute_pending_for_cpu, which considers:
- * - PPI: dist->irq_state & dist->irq_enable
- * - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target
- * - irq_spi_target is a 'formatted' version of the GICD_ICFGR
- * registers, stored on each vcpu. We only keep one bit of
- * information per interrupt, making sure that only one vcpu can
- * accept the interrupt.
- * - The same is true when injecting an interrupt, except that we only
- * consider a single interrupt at a time. The irq_spi_cpu array
- * contains the target CPU for each SPI.
- *
- * The handling of level interrupts adds some extra complexity. We
- * need to track when the interrupt has been EOIed, so we can sample
- * the 'line' again. This is achieved as such:
- *
- * - When a level interrupt is moved onto a vcpu, the corresponding
- * bit in irq_active is set. As long as this bit is set, the line
- * will be ignored for further interrupts. The interrupt is injected
- * into the vcpu with the GICH_LR_EOI bit set (generate a
- * maintenance interrupt on EOI).
- * - When the interrupt is EOIed, the maintenance interrupt fires,
- * and clears the corresponding bit in irq_active. This allow the
- * interrupt line to be sampled again.
- */
-
-#define VGIC_ADDR_UNDEF (-1)
-#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF)
-
-/* Physical address of vgic virtual cpu interface */
-static phys_addr_t vgic_vcpu_base;
-
-/* Virtual control interface base address */
-static void __iomem *vgic_vctrl_base;
-
-static struct device_node *vgic_node;
-
-#define ACCESS_READ_VALUE (1 << 0)
-#define ACCESS_READ_RAZ (0 << 0)
-#define ACCESS_READ_MASK(x) ((x) & (1 << 0))
-#define ACCESS_WRITE_IGNORED (0 << 1)
-#define ACCESS_WRITE_SETBIT (1 << 1)
-#define ACCESS_WRITE_CLEARBIT (2 << 1)
-#define ACCESS_WRITE_VALUE (3 << 1)
-#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
-
-static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
-static void vgic_update_state(struct kvm *kvm);
-static void vgic_kick_vcpus(struct kvm *kvm);
-static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
-static u32 vgic_nr_lr;
-
-static unsigned int vgic_maint_irq;
-
-static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
- int cpuid, u32 offset)
-{
- offset >>= 2;
- if (!offset)
- return x->percpu[cpuid].reg;
- else
- return x->shared.reg + offset - 1;
-}
-
-static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
- int cpuid, int irq)
-{
- if (irq < VGIC_NR_PRIVATE_IRQS)
- return test_bit(irq, x->percpu[cpuid].reg_ul);
-
- return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul);
-}
-
-static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
- int irq, int val)
-{
- unsigned long *reg;
-
- if (irq < VGIC_NR_PRIVATE_IRQS) {
- reg = x->percpu[cpuid].reg_ul;
- } else {
- reg = x->shared.reg_ul;
- irq -= VGIC_NR_PRIVATE_IRQS;
- }
-
- if (val)
- set_bit(irq, reg);
- else
- clear_bit(irq, reg);
-}
-
-static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
-{
- if (unlikely(cpuid >= VGIC_MAX_CPUS))
- return NULL;
- return x->percpu[cpuid].reg_ul;
-}
-
-static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
-{
- return x->shared.reg_ul;
-}
-
-static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
-{
- offset >>= 2;
- BUG_ON(offset > (VGIC_NR_IRQS / 4));
- if (offset < 4)
- return x->percpu[cpuid] + offset;
- else
- return x->shared + offset - 8;
-}
-
-#define VGIC_CFG_LEVEL 0
-#define VGIC_CFG_EDGE 1
-
-static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- int irq_val;
-
- irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq);
- return irq_val == VGIC_CFG_EDGE;
-}
-
-static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
-}
-
-static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
-}
-
-static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
-}
-
-static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
-}
-
-static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- return vgic_bitmap_get_irq_val(&dist->irq_state, vcpu->vcpu_id, irq);
-}
-
-static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1);
-}
-
-static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 0);
-}
-
-static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
-{
- if (irq < VGIC_NR_PRIVATE_IRQS)
- set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
- else
- set_bit(irq - VGIC_NR_PRIVATE_IRQS,
- vcpu->arch.vgic_cpu.pending_shared);
-}
-
-static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
-{
- if (irq < VGIC_NR_PRIVATE_IRQS)
- clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
- else
- clear_bit(irq - VGIC_NR_PRIVATE_IRQS,
- vcpu->arch.vgic_cpu.pending_shared);
-}
-
-static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
-{
- return *((u32 *)mmio->data) & mask;
-}
-
-static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
-{
- *((u32 *)mmio->data) = value & mask;
-}
-
-/**
- * vgic_reg_access - access vgic register
- * @mmio: pointer to the data describing the mmio access
- * @reg: pointer to the virtual backing of vgic distributor data
- * @offset: least significant 2 bits used for word offset
- * @mode: ACCESS_ mode (see defines above)
- *
- * Helper to make vgic register access easier using one of the access
- * modes defined for vgic register access
- * (read,raz,write-ignored,setbit,clearbit,write)
- */
-static void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
- phys_addr_t offset, int mode)
-{
- int word_offset = (offset & 3) * 8;
- u32 mask = (1UL << (mmio->len * 8)) - 1;
- u32 regval;
-
- /*
- * Any alignment fault should have been delivered to the guest
- * directly (ARM ARM B3.12.7 "Prioritization of aborts").
- */
-
- if (reg) {
- regval = *reg;
- } else {
- BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED));
- regval = 0;
- }
-
- if (mmio->is_write) {
- u32 data = mmio_data_read(mmio, mask) << word_offset;
- switch (ACCESS_WRITE_MASK(mode)) {
- case ACCESS_WRITE_IGNORED:
- return;
-
- case ACCESS_WRITE_SETBIT:
- regval |= data;
- break;
-
- case ACCESS_WRITE_CLEARBIT:
- regval &= ~data;
- break;
-
- case ACCESS_WRITE_VALUE:
- regval = (regval & ~(mask << word_offset)) | data;
- break;
- }
- *reg = regval;
- } else {
- switch (ACCESS_READ_MASK(mode)) {
- case ACCESS_READ_RAZ:
- regval = 0;
- /* fall through */
-
- case ACCESS_READ_VALUE:
- mmio_data_write(mmio, mask, regval >> word_offset);
- }
- }
-}
-
-static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
- u32 reg;
- u32 word_offset = offset & 3;
-
- switch (offset & ~3) {
- case 0: /* CTLR */
- reg = vcpu->kvm->arch.vgic.enabled;
- vgic_reg_access(mmio, ®, word_offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
- if (mmio->is_write) {
- vcpu->kvm->arch.vgic.enabled = reg & 1;
- vgic_update_state(vcpu->kvm);
- return true;
- }
- break;
-
- case 4: /* TYPER */
- reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
- reg |= (VGIC_NR_IRQS >> 5) - 1;
- vgic_reg_access(mmio, ®, word_offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
- break;
-
- case 8: /* IIDR */
- reg = 0x4B00043B;
- vgic_reg_access(mmio, ®, word_offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
- break;
- }
-
- return false;
-}
-
-static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
- vgic_reg_access(mmio, NULL, offset,
- ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
- return false;
-}
-
-static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
- vcpu->vcpu_id, offset);
- vgic_reg_access(mmio, reg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
- if (mmio->is_write) {
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
- vcpu->vcpu_id, offset);
- vgic_reg_access(mmio, reg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
- if (mmio->is_write) {
- if (offset < 4) /* Force SGI enabled */
- *reg |= 0xffff;
- vgic_retire_disabled_irqs(vcpu);
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
- vcpu->vcpu_id, offset);
- vgic_reg_access(mmio, reg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
- if (mmio->is_write) {
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
- vcpu->vcpu_id, offset);
- vgic_reg_access(mmio, reg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
- if (mmio->is_write) {
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
- vcpu->vcpu_id, offset);
- vgic_reg_access(mmio, reg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
- return false;
-}
-
-#define GICD_ITARGETSR_SIZE 32
-#define GICD_CPUTARGETS_BITS 8
-#define GICD_IRQS_PER_ITARGETSR (GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS)
-static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct kvm_vcpu *vcpu;
- int i, c;
- unsigned long *bmap;
- u32 val = 0;
-
- irq -= VGIC_NR_PRIVATE_IRQS;
-
- kvm_for_each_vcpu(c, vcpu, kvm) {
- bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
- for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
- if (test_bit(irq + i, bmap))
- val |= 1 << (c + i * 8);
- }
-
- return val;
-}
-
-static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct kvm_vcpu *vcpu;
- int i, c;
- unsigned long *bmap;
- u32 target;
-
- irq -= VGIC_NR_PRIVATE_IRQS;
-
- /*
- * Pick the LSB in each byte. This ensures we target exactly
- * one vcpu per IRQ. If the byte is null, assume we target
- * CPU0.
- */
- for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) {
- int shift = i * GICD_CPUTARGETS_BITS;
- target = ffs((val >> shift) & 0xffU);
- target = target ? (target - 1) : 0;
- dist->irq_spi_cpu[irq + i] = target;
- kvm_for_each_vcpu(c, vcpu, kvm) {
- bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
- if (c == target)
- set_bit(irq + i, bmap);
- else
- clear_bit(irq + i, bmap);
- }
- }
-}
-
-static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio,
- phys_addr_t offset)
-{
- u32 reg;
-
- /* We treat the banked interrupts targets as read-only */
- if (offset < 32) {
- u32 roreg = 1 << vcpu->vcpu_id;
- roreg |= roreg << 8;
- roreg |= roreg << 16;
-
- vgic_reg_access(mmio, &roreg, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
- return false;
- }
-
- reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U);
- vgic_reg_access(mmio, ®, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
- if (mmio->is_write) {
- vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U);
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-static u32 vgic_cfg_expand(u16 val)
-{
- u32 res = 0;
- int i;
-
- /*
- * Turn a 16bit value like abcd...mnop into a 32bit word
- * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is.
- */
- for (i = 0; i < 16; i++)
- res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1);
-
- return res;
-}
-
-static u16 vgic_cfg_compress(u32 val)
-{
- u16 res = 0;
- int i;
-
- /*
- * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like
- * abcd...mnop which is what we really care about.
- */
- for (i = 0; i < 16; i++)
- res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i;
-
- return res;
-}
-
-/*
- * The distributor uses 2 bits per IRQ for the CFG register, but the
- * LSB is always 0. As such, we only keep the upper bit, and use the
- * two above functions to compress/expand the bits
- */
-static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
- u32 val;
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
- vcpu->vcpu_id, offset >> 1);
- if (offset & 2)
- val = *reg >> 16;
- else
- val = *reg & 0xffff;
-
- val = vgic_cfg_expand(val);
- vgic_reg_access(mmio, &val, offset,
- ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
- if (mmio->is_write) {
- if (offset < 4) {
- *reg = ~0U; /* Force PPIs/SGIs to 1 */
- return false;
- }
-
- val = vgic_cfg_compress(val);
- if (offset & 2) {
- *reg &= 0xffff;
- *reg |= val << 16;
- } else {
- *reg &= 0xffff << 16;
- *reg |= val;
- }
- }
-
- return false;
-}
-
-static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
- struct kvm_exit_mmio *mmio, phys_addr_t offset)
-{
- u32 reg;
- vgic_reg_access(mmio, ®, offset,
- ACCESS_READ_RAZ | ACCESS_WRITE_VALUE);
- if (mmio->is_write) {
- vgic_dispatch_sgi(vcpu, reg);
- vgic_update_state(vcpu->kvm);
- return true;
- }
-
- return false;
-}
-
-/*
- * I would have liked to use the kvm_bus_io_*() API instead, but it
- * cannot cope with banked registers (only the VM pointer is passed
- * around, and we need the vcpu). One of these days, someone please
- * fix it!
- */
-struct mmio_range {
- phys_addr_t base;
- unsigned long len;
- bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
- phys_addr_t offset);
-};
-
-static const struct mmio_range vgic_ranges[] = {
- {
- .base = GIC_DIST_CTRL,
- .len = 12,
- .handle_mmio = handle_mmio_misc,
- },
- {
- .base = GIC_DIST_IGROUP,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_raz_wi,
- },
- {
- .base = GIC_DIST_ENABLE_SET,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_set_enable_reg,
- },
- {
- .base = GIC_DIST_ENABLE_CLEAR,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_clear_enable_reg,
- },
- {
- .base = GIC_DIST_PENDING_SET,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_set_pending_reg,
- },
- {
- .base = GIC_DIST_PENDING_CLEAR,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_clear_pending_reg,
- },
- {
- .base = GIC_DIST_ACTIVE_SET,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_raz_wi,
- },
- {
- .base = GIC_DIST_ACTIVE_CLEAR,
- .len = VGIC_NR_IRQS / 8,
- .handle_mmio = handle_mmio_raz_wi,
- },
- {
- .base = GIC_DIST_PRI,
- .len = VGIC_NR_IRQS,
- .handle_mmio = handle_mmio_priority_reg,
- },
- {
- .base = GIC_DIST_TARGET,
- .len = VGIC_NR_IRQS,
- .handle_mmio = handle_mmio_target_reg,
- },
- {
- .base = GIC_DIST_CONFIG,
- .len = VGIC_NR_IRQS / 4,
- .handle_mmio = handle_mmio_cfg_reg,
- },
- {
- .base = GIC_DIST_SOFTINT,
- .len = 4,
- .handle_mmio = handle_mmio_sgi_reg,
- },
- {}
-};
-
-static const
-struct mmio_range *find_matching_range(const struct mmio_range *ranges,
- struct kvm_exit_mmio *mmio,
- phys_addr_t base)
-{
- const struct mmio_range *r = ranges;
- phys_addr_t addr = mmio->phys_addr - base;
-
- while (r->len) {
- if (addr >= r->base &&
- (addr + mmio->len) <= (r->base + r->len))
- return r;
- r++;
- }
-
- return NULL;
-}
-
-/**
- * vgic_handle_mmio - handle an in-kernel MMIO access
- * @vcpu: pointer to the vcpu performing the access
- * @run: pointer to the kvm_run structure
- * @mmio: pointer to the data describing the access
- *
- * returns true if the MMIO access has been performed in kernel space,
- * and false if it needs to be emulated in user space.
- */
-bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
- struct kvm_exit_mmio *mmio)
-{
- const struct mmio_range *range;
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- unsigned long base = dist->vgic_dist_base;
- bool updated_state;
- unsigned long offset;
-
- if (!irqchip_in_kernel(vcpu->kvm) ||
- mmio->phys_addr < base ||
- (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE))
- return false;
-
- /* We don't support ldrd / strd or ldm / stm to the emulated vgic */
- if (mmio->len > 4) {
- kvm_inject_dabt(vcpu, mmio->phys_addr);
- return true;
- }
-
- range = find_matching_range(vgic_ranges, mmio, base);
- if (unlikely(!range || !range->handle_mmio)) {
- pr_warn("Unhandled access %d %08llx %d\n",
- mmio->is_write, mmio->phys_addr, mmio->len);
- return false;
- }
-
- spin_lock(&vcpu->kvm->arch.vgic.lock);
- offset = mmio->phys_addr - range->base - base;
- updated_state = range->handle_mmio(vcpu, mmio, offset);
- spin_unlock(&vcpu->kvm->arch.vgic.lock);
- kvm_prepare_mmio(run, mmio);
- kvm_handle_mmio_return(vcpu, run);
-
- if (updated_state)
- vgic_kick_vcpus(vcpu->kvm);
-
- return true;
-}
-
-static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
-{
- struct kvm *kvm = vcpu->kvm;
- struct vgic_dist *dist = &kvm->arch.vgic;
- int nrcpus = atomic_read(&kvm->online_vcpus);
- u8 target_cpus;
- int sgi, mode, c, vcpu_id;
-
- vcpu_id = vcpu->vcpu_id;
-
- sgi = reg & 0xf;
- target_cpus = (reg >> 16) & 0xff;
- mode = (reg >> 24) & 3;
-
- switch (mode) {
- case 0:
- if (!target_cpus)
- return;
-
- case 1:
- target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
- break;
-
- case 2:
- target_cpus = 1 << vcpu_id;
- break;
- }
-
- kvm_for_each_vcpu(c, vcpu, kvm) {
- if (target_cpus & 1) {
- /* Flag the SGI as pending */
- vgic_dist_irq_set(vcpu, sgi);
- dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
- kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
- }
-
- target_cpus >>= 1;
- }
-}
-
-static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
- unsigned long pending_private, pending_shared;
- int vcpu_id;
-
- vcpu_id = vcpu->vcpu_id;
- pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
- pend_shared = vcpu->arch.vgic_cpu.pending_shared;
-
- pending = vgic_bitmap_get_cpu_map(&dist->irq_state, vcpu_id);
- enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
- bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
-
- pending = vgic_bitmap_get_shared_map(&dist->irq_state);
- enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
- bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS);
- bitmap_and(pend_shared, pend_shared,
- vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
- VGIC_NR_SHARED_IRQS);
-
- pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
- pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS);
- return (pending_private < VGIC_NR_PRIVATE_IRQS ||
- pending_shared < VGIC_NR_SHARED_IRQS);
-}
-
-/*
- * Update the interrupt state and determine which CPUs have pending
- * interrupts. Must be called with distributor lock held.
- */
-static void vgic_update_state(struct kvm *kvm)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct kvm_vcpu *vcpu;
- int c;
-
- if (!dist->enabled) {
- set_bit(0, &dist->irq_pending_on_cpu);
- return;
- }
-
- kvm_for_each_vcpu(c, vcpu, kvm) {
- if (compute_pending_for_cpu(vcpu)) {
- pr_debug("CPU%d has pending interrupts\n", c);
- set_bit(c, &dist->irq_pending_on_cpu);
- }
- }
-}
-
-#define LR_CPUID(lr) \
- (((lr) & GICH_LR_PHYSID_CPUID) >> GICH_LR_PHYSID_CPUID_SHIFT)
-#define MK_LR_PEND(src, irq) \
- (GICH_LR_PENDING_BIT | ((src) << GICH_LR_PHYSID_CPUID_SHIFT) | (irq))
-
-/*
- * An interrupt may have been disabled after being made pending on the
- * CPU interface (the classic case is a timer running while we're
- * rebooting the guest - the interrupt would kick as soon as the CPU
- * interface gets enabled, with deadly consequences).
- *
- * The solution is to examine already active LRs, and check the
- * interrupt is still enabled. If not, just retire it.
- */
-static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- int lr;
-
- for_each_set_bit(lr, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
- int irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
-
- if (!vgic_irq_is_enabled(vcpu, irq)) {
- vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
- clear_bit(lr, vgic_cpu->lr_used);
- vgic_cpu->vgic_lr[lr] &= ~GICH_LR_STATE;
- if (vgic_irq_is_active(vcpu, irq))
- vgic_irq_clear_active(vcpu, irq);
- }
- }
-}
-
-/*
- * Queue an interrupt to a CPU virtual interface. Return true on success,
- * or false if it wasn't possible to queue it.
- */
-static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- int lr;
-
- /* Sanitize the input... */
- BUG_ON(sgi_source_id & ~7);
- BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
- BUG_ON(irq >= VGIC_NR_IRQS);
-
- kvm_debug("Queue IRQ%d\n", irq);
-
- lr = vgic_cpu->vgic_irq_lr_map[irq];
-
- /* Do we have an active interrupt for the same CPUID? */
- if (lr != LR_EMPTY &&
- (LR_CPUID(vgic_cpu->vgic_lr[lr]) == sgi_source_id)) {
- kvm_debug("LR%d piggyback for IRQ%d %x\n",
- lr, irq, vgic_cpu->vgic_lr[lr]);
- BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
- vgic_cpu->vgic_lr[lr] |= GICH_LR_PENDING_BIT;
- return true;
- }
-
- /* Try to use another LR for this interrupt */
- lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
- vgic_cpu->nr_lr);
- if (lr >= vgic_cpu->nr_lr)
- return false;
-
- kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
- vgic_cpu->vgic_lr[lr] = MK_LR_PEND(sgi_source_id, irq);
- vgic_cpu->vgic_irq_lr_map[irq] = lr;
- set_bit(lr, vgic_cpu->lr_used);
-
- if (!vgic_irq_is_edge(vcpu, irq))
- vgic_cpu->vgic_lr[lr] |= GICH_LR_EOI;
-
- return true;
-}
-
-static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- unsigned long sources;
- int vcpu_id = vcpu->vcpu_id;
- int c;
-
- sources = dist->irq_sgi_sources[vcpu_id][irq];
-
- for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
- if (vgic_queue_irq(vcpu, c, irq))
- clear_bit(c, &sources);
- }
-
- dist->irq_sgi_sources[vcpu_id][irq] = sources;
-
- /*
- * If the sources bitmap has been cleared it means that we
- * could queue all the SGIs onto link registers (see the
- * clear_bit above), and therefore we are done with them in
- * our emulated gic and can get rid of them.
- */
- if (!sources) {
- vgic_dist_irq_clear(vcpu, irq);
- vgic_cpu_irq_clear(vcpu, irq);
- return true;
- }
-
- return false;
-}
-
-static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
-{
- if (vgic_irq_is_active(vcpu, irq))
- return true; /* level interrupt, already queued */
-
- if (vgic_queue_irq(vcpu, 0, irq)) {
- if (vgic_irq_is_edge(vcpu, irq)) {
- vgic_dist_irq_clear(vcpu, irq);
- vgic_cpu_irq_clear(vcpu, irq);
- } else {
- vgic_irq_set_active(vcpu, irq);
- }
-
- return true;
- }
-
- return false;
-}
-
-/*
- * Fill the list registers with pending interrupts before running the
- * guest.
- */
-static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- int i, vcpu_id;
- int overflow = 0;
-
- vcpu_id = vcpu->vcpu_id;
-
- /*
- * We may not have any pending interrupt, or the interrupts
- * may have been serviced from another vcpu. In all cases,
- * move along.
- */
- if (!kvm_vgic_vcpu_pending_irq(vcpu)) {
- pr_debug("CPU%d has no pending interrupt\n", vcpu_id);
- goto epilog;
- }
-
- /* SGIs */
- for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) {
- if (!vgic_queue_sgi(vcpu, i))
- overflow = 1;
- }
-
- /* PPIs */
- for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) {
- if (!vgic_queue_hwirq(vcpu, i))
- overflow = 1;
- }
-
- /* SPIs */
- for_each_set_bit(i, vgic_cpu->pending_shared, VGIC_NR_SHARED_IRQS) {
- if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
- overflow = 1;
- }
-
-epilog:
- if (overflow) {
- vgic_cpu->vgic_hcr |= GICH_HCR_UIE;
- } else {
- vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
- /*
- * We're about to run this VCPU, and we've consumed
- * everything the distributor had in store for
- * us. Claim we don't have anything pending. We'll
- * adjust that if needed while exiting.
- */
- clear_bit(vcpu_id, &dist->irq_pending_on_cpu);
- }
-}
-
-static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- bool level_pending = false;
-
- kvm_debug("MISR = %08x\n", vgic_cpu->vgic_misr);
-
- if (vgic_cpu->vgic_misr & GICH_MISR_EOI) {
- /*
- * Some level interrupts have been EOIed. Clear their
- * active bit.
- */
- int lr, irq;
-
- for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_eisr,
- vgic_cpu->nr_lr) {
- irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
-
- vgic_irq_clear_active(vcpu, irq);
- vgic_cpu->vgic_lr[lr] &= ~GICH_LR_EOI;
-
- /* Any additional pending interrupt? */
- if (vgic_dist_irq_is_pending(vcpu, irq)) {
- vgic_cpu_irq_set(vcpu, irq);
- level_pending = true;
- } else {
- vgic_cpu_irq_clear(vcpu, irq);
- }
-
- /*
- * Despite being EOIed, the LR may not have
- * been marked as empty.
- */
- set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr);
- vgic_cpu->vgic_lr[lr] &= ~GICH_LR_ACTIVE_BIT;
- }
- }
-
- if (vgic_cpu->vgic_misr & GICH_MISR_U)
- vgic_cpu->vgic_hcr &= ~GICH_HCR_UIE;
-
- return level_pending;
-}
-
-/*
- * Sync back the VGIC state after a guest run. The distributor lock is
- * needed so we don't get preempted in the middle of the state processing.
- */
-static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- int lr, pending;
- bool level_pending;
-
- level_pending = vgic_process_maintenance(vcpu);
-
- /* Clear mappings for empty LRs */
- for_each_set_bit(lr, (unsigned long *)vgic_cpu->vgic_elrsr,
- vgic_cpu->nr_lr) {
- int irq;
-
- if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
- continue;
-
- irq = vgic_cpu->vgic_lr[lr] & GICH_LR_VIRTUALID;
-
- BUG_ON(irq >= VGIC_NR_IRQS);
- vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
- }
-
- /* Check if we still have something up our sleeve... */
- pending = find_first_zero_bit((unsigned long *)vgic_cpu->vgic_elrsr,
- vgic_cpu->nr_lr);
- if (level_pending || pending < vgic_cpu->nr_lr)
- set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
-}
-
-void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- if (!irqchip_in_kernel(vcpu->kvm))
- return;
-
- spin_lock(&dist->lock);
- __kvm_vgic_flush_hwstate(vcpu);
- spin_unlock(&dist->lock);
-}
-
-void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- if (!irqchip_in_kernel(vcpu->kvm))
- return;
-
- spin_lock(&dist->lock);
- __kvm_vgic_sync_hwstate(vcpu);
- spin_unlock(&dist->lock);
-}
-
-int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
-{
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
-
- if (!irqchip_in_kernel(vcpu->kvm))
- return 0;
-
- return test_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
-}
-
-static void vgic_kick_vcpus(struct kvm *kvm)
-{
- struct kvm_vcpu *vcpu;
- int c;
-
- /*
- * We've injected an interrupt, time to find out who deserves
- * a good kick...
- */
- kvm_for_each_vcpu(c, vcpu, kvm) {
- if (kvm_vgic_vcpu_pending_irq(vcpu))
- kvm_vcpu_kick(vcpu);
- }
-}
-
-static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
-{
- int is_edge = vgic_irq_is_edge(vcpu, irq);
- int state = vgic_dist_irq_is_pending(vcpu, irq);
-
- /*
- * Only inject an interrupt if:
- * - edge triggered and we have a rising edge
- * - level triggered and we change level
- */
- if (is_edge)
- return level > state;
- else
- return level != state;
-}
-
-static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
- unsigned int irq_num, bool level)
-{
- struct vgic_dist *dist = &kvm->arch.vgic;
- struct kvm_vcpu *vcpu;
- int is_edge, is_level;
- int enabled;
- bool ret = true;
-
- spin_lock(&dist->lock);
-
- vcpu = kvm_get_vcpu(kvm, cpuid);
- is_edge = vgic_irq_is_edge(vcpu, irq_num);
- is_level = !is_edge;
-
- if (!vgic_validate_injection(vcpu, irq_num, level)) {
- ret = false;
- goto out;
- }
-
- if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
- cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
- vcpu = kvm_get_vcpu(kvm, cpuid);
- }
-
- kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
-
- if (level)
- vgic_dist_irq_set(vcpu, irq_num);
- else
- vgic_dist_irq_clear(vcpu, irq_num);
-
- enabled = vgic_irq_is_enabled(vcpu, irq_num);
-
- if (!enabled) {
- ret = false;
- goto out;
- }
-
- if (is_level && vgic_irq_is_active(vcpu, irq_num)) {
- /*
- * Level interrupt in progress, will be picked up
- * when EOId.
- */
- ret = false;
- goto out;
- }
-
- if (level) {
- vgic_cpu_irq_set(vcpu, irq_num);
- set_bit(cpuid, &dist->irq_pending_on_cpu);
- }
-
-out:
- spin_unlock(&dist->lock);
-
- return ret;
-}
-
-/**
- * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
- * @kvm: The VM structure pointer
- * @cpuid: The CPU for PPIs
- * @irq_num: The IRQ number that is assigned to the device
- * @level: Edge-triggered: true: to trigger the interrupt
- * false: to ignore the call
- * Level-sensitive true: activates an interrupt
- * false: deactivates an interrupt
- *
- * The GIC is not concerned with devices being active-LOW or active-HIGH for
- * level-sensitive interrupts. You can think of the level parameter as 1
- * being HIGH and 0 being LOW and all devices being active-HIGH.
- */
-int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
- bool level)
-{
- if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
- vgic_kick_vcpus(kvm);
-
- return 0;
-}
-
-static irqreturn_t vgic_maintenance_handler(int irq, void *data)
-{
- /*
- * We cannot rely on the vgic maintenance interrupt to be
- * delivered synchronously. This means we can only use it to
- * exit the VM, and we perform the handling of EOIed
- * interrupts on the exit path (see vgic_process_maintenance).
- */
- return IRQ_HANDLED;
-}
-
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- int i;
-
- if (!irqchip_in_kernel(vcpu->kvm))
- return 0;
-
- if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
- return -EBUSY;
-
- for (i = 0; i < VGIC_NR_IRQS; i++) {
- if (i < VGIC_NR_PPIS)
- vgic_bitmap_set_irq_val(&dist->irq_enabled,
- vcpu->vcpu_id, i, 1);
- if (i < VGIC_NR_PRIVATE_IRQS)
- vgic_bitmap_set_irq_val(&dist->irq_cfg,
- vcpu->vcpu_id, i, VGIC_CFG_EDGE);
-
- vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
- }
-
- /*
- * By forcing VMCR to zero, the GIC will restore the binary
- * points to their reset values. Anything else resets to zero
- * anyway.
- */
- vgic_cpu->vgic_vmcr = 0;
-
- vgic_cpu->nr_lr = vgic_nr_lr;
- vgic_cpu->vgic_hcr = GICH_HCR_EN; /* Get the show on the road... */
-
- return 0;
-}
-
-static void vgic_init_maintenance_interrupt(void *info)
-{
- enable_percpu_irq(vgic_maint_irq, 0);
-}
-
-static int vgic_cpu_notify(struct notifier_block *self,
- unsigned long action, void *cpu)
-{
- switch (action) {
- case CPU_STARTING:
- case CPU_STARTING_FROZEN:
- vgic_init_maintenance_interrupt(NULL);
- break;
- case CPU_DYING:
- case CPU_DYING_FROZEN:
- disable_percpu_irq(vgic_maint_irq);
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block vgic_cpu_nb = {
- .notifier_call = vgic_cpu_notify,
-};
-
-int kvm_vgic_hyp_init(void)
-{
- int ret;
- struct resource vctrl_res;
- struct resource vcpu_res;
-
- vgic_node = of_find_compatible_node(NULL, NULL, "arm,cortex-a15-gic");
- if (!vgic_node) {
- kvm_err("error: no compatible vgic node in DT\n");
- return -ENODEV;
- }
-
- vgic_maint_irq = irq_of_parse_and_map(vgic_node, 0);
- if (!vgic_maint_irq) {
- kvm_err("error getting vgic maintenance irq from DT\n");
- ret = -ENXIO;
- goto out;
- }
-
- ret = request_percpu_irq(vgic_maint_irq, vgic_maintenance_handler,
- "vgic", kvm_get_running_vcpus());
- if (ret) {
- kvm_err("Cannot register interrupt %d\n", vgic_maint_irq);
- goto out;
- }
-
- ret = register_cpu_notifier(&vgic_cpu_nb);
- if (ret) {
- kvm_err("Cannot register vgic CPU notifier\n");
- goto out_free_irq;
- }
-
- ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
- if (ret) {
- kvm_err("Cannot obtain VCTRL resource\n");
- goto out_free_irq;
- }
-
- vgic_vctrl_base = of_iomap(vgic_node, 2);
- if (!vgic_vctrl_base) {
- kvm_err("Cannot ioremap VCTRL\n");
- ret = -ENOMEM;
- goto out_free_irq;
- }
-
- vgic_nr_lr = readl_relaxed(vgic_vctrl_base + GICH_VTR);
- vgic_nr_lr = (vgic_nr_lr & 0x3f) + 1;
-
- ret = create_hyp_io_mappings(vgic_vctrl_base,
- vgic_vctrl_base + resource_size(&vctrl_res),
- vctrl_res.start);
- if (ret) {
- kvm_err("Cannot map VCTRL into hyp\n");
- goto out_unmap;
- }
-
- kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
- vctrl_res.start, vgic_maint_irq);
- on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
- if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
- kvm_err("Cannot obtain VCPU resource\n");
- ret = -ENXIO;
- goto out_unmap;
- }
- vgic_vcpu_base = vcpu_res.start;
-
- goto out;
-
-out_unmap:
- iounmap(vgic_vctrl_base);
-out_free_irq:
- free_percpu_irq(vgic_maint_irq, kvm_get_running_vcpus());
-out:
- of_node_put(vgic_node);
- return ret;
-}
-
-int kvm_vgic_init(struct kvm *kvm)
-{
- int ret = 0, i;
-
- mutex_lock(&kvm->lock);
-
- if (vgic_initialized(kvm))
- goto out;
-
- if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
- IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) {
- kvm_err("Need to set vgic cpu and dist addresses first\n");
- ret = -ENXIO;
- goto out;
- }
-
- ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
- vgic_vcpu_base, KVM_VGIC_V2_CPU_SIZE);
- if (ret) {
- kvm_err("Unable to remap VGIC CPU to VCPU\n");
- goto out;
- }
-
- for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
- vgic_set_target_reg(kvm, 0, i);
-
- kvm_timer_init(kvm);
- kvm->arch.vgic.ready = true;
-out:
- mutex_unlock(&kvm->lock);
- return ret;
-}
-
-int kvm_vgic_create(struct kvm *kvm)
-{
- int ret = 0;
-
- mutex_lock(&kvm->lock);
-
- if (atomic_read(&kvm->online_vcpus) || kvm->arch.vgic.vctrl_base) {
- ret = -EEXIST;
- goto out;
- }
-
- spin_lock_init(&kvm->arch.vgic.lock);
- kvm->arch.vgic.vctrl_base = vgic_vctrl_base;
- kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
- kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
-
-out:
- mutex_unlock(&kvm->lock);
- return ret;
-}
-
-static bool vgic_ioaddr_overlap(struct kvm *kvm)
-{
- phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
- phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
-
- if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu))
- return 0;
- if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) ||
- (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist))
- return -EBUSY;
- return 0;
-}
-
-static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
- phys_addr_t addr, phys_addr_t size)
-{
- int ret;
-
- if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
- return -EEXIST;
- if (addr + size < addr)
- return -EINVAL;
-
- ret = vgic_ioaddr_overlap(kvm);
- if (ret)
- return ret;
- *ioaddr = addr;
- return ret;
-}
-
-int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
-{
- int r = 0;
- struct vgic_dist *vgic = &kvm->arch.vgic;
-
- if (addr & ~KVM_PHYS_MASK)
- return -E2BIG;
-
- if (addr & (SZ_4K - 1))
- return -EINVAL;
-
- mutex_lock(&kvm->lock);
- switch (type) {
- case KVM_VGIC_V2_ADDR_TYPE_DIST:
- r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base,
- addr, KVM_VGIC_V2_DIST_SIZE);
- break;
- case KVM_VGIC_V2_ADDR_TYPE_CPU:
- r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base,
- addr, KVM_VGIC_V2_CPU_SIZE);
- break;
- default:
- r = -ENODEV;
- }
-
- mutex_unlock(&kvm->lock);
- return r;
-}
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib/copy_template.S
index 805e3f8..3bc8eb8 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib/copy_template.S
@@ -197,24 +197,24 @@
12: PLD( pld [r1, #124] )
13: ldr4w r1, r4, r5, r6, r7, abort=19f
- mov r3, lr, pull #\pull
+ mov r3, lr, lspull #\pull
subs r2, r2, #32
ldr4w r1, r8, r9, ip, lr, abort=19f
- orr r3, r3, r4, push #\push
- mov r4, r4, pull #\pull
- orr r4, r4, r5, push #\push
- mov r5, r5, pull #\pull
- orr r5, r5, r6, push #\push
- mov r6, r6, pull #\pull
- orr r6, r6, r7, push #\push
- mov r7, r7, pull #\pull
- orr r7, r7, r8, push #\push
- mov r8, r8, pull #\pull
- orr r8, r8, r9, push #\push
- mov r9, r9, pull #\pull
- orr r9, r9, ip, push #\push
- mov ip, ip, pull #\pull
- orr ip, ip, lr, push #\push
+ orr r3, r3, r4, lspush #\push
+ mov r4, r4, lspull #\pull
+ orr r4, r4, r5, lspush #\push
+ mov r5, r5, lspull #\pull
+ orr r5, r5, r6, lspush #\push
+ mov r6, r6, lspull #\pull
+ orr r6, r6, r7, lspush #\push
+ mov r7, r7, lspull #\pull
+ orr r7, r7, r8, lspush #\push
+ mov r8, r8, lspull #\pull
+ orr r8, r8, r9, lspush #\push
+ mov r9, r9, lspull #\pull
+ orr r9, r9, ip, lspush #\push
+ mov ip, ip, lspull #\pull
+ orr ip, ip, lr, lspush #\push
str8w r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
bge 12b
PLD( cmn r2, #96 )
@@ -225,10 +225,10 @@
14: ands ip, r2, #28
beq 16f
-15: mov r3, lr, pull #\pull
+15: mov r3, lr, lspull #\pull
ldr1w r1, lr, abort=21f
subs ip, ip, #4
- orr r3, r3, lr, push #\push
+ orr r3, r3, lr, lspush #\push
str1w r0, r3, abort=21f
bgt 15b
CALGN( cmp r2, #0 )
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index d620a5f..d6e742d 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -141,7 +141,7 @@
tst len, #2
mov r5, r4, get_byte_0
beq .Lexit
- adcs sum, sum, r4, push #16
+ adcs sum, sum, r4, lspush #16
strb r5, [dst], #1
mov r5, r4, get_byte_1
strb r5, [dst], #1
@@ -171,23 +171,23 @@
cmp ip, #2
beq .Lsrc2_aligned
bhi .Lsrc3_aligned
- mov r4, r5, pull #8 @ C = 0
+ mov r4, r5, lspull #8 @ C = 0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- orr r4, r4, r5, push #24
- mov r5, r5, pull #8
- orr r5, r5, r6, push #24
- mov r6, r6, pull #8
- orr r6, r6, r7, push #24
- mov r7, r7, pull #8
- orr r7, r7, r8, push #24
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
+ mov r7, r7, lspull #8
+ orr r7, r7, r8, lspush #24
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #8
+ mov r4, r8, lspull #8
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -196,50 +196,50 @@
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #24
- mov r5, r5, pull #8
- orr r5, r5, r6, push #24
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #8
+ mov r4, r6, lspull #8
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #24
+ orr r4, r4, r5, lspush #24
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #8
+ mov r4, r5, lspull #8
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
tst len, #2
beq .Lexit
- adcs sum, sum, r4, push #16
+ adcs sum, sum, r4, lspush #16
strb r5, [dst], #1
mov r5, r4, get_byte_1
strb r5, [dst], #1
mov r5, r4, get_byte_2
b .Lexit
-.Lsrc2_aligned: mov r4, r5, pull #16
+.Lsrc2_aligned: mov r4, r5, lspull #16
adds sum, sum, #0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- orr r4, r4, r5, push #16
- mov r5, r5, pull #16
- orr r5, r5, r6, push #16
- mov r6, r6, pull #16
- orr r6, r6, r7, push #16
- mov r7, r7, pull #16
- orr r7, r7, r8, push #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
+ mov r7, r7, lspull #16
+ orr r7, r7, r8, lspush #16
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #16
+ mov r4, r8, lspull #16
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -248,20 +248,20 @@
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #16
- mov r5, r5, pull #16
- orr r5, r5, r6, push #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #16
+ mov r4, r6, lspull #16
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #16
+ orr r4, r4, r5, lspush #16
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #16
+ mov r4, r5, lspull #16
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
@@ -276,24 +276,24 @@
load1b r5
b .Lexit
-.Lsrc3_aligned: mov r4, r5, pull #24
+.Lsrc3_aligned: mov r4, r5, lspull #24
adds sum, sum, #0
bics ip, len, #15
beq 2f
1: load4l r5, r6, r7, r8
- orr r4, r4, r5, push #8
- mov r5, r5, pull #24
- orr r5, r5, r6, push #8
- mov r6, r6, pull #24
- orr r6, r6, r7, push #8
- mov r7, r7, pull #24
- orr r7, r7, r8, push #8
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
+ mov r7, r7, lspull #24
+ orr r7, r7, r8, lspush #8
stmia dst!, {r4, r5, r6, r7}
adcs sum, sum, r4
adcs sum, sum, r5
adcs sum, sum, r6
adcs sum, sum, r7
- mov r4, r8, pull #24
+ mov r4, r8, lspull #24
sub ip, ip, #16
teq ip, #0
bne 1b
@@ -302,20 +302,20 @@
tst ip, #8
beq 3f
load2l r5, r6
- orr r4, r4, r5, push #8
- mov r5, r5, pull #24
- orr r5, r5, r6, push #8
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
stmia dst!, {r4, r5}
adcs sum, sum, r4
adcs sum, sum, r5
- mov r4, r6, pull #24
+ mov r4, r6, lspull #24
tst ip, #4
beq 4f
3: load1l r5
- orr r4, r4, r5, push #8
+ orr r4, r4, r5, lspush #8
str r4, [dst], #4
adcs sum, sum, r4
- mov r4, r5, pull #24
+ mov r4, r5, lspull #24
4: ands len, len, #3
beq .Ldone
mov r5, r4, get_byte_0
@@ -326,7 +326,7 @@
load1l r4
mov r5, r4, get_byte_0
strb r5, [dst], #1
- adcs sum, sum, r4, push #24
+ adcs sum, sum, r4, lspush #24
mov r5, r4, get_byte_1
b .Lexit
FN_EXIT
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib/io-readsl.S
index 5fb97e7..7a74309 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib/io-readsl.S
@@ -47,25 +47,25 @@
strb ip, [r1], #1
4: subs r2, r2, #1
- mov ip, r3, pull #24
+ mov ip, r3, lspull #24
ldrne r3, [r0]
- orrne ip, ip, r3, push #8
+ orrne ip, ip, r3, lspush #8
strne ip, [r1], #4
bne 4b
b 8f
5: subs r2, r2, #1
- mov ip, r3, pull #16
+ mov ip, r3, lspull #16
ldrne r3, [r0]
- orrne ip, ip, r3, push #16
+ orrne ip, ip, r3, lspush #16
strne ip, [r1], #4
bne 5b
b 7f
6: subs r2, r2, #1
- mov ip, r3, pull #8
+ mov ip, r3, lspull #8
ldrne r3, [r0]
- orrne ip, ip, r3, push #24
+ orrne ip, ip, r3, lspush #24
strne ip, [r1], #4
bne 6b
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib/io-writesl.S
index 8d3b781..d0d104a 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib/io-writesl.S
@@ -41,26 +41,26 @@
blt 5f
bgt 6f
-4: mov ip, r3, pull #16
+4: mov ip, r3, lspull #16
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #16
+ orr ip, ip, r3, lspush #16
str ip, [r0]
bne 4b
mov pc, lr
-5: mov ip, r3, pull #8
+5: mov ip, r3, lspull #8
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #24
+ orr ip, ip, r3, lspush #24
str ip, [r0]
bne 5b
mov pc, lr
-6: mov ip, r3, pull #24
+6: mov ip, r3, lspull #24
ldr r3, [r1], #4
subs r2, r2, #1
- orr ip, ip, r3, push #8
+ orr ip, ip, r3, lspush #8
str ip, [r0]
bne 6b
mov pc, lr
diff --git a/arch/arm/lib/memmove.S b/arch/arm/lib/memmove.S
index 938fc14..d1fc0c0 100644
--- a/arch/arm/lib/memmove.S
+++ b/arch/arm/lib/memmove.S
@@ -147,24 +147,24 @@
12: PLD( pld [r1, #-128] )
13: ldmdb r1!, {r7, r8, r9, ip}
- mov lr, r3, push #\push
+ mov lr, r3, lspush #\push
subs r2, r2, #32
ldmdb r1!, {r3, r4, r5, r6}
- orr lr, lr, ip, pull #\pull
- mov ip, ip, push #\push
- orr ip, ip, r9, pull #\pull
- mov r9, r9, push #\push
- orr r9, r9, r8, pull #\pull
- mov r8, r8, push #\push
- orr r8, r8, r7, pull #\pull
- mov r7, r7, push #\push
- orr r7, r7, r6, pull #\pull
- mov r6, r6, push #\push
- orr r6, r6, r5, pull #\pull
- mov r5, r5, push #\push
- orr r5, r5, r4, pull #\pull
- mov r4, r4, push #\push
- orr r4, r4, r3, pull #\pull
+ orr lr, lr, ip, lspull #\pull
+ mov ip, ip, lspush #\push
+ orr ip, ip, r9, lspull #\pull
+ mov r9, r9, lspush #\push
+ orr r9, r9, r8, lspull #\pull
+ mov r8, r8, lspush #\push
+ orr r8, r8, r7, lspull #\pull
+ mov r7, r7, lspush #\push
+ orr r7, r7, r6, lspull #\pull
+ mov r6, r6, lspush #\push
+ orr r6, r6, r5, lspull #\pull
+ mov r5, r5, lspush #\push
+ orr r5, r5, r4, lspull #\pull
+ mov r4, r4, lspush #\push
+ orr r4, r4, r3, lspull #\pull
stmdb r0!, {r4 - r9, ip, lr}
bge 12b
PLD( cmn r2, #96 )
@@ -175,10 +175,10 @@
14: ands ip, r2, #28
beq 16f
-15: mov lr, r3, push #\push
+15: mov lr, r3, lspush #\push
ldr r3, [r1, #-4]!
subs ip, ip, #4
- orr lr, lr, r3, pull #\pull
+ orr lr, lr, r3, lspull #\pull
str lr, [r0, #-4]!
bgt 15b
CALGN( cmp r2, #0 )
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index 5c908b1..e505209 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -117,9 +117,9 @@
.Lc2u_1fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_1nowords
- mov r3, r7, pull #8
+ mov r3, r7, lspull #8
ldr r7, [r1], #4
- orr r3, r3, r7, push #24
+ orr r3, r3, r7, lspush #24
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -131,30 +131,30 @@
subs ip, ip, #16
blt .Lc2u_1rem8lp
-.Lc2u_1cpy8lp: mov r3, r7, pull #8
+.Lc2u_1cpy8lp: mov r3, r7, lspull #8
ldmia r1!, {r4 - r7}
subs ip, ip, #16
- orr r3, r3, r4, push #24
- mov r4, r4, pull #8
- orr r4, r4, r5, push #24
- mov r5, r5, pull #8
- orr r5, r5, r6, push #24
- mov r6, r6, pull #8
- orr r6, r6, r7, push #24
+ orr r3, r3, r4, lspush #24
+ mov r4, r4, lspull #8
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_1cpy8lp
.Lc2u_1rem8lp: tst ip, #8
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #24
- movne r4, r4, pull #8
- orrne r4, r4, r7, push #24
+ orrne r3, r3, r4, lspush #24
+ movne r4, r4, lspull #8
+ orrne r4, r4, r7, lspush #24
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #24
+ orrne r3, r3, r7, lspush #24
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_1fupi
@@ -172,9 +172,9 @@
.Lc2u_2fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_2nowords
- mov r3, r7, pull #16
+ mov r3, r7, lspull #16
ldr r7, [r1], #4
- orr r3, r3, r7, push #16
+ orr r3, r3, r7, lspush #16
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -186,30 +186,30 @@
subs ip, ip, #16
blt .Lc2u_2rem8lp
-.Lc2u_2cpy8lp: mov r3, r7, pull #16
+.Lc2u_2cpy8lp: mov r3, r7, lspull #16
ldmia r1!, {r4 - r7}
subs ip, ip, #16
- orr r3, r3, r4, push #16
- mov r4, r4, pull #16
- orr r4, r4, r5, push #16
- mov r5, r5, pull #16
- orr r5, r5, r6, push #16
- mov r6, r6, pull #16
- orr r6, r6, r7, push #16
+ orr r3, r3, r4, lspush #16
+ mov r4, r4, lspull #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_2cpy8lp
.Lc2u_2rem8lp: tst ip, #8
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #16
- movne r4, r4, pull #16
- orrne r4, r4, r7, push #16
+ orrne r3, r3, r4, lspush #16
+ movne r4, r4, lspull #16
+ orrne r4, r4, r7, lspush #16
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #16
+ orrne r3, r3, r7, lspush #16
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_2fupi
@@ -227,9 +227,9 @@
.Lc2u_3fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lc2u_3nowords
- mov r3, r7, pull #24
+ mov r3, r7, lspull #24
ldr r7, [r1], #4
- orr r3, r3, r7, push #8
+ orr r3, r3, r7, lspush #8
USER( TUSER( str) r3, [r0], #4) @ May fault
mov ip, r0, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -241,30 +241,30 @@
subs ip, ip, #16
blt .Lc2u_3rem8lp
-.Lc2u_3cpy8lp: mov r3, r7, pull #24
+.Lc2u_3cpy8lp: mov r3, r7, lspull #24
ldmia r1!, {r4 - r7}
subs ip, ip, #16
- orr r3, r3, r4, push #8
- mov r4, r4, pull #24
- orr r4, r4, r5, push #8
- mov r5, r5, pull #24
- orr r5, r5, r6, push #8
- mov r6, r6, pull #24
- orr r6, r6, r7, push #8
+ orr r3, r3, r4, lspush #8
+ mov r4, r4, lspull #24
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
stmia r0!, {r3 - r6} @ Shouldnt fault
bpl .Lc2u_3cpy8lp
.Lc2u_3rem8lp: tst ip, #8
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldmneia r1!, {r4, r7}
- orrne r3, r3, r4, push #8
- movne r4, r4, pull #24
- orrne r4, r4, r7, push #8
+ orrne r3, r3, r4, lspush #8
+ movne r4, r4, lspull #24
+ orrne r4, r4, r7, lspush #8
stmneia r0!, {r3 - r4} @ Shouldnt fault
tst ip, #4
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldrne r7, [r1], #4
- orrne r3, r3, r7, push #8
+ orrne r3, r3, r7, lspush #8
TUSER( strne) r3, [r0], #4 @ Shouldnt fault
ands ip, ip, #3
beq .Lc2u_3fupi
@@ -382,9 +382,9 @@
.Lcfu_1fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_1nowords
- mov r3, r7, pull #8
+ mov r3, r7, lspull #8
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #24
+ orr r3, r3, r7, lspush #24
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -396,30 +396,30 @@
subs ip, ip, #16
blt .Lcfu_1rem8lp
-.Lcfu_1cpy8lp: mov r3, r7, pull #8
+.Lcfu_1cpy8lp: mov r3, r7, lspull #8
ldmia r1!, {r4 - r7} @ Shouldnt fault
subs ip, ip, #16
- orr r3, r3, r4, push #24
- mov r4, r4, pull #8
- orr r4, r4, r5, push #24
- mov r5, r5, pull #8
- orr r5, r5, r6, push #24
- mov r6, r6, pull #8
- orr r6, r6, r7, push #24
+ orr r3, r3, r4, lspush #24
+ mov r4, r4, lspull #8
+ orr r4, r4, r5, lspush #24
+ mov r5, r5, lspull #8
+ orr r5, r5, r6, lspush #24
+ mov r6, r6, lspull #8
+ orr r6, r6, r7, lspush #24
stmia r0!, {r3 - r6}
bpl .Lcfu_1cpy8lp
.Lcfu_1rem8lp: tst ip, #8
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #24
- movne r4, r4, pull #8
- orrne r4, r4, r7, push #24
+ orrne r3, r3, r4, lspush #24
+ movne r4, r4, lspull #8
+ orrne r4, r4, r7, lspush #24
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #8
+ movne r3, r7, lspull #8
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #24
+ orrne r3, r3, r7, lspush #24
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_1fupi
@@ -437,9 +437,9 @@
.Lcfu_2fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_2nowords
- mov r3, r7, pull #16
+ mov r3, r7, lspull #16
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #16
+ orr r3, r3, r7, lspush #16
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -452,30 +452,30 @@
blt .Lcfu_2rem8lp
-.Lcfu_2cpy8lp: mov r3, r7, pull #16
+.Lcfu_2cpy8lp: mov r3, r7, lspull #16
ldmia r1!, {r4 - r7} @ Shouldnt fault
subs ip, ip, #16
- orr r3, r3, r4, push #16
- mov r4, r4, pull #16
- orr r4, r4, r5, push #16
- mov r5, r5, pull #16
- orr r5, r5, r6, push #16
- mov r6, r6, pull #16
- orr r6, r6, r7, push #16
+ orr r3, r3, r4, lspush #16
+ mov r4, r4, lspull #16
+ orr r4, r4, r5, lspush #16
+ mov r5, r5, lspull #16
+ orr r5, r5, r6, lspush #16
+ mov r6, r6, lspull #16
+ orr r6, r6, r7, lspush #16
stmia r0!, {r3 - r6}
bpl .Lcfu_2cpy8lp
.Lcfu_2rem8lp: tst ip, #8
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #16
- movne r4, r4, pull #16
- orrne r4, r4, r7, push #16
+ orrne r3, r3, r4, lspush #16
+ movne r4, r4, lspull #16
+ orrne r4, r4, r7, lspush #16
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #16
+ movne r3, r7, lspull #16
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #16
+ orrne r3, r3, r7, lspush #16
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_2fupi
@@ -493,9 +493,9 @@
.Lcfu_3fupi: subs r2, r2, #4
addmi ip, r2, #4
bmi .Lcfu_3nowords
- mov r3, r7, pull #24
+ mov r3, r7, lspull #24
USER( TUSER( ldr) r7, [r1], #4) @ May fault
- orr r3, r3, r7, push #8
+ orr r3, r3, r7, lspush #8
str r3, [r0], #4
mov ip, r1, lsl #32 - PAGE_SHIFT
rsb ip, ip, #0
@@ -507,30 +507,30 @@
subs ip, ip, #16
blt .Lcfu_3rem8lp
-.Lcfu_3cpy8lp: mov r3, r7, pull #24
+.Lcfu_3cpy8lp: mov r3, r7, lspull #24
ldmia r1!, {r4 - r7} @ Shouldnt fault
- orr r3, r3, r4, push #8
- mov r4, r4, pull #24
- orr r4, r4, r5, push #8
- mov r5, r5, pull #24
- orr r5, r5, r6, push #8
- mov r6, r6, pull #24
- orr r6, r6, r7, push #8
+ orr r3, r3, r4, lspush #8
+ mov r4, r4, lspull #24
+ orr r4, r4, r5, lspush #8
+ mov r5, r5, lspull #24
+ orr r5, r5, r6, lspush #8
+ mov r6, r6, lspull #24
+ orr r6, r6, r7, lspush #8
stmia r0!, {r3 - r6}
subs ip, ip, #16
bpl .Lcfu_3cpy8lp
.Lcfu_3rem8lp: tst ip, #8
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
ldmneia r1!, {r4, r7} @ Shouldnt fault
- orrne r3, r3, r4, push #8
- movne r4, r4, pull #24
- orrne r4, r4, r7, push #8
+ orrne r3, r3, r4, lspush #8
+ movne r4, r4, lspull #24
+ orrne r4, r4, r7, lspush #8
stmneia r0!, {r3 - r4}
tst ip, #4
- movne r3, r7, pull #24
+ movne r3, r7, lspull #24
USER( TUSER( ldrne) r7, [r1], #4) @ May fault
- orrne r3, r3, r7, push #8
+ orrne r3, r3, r7, lspush #8
strne r3, [r0], #4
ands ip, ip, #3
beq .Lcfu_3fupi
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index 788562d..c336efd 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -2,7 +2,7 @@
# Makefile for the linux kernel.
#
-obj-y := irq.o gpio.o setup.o
+obj-y := irq.o gpio.o setup.o sysirq_mask.o
obj-m :=
obj-n :=
obj- :=
diff --git a/arch/arm/mach-at91/at91sam9260.c b/arch/arm/mach-at91/at91sam9260.c
index a8ce245..cdb1fb6 100644
--- a/arch/arm/mach-at91/at91sam9260.c
+++ b/arch/arm/mach-at91/at91sam9260.c
@@ -351,6 +351,8 @@
at91_extern_irq = (1 << AT91SAM9260_ID_IRQ0) | (1 << AT91SAM9260_ID_IRQ1)
| (1 << AT91SAM9260_ID_IRQ2);
+ at91_sysirq_mask_rtt(AT91SAM9260_BASE_RTT);
+
/* Register GPIO subsystem */
at91_gpio_init(at91sam9260_gpio, 3);
}
diff --git a/arch/arm/mach-at91/at91sam9261.c b/arch/arm/mach-at91/at91sam9261.c
index 25efb5a..7c9d2ea 100644
--- a/arch/arm/mach-at91/at91sam9261.c
+++ b/arch/arm/mach-at91/at91sam9261.c
@@ -293,6 +293,8 @@
at91_extern_irq = (1 << AT91SAM9261_ID_IRQ0) | (1 << AT91SAM9261_ID_IRQ1)
| (1 << AT91SAM9261_ID_IRQ2);
+ at91_sysirq_mask_rtt(AT91SAM9261_BASE_RTT);
+
/* Register GPIO subsystem */
at91_gpio_init(at91sam9261_gpio, 3);
}
diff --git a/arch/arm/mach-at91/at91sam9263.c b/arch/arm/mach-at91/at91sam9263.c
index f44ffd2..c6b2f47 100644
--- a/arch/arm/mach-at91/at91sam9263.c
+++ b/arch/arm/mach-at91/at91sam9263.c
@@ -329,6 +329,9 @@
arm_pm_restart = at91sam9_alt_restart;
at91_extern_irq = (1 << AT91SAM9263_ID_IRQ0) | (1 << AT91SAM9263_ID_IRQ1);
+ at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT0);
+ at91_sysirq_mask_rtt(AT91SAM9263_BASE_RTT1);
+
/* Register GPIO subsystem */
at91_gpio_init(at91sam9263_gpio, 5);
}
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 8b7fce0..e381fa1 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -376,6 +376,9 @@
arm_pm_restart = at91sam9g45_restart;
at91_extern_irq = (1 << AT91SAM9G45_ID_IRQ0);
+ at91_sysirq_mask_rtc(AT91SAM9G45_BASE_RTC);
+ at91_sysirq_mask_rtt(AT91SAM9G45_BASE_RTT);
+
/* Register GPIO subsystem */
at91_gpio_init(at91sam9g45_gpio, 5);
}
diff --git a/arch/arm/mach-at91/at91sam9n12.c b/arch/arm/mach-at91/at91sam9n12.c
index c7d670d..4d6001c 100644
--- a/arch/arm/mach-at91/at91sam9n12.c
+++ b/arch/arm/mach-at91/at91sam9n12.c
@@ -223,7 +223,13 @@
at91_init_sram(0, AT91SAM9N12_SRAM_BASE, AT91SAM9N12_SRAM_SIZE);
}
+static void __init at91sam9n12_initialize(void)
+{
+ at91_sysirq_mask_rtc(AT91SAM9N12_BASE_RTC);
+}
+
AT91_SOC_START(at91sam9n12)
.map_io = at91sam9n12_map_io,
.register_clocks = at91sam9n12_register_clocks,
+ .init = at91sam9n12_initialize,
AT91_SOC_END
diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c
index f77fae5..5615d28 100644
--- a/arch/arm/mach-at91/at91sam9rl.c
+++ b/arch/arm/mach-at91/at91sam9rl.c
@@ -295,6 +295,9 @@
arm_pm_restart = at91sam9_alt_restart;
at91_extern_irq = (1 << AT91SAM9RL_ID_IRQ0);
+ at91_sysirq_mask_rtc(AT91SAM9RL_BASE_RTC);
+ at91_sysirq_mask_rtt(AT91SAM9RL_BASE_RTT);
+
/* Register GPIO subsystem */
at91_gpio_init(at91sam9rl_gpio, 4);
}
diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c
index e631fec..7b4f8483 100644
--- a/arch/arm/mach-at91/at91sam9x5.c
+++ b/arch/arm/mach-at91/at91sam9x5.c
@@ -318,6 +318,11 @@
at91_init_sram(0, AT91SAM9X5_SRAM_BASE, AT91SAM9X5_SRAM_SIZE);
}
+static void __init at91sam9x5_initialize(void)
+{
+ at91_sysirq_mask_rtc(AT91SAM9X5_BASE_RTC);
+}
+
/* --------------------------------------------------------------------
* Interrupt initialization
* -------------------------------------------------------------------- */
@@ -325,4 +330,5 @@
AT91_SOC_START(at91sam9x5)
.map_io = at91sam9x5_map_io,
.register_clocks = at91sam9x5_register_clocks,
+ .init = at91sam9x5_initialize,
AT91_SOC_END
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index da84188..64f9f10 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -947,6 +947,7 @@
}
at91_pmc_write(AT91_PMC_SCDR, scdr);
+ at91_pmc_write(AT91_PMC_PCDR, pcdr);
if (cpu_is_sama5d3())
at91_pmc_write(AT91_PMC_PCDR1, pcdr1);
diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
index 78ab065..d949ab4 100644
--- a/arch/arm/mach-at91/generic.h
+++ b/arch/arm/mach-at91/generic.h
@@ -33,6 +33,8 @@
struct device_node *parent);
extern int __init at91_aic5_of_init(struct device_node *node,
struct device_node *parent);
+extern void __init at91_sysirq_mask_rtc(u32 rtc_base);
+extern void __init at91_sysirq_mask_rtt(u32 rtt_base);
/* Timer */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9n12.h b/arch/arm/mach-at91/include/mach/at91sam9n12.h
index d374b87..0151bcf 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9n12.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9n12.h
@@ -49,6 +49,11 @@
#define AT91SAM9N12_BASE_USART3 0xf8028000
/*
+ * System Peripherals
+ */
+#define AT91SAM9N12_BASE_RTC 0xfffffeb0
+
+/*
* Internal Memory.
*/
#define AT91SAM9N12_SRAM_BASE 0x00300000 /* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/include/mach/at91sam9x5.h b/arch/arm/mach-at91/include/mach/at91sam9x5.h
index c75ee19..2fc76c4 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9x5.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9x5.h
@@ -55,6 +55,11 @@
#define AT91SAM9X5_BASE_USART2 0xf8024000
/*
+ * System Peripherals
+ */
+#define AT91SAM9X5_BASE_RTC 0xfffffeb0
+
+/*
* Internal Memory.
*/
#define AT91SAM9X5_SRAM_BASE 0x00300000 /* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/include/mach/sama5d3.h b/arch/arm/mach-at91/include/mach/sama5d3.h
index 6dc81ee..3abbc42 100644
--- a/arch/arm/mach-at91/include/mach/sama5d3.h
+++ b/arch/arm/mach-at91/include/mach/sama5d3.h
@@ -65,6 +65,11 @@
#define SAMA5D3_ID_IRQ0 47 /* Advanced Interrupt Controller (IRQ0) */
/*
+ * System Peripherals
+ */
+#define SAMA5D3_BASE_RTC 0xfffffeb0
+
+/*
* Internal Memory
*/
#define SAMA5D3_SRAM_BASE 0x00300000 /* Internal SRAM base address */
diff --git a/arch/arm/mach-at91/pm.h b/arch/arm/mach-at91/pm.h
index 2f5908f..d8af075 100644
--- a/arch/arm/mach-at91/pm.h
+++ b/arch/arm/mach-at91/pm.h
@@ -37,7 +37,7 @@
" mcr p15, 0, %0, c7, c0, 4\n\t"
" str %5, [%1, %2]"
:
- : "r" (0), "r" (AT91_BASE_SYS), "r" (AT91RM9200_SDRAMC_LPR),
+ : "r" (0), "r" (at91_ramc_base[0]), "r" (AT91RM9200_SDRAMC_LPR),
"r" (1), "r" (AT91RM9200_SDRAMC_SRR),
"r" (lpr));
}
diff --git a/arch/arm/mach-at91/sam9_smc.c b/arch/arm/mach-at91/sam9_smc.c
index 99a0a1d2..b26156b 100644
--- a/arch/arm/mach-at91/sam9_smc.c
+++ b/arch/arm/mach-at91/sam9_smc.c
@@ -101,7 +101,7 @@
/* Pulse register */
val = __raw_readl(base + AT91_SMC_PULSE);
- config->nwe_setup = val & AT91_SMC_NWEPULSE;
+ config->nwe_pulse = val & AT91_SMC_NWEPULSE;
config->ncs_write_pulse = (val & AT91_SMC_NCS_WRPULSE) >> 8;
config->nrd_pulse = (val & AT91_SMC_NRDPULSE) >> 16;
config->ncs_read_pulse = (val & AT91_SMC_NCS_RDPULSE) >> 24;
diff --git a/arch/arm/mach-at91/sama5d3.c b/arch/arm/mach-at91/sama5d3.c
index 4012797..a28873f 100644
--- a/arch/arm/mach-at91/sama5d3.c
+++ b/arch/arm/mach-at91/sama5d3.c
@@ -95,19 +95,19 @@
.name = "twi0_clk",
.pid = SAMA5D3_ID_TWI0,
.type = CLK_TYPE_PERIPHERAL,
- .div = AT91_PMC_PCR_DIV2,
+ .div = AT91_PMC_PCR_DIV8,
};
static struct clk twi1_clk = {
.name = "twi1_clk",
.pid = SAMA5D3_ID_TWI1,
.type = CLK_TYPE_PERIPHERAL,
- .div = AT91_PMC_PCR_DIV2,
+ .div = AT91_PMC_PCR_DIV8,
};
static struct clk twi2_clk = {
.name = "twi2_clk",
.pid = SAMA5D3_ID_TWI2,
.type = CLK_TYPE_PERIPHERAL,
- .div = AT91_PMC_PCR_DIV2,
+ .div = AT91_PMC_PCR_DIV8,
};
static struct clk mmc0_clk = {
.name = "mci0_clk",
@@ -371,7 +371,13 @@
at91_init_sram(0, SAMA5D3_SRAM_BASE, SAMA5D3_SRAM_SIZE);
}
+static void __init sama5d3_initialize(void)
+{
+ at91_sysirq_mask_rtc(SAMA5D3_BASE_RTC);
+}
+
AT91_SOC_START(sama5d3)
.map_io = sama5d3_map_io,
.register_clocks = sama5d3_register_clocks,
+ .init = sama5d3_initialize,
AT91_SOC_END
diff --git a/arch/arm/mach-at91/sysirq_mask.c b/arch/arm/mach-at91/sysirq_mask.c
new file mode 100644
index 0000000..f8bc351
--- /dev/null
+++ b/arch/arm/mach-at91/sysirq_mask.c
@@ -0,0 +1,75 @@
+/*
+ * sysirq_mask.c - System-interrupt masking
+ *
+ * Copyright (C) 2013 Johan Hovold <jhovold@gmail.com>
+ *
+ * Functions to disable system interrupts from backup-powered peripherals.
+ *
+ * The RTC and RTT-peripherals are generally powered by backup power (VDDBU)
+ * and are not reset on wake-up, user, watchdog or software reset. This means
+ * that their interrupts may be enabled during early boot (e.g. after a user
+ * reset).
+ *
+ * As the RTC and RTT share the system-interrupt line with the PIT, an
+ * interrupt occurring before a handler has been installed would lead to the
+ * system interrupt being disabled and prevent the system from booting.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <mach/at91_rtt.h>
+
+#include "generic.h"
+
+#define AT91_RTC_IDR 0x24 /* Interrupt Disable Register */
+#define AT91_RTC_IMR 0x28 /* Interrupt Mask Register */
+#define AT91_RTC_IRQ_MASK 0x1f /* Available IRQs mask */
+
+void __init at91_sysirq_mask_rtc(u32 rtc_base)
+{
+ void __iomem *base;
+
+ base = ioremap(rtc_base, 64);
+ if (!base)
+ return;
+
+ /*
+ * sam9x5 SoCs have the following errata:
+ * "RTC: Interrupt Mask Register cannot be used
+ * Interrupt Mask Register read always returns 0."
+ *
+ * Hence we're not relying on IMR values to disable
+ * interrupts.
+ */
+ writel_relaxed(AT91_RTC_IRQ_MASK, base + AT91_RTC_IDR);
+ (void)readl_relaxed(base + AT91_RTC_IMR); /* flush */
+
+ iounmap(base);
+}
+
+void __init at91_sysirq_mask_rtt(u32 rtt_base)
+{
+ void __iomem *base;
+ void __iomem *reg;
+ u32 mode;
+
+ base = ioremap(rtt_base, 16);
+ if (!base)
+ return;
+
+ reg = base + AT91_RTT_MR;
+
+ mode = readl_relaxed(reg);
+ if (mode & (AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN)) {
+ pr_info("AT91: Disabling rtt irq\n");
+ mode &= ~(AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN);
+ writel_relaxed(mode, reg);
+ (void)readl_relaxed(reg); /* flush */
+ }
+
+ iounmap(base);
+}
diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c
index dff4ddc..139e42d 100644
--- a/arch/arm/mach-davinci/board-dm355-leopard.c
+++ b/arch/arm/mach-davinci/board-dm355-leopard.c
@@ -75,6 +75,7 @@
.parts = davinci_nand_partitions,
.nr_parts = ARRAY_SIZE(davinci_nand_partitions),
.ecc_mode = NAND_ECC_HW_SYNDROME,
+ .ecc_bits = 4,
.bbt_options = NAND_BBT_USE_FLASH,
};
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index a33686a..fa4bfaf 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -153,6 +153,7 @@
.parts = davinci_evm_nandflash_partition,
.nr_parts = ARRAY_SIZE(davinci_evm_nandflash_partition),
.ecc_mode = NAND_ECC_HW,
+ .ecc_bits = 1,
.bbt_options = NAND_BBT_USE_FLASH,
.timing = &davinci_evm_nandflash_timing,
};
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index fbb8e5a..0c005e8 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -90,6 +90,7 @@
.parts = davinci_nand_partitions,
.nr_parts = ARRAY_SIZE(davinci_nand_partitions),
.ecc_mode = NAND_ECC_HW,
+ .ecc_bits = 1,
.options = 0,
};
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index 2bc112a..808233b 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -88,6 +88,7 @@
.parts = davinci_ntosd2_nandflash_partition,
.nr_parts = ARRAY_SIZE(davinci_ntosd2_nandflash_partition),
.ecc_mode = NAND_ECC_HW,
+ .ecc_bits = 1,
.bbt_options = NAND_BBT_USE_FLASH,
};
diff --git a/arch/arm/mach-ebsa110/core.c b/arch/arm/mach-ebsa110/core.c
index b13cc74..8a53f34 100644
--- a/arch/arm/mach-ebsa110/core.c
+++ b/arch/arm/mach-ebsa110/core.c
@@ -116,7 +116,7 @@
iotable_init(ebsa110_io_desc, ARRAY_SIZE(ebsa110_io_desc));
}
-static void __iomem *ebsa110_ioremap_caller(unsigned long cookie, size_t size,
+static void __iomem *ebsa110_ioremap_caller(phys_addr_t cookie, size_t size,
unsigned int flags, void *caller)
{
return (void __iomem *)cookie;
diff --git a/arch/arm/mach-exynos/mach-exynos5-dt.c b/arch/arm/mach-exynos/mach-exynos5-dt.c
index 753b94f..d88234e 100644
--- a/arch/arm/mach-exynos/mach-exynos5-dt.c
+++ b/arch/arm/mach-exynos/mach-exynos5-dt.c
@@ -14,6 +14,7 @@
#include <linux/memblock.h>
#include <linux/io.h>
#include <linux/clocksource.h>
+#include <linux/dma-mapping.h>
#include <asm/mach/arch.h>
#include <mach/regs-pmu.h>
@@ -23,11 +24,31 @@
#include "common.h"
+static u64 dma_mask64 = DMA_BIT_MASK(64);
+
static void __init exynos5_dt_map_io(void)
{
exynos_init_io(NULL, 0);
}
+static int exynos5250_platform_notifier(struct notifier_block *nb,
+ unsigned long event, void *__dev)
+{
+ struct device *dev = __dev;
+
+ if (event != BUS_NOTIFY_ADD_DEVICE)
+ return NOTIFY_DONE;
+
+ dev->dma_mask = &dma_mask64;
+ dev->coherent_dma_mask = DMA_BIT_MASK(64);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block exynos5250_platform_nb = {
+ .notifier_call = exynos5250_platform_notifier,
+};
+
static void __init exynos5_dt_machine_init(void)
{
struct device_node *i2c_np;
@@ -52,6 +73,11 @@
}
}
+ if (config_enabled(CONFIG_ARM_LPAE) &&
+ of_machine_is_compatible("samsung,exynos5250"))
+ bus_register_notifier(&platform_bus_type,
+ &exynos5250_platform_nb);
+
of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
}
diff --git a/arch/arm/mach-footbridge/common.c b/arch/arm/mach-footbridge/common.c
index a42b369..95d0b6e 100644
--- a/arch/arm/mach-footbridge/common.c
+++ b/arch/arm/mach-footbridge/common.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/io.h>
#include <linux/spinlock.h>
+#include <video/vga.h>
#include <asm/pgtable.h>
#include <asm/page.h>
@@ -196,6 +197,8 @@
iotable_init(ebsa285_host_io_desc, ARRAY_SIZE(ebsa285_host_io_desc));
pci_map_io_early(__phys_to_pfn(DC21285_PCI_IO));
}
+
+ vga_base = PCIMEM_BASE;
}
void footbridge_restart(char mode, const char *cmd)
diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 9ee78f7..782f6c7 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -96,11 +96,12 @@
void __init footbridge_timer_init(void)
{
struct clock_event_device *ce = &ckevt_dc21285;
+ unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16);
- clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16);
+ clocksource_register_hz(&cksrc_dc21285, rate);
setup_irq(ce->irq, &footbridge_timer_irq);
ce->cpumask = cpumask_of(smp_processor_id());
- clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff);
+ clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
}
diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c
index a7cd2cf..7c2fdae 100644
--- a/arch/arm/mach-footbridge/dc21285.c
+++ b/arch/arm/mach-footbridge/dc21285.c
@@ -18,7 +18,6 @@
#include <linux/irq.h>
#include <linux/io.h>
#include <linux/spinlock.h>
-#include <video/vga.h>
#include <asm/irq.h>
#include <asm/mach/pci.h>
@@ -276,8 +275,6 @@
sys->mem_offset = DC21285_PCI_MEM;
- pci_ioremap_io(0, DC21285_PCI_IO);
-
pci_add_resource_offset(&sys->resources, &res[0], sys->mem_offset);
pci_add_resource_offset(&sys->resources, &res[1], sys->mem_offset);
@@ -293,7 +290,6 @@
int cfn_mode;
pcibios_min_mem = 0x81000000;
- vga_base = PCIMEM_BASE;
mem_size = (unsigned int)high_memory - PAGE_OFFSET;
for (mem_mask = 0x00100000; mem_mask < 0x10000000; mem_mask <<= 1)
diff --git a/arch/arm/mach-footbridge/ebsa285.c b/arch/arm/mach-footbridge/ebsa285.c
index b082435..1a7235f 100644
--- a/arch/arm/mach-footbridge/ebsa285.c
+++ b/arch/arm/mach-footbridge/ebsa285.c
@@ -30,21 +30,24 @@
const char *name;
const char *trigger;
} ebsa285_leds[] = {
- { "ebsa285:amber", "heartbeat", },
- { "ebsa285:green", "cpu0", },
+ { "ebsa285:amber", "cpu0", },
+ { "ebsa285:green", "heartbeat", },
{ "ebsa285:red",},
};
+static unsigned char hw_led_state;
+
static void ebsa285_led_set(struct led_classdev *cdev,
enum led_brightness b)
{
struct ebsa285_led *led = container_of(cdev,
struct ebsa285_led, cdev);
- if (b != LED_OFF)
- *XBUS_LEDS |= led->mask;
+ if (b == LED_OFF)
+ hw_led_state |= led->mask;
else
- *XBUS_LEDS &= ~led->mask;
+ hw_led_state &= ~led->mask;
+ *XBUS_LEDS = hw_led_state;
}
static enum led_brightness ebsa285_led_get(struct led_classdev *cdev)
@@ -52,18 +55,19 @@
struct ebsa285_led *led = container_of(cdev,
struct ebsa285_led, cdev);
- return (*XBUS_LEDS & led->mask) ? LED_FULL : LED_OFF;
+ return hw_led_state & led->mask ? LED_OFF : LED_FULL;
}
static int __init ebsa285_leds_init(void)
{
int i;
- if (machine_is_ebsa285())
+ if (!machine_is_ebsa285())
return -ENODEV;
- /* 3 LEDS All ON */
- *XBUS_LEDS |= XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+ /* 3 LEDS all off */
+ hw_led_state = XBUS_LED_AMBER | XBUS_LED_GREEN | XBUS_LED_RED;
+ *XBUS_LEDS = hw_led_state;
for (i = 0; i < ARRAY_SIZE(ebsa285_leds); i++) {
struct ebsa285_led *led;
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index cd9fcb1..b8466fb 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -2,6 +2,7 @@
bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7
select ARCH_HAS_CPUFREQ
select ARCH_HAS_OPP
+ select ARCH_SUPPORTS_BIG_ENDIAN
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARM_AMBA
select ARM_GIC
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index e7df2dd..c37d31e 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/irqchip.h>
#include <linux/irqdomain.h>
+#include <linux/pl320-ipc.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
@@ -65,13 +66,12 @@
HB_JUMP_TABLE_PHYS(cpu) + 15);
}
-#ifdef CONFIG_CACHE_L2X0
static void highbank_l2x0_disable(void)
{
+ outer_flush_all();
/* Disable PL310 L2 Cache controller */
highbank_smc1(0x102, 0x0);
}
-#endif
static void __init highbank_init_irq(void)
{
@@ -80,12 +80,13 @@
if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9"))
highbank_scu_map_io();
-#ifdef CONFIG_CACHE_L2X0
/* Enable PL310 L2 Cache controller */
- highbank_smc1(0x102, 0x1);
- l2x0_of_init(0, ~0UL);
- outer_cache.disable = highbank_l2x0_disable;
-#endif
+ if (IS_ENABLED(CONFIG_CACHE_L2X0) &&
+ of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) {
+ highbank_smc1(0x102, 0x1);
+ l2x0_of_init(0, ~0UL);
+ outer_cache.disable = highbank_l2x0_disable;
+ }
}
static void __init highbank_timer_init(void)
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 4e3148c..2acaded 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -301,8 +301,8 @@
post_div_table[1].div = 1;
post_div_table[2].div = 1;
video_div_table[1].div = 1;
- video_div_table[2].div = 1;
- };
+ video_div_table[3].div = 1;
+ }
/* type name parent_name base div_mask */
clk[pll1_sys] = imx_clk_pllv3(IMX_PLLV3_SYS, "pll1_sys", "osc", base, 0x7f);
@@ -424,7 +424,7 @@
clk[asrc_podf] = imx_clk_divider("asrc_podf", "asrc_pred", base + 0x30, 9, 3);
clk[spdif_pred] = imx_clk_divider("spdif_pred", "spdif_sel", base + 0x30, 25, 3);
clk[spdif_podf] = imx_clk_divider("spdif_podf", "spdif_pred", base + 0x30, 22, 3);
- clk[can_root] = imx_clk_divider("can_root", "pll3_usb_otg", base + 0x20, 2, 6);
+ clk[can_root] = imx_clk_divider("can_root", "pll3_60m", base + 0x20, 2, 6);
clk[ecspi_root] = imx_clk_divider("ecspi_root", "pll3_60m", base + 0x38, 19, 6);
clk[gpu2d_core_podf] = imx_clk_divider("gpu2d_core_podf", "gpu2d_core_sel", base + 0x18, 23, 3);
clk[gpu3d_core_podf] = imx_clk_divider("gpu3d_core_podf", "gpu3d_core_sel", base + 0x18, 26, 3);
diff --git a/arch/arm/mach-imx/devices/platform-ipu-core.c b/arch/arm/mach-imx/devices/platform-ipu-core.c
index fc4dd7c..6bd7c3f 100644
--- a/arch/arm/mach-imx/devices/platform-ipu-core.c
+++ b/arch/arm/mach-imx/devices/platform-ipu-core.c
@@ -77,7 +77,7 @@
pdev = platform_device_alloc("mx3-camera", 0);
if (!pdev)
- goto err;
+ return ERR_PTR(-ENOMEM);
pdev->dev.dma_mask = kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL);
if (!pdev->dev.dma_mask)
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index e0e69a6..eed32ca 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -65,7 +65,7 @@
: "=r" (reg));
}
-static void __iomem *imx3_ioremap_caller(unsigned long phys_addr, size_t size,
+static void __iomem *imx3_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 8c60fcb..2f4c924 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -199,7 +199,8 @@
static void cp_clcd_enable(struct clcd_fb *fb)
{
struct fb_var_screeninfo *var = &fb->fb.var;
- u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2;
+ u32 val = CM_CTRL_STATIC1 | CM_CTRL_STATIC2
+ | CM_CTRL_LCDEN0 | CM_CTRL_LCDEN1;
if (var->bits_per_pixel <= 8 ||
(var->bits_per_pixel == 16 && var->green.length == 5))
diff --git a/arch/arm/mach-iop13xx/io.c b/arch/arm/mach-iop13xx/io.c
index 183dc8b..faaf7d4 100644
--- a/arch/arm/mach-iop13xx/io.c
+++ b/arch/arm/mach-iop13xx/io.c
@@ -23,7 +23,7 @@
#include "pci.h"
-static void __iomem *__iop13xx_ioremap_caller(unsigned long cookie,
+static void __iomem *__iop13xx_ioremap_caller(phys_addr_t cookie,
size_t size, unsigned int mtype, void *caller)
{
void __iomem * retval;
diff --git a/arch/arm/mach-ixp4xx/Kconfig b/arch/arm/mach-ixp4xx/Kconfig
index 73a2d90..72de05f 100644
--- a/arch/arm/mach-ixp4xx/Kconfig
+++ b/arch/arm/mach-ixp4xx/Kconfig
@@ -1,9 +1,5 @@
if ARCH_IXP4XX
-config ARCH_SUPPORTS_BIG_ENDIAN
- bool
- default y
-
menu "Intel IXP4xx Implementation Options"
comment "IXP4xx Platforms"
diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c
index 6600cff..d7223b3 100644
--- a/arch/arm/mach-ixp4xx/common.c
+++ b/arch/arm/mach-ixp4xx/common.c
@@ -559,7 +559,7 @@
* fallback to the default.
*/
-static void __iomem *ixp4xx_ioremap_caller(unsigned long addr, size_t size,
+static void __iomem *ixp4xx_ioremap_caller(phys_addr_t addr, size_t size,
unsigned int mtype, void *caller)
{
if (!is_pci_memory(addr))
diff --git a/arch/arm/mach-msm/common.h b/arch/arm/mach-msm/common.h
index ce8215a..421cf77 100644
--- a/arch/arm/mach-msm/common.h
+++ b/arch/arm/mach-msm/common.h
@@ -23,7 +23,7 @@
extern void msm_map_msm8960_io(void);
extern void msm_map_qsd8x50_io(void);
-extern void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+extern void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller);
extern struct smp_operations msm_smp_ops;
diff --git a/arch/arm/mach-msm/io.c b/arch/arm/mach-msm/io.c
index 123ef9c..fd65b6d 100644
--- a/arch/arm/mach-msm/io.c
+++ b/arch/arm/mach-msm/io.c
@@ -172,7 +172,7 @@
}
#endif /* CONFIG_ARCH_MSM7X30 */
-void __iomem *__msm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__msm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
if (mtype == MT_DEVICE) {
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 80a8bca..317cdb8 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -1,5 +1,6 @@
config ARCH_MVEBU
bool "Marvell SOCs with Device Tree support" if ARCH_MULTI_V7
+ select ARCH_SUPPORTS_BIG_ENDIAN
select CLKSRC_MMIO
select COMMON_CLK
select GENERIC_CLOCKEVENTS
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 8278960..3ee701f 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -141,6 +141,29 @@
{
struct device_node *np;
+ /*
+ * The coherency fabric is needed:
+ * - For coherency between processors on Armada XP, so only
+ * when SMP is enabled.
+ * - For coherency between the processor and I/O devices, but
+ * this coherency requires many pre-requisites (write
+ * allocate cache policy, shareable pages, SMP bit set) that
+ * are only meant in SMP situations.
+ *
+ * Note that this means that on Armada 370, there is currently
+ * no way to use hardware I/O coherency, because even when
+ * CONFIG_SMP is enabled, is_smp() returns false due to the
+ * Armada 370 being a single-core processor. To lift this
+ * limitation, we would have to find a way to make the cache
+ * policy set to write-allocate (on all Armada SoCs), and to
+ * set the shareable attribute in page tables (on all Armada
+ * SoCs except the Armada 370). Unfortunately, such decisions
+ * are taken very early in the kernel boot process, at a point
+ * where we don't know yet on which SoC we are running.
+ */
+ if (!is_smp())
+ return 0;
+
np = of_find_matching_node(NULL, of_coherency_table);
if (np) {
pr_info("Initializing Coherency fabric\n");
diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S
index 5476669..ee7598f 100644
--- a/arch/arm/mach-mvebu/coherency_ll.S
+++ b/arch/arm/mach-mvebu/coherency_ll.S
@@ -20,6 +20,8 @@
#define ARMADA_XP_CFB_CTL_REG_OFFSET 0x0
#define ARMADA_XP_CFB_CFG_REG_OFFSET 0x4
+#include <asm/assembler.h>
+
.text
/*
* r0: Coherency fabric base register address
@@ -29,6 +31,7 @@
/* Create bit by cpu index */
mov r3, #(1 << 24)
lsl r1, r3, r1
+ARM_BE8(rev r1, r1)
/* Add CPU to SMP group - Atomic */
add r3, r0, #ARMADA_XP_CFB_CTL_REG_OFFSET
diff --git a/arch/arm/mach-mvebu/headsmp.S b/arch/arm/mach-mvebu/headsmp.S
index a06e0ed..458ed3f 100644
--- a/arch/arm/mach-mvebu/headsmp.S
+++ b/arch/arm/mach-mvebu/headsmp.S
@@ -21,6 +21,8 @@
#include <linux/linkage.h>
#include <linux/init.h>
+#include <asm/assembler.h>
+
/*
* At this stage the secondary CPUs don't have acces yet to the MMU, so
* we have to provide physical addresses
@@ -35,6 +37,7 @@
* startup
*/
ENTRY(armada_xp_secondary_startup)
+ ARM_BE8(setend be ) @ go BE8 if entered LE
/* Read CPU id */
mrc p15, 0, r1, c0, c0, 5
diff --git a/arch/arm/mach-mxs/pm.h b/arch/arm/mach-mxs/pm.h
index f57e7cd..09d77b0 100644
--- a/arch/arm/mach-mxs/pm.h
+++ b/arch/arm/mach-mxs/pm.h
@@ -9,6 +9,10 @@
#ifndef __ARCH_MXS_PM_H
#define __ARCH_MXS_PM_H
+#ifdef CONFIG_PM
void mxs_pm_init(void);
+#else
+#define mxs_pm_init NULL
+#endif
#endif
diff --git a/arch/arm/mach-omap1/board-h2.c b/arch/arm/mach-omap1/board-h2.c
index 0dac3d2..d712c51 100644
--- a/arch/arm/mach-omap1/board-h2.c
+++ b/arch/arm/mach-omap1/board-h2.c
@@ -379,7 +379,7 @@
/* usb1 has a Mini-AB port and external isp1301 transceiver */
.otg = 2,
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
.hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */
/* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */
#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-h3.c b/arch/arm/mach-omap1/board-h3.c
index 816ecd1..bfed4f9 100644
--- a/arch/arm/mach-omap1/board-h3.c
+++ b/arch/arm/mach-omap1/board-h3.c
@@ -366,7 +366,7 @@
/* usb1 has a Mini-AB port and external isp1301 transceiver */
.otg = 2,
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
.hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */
#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
/* NONSTANDARD CABLE NEEDED (B-to-Mini-B) */
diff --git a/arch/arm/mach-omap1/board-innovator.c b/arch/arm/mach-omap1/board-innovator.c
index bd5f02e..c49ce83 100644
--- a/arch/arm/mach-omap1/board-innovator.c
+++ b/arch/arm/mach-omap1/board-innovator.c
@@ -312,7 +312,7 @@
/* usb1 has a Mini-AB port and external isp1301 transceiver */
.otg = 2,
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
.hmc_mode = 19, /* 0:host(off) 1:dev|otg 2:disabled */
/* .hmc_mode = 21,*/ /* 0:host(off) 1:dev(loopback) 2:host(loopback) */
#elif defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index a7ce692..006fbb5 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -280,7 +280,7 @@
* be used, with a NONSTANDARD gender-bending cable/dongle, as
* a peripheral.
*/
-#ifdef CONFIG_USB_GADGET_OMAP
+#if IS_ENABLED(CONFIG_USB_OMAP)
.register_dev = 1,
.hmc_mode = 0,
#else
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index f49cd51..42afc66 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -394,14 +394,6 @@
select OMAP_PACKAGE_CBS
select REGULATOR_FIXED_VOLTAGE if REGULATOR
-config OMAP3_EMU
- bool "OMAP3 debugging peripherals"
- depends on ARCH_OMAP3
- select ARM_AMBA
- select OC_ETM
- help
- Say Y here to enable debugging hardware of omap3
-
config OMAP3_SDRC_AC_TIMING
bool "Enable SDRC AC timing register changes"
depends on ARCH_OMAP3
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 55a9d67..e2f7210 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -200,7 +200,6 @@
obj-$(CONFIG_ARCH_OMAP4) += omap_hwmod_44xx_data.o
# EMU peripherals
-obj-$(CONFIG_OMAP3_EMU) += emu.o
obj-$(CONFIG_HW_PERF_EVENTS) += pmu.o
obj-$(CONFIG_OMAP_MBOX_FWK) += mailbox_mach.o
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 45cd264..da6d407 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -418,7 +418,8 @@
.clkdm_name = "dpll4_clkdm",
};
-DEFINE_STRUCT_CLK(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, dpll4_m5x2_ck_ops);
+DEFINE_STRUCT_CLK_FLAGS(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names,
+ dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT);
static struct clk dpll4_m5x2_ck_3630 = {
.name = "dpll4_m5x2_ck",
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 2adb268..6124da1 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -323,7 +323,8 @@
scratchpad_contents.public_restore_ptr =
virt_to_phys(omap3_restore_3630);
else if (omap_rev() != OMAP3430_REV_ES3_0 &&
- omap_rev() != OMAP3430_REV_ES3_1)
+ omap_rev() != OMAP3430_REV_ES3_1 &&
+ omap_rev() != OMAP3430_REV_ES3_1_2)
scratchpad_contents.public_restore_ptr =
virt_to_phys(omap3_restore);
else
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index c443f2e..f98410a 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -14,6 +14,7 @@
#include <linux/cpuidle.h>
#include <linux/cpu_pm.h>
#include <linux/export.h>
+#include <linux/clockchips.h>
#include <asm/cpuidle.h>
#include <asm/proc-fns.h>
@@ -80,6 +81,7 @@
int index)
{
struct idle_statedata *cx = state_ptr + index;
+ int cpu_id = smp_processor_id();
/*
* CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -104,6 +106,8 @@
}
}
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+
/*
* Call idle CPU PM enter notifier chain so that
* VFP and per CPU interrupt context is saved.
@@ -147,6 +151,8 @@
(cx->mpu_logic_state == PWRDM_POWER_OFF))
cpu_cluster_pm_exit();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+
fail:
cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
cpu_done[dev->cpu] = false;
@@ -154,6 +160,16 @@
return index;
}
+/*
+ * For each cpu, setup the broadcast timer because local timers
+ * stops for the states above C1.
+ */
+static void omap_setup_broadcast_timer(void *arg)
+{
+ int cpu = smp_processor_id();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
static struct cpuidle_driver omap4_idle_driver = {
.name = "omap4_idle",
.owner = THIS_MODULE,
@@ -171,8 +187,7 @@
/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
.exit_latency = 328 + 440,
.target_residency = 960,
- .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
- CPUIDLE_FLAG_TIMER_STOP,
+ .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
.enter = omap_enter_idle_coupled,
.name = "C2",
.desc = "CPUx OFF, MPUSS CSWR",
@@ -181,8 +196,7 @@
/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
.exit_latency = 460 + 518,
.target_residency = 1100,
- .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
- CPUIDLE_FLAG_TIMER_STOP,
+ .flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
.enter = omap_enter_idle_coupled,
.name = "C3",
.desc = "CPUx OFF, MPUSS OSWR",
@@ -213,5 +227,8 @@
if (!cpu_clkdm[0] || !cpu_clkdm[1])
return -ENODEV;
+ /* Configure the broadcast timer on each cpu */
+ on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
+
return cpuidle_register(&omap4_idle_driver, cpu_online_mask);
}
diff --git a/arch/arm/mach-omap2/emu.c b/arch/arm/mach-omap2/emu.c
deleted file mode 100644
index cbeaca2..0000000
--- a/arch/arm/mach-omap2/emu.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * emu.c
- *
- * ETM and ETB CoreSight components' resources as found in OMAP3xxx.
- *
- * Copyright (C) 2009 Nokia Corporation.
- * Alexander Shishkin
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/amba/bus.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-
-#include "soc.h"
-#include "iomap.h"
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Alexander Shishkin");
-
-/* Cortex CoreSight components within omap3xxx EMU */
-#define ETM_BASE (L4_EMU_34XX_PHYS + 0x10000)
-#define DBG_BASE (L4_EMU_34XX_PHYS + 0x11000)
-#define ETB_BASE (L4_EMU_34XX_PHYS + 0x1b000)
-#define DAPCTL (L4_EMU_34XX_PHYS + 0x1d000)
-
-static AMBA_APB_DEVICE(omap3_etb, "etb", 0x000bb907, ETB_BASE, { }, NULL);
-static AMBA_APB_DEVICE(omap3_etm, "etm", 0x102bb921, ETM_BASE, { }, NULL);
-
-static int __init emu_init(void)
-{
- if (!cpu_is_omap34xx())
- return -ENODEV;
-
- amba_device_register(&omap3_etb_device, &iomem_resource);
- amba_device_register(&omap3_etm_device, &iomem_resource);
-
- return 0;
-}
-
-omap_subsys_initcall(emu_init);
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 6c4da12..55bcb77 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -1335,7 +1335,7 @@
of_property_read_bool(np, "gpmc,time-para-granularity");
}
-#ifdef CONFIG_MTD_NAND
+#if IS_ENABLED(CONFIG_MTD_NAND)
static const char * const nand_ecc_opts[] = {
[OMAP_ECC_HAMMING_CODE_DEFAULT] = "sw",
@@ -1391,7 +1391,7 @@
}
#endif
-#ifdef CONFIG_MTD_ONENAND
+#if IS_ENABLED(CONFIG_MTD_ONENAND)
static int gpmc_probe_onenand_child(struct platform_device *pdev,
struct device_node *child)
{
diff --git a/arch/arm/mach-omap2/irq.c b/arch/arm/mach-omap2/irq.c
index 3926f37..6037a9a 100644
--- a/arch/arm/mach-omap2/irq.c
+++ b/arch/arm/mach-omap2/irq.c
@@ -222,6 +222,7 @@
static inline void omap_intc_handle_irq(void __iomem *base_addr, struct pt_regs *regs)
{
u32 irqnr;
+ int handled_irq = 0;
do {
irqnr = readl_relaxed(base_addr + 0x98);
@@ -233,7 +234,7 @@
goto out;
irqnr = readl_relaxed(base_addr + 0xd8);
-#ifdef CONFIG_SOC_TI81XX
+#if IS_ENABLED(CONFIG_SOC_TI81XX) || IS_ENABLED(CONFIG_SOC_AM33XX)
if (irqnr)
goto out;
irqnr = readl_relaxed(base_addr + 0xf8);
@@ -249,8 +250,15 @@
if (irqnr) {
irqnr = irq_find_mapping(domain, irqnr);
handle_IRQ(irqnr, regs);
+ handled_irq = 1;
}
} while (irqnr);
+
+ /* If an irq is masked or deasserted while active, we will
+ * keep ending up here with no irq handled. So remove it from
+ * the INTC with an ack.*/
+ if (!handled_irq)
+ omap_ack_irq(NULL);
}
asmlinkage void __exception_irq_entry omap2_intc_handle_irq(struct pt_regs *regs)
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index f82cf87..94c2f6d 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -183,8 +183,10 @@
m0_entry = mux->muxnames[0];
/* First check for full name in mode0.muxmode format */
- if (mode0_len && strncmp(muxname, m0_entry, mode0_len))
- continue;
+ if (mode0_len)
+ if (strncmp(muxname, m0_entry, mode0_len) ||
+ (strlen(m0_entry) != mode0_len))
+ continue;
/* Then check for muxmode only */
for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 13b27ff..ab99ab8 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -162,6 +162,7 @@
static void omap4_l2x0_disable(void)
{
+ outer_flush_all();
/* Disable PL310 L2 Cache controller */
omap_smc1(0x102, 0x0);
}
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 7341eff..62e40a9 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -399,7 +399,7 @@
}
/**
- * _set_softreset: set OCP_SYSCONFIG.CLOCKACTIVITY bits in @v
+ * _set_softreset: set OCP_SYSCONFIG.SOFTRESET bit in @v
* @oh: struct omap_hwmod *
* @v: pointer to register contents to modify
*
@@ -427,6 +427,36 @@
}
/**
+ * _clear_softreset: clear OCP_SYSCONFIG.SOFTRESET bit in @v
+ * @oh: struct omap_hwmod *
+ * @v: pointer to register contents to modify
+ *
+ * Clear the SOFTRESET bit in @v for hwmod @oh. Returns -EINVAL upon
+ * error or 0 upon success.
+ */
+static int _clear_softreset(struct omap_hwmod *oh, u32 *v)
+{
+ u32 softrst_mask;
+
+ if (!oh->class->sysc ||
+ !(oh->class->sysc->sysc_flags & SYSC_HAS_SOFTRESET))
+ return -EINVAL;
+
+ if (!oh->class->sysc->sysc_fields) {
+ WARN(1,
+ "omap_hwmod: %s: sysc_fields absent for sysconfig class\n",
+ oh->name);
+ return -EINVAL;
+ }
+
+ softrst_mask = (0x1 << oh->class->sysc->sysc_fields->srst_shift);
+
+ *v &= ~softrst_mask;
+
+ return 0;
+}
+
+/**
* _wait_softreset_complete - wait for an OCP softreset to complete
* @oh: struct omap_hwmod * to wait on
*
@@ -1909,6 +1939,12 @@
ret = _set_softreset(oh, &v);
if (ret)
goto dis_opt_clks;
+
+ _write_sysconfig(v, oh);
+ ret = _clear_softreset(oh, &v);
+ if (ret)
+ goto dis_opt_clks;
+
_write_sysconfig(v, oh);
if (oh->class->sysc->srst_udelay)
@@ -2141,6 +2177,8 @@
oh->mux->pads_dynamic))) {
omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED);
_reconfigure_io_chain();
+ } else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+ _reconfigure_io_chain();
}
_add_initiator_dep(oh, mpu_oh);
@@ -2247,6 +2285,8 @@
if (oh->mux && oh->mux->pads_dynamic) {
omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE);
_reconfigure_io_chain();
+ } else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+ _reconfigure_io_chain();
}
oh->_state = _HWMOD_STATE_IDLE;
@@ -3148,6 +3188,11 @@
goto error;
_write_sysconfig(v, oh);
+ ret = _clear_softreset(oh, &v);
+ if (ret)
+ goto error;
+ _write_sysconfig(v, oh);
+
error:
return ret;
}
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
index d05fc7b..83735b7 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_ipblock_data.c
@@ -796,7 +796,7 @@
/* gpmc */
static struct omap_hwmod_irq_info omap2xxx_gpmc_irqs[] = {
- { .irq = 20 },
+ { .irq = 20 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -841,7 +841,7 @@
};
static struct omap_hwmod_irq_info omap2_rng_mpu_irqs[] = {
- { .irq = 52 },
+ { .irq = 52 + OMAP_INTC_START, },
{ .irq = -1 }
};
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index 31c7126..8691c8c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1930,7 +1930,8 @@
.syss_offs = 0x0014,
.sysc_flags = (SYSC_HAS_MIDLEMODE | SYSC_HAS_CLOCKACTIVITY |
SYSC_HAS_SIDLEMODE | SYSC_HAS_ENAWAKEUP |
- SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE),
+ SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE |
+ SYSS_HAS_RESET_STATUS),
.idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART),
.sysc_fields = &omap_hwmod_sysc_type1,
@@ -1954,7 +1955,7 @@
static struct omap_hwmod omap3xxx_usb_host_hs_hwmod = {
.name = "usb_host_hs",
.class = &omap3xxx_usb_host_hs_hwmod_class,
- .clkdm_name = "l3_init_clkdm",
+ .clkdm_name = "usbhost_clkdm",
.mpu_irqs = omap3xxx_usb_host_hs_irqs,
.main_clk = "usbhost_48m_fck",
.prcm = {
@@ -2008,15 +2009,7 @@
* hence HWMOD_SWSUP_MSTANDBY
*/
- /*
- * During system boot; If the hwmod framework resets the module
- * the module will have smart idle settings; which can lead to deadlock
- * (above Errata Id:i660); so, dont reset the module during boot;
- * Use HWMOD_INIT_NO_RESET.
- */
-
- .flags = HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY |
- HWMOD_INIT_NO_RESET,
+ .flags = HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
};
/*
@@ -2047,7 +2040,7 @@
static struct omap_hwmod omap3xxx_usb_tll_hs_hwmod = {
.name = "usb_tll_hs",
.class = &omap3xxx_usb_tll_hs_hwmod_class,
- .clkdm_name = "l3_init_clkdm",
+ .clkdm_name = "core_l4_clkdm",
.mpu_irqs = omap3xxx_usb_tll_hs_irqs,
.main_clk = "usbtll_fck",
.prcm = {
@@ -2159,7 +2152,7 @@
};
static struct omap_hwmod_irq_info omap3xxx_gpmc_irqs[] = {
- { .irq = 20 },
+ { .irq = 20 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -2993,7 +2986,7 @@
static struct omap_hwmod omap3xxx_mmu_isp_hwmod;
static struct omap_hwmod_irq_info omap3xxx_mmu_isp_irqs[] = {
- { .irq = 24 },
+ { .irq = 24 + OMAP_INTC_START, },
{ .irq = -1 }
};
@@ -3035,7 +3028,7 @@
static struct omap_hwmod omap3xxx_mmu_iva_hwmod;
static struct omap_hwmod_irq_info omap3xxx_mmu_iva_irqs[] = {
- { .irq = 28 },
+ { .irq = 28 + OMAP_INTC_START, },
{ .irq = -1 }
};
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 7bdd22a..d4d0fce 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -103,7 +103,7 @@
#define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD (1 << 0)
-#if defined(CONFIG_ARCH_OMAP4)
+#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
extern u16 pm44xx_errata;
#define IS_PM44XX_ERRATUM(id) (pm44xx_errata & (id))
#else
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index f8b23b8..3f3259e 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -503,11 +503,11 @@
rate = clk_get_rate(sys_clk);
/* Numerator/denumerator values refer TRM Realtime Counter section */
switch (rate) {
- case 1200000:
+ case 12000000:
num = 64;
den = 125;
break;
- case 1300000:
+ case 13000000:
num = 768;
den = 1625;
break;
@@ -515,11 +515,11 @@
num = 8;
den = 25;
break;
- case 2600000:
+ case 26000000:
num = 384;
den = 1625;
break;
- case 2700000:
+ case 27000000:
num = 256;
den = 1125;
break;
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index a5b8fead..9cb7ea7 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -26,6 +26,7 @@
#include <linux/i2c.h>
#include <linux/i2c/pxa-i2c.h>
#include <linux/io.h>
+#include <linux/regulator/machine.h>
#include <linux/spi/spi.h>
#include <linux/spi/ads7846.h>
#include <linux/spi/corgi_lcd.h>
@@ -711,6 +712,8 @@
sharpsl_nand_partitions[1].size = 53 * 1024 * 1024;
platform_add_devices(devices, ARRAY_SIZE(devices));
+
+ regulator_has_full_constraints();
}
static void __init fixup_corgi(struct tag *tags, char **cmdline,
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 133109e..a07accf 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -891,6 +891,8 @@
mdelay(10);
gpio_set_value(GPIO71_HX4700_ASIC3_nRESET, 1);
mdelay(10);
+
+ regulator_has_full_constraints();
}
MACHINE_START(H4700, "HP iPAQ HX4700")
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 50ccd5f..362c05f 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -25,6 +25,7 @@
#include <linux/gpio.h>
#include <linux/i2c.h>
#include <linux/i2c/pxa-i2c.h>
+#include <linux/regulator/machine.h>
#include <linux/spi/spi.h>
#include <linux/spi/ads7846.h>
#include <linux/spi/pxa2xx_spi.h>
@@ -452,6 +453,7 @@
pxa_set_i2c_info(NULL);
i2c_register_board_info(0, ARRAY_AND_SIZE(poodle_i2c_devices));
poodle_init_spi();
+ regulator_has_full_constraints();
}
static void __init fixup_poodle(struct tag *tags, char **cmdline,
diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c
index 3fab583..0616390 100644
--- a/arch/arm/mach-pxa/reset.c
+++ b/arch/arm/mach-pxa/reset.c
@@ -13,6 +13,7 @@
#include <mach/regs-ost.h>
#include <mach/reset.h>
+#include <mach/smemc.h>
unsigned int reset_status;
EXPORT_SYMBOL(reset_status);
@@ -81,6 +82,12 @@
writel_relaxed(OSSR_M3, OSSR);
/* ... in 100 ms */
writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3);
+ /*
+ * SDRAM hangs on watchdog reset on Marvell PXA270 (erratum 71)
+ * we put SDRAM into self-refresh to prevent that
+ */
+ while (1)
+ writel_relaxed(MDREFR_SLFRSH, MDREFR);
}
void pxa_restart(char mode, const char *cmd)
@@ -104,4 +111,3 @@
break;
}
}
-
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 3d91d2e..d91fcf4 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -424,57 +424,57 @@
* Tosa Keyboard
*/
static const uint32_t tosakbd_keymap[] = {
- KEY(0, 2, KEY_W),
- KEY(0, 6, KEY_K),
- KEY(0, 7, KEY_BACKSPACE),
- KEY(0, 8, KEY_P),
- KEY(1, 1, KEY_Q),
- KEY(1, 2, KEY_E),
- KEY(1, 3, KEY_T),
- KEY(1, 4, KEY_Y),
- KEY(1, 6, KEY_O),
- KEY(1, 7, KEY_I),
- KEY(1, 8, KEY_COMMA),
- KEY(2, 1, KEY_A),
- KEY(2, 2, KEY_D),
- KEY(2, 3, KEY_G),
- KEY(2, 4, KEY_U),
- KEY(2, 6, KEY_L),
- KEY(2, 7, KEY_ENTER),
- KEY(2, 8, KEY_DOT),
- KEY(3, 1, KEY_Z),
- KEY(3, 2, KEY_C),
- KEY(3, 3, KEY_V),
- KEY(3, 4, KEY_J),
- KEY(3, 5, TOSA_KEY_ADDRESSBOOK),
- KEY(3, 6, TOSA_KEY_CANCEL),
- KEY(3, 7, TOSA_KEY_CENTER),
- KEY(3, 8, TOSA_KEY_OK),
- KEY(3, 9, KEY_LEFTSHIFT),
- KEY(4, 1, KEY_S),
- KEY(4, 2, KEY_R),
- KEY(4, 3, KEY_B),
- KEY(4, 4, KEY_N),
- KEY(4, 5, TOSA_KEY_CALENDAR),
- KEY(4, 6, TOSA_KEY_HOMEPAGE),
- KEY(4, 7, KEY_LEFTCTRL),
- KEY(4, 8, TOSA_KEY_LIGHT),
- KEY(4, 10, KEY_RIGHTSHIFT),
- KEY(5, 1, KEY_TAB),
- KEY(5, 2, KEY_SLASH),
- KEY(5, 3, KEY_H),
- KEY(5, 4, KEY_M),
- KEY(5, 5, TOSA_KEY_MENU),
- KEY(5, 7, KEY_UP),
- KEY(5, 11, TOSA_KEY_FN),
- KEY(6, 1, KEY_X),
- KEY(6, 2, KEY_F),
- KEY(6, 3, KEY_SPACE),
- KEY(6, 4, KEY_APOSTROPHE),
- KEY(6, 5, TOSA_KEY_MAIL),
- KEY(6, 6, KEY_LEFT),
- KEY(6, 7, KEY_DOWN),
- KEY(6, 8, KEY_RIGHT),
+ KEY(0, 1, KEY_W),
+ KEY(0, 5, KEY_K),
+ KEY(0, 6, KEY_BACKSPACE),
+ KEY(0, 7, KEY_P),
+ KEY(1, 0, KEY_Q),
+ KEY(1, 1, KEY_E),
+ KEY(1, 2, KEY_T),
+ KEY(1, 3, KEY_Y),
+ KEY(1, 5, KEY_O),
+ KEY(1, 6, KEY_I),
+ KEY(1, 7, KEY_COMMA),
+ KEY(2, 0, KEY_A),
+ KEY(2, 1, KEY_D),
+ KEY(2, 2, KEY_G),
+ KEY(2, 3, KEY_U),
+ KEY(2, 5, KEY_L),
+ KEY(2, 6, KEY_ENTER),
+ KEY(2, 7, KEY_DOT),
+ KEY(3, 0, KEY_Z),
+ KEY(3, 1, KEY_C),
+ KEY(3, 2, KEY_V),
+ KEY(3, 3, KEY_J),
+ KEY(3, 4, TOSA_KEY_ADDRESSBOOK),
+ KEY(3, 5, TOSA_KEY_CANCEL),
+ KEY(3, 6, TOSA_KEY_CENTER),
+ KEY(3, 7, TOSA_KEY_OK),
+ KEY(3, 8, KEY_LEFTSHIFT),
+ KEY(4, 0, KEY_S),
+ KEY(4, 1, KEY_R),
+ KEY(4, 2, KEY_B),
+ KEY(4, 3, KEY_N),
+ KEY(4, 4, TOSA_KEY_CALENDAR),
+ KEY(4, 5, TOSA_KEY_HOMEPAGE),
+ KEY(4, 6, KEY_LEFTCTRL),
+ KEY(4, 7, TOSA_KEY_LIGHT),
+ KEY(4, 9, KEY_RIGHTSHIFT),
+ KEY(5, 0, KEY_TAB),
+ KEY(5, 1, KEY_SLASH),
+ KEY(5, 2, KEY_H),
+ KEY(5, 3, KEY_M),
+ KEY(5, 4, TOSA_KEY_MENU),
+ KEY(5, 6, KEY_UP),
+ KEY(5, 10, TOSA_KEY_FN),
+ KEY(6, 0, KEY_X),
+ KEY(6, 1, KEY_F),
+ KEY(6, 2, KEY_SPACE),
+ KEY(6, 3, KEY_APOSTROPHE),
+ KEY(6, 4, TOSA_KEY_MAIL),
+ KEY(6, 5, KEY_LEFT),
+ KEY(6, 6, KEY_DOWN),
+ KEY(6, 7, KEY_RIGHT),
};
static struct matrix_keymap_data tosakbd_keymap_data = {
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2410.c b/arch/arm/mach-s3c24xx/clock-s3c2410.c
index 34fffdf..5645536 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2410.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2410.c
@@ -119,66 +119,101 @@
}
};
-static struct clk init_clocks[] = {
- {
- .name = "lcd",
- .parent = &clk_h,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_LCDC,
- }, {
- .name = "gpio",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_GPIO,
- }, {
- .name = "usb-host",
- .parent = &clk_h,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_USBH,
- }, {
- .name = "usb-device",
- .parent = &clk_h,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_USBD,
- }, {
- .name = "timers",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_PWMT,
- }, {
- .name = "uart",
- .devname = "s3c2410-uart.0",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_UART0,
- }, {
- .name = "uart",
- .devname = "s3c2410-uart.1",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_UART1,
- }, {
- .name = "uart",
- .devname = "s3c2410-uart.2",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_UART2,
- }, {
- .name = "rtc",
- .parent = &clk_p,
- .enable = s3c2410_clkcon_enable,
- .ctrlbit = S3C2410_CLKCON_RTC,
- }, {
- .name = "watchdog",
- .parent = &clk_p,
- .ctrlbit = 0,
- }, {
- .name = "usb-bus-host",
- .parent = &clk_usb_bus,
- }, {
- .name = "usb-bus-gadget",
- .parent = &clk_usb_bus,
- },
+static struct clk clk_lcd = {
+ .name = "lcd",
+ .parent = &clk_h,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_LCDC,
+};
+
+static struct clk clk_gpio = {
+ .name = "gpio",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_GPIO,
+};
+
+static struct clk clk_usb_host = {
+ .name = "usb-host",
+ .parent = &clk_h,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_USBH,
+};
+
+static struct clk clk_usb_device = {
+ .name = "usb-device",
+ .parent = &clk_h,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_USBD,
+};
+
+static struct clk clk_timers = {
+ .name = "timers",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_PWMT,
+};
+
+struct clk s3c24xx_clk_uart0 = {
+ .name = "uart",
+ .devname = "s3c2410-uart.0",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_UART0,
+};
+
+struct clk s3c24xx_clk_uart1 = {
+ .name = "uart",
+ .devname = "s3c2410-uart.1",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_UART1,
+};
+
+struct clk s3c24xx_clk_uart2 = {
+ .name = "uart",
+ .devname = "s3c2410-uart.2",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_UART2,
+};
+
+static struct clk clk_rtc = {
+ .name = "rtc",
+ .parent = &clk_p,
+ .enable = s3c2410_clkcon_enable,
+ .ctrlbit = S3C2410_CLKCON_RTC,
+};
+
+static struct clk clk_watchdog = {
+ .name = "watchdog",
+ .parent = &clk_p,
+ .ctrlbit = 0,
+};
+
+static struct clk clk_usb_bus_host = {
+ .name = "usb-bus-host",
+ .parent = &clk_usb_bus,
+};
+
+static struct clk clk_usb_bus_gadget = {
+ .name = "usb-bus-gadget",
+ .parent = &clk_usb_bus,
+};
+
+static struct clk *init_clocks[] = {
+ &clk_lcd,
+ &clk_gpio,
+ &clk_usb_host,
+ &clk_usb_device,
+ &clk_timers,
+ &s3c24xx_clk_uart0,
+ &s3c24xx_clk_uart1,
+ &s3c24xx_clk_uart2,
+ &clk_rtc,
+ &clk_watchdog,
+ &clk_usb_bus_host,
+ &clk_usb_bus_gadget,
};
/* s3c2410_baseclk_add()
@@ -195,7 +230,6 @@
{
unsigned long clkslow = __raw_readl(S3C2410_CLKSLOW);
unsigned long clkcon = __raw_readl(S3C2410_CLKCON);
- struct clk *clkp;
struct clk *xtal;
int ret;
int ptr;
@@ -207,8 +241,9 @@
/* register clocks from clock array */
- clkp = init_clocks;
- for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++, clkp++) {
+ for (ptr = 0; ptr < ARRAY_SIZE(init_clocks); ptr++) {
+ struct clk *clkp = init_clocks[ptr];
+
/* ensure that we note the clock state */
clkp->usage = clkcon & clkp->ctrlbit ? 1 : 0;
diff --git a/arch/arm/mach-s3c24xx/clock-s3c2440.c b/arch/arm/mach-s3c24xx/clock-s3c2440.c
index 1069b56..aaf006d 100644
--- a/arch/arm/mach-s3c24xx/clock-s3c2440.c
+++ b/arch/arm/mach-s3c24xx/clock-s3c2440.c
@@ -166,6 +166,9 @@
CLKDEV_INIT(NULL, "clk_uart_baud1", &s3c24xx_uclk),
CLKDEV_INIT(NULL, "clk_uart_baud2", &clk_p),
CLKDEV_INIT(NULL, "clk_uart_baud3", &s3c2440_clk_fclk_n),
+ CLKDEV_INIT("s3c2440-uart.0", "uart", &s3c24xx_clk_uart0),
+ CLKDEV_INIT("s3c2440-uart.1", "uart", &s3c24xx_clk_uart1),
+ CLKDEV_INIT("s3c2440-uart.2", "uart", &s3c24xx_clk_uart2),
CLKDEV_INIT("s3c2440-camif", "camera", &s3c2440_clk_cam_upll),
};
diff --git a/arch/arm/mach-s3c64xx/crag6410.h b/arch/arm/mach-s3c64xx/crag6410.h
index 4c3c999..81dc722 100644
--- a/arch/arm/mach-s3c64xx/crag6410.h
+++ b/arch/arm/mach-s3c64xx/crag6410.h
@@ -14,6 +14,7 @@
#include <linux/gpio.h>
#define GLENFARCLAS_PMIC_IRQ_BASE IRQ_BOARD_START
+#define BANFF_PMIC_IRQ_BASE (IRQ_BOARD_START + 64)
#define PCA935X_GPIO_BASE GPIO_BOARD_START
#define CODEC_GPIO_BASE (GPIO_BOARD_START + 8)
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410.c b/arch/arm/mach-s3c64xx/mach-crag6410.c
index 8ad88ac..5fa9ac9 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410.c
@@ -558,6 +558,7 @@
static struct wm831x_pdata crag_pmic_pdata = {
.wm831x_num = 1,
+ .irq_base = BANFF_PMIC_IRQ_BASE,
.gpio_base = BANFF_PMIC_GPIO_BASE,
.soft_shutdown = true,
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index e838ba2..c9808c6 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -512,6 +512,9 @@
* Its called GPCLKR0 in my SA1110 manual.
*/
Ser1SDCR0 |= SDCR0_SUS;
+ MSC1 = (MSC1 & ~0xffff) |
+ MSC_NonBrst | MSC_32BitStMem |
+ MSC_RdAcc(2) | MSC_WrAcc(2) | MSC_Rec(0);
if (!machine_has_neponset())
sa1100_register_uart_fns(&assabet_port_fns);
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d..50e1d85 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
#ifndef __ASM_ARCH_COLLIE_H
#define __ASM_ARCH_COLLIE_H
+#include "hardware.h" /* Gives GPIO_MAX */
+
extern void locomolcd_power(int on);
#define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1)
diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c
index 6645d1e..34853d5 100644
--- a/arch/arm/mach-sa1100/pm.c
+++ b/arch/arm/mach-sa1100/pm.c
@@ -81,6 +81,7 @@
/*
* Ensure not to come back here if it wasn't intended
*/
+ RCSR = RCSR_SMR;
PSPR = 0;
/*
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index b85b288..803c9fc 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -437,7 +437,7 @@
.id = 0,
.dev = {
.platform_data = &lcdc0_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -534,7 +534,7 @@
.id = 1,
.dev = {
.platform_data = &hdmi_lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index e6b775a..4d610e6 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -332,7 +332,7 @@
.resource = lcdc_resources,
.dev = {
.platform_data = &lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index fa3407d..3b917bc 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -421,7 +421,7 @@
.resource = lcdc_resources,
.dev = {
.platform_data = &lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
@@ -497,7 +497,7 @@
.id = 1,
.dev = {
.platform_data = &hdmi_lcdc_info,
- .coherent_dma_mask = ~0,
+ .coherent_dma_mask = DMA_BIT_MASK(32),
},
};
diff --git a/arch/arm/mach-shmobile/setup-emev2.c b/arch/arm/mach-shmobile/setup-emev2.c
index 899a86c..1ccddd2 100644
--- a/arch/arm/mach-shmobile/setup-emev2.c
+++ b/arch/arm/mach-shmobile/setup-emev2.c
@@ -287,14 +287,14 @@
static struct resource gio3_resources[] = {
[0] = {
.name = "GIO_096",
- .start = 0xe0050100,
- .end = 0xe005012b,
+ .start = 0xe0050180,
+ .end = 0xe00501ab,
.flags = IORESOURCE_MEM,
},
[1] = {
.name = "GIO_096",
- .start = 0xe0050140,
- .end = 0xe005015f,
+ .start = 0xe00501c0,
+ .end = 0xe00501df,
.flags = IORESOURCE_MEM,
},
[2] = {
diff --git a/arch/arm/mach-shmobile/setup-r8a73a4.c b/arch/arm/mach-shmobile/setup-r8a73a4.c
index c5a75a7..7f45c2e 100644
--- a/arch/arm/mach-shmobile/setup-r8a73a4.c
+++ b/arch/arm/mach-shmobile/setup-r8a73a4.c
@@ -62,7 +62,7 @@
static const struct plat_sci_port scif[] = {
SCIFA_DATA(SCIFA0, 0xe6c40000, gic_spi(144)), /* SCIFA0 */
SCIFA_DATA(SCIFA1, 0xe6c50000, gic_spi(145)), /* SCIFA1 */
- SCIFB_DATA(SCIFB0, 0xe6c50000, gic_spi(145)), /* SCIFB0 */
+ SCIFB_DATA(SCIFB0, 0xe6c20000, gic_spi(148)), /* SCIFB0 */
SCIFB_DATA(SCIFB1, 0xe6c30000, gic_spi(149)), /* SCIFB1 */
SCIFB_DATA(SCIFB2, 0xe6ce0000, gic_spi(150)), /* SCIFB2 */
SCIFB_DATA(SCIFB3, 0xe6cf0000, gic_spi(151)), /* SCIFB3 */
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 9696f36..ea788c8 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -814,6 +814,7 @@
static struct renesas_intc_irqpin_config irqpin0_platform_data = {
.irq_base = irq_pin(0), /* IRQ0 -> IRQ7 */
+ .control_parent = true,
};
static struct resource irqpin0_resources[] = {
@@ -875,6 +876,7 @@
static struct renesas_intc_irqpin_config irqpin2_platform_data = {
.irq_base = irq_pin(16), /* IRQ16 -> IRQ23 */
+ .control_parent = true,
};
static struct resource irqpin2_resources[] = {
@@ -905,6 +907,7 @@
static struct renesas_intc_irqpin_config irqpin3_platform_data = {
.irq_base = irq_pin(24), /* IRQ24 -> IRQ31 */
+ .control_parent = true,
};
static struct resource irqpin3_resources[] = {
diff --git a/arch/arm/mach-tegra/common.c b/arch/arm/mach-tegra/common.c
index 9f852c6..d5ebcd0 100644
--- a/arch/arm/mach-tegra/common.c
+++ b/arch/arm/mach-tegra/common.c
@@ -22,6 +22,7 @@
#include <linux/io.h>
#include <linux/clk.h>
#include <linux/delay.h>
+#include <linux/of.h>
#include <linux/irqchip.h>
#include <linux/clk/tegra.h>
@@ -80,10 +81,20 @@
static void __init tegra_init_cache(void)
{
#ifdef CONFIG_CACHE_L2X0
+ static const struct of_device_id pl310_ids[] __initconst = {
+ { .compatible = "arm,pl310-cache", },
+ {}
+ };
+
+ struct device_node *np;
int ret;
void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000;
u32 aux_ctrl, cache_type;
+ np = of_find_matching_node(NULL, pl310_ids);
+ if (!np)
+ return;
+
cache_type = readl(p + L2X0_CACHE_TYPE);
aux_ctrl = (cache_type & 0x700) << (17-8);
aux_ctrl |= 0x7C400001;
diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h
index ec08740..6f938cc 100644
--- a/arch/arm/mach-versatile/include/mach/platform.h
+++ b/arch/arm/mach-versatile/include/mach/platform.h
@@ -231,12 +231,14 @@
/* PCI space */
#define VERSATILE_PCI_BASE 0x41000000 /* PCI Interface */
#define VERSATILE_PCI_CFG_BASE 0x42000000
+#define VERSATILE_PCI_IO_BASE 0x43000000
#define VERSATILE_PCI_MEM_BASE0 0x44000000
#define VERSATILE_PCI_MEM_BASE1 0x50000000
#define VERSATILE_PCI_MEM_BASE2 0x60000000
/* Sizes of above maps */
#define VERSATILE_PCI_BASE_SIZE 0x01000000
#define VERSATILE_PCI_CFG_BASE_SIZE 0x02000000
+#define VERSATILE_PCI_IO_BASE_SIZE 0x01000000
#define VERSATILE_PCI_MEM_BASE0_SIZE 0x0c000000 /* 32Mb */
#define VERSATILE_PCI_MEM_BASE1_SIZE 0x10000000 /* 256Mb */
#define VERSATILE_PCI_MEM_BASE2_SIZE 0x10000000 /* 256Mb */
diff --git a/arch/arm/mach-versatile/pci.c b/arch/arm/mach-versatile/pci.c
index e92e5e0..c97be4e 100644
--- a/arch/arm/mach-versatile/pci.c
+++ b/arch/arm/mach-versatile/pci.c
@@ -43,9 +43,9 @@
#define PCI_IMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x0)
#define PCI_IMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x4)
#define PCI_IMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x8)
-#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x10)
-#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
-#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP0 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x14)
+#define PCI_SMAP1 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x18)
+#define PCI_SMAP2 __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0x1c)
#define PCI_SELFID __IO_ADDRESS(VERSATILE_PCI_CORE_BASE+0xc)
#define DEVICE_ID_OFFSET 0x00
@@ -170,8 +170,8 @@
.write = versatile_write_config,
};
-static struct resource io_mem = {
- .name = "PCI I/O space",
+static struct resource unused_mem = {
+ .name = "PCI unused",
.start = VERSATILE_PCI_MEM_BASE0,
.end = VERSATILE_PCI_MEM_BASE0+VERSATILE_PCI_MEM_BASE0_SIZE-1,
.flags = IORESOURCE_MEM,
@@ -195,9 +195,9 @@
{
int ret = 0;
- ret = request_resource(&iomem_resource, &io_mem);
+ ret = request_resource(&iomem_resource, &unused_mem);
if (ret) {
- printk(KERN_ERR "PCI: unable to allocate I/O "
+ printk(KERN_ERR "PCI: unable to allocate unused "
"memory region (%d)\n", ret);
goto out;
}
@@ -205,7 +205,7 @@
if (ret) {
printk(KERN_ERR "PCI: unable to allocate non-prefetchable "
"memory region (%d)\n", ret);
- goto release_io_mem;
+ goto release_unused_mem;
}
ret = request_resource(&iomem_resource, &pre_mem);
if (ret) {
@@ -225,8 +225,8 @@
release_non_mem:
release_resource(&non_mem);
- release_io_mem:
- release_resource(&io_mem);
+ release_unused_mem:
+ release_resource(&unused_mem);
out:
return ret;
}
@@ -246,7 +246,7 @@
goto out;
}
- ret = pci_ioremap_io(0, VERSATILE_PCI_MEM_BASE0);
+ ret = pci_ioremap_io(0, VERSATILE_PCI_IO_BASE);
if (ret)
goto out;
@@ -295,6 +295,19 @@
__raw_writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2);
/*
+ * For many years the kernel and QEMU were symbiotically buggy
+ * in that they both assumed the same broken IRQ mapping.
+ * QEMU therefore attempts to auto-detect old broken kernels
+ * so that they still work on newer QEMU as they did on old
+ * QEMU. Since we now use the correct (ie matching-hardware)
+ * IRQ mapping we write a definitely different value to a
+ * PCI_INTERRUPT_LINE register to tell QEMU that we expect
+ * real hardware behaviour and it need not be backwards
+ * compatible for us. This write is harmless on real hardware.
+ */
+ __raw_writel(0, VERSATILE_PCI_VIRT_BASE+PCI_INTERRUPT_LINE);
+
+ /*
* Do not to map Versatile FPGA PCI device into memory space
*/
pci_slot_ignore |= (1 << myslot);
@@ -327,13 +340,13 @@
{
int irq;
- /* slot, pin, irq
- * 24 1 IRQ_SIC_PCI0
- * 25 1 IRQ_SIC_PCI1
- * 26 1 IRQ_SIC_PCI2
- * 27 1 IRQ_SIC_PCI3
+ /*
+ * Slot INTA INTB INTC INTD
+ * 31 PCI1 PCI2 PCI3 PCI0
+ * 30 PCI0 PCI1 PCI2 PCI3
+ * 29 PCI3 PCI0 PCI1 PCI2
*/
- irq = IRQ_SIC_PCI0 + ((slot - 24 + pin - 1) & 3);
+ irq = IRQ_SIC_PCI0 + ((slot + 2 + pin - 1) & 3);
return irq;
}
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 5907e10..39858ba 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,6 +1,9 @@
config ARCH_VEXPRESS
bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
+ select ARCH_HAS_CPUFREQ
+ select ARCH_HAS_OPP
select ARCH_REQUIRE_GPIOLIB
+ select ARCH_SUPPORTS_BIG_ENDIAN
select ARM_AMBA
select ARM_GIC
select ARM_TIMER_SP804
@@ -56,5 +59,23 @@
config ARCH_VEXPRESS_CA9X4
bool "Versatile Express Cortex-A9x4 tile"
+ select ARM_ERRATA_643719
+
+config ARCH_VEXPRESS_DCSCB
+ bool "Dual Cluster System Control Block (DCSCB) support"
+ depends on MCPM
+ select ARM_CCI
+ help
+ Support for the Dual Cluster System Configuration Block (DCSCB).
+ This is needed to provide CPU and cluster power management
+ on RTSM implementing big.LITTLE.
+
+config ARCH_VEXPRESS_TC2
+ bool "TC2 cluster management"
+ depends on MCPM
+ select VEXPRESS_SPC
+ select ARM_CCI
+ help
+ Support for CPU and cluster power management on TC2.
endmenu
diff --git a/arch/arm/mach-vexpress/Makefile b/arch/arm/mach-vexpress/Makefile
index 42703e8..14193dc 100644
--- a/arch/arm/mach-vexpress/Makefile
+++ b/arch/arm/mach-vexpress/Makefile
@@ -6,5 +6,13 @@
obj-y := v2m.o
obj-$(CONFIG_ARCH_VEXPRESS_CA9X4) += ct-ca9x4.o
+obj-$(CONFIG_ARCH_VEXPRESS_DCSCB) += dcscb.o dcscb_setup.o
+CFLAGS_REMOVE_dcscb.o = -pg
+obj-$(CONFIG_ARCH_VEXPRESS_TC2) += tc2_pm.o tc2_pm_setup.o
+CFLAGS_REMOVE_tc2_pm.o = -pg
+ifeq ($(CONFIG_ARCH_VEXPRESS_TC2),y)
+obj-$(CONFIG_ARM_PSCI) += tc2_pm_psci.o
+CFLAGS_REMOVE_tc2_pm_psci.o = -pg
+endif
obj-$(CONFIG_SMP) += platsmp.o
obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o
diff --git a/arch/arm/mach-vexpress/core.h b/arch/arm/mach-vexpress/core.h
index f134cd4..bde4374 100644
--- a/arch/arm/mach-vexpress/core.h
+++ b/arch/arm/mach-vexpress/core.h
@@ -6,6 +6,8 @@
void vexpress_dt_smp_map_io(void);
+bool vexpress_smp_init_ops(void);
+
extern struct smp_operations vexpress_smp_ops;
extern void vexpress_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
new file mode 100644
index 0000000..b35700f
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -0,0 +1,236 @@
+/*
+ * arch/arm/mach-vexpress/dcscb.c - Dual Cluster System Configuration Block
+ *
+ * Created by: Nicolas Pitre, May 2012
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/of_address.h>
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+
+#define RST_HOLD0 0x0
+#define RST_HOLD1 0x4
+#define SYS_SWRESET 0x8
+#define RST_STAT0 0xc
+#define RST_STAT1 0x10
+#define EAG_CFG_R 0x20
+#define EAG_CFG_W 0x24
+#define KFC_CFG_R 0x28
+#define KFC_CFG_W 0x2c
+#define DCS_CFG_R 0x30
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() while its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t dcscb_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static void __iomem *dcscb_base;
+static int dcscb_use_count[4][2];
+static int dcscb_allcpus_mask[2];
+
+static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
+{
+ unsigned int rst_hold, cpumask = (1 << cpu);
+ unsigned int all_mask = dcscb_allcpus_mask[cluster];
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ if (cpu >= 4 || cluster >= 2)
+ return -EINVAL;
+
+ /*
+ * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+ * variant exists, we need to disable IRQs manually here.
+ */
+ local_irq_disable();
+ arch_spin_lock(&dcscb_lock);
+
+ dcscb_use_count[cpu][cluster]++;
+ if (dcscb_use_count[cpu][cluster] == 1) {
+ rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+ if (rst_hold & (1 << 8)) {
+ /* remove cluster reset and add individual CPU's reset */
+ rst_hold &= ~(1 << 8);
+ rst_hold |= all_mask;
+ }
+ rst_hold &= ~(cpumask | (cpumask << 4));
+ writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+ } else if (dcscb_use_count[cpu][cluster] != 2) {
+ /*
+ * The only possible values are:
+ * 0 = CPU down
+ * 1 = CPU (still) up
+ * 2 = CPU requested to be up before it had a chance
+ * to actually make itself down.
+ * Any other value is a bug.
+ */
+ BUG();
+ }
+
+ arch_spin_unlock(&dcscb_lock);
+ local_irq_enable();
+
+ return 0;
+}
+
+static void dcscb_power_down(void)
+{
+ unsigned int mpidr, cpu, cluster, rst_hold, cpumask, all_mask;
+ bool last_man = false, skip_wfi = false;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ cpumask = (1 << cpu);
+ all_mask = dcscb_allcpus_mask[cluster];
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cpu >= 4 || cluster >= 2);
+
+ __mcpm_cpu_going_down(cpu, cluster);
+
+ arch_spin_lock(&dcscb_lock);
+ BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+ dcscb_use_count[cpu][cluster]--;
+ if (dcscb_use_count[cpu][cluster] == 0) {
+ rst_hold = readl_relaxed(dcscb_base + RST_HOLD0 + cluster * 4);
+ rst_hold |= cpumask;
+ if (((rst_hold | (rst_hold >> 4)) & all_mask) == all_mask) {
+ rst_hold |= (1 << 8);
+ last_man = true;
+ }
+ writel_relaxed(rst_hold, dcscb_base + RST_HOLD0 + cluster * 4);
+ } else if (dcscb_use_count[cpu][cluster] == 1) {
+ /*
+ * A power_up request went ahead of us.
+ * Even if we do not want to shut this CPU down,
+ * the caller expects a certain state as if the WFI
+ * was aborted. So let's continue with cache cleaning.
+ */
+ skip_wfi = true;
+ } else
+ BUG();
+
+ if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+ arch_spin_unlock(&dcscb_lock);
+
+ /* Flush all cache levels for this cluster. */
+ v7_exit_coherency_flush(all);
+
+ /*
+ * This is a harmless no-op. On platforms with a real
+ * outer cache this might either be needed or not,
+ * depending on where the outer cache sits.
+ */
+ outer_flush_all();
+
+ /*
+ * Disable cluster-level coherency by masking
+ * incoming snoops and DVM messages:
+ */
+ cci_disable_port_by_cpu(mpidr);
+
+ __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+ } else {
+ arch_spin_unlock(&dcscb_lock);
+
+ /* Disable and flush the local CPU cache. */
+ v7_exit_coherency_flush(louis);
+ }
+
+ __mcpm_cpu_down(cpu, cluster);
+
+ /* Now we are prepared for power-down, do it: */
+ dsb();
+ if (!skip_wfi)
+ wfi();
+
+ /* Not dead at this point? Let our caller cope. */
+}
+
+static const struct mcpm_platform_ops dcscb_power_ops = {
+ .power_up = dcscb_power_up,
+ .power_down = dcscb_power_down,
+};
+
+static void __init dcscb_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cpu >= 4 || cluster >= 2);
+ dcscb_use_count[cpu][cluster] = 1;
+}
+
+extern void dcscb_power_up_setup(unsigned int affinity_level);
+
+static int __init dcscb_init(void)
+{
+ struct device_node *node;
+ unsigned int cfg;
+ int ret;
+
+ ret = psci_probe();
+ if (!ret) {
+ pr_debug("psci found. Aborting native init\n");
+ return -ENODEV;
+ }
+
+ if (!cci_probed())
+ return -ENODEV;
+
+ node = of_find_compatible_node(NULL, NULL, "arm,rtsm,dcscb");
+ if (!node)
+ return -ENODEV;
+ dcscb_base = of_iomap(node, 0);
+ if (!dcscb_base)
+ return -EADDRNOTAVAIL;
+ cfg = readl_relaxed(dcscb_base + DCS_CFG_R);
+ dcscb_allcpus_mask[0] = (1 << (((cfg >> 16) >> (0 << 2)) & 0xf)) - 1;
+ dcscb_allcpus_mask[1] = (1 << (((cfg >> 16) >> (1 << 2)) & 0xf)) - 1;
+ dcscb_usage_count_init();
+
+ ret = mcpm_platform_register(&dcscb_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(dcscb_power_up_setup);
+ if (ret) {
+ iounmap(dcscb_base);
+ return ret;
+ }
+
+ pr_info("VExpress DCSCB support installed\n");
+
+ /*
+ * Future entries into the kernel can now go
+ * through the cluster entry vectors.
+ */
+ vexpress_flags_set(virt_to_phys(mcpm_entry_point));
+
+ return 0;
+}
+
+early_initcall(dcscb_init);
diff --git a/arch/arm/mach-vexpress/dcscb_setup.S b/arch/arm/mach-vexpress/dcscb_setup.S
new file mode 100644
index 0000000..4bb7fbe
--- /dev/null
+++ b/arch/arm/mach-vexpress/dcscb_setup.S
@@ -0,0 +1,38 @@
+/*
+ * arch/arm/include/asm/dcscb_setup.S
+ *
+ * Created by: Dave Martin, 2012-06-22
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+
+ENTRY(dcscb_power_up_setup)
+
+ cmp r0, #0 @ check affinity level
+ beq 2f
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ *
+ * A15/A7 may not require explicit L2 invalidation on reset, dependent
+ * on hardware integration decisions.
+ * For now, this code assumes that L2 is either already invalidated,
+ * or invalidation is not required.
+ */
+
+ b cci_enable_port_for_self
+
+2: @ Implementation-specific local CPU setup operations should go here,
+ @ if any. In this case, there is nothing to do.
+
+ bx lr
+
+ENDPROC(dcscb_power_up_setup)
diff --git a/arch/arm/mach-vexpress/include/mach/tc2.h b/arch/arm/mach-vexpress/include/mach/tc2.h
new file mode 100644
index 0000000..d3b5a22
--- /dev/null
+++ b/arch/arm/mach-vexpress/include/mach/tc2.h
@@ -0,0 +1,10 @@
+#ifndef __MACH_TC2_H
+#define __MACH_TC2_H
+
+/*
+ * cpu and cluster limits
+ */
+#define TC2_MAX_CPUS 3
+#define TC2_MAX_CLUSTERS 2
+
+#endif
diff --git a/arch/arm/mach-vexpress/platsmp.c b/arch/arm/mach-vexpress/platsmp.c
index dc1ace5..b4a5f0d 100644
--- a/arch/arm/mach-vexpress/platsmp.c
+++ b/arch/arm/mach-vexpress/platsmp.c
@@ -12,9 +12,11 @@
#include <linux/errno.h>
#include <linux/smp.h>
#include <linux/io.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/vexpress.h>
+#include <asm/mcpm.h>
#include <asm/smp_scu.h>
#include <asm/mach/map.h>
@@ -51,7 +53,7 @@
{
if (of_flat_dt_match(node, vexpress_dt_cortex_a9_match)) {
phys_addr_t phys_addr;
- __be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
+ const __be32 *reg = of_get_flat_dt_prop(node, "reg", NULL);
if (WARN_ON(!reg))
return -EINVAL;
@@ -203,3 +205,21 @@
.cpu_die = vexpress_cpu_die,
#endif
};
+
+bool __init vexpress_smp_init_ops(void)
+{
+#ifdef CONFIG_MCPM
+ /*
+ * The best way to detect a multi-cluster configuration at the moment
+ * is to look for the presence of a CCI in the system.
+ * Override the default vexpress_smp_ops if so.
+ */
+ struct device_node *node;
+ node = of_find_compatible_node(NULL, NULL, "arm,cci-400");
+ if (node && of_device_is_available(node)) {
+ mcpm_smp_set_ops();
+ return true;
+ }
+#endif
+ return false;
+}
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
new file mode 100644
index 0000000..9fc264a
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -0,0 +1,277 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm.c - TC2 power management support
+ *
+ * Created by: Nicolas Pitre, October 2012
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * Some portions of this file were originally written by Achin Gupta
+ * Copyright: (C) 2012 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+#include <asm/psci.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+#include <linux/arm-cci.h>
+
+/*
+ * We can't use regular spinlocks. In the switcher case, it is possible
+ * for an outbound CPU to call power_down() after its inbound counterpart
+ * is already live using the same logical CPU number which trips lockdep
+ * debugging.
+ */
+static arch_spinlock_t tc2_pm_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+static int tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_power_up(unsigned int cpu, unsigned int cluster)
+{
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ if (cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster))
+ return -EINVAL;
+
+ /*
+ * Since this is called with IRQs enabled, and no arch_spin_lock_irq
+ * variant exists, we need to disable IRQs manually here.
+ */
+ local_irq_disable();
+ arch_spin_lock(&tc2_pm_lock);
+
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster])
+ vexpress_spc_powerdown_enable(cluster, 0);
+
+ tc2_pm_use_count[cpu][cluster]++;
+ if (tc2_pm_use_count[cpu][cluster] == 1) {
+ vexpress_spc_write_resume_reg(cluster, cpu,
+ virt_to_phys(mcpm_entry_point));
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+ } else if (tc2_pm_use_count[cpu][cluster] != 2) {
+ /*
+ * The only possible values are:
+ * 0 = CPU down
+ * 1 = CPU (still) up
+ * 2 = CPU requested to be up before it had a chance
+ * to actually make itself down.
+ * Any other value is a bug.
+ */
+ BUG();
+ }
+
+ arch_spin_unlock(&tc2_pm_lock);
+ local_irq_enable();
+
+ return 0;
+}
+
+static void tc2_pm_down(u64 residency)
+{
+ unsigned int mpidr, cpu, cluster;
+ bool last_man = false, skip_wfi = false;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ __mcpm_cpu_going_down(cpu, cluster);
+
+ arch_spin_lock(&tc2_pm_lock);
+ BUG_ON(__mcpm_cluster_state(cluster) != CLUSTER_UP);
+ tc2_pm_use_count[cpu][cluster]--;
+ if (tc2_pm_use_count[cpu][cluster] == 0) {
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 1);
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster] &&
+ (!residency || residency > 5000)) {
+ vexpress_spc_powerdown_enable(cluster, 1);
+ vexpress_spc_set_global_wakeup_intr(1);
+ last_man = true;
+ }
+ } else if (tc2_pm_use_count[cpu][cluster] == 1) {
+ /*
+ * A power_up request went ahead of us.
+ * Even if we do not want to shut this CPU down,
+ * the caller expects a certain state as if the WFI
+ * was aborted. So let's continue with cache cleaning.
+ */
+ skip_wfi = true;
+ } else
+ BUG();
+
+ /*
+ * If the CPU is committed to power down, make sure
+ * the power controller will be in charge of waking it
+ * up upon IRQ, ie IRQ lines are cut from GIC CPU IF
+ * to the CPU by disabling the GIC CPU IF to prevent wfi
+ * from completing execution behind power controller back
+ */
+ if (!skip_wfi)
+ gic_cpu_if_down();
+
+ if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
+ arch_spin_unlock(&tc2_pm_lock);
+
+ if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A15) {
+ /*
+ * On the Cortex-A15 we need to disable
+ * L2 prefetching before flushing the cache.
+ */
+ asm volatile(
+ "mcr p15, 1, %0, c15, c0, 3 \n\t"
+ "isb \n\t"
+ "dsb "
+ : : "r" (0x400) );
+ }
+
+ v7_exit_coherency_flush(all);
+
+ cci_disable_port_by_cpu(mpidr);
+
+ __mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+ } else {
+ /*
+ * If last man then undo any setup done previously.
+ */
+ if (last_man) {
+ vexpress_spc_powerdown_enable(cluster, 0);
+ vexpress_spc_set_global_wakeup_intr(0);
+ }
+
+ arch_spin_unlock(&tc2_pm_lock);
+
+ v7_exit_coherency_flush(louis);
+ }
+
+ __mcpm_cpu_down(cpu, cluster);
+
+ /* Now we are prepared for power-down, do it: */
+ if (!skip_wfi)
+ wfi();
+
+ /* Not dead at this point? Let our caller cope. */
+}
+
+static void tc2_pm_power_down(void)
+{
+ tc2_pm_down(0);
+}
+
+static void tc2_pm_suspend(u64 residency)
+{
+ extern void tc2_resume(void);
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+ vexpress_spc_write_resume_reg(cluster, cpu,
+ virt_to_phys(tc2_resume));
+
+ tc2_pm_down(residency);
+}
+
+static void tc2_pm_powered_up(void)
+{
+ unsigned int mpidr, cpu, cluster;
+ unsigned long flags;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ local_irq_save(flags);
+ arch_spin_lock(&tc2_pm_lock);
+
+ if (!tc2_pm_use_count[0][cluster] &&
+ !tc2_pm_use_count[1][cluster] &&
+ !tc2_pm_use_count[2][cluster]) {
+ vexpress_spc_powerdown_enable(cluster, 0);
+ vexpress_spc_set_global_wakeup_intr(0);
+ }
+
+ if (!tc2_pm_use_count[cpu][cluster])
+ tc2_pm_use_count[cpu][cluster] = 1;
+
+ vexpress_spc_set_cpu_wakeup_irq(cpu, cluster, 0);
+ vexpress_spc_write_resume_reg(cluster, cpu, 0);
+
+ arch_spin_unlock(&tc2_pm_lock);
+ local_irq_restore(flags);
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+ .power_up = tc2_pm_power_up,
+ .power_down = tc2_pm_power_down,
+ .suspend = tc2_pm_suspend,
+ .powered_up = tc2_pm_powered_up,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ tc2_pm_use_count[cpu][cluster] = 1;
+}
+
+extern void tc2_pm_power_up_setup(unsigned int affinity_level);
+
+static int __init tc2_pm_init(void)
+{
+ int ret;
+
+ ret = psci_probe();
+ if (!ret) {
+ pr_debug("psci found. Aborting native init\n");
+ return -ENODEV;
+ }
+
+ if (!vexpress_spc_check_loaded())
+ return -ENODEV;
+
+ tc2_pm_usage_count_init();
+
+ ret = mcpm_platform_register(&tc2_pm_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(tc2_pm_power_up_setup);
+ if (!ret)
+ pr_info("TC2 power management initialized\n");
+ return ret;
+}
+
+early_initcall(tc2_pm_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_psci.c b/arch/arm/mach-vexpress/tc2_pm_psci.c
new file mode 100644
index 0000000..c2fdc22
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_psci.c
@@ -0,0 +1,173 @@
+/*
+ * arch/arm/mach-vexpress/tc2_pm_psci.c - TC2 PSCI support
+ *
+ * Created by: Achin Gupta, December 2012
+ * Copyright: (C) 2012 ARM Limited
+ *
+ * Some portions of this file were originally written by Nicolas Pitre
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+
+#include <asm/mcpm.h>
+#include <asm/proc-fns.h>
+#include <asm/cacheflush.h>
+#include <asm/psci.h>
+#include <asm/atomic.h>
+#include <asm/cputype.h>
+#include <asm/cp15.h>
+
+#include <mach/motherboard.h>
+#include <mach/tc2.h>
+
+#include <linux/vexpress.h>
+
+/*
+ * Platform specific state id understood by the firmware and used to
+ * program the power controller
+ */
+#define PSCI_POWER_STATE_ID 0
+
+static atomic_t tc2_pm_use_count[TC2_MAX_CPUS][TC2_MAX_CLUSTERS];
+
+static int tc2_pm_psci_power_up(unsigned int cpu, unsigned int cluster)
+{
+ unsigned int mpidr = (cluster << 8) | cpu;
+ int ret = 0;
+
+ BUG_ON(!psci_ops.cpu_on);
+
+ switch (atomic_inc_return(&tc2_pm_use_count[cpu][cluster])) {
+ case 1:
+ /*
+ * This is a request to power up a cpu that linux thinks has
+ * been powered down. Retries are needed if the firmware has
+ * seen the power down request as yet.
+ */
+ do
+ ret = psci_ops.cpu_on(mpidr,
+ virt_to_phys(mcpm_entry_point));
+ while (ret == -EAGAIN);
+
+ return ret;
+ case 2:
+ /* This power up request has overtaken a power down request */
+ return ret;
+ default:
+ /* Any other value is a bug */
+ BUG();
+ }
+}
+
+static void tc2_pm_psci_power_down(void)
+{
+ struct psci_power_state power_state;
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ BUG_ON(!psci_ops.cpu_off);
+
+ switch (atomic_dec_return(&tc2_pm_use_count[cpu][cluster])) {
+ case 1:
+ /*
+ * Overtaken by a power up. Flush caches, exit coherency,
+ * return & fake a reset
+ */
+ set_cr(get_cr() & ~CR_C);
+
+ flush_cache_louis();
+
+ asm volatile ("clrex");
+ set_auxcr(get_auxcr() & ~(1 << 6));
+
+ return;
+ case 0:
+ /* A normal request to possibly power down the cluster */
+ power_state.id = PSCI_POWER_STATE_ID;
+ power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+ power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+ psci_ops.cpu_off(power_state);
+
+ /* On success this function never returns */
+ default:
+ /* Any other value is a bug */
+ BUG();
+ }
+}
+
+static void tc2_pm_psci_suspend(u64 unused)
+{
+ struct psci_power_state power_state;
+
+ BUG_ON(!psci_ops.cpu_suspend);
+
+ /* On TC2 always attempt to power down the cluster */
+ power_state.id = PSCI_POWER_STATE_ID;
+ power_state.type = PSCI_POWER_STATE_TYPE_POWER_DOWN;
+ power_state.affinity_level = PSCI_POWER_STATE_AFFINITY_LEVEL1;
+
+ psci_ops.cpu_suspend(power_state, virt_to_phys(mcpm_entry_point));
+
+ /* On success this function never returns */
+ BUG();
+}
+
+static const struct mcpm_platform_ops tc2_pm_power_ops = {
+ .power_up = tc2_pm_psci_power_up,
+ .power_down = tc2_pm_psci_power_down,
+ .suspend = tc2_pm_psci_suspend,
+};
+
+static void __init tc2_pm_usage_count_init(void)
+{
+ unsigned int mpidr, cpu, cluster;
+
+ mpidr = read_cpuid_mpidr();
+ cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+
+ pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
+ BUG_ON(cluster >= TC2_MAX_CLUSTERS ||
+ cpu >= vexpress_spc_get_nb_cpus(cluster));
+
+ atomic_set(&tc2_pm_use_count[cpu][cluster], 1);
+}
+
+static int __init tc2_pm_psci_init(void)
+{
+ int ret;
+
+ ret = psci_probe();
+ if (ret) {
+ pr_debug("psci not found. Aborting psci init\n");
+ return -ENODEV;
+ }
+
+ if (!vexpress_spc_check_loaded()) {
+ pr_debug("spc not found. Aborting psci init\n");
+ return -ENODEV;
+ }
+
+ tc2_pm_usage_count_init();
+
+ ret = mcpm_platform_register(&tc2_pm_power_ops);
+ if (!ret)
+ ret = mcpm_sync_init(NULL);
+ if (!ret)
+ pr_info("TC2 power management initialized\n");
+ return ret;
+}
+
+early_initcall(tc2_pm_psci_init);
diff --git a/arch/arm/mach-vexpress/tc2_pm_setup.S b/arch/arm/mach-vexpress/tc2_pm_setup.S
new file mode 100644
index 0000000..a18dafe
--- /dev/null
+++ b/arch/arm/mach-vexpress/tc2_pm_setup.S
@@ -0,0 +1,68 @@
+/*
+ * arch/arm/include/asm/tc2_pm_setup.S
+ *
+ * Created by: Nicolas Pitre, October 2012
+ ( (based on dcscb_setup.S by Dave Martin)
+ * Copyright: (C) 2012 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+
+#include <linux/linkage.h>
+#include <asm/mcpm.h>
+
+
+#define SPC_PHYS_BASE 0x7FFF0000
+#define SPC_WAKE_INT_STAT 0xb2c
+
+#define SNOOP_CTL_A15 0x404
+#define SNOOP_CTL_A7 0x504
+
+#define A15_SNOOP_MASK (0x3 << 7)
+#define A7_SNOOP_MASK (0x1 << 13)
+
+#define A15_BX_ADDR0 0xB68
+
+
+ENTRY(tc2_resume)
+ mrc p15, 0, r0, c0, c0, 5
+ ubfx r1, r0, #0, #4 @ r1 = cpu
+ ubfx r2, r0, #8, #4 @ r2 = cluster
+ add r1, r1, r2, lsl #2 @ r1 = index of CPU in WAKE_INT_STAT
+ ldr r3, =SPC_PHYS_BASE + SPC_WAKE_INT_STAT
+ ldr r3, [r3]
+ lsr r3, r1
+ tst r3, #1
+ wfieq @ if no pending IRQ reenters wfi
+ b mcpm_entry_point
+ENDPROC(tc2_resume)
+
+/*
+ * Enable cluster-level coherency, in preparation for turning on the MMU.
+ * The ACTLR SMP bit does not need to be set here, because cpu_resume()
+ * already restores that.
+ */
+
+ENTRY(tc2_pm_power_up_setup)
+
+ cmp r0, #0
+ beq 2f
+
+ b cci_enable_port_for_self
+
+2: @ Clear the BX addr register
+ ldr r3, =SPC_PHYS_BASE + A15_BX_ADDR0
+ mrc p15, 0, r0, c0, c0, 5 @ MPIDR
+ ubfx r1, r0, #8, #4 @ cluster
+ ubfx r0, r0, #0, #4 @ cpu
+ add r3, r3, r1, lsl #4
+ mov r1, #0
+ str r1, [r3, r0, lsl #2]
+ dsb
+
+ bx lr
+
+ENDPROC(tc2_pm_power_up_setup)
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 8802030..057f99b 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -10,6 +10,7 @@
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/irqchip.h>
+#include <linux/memblock.h>
#include <linux/of_address.h>
#include <linux/of_fdt.h>
#include <linux/of_irq.h>
@@ -373,6 +374,31 @@
.init_machine = v2m_init,
MACHINE_END
+static void __init v2m_dt_hdlcd_init(void)
+{
+ struct device_node *node;
+ int len, na, ns;
+ const __be32 *prop;
+ phys_addr_t fb_base, fb_size;
+
+ node = of_find_compatible_node(NULL, NULL, "arm,hdlcd");
+ if (!node)
+ return;
+
+ na = of_n_addr_cells(node);
+ ns = of_n_size_cells(node);
+
+ prop = of_get_property(node, "framebuffer", &len);
+ if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+ return;
+
+ fb_base = of_read_number(prop, na);
+ fb_size = of_read_number(prop + na, ns);
+
+ if (WARN_ON(memblock_remove(fb_base, fb_size)))
+ return;
+};
+
static struct map_desc v2m_rs1_io_desc __initdata = {
.virtual = V2M_PERIPH,
.pfn = __phys_to_pfn(0x1c000000),
@@ -423,6 +449,8 @@
pr_warning("vexpress: DT HBI (%x) is not matching "
"hardware (%x)!\n", dt_hbi, hbi);
}
+
+ v2m_dt_hdlcd_init();
}
static void __init v2m_dt_timer_init(void)
@@ -456,6 +484,7 @@
DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
.dt_compat = v2m_dt_match,
.smp = smp_ops(vexpress_smp_ops),
+ .smp_init = smp_init_ops(vexpress_smp_init_ops),
.map_io = v2m_dt_map_io,
.init_early = v2m_dt_init_early,
.init_irq = irqchip_init,
diff --git a/arch/arm/mach-virt/Makefile b/arch/arm/mach-virt/Makefile
index 042afc1..7ddbfa6 100644
--- a/arch/arm/mach-virt/Makefile
+++ b/arch/arm/mach-virt/Makefile
@@ -3,4 +3,3 @@
#
obj-y := virt.o
-obj-$(CONFIG_SMP) += platsmp.o
diff --git a/arch/arm/mach-virt/platsmp.c b/arch/arm/mach-virt/platsmp.c
deleted file mode 100644
index f4143f5..0000000
--- a/arch/arm/mach-virt/platsmp.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Dummy Virtual Machine - does what it says on the tin.
- *
- * Copyright (C) 2012 ARM Ltd
- * Author: Will Deacon <will.deacon@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/of.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-extern void secondary_startup(void);
-
-static void __init virt_smp_init_cpus(void)
-{
-}
-
-static void __init virt_smp_prepare_cpus(unsigned int max_cpus)
-{
-}
-
-static int __cpuinit virt_boot_secondary(unsigned int cpu,
- struct task_struct *idle)
-{
- if (psci_ops.cpu_on)
- return psci_ops.cpu_on(cpu_logical_map(cpu),
- __pa(secondary_startup));
- return -ENODEV;
-}
-
-struct smp_operations __initdata virt_smp_ops = {
- .smp_init_cpus = virt_smp_init_cpus,
- .smp_prepare_cpus = virt_smp_prepare_cpus,
- .smp_boot_secondary = virt_boot_secondary,
-};
diff --git a/arch/arm/mach-virt/virt.c b/arch/arm/mach-virt/virt.c
index 061f283..a67d2dd 100644
--- a/arch/arm/mach-virt/virt.c
+++ b/arch/arm/mach-virt/virt.c
@@ -36,11 +36,8 @@
NULL
};
-extern struct smp_operations virt_smp_ops;
-
DT_MACHINE_START(VIRT, "Dummy Virtual Machine")
.init_irq = irqchip_init,
.init_machine = virt_init,
- .smp = smp_ops(virt_smp_ops),
.dt_compat = virt_dt_match,
MACHINE_END
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 35955b5..2e71959 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -411,28 +411,31 @@
select CPU_USE_DOMAINS if MMU
select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
select TLS_REG_EMUL if SMP || !MMU
+ select NEED_KUSER_HELPERS
config CPU_32v4
bool
select CPU_USE_DOMAINS if MMU
select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
select TLS_REG_EMUL if SMP || !MMU
+ select NEED_KUSER_HELPERS
config CPU_32v4T
bool
select CPU_USE_DOMAINS if MMU
select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
select TLS_REG_EMUL if SMP || !MMU
+ select NEED_KUSER_HELPERS
config CPU_32v5
bool
select CPU_USE_DOMAINS if MMU
select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
select TLS_REG_EMUL if SMP || !MMU
+ select NEED_KUSER_HELPERS
config CPU_32v6
bool
- select CPU_USE_DOMAINS if CPU_V6 && MMU
select TLS_REG_EMUL if !CPU_32v6K && !MMU
config CPU_32v6K
@@ -647,7 +650,7 @@
config SWP_EMULATE
bool "Emulate SWP/SWPB instructions"
- depends on !CPU_USE_DOMAINS && CPU_V7
+ depends on CPU_V7
default y if SMP
select HAVE_PROC_CPU if PROC_FS
help
@@ -756,6 +759,7 @@
config TLS_REG_EMUL
bool
+ select NEED_KUSER_HELPERS
help
An SMP system using a pre-ARMv6 processor (there are apparently
a few prototypes like that in existence) and therefore access to
@@ -763,11 +767,44 @@
config NEEDS_SYSCALL_FOR_CMPXCHG
bool
+ select NEED_KUSER_HELPERS
help
SMP on a pre-ARMv6 processor? Well OK then.
Forget about fast user space cmpxchg support.
It is just not possible.
+config NEED_KUSER_HELPERS
+ bool
+
+config KUSER_HELPERS
+ bool "Enable kuser helpers in vector page" if !NEED_KUSER_HELPERS
+ depends on MMU
+ default y
+ help
+ Warning: disabling this option may break user programs.
+
+ Provide kuser helpers in the vector page. The kernel provides
+ helper code to userspace in read only form at a fixed location
+ in the high vector page to allow userspace to be independent of
+ the CPU type fitted to the system. This permits binaries to be
+ run on ARMv4 through to ARMv7 without modification.
+
+ See Documentation/arm/kernel_user_helpers.txt for details.
+
+ However, the fixed address nature of these helpers can be used
+ by ROP (return orientated programming) authors when creating
+ exploits.
+
+ If all of the binaries and libraries which run on your platform
+ are built specifically for your platform, and make no use of
+ these helpers, then you can turn this option off to hinder
+ such exploits. However, in that case, if a binary or library
+ relying on those helpers is run, it will receive a SIGILL signal,
+ which will terminate the program.
+
+ Say N here only if you are absolutely certain that you do not
+ need these helpers; otherwise, the safe option is to say Y.
+
config DMA_CACHE_RWFO
bool "Enable read/write for ownership DMA cache maintenance"
depends on CPU_V6K && SMP
@@ -895,3 +932,9 @@
help
This option allows the use of custom mandatory barriers
included via the mach/barriers.h file.
+
+config ARCH_SUPPORTS_BIG_ENDIAN
+ bool
+ help
+ This option specifies the architecture can support big endian
+ operation.
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 9e51be9..224a9cc 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -16,6 +16,7 @@
obj-$(CONFIG_ALIGNMENT_TRAP) += alignment.o
obj-$(CONFIG_HIGHMEM) += highmem.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_CPU_ABRT_NOMMU) += abort-nommu.o
obj-$(CONFIG_CPU_ABRT_EV4) += abort-ev4.o
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8074199..8c48c5c 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -17,12 +17,6 @@
*/
.align 5
ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
- sub r1, sp, #4 @ Get unused stack location
- strex r0, r1, [r1] @ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
- clrex
-#endif
mrc p15, 0, r1, c5, c0, 0 @ get FSR
mrc p15, 0, r0, c6, c0, 0 @ get FAR
/*
@@ -38,9 +32,8 @@
bne do_DataAbort
bic r1, r1, #1 << 11 @ clear bit 11 of FSR
ldr r3, [r4] @ read aborted ARM instruction
-#ifdef CONFIG_CPU_ENDIAN_BE8
- rev r3, r3
-#endif
+ ARM_BE8(rev r3, r3)
+
do_ldrd_abort tmp=ip, insn=r3
tst r3, #1 << 20 @ L = 0 -> write
orreq r1, r1, #1 << 11 @ yes.
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 7033752..4812ad0 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -13,12 +13,6 @@
*/
.align 5
ENTRY(v7_early_abort)
- /*
- * The effect of data aborts on on the exclusive access monitor are
- * UNPREDICTABLE. Do a CLREX to clear the state
- */
- clrex
-
mrc p15, 0, r1, c5, c0, 0 @ get FSR
mrc p15, 0, r0, c6, c0, 0 @ get FAR
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f4585b..d301662 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -25,6 +25,7 @@
#include <asm/cp15.h>
#include <asm/system_info.h>
#include <asm/unaligned.h>
+#include <asm/opcodes.h>
#include "fault.h"
@@ -39,6 +40,7 @@
* This code is not portable to processors with late data abort handling.
*/
#define CODING_BITS(i) (i & 0x0e000000)
+#define COND_BITS(i) (i & 0xf0000000)
#define LDST_I_BIT(i) (i & (1 << 26)) /* Immediate constant */
#define LDST_P_BIT(i) (i & (1 << 24)) /* Preindex */
@@ -762,21 +764,25 @@
if (thumb_mode(regs)) {
u16 *ptr = (u16 *)(instrptr & ~1);
fault = probe_kernel_address(ptr, tinstr);
+ tinstr = __mem_to_opcode_thumb16(tinstr);
if (!fault) {
if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
IS_T32(tinstr)) {
/* Thumb-2 32-bit */
u16 tinst2 = 0;
fault = probe_kernel_address(ptr + 1, tinst2);
- instr = (tinstr << 16) | tinst2;
+ tinst2 = __mem_to_opcode_thumb16(tinst2);
+ instr = __opcode_thumb32_compose(tinstr, tinst2);
thumb2_32b = 1;
} else {
isize = 2;
instr = thumb2arm(tinstr);
}
}
- } else
+ } else {
fault = probe_kernel_address(instrptr, instr);
+ instr = __mem_to_opcode_arm(instr);
+ }
if (fault) {
type = TYPE_FAULT;
@@ -812,6 +818,8 @@
break;
case 0x04000000: /* ldr or str immediate */
+ if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+ goto bad;
offset.un = OFFSET_BITS(instr);
handler = do_alignment_ldrstr;
break;
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 515b000..a84e053 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -146,18 +146,18 @@
ldr r7, =0x7fff
ands r7, r7, r1, lsr #13 @ extract max number of the index size
loop1:
- mov r9, r4 @ create working copy of max way size
+ mov r9, r7 @ create working copy of max index
loop2:
- ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11
- THUMB( lsl r6, r9, r5 )
+ ARM( orr r11, r10, r4, lsl r5 ) @ factor way and cache number into r11
+ THUMB( lsl r6, r4, r5 )
THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11
- ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11
- THUMB( lsl r6, r7, r2 )
+ ARM( orr r11, r11, r9, lsl r2 ) @ factor index number into r11
+ THUMB( lsl r6, r9, r2 )
THUMB( orr r11, r11, r6 ) @ factor index number into r11
mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way
- subs r9, r9, #1 @ decrement the way
+ subs r9, r9, #1 @ decrement the index
bge loop2
- subs r7, r7, #1 @ decrement the index
+ subs r4, r4, #1 @ decrement the way
bge loop1
skip:
add r10, r10, #2 @ increment cache number
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 2ac3737..eeab06e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -39,19 +39,43 @@
* non 64-bit operations.
*/
#define ASID_FIRST_VERSION (1ULL << ASID_BITS)
-#define NUM_USER_ASIDS (ASID_FIRST_VERSION - 1)
-
-#define ASID_TO_IDX(asid) ((asid & ~ASID_MASK) - 1)
-#define IDX_TO_ASID(idx) ((idx + 1) & ~ASID_MASK)
+#define NUM_USER_ASIDS ASID_FIRST_VERSION
static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
static DEFINE_PER_CPU(u64, reserved_asids);
static cpumask_t tlb_flush_pending;
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+ cpumask_t *mask)
+{
+ int cpu;
+ unsigned long flags;
+ u64 context_id, asid;
+
+ raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+ context_id = mm->context.id.counter;
+ for_each_online_cpu(cpu) {
+ if (cpu == this_cpu)
+ continue;
+ /*
+ * We only need to send an IPI if the other CPUs are
+ * running the same ASID as the one being invalidated.
+ */
+ asid = per_cpu(active_asids, cpu).counter;
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, cpu);
+ if (context_id == asid)
+ cpumask_set_cpu(cpu, mask);
+ }
+ raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
#ifdef CONFIG_ARM_LPAE
static void cpu_set_reserved_ttbr0(void)
{
@@ -128,7 +152,16 @@
asid = 0;
} else {
asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
- __set_bit(ASID_TO_IDX(asid), asid_map);
+ /*
+ * If this CPU has already been through a
+ * rollover, but hasn't run another task in
+ * the meantime, we must preserve its reserved
+ * ASID, as this is the only trace we have of
+ * the process it is still running.
+ */
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, i);
+ __set_bit(asid & ~ASID_MASK, asid_map);
}
per_cpu(reserved_asids, i) = asid;
}
@@ -167,17 +200,19 @@
/*
* Allocate a free ASID. If we can't find one, take a
* note of the currently active ASIDs and mark the TLBs
- * as requiring flushes.
+ * as requiring flushes. We always count from ASID #1,
+ * as we reserve ASID #0 to switch via TTBR0 and indicate
+ * rollover events.
*/
- asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
if (asid == NUM_USER_ASIDS) {
generation = atomic64_add_return(ASID_FIRST_VERSION,
&asid_generation);
flush_context(cpu);
- asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
}
__set_bit(asid, asid_map);
- asid = generation | IDX_TO_ASID(asid);
+ asid |= generation;
cpumask_clear(mm_cpumask(mm));
}
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ef3e0f3..f7cc937 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -250,7 +250,7 @@
#ifdef CONFIG_MMU
#ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#warning ARM Coherent DMA allocator does not (yet) support huge TLB
#endif
static void *__alloc_from_contiguous(struct device *dev, size_t size,
@@ -265,37 +265,19 @@
__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
const void *caller)
{
- struct vm_struct *area;
- unsigned long addr;
-
/*
* DMA allocation can be mapped to user space, so lets
* set VM_USERMAP flags too.
*/
- area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
- caller);
- if (!area)
- return NULL;
- addr = (unsigned long)area->addr;
- area->phys_addr = __pfn_to_phys(page_to_pfn(page));
-
- if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
- vunmap((void *)addr);
- return NULL;
- }
- return (void *)addr;
+ return dma_common_contiguous_remap(page, size,
+ VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+ prot, caller);
}
static void __dma_free_remap(void *cpu_addr, size_t size)
{
- unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
- struct vm_struct *area = find_vm_area(cpu_addr);
- if (!area || (area->flags & flags) != flags) {
- WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
- return;
- }
- unmap_kernel_range((unsigned long)cpu_addr, size);
- vunmap(cpu_addr);
+ dma_common_free_remap(cpu_addr, size,
+ VM_ARM_DMA_CONSISTENT | VM_USERMAP);
}
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
@@ -358,7 +340,7 @@
if (!pages)
goto no_pages;
- if (IS_ENABLED(CONFIG_CMA))
+ if (IS_ENABLED(CONFIG_DMA_CMA))
ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
atomic_pool_init);
else
@@ -429,12 +411,21 @@
map.type = MT_MEMORY_DMA_READY;
/*
- * Clear previous low-memory mapping
+ * Clear previous low-memory mapping to ensure that the
+ * TLB does not see any conflicting entries, then flush
+ * the TLB of the old entries before creating new mappings.
+ *
+ * This ensures that any speculatively loaded TLB entries
+ * (even though they may be rare) can not cause any problems,
+ * and ensures that this code is architecturally compliant.
*/
for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
+ flush_tlb_kernel_range(__phys_to_virt(start),
+ __phys_to_virt(end));
+
iotable_init(&map, 1);
}
}
@@ -670,7 +661,7 @@
addr = __alloc_simple_buffer(dev, size, gfp, &page);
else if (!(gfp & __GFP_WAIT))
addr = __alloc_from_pool(size, &page);
- else if (!IS_ENABLED(CONFIG_CMA))
+ else if (!IS_ENABLED(CONFIG_DMA_CMA))
addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
else
addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -759,7 +750,7 @@
__dma_free_buffer(page, size);
} else if (__free_from_pool(cpu_addr, size)) {
return;
- } else if (!IS_ENABLED(CONFIG_CMA)) {
+ } else if (!IS_ENABLED(CONFIG_DMA_CMA)) {
__dma_free_remap(cpu_addr, size);
__dma_free_buffer(page, size);
} else {
@@ -1167,29 +1158,8 @@
__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
const void *caller)
{
- unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
- struct vm_struct *area;
- unsigned long p;
-
- area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
- caller);
- if (!area)
- return NULL;
-
- area->pages = pages;
- area->nr_pages = nr_pages;
- p = (unsigned long)area->addr;
-
- for (i = 0; i < nr_pages; i++) {
- phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
- if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
- goto err;
- p += PAGE_SIZE;
- }
- return area->addr;
-err:
- unmap_kernel_range((unsigned long)area->addr, size);
- vunmap(area->addr);
+ return dma_common_pages_remap(pages, size,
+ VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
return NULL;
}
@@ -1311,7 +1281,7 @@
*handle = DMA_ERROR_CODE;
size = PAGE_ALIGN(size);
- if (gfp & GFP_ATOMIC)
+ if (!(gfp & __GFP_WAIT))
return __iommu_alloc_atomic(dev, size, handle);
pages = __iommu_alloc_buffer(dev, size, gfp, attrs);
@@ -1386,8 +1356,8 @@
}
if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
- unmap_kernel_range((unsigned long)cpu_addr, size);
- vunmap(cpu_addr);
+ dma_common_free_remap(cpu_addr, size,
+ VM_ARM_DMA_CONSISTENT | VM_USERMAP);
}
__iommu_remove_mapping(dev, handle, size);
diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c
index 9d28562..312e15e 100644
--- a/arch/arm/mm/extable.c
+++ b/arch/arm/mm/extable.c
@@ -9,8 +9,13 @@
const struct exception_table_entry *fixup;
fixup = search_exception_tables(instruction_pointer(regs));
- if (fixup)
+ if (fixup) {
regs->ARM_pc = fixup->fixup;
+#ifdef CONFIG_THUMB2_KERNEL
+ /* Clear the IT state to avoid nasty surprises in the fixup */
+ regs->ARM_cpsr &= ~PSR_IT_MASK;
+#endif
+ }
return fixup != NULL;
}
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 5dbf13f..54fcdda 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -261,9 +261,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- int write = fsr & FSR_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, fsr))
return 0;
@@ -282,6 +280,11 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (fsr & FSR_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -349,6 +352,13 @@
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -359,13 +369,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
@@ -446,8 +449,16 @@
if (pud_none(*pud_k))
goto bad_area;
- if (!pud_present(*pud))
+ if (!pud_present(*pud)) {
set_pud(pud, *pud_k);
+ /*
+ * There is a small window during free_pgtables() where the
+ * user *pud entry is 0 but the TLB has not been invalidated
+ * and we get a level 2 (pmd) translation fault caused by the
+ * intermediate TLB caching of the old level 1 (pud) entry.
+ */
+ flush_tlb_kernel_page(addr);
+ }
pmd = pmd_offset(pud, addr);
pmd_k = pmd_offset(pud_k, addr);
@@ -470,8 +481,9 @@
#endif
if (pmd_none(pmd_k[index]))
goto bad_area;
+ if (!pmd_present(pmd[index]))
+ copy_pmd(pmd, pmd_k);
- copy_pmd(pmd, pmd_k);
return 0;
bad_area:
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 32aa586..c9e37aa 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
#include <asm/highmem.h>
#include <asm/smp_plat.h>
#include <asm/tlbflush.h>
+#include <linux/hugetlb.h>
#include "mm.h"
@@ -168,19 +169,23 @@
* coherent with the kernels mapping.
*/
if (!PageHighMem(page)) {
- __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
+ size_t page_size = PAGE_SIZE << compound_order(page);
+ __cpuc_flush_dcache_area(page_address(page), page_size);
} else {
- void *addr;
-
+ unsigned long i;
if (cache_is_vipt_nonaliasing()) {
- addr = kmap_atomic(page);
- __cpuc_flush_dcache_area(addr, PAGE_SIZE);
- kunmap_atomic(addr);
- } else {
- addr = kmap_high_get(page);
- if (addr) {
+ for (i = 0; i < (1 << compound_order(page)); i++) {
+ void *addr = kmap_atomic(page);
__cpuc_flush_dcache_area(addr, PAGE_SIZE);
- kunmap_high(page);
+ kunmap_atomic(addr);
+ }
+ } else {
+ for (i = 0; i < (1 << compound_order(page)); i++) {
+ void *addr = kmap_high_get(page);
+ if (addr) {
+ __cpuc_flush_dcache_area(addr, PAGE_SIZE);
+ kunmap_high(page);
+ }
}
}
}
diff --git a/arch/arm/mm/fsr-3level.c b/arch/arm/mm/fsr-3level.c
index 05a4e94..ab4409a 100644
--- a/arch/arm/mm/fsr-3level.c
+++ b/arch/arm/mm/fsr-3level.c
@@ -9,11 +9,11 @@
{ do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "reserved access flag fault" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
{ do_bad, SIGBUS, 0, "reserved permission fault" },
{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
- { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
{ do_bad, SIGBUS, 0, "synchronous external abort" },
{ do_bad, SIGBUS, 0, "asynchronous external abort" },
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
new file mode 100644
index 0000000..3d1e4a2
--- /dev/null
+++ b/arch/arm/mm/hugetlbpage.c
@@ -0,0 +1,101 @@
+/*
+ * arch/arm/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+/*
+ * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot
+ * of type casting from pmd_t * to pte_t *.
+ */
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_present(*pgd)) {
+ pud = pud_offset(pgd, addr);
+ if (pud_present(*pud))
+ pmd = pmd_offset(pud, addr);
+ }
+
+ return (pte_t *)pmd;
+}
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+ int write)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+int pud_huge(pud_t pud)
+{
+ return 0;
+}
+
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+ return 0;
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pte_t *pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ pud = pud_alloc(mm, pgd, addr);
+ if (pud)
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+
+ return pte;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+ pmd_t *pmd, int write)
+{
+ struct page *page;
+
+ page = pte_page(*(pte_t *)pmd);
+ if (page)
+ page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+ return page;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+ return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 83cb3ac..9908373 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -10,6 +10,7 @@
#include <asm/system_info.h>
pgd_t *idmap_pgd;
+phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
#ifdef CONFIG_ARM_LPAE
static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
@@ -24,6 +25,13 @@
pr_warning("Failed to allocate identity pmd.\n");
return;
}
+ /*
+ * Copy the original PMD to ensure that the PMD entries for
+ * the kernel image are preserved.
+ */
+ if (!pud_none(*pud))
+ memcpy(pmd, pmd_offset(pud, 0),
+ PTRS_PER_PMD * sizeof(pmd_t));
pud_populate(&init_mm, pud, pmd);
pmd += pmd_index(addr);
} else
@@ -67,8 +75,8 @@
unsigned long addr, end;
unsigned long next;
- addr = virt_to_phys(text_start);
- end = virt_to_phys(text_end);
+ addr = virt_to_idmap(text_start);
+ end = virt_to_idmap(text_end);
prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 9a5cdc0..c12ae66 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -76,7 +76,7 @@
__tagtable(ATAG_INITRD2, parse_tag_initrd2);
#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start, unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
phys_initrd_start = start;
phys_initrd_size = end - start;
@@ -600,7 +600,7 @@
#ifdef CONFIG_SA1111
/* now that our DMA memory is actually so designated, we can free it */
- free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL);
+ free_reserved_area(__va(PHYS_OFFSET), swapper_pg_dir, 0, NULL);
#endif
free_highpages();
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 04d9006..f123d6e 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -331,10 +331,10 @@
return (void __iomem *) (offset + addr);
}
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
- unsigned long last_addr;
+ phys_addr_t last_addr;
unsigned long offset = phys_addr & ~PAGE_MASK;
unsigned long pfn = __phys_to_pfn(phys_addr);
@@ -367,12 +367,12 @@
}
EXPORT_SYMBOL(__arm_ioremap_pfn);
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t,
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
unsigned int, void *) =
__arm_ioremap_caller;
void __iomem *
-__arm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
+__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
{
return arch_ioremap_caller(phys_addr, size, mtype,
__builtin_return_address(0));
@@ -387,7 +387,7 @@
* CONFIG_GENERIC_ALLOCATOR for allocating external memory.
*/
void __iomem *
-__arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
+__arm_ioremap_exec(phys_addr_t phys_addr, size_t size, bool cached)
{
unsigned int mtype;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 10062ce..5ef506c 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -146,7 +146,7 @@
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
- info.low_limit = PAGE_SIZE;
+ info.low_limit = FIRST_USER_ADDRESS;
info.high_limit = mm->mmap_base;
info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
info.align_offset = pgoff << PAGE_SHIFT;
@@ -204,13 +204,11 @@
}
/*
- * We don't use supersection mappings for mmap() on /dev/mem, which
- * means that we can't map the memory area above the 4G barrier into
- * userspace.
+ * Do not allow /dev/mem mappings beyond the supported physical range.
*/
int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
- return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
+ return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
}
#ifdef CONFIG_STRICT_DEVMEM
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 4d409e6..4c7d5cd 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -459,6 +459,16 @@
hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte;
/*
+ * We don't use domains on ARMv6 (since this causes problems with
+ * v6/v7 kernels), so we must use a separate memory type for user
+ * r/o, kernel r/w to map the vectors page.
+ */
+#ifndef CONFIG_ARM_LPAE
+ if (cpu_arch == CPU_ARCH_ARMv6)
+ vecs_pgprot |= L_PTE_MT_VECTORS;
+#endif
+
+ /*
* ARMv6 and above have extended page tables.
*/
if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
@@ -675,7 +685,8 @@
}
static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
- unsigned long end, unsigned long phys, const struct mem_type *type)
+ unsigned long end, phys_addr_t phys,
+ const struct mem_type *type)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
@@ -1175,7 +1186,7 @@
/*
* Allocate the vector page early.
*/
- vectors = early_alloc(PAGE_SIZE);
+ vectors = early_alloc(PAGE_SIZE * 2);
early_trap_init(vectors);
@@ -1220,15 +1231,27 @@
map.pfn = __phys_to_pfn(virt_to_phys(vectors));
map.virtual = 0xffff0000;
map.length = PAGE_SIZE;
+#ifdef CONFIG_KUSER_HELPERS
map.type = MT_HIGH_VECTORS;
+#else
+ map.type = MT_LOW_VECTORS;
+#endif
create_mapping(&map);
if (!vectors_high()) {
map.virtual = 0;
+ map.length = PAGE_SIZE * 2;
map.type = MT_LOW_VECTORS;
create_mapping(&map);
}
+ /* Now create a kernel read-only mapping */
+ map.pfn += 1;
+ map.virtual = 0xffff0000 + PAGE_SIZE;
+ map.length = PAGE_SIZE;
+ map.type = MT_LOW_VECTORS;
+ create_mapping(&map);
+
/*
* Ask the machine support to map in the statically mapped devices.
*/
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index eb5293a..7fe0524 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -87,16 +87,16 @@
return __arm_ioremap_pfn(pfn, offset, size, mtype);
}
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
unsigned int mtype)
{
return (void __iomem *)phys_addr;
}
EXPORT_SYMBOL(__arm_ioremap);
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
unsigned int mtype, void *caller)
{
return __arm_ioremap(phys_addr, size, mtype);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 0acb089..1046b37 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -87,7 +87,8 @@
init_pud = pud_offset(init_pgd, 0);
init_pmd = pmd_offset(init_pud, 0);
init_pte = pte_offset_map(init_pmd, 0);
- set_pte_ext(new_pte, *init_pte, 0);
+ set_pte_ext(new_pte + 0, init_pte[0], 0);
+ set_pte_ext(new_pte + 1, init_pte[1], 0);
pte_unmap(init_pte);
pte_unmap(new_pte);
}
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e3c48a3..ee1d805 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -112,13 +112,9 @@
* 100x 1 0 1 r/o no acc
* 10x0 1 0 1 r/o no acc
* 1011 0 0 1 r/w no acc
- * 110x 0 1 0 r/w r/o
- * 11x0 0 1 0 r/w r/o
- * 1111 0 1 1 r/w r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
* 110x 1 1 1 r/o r/o
* 11x0 1 1 1 r/o r/o
+ * 1111 0 1 1 r/w r/w
*/
.macro armv6_mt_table pfx
\pfx\()_mt_table:
@@ -137,7 +133,7 @@
.long PTE_EXT_TEX(2) @ L_PTE_MT_DEV_NONSHARED
.long 0x00 @ unused
.long 0x00 @ unused
- .long 0x00 @ unused
+ .long PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX @ L_PTE_MT_VECTORS
.endm
.macro armv6_set_pte_ext pfx
@@ -158,24 +154,21 @@
tst r1, #L_PTE_USER
orrne r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
- @ allow kernel read/write access to read-only user pages
tstne r3, #PTE_EXT_APX
- bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+ @ user read-only -> kernel read-only
+ bicne r3, r3, #PTE_EXT_AP0
tst r1, #L_PTE_XN
orrne r3, r3, #PTE_EXT_XN
- orr r3, r3, r2
+ eor r3, r3, r2
tst r1, #L_PTE_YOUNG
tstne r1, #L_PTE_PRESENT
moveq r3, #0
-#ifndef CONFIG_CPU_USE_DOMAINS
tstne r1, #L_PTE_NONE
movne r3, #0
-#endif
str r3, [r0]
mcr p15, 0, r0, c7, c10, 1 @ flush_pte
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 919405e..b96c6e6 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -206,7 +206,6 @@
mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache
mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache
mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache
- mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
#ifdef CONFIG_MMU
mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs
mcr p15, 0, r0, c2, c0, 2 @ TTB control register
@@ -216,11 +215,11 @@
ALT_UP(orr r8, r8, #TTB_FLAGS_UP)
mcr p15, 0, r8, c2, c0, 1 @ load TTB1
#endif /* CONFIG_MMU */
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and
+ @ complete invalidations
adr r5, v6_crval
ldmia r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
- orr r6, r6, #1 << 25 @ big-endian page tables
-#endif
+ ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
mrc p15, 0, r0, c1, c0, 0 @ read control register
bic r0, r0, r5 @ clear bits them
orr r0, r0, r6 @ set them
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 9704097..bb20ba0 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -90,27 +90,20 @@
tst r1, #L_PTE_USER
orrne r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
- @ allow kernel read/write access to read-only user pages
- tstne r3, #PTE_EXT_APX
- bicne r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
tst r1, #L_PTE_XN
orrne r3, r3, #PTE_EXT_XN
tst r1, #L_PTE_YOUNG
tstne r1, #L_PTE_VALID
-#ifndef CONFIG_CPU_USE_DOMAINS
eorne r1, r1, #L_PTE_NONE
tstne r1, #L_PTE_NONE
-#endif
moveq r3, #0
ARM( str r3, [r0, #2048]! )
THUMB( add r0, r0, #2048 )
THUMB( str r3, [r0] )
- ALT_SMP(mov pc,lr)
+ ALT_SMP(W(nop))
ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte
#endif
mov pc, lr
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 363027e..110e738 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -56,6 +56,14 @@
mov pc, lr
ENDPROC(cpu_v7_switch_mm)
+#ifdef __ARMEB__
+#define rl r3
+#define rh r2
+#else
+#define rl r2
+#define rh r3
+#endif
+
/*
* cpu_v7_set_pte_ext(ptep, pte)
*
@@ -65,15 +73,20 @@
*/
ENTRY(cpu_v7_set_pte_ext)
#ifdef CONFIG_MMU
- tst r2, #L_PTE_VALID
+ tst rl, #L_PTE_VALID
beq 1f
- tst r3, #1 << (57 - 32) @ L_PTE_NONE
- bicne r2, #L_PTE_VALID
+ tst rh, #1 << (57 - 32) @ L_PTE_NONE
+ bicne rl, #L_PTE_VALID
bne 1f
- tst r3, #1 << (55 - 32) @ L_PTE_DIRTY
- orreq r2, #L_PTE_RDONLY
+
+ eor ip, rh, #1 << (55 - 32) @ toggle L_PTE_DIRTY in temp reg to
+ @ test for !L_PTE_DIRTY || L_PTE_RDONLY
+ tst ip, #1 << (55 - 32) | 1 << (58 - 32)
+ orrne rl, #PTE_AP2
+ biceq rl, #PTE_AP2
+
1: strd r2, r3, [r0]
- ALT_SMP(mov pc, lr)
+ ALT_SMP(W(nop))
ALT_UP (mcr p15, 0, r0, c7, c10, 1) @ flush_pte
#endif
mov pc, lr
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index e35fec3..50c9943 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -75,13 +75,14 @@
ENDPROC(cpu_v7_do_idle)
ENTRY(cpu_v7_dcache_clean_area)
- ALT_SMP(mov pc, lr) @ MP extensions imply L1 PTW
- ALT_UP(W(nop))
- dcache_line_size r2, r3
-1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
+ ALT_SMP(W(nop)) @ MP extensions imply L1 PTW
+ ALT_UP_B(1f)
+ mov pc, lr
+1: dcache_line_size r2, r3
+2: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
add r0, r0, r2
subs r1, r1, r2
- bhi 1b
+ bhi 2b
dsb
mov pc, lr
ENDPROC(cpu_v7_dcache_clean_area)
@@ -200,7 +201,6 @@
/* Auxiliary Debug Modes Control 1 Register */
#define PJ4B_STATIC_BP (1 << 2) /* Enable Static BP */
#define PJ4B_INTER_PARITY (1 << 8) /* Disable Internal Parity Handling */
-#define PJ4B_BCK_OFF_STREX (1 << 5) /* Enable the back off of STREX instr */
#define PJ4B_CLEAN_LINE (1 << 16) /* Disable data transfer for clean line */
/* Auxiliary Debug Modes Control 2 Register */
@@ -223,7 +223,6 @@
/* Auxiliary Debug Modes Control 1 Register */
mrc p15, 1, r0, c15, c1, 1
orr r0, r0, #PJ4B_CLEAN_LINE
- orr r0, r0, #PJ4B_BCK_OFF_STREX
orr r0, r0, #PJ4B_INTER_PARITY
bic r0, r0, #PJ4B_STATIC_BP
mcr p15, 1, r0, c15, c1, 1
@@ -328,7 +327,6 @@
3: mov r10, #0
mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate
- dsb
#ifdef CONFIG_MMU
mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs
v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup
@@ -337,6 +335,7 @@
mcr p15, 0, r5, c10, c2, 0 @ write PRRR
mcr p15, 0, r6, c10, c2, 1 @ write NMRR
#endif
+ dsb @ Complete invalidations
#ifndef CONFIG_ARM_THUMBEE
mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE
and r0, r0, #(0xf << 12) @ ThumbEE enabled field
@@ -351,9 +350,7 @@
#endif
adr r5, v7_crval
ldmia r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
- orr r6, r6, #1 << 25 @ big-endian page tables
-#endif
+ ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables
#ifdef CONFIG_SWP_EMULATE
orr r5, r5, #(1 << 10) @ set SW bit in "clear"
bic r6, r6, #(1 << 10) @ clear it in "mmuset"
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index e766f88..08b51b7 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -535,7 +535,7 @@
mrc p15, 0, r5, c15, c1, 0 @ CP access reg
mrc p15, 0, r6, c13, c0, 0 @ PID
mrc p15, 0, r7, c3, c0, 0 @ domain ID
- mrc p15, 0, r8, c1, c1, 0 @ auxiliary control reg
+ mrc p15, 0, r8, c1, c0, 1 @ auxiliary control reg
mrc p15, 0, r9, c1, c0, 0 @ control reg
bic r4, r4, #2 @ clear frequency change bit
stmia r0, {r4 - r9} @ store cp regs
@@ -552,7 +552,7 @@
mcr p15, 0, r6, c13, c0, 0 @ PID
mcr p15, 0, r7, c3, c0, 0 @ domain ID
mcr p15, 0, r1, c2, c0, 0 @ translation table base addr
- mcr p15, 0, r8, c1, c1, 0 @ auxiliary control reg
+ mcr p15, 0, r8, c1, c0, 1 @ auxiliary control reg
mov r0, r9 @ control register
b cpu_resume_mmu
ENDPROC(cpu_xscale_do_resume)
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 1a643ee..78351ca 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -19,6 +19,7 @@
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
#include <asm/hwcap.h>
+#include <asm/opcodes.h>
#include "bpf_jit_32.h"
@@ -113,8 +114,11 @@
static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
{
+ inst |= (cond << 28);
+ inst = __opcode_to_mem_arm(inst);
+
if (ctx->target != NULL)
- ctx->target[ctx->idx] = inst | (cond << 28);
+ ctx->target[ctx->idx] = inst;
ctx->idx++;
}
@@ -637,10 +641,10 @@
emit(ARM_MUL(r_A, r_A, r_X), ctx);
break;
case BPF_S_ALU_DIV_K:
- /* current k == reciprocal_value(userspace k) */
+ if (k == 1)
+ break;
emit_mov_i(r_scratch, k, ctx);
- /* A = top 32 bits of the product */
- emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+ emit_udiv(r_A, r_A, r_scratch, ctx);
break;
case BPF_S_ALU_DIV_X:
update_on_xread(ctx);
diff --git a/arch/arm/plat-samsung/include/plat/clock.h b/arch/arm/plat-samsung/include/plat/clock.h
index a62753d..df45d6e 100644
--- a/arch/arm/plat-samsung/include/plat/clock.h
+++ b/arch/arm/plat-samsung/include/plat/clock.h
@@ -83,6 +83,11 @@
extern struct clksrc_clk clk_epllref;
extern struct clksrc_clk clk_esysclk;
+/* S3C24XX UART clocks */
+extern struct clk s3c24xx_clk_uart0;
+extern struct clk s3c24xx_clk_uart1;
+extern struct clk s3c24xx_clk_uart2;
+
/* S3C64XX specific clocks */
extern struct clk clk_h2;
extern struct clk clk_27m;
diff --git a/arch/arm/plat-samsung/s5p-dev-mfc.c b/arch/arm/plat-samsung/s5p-dev-mfc.c
index a93fb6f..586ca73 100644
--- a/arch/arm/plat-samsung/s5p-dev-mfc.c
+++ b/arch/arm/plat-samsung/s5p-dev-mfc.c
@@ -116,8 +116,8 @@
int __init s5p_fdt_find_mfc_mem(unsigned long node, const char *uname,
int depth, void *data)
{
- __be32 *prop;
- unsigned long len;
+ const __be32 *prop;
+ int len;
struct s5p_mfc_dt_meminfo *mfc_mem = data;
if (!data)
diff --git a/arch/arm/plat-versatile/headsmp.S b/arch/arm/plat-versatile/headsmp.S
index b178d44..40f27e5 100644
--- a/arch/arm/plat-versatile/headsmp.S
+++ b/arch/arm/plat-versatile/headsmp.S
@@ -10,8 +10,7 @@
*/
#include <linux/linkage.h>
#include <linux/init.h>
-
- __INIT
+#include <asm/assembler.h>
/*
* Realview/Versatile Express specific entry point for secondary CPUs.
@@ -19,6 +18,7 @@
* until we're ready for them to initialise.
*/
ENTRY(versatile_secondary_startup)
+ ARM_BE8(setend be)
mrc p15, 0, r0, c0, c0, 5
bic r0, #0xff000000
adr r4, 1f
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 13609e0..81edd31 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -170,6 +170,7 @@
per_cpu(xen_vcpu, cpu) = vcpup;
enable_percpu_irq(xen_events_irq, 0);
+ put_cpu();
}
static void xen_restart(char str, const char *cmd)
@@ -272,12 +273,15 @@
static int __init xen_pm_init(void)
{
+ if (!xen_domain())
+ return -ENODEV;
+
pm_power_off = xen_power_off;
arm_pm_restart = xen_restart;
return 0;
}
-subsys_initcall(xen_pm_init);
+late_initcall(xen_pm_init);
static irqreturn_t xen_arm_callback(int irq, void *arg)
{
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 50d0900..9742106 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,36 +1,67 @@
config ARM64
def_bool y
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+ select ARCH_HAS_OPP
+ select ARCH_USE_CMPXCHG_LOCKREF
+ select ARCH_HAS_OPP
+ select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+ select ARCH_SUPPORTS_ATOMIC_RMW
+ select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
select ARCH_WANT_FRAME_POINTERS
select ARM_AMBA
select ARM_ARCH_TIMER
select ARM_GIC
+ select ARM_GIC_V3
+ select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
select COMMON_CLK
+ select CPU_PM if (SUSPEND || CPU_IDLE)
+ select DCACHE_WORD_ACCESS
+ select GENERIC_ALLOCATOR
select GENERIC_CLOCKEVENTS
+ select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+ select GENERIC_CPU_AUTOPROBE
+ select GENERIC_EARLY_IOREMAP
select GENERIC_IOMAP
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_SMP_IDLE_THREAD
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL
select HARDIRQS_SW_RESEND
+ select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
+ select HAVE_C_RECORDMCOUNT
+ select HAVE_CC_STACKPROTECTOR
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_API_DEBUG
select HAVE_DMA_ATTRS
+ select HAVE_DMA_CONTIGUOUS
+ select HAVE_DYNAMIC_FTRACE
+ select HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FUNCTION_TRACER
+ select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_GENERIC_DMA_COHERENT
select HAVE_GENERIC_HARDIRQS
select HAVE_HW_BREAKPOINT if PERF_EVENTS
select HAVE_MEMBLOCK
+ select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
+ select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_SYSCALL_TRACEPOINTS
select IRQ_DOMAIN
select MODULES_USE_ELF_RELA
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
+ select OF_RESERVED_MEM
select PERF_USE_VMALLOC
select POWER_RESET
select POWER_SUPPLY
@@ -61,11 +92,7 @@
config TRACE_IRQFLAGS_SUPPORT
def_bool y
-config GENERIC_LOCKBREAK
- def_bool y
- depends on SMP && PREEMPT
-
-config RWSEM_GENERIC_SPINLOCK
+config RWSEM_XCHGADD_ALGORITHM
def_bool y
config GENERIC_HWEIGHT
@@ -77,7 +104,7 @@
config GENERIC_CALIBRATE_DELAY
def_bool y
-config ZONE_DMA32
+config ZONE_DMA
def_bool y
config ARCH_DMA_ADDR_T_64BIT
@@ -95,6 +122,9 @@
config IOMMU_HELPER
def_bool SWIOTLB
+config FIX_EARLYCON_MEM
+ def_bool y
+
source "init/Kconfig"
source "kernel/Kconfig.freezer"
@@ -111,6 +141,11 @@
This enables support for the ARMv8 software model (Versatile
Express).
+config ARCH_XGENE
+ bool "AppliedMicro X-Gene SOC Family"
+ help
+ This enables support for AppliedMicro X-Gene SOC Family
+
endmenu
menu "Bus support"
@@ -156,6 +191,11 @@
look-up. AArch32 emulation is not available when this feature
is enabled.
+config CPU_BIG_ENDIAN
+ bool "Build big-endian kernel"
+ help
+ Say Y if you plan on running a kernel in big-endian mode.
+
config SMP
bool "Symmetric Multi-Processing"
select USE_GENERIC_SMP_HELPERS
@@ -170,11 +210,131 @@
If you don't know what to do here, say N.
+config SCHED_MC
+ bool "Multi-core scheduler support"
+ depends on SMP
+ help
+ Multi-core scheduler support improves the CPU scheduler's decision
+ making when dealing with multi-core CPU chips at a cost of slightly
+ increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+ bool "SMT scheduler support"
+ depends on SMP
+ help
+ Improves the CPU scheduler's decision making when dealing with
+ MultiThreading at a cost of slightly increased overhead in some
+ places. If unsure say N here.
+
+config DISABLE_CPU_SCHED_DOMAIN_BALANCE
+ bool "(EXPERIMENTAL) Disable CPU level scheduler load-balancing"
+ help
+ Disables scheduler load-balancing at CPU sched domain level.
+
+config SCHED_HMP
+ bool "(EXPERIMENTAL) Heterogenous multiprocessor scheduling"
+ depends on DISABLE_CPU_SCHED_DOMAIN_BALANCE && SCHED_MC && FAIR_GROUP_SCHED && !SCHED_AUTOGROUP
+ help
+ Experimental scheduler optimizations for heterogeneous platforms.
+ Attempts to introspectively select task affinity to optimize power
+ and performance. Basic support for multiple (>2) cpu types is in place,
+ but it has only been tested with two types of cpus.
+ There is currently no support for migration of task groups, hence
+ !SCHED_AUTOGROUP. Furthermore, normal load-balancing must be disabled
+ between cpus of different type (DISABLE_CPU_SCHED_DOMAIN_BALANCE).
+
+config SCHED_HMP_PRIO_FILTER
+ bool "(EXPERIMENTAL) Filter HMP migrations by task priority"
+ depends on SCHED_HMP
+ help
+ Enables task priority based HMP migration filter. Any task with
+ a NICE value above the threshold will always be on low-power cpus
+ with less compute capacity.
+
+config SCHED_HMP_PRIO_FILTER_VAL
+ int "NICE priority threshold"
+ default 5
+ depends on SCHED_HMP_PRIO_FILTER
+
+config HMP_FAST_CPU_MASK
+ string "HMP scheduler fast CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the fast CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_SLOW_CPU_MASK
+ string "HMP scheduler slow CPU mask"
+ depends on SCHED_HMP
+ help
+ Leave empty to use device tree information.
+ Specify the cpuids of the slow CPUs in the system as a list string,
+ e.g. cpuid 0+1 should be specified as 0-1.
+
+config HMP_VARIABLE_SCALE
+ bool "Allows changing the load tracking scale through sysfs"
+ depends on SCHED_HMP
+ help
+ When turned on, this option exports the thresholds and load average
+ period value for the load tracking patches through sysfs.
+ The values can be modified to change the rate of load accumulation
+ and the thresholds used for HMP migration.
+ The load_avg_period_ms is the time in ms to reach a load average of
+ 0.5 for an idle task of 0 load average ratio that start a busy loop.
+ The up_threshold and down_threshold is the value to go to a faster
+ CPU or to go back to a slower cpu.
+ The {up,down}_threshold are devided by 1024 before being compared
+ to the load average.
+ For examples, with load_avg_period_ms = 128 and up_threshold = 512,
+ a running task with a load of 0 will be migrated to a bigger CPU after
+ 128ms, because after 128ms its load_avg_ratio is 0.5 and the real
+ up_threshold is 0.5.
+ This patch has the same behavior as changing the Y of the load
+ average computation to
+ (1002/1024)^(LOAD_AVG_PERIOD/load_avg_period_ms)
+ but it remove intermadiate overflows in computation.
+
+config HMP_FREQUENCY_INVARIANT_SCALE
+ bool "(EXPERIMENTAL) Frequency-Invariant Tracked Load for HMP"
+ depends on HMP_VARIABLE_SCALE && CPU_FREQ
+ help
+ Scales the current load contribution in line with the frequency
+ of the CPU that the task was executed on.
+ In this version, we use a simple linear scale derived from the
+ maximum frequency reported by CPUFreq.
+ Restricting tracked load to be scaled by the CPU's frequency
+ represents the consumption of possible compute capacity
+ (rather than consumption of actual instantaneous capacity as
+ normal) and allows the HMP migration's simple threshold
+ migration strategy to interact more predictably with CPUFreq's
+ asynchronous compute capacity changes.
+
+config SCHED_HMP_LITTLE_PACKING
+ bool "Small task packing for HMP"
+ depends on SCHED_HMP
+ default n
+ help
+ Allows the HMP Scheduler to pack small tasks into CPUs in the
+ smallest HMP domain.
+ Controlled by two sysfs files in sys/kernel/hmp.
+ packing_enable: 1 to enable, 0 to disable packing. Default 1.
+ packing_limit: runqueue load ratio where a RQ is considered
+ to be full. Default is NICE_0_LOAD * 9/8.
+
config NR_CPUS
int "Maximum number of CPUs (2-32)"
range 2 32
depends on SMP
- default "4"
+ # These have to remain sorted largest to smallest
+ default "8"
+
+config HOTPLUG_CPU
+ bool "Support for hot-pluggable CPUs"
+ depends on SMP
+ help
+ Say Y here to experiment with turning CPUs off and on. CPUs
+ can be controlled through /sys/devices/system/cpu.
source kernel/Kconfig.preempt
@@ -206,8 +366,25 @@
Enable hardware performance counter support for perf events. If
disabled, perf events will use software events only.
+config SYS_SUPPORTS_HUGETLBFS
+ def_bool y
+
+config ARCH_WANT_GENERAL_HUGETLB
+ def_bool y
+
+config ARCH_WANT_HUGE_PMD_SHARE
+ def_bool y if !ARM64_64K_PAGES
+
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ def_bool y
+
source "mm/Kconfig"
+config FORCE_MAX_ZONEORDER
+ int
+ default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
+ default "11"
+
endmenu
menu "Boot options"
@@ -228,6 +405,20 @@
This is useful if you cannot or don't want to change the
command-line options your boot loader passes to the kernel.
+config EFI
+ bool "UEFI runtime support"
+ depends on OF && !CPU_BIG_ENDIAN
+ select LIBFDT
+ select UCS2_STRING
+ select EFI_PARAMS_FROM_FDT
+ default y
+ help
+ This option provides support for runtime services provided
+ by UEFI firmware (such as non-volatile variables, realtime
+ clock, and platform reset). A UEFI stub is also provided to
+ allow the kernel to be booted as an EFI application. This
+ is only useful on systems that have UEFI firmware.
+
endmenu
menu "Userspace binary formats"
@@ -255,16 +446,42 @@
endmenu
+menu "Power management options"
+
+source "kernel/power/Kconfig"
+
+source "drivers/cpufreq/Kconfig"
+config ARCH_SUSPEND_POSSIBLE
+ def_bool y
+
+config ARM64_CPU_SUSPEND
+ def_bool PM_SLEEP
+
+endmenu
+
+menu "CPU Power Management"
+
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
source "net/Kconfig"
source "drivers/Kconfig"
+source "drivers/firmware/Kconfig"
+
source "fs/Kconfig"
+source "arch/arm64/kvm/Kconfig"
+
source "arch/arm64/Kconfig.debug"
source "security/Kconfig"
source "crypto/Kconfig"
+if CRYPTO
+source "arch/arm64/crypto/Kconfig"
+endif
source "lib/Kconfig"
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 1a6bfe9..bb55717 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -13,6 +13,20 @@
Enables the display of the minimum amount of free stack which each
task has ever had available in the sysrq-T output.
+config STRICT_DEVMEM
+ bool "Filter access to /dev/mem"
+ depends on MMU
+ help
+ If this option is disabled, you allow userspace (root) access to all
+ of memory, including kernel and userspace memory. Accidental
+ access to this is obviously disastrous, but specific access can
+ be used by people debugging the kernel.
+
+ If this option is switched on, the /dev/mem file only allows
+ userspace access to memory mapped peripherals.
+
+ If in doubt, say Y.
+
config EARLY_PRINTK
bool "Early printk support"
default y
@@ -30,4 +44,15 @@
instructions during context switch. Say Y here only if you are
planning to use hardware trace tools with this kernel.
+config DEBUG_SET_MODULE_RONX
+ bool "Set loadable kernel module data as NX and text as RO"
+ depends on MODULES
+ help
+ This option helps catch unintended modifications to loadable
+ kernel module's text and read-only data. It also prevents execution
+ of module data. Such protection may interfere with run-time code
+ patching and dynamic kernel tracing - and they might also protect
+ against certain classes of kernel exploits.
+ If in doubt, say "N".
+
endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index c95c5cb..3e7882c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -20,9 +20,15 @@
KBUILD_DEFCONFIG := defconfig
KBUILD_CFLAGS += -mgeneral-regs-only
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+KBUILD_CPPFLAGS += -mbig-endian
+AS += -EB
+LD += -EB
+else
KBUILD_CPPFLAGS += -mlittle-endian
AS += -EL
LD += -EL
+endif
comma = ,
@@ -32,11 +38,17 @@
head-y := arch/arm64/kernel/head.o
# The byte offset of the kernel image in RAM from the start of RAM.
+ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
+TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}')
+else
TEXT_OFFSET := 0x00080000
+endif
export TEXT_OFFSET GZFLAGS
core-y += arch/arm64/kernel/ arch/arm64/mm/
+core-$(CONFIG_KVM) += arch/arm64/kvm/
+core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
libs-y := arch/arm64/lib/ $(libs-y)
libs-y += $(LIBGCC)
@@ -60,6 +72,10 @@
dtbs: scripts
$(Q)$(MAKE) $(build)=$(boot)/dts dtbs
+PHONY += vdso_install
+vdso_install:
+ $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
+
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile
index 68457e9..ef388176 100644
--- a/arch/arm64/boot/dts/Makefile
+++ b/arch/arm64/boot/dts/Makefile
@@ -1,4 +1,7 @@
-dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb foundation-v8.dtb \
+ fvp-base-gicv2-psci.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb
+dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb
targets += dtbs
targets += $(dtb-y)
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
new file mode 100644
index 0000000..6541962
--- /dev/null
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -0,0 +1,30 @@
+/*
+ * dts file for AppliedMicro (APM) Mustang Board
+ *
+ * Copyright (C) 2013, Applied Micro Circuits Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+/dts-v1/;
+
+/include/ "apm-storm.dtsi"
+
+/ {
+ model = "APM X-Gene Mustang board";
+ compatible = "apm,mustang", "apm,xgene-storm";
+
+ chosen { };
+
+ memory {
+ device_type = "memory";
+ reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
+ };
+};
+
+&serial0 {
+ status = "ok";
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
new file mode 100644
index 0000000..42edf19
--- /dev/null
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -0,0 +1,398 @@
+/*
+ * dts file for AppliedMicro (APM) X-Gene Storm SOC
+ *
+ * Copyright (C) 2013, Applied Micro Circuits Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ */
+
+/ {
+ compatible = "apm,xgene-storm";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ cpus {
+ #address-cells = <2>;
+ #size-cells = <0>;
+
+ cpu@000 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x000>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@001 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x001>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@100 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x100>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@101 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x101>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@200 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x200>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@201 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x201>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@300 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x300>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ cpu@301 {
+ device_type = "cpu";
+ compatible = "apm,potenza", "arm,armv8";
+ reg = <0x0 0x301>;
+ enable-method = "spin-table";
+ cpu-release-addr = <0x1 0x0000fff8>;
+ };
+ };
+
+ gic: interrupt-controller@78010000 {
+ compatible = "arm,cortex-a15-gic";
+ #interrupt-cells = <3>;
+ interrupt-controller;
+ reg = <0x0 0x78010000 0x0 0x1000>, /* GIC Dist */
+ <0x0 0x78020000 0x0 0x1000>, /* GIC CPU */
+ <0x0 0x78040000 0x0 0x2000>, /* GIC VCPU Control */
+ <0x0 0x78060000 0x0 0x2000>; /* GIC VCPU */
+ interrupts = <1 9 0xf04>; /* GIC Maintenence IRQ */
+ };
+
+ timer {
+ compatible = "arm,armv8-timer";
+ interrupts = <1 0 0xff01>, /* Secure Phys IRQ */
+ <1 13 0xff01>, /* Non-secure Phys IRQ */
+ <1 14 0xff01>, /* Virt IRQ */
+ <1 15 0xff01>; /* Hyp IRQ */
+ clock-frequency = <50000000>;
+ };
+
+ soc {
+ compatible = "simple-bus";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ refclk: refclk {
+ compatible = "fixed-clock";
+ #clock-cells = <1>;
+ clock-frequency = <100000000>;
+ clock-output-names = "refclk";
+ };
+
+ pcppll: pcppll@17000100 {
+ compatible = "apm,xgene-pcppll-clock";
+ #clock-cells = <1>;
+ clocks = <&refclk 0>;
+ clock-names = "pcppll";
+ reg = <0x0 0x17000100 0x0 0x1000>;
+ clock-output-names = "pcppll";
+ type = <0>;
+ };
+
+ socpll: socpll@17000120 {
+ compatible = "apm,xgene-socpll-clock";
+ #clock-cells = <1>;
+ clocks = <&refclk 0>;
+ clock-names = "socpll";
+ reg = <0x0 0x17000120 0x0 0x1000>;
+ clock-output-names = "socpll";
+ type = <1>;
+ };
+
+ socplldiv2: socplldiv2 {
+ compatible = "fixed-factor-clock";
+ #clock-cells = <1>;
+ clocks = <&socpll 0>;
+ clock-names = "socplldiv2";
+ clock-mult = <1>;
+ clock-div = <2>;
+ clock-output-names = "socplldiv2";
+ };
+
+ qmlclk: qmlclk {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ clock-names = "qmlclk";
+ reg = <0x0 0x1703C000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "qmlclk";
+ };
+
+ ethclk: ethclk {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ clock-names = "ethclk";
+ reg = <0x0 0x17000000 0x0 0x1000>;
+ reg-names = "div-reg";
+ divider-offset = <0x238>;
+ divider-width = <0x9>;
+ divider-shift = <0x0>;
+ clock-output-names = "ethclk";
+ };
+
+ eth8clk: eth8clk {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <ðclk 0>;
+ clock-names = "eth8clk";
+ reg = <0x0 0x1702C000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "eth8clk";
+ };
+
+ sataphy1clk: sataphy1clk@1f21c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f21c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sataphy1clk";
+ status = "disabled";
+ csr-offset = <0x4>;
+ csr-mask = <0x00>;
+ enable-offset = <0x0>;
+ enable-mask = <0x06>;
+ };
+
+ sataphy2clk: sataphy1clk@1f22c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f22c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sataphy2clk";
+ status = "ok";
+ csr-offset = <0x4>;
+ csr-mask = <0x3a>;
+ enable-offset = <0x0>;
+ enable-mask = <0x06>;
+ };
+
+ sataphy3clk: sataphy1clk@1f23c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f23c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sataphy3clk";
+ status = "ok";
+ csr-offset = <0x4>;
+ csr-mask = <0x3a>;
+ enable-offset = <0x0>;
+ enable-mask = <0x06>;
+ };
+
+ sata01clk: sata01clk@1f21c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f21c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sata01clk";
+ csr-offset = <0x4>;
+ csr-mask = <0x05>;
+ enable-offset = <0x0>;
+ enable-mask = <0x39>;
+ };
+
+ sata23clk: sata23clk@1f22c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f22c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sata23clk";
+ csr-offset = <0x4>;
+ csr-mask = <0x05>;
+ enable-offset = <0x0>;
+ enable-mask = <0x39>;
+ };
+
+ sata45clk: sata45clk@1f23c000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x1f23c000 0x0 0x1000>;
+ reg-names = "csr-reg";
+ clock-output-names = "sata45clk";
+ csr-offset = <0x4>;
+ csr-mask = <0x05>;
+ enable-offset = <0x0>;
+ enable-mask = <0x39>;
+ };
+
+ rtcclk: rtcclk@17000000 {
+ compatible = "apm,xgene-device-clock";
+ #clock-cells = <1>;
+ clocks = <&socplldiv2 0>;
+ reg = <0x0 0x17000000 0x0 0x2000>;
+ reg-names = "csr-reg";
+ csr-offset = <0xc>;
+ csr-mask = <0x2>;
+ enable-offset = <0x10>;
+ enable-mask = <0x2>;
+ clock-output-names = "rtcclk";
+ };
+ };
+
+ serial0: serial@1c020000 {
+ status = "disabled";
+ device_type = "serial";
+ compatible = "ns16550a";
+ reg = <0 0x1c020000 0x0 0x1000>;
+ reg-shift = <2>;
+ clock-frequency = <10000000>; /* Updated by bootloader */
+ interrupt-parent = <&gic>;
+ interrupts = <0x0 0x4c 0x4>;
+ };
+
+ serial1: serial@1c021000 {
+ status = "disabled";
+ device_type = "serial";
+ compatible = "ns16550a";
+ reg = <0 0x1c021000 0x0 0x1000>;
+ reg-shift = <2>;
+ clock-frequency = <10000000>; /* Updated by bootloader */
+ interrupt-parent = <&gic>;
+ interrupts = <0x0 0x4d 0x4>;
+ };
+
+ serial2: serial@1c022000 {
+ status = "disabled";
+ device_type = "serial";
+ compatible = "ns16550a";
+ reg = <0 0x1c022000 0x0 0x1000>;
+ reg-shift = <2>;
+ clock-frequency = <10000000>; /* Updated by bootloader */
+ interrupt-parent = <&gic>;
+ interrupts = <0x0 0x4e 0x4>;
+ };
+
+ serial3: serial@1c023000 {
+ status = "disabled";
+ device_type = "serial";
+ compatible = "ns16550a";
+ reg = <0 0x1c023000 0x0 0x1000>;
+ reg-shift = <2>;
+ clock-frequency = <10000000>; /* Updated by bootloader */
+ interrupt-parent = <&gic>;
+ interrupts = <0x0 0x4f 0x4>;
+ };
+
+ phy1: phy@1f21a000 {
+ compatible = "apm,xgene-phy";
+ reg = <0x0 0x1f21a000 0x0 0x100>;
+ #phy-cells = <1>;
+ clocks = <&sataphy1clk 0>;
+ status = "disabled";
+ apm,tx-boost-gain = <30 30 30 30 30 30>;
+ apm,tx-eye-tuning = <2 10 10 2 10 10>;
+ };
+
+ phy2: phy@1f22a000 {
+ compatible = "apm,xgene-phy";
+ reg = <0x0 0x1f22a000 0x0 0x100>;
+ #phy-cells = <1>;
+ clocks = <&sataphy2clk 0>;
+ status = "ok";
+ apm,tx-boost-gain = <30 30 30 30 30 30>;
+ apm,tx-eye-tuning = <1 10 10 2 10 10>;
+ };
+
+ phy3: phy@1f23a000 {
+ compatible = "apm,xgene-phy";
+ reg = <0x0 0x1f23a000 0x0 0x100>;
+ #phy-cells = <1>;
+ clocks = <&sataphy3clk 0>;
+ status = "ok";
+ apm,tx-boost-gain = <31 31 31 31 31 31>;
+ apm,tx-eye-tuning = <2 10 10 2 10 10>;
+ };
+
+ sata1: sata@1a000000 {
+ compatible = "apm,xgene-ahci";
+ reg = <0x0 0x1a000000 0x0 0x1000>,
+ <0x0 0x1f210000 0x0 0x1000>,
+ <0x0 0x1f21d000 0x0 0x1000>,
+ <0x0 0x1f21e000 0x0 0x1000>,
+ <0x0 0x1f217000 0x0 0x1000>;
+ interrupts = <0x0 0x86 0x4>;
+ status = "disabled";
+ clocks = <&sata01clk 0>;
+ phys = <&phy1 0>;
+ phy-names = "sata-phy";
+ };
+
+ sata2: sata@1a400000 {
+ compatible = "apm,xgene-ahci";
+ reg = <0x0 0x1a400000 0x0 0x1000>,
+ <0x0 0x1f220000 0x0 0x1000>,
+ <0x0 0x1f22d000 0x0 0x1000>,
+ <0x0 0x1f22e000 0x0 0x1000>,
+ <0x0 0x1f227000 0x0 0x1000>;
+ interrupts = <0x0 0x87 0x4>;
+ status = "ok";
+ clocks = <&sata23clk 0>;
+ phys = <&phy2 0>;
+ phy-names = "sata-phy";
+ };
+
+ sata3: sata@1a800000 {
+ compatible = "apm,xgene-ahci";
+ reg = <0x0 0x1a800000 0x0 0x1000>,
+ <0x0 0x1f230000 0x0 0x1000>,
+ <0x0 0x1f23d000 0x0 0x1000>,
+ <0x0 0x1f23e000 0x0 0x1000>;
+ interrupts = <0x0 0x88 0x4>;
+ status = "ok";
+ clocks = <&sata45clk 0>;
+ phys = <&phy3 0>;
+ phy-names = "sata-phy";
+ };
+
+ rtc: rtc@10510000 {
+ compatible = "apm,xgene-rtc";
+ reg = <0x0 0x10510000 0x0 0x400>;
+ interrupts = <0x0 0x46 0x4>;
+ #clock-cells = <1>;
+ clocks = <&rtcclk 0>;
+ };
+ };
+};
diff --git a/arch/arm64/boot/dts/clcd-panels.dtsi b/arch/arm64/boot/dts/clcd-panels.dtsi
new file mode 100644
index 0000000..0b0ff6e
--- /dev/null
+++ b/arch/arm64/boot/dts/clcd-panels.dtsi
@@ -0,0 +1,52 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ */
+
+/ {
+ panels {
+ panel@0 {
+ compatible = "panel";
+ mode = "VGA";
+ refresh = <60>;
+ xres = <640>;
+ yres = <480>;
+ pixclock = <39721>;
+ left_margin = <40>;
+ right_margin = <24>;
+ upper_margin = <32>;
+ lower_margin = <11>;
+ hsync_len = <96>;
+ vsync_len = <2>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+
+ panel@1 {
+ compatible = "panel";
+ mode = "XVGA";
+ refresh = <60>;
+ xres = <1024>;
+ yres = <768>;
+ pixclock = <15748>;
+ left_margin = <152>;
+ right_margin = <48>;
+ upper_margin = <23>;
+ lower_margin = <3>;
+ hsync_len = <104>;
+ vsync_len = <4>;
+ sync = <0>;
+ vmode = "FB_VMODE_NONINTERLACED";
+
+ tim2 = "TIM2_BCD", "TIM2_IPC";
+ cntl = "CNTL_LCDTFT", "CNTL_BGR", "CNTL_LCDVCOMP(1)";
+ caps = "CLCD_CAP_5551", "CLCD_CAP_565", "CLCD_CAP_888";
+ bpp = <16>;
+ };
+ };
+};
diff --git a/arch/arm64/boot/dts/foundation-v8.dts b/arch/arm64/boot/dts/foundation-v8.dts
index 84fcc50..519c4b2 100644
--- a/arch/arm64/boot/dts/foundation-v8.dts
+++ b/arch/arm64/boot/dts/foundation-v8.dts
@@ -6,6 +6,8 @@
/dts-v1/;
+/memreserve/ 0x80000000 0x00010000;
+
/ {
model = "Foundation-v8A";
compatible = "arm,foundation-aarch64", "arm,vexpress";
diff --git a/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
new file mode 100644
index 0000000..ed55571
--- /dev/null
+++ b/arch/arm64/boot/dts/fvp-base-gicv2-psci.dts
@@ -0,0 +1,294 @@
+/*
+ * Copyright (c) 2013, ARM Limited. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * Redistributions of source code must retain the above copyright notice, this
+ * list of conditions and the following disclaimer.
+ *
+ * Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * Neither the name of ARM nor the names of its contributors may be used
+ * to endorse or promote products derived from this software without specific
+ * prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x80000000 0x00010000;
+
+/ {
+};
+
+/ {
+ model = "FVP Base";
+ compatible = "arm,vfp-base", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ chosen { };
+
+ aliases {
+ serial0 = &v2m_serial0;
+ serial1 = &v2m_serial1;
+ serial2 = &v2m_serial2;
+ serial3 = &v2m_serial3;
+ };
+
+ psci {
+ compatible = "arm,psci";
+ method = "smc";
+ cpu_suspend = <0x84000001>;
+ cpu_off = <0x84000002>;
+ cpu_on = <0xc4000003>;
+ };
+
+ cpus {
+ #address-cells = <2>;
+ #size-cells = <0>;
+
+ idle-states {
+ entry-method = "arm,psci";
+
+ CPU_SLEEP_0: cpu-sleep-0 {
+ compatible = "arm,idle-state";
+ entry-method-param = <0x0010000>;
+ entry-latency-us = <40>;
+ exit-latency-us = <100>;
+ min-residency-us = <150>;
+ };
+
+ CLUSTER_SLEEP_0: cluster-sleep-0 {
+ compatible = "arm,idle-state";
+ entry-method-param = <0x1010000>;
+ entry-latency-us = <500>;
+ exit-latency-us = <1000>;
+ min-residency-us = <2500>;
+ };
+ };
+
+ big0: cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57", "arm,armv8";
+ reg = <0x0 0x0>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ big1: cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57", "arm,armv8";
+ reg = <0x0 0x1>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ big2: cpu@2 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57", "arm,armv8";
+ reg = <0x0 0x2>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ big3: cpu@3 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57", "arm,armv8";
+ reg = <0x0 0x3>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ little0: cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53", "arm,armv8";
+ reg = <0x0 0x100>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ little1: cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53", "arm,armv8";
+ reg = <0x0 0x101>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ little2: cpu@102 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53", "arm,armv8";
+ reg = <0x0 0x102>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+ little3: cpu@103 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53", "arm,armv8";
+ reg = <0x0 0x103>;
+ enable-method = "psci";
+ clock-frequency = <1000000>;
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+ };
+
+ cpu-map {
+ cluster0 {
+ core0 {
+ cpu = <&big0>;
+ };
+ core1 {
+ cpu = <&big1>;
+ };
+ core2 {
+ cpu = <&big2>;
+ };
+ core3 {
+ cpu = <&big3>;
+ };
+ };
+ cluster1 {
+ core0 {
+ cpu = <&little0>;
+ };
+ core1 {
+ cpu = <&little1>;
+ };
+ core2 {
+ cpu = <&little2>;
+ };
+ core3 {
+ cpu = <&little3>;
+ };
+ };
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x00000000 0x80000000 0 0x80000000>,
+ <0x00000008 0x80000000 0 0x80000000>;
+ };
+
+ gic: interrupt-controller@2f000000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x0 0x2f000000 0 0x10000>,
+ <0x0 0x2c000000 0 0x2000>,
+ <0x0 0x2c010000 0 0x2000>,
+ <0x0 0x2c02F000 0 0x2000>;
+ interrupts = <1 9 0xf04>;
+ };
+
+ timer {
+ compatible = "arm,armv8-timer";
+ interrupts = <1 13 0xff01>,
+ <1 14 0xff01>,
+ <1 11 0xff01>,
+ <1 10 0xff01>;
+ clock-frequency = <100000000>;
+ };
+
+ timer@2a810000 {
+ compatible = "arm,armv7-timer-mem";
+ reg = <0x0 0x2a810000 0x0 0x10000>;
+ clock-frequency = <100000000>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ frame@2a820000 {
+ frame-number = <0>;
+ interrupts = <0 25 4>;
+ reg = <0x0 0x2a820000 0x0 0x10000>;
+ };
+ };
+
+ pmu {
+ compatible = "arm,armv8-pmuv3";
+ interrupts = <0 60 4>,
+ <0 61 4>,
+ <0 62 4>,
+ <0 63 4>;
+ };
+
+ smb {
+ compatible = "simple-bus";
+
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 63>;
+ interrupt-map = <0 0 0 &gic 0 0 4>,
+ <0 0 1 &gic 0 1 4>,
+ <0 0 2 &gic 0 2 4>,
+ <0 0 3 &gic 0 3 4>,
+ <0 0 4 &gic 0 4 4>,
+ <0 0 5 &gic 0 5 4>,
+ <0 0 6 &gic 0 6 4>,
+ <0 0 7 &gic 0 7 4>,
+ <0 0 8 &gic 0 8 4>,
+ <0 0 9 &gic 0 9 4>,
+ <0 0 10 &gic 0 10 4>,
+ <0 0 11 &gic 0 11 4>,
+ <0 0 12 &gic 0 12 4>,
+ <0 0 13 &gic 0 13 4>,
+ <0 0 14 &gic 0 14 4>,
+ <0 0 15 &gic 0 15 4>,
+ <0 0 16 &gic 0 16 4>,
+ <0 0 17 &gic 0 17 4>,
+ <0 0 18 &gic 0 18 4>,
+ <0 0 19 &gic 0 19 4>,
+ <0 0 20 &gic 0 20 4>,
+ <0 0 21 &gic 0 21 4>,
+ <0 0 22 &gic 0 22 4>,
+ <0 0 23 &gic 0 23 4>,
+ <0 0 24 &gic 0 24 4>,
+ <0 0 25 &gic 0 25 4>,
+ <0 0 26 &gic 0 26 4>,
+ <0 0 27 &gic 0 27 4>,
+ <0 0 28 &gic 0 28 4>,
+ <0 0 29 &gic 0 29 4>,
+ <0 0 30 &gic 0 30 4>,
+ <0 0 31 &gic 0 31 4>,
+ <0 0 32 &gic 0 32 4>,
+ <0 0 33 &gic 0 33 4>,
+ <0 0 34 &gic 0 34 4>,
+ <0 0 35 &gic 0 35 4>,
+ <0 0 36 &gic 0 36 4>,
+ <0 0 37 &gic 0 37 4>,
+ <0 0 38 &gic 0 38 4>,
+ <0 0 39 &gic 0 39 4>,
+ <0 0 40 &gic 0 40 4>,
+ <0 0 41 &gic 0 41 4>,
+ <0 0 42 &gic 0 42 4>;
+
+ /include/ "rtsm_ve-motherboard.dtsi"
+ };
+};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/juno.dts b/arch/arm64/boot/dts/juno.dts
new file mode 100644
index 0000000..f260d70
--- /dev/null
+++ b/arch/arm64/boot/dts/juno.dts
@@ -0,0 +1,498 @@
+/*
+ * ARM Ltd. Juno Plaform
+ *
+ * Fast Models FVP v2 support
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+ model = "Juno";
+ compatible = "arm,juno", "arm,vexpress";
+ interrupt-parent = <&gic>;
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ aliases {
+ serial0 = &soc_uart0;
+ };
+
+ cpus {
+ #address-cells = <2>;
+ #size-cells = <0>;
+
+ cpu@100 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53","arm,armv8";
+ reg = <0x0 0x100>;
+ enable-method = "psci";
+ };
+
+ cpu@101 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53","arm,armv8";
+ reg = <0x0 0x101>;
+ enable-method = "psci";
+ };
+
+ cpu@102 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53","arm,armv8";
+ reg = <0x0 0x102>;
+ enable-method = "psci";
+ };
+
+ cpu@103 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a53","arm,armv8";
+ reg = <0x0 0x103>;
+ enable-method = "psci";
+ };
+
+ cpu@0 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57","arm,armv8";
+ reg = <0x0 0x0>;
+ enable-method = "psci";
+ };
+
+ cpu@1 {
+ device_type = "cpu";
+ compatible = "arm,cortex-a57","arm,armv8";
+ reg = <0x0 0x1>;
+ enable-method = "psci";
+ };
+ };
+
+ memory@80000000 {
+ device_type = "memory";
+ reg = <0x00000000 0x80000000 0x0 0x7f000000>,
+ <0x00000008 0x80000000 0x1 0x80000000>;
+ };
+
+ /* memory@14000000 {
+ device_type = "memory";
+ reg = <0x00000000 0x14000000 0x0 0x02000000>;
+ }; */
+
+ gic: interrupt-controller@2c001000 {
+ compatible = "arm,cortex-a15-gic", "arm,cortex-a9-gic";
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+ reg = <0x0 0x2c010000 0 0x1000>,
+ <0x0 0x2c02f000 0 0x1000>,
+ <0x0 0x2c04f000 0 0x2000>,
+ <0x0 0x2c06f000 0 0x2000>;
+ interrupts = <GIC_PPI 9 0xf04>;
+ };
+
+ msi0: msi@2c1c0000 {
+ compatible = "arm,gic-msi";
+ reg = <0x0 0x2c1c0000 0 0x10000
+ 0x0 0x2c1d0000 0 0x10000
+ 0x0 0x2c1e0000 0 0x10000
+ 0x0 0x2c1f0000 0 0x10000>;
+ };
+
+ timer {
+ compatible = "arm,armv8-timer";
+ interrupts = <GIC_PPI 13 0xff01>,
+ <GIC_PPI 14 0xff01>,
+ <GIC_PPI 11 0xff01>,
+ <GIC_PPI 10 0xff01>;
+ };
+
+ pmu {
+ compatible = "arm,armv8-pmuv3";
+ interrupts = <GIC_SPI 60 4>,
+ <GIC_SPI 61 4>,
+ <GIC_SPI 62 4>,
+ <GIC_SPI 63 4>;
+ };
+
+ psci {
+ compatible = "arm,psci";
+ method = "smc";
+ cpu_suspend = <0xC4000001>;
+ cpu_off = <0x84000002>;
+ cpu_on = <0xC4000003>;
+ migrate = <0xC4000005>;
+ };
+
+ pci0: pci@30000000 {
+ compatible = "arm,pcie-xr3";
+ device_type = "pci";
+ reg = <0 0x7ff30000 0 0x1000
+ 0 0x7ff20000 0 0x10000
+ 0 0x40000000 0 0x10000000>;
+ bus-range = <0 255>;
+ #address-cells = <3>;
+ #size-cells = <2>;
+ ranges = <0x01000000 0x0 0x00000000 0x00 0x5ff00000 0x0 0x00100000
+ 0x02000000 0x0 0x00000000 0x40 0x00000000 0x0 0x80000000
+ 0x42000000 0x0 0x80000000 0x40 0x80000000 0x0 0x80000000>;
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 0 7>;
+ interrupt-map = <0 0 0 1 &gic 0 136 4
+ 0 0 0 2 &gic 0 137 4
+ 0 0 0 3 &gic 0 138 4
+ 0 0 0 4 &gic 0 139 4>;
+ };
+
+ scpi: scpi@2b1f0000 {
+ compatible = "arm,scpi-mhu";
+ reg = <0x0 0x2b1f0000 0x0 0x10000>, /* MHU registers */
+ <0x0 0x2e000000 0x0 0x10000>; /* Payload area */
+ interrupts = <0 36 4>, /* low priority interrupt */
+ <0 35 4>, /* high priority interrupt */
+ <0 37 4>; /* secure channel interrupt */
+ #clock-cells = <1>;
+ clock-output-names = "a57", "a53", "gpu", "hdlcd0", "hdlcd1";
+ };
+
+ hdlcd0_osc: scpi_osc@3 {
+ compatible = "arm,scpi-osc";
+ #clock-cells = <0>;
+ clocks = <&scpi 3>;
+ frequency-range = <23000000 210000000>;
+ clock-output-names = "pxlclk0";
+ };
+
+ hdlcd1_osc: scpi_osc@4 {
+ compatible = "arm,scpi-osc";
+ #clock-cells = <0>;
+ clocks = <&scpi 4>;
+ frequency-range = <23000000 210000000>;
+ clock-output-names = "pxlclk1";
+ };
+
+ soc_uartclk: refclk72738khz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <7273800>;
+ clock-output-names = "juno:uartclk";
+ };
+
+ soc_refclk24mhz: clk24mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <24000000>;
+ clock-output-names = "juno:clk24mhz";
+ };
+
+ mb_eth25mhz: clk25mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <25000000>;
+ clock-output-names = "ethclk25mhz";
+ };
+
+ soc_usb48mhz: clk48mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <48000000>;
+ clock-output-names = "clk48mhz";
+ };
+
+ soc_smc50mhz: clk50mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <50000000>;
+ clock-output-names = "smc_clk";
+ };
+
+ soc_refclk100mhz: refclk100mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <100000000>;
+ clock-output-names = "apb_pclk";
+ };
+
+ soc_faxiclk: refclk533mhz {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <533000000>;
+ clock-output-names = "faxi_clk";
+ };
+
+ soc_fixed_3v3: fixedregulator@0 {
+ compatible = "regulator-fixed";
+ regulator-name = "3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ regulator-always-on;
+ };
+
+ memory-controller@7ffd0000 {
+ compatible = "arm,pl354", "arm,primecell";
+ reg = <0 0x7ffd0000 0 0x1000>;
+ interrupts = <0 86 4>,
+ <0 87 4>;
+ clocks = <&soc_smc50mhz>;
+ clock-names = "apb_pclk";
+ chip5-memwidth = <16>;
+ };
+
+ dma0: dma@0x7ff00000 {
+ compatible = "arm,pl330", "arm,primecell";
+ reg = <0x0 0x7ff00000 0 0x1000>;
+ interrupts = <0 95 4>,
+ <0 88 4>,
+ <0 89 4>,
+ <0 90 4>,
+ <0 91 4>,
+ <0 108 4>,
+ <0 109 4>,
+ <0 110 4>,
+ <0 111 4>;
+ #dma-cells = <1>;
+ #dma-channels = <8>;
+ #dma-requests = <32>;
+ clocks = <&soc_faxiclk>;
+ clock-names = "apb_pclk";
+ };
+
+ soc_uart0: uart@7ff80000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0 0x7ff80000 0x0 0x1000>;
+ interrupts = <0 83 4>;
+ clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+ clock-names = "uartclk", "apb_pclk";
+ dmas = <&dma0 1
+ &dma0 2>;
+ dma-names = "rx", "tx";
+ };
+
+ /* this UART is reserved for secure software.
+ soc_uart1: uart@7ff70000 {
+ compatible = "arm,pl011", "arm,primecell";
+ reg = <0x0 0x7ff70000 0x0 0x1000>;
+ interrupts = <0 84 4>;
+ clocks = <&soc_uartclk>, <&soc_refclk100mhz>;
+ clock-names = "uartclk", "apb_pclk";
+ }; */
+
+ ulpi_phy: phy@0 {
+ compatible = "phy-ulpi-generic";
+ reg = <0x0 0x94 0x0 0x4>;
+ phy-id = <0>;
+ };
+
+ ehci@7ffc0000 {
+ compatible = "snps,ehci-h20ahb";
+ /* compatible = "arm,h20ahb-ehci"; */
+ reg = <0x0 0x7ffc0000 0x0 0x10000>;
+ interrupts = <0 117 4>;
+ clocks = <&soc_usb48mhz>;
+ clock-names = "otg";
+ phys = <&ulpi_phy>;
+ };
+
+ ohci@0x7ffb0000 {
+ compatible = "generic-ohci";
+ reg = <0x0 0x7ffb0000 0x0 0x10000>;
+ interrupts = <0 116 4>;
+ clocks = <&soc_usb48mhz>;
+ clock-names = "otg";
+ };
+
+ i2c@0x7ffa0000 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ compatible = "snps,designware-i2c";
+ reg = <0x0 0x7ffa0000 0x0 0x1000>;
+ interrupts = <0 104 4>;
+ clock-frequency = <400000>;
+ i2c-sda-hold-time-ns = <500>;
+ clocks = <&soc_smc50mhz>;
+
+ dvi0: dvi-transmitter@70 {
+ compatible = "nxp,tda998x";
+ reg = <0x70>;
+ };
+
+ dvi1: dvi-transmitter@71 {
+ compatible = "nxp,tda998x";
+ reg = <0x71>;
+ };
+ };
+
+ /* mmci@1c050000 {
+ compatible = "arm,pl180", "arm,primecell";
+ reg = <0x0 0x1c050000 0x0 0x1000>;
+ interrupts = <0 73 4>,
+ <0 74 4>;
+ max-frequency = <12000000>;
+ vmmc-supply = <&soc_fixed_3v3>;
+ clocks = <&soc_refclk24mhz>, <&soc_refclk100mhz>;
+ clock-names = "mclk", "apb_pclk";
+ }; */
+
+ hdlcd@7ff60000 {
+ compatible = "arm,hdlcd";
+ reg = <0 0x7ff60000 0 0x1000>;
+ interrupts = <0 85 4>;
+ clocks = <&hdlcd0_osc>;
+ clock-names = "pxlclk";
+ i2c-slave = <&dvi0>;
+
+ /* display-timings {
+ native-mode = <&timing0>;
+ timing0: timing@0 {
+ /* 1024 x 768 framebufer, standard VGA timings * /
+ clock-frequency = <65000>;
+ hactive = <1024>;
+ vactive = <768>;
+ hfront-porch = <24>;
+ hback-porch = <160>;
+ hsync-len = <136>;
+ vfront-porch = <3>;
+ vback-porch = <29>;
+ vsync-len = <6>;
+ };
+ }; */
+ };
+
+ hdlcd@7ff50000 {
+ compatible = "arm,hdlcd";
+ reg = <0 0x7ff50000 0 0x1000>;
+ interrupts = <0 93 4>;
+ clocks = <&hdlcd1_osc>;
+ clock-names = "pxlclk";
+ i2c-slave = <&dvi1>;
+
+ display-timings {
+ native-mode = <&timing1>;
+ timing1: timing@1 {
+ /* 1024 x 768 framebufer, standard VGA timings */
+ clock-frequency = <65000>;
+ hactive = <1024>;
+ vactive = <768>;
+ hfront-porch = <24>;
+ hback-porch = <160>;
+ hsync-len = <136>;
+ vfront-porch = <3>;
+ vback-porch = <29>;
+ vsync-len = <6>;
+ };
+ };
+ };
+
+ smb {
+ compatible = "simple-bus";
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges = <0 0 0 0x08000000 0x04000000>,
+ <1 0 0 0x14000000 0x04000000>,
+ <2 0 0 0x18000000 0x04000000>,
+ <3 0 0 0x1c000000 0x04000000>,
+ <4 0 0 0x0c000000 0x04000000>,
+ <5 0 0 0x10000000 0x04000000>;
+
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 15>;
+ interrupt-map = <0 0 0 &gic 0 68 4>,
+ <0 0 1 &gic 0 69 4>,
+ <0 0 2 &gic 0 70 4>,
+ <0 0 3 &gic 0 160 4>,
+ <0 0 4 &gic 0 161 4>,
+ <0 0 5 &gic 0 162 4>,
+ <0 0 6 &gic 0 163 4>,
+ <0 0 7 &gic 0 164 4>,
+ <0 0 8 &gic 0 165 4>,
+ <0 0 9 &gic 0 166 4>,
+ <0 0 10 &gic 0 167 4>,
+ <0 0 11 &gic 0 168 4>,
+ <0 0 12 &gic 0 169 4>;
+
+ motherboard {
+ model = "V2M-Juno";
+ arm,hbi = <0x252>;
+ arm,vexpress,site = <0>;
+ arm,v2m-memory-map = "rs1";
+ compatible = "arm,vexpress,v2p-p1", "simple-bus";
+ #address-cells = <2>; /* SMB chipselect number and offset */
+ #size-cells = <1>;
+ #interrupt-cells = <1>;
+ ranges;
+
+ usb@5,00000000 {
+ compatible = "nxp,usb-isp1763";
+ reg = <5 0x00000000 0x20000>;
+ bus-width = <16>;
+ interrupts = <4>;
+ };
+
+ ethernet@2,00000000 {
+ compatible = "smsc,lan9118", "smsc,lan9115";
+ reg = <2 0x00000000 0x10000>;
+ interrupts = <3>;
+ phy-mode = "mii";
+ reg-io-width = <4>;
+ smsc,irq-active-high;
+ smsc,irq-push-pull;
+ clocks = <&mb_eth25mhz>;
+ vdd33a-supply = <&soc_fixed_3v3>; /* change this */
+ vddvario-supply = <&soc_fixed_3v3>; /* and this */
+ };
+
+ iofpga@3,00000000 {
+ compatible = "arm,amba-bus", "simple-bus";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0 3 0 0x200000>;
+
+ kmi@060000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x060000 0x1000>;
+ interrupts = <8>;
+ clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ kmi@070000 {
+ compatible = "arm,pl050", "arm,primecell";
+ reg = <0x070000 0x1000>;
+ interrupts = <8>;
+ clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+ clock-names = "KMIREFCLK", "apb_pclk";
+ };
+
+ wdt@0f0000 {
+ compatible = "arm,sp805", "arm,primecell";
+ reg = <0x0f0000 0x10000>;
+ interrupts = <7>;
+ clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+ clock-names = "wdogclk", "apb_pclk";
+ };
+
+ v2m_timer01: timer@110000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x110000 0x10000>;
+ interrupts = <9>;
+ clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+ clock-names = "timclken1", "apb_pclk";
+ };
+
+ v2m_timer23: timer@120000 {
+ compatible = "arm,sp804", "arm,primecell";
+ reg = <0x120000 0x10000>;
+ interrupts = <9>;
+ clocks = <&soc_refclk24mhz>, <&soc_smc50mhz>;
+ clock-names = "timclken1", "apb_pclk";
+ };
+
+ rtc@170000 {
+ compatible = "arm,pl031", "arm,primecell";
+ reg = <0x170000 0x10000>;
+ interrupts = <0>;
+ clocks = <&soc_smc50mhz>;
+ clock-names = "apb_pclk";
+ };
+ };
+ };
+ };
+};
diff --git a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
index 572005e..28ed4ba 100644
--- a/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
+++ b/arch/arm64/boot/dts/rtsm_ve-aemv8a.dts
@@ -27,37 +27,70 @@
serial3 = &v2m_serial3;
};
+ psci {
+ compatible = "arm,psci";
+ method = "smc";
+ /*
+ * Function IDs usage and compliancy with PSCI v0.2 still
+ * under discussion. Current IDs should be considered
+ * temporary for demonstration purposes.
+ */
+ cpu_suspend = <0x84000001>;
+ cpu_off = <0x84000002>;
+ cpu_on = <0x84000003>;
+ };
+
cpus {
#address-cells = <2>;
#size-cells = <0>;
+ idle-states {
+ entry-method = "arm,psci";
+
+ CPU_SLEEP_0: cpu-sleep-0 {
+ compatible = "arm,idle-state";
+ entry-method-param = <0x0010000>;
+ entry-latency-us = <40>;
+ exit-latency-us = <100>;
+ min-residency-us = <150>;
+ };
+
+ CLUSTER_SLEEP_0: cluster-sleep-0 {
+ compatible = "arm,idle-state";
+ entry-method-param = <0x1010000>;
+ entry-latency-us = <500>;
+ exit-latency-us = <1000>;
+ min-residency-us = <2500>;
+ };
+ };
+
cpu@0 {
device_type = "cpu";
compatible = "arm,armv8";
reg = <0x0 0x0>;
- enable-method = "spin-table";
- cpu-release-addr = <0x0 0x8000fff8>;
+ enable-method = "psci";
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
};
cpu@1 {
device_type = "cpu";
compatible = "arm,armv8";
reg = <0x0 0x1>;
- enable-method = "spin-table";
- cpu-release-addr = <0x0 0x8000fff8>;
+ enable-method = "psci";
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
};
cpu@2 {
device_type = "cpu";
compatible = "arm,armv8";
reg = <0x0 0x2>;
- enable-method = "spin-table";
- cpu-release-addr = <0x0 0x8000fff8>;
+ enable-method = "psci";
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
};
cpu@3 {
device_type = "cpu";
compatible = "arm,armv8";
reg = <0x0 0x3>;
- enable-method = "spin-table";
- cpu-release-addr = <0x0 0x8000fff8>;
+ enable-method = "psci";
+ cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
};
};
@@ -157,3 +190,5 @@
/include/ "rtsm_ve-motherboard.dtsi"
};
};
+
+/include/ "clcd-panels.dtsi"
diff --git a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
index b45e5f3..b683d47 100644
--- a/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
+++ b/arch/arm64/boot/dts/rtsm_ve-motherboard.dtsi
@@ -182,6 +182,15 @@
interrupts = <14>;
clocks = <&v2m_oscclk1>, <&v2m_clk24mhz>;
clock-names = "clcdclk", "apb_pclk";
+ mode = "XVGA";
+ use_dma = <0>;
+ framebuffer = <0x18000000 0x00180000>;
+ };
+
+ virtio_block@0130000 {
+ compatible = "virtio,mmio";
+ reg = <0x130000 0x200>;
+ interrupts = <42>;
};
};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 8d9696ad..8e32314 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
# CONFIG_LOCALVERSION_AUTO is not set
# CONFIG_SWAP is not set
CONFIG_SYSVIPC=y
@@ -19,13 +18,17 @@
CONFIG_KALLSYMS_ALL=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
+CONFIG_JUMP_LABEL=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
# CONFIG_IOSCHED_DEADLINE is not set
CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_XGENE=y
CONFIG_SMP=y
+CONFIG_PREEMPT=y
CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_CMA=y
CONFIG_CMDLINE="console=ttyAMA0"
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_COMPAT=y
@@ -42,29 +45,42 @@
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
# CONFIG_BLK_DEV is not set
+CONFIG_DMA_CMA=y
CONFIG_SCSI=y
# CONFIG_SCSI_PROC_FS is not set
CONFIG_BLK_DEV_SD=y
# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_PATA_PLATFORM=y
+CONFIG_PATA_OF_PLATFORM=y
CONFIG_NETDEVICES=y
-CONFIG_MII=y
CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
# CONFIG_WLAN is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_SERIO_I8042 is not set
# CONFIG_SERIO_SERPORT is not set
CONFIG_LEGACY_PTY_COUNT=16
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
# CONFIG_HW_RANDOM is not set
# CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
CONFIG_FB=y
# CONFIG_VGA_CONSOLE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
@@ -86,3 +102,4 @@
CONFIG_DEBUG_INFO=y
# CONFIG_FTRACE is not set
CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_DMA_CMA=y
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 0000000..5562652
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,53 @@
+
+menuconfig ARM64_CRYPTO
+ bool "ARM64 Accelerated Cryptographic Algorithms"
+ depends on ARM64
+ help
+ Say Y here to choose from a selection of cryptographic algorithms
+ implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA1_ARM64_CE
+ tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_SHA2_ARM64_CE
+ tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_GHASH_ARM64_CE
+ tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64_CE
+ tristate "AES core cipher using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_AES
+
+config CRYPTO_AES_ARM64_CE_CCM
+ tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_AES
+ select CRYPTO_AEAD
+
+config CRYPTO_AES_ARM64_CE_BLK
+ tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_AES
+ select CRYPTO_ABLK_HELPER
+
+config CRYPTO_AES_ARM64_NEON_BLK
+ tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+ depends on ARM64 && KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_AES
+ select CRYPTO_ABLK_HELPER
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 0000000..2070a56
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,38 @@
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE
+AFLAGS_aes-neon.o := -DINTERLEAVE=4
+
+CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+ $(call if_changed_dep,cc_o_c)
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 0000000..432e484
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,222 @@
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ /*
+ * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+ * u32 *macp, u8 const rk[], u32 rounds);
+ */
+ENTRY(ce_aes_ccm_auth_data)
+ ldr w8, [x3] /* leftover from prev round? */
+ ld1 {v0.2d}, [x0] /* load mac */
+ cbz w8, 1f
+ sub w8, w8, #16
+ eor v1.16b, v1.16b, v1.16b
+0: ldrb w7, [x1], #1 /* get 1 byte of input */
+ subs w2, w2, #1
+ add w8, w8, #1
+ ins v1.b[0], w7
+ ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */
+ beq 8f /* out of input? */
+ cbnz w8, 0b
+ eor v0.16b, v0.16b, v1.16b
+1: ld1 {v3.2d}, [x4] /* load first round key */
+ prfm pldl1strm, [x1]
+ cmp w5, #12 /* which key size? */
+ add x6, x4, #16
+ sub w7, w5, #2 /* modified # of rounds */
+ bmi 2f
+ bne 5f
+ mov v5.16b, v3.16b
+ b 4f
+2: mov v4.16b, v3.16b
+ ld1 {v5.2d}, [x6], #16 /* load 2nd round key */
+3: aese v0.16b, v4.16b
+ aesmc v0.16b, v0.16b
+4: ld1 {v3.2d}, [x6], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aesmc v0.16b, v0.16b
+5: ld1 {v4.2d}, [x6], #16 /* load next round key */
+ subs w7, w7, #3
+ aese v0.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ ld1 {v5.2d}, [x6], #16 /* load next round key */
+ bpl 3b
+ aese v0.16b, v4.16b
+ subs w2, w2, #16 /* last data? */
+ eor v0.16b, v0.16b, v5.16b /* final round */
+ bmi 6f
+ ld1 {v1.16b}, [x1], #16 /* load next input block */
+ eor v0.16b, v0.16b, v1.16b /* xor with mac */
+ bne 1b
+6: st1 {v0.2d}, [x0] /* store mac */
+ beq 10f
+ adds w2, w2, #16
+ beq 10f
+ mov w8, w2
+7: ldrb w7, [x1], #1
+ umov w6, v0.b[0]
+ eor w6, w6, w7
+ strb w6, [x0], #1
+ subs w2, w2, #1
+ beq 10f
+ ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */
+ b 7b
+8: mov w7, w8
+ add w8, w8, #16
+9: ext v1.16b, v1.16b, v1.16b, #1
+ adds w7, w7, #1
+ bne 9b
+ eor v0.16b, v0.16b, v1.16b
+ st1 {v0.2d}, [x0]
+10: str w8, [x3]
+ ret
+ENDPROC(ce_aes_ccm_auth_data)
+
+ /*
+ * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+ * u32 rounds);
+ */
+ENTRY(ce_aes_ccm_final)
+ ld1 {v3.2d}, [x2], #16 /* load first round key */
+ ld1 {v0.2d}, [x0] /* load mac */
+ cmp w3, #12 /* which key size? */
+ sub w3, w3, #2 /* modified # of rounds */
+ ld1 {v1.2d}, [x1] /* load 1st ctriv */
+ bmi 0f
+ bne 3f
+ mov v5.16b, v3.16b
+ b 2f
+0: mov v4.16b, v3.16b
+1: ld1 {v5.2d}, [x2], #16 /* load next round key */
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+2: ld1 {v3.2d}, [x2], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aese v1.16b, v5.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+3: ld1 {v4.2d}, [x2], #16 /* load next round key */
+ subs w3, w3, #3
+ aese v0.16b, v3.16b
+ aese v1.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+ bpl 1b
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ /* final round key cancels out */
+ eor v0.16b, v0.16b, v1.16b /* en-/decrypt the mac */
+ st1 {v0.2d}, [x0] /* store result */
+ ret
+ENDPROC(ce_aes_ccm_final)
+
+ .macro aes_ccm_do_crypt,enc
+ ldr x8, [x6, #8] /* load lower ctr */
+ ld1 {v0.2d}, [x5] /* load mac */
+ rev x8, x8 /* keep swabbed ctr in reg */
+0: /* outer loop */
+ ld1 {v1.1d}, [x6] /* load upper ctr */
+ prfm pldl1strm, [x1]
+ add x8, x8, #1
+ rev x9, x8
+ cmp w4, #12 /* which key size? */
+ sub w7, w4, #2 /* get modified # of rounds */
+ ins v1.d[1], x9 /* no carry in lower ctr */
+ ld1 {v3.2d}, [x3] /* load first round key */
+ add x10, x3, #16
+ bmi 1f
+ bne 4f
+ mov v5.16b, v3.16b
+ b 3f
+1: mov v4.16b, v3.16b
+ ld1 {v5.2d}, [x10], #16 /* load 2nd round key */
+2: /* inner loop: 3 rounds, 2x interleaved */
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+3: ld1 {v3.2d}, [x10], #16 /* load next round key */
+ aese v0.16b, v5.16b
+ aese v1.16b, v5.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+4: ld1 {v4.2d}, [x10], #16 /* load next round key */
+ subs w7, w7, #3
+ aese v0.16b, v3.16b
+ aese v1.16b, v3.16b
+ aesmc v0.16b, v0.16b
+ aesmc v1.16b, v1.16b
+ ld1 {v5.2d}, [x10], #16 /* load next round key */
+ bpl 2b
+ aese v0.16b, v4.16b
+ aese v1.16b, v4.16b
+ subs w2, w2, #16
+ bmi 6f /* partial block? */
+ ld1 {v2.16b}, [x1], #16 /* load next input block */
+ .if \enc == 1
+ eor v2.16b, v2.16b, v5.16b /* final round enc+mac */
+ eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */
+ .else
+ eor v2.16b, v2.16b, v1.16b /* xor with crypted ctr */
+ eor v1.16b, v2.16b, v5.16b /* final round enc */
+ .endif
+ eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
+ st1 {v1.16b}, [x0], #16 /* write output block */
+ bne 0b
+ rev x8, x8
+ st1 {v0.2d}, [x5] /* store mac */
+ str x8, [x6, #8] /* store lsb end of ctr (BE) */
+5: ret
+
+6: eor v0.16b, v0.16b, v5.16b /* final round mac */
+ eor v1.16b, v1.16b, v5.16b /* final round enc */
+ st1 {v0.2d}, [x5] /* store mac */
+ add w2, w2, #16 /* process partial tail block */
+7: ldrb w9, [x1], #1 /* get 1 byte of input */
+ umov w6, v1.b[0] /* get top crypted ctr byte */
+ umov w7, v0.b[0] /* get top mac byte */
+ .if \enc == 1
+ eor w7, w7, w9
+ eor w9, w9, w6
+ .else
+ eor w9, w9, w6
+ eor w7, w7, w9
+ .endif
+ strb w9, [x0], #1 /* store out byte */
+ strb w7, [x5], #1 /* store mac byte */
+ subs w2, w2, #1
+ beq 5b
+ ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */
+ ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */
+ b 7b
+ .endm
+
+ /*
+ * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+ * u8 const rk[], u32 rounds, u8 mac[],
+ * u8 ctr[]);
+ * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+ * u8 const rk[], u32 rounds, u8 mac[],
+ * u8 ctr[]);
+ */
+ENTRY(ce_aes_ccm_encrypt)
+ aes_ccm_do_crypt 1
+ENDPROC(ce_aes_ccm_encrypt)
+
+ENTRY(ce_aes_ccm_decrypt)
+ aes_ccm_do_crypt 0
+ENDPROC(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 0000000..9e6cdde9
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,297 @@
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/scatterwalk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+ u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+ u32 const rk[], u32 rounds, u8 mac[],
+ u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+ u32 const rk[], u32 rounds, u8 mac[],
+ u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+ u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+ int ret;
+
+ ret = crypto_aes_expand_key(ctx, in_key, key_len);
+ if (!ret)
+ return 0;
+
+ tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ if ((authsize & 1) || authsize < 4)
+ return -EINVAL;
+ return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ __be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+ u32 l = req->iv[0] + 1;
+
+ /* verify that CCM dimension 'L' is set correctly in the IV */
+ if (l < 2 || l > 8)
+ return -EINVAL;
+
+ /* verify that msglen can in fact be represented in L bytes */
+ if (l < 4 && msglen >> (8 * l))
+ return -EOVERFLOW;
+
+ /*
+ * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+ * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+ */
+ n[0] = 0;
+ n[1] = cpu_to_be32(msglen);
+
+ memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+ /*
+ * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+ * - bits 0..2 : max # of bytes required to represent msglen, minus 1
+ * (already set by caller)
+ * - bits 3..5 : size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+ * - bit 6 : indicates presence of authenticate-only data
+ */
+ maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+ if (req->assoclen)
+ maciv[0] |= 0x40;
+
+ memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+ return 0;
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+ struct scatter_walk walk;
+ u32 len = req->assoclen;
+ u32 macp = 0;
+
+ /* prepend the AAD with a length tag */
+ if (len < 0xff00) {
+ ltag.l = cpu_to_be16(len);
+ ltag.len = 2;
+ } else {
+ ltag.l = cpu_to_be16(0xfffe);
+ put_unaligned_be32(len, <ag.h);
+ ltag.len = 6;
+ }
+
+ ce_aes_ccm_auth_data(mac, (u8 *)<ag, ltag.len, &macp, ctx->key_enc,
+ num_rounds(ctx));
+ scatterwalk_start(&walk, req->assoc);
+
+ do {
+ u32 n = scatterwalk_clamp(&walk, len);
+ u8 *p;
+
+ if (!n) {
+ scatterwalk_start(&walk, sg_next(walk.sg));
+ n = scatterwalk_clamp(&walk, len);
+ }
+ p = scatterwalk_map(&walk);
+ ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
+ num_rounds(ctx));
+ len -= n;
+
+ scatterwalk_unmap(p);
+ scatterwalk_advance(&walk, n);
+ scatterwalk_done(&walk, 0, len);
+ } while (len);
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ struct blkcipher_desc desc = { .info = req->iv };
+ struct blkcipher_walk walk;
+ u8 __aligned(8) mac[AES_BLOCK_SIZE];
+ u8 buf[AES_BLOCK_SIZE];
+ u32 len = req->cryptlen;
+ int err;
+
+ err = ccm_init_mac(req, mac, len);
+ if (err)
+ return err;
+
+ kernel_neon_begin_partial(6);
+
+ if (req->assoclen)
+ ccm_calculate_auth_mac(req, mac);
+
+ /* preserve the original iv for the final round */
+ memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+ blkcipher_walk_init(&walk, req->dst, req->src, len);
+ err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+ AES_BLOCK_SIZE);
+
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ if (walk.nbytes == len)
+ tail = 0;
+
+ ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
+
+ len -= walk.nbytes - tail;
+ err = blkcipher_walk_done(&desc, &walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+ kernel_neon_end();
+
+ if (err)
+ return err;
+
+ /* copy authtag to end of dst */
+ scatterwalk_map_and_copy(mac, req->dst, req->cryptlen,
+ crypto_aead_authsize(aead), 1);
+
+ return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+ unsigned int authsize = crypto_aead_authsize(aead);
+ struct blkcipher_desc desc = { .info = req->iv };
+ struct blkcipher_walk walk;
+ u8 __aligned(8) mac[AES_BLOCK_SIZE];
+ u8 buf[AES_BLOCK_SIZE];
+ u32 len = req->cryptlen - authsize;
+ int err;
+
+ err = ccm_init_mac(req, mac, len);
+ if (err)
+ return err;
+
+ kernel_neon_begin_partial(6);
+
+ if (req->assoclen)
+ ccm_calculate_auth_mac(req, mac);
+
+ /* preserve the original iv for the final round */
+ memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+ blkcipher_walk_init(&walk, req->dst, req->src, len);
+ err = blkcipher_aead_walk_virt_block(&desc, &walk, aead,
+ AES_BLOCK_SIZE);
+
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+ if (walk.nbytes == len)
+ tail = 0;
+
+ ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
+
+ len -= walk.nbytes - tail;
+ err = blkcipher_walk_done(&desc, &walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
+ kernel_neon_end();
+
+ if (err)
+ return err;
+
+ /* compare calculated auth tag with the stored one */
+ scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize,
+ authsize, 0);
+
+ if (memcmp(mac, buf, authsize))
+ return -EBADMSG;
+ return 0;
+}
+
+static struct crypto_alg ccm_aes_alg = {
+ .cra_name = "ccm(aes)",
+ .cra_driver_name = "ccm-aes-ce",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_AEAD,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_aead_type,
+ .cra_module = THIS_MODULE,
+ .cra_aead = {
+ .ivsize = AES_BLOCK_SIZE,
+ .maxauthsize = AES_BLOCK_SIZE,
+ .setkey = ccm_setkey,
+ .setauthsize = ccm_setauthsize,
+ .encrypt = ccm_encrypt,
+ .decrypt = ccm_decrypt,
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ if (!(elf_hwcap & HWCAP_AES))
+ return -ENODEV;
+ return crypto_register_alg(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
new file mode 100644
index 0000000..2075e1a
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -0,0 +1,155 @@
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <crypto/aes.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+ u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct aes_block *out = (struct aes_block *)dst;
+ struct aes_block const *in = (struct aes_block *)src;
+ void *dummy0;
+ int dummy1;
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]], #16 ;"
+ " cmp %w[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aese v0.16b, v2.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aese v0.16b, v3.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %w[rounds], %w[rounds], #3 ;"
+ " aese v0.16b, v1.16b ;"
+ " aesmc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aese v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=Q"(*out),
+ [key] "=r"(dummy0),
+ [rounds] "=r"(dummy1)
+ : [in] "Q"(*in),
+ "1"(ctx->key_enc),
+ "2"(num_rounds(ctx) - 2)
+ : "cc");
+
+ kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+ struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct aes_block *out = (struct aes_block *)dst;
+ struct aes_block const *in = (struct aes_block *)src;
+ void *dummy0;
+ int dummy1;
+
+ kernel_neon_begin_partial(4);
+
+ __asm__(" ld1 {v0.16b}, %[in] ;"
+ " ld1 {v1.2d}, [%[key]], #16 ;"
+ " cmp %w[rounds], #10 ;"
+ " bmi 0f ;"
+ " bne 3f ;"
+ " mov v3.16b, v1.16b ;"
+ " b 2f ;"
+ "0: mov v2.16b, v1.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ "1: aesd v0.16b, v2.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "2: ld1 {v1.2d}, [%[key]], #16 ;"
+ " aesd v0.16b, v3.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ "3: ld1 {v2.2d}, [%[key]], #16 ;"
+ " subs %w[rounds], %w[rounds], #3 ;"
+ " aesd v0.16b, v1.16b ;"
+ " aesimc v0.16b, v0.16b ;"
+ " ld1 {v3.2d}, [%[key]], #16 ;"
+ " bpl 1b ;"
+ " aesd v0.16b, v2.16b ;"
+ " eor v0.16b, v0.16b, v3.16b ;"
+ " st1 {v0.16b}, %[out] ;"
+
+ : [out] "=Q"(*out),
+ [key] "=r"(dummy0),
+ [rounds] "=r"(dummy1)
+ : [in] "Q"(*in),
+ "1"(ctx->key_dec),
+ "2"(num_rounds(ctx) - 2)
+ : "cc");
+
+ kernel_neon_end();
+}
+
+static struct crypto_alg aes_alg = {
+ .cra_name = "aes",
+ .cra_driver_name = "aes-ce",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_cipher = {
+ .cia_min_keysize = AES_MIN_KEY_SIZE,
+ .cia_max_keysize = AES_MAX_KEY_SIZE,
+ .cia_setkey = crypto_aes_set_key,
+ .cia_encrypt = aes_cipher_encrypt,
+ .cia_decrypt = aes_cipher_decrypt
+ }
+};
+
+static int __init aes_mod_init(void)
+{
+ return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+ crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 0000000..685a18f
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,133 @@
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ * Crypto Extensions
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func) ENTRY(ce_ ## func)
+#define AES_ENDPROC(func) ENDPROC(ce_ ## func)
+
+ .arch armv8-a+crypto
+
+ /* preload all round keys */
+ .macro load_round_keys, rounds, rk
+ cmp \rounds, #12
+ blo 2222f /* 128 bits */
+ beq 1111f /* 192 bits */
+ ld1 {v17.16b-v18.16b}, [\rk], #32
+1111: ld1 {v19.16b-v20.16b}, [\rk], #32
+2222: ld1 {v21.16b-v24.16b}, [\rk], #64
+ ld1 {v25.16b-v28.16b}, [\rk], #64
+ ld1 {v29.16b-v31.16b}, [\rk]
+ .endm
+
+ /* prepare for encryption with key in rk[] */
+ .macro enc_prepare, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ /* prepare for encryption (again) but with new key in rk[] */
+ .macro enc_switch_key, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ /* prepare for decryption with key in rk[] */
+ .macro dec_prepare, rounds, rk, ignore
+ load_round_keys \rounds, \rk
+ .endm
+
+ .macro do_enc_Nx, de, mc, k, i0, i1, i2, i3
+ aes\de \i0\().16b, \k\().16b
+ .ifnb \i1
+ aes\de \i1\().16b, \k\().16b
+ .ifnb \i3
+ aes\de \i2\().16b, \k\().16b
+ aes\de \i3\().16b, \k\().16b
+ .endif
+ .endif
+ aes\mc \i0\().16b, \i0\().16b
+ .ifnb \i1
+ aes\mc \i1\().16b, \i1\().16b
+ .ifnb \i3
+ aes\mc \i2\().16b, \i2\().16b
+ aes\mc \i3\().16b, \i3\().16b
+ .endif
+ .endif
+ .endm
+
+ /* up to 4 interleaved encryption rounds with the same round key */
+ .macro round_Nx, enc, k, i0, i1, i2, i3
+ .ifc \enc, e
+ do_enc_Nx e, mc, \k, \i0, \i1, \i2, \i3
+ .else
+ do_enc_Nx d, imc, \k, \i0, \i1, \i2, \i3
+ .endif
+ .endm
+
+ /* up to 4 interleaved final rounds */
+ .macro fin_round_Nx, de, k, k2, i0, i1, i2, i3
+ aes\de \i0\().16b, \k\().16b
+ .ifnb \i1
+ aes\de \i1\().16b, \k\().16b
+ .ifnb \i3
+ aes\de \i2\().16b, \k\().16b
+ aes\de \i3\().16b, \k\().16b
+ .endif
+ .endif
+ eor \i0\().16b, \i0\().16b, \k2\().16b
+ .ifnb \i1
+ eor \i1\().16b, \i1\().16b, \k2\().16b
+ .ifnb \i3
+ eor \i2\().16b, \i2\().16b, \k2\().16b
+ eor \i3\().16b, \i3\().16b, \k2\().16b
+ .endif
+ .endif
+ .endm
+
+ /* up to 4 interleaved blocks */
+ .macro do_block_Nx, enc, rounds, i0, i1, i2, i3
+ cmp \rounds, #12
+ blo 2222f /* 128 bits */
+ beq 1111f /* 192 bits */
+ round_Nx \enc, v17, \i0, \i1, \i2, \i3
+ round_Nx \enc, v18, \i0, \i1, \i2, \i3
+1111: round_Nx \enc, v19, \i0, \i1, \i2, \i3
+ round_Nx \enc, v20, \i0, \i1, \i2, \i3
+2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+ round_Nx \enc, \key, \i0, \i1, \i2, \i3
+ .endr
+ fin_round_Nx \enc, v30, v31, \i0, \i1, \i2, \i3
+ .endm
+
+ .macro encrypt_block, in, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \in
+ .endm
+
+ .macro encrypt_block2x, i0, i1, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \i0, \i1
+ .endm
+
+ .macro encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+ do_block_Nx e, \rounds, \i0, \i1, \i2, \i3
+ .endm
+
+ .macro decrypt_block, in, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \in
+ .endm
+
+ .macro decrypt_block2x, i0, i1, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \i0, \i1
+ .endm
+
+ .macro decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+ do_block_Nx d, \rounds, \i0, \i1, \i2, \i3
+ .endm
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 0000000..60f2f4c
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,446 @@
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE "ce"
+#define PRIO 300
+#define aes_ecb_encrypt ce_aes_ecb_encrypt
+#define aes_ecb_decrypt ce_aes_ecb_decrypt
+#define aes_cbc_encrypt ce_aes_cbc_encrypt
+#define aes_cbc_decrypt ce_aes_cbc_decrypt
+#define aes_ctr_encrypt ce_aes_ctr_encrypt
+#define aes_xts_encrypt ce_aes_xts_encrypt
+#define aes_xts_decrypt ce_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE "neon"
+#define PRIO 200
+#define aes_ecb_encrypt neon_aes_ecb_encrypt
+#define aes_ecb_decrypt neon_aes_ecb_decrypt
+#define aes_cbc_encrypt neon_aes_cbc_encrypt
+#define aes_cbc_decrypt neon_aes_cbc_decrypt
+#define aes_ctr_encrypt neon_aes_ctr_encrypt
+#define aes_xts_encrypt neon_aes_xts_encrypt
+#define aes_xts_decrypt neon_aes_xts_decrypt
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+MODULE_ALIAS("ecb(aes)");
+MODULE_ALIAS("cbc(aes)");
+MODULE_ALIAS("ctr(aes)");
+MODULE_ALIAS("xts(aes)");
+#endif
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, int first);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, int first);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int first);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 iv[], int first);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+ int rounds, int blocks, u8 ctr[], int first);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+ int rounds, int blocks, u8 const rk2[], u8 iv[],
+ int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+ int rounds, int blocks, u8 const rk2[], u8 iv[],
+ int first);
+
+struct crypto_aes_xts_ctx {
+ struct crypto_aes_ctx key1;
+ struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+ int ret;
+
+ ret = crypto_aes_expand_key(&ctx->key1, in_key, key_len / 2);
+ if (!ret)
+ ret = crypto_aes_expand_key(&ctx->key2, &in_key[key_len / 2],
+ key_len / 2);
+ if (!ret)
+ return 0;
+
+ tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_dec, rounds, blocks, first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+ first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_dec, rounds, blocks, walk.iv,
+ first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+ return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key_length / 4;
+ struct blkcipher_walk walk;
+ int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+ first = 1;
+ kernel_neon_begin();
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key_enc, rounds, blocks, walk.iv,
+ first);
+ first = 0;
+ nbytes -= blocks * AES_BLOCK_SIZE;
+ if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+ break;
+ err = blkcipher_walk_done(desc, &walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (nbytes) {
+ u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+ u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+ /*
+ * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+ * to tell aes_ctr_encrypt() to only read half a block.
+ */
+ blocks = (nbytes <= 8) ? -1 : 1;
+
+ aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc, rounds,
+ blocks, walk.iv, first);
+ memcpy(tdst, tail, nbytes);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key1.key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key1.key_enc, rounds, blocks,
+ (u8 *)ctx->key2.key_enc, walk.iv, first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ int err, first, rounds = 6 + ctx->key1.key_length / 4;
+ struct blkcipher_walk walk;
+ unsigned int blocks;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ kernel_neon_begin();
+ for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+ aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ (u8 *)ctx->key1.key_dec, rounds, blocks,
+ (u8 *)ctx->key2.key_enc, walk.iv, first);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+ kernel_neon_end();
+
+ return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+ .cra_name = "__ecb-aes-" MODE,
+ .cra_driver_name = "__driver-ecb-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = crypto_aes_set_key,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+ },
+}, {
+ .cra_name = "__cbc-aes-" MODE,
+ .cra_driver_name = "__driver-cbc-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = crypto_aes_set_key,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ },
+}, {
+ .cra_name = "__ctr-aes-" MODE,
+ .cra_driver_name = "__driver-ctr-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = crypto_aes_set_key,
+ .encrypt = ctr_encrypt,
+ .decrypt = ctr_encrypt,
+ },
+}, {
+ .cra_name = "__xts-aes-" MODE,
+ .cra_driver_name = "__driver-xts-aes-" MODE,
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_xts_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_blkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = xts_set_key,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ },
+}, {
+ .cra_name = "ecb(aes)",
+ .cra_driver_name = "ecb-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "cbc(aes)",
+ .cra_driver_name = "cbc-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "ctr(aes)",
+ .cra_driver_name = "ctr-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+}, {
+ .cra_name = "xts(aes)",
+ .cra_driver_name = "xts-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_helper_ctx),
+ .cra_alignmask = 7,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_init = ablk_init,
+ .cra_exit = ablk_exit,
+ .cra_ablkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ }
+} };
+
+static int __init aes_init(void)
+{
+ return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+ crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 0000000..f6e372c
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,532 @@
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+ .text
+ .align 4
+
+/*
+ * There are several ways to instantiate this code:
+ * - no interleave, all inline
+ * - 2-way interleave, 2x calls out of line (-DINTERLEAVE=2)
+ * - 2-way interleave, all inline (-DINTERLEAVE=2 -DINTERLEAVE_INLINE)
+ * - 4-way interleave, 4x calls out of line (-DINTERLEAVE=4)
+ * - 4-way interleave, all inline (-DINTERLEAVE=4 -DINTERLEAVE_INLINE)
+ *
+ * Macros imported by this code:
+ * - enc_prepare - setup NEON registers for encryption
+ * - dec_prepare - setup NEON registers for decryption
+ * - enc_switch_key - change to new key after having prepared for encryption
+ * - encrypt_block - encrypt a single block
+ * - decrypt block - decrypt a single block
+ * - encrypt_block2x - encrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - decrypt_block2x - decrypt 2 blocks in parallel (if INTERLEAVE == 2)
+ * - encrypt_block4x - encrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ * - decrypt_block4x - decrypt 4 blocks in parallel (if INTERLEAVE == 4)
+ */
+
+#if defined(INTERLEAVE) && !defined(INTERLEAVE_INLINE)
+#define FRAME_PUSH stp x29, x30, [sp,#-16]! ; mov x29, sp
+#define FRAME_POP ldp x29, x30, [sp],#16
+
+#if INTERLEAVE == 2
+
+aes_encrypt_block2x:
+ encrypt_block2x v0, v1, w3, x2, x6, w7
+ ret
+ENDPROC(aes_encrypt_block2x)
+
+aes_decrypt_block2x:
+ decrypt_block2x v0, v1, w3, x2, x6, w7
+ ret
+ENDPROC(aes_decrypt_block2x)
+
+#elif INTERLEAVE == 4
+
+aes_encrypt_block4x:
+ encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ ret
+ENDPROC(aes_encrypt_block4x)
+
+aes_decrypt_block4x:
+ decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ ret
+ENDPROC(aes_decrypt_block4x)
+
+#else
+#error INTERLEAVE should equal 2 or 4
+#endif
+
+ .macro do_encrypt_block2x
+ bl aes_encrypt_block2x
+ .endm
+
+ .macro do_decrypt_block2x
+ bl aes_decrypt_block2x
+ .endm
+
+ .macro do_encrypt_block4x
+ bl aes_encrypt_block4x
+ .endm
+
+ .macro do_decrypt_block4x
+ bl aes_decrypt_block4x
+ .endm
+
+#else
+#define FRAME_PUSH
+#define FRAME_POP
+
+ .macro do_encrypt_block2x
+ encrypt_block2x v0, v1, w3, x2, x6, w7
+ .endm
+
+ .macro do_decrypt_block2x
+ decrypt_block2x v0, v1, w3, x2, x6, w7
+ .endm
+
+ .macro do_encrypt_block4x
+ encrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ .endm
+
+ .macro do_decrypt_block4x
+ decrypt_block4x v0, v1, v2, v3, w3, x2, x6, w7
+ .endm
+
+#endif
+
+ /*
+ * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, int first)
+ * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, int first)
+ */
+
+AES_ENTRY(aes_ecb_encrypt)
+ FRAME_PUSH
+ cbz w5, .LecbencloopNx
+
+ enc_prepare w3, x2, x5
+
+.LecbencloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lecbenc1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
+ do_encrypt_block2x
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ do_encrypt_block4x
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LecbencloopNx
+.Lecbenc1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lecbencout
+#endif
+.Lecbencloop:
+ ld1 {v0.16b}, [x1], #16 /* get next pt block */
+ encrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lecbencloop
+.Lecbencout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ecb_encrypt)
+
+
+AES_ENTRY(aes_ecb_decrypt)
+ FRAME_PUSH
+ cbz w5, .LecbdecloopNx
+
+ dec_prepare w3, x2, x5
+
+.LecbdecloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lecbdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ do_decrypt_block2x
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ do_decrypt_block4x
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LecbdecloopNx
+.Lecbdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lecbdecout
+#endif
+.Lecbdecloop:
+ ld1 {v0.16b}, [x1], #16 /* get next ct block */
+ decrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lecbdecloop
+.Lecbdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ecb_decrypt)
+
+
+ /*
+ * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int first)
+ * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 iv[], int first)
+ */
+
+AES_ENTRY(aes_cbc_encrypt)
+ cbz w6, .Lcbcencloop
+
+ ld1 {v0.16b}, [x5] /* get iv */
+ enc_prepare w3, x2, x5
+
+.Lcbcencloop:
+ ld1 {v1.16b}, [x1], #16 /* get next pt block */
+ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */
+ encrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lcbcencloop
+ ret
+AES_ENDPROC(aes_cbc_encrypt)
+
+
+AES_ENTRY(aes_cbc_decrypt)
+ FRAME_PUSH
+ cbz w6, .LcbcdecloopNx
+
+ ld1 {v7.16b}, [x5] /* get iv */
+ dec_prepare w3, x2, x5
+
+.LcbcdecloopNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lcbcdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ mov v2.16b, v0.16b
+ mov v3.16b, v1.16b
+ do_decrypt_block2x
+ eor v0.16b, v0.16b, v7.16b
+ eor v1.16b, v1.16b, v2.16b
+ mov v7.16b, v3.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ mov v4.16b, v0.16b
+ mov v5.16b, v1.16b
+ mov v6.16b, v2.16b
+ do_decrypt_block4x
+ sub x1, x1, #16
+ eor v0.16b, v0.16b, v7.16b
+ eor v1.16b, v1.16b, v4.16b
+ ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */
+ eor v2.16b, v2.16b, v5.16b
+ eor v3.16b, v3.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+#endif
+ b .LcbcdecloopNx
+.Lcbcdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lcbcdecout
+#endif
+.Lcbcdecloop:
+ ld1 {v1.16b}, [x1], #16 /* get next ct block */
+ mov v0.16b, v1.16b /* ...and copy to v0 */
+ decrypt_block v0, w3, x2, x5, w6
+ eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
+ mov v7.16b, v1.16b /* ct is next iv */
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ bne .Lcbcdecloop
+.Lcbcdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_cbc_decrypt)
+
+
+ /*
+ * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+ * int blocks, u8 ctr[], int first)
+ */
+
+AES_ENTRY(aes_ctr_encrypt)
+ FRAME_PUSH
+ cbnz w6, .Lctrfirst /* 1st time around? */
+ umov x5, v4.d[1] /* keep swabbed ctr in reg */
+ rev x5, x5
+#if INTERLEAVE >= 2
+ cmn w5, w4 /* 32 bit overflow? */
+ bcs .Lctrinc
+ add x5, x5, #1 /* increment BE ctr */
+ b .LctrincNx
+#else
+ b .Lctrinc
+#endif
+.Lctrfirst:
+ enc_prepare w3, x2, x6
+ ld1 {v4.16b}, [x5]
+ umov x5, v4.d[1] /* keep swabbed ctr in reg */
+ rev x5, x5
+#if INTERLEAVE >= 2
+ cmn w5, w4 /* 32 bit overflow? */
+ bcs .Lctrloop
+.LctrloopNx:
+ subs w4, w4, #INTERLEAVE
+ bmi .Lctr1x
+#if INTERLEAVE == 2
+ mov v0.8b, v4.8b
+ mov v1.8b, v4.8b
+ rev x7, x5
+ add x5, x5, #1
+ ins v0.d[1], x7
+ rev x7, x5
+ add x5, x5, #1
+ ins v1.d[1], x7
+ ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */
+ do_encrypt_block2x
+ eor v0.16b, v0.16b, v2.16b
+ eor v1.16b, v1.16b, v3.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+#else
+ ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
+ dup v7.4s, w5
+ mov v0.16b, v4.16b
+ add v7.4s, v7.4s, v8.4s
+ mov v1.16b, v4.16b
+ rev32 v8.16b, v7.16b
+ mov v2.16b, v4.16b
+ mov v3.16b, v4.16b
+ mov v1.s[3], v8.s[0]
+ mov v2.s[3], v8.s[1]
+ mov v3.s[3], v8.s[2]
+ ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */
+ do_encrypt_block4x
+ eor v0.16b, v5.16b, v0.16b
+ ld1 {v5.16b}, [x1], #16 /* get 1 input block */
+ eor v1.16b, v6.16b, v1.16b
+ eor v2.16b, v7.16b, v2.16b
+ eor v3.16b, v5.16b, v3.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ add x5, x5, #INTERLEAVE
+#endif
+ cbz w4, .LctroutNx
+.LctrincNx:
+ rev x7, x5
+ ins v4.d[1], x7
+ b .LctrloopNx
+.LctroutNx:
+ sub x5, x5, #1
+ rev x7, x5
+ ins v4.d[1], x7
+ b .Lctrout
+.Lctr1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lctrout
+#endif
+.Lctrloop:
+ mov v0.16b, v4.16b
+ encrypt_block v0, w3, x2, x6, w7
+ subs w4, w4, #1
+ bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */
+ ld1 {v3.16b}, [x1], #16
+ eor v3.16b, v0.16b, v3.16b
+ st1 {v3.16b}, [x0], #16
+ beq .Lctrout
+.Lctrinc:
+ adds x5, x5, #1 /* increment BE ctr */
+ rev x7, x5
+ ins v4.d[1], x7
+ bcc .Lctrloop /* no overflow? */
+ umov x7, v4.d[0] /* load upper word of ctr */
+ rev x7, x7 /* ... to handle the carry */
+ add x7, x7, #1
+ rev x7, x7
+ ins v4.d[0], x7
+ b .Lctrloop
+.Lctrhalfblock:
+ ld1 {v3.8b}, [x1]
+ eor v3.8b, v0.8b, v3.8b
+ st1 {v3.8b}, [x0]
+.Lctrout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_ctr_encrypt)
+ .ltorg
+
+
+ /*
+ * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+ * int blocks, u8 const rk2[], u8 iv[], int first)
+ * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+ * int blocks, u8 const rk2[], u8 iv[], int first)
+ */
+
+ .macro next_tweak, out, in, const, tmp
+ sshr \tmp\().2d, \in\().2d, #63
+ and \tmp\().16b, \tmp\().16b, \const\().16b
+ add \out\().2d, \in\().2d, \in\().2d
+ ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+ eor \out\().16b, \out\().16b, \tmp\().16b
+ .endm
+
+.Lxts_mul_x:
+ .word 1, 0, 0x87, 0
+
+AES_ENTRY(aes_xts_encrypt)
+ FRAME_PUSH
+ cbz w7, .LxtsencloopNx
+
+ ld1 {v4.16b}, [x6]
+ enc_prepare w3, x5, x6
+ encrypt_block v4, w3, x5, x6, w7 /* first tweak */
+ enc_switch_key w3, x2, x6
+ ldr q7, .Lxts_mul_x
+ b .LxtsencNx
+
+.LxtsencloopNx:
+ ldr q7, .Lxts_mul_x
+ next_tweak v4, v4, v7, v8
+.LxtsencNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lxtsenc1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 pt blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ do_encrypt_block2x
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+ cbz w4, .LxtsencoutNx
+ next_tweak v4, v5, v7, v8
+ b .LxtsencNx
+.LxtsencoutNx:
+ mov v4.16b, v5.16b
+ b .Lxtsencout
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ next_tweak v6, v5, v7, v8
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ next_tweak v7, v6, v7, v8
+ eor v3.16b, v3.16b, v7.16b
+ do_encrypt_block4x
+ eor v3.16b, v3.16b, v7.16b
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ mov v4.16b, v7.16b
+ cbz w4, .Lxtsencout
+ b .LxtsencloopNx
+#endif
+.Lxtsenc1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lxtsencout
+#endif
+.Lxtsencloop:
+ ld1 {v1.16b}, [x1], #16
+ eor v0.16b, v1.16b, v4.16b
+ encrypt_block v0, w3, x2, x6, w7
+ eor v0.16b, v0.16b, v4.16b
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ beq .Lxtsencout
+ next_tweak v4, v4, v7, v8
+ b .Lxtsencloop
+.Lxtsencout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_xts_encrypt)
+
+
+AES_ENTRY(aes_xts_decrypt)
+ FRAME_PUSH
+ cbz w7, .LxtsdecloopNx
+
+ ld1 {v4.16b}, [x6]
+ enc_prepare w3, x5, x6
+ encrypt_block v4, w3, x5, x6, w7 /* first tweak */
+ dec_prepare w3, x2, x6
+ ldr q7, .Lxts_mul_x
+ b .LxtsdecNx
+
+.LxtsdecloopNx:
+ ldr q7, .Lxts_mul_x
+ next_tweak v4, v4, v7, v8
+.LxtsdecNx:
+#if INTERLEAVE >= 2
+ subs w4, w4, #INTERLEAVE
+ bmi .Lxtsdec1x
+#if INTERLEAVE == 2
+ ld1 {v0.16b-v1.16b}, [x1], #32 /* get 2 ct blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ do_decrypt_block2x
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ st1 {v0.16b-v1.16b}, [x0], #32
+ cbz w4, .LxtsdecoutNx
+ next_tweak v4, v5, v7, v8
+ b .LxtsdecNx
+.LxtsdecoutNx:
+ mov v4.16b, v5.16b
+ b .Lxtsdecout
+#else
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ next_tweak v5, v4, v7, v8
+ eor v0.16b, v0.16b, v4.16b
+ next_tweak v6, v5, v7, v8
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ next_tweak v7, v6, v7, v8
+ eor v3.16b, v3.16b, v7.16b
+ do_decrypt_block4x
+ eor v3.16b, v3.16b, v7.16b
+ eor v0.16b, v0.16b, v4.16b
+ eor v1.16b, v1.16b, v5.16b
+ eor v2.16b, v2.16b, v6.16b
+ st1 {v0.16b-v3.16b}, [x0], #64
+ mov v4.16b, v7.16b
+ cbz w4, .Lxtsdecout
+ b .LxtsdecloopNx
+#endif
+.Lxtsdec1x:
+ adds w4, w4, #INTERLEAVE
+ beq .Lxtsdecout
+#endif
+.Lxtsdecloop:
+ ld1 {v1.16b}, [x1], #16
+ eor v0.16b, v1.16b, v4.16b
+ decrypt_block v0, w3, x2, x6, w7
+ eor v0.16b, v0.16b, v4.16b
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
+ beq .Lxtsdecout
+ next_tweak v4, v4, v7, v8
+ b .Lxtsdecloop
+.Lxtsdecout:
+ FRAME_POP
+ ret
+AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 0000000..b93170e
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,382 @@
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+#define AES_ENTRY(func) ENTRY(neon_ ## func)
+#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
+
+ /* multiply by polynomial 'x' in GF(2^8) */
+ .macro mul_by_x, out, in, temp, const
+ sshr \temp, \in, #7
+ add \out, \in, \in
+ and \temp, \temp, \const
+ eor \out, \out, \temp
+ .endm
+
+ /* preload the entire Sbox */
+ .macro prepare, sbox, shiftrows, temp
+ adr \temp, \sbox
+ movi v12.16b, #0x40
+ ldr q13, \shiftrows
+ movi v14.16b, #0x1b
+ ld1 {v16.16b-v19.16b}, [\temp], #64
+ ld1 {v20.16b-v23.16b}, [\temp], #64
+ ld1 {v24.16b-v27.16b}, [\temp], #64
+ ld1 {v28.16b-v31.16b}, [\temp]
+ .endm
+
+ /* do preload for encryption */
+ .macro enc_prepare, ignore0, ignore1, temp
+ prepare .LForward_Sbox, .LForward_ShiftRows, \temp
+ .endm
+
+ .macro enc_switch_key, ignore0, ignore1, temp
+ /* do nothing */
+ .endm
+
+ /* do preload for decryption */
+ .macro dec_prepare, ignore0, ignore1, temp
+ prepare .LReverse_Sbox, .LReverse_ShiftRows, \temp
+ .endm
+
+ /* apply SubBytes transformation using the the preloaded Sbox */
+ .macro sub_bytes, in
+ sub v9.16b, \in\().16b, v12.16b
+ tbl \in\().16b, {v16.16b-v19.16b}, \in\().16b
+ sub v10.16b, v9.16b, v12.16b
+ tbx \in\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v11.16b, v10.16b, v12.16b
+ tbx \in\().16b, {v24.16b-v27.16b}, v10.16b
+ tbx \in\().16b, {v28.16b-v31.16b}, v11.16b
+ .endm
+
+ /* apply MixColumns transformation */
+ .macro mix_columns, in
+ mul_by_x v10.16b, \in\().16b, v9.16b, v14.16b
+ rev32 v8.8h, \in\().8h
+ eor \in\().16b, v10.16b, \in\().16b
+ shl v9.4s, v8.4s, #24
+ shl v11.4s, \in\().4s, #24
+ sri v9.4s, v8.4s, #8
+ sri v11.4s, \in\().4s, #8
+ eor v9.16b, v9.16b, v8.16b
+ eor v10.16b, v10.16b, v9.16b
+ eor \in\().16b, v10.16b, v11.16b
+ .endm
+
+ /* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+ .macro inv_mix_columns, in
+ mul_by_x v11.16b, \in\().16b, v10.16b, v14.16b
+ mul_by_x v11.16b, v11.16b, v10.16b, v14.16b
+ eor \in\().16b, \in\().16b, v11.16b
+ rev32 v11.8h, v11.8h
+ eor \in\().16b, \in\().16b, v11.16b
+ mix_columns \in
+ .endm
+
+ .macro do_block, enc, in, rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
+ tbl \in\().16b, {\in\().16b}, v13.16b /* ShiftRows */
+ sub_bytes \in
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns \in
+ .else
+ inv_mix_columns \in
+ .endif
+ b 1111b
+2222: eor \in\().16b, \in\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro encrypt_block, in, rounds, rk, rkp, i
+ do_block 1, \in, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block, in, rounds, rk, rkp, i
+ do_block 0, \in, \rounds, \rk, \rkp, \i
+ .endm
+
+ /*
+ * Interleaved versions: functionally equivalent to the
+ * ones above, but applied to 2 or 4 AES states in parallel.
+ */
+
+ .macro sub_bytes_2x, in0, in1
+ sub v8.16b, \in0\().16b, v12.16b
+ sub v9.16b, \in1\().16b, v12.16b
+ tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+ tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+ sub v10.16b, v8.16b, v12.16b
+ sub v11.16b, v9.16b, v12.16b
+ tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
+ tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v8.16b, v10.16b, v12.16b
+ sub v9.16b, v11.16b, v12.16b
+ tbx \in0\().16b, {v24.16b-v27.16b}, v10.16b
+ tbx \in1\().16b, {v24.16b-v27.16b}, v11.16b
+ tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
+ tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
+ .endm
+
+ .macro sub_bytes_4x, in0, in1, in2, in3
+ sub v8.16b, \in0\().16b, v12.16b
+ tbl \in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+ sub v9.16b, \in1\().16b, v12.16b
+ tbl \in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+ sub v10.16b, \in2\().16b, v12.16b
+ tbl \in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+ sub v11.16b, \in3\().16b, v12.16b
+ tbl \in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+ tbx \in0\().16b, {v20.16b-v23.16b}, v8.16b
+ tbx \in1\().16b, {v20.16b-v23.16b}, v9.16b
+ sub v8.16b, v8.16b, v12.16b
+ tbx \in2\().16b, {v20.16b-v23.16b}, v10.16b
+ sub v9.16b, v9.16b, v12.16b
+ tbx \in3\().16b, {v20.16b-v23.16b}, v11.16b
+ sub v10.16b, v10.16b, v12.16b
+ tbx \in0\().16b, {v24.16b-v27.16b}, v8.16b
+ sub v11.16b, v11.16b, v12.16b
+ tbx \in1\().16b, {v24.16b-v27.16b}, v9.16b
+ sub v8.16b, v8.16b, v12.16b
+ tbx \in2\().16b, {v24.16b-v27.16b}, v10.16b
+ sub v9.16b, v9.16b, v12.16b
+ tbx \in3\().16b, {v24.16b-v27.16b}, v11.16b
+ sub v10.16b, v10.16b, v12.16b
+ tbx \in0\().16b, {v28.16b-v31.16b}, v8.16b
+ sub v11.16b, v11.16b, v12.16b
+ tbx \in1\().16b, {v28.16b-v31.16b}, v9.16b
+ tbx \in2\().16b, {v28.16b-v31.16b}, v10.16b
+ tbx \in3\().16b, {v28.16b-v31.16b}, v11.16b
+ .endm
+
+ .macro mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+ sshr \tmp0\().16b, \in0\().16b, #7
+ add \out0\().16b, \in0\().16b, \in0\().16b
+ sshr \tmp1\().16b, \in1\().16b, #7
+ and \tmp0\().16b, \tmp0\().16b, \const\().16b
+ add \out1\().16b, \in1\().16b, \in1\().16b
+ and \tmp1\().16b, \tmp1\().16b, \const\().16b
+ eor \out0\().16b, \out0\().16b, \tmp0\().16b
+ eor \out1\().16b, \out1\().16b, \tmp1\().16b
+ .endm
+
+ .macro mix_columns_2x, in0, in1
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ rev32 v10.8h, \in0\().8h
+ rev32 v11.8h, \in1\().8h
+ eor \in0\().16b, v8.16b, \in0\().16b
+ eor \in1\().16b, v9.16b, \in1\().16b
+ shl v12.4s, v10.4s, #24
+ shl v13.4s, v11.4s, #24
+ eor v8.16b, v8.16b, v10.16b
+ sri v12.4s, v10.4s, #8
+ shl v10.4s, \in0\().4s, #24
+ eor v9.16b, v9.16b, v11.16b
+ sri v13.4s, v11.4s, #8
+ shl v11.4s, \in1\().4s, #24
+ sri v10.4s, \in0\().4s, #8
+ eor \in0\().16b, v8.16b, v12.16b
+ sri v11.4s, \in1\().4s, #8
+ eor \in1\().16b, v9.16b, v13.16b
+ eor \in0\().16b, v10.16b, \in0\().16b
+ eor \in1\().16b, v11.16b, \in1\().16b
+ .endm
+
+ .macro inv_mix_cols_2x, in0, in1
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ mul_by_x_2x v8, v9, v8, v9, v10, v11, v14
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ rev32 v8.8h, v8.8h
+ rev32 v9.8h, v9.8h
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ mix_columns_2x \in0, \in1
+ .endm
+
+ .macro inv_mix_cols_4x, in0, in1, in2, in3
+ mul_by_x_2x v8, v9, \in0, \in1, v10, v11, v14
+ mul_by_x_2x v10, v11, \in2, \in3, v12, v13, v14
+ mul_by_x_2x v8, v9, v8, v9, v12, v13, v14
+ mul_by_x_2x v10, v11, v10, v11, v12, v13, v14
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ eor \in2\().16b, \in2\().16b, v10.16b
+ eor \in3\().16b, \in3\().16b, v11.16b
+ rev32 v8.8h, v8.8h
+ rev32 v9.8h, v9.8h
+ rev32 v10.8h, v10.8h
+ rev32 v11.8h, v11.8h
+ eor \in0\().16b, \in0\().16b, v8.16b
+ eor \in1\().16b, \in1\().16b, v9.16b
+ eor \in2\().16b, \in2\().16b, v10.16b
+ eor \in3\().16b, \in3\().16b, v11.16b
+ mix_columns_2x \in0, \in1
+ mix_columns_2x \in2, \in3
+ .endm
+
+ .macro do_block_2x, enc, in0, in1 rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ sub_bytes_2x \in0, \in1
+ tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
+ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns_2x \in0, \in1
+ ldr q13, .LForward_ShiftRows
+ .else
+ inv_mix_cols_2x \in0, \in1
+ ldr q13, .LReverse_ShiftRows
+ .endif
+ movi v12.16b, #0x40
+ b 1111b
+2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+ ld1 {v15.16b}, [\rk]
+ add \rkp, \rk, #16
+ mov \i, \rounds
+1111: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
+ eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
+ sub_bytes_4x \in0, \in1, \in2, \in3
+ tbl \in0\().16b, {\in0\().16b}, v13.16b /* ShiftRows */
+ tbl \in1\().16b, {\in1\().16b}, v13.16b /* ShiftRows */
+ tbl \in2\().16b, {\in2\().16b}, v13.16b /* ShiftRows */
+ tbl \in3\().16b, {\in3\().16b}, v13.16b /* ShiftRows */
+ ld1 {v15.16b}, [\rkp], #16
+ subs \i, \i, #1
+ beq 2222f
+ .if \enc == 1
+ mix_columns_2x \in0, \in1
+ mix_columns_2x \in2, \in3
+ ldr q13, .LForward_ShiftRows
+ .else
+ inv_mix_cols_4x \in0, \in1, \in2, \in3
+ ldr q13, .LReverse_ShiftRows
+ .endif
+ movi v12.16b, #0x40
+ b 1111b
+2222: eor \in0\().16b, \in0\().16b, v15.16b /* ^round key */
+ eor \in1\().16b, \in1\().16b, v15.16b /* ^round key */
+ eor \in2\().16b, \in2\().16b, v15.16b /* ^round key */
+ eor \in3\().16b, \in3\().16b, v15.16b /* ^round key */
+ .endm
+
+ .macro encrypt_block2x, in0, in1, rounds, rk, rkp, i
+ do_block_2x 1, \in0, \in1, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block2x, in0, in1, rounds, rk, rkp, i
+ do_block_2x 0, \in0, \in1, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+ do_block_4x 1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+ .endm
+
+ .macro decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+ do_block_4x 0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+ .endm
+
+#include "aes-modes.S"
+
+ .text
+ .align 4
+.LForward_ShiftRows:
+ .byte 0x0, 0x5, 0xa, 0xf, 0x4, 0x9, 0xe, 0x3
+ .byte 0x8, 0xd, 0x2, 0x7, 0xc, 0x1, 0x6, 0xb
+
+.LReverse_ShiftRows:
+ .byte 0x0, 0xd, 0xa, 0x7, 0x4, 0x1, 0xe, 0xb
+ .byte 0x8, 0x5, 0x2, 0xf, 0xc, 0x9, 0x6, 0x3
+
+.LForward_Sbox:
+ .byte 0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
+ .byte 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
+ .byte 0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
+ .byte 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
+ .byte 0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
+ .byte 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
+ .byte 0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
+ .byte 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
+ .byte 0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
+ .byte 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
+ .byte 0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
+ .byte 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
+ .byte 0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
+ .byte 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
+ .byte 0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
+ .byte 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
+ .byte 0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
+ .byte 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
+ .byte 0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
+ .byte 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
+ .byte 0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
+ .byte 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
+ .byte 0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
+ .byte 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
+ .byte 0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
+ .byte 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
+ .byte 0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
+ .byte 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
+ .byte 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
+ .byte 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
+ .byte 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
+ .byte 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
+
+.LReverse_Sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+ .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 0000000..b9e6eaf41
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,95 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
+ *
+ * Copyright (c) 2009 Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ * Vinodh Gopal
+ * Erdinc Ozturk
+ * Deniz Karakoyunlu
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ DATA .req v0
+ SHASH .req v1
+ IN1 .req v2
+ T1 .req v2
+ T2 .req v3
+ T3 .req v4
+ VZR .req v5
+
+ .text
+ .arch armv8-a+crypto
+
+ /*
+ * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ * struct ghash_key const *k, const char *head)
+ */
+ENTRY(pmull_ghash_update)
+ ld1 {DATA.16b}, [x1]
+ ld1 {SHASH.16b}, [x3]
+ eor VZR.16b, VZR.16b, VZR.16b
+
+ /* do the head block first, if supplied */
+ cbz x4, 0f
+ ld1 {IN1.2d}, [x4]
+ b 1f
+
+0: ld1 {IN1.2d}, [x2], #16
+ sub w0, w0, #1
+1: ext IN1.16b, IN1.16b, IN1.16b, #8
+CPU_LE( rev64 IN1.16b, IN1.16b )
+ eor DATA.16b, DATA.16b, IN1.16b
+
+ /* multiply DATA by SHASH in GF(2^128) */
+ ext T2.16b, DATA.16b, DATA.16b, #8
+ ext T3.16b, SHASH.16b, SHASH.16b, #8
+ eor T2.16b, T2.16b, DATA.16b
+ eor T3.16b, T3.16b, SHASH.16b
+
+ pmull2 T1.1q, SHASH.2d, DATA.2d // a1 * b1
+ pmull DATA.1q, SHASH.1d, DATA.1d // a0 * b0
+ pmull T2.1q, T2.1d, T3.1d // (a1 + a0)(b1 + b0)
+ eor T2.16b, T2.16b, T1.16b // (a0 * b1) + (a1 * b0)
+ eor T2.16b, T2.16b, DATA.16b
+
+ ext T3.16b, VZR.16b, T2.16b, #8
+ ext T2.16b, T2.16b, VZR.16b, #8
+ eor DATA.16b, DATA.16b, T3.16b
+ eor T1.16b, T1.16b, T2.16b // <T1:DATA> is result of
+ // carry-less multiplication
+
+ /* first phase of the reduction */
+ shl T3.2d, DATA.2d, #1
+ eor T3.16b, T3.16b, DATA.16b
+ shl T3.2d, T3.2d, #5
+ eor T3.16b, T3.16b, DATA.16b
+ shl T3.2d, T3.2d, #57
+ ext T2.16b, VZR.16b, T3.16b, #8
+ ext T3.16b, T3.16b, VZR.16b, #8
+ eor DATA.16b, DATA.16b, T2.16b
+ eor T1.16b, T1.16b, T3.16b
+
+ /* second phase of the reduction */
+ ushr T2.2d, DATA.2d, #5
+ eor T2.16b, T2.16b, DATA.16b
+ ushr T2.2d, T2.2d, #1
+ eor T2.16b, T2.16b, DATA.16b
+ ushr T2.2d, T2.2d, #1
+ eor T1.16b, T1.16b, T2.16b
+ eor DATA.16b, DATA.16b, T1.16b
+
+ cbnz w0, 0b
+
+ st1 {DATA.16b}, [x1]
+ ret
+ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 0000000..b92baf3
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,155 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+#define GHASH_BLOCK_SIZE 16
+#define GHASH_DIGEST_SIZE 16
+
+struct ghash_key {
+ u64 a;
+ u64 b;
+};
+
+struct ghash_desc_ctx {
+ u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+ u8 buf[GHASH_BLOCK_SIZE];
+ u32 count;
+};
+
+asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k, const char *head);
+
+static int ghash_init(struct shash_desc *desc)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+ unsigned int len)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ ctx->count += len;
+
+ if ((partial + len) >= GHASH_BLOCK_SIZE) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+ int blocks;
+
+ if (partial) {
+ int p = GHASH_BLOCK_SIZE - partial;
+
+ memcpy(ctx->buf + partial, src, p);
+ src += p;
+ len -= p;
+ }
+
+ blocks = len / GHASH_BLOCK_SIZE;
+ len %= GHASH_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(6);
+ pmull_ghash_update(blocks, ctx->digest, src, key,
+ partial ? ctx->buf : NULL);
+ kernel_neon_end();
+ src += blocks * GHASH_BLOCK_SIZE;
+ }
+ if (len)
+ memcpy(ctx->buf + partial, src, len);
+ return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+ struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+ if (partial) {
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+ memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+ kernel_neon_begin_partial(6);
+ pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
+ kernel_neon_end();
+ }
+ put_unaligned_be64(ctx->digest[1], dst);
+ put_unaligned_be64(ctx->digest[0], dst + 8);
+
+ *ctx = (struct ghash_desc_ctx){};
+ return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+ const u8 *inkey, unsigned int keylen)
+{
+ struct ghash_key *key = crypto_shash_ctx(tfm);
+ u64 a, b;
+
+ if (keylen != GHASH_BLOCK_SIZE) {
+ crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+
+ /* perform multiplication by 'x' in GF(2^128) */
+ b = get_unaligned_be64(inkey);
+ a = get_unaligned_be64(inkey + 8);
+
+ key->a = (a << 1) | (b >> 63);
+ key->b = (b << 1) | (a >> 63);
+
+ if (b >> 63)
+ key->b ^= 0xc200000000000000UL;
+
+ return 0;
+}
+
+static struct shash_alg ghash_alg = {
+ .digestsize = GHASH_DIGEST_SIZE,
+ .init = ghash_init,
+ .update = ghash_update,
+ .final = ghash_final,
+ .setkey = ghash_setkey,
+ .descsize = sizeof(struct ghash_desc_ctx),
+ .base = {
+ .cra_name = "ghash",
+ .cra_driver_name = "ghash-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = GHASH_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct ghash_key),
+ .cra_module = THIS_MODULE,
+ },
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+ return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+ crypto_unregister_shash(&ghash_alg);
+}
+
+module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 0000000..09d57d9
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,153 @@
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ k0 .req v0
+ k1 .req v1
+ k2 .req v2
+ k3 .req v3
+
+ t0 .req v4
+ t1 .req v5
+
+ dga .req q6
+ dgav .req v6
+ dgb .req s7
+ dgbv .req v7
+
+ dg0q .req q12
+ dg0s .req s12
+ dg0v .req v12
+ dg1s .req s13
+ dg1v .req v13
+ dg2s .req s14
+
+ .macro add_only, op, ev, rc, s0, dg1
+ .ifc \ev, ev
+ add t1.4s, v\s0\().4s, \rc\().4s
+ sha1h dg2s, dg0s
+ .ifnb \dg1
+ sha1\op dg0q, \dg1, t0.4s
+ .else
+ sha1\op dg0q, dg1s, t0.4s
+ .endif
+ .else
+ .ifnb \s0
+ add t0.4s, v\s0\().4s, \rc\().4s
+ .endif
+ sha1h dg1s, dg0s
+ sha1\op dg0q, dg2s, t1.4s
+ .endif
+ .endm
+
+ .macro add_update, op, ev, rc, s0, s1, s2, s3, dg1
+ sha1su0 v\s0\().4s, v\s1\().4s, v\s2\().4s
+ add_only \op, \ev, \rc, \s1, \dg1
+ sha1su1 v\s0\().4s, v\s3\().4s
+ .endm
+
+ /*
+ * The SHA1 round constants
+ */
+ .align 4
+.Lsha1_rcon:
+ .word 0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
+
+ /*
+ * void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head, long bytes)
+ */
+ENTRY(sha1_ce_transform)
+ /* load round constants */
+ adr x6, .Lsha1_rcon
+ ld1r {k0.4s}, [x6], #4
+ ld1r {k1.4s}, [x6], #4
+ ld1r {k2.4s}, [x6], #4
+ ld1r {k3.4s}, [x6]
+
+ /* load state */
+ ldr dga, [x2]
+ ldr dgb, [x2, #16]
+
+ /* load partial state (if supplied) */
+ cbz x3, 0f
+ ld1 {v8.4s-v11.4s}, [x3]
+ b 1f
+
+ /* load input */
+0: ld1 {v8.4s-v11.4s}, [x1], #64
+ sub w0, w0, #1
+
+1:
+CPU_LE( rev32 v8.16b, v8.16b )
+CPU_LE( rev32 v9.16b, v9.16b )
+CPU_LE( rev32 v10.16b, v10.16b )
+CPU_LE( rev32 v11.16b, v11.16b )
+
+2: add t0.4s, v8.4s, k0.4s
+ mov dg0v.16b, dgav.16b
+
+ add_update c, ev, k0, 8, 9, 10, 11, dgb
+ add_update c, od, k0, 9, 10, 11, 8
+ add_update c, ev, k0, 10, 11, 8, 9
+ add_update c, od, k0, 11, 8, 9, 10
+ add_update c, ev, k1, 8, 9, 10, 11
+
+ add_update p, od, k1, 9, 10, 11, 8
+ add_update p, ev, k1, 10, 11, 8, 9
+ add_update p, od, k1, 11, 8, 9, 10
+ add_update p, ev, k1, 8, 9, 10, 11
+ add_update p, od, k2, 9, 10, 11, 8
+
+ add_update m, ev, k2, 10, 11, 8, 9
+ add_update m, od, k2, 11, 8, 9, 10
+ add_update m, ev, k2, 8, 9, 10, 11
+ add_update m, od, k2, 9, 10, 11, 8
+ add_update m, ev, k3, 10, 11, 8, 9
+
+ add_update p, od, k3, 11, 8, 9, 10
+ add_only p, ev, k3, 9
+ add_only p, od, k3, 10
+ add_only p, ev, k3, 11
+ add_only p, od
+
+ /* update state */
+ add dgbv.2s, dgbv.2s, dg1v.2s
+ add dgav.4s, dgav.4s, dg0v.4s
+
+ cbnz w0, 0b
+
+ /*
+ * Final block: add padding and total bit count.
+ * Skip if we have no total byte count in x4. In that case, the input
+ * size was not a round multiple of the block size, and the padding is
+ * handled by the C code.
+ */
+ cbz x4, 3f
+ movi v9.2d, #0
+ mov x8, #0x80000000
+ movi v10.2d, #0
+ ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ fmov d8, x8
+ mov x4, #0
+ mov v11.d[0], xzr
+ mov v11.d[1], x7
+ b 2b
+
+ /* store new state */
+3: str dga, [x2]
+ str dgb, [x2, #16]
+ ret
+ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 0000000..6fe83f3
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,174 @@
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sha1_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head, long bytes);
+
+static int sha1_init(struct shash_desc *desc)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha1_state){
+ .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 },
+ };
+ return 0;
+}
+
+static int sha1_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA1_BLOCK_SIZE;
+
+ sctx->count += len;
+
+ if ((partial + len) >= SHA1_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA1_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buffer + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA1_BLOCK_SIZE;
+ len %= SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buffer : NULL, 0);
+ kernel_neon_end();
+
+ data += blocks * SHA1_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buffer + partial, data, len);
+ return 0;
+}
+
+static int sha1_final(struct shash_desc *desc, u8 *out)
+{
+ static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, };
+
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ u32 padlen = SHA1_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA1_BLOCK_SIZE);
+
+ sha1_update(desc, padding, padlen);
+ sha1_update(desc, (const u8 *)&bits, sizeof(bits));
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int blocks;
+ int i;
+
+ if (sctx->count || !len || (len % SHA1_BLOCK_SIZE)) {
+ sha1_update(desc, data, len);
+ return sha1_final(desc, out);
+ }
+
+ /*
+ * Use a fast path if the input is a multiple of 64 bytes. In
+ * this case, there is no need to copy data around, and we can
+ * perform the entire digest calculation in a single invocation
+ * of sha1_ce_transform()
+ */
+ blocks = len / SHA1_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(16);
+ sha1_ce_transform(blocks, data, sctx->state, NULL, len);
+ kernel_neon_end();
+
+ for (i = 0; i < SHA1_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha1_state){};
+ return 0;
+}
+
+static int sha1_export(struct shash_desc *desc, void *out)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha1_import(struct shash_desc *desc, const void *in)
+{
+ struct sha1_state *sctx = shash_desc_ctx(desc);
+ struct sha1_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg alg = {
+ .init = sha1_init,
+ .update = sha1_update,
+ .final = sha1_final,
+ .finup = sha1_finup,
+ .export = sha1_export,
+ .import = sha1_import,
+ .descsize = sizeof(struct sha1_state),
+ .digestsize = SHA1_DIGEST_SIZE,
+ .statesize = sizeof(struct sha1_state),
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+ return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 0000000..7f29fc0
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,156 @@
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .arch armv8-a+crypto
+
+ dga .req q20
+ dgav .req v20
+ dgb .req q21
+ dgbv .req v21
+
+ t0 .req v22
+ t1 .req v23
+
+ dg0q .req q24
+ dg0v .req v24
+ dg1q .req q25
+ dg1v .req v25
+ dg2q .req q26
+ dg2v .req v26
+
+ .macro add_only, ev, rc, s0
+ mov dg2v.16b, dg0v.16b
+ .ifeq \ev
+ add t1.4s, v\s0\().4s, \rc\().4s
+ sha256h dg0q, dg1q, t0.4s
+ sha256h2 dg1q, dg2q, t0.4s
+ .else
+ .ifnb \s0
+ add t0.4s, v\s0\().4s, \rc\().4s
+ .endif
+ sha256h dg0q, dg1q, t1.4s
+ sha256h2 dg1q, dg2q, t1.4s
+ .endif
+ .endm
+
+ .macro add_update, ev, rc, s0, s1, s2, s3
+ sha256su0 v\s0\().4s, v\s1\().4s
+ add_only \ev, \rc, \s1
+ sha256su1 v\s0\().4s, v\s2\().4s, v\s3\().4s
+ .endm
+
+ /*
+ * The SHA-256 round constants
+ */
+ .align 4
+.Lsha2_rcon:
+ .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+ .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+ .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+ .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+ .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+ .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+ .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+ .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+ .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+ .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+ .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+ .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+ .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+ .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+ .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+ .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+ /*
+ * void sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ * u8 *head, long bytes)
+ */
+ENTRY(sha2_ce_transform)
+ /* load round constants */
+ adr x8, .Lsha2_rcon
+ ld1 { v0.4s- v3.4s}, [x8], #64
+ ld1 { v4.4s- v7.4s}, [x8], #64
+ ld1 { v8.4s-v11.4s}, [x8], #64
+ ld1 {v12.4s-v15.4s}, [x8]
+
+ /* load state */
+ ldp dga, dgb, [x2]
+
+ /* load partial input (if supplied) */
+ cbz x3, 0f
+ ld1 {v16.4s-v19.4s}, [x3]
+ b 1f
+
+ /* load input */
+0: ld1 {v16.4s-v19.4s}, [x1], #64
+ sub w0, w0, #1
+
+1:
+CPU_LE( rev32 v16.16b, v16.16b )
+CPU_LE( rev32 v17.16b, v17.16b )
+CPU_LE( rev32 v18.16b, v18.16b )
+CPU_LE( rev32 v19.16b, v19.16b )
+
+2: add t0.4s, v16.4s, v0.4s
+ mov dg0v.16b, dgav.16b
+ mov dg1v.16b, dgbv.16b
+
+ add_update 0, v1, 16, 17, 18, 19
+ add_update 1, v2, 17, 18, 19, 16
+ add_update 0, v3, 18, 19, 16, 17
+ add_update 1, v4, 19, 16, 17, 18
+
+ add_update 0, v5, 16, 17, 18, 19
+ add_update 1, v6, 17, 18, 19, 16
+ add_update 0, v7, 18, 19, 16, 17
+ add_update 1, v8, 19, 16, 17, 18
+
+ add_update 0, v9, 16, 17, 18, 19
+ add_update 1, v10, 17, 18, 19, 16
+ add_update 0, v11, 18, 19, 16, 17
+ add_update 1, v12, 19, 16, 17, 18
+
+ add_only 0, v13, 17
+ add_only 1, v14, 18
+ add_only 0, v15, 19
+ add_only 1
+
+ /* update state */
+ add dgav.4s, dgav.4s, dg0v.4s
+ add dgbv.4s, dgbv.4s, dg1v.4s
+
+ /* handled all input blocks? */
+ cbnz w0, 0b
+
+ /*
+ * Final block: add padding and total bit count.
+ * Skip if we have no total byte count in x4. In that case, the input
+ * size was not a round multiple of the block size, and the padding is
+ * handled by the C code.
+ */
+ cbz x4, 3f
+ movi v17.2d, #0
+ mov x8, #0x80000000
+ movi v18.2d, #0
+ ror x7, x4, #29 // ror(lsl(x4, 3), 32)
+ fmov d16, x8
+ mov x4, #0
+ mov v19.d[0], xzr
+ mov v19.d[1], x7
+ b 2b
+
+ /* store new state */
+3: stp dga, dgb, [x2]
+ ret
+ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 0000000..c294e67
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,255 @@
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage int sha2_ce_transform(int blocks, u8 const *src, u32 *state,
+ u8 *head, long bytes);
+
+static int sha224_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA224_H0, SHA224_H1, SHA224_H2, SHA224_H3,
+ SHA224_H4, SHA224_H5, SHA224_H6, SHA224_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha256_init(struct shash_desc *desc)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+
+ *sctx = (struct sha256_state){
+ .state = {
+ SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+ SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7,
+ }
+ };
+ return 0;
+}
+
+static int sha2_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ unsigned int partial = sctx->count % SHA256_BLOCK_SIZE;
+
+ sctx->count += len;
+
+ if ((partial + len) >= SHA256_BLOCK_SIZE) {
+ int blocks;
+
+ if (partial) {
+ int p = SHA256_BLOCK_SIZE - partial;
+
+ memcpy(sctx->buf + partial, data, p);
+ data += p;
+ len -= p;
+ }
+
+ blocks = len / SHA256_BLOCK_SIZE;
+ len %= SHA256_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(28);
+ sha2_ce_transform(blocks, data, sctx->state,
+ partial ? sctx->buf : NULL, 0);
+ kernel_neon_end();
+
+ data += blocks * SHA256_BLOCK_SIZE;
+ partial = 0;
+ }
+ if (len)
+ memcpy(sctx->buf + partial, data, len);
+ return 0;
+}
+
+static void sha2_final(struct shash_desc *desc)
+{
+ static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, };
+
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be64 bits = cpu_to_be64(sctx->count << 3);
+ u32 padlen = SHA256_BLOCK_SIZE
+ - ((sctx->count + sizeof(bits)) % SHA256_BLOCK_SIZE);
+
+ sha2_update(desc, padding, padlen);
+ sha2_update(desc, (const u8 *)&bits, sizeof(bits));
+}
+
+static int sha224_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha256_final(struct shash_desc *desc, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_final(desc);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static void sha2_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ int blocks;
+
+ if (sctx->count || !len || (len % SHA256_BLOCK_SIZE)) {
+ sha2_update(desc, data, len);
+ sha2_final(desc);
+ return;
+ }
+
+ /*
+ * Use a fast path if the input is a multiple of 64 bytes. In
+ * this case, there is no need to copy data around, and we can
+ * perform the entire digest calculation in a single invocation
+ * of sha2_ce_transform()
+ */
+ blocks = len / SHA256_BLOCK_SIZE;
+
+ kernel_neon_begin_partial(28);
+ sha2_ce_transform(blocks, data, sctx->state, NULL, len);
+ kernel_neon_end();
+ data += blocks * SHA256_BLOCK_SIZE;
+}
+
+static int sha224_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_finup(desc, data, len);
+
+ for (i = 0; i < SHA224_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha256_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ __be32 *dst = (__be32 *)out;
+ int i;
+
+ sha2_finup(desc, data, len);
+
+ for (i = 0; i < SHA256_DIGEST_SIZE / sizeof(__be32); i++)
+ put_unaligned_be32(sctx->state[i], dst++);
+
+ *sctx = (struct sha256_state){};
+ return 0;
+}
+
+static int sha2_export(struct shash_desc *desc, void *out)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state *dst = out;
+
+ *dst = *sctx;
+ return 0;
+}
+
+static int sha2_import(struct shash_desc *desc, const void *in)
+{
+ struct sha256_state *sctx = shash_desc_ctx(desc);
+ struct sha256_state const *src = in;
+
+ *sctx = *src;
+ return 0;
+}
+
+static struct shash_alg algs[] = { {
+ .init = sha224_init,
+ .update = sha2_update,
+ .final = sha224_final,
+ .finup = sha224_finup,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA224_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha224",
+ .cra_driver_name = "sha224-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+}, {
+ .init = sha256_init,
+ .update = sha2_update,
+ .final = sha256_final,
+ .finup = sha256_finup,
+ .export = sha2_export,
+ .import = sha2_import,
+ .descsize = sizeof(struct sha256_state),
+ .digestsize = SHA256_DIGEST_SIZE,
+ .statesize = sizeof(struct sha256_state),
+ .base = {
+ .cra_name = "sha256",
+ .cra_driver_name = "sha256-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .cra_blocksize = SHA256_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+ return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+ crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 79a642d..cfe9860 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -10,6 +10,7 @@
generic-y += div64.h
generic-y += dma.h
generic-y += emergency-restart.h
+generic-y += early_ioremap.h
generic-y += errno.h
generic-y += ftrace.h
generic-y += hw_irq.h
@@ -26,16 +27,17 @@
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += pci.h
-generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
generic-y += resource.h
+generic-y += rwsem.h
generic-y += scatterlist.h
generic-y += sections.h
generic-y += segment.h
generic-y += sembuf.h
generic-y += serial.h
generic-y += shmbuf.h
+generic-y += simd.h
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index bf6ab242..be56d33 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -26,7 +26,13 @@
#include <clocksource/arm_arch_timer.h>
-static inline void arch_timer_reg_write(int access, int reg, u32 val)
+/*
+ * These register accessors are marked inline so the compiler can
+ * nicely work out which register we want, and chuck away the rest of
+ * the code.
+ */
+static __always_inline
+void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
{
if (access == ARCH_TIMER_PHYS_ACCESS) {
switch (reg) {
@@ -36,8 +42,6 @@
case ARCH_TIMER_REG_TVAL:
asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
break;
- default:
- BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
@@ -47,17 +51,14 @@
case ARCH_TIMER_REG_TVAL:
asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
break;
- default:
- BUILD_BUG();
}
- } else {
- BUILD_BUG();
}
isb();
}
-static inline u32 arch_timer_reg_read(int access, int reg)
+static __always_inline
+u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
{
u32 val;
@@ -69,8 +70,6 @@
case ARCH_TIMER_REG_TVAL:
asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
break;
- default:
- BUILD_BUG();
}
} else if (access == ARCH_TIMER_VIRT_ACCESS) {
switch (reg) {
@@ -80,11 +79,7 @@
case ARCH_TIMER_REG_TVAL:
asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
break;
- default:
- BUILD_BUG();
}
- } else {
- BUILD_BUG();
}
return val;
@@ -97,27 +92,47 @@
return val;
}
-static inline void __cpuinit arch_counter_set_user_access(void)
+static inline u32 arch_timer_get_cntkctl(void)
{
u32 cntkctl;
-
- /* Disable user access to the timers and the physical counter. */
asm volatile("mrs %0, cntkctl_el1" : "=r" (cntkctl));
- cntkctl &= ~((3 << 8) | (1 << 0));
+ return cntkctl;
+}
- /* Enable user access to the virtual counter and frequency. */
- cntkctl |= (1 << 1);
+static inline void arch_timer_set_cntkctl(u32 cntkctl)
+{
asm volatile("msr cntkctl_el1, %0" : : "r" (cntkctl));
}
-static inline u64 arch_counter_get_cntpct(void)
+static inline void __cpuinit arch_counter_set_user_access(void)
{
- u64 cval;
+ u32 cntkctl = arch_timer_get_cntkctl();
- isb();
- asm volatile("mrs %0, cntpct_el0" : "=r" (cval));
+ /* Disable user access to the timers and the physical counter */
+ /* Also disable virtual event stream */
+ cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
+ | ARCH_TIMER_USR_VT_ACCESS_EN
+ | ARCH_TIMER_VIRT_EVT_EN
+ | ARCH_TIMER_USR_PCT_ACCESS_EN);
- return cval;
+ /* Enable user access to the virtual counter */
+ cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+
+ arch_timer_set_cntkctl(cntkctl);
+}
+
+static inline void arch_timer_evtstrm_enable(int divider)
+{
+ u32 cntkctl = arch_timer_get_cntkctl();
+ cntkctl &= ~ARCH_TIMER_EVT_TRIGGER_MASK;
+ /* Set the divider and enable virtual event stream */
+ cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+ | ARCH_TIMER_VIRT_EVT_EN;
+ arch_timer_set_cntkctl(cntkctl);
+ elf_hwcap |= HWCAP_EVTSTRM;
+#ifdef CONFIG_COMPAT
+ compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
+#endif
}
static inline u64 arch_counter_get_cntvct(void)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 5aceb83..fd3e392 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -115,3 +115,34 @@
.align 7
b \label
.endm
+
+/*
+ * Select code when configured for BE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_BE(code...) code
+#else
+#define CPU_BE(code...)
+#endif
+
+/*
+ * Select code when configured for LE.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define CPU_LE(code...)
+#else
+#define CPU_LE(code...) code
+#endif
+
+/*
+ * Define a macro that constructs a 64-bit value by concatenating two
+ * 32-bit registers. Note that on big endian systems the order of the
+ * registers is swapped.
+ */
+#ifndef CONFIG_CPU_BIG_ENDIAN
+ .macro regs_to_64, rd, lbits, hbits
+#else
+ .macro regs_to_64, rd, hbits, lbits
+#endif
+ orr \rd, \lbits, \hbits, lsl #32
+ .endm
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 8363644..a049bf7 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -54,8 +54,7 @@
" stxr %w1, %w0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
- : "Ir" (i)
- : "cc");
+ : "Ir" (i));
}
static inline int atomic_add_return(int i, atomic_t *v)
@@ -64,14 +63,15 @@
int result;
asm volatile("// atomic_add_return\n"
-"1: ldaxr %w0, %2\n"
+"1: ldxr %w0, %2\n"
" add %w0, %w0, %w3\n"
" stlxr %w1, %w0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
: "Ir" (i)
- : "cc", "memory");
+ : "memory");
+ smp_mb();
return result;
}
@@ -86,8 +86,7 @@
" stxr %w1, %w0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
- : "Ir" (i)
- : "cc");
+ : "Ir" (i));
}
static inline int atomic_sub_return(int i, atomic_t *v)
@@ -96,14 +95,15 @@
int result;
asm volatile("// atomic_sub_return\n"
-"1: ldaxr %w0, %2\n"
+"1: ldxr %w0, %2\n"
" sub %w0, %w0, %w3\n"
" stlxr %w1, %w0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
: "Ir" (i)
- : "cc", "memory");
+ : "memory");
+ smp_mb();
return result;
}
@@ -112,17 +112,20 @@
unsigned long tmp;
int oldval;
+ smp_mb();
+
asm volatile("// atomic_cmpxchg\n"
-"1: ldaxr %w1, %2\n"
+"1: ldxr %w1, %2\n"
" cmp %w1, %w3\n"
" b.ne 2f\n"
-" stlxr %w0, %w4, %2\n"
+" stxr %w0, %w4, %2\n"
" cbnz %w0, 1b\n"
"2:"
: "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter)
: "Ir" (old), "r" (new)
- : "cc", "memory");
+ : "cc");
+ smp_mb();
return oldval;
}
@@ -173,7 +176,7 @@
*/
#define ATOMIC64_INIT(i) { (i) }
-#define atomic64_read(v) (*(volatile long long *)&(v)->counter)
+#define atomic64_read(v) (*(volatile long *)&(v)->counter)
#define atomic64_set(v,i) (((v)->counter) = (i))
static inline void atomic64_add(u64 i, atomic64_t *v)
@@ -187,8 +190,7 @@
" stxr %w1, %0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
- : "Ir" (i)
- : "cc");
+ : "Ir" (i));
}
static inline long atomic64_add_return(long i, atomic64_t *v)
@@ -197,14 +199,15 @@
unsigned long tmp;
asm volatile("// atomic64_add_return\n"
-"1: ldaxr %0, %2\n"
+"1: ldxr %0, %2\n"
" add %0, %0, %3\n"
" stlxr %w1, %0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
: "Ir" (i)
- : "cc", "memory");
+ : "memory");
+ smp_mb();
return result;
}
@@ -219,8 +222,7 @@
" stxr %w1, %0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
- : "Ir" (i)
- : "cc");
+ : "Ir" (i));
}
static inline long atomic64_sub_return(long i, atomic64_t *v)
@@ -229,14 +231,15 @@
unsigned long tmp;
asm volatile("// atomic64_sub_return\n"
-"1: ldaxr %0, %2\n"
+"1: ldxr %0, %2\n"
" sub %0, %0, %3\n"
" stlxr %w1, %0, %2\n"
" cbnz %w1, 1b"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
: "Ir" (i)
- : "cc", "memory");
+ : "memory");
+ smp_mb();
return result;
}
@@ -245,17 +248,20 @@
long oldval;
unsigned long res;
+ smp_mb();
+
asm volatile("// atomic64_cmpxchg\n"
-"1: ldaxr %1, %2\n"
+"1: ldxr %1, %2\n"
" cmp %1, %3\n"
" b.ne 2f\n"
-" stlxr %w0, %4, %2\n"
+" stxr %w0, %4, %2\n"
" cbnz %w0, 1b\n"
"2:"
: "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter)
: "Ir" (old), "r" (new)
- : "cc", "memory");
+ : "cc");
+ smp_mb();
return oldval;
}
@@ -267,11 +273,12 @@
unsigned long tmp;
asm volatile("// atomic64_dec_if_positive\n"
-"1: ldaxr %0, %2\n"
+"1: ldxr %0, %2\n"
" subs %0, %0, #1\n"
" b.mi 2f\n"
" stlxr %w1, %0, %2\n"
" cbnz %w1, 1b\n"
+" dmb ish\n"
"2:"
: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
:
diff --git a/arch/arm64/include/asm/bL_switcher.h b/arch/arm64/include/asm/bL_switcher.h
new file mode 100644
index 0000000..2bee500
--- /dev/null
+++ b/arch/arm64/include/asm/bL_switcher.h
@@ -0,0 +1,54 @@
+/*
+ * Based on the stubs for the ARM implementation which is:
+ *
+ * Created by: Nicolas Pitre, April 2012
+ * Copyright: (C) 2012-2013 Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/notifier.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+static inline int bL_switch_request(unsigned int cpu,
+ unsigned int new_cluster_id)
+{
+ return -ENOTSUPP;
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE 0
+#define BL_NOTIFY_POST_ENABLE 1
+#define BL_NOTIFY_PRE_DISABLE 2
+#define BL_NOTIFY_POST_DISABLE 3
+
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+
+#endif
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index d4a6333..709f1f6 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,20 +25,71 @@
#define wfi() asm volatile("wfi" : : : "memory")
#define isb() asm volatile("isb" : : : "memory")
-#define dsb() asm volatile("dsb sy" : : : "memory")
+#define dmb(opt) asm volatile("dmb " #opt : : : "memory")
+#define dsb(opt) asm volatile("dsb " #opt : : : "memory")
-#define mb() dsb()
-#define rmb() asm volatile("dsb ld" : : : "memory")
-#define wmb() asm volatile("dsb st" : : : "memory")
+#define mb() dsb(sy)
+#define rmb() dsb(ld)
+#define wmb() dsb(st)
#ifndef CONFIG_SMP
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
#else
-#define smp_mb() asm volatile("dmb ish" : : : "memory")
-#define smp_rmb() asm volatile("dmb ishld" : : : "memory")
-#define smp_wmb() asm volatile("dmb ishst" : : : "memory")
+
+#define smp_mb() dmb(ish)
+#define smp_rmb() dmb(ishld)
+#define smp_wmb() dmb(ishst)
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 4: \
+ asm volatile ("stlr %w1, %0" \
+ : "=Q" (*p) : "r" (v) : "memory"); \
+ break; \
+ case 8: \
+ asm volatile ("stlr %1, %0" \
+ : "=Q" (*p) : "r" (v) : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 4: \
+ asm volatile ("ldar %w0, %1" \
+ : "=r" (___p1) : "Q" (*p) : "memory"); \
+ break; \
+ case 8: \
+ asm volatile ("ldar %0, %1" \
+ : "=r" (___p1) : "Q" (*p) : "memory"); \
+ break; \
+ } \
+ ___p1; \
+})
+
#endif
#define read_barrier_depends() do { } while(0)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 3300cbd..689b637 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -85,6 +85,13 @@
}
/*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
+/*
* Copy user data from/to a page which is mapped into a different
* processes address space. Really, we want to allow our "user
* space" model to handle this.
@@ -116,6 +123,7 @@
static inline void __flush_icache_all(void)
{
asm("ic ialluis");
+ dsb(ish);
}
#define flush_dcache_mmap_lock(mapping) \
@@ -123,9 +131,6 @@
#define flush_dcache_mmap_unlock(mapping) \
spin_unlock_irq(&(mapping)->tree_lock)
-#define flush_icache_user_range(vma,page,addr,len) \
- flush_dcache_page(page)
-
/*
* We don't appear to need to do anything here. In fact, if we did, we'd
* duplicate cache flushing elsewhere performed by flush_dcache_page().
@@ -133,23 +138,18 @@
#define flush_icache_page(vma,page) do { } while (0)
/*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages. On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
*/
static inline void flush_cache_vmap(unsigned long start, unsigned long end)
{
- /*
- * set_pte_at() called from vmap_pte_range() does not
- * have a DSB after cleaning the cache line.
- */
- dsb();
}
static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
{
}
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 8a8ce0e..a84d4c8 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -29,49 +29,55 @@
switch (size) {
case 1:
asm volatile("// __xchg1\n"
- "1: ldaxrb %w0, %2\n"
+ "1: ldxrb %w0, %2\n"
" stlxrb %w1, %w3, %2\n"
" cbnz %w1, 1b\n"
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
: "r" (x)
- : "cc", "memory");
+ : "memory");
break;
case 2:
asm volatile("// __xchg2\n"
- "1: ldaxrh %w0, %2\n"
+ "1: ldxrh %w0, %2\n"
" stlxrh %w1, %w3, %2\n"
" cbnz %w1, 1b\n"
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
: "r" (x)
- : "cc", "memory");
+ : "memory");
break;
case 4:
asm volatile("// __xchg4\n"
- "1: ldaxr %w0, %2\n"
+ "1: ldxr %w0, %2\n"
" stlxr %w1, %w3, %2\n"
" cbnz %w1, 1b\n"
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
: "r" (x)
- : "cc", "memory");
+ : "memory");
break;
case 8:
asm volatile("// __xchg8\n"
- "1: ldaxr %0, %2\n"
+ "1: ldxr %0, %2\n"
" stlxr %w1, %3, %2\n"
" cbnz %w1, 1b\n"
: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
: "r" (x)
- : "cc", "memory");
+ : "memory");
break;
default:
BUILD_BUG();
}
+ smp_mb();
return ret;
}
#define xchg(ptr,x) \
- ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+ __ret; \
+})
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
@@ -158,19 +164,27 @@
return ret;
}
-#define cmpxchg(ptr,o,n) \
- ((__typeof__(*(ptr)))__cmpxchg_mb((ptr), \
- (unsigned long)(o), \
- (unsigned long)(n), \
- sizeof(*(ptr))))
+#define cmpxchg(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
+ sizeof(*(ptr))); \
+ __ret; \
+})
-#define cmpxchg_local(ptr,o,n) \
- ((__typeof__(*(ptr)))__cmpxchg((ptr), \
- (unsigned long)(o), \
- (unsigned long)(n), \
- sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __ret = (__typeof__(*(ptr))) \
+ __cmpxchg((ptr), (unsigned long)(o), \
+ (unsigned long)(n), sizeof(*(ptr))); \
+ __ret; \
+})
#define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n))
#define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n))
+#define cmpxchg64_relaxed(ptr,o,n) cmpxchg_local((ptr),(o),(n))
+
#endif /* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 899af80..56de5aa 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -26,15 +26,19 @@
#include <linux/ptrace.h>
#define COMPAT_USER_HZ 100
+#ifdef __AARCH64EB__
+#define COMPAT_UTS_MACHINE "armv8b\0\0"
+#else
#define COMPAT_UTS_MACHINE "armv8l\0\0"
+#endif
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
-typedef u32 __compat_uid_t;
-typedef u32 __compat_gid_t;
+typedef u16 __compat_uid_t;
+typedef u16 __compat_gid_t;
typedef u16 __compat_uid16_t;
typedef u16 __compat_gid16_t;
typedef u32 __compat_uid32_t;
@@ -73,13 +77,23 @@
};
struct compat_stat {
+#ifdef __AARCH64EB__
+ short st_dev;
+ short __pad1;
+#else
compat_dev_t st_dev;
+#endif
compat_ino_t st_ino;
compat_mode_t st_mode;
compat_ushort_t st_nlink;
__compat_uid16_t st_uid;
__compat_gid16_t st_gid;
+#ifdef __AARCH64EB__
+ short st_rdev;
+ short __pad2;
+#else
compat_dev_t st_rdev;
+#endif
compat_off_t st_size;
compat_off_t st_blksize;
compat_off_t st_blocks;
@@ -214,7 +228,7 @@
return (u32)(unsigned long)uptr;
}
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
static inline void __user *arch_compat_alloc_user_space(long len)
{
@@ -291,11 +305,6 @@
#else /* !CONFIG_COMPAT */
-static inline int is_compat_task(void)
-{
- return 0;
-}
-
static inline int is_compat_thread(struct thread_info *thread)
{
return 0;
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
new file mode 100644
index 0000000..47dfa31
--- /dev/null
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CPU_OPS_H
+#define __ASM_CPU_OPS_H
+
+#include <linux/init.h>
+#include <linux/threads.h>
+
+struct device_node;
+
+/**
+ * struct cpu_operations - Callback operations for hotplugging CPUs.
+ *
+ * @name: Name of the property as appears in a devicetree cpu node's
+ * enable-method property.
+ * @cpu_init: Reads any data necessary for a specific enable-method from the
+ * devicetree, for a given cpu node and proposed logical id.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ * devicetree, for a given cpu node and proposed logical id.
+ * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
+ * mechanism for doing so, tests whether it is possible to boot
+ * the given CPU.
+ * @cpu_boot: Boots a cpu into the kernel.
+ * @cpu_postboot: Optionally, perform any post-boot cleanup or necesary
+ * synchronisation. Called from the cpu being booted.
+ * @cpu_disable: Prepares a cpu to die. May fail for some mechanism-specific
+ * reason, which will cause the hot unplug to be aborted. Called
+ * from the cpu to be killed.
+ * @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the
+ * cpu being killed.
+ * @cpu_kill: Ensures a cpu has left the kernel. Called from another cpu.
+ * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
+ * to wrong parameters or error conditions. Called from the
+ * CPU being suspended. Must be called with IRQs disabled.
+ */
+struct cpu_operations {
+ const char *name;
+ int (*cpu_init)(struct device_node *, unsigned int);
+ int (*cpu_init_idle)(struct device_node *, unsigned int);
+ int (*cpu_prepare)(unsigned int);
+ int (*cpu_boot)(unsigned int);
+ void (*cpu_postboot)(void);
+#ifdef CONFIG_HOTPLUG_CPU
+ int (*cpu_disable)(unsigned int cpu);
+ void (*cpu_die)(unsigned int cpu);
+ int (*cpu_kill)(unsigned int cpu);
+#endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+ int (*cpu_suspend)(unsigned long);
+#endif
+};
+
+extern const struct cpu_operations *cpu_ops[NR_CPUS];
+extern int __init cpu_read_ops(struct device_node *dn, int cpu);
+extern void __init cpu_read_bootcpu_ops(void);
+
+#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 0000000..cd4ac05
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap))
+#define cpu_feature(x) ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+ return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
new file mode 100644
index 0000000..b52a993
--- /dev/null
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_CPUIDLE_H
+#define __ASM_CPUIDLE_H
+
+#ifdef CONFIG_CPU_IDLE
+extern int cpu_init_idle(unsigned int cpu);
+#else
+static inline int cpu_init_idle(unsigned int cpu)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index cf27494..539bea6 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -16,31 +16,54 @@
#ifndef __ASM_CPUTYPE_H
#define __ASM_CPUTYPE_H
-#define ID_MIDR_EL1 "midr_el1"
-#define ID_MPIDR_EL1 "mpidr_el1"
-#define ID_CTR_EL0 "ctr_el0"
-
-#define ID_AA64PFR0_EL1 "id_aa64pfr0_el1"
-#define ID_AA64DFR0_EL1 "id_aa64dfr0_el1"
-#define ID_AA64AFR0_EL1 "id_aa64afr0_el1"
-#define ID_AA64ISAR0_EL1 "id_aa64isar0_el1"
-#define ID_AA64MMFR0_EL1 "id_aa64mmfr0_el1"
-
#define INVALID_HWID ULONG_MAX
#define MPIDR_HWID_BITMASK 0xff00ffffff
+#define MPIDR_LEVEL_BITS_SHIFT 3
+#define MPIDR_LEVEL_BITS (1 << MPIDR_LEVEL_BITS_SHIFT)
+#define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+
+#define MPIDR_LEVEL_SHIFT(level) \
+ (((1 << level) >> 1) << MPIDR_LEVEL_BITS_SHIFT)
+
+#define MPIDR_AFFINITY_LEVEL(mpidr, level) \
+ ((mpidr >> MPIDR_LEVEL_SHIFT(level)) & MPIDR_LEVEL_MASK)
+
#define read_cpuid(reg) ({ \
u64 __val; \
- asm("mrs %0, " reg : "=r" (__val)); \
+ asm("mrs %0, " #reg : "=r" (__val)); \
__val; \
})
-#define ARM_CPU_IMP_ARM 0x41
+#define MIDR_REVISION_MASK 0xf
+#define MIDR_REVISION(midr) ((midr) & MIDR_REVISION_MASK)
+#define MIDR_PARTNUM_SHIFT 4
+#define MIDR_PARTNUM_MASK (0xfff << MIDR_PARTNUM_SHIFT)
+#define MIDR_PARTNUM(midr) \
+ (((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT)
+#define MIDR_ARCHITECTURE_SHIFT 16
+#define MIDR_ARCHITECTURE_MASK (0xf << MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_ARCHITECTURE(midr) \
+ (((midr) & MIDR_ARCHITECTURE_MASK) >> MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_VARIANT_SHIFT 20
+#define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT)
+#define MIDR_VARIANT(midr) \
+ (((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
+#define MIDR_IMPLEMENTOR_SHIFT 24
+#define MIDR_IMPLEMENTOR_MASK (0xff << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR(midr) \
+ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
-#define ARM_CPU_PART_AEM_V8 0xD0F0
-#define ARM_CPU_PART_FOUNDATION 0xD000
-#define ARM_CPU_PART_CORTEX_A57 0xD070
+#define ARM_CPU_IMP_ARM 0x41
+#define ARM_CPU_IMP_APM 0x50
+
+#define ARM_CPU_PART_AEM_V8 0xD0F
+#define ARM_CPU_PART_FOUNDATION 0xD00
+#define ARM_CPU_PART_CORTEX_A57 0xD07
+#define ARM_CPU_PART_CORTEX_A53 0xD03
+
+#define APM_CPU_PART_POTENZA 0x000
#ifndef __ASSEMBLY__
@@ -51,29 +74,31 @@
*/
static inline u32 __attribute_const__ read_cpuid_id(void)
{
- return read_cpuid(ID_MIDR_EL1);
+ return read_cpuid(MIDR_EL1);
}
static inline u64 __attribute_const__ read_cpuid_mpidr(void)
{
- return read_cpuid(ID_MPIDR_EL1);
+ return read_cpuid(MPIDR_EL1);
}
static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
{
- return (read_cpuid_id() & 0xFF000000) >> 24;
+ return MIDR_IMPLEMENTOR(read_cpuid_id());
}
static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
{
- return (read_cpuid_id() & 0xFFF0);
+ return MIDR_PARTNUM(read_cpuid_id());
}
static inline u32 __attribute_const__ read_cpuid_cachetype(void)
{
- return read_cpuid(ID_CTR_EL0);
+ return read_cpuid(CTR_EL0);
}
+void cpuinfo_store_cpu(void);
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 7eaa0b3..aab72ce 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -18,6 +18,15 @@
#ifdef __KERNEL__
+/* Low-level stepping controls. */
+#define DBG_MDSCR_SS (1 << 0)
+#define DBG_SPSR_SS (1 << 21)
+
+/* MDSCR_EL1 enabling bits */
+#define DBG_MDSCR_KDE (1 << 13)
+#define DBG_MDSCR_MDE (1 << 15)
+#define DBG_MDSCR_MASK ~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
+
#define DBG_ESR_EVT(x) (((x) >> 27) & 0x7)
/* AArch64 */
@@ -26,10 +35,52 @@
#define DBG_ESR_EVT_HWWP 0x2
#define DBG_ESR_EVT_BRK 0x6
-enum debug_el {
- DBG_ACTIVE_EL0 = 0,
- DBG_ACTIVE_EL1,
-};
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE 4
+
+/*
+ * ESR values expected for dynamic and compile time BRK instruction
+ */
+#define DBG_ESR_VAL_BRK(x) (0xf2000000 | ((x) & 0xfffff))
+
+/*
+ * #imm16 values used for BRK instruction generation
+ * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_IMM 0x400
+#define KDBG_COMPILED_DBG_BRK_IMM 0x401
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON 0xd4200000
+
+/*
+ * Extract byte from BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+ ((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
+
+/*
+ * Extract byte from BRK #imm16
+ */
+#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
+ (((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+
+#define KGDB_DYN_DGB_BRK_BYTE(x) \
+ (KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+
+#define KGDB_DYN_BRK_INS_BYTE0 KGDB_DYN_DGB_BRK_BYTE(0)
+#define KGDB_DYN_BRK_INS_BYTE1 KGDB_DYN_DGB_BRK_BYTE(1)
+#define KGDB_DYN_BRK_INS_BYTE2 KGDB_DYN_DGB_BRK_BYTE(2)
+#define KGDB_DYN_BRK_INS_BYTE3 KGDB_DYN_DGB_BRK_BYTE(3)
+
+#define CACHE_FLUSH_IS_SAFE 1
/* AArch32 */
#define DBG_ESR_EVT_BKPT 0x4
@@ -43,27 +94,36 @@
#ifndef __ASSEMBLY__
struct task_struct;
-#define local_dbg_save(flags) \
- do { \
- typecheck(unsigned long, flags); \
- asm volatile( \
- "mrs %0, daif // local_dbg_save\n" \
- "msr daifset, #8" \
- : "=r" (flags) : : "memory"); \
- } while (0)
-
-#define local_dbg_restore(flags) \
- do { \
- typecheck(unsigned long, flags); \
- asm volatile( \
- "msr daif, %0 // local_dbg_restore\n" \
- : : "r" (flags) : "memory"); \
- } while (0)
-
#define DBG_ARCH_ID_RESERVED 0 /* In case of ptrace ABI updates. */
+#define DBG_HOOK_HANDLED 0
+#define DBG_HOOK_ERROR 1
+
+struct step_hook {
+ struct list_head node;
+ int (*fn)(struct pt_regs *regs, unsigned int esr);
+};
+
+void register_step_hook(struct step_hook *hook);
+void unregister_step_hook(struct step_hook *hook);
+
+struct break_hook {
+ struct list_head node;
+ u32 esr_val;
+ u32 esr_mask;
+ int (*fn)(struct pt_regs *regs, unsigned int esr);
+};
+
+void register_break_hook(struct break_hook *hook);
+void unregister_break_hook(struct break_hook *hook);
+
u8 debug_monitors_arch(void);
+enum debug_el {
+ DBG_ACTIVE_EL0 = 0,
+ DBG_ACTIVE_EL1,
+};
+
void enable_debug_monitors(enum debug_el el);
void disable_debug_monitors(enum debug_el el);
@@ -83,6 +143,15 @@
}
#endif
+#ifdef CONFIG_COMPAT
+int aarch32_break_handler(struct pt_regs *regs);
+#else
+static int aarch32_break_handler(struct pt_regs *regs)
+{
+ return -EFAULT;
+}
+#endif
+
#endif /* __ASSEMBLY */
#endif /* __KERNEL__ */
#endif /* __ASM_DEBUG_MONITORS_H */
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 0d8453c..cf98b36 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -18,6 +18,9 @@
struct dev_archdata {
struct dma_map_ops *dma_ops;
+#ifdef CONFIG_IOMMU_API
+ void *iommu; /* private IOMMU data */
+#endif
};
struct pdev_archdata {
diff --git a/arch/arm64/include/asm/dma-contiguous.h b/arch/arm64/include/asm/dma-contiguous.h
new file mode 100644
index 0000000..14c4c0c
--- /dev/null
+++ b/arch/arm64/include/asm/dma-contiguous.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (c) 2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _ASM_DMA_CONTIGUOUS_H
+#define _ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 9947768..fa6a0c5 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -23,9 +23,10 @@
#include <asm-generic/dma-coherent.h>
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
+#define DMA_ERROR_CODE (~(dma_addr_t)0)
extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
static inline struct dma_map_ops *get_dma_ops(struct device *dev)
{
@@ -35,6 +36,11 @@
return dev->archdata.dma_ops;
}
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+ dev->archdata.dma_ops = ops;
+}
+
#include <asm-generic/dma-mapping-common.h>
static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -81,8 +87,12 @@
{
}
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags)
+#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_coherent(d, s, h, f) dma_free_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
void *vaddr;
@@ -90,13 +100,14 @@
if (dma_alloc_from_coherent(dev, size, dma_handle, &vaddr))
return vaddr;
- vaddr = ops->alloc(dev, size, dma_handle, flags, NULL);
+ vaddr = ops->alloc(dev, size, dma_handle, flags, attrs);
debug_dma_alloc_coherent(dev, size, *dma_handle, vaddr);
return vaddr;
}
-static inline void dma_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dev_addr)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dev_addr,
+ struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
@@ -104,7 +115,7 @@
return;
debug_dma_free_coherent(dev, size, vaddr, dev_addr);
- ops->free(dev, size, vaddr, dev_addr, NULL);
+ ops->free(dev, size, vaddr, dev_addr, attrs);
}
/*
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
new file mode 100644
index 0000000..5a46c4e
--- /dev/null
+++ b/arch/arm64/include/asm/efi.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_EFI_H
+#define _ASM_EFI_H
+
+#include <asm/io.h>
+
+#ifdef CONFIG_EFI
+extern void efi_init(void);
+extern void efi_idmap_init(void);
+#else
+#define efi_init()
+#define efi_idmap_init()
+#endif
+
+#endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index fe32c0e..01d3aab 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -33,8 +33,6 @@
typedef elf_greg_t elf_gregset_t[ELF_NGREG];
typedef struct user_fpsimd_state elf_fpregset_t;
-#define EM_AARCH64 183
-
/*
* AArch64 static relocation types.
*/
@@ -92,11 +90,24 @@
* These are used to set parameters in the core dumps.
*/
#define ELF_CLASS ELFCLASS64
+#ifdef __AARCH64EB__
+#define ELF_DATA ELFDATA2MSB
+#else
#define ELF_DATA ELFDATA2LSB
+#endif
#define ELF_ARCH EM_AARCH64
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization. This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
#define ELF_PLATFORM_SIZE 16
+#ifdef __AARCH64EB__
+#define ELF_PLATFORM ("aarch64_be")
+#else
#define ELF_PLATFORM ("aarch64")
+#endif
/*
* This is used to ensure we don't load something for the wrong architecture.
@@ -151,8 +162,12 @@
#define arch_randomize_brk arch_randomize_brk
#ifdef CONFIG_COMPAT
-#define EM_ARM 40
+
+#ifdef __AARCH64EB__
+#define COMPAT_ELF_PLATFORM ("v8b")
+#else
#define COMPAT_ELF_PLATFORM ("v8l")
+#endif
#define COMPAT_ELF_ET_DYN_BASE (randomize_et_dyn(2 * TASK_SIZE_32 / 3))
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 7883412..c4a7f94 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -42,7 +42,7 @@
#define ESR_EL1_EC_SP_ALIGN (0x26)
#define ESR_EL1_EC_FP_EXC32 (0x28)
#define ESR_EL1_EC_FP_EXC64 (0x2C)
-#define ESR_EL1_EC_SERRROR (0x2F)
+#define ESR_EL1_EC_SERROR (0x2F)
#define ESR_EL1_EC_BREAKPT_EL0 (0x30)
#define ESR_EL1_EC_BREAKPT_EL1 (0x31)
#define ESR_EL1_EC_SOFTSTP_EL0 (0x32)
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
new file mode 100644
index 0000000..5f7bfe6
--- /dev/null
+++ b/arch/arm64/include/asm/fixmap.h
@@ -0,0 +1,67 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ * Copyright (C) 2013 Mark Salter <msalter@redhat.com>
+ *
+ * Adapted from arch/x86_64 version.
+ *
+ */
+
+#ifndef _ASM_ARM64_FIXMAP_H
+#define _ASM_ARM64_FIXMAP_H
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * page-sized. Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ */
+enum fixed_addresses {
+ FIX_EARLYCON_MEM_BASE,
+ __end_of_permanent_fixed_addresses,
+
+ /*
+ * Temporary boot-time mappings, used by early_ioremap(),
+ * before ioremap() is functional.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+#define NR_FIX_BTMAPS 4
+#else
+#define NR_FIX_BTMAPS 64
+#endif
+#define FIX_BTMAPS_SLOTS 7
+#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+ FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+ FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+ __end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
+
+#define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE)
+
+extern void __early_set_fixmap(enum fixed_addresses idx,
+ phys_addr_t phys, pgprot_t flags);
+
+#define __set_fixmap __early_set_fixmap
+
+#include <asm-generic/fixmap.h>
+
+#endif /* !__ASSEMBLY__ */
+#endif /* _ASM_ARM64_FIXMAP_H */
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
new file mode 100644
index 0000000..c5534fa
--- /dev/null
+++ b/arch/arm64/include/asm/ftrace.h
@@ -0,0 +1,59 @@
+/*
+ * arch/arm64/include/asm/ftrace.h
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_FTRACE_H
+#define __ASM_FTRACE_H
+
+#include <asm/insn.h>
+
+#define MCOUNT_ADDR ((unsigned long)_mcount)
+#define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE
+
+#ifndef __ASSEMBLY__
+#include <linux/compat.h>
+
+extern void _mcount(unsigned long);
+extern void *return_address(unsigned int);
+
+struct dyn_arch_ftrace {
+ /* No extra data needed for arm64 */
+};
+
+extern unsigned long ftrace_graph_call;
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+ /*
+ * addr is the address of the mcount call instruction.
+ * recordmcount does the necessary offset calculation.
+ */
+ return addr;
+}
+
+#define ftrace_return_address(n) return_address(n)
+
+/*
+ * Because AArch32 mode does not share the same syscall table with AArch64,
+ * tracing compat syscalls may result in reporting bogus syscalls or even
+ * hang-up, so just do not trace them.
+ * See kernel/trace/trace_syscalls.c
+ *
+ * x86 code says:
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ return is_compat_task();
+}
+#endif /* ifndef __ASSEMBLY__ */
+
+#endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index c582fa3..5f750dc 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -24,12 +24,14 @@
#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
asm volatile( \
-"1: ldaxr %w1, %2\n" \
+"1: ldxr %w1, %2\n" \
insn "\n" \
"2: stlxr %w3, %w0, %2\n" \
" cbnz %w3, 1b\n" \
+" dmb ish\n" \
"3:\n" \
" .pushsection .fixup,\"ax\"\n" \
+" .align 2\n" \
"4: mov %w0, %w5\n" \
" b 3b\n" \
" .popsection\n" \
@@ -39,7 +41,7 @@
" .popsection\n" \
: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \
: "r" (oparg), "Ir" (-EFAULT) \
- : "cc", "memory")
+ : "memory")
static inline int
futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -110,11 +112,12 @@
return -EFAULT;
asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-"1: ldaxr %w1, %2\n"
+"1: ldxr %w1, %2\n"
" sub %w3, %w1, %w4\n"
" cbnz %w3, 3f\n"
"2: stlxr %w3, %w5, %2\n"
" cbnz %w3, 1b\n"
+" dmb ish\n"
"3:\n"
" .pushsection .fixup,\"ax\"\n"
"4: mov %w0, %w6\n"
@@ -126,7 +129,7 @@
" .popsection\n"
: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
- : "cc", "memory");
+ : "memory");
*uval = val;
return ret;
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 990c051..ae4801d 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
-#define NR_IPI 4
+#define NR_IPI 5
typedef struct {
unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
new file mode 100644
index 0000000..5b7ca8a
--- /dev/null
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -0,0 +1,117 @@
+/*
+ * arch/arm64/include/asm/hugetlb.h
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/include/asm/hugetlb.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_HUGETLB_H
+#define __ASM_HUGETLB_H
+
+#include <asm-generic/hugetlb.h>
+#include <asm/page.h>
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+ return *ptep;
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep)
+{
+ ptep_clear_flush(vma, addr, ptep);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty)
+{
+ return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor,
+ unsigned long ceiling)
+{
+ free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+ unsigned long addr, unsigned long len)
+{
+ return 0;
+}
+
+static inline int prepare_hugepage_range(struct file *file,
+ unsigned long addr, unsigned long len)
+{
+ struct hstate *h = hstate_file(file);
+ if (len & ~huge_page_mask(h))
+ return -EINVAL;
+ if (addr & ~huge_page_mask(h))
+ return -EINVAL;
+ return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+ return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+ return pte_wrprotect(pte);
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+ return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+ clear_bit(PG_dcache_clean, &page->flags);
+}
+
+#endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index d064047..52b484b 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -79,7 +79,6 @@
*/
#define ARM_MAX_BRP 16
#define ARM_MAX_WRP 16
-#define ARM_MAX_HBP_SLOTS (ARM_MAX_BRP + ARM_MAX_WRP)
/* Virtual debug register bases. */
#define AARCH64_DBG_REG_BVR 0
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6d4482f..024c461 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -30,6 +30,13 @@
#define COMPAT_HWCAP_IDIVA (1 << 17)
#define COMPAT_HWCAP_IDIVT (1 << 18)
#define COMPAT_HWCAP_IDIV (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
+#define COMPAT_HWCAP_EVTSTRM (1 << 21)
+
+#define COMPAT_HWCAP2_AES (1 << 0)
+#define COMPAT_HWCAP2_PMULL (1 << 1)
+#define COMPAT_HWCAP2_SHA1 (1 << 2)
+#define COMPAT_HWCAP2_SHA2 (1 << 3)
+#define COMPAT_HWCAP2_CRC32 (1 << 4)
#ifndef __ASSEMBLY__
/*
@@ -37,12 +44,13 @@
* instruction set this cpu supports.
*/
#define ELF_HWCAP (elf_hwcap)
-#define COMPAT_ELF_HWCAP (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
- COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
- COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
- COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
- COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
-extern unsigned int elf_hwcap;
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP (compat_elf_hwcap)
+#define COMPAT_ELF_HWCAP2 (compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
+#endif
+
+extern unsigned long elf_hwcap;
#endif
#endif
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
new file mode 100644
index 0000000..62e7b8b
--- /dev/null
+++ b/arch/arm64/include/asm/insn.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_INSN_H
+#define __ASM_INSN_H
+
+#include <linux/types.h>
+
+/* A64 instructions are always 32 bits. */
+#define AARCH64_INSN_SIZE 4
+
+#ifndef __ASSEMBLY__
+
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section C3.1 "A64 instruction index by encoding":
+ * AArch64 main encoding table
+ * Bit position
+ * 28 27 26 25 Encoding Group
+ * 0 0 - - Unallocated
+ * 1 0 0 - Data processing, immediate
+ * 1 0 1 - Branch, exception generation and system instructions
+ * - 1 - 0 Loads and stores
+ * - 1 0 1 Data processing - register
+ * 0 1 1 1 Data processing - SIMD and floating point
+ * 1 1 1 1 Data processing - SIMD and floating point
+ * "-" means "don't care"
+ */
+enum aarch64_insn_encoding_class {
+ AARCH64_INSN_CLS_UNKNOWN, /* UNALLOCATED */
+ AARCH64_INSN_CLS_DP_IMM, /* Data processing - immediate */
+ AARCH64_INSN_CLS_DP_REG, /* Data processing - register */
+ AARCH64_INSN_CLS_DP_FPSIMD, /* Data processing - SIMD and FP */
+ AARCH64_INSN_CLS_LDST, /* Loads and stores */
+ AARCH64_INSN_CLS_BR_SYS, /* Branch, exception generation and
+ * system instructions */
+};
+
+enum aarch64_insn_hint_op {
+ AARCH64_INSN_HINT_NOP = 0x0 << 5,
+ AARCH64_INSN_HINT_YIELD = 0x1 << 5,
+ AARCH64_INSN_HINT_WFE = 0x2 << 5,
+ AARCH64_INSN_HINT_WFI = 0x3 << 5,
+ AARCH64_INSN_HINT_SEV = 0x4 << 5,
+ AARCH64_INSN_HINT_SEVL = 0x5 << 5,
+};
+
+enum aarch64_insn_imm_type {
+ AARCH64_INSN_IMM_ADR,
+ AARCH64_INSN_IMM_26,
+ AARCH64_INSN_IMM_19,
+ AARCH64_INSN_IMM_16,
+ AARCH64_INSN_IMM_14,
+ AARCH64_INSN_IMM_12,
+ AARCH64_INSN_IMM_9,
+ AARCH64_INSN_IMM_MAX
+};
+
+enum aarch64_insn_branch_type {
+ AARCH64_INSN_BRANCH_NOLINK,
+ AARCH64_INSN_BRANCH_LINK,
+};
+
+#define __AARCH64_INSN_FUNCS(abbr, mask, val) \
+static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
+{ return (code & (mask)) == (val); } \
+static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
+{ return (val); }
+
+__AARCH64_INSN_FUNCS(b, 0xFC000000, 0x14000000)
+__AARCH64_INSN_FUNCS(bl, 0xFC000000, 0x94000000)
+__AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001)
+__AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002)
+__AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003)
+__AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000)
+__AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F)
+
+#undef __AARCH64_INSN_FUNCS
+
+bool aarch64_insn_is_nop(u32 insn);
+
+int aarch64_insn_read(void *addr, u32 *insnp);
+int aarch64_insn_write(void *addr, u32 insn);
+enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
+u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+ u32 insn, u64 imm);
+u32 aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+ enum aarch64_insn_branch_type type);
+u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_op op);
+u32 aarch64_insn_gen_nop(void);
+
+bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
+
+int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
+int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
+int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_INSN_H */
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 2e12258..732e3d5 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -26,6 +26,7 @@
#include <asm/byteorder.h>
#include <asm/barrier.h>
#include <asm/pgtable.h>
+#include <asm/early_ioremap.h>
/*
* Generic IO read/write. These perform native-endian accesses.
@@ -118,7 +119,7 @@
* I/O port access primitives.
*/
#define IO_SPACE_LIMIT 0xffff
-#define PCI_IOBASE ((void __iomem *)(MODULES_VADDR - SZ_2M))
+#define PCI_IOBASE ((void __iomem *)(MODULES_VADDR - SZ_32M))
static inline u8 inb(unsigned long addr)
{
@@ -224,19 +225,13 @@
*/
extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot);
extern void __iounmap(volatile void __iomem *addr);
-
-#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
-#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
+extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
#define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE))
#define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC))
#define iounmap __iounmap
-#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF)
-#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PTE_PXN | PTE_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
-
#define ARCH_HAS_IOREMAP_WC
#include <asm-generic/iomap.h>
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 0332fc0..e1f7ecd 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -4,6 +4,7 @@
#include <asm-generic/irq.h>
extern void (*handle_arch_irq)(struct pt_regs *);
+extern void migrate_irqs(void);
extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
#endif
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index aa11943..0ed52c6 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -87,5 +87,28 @@
return flags & PSR_I_BIT;
}
+/*
+ * save and restore debug state
+ */
+#define local_dbg_save(flags) \
+ do { \
+ typecheck(unsigned long, flags); \
+ asm volatile( \
+ "mrs %0, daif // local_dbg_save\n" \
+ "msr daifset, #8" \
+ : "=r" (flags) : : "memory"); \
+ } while (0)
+
+#define local_dbg_restore(flags) \
+ do { \
+ typecheck(unsigned long, flags); \
+ asm volatile( \
+ "msr daif, %0 // local_dbg_restore\n" \
+ : : "r" (flags) : "memory"); \
+ } while (0)
+
+#define local_dbg_enable() asm("msr daifclr, #8" : : : "memory")
+#define local_dbg_disable() asm("msr daifset, #8" : : : "memory")
+
#endif
#endif
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
new file mode 100644
index 0000000..076a1c7
--- /dev/null
+++ b/arch/arm64/include/asm/jump_label.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Based on arch/arm/include/asm/jump_label.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_JUMP_LABEL_H
+#define __ASM_JUMP_LABEL_H
+#include <linux/types.h>
+#include <asm/insn.h>
+
+#ifdef __KERNEL__
+
+#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
+
+static __always_inline bool arch_static_branch(struct static_key *key)
+{
+ asm goto("1: nop\n\t"
+ ".pushsection __jump_table, \"aw\"\n\t"
+ ".align 3\n\t"
+ ".quad 1b, %l[l_yes], %c0\n\t"
+ ".popsection\n\t"
+ : : "i"(key) : : l_yes);
+
+ return false;
+l_yes:
+ return true;
+}
+
+#endif /* __KERNEL__ */
+
+typedef u64 jump_label_t;
+
+struct jump_entry {
+ jump_label_t code;
+ jump_label_t target;
+ jump_label_t key;
+};
+
+#endif /* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
new file mode 100644
index 0000000..3c8aafc
--- /dev/null
+++ b/arch/arm64/include/asm/kgdb.h
@@ -0,0 +1,84 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/include/kgdb.h
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KGDB_H
+#define __ARM_KGDB_H
+
+#include <linux/ptrace.h>
+#include <asm/debug-monitors.h>
+
+#ifndef __ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+ asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * gdb is expecting the following registers layout.
+ *
+ * General purpose regs:
+ * r0-r30: 64 bit
+ * sp,pc : 64 bit
+ * pstate : 64 bit
+ * Total: 34
+ * FPU regs:
+ * f0-f31: 128 bit
+ * Total: 32
+ * Extra regs
+ * fpsr & fpcr: 32 bit
+ * Total: 2
+ *
+ */
+
+#define _GP_REGS 34
+#define _FP_REGS 32
+#define _EXTRA_REGS 2
+/*
+ * general purpose registers size in bytes.
+ * pstate is only 4 bytes. subtract 4 bytes
+ */
+#define GP_REG_BYTES (_GP_REGS * 8)
+#define DBG_MAX_REG_NUM (_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+
+#define BUFMAX 2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * _GP_REGS: 8 bytes, _FP_REGS: 16 bytes and _EXTRA_REGS: 4 bytes each
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+
+#define NUMREGBYTES ((_GP_REGS * 8) + (_FP_REGS * 16) + \
+ (_EXTRA_REGS * 4))
+
+#endif /* __ASM_KGDB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
new file mode 100644
index 0000000..7fd3e27
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -0,0 +1,259 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_ARM_H__
+#define __ARM64_KVM_ARM_H__
+
+#include <asm/types.h>
+
+/* Hyp Configuration Register (HCR) bits */
+#define HCR_ID (UL(1) << 33)
+#define HCR_CD (UL(1) << 32)
+#define HCR_RW_SHIFT 31
+#define HCR_RW (UL(1) << HCR_RW_SHIFT)
+#define HCR_TRVM (UL(1) << 30)
+#define HCR_HCD (UL(1) << 29)
+#define HCR_TDZ (UL(1) << 28)
+#define HCR_TGE (UL(1) << 27)
+#define HCR_TVM (UL(1) << 26)
+#define HCR_TTLB (UL(1) << 25)
+#define HCR_TPU (UL(1) << 24)
+#define HCR_TPC (UL(1) << 23)
+#define HCR_TSW (UL(1) << 22)
+#define HCR_TAC (UL(1) << 21)
+#define HCR_TIDCP (UL(1) << 20)
+#define HCR_TSC (UL(1) << 19)
+#define HCR_TID3 (UL(1) << 18)
+#define HCR_TID2 (UL(1) << 17)
+#define HCR_TID1 (UL(1) << 16)
+#define HCR_TID0 (UL(1) << 15)
+#define HCR_TWE (UL(1) << 14)
+#define HCR_TWI (UL(1) << 13)
+#define HCR_DC (UL(1) << 12)
+#define HCR_BSU (3 << 10)
+#define HCR_BSU_IS (UL(1) << 10)
+#define HCR_FB (UL(1) << 9)
+#define HCR_VA (UL(1) << 8)
+#define HCR_VI (UL(1) << 7)
+#define HCR_VF (UL(1) << 6)
+#define HCR_AMO (UL(1) << 5)
+#define HCR_IMO (UL(1) << 4)
+#define HCR_FMO (UL(1) << 3)
+#define HCR_PTW (UL(1) << 2)
+#define HCR_SWIO (UL(1) << 1)
+#define HCR_VM (UL(1) << 0)
+
+/*
+ * The bits we set in HCR:
+ * RW: 64bit by default, can be overriden for 32bit VMs
+ * TAC: Trap ACTLR
+ * TSC: Trap SMC
+ * TVM: Trap VM ops (until M+C set in SCTLR_EL1)
+ * TSW: Trap cache operations by set/way
+ * TWE: Trap WFE
+ * TWI: Trap WFI
+ * TIDCP: Trap L2CTLR/L2ECTLR
+ * BSU_IS: Upgrade barriers to the inner shareable domain
+ * FB: Force broadcast of all maintainance operations
+ * AMO: Override CPSR.A and enable signaling with VA
+ * IMO: Override CPSR.I and enable signaling with VI
+ * FMO: Override CPSR.F and enable signaling with VF
+ * SWIO: Turn set/way invalidates into set/way clean+invalidate
+ */
+#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
+ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \
+ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW)
+#define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF)
+#define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO)
+
+
+/* Hyp System Control Register (SCTLR_EL2) bits */
+#define SCTLR_EL2_EE (1 << 25)
+#define SCTLR_EL2_WXN (1 << 19)
+#define SCTLR_EL2_I (1 << 12)
+#define SCTLR_EL2_SA (1 << 3)
+#define SCTLR_EL2_C (1 << 2)
+#define SCTLR_EL2_A (1 << 1)
+#define SCTLR_EL2_M 1
+#define SCTLR_EL2_FLAGS (SCTLR_EL2_M | SCTLR_EL2_A | SCTLR_EL2_C | \
+ SCTLR_EL2_SA | SCTLR_EL2_I)
+
+/* TCR_EL2 Registers bits */
+#define TCR_EL2_TBI (1 << 20)
+#define TCR_EL2_PS (7 << 16)
+#define TCR_EL2_PS_40B (2 << 16)
+#define TCR_EL2_TG0 (1 << 14)
+#define TCR_EL2_SH0 (3 << 12)
+#define TCR_EL2_ORGN0 (3 << 10)
+#define TCR_EL2_IRGN0 (3 << 8)
+#define TCR_EL2_T0SZ 0x3f
+#define TCR_EL2_MASK (TCR_EL2_TG0 | TCR_EL2_SH0 | \
+ TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
+
+#define TCR_EL2_FLAGS (TCR_EL2_PS_40B)
+
+/* VTCR_EL2 Registers bits */
+#define VTCR_EL2_PS_MASK (7 << 16)
+#define VTCR_EL2_TG0_MASK (1 << 14)
+#define VTCR_EL2_TG0_4K (0 << 14)
+#define VTCR_EL2_TG0_64K (1 << 14)
+#define VTCR_EL2_SH0_MASK (3 << 12)
+#define VTCR_EL2_SH0_INNER (3 << 12)
+#define VTCR_EL2_ORGN0_MASK (3 << 10)
+#define VTCR_EL2_ORGN0_WBWA (1 << 10)
+#define VTCR_EL2_IRGN0_MASK (3 << 8)
+#define VTCR_EL2_IRGN0_WBWA (1 << 8)
+#define VTCR_EL2_SL0_MASK (3 << 6)
+#define VTCR_EL2_SL0_LVL1 (1 << 6)
+#define VTCR_EL2_T0SZ_MASK 0x3f
+#define VTCR_EL2_T0SZ_40B 24
+
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
+#ifdef CONFIG_ARM64_64K_PAGES
+/*
+ * Stage2 translation configuration:
+ * 40bits output (PS = 2)
+ * 40bits input (T0SZ = 24)
+ * 64kB pages (TG0 = 1)
+ * 2 level page tables (SL = 1)
+ */
+#define VTCR_EL2_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
+ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+ VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
+#define VTTBR_X (38 - VTCR_EL2_T0SZ_40B)
+#else
+/*
+ * Stage2 translation configuration:
+ * 40bits output (PS = 2)
+ * 40bits input (T0SZ = 24)
+ * 4kB pages (TG0 = 0)
+ * 3 level page tables (SL = 1)
+ */
+#define VTCR_EL2_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
+ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+ VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
+#define VTTBR_X (37 - VTCR_EL2_T0SZ_40B)
+#endif
+
+#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
+#define VTTBR_BADDR_MASK (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT (48LLU)
+#define VTTBR_VMID_MASK (0xffLLU << VTTBR_VMID_SHIFT)
+
+/* Hyp System Trap Register */
+#define HSTR_EL2_TTEE (1 << 16)
+#define HSTR_EL2_T(x) (1 << x)
+
+/* Hyp Coprocessor Trap Register */
+#define CPTR_EL2_TCPAC (1 << 31)
+#define CPTR_EL2_TTA (1 << 20)
+#define CPTR_EL2_TFP (1 << 10)
+
+/* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TDRA (1 << 11)
+#define MDCR_EL2_TDOSA (1 << 10)
+#define MDCR_EL2_TDA (1 << 9)
+#define MDCR_EL2_TDE (1 << 8)
+#define MDCR_EL2_HPME (1 << 7)
+#define MDCR_EL2_TPM (1 << 6)
+#define MDCR_EL2_TPMCR (1 << 5)
+#define MDCR_EL2_HPMN_MASK (0x1F)
+
+/* Exception Syndrome Register (ESR) bits */
+#define ESR_EL2_EC_SHIFT (26)
+#define ESR_EL2_EC (0x3fU << ESR_EL2_EC_SHIFT)
+#define ESR_EL2_IL (1U << 25)
+#define ESR_EL2_ISS (ESR_EL2_IL - 1)
+#define ESR_EL2_ISV_SHIFT (24)
+#define ESR_EL2_ISV (1U << ESR_EL2_ISV_SHIFT)
+#define ESR_EL2_SAS_SHIFT (22)
+#define ESR_EL2_SAS (3U << ESR_EL2_SAS_SHIFT)
+#define ESR_EL2_SSE (1 << 21)
+#define ESR_EL2_SRT_SHIFT (16)
+#define ESR_EL2_SRT_MASK (0x1f << ESR_EL2_SRT_SHIFT)
+#define ESR_EL2_SF (1 << 15)
+#define ESR_EL2_AR (1 << 14)
+#define ESR_EL2_EA (1 << 9)
+#define ESR_EL2_CM (1 << 8)
+#define ESR_EL2_S1PTW (1 << 7)
+#define ESR_EL2_WNR (1 << 6)
+#define ESR_EL2_FSC (0x3f)
+#define ESR_EL2_FSC_TYPE (0x3c)
+
+#define ESR_EL2_CV_SHIFT (24)
+#define ESR_EL2_CV (1U << ESR_EL2_CV_SHIFT)
+#define ESR_EL2_COND_SHIFT (20)
+#define ESR_EL2_COND (0xfU << ESR_EL2_COND_SHIFT)
+
+
+#define FSC_FAULT (0x04)
+#define FSC_PERM (0x0c)
+
+/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
+#define HPFAR_MASK (~0xFUL)
+
+#define ESR_EL2_EC_UNKNOWN (0x00)
+#define ESR_EL2_EC_WFI (0x01)
+#define ESR_EL2_EC_CP15_32 (0x03)
+#define ESR_EL2_EC_CP15_64 (0x04)
+#define ESR_EL2_EC_CP14_MR (0x05)
+#define ESR_EL2_EC_CP14_LS (0x06)
+#define ESR_EL2_EC_FP_ASIMD (0x07)
+#define ESR_EL2_EC_CP10_ID (0x08)
+#define ESR_EL2_EC_CP14_64 (0x0C)
+#define ESR_EL2_EC_ILL_ISS (0x0E)
+#define ESR_EL2_EC_SVC32 (0x11)
+#define ESR_EL2_EC_HVC32 (0x12)
+#define ESR_EL2_EC_SMC32 (0x13)
+#define ESR_EL2_EC_SVC64 (0x15)
+#define ESR_EL2_EC_HVC64 (0x16)
+#define ESR_EL2_EC_SMC64 (0x17)
+#define ESR_EL2_EC_SYS64 (0x18)
+#define ESR_EL2_EC_IABT (0x20)
+#define ESR_EL2_EC_IABT_HYP (0x21)
+#define ESR_EL2_EC_PC_ALIGN (0x22)
+#define ESR_EL2_EC_DABT (0x24)
+#define ESR_EL2_EC_DABT_HYP (0x25)
+#define ESR_EL2_EC_SP_ALIGN (0x26)
+#define ESR_EL2_EC_FP_EXC32 (0x28)
+#define ESR_EL2_EC_FP_EXC64 (0x2C)
+#define ESR_EL2_EC_SERROR (0x2F)
+#define ESR_EL2_EC_BREAKPT (0x30)
+#define ESR_EL2_EC_BREAKPT_HYP (0x31)
+#define ESR_EL2_EC_SOFTSTP (0x32)
+#define ESR_EL2_EC_SOFTSTP_HYP (0x33)
+#define ESR_EL2_EC_WATCHPT (0x34)
+#define ESR_EL2_EC_WATCHPT_HYP (0x35)
+#define ESR_EL2_EC_BKPT32 (0x38)
+#define ESR_EL2_EC_VECTOR32 (0x3A)
+#define ESR_EL2_EC_BRK64 (0x3C)
+
+#define ESR_EL2_EC_xABT_xFSR_EXTABT 0x10
+
+#define ESR_EL2_EC_WFI_ISS_WFE (1 << 0)
+
+#endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
new file mode 100644
index 0000000..4838421
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -0,0 +1,141 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_ASM_H__
+#define __ARM_KVM_ASM_H__
+
+#include <asm/virt.h>
+
+/*
+ * 0 is reserved as an invalid value.
+ * Order *must* be kept in sync with the hyp switch code.
+ */
+#define MPIDR_EL1 1 /* MultiProcessor Affinity Register */
+#define CSSELR_EL1 2 /* Cache Size Selection Register */
+#define SCTLR_EL1 3 /* System Control Register */
+#define ACTLR_EL1 4 /* Auxilliary Control Register */
+#define CPACR_EL1 5 /* Coprocessor Access Control */
+#define TTBR0_EL1 6 /* Translation Table Base Register 0 */
+#define TTBR1_EL1 7 /* Translation Table Base Register 1 */
+#define TCR_EL1 8 /* Translation Control Register */
+#define ESR_EL1 9 /* Exception Syndrome Register */
+#define AFSR0_EL1 10 /* Auxilary Fault Status Register 0 */
+#define AFSR1_EL1 11 /* Auxilary Fault Status Register 1 */
+#define FAR_EL1 12 /* Fault Address Register */
+#define MAIR_EL1 13 /* Memory Attribute Indirection Register */
+#define VBAR_EL1 14 /* Vector Base Address Register */
+#define CONTEXTIDR_EL1 15 /* Context ID Register */
+#define TPIDR_EL0 16 /* Thread ID, User R/W */
+#define TPIDRRO_EL0 17 /* Thread ID, User R/O */
+#define TPIDR_EL1 18 /* Thread ID, Privileged */
+#define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */
+#define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */
+#define PAR_EL1 21 /* Physical Address Register */
+#define MDSCR_EL1 22 /* Monitor Debug System Control Register */
+#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */
+#define DBGBCR15_EL1 38
+#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */
+#define DBGBVR15_EL1 54
+#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */
+#define DBGWCR15_EL1 70
+#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */
+#define DBGWVR15_EL1 86
+#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */
+
+/* 32bit specific registers. Keep them at the end of the range */
+#define DACR32_EL2 88 /* Domain Access Control Register */
+#define IFSR32_EL2 89 /* Instruction Fault Status Register */
+#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */
+#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */
+#define TEECR32_EL1 92 /* ThumbEE Configuration Register */
+#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */
+#define NR_SYS_REGS 94
+
+/* 32bit mapping */
+#define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */
+#define c0_CSSELR (CSSELR_EL1 * 2)/* Cache Size Selection Register */
+#define c1_SCTLR (SCTLR_EL1 * 2) /* System Control Register */
+#define c1_ACTLR (ACTLR_EL1 * 2) /* Auxiliary Control Register */
+#define c1_CPACR (CPACR_EL1 * 2) /* Coprocessor Access Control */
+#define c2_TTBR0 (TTBR0_EL1 * 2) /* Translation Table Base Register 0 */
+#define c2_TTBR0_high (c2_TTBR0 + 1) /* TTBR0 top 32 bits */
+#define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */
+#define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */
+#define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */
+#define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */
+#define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */
+#define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */
+#define c5_ADFSR (AFSR0_EL1 * 2) /* Auxiliary Data Fault Status R */
+#define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */
+#define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */
+#define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */
+#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */
+#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */
+#define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */
+#define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */
+#define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */
+#define c13_CID (CONTEXTIDR_EL1 * 2) /* Context ID Register */
+#define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */
+#define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */
+#define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */
+#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */
+#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */
+#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */
+
+#define cp14_DBGDSCRext (MDSCR_EL1 * 2)
+#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2)
+#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2)
+#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1)
+#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2)
+#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2)
+#define cp14_DBGDCCINT (MDCCINT_EL1 * 2)
+
+#define NR_COPRO_REGS (NR_SYS_REGS * 2)
+
+#define ARM_EXCEPTION_IRQ 0
+#define ARM_EXCEPTION_TRAP 1
+
+#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
+#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
+
+#ifndef __ASSEMBLY__
+struct kvm;
+struct kvm_vcpu;
+
+extern char __kvm_hyp_init[];
+extern char __kvm_hyp_init_end[];
+
+extern char __kvm_hyp_vector[];
+
+#define __kvm_hyp_code_start __hyp_text_start
+#define __kvm_hyp_code_end __hyp_text_end
+
+extern void __kvm_flush_vm_context(void);
+extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+
+extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+
+extern u64 __vgic_v3_get_ich_vtr_el2(void);
+
+extern char __save_vgic_v2_state[];
+extern char __restore_vgic_v2_state[];
+extern char __save_vgic_v3_state[];
+extern char __restore_vgic_v3_state[];
+
+#endif
+
+#endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h
new file mode 100644
index 0000000..0b52377
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_coproc.h
@@ -0,0 +1,57 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/asm/kvm_coproc.h
+ * Copyright (C) 2012 Rusty Russell IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_COPROC_H__
+#define __ARM64_KVM_COPROC_H__
+
+#include <linux/kvm_host.h>
+
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu);
+
+struct kvm_sys_reg_table {
+ const struct sys_reg_desc *table;
+ size_t num;
+};
+
+struct kvm_sys_reg_target_table {
+ struct kvm_sys_reg_table table64;
+ struct kvm_sys_reg_table table32;
+};
+
+void kvm_register_target_sys_reg_table(unsigned int target,
+ struct kvm_sys_reg_target_table *table);
+
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+#define kvm_coproc_table_init kvm_sys_reg_table_init
+void kvm_sys_reg_table_init(void);
+
+struct kvm_one_reg;
+int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices);
+int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
+unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu);
+
+#endif /* __ARM64_KVM_COPROC_H__ */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
new file mode 100644
index 0000000..5674a55
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -0,0 +1,268 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/kvm_emulate.h
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_EMULATE_H__
+#define __ARM64_KVM_EMULATE_H__
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmio.h>
+#include <asm/ptrace.h>
+
+unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num);
+unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu);
+
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr);
+
+void kvm_inject_undefined(struct kvm_vcpu *vcpu);
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
+
+static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu)
+{
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc;
+}
+
+static inline unsigned long *vcpu_elr_el1(const struct kvm_vcpu *vcpu)
+{
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1;
+}
+
+static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
+{
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate;
+}
+
+static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
+{
+ return !!(*vcpu_cpsr(vcpu) & PSR_MODE32_BIT);
+}
+
+static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return kvm_condition_valid32(vcpu);
+
+ return true;
+}
+
+static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ kvm_skip_instr32(vcpu, is_wide_instr);
+ else
+ *vcpu_pc(vcpu) += 4;
+}
+
+static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
+{
+ *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
+}
+
+static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return vcpu_reg32(vcpu, reg_num);
+
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+}
+
+/* Get vcpu SPSR for current mode */
+static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return vcpu_spsr32(vcpu);
+
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1];
+}
+
+static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
+{
+ u32 mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
+
+ if (vcpu_mode_is_32bit(vcpu))
+ return mode > COMPAT_PSR_MODE_USR;
+
+ return mode != PSR_MODE_EL0t;
+}
+
+static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.fault.esr_el2;
+}
+
+static inline unsigned long kvm_vcpu_get_hfar(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.fault.far_el2;
+}
+
+static inline phys_addr_t kvm_vcpu_get_fault_ipa(const struct kvm_vcpu *vcpu)
+{
+ return ((phys_addr_t)vcpu->arch.fault.hpfar_el2 & HPFAR_MASK) << 8;
+}
+
+static inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_ISV);
+}
+
+static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_WNR);
+}
+
+static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_SSE);
+}
+
+static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
+{
+ return (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_SRT_MASK) >> ESR_EL2_SRT_SHIFT;
+}
+
+static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EA);
+}
+
+static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_S1PTW);
+}
+
+static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
+{
+ return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_EL2_SAS) >> ESR_EL2_SAS_SHIFT);
+}
+
+/* This one is not specific to Data Abort */
+static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu)
+{
+ return !!(kvm_vcpu_get_hsr(vcpu) & ESR_EL2_IL);
+}
+
+static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_get_hsr(vcpu) >> ESR_EL2_EC_SHIFT;
+}
+
+static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_trap_get_class(vcpu) == ESR_EL2_EC_IABT;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
+}
+
+static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu)
+{
+ return vcpu_sys_reg(vcpu, MPIDR_EL1);
+}
+
+static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
+ else
+ vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25);
+}
+
+static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
+
+ return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
+}
+
+static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
+ unsigned long data,
+ unsigned int len)
+{
+ if (kvm_vcpu_is_be(vcpu)) {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return be16_to_cpu(data & 0xffff);
+ case 4:
+ return be32_to_cpu(data & 0xffffffff);
+ default:
+ return be64_to_cpu(data);
+ }
+ } else {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return le16_to_cpu(data & 0xffff);
+ case 4:
+ return le32_to_cpu(data & 0xffffffff);
+ default:
+ return le64_to_cpu(data);
+ }
+ }
+
+ return data; /* Leave LE untouched */
+}
+
+static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
+ unsigned long data,
+ unsigned int len)
+{
+ if (kvm_vcpu_is_be(vcpu)) {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return cpu_to_be16(data & 0xffff);
+ case 4:
+ return cpu_to_be32(data & 0xffffffff);
+ default:
+ return cpu_to_be64(data);
+ }
+ } else {
+ switch (len) {
+ case 1:
+ return data & 0xff;
+ case 2:
+ return cpu_to_le16(data & 0xffff);
+ case 4:
+ return cpu_to_le32(data & 0xffffffff);
+ default:
+ return cpu_to_le64(data);
+ }
+ }
+
+ return data; /* Leave LE untouched */
+}
+
+#endif /* __ARM64_KVM_EMULATE_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
new file mode 100644
index 0000000..bcde419
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -0,0 +1,251 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/asm/kvm_host.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_HOST_H__
+#define __ARM64_KVM_HOST_H__
+
+#include <linux/types.h>
+#include <linux/kvm_types.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmio.h>
+
+#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
+#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
+#else
+#define KVM_MAX_VCPUS 0
+#endif
+
+#define KVM_USER_MEM_SLOTS 32
+#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+#include <kvm/arm_vgic.h>
+#include <kvm/arm_arch_timer.h>
+
+#define KVM_VCPU_MAX_FEATURES 3
+
+int __attribute_const__ kvm_target_cpu(void);
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+int kvm_arch_dev_ioctl_check_extension(long ext);
+
+struct kvm_arch {
+ /* The VMID generation used for the virt. memory system */
+ u64 vmid_gen;
+ u32 vmid;
+
+ /* 1-level 2nd stage table and lock */
+ spinlock_t pgd_lock;
+ pgd_t *pgd;
+
+ /* VTTBR value associated with above pgd and vmid */
+ u64 vttbr;
+
+ /* Interrupt controller */
+ struct vgic_dist vgic;
+
+ /* Timer */
+ struct arch_timer_kvm timer;
+};
+
+#define KVM_NR_MEM_OBJS 40
+
+/*
+ * We don't want allocation failures within the mmu code, so we preallocate
+ * enough memory for a single page fault in a cache.
+ */
+struct kvm_mmu_memory_cache {
+ int nobjs;
+ void *objects[KVM_NR_MEM_OBJS];
+};
+
+struct kvm_vcpu_fault_info {
+ u32 esr_el2; /* Hyp Syndrom Register */
+ u64 far_el2; /* Hyp Fault Address Register */
+ u64 hpfar_el2; /* Hyp IPA Fault Address Register */
+};
+
+struct kvm_cpu_context {
+ struct kvm_regs gp_regs;
+ union {
+ u64 sys_regs[NR_SYS_REGS];
+ u32 copro[NR_COPRO_REGS];
+ };
+};
+
+typedef struct kvm_cpu_context kvm_cpu_context_t;
+
+struct kvm_vcpu_arch {
+ struct kvm_cpu_context ctxt;
+
+ /* HYP configuration */
+ u64 hcr_el2;
+
+ /* Exception Information */
+ struct kvm_vcpu_fault_info fault;
+
+ /* Debug state */
+ u64 debug_flags;
+
+ /* Pointer to host CPU context */
+ kvm_cpu_context_t *host_cpu_context;
+
+ /* VGIC state */
+ struct vgic_cpu vgic_cpu;
+ struct arch_timer_cpu timer_cpu;
+
+ /*
+ * Anything that is not used directly from assembly code goes
+ * here.
+ */
+ /* dcache set/way operation pending */
+ int last_pcpu;
+ cpumask_t require_dcache_flush;
+
+ /* Don't run the guest */
+ bool pause;
+
+ /* IO related fields */
+ struct kvm_decode mmio_decode;
+
+ /* Interrupt related fields */
+ u64 irq_lines; /* IRQ and FIQ levels */
+
+ /* Cache some mmu pages needed inside spinlock regions */
+ struct kvm_mmu_memory_cache mmu_page_cache;
+
+ /* Target CPU and feature flags */
+ int target;
+ DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
+
+ /* Detect first run of a vcpu */
+ bool has_run_once;
+};
+
+#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs)
+#define vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)])
+/*
+ * CP14 and CP15 live in the same array, as they are backed by the
+ * same system registers.
+ */
+#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)])
+#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)])
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r))
+#define vcpu_cp15_64_low(v,r) vcpu_cp15((v),(r) + 1)
+#else
+#define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r) + 1)
+#define vcpu_cp15_64_low(v,r) vcpu_cp15((v),(r))
+#endif
+
+struct kvm_vm_stat {
+ u32 remote_tlb_flush;
+};
+
+struct kvm_vcpu_stat {
+ u32 halt_wakeup;
+};
+
+int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+ const struct kvm_vcpu_init *init);
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
+int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_unmap_hva_range(struct kvm *kvm,
+ unsigned long start, unsigned long end);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+
+/* We do not have shadow page tables, hence the empty hooks */
+static inline int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+ return 0;
+}
+
+static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+ return 0;
+}
+
+struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
+
+u64 kvm_call_hyp(void *hypfn, ...);
+
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ int exception_index);
+
+int kvm_perf_init(void);
+int kvm_perf_teardown(void);
+
+static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
+ phys_addr_t pgd_ptr,
+ unsigned long hyp_stack_ptr,
+ unsigned long vector_ptr)
+{
+ /*
+ * Call initialization code, and switch to the full blown
+ * HYP code.
+ */
+ kvm_call_hyp((void *)boot_pgd_ptr, pgd_ptr,
+ hyp_stack_ptr, vector_ptr);
+}
+
+struct vgic_sr_vectors {
+ void *save_vgic;
+ void *restore_vgic;
+};
+
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+ extern struct vgic_sr_vectors __vgic_sr_vectors;
+
+ switch(vgic->type)
+ {
+ case VGIC_V2:
+ __vgic_sr_vectors.save_vgic = __save_vgic_v2_state;
+ __vgic_sr_vectors.restore_vgic = __restore_vgic_v2_state;
+ break;
+
+#ifdef CONFIG_ARM_GIC_V3
+ case VGIC_V3:
+ __vgic_sr_vectors.save_vgic = __save_vgic_v3_state;
+ __vgic_sr_vectors.restore_vgic = __restore_vgic_v3_state;
+ break;
+#endif
+
+ default:
+ BUG();
+ }
+}
+
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+
+#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
new file mode 100644
index 0000000..fc2f689
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_mmio.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_MMIO_H__
+#define __ARM64_KVM_MMIO_H__
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+/*
+ * This is annoying. The mmio code requires this, even if we don't
+ * need any decoding. To be fixed.
+ */
+struct kvm_decode {
+ unsigned long rt;
+ bool sign_extend;
+};
+
+/*
+ * The in-kernel MMIO emulation code wants to use a copy of run->mmio,
+ * which is an anonymous type. Use our own type instead.
+ */
+struct kvm_exit_mmio {
+ phys_addr_t phys_addr;
+ u8 data[8];
+ u32 len;
+ bool is_write;
+};
+
+static inline void kvm_prepare_mmio(struct kvm_run *run,
+ struct kvm_exit_mmio *mmio)
+{
+ run->mmio.phys_addr = mmio->phys_addr;
+ run->mmio.len = mmio->len;
+ run->mmio.is_write = mmio->is_write;
+ memcpy(run->mmio.data, mmio->data, mmio->len);
+ run->exit_reason = KVM_EXIT_MMIO;
+}
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ phys_addr_t fault_ipa);
+
+#endif /* __ARM64_KVM_MMIO_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
new file mode 100644
index 0000000..a030d16
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -0,0 +1,157 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_MMU_H__
+#define __ARM64_KVM_MMU_H__
+
+#include <asm/page.h>
+#include <asm/memory.h>
+
+/*
+ * As we only have the TTBR0_EL2 register, we cannot express
+ * "negative" addresses. This makes it impossible to directly share
+ * mappings with the kernel.
+ *
+ * Instead, give the HYP mode its own VA region at a fixed offset from
+ * the kernel by just masking the top bits (which are all ones for a
+ * kernel address).
+ */
+#define HYP_PAGE_OFFSET_SHIFT VA_BITS
+#define HYP_PAGE_OFFSET_MASK ((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
+#define HYP_PAGE_OFFSET (PAGE_OFFSET & HYP_PAGE_OFFSET_MASK)
+
+/*
+ * Our virtual mapping for the idmap-ed MMU-enable code. Must be
+ * shared across all the page-tables. Conveniently, we use the last
+ * possible page, where no kernel mapping will ever exist.
+ */
+#define TRAMPOLINE_VA (HYP_PAGE_OFFSET_MASK & PAGE_MASK)
+
+#ifdef __ASSEMBLY__
+
+/*
+ * Convert a kernel VA into a HYP VA.
+ * reg: VA to be converted.
+ */
+.macro kern_hyp_va reg
+ and \reg, \reg, #HYP_PAGE_OFFSET_MASK
+.endm
+
+#else
+
+#include <asm/cachetype.h>
+#include <asm/cacheflush.h>
+
+#define KERN_TO_HYP(kva) ((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
+
+/*
+ * We currently only support a 40bit IPA.
+ */
+#define KVM_PHYS_SHIFT (40)
+#define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT)
+#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL)
+
+/* Make sure we get the right size, and thus the right alignment */
+#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - PGDIR_SHIFT))
+#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
+int create_hyp_mappings(void *from, void *to);
+int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
+void free_boot_hyp_pgd(void);
+void free_hyp_pgds(void);
+
+int kvm_alloc_stage2_pgd(struct kvm *kvm);
+void kvm_free_stage2_pgd(struct kvm *kvm);
+int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
+ phys_addr_t pa, unsigned long size);
+
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
+
+void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
+
+phys_addr_t kvm_mmu_get_httbr(void);
+phys_addr_t kvm_mmu_get_boot_httbr(void);
+phys_addr_t kvm_get_idmap_vector(void);
+int kvm_mmu_init(void);
+void kvm_clear_hyp_idmap(void);
+
+#define kvm_set_pte(ptep, pte) set_pte(ptep, pte)
+#define kvm_set_pmd(pmdp, pmd) set_pmd(pmdp, pmd)
+
+static inline void kvm_clean_pgd(pgd_t *pgd) {}
+static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
+static inline void kvm_clean_pte(pte_t *pte) {}
+static inline void kvm_clean_pte_entry(pte_t *pte) {}
+
+static inline void kvm_set_s2pte_writable(pte_t *pte)
+{
+ pte_val(*pte) |= PTE_S2_RDWR;
+}
+
+static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
+{
+ pmd_val(*pmd) |= PMD_S2_RDWR;
+}
+
+#define kvm_pgd_addr_end(addr, end) pgd_addr_end(addr, end)
+#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end)
+#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end)
+
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#ifndef CONFIG_ARM64_64K_PAGES
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#else
+#define kvm_pmd_table_empty(pmdp) (0)
+#endif
+#define kvm_pud_table_empty(pudp) (0)
+
+
+struct kvm;
+
+#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
+
+static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
+{
+ return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
+}
+
+static inline void coherent_cache_guest_page(struct kvm_vcpu *vcpu, hva_t hva,
+ unsigned long size)
+{
+ if (!vcpu_has_cache_enabled(vcpu))
+ kvm_flush_dcache_to_poc((void *)hva, size);
+
+ if (!icache_is_aliasing()) { /* PIPT */
+ flush_icache_range(hva, hva + size);
+ } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */
+ /* any kind of VIPT cache */
+ __flush_icache_all();
+ }
+}
+
+#define kvm_virt_to_phys(x) __virt_to_phys((unsigned long)(x))
+
+void stage2_flush_vm(struct kvm *kvm);
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/kvm_psci.h b/arch/arm64/include/asm/kvm_psci.h
new file mode 100644
index 0000000..bc39e55
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_psci.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_PSCI_H__
+#define __ARM64_KVM_PSCI_H__
+
+#define KVM_ARM_PSCI_0_1 1
+#define KVM_ARM_PSCI_0_2 2
+
+int kvm_psci_version(struct kvm_vcpu *vcpu);
+int kvm_psci_call(struct kvm_vcpu *vcpu);
+
+#endif /* __ARM64_KVM_PSCI_H__ */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 381f556..71cd416 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -33,24 +33,31 @@
#define UL(x) _AC(x, UL)
/*
- * PAGE_OFFSET - the virtual address of the start of the kernel image.
+ * PAGE_OFFSET - the virtual address of the start of the kernel image (top
+ * (VA_BITS - 1))
* VA_BITS - the maximum number of bits for virtual addresses.
* TASK_SIZE - the maximum size of a user space task.
* TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
* The module space lives between the addresses given by TASK_SIZE
* and PAGE_OFFSET - it must be within 128MB of the kernel text.
*/
-#define PAGE_OFFSET UL(0xffffffc000000000)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define VA_BITS (42)
+#else
+#define VA_BITS (39)
+#endif
+#define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1))
#define MODULES_END (PAGE_OFFSET)
#define MODULES_VADDR (MODULES_END - SZ_64M)
-#define EARLYCON_IOBASE (MODULES_VADDR - SZ_4M)
-#define VA_BITS (39)
+#define FIXADDR_TOP (MODULES_VADDR - SZ_2M - PAGE_SIZE)
#define TASK_SIZE_64 (UL(1) << VA_BITS)
#ifdef CONFIG_COMPAT
#define TASK_SIZE_32 UL(0x100000000)
#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+ TASK_SIZE_32 : TASK_SIZE_64)
#else
#define TASK_SIZE TASK_SIZE_64
#endif /* CONFIG_COMPAT */
@@ -90,6 +97,12 @@
#define MT_NORMAL_NC 3
#define MT_NORMAL 4
+/*
+ * Memory types for Stage-2 translation
+ */
+#define MT_S2_NORMAL 0xf
+#define MT_S2_DEVICE_nGnRE 0x1
+
#ifndef __ASSEMBLY__
extern phys_addr_t memstart_addr;
@@ -127,6 +140,7 @@
#define __pa(x) __virt_to_phys((unsigned long)(x))
#define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x)))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+#define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys(x))
/*
* virt_to_page(k) convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 2494fc0..c2f006c 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -22,10 +22,16 @@
void *vdso;
} mm_context_t;
+#define INIT_MM_CONTEXT(name) \
+ .context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
+
#define ASID(mm) ((mm)->context.id & 0xffff)
extern void paging_init(void);
extern void setup_mm_for_reboot(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
+extern void init_mem_pgprot(void);
+/* create an identity mapping for memory (or io if map_io is true) */
+extern void create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io);
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index e2bc385..a9eee33 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -151,12 +151,6 @@
{
unsigned int cpu = smp_processor_id();
-#ifdef CONFIG_SMP
- /* check for possible thread migration */
- if (!cpumask_empty(mm_cpumask(next)) &&
- !cpumask_test_cpu(cpu, mm_cpumask(next)))
- __flush_icache_all();
-#endif
if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
check_and_switch_context(next, tsk);
}
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 46bf666..e84ca63 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -31,6 +31,15 @@
/* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
#define __HAVE_ARCH_GATE_AREA 1
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. Both require a pgd and a next level table to (section) map the
+ * kernel. The the swapper also maps the FDT (see __create_page_tables for
+ * more information).
+ */
+#define SWAPPER_DIR_SIZE (2 * PAGE_SIZE)
+#define IDMAP_DIR_SIZE (2 * PAGE_SIZE)
+
#ifndef __ASSEMBLY__
#ifdef CONFIG_ARM64_64K_PAGES
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
new file mode 100644
index 0000000..5279e57
--- /dev/null
+++ b/arch/arm64/include/asm/percpu.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_PERCPU_H
+#define __ASM_PERCPU_H
+
+#ifdef CONFIG_SMP
+
+static inline void set_my_cpu_offset(unsigned long off)
+{
+ asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
+}
+
+static inline unsigned long __my_cpu_offset(void)
+{
+ unsigned long off;
+
+ /*
+ * We want to allow caching the value, so avoid using volatile and
+ * instead use a fake stack read to hazard against barrier().
+ */
+ asm("mrs %0, tpidr_el1" : "=r" (off) :
+ "Q" (*(const unsigned long *)current_stack_pointer));
+
+ return off;
+}
+#define __my_cpu_offset __my_cpu_offset()
+
+#else /* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x) do { } while (0)
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/percpu.h>
+
+#endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable-2level-hwdef.h b/arch/arm64/include/asm/pgtable-2level-hwdef.h
index 0a8ed3f..2593b49 100644
--- a/arch/arm64/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-2level-hwdef.h
@@ -21,10 +21,10 @@
* 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
* used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
* entry representing 512MB. The user and kernel address spaces are limited to
- * 512GB and therefore we only use 1024 entries in the PGD.
+ * 4TB in the 64KB page configuration.
*/
#define PTRS_PER_PTE 8192
-#define PTRS_PER_PGD 1024
+#define PTRS_PER_PGD 8192
/*
* PGDIR_SHIFT determines the size a top-level page table entry can map.
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
index 3c3ca7d..5f101e6 100644
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ b/arch/arm64/include/asm/pgtable-2level-types.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
#define __ASM_PGTABLE_2LEVEL_TYPES_H
+#include <asm/types.h>
+
typedef u64 pteval_t;
typedef u64 pgdval_t;
typedef pgdval_t pmdval_t;
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-3level-types.h
index 4489615..4e94424 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-3level-types.h
@@ -16,6 +16,8 @@
#ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
#define __ASM_PGTABLE_3LEVEL_TYPES_H
+#include <asm/types.h>
+
typedef u64 pteval_t;
typedef u64 pmdval_t;
typedef u64 pgdval_t;
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 75fd13d..f7af66b 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -25,16 +25,27 @@
/*
* Hardware page table definitions.
*
+ * Level 1 descriptor (PUD).
+ */
+
+#define PUD_TABLE_BIT (_AT(pgdval_t, 1) << 1)
+
+/*
* Level 2 descriptor (PMD).
*/
#define PMD_TYPE_MASK (_AT(pmdval_t, 3) << 0)
#define PMD_TYPE_FAULT (_AT(pmdval_t, 0) << 0)
#define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0)
#define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0)
+#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1)
/*
* Section
*/
+#define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0)
+#define PMD_SECT_PROT_NONE (_AT(pmdval_t, 1) << 58)
+#define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */
+#define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */
#define PMD_SECT_S (_AT(pmdval_t, 3) << 8)
#define PMD_SECT_AF (_AT(pmdval_t, 1) << 10)
#define PMD_SECT_NG (_AT(pmdval_t, 1) << 11)
@@ -53,6 +64,7 @@
#define PTE_TYPE_MASK (_AT(pteval_t, 3) << 0)
#define PTE_TYPE_FAULT (_AT(pteval_t, 0) << 0)
#define PTE_TYPE_PAGE (_AT(pteval_t, 3) << 0)
+#define PTE_TABLE_BIT (_AT(pteval_t, 1) << 1)
#define PTE_USER (_AT(pteval_t, 1) << 6) /* AP[1] */
#define PTE_RDONLY (_AT(pteval_t, 1) << 7) /* AP[2] */
#define PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */
@@ -68,9 +80,29 @@
#define PTE_ATTRINDX_MASK (_AT(pteval_t, 7) << 2)
/*
- * 40-bit physical address supported.
+ * 2nd stage PTE definitions
*/
-#define PHYS_MASK_SHIFT (40)
+#define PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[2:1] */
+#define PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */
+
+#define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */
+
+/*
+ * Memory Attribute override for Stage-2 (MemAttr[3:0])
+ */
+#define PTE_S2_MEMATTR(t) (_AT(pteval_t, (t)) << 2)
+#define PTE_S2_MEMATTR_MASK (_AT(pteval_t, 0xf) << 2)
+
+/*
+ * EL2/HYP PTE/PMD definitions
+ */
+#define PMD_HYP PMD_SECT_USER
+#define PTE_HYP PTE_USER
+
+/*
+ * Highest possible physical address supported.
+ */
+#define PHYS_MASK_SHIFT (48)
#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1)
/*
@@ -90,7 +122,7 @@
#define TCR_SHARED ((UL(3) << 12) | (UL(3) << 28))
#define TCR_TG0_64K (UL(1) << 14)
#define TCR_TG1_64K (UL(1) << 30)
-#define TCR_IPS_40BIT (UL(2) << 32)
#define TCR_ASID16 (UL(1) << 36)
+#define TCR_TBI0 (UL(1) << 37)
#endif
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e333a24..d86b4d4 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -25,15 +25,16 @@
* Software defined PTE bits definition.
*/
#define PTE_VALID (_AT(pteval_t, 1) << 0)
-#define PTE_PROT_NONE (_AT(pteval_t, 1) << 1) /* only when !PTE_VALID */
#define PTE_FILE (_AT(pteval_t, 1) << 2) /* only when !pte_present() */
#define PTE_DIRTY (_AT(pteval_t, 1) << 55)
#define PTE_SPECIAL (_AT(pteval_t, 1) << 56)
+#define PTE_WRITE (_AT(pteval_t, 1) << 57)
+#define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
/*
* VMALLOC and SPARSEMEM_VMEMMAP ranges.
*/
-#define VMALLOC_START UL(0xffffff8000000000)
+#define VMALLOC_START (UL(0xffffffffffffffff) << VA_BITS)
#define VMALLOC_END (PAGE_OFFSET - UL(0x400000000) - SZ_64K)
#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K))
@@ -51,60 +52,59 @@
#endif
#define pgd_ERROR(pgd) __pgd_error(__FILE__, __LINE__, pgd_val(pgd))
-/*
- * The pgprot_* and protection_map entries will be fixed up at runtime to
- * include the cachable and bufferable bits based on memory policy, as well as
- * any architecture dependent bits like global/ASID and SMP shared mapping
- * bits.
- */
-#define _PAGE_DEFAULT PTE_TYPE_PAGE | PTE_AF
+#ifdef CONFIG_SMP
+#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+#else
+#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF)
+#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF)
+#endif
-extern pgprot_t pgprot_default;
+#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL))
-#define __pgprot_modify(prot,mask,bits) \
- __pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+#define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
+#define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
-#define _MOD_PROT(p, b) __pgprot_modify(p, 0, b)
+#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-#define PAGE_NONE __pgprot_modify(pgprot_default, PTE_TYPE_MASK, PTE_PROT_NONE)
-#define PAGE_SHARED _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_SHARED_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_COPY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
-#define PAGE_COPY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
-#define PAGE_READONLY _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
-#define PAGE_READONLY_EXEC _MOD_PROT(pgprot_default, PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
-#define PAGE_KERNEL _MOD_PROT(pgprot_default, PTE_PXN | PTE_UXN | PTE_DIRTY)
-#define PAGE_KERNEL_EXEC _MOD_PROT(pgprot_default, PTE_UXN | PTE_DIRTY)
+#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
-#define __PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE)
-#define __PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define __PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define __PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
-#define __PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
-#define __PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_RDONLY)
-#define __PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_RDONLY)
+#define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP)
+#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
-#endif /* __ASSEMBLY__ */
+#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
+#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDWR | PTE_UXN)
-#define __P000 __PAGE_NONE
-#define __P001 __PAGE_READONLY
-#define __P010 __PAGE_COPY
-#define __P011 __PAGE_COPY
-#define __P100 __PAGE_READONLY_EXEC
-#define __P101 __PAGE_READONLY_EXEC
-#define __P110 __PAGE_COPY_EXEC
-#define __P111 __PAGE_COPY_EXEC
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
+#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define __S000 __PAGE_NONE
-#define __S001 __PAGE_READONLY
-#define __S010 __PAGE_SHARED
-#define __S011 __PAGE_SHARED
-#define __S100 __PAGE_READONLY_EXEC
-#define __S101 __PAGE_READONLY_EXEC
-#define __S110 __PAGE_SHARED_EXEC
-#define __S111 __PAGE_SHARED_EXEC
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY_EXEC
+#define __P101 PAGE_READONLY_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_EXEC
-#ifndef __ASSEMBLY__
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY_EXEC
+#define __S101 PAGE_READONLY_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
@@ -119,7 +119,7 @@
#define pte_none(pte) (!pte_val(pte))
#define pte_clear(mm,addr,ptep) set_pte(ptep, __pte(0))
#define pte_page(pte) (pfn_to_page(pte_pfn(pte)))
-#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + __pte_index(addr))
+#define pte_offset_kernel(dir,addr) (pmd_page_vaddr(*(dir)) + pte_index(addr))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
@@ -129,30 +129,77 @@
/*
* The following only work if pte_present(). Undefined behaviour otherwise.
*/
-#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte) (pte_val(pte) & PTE_AF)
-#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte) (!(pte_val(pte) & PTE_RDONLY))
+#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte) (!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE))
#define pte_exec(pte) (!(pte_val(pte) & PTE_UXN))
#define pte_valid_user(pte) \
((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
-#define PTE_BIT_FUNC(fn,op) \
-static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
+static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
+{
+ pte_val(pte) &= ~pgprot_val(prot);
+ return pte;
+}
-PTE_BIT_FUNC(wrprotect, |= PTE_RDONLY);
-PTE_BIT_FUNC(mkwrite, &= ~PTE_RDONLY);
-PTE_BIT_FUNC(mkclean, &= ~PTE_DIRTY);
-PTE_BIT_FUNC(mkdirty, |= PTE_DIRTY);
-PTE_BIT_FUNC(mkold, &= ~PTE_AF);
-PTE_BIT_FUNC(mkyoung, |= PTE_AF);
-PTE_BIT_FUNC(mkspecial, |= PTE_SPECIAL);
+static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
+{
+ pte_val(pte) |= pgprot_val(prot);
+ return pte;
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_WRITE));
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_DIRTY));
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_DIRTY));
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+ return clear_pte_bit(pte, __pgprot(PTE_AF));
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_AF));
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+ return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
+}
static inline void set_pte(pte_t *ptep, pte_t pte)
{
*ptep = pte;
+
+ /*
+ * Only if the new pte is valid and kernel, otherwise TLB maintenance
+ * or update_mmu_cache() have the necessary barriers.
+ */
+ if (pte_valid_not_user(pte)) {
+ dsb(ishst);
+ isb();
+ }
}
extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -161,10 +208,12 @@
pte_t *ptep, pte_t pte)
{
if (pte_valid_user(pte)) {
- if (pte_exec(pte))
+ if (!pte_special(pte) && pte_exec(pte))
__sync_icache_dcache(pte, addr);
- if (!pte_dirty(pte))
- pte = pte_wrprotect(pte);
+ if (pte_dirty(pte) && pte_write(pte))
+ pte_val(pte) &= ~PTE_RDONLY;
+ else
+ pte_val(pte) |= PTE_RDONLY;
}
set_pte(ptep, pte);
@@ -173,20 +222,78 @@
/*
* Huge pte definitions.
*/
-#define pte_huge(pte) ((pte_val(pte) & PTE_TYPE_MASK) == PTE_TYPE_HUGEPAGE)
-#define pte_mkhuge(pte) (__pte((pte_val(pte) & ~PTE_TYPE_MASK) | PTE_TYPE_HUGEPAGE))
+#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT))
+#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
+
+/*
+ * Hugetlb definitions.
+ */
+#define HUGE_MAX_HSTATE 2
+#define HPAGE_SHIFT PMD_SHIFT
+#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT)
+#define HPAGE_MASK (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define __HAVE_ARCH_PTE_SPECIAL
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+ return __pte(pmd_val(pmd));
+}
+
+static inline pmd_t pte_pmd(pte_t pte)
+{
+ return __pmd(pte_val(pte));
+}
+
+/*
+ * THP definitions.
+ */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
+#define pmd_trans_splitting(pmd) pte_special(pmd_pte(pmd))
+#endif
+
+#define pmd_young(pmd) pte_young(pmd_pte(pmd))
+#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd) pte_write(pmd_pte(pmd))
+
+#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
+
+#define pmd_pfn(pmd) (((pmd_val(pmd) & PMD_MASK) & PHYS_MASK) >> PAGE_SHIFT)
+#define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot)
+
+#define pmd_page(pmd) pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
+
+#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
+
+static inline int has_transparent_hugepage(void)
+{
+ return 1;
+}
+
+#define __pgprot_modify(prot,mask,bits) \
+ __pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
/*
* Mark the prot value as uncacheable and unbufferable.
*/
#define pgprot_noncached(prot) \
- __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
#define pgprot_writecombine(prot) \
- __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_GRE))
+ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
#define pgprot_dmacoherent(prot) \
- __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
+ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
#define __HAVE_PHYS_MEM_ACCESS_PROT
struct file;
extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -197,10 +304,17 @@
#define pmd_bad(pmd) (!(pmd_val(pmd) & 2))
+#define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \
+ PMD_TYPE_TABLE)
+#define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \
+ PMD_TYPE_SECT)
+
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
*pmdp = pmd;
- dsb();
+ dsb(ishst);
+ isb();
}
static inline void pmd_clear(pmd_t *pmdp)
@@ -230,7 +344,8 @@
static inline void set_pud(pud_t *pudp, pud_t pud)
{
*pudp = pud;
- dsb();
+ dsb(ishst);
+ isb();
}
static inline void pud_clear(pud_t *pudp)
@@ -263,36 +378,40 @@
#endif
/* Find an entry in the third-level page table.. */
-#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
- PTE_PROT_NONE | PTE_VALID;
+ PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
return pte;
}
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+ return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
-#define SWAPPER_DIR_SIZE (3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE (2 * PAGE_SIZE)
-
/*
* Encode and decode a swap entry:
* bits 0-1: present (must be zero)
* bit 2: PTE_FILE
* bits 3-8: swap type
- * bits 9-63: swap offset
+ * bits 9-57: swap offset
*/
#define __SWP_TYPE_SHIFT 3
#define __SWP_TYPE_BITS 6
+#define __SWP_OFFSET_BITS 49
#define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1)
#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+#define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1)
#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK)
-#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK)
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
@@ -300,7 +419,7 @@
/*
* Ensure that there are not more swap files than can be encoded in the kernel
- * the PTEs.
+ * PTEs.
*/
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
@@ -308,13 +427,13 @@
* Encode and decode a file entry:
* bits 0-1: present (must be zero)
* bit 2: PTE_FILE
- * bits 3-63: file offset / PAGE_SIZE
+ * bits 3-57: file offset / PAGE_SIZE
*/
#define pte_file(pte) (pte_val(pte) & PTE_FILE)
#define pte_to_pgoff(x) (pte_val(x) >> 3)
#define pgoff_to_pte(x) __pte(((x) << 3) | PTE_FILE)
-#define PTE_FILE_MAX_BITS 61
+#define PTE_FILE_MAX_BITS 55
extern int kern_addr_valid(unsigned long addr);
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index 7cdf466..0d3b0b1 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -26,11 +26,16 @@
#include <asm/page.h>
struct mm_struct;
+struct cpu_suspend_ctx;
extern void cpu_cache_off(void);
extern void cpu_do_idle(void);
extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
+extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
+void cpu_soft_restart(phys_addr_t cpu_reset,
+ unsigned long addr) __attribute__((noreturn));
#include <asm/memory.h>
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ab239b2..001b764 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -107,6 +107,11 @@
regs->pstate = COMPAT_PSR_MODE_USR;
if (pc & 1)
regs->pstate |= COMPAT_PSR_T_BIT;
+
+#ifdef __AARCH64EB__
+ regs->pstate |= COMPAT_PSR_E_BIT;
+#endif
+
regs->compat_sp = sp;
}
#endif
@@ -131,8 +136,8 @@
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
-#define KSTK_EIP(tsk) task_pt_regs(tsk)->pc
-#define KSTK_ESP(tsk) task_pt_regs(tsk)->sp
+#define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk))
/*
* Prefetching support
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index 0604237..e5312ea 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,25 +14,6 @@
#ifndef __ASM_PSCI_H
#define __ASM_PSCI_H
-#define PSCI_POWER_STATE_TYPE_STANDBY 0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1
-
-struct psci_power_state {
- u16 id;
- u8 type;
- u8 affinity_level;
-};
-
-struct psci_operations {
- int (*cpu_suspend)(struct psci_power_state state,
- unsigned long entry_point);
- int (*cpu_off)(struct psci_power_state state);
- int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
- int (*migrate)(unsigned long cpuid);
-};
-
-extern struct psci_operations psci_ops;
-
int psci_init(void);
#endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 41a71ee..5db016e 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -42,6 +42,7 @@
#define COMPAT_PSR_MODE_UND 0x0000001b
#define COMPAT_PSR_MODE_SYS 0x0000001f
#define COMPAT_PSR_T_BIT 0x00000020
+#define COMPAT_PSR_E_BIT 0x00000200
#define COMPAT_PSR_F_BIT 0x00000040
#define COMPAT_PSR_I_BIT 0x00000080
#define COMPAT_PSR_A_BIT 0x00000100
@@ -67,6 +68,7 @@
/* Architecturally defined mapping between AArch32 and AArch64 registers */
#define compat_usr(x) regs[(x)]
+#define compat_fp regs[11]
#define compat_sp regs[13]
#define compat_lr regs[14]
#define compat_sp_hyp regs[15]
@@ -131,7 +133,12 @@
(!((regs)->pstate & PSR_F_BIT))
#define user_stack_pointer(regs) \
- ((regs)->sp)
+ (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp)
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+ return regs->regs[0];
+}
/*
* Are the current registers suitable for user mode? (used to maintain
@@ -163,7 +170,7 @@
return 0;
}
-#define instruction_pointer(regs) (regs)->pc
+#define instruction_pointer(regs) ((unsigned long)(regs)->pc)
#ifdef CONFIG_SMP
extern unsigned long profile_pc(struct pt_regs *regs);
@@ -171,7 +178,5 @@
#define profile_pc(regs) instruction_pointer(regs)
#endif
-extern int aarch32_break_trap(struct pt_regs *regs);
-
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/sigcontext.h b/arch/arm64/include/asm/sigcontext.h
deleted file mode 100644
index dca1094..0000000
--- a/arch/arm64/include/asm/sigcontext.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_SIGCONTEXT_H
-#define __ASM_SIGCONTEXT_H
-
-#include <uapi/asm/sigcontext.h>
-
-/*
- * Auxiliary context saved in the sigcontext.__reserved array. Not exported to
- * user space as it will change with the addition of new context. User space
- * should check the magic/size information.
- */
-struct aux_context {
- struct fpsimd_context fpsimd;
- /* additional context to be added before "end" */
- struct _aarch64_ctx end;
-};
-#endif
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 4b8023c..a498f2c 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -60,21 +60,14 @@
void *stack;
};
extern struct secondary_data secondary_data;
-extern void secondary_holding_pen(void);
-extern volatile unsigned long secondary_holding_pen_release;
+extern void secondary_entry(void);
extern void arch_send_call_function_single_ipi(int cpu);
extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-struct device_node;
+extern int __cpu_disable(void);
-struct smp_enable_ops {
- const char *name;
- int (*init_cpu)(struct device_node *, int);
- int (*prepare_cpu)(int);
-};
-
-extern const struct smp_enable_ops smp_spin_table_ops;
-extern const struct smp_enable_ops smp_psci_ops;
+extern void __cpu_die(unsigned int cpu);
+extern void cpu_die(void);
#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/smp_plat.h b/arch/arm64/include/asm/smp_plat.h
index ed43a0d..59e2823 100644
--- a/arch/arm64/include/asm/smp_plat.h
+++ b/arch/arm64/include/asm/smp_plat.h
@@ -21,6 +21,19 @@
#include <asm/types.h>
+struct mpidr_hash {
+ u64 mask;
+ u32 shift_aff[4];
+ u32 bits;
+};
+
+extern struct mpidr_hash mpidr_hash;
+
+static inline u32 mpidr_hash_size(void)
+{
+ return 1 << mpidr_hash.bits;
+}
+
/*
* Logical CPU mapping.
*/
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 1be62bc..74a9d30 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -17,7 +17,7 @@
#define __ASM_SPARSEMEM_H
#ifdef CONFIG_SPARSEMEM
-#define MAX_PHYSMEM_BITS 40
+#define MAX_PHYSMEM_BITS 48
#define SECTION_SIZE_BITS 30
#endif
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 7065e92..c45b7b1 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -22,17 +22,10 @@
/*
* Spinlock implementation.
*
- * The old value is read exclusively and the new one, if unlocked, is written
- * exclusively. In case of failure, the loop is restarted.
- *
* The memory barriers are implicit with the load-acquire and store-release
* instructions.
- *
- * Unlocked value: 0
- * Locked value: 1
*/
-#define arch_spin_is_locked(x) ((x)->lock != 0)
#define arch_spin_unlock_wait(lock) \
do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
@@ -41,31 +34,51 @@
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
unsigned int tmp;
+ arch_spinlock_t lockval, newval;
asm volatile(
- " sevl\n"
- "1: wfe\n"
- "2: ldaxr %w0, %1\n"
- " cbnz %w0, 1b\n"
- " stxr %w0, %w2, %1\n"
- " cbnz %w0, 2b\n"
- : "=&r" (tmp), "+Q" (lock->lock)
- : "r" (1)
- : "cc", "memory");
+ /* Atomically increment the next ticket. */
+" prfm pstl1strm, %3\n"
+"1: ldaxr %w0, %3\n"
+" add %w1, %w0, %w5\n"
+" stxr %w2, %w1, %3\n"
+" cbnz %w2, 1b\n"
+ /* Did we get the lock? */
+" eor %w1, %w0, %w0, ror #16\n"
+" cbz %w1, 3f\n"
+ /*
+ * No: spin on the owner. Send a local event to avoid missing an
+ * unlock before the exclusive load.
+ */
+" sevl\n"
+"2: wfe\n"
+" ldaxrh %w2, %4\n"
+" eor %w1, %w2, %w0, lsr #16\n"
+" cbnz %w1, 2b\n"
+ /* We got the lock. Critical section starts here. */
+"3:"
+ : "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
+ : "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
+ : "memory");
}
static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
unsigned int tmp;
+ arch_spinlock_t lockval;
asm volatile(
- " ldaxr %w0, %1\n"
- " cbnz %w0, 1f\n"
- " stxr %w0, %w2, %1\n"
- "1:\n"
- : "=&r" (tmp), "+Q" (lock->lock)
- : "r" (1)
- : "cc", "memory");
+" prfm pstl1strm, %2\n"
+"1: ldaxr %w0, %2\n"
+" eor %w1, %w0, %w0, ror #16\n"
+" cbnz %w1, 2f\n"
+" add %w0, %w0, %3\n"
+" stxr %w1, %w0, %2\n"
+" cbnz %w1, 1b\n"
+"2:"
+ : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+ : "I" (1 << TICKET_SHIFT)
+ : "memory");
return !tmp;
}
@@ -73,10 +86,29 @@
static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
asm volatile(
- " stlr %w1, %0\n"
- : "=Q" (lock->lock) : "r" (0) : "memory");
+" stlrh %w1, %0\n"
+ : "=Q" (lock->owner)
+ : "r" (lock->owner + 1)
+ : "memory");
}
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+ return lock.owner == lock.next;
+}
+
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+ return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+ arch_spinlock_t lockval = ACCESS_ONCE(*lock);
+ return (lockval.next - lockval.owner) > 1;
+}
+#define arch_spin_is_contended arch_spin_is_contended
+
/*
* Write lock implementation.
*
@@ -100,7 +132,7 @@
" cbnz %w0, 2b\n"
: "=&r" (tmp), "+Q" (rw->lock)
: "r" (0x80000000)
- : "cc", "memory");
+ : "memory");
}
static inline int arch_write_trylock(arch_rwlock_t *rw)
@@ -114,7 +146,7 @@
"1:\n"
: "=&r" (tmp), "+Q" (rw->lock)
: "r" (0x80000000)
- : "cc", "memory");
+ : "memory");
return !tmp;
}
@@ -155,7 +187,7 @@
" cbnz %w1, 2b\n"
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
- : "cc", "memory");
+ : "memory");
}
static inline void arch_read_unlock(arch_rwlock_t *rw)
@@ -169,7 +201,7 @@
" cbnz %w1, 1b\n"
: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
:
- : "cc", "memory");
+ : "memory");
}
static inline int arch_read_trylock(arch_rwlock_t *rw)
@@ -184,7 +216,7 @@
"1:\n"
: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
:
- : "cc", "memory");
+ : "memory");
return !tmp2;
}
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 9a49434..8769275 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,14 +20,14 @@
# error "please don't include this file directly"
#endif
-/* We only require natural alignment for exclusive accesses. */
-#define __lock_aligned
+#define TICKET_SHIFT 16
typedef struct {
- volatile unsigned int lock;
-} arch_spinlock_t;
+ u16 owner;
+ u16 next;
+} __aligned(4) arch_spinlock_t;
-#define __ARCH_SPIN_LOCK_UNLOCKED { 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED { 0 , 0 }
typedef struct {
volatile unsigned int lock;
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
new file mode 100644
index 0000000..fe5e287
--- /dev/null
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function. The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on ARM. This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef __ASM_STACKPROTECTOR_H
+#define __ASM_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+ unsigned long canary;
+
+ /* Try to get a semi random initial value. */
+ get_random_bytes(&canary, sizeof(canary));
+ canary ^= LINUX_VERSION_CODE;
+
+ current->stack_canary = canary;
+ __stack_chk_guard = current->stack_canary;
+}
+
+#endif /* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 3ee8b30..64d2d48 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -22,6 +22,18 @@
#define __HAVE_ARCH_STRCHR
extern char *strchr(const char *, int c);
+#define __HAVE_ARCH_STRCMP
+extern int strcmp(const char *, const char *);
+
+#define __HAVE_ARCH_STRNCMP
+extern int strncmp(const char *, const char *, __kernel_size_t);
+
+#define __HAVE_ARCH_STRLEN
+extern __kernel_size_t strlen(const char *);
+
+#define __HAVE_ARCH_STRNLEN
+extern __kernel_size_t strnlen(const char *, __kernel_size_t);
+
#define __HAVE_ARCH_MEMCPY
extern void *memcpy(void *, const void *, __kernel_size_t);
@@ -34,4 +46,7 @@
#define __HAVE_ARCH_MEMSET
extern void *memset(void *, int, __kernel_size_t);
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, size_t);
+
#endif
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
new file mode 100644
index 0000000..e9c149c
--- /dev/null
+++ b/arch/arm64/include/asm/suspend.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_SUSPEND_H
+#define __ASM_SUSPEND_H
+
+#define NR_CTX_REGS 11
+
+/*
+ * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on
+ * the stack, which must be 16-byte aligned on v8
+ */
+struct cpu_suspend_ctx {
+ /*
+ * This struct must be kept in sync with
+ * cpu_do_{suspend/resume} in mm/proc.S
+ */
+ u64 ctx_regs[NR_CTX_REGS];
+ u64 sp;
+} __aligned(16);
+
+struct sleep_save_sp {
+ phys_addr_t *save_ptr_stash;
+ phys_addr_t save_ptr_stash_phys;
+};
+
+extern void cpu_resume(void);
+extern int cpu_suspend(unsigned long);
+
+#endif
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 89c047f..383771e 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -18,6 +18,7 @@
#include <linux/err.h>
+extern const void *sys_call_table[];
static inline int syscall_get_nr(struct task_struct *task,
struct pt_regs *regs)
@@ -59,6 +60,9 @@
unsigned int i, unsigned int n,
unsigned long *args)
{
+ if (n == 0)
+ return;
+
if (i + n > SYSCALL_MAX_ARGS) {
unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
@@ -82,6 +86,9 @@
unsigned int i, unsigned int n,
const unsigned long *args)
{
+ if (n == 0)
+ return;
+
if (i + n > SYSCALL_MAX_ARGS) {
pr_warning("%s called with max args %d, handling only %d\n",
__func__, i + n, SYSCALL_MAX_ARGS);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 0000000..5c89df0
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,60 @@
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+ ((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#ifdef __ASSEMBLY__
+
+ .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+ .equ __reg_num_x\num, \num
+ .endr
+ .equ __reg_num_xzr, 31
+
+ .macro mrs_s, rt, sreg
+ .inst 0xd5300000|(\sreg)|(__reg_num_\rt)
+ .endm
+
+ .macro msr_s, sreg, rt
+ .inst 0xd5100000|(\sreg)|(__reg_num_\rt)
+ .endm
+
+#else
+
+asm(
+" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
+" .equ __reg_num_x\\num, \\num\n"
+" .endr\n"
+" .equ __reg_num_xzr, 31\n"
+"\n"
+" .macro mrs_s, rt, sreg\n"
+" .inst 0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+" .endm\n"
+"\n"
+" .macro msr_s, sreg, rt\n"
+" .inst 0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+" .endm\n"
+);
+
+#endif
+
+#endif /* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 3659e46..70dd1ac 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -24,10 +24,10 @@
#include <linux/compiler.h>
#ifndef CONFIG_ARM64_64K_PAGES
-#define THREAD_SIZE_ORDER 1
+#define THREAD_SIZE_ORDER 2
#endif
-#define THREAD_SIZE 8192
+#define THREAD_SIZE 16384
#define THREAD_START_SP (THREAD_SIZE - 16)
#ifndef __ASSEMBLY__
@@ -69,14 +69,19 @@
#define init_stack (init_thread_union.stack)
/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+/*
* how to get the thread information struct from C
*/
static inline struct thread_info *current_thread_info(void) __attribute_const__;
static inline struct thread_info *current_thread_info(void)
{
- register unsigned long sp asm ("sp");
- return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
+ return (struct thread_info *)
+ (current_stack_pointer & ~(THREAD_SIZE - 1));
}
#define thread_saved_pc(tsk) \
@@ -97,6 +102,9 @@
/*
* thread information flags:
* TIF_SYSCALL_TRACE - syscall trace active
+ * TIF_SYSCALL_TRACEPOINT - syscall tracepoint for ftrace
+ * TIF_SYSCALL_AUDIT - syscall auditing
+ * TIF_SECOMP - syscall secure computing
* TIF_SIGPENDING - signal pending
* TIF_NEED_RESCHED - rescheduling necessary
* TIF_NOTIFY_RESUME - callback before returning to user
@@ -107,6 +115,9 @@
#define TIF_NEED_RESCHED 1
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_SYSCALL_TRACE 8
+#define TIF_SYSCALL_AUDIT 9
+#define TIF_SYSCALL_TRACEPOINT 10
+#define TIF_SECCOMP 11
#define TIF_POLLING_NRFLAG 16
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_FREEZE 19
@@ -118,10 +129,17 @@
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
+#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_32BIT (1 << TIF_32BIT)
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME)
+#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+
#endif /* __KERNEL__ */
#endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/timex.h b/arch/arm64/include/asm/timex.h
index b24a31a..81a076e 100644
--- a/arch/arm64/include/asm/timex.h
+++ b/arch/arm64/include/asm/timex.h
@@ -16,14 +16,14 @@
#ifndef __ASM_TIMEX_H
#define __ASM_TIMEX_H
+#include <asm/arch_timer.h>
+
/*
* Use the current timer as a cycle counter since this is what we use for
* the delay loop.
*/
-#define get_cycles() ({ cycles_t c; read_current_timer(&c); c; })
+#define get_cycles() arch_counter_get_cntvct()
#include <asm-generic/timex.h>
-#define ARCH_HAS_READ_CURRENT_TIMER
-
#endif
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 654f096..717031a 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@
struct mm_struct *mm;
unsigned int fullmm;
struct vm_area_struct *vma;
+ unsigned long start, end;
unsigned long range_start;
unsigned long range_end;
unsigned int nr;
@@ -97,10 +98,12 @@
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->vma = NULL;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
@@ -187,4 +190,10 @@
#define tlb_migrate_finish(mm) do { } while (0)
+static inline void
+tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+{
+ tlb_add_flush(tlb, addr);
+}
+
#endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 122d632..73f0ce5 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -72,9 +72,9 @@
*/
static inline void flush_tlb_all(void)
{
- dsb();
+ dsb(ishst);
asm("tlbi vmalle1is");
- dsb();
+ dsb(ish);
isb();
}
@@ -82,9 +82,9 @@
{
unsigned long asid = (unsigned long)ASID(mm) << 48;
- dsb();
+ dsb(ishst);
asm("tlbi aside1is, %0" : : "r" (asid));
- dsb();
+ dsb(ish);
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -93,16 +93,60 @@
unsigned long addr = uaddr >> 12 |
((unsigned long)ASID(vma->vm_mm) << 48);
- dsb();
+ dsb(ishst);
asm("tlbi vae1is, %0" : : "r" (addr));
- dsb();
+ dsb(ish);
+}
+
+static inline void __flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+ unsigned long addr;
+ start = asid | (start >> 12);
+ end = asid | (end >> 12);
+
+ dsb(ishst);
+ for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+ asm("tlbi vae1is, %0" : : "r"(addr));
+ dsb(ish);
+}
+
+static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+ unsigned long addr;
+ start >>= 12;
+ end >>= 12;
+
+ dsb(ishst);
+ for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
+ asm("tlbi vaae1is, %0" : : "r"(addr));
+ dsb(ish);
+ isb();
}
/*
- * Convert calls to our calling convention.
+ * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
+ * necessarily a performance improvement.
*/
-#define flush_tlb_range(vma,start,end) __cpu_flush_user_tlb_range(start,end,vma)
-#define flush_tlb_kernel_range(s,e) __cpu_flush_kern_tlb_range(s,e)
+#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT)
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ if ((end - start) <= MAX_TLB_RANGE)
+ __flush_tlb_range(vma, start, end);
+ else
+ flush_tlb_mm(vma->vm_mm);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+ if ((end - start) <= MAX_TLB_RANGE)
+ __flush_tlb_kernel_range(start, end);
+ else
+ flush_tlb_all();
+}
/*
* On AArch64, the cache coherency is handled via the set_pte_at() function.
@@ -111,12 +155,14 @@
unsigned long addr, pte_t *ptep)
{
/*
- * set_pte() does not have a DSB, so make sure that the page table
- * write is visible.
+ * set_pte() does not have a DSB for user mappings, so make sure that
+ * the page table write is visible.
*/
- dsb();
+ dsb(ishst);
}
+#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
+
#endif
#endif
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 0000000..e0171b3
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,70 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+ int thread_id;
+ int core_id;
+ int cluster_id;
+ cpumask_t thread_sibling;
+ cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id)
+#define topology_core_id(cpu) (cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable() (cpu_topology[0].cluster_id != -1)
+#define smt_capable() (cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#ifdef CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE
+/* Common values for CPUs */
+#ifndef SD_CPU_INIT
+#define SD_CPU_INIT (struct sched_domain) { \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = 1, \
+ .busy_idx = 2, \
+ .idle_idx = 1, \
+ .newidle_idx = 0, \
+ .wake_idx = 0, \
+ .forkexec_idx = 0, \
+ \
+ .flags = 0*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 0*SD_BALANCE_WAKE \
+ | 1*SD_WAKE_AFFINE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 0*SD_SERIALIZE \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
+}
+#endif
+#endif /* CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE */
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 008f848..3bf8f4e 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -83,7 +83,7 @@
* Returns 1 if the range is valid, 0 otherwise.
*
* This is equivalent to the following test:
- * (u65)addr + (u65)size < (u65)current->addr_limit
+ * (u65)addr + (u65)size <= current->addr_limit
*
* This needs 65-bit arithmetic.
*/
@@ -91,7 +91,7 @@
({ \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
- asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, cc" \
+ asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \
: "=&r" (flag), "=&r" (roksum) \
: "1" (addr), "Ir" (size), \
"r" (current_thread_info()->addr_limit) \
@@ -100,6 +100,7 @@
})
#define access_ok(type, addr, size) __range_ok(addr, size)
+#define user_addr_max get_fs
/*
* The "__xxx" versions of the user access functions do not verify the address
@@ -166,9 +167,10 @@
#define get_user(x, ptr) \
({ \
- might_sleep(); \
- access_ok(VERIFY_READ, (ptr), sizeof(*(ptr))) ? \
- __get_user((x), (ptr)) : \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \
+ __get_user((x), __p) : \
((x) = 0, -EFAULT); \
})
@@ -227,9 +229,10 @@
#define put_user(x, ptr) \
({ \
- might_sleep(); \
- access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ? \
- __put_user((x), (ptr)) : \
+ __typeof__(*(ptr)) __user *__p = (ptr); \
+ might_fault(); \
+ access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \
+ __put_user((x), __p) : \
-EFAULT; \
})
@@ -238,9 +241,6 @@
extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __strncpy_from_user(char *to, const char __user *from, unsigned long count);
-extern unsigned long __must_check __strnlen_user(const char __user *s, long n);
-
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
if (access_ok(VERIFY_READ, from, n))
@@ -274,24 +274,9 @@
return n;
}
-static inline long __must_check strncpy_from_user(char *dst, const char __user *src, long count)
-{
- long res = -EFAULT;
- if (access_ok(VERIFY_READ, src, 1))
- res = __strncpy_from_user(dst, src, count);
- return res;
-}
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
-#define strlen_user(s) strnlen_user(s, ~0UL >> 1)
-
-static inline long __must_check strnlen_user(const char __user *s, long n)
-{
- unsigned long res = 0;
-
- if (__addr_ok(s))
- res = __strnlen_user(s, n);
-
- return res;
-}
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217..c335479 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -28,3 +28,5 @@
#endif
#define __ARCH_WANT_SYS_CLONE
#include <uapi/asm/unistd.h>
+
+#define NR_syscalls (__NR_syscalls)
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 4398272..7a5df52 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -18,7 +18,8 @@
#ifndef __ASM__VIRT_H
#define __ASM__VIRT_H
-#define BOOT_CPU_MODE_EL2 (0x0e12b007)
+#define BOOT_CPU_MODE_EL1 (0xe11)
+#define BOOT_CPU_MODE_EL2 (0xe12)
#ifndef __ASSEMBLY__
@@ -49,6 +50,10 @@
return __boot_cpu_mode[0] != __boot_cpu_mode[1];
}
+/* The section containing the hypervisor text */
+extern char __hyp_text_start[];
+extern char __hyp_text_end[];
+
#endif /* __ASSEMBLY__ */
#endif /* ! __ASM__VIRT_H */
diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h
new file mode 100644
index 0000000..aab5bf0
--- /dev/null
+++ b/arch/arm64/include/asm/word-at-a-time.h
@@ -0,0 +1,94 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_WORD_AT_A_TIME_H
+#define __ASM_WORD_AT_A_TIME_H
+
+#ifndef __AARCH64EB__
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits,
+ const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+#define prep_zero_mask(a, bits, c) (bits)
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return fls64(mask) >> 3;
+}
+
+#define zero_bytemask(mask) (mask)
+
+#else /* __AARCH64EB__ */
+#include <asm-generic/word-at-a-time.h>
+#endif
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret, offset;
+
+ /* Load word from unaligned pointer addr */
+ asm(
+ "1: ldr %0, %3\n"
+ "2:\n"
+ " .pushsection .fixup,\"ax\"\n"
+ " .align 2\n"
+ "3: and %1, %2, #0x7\n"
+ " bic %2, %2, #0x7\n"
+ " ldr %0, [%2]\n"
+ " lsl %1, %1, #0x3\n"
+#ifndef __AARCH64EB__
+ " lsr %0, %0, %1\n"
+#else
+ " lsl %0, %0, %1\n"
+#endif
+ " b 2b\n"
+ " .popsection\n"
+ " .pushsection __ex_table,\"a\"\n"
+ " .align 3\n"
+ " .quad 1b, 3b\n"
+ " .popsection"
+ : "=&r" (ret), "=&r" (offset)
+ : "r" (addr), "Q" (*(unsigned long *)addr));
+
+ return ret;
+}
+
+#endif /* __ASM_WORD_AT_A_TIME_H */
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index e4b78bd..942376d 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -9,6 +9,7 @@
header-y += fcntl.h
header-y += hwcap.h
header-y += kvm_para.h
+header-y += perf_regs.h
header-y += param.h
header-y += ptrace.h
header-y += setup.h
diff --git a/arch/arm64/include/uapi/asm/byteorder.h b/arch/arm64/include/uapi/asm/byteorder.h
index 2b92046..dc19e95 100644
--- a/arch/arm64/include/uapi/asm/byteorder.h
+++ b/arch/arm64/include/uapi/asm/byteorder.h
@@ -16,6 +16,10 @@
#ifndef __ASM_BYTEORDER_H
#define __ASM_BYTEORDER_H
+#ifdef __AARCH64EB__
+#include <linux/byteorder/big_endian.h>
+#else
#include <linux/byteorder/little_endian.h>
+#endif
#endif /* __ASM_BYTEORDER_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index eea4975..73cf0f5 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -21,6 +21,11 @@
*/
#define HWCAP_FP (1 << 0)
#define HWCAP_ASIMD (1 << 1)
-
+#define HWCAP_EVTSTRM (1 << 2)
+#define HWCAP_AES (1 << 3)
+#define HWCAP_PMULL (1 << 4)
+#define HWCAP_SHA1 (1 << 5)
+#define HWCAP_SHA2 (1 << 6)
+#define HWCAP_CRC32 (1 << 7)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
new file mode 100644
index 0000000..8e38878
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -0,0 +1,201 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/uapi/asm/kvm.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#define KVM_SPSR_EL1 0
+#define KVM_SPSR_SVC KVM_SPSR_EL1
+#define KVM_SPSR_ABT 1
+#define KVM_SPSR_UND 2
+#define KVM_SPSR_IRQ 3
+#define KVM_SPSR_FIQ 4
+#define KVM_NR_SPSR 5
+
+#ifndef __ASSEMBLY__
+#include <linux/psci.h>
+#include <asm/types.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_REG_SIZE(id) \
+ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+struct kvm_regs {
+ struct user_pt_regs regs; /* sp = sp_el0 */
+
+ __u64 sp_el1;
+ __u64 elr_el1;
+
+ __u64 spsr[KVM_NR_SPSR];
+
+ struct user_fpsimd_state fp_regs;
+};
+
+/* Supported Processor Types */
+#define KVM_ARM_TARGET_AEM_V8 0
+#define KVM_ARM_TARGET_FOUNDATION_V8 1
+#define KVM_ARM_TARGET_CORTEX_A57 2
+#define KVM_ARM_TARGET_XGENE_POTENZA 3
+#define KVM_ARM_TARGET_CORTEX_A53 4
+
+#define KVM_ARM_NUM_TARGETS 5
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT 0
+#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT 16
+#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2 0
+
+/* Supported VGIC address types */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST 0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU 1
+
+#define KVM_VGIC_V2_DIST_SIZE 0x1000
+#define KVM_VGIC_V2_CPU_SIZE 0x2000
+
+#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2 2 /* CPU uses PSCI v0.2 */
+
+struct kvm_vcpu_init {
+ __u32 target;
+ __u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+struct kvm_guest_debug_arch {
+};
+
+struct kvm_debug_exit_arch {
+};
+
+struct kvm_sync_regs {
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT 16
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / sizeof(__u32))
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT 8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0
+
+/* AArch64 system registers */
+#define KVM_REG_ARM64_SYSREG (0x0013 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM64_SYSREG_OP0_MASK 0x000000000000c000
+#define KVM_REG_ARM64_SYSREG_OP0_SHIFT 14
+#define KVM_REG_ARM64_SYSREG_OP1_MASK 0x0000000000003800
+#define KVM_REG_ARM64_SYSREG_OP1_SHIFT 11
+#define KVM_REG_ARM64_SYSREG_CRN_MASK 0x0000000000000780
+#define KVM_REG_ARM64_SYSREG_CRN_SHIFT 7
+#define KVM_REG_ARM64_SYSREG_CRM_MASK 0x0000000000000078
+#define KVM_REG_ARM64_SYSREG_CRM_SHIFT 3
+#define KVM_REG_ARM64_SYSREG_OP2_MASK 0x0000000000000007
+#define KVM_REG_ARM64_SYSREG_OP2_SHIFT 0
+
+#define ARM64_SYS_REG_SHIFT_MASK(x,n) \
+ (((x) << KVM_REG_ARM64_SYSREG_ ## n ## _SHIFT) & \
+ KVM_REG_ARM64_SYSREG_ ## n ## _MASK)
+
+#define __ARM64_SYS_REG(op0,op1,crn,crm,op2) \
+ (KVM_REG_ARM64 | KVM_REG_ARM64_SYSREG | \
+ ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \
+ ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \
+ ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \
+ ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \
+ ARM64_SYS_REG_SHIFT_MASK(op2, OP2))
+
+#define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
+
+#define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
+#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
+#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
+#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
+#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT 24
+#define KVM_ARM_IRQ_TYPE_MASK 0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT 16
+#define KVM_ARM_IRQ_VCPU_MASK 0xff
+#define KVM_ARM_IRQ_NUM_SHIFT 0
+#define KVM_ARM_IRQ_NUM_MASK 0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU 0
+#define KVM_ARM_IRQ_TYPE_SPI 1
+#define KVM_ARM_IRQ_TYPE_PPI 2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ 0
+#define KVM_ARM_IRQ_CPU_FIQ 1
+
+/* Highest supported SPI, from VGIC_NR_IRQS */
+#define KVM_ARM_IRQ_GIC_MAX 127
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE 0x95c1ba5e
+#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
+
+#endif
+
+#endif /* __ARM_KVM_H__ */
diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 0000000..172b831
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+ PERF_REG_ARM64_X0,
+ PERF_REG_ARM64_X1,
+ PERF_REG_ARM64_X2,
+ PERF_REG_ARM64_X3,
+ PERF_REG_ARM64_X4,
+ PERF_REG_ARM64_X5,
+ PERF_REG_ARM64_X6,
+ PERF_REG_ARM64_X7,
+ PERF_REG_ARM64_X8,
+ PERF_REG_ARM64_X9,
+ PERF_REG_ARM64_X10,
+ PERF_REG_ARM64_X11,
+ PERF_REG_ARM64_X12,
+ PERF_REG_ARM64_X13,
+ PERF_REG_ARM64_X14,
+ PERF_REG_ARM64_X15,
+ PERF_REG_ARM64_X16,
+ PERF_REG_ARM64_X17,
+ PERF_REG_ARM64_X18,
+ PERF_REG_ARM64_X19,
+ PERF_REG_ARM64_X20,
+ PERF_REG_ARM64_X21,
+ PERF_REG_ARM64_X22,
+ PERF_REG_ARM64_X23,
+ PERF_REG_ARM64_X24,
+ PERF_REG_ARM64_X25,
+ PERF_REG_ARM64_X26,
+ PERF_REG_ARM64_X27,
+ PERF_REG_ARM64_X28,
+ PERF_REG_ARM64_X29,
+ PERF_REG_ARM64_LR,
+ PERF_REG_ARM64_SP,
+ PERF_REG_ARM64_PC,
+ PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 7b4b564..12618cb 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -4,20 +4,35 @@
CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
+CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) \
+ -I$(src)/../../../scripts/dtc/libfdt
+
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_insn.o = -pg
+CFLAGS_REMOVE_return_address.o = -pg
# Object file lists.
arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \
entry-fpsimd.o process.o ptrace.o setup.o signal.o \
sys.o stacktrace.o time.o traps.o io.o vdso.o \
- hyp-stub.o psci.o
+ hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o return_address.o
arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
sys_compat.o
+arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o
arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o smp_psci.o
+arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o
+arm64-obj-$(CONFIG_SMP) += topology.o
+arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
arm64-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
+arm64-obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o
+arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND) += sleep.o suspend.o
+arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o
+arm64-obj-$(CONFIG_CPU_IDLE) += cpuidle.o
+arm64-obj-$(CONFIG_KGDB) += kgdb.o
+arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o
obj-y += $(arm64-obj-y) vdso/
obj-m += $(arm64-obj-m)
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 41b4f62..a85843d 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -29,16 +29,14 @@
#include <asm/checksum.h>
- /* user mem (segment) */
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(clear_page);
+ /* user mem (segment) */
EXPORT_SYMBOL(__copy_from_user);
EXPORT_SYMBOL(__copy_to_user);
EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(__copy_in_user);
/* physical memory */
EXPORT_SYMBOL(memstart_addr);
@@ -46,10 +44,15 @@
/* string / mem functions */
EXPORT_SYMBOL(strchr);
EXPORT_SYMBOL(strrchr);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strnlen);
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(memchr);
+EXPORT_SYMBOL(memcmp);
/* atomic bitops */
EXPORT_SYMBOL(set_bit);
@@ -58,3 +61,7 @@
EXPORT_SYMBOL(test_and_clear_bit);
EXPORT_SYMBOL(change_bit);
EXPORT_SYMBOL(test_and_change_bit);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index a2a4d81..9a9fce0 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -21,9 +21,12 @@
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
+#include <linux/kvm_host.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/cputable.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
#include <asm/vdso_datapage.h>
#include <linux/kbuild.h>
@@ -104,5 +107,59 @@
BLANK();
DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
+ BLANK();
+#ifdef CONFIG_KVM_ARM_HOST
+ DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt));
+ DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs));
+ DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs));
+ DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs));
+ DEFINE(CPU_SP_EL1, offsetof(struct kvm_regs, sp_el1));
+ DEFINE(CPU_ELR_EL1, offsetof(struct kvm_regs, elr_el1));
+ DEFINE(CPU_SPSR, offsetof(struct kvm_regs, spsr));
+ DEFINE(CPU_SYSREGS, offsetof(struct kvm_cpu_context, sys_regs));
+ DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2));
+ DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2));
+ DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
+ DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags));
+ DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2));
+ DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines));
+ DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context));
+ DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
+ DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
+ DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff));
+ DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled));
+ DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
+ DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu));
+ DEFINE(VGIC_SAVE_FN, offsetof(struct vgic_sr_vectors, save_vgic));
+ DEFINE(VGIC_RESTORE_FN, offsetof(struct vgic_sr_vectors, restore_vgic));
+ DEFINE(VGIC_SR_VECTOR_SZ, sizeof(struct vgic_sr_vectors));
+ DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+ DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+ DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+ DEFINE(VGIC_V2_CPU_EISR, offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+ DEFINE(VGIC_V2_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+ DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+ DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
+ DEFINE(VGIC_V3_CPU_HCR, offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
+ DEFINE(VGIC_V3_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
+ DEFINE(VGIC_V3_CPU_MISR, offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
+ DEFINE(VGIC_V3_CPU_EISR, offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
+ DEFINE(VGIC_V3_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
+ DEFINE(VGIC_V3_CPU_AP0R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
+ DEFINE(VGIC_V3_CPU_AP1R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
+ DEFINE(VGIC_V3_CPU_LR, offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
+ DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr));
+ DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr));
+ DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base));
+#endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+ DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx));
+ DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
+ DEFINE(MPIDR_HASH_MASK, offsetof(struct mpidr_hash, mask));
+ DEFINE(MPIDR_HASH_SHIFTS, offsetof(struct mpidr_hash, shift_aff));
+ DEFINE(SLEEP_SAVE_SP_SZ, sizeof(struct sleep_save_sp));
+ DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys));
+ DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash));
+#endif
return 0;
}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
new file mode 100644
index 0000000..24fb449
--- /dev/null
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -0,0 +1,99 @@
+/*
+ * CPU kernel entry/exit control
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
+#include <linux/errno.h>
+#include <linux/of.h>
+#include <linux/string.h>
+
+extern const struct cpu_operations smp_spin_table_ops;
+extern const struct cpu_operations cpu_psci_ops;
+
+const struct cpu_operations *cpu_ops[NR_CPUS];
+
+static const struct cpu_operations *supported_cpu_ops[] __initconst = {
+#ifdef CONFIG_SMP
+ &smp_spin_table_ops,
+#endif
+ &cpu_psci_ops,
+ NULL,
+};
+
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
+{
+ const struct cpu_operations **ops = supported_cpu_ops;
+
+ while (*ops) {
+ if (!strcmp(name, (*ops)->name))
+ return *ops;
+
+ ops++;
+ }
+
+ return NULL;
+}
+
+/*
+ * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ */
+int __init cpu_read_ops(struct device_node *dn, int cpu)
+{
+ const char *enable_method = of_get_property(dn, "enable-method", NULL);
+ if (!enable_method) {
+ /*
+ * The boot CPU may not have an enable method (e.g. when
+ * spin-table is used for secondaries). Don't warn spuriously.
+ */
+ if (cpu != 0)
+ pr_err("%s: missing enable-method property\n",
+ dn->full_name);
+ return -ENOENT;
+ }
+
+ cpu_ops[cpu] = cpu_get_ops(enable_method);
+ if (!cpu_ops[cpu]) {
+ pr_warn("%s: unsupported enable-method property: %s\n",
+ dn->full_name, enable_method);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+void __init cpu_read_bootcpu_ops(void)
+{
+ struct device_node *dn = NULL;
+ u64 mpidr = cpu_logical_map(0);
+
+ while ((dn = of_find_node_by_type(dn, "cpu"))) {
+ u64 hwid;
+ const __be32 *prop;
+
+ prop = of_get_property(dn, "reg", NULL);
+ if (!prop)
+ continue;
+
+ hwid = of_read_number(prop, of_n_addr_cells(dn));
+ if (hwid == mpidr) {
+ cpu_read_ops(dn, 0);
+ of_node_put(dn);
+ return;
+ }
+ }
+}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
new file mode 100644
index 0000000..19d17f5
--- /dev/null
+++ b/arch/arm64/kernel/cpuidle.c
@@ -0,0 +1,31 @@
+/*
+ * ARM64 CPU idle arch support
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include <asm/cpuidle.h>
+#include <asm/cpu_ops.h>
+
+int cpu_init_idle(unsigned int cpu)
+{
+ int ret = -EOPNOTSUPP;
+ struct device_node *cpu_node = of_cpu_device_node_get(cpu);
+
+ if (!cpu_node)
+ return -ENODEV;
+
+ if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
+ ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+
+ of_node_put(cpu_node);
+ return ret;
+}
diff --git a/arch/arm64/kernel/cputable.c b/arch/arm64/kernel/cputable.c
index 63cfc4a..fd3993c 100644
--- a/arch/arm64/kernel/cputable.c
+++ b/arch/arm64/kernel/cputable.c
@@ -22,7 +22,7 @@
extern unsigned long __cpu_setup(void);
-struct cpu_info __initdata cpu_table[] = {
+struct cpu_info cpu_table[] = {
{
.cpu_id_val = 0x000f0000,
.cpu_id_mask = 0x000f0000,
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index f4726dc..e3b37ee 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -24,21 +24,13 @@
#include <linux/init.h>
#include <linux/ptrace.h>
#include <linux/stat.h>
+#include <linux/uaccess.h>
#include <asm/debug-monitors.h>
#include <asm/local.h>
#include <asm/cputype.h>
#include <asm/system_misc.h>
-/* Low-level stepping controls. */
-#define DBG_MDSCR_SS (1 << 0)
-#define DBG_SPSR_SS (1 << 21)
-
-/* MDSCR_EL1 enabling bits */
-#define DBG_MDSCR_KDE (1 << 13)
-#define DBG_MDSCR_MDE (1 << 15)
-#define DBG_MDSCR_MASK ~(DBG_MDSCR_KDE | DBG_MDSCR_MDE)
-
/* Determine debug architecture. */
u8 debug_monitors_arch(void)
{
@@ -137,7 +129,6 @@
static void clear_os_lock(void *unused)
{
asm volatile("msr oslar_el1, %0" : : "r" (0));
- isb();
}
static int __cpuinit os_lock_notify(struct notifier_block *self,
@@ -156,8 +147,9 @@
static int __cpuinit debug_monitors_init(void)
{
/* Clear the OS lock. */
- smp_call_function(clear_os_lock, NULL, 1);
- clear_os_lock(NULL);
+ on_each_cpu(clear_os_lock, NULL, 1);
+ isb();
+ local_dbg_enable();
/* Register hotplug handler. */
register_cpu_notifier(&os_lock_nb);
@@ -187,6 +179,48 @@
regs->pstate = spsr;
}
+/* EL1 Single Step Handler hooks */
+static LIST_HEAD(step_hook);
+static DEFINE_RWLOCK(step_hook_lock);
+
+void register_step_hook(struct step_hook *hook)
+{
+ write_lock(&step_hook_lock);
+ list_add(&hook->node, &step_hook);
+ write_unlock(&step_hook_lock);
+}
+
+void unregister_step_hook(struct step_hook *hook)
+{
+ write_lock(&step_hook_lock);
+ list_del(&hook->node);
+ write_unlock(&step_hook_lock);
+}
+
+/*
+ * Call registered single step handers
+ * There is no Syndrome info to check for determining the handler.
+ * So we call all the registered handlers, until the right handler is
+ * found which returns zero.
+ */
+static int call_step_hook(struct pt_regs *regs, unsigned int esr)
+{
+ struct step_hook *hook;
+ int retval = DBG_HOOK_ERROR;
+
+ read_lock(&step_hook_lock);
+
+ list_for_each_entry(hook, &step_hook, node) {
+ retval = hook->fn(regs, esr);
+ if (retval == DBG_HOOK_HANDLED)
+ break;
+ }
+
+ read_unlock(&step_hook_lock);
+
+ return retval;
+}
+
static int single_step_handler(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
@@ -214,7 +248,9 @@
*/
user_rewind_single_step(current);
} else {
- /* TODO: route to KGDB */
+ if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
+ return 0;
+
pr_warning("Unexpected kernel single-step exception at EL1\n");
/*
* Re-enable stepping since we know that we will be
@@ -226,13 +262,113 @@
return 0;
}
-static int __init single_step_init(void)
+/*
+ * Breakpoint handler is re-entrant as another breakpoint can
+ * hit within breakpoint handler, especically in kprobes.
+ * Use reader/writer locks instead of plain spinlock.
+ */
+static LIST_HEAD(break_hook);
+static DEFINE_RWLOCK(break_hook_lock);
+
+void register_break_hook(struct break_hook *hook)
+{
+ write_lock(&break_hook_lock);
+ list_add(&hook->node, &break_hook);
+ write_unlock(&break_hook_lock);
+}
+
+void unregister_break_hook(struct break_hook *hook)
+{
+ write_lock(&break_hook_lock);
+ list_del(&hook->node);
+ write_unlock(&break_hook_lock);
+}
+
+static int call_break_hook(struct pt_regs *regs, unsigned int esr)
+{
+ struct break_hook *hook;
+ int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
+
+ read_lock(&break_hook_lock);
+ list_for_each_entry(hook, &break_hook, node)
+ if ((esr & hook->esr_mask) == hook->esr_val)
+ fn = hook->fn;
+ read_unlock(&break_hook_lock);
+
+ return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
+}
+
+static int brk_handler(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
+{
+ siginfo_t info;
+
+ if (user_mode(regs)) {
+ info = (siginfo_t) {
+ .si_signo = SIGTRAP,
+ .si_errno = 0,
+ .si_code = TRAP_BRKPT,
+ .si_addr = (void __user *)instruction_pointer(regs),
+ };
+
+ force_sig_info(SIGTRAP, &info, current);
+ } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+ pr_warning("Unexpected kernel BRK exception at EL1\n");
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+int aarch32_break_handler(struct pt_regs *regs)
+{
+ siginfo_t info;
+ unsigned int instr;
+ bool bp = false;
+ void __user *pc = (void __user *)instruction_pointer(regs);
+
+ if (!compat_user_mode(regs))
+ return -EFAULT;
+
+ if (compat_thumb_mode(regs)) {
+ /* get 16-bit Thumb instruction */
+ get_user(instr, (u16 __user *)pc);
+ if (instr == AARCH32_BREAK_THUMB2_LO) {
+ /* get second half of 32-bit Thumb-2 instruction */
+ get_user(instr, (u16 __user *)(pc + 2));
+ bp = instr == AARCH32_BREAK_THUMB2_HI;
+ } else {
+ bp = instr == AARCH32_BREAK_THUMB;
+ }
+ } else {
+ /* 32-bit ARM instruction */
+ get_user(instr, (u32 __user *)pc);
+ bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
+ }
+
+ if (!bp)
+ return -EFAULT;
+
+ info = (siginfo_t) {
+ .si_signo = SIGTRAP,
+ .si_errno = 0,
+ .si_code = TRAP_BRKPT,
+ .si_addr = pc,
+ };
+
+ force_sig_info(SIGTRAP, &info, current);
+ return 0;
+}
+
+static int __init debug_traps_init(void)
{
hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
TRAP_HWBKPT, "single-step handler");
+ hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
+ TRAP_BRKPT, "ptrace BRK handler");
return 0;
}
-arch_initcall(single_step_init);
+arch_initcall(debug_traps_init);
/* Re-enable single step for syscall restarting. */
void user_rewind_single_step(struct task_struct *task)
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
index fbb6e18..ffbbdde 100644
--- a/arch/arm64/kernel/early_printk.c
+++ b/arch/arm64/kernel/early_printk.c
@@ -26,6 +26,8 @@
#include <linux/amba/serial.h>
#include <linux/serial_reg.h>
+#include <asm/fixmap.h>
+
static void __iomem *early_base;
static void (*printch)(char ch);
@@ -141,8 +143,10 @@
}
/* no options parsing yet */
- if (paddr)
- early_base = early_io_map(paddr, EARLYCON_IOBASE);
+ if (paddr) {
+ set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr);
+ early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE);
+ }
printch = match->printch;
early_console = &early_console_dev;
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
new file mode 100644
index 0000000..66716c9
--- /dev/null
+++ b/arch/arm64/kernel/efi-entry.S
@@ -0,0 +1,109 @@
+/*
+ * EFI entry point.
+ *
+ * Copyright (C) 2013, 2014 Red Hat, Inc.
+ * Author: Mark Salter <msalter@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+#include <asm/assembler.h>
+
+#define EFI_LOAD_ERROR 0x8000000000000001
+
+ __INIT
+
+ /*
+ * We arrive here from the EFI boot manager with:
+ *
+ * * CPU in little-endian mode
+ * * MMU on with identity-mapped RAM
+ * * Icache and Dcache on
+ *
+ * We will most likely be running from some place other than where
+ * we want to be. The kernel image wants to be placed at TEXT_OFFSET
+ * from start of RAM.
+ */
+ENTRY(efi_stub_entry)
+ /*
+ * Create a stack frame to save FP/LR with extra space
+ * for image_addr variable passed to efi_entry().
+ */
+ stp x29, x30, [sp, #-32]!
+
+ /*
+ * Call efi_entry to do the real work.
+ * x0 and x1 are already set up by firmware. Current runtime
+ * address of image is calculated and passed via *image_addr.
+ *
+ * unsigned long efi_entry(void *handle,
+ * efi_system_table_t *sys_table,
+ * unsigned long *image_addr) ;
+ */
+ adrp x8, _text
+ add x8, x8, #:lo12:_text
+ add x2, sp, 16
+ str x8, [x2]
+ bl efi_entry
+ cmn x0, #1
+ b.eq efi_load_fail
+
+ /*
+ * efi_entry() will have relocated the kernel image if necessary
+ * and we return here with device tree address in x0 and the kernel
+ * entry point stored at *image_addr. Save those values in registers
+ * which are callee preserved.
+ */
+ mov x20, x0 // DTB address
+ ldr x0, [sp, #16] // relocated _text address
+ mov x21, x0
+
+ /*
+ * Flush dcache covering current runtime addresses
+ * of kernel text/data. Then flush all of icache.
+ */
+ adrp x1, _text
+ add x1, x1, #:lo12:_text
+ adrp x2, _edata
+ add x2, x2, #:lo12:_edata
+ sub x1, x2, x1
+
+ bl __flush_dcache_area
+ ic ialluis
+
+ /* Turn off Dcache and MMU */
+ mrs x0, CurrentEL
+ cmp x0, #PSR_MODE_EL2t
+ ccmp x0, #PSR_MODE_EL2h, #0x4, ne
+ b.ne 1f
+ mrs x0, sctlr_el2
+ bic x0, x0, #1 << 0 // clear SCTLR.M
+ bic x0, x0, #1 << 2 // clear SCTLR.C
+ msr sctlr_el2, x0
+ isb
+ b 2f
+1:
+ mrs x0, sctlr_el1
+ bic x0, x0, #1 << 0 // clear SCTLR.M
+ bic x0, x0, #1 << 2 // clear SCTLR.C
+ msr sctlr_el1, x0
+ isb
+2:
+ /* Jump to kernel entry point */
+ mov x0, x20
+ mov x1, xzr
+ mov x2, xzr
+ mov x3, xzr
+ br x21
+
+efi_load_fail:
+ mov x0, #EFI_LOAD_ERROR
+ ldp x29, x30, [sp], #32
+ ret
+
+ENDPROC(efi_stub_entry)
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
new file mode 100644
index 0000000..e786e6c
--- /dev/null
+++ b/arch/arm64/kernel/efi-stub.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright (C) 2013, 2014 Linaro Ltd; <roy.franz@linaro.org>
+ *
+ * This file implements the EFI boot stub for the arm64 kernel.
+ * Adapted from ARM version by Mark Salter <msalter@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/efi.h>
+#include <linux/libfdt.h>
+#include <asm/sections.h>
+
+/*
+ * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
+ * start of kernel and may not cross a 2MiB boundary. We set alignment to
+ * 2MiB so we know it won't cross a 2MiB boundary.
+ */
+#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */
+#define MAX_FDT_OFFSET SZ_512M
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
+static void efi_char16_printk(efi_system_table_t *sys_table_arg,
+ efi_char16_t *str);
+
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table,
+ void *__image, void **__fh);
+static efi_status_t efi_file_close(void *handle);
+
+static efi_status_t
+efi_file_read(void *handle, unsigned long *size, void *addr);
+
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table, void *__fh,
+ efi_char16_t *filename_16, void **handle, u64 *file_sz);
+
+/* Include shared EFI stub code */
+#include "../../../drivers/firmware/efi/efi-stub-helper.c"
+#include "../../../drivers/firmware/efi/fdt.c"
+#include "../../../drivers/firmware/efi/arm-stub.c"
+
+
+static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+ unsigned long *image_addr,
+ unsigned long *image_size,
+ unsigned long *reserve_addr,
+ unsigned long *reserve_size,
+ unsigned long dram_base,
+ efi_loaded_image_t *image)
+{
+ efi_status_t status;
+ unsigned long kernel_size, kernel_memsize = 0;
+
+ /* Relocate the image, if required. */
+ kernel_size = _edata - _text;
+ if (*image_addr != (dram_base + TEXT_OFFSET)) {
+ kernel_memsize = kernel_size + (_end - _edata);
+ status = efi_relocate_kernel(sys_table, image_addr,
+ kernel_size, kernel_memsize,
+ dram_base + TEXT_OFFSET,
+ PAGE_SIZE);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Failed to relocate kernel\n");
+ return status;
+ }
+ if (*image_addr != (dram_base + TEXT_OFFSET)) {
+ pr_efi_err(sys_table, "Failed to alloc kernel memory\n");
+ efi_free(sys_table, kernel_memsize, *image_addr);
+ return EFI_ERROR;
+ }
+ *image_size = kernel_memsize;
+ }
+
+
+ return EFI_SUCCESS;
+}
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
new file mode 100644
index 0000000..14db1f6
--- /dev/null
+++ b/arch/arm64/kernel/efi.c
@@ -0,0 +1,469 @@
+/*
+ * Extensible Firmware Interface
+ *
+ * Based on Extensible Firmware Interface Specification version 2.4
+ *
+ * Copyright (C) 2013, 2014 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/efi.h>
+#include <linux/export.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cacheflush.h>
+#include <asm/efi.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+
+struct efi_memory_map memmap;
+
+static efi_runtime_services_t *runtime;
+
+static u64 efi_system_table;
+
+static int uefi_debug __initdata;
+static int __init uefi_debug_setup(char *str)
+{
+ uefi_debug = 1;
+
+ return 0;
+}
+early_param("uefi_debug", uefi_debug_setup);
+
+static int __init is_normal_ram(efi_memory_desc_t *md)
+{
+ if (md->attribute & EFI_MEMORY_WB)
+ return 1;
+ return 0;
+}
+
+static void __init efi_setup_idmap(void)
+{
+ struct memblock_region *r;
+ efi_memory_desc_t *md;
+ u64 paddr, npages, size;
+
+ for_each_memblock(memory, r)
+ create_id_mapping(r->base, r->size, 0);
+
+ /* map runtime io spaces */
+ for_each_efi_memory_desc(&memmap, md) {
+ if (!(md->attribute & EFI_MEMORY_RUNTIME) || is_normal_ram(md))
+ continue;
+ paddr = md->phys_addr;
+ npages = md->num_pages;
+ memrange_efi_to_native(&paddr, &npages);
+ size = npages << PAGE_SHIFT;
+ create_id_mapping(paddr, size, 1);
+ }
+}
+
+static int __init uefi_init(void)
+{
+ efi_char16_t *c16;
+ char vendor[100] = "unknown";
+ int i, retval;
+
+ efi.systab = early_memremap(efi_system_table,
+ sizeof(efi_system_table_t));
+ if (efi.systab == NULL) {
+ pr_warn("Unable to map EFI system table.\n");
+ return -ENOMEM;
+ }
+
+ set_bit(EFI_BOOT, &efi.flags);
+ set_bit(EFI_64BIT, &efi.flags);
+
+ /*
+ * Verify the EFI Table
+ */
+ if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
+ pr_err("System table signature incorrect\n");
+ return -EINVAL;
+ }
+ if ((efi.systab->hdr.revision >> 16) < 2)
+ pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n",
+ efi.systab->hdr.revision >> 16,
+ efi.systab->hdr.revision & 0xffff);
+
+ /* Show what we know for posterity */
+ c16 = early_memremap(efi.systab->fw_vendor,
+ sizeof(vendor));
+ if (c16) {
+ for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
+ vendor[i] = c16[i];
+ vendor[i] = '\0';
+ }
+
+ pr_info("EFI v%u.%.02u by %s\n",
+ efi.systab->hdr.revision >> 16,
+ efi.systab->hdr.revision & 0xffff, vendor);
+
+ retval = efi_config_init(NULL);
+ if (retval == 0)
+ set_bit(EFI_CONFIG_TABLES, &efi.flags);
+
+ early_memunmap(c16, sizeof(vendor));
+ early_memunmap(efi.systab, sizeof(efi_system_table_t));
+
+ return retval;
+}
+
+static __initdata char memory_type_name[][32] = {
+ {"Reserved"},
+ {"Loader Code"},
+ {"Loader Data"},
+ {"Boot Code"},
+ {"Boot Data"},
+ {"Runtime Code"},
+ {"Runtime Data"},
+ {"Conventional Memory"},
+ {"Unusable Memory"},
+ {"ACPI Reclaim Memory"},
+ {"ACPI Memory NVS"},
+ {"Memory Mapped I/O"},
+ {"MMIO Port Space"},
+ {"PAL Code"},
+};
+
+/*
+ * Return true for RAM regions we want to permanently reserve.
+ */
+static __init int is_reserve_region(efi_memory_desc_t *md)
+{
+ if (!is_normal_ram(md))
+ return 0;
+
+ if (md->attribute & EFI_MEMORY_RUNTIME)
+ return 1;
+
+ if (md->type == EFI_ACPI_RECLAIM_MEMORY ||
+ md->type == EFI_RESERVED_TYPE)
+ return 1;
+
+ return 0;
+}
+
+static __init void reserve_regions(void)
+{
+ efi_memory_desc_t *md;
+ u64 paddr, npages, size;
+
+ if (uefi_debug)
+ pr_info("Processing EFI memory map:\n");
+
+ for_each_efi_memory_desc(&memmap, md) {
+ paddr = md->phys_addr;
+ npages = md->num_pages;
+
+ if (uefi_debug)
+ pr_info(" 0x%012llx-0x%012llx [%s]",
+ paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
+ memory_type_name[md->type]);
+
+ memrange_efi_to_native(&paddr, &npages);
+ size = npages << PAGE_SHIFT;
+
+ if (is_normal_ram(md))
+ early_init_dt_add_memory_arch(paddr, size);
+
+ if (is_reserve_region(md) ||
+ md->type == EFI_BOOT_SERVICES_CODE ||
+ md->type == EFI_BOOT_SERVICES_DATA) {
+ memblock_reserve(paddr, size);
+ if (uefi_debug)
+ pr_cont("*");
+ }
+
+ if (uefi_debug)
+ pr_cont("\n");
+ }
+}
+
+
+static u64 __init free_one_region(u64 start, u64 end)
+{
+ u64 size = end - start;
+
+ if (uefi_debug)
+ pr_info(" EFI freeing: 0x%012llx-0x%012llx\n", start, end - 1);
+
+ free_bootmem_late(start, size);
+ return size;
+}
+
+static u64 __init free_region(u64 start, u64 end)
+{
+ u64 map_start, map_end, total = 0;
+
+ if (end <= start)
+ return total;
+
+ map_start = (u64)memmap.phys_map;
+ map_end = PAGE_ALIGN(map_start + (memmap.map_end - memmap.map));
+ map_start &= PAGE_MASK;
+
+ if (start < map_end && end > map_start) {
+ /* region overlaps UEFI memmap */
+ if (start < map_start)
+ total += free_one_region(start, map_start);
+
+ if (map_end < end)
+ total += free_one_region(map_end, end);
+ } else
+ total += free_one_region(start, end);
+
+ return total;
+}
+
+static void __init free_boot_services(void)
+{
+ u64 total_freed = 0;
+ u64 keep_end, free_start, free_end;
+ efi_memory_desc_t *md;
+
+ /*
+ * If kernel uses larger pages than UEFI, we have to be careful
+ * not to inadvertantly free memory we want to keep if there is
+ * overlap at the kernel page size alignment. We do not want to
+ * free is_reserve_region() memory nor the UEFI memmap itself.
+ *
+ * The memory map is sorted, so we keep track of the end of
+ * any previous region we want to keep, remember any region
+ * we want to free and defer freeing it until we encounter
+ * the next region we want to keep. This way, before freeing
+ * it, we can clip it as needed to avoid freeing memory we
+ * want to keep for UEFI.
+ */
+
+ keep_end = 0;
+ free_start = 0;
+
+ for_each_efi_memory_desc(&memmap, md) {
+ u64 paddr, npages, size;
+
+ if (is_reserve_region(md)) {
+ /*
+ * We don't want to free any memory from this region.
+ */
+ if (free_start) {
+ /* adjust free_end then free region */
+ if (free_end > md->phys_addr)
+ free_end -= PAGE_SIZE;
+ total_freed += free_region(free_start, free_end);
+ free_start = 0;
+ }
+ keep_end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+ continue;
+ }
+
+ if (md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA) {
+ /* no need to free this region */
+ continue;
+ }
+
+ /*
+ * We want to free memory from this region.
+ */
+ paddr = md->phys_addr;
+ npages = md->num_pages;
+ memrange_efi_to_native(&paddr, &npages);
+ size = npages << PAGE_SHIFT;
+
+ if (free_start) {
+ if (paddr <= free_end)
+ free_end = paddr + size;
+ else {
+ total_freed += free_region(free_start, free_end);
+ free_start = paddr;
+ free_end = paddr + size;
+ }
+ } else {
+ free_start = paddr;
+ free_end = paddr + size;
+ }
+ if (free_start < keep_end) {
+ free_start += PAGE_SIZE;
+ if (free_start >= free_end)
+ free_start = 0;
+ }
+ }
+ if (free_start)
+ total_freed += free_region(free_start, free_end);
+
+ if (total_freed)
+ pr_info("Freed 0x%llx bytes of EFI boot services memory",
+ total_freed);
+}
+
+void __init efi_init(void)
+{
+ struct efi_fdt_params params;
+
+ /* Grab UEFI information placed in FDT by stub */
+ if (!efi_get_fdt_params(¶ms, uefi_debug))
+ return;
+
+ efi_system_table = params.system_table;
+
+ memblock_reserve(params.mmap & PAGE_MASK,
+ PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
+ memmap.phys_map = (void *)params.mmap;
+ memmap.map = early_memremap(params.mmap, params.mmap_size);
+ memmap.map_end = memmap.map + params.mmap_size;
+ memmap.desc_size = params.desc_size;
+ memmap.desc_version = params.desc_ver;
+
+ if (uefi_init() < 0)
+ return;
+
+ reserve_regions();
+}
+
+void __init efi_idmap_init(void)
+{
+ if (!efi_enabled(EFI_BOOT))
+ return;
+
+ /* boot time idmap_pg_dir is incomplete, so fill in missing parts */
+ efi_setup_idmap();
+}
+
+static int __init remap_region(efi_memory_desc_t *md, void **new)
+{
+ u64 paddr, vaddr, npages, size;
+
+ paddr = md->phys_addr;
+ npages = md->num_pages;
+ memrange_efi_to_native(&paddr, &npages);
+ size = npages << PAGE_SHIFT;
+
+ if (is_normal_ram(md))
+ vaddr = (__force u64)ioremap_cache(paddr, size);
+ else
+ vaddr = (__force u64)ioremap(paddr, size);
+
+ if (!vaddr) {
+ pr_err("Unable to remap 0x%llx pages @ %p\n",
+ npages, (void *)paddr);
+ return 0;
+ }
+
+ /* adjust for any rounding when EFI and system pagesize differs */
+ md->virt_addr = vaddr + (md->phys_addr - paddr);
+
+ if (uefi_debug)
+ pr_info(" EFI remap 0x%012llx => %p\n",
+ md->phys_addr, (void *)md->virt_addr);
+
+ memcpy(*new, md, memmap.desc_size);
+ *new += memmap.desc_size;
+
+ return 1;
+}
+
+/*
+ * Switch UEFI from an identity map to a kernel virtual map
+ */
+static int __init arm64_enter_virtual_mode(void)
+{
+ efi_memory_desc_t *md;
+ phys_addr_t virtmap_phys;
+ void *virtmap, *virt_md;
+ efi_status_t status;
+ u64 mapsize;
+ int count = 0;
+ unsigned long flags;
+
+ if (!efi_enabled(EFI_BOOT)) {
+ pr_info("EFI services will not be available.\n");
+ return -1;
+ }
+
+ pr_info("Remapping and enabling EFI services.\n");
+
+ /* replace early memmap mapping with permanent mapping */
+ mapsize = memmap.map_end - memmap.map;
+ early_memunmap(memmap.map, mapsize);
+ memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map,
+ mapsize);
+ memmap.map_end = memmap.map + mapsize;
+
+ efi.memmap = &memmap;
+
+ /* Map the runtime regions */
+ virtmap = kmalloc(mapsize, GFP_KERNEL);
+ if (!virtmap) {
+ pr_err("Failed to allocate EFI virtual memmap\n");
+ return -1;
+ }
+ virtmap_phys = virt_to_phys(virtmap);
+ virt_md = virtmap;
+
+ for_each_efi_memory_desc(&memmap, md) {
+ if (!(md->attribute & EFI_MEMORY_RUNTIME))
+ continue;
+ if (remap_region(md, &virt_md))
+ ++count;
+ }
+
+ efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table);
+ if (efi.systab)
+ set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+ local_irq_save(flags);
+ cpu_switch_mm(idmap_pg_dir, &init_mm);
+
+ /* Call SetVirtualAddressMap with the physical address of the map */
+ runtime = efi.systab->runtime;
+ efi.set_virtual_address_map = runtime->set_virtual_address_map;
+
+ status = efi.set_virtual_address_map(count * memmap.desc_size,
+ memmap.desc_size,
+ memmap.desc_version,
+ (efi_memory_desc_t *)virtmap_phys);
+ cpu_set_reserved_ttbr0();
+ flush_tlb_all();
+ local_irq_restore(flags);
+
+ kfree(virtmap);
+
+ free_boot_services();
+
+ if (status != EFI_SUCCESS) {
+ pr_err("Failed to set EFI virtual address map! [%lx]\n",
+ status);
+ return -1;
+ }
+
+ /* Set up runtime services function pointers */
+ runtime = efi.systab->runtime;
+ efi.get_time = runtime->get_time;
+ efi.set_time = runtime->set_time;
+ efi.get_wakeup_time = runtime->get_wakeup_time;
+ efi.set_wakeup_time = runtime->set_wakeup_time;
+ efi.get_variable = runtime->get_variable;
+ efi.get_next_variable = runtime->get_next_variable;
+ efi.set_variable = runtime->set_variable;
+ efi.query_variable_info = runtime->query_variable_info;
+ efi.update_capsule = runtime->update_capsule;
+ efi.query_capsule_caps = runtime->query_capsule_caps;
+ efi.get_next_high_mono_count = runtime->get_next_high_mono_count;
+ efi.reset_system = runtime->reset_system;
+
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
+ return 0;
+}
+early_initcall(arm64_enter_virtual_mode);
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
new file mode 100644
index 0000000..b051871
--- /dev/null
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -0,0 +1,218 @@
+/*
+ * arch/arm64/kernel/entry-ftrace.S
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+/*
+ * Gcc with -pg will put the following code in the beginning of each function:
+ * mov x0, x30
+ * bl _mcount
+ * [function's body ...]
+ * "bl _mcount" may be replaced to "bl ftrace_caller" or NOP if dynamic
+ * ftrace is enabled.
+ *
+ * Please note that x0 as an argument will not be used here because we can
+ * get lr(x30) of instrumented function at any time by winding up call stack
+ * as long as the kernel is compiled without -fomit-frame-pointer.
+ * (or CONFIG_FRAME_POINTER, this is forced on arm64)
+ *
+ * stack layout after mcount_enter in _mcount():
+ *
+ * current sp/fp => 0:+-----+
+ * in _mcount() | x29 | -> instrumented function's fp
+ * +-----+
+ * | x30 | -> _mcount()'s lr (= instrumented function's pc)
+ * old sp => +16:+-----+
+ * when instrumented | |
+ * function calls | ... |
+ * _mcount() | |
+ * | |
+ * instrumented => +xx:+-----+
+ * function's fp | x29 | -> parent's fp
+ * +-----+
+ * | x30 | -> instrumented function's lr (= parent's pc)
+ * +-----+
+ * | ... |
+ */
+
+ .macro mcount_enter
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
+ .endm
+
+ .macro mcount_exit
+ ldp x29, x30, [sp], #16
+ ret
+ .endm
+
+ .macro mcount_adjust_addr rd, rn
+ sub \rd, \rn, #AARCH64_INSN_SIZE
+ .endm
+
+ /* for instrumented function's parent */
+ .macro mcount_get_parent_fp reg
+ ldr \reg, [x29]
+ ldr \reg, [\reg]
+ .endm
+
+ /* for instrumented function */
+ .macro mcount_get_pc0 reg
+ mcount_adjust_addr \reg, x30
+ .endm
+
+ .macro mcount_get_pc reg
+ ldr \reg, [x29, #8]
+ mcount_adjust_addr \reg, \reg
+ .endm
+
+ .macro mcount_get_lr reg
+ ldr \reg, [x29]
+ ldr \reg, [\reg, #8]
+ mcount_adjust_addr \reg, \reg
+ .endm
+
+ .macro mcount_get_lr_addr reg
+ ldr \reg, [x29]
+ add \reg, \reg, #8
+ .endm
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+/*
+ * void _mcount(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function makes calls, if enabled, to:
+ * - tracer function to probe instrumented function's entry,
+ * - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(_mcount)
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ ldr x0, =ftrace_trace_stop
+ ldr x0, [x0] // if ftrace_trace_stop
+ ret // return;
+#endif
+ mcount_enter
+
+ ldr x0, =ftrace_trace_function
+ ldr x2, [x0]
+ adr x0, ftrace_stub
+ cmp x0, x2 // if (ftrace_trace_function
+ b.eq skip_ftrace_call // != ftrace_stub) {
+
+ mcount_get_pc x0 // function's pc
+ mcount_get_lr x1 // function's lr (= parent's pc)
+ blr x2 // (*ftrace_trace_function)(pc, lr);
+
+#ifndef CONFIG_FUNCTION_GRAPH_TRACER
+skip_ftrace_call: // return;
+ mcount_exit // }
+#else
+ mcount_exit // return;
+ // }
+skip_ftrace_call:
+ ldr x1, =ftrace_graph_return
+ ldr x2, [x1] // if ((ftrace_graph_return
+ cmp x0, x2 // != ftrace_stub)
+ b.ne ftrace_graph_caller
+
+ ldr x1, =ftrace_graph_entry // || (ftrace_graph_entry
+ ldr x2, [x1] // != ftrace_graph_entry_stub))
+ ldr x0, =ftrace_graph_entry_stub
+ cmp x0, x2
+ b.ne ftrace_graph_caller // ftrace_graph_caller();
+
+ mcount_exit
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ENDPROC(_mcount)
+
+#else /* CONFIG_DYNAMIC_FTRACE */
+/*
+ * _mcount() is used to build the kernel with -pg option, but all the branch
+ * instructions to _mcount() are replaced to NOP initially at kernel start up,
+ * and later on, NOP to branch to ftrace_caller() when enabled or branch to
+ * NOP when disabled per-function base.
+ */
+ENTRY(_mcount)
+ ret
+ENDPROC(_mcount)
+
+/*
+ * void ftrace_caller(unsigned long return_address)
+ * @return_address: return address to instrumented function
+ *
+ * This function is a counterpart of _mcount() in 'static' ftrace, and
+ * makes calls to:
+ * - tracer function to probe instrumented function's entry,
+ * - ftrace_graph_caller to set up an exit hook
+ */
+ENTRY(ftrace_caller)
+ mcount_enter
+
+ mcount_get_pc0 x0 // function's pc
+ mcount_get_lr x1 // function's lr
+
+ .global ftrace_call
+ftrace_call: // tracer(pc, lr);
+ nop // This will be replaced with "bl xxx"
+ // where xxx can be any kind of tracer.
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ .global ftrace_graph_call
+ftrace_graph_call: // ftrace_graph_caller();
+ nop // If enabled, this will be replaced
+ // "b ftrace_graph_caller"
+#endif
+
+ mcount_exit
+ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(ftrace_stub)
+ ret
+ENDPROC(ftrace_stub)
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * void ftrace_graph_caller(void)
+ *
+ * Called from _mcount() or ftrace_caller() when function_graph tracer is
+ * selected.
+ * This function w/ prepare_ftrace_return() fakes link register's value on
+ * the call stack in order to intercept instrumented function's return path
+ * and run return_to_handler() later on its exit.
+ */
+ENTRY(ftrace_graph_caller)
+ mcount_get_lr_addr x0 // pointer to function's saved lr
+ mcount_get_pc x1 // function's pc
+ mcount_get_parent_fp x2 // parent's fp
+ bl prepare_ftrace_return // prepare_ftrace_return(&lr, pc, fp)
+
+ mcount_exit
+ENDPROC(ftrace_graph_caller)
+
+/*
+ * void return_to_handler(void)
+ *
+ * Run ftrace_return_to_handler() before going back to parent.
+ * @fp is checked against the value passed by ftrace_graph_caller()
+ * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ */
+ENTRY(return_to_handler)
+ str x0, [sp, #-16]!
+ mov x0, x29 // parent's fp
+ bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
+ mov x30, x0 // restore the original return address
+ ldr x0, [sp], #16
+ ret
+END(return_to_handler)
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index bb64eed..1ee38bd 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -132,7 +132,7 @@
.macro get_thread_info, rd
mov \rd, sp
- and \rd, \rd, #~((1 << 13) - 1) // top of 8K stack
+ and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack
.endm
/*
@@ -286,7 +286,6 @@
* Stack or PC alignment exception handling
*/
mrs x0, far_el1
- mov x1, x25
mov x2, sp
b do_sp_pc_abort
el1_undef:
@@ -299,6 +298,8 @@
/*
* Debug exception handling
*/
+ cmp x24, #ESR_EL1_EC_BRK64 // if BRK64
+ cinc x24, x24, eq // set bit '0'
tbz x24, #0, el1_inv // EL1 only
mrs x0, far_el1
mov x2, sp // struct pt_regs
@@ -322,14 +323,14 @@
#endif
#ifdef CONFIG_PREEMPT
get_thread_info tsk
- ldr x24, [tsk, #TI_PREEMPT] // get preempt count
- add x0, x24, #1 // increment it
- str x0, [tsk, #TI_PREEMPT]
+ ldr w24, [tsk, #TI_PREEMPT] // get preempt count
+ add w0, w24, #1 // increment it
+ str w0, [tsk, #TI_PREEMPT]
#endif
irq_handler
#ifdef CONFIG_PREEMPT
- str x24, [tsk, #TI_PREEMPT] // restore preempt count
- cbnz x24, 1f // preempt count != 0
+ str w24, [tsk, #TI_PREEMPT] // restore preempt count
+ cbnz w24, 1f // preempt count != 0
ldr x0, [tsk, #TI_FLAGS] // get flags
tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling?
bl el1_preempt
@@ -434,6 +435,7 @@
* Data abort handling
*/
mrs x0, far_el1
+ bic x0, x0, #(0xff << 56)
disable_step x1
isb
enable_dbg
@@ -487,6 +489,8 @@
* Undefined instruction
*/
mov x0, sp
+ // enable interrupts before calling the main handler
+ enable_irq
b do_undefinstr
el0_dbg:
/*
@@ -517,15 +521,15 @@
#endif
get_thread_info tsk
#ifdef CONFIG_PREEMPT
- ldr x24, [tsk, #TI_PREEMPT] // get preempt count
- add x23, x24, #1 // increment it
- str x23, [tsk, #TI_PREEMPT]
+ ldr w24, [tsk, #TI_PREEMPT] // get preempt count
+ add w23, w24, #1 // increment it
+ str w23, [tsk, #TI_PREEMPT]
#endif
irq_handler
#ifdef CONFIG_PREEMPT
- ldr x0, [tsk, #TI_PREEMPT]
- str x24, [tsk, #TI_PREEMPT]
- cmp x0, x23
+ ldr w0, [tsk, #TI_PREEMPT]
+ str w24, [tsk, #TI_PREEMPT]
+ cmp w0, w23
b.eq 1f
mov x1, #0
str x1, [x1] // BUG
@@ -652,8 +656,9 @@
enable_irq
get_thread_info tsk
- ldr x16, [tsk, #TI_FLAGS] // check for syscall tracing
- tbnz x16, #TIF_SYSCALL_TRACE, __sys_trace // are we tracing syscalls?
+ ldr x16, [tsk, #TI_FLAGS] // check for syscall hooks
+ tst x16, #_TIF_SYSCALL_WORK
+ b.ne __sys_trace
adr lr, ret_fast_syscall // return address
cmp scno, sc_nr // check upper syscall limit
b.hs ni_sys
@@ -669,9 +674,8 @@
* switches, and waiting for our parent to respond.
*/
__sys_trace:
- mov x1, sp
- mov w0, #0 // trace entry
- bl syscall_trace
+ mov x0, sp
+ bl syscall_trace_enter
adr lr, __sys_trace_return // return address
uxtw scno, w0 // syscall number (possibly new)
mov x1, sp // pointer to regs
@@ -686,9 +690,8 @@
__sys_trace_return:
str x0, [sp] // save returned x0
- mov x1, sp
- mov w0, #1 // trace exit
- bl syscall_trace
+ mov x0, sp
+ bl syscall_trace_exit
b ret_to_user
/*
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index e8b8357..522df9c 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/sched.h>
@@ -79,10 +80,72 @@
void fpsimd_flush_thread(void)
{
+ preempt_disable();
memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
fpsimd_load_state(¤t->thread.fpsimd_state);
+ preempt_enable();
}
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+/*
+ * Kernel-side NEON support functions
+ */
+void kernel_neon_begin(void)
+{
+ /* Avoid using the NEON in interrupt context */
+ BUG_ON(in_interrupt());
+ preempt_disable();
+
+ if (current->mm)
+ fpsimd_save_state(¤t->thread.fpsimd_state);
+}
+EXPORT_SYMBOL(kernel_neon_begin);
+
+void kernel_neon_end(void)
+{
+ if (current->mm)
+ fpsimd_load_state(¤t->thread.fpsimd_state);
+
+ preempt_enable();
+}
+EXPORT_SYMBOL(kernel_neon_end);
+
+#endif /* CONFIG_KERNEL_MODE_NEON */
+
+#ifdef CONFIG_CPU_PM
+static int fpsimd_cpu_pm_notifier(struct notifier_block *self,
+ unsigned long cmd, void *v)
+{
+ switch (cmd) {
+ case CPU_PM_ENTER:
+ if (current->mm)
+ fpsimd_save_state(¤t->thread.fpsimd_state);
+ break;
+ case CPU_PM_EXIT:
+ if (current->mm)
+ fpsimd_load_state(¤t->thread.fpsimd_state);
+ break;
+ case CPU_PM_ENTER_FAILED:
+ default:
+ return NOTIFY_DONE;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_pm_notifier_block = {
+ .notifier_call = fpsimd_cpu_pm_notifier,
+};
+
+static void fpsimd_pm_init(void)
+{
+ cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
+}
+
+#else
+static inline void fpsimd_pm_init(void) { }
+#endif /* CONFIG_CPU_PM */
+
/*
* FP/SIMD support code initialisation.
*/
@@ -101,6 +164,8 @@
else
elf_hwcap |= HWCAP_ASIMD;
+ fpsimd_pm_init();
+
return 0;
}
late_initcall(fpsimd_init);
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
new file mode 100644
index 0000000..649890a
--- /dev/null
+++ b/arch/arm64/kernel/ftrace.c
@@ -0,0 +1,177 @@
+/*
+ * arch/arm64/kernel/ftrace.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ftrace.h>
+#include <linux/swab.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+#include <asm/insn.h>
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Replace a single instruction, which may be a branch or NOP.
+ * If @validate == true, a replaced instruction is checked against 'old'.
+ */
+static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
+ bool validate)
+{
+ u32 replaced;
+
+ /*
+ * Note:
+ * Due to modules and __init, code can disappear and change,
+ * we need to protect against faulting as well as code changing.
+ * We do this by aarch64_insn_*() which use the probe_kernel_*().
+ *
+ * No lock is held here because all the modifications are run
+ * through stop_machine().
+ */
+ if (validate) {
+ if (aarch64_insn_read((void *)pc, &replaced))
+ return -EFAULT;
+
+ if (replaced != old)
+ return -EINVAL;
+ }
+ if (aarch64_insn_patch_text_nosync((void *)pc, new))
+ return -EPERM;
+
+ return 0;
+}
+
+/*
+ * Replace tracer function in ftrace_caller()
+ */
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long pc;
+ u32 new;
+
+ pc = (unsigned long)&ftrace_call;
+ new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, true);
+
+ return ftrace_modify_code(pc, 0, new, false);
+}
+
+/*
+ * Turn on the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+ unsigned long pc = rec->ip;
+ u32 old, new;
+
+ old = aarch64_insn_gen_nop();
+ new = aarch64_insn_gen_branch_imm(pc, addr, true);
+
+ return ftrace_modify_code(pc, old, new, true);
+}
+
+/*
+ * Turn off the call to ftrace_caller() in instrumented function
+ */
+int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
+ unsigned long addr)
+{
+ unsigned long pc = rec->ip;
+ u32 old, new;
+
+ old = aarch64_insn_gen_branch_imm(pc, addr, true);
+ new = aarch64_insn_gen_nop();
+
+ return ftrace_modify_code(pc, old, new, true);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+ *(unsigned long *)data = 0;
+ return 0;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * function_graph tracer expects ftrace_return_to_handler() to be called
+ * on the way back to parent. For this purpose, this function is called
+ * in _mcount() or ftrace_caller() to replace return address (*parent) on
+ * the call stack to return_to_handler.
+ *
+ * Note that @frame_pointer is used only for sanity check later.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+ unsigned long frame_pointer)
+{
+ unsigned long return_hooker = (unsigned long)&return_to_handler;
+ unsigned long old;
+ struct ftrace_graph_ent trace;
+ int err;
+
+ if (unlikely(atomic_read(¤t->tracing_graph_pause)))
+ return;
+
+ /*
+ * Note:
+ * No protection against faulting at *parent, which may be seen
+ * on other archs. It's unlikely on AArch64.
+ */
+ old = *parent;
+ *parent = return_hooker;
+
+ trace.func = self_addr;
+ trace.depth = current->curr_ret_stack + 1;
+
+ /* Only trace if the calling function expects to */
+ if (!ftrace_graph_entry(&trace)) {
+ *parent = old;
+ return;
+ }
+
+ err = ftrace_push_return_trace(old, self_addr, &trace.depth,
+ frame_pointer);
+ if (err == -EBUSY) {
+ *parent = old;
+ return;
+ }
+}
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+/*
+ * Turn on/off the call to ftrace_graph_caller() in ftrace_caller()
+ * depending on @enable.
+ */
+static int ftrace_modify_graph_caller(bool enable)
+{
+ unsigned long pc = (unsigned long)&ftrace_graph_call;
+ u32 branch, nop;
+
+ branch = aarch64_insn_gen_branch_imm(pc,
+ (unsigned long)ftrace_graph_caller, false);
+ nop = aarch64_insn_gen_nop();
+
+ if (enable)
+ return ftrace_modify_code(pc, nop, branch, true);
+ else
+ return ftrace_modify_code(pc, branch, nop, true);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_graph_caller(true);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+ return ftrace_modify_graph_caller(false);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 53dcae4..6254f4a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -22,10 +22,12 @@
#include <linux/linkage.h>
#include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
#include <asm/assembler.h>
#include <asm/ptrace.h>
#include <asm/asm-offsets.h>
+#include <asm/cache.h>
#include <asm/cputype.h>
#include <asm/memory.h>
#include <asm/thread_info.h>
@@ -34,29 +36,21 @@
#include <asm/page.h>
#include <asm/virt.h>
-/*
- * swapper_pg_dir is the virtual address of the initial page table. We place
- * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has
- * 2 pages and is placed below swapper_pg_dir.
- */
#define KERNEL_RAM_VADDR (PAGE_OFFSET + TEXT_OFFSET)
-#if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000
-#error KERNEL_RAM_VADDR must start at 0xXXX80000
+#if (TEXT_OFFSET & 0xfff) != 0
+#error TEXT_OFFSET must be at least 4KB aligned
+#elif (PAGE_OFFSET & 0x1fffff) != 0
+#error PAGE_OFFSET must be at least 2MB aligned
+#elif TEXT_OFFSET > 0x1fffff
+#error TEXT_OFFSET must be less than 2MB
#endif
-#define SWAPPER_DIR_SIZE (3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE (2 * PAGE_SIZE)
-
- .globl swapper_pg_dir
- .equ swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE
-
- .globl idmap_pg_dir
- .equ idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE
-
- .macro pgtbl, ttb0, ttb1, phys
- add \ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE
- sub \ttb0, \ttb1, #IDMAP_DIR_SIZE
+ .macro pgtbl, ttb0, ttb1, virt_to_phys
+ ldr \ttb1, =swapper_pg_dir
+ ldr \ttb0, =idmap_pg_dir
+ add \ttb1, \ttb1, \virt_to_phys
+ add \ttb0, \ttb0, \virt_to_phys
.endm
#ifdef CONFIG_ARM64_64K_PAGES
@@ -107,16 +101,137 @@
/*
* DO NOT MODIFY. Image header expected by Linux boot-loaders.
*/
+#ifdef CONFIG_EFI
+efi_head:
+ /*
+ * This add instruction has no meaningful effect except that
+ * its opcode forms the magic "MZ" signature required by UEFI.
+ */
+ add x13, x18, #0x16
+ b stext
+#else
b stext // branch to kernel start, magic
.long 0 // reserved
+#endif
.quad TEXT_OFFSET // Image load offset from start of RAM
.quad 0 // reserved
.quad 0 // reserved
+ .quad 0 // reserved
+ .quad 0 // reserved
+ .quad 0 // reserved
+ .byte 0x41 // Magic number, "ARM\x64"
+ .byte 0x52
+ .byte 0x4d
+ .byte 0x64
+#ifdef CONFIG_EFI
+ .long pe_header - efi_head // Offset to the PE header.
+#else
+ .word 0 // reserved
+#endif
+
+#ifdef CONFIG_EFI
+ .align 3
+pe_header:
+ .ascii "PE"
+ .short 0
+coff_header:
+ .short 0xaa64 // AArch64
+ .short 2 // nr_sections
+ .long 0 // TimeDateStamp
+ .long 0 // PointerToSymbolTable
+ .long 1 // NumberOfSymbols
+ .short section_table - optional_header // SizeOfOptionalHeader
+ .short 0x206 // Characteristics.
+ // IMAGE_FILE_DEBUG_STRIPPED |
+ // IMAGE_FILE_EXECUTABLE_IMAGE |
+ // IMAGE_FILE_LINE_NUMS_STRIPPED
+optional_header:
+ .short 0x20b // PE32+ format
+ .byte 0x02 // MajorLinkerVersion
+ .byte 0x14 // MinorLinkerVersion
+ .long _edata - stext // SizeOfCode
+ .long 0 // SizeOfInitializedData
+ .long 0 // SizeOfUninitializedData
+ .long efi_stub_entry - efi_head // AddressOfEntryPoint
+ .long stext - efi_head // BaseOfCode
+
+extra_header_fields:
+ .quad 0 // ImageBase
+ .long 0x20 // SectionAlignment
+ .long 0x8 // FileAlignment
+ .short 0 // MajorOperatingSystemVersion
+ .short 0 // MinorOperatingSystemVersion
+ .short 0 // MajorImageVersion
+ .short 0 // MinorImageVersion
+ .short 0 // MajorSubsystemVersion
+ .short 0 // MinorSubsystemVersion
+ .long 0 // Win32VersionValue
+
+ .long _edata - efi_head // SizeOfImage
+
+ // Everything before the kernel image is considered part of the header
+ .long stext - efi_head // SizeOfHeaders
+ .long 0 // CheckSum
+ .short 0xa // Subsystem (EFI application)
+ .short 0 // DllCharacteristics
+ .quad 0 // SizeOfStackReserve
+ .quad 0 // SizeOfStackCommit
+ .quad 0 // SizeOfHeapReserve
+ .quad 0 // SizeOfHeapCommit
+ .long 0 // LoaderFlags
+ .long 0x6 // NumberOfRvaAndSizes
+
+ .quad 0 // ExportTable
+ .quad 0 // ImportTable
+ .quad 0 // ResourceTable
+ .quad 0 // ExceptionTable
+ .quad 0 // CertificationTable
+ .quad 0 // BaseRelocationTable
+
+ // Section table
+section_table:
+
+ /*
+ * The EFI application loader requires a relocation section
+ * because EFI applications must be relocatable. This is a
+ * dummy section as far as we are concerned.
+ */
+ .ascii ".reloc"
+ .byte 0
+ .byte 0 // end of 0 padding of section name
+ .long 0
+ .long 0
+ .long 0 // SizeOfRawData
+ .long 0 // PointerToRawData
+ .long 0 // PointerToRelocations
+ .long 0 // PointerToLineNumbers
+ .short 0 // NumberOfRelocations
+ .short 0 // NumberOfLineNumbers
+ .long 0x42100040 // Characteristics (section flags)
+
+
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0 // end of 0 padding of section name
+ .long _edata - stext // VirtualSize
+ .long stext - efi_head // VirtualAddress
+ .long _edata - stext // SizeOfRawData
+ .long stext - efi_head // PointerToRawData
+
+ .long 0 // PointerToRelocations (0 for executables)
+ .long 0 // PointerToLineNumbers (0 for executables)
+ .short 0 // NumberOfRelocations (0 for executables)
+ .short 0 // NumberOfLineNumbers (0 for executables)
+ .long 0xe0500020 // Characteristics (section flags)
+ .align 5
+#endif
ENTRY(stext)
mov x21, x0 // x21=FDT
+ bl el2_setup // Drop to EL1, w20=cpu_boot_mode
bl __calc_phys_offset // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
- bl el2_setup // Drop to EL1
+ bl set_cpu_boot_mode_flag
mrs x22, midr_el1 // x22=cpuid
mov x0, x22
bl lookup_processor_type
@@ -142,21 +257,30 @@
/*
* If we're fortunate enough to boot at EL2, ensure that the world is
* sane before dropping to EL1.
+ *
+ * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x20 if
+ * booted in EL1 or EL2 respectively.
*/
ENTRY(el2_setup)
mrs x0, CurrentEL
cmp x0, #PSR_MODE_EL2t
ccmp x0, #PSR_MODE_EL2h, #0x4, ne
- ldr x0, =__boot_cpu_mode // Compute __boot_cpu_mode
- add x0, x0, x28
- b.eq 1f
- str wzr, [x0] // Remember we don't have EL2...
+ b.ne 1f
+ mrs x0, sctlr_el2
+CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2
+CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
+ msr sctlr_el2, x0
+ b 2f
+1: mrs x0, sctlr_el1
+CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1
+CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
+ msr sctlr_el1, x0
+ mov w20, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1
+ isb
ret
/* Hyp configuration. */
-1: ldr w1, =BOOT_CPU_MODE_EL2
- str w1, [x0, #4] // This CPU has EL2
- mov x0, #(1 << 31) // 64-bit EL1
+2: mov x0, #(1 << 31) // 64-bit EL1
msr hcr_el2, x0
/* Generic timers. */
@@ -165,6 +289,23 @@
msr cnthctl_el2, x0
msr cntvoff_el2, xzr // Clear virtual offset
+#ifdef CONFIG_ARM_GIC_V3
+ /* GICv3 system register access */
+ mrs x0, id_aa64pfr0_el1
+ ubfx x0, x0, #24, #4
+ cmp x0, #1
+ b.ne 3f
+
+ mrs_s x0, ICC_SRE_EL2
+ orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1
+ orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1
+ msr_s ICC_SRE_EL2, x0
+ isb // Make sure SRE is now set
+ msr_s ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults
+
+3:
+#endif
+
/* Populate ID registers. */
mrs x0, midr_el1
mrs x1, mpidr_el1
@@ -173,7 +314,8 @@
/* sctlr_el1 */
mov x0, #0x0800 // Set/clear RES{1,0} bits
- movk x0, #0x30d0, lsl #16
+CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems
+CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
msr sctlr_el1, x0
/* Coprocessor traps. */
@@ -196,28 +338,41 @@
PSR_MODE_EL1h)
msr spsr_el2, x0
msr elr_el2, lr
+ mov w20, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
eret
ENDPROC(el2_setup)
/*
+ * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
+ * in x20. See arch/arm64/include/asm/virt.h for more info.
+ */
+ENTRY(set_cpu_boot_mode_flag)
+ ldr x1, =__boot_cpu_mode // Compute __boot_cpu_mode
+ add x1, x1, x28
+ cmp w20, #BOOT_CPU_MODE_EL2
+ b.ne 1f
+ add x1, x1, #4
+1: str w20, [x1] // This CPU has booted in EL1
+ dmb sy
+ dc ivac, x1 // Invalidate potentially stale cache line
+ ret
+ENDPROC(set_cpu_boot_mode_flag)
+
+/*
* We need to find out the CPU boot mode long after boot, so we need to
* store it in a writable variable.
*
* This is not in .bss, because we set it sufficiently early that the boot-time
* zeroing of .bss would clobber it.
*/
- .pushsection .data
+ .pushsection .data..cacheline_aligned
ENTRY(__boot_cpu_mode)
+ .align L1_CACHE_SHIFT
.long BOOT_CPU_MODE_EL2
.long 0
.popsection
- .align 3
-2: .quad .
- .quad PAGE_OFFSET
-
#ifdef CONFIG_SMP
- .pushsection .smp.pen.text, "ax"
.align 3
1: .quad .
.quad secondary_holding_pen_release
@@ -227,8 +382,9 @@
* cores are held until we're ready for them to initialise.
*/
ENTRY(secondary_holding_pen)
- bl __calc_phys_offset // x24=phys offset
- bl el2_setup // Drop to EL1
+ bl el2_setup // Drop to EL1, w20=cpu_boot_mode
+ bl __calc_phys_offset // x24=PHYS_OFFSET, x28=PHYS_OFFSET-PAGE_OFFSET
+ bl set_cpu_boot_mode_flag
mrs x0, mpidr_el1
ldr x1, =MPIDR_HWID_BITMASK
and x0, x0, x1
@@ -242,7 +398,16 @@
wfe
b pen
ENDPROC(secondary_holding_pen)
- .popsection
+
+ /*
+ * Secondary entry point that jumps straight into the kernel. Only to
+ * be used where CPUs are brought online dynamically by the kernel.
+ */
+ENTRY(secondary_entry)
+ bl __calc_phys_offset // x2=phys offset
+ bl el2_setup // Drop to EL1
+ b secondary_startup
+ENDPROC(secondary_entry)
ENTRY(secondary_startup)
/*
@@ -254,7 +419,7 @@
mov x23, x0 // x23=current cpu_table
cbz x23, __error_p // invalid processor (x23=0)?
- pgtbl x25, x26, x24 // x25=TTBR0, x26=TTBR1
+ pgtbl x25, x26, x28 // x25=TTBR0, x26=TTBR1
ldr x12, [x23, #CPU_INFO_SETUP]
add x12, x12, x28 // __virt_to_phys
blr x12 // initialise processor
@@ -296,8 +461,13 @@
* x27 = *virtual* address to jump to upon completion
*
* other registers depend on the function called upon completion
+ *
+ * We align the entire function to the smallest power of two larger than it to
+ * ensure it fits within a single block map entry. Otherwise were PHYS_OFFSET
+ * close to the end of a 512MB or 1GB block we might require an additional
+ * table to map the entire function.
*/
- .align 6
+ .align 4
__turn_mmu_on:
msr sctlr_el1, x0
isb
@@ -340,26 +510,18 @@
* Preserves: tbl, flags
* Corrupts: phys, start, end, pstate
*/
- .macro create_block_map, tbl, flags, phys, start, end, idmap=0
+ .macro create_block_map, tbl, flags, phys, start, end
lsr \phys, \phys, #BLOCK_SHIFT
- .if \idmap
- and \start, \phys, #PTRS_PER_PTE - 1 // table index
- .else
lsr \start, \start, #BLOCK_SHIFT
and \start, \start, #PTRS_PER_PTE - 1 // table index
- .endif
orr \phys, \flags, \phys, lsl #BLOCK_SHIFT // table entry
- .ifnc \start,\end
lsr \end, \end, #BLOCK_SHIFT
and \end, \end, #PTRS_PER_PTE - 1 // table end index
- .endif
9999: str \phys, [\tbl, \start, lsl #3] // store the entry
- .ifnc \start,\end
add \start, \start, #1 // next entry
add \phys, \phys, #BLOCK_SIZE // next block
cmp \start, \end
b.ls 9999b
- .endif
.endm
/*
@@ -368,10 +530,19 @@
* - identity mapping to enable the MMU (low address, TTBR0)
* - first few MB of the kernel linear mapping to jump to once the MMU has
* been enabled, including the FDT blob (TTBR1)
- * - UART mapping if CONFIG_EARLY_PRINTK is enabled (TTBR1)
+ * - pgd entry for fixed mappings (TTBR1)
*/
__create_page_tables:
- pgtbl x25, x26, x24 // idmap_pg_dir and swapper_pg_dir addresses
+ pgtbl x25, x26, x28 // idmap_pg_dir and swapper_pg_dir addresses
+ mov x27, lr
+
+ /*
+ * Invalidate the idmap and swapper page tables to avoid potential
+ * dirty cache lines being evicted.
+ */
+ mov x0, x25
+ add x1, x26, #SWAPPER_DIR_SIZE
+ bl __inval_cache_range
/*
* Clear the idmap and swapper page tables.
@@ -391,9 +562,13 @@
* Create the identity mapping.
*/
add x0, x25, #PAGE_SIZE // section table address
- adr x3, __turn_mmu_on // virtual/physical address
+ ldr x3, =KERNEL_START
+ add x3, x3, x28 // __pa(KERNEL_START)
create_pgd_entry x25, x0, x3, x5, x6
- create_block_map x0, x7, x3, x5, x5, idmap=1
+ ldr x6, =KERNEL_END
+ mov x5, x3 // __pa(KERNEL_START)
+ add x6, x6, x28 // __pa(KERNEL_END)
+ create_block_map x0, x7, x3, x5, x6
/*
* Map the kernel image (starting with PHYS_OFFSET).
@@ -401,7 +576,7 @@
add x0, x26, #PAGE_SIZE // section table address
mov x5, #PAGE_OFFSET
create_pgd_entry x26, x0, x5, x3, x6
- ldr x6, =KERNEL_END - 1
+ ldr x6, =KERNEL_END
mov x3, x24 // phys offset
create_block_map x0, x7, x3, x5, x6
@@ -421,15 +596,16 @@
sub x6, x6, #1 // inclusive range
create_block_map x0, x7, x3, x5, x6
1:
-#ifdef CONFIG_EARLY_PRINTK
/*
- * Create the pgd entry for the UART mapping. The full mapping is done
- * later based earlyprintk kernel parameter.
+ * Since the page tables have been populated with non-cacheable
+ * accesses (MMU disabled), invalidate the idmap and swapper page
+ * tables again to remove any speculatively loaded cache lines.
*/
- ldr x5, =EARLYCON_IOBASE // UART virtual address
- add x0, x26, #2 * PAGE_SIZE // section table address
- create_pgd_entry x26, x0, x5, x6, x7
-#endif
+ mov x0, x25
+ add x1, x26, #SWAPPER_DIR_SIZE
+ bl __inval_cache_range
+
+ mov lr, x27
ret
ENDPROC(__create_page_tables)
.ltorg
@@ -438,10 +614,8 @@
.type __switch_data, %object
__switch_data:
.quad __mmap_switched
- .quad __data_loc // x4
- .quad _data // x5
.quad __bss_start // x6
- .quad _end // x7
+ .quad __bss_stop // x7
.quad processor_id // x4
.quad __fdt_pointer // x5
.quad memstart_addr // x6
@@ -454,15 +628,7 @@
__mmap_switched:
adr x3, __switch_data + 8
- ldp x4, x5, [x3], #16
ldp x6, x7, [x3], #16
- cmp x4, x5 // Copy data segment if needed
-1: ccmp x5, x6, #4, ne
- b.eq 2f
- ldr x16, [x4], #8
- str x16, [x5], #8
- b 1b
-2:
1: cmp x6, x7
b.hs 2f
str xzr, [x6], #8 // Clear BSS
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 5ab825c..6de3460 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -20,13 +20,14 @@
#define pr_fmt(fmt) "hw-breakpoint: " fmt
+#include <linux/compat.h>
+#include <linux/cpu_pm.h>
#include <linux/errno.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
#include <linux/smp.h>
-#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
@@ -169,15 +170,68 @@
}
}
-/*
- * Install a perf counter breakpoint.
+enum hw_breakpoint_ops {
+ HW_BREAKPOINT_INSTALL,
+ HW_BREAKPOINT_UNINSTALL,
+ HW_BREAKPOINT_RESTORE
+};
+
+/**
+ * hw_breakpoint_slot_setup - Find and setup a perf slot according to
+ * operations
+ *
+ * @slots: pointer to array of slots
+ * @max_slots: max number of slots
+ * @bp: perf_event to setup
+ * @ops: operation to be carried out on the slot
+ *
+ * Return:
+ * slot index on success
+ * -ENOSPC if no slot is available/matches
+ * -EINVAL on wrong operations parameter
*/
-int arch_install_hw_breakpoint(struct perf_event *bp)
+static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots,
+ struct perf_event *bp,
+ enum hw_breakpoint_ops ops)
+{
+ int i;
+ struct perf_event **slot;
+
+ for (i = 0; i < max_slots; ++i) {
+ slot = &slots[i];
+ switch (ops) {
+ case HW_BREAKPOINT_INSTALL:
+ if (!*slot) {
+ *slot = bp;
+ return i;
+ }
+ break;
+ case HW_BREAKPOINT_UNINSTALL:
+ if (*slot == bp) {
+ *slot = NULL;
+ return i;
+ }
+ break;
+ case HW_BREAKPOINT_RESTORE:
+ if (*slot == bp)
+ return i;
+ break;
+ default:
+ pr_warn_once("Unhandled hw breakpoint ops %d\n", ops);
+ return -EINVAL;
+ }
+ }
+ return -ENOSPC;
+}
+
+static int hw_breakpoint_control(struct perf_event *bp,
+ enum hw_breakpoint_ops ops)
{
struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- struct perf_event **slot, **slots;
+ struct perf_event **slots;
struct debug_info *debug_info = ¤t->thread.debug;
int i, max_slots, ctrl_reg, val_reg, reg_enable;
+ enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege);
u32 ctrl;
if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
@@ -196,67 +250,54 @@
reg_enable = !debug_info->wps_disabled;
}
- for (i = 0; i < max_slots; ++i) {
- slot = &slots[i];
+ i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops);
- if (!*slot) {
- *slot = bp;
- break;
- }
+ if (WARN_ONCE(i < 0, "Can't find any breakpoint slot"))
+ return i;
+
+ switch (ops) {
+ case HW_BREAKPOINT_INSTALL:
+ /*
+ * Ensure debug monitors are enabled at the correct exception
+ * level.
+ */
+ enable_debug_monitors(dbg_el);
+ /* Fall through */
+ case HW_BREAKPOINT_RESTORE:
+ /* Setup the address register. */
+ write_wb_reg(val_reg, i, info->address);
+
+ /* Setup the control register. */
+ ctrl = encode_ctrl_reg(info->ctrl);
+ write_wb_reg(ctrl_reg, i,
+ reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
+ break;
+ case HW_BREAKPOINT_UNINSTALL:
+ /* Reset the control register. */
+ write_wb_reg(ctrl_reg, i, 0);
+
+ /*
+ * Release the debug monitors for the correct exception
+ * level.
+ */
+ disable_debug_monitors(dbg_el);
+ break;
}
- if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
- return -ENOSPC;
-
- /* Ensure debug monitors are enabled at the correct exception level. */
- enable_debug_monitors(debug_exception_level(info->ctrl.privilege));
-
- /* Setup the address register. */
- write_wb_reg(val_reg, i, info->address);
-
- /* Setup the control register. */
- ctrl = encode_ctrl_reg(info->ctrl);
- write_wb_reg(ctrl_reg, i, reg_enable ? ctrl | 0x1 : ctrl & ~0x1);
-
return 0;
}
+/*
+ * Install a perf counter breakpoint.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
+{
+ return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL);
+}
+
void arch_uninstall_hw_breakpoint(struct perf_event *bp)
{
- struct arch_hw_breakpoint *info = counter_arch_bp(bp);
- struct perf_event **slot, **slots;
- int i, max_slots, base;
-
- if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
- /* Breakpoint */
- base = AARCH64_DBG_REG_BCR;
- slots = __get_cpu_var(bp_on_reg);
- max_slots = core_num_brps;
- } else {
- /* Watchpoint */
- base = AARCH64_DBG_REG_WCR;
- slots = __get_cpu_var(wp_on_reg);
- max_slots = core_num_wrps;
- }
-
- /* Remove the breakpoint. */
- for (i = 0; i < max_slots; ++i) {
- slot = &slots[i];
-
- if (*slot == bp) {
- *slot = NULL;
- break;
- }
- }
-
- if (WARN_ONCE(i == max_slots, "Can't find any breakpoint slot"))
- return;
-
- /* Reset the control register. */
- write_wb_reg(base, i, 0);
-
- /* Release the debug monitors for the correct exception level. */
- disable_debug_monitors(debug_exception_level(info->ctrl.privilege));
+ hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL);
}
static int get_hbp_len(u8 hbp_len)
@@ -806,18 +847,36 @@
/*
* CPU initialisation.
*/
-static void reset_ctrl_regs(void *unused)
+static void hw_breakpoint_reset(void *unused)
{
int i;
-
- for (i = 0; i < core_num_brps; ++i) {
- write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
- write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+ struct perf_event **slots;
+ /*
+ * When a CPU goes through cold-boot, it does not have any installed
+ * slot, so it is safe to share the same function for restoring and
+ * resetting breakpoints; when a CPU is hotplugged in, it goes
+ * through the slots, which are all empty, hence it just resets control
+ * and value for debug registers.
+ * When this function is triggered on warm-boot through a CPU PM
+ * notifier some slots might be initialized; if so they are
+ * reprogrammed according to the debug slots content.
+ */
+ for (slots = __get_cpu_var(bp_on_reg), i = 0; i < core_num_brps; ++i) {
+ if (slots[i]) {
+ hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+ } else {
+ write_wb_reg(AARCH64_DBG_REG_BCR, i, 0UL);
+ write_wb_reg(AARCH64_DBG_REG_BVR, i, 0UL);
+ }
}
- for (i = 0; i < core_num_wrps; ++i) {
- write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
- write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+ for (slots = __get_cpu_var(wp_on_reg), i = 0; i < core_num_wrps; ++i) {
+ if (slots[i]) {
+ hw_breakpoint_control(slots[i], HW_BREAKPOINT_RESTORE);
+ } else {
+ write_wb_reg(AARCH64_DBG_REG_WCR, i, 0UL);
+ write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
+ }
}
}
@@ -827,7 +886,7 @@
{
int cpu = (long)hcpu;
if (action == CPU_ONLINE)
- smp_call_function_single(cpu, reset_ctrl_regs, NULL, 1);
+ smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1);
return NOTIFY_OK;
}
@@ -835,6 +894,14 @@
.notifier_call = hw_breakpoint_reset_notify,
};
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
+#else
+static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+{
+}
+#endif
+
/*
* One-time initialisation.
*/
@@ -850,8 +917,8 @@
* Reset the breakpoint resources. We assume that a halting
* debugger will leave the world in a nice state for us.
*/
- smp_call_function(reset_ctrl_regs, NULL, 1);
- reset_ctrl_regs(NULL);
+ smp_call_function(hw_breakpoint_reset, NULL, 1);
+ hw_breakpoint_reset(NULL);
/* Register debug fault handlers. */
hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
@@ -861,6 +928,8 @@
/* Register hotplug notifier. */
register_cpu_notifier(&hw_breakpoint_reset_nb);
+ /* Register cpu_suspend hw breakpoint restore hook */
+ cpu_suspend_set_dbg_restorer(hw_breakpoint_reset);
return 0;
}
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 0959611..a272f33 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -19,6 +19,7 @@
#include <linux/init.h>
#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
#include <asm/assembler.h>
#include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
new file mode 100644
index 0000000..92f3683
--- /dev/null
+++ b/arch/arm64/kernel/insn.c
@@ -0,0 +1,304 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/stop_machine.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/insn.h>
+
+static int aarch64_insn_encoding_class[] = {
+ AARCH64_INSN_CLS_UNKNOWN,
+ AARCH64_INSN_CLS_UNKNOWN,
+ AARCH64_INSN_CLS_UNKNOWN,
+ AARCH64_INSN_CLS_UNKNOWN,
+ AARCH64_INSN_CLS_LDST,
+ AARCH64_INSN_CLS_DP_REG,
+ AARCH64_INSN_CLS_LDST,
+ AARCH64_INSN_CLS_DP_FPSIMD,
+ AARCH64_INSN_CLS_DP_IMM,
+ AARCH64_INSN_CLS_DP_IMM,
+ AARCH64_INSN_CLS_BR_SYS,
+ AARCH64_INSN_CLS_BR_SYS,
+ AARCH64_INSN_CLS_LDST,
+ AARCH64_INSN_CLS_DP_REG,
+ AARCH64_INSN_CLS_LDST,
+ AARCH64_INSN_CLS_DP_FPSIMD,
+};
+
+enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn)
+{
+ return aarch64_insn_encoding_class[(insn >> 25) & 0xf];
+}
+
+/* NOP is an alias of HINT */
+bool __kprobes aarch64_insn_is_nop(u32 insn)
+{
+ if (!aarch64_insn_is_hint(insn))
+ return false;
+
+ switch (insn & 0xFE0) {
+ case AARCH64_INSN_HINT_YIELD:
+ case AARCH64_INSN_HINT_WFE:
+ case AARCH64_INSN_HINT_WFI:
+ case AARCH64_INSN_HINT_SEV:
+ case AARCH64_INSN_HINT_SEVL:
+ return false;
+ default:
+ return true;
+ }
+}
+
+/*
+ * In ARMv8-A, A64 instructions have a fixed length of 32 bits and are always
+ * little-endian.
+ */
+int __kprobes aarch64_insn_read(void *addr, u32 *insnp)
+{
+ int ret;
+ u32 val;
+
+ ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
+ if (!ret)
+ *insnp = le32_to_cpu(val);
+
+ return ret;
+}
+
+int __kprobes aarch64_insn_write(void *addr, u32 insn)
+{
+ insn = cpu_to_le32(insn);
+ return probe_kernel_write(addr, &insn, AARCH64_INSN_SIZE);
+}
+
+static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
+{
+ if (aarch64_get_insn_class(insn) != AARCH64_INSN_CLS_BR_SYS)
+ return false;
+
+ return aarch64_insn_is_b(insn) ||
+ aarch64_insn_is_bl(insn) ||
+ aarch64_insn_is_svc(insn) ||
+ aarch64_insn_is_hvc(insn) ||
+ aarch64_insn_is_smc(insn) ||
+ aarch64_insn_is_brk(insn) ||
+ aarch64_insn_is_nop(insn);
+}
+
+/*
+ * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
+ * Section B2.6.5 "Concurrent modification and execution of instructions":
+ * Concurrent modification and execution of instructions can lead to the
+ * resulting instruction performing any behavior that can be achieved by
+ * executing any sequence of instructions that can be executed from the
+ * same Exception level, except where the instruction before modification
+ * and the instruction after modification is a B, BL, NOP, BKPT, SVC, HVC,
+ * or SMC instruction.
+ */
+bool __kprobes aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn)
+{
+ return __aarch64_insn_hotpatch_safe(old_insn) &&
+ __aarch64_insn_hotpatch_safe(new_insn);
+}
+
+int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
+{
+ u32 *tp = addr;
+ int ret;
+
+ /* A64 instructions must be word aligned */
+ if ((uintptr_t)tp & 0x3)
+ return -EINVAL;
+
+ ret = aarch64_insn_write(tp, insn);
+ if (ret == 0)
+ flush_icache_range((uintptr_t)tp,
+ (uintptr_t)tp + AARCH64_INSN_SIZE);
+
+ return ret;
+}
+
+struct aarch64_insn_patch {
+ void **text_addrs;
+ u32 *new_insns;
+ int insn_cnt;
+ atomic_t cpu_count;
+};
+
+static int __kprobes aarch64_insn_patch_text_cb(void *arg)
+{
+ int i, ret = 0;
+ struct aarch64_insn_patch *pp = arg;
+
+ /* The first CPU becomes master */
+ if (atomic_inc_return(&pp->cpu_count) == 1) {
+ for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
+ ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
+ pp->new_insns[i]);
+ /*
+ * aarch64_insn_patch_text_nosync() calls flush_icache_range(),
+ * which ends with "dsb; isb" pair guaranteeing global
+ * visibility.
+ */
+ atomic_set(&pp->cpu_count, -1);
+ } else {
+ while (atomic_read(&pp->cpu_count) != -1)
+ cpu_relax();
+ isb();
+ }
+
+ return ret;
+}
+
+int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
+{
+ struct aarch64_insn_patch patch = {
+ .text_addrs = addrs,
+ .new_insns = insns,
+ .insn_cnt = cnt,
+ .cpu_count = ATOMIC_INIT(0),
+ };
+
+ if (cnt <= 0)
+ return -EINVAL;
+
+ return stop_machine(aarch64_insn_patch_text_cb, &patch,
+ cpu_online_mask);
+}
+
+int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
+{
+ int ret;
+ u32 insn;
+
+ /* Unsafe to patch multiple instructions without synchronizaiton */
+ if (cnt == 1) {
+ ret = aarch64_insn_read(addrs[0], &insn);
+ if (ret)
+ return ret;
+
+ if (aarch64_insn_hotpatch_safe(insn, insns[0])) {
+ /*
+ * ARMv8 architecture doesn't guarantee all CPUs see
+ * the new instruction after returning from function
+ * aarch64_insn_patch_text_nosync(). So send IPIs to
+ * all other CPUs to achieve instruction
+ * synchronization.
+ */
+ ret = aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
+ kick_all_cpus_sync();
+ return ret;
+ }
+ }
+
+ return aarch64_insn_patch_text_sync(addrs, insns, cnt);
+}
+
+u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
+ u32 insn, u64 imm)
+{
+ u32 immlo, immhi, lomask, himask, mask;
+ int shift;
+
+ switch (type) {
+ case AARCH64_INSN_IMM_ADR:
+ lomask = 0x3;
+ himask = 0x7ffff;
+ immlo = imm & lomask;
+ imm >>= 2;
+ immhi = imm & himask;
+ imm = (immlo << 24) | (immhi);
+ mask = (lomask << 24) | (himask);
+ shift = 5;
+ break;
+ case AARCH64_INSN_IMM_26:
+ mask = BIT(26) - 1;
+ shift = 0;
+ break;
+ case AARCH64_INSN_IMM_19:
+ mask = BIT(19) - 1;
+ shift = 5;
+ break;
+ case AARCH64_INSN_IMM_16:
+ mask = BIT(16) - 1;
+ shift = 5;
+ break;
+ case AARCH64_INSN_IMM_14:
+ mask = BIT(14) - 1;
+ shift = 5;
+ break;
+ case AARCH64_INSN_IMM_12:
+ mask = BIT(12) - 1;
+ shift = 10;
+ break;
+ case AARCH64_INSN_IMM_9:
+ mask = BIT(9) - 1;
+ shift = 12;
+ break;
+ default:
+ pr_err("aarch64_insn_encode_immediate: unknown immediate encoding %d\n",
+ type);
+ return 0;
+ }
+
+ /* Update the immediate field. */
+ insn &= ~(mask << shift);
+ insn |= (imm & mask) << shift;
+
+ return insn;
+}
+
+u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
+ enum aarch64_insn_branch_type type)
+{
+ u32 insn;
+ long offset;
+
+ /*
+ * PC: A 64-bit Program Counter holding the address of the current
+ * instruction. A64 instructions must be word-aligned.
+ */
+ BUG_ON((pc & 0x3) || (addr & 0x3));
+
+ /*
+ * B/BL support [-128M, 128M) offset
+ * ARM64 virtual address arrangement guarantees all kernel and module
+ * texts are within +/-128M.
+ */
+ offset = ((long)addr - (long)pc);
+ BUG_ON(offset < -SZ_128M || offset >= SZ_128M);
+
+ if (type == AARCH64_INSN_BRANCH_LINK)
+ insn = aarch64_insn_get_bl_value();
+ else
+ insn = aarch64_insn_get_b_value();
+
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+ offset >> 2);
+}
+
+u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_op op)
+{
+ return aarch64_insn_get_hint_value() | op;
+}
+
+u32 __kprobes aarch64_insn_gen_nop(void)
+{
+ return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
+}
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index ecb3354..dfa6e3e 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -81,3 +81,64 @@
if (!handle_arch_irq)
panic("No interrupt controller found.");
}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static bool migrate_one_irq(struct irq_desc *desc)
+{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+ const struct cpumask *affinity = d->affinity;
+ struct irq_chip *c;
+ bool ret = false;
+
+ /*
+ * If this is a per-CPU interrupt, or the affinity does not
+ * include this CPU, then we have nothing to do.
+ */
+ if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
+ return false;
+
+ if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+ affinity = cpu_online_mask;
+ ret = true;
+ }
+
+ c = irq_data_get_irq_chip(d);
+ if (!c->irq_set_affinity)
+ pr_debug("IRQ%u: unable to set affinity\n", d->irq);
+ else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
+ cpumask_copy(d->affinity, affinity);
+
+ return ret;
+}
+
+/*
+ * The current CPU has been marked offline. Migrate IRQs off this CPU.
+ * If the affinity settings do not allow other CPUs, force them onto any
+ * available CPU.
+ *
+ * Note: we must iterate over all IRQs, whether they have an attached
+ * action structure or not, as we need to get chained interrupts too.
+ */
+void migrate_irqs(void)
+{
+ unsigned int i;
+ struct irq_desc *desc;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ for_each_irq_desc(i, desc) {
+ bool affinity_broken;
+
+ raw_spin_lock(&desc->lock);
+ affinity_broken = migrate_one_irq(desc);
+ raw_spin_unlock(&desc->lock);
+
+ if (affinity_broken)
+ pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
+ i, smp_processor_id());
+ }
+
+ local_irq_restore(flags);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
new file mode 100644
index 0000000..263a166
--- /dev/null
+++ b/arch/arm64/kernel/jump_label.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright (C) 2013 Huawei Ltd.
+ * Author: Jiang Liu <liuj97@gmail.com>
+ *
+ * Based on arch/arm/kernel/jump_label.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <asm/insn.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+static void __arch_jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ bool is_static)
+{
+ void *addr = (void *)entry->code;
+ u32 insn;
+
+ if (type == JUMP_LABEL_ENABLE) {
+ insn = aarch64_insn_gen_branch_imm(entry->code,
+ entry->target,
+ AARCH64_INSN_BRANCH_NOLINK);
+ } else {
+ insn = aarch64_insn_gen_nop();
+ }
+
+ if (is_static)
+ aarch64_insn_patch_text_nosync(addr, insn);
+ else
+ aarch64_insn_patch_text(&addr, &insn, 1);
+}
+
+void arch_jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type)
+{
+ __arch_jump_label_transform(entry, type, false);
+}
+
+void arch_jump_label_transform_static(struct jump_entry *entry,
+ enum jump_label_type type)
+{
+ __arch_jump_label_transform(entry, type, true);
+}
+
+#endif /* HAVE_JUMP_LABEL */
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
new file mode 100644
index 0000000..75c9cf1
--- /dev/null
+++ b/arch/arm64/kernel/kgdb.c
@@ -0,0 +1,336 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/kernel/kgdb.c
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/kgdb.h>
+#include <asm/traps.h>
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+ { "x0", 8, offsetof(struct pt_regs, regs[0])},
+ { "x1", 8, offsetof(struct pt_regs, regs[1])},
+ { "x2", 8, offsetof(struct pt_regs, regs[2])},
+ { "x3", 8, offsetof(struct pt_regs, regs[3])},
+ { "x4", 8, offsetof(struct pt_regs, regs[4])},
+ { "x5", 8, offsetof(struct pt_regs, regs[5])},
+ { "x6", 8, offsetof(struct pt_regs, regs[6])},
+ { "x7", 8, offsetof(struct pt_regs, regs[7])},
+ { "x8", 8, offsetof(struct pt_regs, regs[8])},
+ { "x9", 8, offsetof(struct pt_regs, regs[9])},
+ { "x10", 8, offsetof(struct pt_regs, regs[10])},
+ { "x11", 8, offsetof(struct pt_regs, regs[11])},
+ { "x12", 8, offsetof(struct pt_regs, regs[12])},
+ { "x13", 8, offsetof(struct pt_regs, regs[13])},
+ { "x14", 8, offsetof(struct pt_regs, regs[14])},
+ { "x15", 8, offsetof(struct pt_regs, regs[15])},
+ { "x16", 8, offsetof(struct pt_regs, regs[16])},
+ { "x17", 8, offsetof(struct pt_regs, regs[17])},
+ { "x18", 8, offsetof(struct pt_regs, regs[18])},
+ { "x19", 8, offsetof(struct pt_regs, regs[19])},
+ { "x20", 8, offsetof(struct pt_regs, regs[20])},
+ { "x21", 8, offsetof(struct pt_regs, regs[21])},
+ { "x22", 8, offsetof(struct pt_regs, regs[22])},
+ { "x23", 8, offsetof(struct pt_regs, regs[23])},
+ { "x24", 8, offsetof(struct pt_regs, regs[24])},
+ { "x25", 8, offsetof(struct pt_regs, regs[25])},
+ { "x26", 8, offsetof(struct pt_regs, regs[26])},
+ { "x27", 8, offsetof(struct pt_regs, regs[27])},
+ { "x28", 8, offsetof(struct pt_regs, regs[28])},
+ { "x29", 8, offsetof(struct pt_regs, regs[29])},
+ { "x30", 8, offsetof(struct pt_regs, regs[30])},
+ { "sp", 8, offsetof(struct pt_regs, sp)},
+ { "pc", 8, offsetof(struct pt_regs, pc)},
+ { "pstate", 8, offsetof(struct pt_regs, pstate)},
+ { "v0", 16, -1 },
+ { "v1", 16, -1 },
+ { "v2", 16, -1 },
+ { "v3", 16, -1 },
+ { "v4", 16, -1 },
+ { "v5", 16, -1 },
+ { "v6", 16, -1 },
+ { "v7", 16, -1 },
+ { "v8", 16, -1 },
+ { "v9", 16, -1 },
+ { "v10", 16, -1 },
+ { "v11", 16, -1 },
+ { "v12", 16, -1 },
+ { "v13", 16, -1 },
+ { "v14", 16, -1 },
+ { "v15", 16, -1 },
+ { "v16", 16, -1 },
+ { "v17", 16, -1 },
+ { "v18", 16, -1 },
+ { "v19", 16, -1 },
+ { "v20", 16, -1 },
+ { "v21", 16, -1 },
+ { "v22", 16, -1 },
+ { "v23", 16, -1 },
+ { "v24", 16, -1 },
+ { "v25", 16, -1 },
+ { "v26", 16, -1 },
+ { "v27", 16, -1 },
+ { "v28", 16, -1 },
+ { "v29", 16, -1 },
+ { "v30", 16, -1 },
+ { "v31", 16, -1 },
+ { "fpsr", 4, -1 },
+ { "fpcr", 4, -1 },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return NULL;
+
+ if (dbg_reg_def[regno].offset != -1)
+ memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+ dbg_reg_def[regno].size);
+ else
+ memset(mem, 0, dbg_reg_def[regno].size);
+ return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+ if (regno >= DBG_MAX_REG_NUM || regno < 0)
+ return -EINVAL;
+
+ if (dbg_reg_def[regno].offset != -1)
+ memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+ dbg_reg_def[regno].size);
+ return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+ struct pt_regs *thread_regs;
+
+ /* Initialize to zero */
+ memset((char *)gdb_regs, 0, NUMREGBYTES);
+ thread_regs = task_pt_regs(task);
+ memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+ regs->pc = pc;
+}
+
+static int compiled_break;
+
+static void kgdb_arch_update_addr(struct pt_regs *regs,
+ char *remcom_in_buffer)
+{
+ unsigned long addr;
+ char *ptr;
+
+ ptr = &remcom_in_buffer[1];
+ if (kgdb_hex2long(&ptr, &addr))
+ kgdb_arch_set_pc(regs, addr);
+ else if (compiled_break == 1)
+ kgdb_arch_set_pc(regs, regs->pc + 4);
+
+ compiled_break = 0;
+}
+
+int kgdb_arch_handle_exception(int exception_vector, int signo,
+ int err_code, char *remcom_in_buffer,
+ char *remcom_out_buffer,
+ struct pt_regs *linux_regs)
+{
+ int err;
+
+ switch (remcom_in_buffer[0]) {
+ case 'D':
+ case 'k':
+ /*
+ * Packet D (Detach), k (kill). No special handling
+ * is required here. Handle same as c packet.
+ */
+ case 'c':
+ /*
+ * Packet c (Continue) to continue executing.
+ * Set pc to required address.
+ * Try to read optional parameter and set pc.
+ * If this was a compiled breakpoint, we need to move
+ * to the next instruction else we will just breakpoint
+ * over and over again.
+ */
+ kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+ atomic_set(&kgdb_cpu_doing_single_step, -1);
+ kgdb_single_step = 0;
+
+ /*
+ * Received continue command, disable single step
+ */
+ if (kernel_active_single_step())
+ kernel_disable_single_step();
+
+ err = 0;
+ break;
+ case 's':
+ /*
+ * Update step address value with address passed
+ * with step packet.
+ * On debug exception return PC is copied to ELR
+ * So just update PC.
+ * If no step address is passed, resume from the address
+ * pointed by PC. Do not update PC
+ */
+ kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+ atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id());
+ kgdb_single_step = 1;
+
+ /*
+ * Enable single step handling
+ */
+ if (!kernel_active_single_step())
+ kernel_enable_single_step(linux_regs);
+ err = 0;
+ break;
+ default:
+ err = -1;
+ }
+ return err;
+}
+
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+ kgdb_handle_exception(1, SIGTRAP, 0, regs);
+ return 0;
+}
+
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+ compiled_break = 1;
+ kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+ return 0;
+}
+
+static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+ kgdb_handle_exception(1, SIGTRAP, 0, regs);
+ return 0;
+}
+
+static struct break_hook kgdb_brkpt_hook = {
+ .esr_mask = 0xffffffff,
+ .esr_val = DBG_ESR_VAL_BRK(KGDB_DYN_DGB_BRK_IMM),
+ .fn = kgdb_brk_fn
+};
+
+static struct break_hook kgdb_compiled_brkpt_hook = {
+ .esr_mask = 0xffffffff,
+ .esr_val = DBG_ESR_VAL_BRK(KDBG_COMPILED_DBG_BRK_IMM),
+ .fn = kgdb_compiled_brk_fn
+};
+
+static struct step_hook kgdb_step_hook = {
+ .fn = kgdb_step_brk_fn
+};
+
+static void kgdb_call_nmi_hook(void *ignored)
+{
+ kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+ local_irq_enable();
+ smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+ local_irq_disable();
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+ struct pt_regs *regs = args->regs;
+
+ if (kgdb_handle_exception(1, args->signr, cmd, regs))
+ return NOTIFY_DONE;
+ return NOTIFY_STOP;
+}
+
+static int
+kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+ unsigned long flags;
+ int ret;
+
+ local_irq_save(flags);
+ ret = __kgdb_notify(ptr, cmd);
+ local_irq_restore(flags);
+
+ return ret;
+}
+
+static struct notifier_block kgdb_notifier = {
+ .notifier_call = kgdb_notify,
+ /*
+ * Want to be lowest priority
+ */
+ .priority = -INT_MAX,
+};
+
+/*
+ * kgdb_arch_init - Perform any architecture specific initalization.
+ * This function will handle the initalization of any architecture
+ * specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+ int ret = register_die_notifier(&kgdb_notifier);
+
+ if (ret != 0)
+ return ret;
+
+ register_break_hook(&kgdb_brkpt_hook);
+ register_break_hook(&kgdb_compiled_brkpt_hook);
+ register_step_hook(&kgdb_step_hook);
+ return 0;
+}
+
+/*
+ * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ * This function will handle the uninitalization of any architecture
+ * specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+ unregister_break_hook(&kgdb_brkpt_hook);
+ unregister_break_hook(&kgdb_compiled_brkpt_hook);
+ unregister_step_hook(&kgdb_step_hook);
+ unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * ARM instructions are always in LE.
+ * Break instruction is encoded in LE format
+ */
+struct kgdb_arch arch_kgdb_ops = {
+ .gdb_bpt_instr = {
+ KGDB_DYN_BRK_INS_BYTE0,
+ KGDB_DYN_BRK_INS_BYTE1,
+ KGDB_DYN_BRK_INS_BYTE2,
+ KGDB_DYN_BRK_INS_BYTE3,
+ }
+};
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 8b69ecb..7787208 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -27,6 +27,9 @@
*
* See Documentation/arm/kernel_user_helpers.txt for formal definitions.
*/
+
+#include <asm/unistd32.h>
+
.align 5
.globl __kuser_helper_start
__kuser_helper_start:
@@ -35,33 +38,32 @@
.inst 0xe92d00f0 // push {r4, r5, r6, r7}
.inst 0xe1c040d0 // ldrd r4, r5, [r0]
.inst 0xe1c160d0 // ldrd r6, r7, [r1]
- .inst 0xf57ff05f // dmb sy
.inst 0xe1b20f9f // 1: ldrexd r0, r1, [r2]
.inst 0xe0303004 // eors r3, r0, r4
.inst 0x00313005 // eoreqs r3, r1, r5
- .inst 0x01a23f96 // strexdeq r3, r6, [r2]
+ .inst 0x01a23e96 // stlexdeq r3, r6, [r2]
.inst 0x03330001 // teqeq r3, #1
.inst 0x0afffff9 // beq 1b
- .inst 0xf57ff05f // dmb sy
+ .inst 0xf57ff05b // dmb ish
.inst 0xe2730000 // rsbs r0, r3, #0
.inst 0xe8bd00f0 // pop {r4, r5, r6, r7}
.inst 0xe12fff1e // bx lr
.align 5
__kuser_memory_barrier: // 0xffff0fa0
- .inst 0xf57ff05f // dmb sy
+ .inst 0xf57ff05b // dmb ish
.inst 0xe12fff1e // bx lr
.align 5
__kuser_cmpxchg: // 0xffff0fc0
- .inst 0xf57ff05f // dmb sy
.inst 0xe1923f9f // 1: ldrex r3, [r2]
.inst 0xe0533000 // subs r3, r3, r0
- .inst 0x01823f91 // strexeq r3, r1, [r2]
+ .inst 0x01823e91 // stlexeq r3, r1, [r2]
.inst 0x03330001 // teqeq r3, #1
.inst 0x0afffffa // beq 1b
+ .inst 0xf57ff05b // dmb ish
.inst 0xe2730000 // rsbs r0, r3, #0
- .inst 0xeaffffef // b <__kuser_memory_barrier>
+ .inst 0xe12fff1e // bx lr
.align 5
__kuser_get_tls: // 0xffff0fe0
@@ -75,3 +77,42 @@
.word ((__kuser_helper_end - __kuser_helper_start) >> 5)
.globl __kuser_helper_end
__kuser_helper_end:
+
+/*
+ * AArch32 sigreturn code
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+ .globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+ /*
+ * ARM Code
+ */
+ .byte __NR_compat_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_sigreturn
+ .byte __NR_compat_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_sigreturn
+
+ /*
+ * Thumb code
+ */
+ .byte __NR_compat_sigreturn, 0x27 // svc #__NR_compat_sigreturn
+ .byte __NR_compat_sigreturn, 0xdf // mov r7, #__NR_compat_sigreturn
+
+ /*
+ * ARM code
+ */
+ .byte __NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_rt_sigreturn
+ .byte __NR_compat_rt_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_rt_sigreturn
+
+ /*
+ * Thumb code
+ */
+ .byte __NR_compat_rt_sigreturn, 0x27 // svc #__NR_compat_rt_sigreturn
+ .byte __NR_compat_rt_sigreturn, 0xdf // mov r7, #__NR_compat_rt_sigreturn
+
+ .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index ca0e3d5..df08a6e 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -25,6 +25,10 @@
#include <linux/mm.h>
#include <linux/moduleloader.h>
#include <linux/vmalloc.h>
+#include <asm/insn.h>
+
+#define AARCH64_INSN_IMM_MOVNZ AARCH64_INSN_IMM_MAX
+#define AARCH64_INSN_IMM_MOVK AARCH64_INSN_IMM_16
void *module_alloc(unsigned long size)
{
@@ -94,25 +98,18 @@
return 0;
}
-enum aarch64_imm_type {
- INSN_IMM_MOVNZ,
- INSN_IMM_MOVK,
- INSN_IMM_ADR,
- INSN_IMM_26,
- INSN_IMM_19,
- INSN_IMM_16,
- INSN_IMM_14,
- INSN_IMM_12,
- INSN_IMM_9,
-};
-
-static u32 encode_insn_immediate(enum aarch64_imm_type type, u32 insn, u64 imm)
+static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
+ int lsb, enum aarch64_insn_imm_type imm_type)
{
- u32 immlo, immhi, lomask, himask, mask;
- int shift;
+ u64 imm, limit = 0;
+ s64 sval;
+ u32 insn = le32_to_cpu(*(u32 *)place);
- switch (type) {
- case INSN_IMM_MOVNZ:
+ sval = do_reloc(op, place, val);
+ sval >>= lsb;
+ imm = sval & 0xffff;
+
+ if (imm_type == AARCH64_INSN_IMM_MOVNZ) {
/*
* For signed MOVW relocations, we have to manipulate the
* instruction encoding depending on whether or not the
@@ -131,70 +128,12 @@
*/
imm = ~imm;
}
- case INSN_IMM_MOVK:
- mask = BIT(16) - 1;
- shift = 5;
- break;
- case INSN_IMM_ADR:
- lomask = 0x3;
- himask = 0x7ffff;
- immlo = imm & lomask;
- imm >>= 2;
- immhi = imm & himask;
- imm = (immlo << 24) | (immhi);
- mask = (lomask << 24) | (himask);
- shift = 5;
- break;
- case INSN_IMM_26:
- mask = BIT(26) - 1;
- shift = 0;
- break;
- case INSN_IMM_19:
- mask = BIT(19) - 1;
- shift = 5;
- break;
- case INSN_IMM_16:
- mask = BIT(16) - 1;
- shift = 5;
- break;
- case INSN_IMM_14:
- mask = BIT(14) - 1;
- shift = 5;
- break;
- case INSN_IMM_12:
- mask = BIT(12) - 1;
- shift = 10;
- break;
- case INSN_IMM_9:
- mask = BIT(9) - 1;
- shift = 12;
- break;
- default:
- pr_err("encode_insn_immediate: unknown immediate encoding %d\n",
- type);
- return 0;
+ imm_type = AARCH64_INSN_IMM_MOVK;
}
- /* Update the immediate field. */
- insn &= ~(mask << shift);
- insn |= (imm & mask) << shift;
-
- return insn;
-}
-
-static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
- int lsb, enum aarch64_imm_type imm_type)
-{
- u64 imm, limit = 0;
- s64 sval;
- u32 insn = *(u32 *)place;
-
- sval = do_reloc(op, place, val);
- sval >>= lsb;
- imm = sval & 0xffff;
-
/* Update the instruction with the new encoding. */
- *(u32 *)place = encode_insn_immediate(imm_type, insn, imm);
+ insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+ *(u32 *)place = cpu_to_le32(insn);
/* Shift out the immediate field. */
sval >>= 16;
@@ -203,9 +142,9 @@
* For unsigned immediates, the overflow check is straightforward.
* For signed immediates, the sign bit is actually the bit past the
* most significant bit of the field.
- * The INSN_IMM_16 immediate type is unsigned.
+ * The AARCH64_INSN_IMM_16 immediate type is unsigned.
*/
- if (imm_type != INSN_IMM_16) {
+ if (imm_type != AARCH64_INSN_IMM_16) {
sval++;
limit++;
}
@@ -218,11 +157,11 @@
}
static int reloc_insn_imm(enum aarch64_reloc_op op, void *place, u64 val,
- int lsb, int len, enum aarch64_imm_type imm_type)
+ int lsb, int len, enum aarch64_insn_imm_type imm_type)
{
u64 imm, imm_mask;
s64 sval;
- u32 insn = *(u32 *)place;
+ u32 insn = le32_to_cpu(*(u32 *)place);
/* Calculate the relocation value. */
sval = do_reloc(op, place, val);
@@ -233,7 +172,8 @@
imm = sval & imm_mask;
/* Update the instruction's immediate field. */
- *(u32 *)place = encode_insn_immediate(imm_type, insn, imm);
+ insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+ *(u32 *)place = cpu_to_le32(insn);
/*
* Extract the upper value bits (including the sign bit) and
@@ -315,125 +255,125 @@
overflow_check = false;
case R_AARCH64_MOVW_UABS_G0:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
- INSN_IMM_16);
+ AARCH64_INSN_IMM_16);
break;
case R_AARCH64_MOVW_UABS_G1_NC:
overflow_check = false;
case R_AARCH64_MOVW_UABS_G1:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
- INSN_IMM_16);
+ AARCH64_INSN_IMM_16);
break;
case R_AARCH64_MOVW_UABS_G2_NC:
overflow_check = false;
case R_AARCH64_MOVW_UABS_G2:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
- INSN_IMM_16);
+ AARCH64_INSN_IMM_16);
break;
case R_AARCH64_MOVW_UABS_G3:
/* We're using the top bits so we can't overflow. */
overflow_check = false;
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
- INSN_IMM_16);
+ AARCH64_INSN_IMM_16);
break;
case R_AARCH64_MOVW_SABS_G0:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_SABS_G1:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_SABS_G2:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_PREL_G0_NC:
overflow_check = false;
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
- INSN_IMM_MOVK);
+ AARCH64_INSN_IMM_MOVK);
break;
case R_AARCH64_MOVW_PREL_G0:
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_PREL_G1_NC:
overflow_check = false;
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
- INSN_IMM_MOVK);
+ AARCH64_INSN_IMM_MOVK);
break;
case R_AARCH64_MOVW_PREL_G1:
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_PREL_G2_NC:
overflow_check = false;
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
- INSN_IMM_MOVK);
+ AARCH64_INSN_IMM_MOVK);
break;
case R_AARCH64_MOVW_PREL_G2:
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
case R_AARCH64_MOVW_PREL_G3:
/* We're using the top bits so we can't overflow. */
overflow_check = false;
ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 48,
- INSN_IMM_MOVNZ);
+ AARCH64_INSN_IMM_MOVNZ);
break;
/* Immediate instruction relocations. */
case R_AARCH64_LD_PREL_LO19:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
- INSN_IMM_19);
+ AARCH64_INSN_IMM_19);
break;
case R_AARCH64_ADR_PREL_LO21:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
- INSN_IMM_ADR);
+ AARCH64_INSN_IMM_ADR);
break;
case R_AARCH64_ADR_PREL_PG_HI21_NC:
overflow_check = false;
case R_AARCH64_ADR_PREL_PG_HI21:
ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
- INSN_IMM_ADR);
+ AARCH64_INSN_IMM_ADR);
break;
case R_AARCH64_ADD_ABS_LO12_NC:
case R_AARCH64_LDST8_ABS_LO12_NC:
overflow_check = false;
ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 0, 12,
- INSN_IMM_12);
+ AARCH64_INSN_IMM_12);
break;
case R_AARCH64_LDST16_ABS_LO12_NC:
overflow_check = false;
ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 1, 11,
- INSN_IMM_12);
+ AARCH64_INSN_IMM_12);
break;
case R_AARCH64_LDST32_ABS_LO12_NC:
overflow_check = false;
ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 2, 10,
- INSN_IMM_12);
+ AARCH64_INSN_IMM_12);
break;
case R_AARCH64_LDST64_ABS_LO12_NC:
overflow_check = false;
ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 3, 9,
- INSN_IMM_12);
+ AARCH64_INSN_IMM_12);
break;
case R_AARCH64_LDST128_ABS_LO12_NC:
overflow_check = false;
ovf = reloc_insn_imm(RELOC_OP_ABS, loc, val, 4, 8,
- INSN_IMM_12);
+ AARCH64_INSN_IMM_12);
break;
case R_AARCH64_TSTBR14:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 14,
- INSN_IMM_14);
+ AARCH64_INSN_IMM_14);
break;
case R_AARCH64_CONDBR19:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 19,
- INSN_IMM_19);
+ AARCH64_INSN_IMM_19);
break;
case R_AARCH64_JUMP26:
case R_AARCH64_CALL26:
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26,
- INSN_IMM_26);
+ AARCH64_INSN_IMM_26);
break;
default:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 9ba33c4..dfcd8fa 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -22,6 +22,7 @@
#include <linux/bitmap.h>
#include <linux/interrupt.h>
+#include <linux/irq.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/perf_event.h>
@@ -107,7 +108,12 @@
static int
armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
{
- int mapping = (*event_map)[config];
+ int mapping;
+
+ if (config >= PERF_COUNT_HW_MAX)
+ return -EINVAL;
+
+ mapping = (*event_map)[config];
return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
}
@@ -317,7 +323,13 @@
struct hw_perf_event fake_event = event->hw;
struct pmu *leader_pmu = event->group_leader->pmu;
- if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+ if (is_software_event(event))
+ return 1;
+
+ if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+ return 1;
+
+ if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
return 1;
return armpmu->get_event_idx(hw_events, &fake_event) >= 0;
@@ -352,26 +364,53 @@
}
static void
+armpmu_disable_percpu_irq(void *data)
+{
+ unsigned int irq = *(unsigned int *)data;
+ disable_percpu_irq(irq);
+}
+
+static void
armpmu_release_hardware(struct arm_pmu *armpmu)
{
- int i, irq, irqs;
+ int irq;
+ unsigned int i, irqs;
struct platform_device *pmu_device = armpmu->plat_device;
irqs = min(pmu_device->num_resources, num_possible_cpus());
+ if (!irqs)
+ return;
- for (i = 0; i < irqs; ++i) {
- if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
- continue;
- irq = platform_get_irq(pmu_device, i);
- if (irq >= 0)
- free_irq(irq, armpmu);
+ irq = platform_get_irq(pmu_device, 0);
+ if (irq <= 0)
+ return;
+
+ if (irq_is_percpu(irq)) {
+ on_each_cpu(armpmu_disable_percpu_irq, &irq, 1);
+ free_percpu_irq(irq, &cpu_hw_events);
+ } else {
+ for (i = 0; i < irqs; ++i) {
+ if (!cpumask_test_and_clear_cpu(i, &armpmu->active_irqs))
+ continue;
+ irq = platform_get_irq(pmu_device, i);
+ if (irq > 0)
+ free_irq(irq, armpmu);
+ }
}
}
+static void
+armpmu_enable_percpu_irq(void *data)
+{
+ unsigned int irq = *(unsigned int *)data;
+ enable_percpu_irq(irq, IRQ_TYPE_NONE);
+}
+
static int
armpmu_reserve_hardware(struct arm_pmu *armpmu)
{
- int i, err, irq, irqs;
+ int err, irq;
+ unsigned int i, irqs;
struct platform_device *pmu_device = armpmu->plat_device;
if (!pmu_device) {
@@ -380,39 +419,59 @@
}
irqs = min(pmu_device->num_resources, num_possible_cpus());
- if (irqs < 1) {
+ if (!irqs) {
pr_err("no irqs for PMUs defined\n");
return -ENODEV;
}
- for (i = 0; i < irqs; ++i) {
- err = 0;
- irq = platform_get_irq(pmu_device, i);
- if (irq < 0)
- continue;
+ irq = platform_get_irq(pmu_device, 0);
+ if (irq <= 0) {
+ pr_err("failed to get valid irq for PMU device\n");
+ return -ENODEV;
+ }
- /*
- * If we have a single PMU interrupt that we can't shift,
- * assume that we're running on a uniprocessor machine and
- * continue. Otherwise, continue without this interrupt.
- */
- if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
- pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
- irq, i);
- continue;
- }
+ if (irq_is_percpu(irq)) {
+ err = request_percpu_irq(irq, armpmu->handle_irq,
+ "arm-pmu", &cpu_hw_events);
- err = request_irq(irq, armpmu->handle_irq,
- IRQF_NOBALANCING,
- "arm-pmu", armpmu);
if (err) {
- pr_err("unable to request IRQ%d for ARM PMU counters\n",
- irq);
+ pr_err("unable to request percpu IRQ%d for ARM PMU counters\n",
+ irq);
armpmu_release_hardware(armpmu);
return err;
}
- cpumask_set_cpu(i, &armpmu->active_irqs);
+ on_each_cpu(armpmu_enable_percpu_irq, &irq, 1);
+ } else {
+ for (i = 0; i < irqs; ++i) {
+ err = 0;
+ irq = platform_get_irq(pmu_device, i);
+ if (irq <= 0)
+ continue;
+
+ /*
+ * If we have a single PMU interrupt that we can't shift,
+ * assume that we're running on a uniprocessor machine and
+ * continue. Otherwise, continue without this interrupt.
+ */
+ if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+ pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+ irq, i);
+ continue;
+ }
+
+ err = request_irq(irq, armpmu->handle_irq,
+ IRQF_NOBALANCING,
+ "arm-pmu", armpmu);
+ if (err) {
+ pr_err("unable to request IRQ%d for ARM PMU counters\n",
+ irq);
+ armpmu_release_hardware(armpmu);
+ return err;
+ }
+
+ cpumask_set_cpu(i, &armpmu->active_irqs);
+ }
}
return 0;
@@ -773,7 +832,7 @@
/*
* PMXEVTYPER: Event selection reg
*/
-#define ARMV8_EVTYPE_MASK 0xc00000ff /* Mask for writable bits */
+#define ARMV8_EVTYPE_MASK 0xc80000ff /* Mask for writable bits */
#define ARMV8_EVTYPE_EVENT 0xff /* Mask for EVENT bits */
/*
@@ -1288,8 +1347,8 @@
* Callchain handling code.
*/
struct frame_tail {
- struct frame_tail __user *fp;
- unsigned long lr;
+ struct frame_tail __user *fp;
+ unsigned long lr;
} __attribute__((packed));
/*
@@ -1326,22 +1385,84 @@
return buftail.fp;
}
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+ compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */
+ u32 sp;
+ u32 lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+ struct perf_callchain_entry *entry)
+{
+ struct compat_frame_tail buftail;
+ unsigned long err;
+
+ /* Also check accessibility of one struct frame_tail beyond */
+ if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+ return NULL;
+
+ pagefault_disable();
+ err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+ pagefault_enable();
+
+ if (err)
+ return NULL;
+
+ perf_callchain_store(entry, buftail.lr);
+
+ /*
+ * Frame pointers should strictly progress back up the stack
+ * (towards higher addresses).
+ */
+ if (tail + 1 >= (struct compat_frame_tail __user *)
+ compat_ptr(buftail.fp))
+ return NULL;
+
+ return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
void perf_callchain_user(struct perf_callchain_entry *entry,
struct pt_regs *regs)
{
- struct frame_tail __user *tail;
-
if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
/* We don't support guest os callchain now */
return;
}
perf_callchain_store(entry, regs->pc);
- tail = (struct frame_tail __user *)regs->regs[29];
- while (entry->nr < PERF_MAX_STACK_DEPTH &&
- tail && !((unsigned long)tail & 0xf))
- tail = user_backtrace(tail, entry);
+ if (!compat_user_mode(regs)) {
+ /* AARCH64 mode */
+ struct frame_tail __user *tail;
+
+ tail = (struct frame_tail __user *)regs->regs[29];
+
+ while (entry->nr < PERF_MAX_STACK_DEPTH &&
+ tail && !((unsigned long)tail & 0xf))
+ tail = user_backtrace(tail, entry);
+ } else {
+#ifdef CONFIG_COMPAT
+ /* AARCH32 compat mode */
+ struct compat_frame_tail __user *tail;
+
+ tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+ while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+ tail && !((unsigned long)tail & 0x3))
+ tail = compat_user_backtrace(tail, entry);
+#endif
+ }
}
/*
@@ -1369,6 +1490,7 @@
frame.fp = regs->regs[29];
frame.sp = regs->sp;
frame.pc = regs->pc;
+
walk_stackframe(&frame, callchain_trace, entry);
}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
new file mode 100644
index 0000000..422ebd6
--- /dev/null
+++ b/arch/arm64/kernel/perf_regs.c
@@ -0,0 +1,46 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+
+#include <asm/compat.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+ return 0;
+
+ /*
+ * Compat (i.e. 32 bit) mode:
+ * - PC has been set in the pt_regs struct in kernel_entry,
+ * - Handle SP and LR here.
+ */
+ if (compat_user_mode(regs)) {
+ if ((u32)idx == PERF_REG_ARM64_SP)
+ return regs->compat_sp;
+ if ((u32)idx == PERF_REG_ARM64_LR)
+ return regs->compat_lr;
+ }
+
+ return regs->regs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM64_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (is_compat_thread(task_thread_info(task)))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 46f02c3..a82af49 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -20,6 +20,7 @@
#include <stdarg.h>
+#include <linux/compat.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/kernel.h>
@@ -33,6 +34,7 @@
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <linux/cpu.h>
+#include <linux/cpuidle.h>
#include <linux/elfcore.h>
#include <linux/pm.h>
#include <linux/tick.h>
@@ -50,29 +52,18 @@
#include <asm/processor.h>
#include <asm/stacktrace.h>
-static void setup_restart(void)
-{
- /*
- * Tell the mm system that we are going to reboot -
- * we may need it to insert some 1:1 mappings so that
- * soft boot works.
- */
- setup_mm_for_reboot();
-
- /* Clean and invalidate caches */
- flush_cache_all();
-
- /* Turn D-cache off */
- cpu_cache_off();
-
- /* Push out any further dirty data, and ensure cache is empty */
- flush_cache_all();
-}
+#ifdef CONFIG_CC_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
void soft_restart(unsigned long addr)
{
- setup_restart();
- cpu_reset(addr);
+ setup_mm_for_reboot();
+ cpu_soft_restart(virt_to_phys(cpu_reset), addr);
+ /* Should never get here */
+ BUG();
}
/*
@@ -98,10 +89,19 @@
* This should do all the clock switching and wait for interrupt
* tricks
*/
- cpu_do_idle();
- local_irq_enable();
+ if (cpuidle_idle_call()) {
+ cpu_do_idle();
+ local_irq_enable();
+ }
}
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+ cpu_die();
+}
+#endif
+
void machine_shutdown(void)
{
#ifdef CONFIG_SMP
@@ -143,15 +143,26 @@
void __show_regs(struct pt_regs *regs)
{
- int i;
+ int i, top_reg;
+ u64 lr, sp;
+
+ if (compat_user_mode(regs)) {
+ lr = regs->compat_lr;
+ sp = regs->compat_sp;
+ top_reg = 12;
+ } else {
+ lr = regs->regs[30];
+ sp = regs->sp;
+ top_reg = 29;
+ }
show_regs_print_info(KERN_DEFAULT);
print_symbol("PC is at %s\n", instruction_pointer(regs));
- print_symbol("LR is at %s\n", regs->regs[30]);
+ print_symbol("LR is at %s\n", lr);
printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
- regs->pc, regs->regs[30], regs->pstate);
- printk("sp : %016llx\n", regs->sp);
- for (i = 29; i >= 0; i--) {
+ regs->pc, lr, regs->pstate);
+ printk("sp : %016llx\n", sp);
+ for (i = top_reg; i >= 0; i--) {
printk("x%-2d: %016llx ", i, regs->regs[i]);
if (i % 2 == 0)
printk("\n");
@@ -172,9 +183,27 @@
{
}
+static void tls_thread_flush(void)
+{
+ asm ("msr tpidr_el0, xzr");
+
+ if (is_compat_task()) {
+ current->thread.tp_value = 0;
+
+ /*
+ * We need to ensure ordering between the shadow state and the
+ * hardware state, so that we don't corrupt the hardware state
+ * with a stale shadow state during context switch.
+ */
+ barrier();
+ asm ("msr tpidrro_el0, xzr");
+ }
+}
+
void flush_thread(void)
{
fpsimd_flush_thread();
+ tls_thread_flush();
flush_ptrace_hw_breakpoint(current);
}
@@ -279,7 +308,7 @@
* Complete any pending TLB or cache maintenance on this CPU in case
* the thread migrates to a different CPU.
*/
- dsb();
+ dsb(ish);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
@@ -290,6 +319,7 @@
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
+ unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
@@ -297,9 +327,11 @@
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
frame.pc = thread_saved_pc(p);
+ stack_page = (unsigned long)task_stack_page(p);
do {
- int ret = unwind_frame(&frame);
- if (ret < 0)
+ if (frame.sp < stack_page ||
+ frame.sp >= stack_page + THREAD_SIZE ||
+ unwind_frame(&frame))
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S
new file mode 100644
index 0000000..cf83e61
--- /dev/null
+++ b/arch/arm64/kernel/psci-call.S
@@ -0,0 +1,28 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2015 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/linkage.h>
+
+/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_hvc)
+ hvc #0
+ ret
+ENDPROC(__invoke_psci_fn_hvc)
+
+/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
+ENTRY(__invoke_psci_fn_smc)
+ smc #0
+ ret
+ENDPROC(__invoke_psci_fn_smc)
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 14f73c4..fc457d0 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -15,97 +15,109 @@
#define pr_fmt(fmt) "psci: " fmt
+#include <linux/cpuidle.h>
#include <linux/init.h>
#include <linux/of.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <linux/reboot.h>
+#include <linux/pm.h>
+#include <linux/delay.h>
+#include <uapi/linux/psci.h>
#include <asm/compiler.h>
+#include <asm/cpu_ops.h>
#include <asm/errno.h>
#include <asm/psci.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+#include <asm/system_misc.h>
-struct psci_operations psci_ops;
+#define PSCI_POWER_STATE_TYPE_STANDBY 0
+#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1
+
+struct psci_power_state {
+ u16 id;
+ u8 type;
+ u8 affinity_level;
+};
+
+struct psci_operations {
+ int (*cpu_suspend)(struct psci_power_state state,
+ unsigned long entry_point);
+ int (*cpu_off)(struct psci_power_state state);
+ int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
+ int (*migrate)(unsigned long cpuid);
+ int (*affinity_info)(unsigned long target_affinity,
+ unsigned long lowest_affinity_level);
+ int (*migrate_info_type)(void);
+};
+
+static struct psci_operations psci_ops;
static int (*invoke_psci_fn)(u64, u64, u64, u64);
+typedef int (*psci_initcall_t)(const struct device_node *);
+
+asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
+asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
enum psci_function {
PSCI_FN_CPU_SUSPEND,
PSCI_FN_CPU_ON,
PSCI_FN_CPU_OFF,
PSCI_FN_MIGRATE,
+ PSCI_FN_AFFINITY_INFO,
+ PSCI_FN_MIGRATE_INFO_TYPE,
PSCI_FN_MAX,
};
-static u32 psci_function_id[PSCI_FN_MAX];
+static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
-#define PSCI_RET_SUCCESS 0
-#define PSCI_RET_EOPNOTSUPP -1
-#define PSCI_RET_EINVAL -2
-#define PSCI_RET_EPERM -3
+static u32 psci_function_id[PSCI_FN_MAX];
static int psci_to_linux_errno(int errno)
{
switch (errno) {
case PSCI_RET_SUCCESS:
return 0;
- case PSCI_RET_EOPNOTSUPP:
+ case PSCI_RET_NOT_SUPPORTED:
return -EOPNOTSUPP;
- case PSCI_RET_EINVAL:
+ case PSCI_RET_INVALID_PARAMS:
return -EINVAL;
- case PSCI_RET_EPERM:
+ case PSCI_RET_DENIED:
return -EPERM;
};
return -EINVAL;
}
-#define PSCI_POWER_STATE_ID_MASK 0xffff
-#define PSCI_POWER_STATE_ID_SHIFT 0
-#define PSCI_POWER_STATE_TYPE_MASK 0x1
-#define PSCI_POWER_STATE_TYPE_SHIFT 16
-#define PSCI_POWER_STATE_AFFL_MASK 0x3
-#define PSCI_POWER_STATE_AFFL_SHIFT 24
-
static u32 psci_power_state_pack(struct psci_power_state state)
{
- return ((state.id & PSCI_POWER_STATE_ID_MASK)
- << PSCI_POWER_STATE_ID_SHIFT) |
- ((state.type & PSCI_POWER_STATE_TYPE_MASK)
- << PSCI_POWER_STATE_TYPE_SHIFT) |
- ((state.affinity_level & PSCI_POWER_STATE_AFFL_MASK)
- << PSCI_POWER_STATE_AFFL_SHIFT);
+ return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
+ & PSCI_0_2_POWER_STATE_ID_MASK) |
+ ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+ & PSCI_0_2_POWER_STATE_TYPE_MASK) |
+ ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+ & PSCI_0_2_POWER_STATE_AFFL_MASK);
}
-/*
- * The following two functions are invoked via the invoke_psci_fn pointer
- * and will not be inlined, allowing us to piggyback on the AAPCS.
- */
-static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1,
- u64 arg2)
+static void psci_power_state_unpack(u32 power_state,
+ struct psci_power_state *state)
{
- asm volatile(
- __asmeq("%0", "x0")
- __asmeq("%1", "x1")
- __asmeq("%2", "x2")
- __asmeq("%3", "x3")
- "hvc #0\n"
- : "+r" (function_id)
- : "r" (arg0), "r" (arg1), "r" (arg2));
-
- return function_id;
+ state->id = (power_state >> PSCI_0_2_POWER_STATE_ID_SHIFT)
+ & PSCI_0_2_POWER_STATE_ID_MASK;
+ state->type = (power_state >> PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+ & PSCI_0_2_POWER_STATE_TYPE_MASK;
+ state->affinity_level = (power_state >> PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+ & PSCI_0_2_POWER_STATE_AFFL_MASK;
}
-static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1,
- u64 arg2)
+static int psci_get_version(void)
{
- asm volatile(
- __asmeq("%0", "x0")
- __asmeq("%1", "x1")
- __asmeq("%2", "x2")
- __asmeq("%3", "x3")
- "smc #0\n"
- : "+r" (function_id)
- : "r" (arg0), "r" (arg1), "r" (arg2));
+ int err;
- return function_id;
+ err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
+ return err;
}
static int psci_cpu_suspend(struct psci_power_state state,
@@ -151,28 +163,36 @@
return psci_to_linux_errno(err);
}
-static const struct of_device_id psci_of_match[] __initconst = {
- { .compatible = "arm,psci", },
- {},
-};
-
-int __init psci_init(void)
+static int psci_affinity_info(unsigned long target_affinity,
+ unsigned long lowest_affinity_level)
{
- struct device_node *np;
+ int err;
+ u32 fn;
+
+ fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
+ err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
+ return err;
+}
+
+static int psci_migrate_info_type(void)
+{
+ int err;
+ u32 fn;
+
+ fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
+ err = invoke_psci_fn(fn, 0, 0, 0);
+ return err;
+}
+
+static int get_set_conduit_method(struct device_node *np)
+{
const char *method;
- u32 id;
- int err = 0;
- np = of_find_matching_node(NULL, psci_of_match);
- if (!np)
- return -ENODEV;
-
- pr_info("probing function IDs from device-tree\n");
+ pr_info("probing for conduit method from DT.\n");
if (of_property_read_string(np, "method", &method)) {
- pr_warning("missing \"method\" property\n");
- err = -ENXIO;
- goto out_put_node;
+ pr_warn("missing \"method\" property\n");
+ return -ENXIO;
}
if (!strcmp("hvc", method)) {
@@ -180,10 +200,98 @@
} else if (!strcmp("smc", method)) {
invoke_psci_fn = __invoke_psci_fn_smc;
} else {
- pr_warning("invalid \"method\" property: %s\n", method);
- err = -EINVAL;
- goto out_put_node;
+ pr_warn("invalid \"method\" property: %s\n", method);
+ return -EINVAL;
}
+ return 0;
+}
+
+static void psci_sys_reset(char str, const char *cmd)
+{
+ invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+}
+
+static void psci_sys_poweroff(void)
+{
+ invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
+}
+
+/*
+ * PSCI Function IDs for v0.2+ are well defined so use
+ * standard values.
+ */
+static int __init psci_0_2_init(struct device_node *np)
+{
+ int err, ver;
+
+ err = get_set_conduit_method(np);
+
+ if (err)
+ goto out_put_node;
+
+ ver = psci_get_version();
+
+ if (ver == PSCI_RET_NOT_SUPPORTED) {
+ /* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
+ pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
+ err = -EOPNOTSUPP;
+ goto out_put_node;
+ } else {
+ pr_info("PSCIv%d.%d detected in firmware.\n",
+ PSCI_VERSION_MAJOR(ver),
+ PSCI_VERSION_MINOR(ver));
+
+ if (PSCI_VERSION_MAJOR(ver) == 0 &&
+ PSCI_VERSION_MINOR(ver) < 2) {
+ err = -EINVAL;
+ pr_err("Conflicting PSCI version detected.\n");
+ goto out_put_node;
+ }
+ }
+
+ pr_info("Using standard PSCI v0.2 function IDs\n");
+ psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN64_CPU_SUSPEND;
+ psci_ops.cpu_suspend = psci_cpu_suspend;
+
+ psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
+ psci_ops.cpu_off = psci_cpu_off;
+
+ psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN64_CPU_ON;
+ psci_ops.cpu_on = psci_cpu_on;
+
+ psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
+ psci_ops.migrate = psci_migrate;
+
+ psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO;
+ psci_ops.affinity_info = psci_affinity_info;
+
+ psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
+ PSCI_0_2_FN_MIGRATE_INFO_TYPE;
+ psci_ops.migrate_info_type = psci_migrate_info_type;
+
+ arm_pm_restart = psci_sys_reset;
+
+ pm_power_off = psci_sys_poweroff;
+
+out_put_node:
+ of_node_put(np);
+ return err;
+}
+
+/*
+ * PSCI < v0.2 get PSCI Function IDs via DT.
+ */
+static int __init psci_0_1_init(struct device_node *np)
+{
+ u32 id;
+ int err;
+
+ err = get_set_conduit_method(np);
+
+ if (err)
+ goto out_put_node;
+
+ pr_info("Using PSCI v0.1 Function IDs from DT\n");
if (!of_property_read_u32(np, "cpu_suspend", &id)) {
psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
@@ -209,3 +317,136 @@
of_node_put(np);
return err;
}
+
+static const struct of_device_id psci_of_match[] __initconst = {
+ { .compatible = "arm,psci", .data = psci_0_1_init},
+ { .compatible = "arm,psci-0.2", .data = psci_0_2_init},
+ {},
+};
+
+int __init psci_init(void)
+{
+ struct device_node *np;
+ const struct of_device_id *matched_np;
+ psci_initcall_t init_fn;
+
+ np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
+
+ if (!np)
+ return -ENODEV;
+
+ init_fn = (psci_initcall_t)matched_np->data;
+ return init_fn(np);
+}
+
+#ifdef CONFIG_SMP
+
+static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+{
+ return 0;
+}
+
+static int __init cpu_psci_cpu_prepare(unsigned int cpu)
+{
+ if (!psci_ops.cpu_on) {
+ pr_err("no cpu_on method, not booting CPU%d\n", cpu);
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static int cpu_psci_cpu_boot(unsigned int cpu)
+{
+ int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
+ if (err)
+ pr_err("failed to boot CPU%d (%d)\n", cpu, err);
+
+ return err;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpu_psci_cpu_disable(unsigned int cpu)
+{
+ /* Fail early if we don't have CPU_OFF support */
+ if (!psci_ops.cpu_off)
+ return -EOPNOTSUPP;
+ return 0;
+}
+
+static void cpu_psci_cpu_die(unsigned int cpu)
+{
+ int ret;
+ /*
+ * There are no known implementations of PSCI actually using the
+ * power state field, pass a sensible default for now.
+ */
+ struct psci_power_state state = {
+ .type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
+ };
+
+ ret = psci_ops.cpu_off(state);
+
+ pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
+}
+
+static int cpu_psci_cpu_kill(unsigned int cpu)
+{
+ int err, i;
+
+ if (!psci_ops.affinity_info)
+ return 1;
+ /*
+ * cpu_kill could race with cpu_die and we can
+ * potentially end up declaring this cpu undead
+ * while it is dying. So, try again a few times.
+ */
+
+ for (i = 0; i < 10; i++) {
+ err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
+ if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
+ pr_info("CPU%d killed.\n", cpu);
+ return 1;
+ }
+
+ msleep(10);
+ pr_info("Retrying again to check for CPU kill\n");
+ }
+
+ pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
+ cpu, err);
+ /* Make op_cpu_kill() fail. */
+ return 0;
+}
+#endif
+#endif
+
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+static int cpu_psci_cpu_suspend(unsigned long index)
+{
+ struct psci_power_state *state = __get_cpu_var(psci_power_state);
+
+ if (!state)
+ return -EOPNOTSUPP;
+
+ return psci_ops.cpu_suspend(state[index], virt_to_phys(cpu_resume));
+}
+#endif
+
+const struct cpu_operations cpu_psci_ops = {
+ .name = "psci",
+#ifdef CONFIG_SMP
+ .cpu_init = cpu_psci_cpu_init,
+ .cpu_prepare = cpu_psci_cpu_prepare,
+ .cpu_boot = cpu_psci_cpu_boot,
+#ifdef CONFIG_HOTPLUG_CPU
+ .cpu_disable = cpu_psci_cpu_disable,
+ .cpu_die = cpu_psci_cpu_die,
+ .cpu_kill = cpu_psci_cpu_kill,
+#endif
+#endif
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+ .cpu_suspend = cpu_psci_cpu_suspend,
+#endif
+};
+
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6e1e77f..5cafe0e 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,6 +19,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
@@ -41,6 +42,9 @@
#include <asm/traps.h>
#include <asm/system_misc.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
/*
* TODO: does not yet catch signals sent when the child dies.
* in exit.c or in signal.c.
@@ -53,28 +57,6 @@
{
}
-/*
- * Handle hitting a breakpoint.
- */
-static int ptrace_break(struct pt_regs *regs)
-{
- siginfo_t info = {
- .si_signo = SIGTRAP,
- .si_errno = 0,
- .si_code = TRAP_BRKPT,
- .si_addr = (void __user *)instruction_pointer(regs),
- };
-
- force_sig_info(SIGTRAP, &info, current);
- return 0;
-}
-
-static int arm64_break_trap(unsigned long addr, unsigned int esr,
- struct pt_regs *regs)
-{
- return ptrace_break(regs);
-}
-
#ifdef CONFIG_HAVE_HW_BREAKPOINT
/*
* Handle hitting a HW-breakpoint.
@@ -103,7 +85,8 @@
break;
}
}
- for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) {
+
+ for (i = 0; i < ARM_MAX_WRP; ++i) {
if (current->thread.debug.hbp_watch[i] == bp) {
info.si_errno = -((i << 1) + 1);
break;
@@ -236,31 +219,29 @@
{
int err, len, type, disabled = !ctrl.enabled;
- if (disabled) {
- len = 0;
- type = HW_BREAKPOINT_EMPTY;
- } else {
- err = arch_bp_generic_fields(ctrl, &len, &type);
- if (err)
- return err;
+ attr->disabled = disabled;
+ if (disabled)
+ return 0;
- switch (note_type) {
- case NT_ARM_HW_BREAK:
- if ((type & HW_BREAKPOINT_X) != type)
- return -EINVAL;
- break;
- case NT_ARM_HW_WATCH:
- if ((type & HW_BREAKPOINT_RW) != type)
- return -EINVAL;
- break;
- default:
+ err = arch_bp_generic_fields(ctrl, &len, &type);
+ if (err)
+ return err;
+
+ switch (note_type) {
+ case NT_ARM_HW_BREAK:
+ if ((type & HW_BREAKPOINT_X) != type)
return -EINVAL;
- }
+ break;
+ case NT_ARM_HW_WATCH:
+ if ((type & HW_BREAKPOINT_RW) != type)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
}
attr->bp_len = len;
attr->bp_type = type;
- attr->disabled = disabled;
return 0;
}
@@ -658,28 +639,34 @@
for (i = 0; i < num_regs; ++i) {
unsigned int idx = start + i;
- void *reg;
+ compat_ulong_t reg;
switch (idx) {
case 15:
- reg = (void *)&task_pt_regs(target)->pc;
+ reg = task_pt_regs(target)->pc;
break;
case 16:
- reg = (void *)&task_pt_regs(target)->pstate;
+ reg = task_pt_regs(target)->pstate;
break;
case 17:
- reg = (void *)&task_pt_regs(target)->orig_x0;
+ reg = task_pt_regs(target)->orig_x0;
break;
default:
- reg = (void *)&task_pt_regs(target)->regs[idx];
+ reg = task_pt_regs(target)->regs[idx];
}
- ret = copy_to_user(ubuf, reg, sizeof(compat_ulong_t));
+ if (kbuf) {
+ memcpy(kbuf, ®, sizeof(reg));
+ kbuf += sizeof(reg);
+ } else {
+ ret = copy_to_user(ubuf, ®, sizeof(reg));
+ if (ret) {
+ ret = -EFAULT;
+ break;
+ }
- if (ret)
- break;
- else
- ubuf += sizeof(compat_ulong_t);
+ ubuf += sizeof(reg);
+ }
}
return ret;
@@ -707,28 +694,35 @@
for (i = 0; i < num_regs; ++i) {
unsigned int idx = start + i;
- void *reg;
+ compat_ulong_t reg;
+
+ if (kbuf) {
+ memcpy(®, kbuf, sizeof(reg));
+ kbuf += sizeof(reg);
+ } else {
+ ret = copy_from_user(®, ubuf, sizeof(reg));
+ if (ret) {
+ ret = -EFAULT;
+ break;
+ }
+
+ ubuf += sizeof(reg);
+ }
switch (idx) {
case 15:
- reg = (void *)&newregs.pc;
+ newregs.pc = reg;
break;
case 16:
- reg = (void *)&newregs.pstate;
+ newregs.pstate = reg;
break;
case 17:
- reg = (void *)&newregs.orig_x0;
+ newregs.orig_x0 = reg;
break;
default:
- reg = (void *)&newregs.regs[idx];
+ newregs.regs[idx] = reg;
}
- ret = copy_from_user(reg, ubuf, sizeof(compat_ulong_t));
-
- if (ret)
- goto out;
- else
- ubuf += sizeof(compat_ulong_t);
}
if (valid_user_regs(&newregs.user_regs))
@@ -736,7 +730,6 @@
else
ret = -EINVAL;
-out:
return ret;
}
@@ -817,33 +810,6 @@
.regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets)
};
-int aarch32_break_trap(struct pt_regs *regs)
-{
- unsigned int instr;
- bool bp = false;
- void __user *pc = (void __user *)instruction_pointer(regs);
-
- if (compat_thumb_mode(regs)) {
- /* get 16-bit Thumb instruction */
- get_user(instr, (u16 __user *)pc);
- if (instr == AARCH32_BREAK_THUMB2_LO) {
- /* get second half of 32-bit Thumb-2 instruction */
- get_user(instr, (u16 __user *)(pc + 2));
- bp = instr == AARCH32_BREAK_THUMB2_HI;
- } else {
- bp = instr == AARCH32_BREAK_THUMB;
- }
- } else {
- /* 32-bit ARM instruction */
- get_user(instr, (u32 __user *)pc);
- bp = (instr & ~0xf0000000) == AARCH32_BREAK_ARM;
- }
-
- if (bp)
- return ptrace_break(regs);
- return 1;
-}
-
static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off,
compat_ulong_t __user *ret)
{
@@ -874,6 +840,7 @@
compat_ulong_t val)
{
int ret;
+ mm_segment_t old_fs = get_fs();
if (off & 3 || off >= COMPAT_USER_SZ)
return -EIO;
@@ -881,10 +848,13 @@
if (off >= sizeof(compat_elf_gregset_t))
return 0;
+ set_fs(KERNEL_DS);
ret = copy_regset_from_user(tsk, &user_aarch32_view,
REGSET_COMPAT_GPR, off,
sizeof(compat_ulong_t),
&val);
+ set_fs(old_fs);
+
return ret;
}
@@ -1111,45 +1081,49 @@
return ptrace_request(child, request, addr, data);
}
+enum ptrace_syscall_dir {
+ PTRACE_SYSCALL_ENTER = 0,
+ PTRACE_SYSCALL_EXIT,
+};
-static int __init ptrace_break_init(void)
+static void tracehook_report_syscall(struct pt_regs *regs,
+ enum ptrace_syscall_dir dir)
{
- hook_debug_fault_code(DBG_ESR_EVT_BRK, arm64_break_trap, SIGTRAP,
- TRAP_BRKPT, "ptrace BRK handler");
- return 0;
-}
-core_initcall(ptrace_break_init);
-
-
-asmlinkage int syscall_trace(int dir, struct pt_regs *regs)
-{
+ int regno;
unsigned long saved_reg;
- if (!test_thread_flag(TIF_SYSCALL_TRACE))
- return regs->syscallno;
+ /*
+ * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
+ * used to denote syscall entry/exit:
+ */
+ regno = (is_compat_task() ? 12 : 7);
+ saved_reg = regs->regs[regno];
+ regs->regs[regno] = dir;
- if (is_compat_task()) {
- /* AArch32 uses ip (r12) for scratch */
- saved_reg = regs->regs[12];
- regs->regs[12] = dir;
- } else {
- /*
- * Save X7. X7 is used to denote syscall entry/exit:
- * X7 = 0 -> entry, = 1 -> exit
- */
- saved_reg = regs->regs[7];
- regs->regs[7] = dir;
- }
-
- if (dir)
+ if (dir == PTRACE_SYSCALL_EXIT)
tracehook_report_syscall_exit(regs, 0);
else if (tracehook_report_syscall_entry(regs))
regs->syscallno = ~0UL;
- if (is_compat_task())
- regs->regs[12] = saved_reg;
- else
- regs->regs[7] = saved_reg;
+ regs->regs[regno] = saved_reg;
+}
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_enter(regs, regs->syscallno);
return regs->syscallno;
}
+
+asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ trace_sys_exit(regs, regs_return_value(regs));
+
+ if (test_thread_flag(TIF_SYSCALL_TRACE))
+ tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
new file mode 100644
index 0000000..89102a6
--- /dev/null
+++ b/arch/arm64/kernel/return_address.c
@@ -0,0 +1,55 @@
+/*
+ * arch/arm64/kernel/return_address.c
+ *
+ * Copyright (C) 2013 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/export.h>
+#include <linux/ftrace.h>
+
+#include <asm/stacktrace.h>
+
+struct return_address_data {
+ unsigned int level;
+ void *addr;
+};
+
+static int save_return_addr(struct stackframe *frame, void *d)
+{
+ struct return_address_data *data = d;
+
+ if (!data->level) {
+ data->addr = (void *)frame->pc;
+ return 1;
+ } else {
+ --data->level;
+ return 0;
+ }
+}
+
+void *return_address(unsigned int level)
+{
+ struct return_address_data data;
+ struct stackframe frame;
+ register unsigned long current_sp asm ("sp");
+
+ data.level = level + 2;
+ data.addr = NULL;
+
+ frame.fp = (unsigned long)__builtin_frame_address(0);
+ frame.sp = current_sp;
+ frame.pc = (unsigned long)return_address; /* dummy */
+
+ walk_stackframe(&frame, save_return_addr, &data);
+
+ if (!data.level)
+ return data.addr;
+ else
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index add6ea6..9d704df 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -41,10 +41,14 @@
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/of_platform.h>
+#include <linux/efi.h>
+#include <linux/personality.h>
+#include <asm/fixmap.h>
#include <asm/cputype.h>
#include <asm/elf.h>
#include <asm/cputable.h>
+#include <asm/cpu_ops.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -53,13 +57,25 @@
#include <asm/traps.h>
#include <asm/memblock.h>
#include <asm/psci.h>
+#include <asm/efi.h>
unsigned int processor_id;
EXPORT_SYMBOL(processor_id);
-unsigned int elf_hwcap __read_mostly;
+unsigned long elf_hwcap __read_mostly;
EXPORT_SYMBOL_GPL(elf_hwcap);
+#ifdef CONFIG_COMPAT
+#define COMPAT_ELF_HWCAP_DEFAULT \
+ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\
+ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\
+ COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\
+ COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
+ COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
+unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
+#endif
+
static const char *cpu_name;
static const char *machine_name;
phys_addr_t __fdt_pointer __initdata;
@@ -97,15 +113,108 @@
printk("%s", buf);
}
+struct cpuinfo_arm64 {
+ struct cpu cpu;
+ u32 reg_midr;
+};
+
+static DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
+
+void cpuinfo_store_cpu(void)
+{
+ struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data);
+ info->reg_midr = read_cpuid_id();
+}
+
+void __init smp_setup_processor_id(void)
+{
+ /*
+ * clear __my_cpu_offset on boot CPU to avoid hang caused by
+ * using percpu variable early, for example, lockdep will
+ * access percpu variable inside lock_release
+ */
+ set_my_cpu_offset(0);
+}
+
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+ return phys_id == cpu_logical_map(cpu);
+}
+
+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ * level in order to build a linear index from an
+ * MPIDR value. Resulting algorithm is a collision
+ * free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+ u32 i, affinity, fs[4], bits[4], ls;
+ u64 mask = 0;
+ /*
+ * Pre-scan the list of MPIDRS and filter out bits that do
+ * not contribute to affinity levels, ie they never toggle.
+ */
+ for_each_possible_cpu(i)
+ mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+ pr_debug("mask of set bits %#llx\n", mask);
+ /*
+ * Find and stash the last and first bit set at all affinity levels to
+ * check how many bits are required to represent them.
+ */
+ for (i = 0; i < 4; i++) {
+ affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+ /*
+ * Find the MSB bit and LSB bits position
+ * to determine how many bits are required
+ * to express the affinity level.
+ */
+ ls = fls(affinity);
+ fs[i] = affinity ? ffs(affinity) - 1 : 0;
+ bits[i] = ls - fs[i];
+ }
+ /*
+ * An index can be created from the MPIDR_EL1 by isolating the
+ * significant bits at each affinity level and by shifting
+ * them in order to compress the 32 bits values space to a
+ * compressed set of values. This is equivalent to hashing
+ * the MPIDR_EL1 through shifting and ORing. It is a collision free
+ * hash though not minimal since some levels might contain a number
+ * of CPUs that is not an exact power of 2 and their bit
+ * representation might contain holes, eg MPIDR_EL1[7:0] = {0x2, 0x80}.
+ */
+ mpidr_hash.shift_aff[0] = MPIDR_LEVEL_SHIFT(0) + fs[0];
+ mpidr_hash.shift_aff[1] = MPIDR_LEVEL_SHIFT(1) + fs[1] - bits[0];
+ mpidr_hash.shift_aff[2] = MPIDR_LEVEL_SHIFT(2) + fs[2] -
+ (bits[1] + bits[0]);
+ mpidr_hash.shift_aff[3] = MPIDR_LEVEL_SHIFT(3) +
+ fs[3] - (bits[2] + bits[1] + bits[0]);
+ mpidr_hash.mask = mask;
+ mpidr_hash.bits = bits[3] + bits[2] + bits[1] + bits[0];
+ pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] aff3[%u] mask[%#llx] bits[%u]\n",
+ mpidr_hash.shift_aff[0],
+ mpidr_hash.shift_aff[1],
+ mpidr_hash.shift_aff[2],
+ mpidr_hash.shift_aff[3],
+ mpidr_hash.mask,
+ mpidr_hash.bits);
+ /*
+ * 4x is an arbitrary value used to warn on a hash table much bigger
+ * than expected on most systems.
+ */
+ if (mpidr_hash_size() > 4 * num_possible_cpus())
+ pr_warn("Large number of MPIDR hash buckets detected\n");
+ __flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
+}
+#endif
+
static void __init setup_processor(void)
{
struct cpu_info *cpu_info;
+ u64 features, block;
- /*
- * locate processor in the list of supported processor
- * types. The linker builds this table for us from the
- * entries in arch/arm/mm/proc.S
- */
cpu_info = lookup_processor_type(read_cpuid_id());
if (!cpu_info) {
printk("CPU configuration botched (ID %08x), unable to continue.\n",
@@ -118,8 +227,71 @@
printk("CPU: %s [%08x] revision %d\n",
cpu_name, read_cpuid_id(), read_cpuid_id() & 15);
- sprintf(init_utsname()->machine, "aarch64");
+ sprintf(init_utsname()->machine, ELF_PLATFORM);
elf_hwcap = 0;
+
+ /*
+ * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks.
+ * The blocks we test below represent incremental functionality
+ * for non-negative values. Negative values are reserved.
+ */
+ features = read_cpuid(ID_AA64ISAR0_EL1);
+ block = (features >> 4) & 0xf;
+ if (!(block & 0x8)) {
+ switch (block) {
+ default:
+ case 2:
+ elf_hwcap |= HWCAP_PMULL;
+ case 1:
+ elf_hwcap |= HWCAP_AES;
+ case 0:
+ break;
+ }
+ }
+
+ block = (features >> 8) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_SHA1;
+
+ block = (features >> 12) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_SHA2;
+
+ block = (features >> 16) & 0xf;
+ if (block && !(block & 0x8))
+ elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+ /*
+ * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+ * the Aarch32 32-bit execution state.
+ */
+ features = read_cpuid(ID_ISAR5_EL1);
+ block = (features >> 4) & 0xf;
+ if (!(block & 0x8)) {
+ switch (block) {
+ default:
+ case 2:
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+ case 1:
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+ case 0:
+ break;
+ }
+ }
+
+ block = (features >> 8) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+ block = (features >> 12) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+ block = (features >> 16) & 0xf;
+ if (block && !(block & 0x8))
+ compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
}
static void __init setup_machine_fdt(phys_addr_t dt_phys)
@@ -127,6 +299,8 @@
struct boot_param_header *devtree;
unsigned long dt_root;
+ cpuinfo_store_cpu();
+
/* Check we have a non-NULL DT pointer */
if (!dt_phys) {
early_print("\n"
@@ -195,25 +369,6 @@
return __va(memblock_alloc(size, align));
}
-/*
- * Limit the memory size that was specified via FDT.
- */
-static int __init early_mem(char *p)
-{
- phys_addr_t limit;
-
- if (!p)
- return 1;
-
- limit = memparse(p, &p) & PAGE_MASK;
- pr_notice("Memory limited to %lldMB\n", limit >> 20);
-
- memblock_enforce_memory_limit(limit);
-
- return 0;
-}
-early_param("mem", early_mem);
-
static void __init request_standard_resources(void)
{
struct memblock_region *region;
@@ -257,20 +412,27 @@
*cmdline_p = boot_command_line;
+ early_ioremap_init();
+
parse_early_param();
+ efi_init();
arm64_memblock_init();
paging_init();
request_standard_resources();
+ efi_idmap_init();
+
unflatten_device_tree();
psci_init();
cpu_logical_map(0) = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+ cpu_read_bootcpu_ops();
#ifdef CONFIG_SMP
smp_init_cpus();
+ smp_build_mpidr_hash();
#endif
#ifdef CONFIG_VT
@@ -288,16 +450,14 @@
of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
return 0;
}
-arch_initcall(arm64_device_init);
-
-static DEFINE_PER_CPU(struct cpu, cpu_data);
+arch_initcall_sync(arm64_device_init);
static int __init topology_init(void)
{
int i;
for_each_possible_cpu(i) {
- struct cpu *cpu = &per_cpu(cpu_data, i);
+ struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
cpu->hotpluggable = 1;
register_cpu(cpu, i);
}
@@ -309,17 +469,50 @@
static const char *hwcap_str[] = {
"fp",
"asimd",
+ "evtstrm",
+ "aes",
+ "pmull",
+ "sha1",
+ "sha2",
+ "crc32",
NULL
};
+#ifdef CONFIG_COMPAT
+static const char *compat_hwcap_str[] = {
+ "swp",
+ "half",
+ "thumb",
+ "26bit",
+ "fastmult",
+ "fpa",
+ "vfp",
+ "edsp",
+ "java",
+ "iwmmxt",
+ "crunch",
+ "thumbee",
+ "neon",
+ "vfpv3",
+ "vfpv3d16",
+ "tls",
+ "vfpv4",
+ "idiva",
+ "idivt",
+ "vfpd32",
+ "lpae",
+ "evtstrm"
+};
+#endif /* CONFIG_COMPAT */
+
static int c_show(struct seq_file *m, void *v)
{
- int i;
-
- seq_printf(m, "Processor\t: %s rev %d (%s)\n",
- cpu_name, read_cpuid_id() & 15, ELF_PLATFORM);
+ int i, j;
for_each_online_cpu(i) {
+ struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
+ u32 midr = cpuinfo->reg_midr;
+
/*
* glibc reads /proc/cpuinfo to determine the number of
* online processors, looking for lines beginning with
@@ -328,28 +521,38 @@
#ifdef CONFIG_SMP
seq_printf(m, "processor\t: %d\n", i);
#endif
- seq_printf(m, "BogoMIPS\t: %lu.%02lu\n\n",
+
+ seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
loops_per_jiffy / (500000UL/HZ),
loops_per_jiffy / (5000UL/HZ) % 100);
+
+ /*
+ * Dump out the common processor features in a single line.
+ * Userspace should read the hwcaps with getauxval(AT_HWCAP)
+ * rather than attempting to parse this, but there's a body of
+ * software which does already (at least for 32-bit).
+ */
+ seq_puts(m, "Features\t:");
+ if (personality(current->personality) == PER_LINUX32) {
+#ifdef CONFIG_COMPAT
+ for (j = 0; compat_hwcap_str[j]; j++)
+ if (COMPAT_ELF_HWCAP & (1 << j))
+ seq_printf(m, " %s", compat_hwcap_str[j]);
+#endif /* CONFIG_COMPAT */
+ } else {
+ for (j = 0; hwcap_str[j]; j++)
+ if (elf_hwcap & (1 << j))
+ seq_printf(m, " %s", hwcap_str[j]);
+ }
+ seq_puts(m, "\n");
+
+ seq_printf(m, "CPU implementer\t: 0x%02x\n", (midr >> 24));
+ seq_printf(m, "CPU architecture: 8\n");
+ seq_printf(m, "CPU variant\t: 0x%x\n", ((midr >> 20) & 0xf));
+ seq_printf(m, "CPU part\t: 0x%03x\n", ((midr >> 4) & 0xfff));
+ seq_printf(m, "CPU revision\t: %d\n\n", (midr & 0xf));
}
- /* dump out the processor features */
- seq_puts(m, "Features\t: ");
-
- for (i = 0; hwcap_str[i]; i++)
- if (elf_hwcap & (1 << i))
- seq_printf(m, "%s ", hwcap_str[i]);
-
- seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
- seq_printf(m, "CPU architecture: AArch64\n");
- seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15);
- seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff);
- seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
-
- seq_puts(m, "\n");
-
- seq_printf(m, "Hardware\t: %s\n", machine_name);
-
return 0;
}
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 890a591..e3cf096 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/personality.h>
@@ -25,7 +26,6 @@
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
-#include <asm/compat.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
#include <asm/cacheflush.h>
@@ -100,8 +100,7 @@
{
sigset_t set;
int i, err;
- struct aux_context __user *aux =
- (struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+ void *aux = sf->uc.uc_mcontext.__reserved;
err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
if (err == 0)
@@ -121,8 +120,11 @@
err |= !valid_user_regs(®s->user_regs);
- if (err == 0)
- err |= restore_fpsimd_context(&aux->fpsimd);
+ if (err == 0) {
+ struct fpsimd_context *fpsimd_ctx =
+ container_of(aux, struct fpsimd_context, head);
+ err |= restore_fpsimd_context(fpsimd_ctx);
+ }
return err;
}
@@ -167,8 +169,8 @@
struct pt_regs *regs, sigset_t *set)
{
int i, err = 0;
- struct aux_context __user *aux =
- (struct aux_context __user *)sf->uc.uc_mcontext.__reserved;
+ void *aux = sf->uc.uc_mcontext.__reserved;
+ struct _aarch64_ctx *end;
/* set up the stack frame for unwinding */
__put_user_error(regs->regs[29], &sf->fp, err);
@@ -185,12 +187,17 @@
err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
- if (err == 0)
- err |= preserve_fpsimd_context(&aux->fpsimd);
+ if (err == 0) {
+ struct fpsimd_context *fpsimd_ctx =
+ container_of(aux, struct fpsimd_context, head);
+ err |= preserve_fpsimd_context(fpsimd_ctx);
+ aux += sizeof(*fpsimd_ctx);
+ }
/* set the "end" magic */
- __put_user_error(0, &aux->end.magic, err);
- __put_user_error(0, &aux->end.size, err);
+ end = aux;
+ __put_user_error(0, &end->magic, err);
+ __put_user_error(0, &end->size, err);
return err;
}
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index e393174..96f545c 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -100,34 +100,6 @@
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-/*
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- */
-#define MOV_R7_NR_SIGRETURN (0xe3a07000 | __NR_compat_sigreturn)
-#define SVC_SYS_SIGRETURN (0xef000000 | __NR_compat_sigreturn)
-#define MOV_R7_NR_RT_SIGRETURN (0xe3a07000 | __NR_compat_rt_sigreturn)
-#define SVC_SYS_RT_SIGRETURN (0xef000000 | __NR_compat_rt_sigreturn)
-
-/*
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-#define SVC_THUMB_SIGRETURN (((0xdf00 | __NR_compat_sigreturn) << 16) | \
- 0x2700 | __NR_compat_sigreturn)
-#define SVC_THUMB_RT_SIGRETURN (((0xdf00 | __NR_compat_rt_sigreturn) << 16) | \
- 0x2700 | __NR_compat_rt_sigreturn)
-
-const compat_ulong_t aarch32_sigret_code[6] = {
- /*
- * AArch32 sigreturn code.
- * We don't construct an OABI SWI - instead we just set the imm24 field
- * to the EABI syscall number so that we create a sane disassembly.
- */
- MOV_R7_NR_SIGRETURN, SVC_SYS_SIGRETURN, SVC_THUMB_SIGRETURN,
- MOV_R7_NR_RT_SIGRETURN, SVC_SYS_RT_SIGRETURN, SVC_THUMB_RT_SIGRETURN,
-};
-
static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
{
compat_sigset_t cset;
@@ -179,8 +151,7 @@
case __SI_TIMER:
err |= __put_user(from->si_tid, &to->si_tid);
err |= __put_user(from->si_overrun, &to->si_overrun);
- err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr,
- &to->si_ptr);
+ err |= __put_user(from->si_int, &to->si_int);
break;
case __SI_POLL:
err |= __put_user(from->si_band, &to->si_band);
@@ -209,7 +180,7 @@
case __SI_MESGQ: /* But this is */
err |= __put_user(from->si_pid, &to->si_pid);
err |= __put_user(from->si_uid, &to->si_uid);
- err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr);
+ err |= __put_user(from->si_int, &to->si_int);
break;
default: /* this is just in case for now ... */
err |= __put_user(from->si_pid, &to->si_pid);
@@ -474,12 +445,13 @@
/* Check if the handler is written for ARM or Thumb */
thumb = handler & 1;
- if (thumb) {
+ if (thumb)
spsr |= COMPAT_PSR_T_BIT;
- spsr &= ~COMPAT_PSR_IT_MASK;
- } else {
+ else
spsr &= ~COMPAT_PSR_T_BIT;
- }
+
+ /* The IT state must be cleared for both ARM and Thumb-2 */
+ spsr &= ~COMPAT_PSR_IT_MASK;
if (ka->sa.sa_flags & SA_RESTORER) {
retcode = ptr_to_compat(ka->sa.sa_restorer);
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
new file mode 100644
index 0000000..b192572
--- /dev/null
+++ b/arch/arm64/kernel/sleep.S
@@ -0,0 +1,184 @@
+#include <linux/errno.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+
+ .text
+/*
+ * Implementation of MPIDR_EL1 hash algorithm through shifting
+ * and OR'ing.
+ *
+ * @dst: register containing hash result
+ * @rs0: register containing affinity level 0 bit shift
+ * @rs1: register containing affinity level 1 bit shift
+ * @rs2: register containing affinity level 2 bit shift
+ * @rs3: register containing affinity level 3 bit shift
+ * @mpidr: register containing MPIDR_EL1 value
+ * @mask: register containing MPIDR mask
+ *
+ * Pseudo C-code:
+ *
+ *u32 dst;
+ *
+ *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 rs3, u64 mpidr, u64 mask) {
+ * u32 aff0, aff1, aff2, aff3;
+ * u64 mpidr_masked = mpidr & mask;
+ * aff0 = mpidr_masked & 0xff;
+ * aff1 = mpidr_masked & 0xff00;
+ * aff2 = mpidr_masked & 0xff0000;
+ * aff2 = mpidr_masked & 0xff00000000;
+ * dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3);
+ *}
+ * Input registers: rs0, rs1, rs2, rs3, mpidr, mask
+ * Output register: dst
+ * Note: input and output registers must be disjoint register sets
+ (eg: a macro instance with mpidr = x1 and dst = x1 is invalid)
+ */
+ .macro compute_mpidr_hash dst, rs0, rs1, rs2, rs3, mpidr, mask
+ and \mpidr, \mpidr, \mask // mask out MPIDR bits
+ and \dst, \mpidr, #0xff // mask=aff0
+ lsr \dst ,\dst, \rs0 // dst=aff0>>rs0
+ and \mask, \mpidr, #0xff00 // mask = aff1
+ lsr \mask ,\mask, \rs1
+ orr \dst, \dst, \mask // dst|=(aff1>>rs1)
+ and \mask, \mpidr, #0xff0000 // mask = aff2
+ lsr \mask ,\mask, \rs2
+ orr \dst, \dst, \mask // dst|=(aff2>>rs2)
+ and \mask, \mpidr, #0xff00000000 // mask = aff3
+ lsr \mask ,\mask, \rs3
+ orr \dst, \dst, \mask // dst|=(aff3>>rs3)
+ .endm
+/*
+ * Save CPU state for a suspend. This saves callee registers, and allocates
+ * space on the kernel stack to save the CPU specific registers + some
+ * other data for resume.
+ *
+ * x0 = suspend finisher argument
+ */
+ENTRY(__cpu_suspend)
+ stp x29, lr, [sp, #-96]!
+ stp x19, x20, [sp,#16]
+ stp x21, x22, [sp,#32]
+ stp x23, x24, [sp,#48]
+ stp x25, x26, [sp,#64]
+ stp x27, x28, [sp,#80]
+ mov x2, sp
+ sub sp, sp, #CPU_SUSPEND_SZ // allocate cpu_suspend_ctx
+ mov x1, sp
+ /*
+ * x1 now points to struct cpu_suspend_ctx allocated on the stack
+ */
+ str x2, [x1, #CPU_CTX_SP]
+ ldr x2, =sleep_save_sp
+ ldr x2, [x2, #SLEEP_SAVE_SP_VIRT]
+#ifdef CONFIG_SMP
+ mrs x7, mpidr_el1
+ ldr x9, =mpidr_hash
+ ldr x10, [x9, #MPIDR_HASH_MASK]
+ /*
+ * Following code relies on the struct mpidr_hash
+ * members size.
+ */
+ ldp w3, w4, [x9, #MPIDR_HASH_SHIFTS]
+ ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
+ compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
+ add x2, x2, x8, lsl #3
+#endif
+ bl __cpu_suspend_finisher
+ /*
+ * Never gets here, unless suspend fails.
+ * Successful cpu_suspend should return from cpu_resume, returning
+ * through this code path is considered an error
+ * If the return value is set to 0 force x0 = -EOPNOTSUPP
+ * to make sure a proper error condition is propagated
+ */
+ cmp x0, #0
+ mov x3, #-EOPNOTSUPP
+ csel x0, x3, x0, eq
+ add sp, sp, #CPU_SUSPEND_SZ // rewind stack pointer
+ ldp x19, x20, [sp, #16]
+ ldp x21, x22, [sp, #32]
+ ldp x23, x24, [sp, #48]
+ ldp x25, x26, [sp, #64]
+ ldp x27, x28, [sp, #80]
+ ldp x29, lr, [sp], #96
+ ret
+ENDPROC(__cpu_suspend)
+ .ltorg
+
+/*
+ * x0 must contain the sctlr value retrieved from restored context
+ */
+ENTRY(cpu_resume_mmu)
+ ldr x3, =cpu_resume_after_mmu
+ msr sctlr_el1, x0 // restore sctlr_el1
+ isb
+ br x3 // global jump to virtual address
+ENDPROC(cpu_resume_mmu)
+cpu_resume_after_mmu:
+ mov x0, #0 // return zero on success
+ ldp x19, x20, [sp, #16]
+ ldp x21, x22, [sp, #32]
+ ldp x23, x24, [sp, #48]
+ ldp x25, x26, [sp, #64]
+ ldp x27, x28, [sp, #80]
+ ldp x29, lr, [sp], #96
+ ret
+ENDPROC(cpu_resume_after_mmu)
+
+ .data
+ENTRY(cpu_resume)
+ bl el2_setup // if in EL2 drop to EL1 cleanly
+#ifdef CONFIG_SMP
+ mrs x1, mpidr_el1
+ adr x4, mpidr_hash_ptr
+ ldr x5, [x4]
+ add x8, x4, x5 // x8 = struct mpidr_hash phys address
+ /* retrieve mpidr_hash members to compute the hash */
+ ldr x2, [x8, #MPIDR_HASH_MASK]
+ ldp w3, w4, [x8, #MPIDR_HASH_SHIFTS]
+ ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
+ compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
+ /* x7 contains hash index, let's use it to grab context pointer */
+#else
+ mov x7, xzr
+#endif
+ adr x0, sleep_save_sp
+ ldr x0, [x0, #SLEEP_SAVE_SP_PHYS]
+ ldr x0, [x0, x7, lsl #3]
+ /* load sp from context */
+ ldr x2, [x0, #CPU_CTX_SP]
+ adr x1, sleep_idmap_phys
+ /* load physical address of identity map page table in x1 */
+ ldr x1, [x1]
+ mov sp, x2
+ /*
+ * cpu_do_resume expects x0 to contain context physical address
+ * pointer and x1 to contain physical address of 1:1 page tables
+ */
+ bl cpu_do_resume // PC relative jump, MMU off
+ b cpu_resume_mmu // Resume MMU, never returns
+ENDPROC(cpu_resume)
+
+ .align 3
+mpidr_hash_ptr:
+ /*
+ * offset of mpidr_hash symbol from current location
+ * used to obtain run-time mpidr_hash address with MMU off
+ */
+ .quad mpidr_hash - .
+/*
+ * physical address of identity mapped page tables
+ */
+ .type sleep_idmap_phys, #object
+ENTRY(sleep_idmap_phys)
+ .quad 0
+/*
+ * struct sleep_save_sp {
+ * phys_addr_t *save_ptr_stash;
+ * phys_addr_t save_ptr_stash_phys;
+ * };
+ */
+ .type sleep_save_sp, #object
+ENTRY(sleep_save_sp)
+ .space SLEEP_SAVE_SP_SZ // struct sleep_save_sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 5d54e37..9a3c7ef 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
#include <asm/atomic.h>
#include <asm/cacheflush.h>
#include <asm/cputype.h>
+#include <asm/cpu_ops.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -48,76 +49,34 @@
#include <asm/tlbflush.h>
#include <asm/ptrace.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/arm-ipi.h>
+
/*
* as from 2.5, kernels no longer have an init_tasks structure
* so we need some other way of telling a new secondary core
* where to place its SVC stack
*/
struct secondary_data secondary_data;
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
enum ipi_msg_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CALL_FUNC_SINGLE,
IPI_CPU_STOP,
+ IPI_TIMER,
};
-static DEFINE_RAW_SPINLOCK(boot_lock);
-
-/*
- * Write secondary_holding_pen_release in a way that is guaranteed to be
- * visible to all observers, irrespective of whether they're taking part
- * in coherency or not. This is necessary for the hotplug code to work
- * reliably.
- */
-static void __cpuinit write_pen_release(u64 val)
-{
- void *start = (void *)&secondary_holding_pen_release;
- unsigned long size = sizeof(secondary_holding_pen_release);
-
- secondary_holding_pen_release = val;
- __flush_dcache_area(start, size);
-}
-
/*
* Boot a secondary CPU, and assign it the specified idle task.
* This also gives us the initial stack to use for this CPU.
*/
static int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
{
- unsigned long timeout;
+ if (cpu_ops[cpu]->cpu_boot)
+ return cpu_ops[cpu]->cpu_boot(cpu);
- /*
- * Set synchronisation state between this boot processor
- * and the secondary one
- */
- raw_spin_lock(&boot_lock);
-
- /*
- * Update the pen release flag.
- */
- write_pen_release(cpu_logical_map(cpu));
-
- /*
- * Send an event, causing the secondaries to read pen_release.
- */
- sev();
-
- timeout = jiffies + (1 * HZ);
- while (time_before(jiffies, timeout)) {
- if (secondary_holding_pen_release == INVALID_HWID)
- break;
- udelay(10);
- }
-
- /*
- * Now the secondary core is starting up let it run its
- * calibrations, then wait for it to finish
- */
- raw_spin_unlock(&boot_lock);
-
- return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
+ return -EOPNOTSUPP;
}
static DECLARE_COMPLETION(cpu_running);
@@ -158,6 +117,11 @@
return ret;
}
+static void __cpuinit smp_store_cpu_info(unsigned int cpuid)
+{
+ store_cpu_topology(cpuid);
+}
+
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
@@ -167,8 +131,6 @@
struct mm_struct *mm = &init_mm;
unsigned int cpu = smp_processor_id();
- printk("CPU%u: Booted secondary processor\n", cpu);
-
/*
* All kernel threads share the same mm context; grab a
* reference and switch to it.
@@ -177,6 +139,9 @@
current->active_mm = mm;
cpumask_set_cpu(cpu, mm_cpumask(mm));
+ set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+ printk("CPU%u: Booted secondary processor\n", cpu);
+
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
* point to zero page to avoid speculatively fetching new entries.
@@ -187,24 +152,20 @@
preempt_disable();
trace_hardirqs_off();
- /*
- * Let the primary processor know we're out of the
- * pen, then head off into the C entry point
- */
- write_pen_release(INVALID_HWID);
+ if (cpu_ops[cpu]->cpu_postboot)
+ cpu_ops[cpu]->cpu_postboot();
/*
- * Synchronise with the boot thread.
- */
- raw_spin_lock(&boot_lock);
- raw_spin_unlock(&boot_lock);
-
- /*
- * Enable local interrupts.
+ * Enable GIC and timers.
*/
notify_cpu_starting(cpu);
- local_irq_enable();
- local_fiq_enable();
+
+ smp_store_cpu_info(cpu);
+
+ /*
+ * Log the CPU info before it is marked online and might get read.
+ */
+ cpuinfo_store_cpu();
/*
* OK, now it's safe to let the boot CPU continue. Wait for
@@ -214,12 +175,134 @@
set_cpu_online(cpu, true);
complete(&cpu_running);
+ local_dbg_enable();
+ local_irq_enable();
+ local_fiq_enable();
+
/*
* OK, it's off to the idle thread for us
*/
cpu_startup_entry(CPUHP_ONLINE);
}
+#ifdef CONFIG_HOTPLUG_CPU
+static int op_cpu_disable(unsigned int cpu)
+{
+ /*
+ * If we don't have a cpu_die method, abort before we reach the point
+ * of no return. CPU0 may not have an cpu_ops, so test for it.
+ */
+ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+ return -EOPNOTSUPP;
+
+ /*
+ * We may need to abort a hot unplug for some other mechanism-specific
+ * reason.
+ */
+ if (cpu_ops[cpu]->cpu_disable)
+ return cpu_ops[cpu]->cpu_disable(cpu);
+
+ return 0;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+ unsigned int cpu = smp_processor_id();
+ int ret;
+
+ ret = op_cpu_disable(cpu);
+ if (ret)
+ return ret;
+
+ /*
+ * Take this CPU offline. Once we clear this, we can't return,
+ * and we must not schedule until we're ready to give up the cpu.
+ */
+ set_cpu_online(cpu, false);
+
+ /*
+ * OK - migrate IRQs away from this CPU
+ */
+ migrate_irqs();
+
+ /*
+ * Remove this CPU from the vm mask set of all processes.
+ */
+ clear_tasks_mm_cpumask(cpu);
+
+ return 0;
+}
+
+static int op_cpu_kill(unsigned int cpu)
+{
+ /*
+ * If we have no means of synchronising with the dying CPU, then assume
+ * that it is really dead. We can only wait for an arbitrary length of
+ * time and hope that it's dead, so let's skip the wait and just hope.
+ */
+ if (!cpu_ops[cpu]->cpu_kill)
+ return 1;
+
+ return cpu_ops[cpu]->cpu_kill(cpu);
+}
+
+static DECLARE_COMPLETION(cpu_died);
+
+/*
+ * called on the thread which is asking for a CPU to be shutdown -
+ * waits until shutdown has completed, or it is timed out.
+ */
+void __cpu_die(unsigned int cpu)
+{
+ if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+ pr_crit("CPU%u: cpu didn't die\n", cpu);
+ return;
+ }
+ pr_notice("CPU%u: shutdown\n", cpu);
+
+ /*
+ * Now that the dying CPU is beyond the point of no return w.r.t.
+ * in-kernel synchronisation, try to get the firwmare to help us to
+ * verify that it has really left the kernel before we consider
+ * clobbering anything it might still be using.
+ */
+ if (!op_cpu_kill(cpu))
+ pr_warn("CPU%d may not have shut down cleanly\n", cpu);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ *
+ * Note that we disable IRQs here, but do not re-enable them
+ * before returning to the caller. This is also the behaviour
+ * of the other hotplug-cpu capable cores, so presumably coming
+ * out of idle fixes this.
+ */
+void cpu_die(void)
+{
+ unsigned int cpu = smp_processor_id();
+
+ idle_task_exit();
+
+ local_irq_disable();
+
+ /* Tell __cpu_die() that this CPU is now safe to dispose of */
+ complete(&cpu_died);
+
+ /*
+ * Actually shutdown the CPU. This must never fail. The specific hotplug
+ * mechanism must perform all required cache maintenance to ensure that
+ * no dirty lines are lost in the process of shutting down the CPU.
+ */
+ cpu_ops[cpu]->cpu_die(cpu);
+
+ BUG();
+}
+#endif
+
void __init smp_cpus_done(unsigned int max_cpus)
{
unsigned long bogosum = loops_per_jiffy * num_online_cpus();
@@ -231,32 +314,11 @@
void __init smp_prepare_boot_cpu(void)
{
+ set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
}
static void (*smp_cross_call)(const struct cpumask *, unsigned int);
-static const struct smp_enable_ops *enable_ops[] __initconst = {
- &smp_spin_table_ops,
- &smp_psci_ops,
- NULL,
-};
-
-static const struct smp_enable_ops *smp_enable_ops[NR_CPUS];
-
-static const struct smp_enable_ops * __init smp_get_enable_ops(const char *name)
-{
- const struct smp_enable_ops **ops = enable_ops;
-
- while (*ops) {
- if (!strcmp(name, (*ops)->name))
- return *ops;
-
- ops++;
- }
-
- return NULL;
-}
-
/*
* Enumerate the possible CPU set from the device tree and build the
* cpu logical map array containing MPIDR values related to logical
@@ -264,9 +326,8 @@
*/
void __init smp_init_cpus(void)
{
- const char *enable_method;
struct device_node *dn = NULL;
- int i, cpu = 1;
+ unsigned int i, cpu = 1;
bool bootcpu_valid = false;
while ((dn = of_find_node_by_type(dn, "cpu"))) {
@@ -335,25 +396,10 @@
if (cpu >= NR_CPUS)
goto next;
- /*
- * We currently support only the "spin-table" enable-method.
- */
- enable_method = of_get_property(dn, "enable-method", NULL);
- if (!enable_method) {
- pr_err("%s: missing enable-method property\n",
- dn->full_name);
+ if (cpu_read_ops(dn, cpu) != 0)
goto next;
- }
- smp_enable_ops[cpu] = smp_get_enable_ops(enable_method);
-
- if (!smp_enable_ops[cpu]) {
- pr_err("%s: invalid enable-method property: %s\n",
- dn->full_name, enable_method);
- goto next;
- }
-
- if (smp_enable_ops[cpu]->init_cpu(dn, cpu))
+ if (cpu_ops[cpu]->cpu_init(dn, cpu))
goto next;
pr_debug("cpu logical map 0x%llx\n", hwid);
@@ -383,8 +429,12 @@
void __init smp_prepare_cpus(unsigned int max_cpus)
{
- int cpu, err;
- unsigned int ncores = num_possible_cpus();
+ int err;
+ unsigned int cpu, ncores = num_possible_cpus();
+
+ init_cpu_topology();
+
+ smp_store_cpu_info(smp_processor_id());
/*
* are we trying to boot more cores than exist?
@@ -411,10 +461,10 @@
if (cpu == smp_processor_id())
continue;
- if (!smp_enable_ops[cpu])
+ if (!cpu_ops[cpu])
continue;
- err = smp_enable_ops[cpu]->prepare_cpu(cpu);
+ err = cpu_ops[cpu]->cpu_prepare(cpu);
if (err)
continue;
@@ -445,6 +495,7 @@
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_TIMER, "Timer broadcast interrupts"),
};
void show_ipi_list(struct seq_file *p, int prec)
@@ -454,7 +505,7 @@
for (i = 0; i < NR_IPI; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i + IPI_RESCHEDULE,
prec >= 4 ? " " : "");
- for_each_present_cpu(cpu)
+ for_each_online_cpu(cpu)
seq_printf(p, "%10u ",
__get_irq_stat(cpu, ipi_irqs[i]));
seq_printf(p, " %s\n", ipi_types[i]);
@@ -530,6 +581,14 @@
irq_exit();
break;
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+ case IPI_TIMER:
+ irq_enter();
+ tick_receive_broadcast();
+ irq_exit();
+ break;
+#endif
+
default:
pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
break;
@@ -542,6 +601,13 @@
smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
}
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+void tick_broadcast(const struct cpumask *mask)
+{
+ smp_cross_call(mask, IPI_TIMER);
+}
+#endif
+
void smp_send_stop(void)
{
unsigned long timeout;
diff --git a/arch/arm64/kernel/smp_psci.c b/arch/arm64/kernel/smp_psci.c
deleted file mode 100644
index 0c53330..0000000
--- a/arch/arm64/kernel/smp_psci.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * PSCI SMP initialisation
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/init.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-
-#include <asm/psci.h>
-#include <asm/smp_plat.h>
-
-static int __init smp_psci_init_cpu(struct device_node *dn, int cpu)
-{
- return 0;
-}
-
-static int __init smp_psci_prepare_cpu(int cpu)
-{
- int err;
-
- if (!psci_ops.cpu_on) {
- pr_err("psci: no cpu_on method, not booting CPU%d\n", cpu);
- return -ENODEV;
- }
-
- err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_holding_pen));
- if (err) {
- pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
- return err;
- }
-
- return 0;
-}
-
-const struct smp_enable_ops smp_psci_ops __initconst = {
- .name = "psci",
- .init_cpu = smp_psci_init_cpu,
- .prepare_cpu = smp_psci_prepare_cpu,
-};
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 7c35fa6..0347d38 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -16,15 +16,38 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/delay.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/smp.h>
#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/cputype.h>
+#include <asm/smp_plat.h>
+
+extern void secondary_holding_pen(void);
+volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
static phys_addr_t cpu_release_addr[NR_CPUS];
-static int __init smp_spin_table_init_cpu(struct device_node *dn, int cpu)
+/*
+ * Write secondary_holding_pen_release in a way that is guaranteed to be
+ * visible to all observers, irrespective of whether they're taking part
+ * in coherency or not. This is necessary for the hotplug code to work
+ * reliably.
+ */
+static void write_pen_release(u64 val)
+{
+ void *start = (void *)&secondary_holding_pen_release;
+ unsigned long size = sizeof(secondary_holding_pen_release);
+
+ secondary_holding_pen_release = val;
+ __flush_dcache_area(start, size);
+}
+
+
+static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
{
/*
* Determine the address from which the CPU is polling.
@@ -40,7 +63,7 @@
return 0;
}
-static int __init smp_spin_table_prepare_cpu(int cpu)
+static int smp_spin_table_cpu_prepare(unsigned int cpu)
{
void **release_addr;
@@ -48,7 +71,16 @@
return -ENODEV;
release_addr = __va(cpu_release_addr[cpu]);
- release_addr[0] = (void *)__pa(secondary_holding_pen);
+
+ /*
+ * We write the release address as LE regardless of the native
+ * endianess of the kernel. Therefore, any boot-loaders that
+ * read this address need to convert this address to the
+ * boot-loader's endianess before jumping. This is mandated by
+ * the boot protocol.
+ */
+ release_addr[0] = (void *) cpu_to_le64(__pa(secondary_holding_pen));
+
__flush_dcache_area(release_addr, sizeof(release_addr[0]));
/*
@@ -59,8 +91,24 @@
return 0;
}
-const struct smp_enable_ops smp_spin_table_ops __initconst = {
+static int smp_spin_table_cpu_boot(unsigned int cpu)
+{
+ /*
+ * Update the pen release flag.
+ */
+ write_pen_release(cpu_logical_map(cpu));
+
+ /*
+ * Send an event, causing the secondaries to read pen_release.
+ */
+ sev();
+
+ return 0;
+}
+
+const struct cpu_operations smp_spin_table_ops = {
.name = "spin-table",
- .init_cpu = smp_spin_table_init_cpu,
- .prepare_cpu = smp_spin_table_prepare_cpu,
+ .cpu_init = smp_spin_table_cpu_init,
+ .cpu_prepare = smp_spin_table_cpu_prepare,
+ .cpu_boot = smp_spin_table_cpu_boot,
};
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d25459f..407991b 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -35,7 +35,7 @@
* ldp x29, x30, [sp]
* add sp, sp, #0x10
*/
-int unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct stackframe *frame)
{
unsigned long high, low;
unsigned long fp = frame->fp;
@@ -43,12 +43,16 @@
low = frame->sp;
high = ALIGN(low, THREAD_SIZE);
- if (fp < low || fp > high || fp & 0xf)
+ if (fp < low || fp > high - 0x18 || fp & 0xf)
return -EINVAL;
frame->sp = fp + 0x10;
frame->fp = *(unsigned long *)(fp);
- frame->pc = *(unsigned long *)(fp + 8);
+ /*
+ * -4 here because we care about the PC at time of bl,
+ * not where the return will go.
+ */
+ frame->pc = *(unsigned long *)(fp + 8) - 4;
return 0;
}
@@ -107,10 +111,9 @@
frame.sp = thread_saved_sp(tsk);
frame.pc = thread_saved_pc(tsk);
} else {
- register unsigned long current_sp asm("sp");
data.no_sched_functions = 0;
frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.sp = current_sp;
+ frame.sp = current_stack_pointer;
frame.pc = (unsigned long)save_stack_trace_tsk;
}
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
new file mode 100644
index 0000000..1fa9ce4
--- /dev/null
+++ b/arch/arm64/kernel/suspend.c
@@ -0,0 +1,140 @@
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu_ops.h>
+#include <asm/debug-monitors.h>
+#include <asm/pgtable.h>
+#include <asm/memory.h>
+#include <asm/smp_plat.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+extern int __cpu_suspend(unsigned long);
+/*
+ * This is called by __cpu_suspend() to save the state, and do whatever
+ * flushing is required to ensure that when the CPU goes to sleep we have
+ * the necessary data available when the caches are not searched.
+ *
+ * @arg: Argument to pass to suspend operations
+ * @ptr: CPU context virtual address
+ * @save_ptr: address of the location where the context physical address
+ * must be saved
+ */
+int __cpu_suspend_finisher(unsigned long arg, struct cpu_suspend_ctx *ptr,
+ phys_addr_t *save_ptr)
+{
+ int cpu = smp_processor_id();
+
+ *save_ptr = virt_to_phys(ptr);
+
+ cpu_do_suspend(ptr);
+ /*
+ * Only flush the context that must be retrieved with the MMU
+ * off. VA primitives ensure the flush is applied to all
+ * cache levels so context is pushed to DRAM.
+ */
+ __flush_dcache_area(ptr, sizeof(*ptr));
+ __flush_dcache_area(save_ptr, sizeof(*save_ptr));
+
+ return cpu_ops[cpu]->cpu_suspend(arg);
+}
+
+/*
+ * This hook is provided so that cpu_suspend code can restore HW
+ * breakpoints as early as possible in the resume path, before reenabling
+ * debug exceptions. Code cannot be run from a CPU PM notifier since by the
+ * time the notifier runs debug exceptions might have been enabled already,
+ * with HW breakpoints registers content still in an unknown state.
+ */
+void (*hw_breakpoint_restore)(void *);
+void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+{
+ /* Prevent multiple restore hook initializations */
+ if (WARN_ON(hw_breakpoint_restore))
+ return;
+ hw_breakpoint_restore = hw_bp_restore;
+}
+
+/**
+ * cpu_suspend
+ *
+ * @arg: argument to pass to the finisher function
+ */
+int cpu_suspend(unsigned long arg)
+{
+ struct mm_struct *mm = current->active_mm;
+ int ret, cpu = smp_processor_id();
+ unsigned long flags;
+
+ /*
+ * If cpu_ops have not been registered or suspend
+ * has not been initialized, cpu_suspend call fails early.
+ */
+ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
+ return -EOPNOTSUPP;
+
+ /*
+ * From this point debug exceptions are disabled to prevent
+ * updates to mdscr register (saved and restored along with
+ * general purpose registers) from kernel debuggers.
+ */
+ local_dbg_save(flags);
+
+ /*
+ * mm context saved on the stack, it will be restored when
+ * the cpu comes out of reset through the identity mapped
+ * page tables, so that the thread address space is properly
+ * set-up on function return.
+ */
+ ret = __cpu_suspend(arg);
+ if (ret == 0) {
+ cpu_switch_mm(mm->pgd, mm);
+ flush_tlb_all();
+
+ /*
+ * Restore per-cpu offset before any kernel
+ * subsystem relying on it has a chance to run.
+ */
+ set_my_cpu_offset(per_cpu_offset(cpu));
+
+ /*
+ * Restore HW breakpoint registers to sane values
+ * before debug exceptions are possibly reenabled
+ * through local_dbg_restore.
+ */
+ if (hw_breakpoint_restore)
+ hw_breakpoint_restore(NULL);
+ }
+
+ /*
+ * Restore pstate flags. OS lock and mdscr have been already
+ * restored, so from this point onwards, debugging is fully
+ * renabled if it was enabled when core started shutdown.
+ */
+ local_dbg_restore(flags);
+
+ return ret;
+}
+
+extern struct sleep_save_sp sleep_save_sp;
+extern phys_addr_t sleep_idmap_phys;
+
+static int cpu_suspend_init(void)
+{
+ void *ctx_ptr;
+
+ /* ctx_ptr is an array of physical addresses */
+ ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL);
+
+ if (WARN_ON(!ctx_ptr))
+ return -ENOMEM;
+
+ sleep_save_sp.save_ptr_stash = ctx_ptr;
+ sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
+ sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
+ __flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
+ __flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
+
+ return 0;
+}
+early_initcall(cpu_suspend_init);
diff --git a/arch/arm64/kernel/sys32.S b/arch/arm64/kernel/sys32.S
index a1b19ed..423a5b3 100644
--- a/arch/arm64/kernel/sys32.S
+++ b/arch/arm64/kernel/sys32.S
@@ -59,48 +59,48 @@
* extension.
*/
compat_sys_pread64_wrapper:
- orr x3, x4, x5, lsl #32
+ regs_to_64 x3, x4, x5
b sys_pread64
ENDPROC(compat_sys_pread64_wrapper)
compat_sys_pwrite64_wrapper:
- orr x3, x4, x5, lsl #32
+ regs_to_64 x3, x4, x5
b sys_pwrite64
ENDPROC(compat_sys_pwrite64_wrapper)
compat_sys_truncate64_wrapper:
- orr x1, x2, x3, lsl #32
+ regs_to_64 x1, x2, x3
b sys_truncate
ENDPROC(compat_sys_truncate64_wrapper)
compat_sys_ftruncate64_wrapper:
- orr x1, x2, x3, lsl #32
+ regs_to_64 x1, x2, x3
b sys_ftruncate
ENDPROC(compat_sys_ftruncate64_wrapper)
compat_sys_readahead_wrapper:
- orr x1, x2, x3, lsl #32
+ regs_to_64 x1, x2, x3
mov w2, w4
b sys_readahead
ENDPROC(compat_sys_readahead_wrapper)
compat_sys_fadvise64_64_wrapper:
mov w6, w1
- orr x1, x2, x3, lsl #32
- orr x2, x4, x5, lsl #32
+ regs_to_64 x1, x2, x3
+ regs_to_64 x2, x4, x5
mov w3, w6
b sys_fadvise64_64
ENDPROC(compat_sys_fadvise64_64_wrapper)
compat_sys_sync_file_range2_wrapper:
- orr x2, x2, x3, lsl #32
- orr x3, x4, x5, lsl #32
+ regs_to_64 x2, x2, x3
+ regs_to_64 x3, x4, x5
b sys_sync_file_range2
ENDPROC(compat_sys_sync_file_range2_wrapper)
compat_sys_fallocate_wrapper:
- orr x2, x2, x3, lsl #32
- orr x3, x4, x5, lsl #32
+ regs_to_64 x2, x2, x3
+ regs_to_64 x3, x4, x5
b sys_fallocate
ENDPROC(compat_sys_fallocate_wrapper)
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 26e9c4ee..7803992 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -79,6 +79,12 @@
case __ARM_NR_compat_set_tls:
current->thread.tp_value = regs->regs[0];
+
+ /*
+ * Protect against register corruption from context switch.
+ * See comment in tls_thread_flush.
+ */
+ barrier();
asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
return 0;
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index a551f88..1ddb2bd 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -18,6 +18,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/clockchips.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
@@ -68,18 +69,14 @@
return arch_timer_read_counter() * sched_clock_mult;
}
-int read_current_timer(unsigned long *timer_value)
-{
- *timer_value = arch_timer_read_counter();
- return 0;
-}
-
void __init time_init(void)
{
u32 arch_timer_rate;
clocksource_of_init();
+ tick_setup_hrtimer_broadcast();
+
arch_timer_rate = arch_timer_get_rate();
if (!arch_timer_rate)
panic("Unable to initialise architected timer.\n");
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 0000000..db8bb29
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,590 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013,2014 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <asm/cputype.h>
+#include <asm/topology.h>
+#include <asm/smp_plat.h>
+
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+ return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+ per_cpu(cpu_scale, cpu) = power;
+}
+
+static int __init get_cpu_for_node(struct device_node *node)
+{
+ struct device_node *cpu_node;
+ int cpu;
+
+ cpu_node = of_parse_phandle(node, "cpu", 0);
+ if (!cpu_node)
+ return -1;
+
+ for_each_possible_cpu(cpu) {
+ if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+ of_node_put(cpu_node);
+ return cpu;
+ }
+ }
+
+ pr_crit("Unable to find CPU node for %s\n", cpu_node->full_name);
+
+ of_node_put(cpu_node);
+ return -1;
+}
+
+static int __init parse_core(struct device_node *core, int cluster_id,
+ int core_id)
+{
+ char name[10];
+ bool leaf = true;
+ int i = 0;
+ int cpu;
+ struct device_node *t;
+
+ do {
+ snprintf(name, sizeof(name), "thread%d", i);
+ t = of_get_child_by_name(core, name);
+ if (t) {
+ leaf = false;
+ cpu = get_cpu_for_node(t);
+ if (cpu >= 0) {
+ cpu_topology[cpu].cluster_id = cluster_id;
+ cpu_topology[cpu].core_id = core_id;
+ cpu_topology[cpu].thread_id = i;
+ } else {
+ pr_err("%s: Can't get CPU for thread\n",
+ t->full_name);
+ of_node_put(t);
+ return -EINVAL;
+ }
+ of_node_put(t);
+ }
+ i++;
+ } while (t);
+
+ cpu = get_cpu_for_node(core);
+ if (cpu >= 0) {
+ if (!leaf) {
+ pr_err("%s: Core has both threads and CPU\n",
+ core->full_name);
+ return -EINVAL;
+ }
+
+ cpu_topology[cpu].cluster_id = cluster_id;
+ cpu_topology[cpu].core_id = core_id;
+ } else if (leaf) {
+ pr_err("%s: Can't get CPU for leaf core\n", core->full_name);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int __init parse_cluster(struct device_node *cluster, int depth)
+{
+ char name[10];
+ bool leaf = true;
+ bool has_cores = false;
+ struct device_node *c;
+ static int cluster_id __initdata;
+ int core_id = 0;
+ int i, ret;
+
+ /*
+ * First check for child clusters; we currently ignore any
+ * information about the nesting of clusters and present the
+ * scheduler with a flat list of them.
+ */
+ i = 0;
+ do {
+ snprintf(name, sizeof(name), "cluster%d", i);
+ c = of_get_child_by_name(cluster, name);
+ if (c) {
+ leaf = false;
+ ret = parse_cluster(c, depth + 1);
+ of_node_put(c);
+ if (ret != 0)
+ return ret;
+ }
+ i++;
+ } while (c);
+
+ /* Now check for cores */
+ i = 0;
+ do {
+ snprintf(name, sizeof(name), "core%d", i);
+ c = of_get_child_by_name(cluster, name);
+ if (c) {
+ has_cores = true;
+
+ if (depth == 0) {
+ pr_err("%s: cpu-map children should be clusters\n",
+ c->full_name);
+ of_node_put(c);
+ return -EINVAL;
+ }
+
+ if (leaf) {
+ ret = parse_core(c, cluster_id, core_id++);
+ } else {
+ pr_err("%s: Non-leaf cluster with core %s\n",
+ cluster->full_name, name);
+ ret = -EINVAL;
+ }
+
+ of_node_put(c);
+ if (ret != 0)
+ return ret;
+ }
+ i++;
+ } while (c);
+
+ if (leaf && !has_cores)
+ pr_warn("%s: empty cluster\n", cluster->full_name);
+
+ if (leaf)
+ cluster_id++;
+
+ return 0;
+}
+
+struct cpu_efficiency {
+ const char *compatible;
+ unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ * 0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+static const struct cpu_efficiency table_efficiency[] = {
+ { "arm,cortex-a57", 3891 },
+ { "arm,cortex-a53", 2048 },
+ { NULL, },
+};
+
+static unsigned long *__cpu_capacity;
+#define cpu_capacity(cpu) __cpu_capacity[cpu]
+
+static unsigned long middle_capacity = 1;
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static int __init parse_dt_topology(void)
+{
+ struct device_node *cn, *map;
+ int ret = 0;
+ int cpu;
+
+ cn = of_find_node_by_path("/cpus");
+ if (!cn) {
+ pr_err("No CPU information found in DT\n");
+ return 0;
+ }
+
+ /*
+ * When topology is provided cpu-map is essentially a root
+ * cluster with restricted subnodes.
+ */
+ map = of_get_child_by_name(cn, "cpu-map");
+ if (!map)
+ goto out;
+
+ ret = parse_cluster(map, 0);
+ if (ret != 0)
+ goto out_map;
+
+ /*
+ * Check that all cores are in the topology; the SMP code will
+ * only mark cores described in the DT as possible.
+ */
+ for_each_possible_cpu(cpu) {
+ if (cpu_topology[cpu].cluster_id == -1) {
+ pr_err("CPU%d: No topology information specified\n",
+ cpu);
+ ret = -EINVAL;
+ }
+ }
+
+out_map:
+ of_node_put(map);
+out:
+ of_node_put(cn);
+ return ret;
+}
+
+static void __init parse_dt_cpu_power(void)
+{
+ const struct cpu_efficiency *cpu_eff;
+ struct device_node *cn;
+ unsigned long min_capacity = ULONG_MAX;
+ unsigned long max_capacity = 0;
+ unsigned long capacity = 0;
+ int cpu;
+
+ __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+ GFP_NOWAIT);
+
+ for_each_possible_cpu(cpu) {
+ const u32 *rate;
+ int len;
+
+ /* Too early to use cpu->of_node */
+ cn = of_get_cpu_node(cpu, NULL);
+ if (!cn) {
+ pr_err("Missing device node for CPU %d\n", cpu);
+ continue;
+ }
+
+ for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+ if (of_device_is_compatible(cn, cpu_eff->compatible))
+ break;
+
+ if (cpu_eff->compatible == NULL) {
+ pr_warn("%s: Unknown CPU type\n", cn->full_name);
+ continue;
+ }
+
+ rate = of_get_property(cn, "clock-frequency", &len);
+ if (!rate || len != 4) {
+ pr_err("%s: Missing clock-frequency property\n",
+ cn->full_name);
+ continue;
+ }
+
+ capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+ /* Save min capacity of the system */
+ if (capacity < min_capacity)
+ min_capacity = capacity;
+
+ /* Save max capacity of the system */
+ if (capacity > max_capacity)
+ max_capacity = capacity;
+
+ cpu_capacity(cpu) = capacity;
+ }
+
+ /* If min and max capacities are equal we bypass the update of the
+ * cpu_scale because all CPUs have the same capacity. Otherwise, we
+ * compute a middle_capacity factor that will ensure that the capacity
+ * of an 'average' CPU of the system will be as close as possible to
+ * SCHED_POWER_SCALE, which is the default value, but with the
+ * constraint explained near table_efficiency[].
+ */
+ if (min_capacity == max_capacity)
+ return;
+ else if (4 * max_capacity < (3 * (max_capacity + min_capacity)))
+ middle_capacity = (min_capacity + max_capacity)
+ >> (SCHED_POWER_SHIFT+1);
+ else
+ middle_capacity = ((max_capacity / 3)
+ >> (SCHED_POWER_SHIFT-1)) + 1;
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_topo_data table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+static void update_cpu_power(unsigned int cpu)
+{
+ if (!cpu_capacity(cpu))
+ return;
+
+ set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+
+ pr_info("CPU%u: update cpu_power %lu\n",
+ cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+ return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+ struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+ int cpu;
+
+ if (cpuid_topo->cluster_id == -1) {
+ /*
+ * DT does not contain topology information for this cpu.
+ */
+ pr_debug("CPU%u: No topology information configured\n", cpuid);
+ return;
+ }
+
+ /* update core and thread sibling masks */
+ for_each_possible_cpu(cpu) {
+ cpu_topo = &cpu_topology[cpu];
+
+ if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+ continue;
+
+ cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+ if (cpu != cpuid)
+ cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+ if (cpuid_topo->core_id != cpu_topo->core_id)
+ continue;
+
+ cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+ if (cpu != cpuid)
+ cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+ }
+}
+
+#ifdef CONFIG_SCHED_HMP
+
+/*
+ * Retrieve logical cpu index corresponding to a given MPIDR[23:0]
+ * - mpidr: MPIDR[23:0] to be used for the look-up
+ *
+ * Returns the cpu logical index or -EINVAL on look-up error
+ */
+static inline int get_logical_index(u32 mpidr)
+{
+ int cpu;
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+ if (cpu_logical_map(cpu) == mpidr)
+ return cpu;
+ return -EINVAL;
+}
+
+static const char * const little_cores[] = {
+ "arm,cortex-a53",
+ NULL,
+};
+
+static bool is_little_cpu(struct device_node *cn)
+{
+ const char * const *lc;
+ for (lc = little_cores; *lc; lc++)
+ if (of_device_is_compatible(cn, *lc))
+ return true;
+ return false;
+}
+
+void __init arch_get_fast_and_slow_cpus(struct cpumask *fast,
+ struct cpumask *slow)
+{
+ struct device_node *cn = NULL;
+ int cpu;
+
+ cpumask_clear(fast);
+ cpumask_clear(slow);
+
+ /*
+ * Use the config options if they are given. This helps testing
+ * HMP scheduling on systems without a big.LITTLE architecture.
+ */
+ if (strlen(CONFIG_HMP_FAST_CPU_MASK) && strlen(CONFIG_HMP_SLOW_CPU_MASK)) {
+ if (cpulist_parse(CONFIG_HMP_FAST_CPU_MASK, fast))
+ WARN(1, "Failed to parse HMP fast cpu mask!\n");
+ if (cpulist_parse(CONFIG_HMP_SLOW_CPU_MASK, slow))
+ WARN(1, "Failed to parse HMP slow cpu mask!\n");
+ return;
+ }
+
+ /*
+ * Else, parse device tree for little cores.
+ */
+ while ((cn = of_find_node_by_type(cn, "cpu"))) {
+
+ const u32 *mpidr;
+ int len;
+
+ mpidr = of_get_property(cn, "reg", &len);
+ if (!mpidr || len != 8) {
+ pr_err("%s missing reg property\n", cn->full_name);
+ continue;
+ }
+
+ cpu = get_logical_index(be32_to_cpup(mpidr+1));
+ if (cpu == -EINVAL) {
+ pr_err("couldn't get logical index for mpidr %x\n",
+ be32_to_cpup(mpidr+1));
+ break;
+ }
+
+ if (is_little_cpu(cn))
+ cpumask_set_cpu(cpu, slow);
+ else
+ cpumask_set_cpu(cpu, fast);
+ }
+
+ if (!cpumask_empty(fast) && !cpumask_empty(slow))
+ return;
+
+ /*
+ * We didn't find both big and little cores so let's call all cores
+ * fast as this will keep the system running, with all cores being
+ * treated equal.
+ */
+ cpumask_setall(fast);
+ cpumask_clear(slow);
+}
+
+struct cpumask hmp_slow_cpu_mask;
+
+void __init arch_get_hmp_domains(struct list_head *hmp_domains_list)
+{
+ struct cpumask hmp_fast_cpu_mask;
+ struct hmp_domain *domain;
+
+ arch_get_fast_and_slow_cpus(&hmp_fast_cpu_mask, &hmp_slow_cpu_mask);
+
+ /*
+ * Initialize hmp_domains
+ * Must be ordered with respect to compute capacity.
+ * Fastest domain at head of list.
+ */
+ if(!cpumask_empty(&hmp_slow_cpu_mask)) {
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_slow_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+ }
+ domain = (struct hmp_domain *)
+ kmalloc(sizeof(struct hmp_domain), GFP_KERNEL);
+ cpumask_copy(&domain->possible_cpus, &hmp_fast_cpu_mask);
+ cpumask_and(&domain->cpus, cpu_online_mask, &domain->possible_cpus);
+ list_add(&domain->hmp_domains, hmp_domains_list);
+}
+#endif /* CONFIG_SCHED_HMP */
+
+/*
+ * cluster_to_logical_mask - return cpu logical mask of CPUs in a cluster
+ * @socket_id: cluster HW identifier
+ * @cluster_mask: the cpumask location to be initialized, modified by the
+ * function only if return value == 0
+ *
+ * Return:
+ *
+ * 0 on success
+ * -EINVAL if cluster_mask is NULL or there is no record matching socket_id
+ */
+int cluster_to_logical_mask(unsigned int socket_id, cpumask_t *cluster_mask)
+{
+ int cpu;
+
+ if (!cluster_mask)
+ return -EINVAL;
+
+ for_each_online_cpu(cpu) {
+ if (socket_id == topology_physical_package_id(cpu)) {
+ cpumask_copy(cluster_mask, topology_core_cpumask(cpu));
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+ update_siblings_masks(cpuid);
+ update_cpu_power(cpuid);
+}
+
+static void __init reset_cpu_topology(void)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+ cpu_topo->thread_id = -1;
+ cpu_topo->core_id = 0;
+ cpu_topo->cluster_id = -1;
+
+ cpumask_clear(&cpu_topo->core_sibling);
+ cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+ cpumask_clear(&cpu_topo->thread_sibling);
+ cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+ }
+}
+
+static void __init reset_cpu_power(void)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu)
+ set_power_scale(cpu, SCHED_POWER_SCALE);
+}
+
+void __init init_cpu_topology(void)
+{
+ reset_cpu_topology();
+
+ /*
+ * Discard anything that was parsed if we hit an error so we
+ * don't use partial information.
+ */
+ if (parse_dt_topology())
+ reset_cpu_topology();
+
+ reset_cpu_power();
+ parse_dt_cpu_power();
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f30852d..12cd34f 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -32,6 +32,7 @@
#include <linux/syscalls.h>
#include <asm/atomic.h>
+#include <asm/debug-monitors.h>
#include <asm/traps.h>
#include <asm/stacktrace.h>
#include <asm/exception.h>
@@ -131,7 +132,6 @@
static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
{
struct stackframe frame;
- const register unsigned long current_sp asm ("sp");
pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
@@ -144,7 +144,7 @@
frame.pc = regs->pc;
} else if (tsk == current) {
frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.sp = current_sp;
+ frame.sp = current_stack_pointer;
frame.pc = (unsigned long)dump_backtrace;
} else {
/*
@@ -155,7 +155,7 @@
frame.pc = thread_saved_pc(tsk);
}
- printk("Call trace:\n");
+ pr_emerg("Call trace:\n");
while (1) {
unsigned long where = frame.pc;
int ret;
@@ -261,11 +261,9 @@
siginfo_t info;
void __user *pc = (void __user *)instruction_pointer(regs);
-#ifdef CONFIG_COMPAT
/* check for AArch32 breakpoint instructions */
- if (compat_user_mode(regs) && aarch32_break_trap(regs) == 0)
+ if (!aarch32_break_handler(regs))
return;
-#endif
if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
printk_ratelimit()) {
@@ -329,17 +327,17 @@
void __pte_error(const char *file, int line, unsigned long val)
{
- printk("%s:%d: bad pte %016lx.\n", file, line, val);
+ pr_crit("%s:%d: bad pte %016lx.\n", file, line, val);
}
void __pmd_error(const char *file, int line, unsigned long val)
{
- printk("%s:%d: bad pmd %016lx.\n", file, line, val);
+ pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val);
}
void __pgd_error(const char *file, int line, unsigned long val)
{
- printk("%s:%d: bad pgd %016lx.\n", file, line, val);
+ pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
}
void __init trap_init(void)
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 6a389dc..84cafbc 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -58,7 +58,10 @@
static int alloc_vectors_page(void)
{
extern char __kuser_helper_start[], __kuser_helper_end[];
+ extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+
int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+ int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
unsigned long vpage;
vpage = get_zeroed_page(GFP_ATOMIC);
@@ -72,7 +75,7 @@
/* sigreturn code */
memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
- aarch32_sigret_code, sizeof(aarch32_sigret_code));
+ __aarch32_sigret_code_start, sigret_sz);
flush_icache_range(vpage, vpage + PAGE_SIZE);
vectors_page[0] = virt_to_page(vpage);
@@ -103,49 +106,31 @@
static int __init vdso_init(void)
{
- struct page *pg;
- char *vbase;
- int i, ret = 0;
+ int i;
+
+ if (memcmp(&vdso_start, "\177ELF", 4)) {
+ pr_err("vDSO is not a valid ELF object!\n");
+ return -EINVAL;
+ }
vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
pr_info("vdso: %ld pages (%ld code, %ld data) at base %p\n",
vdso_pages + 1, vdso_pages, 1L, &vdso_start);
/* Allocate the vDSO pagelist, plus a page for the data. */
- vdso_pagelist = kzalloc(sizeof(struct page *) * (vdso_pages + 1),
+ vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
GFP_KERNEL);
- if (vdso_pagelist == NULL) {
- pr_err("Failed to allocate vDSO pagelist!\n");
+ if (vdso_pagelist == NULL)
return -ENOMEM;
- }
/* Grab the vDSO code pages. */
- for (i = 0; i < vdso_pages; i++) {
- pg = virt_to_page(&vdso_start + i*PAGE_SIZE);
- ClearPageReserved(pg);
- get_page(pg);
- vdso_pagelist[i] = pg;
- }
-
- /* Sanity check the shared object header. */
- vbase = vmap(vdso_pagelist, 1, 0, PAGE_KERNEL);
- if (vbase == NULL) {
- pr_err("Failed to map vDSO pagelist!\n");
- return -ENOMEM;
- } else if (memcmp(vbase, "\177ELF", 4)) {
- pr_err("vDSO is not a valid ELF object!\n");
- ret = -EINVAL;
- goto unmap;
- }
+ for (i = 0; i < vdso_pages; i++)
+ vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
/* Grab the vDSO data page. */
- pg = virt_to_page(vdso_data);
- get_page(pg);
- vdso_pagelist[i] = pg;
+ vdso_pagelist[i] = virt_to_page(vdso_data);
-unmap:
- vunmap(vbase);
- return ret;
+ return 0;
}
arch_initcall(vdso_init);
@@ -153,11 +138,12 @@
int uses_interp)
{
struct mm_struct *mm = current->mm;
- unsigned long vdso_base, vdso_mapping_len;
+ unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
int ret;
+ vdso_text_len = vdso_pages << PAGE_SHIFT;
/* Be sure to map the data page */
- vdso_mapping_len = (vdso_pages + 1) << PAGE_SHIFT;
+ vdso_mapping_len = vdso_text_len + PAGE_SIZE;
down_write(&mm->mmap_sem);
vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
@@ -167,35 +153,52 @@
}
mm->context.vdso = (void *)vdso_base;
- ret = install_special_mapping(mm, vdso_base, vdso_mapping_len,
+ ret = install_special_mapping(mm, vdso_base, vdso_text_len,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_pagelist);
- if (ret) {
- mm->context.vdso = NULL;
+ if (ret)
goto up_fail;
- }
+
+ vdso_base += vdso_text_len;
+ ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
+ VM_READ|VM_MAYREAD,
+ vdso_pagelist + vdso_pages);
+ if (ret)
+ goto up_fail;
+
+ up_write(&mm->mmap_sem);
+ return 0;
up_fail:
+ mm->context.vdso = NULL;
up_write(&mm->mmap_sem);
-
return ret;
}
const char *arch_vma_name(struct vm_area_struct *vma)
{
+ unsigned long vdso_text;
+
+ if (!vma->vm_mm)
+ return NULL;
+
+ vdso_text = (unsigned long)vma->vm_mm->context.vdso;
+
/*
* We can re-use the vdso pointer in mm_context_t for identifying
* the vectors page for compat applications. The vDSO will always
* sit above TASK_UNMAPPED_BASE and so we don't need to worry about
* it conflicting with the vectors base.
*/
- if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) {
+ if (vma->vm_start == vdso_text) {
#ifdef CONFIG_COMPAT
if (vma->vm_start == AARCH32_VECTORS_BASE)
return "[vectors]";
#endif
return "[vdso]";
+ } else if (vma->vm_start == (vdso_text + (vdso_pages << PAGE_SHIFT))) {
+ return "[vvar]";
}
return NULL;
@@ -235,6 +238,8 @@
vdso_data->use_syscall = use_syscall;
vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec;
vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec;
+ vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec;
+ vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec;
if (!use_syscall) {
vdso_data->cs_cycle_last = tk->clock->cycle_last;
@@ -242,8 +247,6 @@
vdso_data->xtime_clock_nsec = tk->xtime_nsec;
vdso_data->cs_mult = tk->mult;
vdso_data->cs_shift = tk->shift;
- vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec;
- vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec;
}
smp_wmb();
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index d8064af..ff3bdde 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -43,13 +43,13 @@
$(call if_changed,vdsosym)
# Assembly rules for the .S files
-$(obj-vdso): %.o: %.S
+$(obj-vdso): %.o: %.S FORCE
$(call if_changed_dep,vdsoas)
# Actual build commands
-quiet_cmd_vdsold = VDSOL $@
- cmd_vdsold = $(CC) $(c_flags) -Wl,-T $^ -o $@
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsold = VDSOL $@
+ cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
+quiet_cmd_vdsoas = VDSOA $@
cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
# Install commands for the unstripped file
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index f0a6d10..fe652ff 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -103,6 +103,8 @@
bl __do_get_tspec
seqcnt_check w9, 1b
+ mov x30, x2
+
cmp w0, #CLOCK_MONOTONIC
b.ne 6f
@@ -118,6 +120,9 @@
ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
b.ne 8f
+ /* xtime_coarse_nsec is already right-shifted */
+ mov x12, #0
+
/* Get coarse timespec. */
adr vdso_data, _vdso_data
3: seqcnt_acquire
@@ -156,7 +161,7 @@
lsr x11, x11, x12
stp x10, x11, [x1, #TSPEC_TV_SEC]
mov x0, xzr
- ret x2
+ ret
7:
mov x30, x2
8: /* Syscall fallback. */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 3fae2be..de93a4b 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -13,10 +13,23 @@
#define ARM_EXIT_DISCARD(x) x
OUTPUT_ARCH(aarch64)
-ENTRY(stext)
+ENTRY(_text)
jiffies = jiffies_64;
+#define HYPERVISOR_TEXT \
+ /* \
+ * Force the alignment to be compatible with \
+ * the vectors requirements \
+ */ \
+ . = ALIGN(2048); \
+ VMLINUX_SYMBOL(__hyp_idmap_text_start) = .; \
+ *(.hyp.idmap.text) \
+ VMLINUX_SYMBOL(__hyp_idmap_text_end) = .; \
+ VMLINUX_SYMBOL(__hyp_text_start) = .; \
+ *(.hyp.text) \
+ VMLINUX_SYMBOL(__hyp_text_end) = .;
+
SECTIONS
{
/*
@@ -41,7 +54,6 @@
}
.text : { /* Real text segment */
_stext = .; /* Text and read-only data */
- *(.smp.pen.text)
__exception_text_start = .;
*(.exception.text)
__exception_text_end = .;
@@ -49,6 +61,7 @@
TEXT_TEXT
SCHED_TEXT
LOCK_TEXT
+ HYPERVISOR_TEXT
*(.fixup)
*(.gnu.warning)
. = ALIGN(16);
@@ -56,7 +69,8 @@
}
RO_DATA(PAGE_SIZE)
-
+ EXCEPTION_TABLE(8)
+ NOTES
_etext = .; /* End of text and rodata section */
. = ALIGN(PAGE_SIZE);
@@ -82,45 +96,29 @@
PERCPU_SECTION(64)
__init_end = .;
- . = ALIGN(THREAD_SIZE);
- __data_loc = .;
- .data : AT(__data_loc) {
- _data = .; /* address in memory */
- _sdata = .;
-
- /*
- * first, the init task union, aligned
- * to an 8192 byte boundary.
- */
- INIT_TASK_DATA(THREAD_SIZE)
- NOSAVE_DATA
- CACHELINE_ALIGNED_DATA(64)
- READ_MOSTLY_DATA(64)
-
- /*
- * The exception fixup table (might need resorting at runtime)
- */
- . = ALIGN(32);
- __start___ex_table = .;
- *(__ex_table)
- __stop___ex_table = .;
-
- /*
- * and the usual data section
- */
- DATA_DATA
- CONSTRUCTORS
-
- _edata = .;
- }
- _edata_loc = __data_loc + SIZEOF(.data);
-
- NOTES
+ . = ALIGN(PAGE_SIZE);
+ _data = .;
+ _sdata = .;
+ RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+ _edata = .;
BSS_SECTION(0, 0, 0)
+
+ . = ALIGN(PAGE_SIZE);
+ idmap_pg_dir = .;
+ . += IDMAP_DIR_SIZE;
+ swapper_pg_dir = .;
+ . += SWAPPER_DIR_SIZE;
+
_end = .;
STABS_DEBUG
.comment 0 : { *(.comment) }
}
+
+/*
+ * The HYP init code can't be more than a page long.
+ */
+ASSERT(((__hyp_idmap_text_start + PAGE_SIZE) > __hyp_idmap_text_end),
+ "HYP init code too big")
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
new file mode 100644
index 0000000..8ba85e9
--- /dev/null
+++ b/arch/arm64/kvm/Kconfig
@@ -0,0 +1,63 @@
+#
+# KVM configuration
+#
+
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+ bool "Virtualization"
+ ---help---
+ Say Y here to get to see options for using your Linux host to run
+ other operating systems inside virtual machines (guests).
+ This option alone does not add any kernel code.
+
+ If you say N, all options in this submenu will be skipped and
+ disabled.
+
+if VIRTUALIZATION
+
+config KVM
+ bool "Kernel-based Virtual Machine (KVM) support"
+ select MMU_NOTIFIER
+ select PREEMPT_NOTIFIERS
+ select ANON_INODES
+ select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select KVM_MMIO
+ select KVM_ARM_HOST
+ select KVM_ARM_VGIC
+ select KVM_ARM_TIMER
+ ---help---
+ Support hosting virtualized guest machines.
+
+ If unsure, say N.
+
+config KVM_ARM_HOST
+ bool
+ ---help---
+ Provides host support for ARM processors.
+
+config KVM_ARM_MAX_VCPUS
+ int "Number maximum supported virtual CPUs per VM"
+ depends on KVM_ARM_HOST
+ default 4
+ help
+ Static number of max supported virtual CPUs per VM.
+
+ If you choose a high number, the vcpu structures will be quite
+ large, so only choose a reasonable number that you expect to
+ actually use.
+
+config KVM_ARM_VGIC
+ bool
+ depends on KVM_ARM_HOST && OF
+ select HAVE_KVM_IRQCHIP
+ ---help---
+ Adds support for a hardware assisted, in-kernel GIC emulation.
+
+config KVM_ARM_TIMER
+ bool
+ depends on KVM_ARM_VGIC
+ ---help---
+ Adds support for the Architected Timers in virtual machines.
+
+endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
new file mode 100644
index 0000000..32a0961
--- /dev/null
+++ b/arch/arm64/kvm/Makefile
@@ -0,0 +1,27 @@
+#
+# Makefile for Kernel-based Virtual Machine module
+#
+
+ccflags-y += -Ivirt/kvm -Iarch/arm64/kvm
+CFLAGS_arm.o := -I.
+CFLAGS_mmu.o := -I.
+
+KVM=../../../virt/kvm
+ARM=../../../arch/arm/kvm
+
+obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
+
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
+
+kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o
+kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
+kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o
+
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o
+kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o
+kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm64/kvm/emulate.c b/arch/arm64/kvm/emulate.c
new file mode 100644
index 0000000..124418d
--- /dev/null
+++ b/arch/arm64/kvm/emulate.c
@@ -0,0 +1,158 @@
+/*
+ * (not much of an) Emulation layer for 32bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * based on arch/arm/kvm/emulate.c
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+
+/*
+ * stolen from arch/arm/kernel/opcodes.c
+ *
+ * condition code lookup table
+ * index into the table is test code: EQ, NE, ... LT, GT, AL, NV
+ *
+ * bit position in short is condition code: NZCV
+ */
+static const unsigned short cc_map[16] = {
+ 0xF0F0, /* EQ == Z set */
+ 0x0F0F, /* NE */
+ 0xCCCC, /* CS == C set */
+ 0x3333, /* CC */
+ 0xFF00, /* MI == N set */
+ 0x00FF, /* PL */
+ 0xAAAA, /* VS == V set */
+ 0x5555, /* VC */
+ 0x0C0C, /* HI == C set && Z clear */
+ 0xF3F3, /* LS == C clear || Z set */
+ 0xAA55, /* GE == (N==V) */
+ 0x55AA, /* LT == (N!=V) */
+ 0x0A05, /* GT == (!Z && (N==V)) */
+ 0xF5FA, /* LE == (Z || (N!=V)) */
+ 0xFFFF, /* AL always */
+ 0 /* NV */
+};
+
+static int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
+{
+ u32 esr = kvm_vcpu_get_hsr(vcpu);
+
+ if (esr & ESR_EL2_CV)
+ return (esr & ESR_EL2_COND) >> ESR_EL2_COND_SHIFT;
+
+ return -1;
+}
+
+/*
+ * Check if a trapped instruction should have been executed or not.
+ */
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+{
+ unsigned long cpsr;
+ u32 cpsr_cond;
+ int cond;
+
+ /* Top two bits non-zero? Unconditional. */
+ if (kvm_vcpu_get_hsr(vcpu) >> 30)
+ return true;
+
+ /* Is condition field valid? */
+ cond = kvm_vcpu_get_condition(vcpu);
+ if (cond == 0xE)
+ return true;
+
+ cpsr = *vcpu_cpsr(vcpu);
+
+ if (cond < 0) {
+ /* This can happen in Thumb mode: examine IT state. */
+ unsigned long it;
+
+ it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3);
+
+ /* it == 0 => unconditional. */
+ if (it == 0)
+ return true;
+
+ /* The cond for this insn works out as the top 4 bits. */
+ cond = (it >> 4);
+ }
+
+ cpsr_cond = cpsr >> 28;
+
+ if (!((cc_map[cond] >> cpsr_cond) & 1))
+ return false;
+
+ return true;
+}
+
+/**
+ * adjust_itstate - adjust ITSTATE when emulating instructions in IT-block
+ * @vcpu: The VCPU pointer
+ *
+ * When exceptions occur while instructions are executed in Thumb IF-THEN
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
+ * to do this little bit of work manually. The fields map like this:
+ *
+ * IT[7:0] -> CPSR[26:25],CPSR[15:10]
+ */
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+{
+ unsigned long itbits, cond;
+ unsigned long cpsr = *vcpu_cpsr(vcpu);
+ bool is_arm = !(cpsr & COMPAT_PSR_T_BIT);
+
+ BUG_ON(is_arm && (cpsr & COMPAT_PSR_IT_MASK));
+
+ if (!(cpsr & COMPAT_PSR_IT_MASK))
+ return;
+
+ cond = (cpsr & 0xe000) >> 13;
+ itbits = (cpsr & 0x1c00) >> (10 - 2);
+ itbits |= (cpsr & (0x3 << 25)) >> 25;
+
+ /* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */
+ if ((itbits & 0x7) == 0)
+ itbits = cond = 0;
+ else
+ itbits = (itbits << 1) & 0x1f;
+
+ cpsr &= ~COMPAT_PSR_IT_MASK;
+ cpsr |= cond << 13;
+ cpsr |= (itbits & 0x1c) << (10 - 2);
+ cpsr |= (itbits & 0x3) << 25;
+ *vcpu_cpsr(vcpu) = cpsr;
+}
+
+/**
+ * kvm_skip_instr - skip a trapped instruction and proceed to the next
+ * @vcpu: The vcpu pointer
+ */
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+ bool is_thumb;
+
+ is_thumb = !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_T_BIT);
+ if (is_thumb && !is_wide_instr)
+ *vcpu_pc(vcpu) += 2;
+ else
+ *vcpu_pc(vcpu) += 4;
+ kvm_adjust_itstate(vcpu);
+}
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
new file mode 100644
index 0000000..7679469
--- /dev/null
+++ b/arch/arm64/kvm/guest.c
@@ -0,0 +1,359 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/guest.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <asm/cputype.h>
+#include <asm/uaccess.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+ { NULL }
+};
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
+ return 0;
+}
+
+static u64 core_reg_offset_from_id(u64 id)
+{
+ return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
+}
+
+static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ /*
+ * Because the kvm_regs structure is a mix of 32, 64 and
+ * 128bit fields, we index it as if it was a 32bit
+ * array. Hence below, nr_regs is the number of entries, and
+ * off the index in the "array".
+ */
+ __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
+ struct kvm_regs *regs = vcpu_gp_regs(vcpu);
+ int nr_regs = sizeof(*regs) / sizeof(__u32);
+ u32 off;
+
+ /* Our ID is an index into the kvm_regs struct. */
+ off = core_reg_offset_from_id(reg->id);
+ if (off >= nr_regs ||
+ (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
+ return -ENOENT;
+
+ if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr;
+ struct kvm_regs *regs = vcpu_gp_regs(vcpu);
+ int nr_regs = sizeof(*regs) / sizeof(__u32);
+ __uint128_t tmp;
+ void *valp = &tmp;
+ u64 off;
+ int err = 0;
+
+ /* Our ID is an index into the kvm_regs struct. */
+ off = core_reg_offset_from_id(reg->id);
+ if (off >= nr_regs ||
+ (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
+ return -ENOENT;
+
+ if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
+ return -EINVAL;
+
+ if (copy_from_user(valp, uaddr, KVM_REG_SIZE(reg->id))) {
+ err = -EFAULT;
+ goto out;
+ }
+
+ if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
+ u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK;
+ switch (mode) {
+ case COMPAT_PSR_MODE_USR:
+ case COMPAT_PSR_MODE_FIQ:
+ case COMPAT_PSR_MODE_IRQ:
+ case COMPAT_PSR_MODE_SVC:
+ case COMPAT_PSR_MODE_ABT:
+ case COMPAT_PSR_MODE_UND:
+ case PSR_MODE_EL0t:
+ case PSR_MODE_EL1t:
+ case PSR_MODE_EL1h:
+ break;
+ default:
+ err = -EINVAL;
+ goto out;
+ }
+ }
+
+ memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+out:
+ return err;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+ return -EINVAL;
+}
+
+static unsigned long num_core_regs(void)
+{
+ return sizeof(struct kvm_regs) / sizeof(__u32);
+}
+
+/**
+ * ARM64 versions of the TIMER registers, always available on arm64
+ */
+
+#define NUM_TIMER_REGS 3
+
+static bool is_timer_reg(u64 index)
+{
+ switch (index) {
+ case KVM_REG_ARM_TIMER_CTL:
+ case KVM_REG_ARM_TIMER_CNT:
+ case KVM_REG_ARM_TIMER_CVAL:
+ return true;
+ }
+ return false;
+}
+
+static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ if (put_user(KVM_REG_ARM_TIMER_CTL, uindices))
+ return -EFAULT;
+ uindices++;
+ if (put_user(KVM_REG_ARM_TIMER_CNT, uindices))
+ return -EFAULT;
+ uindices++;
+ if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+ int ret;
+
+ ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
+ if (ret != 0)
+ return -EFAULT;
+
+ return kvm_arm_timer_set_reg(vcpu, reg->id, val);
+}
+
+static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ void __user *uaddr = (void __user *)(long)reg->addr;
+ u64 val;
+
+ val = kvm_arm_timer_get_reg(vcpu, reg->id);
+ return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id));
+}
+
+/**
+ * kvm_arm_num_regs - how many registers do we present via KVM_GET_ONE_REG
+ *
+ * This is for all registers.
+ */
+unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
+{
+ return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
+ + NUM_TIMER_REGS;
+}
+
+/**
+ * kvm_arm_copy_reg_indices - get indices of all registers.
+ *
+ * We do core registers right here, then we apppend system regs.
+ */
+int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ unsigned int i;
+ const u64 core_reg = KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE;
+ int ret;
+
+ for (i = 0; i < sizeof(struct kvm_regs) / sizeof(__u32); i++) {
+ if (put_user(core_reg | i, uindices))
+ return -EFAULT;
+ uindices++;
+ }
+
+ ret = copy_timer_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += NUM_TIMER_REGS;
+
+ return kvm_arm_copy_sys_reg_indices(vcpu, uindices);
+}
+
+int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ /* We currently use nothing arch-specific in upper 32 bits */
+ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
+ return -EINVAL;
+
+ /* Register group 16 means we want a core register. */
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
+ return get_core_reg(vcpu, reg);
+
+ if (is_timer_reg(reg->id))
+ return get_timer_reg(vcpu, reg);
+
+ return kvm_arm_sys_reg_get_reg(vcpu, reg);
+}
+
+int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ /* We currently use nothing arch-specific in upper 32 bits */
+ if ((reg->id & ~KVM_REG_SIZE_MASK) >> 32 != KVM_REG_ARM64 >> 32)
+ return -EINVAL;
+
+ /* Register group 16 means we set a core register. */
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
+ return set_core_reg(vcpu, reg);
+
+ if (is_timer_reg(reg->id))
+ return set_timer_reg(vcpu, reg);
+
+ return kvm_arm_sys_reg_set_reg(vcpu, reg);
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ return -EINVAL;
+}
+
+int __attribute_const__ kvm_target_cpu(void)
+{
+ unsigned long implementor = read_cpuid_implementor();
+ unsigned long part_number = read_cpuid_part_number();
+
+ switch (implementor) {
+ case ARM_CPU_IMP_ARM:
+ switch (part_number) {
+ case ARM_CPU_PART_AEM_V8:
+ return KVM_ARM_TARGET_AEM_V8;
+ case ARM_CPU_PART_FOUNDATION:
+ return KVM_ARM_TARGET_FOUNDATION_V8;
+ case ARM_CPU_PART_CORTEX_A53:
+ return KVM_ARM_TARGET_CORTEX_A53;
+ case ARM_CPU_PART_CORTEX_A57:
+ return KVM_ARM_TARGET_CORTEX_A57;
+ };
+ break;
+ case ARM_CPU_IMP_APM:
+ switch (part_number) {
+ case APM_CPU_PART_POTENZA:
+ return KVM_ARM_TARGET_XGENE_POTENZA;
+ };
+ break;
+ };
+
+ return -EINVAL;
+}
+
+int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
+ const struct kvm_vcpu_init *init)
+{
+ unsigned int i;
+ int phys_target = kvm_target_cpu();
+
+ if (init->target != phys_target)
+ return -EINVAL;
+
+ vcpu->arch.target = phys_target;
+ bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+
+ /* -ENOENT for unknown features, -EINVAL for invalid combinations. */
+ for (i = 0; i < sizeof(init->features) * 8; i++) {
+ if (init->features[i / 32] & (1 << (i % 32))) {
+ if (i >= KVM_VCPU_MAX_FEATURES)
+ return -ENOENT;
+ set_bit(i, vcpu->arch.features);
+ }
+ }
+
+ /* Now we know what it is, we can reset it. */
+ return kvm_reset_vcpu(vcpu);
+}
+
+int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
+{
+ int target = kvm_target_cpu();
+
+ if (target < 0)
+ return -ENODEV;
+
+ memset(init, 0, sizeof(*init));
+
+ /*
+ * For now, we don't return any features.
+ * In future, we might use features to return target
+ * specific features available for the preferred
+ * target type.
+ */
+ init->target = (__u32)target;
+
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+ return -EINVAL;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+ struct kvm_translation *tr)
+{
+ return -EINVAL;
+}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
new file mode 100644
index 0000000..e28be51
--- /dev/null
+++ b/arch/arm64/kvm/handle_exit.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/handle_exit.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
+#include <asm/kvm_psci.h>
+
+typedef int (*exit_handle_fn)(struct kvm_vcpu *, struct kvm_run *);
+
+static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ int ret;
+
+ ret = kvm_psci_call(vcpu);
+ if (ret < 0) {
+ kvm_inject_undefined(vcpu);
+ return 1;
+ }
+
+ return ret;
+}
+
+static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
+/**
+ * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
+ * instruction executed by a guest
+ *
+ * @vcpu: the vcpu pointer
+ *
+ * WFE: Yield the CPU and come back to this vcpu when the scheduler
+ * decides to.
+ * WFI: Simply call kvm_vcpu_block(), which will halt execution of
+ * world-switches and schedule other host processes until there is an
+ * incoming IRQ or FIQ to the VM.
+ */
+static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE)
+ kvm_vcpu_on_spin(vcpu);
+ else
+ kvm_vcpu_block(vcpu);
+
+ return 1;
+}
+
+static exit_handle_fn arm_exit_handlers[] = {
+ [ESR_EL2_EC_WFI] = kvm_handle_wfx,
+ [ESR_EL2_EC_CP15_32] = kvm_handle_cp15_32,
+ [ESR_EL2_EC_CP15_64] = kvm_handle_cp15_64,
+ [ESR_EL2_EC_CP14_MR] = kvm_handle_cp14_32,
+ [ESR_EL2_EC_CP14_LS] = kvm_handle_cp14_load_store,
+ [ESR_EL2_EC_CP14_64] = kvm_handle_cp14_64,
+ [ESR_EL2_EC_HVC32] = handle_hvc,
+ [ESR_EL2_EC_SMC32] = handle_smc,
+ [ESR_EL2_EC_HVC64] = handle_hvc,
+ [ESR_EL2_EC_SMC64] = handle_smc,
+ [ESR_EL2_EC_SYS64] = kvm_handle_sys_reg,
+ [ESR_EL2_EC_IABT] = kvm_handle_guest_abort,
+ [ESR_EL2_EC_DABT] = kvm_handle_guest_abort,
+};
+
+static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
+{
+ u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+
+ if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
+ !arm_exit_handlers[hsr_ec]) {
+ kvm_err("Unknown exception class: hsr: %#08x\n",
+ (unsigned int)kvm_vcpu_get_hsr(vcpu));
+ BUG();
+ }
+
+ return arm_exit_handlers[hsr_ec];
+}
+
+/*
+ * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
+ * proper exit to userspace.
+ */
+int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ int exception_index)
+{
+ exit_handle_fn exit_handler;
+
+ switch (exception_index) {
+ case ARM_EXCEPTION_IRQ:
+ return 1;
+ case ARM_EXCEPTION_TRAP:
+ /*
+ * See ARM ARM B1.14.1: "Hyp traps on instructions
+ * that fail their condition code check"
+ */
+ if (!kvm_condition_valid(vcpu)) {
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ return 1;
+ }
+
+ exit_handler = kvm_get_exit_handler(vcpu);
+
+ return exit_handler(vcpu, run);
+ default:
+ kvm_pr_unimpl("Unsupported exception type: %d",
+ exception_index);
+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ return 0;
+ }
+}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
new file mode 100644
index 0000000..d968796
--- /dev/null
+++ b/arch/arm64/kvm/hyp-init.S
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+ .text
+ .pushsection .hyp.idmap.text, "ax"
+
+ .align 11
+
+ENTRY(__kvm_hyp_init)
+ ventry __invalid // Synchronous EL2t
+ ventry __invalid // IRQ EL2t
+ ventry __invalid // FIQ EL2t
+ ventry __invalid // Error EL2t
+
+ ventry __invalid // Synchronous EL2h
+ ventry __invalid // IRQ EL2h
+ ventry __invalid // FIQ EL2h
+ ventry __invalid // Error EL2h
+
+ ventry __do_hyp_init // Synchronous 64-bit EL1
+ ventry __invalid // IRQ 64-bit EL1
+ ventry __invalid // FIQ 64-bit EL1
+ ventry __invalid // Error 64-bit EL1
+
+ ventry __invalid // Synchronous 32-bit EL1
+ ventry __invalid // IRQ 32-bit EL1
+ ventry __invalid // FIQ 32-bit EL1
+ ventry __invalid // Error 32-bit EL1
+
+__invalid:
+ b .
+
+ /*
+ * x0: HYP boot pgd
+ * x1: HYP pgd
+ * x2: HYP stack
+ * x3: HYP vectors
+ */
+__do_hyp_init:
+
+ msr ttbr0_el2, x0
+
+ mrs x4, tcr_el1
+ ldr x5, =TCR_EL2_MASK
+ and x4, x4, x5
+ ldr x5, =TCR_EL2_FLAGS
+ orr x4, x4, x5
+ msr tcr_el2, x4
+
+ ldr x4, =VTCR_EL2_FLAGS
+ /*
+ * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
+ * VTCR_EL2.
+ */
+ mrs x5, ID_AA64MMFR0_EL1
+ bfi x4, x5, #16, #3
+ msr vtcr_el2, x4
+
+ mrs x4, mair_el1
+ msr mair_el2, x4
+ isb
+
+ mrs x4, sctlr_el2
+ and x4, x4, #SCTLR_EL2_EE // preserve endianness of EL2
+ ldr x5, =SCTLR_EL2_FLAGS
+ orr x4, x4, x5
+ msr sctlr_el2, x4
+ isb
+
+ /* MMU is now enabled. Get ready for the trampoline dance */
+ ldr x4, =TRAMPOLINE_VA
+ adr x5, target
+ bfi x4, x5, #0, #PAGE_SHIFT
+ br x4
+
+target: /* We're now in the trampoline code, switch page tables */
+ msr ttbr0_el2, x1
+ isb
+
+ /* Invalidate the old TLBs */
+ tlbi alle2
+ dsb sy
+
+ /* Set the stack and new vectors */
+ kern_hyp_va x2
+ mov sp, x2
+ kern_hyp_va x3
+ msr vbar_el2, x3
+
+ /* Hello, World! */
+ eret
+ENDPROC(__kvm_hyp_init)
+
+ .ltorg
+
+ .popsection
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
new file mode 100644
index 0000000..b72aa9f
--- /dev/null
+++ b/arch/arm64/kvm/hyp.S
@@ -0,0 +1,1274 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/debug-monitors.h>
+#include <asm/fpsimdmacros.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+#define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x)
+#define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_SPSR_OFFSET(x) CPU_GP_REG_OFFSET(CPU_SPSR + 8*x)
+#define CPU_SYSREG_OFFSET(x) (CPU_SYSREGS + 8*x)
+
+ .text
+ .pushsection .hyp.text, "ax"
+ .align PAGE_SHIFT
+
+.macro save_common_regs
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ add x3, x2, #CPU_XREG_OFFSET(19)
+ stp x19, x20, [x3]
+ stp x21, x22, [x3, #16]
+ stp x23, x24, [x3, #32]
+ stp x25, x26, [x3, #48]
+ stp x27, x28, [x3, #64]
+ stp x29, lr, [x3, #80]
+
+ mrs x19, sp_el0
+ mrs x20, elr_el2 // EL1 PC
+ mrs x21, spsr_el2 // EL1 pstate
+
+ stp x19, x20, [x3, #96]
+ str x21, [x3, #112]
+
+ mrs x22, sp_el1
+ mrs x23, elr_el1
+ mrs x24, spsr_el1
+
+ str x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
+ str x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
+ str x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
+.endm
+
+.macro restore_common_regs
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
+ ldr x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)]
+ ldr x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)]
+
+ msr sp_el1, x22
+ msr elr_el1, x23
+ msr spsr_el1, x24
+
+ add x3, x2, #CPU_XREG_OFFSET(31) // SP_EL0
+ ldp x19, x20, [x3]
+ ldr x21, [x3, #16]
+
+ msr sp_el0, x19
+ msr elr_el2, x20 // EL1 PC
+ msr spsr_el2, x21 // EL1 pstate
+
+ add x3, x2, #CPU_XREG_OFFSET(19)
+ ldp x19, x20, [x3]
+ ldp x21, x22, [x3, #16]
+ ldp x23, x24, [x3, #32]
+ ldp x25, x26, [x3, #48]
+ ldp x27, x28, [x3, #64]
+ ldp x29, lr, [x3, #80]
+.endm
+
+.macro save_host_regs
+ save_common_regs
+.endm
+
+.macro restore_host_regs
+ restore_common_regs
+.endm
+
+.macro save_fpsimd
+ // x2: cpu context address
+ // x3, x4: tmp regs
+ add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+ fpsimd_save x3, 4
+.endm
+
+.macro restore_fpsimd
+ // x2: cpu context address
+ // x3, x4: tmp regs
+ add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
+ fpsimd_restore x3, 4
+.endm
+
+.macro save_guest_regs
+ // x0 is the vcpu address
+ // x1 is the return code, do not corrupt!
+ // x2 is the cpu context
+ // x3 is a tmp register
+ // Guest's x0-x3 are on the stack
+
+ // Compute base to save registers
+ add x3, x2, #CPU_XREG_OFFSET(4)
+ stp x4, x5, [x3]
+ stp x6, x7, [x3, #16]
+ stp x8, x9, [x3, #32]
+ stp x10, x11, [x3, #48]
+ stp x12, x13, [x3, #64]
+ stp x14, x15, [x3, #80]
+ stp x16, x17, [x3, #96]
+ str x18, [x3, #112]
+
+ pop x6, x7 // x2, x3
+ pop x4, x5 // x0, x1
+
+ add x3, x2, #CPU_XREG_OFFSET(0)
+ stp x4, x5, [x3]
+ stp x6, x7, [x3, #16]
+
+ save_common_regs
+.endm
+
+.macro restore_guest_regs
+ // x0 is the vcpu address.
+ // x2 is the cpu context
+ // x3 is a tmp register
+
+ // Prepare x0-x3 for later restore
+ add x3, x2, #CPU_XREG_OFFSET(0)
+ ldp x4, x5, [x3]
+ ldp x6, x7, [x3, #16]
+ push x4, x5 // Push x0-x3 on the stack
+ push x6, x7
+
+ // x4-x18
+ ldp x4, x5, [x3, #32]
+ ldp x6, x7, [x3, #48]
+ ldp x8, x9, [x3, #64]
+ ldp x10, x11, [x3, #80]
+ ldp x12, x13, [x3, #96]
+ ldp x14, x15, [x3, #112]
+ ldp x16, x17, [x3, #128]
+ ldr x18, [x3, #144]
+
+ // x19-x29, lr, sp*, elr*, spsr*
+ restore_common_regs
+
+ // Last bits of the 64bit state
+ pop x2, x3
+ pop x0, x1
+
+ // Do not touch any register after this!
+.endm
+
+/*
+ * Macros to perform system register save/restore.
+ *
+ * Ordering here is absolutely critical, and must be kept consistent
+ * in {save,restore}_sysregs, {save,restore}_guest_32bit_state,
+ * and in kvm_asm.h.
+ *
+ * In other words, don't touch any of these unless you know what
+ * you are doing.
+ */
+.macro save_sysregs
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
+
+ mrs x4, vmpidr_el2
+ mrs x5, csselr_el1
+ mrs x6, sctlr_el1
+ mrs x7, actlr_el1
+ mrs x8, cpacr_el1
+ mrs x9, ttbr0_el1
+ mrs x10, ttbr1_el1
+ mrs x11, tcr_el1
+ mrs x12, esr_el1
+ mrs x13, afsr0_el1
+ mrs x14, afsr1_el1
+ mrs x15, far_el1
+ mrs x16, mair_el1
+ mrs x17, vbar_el1
+ mrs x18, contextidr_el1
+ mrs x19, tpidr_el0
+ mrs x20, tpidrro_el0
+ mrs x21, tpidr_el1
+ mrs x22, amair_el1
+ mrs x23, cntkctl_el1
+ mrs x24, par_el1
+ mrs x25, mdscr_el1
+
+ stp x4, x5, [x3]
+ stp x6, x7, [x3, #16]
+ stp x8, x9, [x3, #32]
+ stp x10, x11, [x3, #48]
+ stp x12, x13, [x3, #64]
+ stp x14, x15, [x3, #80]
+ stp x16, x17, [x3, #96]
+ stp x18, x19, [x3, #112]
+ stp x20, x21, [x3, #128]
+ stp x22, x23, [x3, #144]
+ stp x24, x25, [x3, #160]
+.endm
+
+.macro save_debug
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ mrs x26, id_aa64dfr0_el1
+ ubfx x24, x26, #12, #4 // Extract BRPs
+ ubfx x25, x26, #20, #4 // Extract WRPs
+ mov w26, #15
+ sub w24, w26, w24 // How many BPs to skip
+ sub w25, w26, w25 // How many WPs to skip
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ mrs x20, dbgbcr15_el1
+ mrs x19, dbgbcr14_el1
+ mrs x18, dbgbcr13_el1
+ mrs x17, dbgbcr12_el1
+ mrs x16, dbgbcr11_el1
+ mrs x15, dbgbcr10_el1
+ mrs x14, dbgbcr9_el1
+ mrs x13, dbgbcr8_el1
+ mrs x12, dbgbcr7_el1
+ mrs x11, dbgbcr6_el1
+ mrs x10, dbgbcr5_el1
+ mrs x9, dbgbcr4_el1
+ mrs x8, dbgbcr3_el1
+ mrs x7, dbgbcr2_el1
+ mrs x6, dbgbcr1_el1
+ mrs x5, dbgbcr0_el1
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ mrs x20, dbgbvr15_el1
+ mrs x19, dbgbvr14_el1
+ mrs x18, dbgbvr13_el1
+ mrs x17, dbgbvr12_el1
+ mrs x16, dbgbvr11_el1
+ mrs x15, dbgbvr10_el1
+ mrs x14, dbgbvr9_el1
+ mrs x13, dbgbvr8_el1
+ mrs x12, dbgbvr7_el1
+ mrs x11, dbgbvr6_el1
+ mrs x10, dbgbvr5_el1
+ mrs x9, dbgbvr4_el1
+ mrs x8, dbgbvr3_el1
+ mrs x7, dbgbvr2_el1
+ mrs x6, dbgbvr1_el1
+ mrs x5, dbgbvr0_el1
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ mrs x20, dbgwcr15_el1
+ mrs x19, dbgwcr14_el1
+ mrs x18, dbgwcr13_el1
+ mrs x17, dbgwcr12_el1
+ mrs x16, dbgwcr11_el1
+ mrs x15, dbgwcr10_el1
+ mrs x14, dbgwcr9_el1
+ mrs x13, dbgwcr8_el1
+ mrs x12, dbgwcr7_el1
+ mrs x11, dbgwcr6_el1
+ mrs x10, dbgwcr5_el1
+ mrs x9, dbgwcr4_el1
+ mrs x8, dbgwcr3_el1
+ mrs x7, dbgwcr2_el1
+ mrs x6, dbgwcr1_el1
+ mrs x5, dbgwcr0_el1
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ mrs x20, dbgwvr15_el1
+ mrs x19, dbgwvr14_el1
+ mrs x18, dbgwvr13_el1
+ mrs x17, dbgwvr12_el1
+ mrs x16, dbgwvr11_el1
+ mrs x15, dbgwvr10_el1
+ mrs x14, dbgwvr9_el1
+ mrs x13, dbgwvr8_el1
+ mrs x12, dbgwvr7_el1
+ mrs x11, dbgwvr6_el1
+ mrs x10, dbgwvr5_el1
+ mrs x9, dbgwvr4_el1
+ mrs x8, dbgwvr3_el1
+ mrs x7, dbgwvr2_el1
+ mrs x6, dbgwvr1_el1
+ mrs x5, dbgwvr0_el1
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+
+1:
+ str x20, [x3, #(15 * 8)]
+ str x19, [x3, #(14 * 8)]
+ str x18, [x3, #(13 * 8)]
+ str x17, [x3, #(12 * 8)]
+ str x16, [x3, #(11 * 8)]
+ str x15, [x3, #(10 * 8)]
+ str x14, [x3, #(9 * 8)]
+ str x13, [x3, #(8 * 8)]
+ str x12, [x3, #(7 * 8)]
+ str x11, [x3, #(6 * 8)]
+ str x10, [x3, #(5 * 8)]
+ str x9, [x3, #(4 * 8)]
+ str x8, [x3, #(3 * 8)]
+ str x7, [x3, #(2 * 8)]
+ str x6, [x3, #(1 * 8)]
+ str x5, [x3, #(0 * 8)]
+
+ mrs x21, mdccint_el1
+ str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+.endm
+
+.macro restore_sysregs
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1)
+
+ ldp x4, x5, [x3]
+ ldp x6, x7, [x3, #16]
+ ldp x8, x9, [x3, #32]
+ ldp x10, x11, [x3, #48]
+ ldp x12, x13, [x3, #64]
+ ldp x14, x15, [x3, #80]
+ ldp x16, x17, [x3, #96]
+ ldp x18, x19, [x3, #112]
+ ldp x20, x21, [x3, #128]
+ ldp x22, x23, [x3, #144]
+ ldp x24, x25, [x3, #160]
+
+ msr vmpidr_el2, x4
+ msr csselr_el1, x5
+ msr sctlr_el1, x6
+ msr actlr_el1, x7
+ msr cpacr_el1, x8
+ msr ttbr0_el1, x9
+ msr ttbr1_el1, x10
+ msr tcr_el1, x11
+ msr esr_el1, x12
+ msr afsr0_el1, x13
+ msr afsr1_el1, x14
+ msr far_el1, x15
+ msr mair_el1, x16
+ msr vbar_el1, x17
+ msr contextidr_el1, x18
+ msr tpidr_el0, x19
+ msr tpidrro_el0, x20
+ msr tpidr_el1, x21
+ msr amair_el1, x22
+ msr cntkctl_el1, x23
+ msr par_el1, x24
+ msr mdscr_el1, x25
+.endm
+
+.macro restore_debug
+ // x2: base address for cpu context
+ // x3: tmp register
+
+ mrs x26, id_aa64dfr0_el1
+ ubfx x24, x26, #12, #4 // Extract BRPs
+ ubfx x25, x26, #20, #4 // Extract WRPs
+ mov w26, #15
+ sub w24, w26, w24 // How many BPs to skip
+ sub w25, w26, w25 // How many WPs to skip
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ msr dbgbcr15_el1, x20
+ msr dbgbcr14_el1, x19
+ msr dbgbcr13_el1, x18
+ msr dbgbcr12_el1, x17
+ msr dbgbcr11_el1, x16
+ msr dbgbcr10_el1, x15
+ msr dbgbcr9_el1, x14
+ msr dbgbcr8_el1, x13
+ msr dbgbcr7_el1, x12
+ msr dbgbcr6_el1, x11
+ msr dbgbcr5_el1, x10
+ msr dbgbcr4_el1, x9
+ msr dbgbcr3_el1, x8
+ msr dbgbcr2_el1, x7
+ msr dbgbcr1_el1, x6
+ msr dbgbcr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x24, lsl #2
+ br x26
+1:
+ msr dbgbvr15_el1, x20
+ msr dbgbvr14_el1, x19
+ msr dbgbvr13_el1, x18
+ msr dbgbvr12_el1, x17
+ msr dbgbvr11_el1, x16
+ msr dbgbvr10_el1, x15
+ msr dbgbvr9_el1, x14
+ msr dbgbvr8_el1, x13
+ msr dbgbvr7_el1, x12
+ msr dbgbvr6_el1, x11
+ msr dbgbvr5_el1, x10
+ msr dbgbvr4_el1, x9
+ msr dbgbvr3_el1, x8
+ msr dbgbvr2_el1, x7
+ msr dbgbvr1_el1, x6
+ msr dbgbvr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ msr dbgwcr15_el1, x20
+ msr dbgwcr14_el1, x19
+ msr dbgwcr13_el1, x18
+ msr dbgwcr12_el1, x17
+ msr dbgwcr11_el1, x16
+ msr dbgwcr10_el1, x15
+ msr dbgwcr9_el1, x14
+ msr dbgwcr8_el1, x13
+ msr dbgwcr7_el1, x12
+ msr dbgwcr6_el1, x11
+ msr dbgwcr5_el1, x10
+ msr dbgwcr4_el1, x9
+ msr dbgwcr3_el1, x8
+ msr dbgwcr2_el1, x7
+ msr dbgwcr1_el1, x6
+ msr dbgwcr0_el1, x5
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1)
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ ldr x20, [x3, #(15 * 8)]
+ ldr x19, [x3, #(14 * 8)]
+ ldr x18, [x3, #(13 * 8)]
+ ldr x17, [x3, #(12 * 8)]
+ ldr x16, [x3, #(11 * 8)]
+ ldr x15, [x3, #(10 * 8)]
+ ldr x14, [x3, #(9 * 8)]
+ ldr x13, [x3, #(8 * 8)]
+ ldr x12, [x3, #(7 * 8)]
+ ldr x11, [x3, #(6 * 8)]
+ ldr x10, [x3, #(5 * 8)]
+ ldr x9, [x3, #(4 * 8)]
+ ldr x8, [x3, #(3 * 8)]
+ ldr x7, [x3, #(2 * 8)]
+ ldr x6, [x3, #(1 * 8)]
+ ldr x5, [x3, #(0 * 8)]
+
+ adr x26, 1f
+ add x26, x26, x25, lsl #2
+ br x26
+1:
+ msr dbgwvr15_el1, x20
+ msr dbgwvr14_el1, x19
+ msr dbgwvr13_el1, x18
+ msr dbgwvr12_el1, x17
+ msr dbgwvr11_el1, x16
+ msr dbgwvr10_el1, x15
+ msr dbgwvr9_el1, x14
+ msr dbgwvr8_el1, x13
+ msr dbgwvr7_el1, x12
+ msr dbgwvr6_el1, x11
+ msr dbgwvr5_el1, x10
+ msr dbgwvr4_el1, x9
+ msr dbgwvr3_el1, x8
+ msr dbgwvr2_el1, x7
+ msr dbgwvr1_el1, x6
+ msr dbgwvr0_el1, x5
+
+ ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)]
+ msr mdccint_el1, x21
+.endm
+
+.macro skip_32bit_state tmp, target
+ // Skip 32bit state if not needed
+ mrs \tmp, hcr_el2
+ tbnz \tmp, #HCR_RW_SHIFT, \target
+.endm
+
+.macro skip_tee_state tmp, target
+ // Skip ThumbEE state if not needed
+ mrs \tmp, id_pfr0_el1
+ tbz \tmp, #12, \target
+.endm
+
+.macro skip_debug_state tmp, target
+ ldr \tmp, [x0, #VCPU_DEBUG_FLAGS]
+ tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target
+.endm
+
+.macro compute_debug_state target
+ // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY
+ // is set, we do a full save/restore cycle and disable trapping.
+ add x25, x0, #VCPU_CONTEXT
+
+ // Check the state of MDSCR_EL1
+ ldr x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)]
+ and x26, x25, #DBG_MDSCR_KDE
+ and x25, x25, #DBG_MDSCR_MDE
+ adds xzr, x25, x26
+ b.eq 9998f // Nothing to see there
+
+ // If any interesting bits was set, we must set the flag
+ mov x26, #KVM_ARM64_DEBUG_DIRTY
+ str x26, [x0, #VCPU_DEBUG_FLAGS]
+ b 9999f // Don't skip restore
+
+9998:
+ // Otherwise load the flags from memory in case we recently
+ // trapped
+ skip_debug_state x25, \target
+9999:
+.endm
+
+.macro save_guest_32bit_state
+ skip_32bit_state x3, 1f
+
+ add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
+ mrs x4, spsr_abt
+ mrs x5, spsr_und
+ mrs x6, spsr_irq
+ mrs x7, spsr_fiq
+ stp x4, x5, [x3]
+ stp x6, x7, [x3, #16]
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
+ mrs x4, dacr32_el2
+ mrs x5, ifsr32_el2
+ mrs x6, fpexc32_el2
+ stp x4, x5, [x3]
+ str x6, [x3, #16]
+
+ skip_debug_state x8, 2f
+ mrs x7, dbgvcr32_el2
+ str x7, [x3, #24]
+2:
+ skip_tee_state x8, 1f
+
+ add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
+ mrs x4, teecr32_el1
+ mrs x5, teehbr32_el1
+ stp x4, x5, [x3]
+1:
+.endm
+
+.macro restore_guest_32bit_state
+ skip_32bit_state x3, 1f
+
+ add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT)
+ ldp x4, x5, [x3]
+ ldp x6, x7, [x3, #16]
+ msr spsr_abt, x4
+ msr spsr_und, x5
+ msr spsr_irq, x6
+ msr spsr_fiq, x7
+
+ add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2)
+ ldp x4, x5, [x3]
+ ldr x6, [x3, #16]
+ msr dacr32_el2, x4
+ msr ifsr32_el2, x5
+ msr fpexc32_el2, x6
+
+ skip_debug_state x8, 2f
+ ldr x7, [x3, #24]
+ msr dbgvcr32_el2, x7
+2:
+ skip_tee_state x8, 1f
+
+ add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
+ ldp x4, x5, [x3]
+ msr teecr32_el1, x4
+ msr teehbr32_el1, x5
+1:
+.endm
+
+.macro activate_traps
+ ldr x2, [x0, #VCPU_HCR_EL2]
+ msr hcr_el2, x2
+ ldr x2, =(CPTR_EL2_TTA)
+ msr cptr_el2, x2
+
+ ldr x2, =(1 << 15) // Trap CP15 Cr=15
+ msr hstr_el2, x2
+
+ mrs x2, mdcr_el2
+ and x2, x2, #MDCR_EL2_HPMN_MASK
+ orr x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR)
+ orr x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA)
+
+ // Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap
+ // if not dirty.
+ ldr x3, [x0, #VCPU_DEBUG_FLAGS]
+ tbnz x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f
+ orr x2, x2, #MDCR_EL2_TDA
+1:
+ msr mdcr_el2, x2
+.endm
+
+.macro deactivate_traps
+ mov x2, #HCR_RW
+ msr hcr_el2, x2
+ msr cptr_el2, xzr
+ msr hstr_el2, xzr
+
+ mrs x2, mdcr_el2
+ and x2, x2, #MDCR_EL2_HPMN_MASK
+ msr mdcr_el2, x2
+.endm
+
+.macro activate_vm
+ ldr x1, [x0, #VCPU_KVM]
+ kern_hyp_va x1
+ ldr x2, [x1, #KVM_VTTBR]
+ msr vttbr_el2, x2
+.endm
+
+.macro deactivate_vm
+ msr vttbr_el2, xzr
+.endm
+
+/*
+ * Call into the vgic backend for state saving
+ */
+.macro save_vgic_state
+ adr x24, __vgic_sr_vectors
+ ldr x24, [x24, VGIC_SAVE_FN]
+ kern_hyp_va x24
+ blr x24
+ mrs x24, hcr_el2
+ mov x25, #HCR_INT_OVERRIDE
+ neg x25, x25
+ and x24, x24, x25
+ msr hcr_el2, x24
+.endm
+
+/*
+ * Call into the vgic backend for state restoring
+ */
+.macro restore_vgic_state
+ mrs x24, hcr_el2
+ ldr x25, [x0, #VCPU_IRQ_LINES]
+ orr x24, x24, #HCR_INT_OVERRIDE
+ orr x24, x24, x25
+ msr hcr_el2, x24
+ adr x24, __vgic_sr_vectors
+ ldr x24, [x24, #VGIC_RESTORE_FN]
+ kern_hyp_va x24
+ blr x24
+.endm
+
+.macro save_timer_state
+ // x0: vcpu pointer
+ ldr x2, [x0, #VCPU_KVM]
+ kern_hyp_va x2
+ ldr w3, [x2, #KVM_TIMER_ENABLED]
+ cbz w3, 1f
+
+ mrs x3, cntv_ctl_el0
+ and x3, x3, #3
+ str w3, [x0, #VCPU_TIMER_CNTV_CTL]
+ bic x3, x3, #1 // Clear Enable
+ msr cntv_ctl_el0, x3
+
+ isb
+
+ mrs x3, cntv_cval_el0
+ str x3, [x0, #VCPU_TIMER_CNTV_CVAL]
+
+1:
+ // Allow physical timer/counter access for the host
+ mrs x2, cnthctl_el2
+ orr x2, x2, #3
+ msr cnthctl_el2, x2
+
+ // Clear cntvoff for the host
+ msr cntvoff_el2, xzr
+.endm
+
+.macro restore_timer_state
+ // x0: vcpu pointer
+ // Disallow physical timer access for the guest
+ // Physical counter access is allowed
+ mrs x2, cnthctl_el2
+ orr x2, x2, #1
+ bic x2, x2, #2
+ msr cnthctl_el2, x2
+
+ ldr x2, [x0, #VCPU_KVM]
+ kern_hyp_va x2
+ ldr w3, [x2, #KVM_TIMER_ENABLED]
+ cbz w3, 1f
+
+ ldr x3, [x2, #KVM_TIMER_CNTVOFF]
+ msr cntvoff_el2, x3
+ ldr x2, [x0, #VCPU_TIMER_CNTV_CVAL]
+ msr cntv_cval_el0, x2
+ isb
+
+ ldr w2, [x0, #VCPU_TIMER_CNTV_CTL]
+ and x2, x2, #3
+ msr cntv_ctl_el0, x2
+1:
+.endm
+
+__save_sysregs:
+ save_sysregs
+ ret
+
+__restore_sysregs:
+ restore_sysregs
+ ret
+
+__save_debug:
+ save_debug
+ ret
+
+__restore_debug:
+ restore_debug
+ ret
+
+__save_fpsimd:
+ save_fpsimd
+ ret
+
+__restore_fpsimd:
+ restore_fpsimd
+ ret
+
+/*
+ * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu);
+ *
+ * This is the world switch. The first half of the function
+ * deals with entering the guest, and anything from __kvm_vcpu_return
+ * to the end of the function deals with reentering the host.
+ * On the enter path, only x0 (vcpu pointer) must be preserved until
+ * the last moment. On the exit path, x0 (vcpu pointer) and x1 (exception
+ * code) must both be preserved until the epilogue.
+ * In both cases, x2 points to the CPU context we're saving/restoring from/to.
+ */
+ENTRY(__kvm_vcpu_run)
+ kern_hyp_va x0
+ msr tpidr_el2, x0 // Save the vcpu register
+
+ // Host context
+ ldr x2, [x0, #VCPU_HOST_CONTEXT]
+ kern_hyp_va x2
+
+ save_host_regs
+ bl __save_fpsimd
+ bl __save_sysregs
+
+ compute_debug_state 1f
+ bl __save_debug
+1:
+ activate_traps
+ activate_vm
+
+ restore_vgic_state
+ restore_timer_state
+
+ // Guest context
+ add x2, x0, #VCPU_CONTEXT
+
+ bl __restore_sysregs
+ bl __restore_fpsimd
+
+ skip_debug_state x3, 1f
+ bl __restore_debug
+1:
+ restore_guest_32bit_state
+ restore_guest_regs
+
+ // That's it, no more messing around.
+ eret
+
+__kvm_vcpu_return:
+ // Assume x0 is the vcpu pointer, x1 the return code
+ // Guest's x0-x3 are on the stack
+
+ // Guest context
+ add x2, x0, #VCPU_CONTEXT
+
+ save_guest_regs
+ bl __save_fpsimd
+ bl __save_sysregs
+
+ skip_debug_state x3, 1f
+ bl __save_debug
+1:
+ save_guest_32bit_state
+
+ save_timer_state
+ save_vgic_state
+
+ deactivate_traps
+ deactivate_vm
+
+ // Host context
+ ldr x2, [x0, #VCPU_HOST_CONTEXT]
+ kern_hyp_va x2
+
+ bl __restore_sysregs
+ bl __restore_fpsimd
+
+ skip_debug_state x3, 1f
+ // Clear the dirty flag for the next run, as all the state has
+ // already been saved. Note that we nuke the whole 64bit word.
+ // If we ever add more flags, we'll have to be more careful...
+ str xzr, [x0, #VCPU_DEBUG_FLAGS]
+ bl __restore_debug
+1:
+ restore_host_regs
+
+ mov x0, x1
+ ret
+END(__kvm_vcpu_run)
+
+// void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa);
+ENTRY(__kvm_tlb_flush_vmid_ipa)
+ dsb ishst
+
+ kern_hyp_va x0
+ ldr x2, [x0, #KVM_VTTBR]
+ msr vttbr_el2, x2
+ isb
+
+ /*
+ * We could do so much better if we had the VA as well.
+ * Instead, we invalidate Stage-2 for this IPA, and the
+ * whole of Stage-1. Weep...
+ */
+ tlbi ipas2e1is, x1
+ /*
+ * We have to ensure completion of the invalidation at Stage-2,
+ * since a table walk on another CPU could refill a TLB with a
+ * complete (S1 + S2) walk based on the old Stage-2 mapping if
+ * the Stage-1 invalidation happened first.
+ */
+ dsb ish
+ tlbi vmalle1is
+ dsb ish
+ isb
+
+ msr vttbr_el2, xzr
+ ret
+ENDPROC(__kvm_tlb_flush_vmid_ipa)
+
+ENTRY(__kvm_flush_vm_context)
+ dsb ishst
+ tlbi alle1is
+ ic ialluis
+ dsb ish
+ ret
+ENDPROC(__kvm_flush_vm_context)
+
+ // struct vgic_sr_vectors __vgi_sr_vectors;
+ .align 3
+ENTRY(__vgic_sr_vectors)
+ .skip VGIC_SR_VECTOR_SZ
+ENDPROC(__vgic_sr_vectors)
+
+__kvm_hyp_panic:
+ // Guess the context by looking at VTTBR:
+ // If zero, then we're already a host.
+ // Otherwise restore a minimal host context before panicing.
+ mrs x0, vttbr_el2
+ cbz x0, 1f
+
+ mrs x0, tpidr_el2
+
+ deactivate_traps
+ deactivate_vm
+
+ ldr x2, [x0, #VCPU_HOST_CONTEXT]
+ kern_hyp_va x2
+
+ bl __restore_sysregs
+
+1: adr x0, __hyp_panic_str
+ adr x1, 2f
+ ldp x2, x3, [x1]
+ sub x0, x0, x2
+ add x0, x0, x3
+ mrs x1, spsr_el2
+ mrs x2, elr_el2
+ mrs x3, esr_el2
+ mrs x4, far_el2
+ mrs x5, hpfar_el2
+ mrs x6, par_el1
+ mrs x7, tpidr_el2
+
+ mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
+ PSR_MODE_EL1h)
+ msr spsr_el2, lr
+ ldr lr, =panic
+ msr elr_el2, lr
+ eret
+
+ .align 3
+2: .quad HYP_PAGE_OFFSET
+ .quad PAGE_OFFSET
+ENDPROC(__kvm_hyp_panic)
+
+__hyp_panic_str:
+ .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+
+ .align 2
+
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed). The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
+ENTRY(kvm_call_hyp)
+ hvc #0
+ ret
+ENDPROC(kvm_call_hyp)
+
+.macro invalid_vector label, target
+ .align 2
+\label:
+ b \target
+ENDPROC(\label)
+.endm
+
+ /* None of these should ever happen */
+ invalid_vector el2t_sync_invalid, __kvm_hyp_panic
+ invalid_vector el2t_irq_invalid, __kvm_hyp_panic
+ invalid_vector el2t_fiq_invalid, __kvm_hyp_panic
+ invalid_vector el2t_error_invalid, __kvm_hyp_panic
+ invalid_vector el2h_sync_invalid, __kvm_hyp_panic
+ invalid_vector el2h_irq_invalid, __kvm_hyp_panic
+ invalid_vector el2h_fiq_invalid, __kvm_hyp_panic
+ invalid_vector el2h_error_invalid, __kvm_hyp_panic
+ invalid_vector el1_sync_invalid, __kvm_hyp_panic
+ invalid_vector el1_irq_invalid, __kvm_hyp_panic
+ invalid_vector el1_fiq_invalid, __kvm_hyp_panic
+ invalid_vector el1_error_invalid, __kvm_hyp_panic
+
+el1_sync: // Guest trapped into EL2
+ push x0, x1
+ push x2, x3
+
+ mrs x1, esr_el2
+ lsr x2, x1, #ESR_EL2_EC_SHIFT
+
+ cmp x2, #ESR_EL2_EC_HVC64
+ b.ne el1_trap
+
+ mrs x3, vttbr_el2 // If vttbr is valid, the 64bit guest
+ cbnz x3, el1_trap // called HVC
+
+ /* Here, we're pretty sure the host called HVC. */
+ pop x2, x3
+ pop x0, x1
+
+ /* Check for __hyp_get_vectors */
+ cbnz x0, 1f
+ mrs x0, vbar_el2
+ b 2f
+
+1: push lr, xzr
+
+ /*
+ * Compute the function address in EL2, and shuffle the parameters.
+ */
+ kern_hyp_va x0
+ mov lr, x0
+ mov x0, x1
+ mov x1, x2
+ mov x2, x3
+ blr lr
+
+ pop lr, xzr
+2: eret
+
+el1_trap:
+ /*
+ * x1: ESR
+ * x2: ESR_EC
+ */
+ cmp x2, #ESR_EL2_EC_DABT
+ mov x0, #ESR_EL2_EC_IABT
+ ccmp x2, x0, #4, ne
+ b.ne 1f // Not an abort we care about
+
+ /* This is an abort. Check for permission fault */
+ and x2, x1, #ESR_EL2_FSC_TYPE
+ cmp x2, #FSC_PERM
+ b.ne 1f // Not a permission fault
+
+ /*
+ * Check for Stage-1 page table walk, which is guaranteed
+ * to give a valid HPFAR_EL2.
+ */
+ tbnz x1, #7, 1f // S1PTW is set
+
+ /* Preserve PAR_EL1 */
+ mrs x3, par_el1
+ push x3, xzr
+
+ /*
+ * Permission fault, HPFAR_EL2 is invalid.
+ * Resolve the IPA the hard way using the guest VA.
+ * Stage-1 translation already validated the memory access rights.
+ * As such, we can use the EL1 translation regime, and don't have
+ * to distinguish between EL0 and EL1 access.
+ */
+ mrs x2, far_el2
+ at s1e1r, x2
+ isb
+
+ /* Read result */
+ mrs x3, par_el1
+ pop x0, xzr // Restore PAR_EL1 from the stack
+ msr par_el1, x0
+ tbnz x3, #0, 3f // Bail out if we failed the translation
+ ubfx x3, x3, #12, #36 // Extract IPA
+ lsl x3, x3, #4 // and present it like HPFAR
+ b 2f
+
+1: mrs x3, hpfar_el2
+ mrs x2, far_el2
+
+2: mrs x0, tpidr_el2
+ str w1, [x0, #VCPU_ESR_EL2]
+ str x2, [x0, #VCPU_FAR_EL2]
+ str x3, [x0, #VCPU_HPFAR_EL2]
+
+ mov x1, #ARM_EXCEPTION_TRAP
+ b __kvm_vcpu_return
+
+ /*
+ * Translation failed. Just return to the guest and
+ * let it fault again. Another CPU is probably playing
+ * behind our back.
+ */
+3: pop x2, x3
+ pop x0, x1
+
+ eret
+
+el1_irq:
+ push x0, x1
+ push x2, x3
+ mrs x0, tpidr_el2
+ mov x1, #ARM_EXCEPTION_IRQ
+ b __kvm_vcpu_return
+
+ .ltorg
+
+ .align 11
+
+ENTRY(__kvm_hyp_vector)
+ ventry el2t_sync_invalid // Synchronous EL2t
+ ventry el2t_irq_invalid // IRQ EL2t
+ ventry el2t_fiq_invalid // FIQ EL2t
+ ventry el2t_error_invalid // Error EL2t
+
+ ventry el2h_sync_invalid // Synchronous EL2h
+ ventry el2h_irq_invalid // IRQ EL2h
+ ventry el2h_fiq_invalid // FIQ EL2h
+ ventry el2h_error_invalid // Error EL2h
+
+ ventry el1_sync // Synchronous 64-bit EL1
+ ventry el1_irq // IRQ 64-bit EL1
+ ventry el1_fiq_invalid // FIQ 64-bit EL1
+ ventry el1_error_invalid // Error 64-bit EL1
+
+ ventry el1_sync // Synchronous 32-bit EL1
+ ventry el1_irq // IRQ 32-bit EL1
+ ventry el1_fiq_invalid // FIQ 32-bit EL1
+ ventry el1_error_invalid // Error 32-bit EL1
+ENDPROC(__kvm_hyp_vector)
+
+ .popsection
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
new file mode 100644
index 0000000..81a02a8
--- /dev/null
+++ b/arch/arm64/kvm/inject_fault.c
@@ -0,0 +1,203 @@
+/*
+ * Fault injection for both 32 and 64bit guests.
+ *
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Based on arch/arm/kvm/emulate.c
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/esr.h>
+
+#define PSTATE_FAULT_BITS_64 (PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
+ PSR_I_BIT | PSR_D_BIT)
+#define EL1_EXCEPT_SYNC_OFFSET 0x200
+
+static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
+{
+ unsigned long cpsr;
+ unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
+ bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
+ u32 return_offset = (is_thumb) ? 4 : 0;
+ u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+
+ cpsr = mode | COMPAT_PSR_I_BIT;
+
+ if (sctlr & (1 << 30))
+ cpsr |= COMPAT_PSR_T_BIT;
+ if (sctlr & (1 << 25))
+ cpsr |= COMPAT_PSR_E_BIT;
+
+ *vcpu_cpsr(vcpu) = cpsr;
+
+ /* Note: These now point to the banked copies */
+ *vcpu_spsr(vcpu) = new_spsr_value;
+ *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+
+ /* Branch to exception vector */
+ if (sctlr & (1 << 13))
+ vect_offset += 0xffff0000;
+ else /* always have security exceptions */
+ vect_offset += vcpu_cp15(vcpu, c12_VBAR);
+
+ *vcpu_pc(vcpu) = vect_offset;
+}
+
+static void inject_undef32(struct kvm_vcpu *vcpu)
+{
+ prepare_fault32(vcpu, COMPAT_PSR_MODE_UND, 4);
+}
+
+/*
+ * Modelled after TakeDataAbortException() and TakePrefetchAbortException
+ * pseudocode.
+ */
+static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
+ unsigned long addr)
+{
+ u32 vect_offset;
+ u32 *far, *fsr;
+ bool is_lpae;
+
+ if (is_pabt) {
+ vect_offset = 12;
+ far = &vcpu_cp15(vcpu, c6_IFAR);
+ fsr = &vcpu_cp15(vcpu, c5_IFSR);
+ } else { /* !iabt */
+ vect_offset = 16;
+ far = &vcpu_cp15(vcpu, c6_DFAR);
+ fsr = &vcpu_cp15(vcpu, c5_DFSR);
+ }
+
+ prepare_fault32(vcpu, COMPAT_PSR_MODE_ABT | COMPAT_PSR_A_BIT, vect_offset);
+
+ *far = addr;
+
+ /* Give the guest an IMPLEMENTATION DEFINED exception */
+ is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
+ if (is_lpae)
+ *fsr = 1 << 9 | 0x34;
+ else
+ *fsr = 0x14;
+}
+
+static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
+{
+ unsigned long cpsr = *vcpu_cpsr(vcpu);
+ bool is_aarch32;
+ u32 esr = 0;
+
+ is_aarch32 = vcpu_mode_is_32bit(vcpu);
+
+ *vcpu_spsr(vcpu) = cpsr;
+ *vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+
+ *vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+ *vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
+
+ vcpu_sys_reg(vcpu, FAR_EL1) = addr;
+
+ /*
+ * Build an {i,d}abort, depending on the level and the
+ * instruction set. Report an external synchronous abort.
+ */
+ if (kvm_vcpu_trap_il_is32bit(vcpu))
+ esr |= ESR_EL1_IL;
+
+ /*
+ * Here, the guest runs in AArch64 mode when in EL1. If we get
+ * an AArch32 fault, it means we managed to trap an EL0 fault.
+ */
+ if (is_aarch32 || (cpsr & PSR_MODE_MASK) == PSR_MODE_EL0t)
+ esr |= (ESR_EL1_EC_IABT_EL0 << ESR_EL1_EC_SHIFT);
+ else
+ esr |= (ESR_EL1_EC_IABT_EL1 << ESR_EL1_EC_SHIFT);
+
+ if (!is_iabt)
+ esr |= ESR_EL1_EC_DABT_EL0;
+
+ vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_EL2_EC_xABT_xFSR_EXTABT;
+}
+
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+ unsigned long cpsr = *vcpu_cpsr(vcpu);
+ u32 esr = (ESR_EL1_EC_UNKNOWN << ESR_EL1_EC_SHIFT);
+
+ *vcpu_spsr(vcpu) = cpsr;
+ *vcpu_elr_el1(vcpu) = *vcpu_pc(vcpu);
+
+ *vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+ *vcpu_pc(vcpu) = vcpu_sys_reg(vcpu, VBAR_EL1) + EL1_EXCEPT_SYNC_OFFSET;
+
+ /*
+ * Build an unknown exception, depending on the instruction
+ * set.
+ */
+ if (kvm_vcpu_trap_il_is32bit(vcpu))
+ esr |= ESR_EL1_IL;
+
+ vcpu_sys_reg(vcpu, ESR_EL1) = esr;
+}
+
+/**
+ * kvm_inject_dabt - inject a data abort into the guest
+ * @vcpu: The VCPU to receive the undefined exception
+ * @addr: The address to report in the DFAR
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+ if (!(vcpu->arch.hcr_el2 & HCR_RW))
+ inject_abt32(vcpu, false, addr);
+
+ inject_abt64(vcpu, false, addr);
+}
+
+/**
+ * kvm_inject_pabt - inject a prefetch abort into the guest
+ * @vcpu: The VCPU to receive the undefined exception
+ * @addr: The address to report in the DFAR
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+ if (!(vcpu->arch.hcr_el2 & HCR_RW))
+ inject_abt32(vcpu, true, addr);
+
+ inject_abt64(vcpu, true, addr);
+}
+
+/**
+ * kvm_inject_undefined - inject an undefined instruction into the guest
+ *
+ * It is assumed that this code is called from the VCPU thread and that the
+ * VCPU therefore is not currently executing guest code.
+ */
+void kvm_inject_undefined(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.hcr_el2 & HCR_RW))
+ inject_undef32(vcpu);
+
+ inject_undef64(vcpu);
+}
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
new file mode 100644
index 0000000..bbc6ae3
--- /dev/null
+++ b/arch/arm64/kvm/regmap.c
@@ -0,0 +1,168 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/emulate.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/ptrace.h>
+
+#define VCPU_NR_MODES 6
+#define REG_OFFSET(_reg) \
+ (offsetof(struct user_pt_regs, _reg) / sizeof(unsigned long))
+
+#define USR_REG_OFFSET(R) REG_OFFSET(compat_usr(R))
+
+static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
+ /* USR Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+ USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+ USR_REG_OFFSET(12), USR_REG_OFFSET(13), USR_REG_OFFSET(14),
+ REG_OFFSET(pc)
+ },
+
+ /* FIQ Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7),
+ REG_OFFSET(compat_r8_fiq), /* r8 */
+ REG_OFFSET(compat_r9_fiq), /* r9 */
+ REG_OFFSET(compat_r10_fiq), /* r10 */
+ REG_OFFSET(compat_r11_fiq), /* r11 */
+ REG_OFFSET(compat_r12_fiq), /* r12 */
+ REG_OFFSET(compat_sp_fiq), /* r13 */
+ REG_OFFSET(compat_lr_fiq), /* r14 */
+ REG_OFFSET(pc)
+ },
+
+ /* IRQ Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+ USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+ USR_REG_OFFSET(12),
+ REG_OFFSET(compat_sp_irq), /* r13 */
+ REG_OFFSET(compat_lr_irq), /* r14 */
+ REG_OFFSET(pc)
+ },
+
+ /* SVC Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+ USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+ USR_REG_OFFSET(12),
+ REG_OFFSET(compat_sp_svc), /* r13 */
+ REG_OFFSET(compat_lr_svc), /* r14 */
+ REG_OFFSET(pc)
+ },
+
+ /* ABT Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+ USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+ USR_REG_OFFSET(12),
+ REG_OFFSET(compat_sp_abt), /* r13 */
+ REG_OFFSET(compat_lr_abt), /* r14 */
+ REG_OFFSET(pc)
+ },
+
+ /* UND Registers */
+ {
+ USR_REG_OFFSET(0), USR_REG_OFFSET(1), USR_REG_OFFSET(2),
+ USR_REG_OFFSET(3), USR_REG_OFFSET(4), USR_REG_OFFSET(5),
+ USR_REG_OFFSET(6), USR_REG_OFFSET(7), USR_REG_OFFSET(8),
+ USR_REG_OFFSET(9), USR_REG_OFFSET(10), USR_REG_OFFSET(11),
+ USR_REG_OFFSET(12),
+ REG_OFFSET(compat_sp_und), /* r13 */
+ REG_OFFSET(compat_lr_und), /* r14 */
+ REG_OFFSET(pc)
+ },
+};
+
+/*
+ * Return a pointer to the register number valid in the current mode of
+ * the virtual CPU.
+ */
+unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
+{
+ unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
+ unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+
+ switch (mode) {
+ case COMPAT_PSR_MODE_USR ... COMPAT_PSR_MODE_SVC:
+ mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */
+ break;
+
+ case COMPAT_PSR_MODE_ABT:
+ mode = 4;
+ break;
+
+ case COMPAT_PSR_MODE_UND:
+ mode = 5;
+ break;
+
+ case COMPAT_PSR_MODE_SYS:
+ mode = 0; /* SYS maps to USR */
+ break;
+
+ default:
+ BUG();
+ }
+
+ return reg_array + vcpu_reg_offsets[mode][reg_num];
+}
+
+/*
+ * Return the SPSR for the current mode of the virtual CPU.
+ */
+unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu)
+{
+ unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+ switch (mode) {
+ case COMPAT_PSR_MODE_SVC:
+ mode = KVM_SPSR_SVC;
+ break;
+ case COMPAT_PSR_MODE_ABT:
+ mode = KVM_SPSR_ABT;
+ break;
+ case COMPAT_PSR_MODE_UND:
+ mode = KVM_SPSR_UND;
+ break;
+ case COMPAT_PSR_MODE_IRQ:
+ mode = KVM_SPSR_IRQ;
+ break;
+ case COMPAT_PSR_MODE_FIQ:
+ mode = KVM_SPSR_FIQ;
+ break;
+ default:
+ BUG();
+ }
+
+ return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[mode];
+}
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
new file mode 100644
index 0000000..70a7816
--- /dev/null
+++ b/arch/arm64/kvm/reset.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/reset.c
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/errno.h>
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+
+#include <kvm/arm_arch_timer.h>
+
+#include <asm/cputype.h>
+#include <asm/ptrace.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_coproc.h>
+
+/*
+ * ARMv8 Reset Values
+ */
+static const struct kvm_regs default_regs_reset = {
+ .regs.pstate = (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT |
+ PSR_F_BIT | PSR_D_BIT),
+};
+
+static const struct kvm_regs default_regs_reset32 = {
+ .regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT |
+ COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT),
+};
+
+static const struct kvm_irq_level default_vtimer_irq = {
+ .irq = 27,
+ .level = 1,
+};
+
+static bool cpu_has_32bit_el1(void)
+{
+ u64 pfr0;
+
+ pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+ return !!(pfr0 & 0x20);
+}
+
+int kvm_arch_dev_ioctl_check_extension(long ext)
+{
+ int r;
+
+ switch (ext) {
+ case KVM_CAP_ARM_EL1_32BIT:
+ r = cpu_has_32bit_el1();
+ break;
+ default:
+ r = 0;
+ }
+
+ return r;
+}
+
+/**
+ * kvm_reset_vcpu - sets core registers and sys_regs to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on
+ * the virtual CPU struct to their architectually defined reset
+ * values.
+ */
+int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
+{
+ const struct kvm_irq_level *cpu_vtimer_irq;
+ const struct kvm_regs *cpu_reset;
+
+ switch (vcpu->arch.target) {
+ default:
+ if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
+ if (!cpu_has_32bit_el1())
+ return -EINVAL;
+ cpu_reset = &default_regs_reset32;
+ vcpu->arch.hcr_el2 &= ~HCR_RW;
+ } else {
+ cpu_reset = &default_regs_reset;
+ }
+
+ cpu_vtimer_irq = &default_vtimer_irq;
+ break;
+ }
+
+ /* Reset core registers */
+ memcpy(vcpu_gp_regs(vcpu), cpu_reset, sizeof(*cpu_reset));
+
+ /* Reset system registers */
+ kvm_reset_sys_regs(vcpu);
+
+ /* Reset timer */
+ kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
+
+ return 0;
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
new file mode 100644
index 0000000..4cc3b719
--- /dev/null
+++ b/arch/arm64/kvm/sys_regs.c
@@ -0,0 +1,1528 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/coproc.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: Rusty Russell <rusty@rustcorp.com.au>
+ * Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/mm.h>
+#include <linux/kvm_host.h>
+#include <linux/uaccess.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
+#include <asm/cacheflush.h>
+#include <asm/cputype.h>
+#include <asm/debug-monitors.h>
+#include <trace/events/kvm.h>
+
+#include "sys_regs.h"
+
+/*
+ * All of this file is extremly similar to the ARM coproc.c, but the
+ * types are different. My gut feeling is that it should be pretty
+ * easy to merge, but that would be an ABI breakage -- again. VFP
+ * would also need to be abstracted.
+ *
+ * For AArch32, we only take care of what is being trapped. Anything
+ * that has to do with init and userspace access has to go via the
+ * 64bit interface.
+ */
+
+/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
+static u32 cache_levels;
+
+/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
+#define CSSELR_MAX 12
+
+/* Which cache CCSIDR represents depends on CSSELR value. */
+static u32 get_ccsidr(u32 csselr)
+{
+ u32 ccsidr;
+
+ /* Make sure noone else changes CSSELR during this! */
+ local_irq_disable();
+ /* Put value into CSSELR */
+ asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+ isb();
+ /* Read result out of CCSIDR */
+ asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
+ local_irq_enable();
+
+ return ccsidr;
+}
+
+static void do_dc_cisw(u32 val)
+{
+ asm volatile("dc cisw, %x0" : : "r" (val));
+ dsb(ish);
+}
+
+static void do_dc_csw(u32 val)
+{
+ asm volatile("dc csw, %x0" : : "r" (val));
+ dsb(ish);
+}
+
+/* See note at ARM ARM B1.14.4 */
+static bool access_dcsw(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ unsigned long val;
+ int cpu;
+
+ if (!p->is_write)
+ return read_from_write_only(vcpu, p);
+
+ cpu = get_cpu();
+
+ cpumask_setall(&vcpu->arch.require_dcache_flush);
+ cpumask_clear_cpu(cpu, &vcpu->arch.require_dcache_flush);
+
+ /* If we were already preempted, take the long way around */
+ if (cpu != vcpu->arch.last_pcpu) {
+ flush_cache_all();
+ goto done;
+ }
+
+ val = *vcpu_reg(vcpu, p->Rt);
+
+ switch (p->CRm) {
+ case 6: /* Upgrade DCISW to DCCISW, as per HCR.SWIO */
+ case 14: /* DCCISW */
+ do_dc_cisw(val);
+ break;
+
+ case 10: /* DCCSW */
+ do_dc_csw(val);
+ break;
+ }
+
+done:
+ put_cpu();
+
+ return true;
+}
+
+/*
+ * Generic accessor for VM registers. Only called as long as HCR_TVM
+ * is set.
+ */
+static bool access_vm_reg(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ unsigned long val;
+
+ BUG_ON(!p->is_write);
+
+ val = *vcpu_reg(vcpu, p->Rt);
+ if (!p->is_aarch32) {
+ vcpu_sys_reg(vcpu, r->reg) = val;
+ } else {
+ if (!p->is_32bit)
+ vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
+ vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+ }
+
+ return true;
+}
+
+/*
+ * SCTLR_EL1 accessor. Only called as long as HCR_TVM is set. If the
+ * guest enables the MMU, we stop trapping the VM sys_regs and leave
+ * it in complete control of the caches.
+ */
+static bool access_sctlr(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ access_vm_reg(vcpu, p, r);
+
+ if (vcpu_has_cache_enabled(vcpu)) { /* MMU+Caches enabled? */
+ vcpu->arch.hcr_el2 &= ~HCR_TVM;
+ stage2_flush_vm(vcpu->kvm);
+ }
+
+ return true;
+}
+
+static bool trap_raz_wi(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+ else
+ return read_zero(vcpu, p);
+}
+
+static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = (1 << 3);
+ return true;
+ }
+}
+
+static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ u32 val;
+ asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
+ *vcpu_reg(vcpu, p->Rt) = val;
+ return true;
+ }
+}
+
+/*
+ * We want to avoid world-switching all the DBG registers all the
+ * time:
+ *
+ * - If we've touched any debug register, it is likely that we're
+ * going to touch more of them. It then makes sense to disable the
+ * traps and start doing the save/restore dance
+ * - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
+ * then mandatory to save/restore the registers, as the guest
+ * depends on them.
+ *
+ * For this, we use a DIRTY bit, indicating the guest has modified the
+ * debug registers, used as follow:
+ *
+ * On guest entry:
+ * - If the dirty bit is set (because we're coming back from trapping),
+ * disable the traps, save host registers, restore guest registers.
+ * - If debug is actively in use (DBG_MDSCR_KDE or DBG_MDSCR_MDE set),
+ * set the dirty bit, disable the traps, save host registers,
+ * restore guest registers.
+ * - Otherwise, enable the traps
+ *
+ * On guest exit:
+ * - If the dirty bit is set, save guest registers, restore host
+ * registers and clear the dirty bit. This ensure that the host can
+ * now use the debug registers.
+ */
+static bool trap_debug_regs(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+ vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+ }
+
+ return true;
+}
+
+static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ u64 amair;
+
+ asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
+ vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
+}
+
+static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ /*
+ * Simply map the vcpu_id into the Aff0 field of the MPIDR.
+ */
+ vcpu_sys_reg(vcpu, MPIDR_EL1) = (1UL << 31) | (vcpu->vcpu_id & 0xff);
+}
+
+/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
+#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
+ /* DBGBVRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
+ trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \
+ /* DBGBCRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
+ trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \
+ /* DBGWVRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
+ trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \
+ /* DBGWCRn_EL1 */ \
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
+ trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 }
+
+/*
+ * Architected system registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * We could trap ID_DFR0 and tell the guest we don't support performance
+ * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
+ * NAKed, so it will read the PMCR anyway.
+ *
+ * Therefore we tell the guest we have 0 counters. Unfortunately, we
+ * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
+ * all PM registers, which doesn't crash the guest kernel at least.
+ *
+ * Debug handling: We do trap most, if not all debug related system
+ * registers. The implementation is good enough to ensure that a guest
+ * can use these with minimal performance degradation. The drawback is
+ * that we don't implement any of the external debug, none of the
+ * OSlock protocol. This should be revisited if we ever encounter a
+ * more demanding guest...
+ */
+static const struct sys_reg_desc sys_reg_descs[] = {
+ /* DC ISW */
+ { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010),
+ access_dcsw },
+ /* DC CSW */
+ { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010),
+ access_dcsw },
+ /* DC CISW */
+ { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
+ access_dcsw },
+
+ DBG_BCR_BVR_WCR_WVR_EL1(0),
+ DBG_BCR_BVR_WCR_WVR_EL1(1),
+ /* MDCCINT_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+ trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+ /* MDSCR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+ trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+ DBG_BCR_BVR_WCR_WVR_EL1(2),
+ DBG_BCR_BVR_WCR_WVR_EL1(3),
+ DBG_BCR_BVR_WCR_WVR_EL1(4),
+ DBG_BCR_BVR_WCR_WVR_EL1(5),
+ DBG_BCR_BVR_WCR_WVR_EL1(6),
+ DBG_BCR_BVR_WCR_WVR_EL1(7),
+ DBG_BCR_BVR_WCR_WVR_EL1(8),
+ DBG_BCR_BVR_WCR_WVR_EL1(9),
+ DBG_BCR_BVR_WCR_WVR_EL1(10),
+ DBG_BCR_BVR_WCR_WVR_EL1(11),
+ DBG_BCR_BVR_WCR_WVR_EL1(12),
+ DBG_BCR_BVR_WCR_WVR_EL1(13),
+ DBG_BCR_BVR_WCR_WVR_EL1(14),
+ DBG_BCR_BVR_WCR_WVR_EL1(15),
+
+ /* MDRAR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+ trap_raz_wi },
+ /* OSLAR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
+ trap_raz_wi },
+ /* OSLSR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
+ trap_oslsr_el1 },
+ /* OSDLR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
+ trap_raz_wi },
+ /* DBGPRCR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
+ trap_raz_wi },
+ /* DBGCLAIMSET_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
+ trap_raz_wi },
+ /* DBGCLAIMCLR_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
+ trap_raz_wi },
+ /* DBGAUTHSTATUS_EL1 */
+ { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
+ trap_dbgauthstatus_el1 },
+
+ /* TEECR32_EL1 */
+ { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
+ NULL, reset_val, TEECR32_EL1, 0 },
+ /* TEEHBR32_EL1 */
+ { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
+ NULL, reset_val, TEEHBR32_EL1, 0 },
+
+ /* MDCCSR_EL1 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
+ trap_raz_wi },
+ /* DBGDTR_EL0 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
+ trap_raz_wi },
+ /* DBGDTR[TR]X_EL0 */
+ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
+ trap_raz_wi },
+
+ /* DBGVCR32_EL2 */
+ { Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
+ NULL, reset_val, DBGVCR32_EL2, 0 },
+
+ /* MPIDR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101),
+ NULL, reset_mpidr, MPIDR_EL1 },
+ /* SCTLR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
+ access_sctlr, reset_val, SCTLR_EL1, 0x00C50078 },
+ /* CPACR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
+ NULL, reset_val, CPACR_EL1, 0 },
+ /* TTBR0_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
+ access_vm_reg, reset_unknown, TTBR0_EL1 },
+ /* TTBR1_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
+ access_vm_reg, reset_unknown, TTBR1_EL1 },
+ /* TCR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
+ access_vm_reg, reset_val, TCR_EL1, 0 },
+
+ /* AFSR0_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
+ access_vm_reg, reset_unknown, AFSR0_EL1 },
+ /* AFSR1_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
+ access_vm_reg, reset_unknown, AFSR1_EL1 },
+ /* ESR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
+ access_vm_reg, reset_unknown, ESR_EL1 },
+ /* FAR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
+ access_vm_reg, reset_unknown, FAR_EL1 },
+ /* PAR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
+ NULL, reset_unknown, PAR_EL1 },
+
+ /* PMINTENSET_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
+ trap_raz_wi },
+ /* PMINTENCLR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
+ trap_raz_wi },
+
+ /* MAIR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
+ access_vm_reg, reset_unknown, MAIR_EL1 },
+ /* AMAIR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
+ access_vm_reg, reset_amair_el1, AMAIR_EL1 },
+
+ /* VBAR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
+ NULL, reset_val, VBAR_EL1, 0 },
+ /* CONTEXTIDR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
+ access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
+ /* TPIDR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
+ NULL, reset_unknown, TPIDR_EL1 },
+
+ /* CNTKCTL_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000),
+ NULL, reset_val, CNTKCTL_EL1, 0},
+
+ /* CSSELR_EL1 */
+ { Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
+ NULL, reset_unknown, CSSELR_EL1 },
+
+ /* PMCR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
+ trap_raz_wi },
+ /* PMCNTENSET_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
+ trap_raz_wi },
+ /* PMCNTENCLR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
+ trap_raz_wi },
+ /* PMOVSCLR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
+ trap_raz_wi },
+ /* PMSWINC_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
+ trap_raz_wi },
+ /* PMSELR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
+ trap_raz_wi },
+ /* PMCEID0_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
+ trap_raz_wi },
+ /* PMCEID1_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
+ trap_raz_wi },
+ /* PMCCNTR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
+ trap_raz_wi },
+ /* PMXEVTYPER_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
+ trap_raz_wi },
+ /* PMXEVCNTR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
+ trap_raz_wi },
+ /* PMUSERENR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
+ trap_raz_wi },
+ /* PMOVSSET_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
+ trap_raz_wi },
+
+ /* TPIDR_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
+ NULL, reset_unknown, TPIDR_EL0 },
+ /* TPIDRRO_EL0 */
+ { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
+ NULL, reset_unknown, TPIDRRO_EL0 },
+
+ /* DACR32_EL2 */
+ { Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
+ NULL, reset_unknown, DACR32_EL2 },
+ /* IFSR32_EL2 */
+ { Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0000), Op2(0b001),
+ NULL, reset_unknown, IFSR32_EL2 },
+ /* FPEXC32_EL2 */
+ { Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0011), Op2(0b000),
+ NULL, reset_val, FPEXC32_EL2, 0x70 },
+};
+
+static bool trap_dbgidr(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ return ignore_write(vcpu, p);
+ } else {
+ u64 dfr = read_cpuid(ID_AA64DFR0_EL1);
+ u64 pfr = read_cpuid(ID_AA64PFR0_EL1);
+ u32 el3 = !!((pfr >> 12) & 0xf);
+
+ *vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) |
+ (((dfr >> 12) & 0xf) << 24) |
+ (((dfr >> 28) & 0xf) << 20) |
+ (6 << 16) | (el3 << 14) | (el3 << 12));
+ return true;
+ }
+}
+
+static bool trap_debug32(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+ vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+ } else {
+ *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+ }
+
+ return true;
+}
+
+#define DBG_BCR_BVR_WCR_WVR(n) \
+ /* DBGBVRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32, \
+ NULL, (cp14_DBGBVR0 + (n) * 2) }, \
+ /* DBGBCRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32, \
+ NULL, (cp14_DBGBCR0 + (n) * 2) }, \
+ /* DBGWVRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32, \
+ NULL, (cp14_DBGWVR0 + (n) * 2) }, \
+ /* DBGWCRn */ \
+ { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32, \
+ NULL, (cp14_DBGWCR0 + (n) * 2) }
+
+#define DBGBXVR(n) \
+ { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32, \
+ NULL, cp14_DBGBXVR0 + n * 2 }
+
+/*
+ * Trapped cp14 registers. We generally ignore most of the external
+ * debug, on the principle that they don't really make sense to a
+ * guest. Revisit this one day, whould this principle change.
+ */
+static const struct sys_reg_desc cp14_regs[] = {
+ /* DBGIDR */
+ { Op1( 0), CRn( 0), CRm( 0), Op2( 0), trap_dbgidr },
+ /* DBGDTRRXext */
+ { Op1( 0), CRn( 0), CRm( 0), Op2( 2), trap_raz_wi },
+
+ DBG_BCR_BVR_WCR_WVR(0),
+ /* DBGDSCRint */
+ { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(1),
+ /* DBGDCCINT */
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+ /* DBGDSCRext */
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+ DBG_BCR_BVR_WCR_WVR(2),
+ /* DBGDTR[RT]Xint */
+ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
+ /* DBGDTR[RT]Xext */
+ { Op1( 0), CRn( 0), CRm( 3), Op2( 2), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(3),
+ DBG_BCR_BVR_WCR_WVR(4),
+ DBG_BCR_BVR_WCR_WVR(5),
+ /* DBGWFAR */
+ { Op1( 0), CRn( 0), CRm( 6), Op2( 0), trap_raz_wi },
+ /* DBGOSECCR */
+ { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
+ DBG_BCR_BVR_WCR_WVR(6),
+ /* DBGVCR */
+ { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+ DBG_BCR_BVR_WCR_WVR(7),
+ DBG_BCR_BVR_WCR_WVR(8),
+ DBG_BCR_BVR_WCR_WVR(9),
+ DBG_BCR_BVR_WCR_WVR(10),
+ DBG_BCR_BVR_WCR_WVR(11),
+ DBG_BCR_BVR_WCR_WVR(12),
+ DBG_BCR_BVR_WCR_WVR(13),
+ DBG_BCR_BVR_WCR_WVR(14),
+ DBG_BCR_BVR_WCR_WVR(15),
+
+ /* DBGDRAR (32bit) */
+ { Op1( 0), CRn( 1), CRm( 0), Op2( 0), trap_raz_wi },
+
+ DBGBXVR(0),
+ /* DBGOSLAR */
+ { Op1( 0), CRn( 1), CRm( 0), Op2( 4), trap_raz_wi },
+ DBGBXVR(1),
+ /* DBGOSLSR */
+ { Op1( 0), CRn( 1), CRm( 1), Op2( 4), trap_oslsr_el1 },
+ DBGBXVR(2),
+ DBGBXVR(3),
+ /* DBGOSDLR */
+ { Op1( 0), CRn( 1), CRm( 3), Op2( 4), trap_raz_wi },
+ DBGBXVR(4),
+ /* DBGPRCR */
+ { Op1( 0), CRn( 1), CRm( 4), Op2( 4), trap_raz_wi },
+ DBGBXVR(5),
+ DBGBXVR(6),
+ DBGBXVR(7),
+ DBGBXVR(8),
+ DBGBXVR(9),
+ DBGBXVR(10),
+ DBGBXVR(11),
+ DBGBXVR(12),
+ DBGBXVR(13),
+ DBGBXVR(14),
+ DBGBXVR(15),
+
+ /* DBGDSAR (32bit) */
+ { Op1( 0), CRn( 2), CRm( 0), Op2( 0), trap_raz_wi },
+
+ /* DBGDEVID2 */
+ { Op1( 0), CRn( 7), CRm( 0), Op2( 7), trap_raz_wi },
+ /* DBGDEVID1 */
+ { Op1( 0), CRn( 7), CRm( 1), Op2( 7), trap_raz_wi },
+ /* DBGDEVID */
+ { Op1( 0), CRn( 7), CRm( 2), Op2( 7), trap_raz_wi },
+ /* DBGCLAIMSET */
+ { Op1( 0), CRn( 7), CRm( 8), Op2( 6), trap_raz_wi },
+ /* DBGCLAIMCLR */
+ { Op1( 0), CRn( 7), CRm( 9), Op2( 6), trap_raz_wi },
+ /* DBGAUTHSTATUS */
+ { Op1( 0), CRn( 7), CRm(14), Op2( 6), trap_dbgauthstatus_el1 },
+};
+
+/* Trapped cp14 64bit registers */
+static const struct sys_reg_desc cp14_64_regs[] = {
+ /* DBGDRAR (64bit) */
+ { Op1( 0), CRm( 1), .access = trap_raz_wi },
+
+ /* DBGDSAR (64bit) */
+ { Op1( 0), CRm( 2), .access = trap_raz_wi },
+};
+
+/*
+ * Trapped cp15 registers. TTBR0/TTBR1 get a double encoding,
+ * depending on the way they are accessed (as a 32bit or a 64bit
+ * register).
+ */
+static const struct sys_reg_desc cp15_regs[] = {
+ { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_sctlr, NULL, c1_SCTLR },
+ { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+ { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 },
+ { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR },
+ { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR },
+ { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR },
+ { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR },
+ { Op1( 0), CRn( 5), CRm( 1), Op2( 0), access_vm_reg, NULL, c5_ADFSR },
+ { Op1( 0), CRn( 5), CRm( 1), Op2( 1), access_vm_reg, NULL, c5_AIFSR },
+ { Op1( 0), CRn( 6), CRm( 0), Op2( 0), access_vm_reg, NULL, c6_DFAR },
+ { Op1( 0), CRn( 6), CRm( 0), Op2( 2), access_vm_reg, NULL, c6_IFAR },
+
+ /*
+ * DC{C,I,CI}SW operations:
+ */
+ { Op1( 0), CRn( 7), CRm( 6), Op2( 2), access_dcsw },
+ { Op1( 0), CRn( 7), CRm(10), Op2( 2), access_dcsw },
+ { Op1( 0), CRn( 7), CRm(14), Op2( 2), access_dcsw },
+
+ /* PMU */
+ { Op1( 0), CRn( 9), CRm(12), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 2), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 3), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 5), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 6), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(12), Op2( 7), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(13), Op2( 2), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 0), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 1), trap_raz_wi },
+ { Op1( 0), CRn( 9), CRm(14), Op2( 2), trap_raz_wi },
+
+ { Op1( 0), CRn(10), CRm( 2), Op2( 0), access_vm_reg, NULL, c10_PRRR },
+ { Op1( 0), CRn(10), CRm( 2), Op2( 1), access_vm_reg, NULL, c10_NMRR },
+ { Op1( 0), CRn(10), CRm( 3), Op2( 0), access_vm_reg, NULL, c10_AMAIR0 },
+ { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
+ { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
+};
+
+static const struct sys_reg_desc cp15_64_regs[] = {
+ { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR0 },
+ { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, c2_TTBR1 },
+};
+
+/* Target specific emulation tables */
+static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS];
+
+void kvm_register_target_sys_reg_table(unsigned int target,
+ struct kvm_sys_reg_target_table *table)
+{
+ target_tables[target] = table;
+}
+
+/* Get specific register table for this target. */
+static const struct sys_reg_desc *get_target_table(unsigned target,
+ bool mode_is_64,
+ size_t *num)
+{
+ struct kvm_sys_reg_target_table *table;
+
+ table = target_tables[target];
+ if (mode_is_64) {
+ *num = table->table64.num;
+ return table->table64.table;
+ } else {
+ *num = table->table32.num;
+ return table->table32.table;
+ }
+}
+
+static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
+ const struct sys_reg_desc table[],
+ unsigned int num)
+{
+ unsigned int i;
+
+ for (i = 0; i < num; i++) {
+ const struct sys_reg_desc *r = &table[i];
+
+ if (params->Op0 != r->Op0)
+ continue;
+ if (params->Op1 != r->Op1)
+ continue;
+ if (params->CRn != r->CRn)
+ continue;
+ if (params->CRm != r->CRm)
+ continue;
+ if (params->Op2 != r->Op2)
+ continue;
+
+ return r;
+ }
+ return NULL;
+}
+
+int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
+/*
+ * emulate_cp -- tries to match a sys_reg access in a handling table, and
+ * call the corresponding trap handler.
+ *
+ * @params: pointer to the descriptor of the access
+ * @table: array of trap descriptors
+ * @num: size of the trap descriptor array
+ *
+ * Return 0 if the access has been handled, and -1 if not.
+ */
+static int emulate_cp(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params,
+ const struct sys_reg_desc *table,
+ size_t num)
+{
+ const struct sys_reg_desc *r;
+
+ if (!table)
+ return -1; /* Not handled */
+
+ r = find_reg(params, table, num);
+
+ if (r) {
+ /*
+ * Not having an accessor means that we have
+ * configured a trap that we don't know how to
+ * handle. This certainly qualifies as a gross bug
+ * that should be fixed right away.
+ */
+ BUG_ON(!r->access);
+
+ if (likely(r->access(vcpu, params, r))) {
+ /* Skip instruction, since it was emulated */
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ }
+
+ /* Handled */
+ return 0;
+ }
+
+ /* Not handled */
+ return -1;
+}
+
+static void unhandled_cp_access(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *params)
+{
+ u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu);
+ int cp;
+
+ switch(hsr_ec) {
+ case ESR_EL2_EC_CP15_32:
+ case ESR_EL2_EC_CP15_64:
+ cp = 15;
+ break;
+ case ESR_EL2_EC_CP14_MR:
+ case ESR_EL2_EC_CP14_64:
+ cp = 14;
+ break;
+ default:
+ WARN_ON((cp = -1));
+ }
+
+ kvm_err("Unsupported guest CP%d access at: %08lx\n",
+ cp, *vcpu_pc(vcpu));
+ print_sys_reg_instr(params);
+ kvm_inject_undefined(vcpu);
+}
+
+/**
+ * kvm_handle_cp_64 -- handles a mrrc/mcrr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *global,
+ size_t nr_global,
+ const struct sys_reg_desc *target_specific,
+ size_t nr_specific)
+{
+ struct sys_reg_params params;
+ u32 hsr = kvm_vcpu_get_hsr(vcpu);
+ int Rt2 = (hsr >> 10) & 0xf;
+
+ params.is_aarch32 = true;
+ params.is_32bit = false;
+ params.CRm = (hsr >> 1) & 0xf;
+ params.Rt = (hsr >> 5) & 0xf;
+ params.is_write = ((hsr & 1) == 0);
+
+ params.Op0 = 0;
+ params.Op1 = (hsr >> 16) & 0xf;
+ params.Op2 = 0;
+ params.CRn = 0;
+
+ /*
+ * Massive hack here. Store Rt2 in the top 32bits so we only
+ * have one register to deal with. As we use the same trap
+ * backends between AArch32 and AArch64, we get away with it.
+ */
+ if (params.is_write) {
+ u64 val = *vcpu_reg(vcpu, params.Rt);
+ val &= 0xffffffff;
+ val |= *vcpu_reg(vcpu, Rt2) << 32;
+ *vcpu_reg(vcpu, params.Rt) = val;
+ }
+
+ if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific))
+ goto out;
+ if (!emulate_cp(vcpu, ¶ms, global, nr_global))
+ goto out;
+
+ unhandled_cp_access(vcpu, ¶ms);
+
+out:
+ /* Do the opposite hack for the read side */
+ if (!params.is_write) {
+ u64 val = *vcpu_reg(vcpu, params.Rt);
+ val >>= 32;
+ *vcpu_reg(vcpu, Rt2) = val;
+ }
+
+ return 1;
+}
+
+/**
+ * kvm_handle_cp15_32 -- handles a mrc/mcr trap on a guest CP15 access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *global,
+ size_t nr_global,
+ const struct sys_reg_desc *target_specific,
+ size_t nr_specific)
+{
+ struct sys_reg_params params;
+ u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+ params.is_aarch32 = true;
+ params.is_32bit = true;
+ params.CRm = (hsr >> 1) & 0xf;
+ params.Rt = (hsr >> 5) & 0xf;
+ params.is_write = ((hsr & 1) == 0);
+ params.CRn = (hsr >> 10) & 0xf;
+ params.Op0 = 0;
+ params.Op1 = (hsr >> 14) & 0x7;
+ params.Op2 = (hsr >> 17) & 0x7;
+
+ if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific))
+ return 1;
+ if (!emulate_cp(vcpu, ¶ms, global, nr_global))
+ return 1;
+
+ unhandled_cp_access(vcpu, ¶ms);
+ return 1;
+}
+
+int kvm_handle_cp15_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ const struct sys_reg_desc *target_specific;
+ size_t num;
+
+ target_specific = get_target_table(vcpu->arch.target, false, &num);
+ return kvm_handle_cp_64(vcpu,
+ cp15_64_regs, ARRAY_SIZE(cp15_64_regs),
+ target_specific, num);
+}
+
+int kvm_handle_cp15_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ const struct sys_reg_desc *target_specific;
+ size_t num;
+
+ target_specific = get_target_table(vcpu->arch.target, false, &num);
+ return kvm_handle_cp_32(vcpu,
+ cp15_regs, ARRAY_SIZE(cp15_regs),
+ target_specific, num);
+}
+
+int kvm_handle_cp14_64(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ return kvm_handle_cp_64(vcpu,
+ cp14_64_regs, ARRAY_SIZE(cp14_64_regs),
+ NULL, 0);
+}
+
+int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ return kvm_handle_cp_32(vcpu,
+ cp14_regs, ARRAY_SIZE(cp14_regs),
+ NULL, 0);
+}
+
+static int emulate_sys_reg(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params)
+{
+ size_t num;
+ const struct sys_reg_desc *table, *r;
+
+ table = get_target_table(vcpu->arch.target, true, &num);
+
+ /* Search target-specific then generic table. */
+ r = find_reg(params, table, num);
+ if (!r)
+ r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+ if (likely(r)) {
+ /*
+ * Not having an accessor means that we have
+ * configured a trap that we don't know how to
+ * handle. This certainly qualifies as a gross bug
+ * that should be fixed right away.
+ */
+ BUG_ON(!r->access);
+
+ if (likely(r->access(vcpu, params, r))) {
+ /* Skip instruction, since it was emulated */
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+ return 1;
+ }
+ /* If access function fails, it should complain. */
+ } else {
+ kvm_err("Unsupported guest sys_reg access at: %lx\n",
+ *vcpu_pc(vcpu));
+ print_sys_reg_instr(params);
+ }
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
+static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *table, size_t num)
+{
+ unsigned long i;
+
+ for (i = 0; i < num; i++)
+ if (table[i].reset)
+ table[i].reset(vcpu, &table[i]);
+}
+
+/**
+ * kvm_handle_sys_reg -- handles a mrs/msr trap on a guest sys_reg access
+ * @vcpu: The VCPU pointer
+ * @run: The kvm_run struct
+ */
+int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ struct sys_reg_params params;
+ unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+
+ params.is_aarch32 = false;
+ params.is_32bit = false;
+ params.Op0 = (esr >> 20) & 3;
+ params.Op1 = (esr >> 14) & 0x7;
+ params.CRn = (esr >> 10) & 0xf;
+ params.CRm = (esr >> 1) & 0xf;
+ params.Op2 = (esr >> 17) & 0x7;
+ params.Rt = (esr >> 5) & 0x1f;
+ params.is_write = !(esr & 1);
+
+ return emulate_sys_reg(vcpu, ¶ms);
+}
+
+/******************************************************************************
+ * Userspace API
+ *****************************************************************************/
+
+static bool index_to_params(u64 id, struct sys_reg_params *params)
+{
+ switch (id & KVM_REG_SIZE_MASK) {
+ case KVM_REG_SIZE_U64:
+ /* Any unused index bits means it's not valid. */
+ if (id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK
+ | KVM_REG_ARM_COPROC_MASK
+ | KVM_REG_ARM64_SYSREG_OP0_MASK
+ | KVM_REG_ARM64_SYSREG_OP1_MASK
+ | KVM_REG_ARM64_SYSREG_CRN_MASK
+ | KVM_REG_ARM64_SYSREG_CRM_MASK
+ | KVM_REG_ARM64_SYSREG_OP2_MASK))
+ return false;
+ params->Op0 = ((id & KVM_REG_ARM64_SYSREG_OP0_MASK)
+ >> KVM_REG_ARM64_SYSREG_OP0_SHIFT);
+ params->Op1 = ((id & KVM_REG_ARM64_SYSREG_OP1_MASK)
+ >> KVM_REG_ARM64_SYSREG_OP1_SHIFT);
+ params->CRn = ((id & KVM_REG_ARM64_SYSREG_CRN_MASK)
+ >> KVM_REG_ARM64_SYSREG_CRN_SHIFT);
+ params->CRm = ((id & KVM_REG_ARM64_SYSREG_CRM_MASK)
+ >> KVM_REG_ARM64_SYSREG_CRM_SHIFT);
+ params->Op2 = ((id & KVM_REG_ARM64_SYSREG_OP2_MASK)
+ >> KVM_REG_ARM64_SYSREG_OP2_SHIFT);
+ return true;
+ default:
+ return false;
+ }
+}
+
+/* Decode an index value, and find the sys_reg_desc entry. */
+static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
+ u64 id)
+{
+ size_t num;
+ const struct sys_reg_desc *table, *r;
+ struct sys_reg_params params;
+
+ /* We only do sys_reg for now. */
+ if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM64_SYSREG)
+ return NULL;
+
+ if (!index_to_params(id, ¶ms))
+ return NULL;
+
+ table = get_target_table(vcpu->arch.target, true, &num);
+ r = find_reg(¶ms, table, num);
+ if (!r)
+ r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+ /* Not saved in the sys_reg array? */
+ if (r && !r->reg)
+ r = NULL;
+
+ return r;
+}
+
+/*
+ * These are the invariant sys_reg registers: we let the guest see the
+ * host versions of these, so they're part of the guest state.
+ *
+ * A future CPU may provide a mechanism to present different values to
+ * the guest, or a future kvm may trap them.
+ */
+
+#define FUNCTION_INVARIANT(reg) \
+ static void get_##reg(struct kvm_vcpu *v, \
+ const struct sys_reg_desc *r) \
+ { \
+ u64 val; \
+ \
+ asm volatile("mrs %0, " __stringify(reg) "\n" \
+ : "=r" (val)); \
+ ((struct sys_reg_desc *)r)->val = val; \
+ }
+
+FUNCTION_INVARIANT(midr_el1)
+FUNCTION_INVARIANT(ctr_el0)
+FUNCTION_INVARIANT(revidr_el1)
+FUNCTION_INVARIANT(id_pfr0_el1)
+FUNCTION_INVARIANT(id_pfr1_el1)
+FUNCTION_INVARIANT(id_dfr0_el1)
+FUNCTION_INVARIANT(id_afr0_el1)
+FUNCTION_INVARIANT(id_mmfr0_el1)
+FUNCTION_INVARIANT(id_mmfr1_el1)
+FUNCTION_INVARIANT(id_mmfr2_el1)
+FUNCTION_INVARIANT(id_mmfr3_el1)
+FUNCTION_INVARIANT(id_isar0_el1)
+FUNCTION_INVARIANT(id_isar1_el1)
+FUNCTION_INVARIANT(id_isar2_el1)
+FUNCTION_INVARIANT(id_isar3_el1)
+FUNCTION_INVARIANT(id_isar4_el1)
+FUNCTION_INVARIANT(id_isar5_el1)
+FUNCTION_INVARIANT(clidr_el1)
+FUNCTION_INVARIANT(aidr_el1)
+
+/* ->val is filled in by kvm_sys_reg_table_init() */
+static struct sys_reg_desc invariant_sys_regs[] = {
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000),
+ NULL, get_midr_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110),
+ NULL, get_revidr_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000),
+ NULL, get_id_pfr0_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001),
+ NULL, get_id_pfr1_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010),
+ NULL, get_id_dfr0_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011),
+ NULL, get_id_afr0_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100),
+ NULL, get_id_mmfr0_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101),
+ NULL, get_id_mmfr1_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110),
+ NULL, get_id_mmfr2_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111),
+ NULL, get_id_mmfr3_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
+ NULL, get_id_isar0_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001),
+ NULL, get_id_isar1_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
+ NULL, get_id_isar2_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011),
+ NULL, get_id_isar3_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100),
+ NULL, get_id_isar4_el1 },
+ { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101),
+ NULL, get_id_isar5_el1 },
+ { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001),
+ NULL, get_clidr_el1 },
+ { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111),
+ NULL, get_aidr_el1 },
+ { Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001),
+ NULL, get_ctr_el0 },
+};
+
+static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)
+{
+ if (copy_from_user(val, uaddr, KVM_REG_SIZE(id)) != 0)
+ return -EFAULT;
+ return 0;
+}
+
+static int reg_to_user(void __user *uaddr, const u64 *val, u64 id)
+{
+ if (copy_to_user(uaddr, val, KVM_REG_SIZE(id)) != 0)
+ return -EFAULT;
+ return 0;
+}
+
+static int get_invariant_sys_reg(u64 id, void __user *uaddr)
+{
+ struct sys_reg_params params;
+ const struct sys_reg_desc *r;
+
+ if (!index_to_params(id, ¶ms))
+ return -ENOENT;
+
+ r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
+ if (!r)
+ return -ENOENT;
+
+ return reg_to_user(uaddr, &r->val, id);
+}
+
+static int set_invariant_sys_reg(u64 id, void __user *uaddr)
+{
+ struct sys_reg_params params;
+ const struct sys_reg_desc *r;
+ int err;
+ u64 val = 0; /* Make sure high bits are 0 for 32-bit regs */
+
+ if (!index_to_params(id, ¶ms))
+ return -ENOENT;
+ r = find_reg(¶ms, invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs));
+ if (!r)
+ return -ENOENT;
+
+ err = reg_from_user(&val, uaddr, id);
+ if (err)
+ return err;
+
+ /* This is what we mean by invariant: you can't change it. */
+ if (r->val != val)
+ return -EINVAL;
+
+ return 0;
+}
+
+static bool is_valid_cache(u32 val)
+{
+ u32 level, ctype;
+
+ if (val >= CSSELR_MAX)
+ return false;
+
+ /* Bottom bit is Instruction or Data bit. Next 3 bits are level. */
+ level = (val >> 1);
+ ctype = (cache_levels >> (level * 3)) & 7;
+
+ switch (ctype) {
+ case 0: /* No cache */
+ return false;
+ case 1: /* Instruction cache only */
+ return (val & 1);
+ case 2: /* Data cache only */
+ case 4: /* Unified cache */
+ return !(val & 1);
+ case 3: /* Separate instruction and data caches */
+ return true;
+ default: /* Reserved: we can't know instruction or data. */
+ return false;
+ }
+}
+
+static int demux_c15_get(u64 id, void __user *uaddr)
+{
+ u32 val;
+ u32 __user *uval = uaddr;
+
+ /* Fail if we have unknown bits set. */
+ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
+ | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
+ return -ENOENT;
+
+ switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
+ case KVM_REG_ARM_DEMUX_ID_CCSIDR:
+ if (KVM_REG_SIZE(id) != 4)
+ return -ENOENT;
+ val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
+ >> KVM_REG_ARM_DEMUX_VAL_SHIFT;
+ if (!is_valid_cache(val))
+ return -ENOENT;
+
+ return put_user(get_ccsidr(val), uval);
+ default:
+ return -ENOENT;
+ }
+}
+
+static int demux_c15_set(u64 id, void __user *uaddr)
+{
+ u32 val, newval;
+ u32 __user *uval = uaddr;
+
+ /* Fail if we have unknown bits set. */
+ if (id & ~(KVM_REG_ARCH_MASK|KVM_REG_SIZE_MASK|KVM_REG_ARM_COPROC_MASK
+ | ((1 << KVM_REG_ARM_COPROC_SHIFT)-1)))
+ return -ENOENT;
+
+ switch (id & KVM_REG_ARM_DEMUX_ID_MASK) {
+ case KVM_REG_ARM_DEMUX_ID_CCSIDR:
+ if (KVM_REG_SIZE(id) != 4)
+ return -ENOENT;
+ val = (id & KVM_REG_ARM_DEMUX_VAL_MASK)
+ >> KVM_REG_ARM_DEMUX_VAL_SHIFT;
+ if (!is_valid_cache(val))
+ return -ENOENT;
+
+ if (get_user(newval, uval))
+ return -EFAULT;
+
+ /* This is also invariant: you can't change it. */
+ if (newval != get_ccsidr(val))
+ return -EINVAL;
+ return 0;
+ default:
+ return -ENOENT;
+ }
+}
+
+int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ const struct sys_reg_desc *r;
+ void __user *uaddr = (void __user *)(unsigned long)reg->addr;
+
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
+ return demux_c15_get(reg->id, uaddr);
+
+ if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
+ return -ENOENT;
+
+ r = index_to_sys_reg_desc(vcpu, reg->id);
+ if (!r)
+ return get_invariant_sys_reg(reg->id, uaddr);
+
+ return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id);
+}
+
+int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
+{
+ const struct sys_reg_desc *r;
+ void __user *uaddr = (void __user *)(unsigned long)reg->addr;
+
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_DEMUX)
+ return demux_c15_set(reg->id, uaddr);
+
+ if (KVM_REG_SIZE(reg->id) != sizeof(__u64))
+ return -ENOENT;
+
+ r = index_to_sys_reg_desc(vcpu, reg->id);
+ if (!r)
+ return set_invariant_sys_reg(reg->id, uaddr);
+
+ return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id);
+}
+
+static unsigned int num_demux_regs(void)
+{
+ unsigned int i, count = 0;
+
+ for (i = 0; i < CSSELR_MAX; i++)
+ if (is_valid_cache(i))
+ count++;
+
+ return count;
+}
+
+static int write_demux_regids(u64 __user *uindices)
+{
+ u64 val = KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX;
+ unsigned int i;
+
+ val |= KVM_REG_ARM_DEMUX_ID_CCSIDR;
+ for (i = 0; i < CSSELR_MAX; i++) {
+ if (!is_valid_cache(i))
+ continue;
+ if (put_user(val | i, uindices))
+ return -EFAULT;
+ uindices++;
+ }
+ return 0;
+}
+
+static u64 sys_reg_to_index(const struct sys_reg_desc *reg)
+{
+ return (KVM_REG_ARM64 | KVM_REG_SIZE_U64 |
+ KVM_REG_ARM64_SYSREG |
+ (reg->Op0 << KVM_REG_ARM64_SYSREG_OP0_SHIFT) |
+ (reg->Op1 << KVM_REG_ARM64_SYSREG_OP1_SHIFT) |
+ (reg->CRn << KVM_REG_ARM64_SYSREG_CRN_SHIFT) |
+ (reg->CRm << KVM_REG_ARM64_SYSREG_CRM_SHIFT) |
+ (reg->Op2 << KVM_REG_ARM64_SYSREG_OP2_SHIFT));
+}
+
+static bool copy_reg_to_user(const struct sys_reg_desc *reg, u64 __user **uind)
+{
+ if (!*uind)
+ return true;
+
+ if (put_user(sys_reg_to_index(reg), *uind))
+ return false;
+
+ (*uind)++;
+ return true;
+}
+
+/* Assumed ordered tables, see kvm_sys_reg_table_init. */
+static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind)
+{
+ const struct sys_reg_desc *i1, *i2, *end1, *end2;
+ unsigned int total = 0;
+ size_t num;
+
+ /* We check for duplicates here, to allow arch-specific overrides. */
+ i1 = get_target_table(vcpu->arch.target, true, &num);
+ end1 = i1 + num;
+ i2 = sys_reg_descs;
+ end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs);
+
+ BUG_ON(i1 == end1 || i2 == end2);
+
+ /* Walk carefully, as both tables may refer to the same register. */
+ while (i1 || i2) {
+ int cmp = cmp_sys_reg(i1, i2);
+ /* target-specific overrides generic entry. */
+ if (cmp <= 0) {
+ /* Ignore registers we trap but don't save. */
+ if (i1->reg) {
+ if (!copy_reg_to_user(i1, &uind))
+ return -EFAULT;
+ total++;
+ }
+ } else {
+ /* Ignore registers we trap but don't save. */
+ if (i2->reg) {
+ if (!copy_reg_to_user(i2, &uind))
+ return -EFAULT;
+ total++;
+ }
+ }
+
+ if (cmp <= 0 && ++i1 == end1)
+ i1 = NULL;
+ if (cmp >= 0 && ++i2 == end2)
+ i2 = NULL;
+ }
+ return total;
+}
+
+unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu)
+{
+ return ARRAY_SIZE(invariant_sys_regs)
+ + num_demux_regs()
+ + walk_sys_regs(vcpu, (u64 __user *)NULL);
+}
+
+int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
+{
+ unsigned int i;
+ int err;
+
+ /* Then give them all the invariant registers' indices. */
+ for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++) {
+ if (put_user(sys_reg_to_index(&invariant_sys_regs[i]), uindices))
+ return -EFAULT;
+ uindices++;
+ }
+
+ err = walk_sys_regs(vcpu, uindices);
+ if (err < 0)
+ return err;
+ uindices += err;
+
+ return write_demux_regids(uindices);
+}
+
+static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n)
+{
+ unsigned int i;
+
+ for (i = 1; i < n; i++) {
+ if (cmp_sys_reg(&table[i-1], &table[i]) >= 0) {
+ kvm_err("sys_reg table %p out of order (%d)\n", table, i - 1);
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+void kvm_sys_reg_table_init(void)
+{
+ unsigned int i;
+ struct sys_reg_desc clidr;
+
+ /* Make sure tables are unique and in order. */
+ BUG_ON(check_sysreg_table(sys_reg_descs, ARRAY_SIZE(sys_reg_descs)));
+ BUG_ON(check_sysreg_table(cp14_regs, ARRAY_SIZE(cp14_regs)));
+ BUG_ON(check_sysreg_table(cp14_64_regs, ARRAY_SIZE(cp14_64_regs)));
+ BUG_ON(check_sysreg_table(cp15_regs, ARRAY_SIZE(cp15_regs)));
+ BUG_ON(check_sysreg_table(cp15_64_regs, ARRAY_SIZE(cp15_64_regs)));
+ BUG_ON(check_sysreg_table(invariant_sys_regs, ARRAY_SIZE(invariant_sys_regs)));
+
+ /* We abuse the reset function to overwrite the table itself. */
+ for (i = 0; i < ARRAY_SIZE(invariant_sys_regs); i++)
+ invariant_sys_regs[i].reset(NULL, &invariant_sys_regs[i]);
+
+ /*
+ * CLIDR format is awkward, so clean it up. See ARM B4.1.20:
+ *
+ * If software reads the Cache Type fields from Ctype1
+ * upwards, once it has seen a value of 0b000, no caches
+ * exist at further-out levels of the hierarchy. So, for
+ * example, if Ctype3 is the first Cache Type field with a
+ * value of 0b000, the values of Ctype4 to Ctype7 must be
+ * ignored.
+ */
+ get_clidr_el1(NULL, &clidr); /* Ugly... */
+ cache_levels = clidr.val;
+ for (i = 0; i < 7; i++)
+ if (((cache_levels >> (i*3)) & 7) == 0)
+ break;
+ /* Clear all higher bits. */
+ cache_levels &= (1 << (i*3))-1;
+}
+
+/**
+ * kvm_reset_sys_regs - sets system registers to reset value
+ * @vcpu: The VCPU pointer
+ *
+ * This function finds the right table above and sets the registers on the
+ * virtual CPU struct to their architecturally defined reset values.
+ */
+void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
+{
+ size_t num;
+ const struct sys_reg_desc *table;
+
+ /* Catch someone adding a register without putting in reset entry. */
+ memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs));
+
+ /* Generic chip reset first (so target could override). */
+ reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+
+ table = get_target_table(vcpu->arch.target, true, &num);
+ reset_sys_reg_descs(vcpu, table, num);
+
+ for (num = 1; num < NR_SYS_REGS; num++)
+ if (vcpu_sys_reg(vcpu, num) == 0x4242424242424242)
+ panic("Didn't reset vcpu_sys_reg(%zi)", num);
+}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
new file mode 100644
index 0000000..d411e25
--- /dev/null
+++ b/arch/arm64/kvm/sys_regs.h
@@ -0,0 +1,140 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/kvm/coproc.h
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__
+#define __ARM64_KVM_SYS_REGS_LOCAL_H__
+
+struct sys_reg_params {
+ u8 Op0;
+ u8 Op1;
+ u8 CRn;
+ u8 CRm;
+ u8 Op2;
+ u8 Rt;
+ bool is_write;
+ bool is_aarch32;
+ bool is_32bit; /* Only valid if is_aarch32 is true */
+};
+
+struct sys_reg_desc {
+ /* MRS/MSR instruction which accesses it. */
+ u8 Op0;
+ u8 Op1;
+ u8 CRn;
+ u8 CRm;
+ u8 Op2;
+
+ /* Trapped access from guest, if non-NULL. */
+ bool (*access)(struct kvm_vcpu *,
+ const struct sys_reg_params *,
+ const struct sys_reg_desc *);
+
+ /* Initialization for vcpu. */
+ void (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *);
+
+ /* Index into sys_reg[], or 0 if we don't need to save it. */
+ int reg;
+
+ /* Value (usually reset value) */
+ u64 val;
+};
+
+static inline void print_sys_reg_instr(const struct sys_reg_params *p)
+{
+ /* Look, we even formatted it for you to paste into the table! */
+ kvm_pr_unimpl(" { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n",
+ p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read");
+}
+
+static inline bool ignore_write(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p)
+{
+ return true;
+}
+
+static inline bool read_zero(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p)
+{
+ *vcpu_reg(vcpu, p->Rt) = 0;
+ return true;
+}
+
+static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params)
+{
+ kvm_debug("sys_reg write to read-only register at: %lx\n",
+ *vcpu_pc(vcpu));
+ print_sys_reg_instr(params);
+ return false;
+}
+
+static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params)
+{
+ kvm_debug("sys_reg read to write-only register at: %lx\n",
+ *vcpu_pc(vcpu));
+ print_sys_reg_instr(params);
+ return false;
+}
+
+/* Reset functions */
+static inline void reset_unknown(struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *r)
+{
+ BUG_ON(!r->reg);
+ BUG_ON(r->reg >= NR_SYS_REGS);
+ vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+}
+
+static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ BUG_ON(!r->reg);
+ BUG_ON(r->reg >= NR_SYS_REGS);
+ vcpu_sys_reg(vcpu, r->reg) = r->val;
+}
+
+static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
+ const struct sys_reg_desc *i2)
+{
+ BUG_ON(i1 == i2);
+ if (!i1)
+ return 1;
+ else if (!i2)
+ return -1;
+ if (i1->Op0 != i2->Op0)
+ return i1->Op0 - i2->Op0;
+ if (i1->Op1 != i2->Op1)
+ return i1->Op1 - i2->Op1;
+ if (i1->CRn != i2->CRn)
+ return i1->CRn - i2->CRn;
+ if (i1->CRm != i2->CRm)
+ return i1->CRm - i2->CRm;
+ return i1->Op2 - i2->Op2;
+}
+
+
+#define Op0(_x) .Op0 = _x
+#define Op1(_x) .Op1 = _x
+#define CRn(_x) .CRn = _x
+#define CRm(_x) .CRm = _x
+#define Op2(_x) .Op2 = _x
+
+#endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
new file mode 100644
index 0000000..475fd29
--- /dev/null
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Based on arch/arm/kvm/coproc_a15.c:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Authors: Rusty Russell <rusty@rustcorp.au>
+ * Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kvm_host.h>
+#include <asm/cputype.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_coproc.h>
+#include <linux/init.h>
+
+#include "sys_regs.h"
+
+static bool access_actlr(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write)
+ return ignore_write(vcpu, p);
+
+ *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+ return true;
+}
+
+static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ u64 actlr;
+
+ asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr));
+ vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr;
+}
+
+/*
+ * Implementation specific sys-reg registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ */
+static const struct sys_reg_desc genericv8_sys_regs[] = {
+ /* ACTLR_EL1 */
+ { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
+ access_actlr, reset_actlr, ACTLR_EL1 },
+};
+
+static const struct sys_reg_desc genericv8_cp15_regs[] = {
+ /* ACTLR */
+ { Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
+ access_actlr },
+};
+
+static struct kvm_sys_reg_target_table genericv8_target_table = {
+ .table64 = {
+ .table = genericv8_sys_regs,
+ .num = ARRAY_SIZE(genericv8_sys_regs),
+ },
+ .table32 = {
+ .table = genericv8_cp15_regs,
+ .num = ARRAY_SIZE(genericv8_cp15_regs),
+ },
+};
+
+static int __init sys_reg_genericv8_init(void)
+{
+ unsigned int i;
+
+ for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++)
+ BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1],
+ &genericv8_sys_regs[i]) >= 0);
+
+ kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8,
+ &genericv8_target_table);
+ kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8,
+ &genericv8_target_table);
+ kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53,
+ &genericv8_target_table);
+ kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57,
+ &genericv8_target_table);
+ kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA,
+ &genericv8_target_table);
+
+ return 0;
+}
+late_initcall(sys_reg_genericv8_init);
diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S
new file mode 100644
index 0000000..ae21177
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v2-switch.S
@@ -0,0 +1,133 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+ .text
+ .pushsection .hyp.text, "ax"
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+ENTRY(__save_vgic_v2_state)
+__save_vgic_v2_state:
+ /* Get VGIC VCTRL base into x2 */
+ ldr x2, [x0, #VCPU_KVM]
+ kern_hyp_va x2
+ ldr x2, [x2, #KVM_VGIC_VCTRL]
+ kern_hyp_va x2
+ cbz x2, 2f // disabled
+
+ /* Compute the address of struct vgic_cpu */
+ add x3, x0, #VCPU_VGIC_CPU
+
+ /* Save all interesting registers */
+ ldr w4, [x2, #GICH_HCR]
+ ldr w5, [x2, #GICH_VMCR]
+ ldr w6, [x2, #GICH_MISR]
+ ldr w7, [x2, #GICH_EISR0]
+ ldr w8, [x2, #GICH_EISR1]
+ ldr w9, [x2, #GICH_ELRSR0]
+ ldr w10, [x2, #GICH_ELRSR1]
+ ldr w11, [x2, #GICH_APR]
+CPU_BE( rev w4, w4 )
+CPU_BE( rev w5, w5 )
+CPU_BE( rev w6, w6 )
+CPU_BE( rev w7, w7 )
+CPU_BE( rev w8, w8 )
+CPU_BE( rev w9, w9 )
+CPU_BE( rev w10, w10 )
+CPU_BE( rev w11, w11 )
+
+ str w4, [x3, #VGIC_V2_CPU_HCR]
+ str w5, [x3, #VGIC_V2_CPU_VMCR]
+ str w6, [x3, #VGIC_V2_CPU_MISR]
+ str w7, [x3, #VGIC_V2_CPU_EISR]
+ str w8, [x3, #(VGIC_V2_CPU_EISR + 4)]
+ str w9, [x3, #VGIC_V2_CPU_ELRSR]
+ str w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)]
+ str w11, [x3, #VGIC_V2_CPU_APR]
+
+ /* Clear GICH_HCR */
+ str wzr, [x2, #GICH_HCR]
+
+ /* Save list registers */
+ add x2, x2, #GICH_LR0
+ ldr w4, [x3, #VGIC_CPU_NR_LR]
+ add x3, x3, #VGIC_V2_CPU_LR
+1: ldr w5, [x2], #4
+CPU_BE( rev w5, w5 )
+ str w5, [x3], #4
+ sub w4, w4, #1
+ cbnz w4, 1b
+2:
+ ret
+ENDPROC(__save_vgic_v2_state)
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+ENTRY(__restore_vgic_v2_state)
+__restore_vgic_v2_state:
+ /* Get VGIC VCTRL base into x2 */
+ ldr x2, [x0, #VCPU_KVM]
+ kern_hyp_va x2
+ ldr x2, [x2, #KVM_VGIC_VCTRL]
+ kern_hyp_va x2
+ cbz x2, 2f // disabled
+
+ /* Compute the address of struct vgic_cpu */
+ add x3, x0, #VCPU_VGIC_CPU
+
+ /* We only restore a minimal set of registers */
+ ldr w4, [x3, #VGIC_V2_CPU_HCR]
+ ldr w5, [x3, #VGIC_V2_CPU_VMCR]
+ ldr w6, [x3, #VGIC_V2_CPU_APR]
+CPU_BE( rev w4, w4 )
+CPU_BE( rev w5, w5 )
+CPU_BE( rev w6, w6 )
+
+ str w4, [x2, #GICH_HCR]
+ str w5, [x2, #GICH_VMCR]
+ str w6, [x2, #GICH_APR]
+
+ /* Restore list registers */
+ add x2, x2, #GICH_LR0
+ ldr w4, [x3, #VGIC_CPU_NR_LR]
+ add x3, x3, #VGIC_V2_CPU_LR
+1: ldr w5, [x3], #4
+CPU_BE( rev w5, w5 )
+ str w5, [x2], #4
+ sub w4, w4, #1
+ cbnz w4, 1b
+2:
+ ret
+ENDPROC(__restore_vgic_v2_state)
+
+ .popsection
diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S
new file mode 100644
index 0000000..d160469
--- /dev/null
+++ b/arch/arm64/kvm/vgic-v3-switch.S
@@ -0,0 +1,267 @@
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/assembler.h>
+#include <asm/memory.h>
+#include <asm/asm-offsets.h>
+#include <asm/kvm.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_arm.h>
+
+ .text
+ .pushsection .hyp.text, "ax"
+
+/*
+ * We store LRs in reverse order to let the CPU deal with streaming
+ * access. Use this macro to make it look saner...
+ */
+#define LR_OFFSET(n) (VGIC_V3_CPU_LR + (15 - n) * 8)
+
+/*
+ * Save the VGIC CPU state into memory
+ * x0: Register pointing to VCPU struct
+ * Do not corrupt x1!!!
+ */
+.macro save_vgic_v3_state
+ // Compute the address of struct vgic_cpu
+ add x3, x0, #VCPU_VGIC_CPU
+
+ // Make sure stores to the GIC via the memory mapped interface
+ // are now visible to the system register interface
+ dsb st
+
+ // Save all interesting registers
+ mrs_s x4, ICH_HCR_EL2
+ mrs_s x5, ICH_VMCR_EL2
+ mrs_s x6, ICH_MISR_EL2
+ mrs_s x7, ICH_EISR_EL2
+ mrs_s x8, ICH_ELSR_EL2
+
+ str w4, [x3, #VGIC_V3_CPU_HCR]
+ str w5, [x3, #VGIC_V3_CPU_VMCR]
+ str w6, [x3, #VGIC_V3_CPU_MISR]
+ str w7, [x3, #VGIC_V3_CPU_EISR]
+ str w8, [x3, #VGIC_V3_CPU_ELRSR]
+
+ msr_s ICH_HCR_EL2, xzr
+
+ mrs_s x21, ICH_VTR_EL2
+ mvn w22, w21
+ ubfiz w23, w22, 2, 4 // w23 = (15 - ListRegs) * 4
+
+ adr x24, 1f
+ add x24, x24, x23
+ br x24
+
+1:
+ mrs_s x20, ICH_LR15_EL2
+ mrs_s x19, ICH_LR14_EL2
+ mrs_s x18, ICH_LR13_EL2
+ mrs_s x17, ICH_LR12_EL2
+ mrs_s x16, ICH_LR11_EL2
+ mrs_s x15, ICH_LR10_EL2
+ mrs_s x14, ICH_LR9_EL2
+ mrs_s x13, ICH_LR8_EL2
+ mrs_s x12, ICH_LR7_EL2
+ mrs_s x11, ICH_LR6_EL2
+ mrs_s x10, ICH_LR5_EL2
+ mrs_s x9, ICH_LR4_EL2
+ mrs_s x8, ICH_LR3_EL2
+ mrs_s x7, ICH_LR2_EL2
+ mrs_s x6, ICH_LR1_EL2
+ mrs_s x5, ICH_LR0_EL2
+
+ adr x24, 1f
+ add x24, x24, x23
+ br x24
+
+1:
+ str x20, [x3, #LR_OFFSET(15)]
+ str x19, [x3, #LR_OFFSET(14)]
+ str x18, [x3, #LR_OFFSET(13)]
+ str x17, [x3, #LR_OFFSET(12)]
+ str x16, [x3, #LR_OFFSET(11)]
+ str x15, [x3, #LR_OFFSET(10)]
+ str x14, [x3, #LR_OFFSET(9)]
+ str x13, [x3, #LR_OFFSET(8)]
+ str x12, [x3, #LR_OFFSET(7)]
+ str x11, [x3, #LR_OFFSET(6)]
+ str x10, [x3, #LR_OFFSET(5)]
+ str x9, [x3, #LR_OFFSET(4)]
+ str x8, [x3, #LR_OFFSET(3)]
+ str x7, [x3, #LR_OFFSET(2)]
+ str x6, [x3, #LR_OFFSET(1)]
+ str x5, [x3, #LR_OFFSET(0)]
+
+ tbnz w21, #29, 6f // 6 bits
+ tbz w21, #30, 5f // 5 bits
+ // 7 bits
+ mrs_s x20, ICH_AP0R3_EL2
+ str w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+ mrs_s x19, ICH_AP0R2_EL2
+ str w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+6: mrs_s x18, ICH_AP0R1_EL2
+ str w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+5: mrs_s x17, ICH_AP0R0_EL2
+ str w17, [x3, #VGIC_V3_CPU_AP0R]
+
+ tbnz w21, #29, 6f // 6 bits
+ tbz w21, #30, 5f // 5 bits
+ // 7 bits
+ mrs_s x20, ICH_AP1R3_EL2
+ str w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+ mrs_s x19, ICH_AP1R2_EL2
+ str w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+6: mrs_s x18, ICH_AP1R1_EL2
+ str w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+5: mrs_s x17, ICH_AP1R0_EL2
+ str w17, [x3, #VGIC_V3_CPU_AP1R]
+
+ // Restore SRE_EL1 access and re-enable SRE at EL1.
+ mrs_s x5, ICC_SRE_EL2
+ orr x5, x5, #ICC_SRE_EL2_ENABLE
+ msr_s ICC_SRE_EL2, x5
+ isb
+ mov x5, #1
+ msr_s ICC_SRE_EL1, x5
+.endm
+
+/*
+ * Restore the VGIC CPU state from memory
+ * x0: Register pointing to VCPU struct
+ */
+.macro restore_vgic_v3_state
+ // Disable SRE_EL1 access. Necessary, otherwise
+ // ICH_VMCR_EL2.VFIQEn becomes one, and FIQ happens...
+ msr_s ICC_SRE_EL1, xzr
+ isb
+
+ // Compute the address of struct vgic_cpu
+ add x3, x0, #VCPU_VGIC_CPU
+
+ // Restore all interesting registers
+ ldr w4, [x3, #VGIC_V3_CPU_HCR]
+ ldr w5, [x3, #VGIC_V3_CPU_VMCR]
+
+ msr_s ICH_HCR_EL2, x4
+ msr_s ICH_VMCR_EL2, x5
+
+ mrs_s x21, ICH_VTR_EL2
+
+ tbnz w21, #29, 6f // 6 bits
+ tbz w21, #30, 5f // 5 bits
+ // 7 bits
+ ldr w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)]
+ msr_s ICH_AP1R3_EL2, x20
+ ldr w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)]
+ msr_s ICH_AP1R2_EL2, x19
+6: ldr w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)]
+ msr_s ICH_AP1R1_EL2, x18
+5: ldr w17, [x3, #VGIC_V3_CPU_AP1R]
+ msr_s ICH_AP1R0_EL2, x17
+
+ tbnz w21, #29, 6f // 6 bits
+ tbz w21, #30, 5f // 5 bits
+ // 7 bits
+ ldr w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)]
+ msr_s ICH_AP0R3_EL2, x20
+ ldr w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)]
+ msr_s ICH_AP0R2_EL2, x19
+6: ldr w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)]
+ msr_s ICH_AP0R1_EL2, x18
+5: ldr w17, [x3, #VGIC_V3_CPU_AP0R]
+ msr_s ICH_AP0R0_EL2, x17
+
+ and w22, w21, #0xf
+ mvn w22, w21
+ ubfiz w23, w22, 2, 4 // w23 = (15 - ListRegs) * 4
+
+ adr x24, 1f
+ add x24, x24, x23
+ br x24
+
+1:
+ ldr x20, [x3, #LR_OFFSET(15)]
+ ldr x19, [x3, #LR_OFFSET(14)]
+ ldr x18, [x3, #LR_OFFSET(13)]
+ ldr x17, [x3, #LR_OFFSET(12)]
+ ldr x16, [x3, #LR_OFFSET(11)]
+ ldr x15, [x3, #LR_OFFSET(10)]
+ ldr x14, [x3, #LR_OFFSET(9)]
+ ldr x13, [x3, #LR_OFFSET(8)]
+ ldr x12, [x3, #LR_OFFSET(7)]
+ ldr x11, [x3, #LR_OFFSET(6)]
+ ldr x10, [x3, #LR_OFFSET(5)]
+ ldr x9, [x3, #LR_OFFSET(4)]
+ ldr x8, [x3, #LR_OFFSET(3)]
+ ldr x7, [x3, #LR_OFFSET(2)]
+ ldr x6, [x3, #LR_OFFSET(1)]
+ ldr x5, [x3, #LR_OFFSET(0)]
+
+ adr x24, 1f
+ add x24, x24, x23
+ br x24
+
+1:
+ msr_s ICH_LR15_EL2, x20
+ msr_s ICH_LR14_EL2, x19
+ msr_s ICH_LR13_EL2, x18
+ msr_s ICH_LR12_EL2, x17
+ msr_s ICH_LR11_EL2, x16
+ msr_s ICH_LR10_EL2, x15
+ msr_s ICH_LR9_EL2, x14
+ msr_s ICH_LR8_EL2, x13
+ msr_s ICH_LR7_EL2, x12
+ msr_s ICH_LR6_EL2, x11
+ msr_s ICH_LR5_EL2, x10
+ msr_s ICH_LR4_EL2, x9
+ msr_s ICH_LR3_EL2, x8
+ msr_s ICH_LR2_EL2, x7
+ msr_s ICH_LR1_EL2, x6
+ msr_s ICH_LR0_EL2, x5
+
+ // Ensure that the above will have reached the
+ // (re)distributors. This ensure the guest will read
+ // the correct values from the memory-mapped interface.
+ isb
+ dsb sy
+
+ // Prevent the guest from touching the GIC system registers
+ mrs_s x5, ICC_SRE_EL2
+ and x5, x5, #~ICC_SRE_EL2_ENABLE
+ msr_s ICC_SRE_EL2, x5
+.endm
+
+ENTRY(__save_vgic_v3_state)
+ save_vgic_v3_state
+ ret
+ENDPROC(__save_vgic_v3_state)
+
+ENTRY(__restore_vgic_v3_state)
+ restore_vgic_v3_state
+ ret
+ENDPROC(__restore_vgic_v3_state)
+
+ENTRY(__vgic_v3_get_ich_vtr_el2)
+ mrs_s x0, ICH_VTR_EL2
+ ret
+ENDPROC(__vgic_v3_get_ich_vtr_el2)
+
+ .popsection
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 59acc0e..d98d3e3 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,6 +1,5 @@
-lib-y := bitops.o delay.o \
- strncpy_from_user.o strnlen_user.o clear_user.o \
- copy_from_user.o copy_to_user.o copy_in_user.o \
- copy_page.o clear_page.o \
- memchr.o memcpy.o memmove.o memset.o \
+lib-y := bitops.o clear_user.o delay.o copy_from_user.o \
+ copy_to_user.o copy_in_user.o copy_page.o \
+ clear_page.o memchr.o memcpy.o memmove.o memset.o \
+ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \
strchr.o strrchr.o
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
index e5db797..7dac371 100644
--- a/arch/arm64/lib/bitops.S
+++ b/arch/arm64/lib/bitops.S
@@ -46,11 +46,12 @@
mov x2, #1
add x1, x1, x0, lsr #3 // Get word offset
lsl x4, x2, x3 // Create mask
-1: ldaxr x2, [x1]
+1: ldxr x2, [x1]
lsr x0, x2, x3 // Save old value of bit
\instr x2, x2, x4 // toggle bit
stlxr w5, x2, [x1]
cbnz w5, 1b
+ dmb ish
and x0, x0, #1
3: ret
ENDPROC(\name )
diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S
index 6e0ed93..c17967f 100644
--- a/arch/arm64/lib/clear_user.S
+++ b/arch/arm64/lib/clear_user.S
@@ -46,7 +46,7 @@
sub x1, x1, #2
4: adds x1, x1, #1
b.mi 5f
- strb wzr, [x0]
+USER(9f, strb wzr, [x0] )
5: mov x0, #0
ret
ENDPROC(__clear_user)
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
new file mode 100644
index 0000000..6ea0776
--- /dev/null
+++ b/arch/arm64/lib/memcmp.S
@@ -0,0 +1,258 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+* compare memory areas(when two memory areas' offset are different,
+* alignment handled by the hardware)
+*
+* Parameters:
+* x0 - const memory area 1 pointer
+* x1 - const memory area 2 pointer
+* x2 - the maximal compare byte length
+* Returns:
+* x0 - a compare result, maybe less than, equal to, or greater than ZERO
+*/
+
+/* Parameters and result. */
+src1 .req x0
+src2 .req x1
+limit .req x2
+result .req x0
+
+/* Internal variables. */
+data1 .req x3
+data1w .req w3
+data2 .req x4
+data2w .req w4
+has_nul .req x5
+diff .req x6
+endloop .req x7
+tmp1 .req x8
+tmp2 .req x9
+tmp3 .req x10
+pos .req x11
+limit_wd .req x12
+mask .req x13
+
+ENTRY(memcmp)
+ cbz limit, .Lret0
+ eor tmp1, src1, src2
+ tst tmp1, #7
+ b.ne .Lmisaligned8
+ ands tmp1, src1, #7
+ b.ne .Lmutual_align
+ sub limit_wd, limit, #1 /* limit != 0, so no underflow. */
+ lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */
+ /*
+ * The input source addresses are at alignment boundary.
+ * Directly compare eight bytes each time.
+ */
+.Lloop_aligned:
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+.Lstart_realigned:
+ subs limit_wd, limit_wd, #1
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ csinv endloop, diff, xzr, cs /* Last Dword or differences. */
+ cbz endloop, .Lloop_aligned
+
+ /* Not reached the limit, must have found a diff. */
+ tbz limit_wd, #63, .Lnot_limit
+
+ /* Limit % 8 == 0 => the diff is in the last 8 bytes. */
+ ands limit, limit, #7
+ b.eq .Lnot_limit
+ /*
+ * The remained bytes less than 8. It is needed to extract valid data
+ * from last eight bytes of the intended memory range.
+ */
+ lsl limit, limit, #3 /* bytes-> bits. */
+ mov mask, #~0
+CPU_BE( lsr mask, mask, limit )
+CPU_LE( lsl mask, mask, limit )
+ bic data1, data1, mask
+ bic data2, data2, mask
+
+ orr diff, diff, mask
+ b .Lnot_limit
+
+.Lmutual_align:
+ /*
+ * Sources are mutually aligned, but are not currently at an
+ * alignment boundary. Round down the addresses and then mask off
+ * the bytes that precede the start point.
+ */
+ bic src1, src1, #7
+ bic src2, src2, #7
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+ /*
+ * We can not add limit with alignment offset(tmp1) here. Since the
+ * addition probably make the limit overflown.
+ */
+ sub limit_wd, limit, #1/*limit != 0, so no underflow.*/
+ and tmp3, limit_wd, #7
+ lsr limit_wd, limit_wd, #3
+ add tmp3, tmp3, tmp1
+ add limit_wd, limit_wd, tmp3, lsr #3
+ add limit, limit, tmp1/* Adjust the limit for the extra. */
+
+ lsl tmp1, tmp1, #3/* Bytes beyond alignment -> bits.*/
+ neg tmp1, tmp1/* Bits to alignment -64. */
+ mov tmp2, #~0
+ /*mask off the non-intended bytes before the start address.*/
+CPU_BE( lsl tmp2, tmp2, tmp1 )/*Big-endian.Early bytes are at MSB*/
+ /* Little-endian. Early bytes are at LSB. */
+CPU_LE( lsr tmp2, tmp2, tmp1 )
+
+ orr data1, data1, tmp2
+ orr data2, data2, tmp2
+ b .Lstart_realigned
+
+ /*src1 and src2 have different alignment offset.*/
+.Lmisaligned8:
+ cmp limit, #8
+ b.lo .Ltiny8proc /*limit < 8: compare byte by byte*/
+
+ and tmp1, src1, #7
+ neg tmp1, tmp1
+ add tmp1, tmp1, #8/*valid length in the first 8 bytes of src1*/
+ and tmp2, src2, #7
+ neg tmp2, tmp2
+ add tmp2, tmp2, #8/*valid length in the first 8 bytes of src2*/
+ subs tmp3, tmp1, tmp2
+ csel pos, tmp1, tmp2, hi /*Choose the maximum.*/
+
+ sub limit, limit, pos
+ /*compare the proceeding bytes in the first 8 byte segment.*/
+.Ltinycmp:
+ ldrb data1w, [src1], #1
+ ldrb data2w, [src2], #1
+ subs pos, pos, #1
+ ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */
+ b.eq .Ltinycmp
+ cbnz pos, 1f /*diff occurred before the last byte.*/
+ cmp data1w, data2w
+ b.eq .Lstart_align
+1:
+ sub result, data1, data2
+ ret
+
+.Lstart_align:
+ lsr limit_wd, limit, #3
+ cbz limit_wd, .Lremain8
+
+ ands xzr, src1, #7
+ b.eq .Lrecal_offset
+ /*process more leading bytes to make src1 aligned...*/
+ add src1, src1, tmp3 /*backwards src1 to alignment boundary*/
+ add src2, src2, tmp3
+ sub limit, limit, tmp3
+ lsr limit_wd, limit, #3
+ cbz limit_wd, .Lremain8
+ /*load 8 bytes from aligned SRC1..*/
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+
+ subs limit_wd, limit_wd, #1
+ eor diff, data1, data2 /*Non-zero if differences found.*/
+ csinv endloop, diff, xzr, ne
+ cbnz endloop, .Lunequal_proc
+ /*How far is the current SRC2 from the alignment boundary...*/
+ and tmp3, tmp3, #7
+
+.Lrecal_offset:/*src1 is aligned now..*/
+ neg pos, tmp3
+.Lloopcmp_proc:
+ /*
+ * Divide the eight bytes into two parts. First,backwards the src2
+ * to an alignment boundary,load eight bytes and compare from
+ * the SRC2 alignment boundary. If all 8 bytes are equal,then start
+ * the second part's comparison. Otherwise finish the comparison.
+ * This special handle can garantee all the accesses are in the
+ * thread/task space in avoid to overrange access.
+ */
+ ldr data1, [src1,pos]
+ ldr data2, [src2,pos]
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ cbnz diff, .Lnot_limit
+
+ /*The second part process*/
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ subs limit_wd, limit_wd, #1
+ csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
+ cbz endloop, .Lloopcmp_proc
+.Lunequal_proc:
+ cbz diff, .Lremain8
+
+/*There is differnence occured in the latest comparison.*/
+.Lnot_limit:
+/*
+* For little endian,reverse the low significant equal bits into MSB,then
+* following CLZ can find how many equal bits exist.
+*/
+CPU_LE( rev diff, diff )
+CPU_LE( rev data1, data1 )
+CPU_LE( rev data2, data2 )
+
+ /*
+ * The MS-non-zero bit of DIFF marks either the first bit
+ * that is different, or the end of the significant data.
+ * Shifting left now will bring the critical information into the
+ * top bits.
+ */
+ clz pos, diff
+ lsl data1, data1, pos
+ lsl data2, data2, pos
+ /*
+ * We need to zero-extend (char is unsigned) the value and then
+ * perform a signed subtraction.
+ */
+ lsr data1, data1, #56
+ sub result, data1, data2, lsr #56
+ ret
+
+.Lremain8:
+ /* Limit % 8 == 0 =>. all data are equal.*/
+ ands limit, limit, #7
+ b.eq .Lret0
+
+.Ltiny8proc:
+ ldrb data1w, [src1], #1
+ ldrb data2w, [src2], #1
+ subs limit, limit, #1
+
+ ccmp data1w, data2w, #0, ne /* NZCV = 0b0000. */
+ b.eq .Ltiny8proc
+ sub result, data1, data2
+ ret
+.Lret0:
+ mov result, #0
+ ret
+ENDPROC(memcmp)
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 27b5003..8a9a96d 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -1,5 +1,13 @@
/*
* Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -16,6 +24,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
/*
* Copy a buffer from src to dest (alignment handled by the hardware)
@@ -27,27 +36,166 @@
* Returns:
* x0 - dest
*/
+dstin .req x0
+src .req x1
+count .req x2
+tmp1 .req x3
+tmp1w .req w3
+tmp2 .req x4
+tmp2w .req w4
+tmp3 .req x5
+tmp3w .req w5
+dst .req x6
+
+A_l .req x7
+A_h .req x8
+B_l .req x9
+B_h .req x10
+C_l .req x11
+C_h .req x12
+D_l .req x13
+D_h .req x14
+
ENTRY(memcpy)
- mov x4, x0
- subs x2, x2, #8
- b.mi 2f
-1: ldr x3, [x1], #8
- subs x2, x2, #8
- str x3, [x4], #8
- b.pl 1b
-2: adds x2, x2, #4
- b.mi 3f
- ldr w3, [x1], #4
- sub x2, x2, #4
- str w3, [x4], #4
-3: adds x2, x2, #2
- b.mi 4f
- ldrh w3, [x1], #2
- sub x2, x2, #2
- strh w3, [x4], #2
-4: adds x2, x2, #1
- b.mi 5f
- ldrb w3, [x1]
- strb w3, [x4]
-5: ret
+ mov dst, dstin
+ cmp count, #16
+ /*When memory length is less than 16, the accessed are not aligned.*/
+ b.lo .Ltiny15
+
+ neg tmp2, src
+ ands tmp2, tmp2, #15/* Bytes to reach alignment. */
+ b.eq .LSrcAligned
+ sub count, count, tmp2
+ /*
+ * Copy the leading memory data from src to dst in an increasing
+ * address order.By this way,the risk of overwritting the source
+ * memory data is eliminated when the distance between src and
+ * dst is less than 16. The memory accesses here are alignment.
+ */
+ tbz tmp2, #0, 1f
+ ldrb tmp1w, [src], #1
+ strb tmp1w, [dst], #1
+1:
+ tbz tmp2, #1, 2f
+ ldrh tmp1w, [src], #2
+ strh tmp1w, [dst], #2
+2:
+ tbz tmp2, #2, 3f
+ ldr tmp1w, [src], #4
+ str tmp1w, [dst], #4
+3:
+ tbz tmp2, #3, .LSrcAligned
+ ldr tmp1, [src],#8
+ str tmp1, [dst],#8
+
+.LSrcAligned:
+ cmp count, #64
+ b.ge .Lcpy_over64
+ /*
+ * Deal with small copies quickly by dropping straight into the
+ * exit block.
+ */
+.Ltail63:
+ /*
+ * Copy up to 48 bytes of data. At this point we only need the
+ * bottom 6 bits of count to be accurate.
+ */
+ ands tmp1, count, #0x30
+ b.eq .Ltiny15
+ cmp tmp1w, #0x20
+ b.eq 1f
+ b.lt 2f
+ ldp A_l, A_h, [src], #16
+ stp A_l, A_h, [dst], #16
+1:
+ ldp A_l, A_h, [src], #16
+ stp A_l, A_h, [dst], #16
+2:
+ ldp A_l, A_h, [src], #16
+ stp A_l, A_h, [dst], #16
+.Ltiny15:
+ /*
+ * Prefer to break one ldp/stp into several load/store to access
+ * memory in an increasing address order,rather than to load/store 16
+ * bytes from (src-16) to (dst-16) and to backward the src to aligned
+ * address,which way is used in original cortex memcpy. If keeping
+ * the original memcpy process here, memmove need to satisfy the
+ * precondition that src address is at least 16 bytes bigger than dst
+ * address,otherwise some source data will be overwritten when memove
+ * call memcpy directly. To make memmove simpler and decouple the
+ * memcpy's dependency on memmove, withdrew the original process.
+ */
+ tbz count, #3, 1f
+ ldr tmp1, [src], #8
+ str tmp1, [dst], #8
+1:
+ tbz count, #2, 2f
+ ldr tmp1w, [src], #4
+ str tmp1w, [dst], #4
+2:
+ tbz count, #1, 3f
+ ldrh tmp1w, [src], #2
+ strh tmp1w, [dst], #2
+3:
+ tbz count, #0, .Lexitfunc
+ ldrb tmp1w, [src]
+ strb tmp1w, [dst]
+
+.Lexitfunc:
+ ret
+
+.Lcpy_over64:
+ subs count, count, #128
+ b.ge .Lcpy_body_large
+ /*
+ * Less than 128 bytes to copy, so handle 64 here and then jump
+ * to the tail.
+ */
+ ldp A_l, A_h, [src],#16
+ stp A_l, A_h, [dst],#16
+ ldp B_l, B_h, [src],#16
+ ldp C_l, C_h, [src],#16
+ stp B_l, B_h, [dst],#16
+ stp C_l, C_h, [dst],#16
+ ldp D_l, D_h, [src],#16
+ stp D_l, D_h, [dst],#16
+
+ tst count, #0x3f
+ b.ne .Ltail63
+ ret
+
+ /*
+ * Critical loop. Start at a new cache line boundary. Assuming
+ * 64 bytes per line this ensures the entire loop is in one line.
+ */
+ .p2align L1_CACHE_SHIFT
+.Lcpy_body_large:
+ /* pre-get 64 bytes data. */
+ ldp A_l, A_h, [src],#16
+ ldp B_l, B_h, [src],#16
+ ldp C_l, C_h, [src],#16
+ ldp D_l, D_h, [src],#16
+1:
+ /*
+ * interlace the load of next 64 bytes data block with store of the last
+ * loaded 64 bytes data.
+ */
+ stp A_l, A_h, [dst],#16
+ ldp A_l, A_h, [src],#16
+ stp B_l, B_h, [dst],#16
+ ldp B_l, B_h, [src],#16
+ stp C_l, C_h, [dst],#16
+ ldp C_l, C_h, [src],#16
+ stp D_l, D_h, [dst],#16
+ ldp D_l, D_h, [src],#16
+ subs count, count, #64
+ b.ge 1b
+ stp A_l, A_h, [dst],#16
+ stp B_l, B_h, [dst],#16
+ stp C_l, C_h, [dst],#16
+ stp D_l, D_h, [dst],#16
+
+ tst count, #0x3f
+ b.ne .Ltail63
+ ret
ENDPROC(memcpy)
diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S
index b79fdfa..57b19ea2 100644
--- a/arch/arm64/lib/memmove.S
+++ b/arch/arm64/lib/memmove.S
@@ -1,5 +1,13 @@
/*
* Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -16,6 +24,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
/*
* Move a buffer from src to test (alignment handled by the hardware).
@@ -28,30 +37,161 @@
* Returns:
* x0 - dest
*/
+dstin .req x0
+src .req x1
+count .req x2
+tmp1 .req x3
+tmp1w .req w3
+tmp2 .req x4
+tmp2w .req w4
+tmp3 .req x5
+tmp3w .req w5
+dst .req x6
+
+A_l .req x7
+A_h .req x8
+B_l .req x9
+B_h .req x10
+C_l .req x11
+C_h .req x12
+D_l .req x13
+D_h .req x14
+
ENTRY(memmove)
- cmp x0, x1
- b.ls memcpy
- add x4, x0, x2
- add x1, x1, x2
- subs x2, x2, #8
- b.mi 2f
-1: ldr x3, [x1, #-8]!
- subs x2, x2, #8
- str x3, [x4, #-8]!
- b.pl 1b
-2: adds x2, x2, #4
- b.mi 3f
- ldr w3, [x1, #-4]!
- sub x2, x2, #4
- str w3, [x4, #-4]!
-3: adds x2, x2, #2
- b.mi 4f
- ldrh w3, [x1, #-2]!
- sub x2, x2, #2
- strh w3, [x4, #-2]!
-4: adds x2, x2, #1
- b.mi 5f
- ldrb w3, [x1, #-1]
- strb w3, [x4, #-1]
-5: ret
+ cmp dstin, src
+ b.lo memcpy
+ add tmp1, src, count
+ cmp dstin, tmp1
+ b.hs memcpy /* No overlap. */
+
+ add dst, dstin, count
+ add src, src, count
+ cmp count, #16
+ b.lo .Ltail15 /*probably non-alignment accesses.*/
+
+ ands tmp2, src, #15 /* Bytes to reach alignment. */
+ b.eq .LSrcAligned
+ sub count, count, tmp2
+ /*
+ * process the aligned offset length to make the src aligned firstly.
+ * those extra instructions' cost is acceptable. It also make the
+ * coming accesses are based on aligned address.
+ */
+ tbz tmp2, #0, 1f
+ ldrb tmp1w, [src, #-1]!
+ strb tmp1w, [dst, #-1]!
+1:
+ tbz tmp2, #1, 2f
+ ldrh tmp1w, [src, #-2]!
+ strh tmp1w, [dst, #-2]!
+2:
+ tbz tmp2, #2, 3f
+ ldr tmp1w, [src, #-4]!
+ str tmp1w, [dst, #-4]!
+3:
+ tbz tmp2, #3, .LSrcAligned
+ ldr tmp1, [src, #-8]!
+ str tmp1, [dst, #-8]!
+
+.LSrcAligned:
+ cmp count, #64
+ b.ge .Lcpy_over64
+
+ /*
+ * Deal with small copies quickly by dropping straight into the
+ * exit block.
+ */
+.Ltail63:
+ /*
+ * Copy up to 48 bytes of data. At this point we only need the
+ * bottom 6 bits of count to be accurate.
+ */
+ ands tmp1, count, #0x30
+ b.eq .Ltail15
+ cmp tmp1w, #0x20
+ b.eq 1f
+ b.lt 2f
+ ldp A_l, A_h, [src, #-16]!
+ stp A_l, A_h, [dst, #-16]!
+1:
+ ldp A_l, A_h, [src, #-16]!
+ stp A_l, A_h, [dst, #-16]!
+2:
+ ldp A_l, A_h, [src, #-16]!
+ stp A_l, A_h, [dst, #-16]!
+
+.Ltail15:
+ tbz count, #3, 1f
+ ldr tmp1, [src, #-8]!
+ str tmp1, [dst, #-8]!
+1:
+ tbz count, #2, 2f
+ ldr tmp1w, [src, #-4]!
+ str tmp1w, [dst, #-4]!
+2:
+ tbz count, #1, 3f
+ ldrh tmp1w, [src, #-2]!
+ strh tmp1w, [dst, #-2]!
+3:
+ tbz count, #0, .Lexitfunc
+ ldrb tmp1w, [src, #-1]
+ strb tmp1w, [dst, #-1]
+
+.Lexitfunc:
+ ret
+
+.Lcpy_over64:
+ subs count, count, #128
+ b.ge .Lcpy_body_large
+ /*
+ * Less than 128 bytes to copy, so handle 64 bytes here and then jump
+ * to the tail.
+ */
+ ldp A_l, A_h, [src, #-16]
+ stp A_l, A_h, [dst, #-16]
+ ldp B_l, B_h, [src, #-32]
+ ldp C_l, C_h, [src, #-48]
+ stp B_l, B_h, [dst, #-32]
+ stp C_l, C_h, [dst, #-48]
+ ldp D_l, D_h, [src, #-64]!
+ stp D_l, D_h, [dst, #-64]!
+
+ tst count, #0x3f
+ b.ne .Ltail63
+ ret
+
+ /*
+ * Critical loop. Start at a new cache line boundary. Assuming
+ * 64 bytes per line this ensures the entire loop is in one line.
+ */
+ .p2align L1_CACHE_SHIFT
+.Lcpy_body_large:
+ /* pre-load 64 bytes data. */
+ ldp A_l, A_h, [src, #-16]
+ ldp B_l, B_h, [src, #-32]
+ ldp C_l, C_h, [src, #-48]
+ ldp D_l, D_h, [src, #-64]!
+1:
+ /*
+ * interlace the load of next 64 bytes data block with store of the last
+ * loaded 64 bytes data.
+ */
+ stp A_l, A_h, [dst, #-16]
+ ldp A_l, A_h, [src, #-16]
+ stp B_l, B_h, [dst, #-32]
+ ldp B_l, B_h, [src, #-32]
+ stp C_l, C_h, [dst, #-48]
+ ldp C_l, C_h, [src, #-48]
+ stp D_l, D_h, [dst, #-64]!
+ ldp D_l, D_h, [src, #-64]!
+ subs count, count, #64
+ b.ge 1b
+ stp A_l, A_h, [dst, #-16]
+ stp B_l, B_h, [dst, #-32]
+ stp C_l, C_h, [dst, #-48]
+ stp D_l, D_h, [dst, #-64]!
+
+ tst count, #0x3f
+ b.ne .Ltail63
+ ret
ENDPROC(memmove)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index 87e4a68..7c72dfd 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -1,5 +1,13 @@
/*
* Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -16,6 +24,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
/*
* Fill in the buffer with character c (alignment handled by the hardware)
@@ -27,27 +36,181 @@
* Returns:
* x0 - buf
*/
+
+dstin .req x0
+val .req w1
+count .req x2
+tmp1 .req x3
+tmp1w .req w3
+tmp2 .req x4
+tmp2w .req w4
+zva_len_x .req x5
+zva_len .req w5
+zva_bits_x .req x6
+
+A_l .req x7
+A_lw .req w7
+dst .req x8
+tmp3w .req w9
+tmp3 .req x9
+
ENTRY(memset)
- mov x4, x0
- and w1, w1, #0xff
- orr w1, w1, w1, lsl #8
- orr w1, w1, w1, lsl #16
- orr x1, x1, x1, lsl #32
- subs x2, x2, #8
- b.mi 2f
-1: str x1, [x4], #8
- subs x2, x2, #8
- b.pl 1b
-2: adds x2, x2, #4
- b.mi 3f
- sub x2, x2, #4
- str w1, [x4], #4
-3: adds x2, x2, #2
- b.mi 4f
- sub x2, x2, #2
- strh w1, [x4], #2
-4: adds x2, x2, #1
- b.mi 5f
- strb w1, [x4]
-5: ret
+ mov dst, dstin /* Preserve return value. */
+ and A_lw, val, #255
+ orr A_lw, A_lw, A_lw, lsl #8
+ orr A_lw, A_lw, A_lw, lsl #16
+ orr A_l, A_l, A_l, lsl #32
+
+ cmp count, #15
+ b.hi .Lover16_proc
+ /*All store maybe are non-aligned..*/
+ tbz count, #3, 1f
+ str A_l, [dst], #8
+1:
+ tbz count, #2, 2f
+ str A_lw, [dst], #4
+2:
+ tbz count, #1, 3f
+ strh A_lw, [dst], #2
+3:
+ tbz count, #0, 4f
+ strb A_lw, [dst]
+4:
+ ret
+
+.Lover16_proc:
+ /*Whether the start address is aligned with 16.*/
+ neg tmp2, dst
+ ands tmp2, tmp2, #15
+ b.eq .Laligned
+/*
+* The count is not less than 16, we can use stp to store the start 16 bytes,
+* then adjust the dst aligned with 16.This process will make the current
+* memory address at alignment boundary.
+*/
+ stp A_l, A_l, [dst] /*non-aligned store..*/
+ /*make the dst aligned..*/
+ sub count, count, tmp2
+ add dst, dst, tmp2
+
+.Laligned:
+ cbz A_l, .Lzero_mem
+
+.Ltail_maybe_long:
+ cmp count, #64
+ b.ge .Lnot_short
+.Ltail63:
+ ands tmp1, count, #0x30
+ b.eq 3f
+ cmp tmp1w, #0x20
+ b.eq 1f
+ b.lt 2f
+ stp A_l, A_l, [dst], #16
+1:
+ stp A_l, A_l, [dst], #16
+2:
+ stp A_l, A_l, [dst], #16
+/*
+* The last store length is less than 16,use stp to write last 16 bytes.
+* It will lead some bytes written twice and the access is non-aligned.
+*/
+3:
+ ands count, count, #15
+ cbz count, 4f
+ add dst, dst, count
+ stp A_l, A_l, [dst, #-16] /* Repeat some/all of last store. */
+4:
+ ret
+
+ /*
+ * Critical loop. Start at a new cache line boundary. Assuming
+ * 64 bytes per line, this ensures the entire loop is in one line.
+ */
+ .p2align L1_CACHE_SHIFT
+.Lnot_short:
+ sub dst, dst, #16/* Pre-bias. */
+ sub count, count, #64
+1:
+ stp A_l, A_l, [dst, #16]
+ stp A_l, A_l, [dst, #32]
+ stp A_l, A_l, [dst, #48]
+ stp A_l, A_l, [dst, #64]!
+ subs count, count, #64
+ b.ge 1b
+ tst count, #0x3f
+ add dst, dst, #16
+ b.ne .Ltail63
+.Lexitfunc:
+ ret
+
+ /*
+ * For zeroing memory, check to see if we can use the ZVA feature to
+ * zero entire 'cache' lines.
+ */
+.Lzero_mem:
+ cmp count, #63
+ b.le .Ltail63
+ /*
+ * For zeroing small amounts of memory, it's not worth setting up
+ * the line-clear code.
+ */
+ cmp count, #128
+ b.lt .Lnot_short /*count is at least 128 bytes*/
+
+ mrs tmp1, dczid_el0
+ tbnz tmp1, #4, .Lnot_short
+ mov tmp3w, #4
+ and zva_len, tmp1w, #15 /* Safety: other bits reserved. */
+ lsl zva_len, tmp3w, zva_len
+
+ ands tmp3w, zva_len, #63
+ /*
+ * ensure the zva_len is not less than 64.
+ * It is not meaningful to use ZVA if the block size is less than 64.
+ */
+ b.ne .Lnot_short
+.Lzero_by_line:
+ /*
+ * Compute how far we need to go to become suitably aligned. We're
+ * already at quad-word alignment.
+ */
+ cmp count, zva_len_x
+ b.lt .Lnot_short /* Not enough to reach alignment. */
+ sub zva_bits_x, zva_len_x, #1
+ neg tmp2, dst
+ ands tmp2, tmp2, zva_bits_x
+ b.eq 2f /* Already aligned. */
+ /* Not aligned, check that there's enough to copy after alignment.*/
+ sub tmp1, count, tmp2
+ /*
+ * grantee the remain length to be ZVA is bigger than 64,
+ * avoid to make the 2f's process over mem range.*/
+ cmp tmp1, #64
+ ccmp tmp1, zva_len_x, #8, ge /* NZCV=0b1000 */
+ b.lt .Lnot_short
+ /*
+ * We know that there's at least 64 bytes to zero and that it's safe
+ * to overrun by 64 bytes.
+ */
+ mov count, tmp1
+1:
+ stp A_l, A_l, [dst]
+ stp A_l, A_l, [dst, #16]
+ stp A_l, A_l, [dst, #32]
+ subs tmp2, tmp2, #64
+ stp A_l, A_l, [dst, #48]
+ add dst, dst, #64
+ b.ge 1b
+ /* We've overrun a bit, so adjust dst downwards.*/
+ add dst, dst, tmp2
+2:
+ sub count, count, zva_len_x
+3:
+ dc zva, dst
+ add dst, dst, zva_len_x
+ subs count, count, zva_len_x
+ b.ge 3b
+ ands count, count, zva_bits_x
+ b.ne .Ltail_maybe_long
+ ret
ENDPROC(memset)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
new file mode 100644
index 0000000..42f828b
--- /dev/null
+++ b/arch/arm64/lib/strcmp.S
@@ -0,0 +1,234 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * compare two strings
+ *
+ * Parameters:
+ * x0 - const string 1 pointer
+ * x1 - const string 2 pointer
+ * Returns:
+ * x0 - an integer less than, equal to, or greater than zero
+ * if s1 is found, respectively, to be less than, to match,
+ * or be greater than s2.
+ */
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+/* Parameters and result. */
+src1 .req x0
+src2 .req x1
+result .req x0
+
+/* Internal variables. */
+data1 .req x2
+data1w .req w2
+data2 .req x3
+data2w .req w3
+has_nul .req x4
+diff .req x5
+syndrome .req x6
+tmp1 .req x7
+tmp2 .req x8
+tmp3 .req x9
+zeroones .req x10
+pos .req x11
+
+ENTRY(strcmp)
+ eor tmp1, src1, src2
+ mov zeroones, #REP8_01
+ tst tmp1, #7
+ b.ne .Lmisaligned8
+ ands tmp1, src1, #7
+ b.ne .Lmutual_align
+
+ /*
+ * NUL detection works on the principle that (X - 1) & (~X) & 0x80
+ * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+ * can be done in parallel across the entire word.
+ */
+.Lloop_aligned:
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+.Lstart_realigned:
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ bic has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */
+ orr syndrome, diff, has_nul
+ cbz syndrome, .Lloop_aligned
+ b .Lcal_cmpresult
+
+.Lmutual_align:
+ /*
+ * Sources are mutually aligned, but are not currently at an
+ * alignment boundary. Round down the addresses and then mask off
+ * the bytes that preceed the start point.
+ */
+ bic src1, src1, #7
+ bic src2, src2, #7
+ lsl tmp1, tmp1, #3 /* Bytes beyond alignment -> bits. */
+ ldr data1, [src1], #8
+ neg tmp1, tmp1 /* Bits to alignment -64. */
+ ldr data2, [src2], #8
+ mov tmp2, #~0
+ /* Big-endian. Early bytes are at MSB. */
+CPU_BE( lsl tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
+ /* Little-endian. Early bytes are at LSB. */
+CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
+
+ orr data1, data1, tmp2
+ orr data2, data2, tmp2
+ b .Lstart_realigned
+
+.Lmisaligned8:
+ /*
+ * Get the align offset length to compare per byte first.
+ * After this process, one string's address will be aligned.
+ */
+ and tmp1, src1, #7
+ neg tmp1, tmp1
+ add tmp1, tmp1, #8
+ and tmp2, src2, #7
+ neg tmp2, tmp2
+ add tmp2, tmp2, #8
+ subs tmp3, tmp1, tmp2
+ csel pos, tmp1, tmp2, hi /*Choose the maximum. */
+.Ltinycmp:
+ ldrb data1w, [src1], #1
+ ldrb data2w, [src2], #1
+ subs pos, pos, #1
+ ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */
+ ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */
+ b.eq .Ltinycmp
+ cbnz pos, 1f /*find the null or unequal...*/
+ cmp data1w, #1
+ ccmp data1w, data2w, #0, cs
+ b.eq .Lstart_align /*the last bytes are equal....*/
+1:
+ sub result, data1, data2
+ ret
+
+.Lstart_align:
+ ands xzr, src1, #7
+ b.eq .Lrecal_offset
+ /*process more leading bytes to make str1 aligned...*/
+ add src1, src1, tmp3
+ add src2, src2, tmp3
+ /*load 8 bytes from aligned str1 and non-aligned str2..*/
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ bic has_nul, tmp1, tmp2
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ orr syndrome, diff, has_nul
+ cbnz syndrome, .Lcal_cmpresult
+ /*How far is the current str2 from the alignment boundary...*/
+ and tmp3, tmp3, #7
+.Lrecal_offset:
+ neg pos, tmp3
+.Lloopcmp_proc:
+ /*
+ * Divide the eight bytes into two parts. First,backwards the src2
+ * to an alignment boundary,load eight bytes from the SRC2 alignment
+ * boundary,then compare with the relative bytes from SRC1.
+ * If all 8 bytes are equal,then start the second part's comparison.
+ * Otherwise finish the comparison.
+ * This special handle can garantee all the accesses are in the
+ * thread/task space in avoid to overrange access.
+ */
+ ldr data1, [src1,pos]
+ ldr data2, [src2,pos]
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ bic has_nul, tmp1, tmp2
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ orr syndrome, diff, has_nul
+ cbnz syndrome, .Lcal_cmpresult
+
+ /*The second part process*/
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ bic has_nul, tmp1, tmp2
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ orr syndrome, diff, has_nul
+ cbz syndrome, .Lloopcmp_proc
+
+.Lcal_cmpresult:
+ /*
+ * reversed the byte-order as big-endian,then CLZ can find the most
+ * significant zero bits.
+ */
+CPU_LE( rev syndrome, syndrome )
+CPU_LE( rev data1, data1 )
+CPU_LE( rev data2, data2 )
+
+ /*
+ * For big-endian we cannot use the trick with the syndrome value
+ * as carry-propagation can corrupt the upper bits if the trailing
+ * bytes in the string contain 0x01.
+ * However, if there is no NUL byte in the dword, we can generate
+ * the result directly. We ca not just subtract the bytes as the
+ * MSB might be significant.
+ */
+CPU_BE( cbnz has_nul, 1f )
+CPU_BE( cmp data1, data2 )
+CPU_BE( cset result, ne )
+CPU_BE( cneg result, result, lo )
+CPU_BE( ret )
+CPU_BE( 1: )
+ /*Re-compute the NUL-byte detection, using a byte-reversed value. */
+CPU_BE( rev tmp3, data1 )
+CPU_BE( sub tmp1, tmp3, zeroones )
+CPU_BE( orr tmp2, tmp3, #REP8_7f )
+CPU_BE( bic has_nul, tmp1, tmp2 )
+CPU_BE( rev has_nul, has_nul )
+CPU_BE( orr syndrome, diff, has_nul )
+
+ clz pos, syndrome
+ /*
+ * The MS-non-zero bit of the syndrome marks either the first bit
+ * that is different, or the top bit of the first zero byte.
+ * Shifting left now will bring the critical information into the
+ * top bits.
+ */
+ lsl data1, data1, pos
+ lsl data2, data2, pos
+ /*
+ * But we need to zero-extend (char is unsigned) the value and then
+ * perform a signed 32-bit subtraction.
+ */
+ lsr data1, data1, #56
+ sub result, data1, data2, lsr #56
+ ret
+ENDPROC(strcmp)
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
new file mode 100644
index 0000000..987b68b
--- /dev/null
+++ b/arch/arm64/lib/strlen.S
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * calculate the length of a string
+ *
+ * Parameters:
+ * x0 - const string pointer
+ * Returns:
+ * x0 - the return length of specific string
+ */
+
+/* Arguments and results. */
+srcin .req x0
+len .req x0
+
+/* Locals and temporaries. */
+src .req x1
+data1 .req x2
+data2 .req x3
+data2a .req x4
+has_nul1 .req x5
+has_nul2 .req x6
+tmp1 .req x7
+tmp2 .req x8
+tmp3 .req x9
+tmp4 .req x10
+zeroones .req x11
+pos .req x12
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+ENTRY(strlen)
+ mov zeroones, #REP8_01
+ bic src, srcin, #15
+ ands tmp1, srcin, #15
+ b.ne .Lmisaligned
+ /*
+ * NUL detection works on the principle that (X - 1) & (~X) & 0x80
+ * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+ * can be done in parallel across the entire word.
+ */
+ /*
+ * The inner loop deals with two Dwords at a time. This has a
+ * slightly higher start-up cost, but we should win quite quickly,
+ * especially on cores with a high number of issue slots per
+ * cycle, as we get much better parallelism out of the operations.
+ */
+.Lloop:
+ ldp data1, data2, [src], #16
+.Lrealigned:
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ sub tmp3, data2, zeroones
+ orr tmp4, data2, #REP8_7f
+ bic has_nul1, tmp1, tmp2
+ bics has_nul2, tmp3, tmp4
+ ccmp has_nul1, #0, #0, eq /* NZCV = 0000 */
+ b.eq .Lloop
+
+ sub len, src, srcin
+ cbz has_nul1, .Lnul_in_data2
+CPU_BE( mov data2, data1 ) /*prepare data to re-calculate the syndrome*/
+ sub len, len, #8
+ mov has_nul2, has_nul1
+.Lnul_in_data2:
+ /*
+ * For big-endian, carry propagation (if the final byte in the
+ * string is 0x01) means we cannot use has_nul directly. The
+ * easiest way to get the correct byte is to byte-swap the data
+ * and calculate the syndrome a second time.
+ */
+CPU_BE( rev data2, data2 )
+CPU_BE( sub tmp1, data2, zeroones )
+CPU_BE( orr tmp2, data2, #REP8_7f )
+CPU_BE( bic has_nul2, tmp1, tmp2 )
+
+ sub len, len, #8
+ rev has_nul2, has_nul2
+ clz pos, has_nul2
+ add len, len, pos, lsr #3 /* Bits to bytes. */
+ ret
+
+.Lmisaligned:
+ cmp tmp1, #8
+ neg tmp1, tmp1
+ ldp data1, data2, [src], #16
+ lsl tmp1, tmp1, #3 /* Bytes beyond alignment -> bits. */
+ mov tmp2, #~0
+ /* Big-endian. Early bytes are at MSB. */
+CPU_BE( lsl tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
+ /* Little-endian. Early bytes are at LSB. */
+CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
+
+ orr data1, data1, tmp2
+ orr data2a, data2, tmp2
+ csinv data1, data1, xzr, le
+ csel data2, data2, data2a, le
+ b .Lrealigned
+ENDPROC(strlen)
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
new file mode 100644
index 0000000..0224cf5
--- /dev/null
+++ b/arch/arm64/lib/strncmp.S
@@ -0,0 +1,310 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * compare two strings
+ *
+ * Parameters:
+ * x0 - const string 1 pointer
+ * x1 - const string 2 pointer
+ * x2 - the maximal length to be compared
+ * Returns:
+ * x0 - an integer less than, equal to, or greater than zero if s1 is found,
+ * respectively, to be less than, to match, or be greater than s2.
+ */
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+/* Parameters and result. */
+src1 .req x0
+src2 .req x1
+limit .req x2
+result .req x0
+
+/* Internal variables. */
+data1 .req x3
+data1w .req w3
+data2 .req x4
+data2w .req w4
+has_nul .req x5
+diff .req x6
+syndrome .req x7
+tmp1 .req x8
+tmp2 .req x9
+tmp3 .req x10
+zeroones .req x11
+pos .req x12
+limit_wd .req x13
+mask .req x14
+endloop .req x15
+
+ENTRY(strncmp)
+ cbz limit, .Lret0
+ eor tmp1, src1, src2
+ mov zeroones, #REP8_01
+ tst tmp1, #7
+ b.ne .Lmisaligned8
+ ands tmp1, src1, #7
+ b.ne .Lmutual_align
+ /* Calculate the number of full and partial words -1. */
+ /*
+ * when limit is mulitply of 8, if not sub 1,
+ * the judgement of last dword will wrong.
+ */
+ sub limit_wd, limit, #1 /* limit != 0, so no underflow. */
+ lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */
+
+ /*
+ * NUL detection works on the principle that (X - 1) & (~X) & 0x80
+ * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+ * can be done in parallel across the entire word.
+ */
+.Lloop_aligned:
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+.Lstart_realigned:
+ subs limit_wd, limit_wd, #1
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ csinv endloop, diff, xzr, pl /* Last Dword or differences.*/
+ bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */
+ ccmp endloop, #0, #0, eq
+ b.eq .Lloop_aligned
+
+ /*Not reached the limit, must have found the end or a diff. */
+ tbz limit_wd, #63, .Lnot_limit
+
+ /* Limit % 8 == 0 => all bytes significant. */
+ ands limit, limit, #7
+ b.eq .Lnot_limit
+
+ lsl limit, limit, #3 /* Bits -> bytes. */
+ mov mask, #~0
+CPU_BE( lsr mask, mask, limit )
+CPU_LE( lsl mask, mask, limit )
+ bic data1, data1, mask
+ bic data2, data2, mask
+
+ /* Make sure that the NUL byte is marked in the syndrome. */
+ orr has_nul, has_nul, mask
+
+.Lnot_limit:
+ orr syndrome, diff, has_nul
+ b .Lcal_cmpresult
+
+.Lmutual_align:
+ /*
+ * Sources are mutually aligned, but are not currently at an
+ * alignment boundary. Round down the addresses and then mask off
+ * the bytes that precede the start point.
+ * We also need to adjust the limit calculations, but without
+ * overflowing if the limit is near ULONG_MAX.
+ */
+ bic src1, src1, #7
+ bic src2, src2, #7
+ ldr data1, [src1], #8
+ neg tmp3, tmp1, lsl #3 /* 64 - bits(bytes beyond align). */
+ ldr data2, [src2], #8
+ mov tmp2, #~0
+ sub limit_wd, limit, #1 /* limit != 0, so no underflow. */
+ /* Big-endian. Early bytes are at MSB. */
+CPU_BE( lsl tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */
+ /* Little-endian. Early bytes are at LSB. */
+CPU_LE( lsr tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */
+
+ and tmp3, limit_wd, #7
+ lsr limit_wd, limit_wd, #3
+ /* Adjust the limit. Only low 3 bits used, so overflow irrelevant.*/
+ add limit, limit, tmp1
+ add tmp3, tmp3, tmp1
+ orr data1, data1, tmp2
+ orr data2, data2, tmp2
+ add limit_wd, limit_wd, tmp3, lsr #3
+ b .Lstart_realigned
+
+/*when src1 offset is not equal to src2 offset...*/
+.Lmisaligned8:
+ cmp limit, #8
+ b.lo .Ltiny8proc /*limit < 8... */
+ /*
+ * Get the align offset length to compare per byte first.
+ * After this process, one string's address will be aligned.*/
+ and tmp1, src1, #7
+ neg tmp1, tmp1
+ add tmp1, tmp1, #8
+ and tmp2, src2, #7
+ neg tmp2, tmp2
+ add tmp2, tmp2, #8
+ subs tmp3, tmp1, tmp2
+ csel pos, tmp1, tmp2, hi /*Choose the maximum. */
+ /*
+ * Here, limit is not less than 8, so directly run .Ltinycmp
+ * without checking the limit.*/
+ sub limit, limit, pos
+.Ltinycmp:
+ ldrb data1w, [src1], #1
+ ldrb data2w, [src2], #1
+ subs pos, pos, #1
+ ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */
+ ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */
+ b.eq .Ltinycmp
+ cbnz pos, 1f /*find the null or unequal...*/
+ cmp data1w, #1
+ ccmp data1w, data2w, #0, cs
+ b.eq .Lstart_align /*the last bytes are equal....*/
+1:
+ sub result, data1, data2
+ ret
+
+.Lstart_align:
+ lsr limit_wd, limit, #3
+ cbz limit_wd, .Lremain8
+ /*process more leading bytes to make str1 aligned...*/
+ ands xzr, src1, #7
+ b.eq .Lrecal_offset
+ add src1, src1, tmp3 /*tmp3 is positive in this branch.*/
+ add src2, src2, tmp3
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+
+ sub limit, limit, tmp3
+ lsr limit_wd, limit, #3
+ subs limit_wd, limit_wd, #1
+
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
+ bics has_nul, tmp1, tmp2
+ ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
+ b.ne .Lunequal_proc
+ /*How far is the current str2 from the alignment boundary...*/
+ and tmp3, tmp3, #7
+.Lrecal_offset:
+ neg pos, tmp3
+.Lloopcmp_proc:
+ /*
+ * Divide the eight bytes into two parts. First,backwards the src2
+ * to an alignment boundary,load eight bytes from the SRC2 alignment
+ * boundary,then compare with the relative bytes from SRC1.
+ * If all 8 bytes are equal,then start the second part's comparison.
+ * Otherwise finish the comparison.
+ * This special handle can garantee all the accesses are in the
+ * thread/task space in avoid to overrange access.
+ */
+ ldr data1, [src1,pos]
+ ldr data2, [src2,pos]
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ csinv endloop, diff, xzr, eq
+ cbnz endloop, .Lunequal_proc
+
+ /*The second part process*/
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+ subs limit_wd, limit_wd, #1
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/
+ bics has_nul, tmp1, tmp2
+ ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/
+ b.eq .Lloopcmp_proc
+
+.Lunequal_proc:
+ orr syndrome, diff, has_nul
+ cbz syndrome, .Lremain8
+.Lcal_cmpresult:
+ /*
+ * reversed the byte-order as big-endian,then CLZ can find the most
+ * significant zero bits.
+ */
+CPU_LE( rev syndrome, syndrome )
+CPU_LE( rev data1, data1 )
+CPU_LE( rev data2, data2 )
+ /*
+ * For big-endian we cannot use the trick with the syndrome value
+ * as carry-propagation can corrupt the upper bits if the trailing
+ * bytes in the string contain 0x01.
+ * However, if there is no NUL byte in the dword, we can generate
+ * the result directly. We can't just subtract the bytes as the
+ * MSB might be significant.
+ */
+CPU_BE( cbnz has_nul, 1f )
+CPU_BE( cmp data1, data2 )
+CPU_BE( cset result, ne )
+CPU_BE( cneg result, result, lo )
+CPU_BE( ret )
+CPU_BE( 1: )
+ /* Re-compute the NUL-byte detection, using a byte-reversed value.*/
+CPU_BE( rev tmp3, data1 )
+CPU_BE( sub tmp1, tmp3, zeroones )
+CPU_BE( orr tmp2, tmp3, #REP8_7f )
+CPU_BE( bic has_nul, tmp1, tmp2 )
+CPU_BE( rev has_nul, has_nul )
+CPU_BE( orr syndrome, diff, has_nul )
+ /*
+ * The MS-non-zero bit of the syndrome marks either the first bit
+ * that is different, or the top bit of the first zero byte.
+ * Shifting left now will bring the critical information into the
+ * top bits.
+ */
+ clz pos, syndrome
+ lsl data1, data1, pos
+ lsl data2, data2, pos
+ /*
+ * But we need to zero-extend (char is unsigned) the value and then
+ * perform a signed 32-bit subtraction.
+ */
+ lsr data1, data1, #56
+ sub result, data1, data2, lsr #56
+ ret
+
+.Lremain8:
+ /* Limit % 8 == 0 => all bytes significant. */
+ ands limit, limit, #7
+ b.eq .Lret0
+.Ltiny8proc:
+ ldrb data1w, [src1], #1
+ ldrb data2w, [src2], #1
+ subs limit, limit, #1
+
+ ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */
+ ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */
+ b.eq .Ltiny8proc
+ sub result, data1, data2
+ ret
+
+.Lret0:
+ mov result, #0
+ ret
+ENDPROC(strncmp)
diff --git a/arch/arm64/lib/strncpy_from_user.S b/arch/arm64/lib/strncpy_from_user.S
deleted file mode 100644
index 56e448a..0000000
--- a/arch/arm64/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Based on arch/arm/lib/strncpy_from_user.S
- *
- * Copyright (C) 1995-2000 Russell King
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
- .text
- .align 5
-
-/*
- * Copy a string from user space to kernel space.
- * x0 = dst, x1 = src, x2 = byte length
- * returns the number of characters copied (strlen of copied string),
- * -EFAULT on exception, or "len" if we fill the whole buffer
- */
-ENTRY(__strncpy_from_user)
- mov x4, x1
-1: subs x2, x2, #1
- bmi 2f
-USER(9f, ldrb w3, [x1], #1 )
- strb w3, [x0], #1
- cbnz w3, 1b
- sub x1, x1, #1 // take NUL character out of count
-2: sub x0, x1, x4
- ret
-ENDPROC(__strncpy_from_user)
-
- .section .fixup,"ax"
- .align 0
-9: strb wzr, [x0] // null terminate
- mov x0, #-EFAULT
- ret
- .previous
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
new file mode 100644
index 0000000..2ca6657
--- /dev/null
+++ b/arch/arm64/lib/strnlen.S
@@ -0,0 +1,171 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * determine the length of a fixed-size string
+ *
+ * Parameters:
+ * x0 - const string pointer
+ * x1 - maximal string length
+ * Returns:
+ * x0 - the return length of specific string
+ */
+
+/* Arguments and results. */
+srcin .req x0
+len .req x0
+limit .req x1
+
+/* Locals and temporaries. */
+src .req x2
+data1 .req x3
+data2 .req x4
+data2a .req x5
+has_nul1 .req x6
+has_nul2 .req x7
+tmp1 .req x8
+tmp2 .req x9
+tmp3 .req x10
+tmp4 .req x11
+zeroones .req x12
+pos .req x13
+limit_wd .req x14
+
+#define REP8_01 0x0101010101010101
+#define REP8_7f 0x7f7f7f7f7f7f7f7f
+#define REP8_80 0x8080808080808080
+
+ENTRY(strnlen)
+ cbz limit, .Lhit_limit
+ mov zeroones, #REP8_01
+ bic src, srcin, #15
+ ands tmp1, srcin, #15
+ b.ne .Lmisaligned
+ /* Calculate the number of full and partial words -1. */
+ sub limit_wd, limit, #1 /* Limit != 0, so no underflow. */
+ lsr limit_wd, limit_wd, #4 /* Convert to Qwords. */
+
+ /*
+ * NUL detection works on the principle that (X - 1) & (~X) & 0x80
+ * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+ * can be done in parallel across the entire word.
+ */
+ /*
+ * The inner loop deals with two Dwords at a time. This has a
+ * slightly higher start-up cost, but we should win quite quickly,
+ * especially on cores with a high number of issue slots per
+ * cycle, as we get much better parallelism out of the operations.
+ */
+.Lloop:
+ ldp data1, data2, [src], #16
+.Lrealigned:
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ sub tmp3, data2, zeroones
+ orr tmp4, data2, #REP8_7f
+ bic has_nul1, tmp1, tmp2
+ bic has_nul2, tmp3, tmp4
+ subs limit_wd, limit_wd, #1
+ orr tmp1, has_nul1, has_nul2
+ ccmp tmp1, #0, #0, pl /* NZCV = 0000 */
+ b.eq .Lloop
+
+ cbz tmp1, .Lhit_limit /* No null in final Qword. */
+
+ /*
+ * We know there's a null in the final Qword. The easiest thing
+ * to do now is work out the length of the string and return
+ * MIN (len, limit).
+ */
+ sub len, src, srcin
+ cbz has_nul1, .Lnul_in_data2
+CPU_BE( mov data2, data1 ) /*perpare data to re-calculate the syndrome*/
+
+ sub len, len, #8
+ mov has_nul2, has_nul1
+.Lnul_in_data2:
+ /*
+ * For big-endian, carry propagation (if the final byte in the
+ * string is 0x01) means we cannot use has_nul directly. The
+ * easiest way to get the correct byte is to byte-swap the data
+ * and calculate the syndrome a second time.
+ */
+CPU_BE( rev data2, data2 )
+CPU_BE( sub tmp1, data2, zeroones )
+CPU_BE( orr tmp2, data2, #REP8_7f )
+CPU_BE( bic has_nul2, tmp1, tmp2 )
+
+ sub len, len, #8
+ rev has_nul2, has_nul2
+ clz pos, has_nul2
+ add len, len, pos, lsr #3 /* Bits to bytes. */
+ cmp len, limit
+ csel len, len, limit, ls /* Return the lower value. */
+ ret
+
+.Lmisaligned:
+ /*
+ * Deal with a partial first word.
+ * We're doing two things in parallel here;
+ * 1) Calculate the number of words (but avoiding overflow if
+ * limit is near ULONG_MAX) - to do this we need to work out
+ * limit + tmp1 - 1 as a 65-bit value before shifting it;
+ * 2) Load and mask the initial data words - we force the bytes
+ * before the ones we are interested in to 0xff - this ensures
+ * early bytes will not hit any zero detection.
+ */
+ ldp data1, data2, [src], #16
+
+ sub limit_wd, limit, #1
+ and tmp3, limit_wd, #15
+ lsr limit_wd, limit_wd, #4
+
+ add tmp3, tmp3, tmp1
+ add limit_wd, limit_wd, tmp3, lsr #4
+
+ neg tmp4, tmp1
+ lsl tmp4, tmp4, #3 /* Bytes beyond alignment -> bits. */
+
+ mov tmp2, #~0
+ /* Big-endian. Early bytes are at MSB. */
+CPU_BE( lsl tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */
+ /* Little-endian. Early bytes are at LSB. */
+CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */
+
+ cmp tmp1, #8
+
+ orr data1, data1, tmp2
+ orr data2a, data2, tmp2
+
+ csinv data1, data1, xzr, le
+ csel data2, data2, data2a, le
+ b .Lrealigned
+
+.Lhit_limit:
+ mov len, limit
+ ret
+ENDPROC(strnlen)
diff --git a/arch/arm64/lib/strnlen_user.S b/arch/arm64/lib/strnlen_user.S
deleted file mode 100644
index 7f7b176..0000000
--- a/arch/arm64/lib/strnlen_user.S
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Based on arch/arm/lib/strnlen_user.S
- *
- * Copyright (C) 1995-2000 Russell King
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
- .text
- .align 5
-
-/* Prototype: unsigned long __strnlen_user(const char *str, long n)
- * Purpose : get length of a string in user memory
- * Params : str - address of string in user memory
- * Returns : length of string *including terminator*
- * or zero on exception, or n if too long
- */
-ENTRY(__strnlen_user)
- mov x2, x0
-1: subs x1, x1, #1
- b.mi 2f
-USER(9f, ldrb w3, [x0], #1 )
- cbnz w3, 1b
-2: sub x0, x0, x2
- ret
-ENDPROC(__strnlen_user)
-
- .section .fixup,"ax"
- .align 0
-9: mov x0, #0
- ret
- .previous
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 3140a2a..c56179e 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -1,4 +1,5 @@
obj-y := dma-mapping.o extable.o fault.o init.o \
cache.o copypage.o flush.o \
ioremap.o mmap.o pgd.o mmu.o \
- context.o tlb.o proc.o
+ context.o proc.o pageattr.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 48a3860..2366383 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -30,8 +30,8 @@
*
* Corrupted registers: x0-x7, x9-x11
*/
-ENTRY(__flush_dcache_all)
- dsb sy // ensure ordering with previous memory accesses
+__flush_dcache_all:
+ dmb sy // ensure ordering with previous memory accesses
mrs x0, clidr_el1 // read clidr
and x3, x0, #0x7000000 // extract loc from clidr
lsr x3, x3, #23 // left align loc bit field
@@ -128,7 +128,7 @@
add x4, x4, x2
cmp x4, x1
b.lo 1b
- dsb sy
+ dsb ish
icache_line_size x2, x3
sub x3, x2, #1
@@ -139,14 +139,14 @@
cmp x4, x1
b.lo 1b
9: // ignore any faulting cache operation
- dsb sy
+ dsb ish
isb
ret
ENDPROC(flush_icache_range)
ENDPROC(__flush_cache_user_range)
/*
- * __flush_kern_dcache_page(kaddr)
+ * __flush_dcache_area(kaddr, size)
*
* Ensure that the data held in the page kaddr is written back to the
* page in question.
@@ -166,3 +166,97 @@
dsb sy
ret
ENDPROC(__flush_dcache_area)
+
+/*
+ * __inval_cache_range(start, end)
+ * - start - start address of region
+ * - end - end address of region
+ */
+ENTRY(__inval_cache_range)
+ /* FALLTHROUGH */
+
+/*
+ * __dma_inv_range(start, end)
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+__dma_inv_range:
+ dcache_line_size x2, x3
+ sub x3, x2, #1
+ tst x1, x3 // end cache line aligned?
+ bic x1, x1, x3
+ b.eq 1f
+ dc civac, x1 // clean & invalidate D / U line
+1: tst x0, x3 // start cache line aligned?
+ bic x0, x0, x3
+ b.eq 2f
+ dc civac, x0 // clean & invalidate D / U line
+ b 3f
+2: dc ivac, x0 // invalidate D / U line
+3: add x0, x0, x2
+ cmp x0, x1
+ b.lo 2b
+ dsb sy
+ ret
+ENDPROC(__inval_cache_range)
+ENDPROC(__dma_inv_range)
+
+/*
+ * __dma_clean_range(start, end)
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+__dma_clean_range:
+ dcache_line_size x2, x3
+ sub x3, x2, #1
+ bic x0, x0, x3
+1: dc cvac, x0 // clean D / U line
+ add x0, x0, x2
+ cmp x0, x1
+ b.lo 1b
+ dsb sy
+ ret
+ENDPROC(__dma_clean_range)
+
+/*
+ * __dma_flush_range(start, end)
+ * - start - virtual start address of region
+ * - end - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+ dcache_line_size x2, x3
+ sub x3, x2, #1
+ bic x0, x0, x3
+1: dc civac, x0 // clean & invalidate D / U line
+ add x0, x0, x2
+ cmp x0, x1
+ b.lo 1b
+ dsb sy
+ ret
+ENDPROC(__dma_flush_range)
+
+/*
+ * __dma_map_area(start, size, dir)
+ * - start - kernel virtual start address
+ * - size - size of region
+ * - dir - DMA direction
+ */
+ENTRY(__dma_map_area)
+ add x1, x1, x0
+ cmp w2, #DMA_FROM_DEVICE
+ b.eq __dma_inv_range
+ b __dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ * __dma_unmap_area(start, size, dir)
+ * - start - kernel virtual start address
+ * - size - size of region
+ * - dir - DMA direction
+ */
+ENTRY(__dma_unmap_area)
+ add x1, x1, x0
+ cmp w2, #DMA_TO_DEVICE
+ b.ne __dma_inv_range
+ ret
+ENDPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 9aecbac..13bbc3be 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -27,8 +27,10 @@
copy_page(kto, kfrom);
__flush_dcache_area(kto, PAGE_SIZE);
}
+EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
{
clear_page(kaddr);
}
+EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 4bd7579..eeb1cf3 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -20,35 +20,333 @@
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/slab.h>
+#include <linux/genalloc.h>
#include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>
+#include <linux/amba/bus.h>
#include <asm/cacheflush.h>
struct dma_map_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
-static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags,
- struct dma_attrs *attrs)
+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+ bool coherent)
{
- if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+ if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+ return pgprot_writecombine(prot);
+ else if (!coherent)
+ return pgprot_dmacoherent(prot);
+ return prot;
+}
+
+static struct gen_pool *atomic_pool;
+
+#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
+static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE;
+
+static int __init early_coherent_pool(char *p)
+{
+ atomic_pool_size = memparse(p, &p);
+ return 0;
+}
+early_param("coherent_pool", early_coherent_pool);
+
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
+{
+ unsigned long val;
+ void *ptr = NULL;
+
+ if (!atomic_pool) {
+ WARN(1, "coherent pool not initialised!\n");
+ return NULL;
+ }
+
+ val = gen_pool_alloc(atomic_pool, size);
+ if (val) {
+ phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val);
+
+ *ret_page = phys_to_page(phys);
+ ptr = (void *)val;
+ }
+
+ return ptr;
+}
+
+static bool __in_atomic_pool(void *start, size_t size)
+{
+ return addr_in_gen_pool(atomic_pool, (unsigned long)start, size);
+}
+
+static int __free_from_pool(void *start, size_t size)
+{
+ if (!__in_atomic_pool(start, size))
+ return 0;
+
+ gen_pool_free(atomic_pool, (unsigned long)start, size);
+
+ return 1;
+}
+
+static void *__dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
+{
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
dev->coherent_dma_mask <= DMA_BIT_MASK(32))
- flags |= GFP_DMA32;
- return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+ flags |= GFP_DMA;
+ if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
+ struct page *page;
+
+ size = PAGE_ALIGN(size);
+ page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+ get_order(size));
+ if (!page)
+ return NULL;
+
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+ return page_address(page);
+ } else {
+ return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+ }
}
-static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle,
- struct dma_attrs *attrs)
+static void __dma_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
{
- swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+ bool freed;
+ phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
+ if (dev == NULL) {
+ WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+ return;
+ }
+
+ freed = dma_release_from_contiguous(dev,
+ phys_to_page(paddr),
+ size >> PAGE_SHIFT);
+ if (!freed)
+ swiotlb_free_coherent(dev, size, vaddr, dma_handle);
}
-static struct dma_map_ops arm64_swiotlb_dma_ops = {
- .alloc = arm64_swiotlb_alloc_coherent,
- .free = arm64_swiotlb_free_coherent,
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags,
+ struct dma_attrs *attrs)
+{
+ struct page *page;
+ void *ptr, *coherent_ptr;
+
+ size = PAGE_ALIGN(size);
+
+ if (!(flags & __GFP_WAIT)) {
+ struct page *page = NULL;
+ void *addr = __alloc_from_pool(size, &page);
+
+ if (addr)
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+
+ return addr;
+
+ }
+
+ ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+ if (!ptr)
+ goto no_mem;
+
+ /* remove any dirty cache lines on the kernel alias */
+ __dma_flush_range(ptr, ptr + size);
+
+ /* create a coherent mapping */
+ page = virt_to_page(ptr);
+ coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+ __get_dma_pgprot(attrs,
+ __pgprot(PROT_NORMAL_NC), false),
+ NULL);
+ if (!coherent_ptr)
+ goto no_map;
+
+ return coherent_ptr;
+
+no_map:
+ __dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+ *dma_handle = ~0;
+ return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_handle,
+ struct dma_attrs *attrs)
+{
+ void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+ if (__free_from_pool(vaddr, size))
+ return;
+ vunmap(vaddr);
+ __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ dma_addr_t dev_addr;
+
+ dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+ return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+ swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ struct scatterlist *sg;
+ int i, ret;
+
+ ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+ for_each_sg(sgl, sg, ret, i)
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+
+ return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir,
+ struct dma_attrs *attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+ swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+ swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+ dma_addr_t dev_addr, size_t size,
+ enum dma_data_direction dir)
+{
+ swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+ swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+ for_each_sg(sgl, sg, nelems, i)
+ __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+ sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+ int ret = -ENXIO;
+ unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+ PAGE_SHIFT;
+ unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+ unsigned long off = vma->vm_pgoff;
+
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+ ret = remap_pfn_range(vma, vma->vm_start,
+ pfn + off,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot);
+ }
+
+ return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
+{
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+ return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ struct dma_attrs *attrs)
+{
+ /* Just use whatever page_prot attributes were specified */
+ return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+ .alloc = __dma_alloc_noncoherent,
+ .free = __dma_free_noncoherent,
+ .mmap = __swiotlb_mmap_noncoherent,
+ .map_page = __swiotlb_map_page,
+ .unmap_page = __swiotlb_unmap_page,
+ .map_sg = __swiotlb_map_sg_attrs,
+ .unmap_sg = __swiotlb_unmap_sg_attrs,
+ .sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+ .sync_single_for_device = __swiotlb_sync_single_for_device,
+ .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+ .sync_sg_for_device = __swiotlb_sync_sg_for_device,
+ .dma_supported = swiotlb_dma_supported,
+ .mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
+ .alloc = __dma_alloc_coherent,
+ .free = __dma_free_coherent,
+ .mmap = __swiotlb_mmap_coherent,
.map_page = swiotlb_map_page,
.unmap_page = swiotlb_unmap_page,
.map_sg = swiotlb_map_sg_attrs,
@@ -60,13 +358,119 @@
.dma_supported = swiotlb_dma_supported,
.mapping_error = swiotlb_dma_mapping_error,
};
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
-void __init arm64_swiotlb_init(void)
+static int dma_bus_notifier(struct notifier_block *nb,
+ unsigned long event, void *_dev)
{
- dma_ops = &arm64_swiotlb_dma_ops;
- swiotlb_init(1);
+ struct device *dev = _dev;
+
+ if (event != BUS_NOTIFY_ADD_DEVICE)
+ return NOTIFY_DONE;
+
+ if (of_property_read_bool(dev->of_node, "dma-coherent"))
+ set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+
+ return NOTIFY_OK;
}
+static struct notifier_block platform_bus_nb = {
+ .notifier_call = dma_bus_notifier,
+};
+
+static struct notifier_block amba_bus_nb = {
+ .notifier_call = dma_bus_notifier,
+};
+
+extern int swiotlb_late_init_with_default_size(size_t default_size);
+
+static int __init atomic_pool_init(void)
+{
+ pgprot_t prot = __pgprot(PROT_NORMAL_NC);
+ unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT;
+ struct page *page;
+ void *addr;
+ unsigned int pool_size_order = get_order(atomic_pool_size);
+
+ if (dev_get_cma_area(NULL))
+ page = dma_alloc_from_contiguous(NULL, nr_pages,
+ pool_size_order);
+ else
+ page = alloc_pages(GFP_DMA, pool_size_order);
+
+ if (page) {
+ int ret;
+ void *page_addr = page_address(page);
+
+ memset(page_addr, 0, atomic_pool_size);
+ __dma_flush_range(page_addr, page_addr + atomic_pool_size);
+
+ atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
+ if (!atomic_pool)
+ goto free_page;
+
+ addr = dma_common_contiguous_remap(page, atomic_pool_size,
+ VM_USERMAP, prot, atomic_pool_init);
+
+ if (!addr)
+ goto destroy_genpool;
+
+ ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr,
+ page_to_phys(page),
+ atomic_pool_size, -1);
+ if (ret)
+ goto remove_mapping;
+
+ gen_pool_set_algo(atomic_pool,
+ gen_pool_first_fit_order_align,
+ (void *)PAGE_SHIFT);
+
+ pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
+ atomic_pool_size / 1024);
+ return 0;
+ }
+ goto out;
+
+remove_mapping:
+ dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+destroy_genpool:
+ gen_pool_destroy(atomic_pool);
+ atomic_pool = NULL;
+free_page:
+ if (!dma_release_from_contiguous(NULL, page, nr_pages))
+ __free_pages(page, pool_size_order);
+out:
+ pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n",
+ atomic_pool_size / 1024);
+ return -ENOMEM;
+}
+
+static int __init swiotlb_late_init(void)
+{
+ size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+ /*
+ * These must be registered before of_platform_populate().
+ */
+ bus_register_notifier(&platform_bus_type, &platform_bus_nb);
+ bus_register_notifier(&amba_bustype, &amba_bus_nb);
+
+ dma_ops = &noncoherent_swiotlb_dma_ops;
+
+ return swiotlb_late_init_with_default_size(swiotlb_size);
+}
+
+static int __init arm64_dma_init(void)
+{
+ int ret = 0;
+
+ ret |= swiotlb_late_init();
+ ret |= atomic_pool_init();
+
+ return ret;
+}
+arch_initcall(arm64_dma_init);
+
#define PREALLOC_DMA_DEBUG_ENTRIES 4096
static int __init dma_debug_do_init(void)
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1426468..c23751b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -130,7 +130,7 @@
force_sig_info(sig, &si, tsk);
}
-void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
@@ -152,25 +152,8 @@
#define ESR_CM (1 << 8)
#define ESR_LNX_EXEC (1 << 24)
-/*
- * Check that the permissions on the VMA allow for the fault which occurred.
- * If we encountered a write fault, we must have write permission, otherwise
- * we allow any permission.
- */
-static inline bool access_error(unsigned int esr, struct vm_area_struct *vma)
-{
- unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
-
- if (esr & ESR_WRITE)
- mask = VM_WRITE;
- if (esr & ESR_LNX_EXEC)
- mask = VM_EXEC;
-
- return vma->vm_flags & mask ? false : true;
-}
-
static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
- unsigned int esr, unsigned int flags,
+ unsigned int mm_flags, unsigned long vm_flags,
struct task_struct *tsk)
{
struct vm_area_struct *vma;
@@ -188,12 +171,17 @@
* it.
*/
good_area:
- if (access_error(esr, vma)) {
+ /*
+ * Check that the permissions on the VMA allow for the fault which
+ * occurred. If we encountered a write or exec fault, we must have
+ * appropriate permissions, otherwise we allow any permission.
+ */
+ if (!(vma->vm_flags & vm_flags)) {
fault = VM_FAULT_BADACCESS;
goto out;
}
- return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
+ return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
check_stack:
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
@@ -208,9 +196,8 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- bool write = (esr & ESR_WRITE) && !(esr & ESR_CM);
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+ unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -226,6 +213,16 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ mm_flags |= FAULT_FLAG_USER;
+
+ if (esr & ESR_LNX_EXEC) {
+ vm_flags = VM_EXEC;
+ } else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
+ vm_flags = VM_WRITE;
+ mm_flags |= FAULT_FLAG_WRITE;
+ }
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -248,7 +245,7 @@
#endif
}
- fault = __do_page_fault(mm, addr, esr, flags, tsk);
+ fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
/*
* If we need to retry but a fatal signal is pending, handle the
@@ -265,7 +262,7 @@
*/
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
- if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
@@ -280,7 +277,7 @@
* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
* starvation.
*/
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
goto retry;
}
}
@@ -294,6 +291,13 @@
VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we have no context to
+ * handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -304,13 +308,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we have no context to
- * handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to successfully fix up
@@ -365,17 +362,6 @@
}
/*
- * Some section permission faults need to be handled gracefully. They can
- * happen due to a __{get,put}_user during an oops.
- */
-static int do_sect_fault(unsigned long addr, unsigned int esr,
- struct pt_regs *regs)
-{
- do_bad_area(addr, esr, regs);
- return 0;
-}
-
-/*
* This abort handler always returns "fault".
*/
static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
@@ -398,12 +384,12 @@
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
{ do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "reserved access flag fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
{ do_bad, SIGBUS, 0, "reserved permission fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
- { do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
+ { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
{ do_bad, SIGBUS, 0, "synchronous external abort" },
{ do_bad, SIGBUS, 0, "asynchronous external abort" },
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 88611c3..0d64089 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -70,23 +70,17 @@
#endif
}
-void __flush_dcache_page(struct page *page)
-{
- __flush_dcache_area(page_address(page), PAGE_SIZE);
-}
-
void __sync_icache_dcache(pte_t pte, unsigned long addr)
{
- unsigned long pfn;
- struct page *page;
+ struct page *page = pte_page(pte);
- pfn = pte_pfn(pte);
- if (!pfn_valid(pfn))
+ /* no flushing needed for anonymous pages */
+ if (!page_mapping(page))
return;
- page = pfn_to_page(pfn);
if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
- __flush_dcache_page(page);
+ __flush_dcache_area(page_address(page),
+ PAGE_SIZE << compound_order(page));
__flush_icache_all();
} else if (icache_is_aivivt()) {
__flush_icache_all();
@@ -94,28 +88,14 @@
}
/*
- * Ensure cache coherency between kernel mapping and userspace mapping of this
- * page.
+ * This function is called when a page has been modified by the kernel. Mark
+ * it as dirty for later flushing when mapped in user space (if executable,
+ * see __sync_icache_dcache).
*/
void flush_dcache_page(struct page *page)
{
- struct address_space *mapping;
-
- /*
- * The zero page is never written to, so never has any dirty cache
- * lines, and therefore never needs to be flushed.
- */
- if (page == ZERO_PAGE(0))
- return;
-
- mapping = page_mapping(page);
- if (mapping && mapping_mapped(mapping)) {
- __flush_dcache_page(page);
- __flush_icache_all();
- set_bit(PG_dcache_clean, &page->flags);
- } else {
+ if (test_bit(PG_dcache_clean, &page->flags))
clear_bit(PG_dcache_clean, &page->flags);
- }
}
EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
new file mode 100644
index 0000000..023747b
--- /dev/null
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -0,0 +1,74 @@
+/*
+ * arch/arm64/mm/hugetlbpage.c
+ *
+ * Copyright (C) 2013 Linaro Ltd.
+ *
+ * Based on arch/x86/mm/hugetlbpage.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
+#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+ return 0;
+}
+#endif
+
+struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
+ int write)
+{
+ return ERR_PTR(-EINVAL);
+}
+
+int pmd_huge(pmd_t pmd)
+{
+ return !(pmd_val(pmd) & PMD_TABLE_BIT);
+}
+
+int pud_huge(pud_t pud)
+{
+#ifndef __PAGETABLE_PMD_FOLDED
+ return !(pud_val(pud) & PUD_TABLE_BIT);
+#else
+ return 0;
+#endif
+}
+
+static __init int setup_hugepagesz(char *opt)
+{
+ unsigned long ps = memparse(opt, &opt);
+ if (ps == PMD_SIZE) {
+ hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+ } else if (ps == PUD_SIZE) {
+ hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+ } else {
+ pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20);
+ return 0;
+ }
+ return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index f497ca7..f2bded0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,8 @@
#include <linux/memblock.h>
#include <linux/sort.h>
#include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
#include <asm/prom.h>
#include <asm/sections.h>
@@ -44,8 +46,7 @@
phys_addr_t memstart_addr __read_mostly = 0;
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
phys_initrd_start = start;
phys_initrd_size = end - start;
@@ -67,22 +68,31 @@
}
early_param("initrd", early_initrd);
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+/*
+ * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
+ * currently assumes that for memory starting above 4G, 32-bit devices will
+ * use a DMA offset.
+ */
+static phys_addr_t max_zone_dma_phys(void)
+{
+ phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
+ return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+}
static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
struct memblock_region *reg;
unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
- unsigned long max_dma32 = min;
+ unsigned long max_dma = min;
memset(zone_size, 0, sizeof(zone_size));
-#ifdef CONFIG_ZONE_DMA32
/* 4GB maximum for 32-bit only capable devices */
- max_dma32 = max(min, min(max, MAX_DMA32_PFN));
- zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
- zone_size[ZONE_NORMAL] = max - max_dma32;
+ if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+ max_dma = PFN_DOWN(max_zone_dma_phys());
+ zone_size[ZONE_DMA] = max_dma - min;
+ }
+ zone_size[ZONE_NORMAL] = max - max_dma;
memcpy(zhole_size, zone_size, sizeof(zhole_size));
@@ -92,15 +102,15 @@
if (start >= max)
continue;
-#ifdef CONFIG_ZONE_DMA32
- if (start < max_dma32) {
- unsigned long dma_end = min(end, max_dma32);
- zhole_size[ZONE_DMA32] -= dma_end - start;
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+ unsigned long dma_end = min(end, max_dma);
+ zhole_size[ZONE_DMA] -= dma_end - start;
}
-#endif
- if (end > max_dma32) {
+
+ if (end > max_dma) {
unsigned long normal_end = min(end, max);
- unsigned long normal_start = max(start, max_dma32);
+ unsigned long normal_start = max(start, max_dma);
zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
}
}
@@ -131,11 +141,34 @@
}
#endif
+static phys_addr_t memory_limit = (phys_addr_t)ULLONG_MAX;
+
+/*
+ * Limit the memory size that was specified via FDT.
+ */
+static int __init early_mem(char *p)
+{
+ if (!p)
+ return 1;
+
+ memory_limit = memparse(p, &p) & PAGE_MASK;
+ pr_notice("Memory limited to %lldMB\n", memory_limit >> 20);
+
+ return 0;
+}
+early_param("mem", early_mem);
+
void __init arm64_memblock_init(void)
{
u64 *reserve_map, base, size;
+ phys_addr_t dma_phys_limit = 0;
- /* Register the kernel text, kernel data and initrd with memblock */
+ memblock_enforce_memory_limit(memory_limit);
+
+ /*
+ * Register the kernel text, kernel data, initrd, and initial
+ * pagetables with memblock.
+ */
memblock_reserve(__pa(_text), _end - _text);
#ifdef CONFIG_BLK_DEV_INITRD
if (phys_initrd_size) {
@@ -147,13 +180,6 @@
}
#endif
- /*
- * Reserve the page tables. These are already in use,
- * and can only be in node 0.
- */
- memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE);
- memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
-
/* Reserve the dtb region */
memblock_reserve(virt_to_phys(initial_boot_params),
be32_to_cpu(initial_boot_params->totalsize));
@@ -173,6 +199,13 @@
memblock_reserve(base, size);
}
+ early_init_fdt_scan_reserved_mem();
+
+ /* 4GB maximum for 32-bit only capable devices */
+ if (IS_ENABLED(CONFIG_ZONE_DMA))
+ dma_phys_limit = max_zone_dma_phys();
+ dma_contiguous_reserve(dma_phys_limit);
+
memblock_allow_resize();
memblock_dump_all();
}
@@ -283,8 +316,6 @@
unsigned long reserved_pages, free_pages;
struct memblock_region *reg;
- arm64_swiotlb_init();
-
max_mapnr = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
#ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 1725cd6..cf25fa9 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -25,6 +25,10 @@
#include <linux/vmalloc.h>
#include <linux/io.h>
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+
static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size,
pgprot_t prot, void *caller)
{
@@ -82,3 +86,105 @@
vunmap(addr);
}
EXPORT_SYMBOL(__iounmap);
+
+void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
+{
+ /* For normal memory we already have a cacheable mapping. */
+ if (pfn_valid(__phys_to_pfn(phys_addr)))
+ return (void __iomem *)__phys_to_virt(phys_addr);
+
+ return __ioremap_caller(phys_addr, size, __pgprot(PROT_NORMAL),
+ __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+#ifndef CONFIG_ARM64_64K_PAGES
+static pte_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss;
+#endif
+
+static inline pud_t * __init early_ioremap_pud(unsigned long addr)
+{
+ pgd_t *pgd;
+
+ pgd = pgd_offset_k(addr);
+ BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
+
+ return pud_offset(pgd, addr);
+}
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+ pud_t *pud = early_ioremap_pud(addr);
+
+ BUG_ON(pud_none(*pud) || pud_bad(*pud));
+
+ return pmd_offset(pud, addr);
+}
+
+static inline pte_t * __init early_ioremap_pte(unsigned long addr)
+{
+ pmd_t *pmd = early_ioremap_pmd(addr);
+
+ BUG_ON(pmd_none(*pmd) || pmd_bad(*pmd));
+
+ return pte_offset_kernel(pmd, addr);
+}
+
+void __init early_ioremap_init(void)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ unsigned long addr = fix_to_virt(FIX_BTMAP_BEGIN);
+
+ pgd = pgd_offset_k(addr);
+ pud = pud_offset(pgd, addr);
+ pud_populate(&init_mm, pud, bm_pmd);
+ pmd = pmd_offset(pud, addr);
+ pmd_populate_kernel(&init_mm, pmd, bm_pte);
+
+ /*
+ * The boot-ioremap range spans multiple pmds, for which
+ * we are not prepared:
+ */
+ BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+ != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+
+ if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+ WARN_ON(1);
+ pr_warn("pmd %p != %p\n",
+ pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
+ pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+ fix_to_virt(FIX_BTMAP_BEGIN));
+ pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n",
+ fix_to_virt(FIX_BTMAP_END));
+
+ pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END);
+ pr_warn("FIX_BTMAP_BEGIN: %d\n",
+ FIX_BTMAP_BEGIN);
+ }
+
+ early_ioremap_setup();
+}
+
+void __init __early_set_fixmap(enum fixed_addresses idx,
+ phys_addr_t phys, pgprot_t flags)
+{
+ unsigned long addr = __fix_to_virt(idx);
+ pte_t *pte;
+
+ if (idx >= __end_of_fixed_addresses) {
+ BUG();
+ return;
+ }
+
+ pte = early_ioremap_pte(addr);
+
+ if (pgprot_val(flags))
+ set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+ else {
+ pte_clear(&init_mm, addr, pte);
+ flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
+ }
+}
diff --git a/arch/arm64/mm/mm.h b/arch/arm64/mm/mm.h
index 916701e..d519f4f 100644
--- a/arch/arm64/mm/mm.h
+++ b/arch/arm64/mm/mm.h
@@ -1,3 +1,2 @@
-extern void __flush_dcache_page(struct page *page);
extern void __init bootmem_init(void);
extern void __init arm64_swiotlb_init(void);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index eeecc9c..a2155ca 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -43,11 +43,6 @@
struct page *empty_zero_page;
EXPORT_SYMBOL(empty_zero_page);
-pgprot_t pgprot_default;
-EXPORT_SYMBOL(pgprot_default);
-
-static pmdval_t prot_sect_kernel;
-
struct cachepolicy {
const char policy[16];
u64 mair;
@@ -122,33 +117,6 @@
}
early_param("cachepolicy", early_cachepolicy);
-/*
- * Adjust the PMD section entries according to the CPU in use.
- */
-static void __init init_mem_pgprot(void)
-{
- pteval_t default_pgprot;
- int i;
-
- default_pgprot = PTE_ATTRINDX(MT_NORMAL);
- prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL);
-
-#ifdef CONFIG_SMP
- /*
- * Mark memory with the "shared" attribute for SMP systems
- */
- default_pgprot |= PTE_SHARED;
- prot_sect_kernel |= PMD_SECT_S;
-#endif
-
- for (i = 0; i < 16; i++) {
- unsigned long v = pgprot_val(protection_map[i]);
- protection_map[i] = __pgprot(v | default_pgprot);
- }
-
- pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot);
-}
-
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
@@ -168,7 +136,8 @@
}
static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
- unsigned long end, unsigned long pfn)
+ unsigned long end, unsigned long pfn,
+ pgprot_t prot)
{
pte_t *pte;
@@ -180,16 +149,28 @@
pte = pte_offset_kernel(pmd, addr);
do {
- set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+ set_pte(pte, pfn_pte(pfn, prot));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
}
static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys)
+ unsigned long end, phys_addr_t phys,
+ int map_io)
{
pmd_t *pmd;
unsigned long next;
+ pmdval_t prot_sect;
+ pgprot_t prot_pte;
+
+ if (map_io) {
+ prot_sect = PMD_TYPE_SECT | PMD_SECT_AF |
+ PMD_ATTRINDX(MT_DEVICE_nGnRE);
+ prot_pte = __pgprot(PROT_DEVICE_nGnRE);
+ } else {
+ prot_sect = PROT_SECT_NORMAL_EXEC;
+ prot_pte = PAGE_KERNEL_EXEC;
+ }
/*
* Check for initial section mappings in the pgd/pud and remove them.
@@ -203,23 +184,33 @@
do {
next = pmd_addr_end(addr, end);
/* try section mapping first */
- if (((addr | next | phys) & ~SECTION_MASK) == 0)
- set_pmd(pmd, __pmd(phys | prot_sect_kernel));
- else
- alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));
+ if (((addr | next | phys) & ~SECTION_MASK) == 0) {
+ pmd_t old_pmd =*pmd;
+ set_pmd(pmd, __pmd(phys | prot_sect));
+ /*
+ * Check for previous table entries created during
+ * boot (__create_page_tables) and flush them.
+ */
+ if (!pmd_none(old_pmd))
+ flush_tlb_all();
+ } else {
+ alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+ prot_pte);
+ }
phys += next - addr;
} while (pmd++, addr = next, addr != end);
}
static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
- unsigned long end, unsigned long phys)
+ unsigned long end, unsigned long phys,
+ int map_io)
{
pud_t *pud = pud_offset(pgd, addr);
unsigned long next;
do {
next = pud_addr_end(addr, end);
- alloc_init_pmd(pud, addr, next, phys);
+ alloc_init_pmd(pud, addr, next, phys, map_io);
phys += next - addr;
} while (pud++, addr = next, addr != end);
}
@@ -228,74 +219,60 @@
* Create the page directory entries and any necessary page tables for the
* mapping specified by 'md'.
*/
-static void __init create_mapping(phys_addr_t phys, unsigned long virt,
- phys_addr_t size)
+static void __init __create_mapping(pgd_t *pgd, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ int map_io)
{
unsigned long addr, length, end, next;
- pgd_t *pgd;
-
- if (virt < VMALLOC_START) {
- pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n",
- phys, virt);
- return;
- }
addr = virt & PAGE_MASK;
length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));
- pgd = pgd_offset_k(addr);
end = addr + length;
do {
next = pgd_addr_end(addr, end);
- alloc_init_pud(pgd, addr, next, phys);
+ alloc_init_pud(pgd, addr, next, phys, map_io);
phys += next - addr;
} while (pgd++, addr = next, addr != end);
}
-#ifdef CONFIG_EARLY_PRINTK
-/*
- * Create an early I/O mapping using the pgd/pmd entries already populated
- * in head.S as this function is called too early to allocated any memory. The
- * mapping size is 2MB with 4KB pages or 64KB or 64KB pages.
- */
-void __iomem * __init early_io_map(phys_addr_t phys, unsigned long virt)
+static void __init create_mapping(phys_addr_t phys, unsigned long virt,
+ phys_addr_t size)
{
- unsigned long size, mask;
- bool page64k = IS_ENABLED(CONFIG_ARM64_64K_PAGES);
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- /*
- * No early pte entries with !ARM64_64K_PAGES configuration, so using
- * sections (pmd).
- */
- size = page64k ? PAGE_SIZE : SECTION_SIZE;
- mask = ~(size - 1);
-
- pgd = pgd_offset_k(virt);
- pud = pud_offset(pgd, virt);
- if (pud_none(*pud))
- return NULL;
- pmd = pmd_offset(pud, virt);
-
- if (page64k) {
- if (pmd_none(*pmd))
- return NULL;
- pte = pte_offset_kernel(pmd, virt);
- set_pte(pte, __pte((phys & mask) | PROT_DEVICE_nGnRE));
- } else {
- set_pmd(pmd, __pmd((phys & mask) | PROT_SECT_DEVICE_nGnRE));
+ if (virt < VMALLOC_START) {
+ pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+ &phys, virt);
+ return;
}
-
- return (void __iomem *)((virt & mask) + (phys & ~mask));
+ __create_mapping(pgd_offset_k(virt & PAGE_MASK), phys, virt, size, 0);
}
-#endif
+
+void __init create_id_mapping(phys_addr_t addr, phys_addr_t size, int map_io)
+{
+ if ((addr >> PGDIR_SHIFT) >= ARRAY_SIZE(idmap_pg_dir)) {
+ pr_warn("BUG: not creating id mapping for %pa\n", &addr);
+ return;
+ }
+ __create_mapping(&idmap_pg_dir[pgd_index(addr)],
+ addr, addr, size, map_io);
+}
static void __init map_mem(void)
{
struct memblock_region *reg;
+ phys_addr_t limit;
+
+ /*
+ * Temporarily limit the memblock range. We need to do this as
+ * create_mapping requires puds, pmds and ptes to be allocated from
+ * memory addressable from the initial direct kernel mapping.
+ *
+ * The initial direct kernel mapping, located at swapper_pg_dir,
+ * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (which must be
+ * aligned to 2MB as per Documentation/arm64/booting.txt).
+ */
+ limit = PHYS_OFFSET + PGDIR_SIZE;
+ memblock_set_current_limit(limit);
/* map all the memory banks */
for_each_memblock(memory, reg) {
@@ -305,8 +282,27 @@
if (start >= end)
break;
+#ifndef CONFIG_ARM64_64K_PAGES
+ /*
+ * For the first memory bank align the start address and
+ * current memblock limit to prevent create_mapping() from
+ * allocating pte page tables from unmapped memory.
+ * When 64K pages are enabled, the pte page table for the
+ * first PGDIR_SIZE is already present in swapper_pg_dir.
+ */
+ if (start < limit)
+ start = ALIGN(start, PMD_SIZE);
+ if (end < limit) {
+ limit = end & PMD_MASK;
+ memblock_set_current_limit(limit);
+ }
+#endif
+
create_mapping(start, __phys_to_virt(start), end - start);
}
+
+ /* Limit no longer required. */
+ memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
}
/*
@@ -317,13 +313,6 @@
{
void *zero_page;
- /*
- * Maximum PGDIR_SIZE addressable via the initial direct kernel
- * mapping in swapper_pg_dir.
- */
- memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);
-
- init_mem_pgprot();
map_mem();
/*
@@ -339,7 +328,6 @@
bootmem_init();
empty_zero_page = virt_to_page(zero_page);
- __flush_dcache_page(empty_zero_page);
/*
* TTBR0 is only used for the identity mapping at this stage. Make it
@@ -383,6 +371,9 @@
if (pmd_none(*pmd))
return 0;
+ if (pmd_sect(*pmd))
+ return pfn_valid(pmd_pfn(*pmd));
+
pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte))
return 0;
@@ -423,7 +414,7 @@
if (!p)
return -ENOMEM;
- set_pmd(pmd, __pmd(__pa(p) | prot_sect_kernel));
+ set_pmd(pmd, __pmd(__pa(p) | PROT_SECT_NORMAL));
} else
vmemmap_verify((pte_t *)pmd, node, addr, next);
} while (addr = next, addr != end);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
new file mode 100644
index 0000000..75e744e
--- /dev/null
+++ b/arch/arm64/mm/pageattr.c
@@ -0,0 +1,96 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+struct page_change_data {
+ pgprot_t set_mask;
+ pgprot_t clear_mask;
+};
+
+static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
+ void *data)
+{
+ struct page_change_data *cdata = data;
+ pte_t pte = *ptep;
+
+ pte = clear_pte_bit(pte, cdata->clear_mask);
+ pte = set_pte_bit(pte, cdata->set_mask);
+
+ set_pte(ptep, pte);
+ return 0;
+}
+
+static int change_memory_common(unsigned long addr, int numpages,
+ pgprot_t set_mask, pgprot_t clear_mask)
+{
+ unsigned long start = addr;
+ unsigned long size = PAGE_SIZE*numpages;
+ unsigned long end = start + size;
+ int ret;
+ struct page_change_data data;
+
+ if (!IS_ALIGNED(addr, PAGE_SIZE)) {
+ addr &= PAGE_MASK;
+ WARN_ON_ONCE(1);
+ }
+
+ if (!is_module_address(start) || !is_module_address(end - 1))
+ return -EINVAL;
+
+ data.set_mask = set_mask;
+ data.clear_mask = clear_mask;
+
+ ret = apply_to_page_range(&init_mm, start, size, change_page_range,
+ &data);
+
+ flush_tlb_kernel_range(start, end);
+ return ret;
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_RDONLY),
+ __pgprot(PTE_WRITE));
+}
+EXPORT_SYMBOL_GPL(set_memory_ro);
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_WRITE),
+ __pgprot(PTE_RDONLY));
+}
+EXPORT_SYMBOL_GPL(set_memory_rw);
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(PTE_PXN),
+ __pgprot(0));
+}
+EXPORT_SYMBOL_GPL(set_memory_nx);
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+ return change_memory_common(addr, numpages,
+ __pgprot(0),
+ __pgprot(PTE_PXN));
+}
+EXPORT_SYMBOL_GPL(set_memory_x);
diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c
index 7083cda..62c6101 100644
--- a/arch/arm64/mm/pgd.c
+++ b/arch/arm64/mm/pgd.c
@@ -32,17 +32,10 @@
pgd_t *pgd_alloc(struct mm_struct *mm)
{
- pgd_t *new_pgd;
-
if (PGD_SIZE == PAGE_SIZE)
- new_pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+ return (pgd_t *)get_zeroed_page(GFP_KERNEL);
else
- new_pgd = kzalloc(PGD_SIZE, GFP_KERNEL);
-
- if (!new_pgd)
- return NULL;
-
- return new_pgd;
+ return kzalloc(PGD_SIZE, GFP_KERNEL);
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
index 8957b82..005d29e 100644
--- a/arch/arm64/mm/proc-macros.S
+++ b/arch/arm64/mm/proc-macros.S
@@ -38,8 +38,7 @@
*/
.macro dcache_line_size, reg, tmp
mrs \tmp, ctr_el0 // read CTR
- lsr \tmp, \tmp, #16
- and \tmp, \tmp, #0xf // cache line size encoding
+ ubfm \tmp, \tmp, #16, #19 // cache line size encoding
mov \reg, #4 // bytes per word
lsl \reg, \reg, \tmp // actual cache line size
.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index f84fcf7..c133ae5 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -69,6 +69,21 @@
ret x0
ENDPROC(cpu_reset)
+ENTRY(cpu_soft_restart)
+ /* Save address of cpu_reset() and reset address */
+ mov x19, x0
+ mov x20, x1
+
+ /* Turn D-cache off */
+ bl cpu_cache_off
+
+ /* Push out all dirty data, and ensure cache is empty */
+ bl flush_cache_all
+
+ mov x0, x20
+ ret x19
+ENDPROC(cpu_soft_restart)
+
/*
* cpu_do_idle()
*
@@ -80,8 +95,77 @@
ret
ENDPROC(cpu_do_idle)
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+/**
+ * cpu_do_suspend - save CPU registers context
+ *
+ * x0: virtual address of context pointer
+ */
+ENTRY(cpu_do_suspend)
+ mrs x2, tpidr_el0
+ mrs x3, tpidrro_el0
+ mrs x4, contextidr_el1
+ mrs x5, mair_el1
+ mrs x6, cpacr_el1
+ mrs x7, ttbr1_el1
+ mrs x8, tcr_el1
+ mrs x9, vbar_el1
+ mrs x10, mdscr_el1
+ mrs x11, oslsr_el1
+ mrs x12, sctlr_el1
+ stp x2, x3, [x0]
+ stp x4, x5, [x0, #16]
+ stp x6, x7, [x0, #32]
+ stp x8, x9, [x0, #48]
+ stp x10, x11, [x0, #64]
+ str x12, [x0, #80]
+ ret
+ENDPROC(cpu_do_suspend)
+
+/**
+ * cpu_do_resume - restore CPU register context
+ *
+ * x0: Physical address of context pointer
+ * x1: ttbr0_el1 to be restored
+ *
+ * Returns:
+ * sctlr_el1 value in x0
+ */
+ENTRY(cpu_do_resume)
+ /*
+ * Invalidate local tlb entries before turning on MMU
+ */
+ tlbi vmalle1
+ ldp x2, x3, [x0]
+ ldp x4, x5, [x0, #16]
+ ldp x6, x7, [x0, #32]
+ ldp x8, x9, [x0, #48]
+ ldp x10, x11, [x0, #64]
+ ldr x12, [x0, #80]
+ msr tpidr_el0, x2
+ msr tpidrro_el0, x3
+ msr contextidr_el1, x4
+ msr mair_el1, x5
+ msr cpacr_el1, x6
+ msr ttbr0_el1, x1
+ msr ttbr1_el1, x7
+ msr tcr_el1, x8
+ msr vbar_el1, x9
+ msr mdscr_el1, x10
+ /*
+ * Restore oslsr_el1 by writing oslar_el1
+ */
+ ubfx x11, x11, #1, #1
+ msr oslar_el1, x11
+ mov x0, x12
+ dsb nsh // Make sure local tlb invalidation completed
+ isb
+ ret
+ENDPROC(cpu_do_resume)
+#endif
+
/*
- * cpu_switch_mm(pgd_phys, tsk)
+ * cpu_do_switch_mm(pgd_phys, tsk)
*
* Set the translation table base pointer to be pgd_phys.
*
@@ -104,19 +188,13 @@
* value of the SCTLR_EL1 register.
*/
ENTRY(__cpu_setup)
- /*
- * Preserve the link register across the function call.
- */
- mov x28, lr
- bl __flush_dcache_all
- mov lr, x28
ic iallu // I+BTB cache invalidate
- dsb sy
+ tlbi vmalle1is // invalidate I + D TLBs
+ dsb ish
mov x0, #3 << 20
msr cpacr_el1, x0 // Enable FP/ASIMD
msr mdscr_el1, xzr // Reset mdscr_el1
- tlbi vmalle1is // invalidate I + D TLBs
/*
* Memory region attributes for LPAE:
*
@@ -146,8 +224,14 @@
* Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
* both user and kernel.
*/
- ldr x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
- TCR_ASID16 | (1 << 31)
+ ldr x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | \
+ TCR_ASID16 | TCR_TBI0 | (1 << 31)
+ /*
+ * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
+ * TCR_EL1.
+ */
+ mrs x9, ID_AA64MMFR0_EL1
+ bfi x10, x9, #32, #3
#ifdef CONFIG_ARM64_64K_PAGES
orr x10, x10, TCR_TG0_64K
orr x10, x10, TCR_TG1_64K
@@ -162,9 +246,9 @@
* CE0 XWHW CZ ME TEEA S
* .... .IEE .... NEAI TE.I ..AD DEN0 ACAM
* 0011 0... 1101 ..0. ..0. 10.. .... .... < hardware reserved
- * .... .100 .... 01.1 11.1 ..01 0001 1101 < software settings
+ * .... .1.. .... 01.1 11.1 ..01 0001 1101 < software settings
*/
.type crval, #object
crval:
- .word 0x030802e2 // clear
+ .word 0x000802e2 // clear
.word 0x0405d11d // set
diff --git a/arch/arm64/mm/tlb.S b/arch/arm64/mm/tlb.S
deleted file mode 100644
index 8ae80a1..0000000
--- a/arch/arm64/mm/tlb.S
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Based on arch/arm/mm/tlb.S
- *
- * Copyright (C) 1997-2002 Russell King
- * Copyright (C) 2012 ARM Ltd.
- * Written by Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-#include "proc-macros.S"
-
-/*
- * __cpu_flush_user_tlb_range(start, end, vma)
- *
- * Invalidate a range of TLB entries in the specified address space.
- *
- * - start - start address (may not be aligned)
- * - end - end address (exclusive, may not be aligned)
- * - vma - vma_struct describing address range
- */
-ENTRY(__cpu_flush_user_tlb_range)
- vma_vm_mm x3, x2 // get vma->vm_mm
- mmid x3, x3 // get vm_mm->context.id
- dsb sy
- lsr x0, x0, #12 // align address
- lsr x1, x1, #12
- bfi x0, x3, #48, #16 // start VA and ASID
- bfi x1, x3, #48, #16 // end VA and ASID
-1: tlbi vae1is, x0 // TLB invalidate by address and ASID
- add x0, x0, #1
- cmp x0, x1
- b.lo 1b
- dsb sy
- ret
-ENDPROC(__cpu_flush_user_tlb_range)
-
-/*
- * __cpu_flush_kern_tlb_range(start,end)
- *
- * Invalidate a range of kernel TLB entries.
- *
- * - start - start address (may not be aligned)
- * - end - end address (exclusive, may not be aligned)
- */
-ENTRY(__cpu_flush_kern_tlb_range)
- dsb sy
- lsr x0, x0, #12 // align address
- lsr x1, x1, #12
-1: tlbi vaae1is, x0 // TLB invalidate by address
- add x0, x0, #1
- cmp x0, x1
- b.lo 1b
- dsb sy
- isb
- ret
-ENDPROC(__cpu_flush_kern_tlb_range)
diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile
index 22fb665..dba48a5d 100644
--- a/arch/avr32/Makefile
+++ b/arch/avr32/Makefile
@@ -11,7 +11,7 @@
KBUILD_DEFCONFIG := atstk1002_defconfig
-KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic
+KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic -D__linux__
KBUILD_AFLAGS += -mrelax -mno-pic
KBUILD_CFLAGS_MODULE += -mno-relax
LDFLAGS_vmlinux += --relax
diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c
index 9764a1a..c1466a8 100644
--- a/arch/avr32/boards/mimc200/fram.c
+++ b/arch/avr32/boards/mimc200/fram.c
@@ -11,6 +11,7 @@
#define FRAM_VERSION "1.0"
#include <linux/miscdevice.h>
+#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/mm.h>
#include <linux/io.h>
diff --git a/arch/avr32/boot/u-boot/head.S b/arch/avr32/boot/u-boot/head.S
index 4488fa2..2ffc298 100644
--- a/arch/avr32/boot/u-boot/head.S
+++ b/arch/avr32/boot/u-boot/head.S
@@ -8,6 +8,8 @@
* published by the Free Software Foundation.
*/
#include <asm/setup.h>
+#include <asm/thread_info.h>
+#include <asm/sysreg.h>
/*
* The kernel is loaded where we want it to be and all caches
@@ -20,11 +22,6 @@
.section .init.text,"ax"
.global _start
_start:
- /* Check if the boot loader actually provided a tag table */
- lddpc r0, magic_number
- cp.w r12, r0
- brne no_tag_table
-
/* Initialize .bss */
lddpc r2, bss_start_addr
lddpc r3, end_addr
@@ -34,6 +31,25 @@
cp r2, r3
brlo 1b
+ /* Initialize status register */
+ lddpc r0, init_sr
+ mtsr SYSREG_SR, r0
+
+ /* Set initial stack pointer */
+ lddpc sp, stack_addr
+ sub sp, -THREAD_SIZE
+
+#ifdef CONFIG_FRAME_POINTER
+ /* Mark last stack frame */
+ mov lr, 0
+ mov r7, 0
+#endif
+
+ /* Check if the boot loader actually provided a tag table */
+ lddpc r0, magic_number
+ cp.w r12, r0
+ brne no_tag_table
+
/*
* Save the tag table address for later use. This must be done
* _after_ .bss has been initialized...
@@ -53,8 +69,15 @@
.long __bss_start
end_addr:
.long _end
+init_sr:
+ .long 0x007f0000 /* Supervisor mode, everything masked */
+stack_addr:
+ .long init_thread_union
+panic_addr:
+ .long panic
no_tag_table:
sub r12, pc, (. - 2f)
- bral panic
+ /* branch to panic() which can be far away with that construct */
+ lddpc pc, panic_addr
2: .asciz "Boot loader didn't provide correct magic number\n"
diff --git a/arch/avr32/kernel/entry-avr32b.S b/arch/avr32/kernel/entry-avr32b.S
index 9899d3c..7301f48 100644
--- a/arch/avr32/kernel/entry-avr32b.S
+++ b/arch/avr32/kernel/entry-avr32b.S
@@ -401,9 +401,10 @@
/* We should never get here... */
bad_return:
sub r12, pc, (. - 1f)
- bral panic
+ lddpc pc, 2f
.align 2
1: .asciz "Return from critical exception!"
+2: .long panic
.align 1
do_bus_error_write:
diff --git a/arch/avr32/kernel/head.S b/arch/avr32/kernel/head.S
index 6163bd0..59eae6d 100644
--- a/arch/avr32/kernel/head.S
+++ b/arch/avr32/kernel/head.S
@@ -10,33 +10,13 @@
#include <linux/linkage.h>
#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/sysreg.h>
.section .init.text,"ax"
.global kernel_entry
kernel_entry:
- /* Initialize status register */
- lddpc r0, init_sr
- mtsr SYSREG_SR, r0
-
- /* Set initial stack pointer */
- lddpc sp, stack_addr
- sub sp, -THREAD_SIZE
-
-#ifdef CONFIG_FRAME_POINTER
- /* Mark last stack frame */
- mov lr, 0
- mov r7, 0
-#endif
-
/* Start the show */
lddpc pc, kernel_start_addr
.align 2
-init_sr:
- .long 0x007f0000 /* Supervisor mode, everything masked */
-stack_addr:
- .long init_thread_union
kernel_start_addr:
.long start_kernel
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index 869a1c6..12f828a 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -98,7 +98,14 @@
case CLOCK_EVT_MODE_SHUTDOWN:
sysreg_write(COMPARE, 0);
pr_debug("%s: stop\n", evdev->name);
- cpu_idle_poll_ctrl(false);
+ if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
+ evdev->mode == CLOCK_EVT_MODE_RESUME) {
+ /*
+ * Only disable idle poll if we have forced that
+ * in a previous call.
+ */
+ cpu_idle_poll_ctrl(false);
+ }
break;
default:
BUG();
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index b2f2d2d..d223a8b 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -86,6 +86,8 @@
local_irq_enable();
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -140,6 +142,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -228,9 +232,9 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- pagefault_out_of_memory();
if (!user_mode(regs))
goto no_context;
+ pagefault_out_of_memory();
return;
do_sigbus:
diff --git a/arch/blackfin/include/asm/ftrace.h b/arch/blackfin/include/asm/ftrace.h
index 8a02950..2f1c3c2 100644
--- a/arch/blackfin/include/asm/ftrace.h
+++ b/arch/blackfin/include/asm/ftrace.h
@@ -66,16 +66,7 @@
#endif /* CONFIG_FRAME_POINTER */
-#define HAVE_ARCH_CALLER_ADDR
-
-/* inline function or macro may lead to unexpected result */
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
#endif /* __ASSEMBLY__ */
diff --git a/arch/c6x/kernel/devicetree.c b/arch/c6x/kernel/devicetree.c
index bdb56f0..287d0e6 100644
--- a/arch/c6x/kernel/devicetree.c
+++ b/arch/c6x/kernel/devicetree.c
@@ -33,8 +33,7 @@
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/c6x/kernel/time.c b/arch/c6x/kernel/time.c
index 356ee84..04845aa 100644
--- a/arch/c6x/kernel/time.c
+++ b/arch/c6x/kernel/time.c
@@ -49,7 +49,7 @@
return (tsc * sched_clock_multiplier) >> SCHED_CLOCK_SHIFT;
}
-void time_init(void)
+void __init time_init(void)
{
u64 tmp = (u64)NSEC_PER_SEC << SCHED_CLOCK_SHIFT;
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index a9fcd89..b74ccb5 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -18,6 +18,7 @@
#include <linux/initrd.h>
#include <asm/sections.h>
+#include <asm/uaccess.h>
/*
* ZERO_PAGE is a special page that is used for zero-initialized
diff --git a/arch/cris/include/asm/io.h b/arch/cris/include/asm/io.h
index ac12ae2..db9a16c 100644
--- a/arch/cris/include/asm/io.h
+++ b/arch/cris/include/asm/io.h
@@ -3,6 +3,7 @@
#include <asm/page.h> /* for __va, __pa */
#include <arch/io.h>
+#include <asm-generic/iomap.h>
#include <linux/kernel.h>
struct cris_io_operations
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 73312ab..2686a7a 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -58,8 +58,7 @@
struct vm_area_struct * vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((writeaccess & 1) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
D(printk(KERN_DEBUG
"Page fault for %lX on %X at %lX, prot %d write %d\n",
@@ -117,6 +116,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -155,6 +156,7 @@
} else if (writeaccess == 1) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
@@ -174,6 +176,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 331c1e2..ec4917d 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -34,11 +34,11 @@
struct vm_area_struct *vma;
struct mm_struct *mm;
unsigned long _pme, lrai, lrad, fixup;
+ unsigned long flags = 0;
siginfo_t info;
pgd_t *pge;
pud_t *pue;
pte_t *pte;
- int write;
int fault;
#if 0
@@ -81,6 +81,9 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(__frame))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, ear0);
@@ -129,7 +132,6 @@
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (esr0 & ESR0_ATXC) {
default:
/* handle write to write protected page */
@@ -140,7 +142,7 @@
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write = 1;
+ flags |= FAULT_FLAG_WRITE;
break;
/* handle read from protected page */
@@ -162,10 +164,12 @@
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, ear0, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, ear0, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c
index 1bd276d..8704c93 100644
--- a/arch/hexagon/mm/vm_fault.c
+++ b/arch/hexagon/mm/vm_fault.c
@@ -53,8 +53,7 @@
int si_code = SEGV_MAPERR;
int fault;
const struct exception_table_entry *fixup;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (cause > 0 ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
/*
* If we're in an interrupt or have no user context,
@@ -65,6 +64,8 @@
local_irq_enable();
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -96,6 +97,7 @@
case FLT_STORE:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
break;
}
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index 989dd3f..cf03097 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -238,9 +238,6 @@
#define KVM_NR_PAGE_SIZES 1
#define KVM_PAGES_PER_HPAGE(x) 1
-struct kvm;
-struct kvm_vcpu;
-
struct kvm_mmio_req {
uint64_t addr; /* physical address */
uint64_t size; /* size in bytes */
@@ -599,6 +596,18 @@
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_commit_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ enum kvm_mr_change change) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+
#endif /* __ASSEMBLY__*/
#endif
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index e0a899a..5a84b3a 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -319,7 +319,7 @@
regs->loadrs = 0; \
regs->r8 = get_dumpable(current->mm); /* set "don't zap registers" flag */ \
regs->r12 = new_sp - 16; /* allocate 16 byte scratch area */ \
- if (unlikely(!get_dumpable(current->mm))) { \
+ if (unlikely(get_dumpable(current->mm) != SUID_DUMP_USER)) { \
/* \
* Zap scratch regs to avoid leaking bits between processes with different \
* uid/privileges. \
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de..bc5efc7 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
* unmapping a portion of the virtual address space, these hooks are called according to
* the following template:
*
- * tlb <- tlb_gather_mmu(mm, full_mm_flush); // start unmap for address space MM
+ * tlb <- tlb_gather_mmu(mm, start, end); // start unmap for address space MM
* {
* for each vma that needs a shootdown do {
* tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@
unsigned int max;
unsigned char fullmm; /* non-zero means full mm flush */
unsigned char need_flush; /* really unmapped some PTEs? */
+ unsigned long start, end;
unsigned long start_addr;
unsigned long end_addr;
struct page **pages;
@@ -155,13 +156,15 @@
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
tlb->max = ARRAY_SIZE(tlb->local);
tlb->pages = tlb->local;
tlb->nr = 0;
- tlb->fullmm = full_mm_flush;
+ tlb->fullmm = !(start | (end+1));
+ tlb->start = start;
+ tlb->end = end;
tlb->start_addr = ~0UL;
}
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index f034563..ff09680 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -44,10 +44,15 @@
#define EFI_DEBUG 0
+static __initdata unsigned long palo_phys;
+
+static __initdata efi_config_table_type_t arch_tables[] = {
+ {PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID, "PALO", &palo_phys},
+ {NULL_GUID, NULL, 0},
+};
+
extern efi_status_t efi_call_phys (void *, ...);
-struct efi efi;
-EXPORT_SYMBOL(efi);
static efi_runtime_services_t *runtime;
static u64 mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL;
@@ -423,9 +428,9 @@
* Parse and handle PALO table which is published at:
* http://www.dig64.org/home/DIG64_PALO_R1_0.pdf
*/
-static void __init handle_palo(unsigned long palo_phys)
+static void __init handle_palo(unsigned long phys_addr)
{
- struct palo_table *palo = __va(palo_phys);
+ struct palo_table *palo = __va(phys_addr);
u8 checksum;
if (strncmp(palo->signature, PALO_SIG, sizeof(PALO_SIG) - 1)) {
@@ -467,12 +472,13 @@
efi_init (void)
{
void *efi_map_start, *efi_map_end;
- efi_config_table_t *config_tables;
efi_char16_t *c16;
u64 efi_desc_size;
char *cp, vendor[100] = "unknown";
int i;
- unsigned long palo_phys;
+
+ set_bit(EFI_BOOT, &efi.flags);
+ set_bit(EFI_64BIT, &efi.flags);
/*
* It's too early to be able to use the standard kernel command line
@@ -514,8 +520,6 @@
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff);
- config_tables = __va(efi.systab->tables);
-
/* Show what we know for posterity */
c16 = __va(efi.systab->fw_vendor);
if (c16) {
@@ -528,43 +532,12 @@
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff, vendor);
- efi.mps = EFI_INVALID_TABLE_ADDR;
- efi.acpi = EFI_INVALID_TABLE_ADDR;
- efi.acpi20 = EFI_INVALID_TABLE_ADDR;
- efi.smbios = EFI_INVALID_TABLE_ADDR;
- efi.sal_systab = EFI_INVALID_TABLE_ADDR;
- efi.boot_info = EFI_INVALID_TABLE_ADDR;
- efi.hcdp = EFI_INVALID_TABLE_ADDR;
- efi.uga = EFI_INVALID_TABLE_ADDR;
+ set_bit(EFI_SYSTEM_TABLES, &efi.flags);
palo_phys = EFI_INVALID_TABLE_ADDR;
- for (i = 0; i < (int) efi.systab->nr_tables; i++) {
- if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
- efi.mps = config_tables[i].table;
- printk(" MPS=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) {
- efi.acpi20 = config_tables[i].table;
- printk(" ACPI 2.0=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) {
- efi.acpi = config_tables[i].table;
- printk(" ACPI=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) {
- efi.smbios = config_tables[i].table;
- printk(" SMBIOS=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid, SAL_SYSTEM_TABLE_GUID) == 0) {
- efi.sal_systab = config_tables[i].table;
- printk(" SALsystab=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
- efi.hcdp = config_tables[i].table;
- printk(" HCDP=0x%lx", config_tables[i].table);
- } else if (efi_guidcmp(config_tables[i].guid,
- PROCESSOR_ABSTRACTION_LAYER_OVERWRITE_GUID) == 0) {
- palo_phys = config_tables[i].table;
- printk(" PALO=0x%lx", config_tables[i].table);
- }
- }
- printk("\n");
+ if (efi_config_init(arch_tables) != 0)
+ return;
if (palo_phys != EFI_INVALID_TABLE_ADDR)
handle_palo(palo_phys);
@@ -689,6 +662,8 @@
return;
}
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
/*
* Now that EFI is in virtual mode, we call the EFI functions more
* efficiently:
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index 990b864..3d50ea9 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -25,6 +25,7 @@
select PREEMPT_NOTIFIERS
select ANON_INODES
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select KVM_APIC_ARCHITECTURE
select KVM_MMIO
diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile
index 1a40537..18e45ec 100644
--- a/arch/ia64/kvm/Makefile
+++ b/arch/ia64/kvm/Makefile
@@ -47,12 +47,13 @@
ccflags-y := -Ivirt/kvm -Iarch/ia64/kvm/
asflags-y := -Ivirt/kvm -Iarch/ia64/kvm/
+KVM := ../../../virt/kvm
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
- coalesced_mmio.o irq_comm.o)
+common-objs = $(KVM)/kvm_main.o $(KVM)/ioapic.o \
+ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o
ifeq ($(CONFIG_KVM_DEVICE_ASSIGNMENT),y)
-common-objs += $(addprefix ../../../virt/kvm/, assigned-dev.o iommu.o)
+common-objs += $(KVM)/assigned-dev.o $(KVM)/iommu.o
endif
kvm-objs := $(common-objs) kvm-ia64.o kvm_fw.o
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 5b2dc0d..c9aa236 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -125,7 +125,7 @@
static DEFINE_SPINLOCK(vp_lock);
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
long status;
long tmp_base;
@@ -160,7 +160,7 @@
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
long status;
@@ -190,7 +190,7 @@
*(int *)rtn = 0;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -702,7 +702,7 @@
out:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
if (r > 0) {
- kvm_resched(vcpu);
+ cond_resched();
idx = srcu_read_lock(&vcpu->kvm->srcu);
goto again;
}
@@ -1363,10 +1363,6 @@
}
}
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_iommu_unmap_guest(kvm);
@@ -1375,10 +1371,6 @@
kvm_release_vm_pages(kvm);
}
-void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
-{
-}
-
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
if (cpu != vcpu->cpu) {
@@ -1467,7 +1459,6 @@
kfree(vcpu->arch.apic);
}
-
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -1550,12 +1541,8 @@
return VM_FAULT_SIGBUS;
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
- struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
return 0;
}
@@ -1591,14 +1578,6 @@
return 0;
}
-void kvm_arch_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- const struct kvm_memory_slot *old,
- enum kvm_mr_change change)
-{
- return;
-}
-
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
kvm_flush_remote_tlbs(kvm);
@@ -1847,10 +1826,6 @@
return 0;
}
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
{
return __apic_accept_irq(vcpu, irq->vector);
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 6cf0341..ba5ba7a 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -90,8 +90,6 @@
mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
- flags |= ((mask & VM_WRITE) ? FAULT_FLAG_WRITE : 0);
-
/* mmap_sem is performance critical.... */
prefetchw(&mm->mmap_sem);
@@ -119,6 +117,10 @@
if (notify_page_fault(regs, TRAP_BRKPT))
return;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (mask & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
@@ -170,6 +172,8 @@
*/
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
+ } else if (fault & VM_FAULT_SIGSEGV) {
+ goto bad_area;
} else if (fault & VM_FAULT_SIGBUS) {
signal = SIGBUS;
goto bad_area;
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index 3cdfa9c..e3d4d48901 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -78,7 +78,7 @@
struct mm_struct *mm;
struct vm_area_struct * vma;
unsigned long page, addr;
- int write;
+ unsigned long flags = 0;
int fault;
siginfo_t info;
@@ -117,6 +117,9 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (error_code & ACE_USERMODE)
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -166,14 +169,13 @@
*/
good_area:
info.si_code = SEGV_ACCERR;
- write = 0;
switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
default: /* 3: write, present */
/* fall through */
case ACE_WRITE: /* write, not present */
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
- write++;
+ flags |= FAULT_FLAG_WRITE;
break;
case ACE_PROTECTION: /* read, present */
case 0: /* read, not present */
@@ -194,10 +196,12 @@
*/
addr = (address & PAGE_MASK);
set_thread_fault_code(error_code);
- fault = handle_mm_fault(mm, vma, addr, write ? FAULT_FLAG_WRITE : 0);
+ fault = handle_mm_fault(mm, vma, addr, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 821170e..b969eea 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -16,6 +16,7 @@
select FPU if MMU
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+ select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
select HAVE_MOD_ARCH_SPECIFIC
select MODULES_USE_ELF_REL
select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 2291a7d..fa277ae 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,9 +18,11 @@
#include <asm/machdep.h>
#include <asm/natfeat.h>
+extern long nf_get_id2(const char *feature_name);
+
asm("\n"
-" .global nf_get_id,nf_call\n"
-"nf_get_id:\n"
+" .global nf_get_id2,nf_call\n"
+"nf_get_id2:\n"
" .short 0x7300\n"
" rts\n"
"nf_call:\n"
@@ -29,12 +31,25 @@
"1: moveq.l #0,%d0\n"
" rts\n"
" .section __ex_table,\"a\"\n"
-" .long nf_get_id,1b\n"
+" .long nf_get_id2,1b\n"
" .long nf_call,1b\n"
" .previous");
-EXPORT_SYMBOL_GPL(nf_get_id);
EXPORT_SYMBOL_GPL(nf_call);
+long nf_get_id(const char *feature_name)
+{
+ /* feature_name may be in vmalloc()ed memory, so make a copy */
+ char name_copy[32];
+ size_t n;
+
+ n = strlcpy(name_copy, feature_name, sizeof(name_copy));
+ if (n >= sizeof(name_copy))
+ return 0;
+
+ return nf_get_id2(name_copy);
+}
+EXPORT_SYMBOL_GPL(nf_get_id);
+
void nfprint(const char *fmt, ...)
{
static char buf[256];
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index 444ea8a..ef881cf 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -15,16 +15,17 @@
unsigned long long n64; \
} __n; \
unsigned long __rem, __upper; \
+ unsigned long __base = (base); \
\
__n.n64 = (n); \
if ((__upper = __n.n32[0])) { \
asm ("divul.l %2,%1:%0" \
- : "=d" (__n.n32[0]), "=d" (__upper) \
- : "d" (base), "0" (__n.n32[0])); \
+ : "=d" (__n.n32[0]), "=d" (__upper) \
+ : "d" (__base), "0" (__n.n32[0])); \
} \
asm ("divu.l %2,%1:%0" \
- : "=d" (__n.n32[1]), "=d" (__rem) \
- : "d" (base), "1" (__upper), "0" (__n.n32[1])); \
+ : "=d" (__n.n32[1]), "=d" (__rem) \
+ : "d" (__base), "1" (__upper), "0" (__n.n32[1])); \
(n) = __n.n64; \
__rem; \
})
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index a563727..f0eef04 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -88,6 +88,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -151,6 +153,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto map_err;
else if (fault & VM_FAULT_SIGBUS)
goto bus_err;
BUG();
diff --git a/arch/m68k/mm/hwtest.c b/arch/m68k/mm/hwtest.c
index 2c7dde3..2a5259f 100644
--- a/arch/m68k/mm/hwtest.c
+++ b/arch/m68k/mm/hwtest.c
@@ -28,9 +28,11 @@
int hwreg_present( volatile void *regp )
{
int ret = 0;
+ unsigned long flags;
long save_sp, save_vbr;
long tmp_vectors[3];
+ local_irq_save(flags);
__asm__ __volatile__
( "movec %/vbr,%2\n\t"
"movel #Lberr1,%4@(8)\n\t"
@@ -46,6 +48,7 @@
: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
: "a" (regp), "a" (tmp_vectors)
);
+ local_irq_restore(flags);
return( ret );
}
@@ -58,9 +61,11 @@
int hwreg_write( volatile void *regp, unsigned short val )
{
int ret;
+ unsigned long flags;
long save_sp, save_vbr;
long tmp_vectors[3];
+ local_irq_save(flags);
__asm__ __volatile__
( "movec %/vbr,%2\n\t"
"movel #Lberr2,%4@(8)\n\t"
@@ -78,6 +83,7 @@
: "=&d" (ret), "=&r" (save_sp), "=&r" (save_vbr)
: "a" (regp), "a" (tmp_vectors), "g" (val)
);
+ local_irq_restore(flags);
return( ret );
}
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index c90bfc6..e355a4c 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -15,6 +15,7 @@
volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE;
barrier();
*flushptr = 0;
+ barrier();
}
#else /* CONFIG_METAG_META21 */
@@ -35,6 +36,7 @@
*flushptr = 0;
*flushptr = 0;
*flushptr = 0;
+ barrier();
}
#endif /* !CONFIG_METAG_META21 */
@@ -68,6 +70,7 @@
volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK;
barrier();
*flushptr = 0;
+ barrier();
}
#define smp_mb() fence()
#define smp_rmb() fence()
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index 9b029a7..b88e9cb 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -22,6 +22,8 @@
/* Add an extra page of padding at the top of the stack for the guard page. */
#define STACK_TOP (TASK_SIZE - PAGE_SIZE)
#define STACK_TOP_MAX STACK_TOP
+/* Maximum virtual space for stack */
+#define STACK_SIZE_MAX (1 << 28) /* 256 MB */
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
@@ -147,8 +149,8 @@
unsigned long get_wchan(struct task_struct *p);
-#define KSTK_EIP(tsk) ((tsk)->thread.kernel_context->CurrPC)
-#define KSTK_ESP(tsk) ((tsk)->thread.kernel_context->AX[0].U0)
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->ctx.CurrPC)
+#define KSTK_ESP(tsk) (task_pt_regs(tsk)->ctx.AX[0].U0)
#define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0)
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 2c75bf7..2de5dc6 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -53,8 +53,7 @@
struct vm_area_struct *vma, *prev_vma;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write_access ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
@@ -109,6 +108,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -121,6 +122,7 @@
if (write_access) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto bad_area;
@@ -139,6 +141,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -224,8 +228,10 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return 1;
+ }
no_context:
/* Are we prepared to handle this kernel fault? */
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
index d05b845..bdc4811 100644
--- a/arch/metag/mm/init.c
+++ b/arch/metag/mm/init.c
@@ -419,10 +419,9 @@
#endif
#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
- pr_err("%s(%lx, %lx)\n",
+ pr_err("%s(%llx, %llx)\n",
__func__, start, end);
}
#endif /* CONFIG_OF_FLATTREE */
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d22a4ec..9374e97 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -1,5 +1,6 @@
config MICROBLAZE
def_bool y
+ select ARCH_HAS_GCOV_PROFILE_ALL
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_FUNCTION_TRACER
@@ -28,7 +29,7 @@
select GENERIC_CLOCKEVENTS
select GENERIC_IDLE_POLL_SETUP
select MODULES_USE_ELF_RELA
- select CLONE_BACKWARDS
+ select CLONE_BACKWARDS3
config SWAP
def_bool n
diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c
index 0a2c68f..c9c766f 100644
--- a/arch/microblaze/kernel/prom.c
+++ b/arch/microblaze/kernel/prom.c
@@ -52,13 +52,13 @@
}
#ifdef CONFIG_EARLY_PRINTK
-static char *stdout;
+static const char *stdout;
static int __init early_init_dt_scan_chosen_serial(unsigned long node,
const char *uname, int depth, void *data)
{
- unsigned long l;
- char *p;
+ int l;
+ const char *p;
pr_debug("%s: depth: %d, uname: %s\n", __func__, depth, uname);
@@ -89,7 +89,7 @@
(strncmp(p, "xlnx,opb-uartlite", 17) == 0) ||
(strncmp(p, "xlnx,axi-uartlite", 17) == 0) ||
(strncmp(p, "xlnx,mdm", 8) == 0)) {
- unsigned int *addrp;
+ const unsigned int *addrp;
*(u32 *)data = UARTLITE;
@@ -136,8 +136,7 @@
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 731f739..d46a5eb 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -92,8 +92,7 @@
int code = SEGV_MAPERR;
int is_write = error_code & ESR_S;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
regs->ear = address;
regs->esr = error_code;
@@ -121,6 +120,9 @@
die("Weird page fault", regs, SIGSEGV);
}
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -199,6 +201,7 @@
if (unlikely(is_write)) {
if (unlikely(!(vma->vm_flags & VM_WRITE)))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
@@ -221,6 +224,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 7a58ab9..e53e2b4 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -27,6 +27,7 @@
select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
+ select GENERIC_PCI_IOMAP
select HAVE_ARCH_JUMP_LABEL
select ARCH_WANT_IPC_PARSE_VERSION
select IRQ_FORCED_THREADING
@@ -2412,7 +2413,6 @@
bool "Support for PCI controller"
depends on HW_HAS_PCI
select PCI_DOMAINS
- select GENERIC_PCI_IOMAP
select NO_GENERIC_PCI_IOPORT_MAP
help
Find out whether you have a PCI motherboard. PCI is the name of a
diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 765ef30..733017b 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -164,7 +164,7 @@
ath79_ahb_clk.rate = freq / t;
}
- ath79_wdt_clk.rate = ath79_ref_clk.rate;
+ ath79_wdt_clk.rate = ath79_ahb_clk.rate;
ath79_uart_clk.rate = ath79_ref_clk.rate;
}
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index 2c95730..d498a1f 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/string.h>
#include <asm/addrspace.h>
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index a22f06a..45c1a6c 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -635,7 +635,7 @@
cpumask_clear(&new_affinity);
cpumask_set_cpu(cpumask_first(cpu_online_mask), &new_affinity);
}
- __irq_set_affinity_locked(data, &new_affinity);
+ irq_set_affinity_locked(data, &new_affinity, false);
}
static int octeon_irq_ciu_set_affinity(struct irq_data *data,
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 01b1b3f..6430e7a 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -7,6 +7,7 @@
* Copyright (C) 2008, 2009 Wind River Systems
* written by Ralf Baechle <ralf@linux-mips.org>
*/
+#include <linux/compiler.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/console.h>
@@ -462,6 +463,18 @@
octeon_kill_core(NULL);
}
+static char __read_mostly octeon_system_type[80];
+
+static int __init init_octeon_system_type(void)
+{
+ snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)",
+ cvmx_board_type_to_string(octeon_bootinfo->board_type),
+ octeon_model_get_string(read_c0_prid()));
+
+ return 0;
+}
+early_initcall(init_octeon_system_type);
+
/**
* Handle all the error condition interrupts that might occur.
*
@@ -481,11 +494,7 @@
*/
const char *octeon_board_type_string(void)
{
- static char name[80];
- sprintf(name, "%s (%s)",
- cvmx_board_type_to_string(octeon_bootinfo->board_type),
- octeon_model_get_string(read_c0_prid()));
- return name;
+ return octeon_system_type;
}
const char *get_system_type(void)
@@ -712,7 +721,7 @@
if (cvmx_read_csr(CVMX_L2D_FUS3) & (3ull << 34)) {
pr_info("Skipping L2 locking due to reduced L2 cache size\n");
} else {
- uint32_t ebase = read_c0_ebase() & 0x3ffff000;
+ uint32_t __maybe_unused ebase = read_c0_ebase() & 0x3ffff000;
#ifdef CONFIG_CAVIUM_OCTEON_LOCK_L2_TLB
/* TLB refill */
cvmx_l2c_lock_mem_region(ebase, 0x100);
@@ -996,7 +1005,7 @@
cvmx_bootmem_unlock();
/* Add the memory region for the kernel. */
kernel_start = (unsigned long) _text;
- kernel_size = ALIGN(_end - _text, 0x100000);
+ kernel_size = _end - _text;
/* Adjust for physical offset. */
kernel_start &= ~0xffffffff80000000ULL;
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index b7e5985..b84e1fb 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -170,6 +170,11 @@
extern void __iomem * __ioremap(phys_t offset, phys_t size, unsigned long flags);
extern void __iounmap(const volatile void __iomem *addr);
+#ifndef CONFIG_PCI
+struct pci_dev;
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) {}
+#endif
+
static inline void __iomem * __ioremap_mode(phys_t offset, unsigned long size,
unsigned long flags)
{
diff --git a/arch/mips/include/asm/jump_label.h b/arch/mips/include/asm/jump_label.h
index 4d6d77e..e194f95 100644
--- a/arch/mips/include/asm/jump_label.h
+++ b/arch/mips/include/asm/jump_label.h
@@ -22,7 +22,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:\tnop\n\t"
+ asm_volatile_goto("1:\tnop\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
WORD_INSN " 1b, %l[l_yes], %0\n\t"
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 4d6fa0b..5e3f4b0 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -71,11 +71,6 @@
#define CAUSEB_DC 27
#define CAUSEF_DC (_ULCAST_(1) << 27)
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-struct kvm_interrupt;
-
extern atomic_t kvm_mips_instance;
extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn);
extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn);
@@ -659,5 +654,16 @@
extern int kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
#endif /* __MIPS_KVM_HOST_H__ */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 87e6207..3d0074e 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -14,6 +14,7 @@
#define _ASM_MIPSREGS_H
#include <linux/linkage.h>
+#include <linux/types.h>
#include <asm/hazards.h>
#include <asm/war.h>
diff --git a/arch/mips/include/asm/reg.h b/arch/mips/include/asm/reg.h
index 910e71a..b8343cc 100644
--- a/arch/mips/include/asm/reg.h
+++ b/arch/mips/include/asm/reg.h
@@ -12,116 +12,194 @@
#ifndef __ASM_MIPS_REG_H
#define __ASM_MIPS_REG_H
-
-#if defined(CONFIG_32BIT) || defined(WANT_COMPAT_REG_H)
-
-#define EF_R0 6
-#define EF_R1 7
-#define EF_R2 8
-#define EF_R3 9
-#define EF_R4 10
-#define EF_R5 11
-#define EF_R6 12
-#define EF_R7 13
-#define EF_R8 14
-#define EF_R9 15
-#define EF_R10 16
-#define EF_R11 17
-#define EF_R12 18
-#define EF_R13 19
-#define EF_R14 20
-#define EF_R15 21
-#define EF_R16 22
-#define EF_R17 23
-#define EF_R18 24
-#define EF_R19 25
-#define EF_R20 26
-#define EF_R21 27
-#define EF_R22 28
-#define EF_R23 29
-#define EF_R24 30
-#define EF_R25 31
+#define MIPS32_EF_R0 6
+#define MIPS32_EF_R1 7
+#define MIPS32_EF_R2 8
+#define MIPS32_EF_R3 9
+#define MIPS32_EF_R4 10
+#define MIPS32_EF_R5 11
+#define MIPS32_EF_R6 12
+#define MIPS32_EF_R7 13
+#define MIPS32_EF_R8 14
+#define MIPS32_EF_R9 15
+#define MIPS32_EF_R10 16
+#define MIPS32_EF_R11 17
+#define MIPS32_EF_R12 18
+#define MIPS32_EF_R13 19
+#define MIPS32_EF_R14 20
+#define MIPS32_EF_R15 21
+#define MIPS32_EF_R16 22
+#define MIPS32_EF_R17 23
+#define MIPS32_EF_R18 24
+#define MIPS32_EF_R19 25
+#define MIPS32_EF_R20 26
+#define MIPS32_EF_R21 27
+#define MIPS32_EF_R22 28
+#define MIPS32_EF_R23 29
+#define MIPS32_EF_R24 30
+#define MIPS32_EF_R25 31
/*
* k0/k1 unsaved
*/
-#define EF_R26 32
-#define EF_R27 33
+#define MIPS32_EF_R26 32
+#define MIPS32_EF_R27 33
-#define EF_R28 34
-#define EF_R29 35
-#define EF_R30 36
-#define EF_R31 37
+#define MIPS32_EF_R28 34
+#define MIPS32_EF_R29 35
+#define MIPS32_EF_R30 36
+#define MIPS32_EF_R31 37
/*
* Saved special registers
*/
-#define EF_LO 38
-#define EF_HI 39
+#define MIPS32_EF_LO 38
+#define MIPS32_EF_HI 39
-#define EF_CP0_EPC 40
-#define EF_CP0_BADVADDR 41
-#define EF_CP0_STATUS 42
-#define EF_CP0_CAUSE 43
-#define EF_UNUSED0 44
+#define MIPS32_EF_CP0_EPC 40
+#define MIPS32_EF_CP0_BADVADDR 41
+#define MIPS32_EF_CP0_STATUS 42
+#define MIPS32_EF_CP0_CAUSE 43
+#define MIPS32_EF_UNUSED0 44
-#define EF_SIZE 180
+#define MIPS32_EF_SIZE 180
-#endif
-
-#if defined(CONFIG_64BIT) && !defined(WANT_COMPAT_REG_H)
-
-#define EF_R0 0
-#define EF_R1 1
-#define EF_R2 2
-#define EF_R3 3
-#define EF_R4 4
-#define EF_R5 5
-#define EF_R6 6
-#define EF_R7 7
-#define EF_R8 8
-#define EF_R9 9
-#define EF_R10 10
-#define EF_R11 11
-#define EF_R12 12
-#define EF_R13 13
-#define EF_R14 14
-#define EF_R15 15
-#define EF_R16 16
-#define EF_R17 17
-#define EF_R18 18
-#define EF_R19 19
-#define EF_R20 20
-#define EF_R21 21
-#define EF_R22 22
-#define EF_R23 23
-#define EF_R24 24
-#define EF_R25 25
+#define MIPS64_EF_R0 0
+#define MIPS64_EF_R1 1
+#define MIPS64_EF_R2 2
+#define MIPS64_EF_R3 3
+#define MIPS64_EF_R4 4
+#define MIPS64_EF_R5 5
+#define MIPS64_EF_R6 6
+#define MIPS64_EF_R7 7
+#define MIPS64_EF_R8 8
+#define MIPS64_EF_R9 9
+#define MIPS64_EF_R10 10
+#define MIPS64_EF_R11 11
+#define MIPS64_EF_R12 12
+#define MIPS64_EF_R13 13
+#define MIPS64_EF_R14 14
+#define MIPS64_EF_R15 15
+#define MIPS64_EF_R16 16
+#define MIPS64_EF_R17 17
+#define MIPS64_EF_R18 18
+#define MIPS64_EF_R19 19
+#define MIPS64_EF_R20 20
+#define MIPS64_EF_R21 21
+#define MIPS64_EF_R22 22
+#define MIPS64_EF_R23 23
+#define MIPS64_EF_R24 24
+#define MIPS64_EF_R25 25
/*
* k0/k1 unsaved
*/
-#define EF_R26 26
-#define EF_R27 27
+#define MIPS64_EF_R26 26
+#define MIPS64_EF_R27 27
-#define EF_R28 28
-#define EF_R29 29
-#define EF_R30 30
-#define EF_R31 31
+#define MIPS64_EF_R28 28
+#define MIPS64_EF_R29 29
+#define MIPS64_EF_R30 30
+#define MIPS64_EF_R31 31
/*
* Saved special registers
*/
-#define EF_LO 32
-#define EF_HI 33
+#define MIPS64_EF_LO 32
+#define MIPS64_EF_HI 33
-#define EF_CP0_EPC 34
-#define EF_CP0_BADVADDR 35
-#define EF_CP0_STATUS 36
-#define EF_CP0_CAUSE 37
+#define MIPS64_EF_CP0_EPC 34
+#define MIPS64_EF_CP0_BADVADDR 35
+#define MIPS64_EF_CP0_STATUS 36
+#define MIPS64_EF_CP0_CAUSE 37
-#define EF_SIZE 304 /* size in bytes */
+#define MIPS64_EF_SIZE 304 /* size in bytes */
+
+#if defined(CONFIG_32BIT)
+
+#define EF_R0 MIPS32_EF_R0
+#define EF_R1 MIPS32_EF_R1
+#define EF_R2 MIPS32_EF_R2
+#define EF_R3 MIPS32_EF_R3
+#define EF_R4 MIPS32_EF_R4
+#define EF_R5 MIPS32_EF_R5
+#define EF_R6 MIPS32_EF_R6
+#define EF_R7 MIPS32_EF_R7
+#define EF_R8 MIPS32_EF_R8
+#define EF_R9 MIPS32_EF_R9
+#define EF_R10 MIPS32_EF_R10
+#define EF_R11 MIPS32_EF_R11
+#define EF_R12 MIPS32_EF_R12
+#define EF_R13 MIPS32_EF_R13
+#define EF_R14 MIPS32_EF_R14
+#define EF_R15 MIPS32_EF_R15
+#define EF_R16 MIPS32_EF_R16
+#define EF_R17 MIPS32_EF_R17
+#define EF_R18 MIPS32_EF_R18
+#define EF_R19 MIPS32_EF_R19
+#define EF_R20 MIPS32_EF_R20
+#define EF_R21 MIPS32_EF_R21
+#define EF_R22 MIPS32_EF_R22
+#define EF_R23 MIPS32_EF_R23
+#define EF_R24 MIPS32_EF_R24
+#define EF_R25 MIPS32_EF_R25
+#define EF_R26 MIPS32_EF_R26
+#define EF_R27 MIPS32_EF_R27
+#define EF_R28 MIPS32_EF_R28
+#define EF_R29 MIPS32_EF_R29
+#define EF_R30 MIPS32_EF_R30
+#define EF_R31 MIPS32_EF_R31
+#define EF_LO MIPS32_EF_LO
+#define EF_HI MIPS32_EF_HI
+#define EF_CP0_EPC MIPS32_EF_CP0_EPC
+#define EF_CP0_BADVADDR MIPS32_EF_CP0_BADVADDR
+#define EF_CP0_STATUS MIPS32_EF_CP0_STATUS
+#define EF_CP0_CAUSE MIPS32_EF_CP0_CAUSE
+#define EF_UNUSED0 MIPS32_EF_UNUSED0
+#define EF_SIZE MIPS32_EF_SIZE
+
+#elif defined(CONFIG_64BIT)
+
+#define EF_R0 MIPS64_EF_R0
+#define EF_R1 MIPS64_EF_R1
+#define EF_R2 MIPS64_EF_R2
+#define EF_R3 MIPS64_EF_R3
+#define EF_R4 MIPS64_EF_R4
+#define EF_R5 MIPS64_EF_R5
+#define EF_R6 MIPS64_EF_R6
+#define EF_R7 MIPS64_EF_R7
+#define EF_R8 MIPS64_EF_R8
+#define EF_R9 MIPS64_EF_R9
+#define EF_R10 MIPS64_EF_R10
+#define EF_R11 MIPS64_EF_R11
+#define EF_R12 MIPS64_EF_R12
+#define EF_R13 MIPS64_EF_R13
+#define EF_R14 MIPS64_EF_R14
+#define EF_R15 MIPS64_EF_R15
+#define EF_R16 MIPS64_EF_R16
+#define EF_R17 MIPS64_EF_R17
+#define EF_R18 MIPS64_EF_R18
+#define EF_R19 MIPS64_EF_R19
+#define EF_R20 MIPS64_EF_R20
+#define EF_R21 MIPS64_EF_R21
+#define EF_R22 MIPS64_EF_R22
+#define EF_R23 MIPS64_EF_R23
+#define EF_R24 MIPS64_EF_R24
+#define EF_R25 MIPS64_EF_R25
+#define EF_R26 MIPS64_EF_R26
+#define EF_R27 MIPS64_EF_R27
+#define EF_R28 MIPS64_EF_R28
+#define EF_R29 MIPS64_EF_R29
+#define EF_R30 MIPS64_EF_R30
+#define EF_R31 MIPS64_EF_R31
+#define EF_LO MIPS64_EF_LO
+#define EF_HI MIPS64_EF_HI
+#define EF_CP0_EPC MIPS64_EF_CP0_EPC
+#define EF_CP0_BADVADDR MIPS64_EF_CP0_BADVADDR
+#define EF_CP0_STATUS MIPS64_EF_CP0_STATUS
+#define EF_CP0_CAUSE MIPS64_EF_CP0_CAUSE
+#define EF_SIZE MIPS64_EF_SIZE
#endif /* CONFIG_64BIT */
diff --git a/arch/mips/include/asm/suspend.h b/arch/mips/include/asm/suspend.h
deleted file mode 100644
index 3adac3b..0000000
--- a/arch/mips/include/asm/suspend.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_SUSPEND_H
-#define __ASM_SUSPEND_H
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
-#endif /* __ASM_SUSPEND_H */
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 895320e..e6e5d91 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -131,6 +131,8 @@
#define _TIF_FPUBOUND (1<<TIF_FPUBOUND)
#define _TIF_LOAD_WATCH (1<<TIF_LOAD_WATCH)
+#define _TIF_WORK_SYSCALL_ENTRY (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP)
+
/* work to do in syscall_trace_leave() */
#define _TIF_WORK_SYSCALL_EXIT (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT)
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 202e581..7fdf1de 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -58,12 +58,6 @@
#include <asm/processor.h>
-/*
- * When this file is selected, we are definitely running a 64bit kernel.
- * So using the right regs define in asm/reg.h
- */
-#define WANT_COMPAT_REG_H
-
/* These MUST be defined before elf.h gets included */
extern void elf32_core_copy_regs(elf_gregset_t grp, struct pt_regs *regs);
#define ELF_CORE_COPY_REGS(_dest, _regs) elf32_core_copy_regs(_dest, _regs);
@@ -135,21 +129,21 @@
{
int i;
- for (i = 0; i < EF_R0; i++)
+ for (i = 0; i < MIPS32_EF_R0; i++)
grp[i] = 0;
- grp[EF_R0] = 0;
+ grp[MIPS32_EF_R0] = 0;
for (i = 1; i <= 31; i++)
- grp[EF_R0 + i] = (elf_greg_t) regs->regs[i];
- grp[EF_R26] = 0;
- grp[EF_R27] = 0;
- grp[EF_LO] = (elf_greg_t) regs->lo;
- grp[EF_HI] = (elf_greg_t) regs->hi;
- grp[EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
- grp[EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
- grp[EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
- grp[EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
-#ifdef EF_UNUSED0
- grp[EF_UNUSED0] = 0;
+ grp[MIPS32_EF_R0 + i] = (elf_greg_t) regs->regs[i];
+ grp[MIPS32_EF_R26] = 0;
+ grp[MIPS32_EF_R27] = 0;
+ grp[MIPS32_EF_LO] = (elf_greg_t) regs->lo;
+ grp[MIPS32_EF_HI] = (elf_greg_t) regs->hi;
+ grp[MIPS32_EF_CP0_EPC] = (elf_greg_t) regs->cp0_epc;
+ grp[MIPS32_EF_CP0_BADVADDR] = (elf_greg_t) regs->cp0_badvaddr;
+ grp[MIPS32_EF_CP0_STATUS] = (elf_greg_t) regs->cp0_status;
+ grp[MIPS32_EF_CP0_CAUSE] = (elf_greg_t) regs->cp0_cause;
+#ifdef MIPS32_EF_UNUSED0
+ grp[MIPS32_EF_UNUSED0] = 0;
#endif
}
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index c01b307..bffbbc5 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -256,11 +256,13 @@
/* Setup Intr to Pin mapping */
if (pin & GIC_MAP_TO_NMI_MSK) {
+ int i;
+
GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin);
/* FIXME: hack to route NMI to all cpu's */
- for (cpu = 0; cpu < NR_CPUS; cpu += 32) {
+ for (i = 0; i < NR_CPUS; i += 32) {
GICWRITE(GIC_REG_ADDR(SHARED,
- GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)),
+ GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)),
0xffffffff);
}
} else {
diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index fab40f7..ac9facc 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -131,7 +131,7 @@
board_bind_eic_interrupt = &msc_bind_eic_interrupt;
- for (; nirq >= 0; nirq--, imp++) {
+ for (; nirq > 0; nirq--, imp++) {
int n = imp->im_irq;
switch (imp->im_type) {
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index 72ef2d2..ab941a3 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -56,6 +56,8 @@
.irq_mask_ack = mask_mips_irq,
.irq_unmask = unmask_mips_irq,
.irq_eoi = unmask_mips_irq,
+ .irq_disable = mask_mips_irq,
+ .irq_enable = unmask_mips_irq,
};
/*
@@ -92,6 +94,8 @@
.irq_mask_ack = mips_mt_cpu_irq_ack,
.irq_unmask = unmask_mips_irq,
.irq_eoi = unmask_mips_irq,
+ .irq_disable = mask_mips_irq,
+ .irq_enable = unmask_mips_irq,
};
void __init mips_cpu_irq_init(void)
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 33d0671..3efbf0b 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -123,7 +123,11 @@
nop
#endif
b ftrace_stub
+#ifdef CONFIG_32BIT
+ addiu sp, sp, 8
+#else
nop
+#endif
static_trace:
MCOUNT_SAVE_REGS
@@ -133,6 +137,9 @@
move a1, AT /* arg2: parent's return address */
MCOUNT_RESTORE_REGS
+#ifdef CONFIG_32BIT
+ addiu sp, sp, 8
+#endif
.globl ftrace_stub
ftrace_stub:
RETURN_BACK
@@ -181,6 +188,11 @@
jal prepare_ftrace_return
nop
MCOUNT_RESTORE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_32BIT
+ addiu sp, sp, 8
+#endif
+#endif
RETURN_BACK
END(ftrace_graph_caller)
diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c
index 6e58e97..cedeb56 100644
--- a/arch/mips/kernel/mips_ksyms.c
+++ b/arch/mips/kernel/mips_ksyms.c
@@ -14,6 +14,7 @@
#include <linux/mm.h>
#include <asm/uaccess.h>
#include <asm/ftrace.h>
+#include <asm/fpu.h>
extern void *__bzero(void *__s, size_t __count);
extern long __strncpy_from_user_nocheck_asm(char *__to,
@@ -26,6 +27,13 @@
extern long __strnlen_user_asm(const char *s);
/*
+ * Core architecture code
+ */
+#ifdef CONFIG_CPU_R4K_FPU
+EXPORT_SYMBOL_GPL(_save_fp);
+#endif
+
+/*
* String functions
*/
EXPORT_SYMBOL(memset);
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index 5712bb5..32b8788 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -58,8 +58,7 @@
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9c6299c..1b95b24 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -161,6 +161,7 @@
__get_user(fregs[i], i + (__u64 __user *) data);
__get_user(child->thread.fpu.fcr31, data + 64);
+ child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X;
/* FIR may not be written. */
@@ -451,7 +452,7 @@
break;
#endif
case FPC_CSR:
- child->thread.fpu.fcr31 = data;
+ child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X;
break;
case DSP_BASE ... DSP_BASE + 5: {
dspreg_t *dregs;
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 9b36424..ed5bafb 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -52,7 +52,7 @@
stack_done:
lw t0, TI_FLAGS($28) # syscall tracing enabled?
- li t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+ li t1, _TIF_WORK_SYSCALL_ENTRY
and t0, t1
bnez t0, syscall_trace_entry # -> yes
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 97a5909..be6627e 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -54,7 +54,7 @@
sd a3, PT_R26(sp) # save a3 for syscall restarting
- li t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+ li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
bnez t0, syscall_trace_entry
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index edcb659..cab1507 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -47,7 +47,7 @@
sd a3, PT_R26(sp) # save a3 for syscall restarting
- li t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+ li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
bnez t0, n32_syscall_trace_entry
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 74f485d..37605dc 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -81,7 +81,7 @@
PTR 4b, bad_stack
.previous
- li t1, _TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT
+ li t1, _TIF_WORK_SYSCALL_ENTRY
LONG_L t0, TI_FLAGS($28) # syscall tracing enabled?
and t0, t1, t0
bnez t0, trace_a_syscall
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 6e7862a..caeec21 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -109,10 +109,10 @@
else
#endif /* CONFIG_MIPS_MT_SMTC */
cpu_probe();
- cpu_report();
per_cpu_trap_init(false);
mips_clockevent_init();
mp_ops->init_secondary();
+ cpu_report();
/*
* XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 203d885..2c81265 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -604,7 +604,6 @@
case sdc1_op:
die_if_kernel("Unaligned FP access in kernel code", regs);
BUG_ON(!used_math());
- BUG_ON(!is_fpu_owner());
lose_fpu(1); /* Save FPU state for the emulator. */
res = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1,
diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S
index dca2aa6..920b632 100644
--- a/arch/mips/kvm/kvm_locore.S
+++ b/arch/mips/kvm/kvm_locore.S
@@ -431,7 +431,7 @@
/* Setup status register for running guest in UM */
.set at
or v1, v1, (ST0_EXL | KSU_USER | ST0_IE)
- and v1, v1, ~ST0_CU0
+ and v1, v1, ~(ST0_CU0 | ST0_MX)
.set noat
mtc0 v1, CP0_STATUS
ehb
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c
index dd203e5..b1632c2 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/kvm_mips.c
@@ -15,6 +15,7 @@
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
+#include <asm/fpu.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
@@ -149,9 +150,7 @@
if (kvm->arch.guest_pmap[i] != KVM_INVALID_PAGE)
kvm_mips_release_pfn_clean(kvm->arch.guest_pmap[i]);
}
-
- if (kvm->arch.guest_pmap)
- kfree(kvm->arch.guest_pmap);
+ kfree(kvm->arch.guest_pmap);
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_arch_vcpu_free(vcpu);
@@ -198,16 +197,21 @@
return -ENOIOCTLCMD;
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
}
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
return 0;
}
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -299,7 +303,7 @@
if (cpu_has_veic || cpu_has_vint) {
size = 0x200 + VECTORSPACING * 64;
} else {
- size = 0x200;
+ size = 0x4000;
}
/* Save Linux EBASE */
@@ -384,12 +388,9 @@
kvm_mips_dump_stats(vcpu);
- if (vcpu->arch.guest_ebase)
- kfree(vcpu->arch.guest_ebase);
-
- if (vcpu->arch.kseg0_commpage)
- kfree(vcpu->arch.kseg0_commpage);
-
+ kfree(vcpu->arch.guest_ebase);
+ kfree(vcpu->arch.kseg0_commpage);
+ kfree(vcpu);
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -418,11 +419,13 @@
vcpu->mmio_needed = 0;
}
+ lose_fpu(1);
+
+ local_irq_disable();
/* Check if we have any exceptions/interrupts pending */
kvm_mips_deliver_interrupts(vcpu,
kvm_read_c0_guest_cause(vcpu->arch.cop0));
- local_irq_disable();
kvm_guest_enter();
r = __kvm_mips_vcpu_run(run, vcpu);
@@ -1022,9 +1025,6 @@
{
uint32_t status = read_c0_status();
- if (cpu_has_fpu)
- status |= (ST0_CU1);
-
if (cpu_has_dsp)
status |= (ST0_MX);
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c
index 4b6274b..e75ef82 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/kvm_mips_emul.c
@@ -1571,17 +1571,17 @@
arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0);
#else
/* UserLocal not implemented */
- er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
+ er = EMULATE_FAIL;
#endif
break;
default:
- printk("RDHWR not supported\n");
+ kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc);
er = EMULATE_FAIL;
break;
}
} else {
- printk("Emulate RI not supported @ %p: %#x\n", opc, inst);
+ kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst);
er = EMULATE_FAIL;
}
@@ -1590,6 +1590,7 @@
*/
if (er == EMULATE_FAIL) {
vcpu->arch.pc = curr_pc;
+ er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
}
return er;
}
diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h
index bc9e0f4..e51621e 100644
--- a/arch/mips/kvm/trace.h
+++ b/arch/mips/kvm/trace.h
@@ -26,18 +26,18 @@
TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason),
TP_ARGS(vcpu, reason),
TP_STRUCT__entry(
- __field(struct kvm_vcpu *, vcpu)
+ __field(unsigned long, pc)
__field(unsigned int, reason)
),
TP_fast_assign(
- __entry->vcpu = vcpu;
+ __entry->pc = vcpu->arch.pc;
__entry->reason = reason;
),
TP_printk("[%s]PC: 0x%08lx",
kvm_mips_exit_types_str[__entry->reason],
- __entry->vcpu->arch.pc)
+ __entry->pc)
);
#endif /* _TRACE_KVM_H */
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/lantiq/dts/easy50712.dts
index fac1f5b..143b8a3 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/lantiq/dts/easy50712.dts
@@ -8,6 +8,7 @@
};
memory@0 {
+ device_type = "memory";
reg = <0x0 0x2000000>;
};
diff --git a/arch/mips/loongson/common/Makefile b/arch/mips/loongson/common/Makefile
index 4c57b3e..33f76e6 100644
--- a/arch/mips/loongson/common/Makefile
+++ b/arch/mips/loongson/common/Makefile
@@ -10,7 +10,8 @@
# Serial port support
#
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
-obj-$(CONFIG_SERIAL_8250) += serial.o
+loongson-serial-$(CONFIG_SERIAL_8250) := serial.o
+obj-y += $(loongson-serial-m) $(loongson-serial-y)
obj-$(CONFIG_LOONGSON_UART_BASE) += uart_base.o
obj-$(CONFIG_LOONGSON_MC146818) += rtc.o
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 21813be..c2ec87e 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -12,6 +12,7 @@
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/linkage.h>
+#include <linux/preempt.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/mm.h>
@@ -601,11 +602,13 @@
/* Catch bad driver code */
BUG_ON(size == 0);
+ preempt_disable();
if (cpu_has_inclusive_pcaches) {
if (size >= scache_size)
r4k_blast_scache();
else
blast_scache_range(addr, addr + size);
+ preempt_enable();
__sync();
return;
}
@@ -621,6 +624,7 @@
R4600_HIT_CACHEOP_WAR_IMPL;
blast_dcache_range(addr, addr + size);
}
+ preempt_enable();
bc_wback_inv(addr, size);
__sync();
@@ -631,6 +635,7 @@
/* Catch bad driver code */
BUG_ON(size == 0);
+ preempt_disable();
if (cpu_has_inclusive_pcaches) {
if (size >= scache_size)
r4k_blast_scache();
@@ -645,6 +650,7 @@
*/
blast_inv_scache_range(addr, addr + size);
}
+ preempt_enable();
__sync();
return;
}
@@ -655,6 +661,7 @@
R4600_HIT_CACHEOP_WAR_IMPL;
blast_inv_dcache_range(addr, addr + size);
}
+ preempt_enable();
bc_inv(addr, size);
__sync();
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index caf92ec..23129d1 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -50,16 +50,20 @@
}
/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
+ * speculatively fill random cachelines with stale data at any time,
+ * requiring an extra flush post-DMA.
+ *
* Warning on the terminology - Linux calls an uncached area coherent;
* MIPS terminology calls memory areas with hardware maintained coherency
* coherent.
*/
-
-static inline int cpu_is_noncoherent_r10000(struct device *dev)
+static inline int cpu_needs_post_dma_flush(struct device *dev)
{
return !plat_device_is_coherent(dev) &&
(current_cpu_type() == CPU_R10000 ||
- current_cpu_type() == CPU_R12000);
+ current_cpu_type() == CPU_R12000 ||
+ current_cpu_type() == CPU_BMIPS5000);
}
static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
@@ -230,7 +234,7 @@
static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
size_t size, enum dma_data_direction direction, struct dma_attrs *attrs)
{
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(dma_addr_to_page(dev, dma_addr),
dma_addr & ~PAGE_MASK, size, direction);
@@ -281,7 +285,7 @@
static void mips_dma_sync_single_for_cpu(struct device *dev,
dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
{
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(dma_addr_to_page(dev, dma_handle),
dma_handle & ~PAGE_MASK, size, direction);
}
@@ -302,7 +306,7 @@
/* Make sure that gcc doesn't leave the empty loop body. */
for (i = 0; i < nelems; i++, sg++) {
- if (cpu_is_noncoherent_r10000(dev))
+ if (cpu_needs_post_dma_flush(dev))
__dma_sync(sg_page(sg), sg->offset, sg->length,
direction);
}
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 0fead53..c40a8d1 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -41,8 +41,7 @@
const int field = sizeof(unsigned long) * 2;
siginfo_t info;
int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
#if 0
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
@@ -92,6 +91,8 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -113,6 +114,7 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (cpu_has_rixi) {
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
@@ -155,6 +157,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -240,6 +244,8 @@
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!user_mode(regs))
+ goto no_context;
pagefault_out_of_memory();
return;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 9b973e0..d340d53 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -74,6 +74,7 @@
*/
unsigned long empty_zero_page, zero_page_mask;
EXPORT_SYMBOL_GPL(empty_zero_page);
+EXPORT_SYMBOL(zero_page_mask);
/*
* Not static inline because used by IP27 special magic initialization code
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index afeef93..a91a7a9 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1091,6 +1091,7 @@
struct mips_huge_tlb_info {
int huge_pte;
int restore_scratch;
+ bool need_reload_pte;
};
static struct mips_huge_tlb_info __cpuinit
@@ -1105,6 +1106,7 @@
rv.huge_pte = scratch;
rv.restore_scratch = 0;
+ rv.need_reload_pte = false;
if (check_for_high_segbits) {
UASM_i_MFC0(p, tmp, C0_BADVADDR);
@@ -1293,6 +1295,7 @@
} else {
htlb_info.huge_pte = K0;
htlb_info.restore_scratch = 0;
+ htlb_info.need_reload_pte = true;
vmalloc_mode = refill_noscratch;
/*
* create the plain linear handler
@@ -1329,6 +1332,8 @@
}
#ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
uasm_l_tlb_huge_update(&l, p);
+ if (htlb_info.need_reload_pte)
+ UASM_i_LW(&p, htlb_info.huge_pte, 0, K1);
build_huge_update_entries(&p, htlb_info.huge_pte, K1);
build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random,
htlb_info.restore_scratch);
diff --git a/arch/mips/oprofile/backtrace.c b/arch/mips/oprofile/backtrace.c
index 6854ed5..83a1dfd 100644
--- a/arch/mips/oprofile/backtrace.c
+++ b/arch/mips/oprofile/backtrace.c
@@ -92,7 +92,7 @@
/* This marks the end of the previous function,
which means we overran. */
break;
- stack_size = (unsigned) stack_adjustment;
+ stack_size = (unsigned long) stack_adjustment;
} else if (is_ra_save_ins(&ip)) {
int ra_slot = ip.i_format.simmediate;
if (ra_slot < 0)
diff --git a/arch/mips/power/cpu.c b/arch/mips/power/cpu.c
index 521e596..2129e67 100644
--- a/arch/mips/power/cpu.c
+++ b/arch/mips/power/cpu.c
@@ -7,7 +7,7 @@
* Author: Hu Hongbing <huhb@lemote.com>
* Wu Zhangjin <wuzhangjin@gmail.com>
*/
-#include <asm/suspend.h>
+#include <asm/sections.h>
#include <asm/fpu.h>
#include <asm/dsp.h>
diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S
index 7e0277a..e7567c8 100644
--- a/arch/mips/power/hibernate.S
+++ b/arch/mips/power/hibernate.S
@@ -30,6 +30,8 @@
END(swsusp_arch_suspend)
LEAF(swsusp_arch_resume)
+ /* Avoid TLB mismatch during and after kernel resume */
+ jal local_flush_tlb_all
PTR_L t0, restore_pblist
0:
PTR_L t1, PBE_ADDRESS(t0) /* source */
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/ralink/dts/mt7620a_eval.dts
index 35eb874..709f581 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/ralink/dts/mt7620a_eval.dts
@@ -7,6 +7,7 @@
model = "Ralink MT7620A evaluation board";
memory@0 {
+ device_type = "memory";
reg = <0x0 0x2000000>;
};
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/ralink/dts/rt2880_eval.dts
index 322d700..0a685db 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/ralink/dts/rt2880_eval.dts
@@ -7,6 +7,7 @@
model = "Ralink RT2880 evaluation board";
memory@0 {
+ device_type = "memory";
reg = <0x8000000 0x2000000>;
};
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts
index 0ac73ea..ec9e9a0 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/ralink/dts/rt3052_eval.dts
@@ -7,6 +7,7 @@
model = "Ralink RT3052 evaluation board";
memory@0 {
+ device_type = "memory";
reg = <0x0 0x2000000>;
};
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/ralink/dts/rt3883_eval.dts
index 2fa6b33..e8df21a 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/ralink/dts/rt3883_eval.dts
@@ -7,6 +7,7 @@
model = "Ralink RT3883 evaluation board";
memory@0 {
+ device_type = "memory";
reg = <0x0 0x2000000>;
};
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index d48a84f..0c2cc5d 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -171,6 +171,8 @@
if (in_atomic() || !mm)
goto no_context;
+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
@@ -260,6 +262,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -345,9 +349,10 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- printk(KERN_ALERT "VM: killing process %s\n", tsk->comm);
- if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
- do_exit(SIGKILL);
+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
+ pagefault_out_of_memory();
+ return;
+ }
goto no_context;
do_sigbus:
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index d8a455e..fec8bf9 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -853,38 +853,45 @@
/* ========================================================[ return ] === */
-_work_pending:
- /*
- * if (current_thread_info->flags & _TIF_NEED_RESCHED)
- * schedule();
- */
- l.lwz r5,TI_FLAGS(r10)
- l.andi r3,r5,_TIF_NEED_RESCHED
- l.sfnei r3,0
- l.bnf _work_notifysig
- l.nop
- l.jal schedule
- l.nop
- l.j _resume_userspace
- l.nop
-
-/* Handle pending signals and notify-resume requests.
- * do_notify_resume must be passed the latest pushed pt_regs, not
- * necessarily the "userspace" ones. Also, pt_regs->syscallno
- * must be set so that the syscall restart functionality works.
- */
-_work_notifysig:
- l.jal do_notify_resume
- l.ori r3,r1,0 /* pt_regs */
-
_resume_userspace:
DISABLE_INTERRUPTS(r3,r4)
- l.lwz r3,TI_FLAGS(r10)
- l.andi r3,r3,_TIF_WORK_MASK
- l.sfnei r3,0
- l.bf _work_pending
+ l.lwz r4,TI_FLAGS(r10)
+ l.andi r13,r4,_TIF_WORK_MASK
+ l.sfeqi r13,0
+ l.bf _restore_all
l.nop
+_work_pending:
+ l.lwz r5,PT_ORIG_GPR11(r1)
+ l.sfltsi r5,0
+ l.bnf 1f
+ l.nop
+ l.andi r5,r5,0
+1:
+ l.jal do_work_pending
+ l.ori r3,r1,0 /* pt_regs */
+
+ l.sfeqi r11,0
+ l.bf _restore_all
+ l.nop
+ l.sfltsi r11,0
+ l.bnf 1f
+ l.nop
+ l.and r11,r11,r0
+ l.ori r11,r11,__NR_restart_syscall
+ l.j _syscall_check_trace_enter
+ l.nop
+1:
+ l.lwz r11,PT_ORIG_GPR11(r1)
+ /* Restore arg registers */
+ l.lwz r3,PT_GPR3(r1)
+ l.lwz r4,PT_GPR4(r1)
+ l.lwz r5,PT_GPR5(r1)
+ l.lwz r6,PT_GPR6(r1)
+ l.lwz r7,PT_GPR7(r1)
+ l.j _syscall_check_trace_enter
+ l.lwz r8,PT_GPR8(r1)
+
_restore_all:
RESTORE_ALL
/* This returns to userspace code */
diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c
index 5869e3f..150215a 100644
--- a/arch/openrisc/kernel/prom.c
+++ b/arch/openrisc/kernel/prom.c
@@ -96,8 +96,7 @@
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c
index ae167f7..c277ec8 100644
--- a/arch/openrisc/kernel/signal.c
+++ b/arch/openrisc/kernel/signal.c
@@ -28,24 +28,24 @@
#include <linux/tracehook.h>
#include <asm/processor.h>
+#include <asm/syscall.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#define DEBUG_SIG 0
struct rt_sigframe {
- struct siginfo *pinfo;
- void *puc;
struct siginfo info;
struct ucontext uc;
unsigned char retcode[16]; /* trampoline code */
};
-static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc)
+static int restore_sigcontext(struct pt_regs *regs,
+ struct sigcontext __user *sc)
{
- unsigned int err = 0;
+ int err = 0;
- /* Alwys make any pending restarted system call return -EINTR */
+ /* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
/*
@@ -53,25 +53,21 @@
* (sc is already checked for VERIFY_READ since the sigframe was
* checked in sys_sigreturn previously)
*/
- if (__copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long)))
- goto badframe;
- if (__copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long)))
- goto badframe;
- if (__copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long)))
- goto badframe;
+ err |= __copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long));
+ err |= __copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long));
+ err |= __copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long));
/* make sure the SM-bit is cleared so user-mode cannot fool us */
regs->sr &= ~SPR_SR_SM;
+ regs->orig_gpr11 = -1; /* Avoid syscall restart checks */
+
/* TODO: the other ports use regs->orig_XX to disable syscall checks
* after this completes, but we don't use that mechanism. maybe we can
* use it now ?
*/
return err;
-
-badframe:
- return 1;
}
asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs)
@@ -111,21 +107,18 @@
* Set up a signal frame.
*/
-static int setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs,
- unsigned long mask)
+static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
{
int err = 0;
/* copy the regs */
-
+ /* There should be no need to save callee-saved registers here...
+ * ...but we save them anyway. Revisit this
+ */
err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long));
err |= __copy_to_user(&sc->regs.pc, ®s->pc, sizeof(unsigned long));
err |= __copy_to_user(&sc->regs.sr, ®s->sr, sizeof(unsigned long));
- /* then some other stuff */
-
- err |= __put_user(mask, &sc->oldmask);
-
return err;
}
@@ -181,24 +174,18 @@
int err = 0;
frame = get_sigframe(ka, regs, sizeof(*frame));
-
if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
goto give_sigsegv;
- err |= __put_user(&frame->info, &frame->pinfo);
- err |= __put_user(&frame->uc, &frame->puc);
-
+ /* Create siginfo. */
if (ka->sa.sa_flags & SA_SIGINFO)
err |= copy_siginfo_to_user(&frame->info, info);
- if (err)
- goto give_sigsegv;
- /* Clear all the bits of the ucontext we don't use. */
- err |= __clear_user(&frame->uc, offsetof(struct ucontext, uc_mcontext));
+ /* Create the ucontext. */
err |= __put_user(0, &frame->uc.uc_flags);
err |= __put_user(NULL, &frame->uc.uc_link);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0]);
+ err |= setup_sigcontext(regs, &frame->uc.uc_mcontext);
err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
@@ -207,9 +194,12 @@
/* trampoline - the desired return ip is the retcode itself */
return_ip = (unsigned long)&frame->retcode;
- /* This is l.ori r11,r0,__NR_sigreturn, l.sys 1 */
- err |= __put_user(0xa960, (short *)(frame->retcode + 0));
- err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2));
+ /* This is:
+ l.ori r11,r0,__NR_sigreturn
+ l.sys 1
+ */
+ err |= __put_user(0xa960, (short *)(frame->retcode + 0));
+ err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2));
err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4));
err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8));
@@ -262,82 +252,106 @@
* mode below.
*/
-void do_signal(struct pt_regs *regs)
+int do_signal(struct pt_regs *regs, int syscall)
{
siginfo_t info;
int signr;
struct k_sigaction ka;
+ unsigned long continue_addr = 0;
+ unsigned long restart_addr = 0;
+ unsigned long retval = 0;
+ int restart = 0;
+
+ if (syscall) {
+ continue_addr = regs->pc;
+ restart_addr = continue_addr - 4;
+ retval = regs->gpr[11];
+
+ /*
+ * Setup syscall restart here so that a debugger will
+ * see the already changed PC.
+ */
+ switch (retval) {
+ case -ERESTART_RESTARTBLOCK:
+ restart = -2;
+ /* Fall through */
+ case -ERESTARTNOHAND:
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ restart++;
+ regs->gpr[11] = regs->orig_gpr11;
+ regs->pc = restart_addr;
+ break;
+ }
+ }
/*
- * We want the common case to go fast, which
- * is why we may in certain cases get here from
- * kernel mode. Just return without doing anything
- * if so.
+ * Get the signal to deliver. When running under ptrace, at this
+ * point the debugger may change all our registers ...
*/
- if (!user_mode(regs))
- return;
-
signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-
- /* If we are coming out of a syscall then we need
- * to check if the syscall was interrupted and wants to be
- * restarted after handling the signal. If so, the original
- * syscall number is put back into r11 and the PC rewound to
- * point at the l.sys instruction that resulted in the
- * original syscall. Syscall results other than the four
- * below mean that the syscall executed to completion and no
- * restart is necessary.
+ /*
+ * Depending on the signal settings we may need to revert the
+ * decision to restart the system call. But skip this if a
+ * debugger has chosen to restart at a different PC.
*/
- if (regs->orig_gpr11) {
- int restart = 0;
-
- switch (regs->gpr[11]) {
- case -ERESTART_RESTARTBLOCK:
- case -ERESTARTNOHAND:
- /* Restart if there is no signal handler */
- restart = (signr <= 0);
- break;
- case -ERESTARTSYS:
- /* Restart if there no signal handler or
- * SA_RESTART flag is set */
- restart = (signr <= 0 || (ka.sa.sa_flags & SA_RESTART));
- break;
- case -ERESTARTNOINTR:
- /* Always restart */
- restart = 1;
- break;
+ if (signr > 0) {
+ if (unlikely(restart) && regs->pc == restart_addr) {
+ if (retval == -ERESTARTNOHAND ||
+ retval == -ERESTART_RESTARTBLOCK
+ || (retval == -ERESTARTSYS
+ && !(ka.sa.sa_flags & SA_RESTART))) {
+ /* No automatic restart */
+ regs->gpr[11] = -EINTR;
+ regs->pc = continue_addr;
+ }
}
- if (restart) {
- if (regs->gpr[11] == -ERESTART_RESTARTBLOCK)
- regs->gpr[11] = __NR_restart_syscall;
- else
- regs->gpr[11] = regs->orig_gpr11;
- regs->pc -= 4;
- } else {
- regs->gpr[11] = -EINTR;
- }
- }
-
- if (signr <= 0) {
- /* no signal to deliver so we just put the saved sigmask
- * back */
- restore_saved_sigmask();
- } else { /* signr > 0 */
- /* Whee! Actually deliver the signal. */
handle_signal(signr, &info, &ka, regs);
+ } else {
+ /* no handler */
+ restore_saved_sigmask();
+ /*
+ * Restore pt_regs PC as syscall restart will be handled by
+ * kernel without return to userspace
+ */
+ if (unlikely(restart) && regs->pc == restart_addr) {
+ regs->pc = continue_addr;
+ return restart;
+ }
}
- return;
+ return 0;
}
-asmlinkage void do_notify_resume(struct pt_regs *regs)
+asmlinkage int
+do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
{
- if (current_thread_info()->flags & _TIF_SIGPENDING)
- do_signal(regs);
-
- if (current_thread_info()->flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
- tracehook_notify_resume(regs);
- }
+ do {
+ if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+ schedule();
+ } else {
+ if (unlikely(!user_mode(regs)))
+ return 0;
+ local_irq_enable();
+ if (thread_flags & _TIF_SIGPENDING) {
+ int restart = do_signal(regs, syscall);
+ if (unlikely(restart)) {
+ /*
+ * Restart without handlers.
+ * Deal with it without leaving
+ * the kernel space.
+ */
+ return restart;
+ }
+ syscall = 0;
+ } else {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ }
+ }
+ local_irq_disable();
+ thread_flags = current_thread_info()->flags;
+ } while (thread_flags & _TIF_WORK_MASK);
+ return 0;
}
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index e2bfafc..230ac20 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -86,6 +86,7 @@
if (user_mode(regs)) {
/* Exception was in userspace: reenable interrupts */
local_irq_enable();
+ flags |= FAULT_FLAG_USER;
} else {
/* If exception was in a syscall, then IRQ's may have
* been enabled or disabled. If they were enabled,
@@ -170,6 +171,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -267,10 +270,10 @@
__asm__ __volatile__("l.nop 1");
up_read(&mm->mmap_sem);
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 96ec398..94607bf 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -46,7 +46,12 @@
# These flags should be implied by an hppa-linux configuration, but they
# are not in gcc 3.2.
-cflags-y += -mno-space-regs -mfast-indirect-calls
+cflags-y += -mno-space-regs
+
+# -mfast-indirect-calls is only relevant for 32-bit kernels.
+ifndef CONFIG_64BIT
+cflags-y += -mfast-indirect-calls
+endif
# Currently we save and restore fpregs on all kernel entry/interruption paths.
# If that gets optimized, we might need to disable the use of fpregs in the
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index f0e2784..de65f66 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -125,15 +125,10 @@
void mark_rodata_ro(void);
#endif
-#ifdef CONFIG_PA8X00
-/* Only pa8800, pa8900 needs this */
-
#include <asm/kmap_types.h>
#define ARCH_HAS_KMAP
-void kunmap_parisc(void *addr);
-
static inline void *kmap(struct page *page)
{
might_sleep();
@@ -142,7 +137,7 @@
static inline void kunmap(struct page *page)
{
- kunmap_parisc(page_address(page));
+ flush_kernel_dcache_page_addr(page_address(page));
}
static inline void *kmap_atomic(struct page *page)
@@ -153,14 +148,13 @@
static inline void __kunmap_atomic(void *addr)
{
- kunmap_parisc(addr);
+ flush_kernel_dcache_page_addr(addr);
pagefault_enable();
}
#define kmap_atomic_prot(page, prot) kmap_atomic(page)
#define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn))
#define kmap_atomic_to_page(ptr) virt_to_page(ptr)
-#endif
#endif /* _PARISC_CACHEFLUSH_H */
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
index 72c0faf..544ed8e 100644
--- a/arch/parisc/include/asm/ftrace.h
+++ b/arch/parisc/include/asm/ftrace.h
@@ -24,15 +24,7 @@
extern unsigned long return_address(unsigned int);
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 return_address(1)
-#define CALLER_ADDR2 return_address(2)
-#define CALLER_ADDR3 return_address(3)
-#define CALLER_ADDR4 return_address(4)
-#define CALLER_ADDR5 return_address(5)
-#define CALLER_ADDR6 return_address(6)
+#define ftrace_return_address(n) return_address(n)
#endif /* __ASSEMBLY__ */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index b7adb2a..637fe03 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -28,9 +28,9 @@
void clear_page_asm(void *page);
void copy_page_asm(void *to, void *from);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *pg);
+#define clear_user_page(vto, vaddr, page) clear_page_asm(vto)
void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
- struct page *pg);
+ struct page *pg);
/* #define CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/include/asm/parisc-device.h b/arch/parisc/include/asm/parisc-device.h
index 9afdad6..eaf4dc1 100644
--- a/arch/parisc/include/asm/parisc-device.h
+++ b/arch/parisc/include/asm/parisc-device.h
@@ -23,6 +23,7 @@
/* generic info returned from pdc_pat_cell_module() */
unsigned long mod_info; /* PAT specific - Misc Module info */
unsigned long pmod_loc; /* physical Module location */
+ unsigned long mod0;
#endif
u64 dma_mask; /* DMA mask for I/O */
struct device dev;
@@ -61,4 +62,6 @@
extern struct bus_type parisc_bus_type;
+int iosapic_serial_irq(struct parisc_device *dev);
+
#endif /*_ASM_PARISC_PARISC_DEVICE_H_*/
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index cc2290a..c6ee865 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -53,6 +53,8 @@
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX DEFAULT_TASK_SIZE
+#define STACK_SIZE_MAX (1 << 30) /* 1 GB */
+
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
new file mode 100644
index 0000000..748016c
--- /dev/null
+++ b/arch/parisc/include/asm/socket.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <uapi/asm/socket.h>
+
+/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
+ * have to define SOCK_NONBLOCK to a different value here.
+ */
+#define SOCK_NONBLOCK 0x40000000
+
+#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/asm/special_insns.h b/arch/parisc/include/asm/special_insns.h
index d306b75..e150930 100644
--- a/arch/parisc/include/asm/special_insns.h
+++ b/arch/parisc/include/asm/special_insns.h
@@ -32,9 +32,12 @@
cr; \
})
-#define mtsp(gr, cr) \
- __asm__ __volatile__("mtsp %0,%1" \
+#define mtsp(val, cr) \
+ { if (__builtin_constant_p(val) && ((val) == 0)) \
+ __asm__ __volatile__("mtsp %%r0,%0" : : "i" (cr) : "memory"); \
+ else \
+ __asm__ __volatile__("mtsp %0,%1" \
: /* no outputs */ \
- : "r" (gr), "i" (cr) : "memory")
+ : "r" (val), "i" (cr) : "memory"); }
#endif /* __PARISC_SPECIAL_INSNS_H */
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
index 5273da9..9d086a5 100644
--- a/arch/parisc/include/asm/tlbflush.h
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -63,13 +63,14 @@
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long addr)
{
- unsigned long flags;
+ unsigned long flags, sid;
/* For one page, it's not worth testing the split_tlb variable */
mb();
- mtsp(vma->vm_mm->context,1);
+ sid = vma->vm_mm->context;
purge_tlb_start(flags);
+ mtsp(sid, 1);
pdtlb(addr);
pitlb(addr);
purge_tlb_end(flags);
diff --git a/arch/parisc/include/uapi/asm/shmbuf.h b/arch/parisc/include/uapi/asm/shmbuf.h
index 0a3eada..f395cde 100644
--- a/arch/parisc/include/uapi/asm/shmbuf.h
+++ b/arch/parisc/include/uapi/asm/shmbuf.h
@@ -36,23 +36,16 @@
unsigned int __unused2;
};
-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
struct shminfo64 {
- unsigned int shmmax;
- unsigned int shmmin;
- unsigned int shmmni;
- unsigned int shmseg;
- unsigned int shmall;
- unsigned int __unused1;
- unsigned int __unused2;
- unsigned int __unused3;
- unsigned int __unused4;
+ unsigned long shmmax;
+ unsigned long shmmin;
+ unsigned long shmmni;
+ unsigned long shmseg;
+ unsigned long shmall;
+ unsigned long __unused1;
+ unsigned long __unused2;
+ unsigned long __unused3;
+ unsigned long __unused4;
};
#endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index a2fa2971..f5645d6 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -69,8 +69,6 @@
#define SA_NOMASK SA_NODEFER
#define SA_ONESHOT SA_RESETHAND
-#define SA_RESTORER 0x04000000 /* obsolete -- ignored */
-
#define MINSIGSTKSZ 2048
#define SIGSTKSZ 8192
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 70c512a..4fecb26 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
+#ifndef _UAPI_ASM_SOCKET_H
+#define _UAPI_ASM_SOCKET_H
#include <asm/sockios.h>
@@ -73,9 +73,4 @@
#define SO_SELECT_ERR_QUEUE 0x4026
-/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
- * have to define SOCK_NONBLOCK to a different value here.
- */
-#define SOCK_NONBLOCK 0x40000000
-
-#endif /* _ASM_SOCKET_H */
+#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 65fb4cb..ac87a40 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -71,18 +71,27 @@
}
EXPORT_SYMBOL(flush_cache_all_local);
+/* Virtual address of pfn. */
+#define pfn_va(pfn) __va(PFN_PHYS(pfn))
+
void
update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
{
- struct page *page = pte_page(*ptep);
+ unsigned long pfn = pte_pfn(*ptep);
+ struct page *page;
- if (pfn_valid(page_to_pfn(page)) && page_mapping(page) &&
- test_bit(PG_dcache_dirty, &page->flags)) {
+ /* We don't have pte special. As a result, we can be called with
+ an invalid pfn and we don't need to flush the kernel dcache page.
+ This occurs with FireGL card in C8000. */
+ if (!pfn_valid(pfn))
+ return;
- flush_kernel_dcache_page(page);
+ page = pfn_to_page(pfn);
+ if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) {
+ flush_kernel_dcache_page_addr(pfn_va(pfn));
clear_bit(PG_dcache_dirty, &page->flags);
} else if (parisc_requires_coherency())
- flush_kernel_dcache_page(page);
+ flush_kernel_dcache_page_addr(pfn_va(pfn));
}
void
@@ -379,41 +388,20 @@
}
EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *page)
-{
- clear_page_asm(vto);
- if (!parisc_requires_coherency())
- flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(clear_user_page);
-
void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
struct page *pg)
{
- /* Copy using kernel mapping. No coherency is needed
- (all in kmap/kunmap) on machines that don't support
- non-equivalent aliasing. However, the `from' page
- needs to be flushed before it can be accessed through
- the kernel mapping. */
+ /* Copy using kernel mapping. No coherency is needed (all in
+ kunmap) for the `to' page. However, the `from' page needs to
+ be flushed through a mapping equivalent to the user mapping
+ before it can be accessed through the kernel mapping. */
preempt_disable();
flush_dcache_page_asm(__pa(vfrom), vaddr);
preempt_enable();
copy_page_asm(vto, vfrom);
- if (!parisc_requires_coherency())
- flush_kernel_dcache_page_asm(vto);
}
EXPORT_SYMBOL(copy_user_page);
-#ifdef CONFIG_PA8X00
-
-void kunmap_parisc(void *addr)
-{
- if (parisc_requires_coherency())
- flush_kernel_dcache_page_addr(addr);
-}
-EXPORT_SYMBOL(kunmap_parisc);
-#endif
-
void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
{
unsigned long flags;
@@ -440,8 +428,8 @@
else {
unsigned long flags;
- mtsp(sid, 1);
purge_tlb_start(flags);
+ mtsp(sid, 1);
if (split_tlb) {
while (npages--) {
pdtlb(start);
@@ -495,44 +483,42 @@
void flush_cache_mm(struct mm_struct *mm)
{
+ struct vm_area_struct *vma;
+ pgd_t *pgd;
+
/* Flushing the whole cache on each cpu takes forever on
rp3440, etc. So, avoid it if the mm isn't too big. */
- if (mm_total_size(mm) < parisc_cache_flush_threshold) {
- struct vm_area_struct *vma;
+ if (mm_total_size(mm) >= parisc_cache_flush_threshold) {
+ flush_cache_all();
+ return;
+ }
- if (mm->context == mfsp(3)) {
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- flush_user_dcache_range_asm(vma->vm_start,
- vma->vm_end);
- if (vma->vm_flags & VM_EXEC)
- flush_user_icache_range_asm(
- vma->vm_start, vma->vm_end);
- }
- } else {
- pgd_t *pgd = mm->pgd;
-
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- unsigned long addr;
-
- for (addr = vma->vm_start; addr < vma->vm_end;
- addr += PAGE_SIZE) {
- pte_t *ptep = get_ptep(pgd, addr);
- if (ptep != NULL) {
- pte_t pte = *ptep;
- __flush_cache_page(vma, addr,
- page_to_phys(pte_page(pte)));
- }
- }
- }
+ if (mm->context == mfsp(3)) {
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ flush_user_dcache_range_asm(vma->vm_start, vma->vm_end);
+ if ((vma->vm_flags & VM_EXEC) == 0)
+ continue;
+ flush_user_icache_range_asm(vma->vm_start, vma->vm_end);
}
return;
}
-#ifdef CONFIG_SMP
- flush_cache_all();
-#else
- flush_cache_all_local();
-#endif
+ pgd = mm->pgd;
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ unsigned long addr;
+
+ for (addr = vma->vm_start; addr < vma->vm_end;
+ addr += PAGE_SIZE) {
+ unsigned long pfn;
+ pte_t *ptep = get_ptep(pgd, addr);
+ if (!ptep)
+ continue;
+ pfn = pte_pfn(*ptep);
+ if (!pfn_valid(pfn))
+ continue;
+ __flush_cache_page(vma, addr, PFN_PHYS(pfn));
+ }
+ }
}
void
@@ -556,33 +542,32 @@
void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
+ unsigned long addr;
+ pgd_t *pgd;
+
BUG_ON(!vma->vm_mm->context);
- if ((end - start) < parisc_cache_flush_threshold) {
- if (vma->vm_mm->context == mfsp(3)) {
- flush_user_dcache_range_asm(start, end);
- if (vma->vm_flags & VM_EXEC)
- flush_user_icache_range_asm(start, end);
- } else {
- unsigned long addr;
- pgd_t *pgd = vma->vm_mm->pgd;
-
- for (addr = start & PAGE_MASK; addr < end;
- addr += PAGE_SIZE) {
- pte_t *ptep = get_ptep(pgd, addr);
- if (ptep != NULL) {
- pte_t pte = *ptep;
- flush_cache_page(vma,
- addr, pte_pfn(pte));
- }
- }
- }
- } else {
-#ifdef CONFIG_SMP
+ if ((end - start) >= parisc_cache_flush_threshold) {
flush_cache_all();
-#else
- flush_cache_all_local();
-#endif
+ return;
+ }
+
+ if (vma->vm_mm->context == mfsp(3)) {
+ flush_user_dcache_range_asm(start, end);
+ if (vma->vm_flags & VM_EXEC)
+ flush_user_icache_range_asm(start, end);
+ return;
+ }
+
+ pgd = vma->vm_mm->pgd;
+ for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+ unsigned long pfn;
+ pte_t *ptep = get_ptep(pgd, addr);
+ if (!ptep)
+ continue;
+ pfn = pte_pfn(*ptep);
+ if (pfn_valid(pfn))
+ __flush_cache_page(vma, addr, PFN_PHYS(pfn));
}
}
@@ -591,9 +576,10 @@
{
BUG_ON(!vma->vm_mm->context);
- flush_tlb_page(vma, vmaddr);
- __flush_cache_page(vma, vmaddr, page_to_phys(pfn_to_page(pfn)));
-
+ if (pfn_valid(pfn)) {
+ flush_tlb_page(vma, vmaddr);
+ __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+ }
}
#ifdef CONFIG_PARISC_TMPALIAS
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 8722756..c22c3d8 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1205,7 +1205,8 @@
{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"},
{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"},
{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"},
- {HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
+ {HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"},
+ {HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"},
{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"},
{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"},
{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"},
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index 37aabd7..d2d5825 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -195,6 +195,8 @@
ldw MEM_PDC_HI(%r0),%r6
depd %r6, 31, 32, %r3 /* move to upper word */
+ mfctl %cr30,%r6 /* PCX-W2 firmware bug */
+
ldo PDC_PSW(%r0),%arg0 /* 21 */
ldo PDC_PSW_SET_DEFAULTS(%r0),%arg1 /* 2 */
ldo PDC_PSW_WIDE_BIT(%r0),%arg2 /* 2 */
@@ -203,6 +205,8 @@
copy %r0,%arg3
stext_pdc_ret:
+ mtctl %r6,%cr30 /* restore task thread info */
+
/* restore rfi target address*/
ldd TI_TASK-THREAD_SZ_ALGN(%sp), %r10
tophys_r1 %r10
diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c
index 3295ef4..f0b6722 100644
--- a/arch/parisc/kernel/inventory.c
+++ b/arch/parisc/kernel/inventory.c
@@ -211,6 +211,7 @@
/* REVISIT: who is the consumer of this? not sure yet... */
dev->mod_info = pa_pdc_cell->mod_info; /* pass to PAT_GET_ENTITY() */
dev->pmod_loc = pa_pdc_cell->mod_location;
+ dev->mod0 = pa_pdc_cell->mod[0];
register_parisc_device(dev); /* advertise device */
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 5dfd248..0d3a9d4 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -61,8 +61,15 @@
return (unsigned long) mapping >> 8;
}
-static unsigned long get_shared_area(struct address_space *mapping,
- unsigned long addr, unsigned long len, unsigned long pgoff)
+static unsigned long shared_align_offset(struct file *filp, unsigned long pgoff)
+{
+ struct address_space *mapping = filp ? filp->f_mapping : NULL;
+
+ return (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+}
+
+static unsigned long get_shared_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff)
{
struct vm_unmapped_area_info info;
@@ -71,7 +78,7 @@
info.low_limit = PAGE_ALIGN(addr);
info.high_limit = TASK_SIZE;
info.align_mask = PAGE_MASK & (SHMLBA - 1);
- info.align_offset = (get_offset(mapping) + pgoff) << PAGE_SHIFT;
+ info.align_offset = shared_align_offset(filp, pgoff);
return vm_unmapped_area(&info);
}
@@ -82,20 +89,18 @@
return -ENOMEM;
if (flags & MAP_FIXED) {
if ((flags & MAP_SHARED) &&
- (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
+ (addr - shared_align_offset(filp, pgoff)) & (SHMLBA - 1))
return -EINVAL;
return addr;
}
if (!addr)
addr = TASK_UNMAPPED_BASE;
- if (filp) {
- addr = get_shared_area(filp->f_mapping, addr, len, pgoff);
- } else if(flags & MAP_SHARED) {
- addr = get_shared_area(NULL, addr, len, pgoff);
- } else {
+ if (filp || (flags & MAP_SHARED))
+ addr = get_shared_area(filp, addr, len, pgoff);
+ else
addr = get_unshared_area(addr, len);
- }
+
return addr;
}
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 0c91072..b24732d 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -286,11 +286,11 @@
ENTRY_COMP(msgsnd)
ENTRY_COMP(msgrcv)
ENTRY_SAME(msgget) /* 190 */
- ENTRY_SAME(msgctl)
- ENTRY_SAME(shmat)
+ ENTRY_COMP(msgctl)
+ ENTRY_COMP(shmat)
ENTRY_SAME(shmdt)
ENTRY_SAME(shmget)
- ENTRY_SAME(shmctl) /* 195 */
+ ENTRY_COMP(shmctl) /* 195 */
ENTRY_SAME(ni_syscall) /* streams1 */
ENTRY_SAME(ni_syscall) /* streams2 */
ENTRY_SAME(lstat64)
@@ -323,7 +323,7 @@
ENTRY_SAME(epoll_ctl) /* 225 */
ENTRY_SAME(epoll_wait)
ENTRY_SAME(remap_file_pages)
- ENTRY_SAME(semtimedop)
+ ENTRY_COMP(semtimedop)
ENTRY_COMP(mq_open)
ENTRY_SAME(mq_unlink) /* 230 */
ENTRY_COMP(mq_timedsend)
@@ -392,7 +392,7 @@
ENTRY_COMP(vmsplice)
ENTRY_COMP(move_pages) /* 295 */
ENTRY_SAME(getcpu)
- ENTRY_SAME(epoll_pwait)
+ ENTRY_COMP(epoll_pwait)
ENTRY_COMP(statfs64)
ENTRY_COMP(fstatfs64)
ENTRY_COMP(kexec_load) /* 300 */
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 04e47c6..b3f87a3 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -805,14 +805,14 @@
else {
/*
- * The kernel should never fault on its own address space.
+ * The kernel should never fault on its own address space,
+ * unless pagefault_disable() was called before.
*/
- if (fault_space == 0)
+ if (fault_space == 0 && !in_atomic())
{
pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC);
parisc_terminate("Kernel Fault", regs, code, fault_address);
-
}
}
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index a49cc81..ac4370b 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -2,6 +2,7 @@
* Optimized memory copy routines.
*
* Copyright (C) 2004 Randolph Chung <tausq@debian.org>
+ * Copyright (C) 2013 Helge Deller <deller@gmx.de>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -153,17 +154,21 @@
#define prefetch_dst(addr) do { } while(0)
#endif
+#define PA_MEMCPY_OK 0
+#define PA_MEMCPY_LOAD_ERROR 1
+#define PA_MEMCPY_STORE_ERROR 2
+
/* Copy from a not-aligned src to an aligned dst, using shifts. Handles 4 words
* per loop. This code is derived from glibc.
*/
-static inline unsigned long copy_dstaligned(unsigned long dst, unsigned long src, unsigned long len, unsigned long o_dst, unsigned long o_src, unsigned long o_len)
+static inline unsigned long copy_dstaligned(unsigned long dst,
+ unsigned long src, unsigned long len)
{
/* gcc complains that a2 and a3 may be uninitialized, but actually
* they cannot be. Initialize a2/a3 to shut gcc up.
*/
register unsigned int a0, a1, a2 = 0, a3 = 0;
int sh_1, sh_2;
- struct exception_data *d;
/* prefetch_src((const void *)src); */
@@ -197,7 +202,7 @@
goto do2;
case 0:
if (len == 0)
- return 0;
+ return PA_MEMCPY_OK;
/* a3 = ((unsigned int *) src)[0];
a0 = ((unsigned int *) src)[1]; */
ldw(s_space, 0, src, a3, cda_ldw_exc);
@@ -256,42 +261,35 @@
preserve_branch(handle_load_error);
preserve_branch(handle_store_error);
- return 0;
+ return PA_MEMCPY_OK;
handle_load_error:
__asm__ __volatile__ ("cda_ldw_exc:\n");
- d = &__get_cpu_var(exception_data);
- DPRINTF("cda_ldw_exc: o_len=%lu fault_addr=%lu o_src=%lu ret=%lu\n",
- o_len, d->fault_addr, o_src, o_len - d->fault_addr + o_src);
- return o_len * 4 - d->fault_addr + o_src;
+ return PA_MEMCPY_LOAD_ERROR;
handle_store_error:
__asm__ __volatile__ ("cda_stw_exc:\n");
- d = &__get_cpu_var(exception_data);
- DPRINTF("cda_stw_exc: o_len=%lu fault_addr=%lu o_dst=%lu ret=%lu\n",
- o_len, d->fault_addr, o_dst, o_len - d->fault_addr + o_dst);
- return o_len * 4 - d->fault_addr + o_dst;
+ return PA_MEMCPY_STORE_ERROR;
}
-/* Returns 0 for success, otherwise, returns number of bytes not transferred. */
-static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
+/* Returns PA_MEMCPY_OK, PA_MEMCPY_LOAD_ERROR or PA_MEMCPY_STORE_ERROR.
+ * In case of an access fault the faulty address can be read from the per_cpu
+ * exception data struct. */
+static unsigned long pa_memcpy_internal(void *dstp, const void *srcp,
+ unsigned long len)
{
register unsigned long src, dst, t1, t2, t3;
register unsigned char *pcs, *pcd;
register unsigned int *pws, *pwd;
register double *pds, *pdd;
- unsigned long ret = 0;
- unsigned long o_dst, o_src, o_len;
- struct exception_data *d;
+ unsigned long ret;
src = (unsigned long)srcp;
dst = (unsigned long)dstp;
pcs = (unsigned char *)srcp;
pcd = (unsigned char *)dstp;
- o_dst = dst; o_src = src; o_len = len;
-
/* prefetch_src((const void *)srcp); */
if (len < THRESHOLD)
@@ -401,7 +399,7 @@
len--;
}
- return 0;
+ return PA_MEMCPY_OK;
unaligned_copy:
/* possibly we are aligned on a word, but not on a double... */
@@ -438,8 +436,7 @@
src = (unsigned long)pcs;
}
- ret = copy_dstaligned(dst, src, len / sizeof(unsigned int),
- o_dst, o_src, o_len);
+ ret = copy_dstaligned(dst, src, len / sizeof(unsigned int));
if (ret)
return ret;
@@ -454,17 +451,41 @@
handle_load_error:
__asm__ __volatile__ ("pmc_load_exc:\n");
- d = &__get_cpu_var(exception_data);
- DPRINTF("pmc_load_exc: o_len=%lu fault_addr=%lu o_src=%lu ret=%lu\n",
- o_len, d->fault_addr, o_src, o_len - d->fault_addr + o_src);
- return o_len - d->fault_addr + o_src;
+ return PA_MEMCPY_LOAD_ERROR;
handle_store_error:
__asm__ __volatile__ ("pmc_store_exc:\n");
+ return PA_MEMCPY_STORE_ERROR;
+}
+
+
+/* Returns 0 for success, otherwise, returns number of bytes not transferred. */
+static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
+{
+ unsigned long ret, fault_addr, reference;
+ struct exception_data *d;
+
+ ret = pa_memcpy_internal(dstp, srcp, len);
+ if (likely(ret == PA_MEMCPY_OK))
+ return 0;
+
+ /* if a load or store fault occured we can get the faulty addr */
d = &__get_cpu_var(exception_data);
- DPRINTF("pmc_store_exc: o_len=%lu fault_addr=%lu o_dst=%lu ret=%lu\n",
- o_len, d->fault_addr, o_dst, o_len - d->fault_addr + o_dst);
- return o_len - d->fault_addr + o_dst;
+ fault_addr = d->fault_addr;
+
+ /* error in load or store? */
+ if (ret == PA_MEMCPY_LOAD_ERROR)
+ reference = (unsigned long) srcp;
+ else
+ reference = (unsigned long) dstp;
+
+ DPRINTF("pa_memcpy: fault type = %lu, len=%lu fault_addr=%lu ref=%lu\n",
+ ret, len, fault_addr, reference);
+
+ if (fault_addr >= reference)
+ return len - (fault_addr - reference);
+ else
+ return len;
}
#ifdef __KERNEL__
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index f247a34..c45130f5 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -180,6 +180,10 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (acc_type & VM_WRITE)
+ flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
vma = find_vma_prev(mm, address, &prev_vma);
@@ -203,8 +207,7 @@
* fault.
*/
- fault = handle_mm_fault(mm, vma, address,
- flags | ((acc_type & VM_WRITE) ? FAULT_FLAG_WRITE : 0));
+ fault = handle_mm_fault(mm, vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
@@ -217,6 +220,8 @@
*/
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto bad_area;
BUG();
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c33e3ad..61f1aed 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -126,6 +126,7 @@
select HAVE_BPF_JIT if PPC64
select HAVE_ARCH_JUMP_LABEL
select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select ARCH_HAS_GCOV_PROFILE_ALL
select GENERIC_SMP_IDLE_THREAD
select GENERIC_CMOS_UPDATE
select GENERIC_TIME_VSYSCALL_OLD
@@ -138,6 +139,7 @@
select ARCH_USE_BUILTIN_BSWAP
select OLD_SIGSUSPEND
select OLD_SIGACTION if PPC32
+ select ARCH_SUPPORTS_ATOMIC_RMW
config EARLY_PRINTK
bool
@@ -572,7 +574,7 @@
config PPC_DENORMALISATION
bool "PowerPC denormalisation exception handling"
depends on PPC_BOOK3S_64
- default "n"
+ default "y" if PPC_POWERNV
---help---
Add support for handling denormalisation of single precision
values. Useful for bare metal only. If unsure say Y here.
@@ -986,6 +988,7 @@
must live at a different physical address than the primary
kernel.
+# This value must have zeroes in the bottom 60 bits otherwise lots will break
config PAGE_OFFSET
hex
default "0xc000000000000000"
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 967fd23..56a4a5d 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -97,7 +97,9 @@
CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
-KBUILD_CPPFLAGS += -Iarch/$(ARCH)
+asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
+
+KBUILD_CPPFLAGS += -Iarch/$(ARCH) $(asinstr)
KBUILD_AFLAGS += -Iarch/$(ARCH)
KBUILD_CFLAGS += -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
CPP = $(CC) -E $(KBUILD_CFLAGS)
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
index 1382fec..7fcb1ac 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-0.dtsi
@@ -50,6 +50,7 @@
fsl,num_tx_queues = <0x8>;
fsl,magic-packet;
local-mac-address = [ 00 00 00 00 00 00 ];
+ ranges;
queue-group@b0000 {
#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
index 221cd2e..9f25427 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-1.dtsi
@@ -50,6 +50,7 @@
fsl,num_tx_queues = <0x8>;
fsl,magic-packet;
local-mac-address = [ 00 00 00 00 00 00 ];
+ ranges;
queue-group@b1000 {
#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
index 61456c3..cd7c318 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec2-2.dtsi
@@ -49,6 +49,7 @@
fsl,num_tx_queues = <0x8>;
fsl,magic-packet;
local-mac-address = [ 00 00 00 00 00 00 ];
+ ranges;
queue-group@b2000 {
#address-cells = <1>;
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index f9e8b94..b51da91 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -154,4 +154,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
-MODULE_ALIAS("sha1-powerpc");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-powerpc");
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf68..ef22898 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
#include <linux/sched.h>
#define COMPAT_USER_HZ 100
+#ifdef __BIG_ENDIAN__
#define COMPAT_UTS_MACHINE "ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE "ppcle\0\0"
+#endif
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 46793b5..e17d94d 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -264,7 +264,7 @@
subi r1,r1,INT_FRAME_SIZE; /* alloc frame on kernel stack */ \
beq- 1f; \
ld r1,PACAKSAVE(r13); /* kernel stack to use */ \
-1: cmpdi cr1,r1,0; /* check if r1 is in userspace */ \
+1: cmpdi cr1,r1,-INT_FRAME_SIZE; /* check if r1 is in userspace */ \
blt+ cr1,3f; /* abort if it is */ \
li r1,(n); /* will be reloaded later */ \
sth r1,PACA_TRAP_SAVE(r13); \
@@ -358,12 +358,12 @@
/* No guest interrupts come through here */ \
SET_SCRATCH0(r13); /* save r13 */ \
EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
- EXC_STD, KVMTEST_PR, vec)
+ EXC_STD, NOTEST, vec)
#define STD_RELON_EXCEPTION_PSERIES_OOL(vec, label) \
.globl label##_relon_pSeries; \
label##_relon_pSeries: \
- EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, vec); \
+ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \
EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_STD)
#define STD_RELON_EXCEPTION_HV(loc, vec, label) \
@@ -374,12 +374,12 @@
/* No guest interrupts come through here */ \
SET_SCRATCH0(r13); /* save r13 */ \
EXCEPTION_RELON_PROLOG_PSERIES(PACA_EXGEN, label##_common, \
- EXC_HV, KVMTEST, vec)
+ EXC_HV, NOTEST, vec)
#define STD_RELON_EXCEPTION_HV_OOL(vec, label) \
.globl label##_relon_hv; \
label##_relon_hv: \
- EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, vec); \
+ EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, vec); \
EXCEPTION_RELON_PROLOG_PSERIES_1(label##_common, EXC_HV)
/* This associate vector numbers with bits in paca->irq_happened */
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index ae098c4..f016bb6 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -19,7 +19,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:\n\t"
+ asm_volatile_goto("1:\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
JUMP_ENTRY_TYPE "1b, %l[l_yes], %c0\n\t"
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cd..f391f3f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -53,7 +53,6 @@
#define KVM_ARCH_WANT_MMU_NOTIFIER
-struct kvm;
extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
extern int kvm_unmap_hva_range(struct kvm *kvm,
unsigned long start, unsigned long end);
@@ -81,10 +80,6 @@
/* Physical Address Mask - allowed range of real mode RAM access */
#define KVM_PAM 0x0fffffffffffffffULL
-struct kvm;
-struct kvm_run;
-struct kvm_vcpu;
-
struct lppaca;
struct slb_shadow;
struct dtl_entry;
@@ -628,4 +623,12 @@
#define __KVM_HAVE_ARCH_WQP
#define __KVM_HAVE_CREATE_DEVICE
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_exit(void) {}
+
#endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe..e2dd05c 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -143,9 +143,11 @@
extern void kvm_release_hpt(struct kvmppc_linear_info *li);
extern int kvmppc_core_init_vm(struct kvm *kvm);
extern void kvmppc_core_destroy_vm(struct kvm *kvm);
-extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+extern void kvmppc_core_free_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
-extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+extern int kvmppc_core_create_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
unsigned long npages);
extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index c1df590..49fa55b 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -82,10 +82,9 @@
void sort_ex_table(struct exception_table_entry *start,
struct exception_table_entry *finish);
-#ifdef CONFIG_MODVERSIONS
+#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64)
#define ARCH_RELOCATES_KCRCTAB
-
-extern const unsigned long reloc_start[];
+#define reloc_start PHYSICAL_START
#endif
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 988c812..b9f4262 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -211,9 +211,19 @@
#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET))
#define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET)
#else
+#ifdef CONFIG_PPC64
+/*
+ * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET
+ * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit.
+ */
+#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET))
+#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL)
+
+#else /* 32-bit, non book E */
#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START))
#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START)
#endif
+#endif
/*
* Unfortunately the PLT is in the BSS in the PPC32 ELF ABI,
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index f265049..960bf64 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -59,7 +59,7 @@
#define PPMU_SIAR_VALID 0x00000010 /* Processor has SIAR Valid bit */
#define PPMU_HAS_SSLOT 0x00000020 /* Has sampled slot in MMCRA */
#define PPMU_HAS_SIER 0x00000040 /* Has SIER */
-#define PPMU_BHRB 0x00000080 /* has BHRB feature enabled */
+#define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */
/*
* Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 27b2386..842846c 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -84,10 +84,8 @@
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- struct page *page = page_address(table);
-
tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(page);
- pgtable_free_tlb(tlb, page, 0);
+ pgtable_page_dtor(table);
+ pgtable_free_tlb(tlb, page_address(table), 0);
}
#endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index b66ae72..64aaf01 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -144,11 +144,9 @@
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
- struct page *page = page_address(table);
-
tlb_flush_pgtable(tlb, address);
- pgtable_page_dtor(page);
- pgtable_free_tlb(tlb, page, 0);
+ pgtable_page_dtor(table);
+ pgtable_free_tlb(tlb, page_address(table), 0);
}
#else /* if CONFIG_PPC_64K_PAGES */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 2f1b6c5..22cee04 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -390,11 +390,16 @@
* ld rY,ADDROFF(name)(rX)
*/
#ifdef __powerpc64__
+#ifdef HAVE_AS_ATHIGH
+#define __AS_ATHIGH high
+#else
+#define __AS_ATHIGH h
+#endif
#define LOAD_REG_IMMEDIATE(reg,expr) \
lis reg,(expr)@highest; \
ori reg,reg,(expr)@higher; \
rldicr reg,reg,32,31; \
- oris reg,reg,(expr)@h; \
+ oris reg,reg,(expr)@__AS_ATHIGH; \
ori reg,reg,(expr)@l;
#define LOAD_REG_ADDR(reg,name) \
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 14a6583..419e712 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -247,6 +247,10 @@
unsigned long tm_orig_msr; /* Thread's MSR on ctx switch */
struct pt_regs ckpt_regs; /* Checkpointed registers */
+ unsigned long tm_tar;
+ unsigned long tm_ppr;
+ unsigned long tm_dscr;
+
/*
* Transactional FP and VSX 0-31 register set.
* NOTE: the sense of these is the opposite of the integer ckpt_regs!
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index bc2da15..ac204e0 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -43,9 +43,6 @@
extern void kdump_move_device_tree(void);
-/* CPU OF node matching */
-struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
-
/* cache lookup */
struct device_node *of_find_next_cache_node(struct device_node *np);
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index d836d94..063fcad 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -40,17 +40,39 @@
#ifndef __ASSEMBLY__
+#include <asm/barrier.h> /* for smp_rmb() */
+
/*
* With 64K pages on hash table, we have a special PTE format that
* uses a second "half" of the page table to encode sub-page information
* in order to deal with 64K made of 4K HW pages. Thus we override the
* generic accessors and iterators here
*/
-#define __real_pte(e,p) ((real_pte_t) { \
- (e), (pte_val(e) & _PAGE_COMBO) ? \
- (pte_val(*((p) + PTRS_PER_PTE))) : 0 })
-#define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \
- (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf))
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+{
+ real_pte_t rpte;
+
+ rpte.pte = pte;
+ rpte.hidx = 0;
+ if (pte_val(pte) & _PAGE_COMBO) {
+ /*
+ * Make sure we order the hidx load against the _PAGE_COMBO
+ * check. The store side ordering is done in __hash_page_4K
+ */
+ smp_rmb();
+ rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE));
+ }
+ return rpte;
+}
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+ if ((pte_val(rpte.pte) & _PAGE_COMBO))
+ return (rpte.hidx >> (index<<2)) & 0xf;
+ return (pte_val(rpte.pte) >> 12) & 0xf;
+}
+
#define __rpte_to_pte(r) ((r).pte)
#define __rpte_sub_valid(rpte, index) \
(pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index)))
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e..637c97f 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -35,6 +35,12 @@
STACK_FRAME_OVERHEAD + 288)
#define STACK_FRAME_MARKER 12
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE 32
+#else
+#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD
+#endif
+
/* Size of dummy stack frame allocated when calling signal handler. */
#define __SIGNAL_FRAMESIZE 128
#define __SIGNAL_FRAMESIZE32 64
@@ -46,6 +52,7 @@
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773)
#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
#define STACK_FRAME_MARKER 2
+#define STACK_FRAME_MIN_SIZE STACK_FRAME_OVERHEAD
/* Size of stack frame allocated when calling signal handler. */
#define __SIGNAL_FRAMESIZE 64
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4a9e408..795f677 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -208,6 +208,7 @@
#define SPRN_ACOP 0x1F /* Available Coprocessor Register */
#define SPRN_TFIAR 0x81 /* Transaction Failure Inst Addr */
#define SPRN_TEXASR 0x82 /* Transaction EXception & Summary */
+#define TEXASR_FS __MASK(63-36) /* Transaction Failure Summary */
#define SPRN_TEXASRU 0x83 /* '' '' '' Upper 32 */
#define SPRN_TFHAR 0x80 /* Transaction Failure Handler Addr */
#define SPRN_CTRLF 0x088
@@ -254,19 +255,28 @@
#define SPRN_HRMOR 0x139 /* Real mode offset register */
#define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */
#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */
+/* HFSCR and FSCR bit numbers are the same */
+#define FSCR_TAR_LG 8 /* Enable Target Address Register */
+#define FSCR_EBB_LG 7 /* Enable Event Based Branching */
+#define FSCR_TM_LG 5 /* Enable Transactional Memory */
+#define FSCR_PM_LG 4 /* Enable prob/priv access to PMU SPRs */
+#define FSCR_BHRB_LG 3 /* Enable Branch History Rolling Buffer*/
+#define FSCR_DSCR_LG 2 /* Enable Data Stream Control Register */
+#define FSCR_VECVSX_LG 1 /* Enable VMX/VSX */
+#define FSCR_FP_LG 0 /* Enable Floating Point */
#define SPRN_FSCR 0x099 /* Facility Status & Control Register */
-#define FSCR_TAR (1 << (63-55)) /* Enable Target Address Register */
-#define FSCR_EBB (1 << (63-56)) /* Enable Event Based Branching */
-#define FSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */
+#define FSCR_TAR __MASK(FSCR_TAR_LG)
+#define FSCR_EBB __MASK(FSCR_EBB_LG)
+#define FSCR_DSCR __MASK(FSCR_DSCR_LG)
#define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */
-#define HFSCR_TAR (1 << (63-55)) /* Enable Target Address Register */
-#define HFSCR_EBB (1 << (63-56)) /* Enable Event Based Branching */
-#define HFSCR_TM (1 << (63-58)) /* Enable Transactional Memory */
-#define HFSCR_PM (1 << (63-60)) /* Enable prob/priv access to PMU SPRs */
-#define HFSCR_BHRB (1 << (63-59)) /* Enable Branch History Rolling Buffer*/
-#define HFSCR_DSCR (1 << (63-61)) /* Enable Data Stream Control Register */
-#define HFSCR_VECVSX (1 << (63-62)) /* Enable VMX/VSX */
-#define HFSCR_FP (1 << (63-63)) /* Enable Floating Point */
+#define HFSCR_TAR __MASK(FSCR_TAR_LG)
+#define HFSCR_EBB __MASK(FSCR_EBB_LG)
+#define HFSCR_TM __MASK(FSCR_TM_LG)
+#define HFSCR_PM __MASK(FSCR_PM_LG)
+#define HFSCR_BHRB __MASK(FSCR_BHRB_LG)
+#define HFSCR_DSCR __MASK(FSCR_DSCR_LG)
+#define HFSCR_VECVSX __MASK(FSCR_VECVSX_LG)
+#define HFSCR_FP __MASK(FSCR_FP_LG)
#define SPRN_TAR 0x32f /* Target Address Register */
#define SPRN_LPCR 0x13E /* LPAR Control Register */
#define LPCR_VPM0 (1ul << (63-0))
@@ -626,6 +636,7 @@
#define MMCR0_TRIGGER 0x00002000UL /* TRIGGER enable */
#define MMCR0_PMAO 0x00000080UL /* performance monitor alert has occurred, set to 0 after handling exception */
#define MMCR0_SHRFC 0x00000040UL /* SHRre freeze conditions between threads */
+#define MMCR0_FC56 0x00000010UL /* freeze counters 5 and 6 */
#define MMCR0_FCTI 0x00000008UL /* freeze counters in tags inactive mode */
#define MMCR0_FCTA 0x00000004UL /* freeze counters in tags active mode */
#define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ffbaabe..48cfc85 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -145,6 +145,10 @@
#define smp_setup_cpu_maps()
static inline void inhibit_secondary_onlining(void) {}
static inline void uninhibit_secondary_onlining(void) {}
+static inline const struct cpumask *cpu_sibling_mask(int cpu)
+{
+ return cpumask_of(cpu);
+}
#endif /* CONFIG_SMP */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 200d763..685ecc8 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -15,6 +15,15 @@
struct thread_struct;
extern struct task_struct *_switch(struct thread_struct *prev,
struct thread_struct *next);
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void save_tar(struct thread_struct *prev)
+{
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ prev->tar = mfspr(SPRN_TAR);
+}
+#else
+static inline void save_tar(struct thread_struct *prev) {}
+#endif
extern void giveup_fpu(struct task_struct *);
extern void load_up_fpu(void);
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 43523fe..05fcdd8 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -190,7 +190,7 @@
SYSCALL_SPU(capget)
SYSCALL_SPU(capset)
COMPAT_SYS(sigaltstack)
-COMPAT_SYS_SPU(sendfile)
+SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
SYSCALL(ni_syscall)
SYSCALL(ni_syscall)
PPC_SYS(vfork)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 161ab66..884b001 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -22,7 +22,15 @@
static inline int cpu_to_node(int cpu)
{
- return numa_cpu_lookup_table[cpu];
+ int nid;
+
+ nid = numa_cpu_lookup_table[cpu];
+
+ /*
+ * During early boot, the numa-cpu lookup table might not have been
+ * setup for all CPUs yet. In such cases, default to node 0.
+ */
+ return (nid < 0) ? 0 : nid;
}
#define parent_node(node) (node)
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 5b76579..de2c0e4 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -41,5 +41,6 @@
#define PPC_FEATURE2_EBB 0x10000000
#define PPC_FEATURE2_ISEL 0x08000000
#define PPC_FEATURE2_TAR 0x04000000
+#define PPC_FEATURE2_VEC_CRYPTO 0x02000000
#endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index ee5b690..52e5758 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -764,6 +764,16 @@
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
+ /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
+ if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
+ nb = 8;
+ flags = LD+SW;
+ } else if (IS_XFORM(instruction) &&
+ ((instruction >> 1) & 0x3ff) == 660) {
+ nb = 8;
+ flags = ST+SW;
+ }
+
/* Byteswap little endian loads and stores */
swiz = 0;
if (regs->msr & MSR_LE) {
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6f16ffa..302886b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -139,6 +139,9 @@
DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+ DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+ DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+ DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
transact_vr[0]));
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 92c6b00..b4437e8 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -788,6 +788,9 @@
{
remove_index_dirs(cache_dir);
+ /* Remove cache dir from sysfs */
+ kobject_del(cache_dir->kobj);
+
kobject_put(cache_dir->kobj);
kfree(cache_dir);
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2a45d0f..b2dc455 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -105,7 +105,8 @@
PPC_FEATURE_PSERIES_PERFMON_COMPAT)
#define COMMON_USER2_POWER8 (PPC_FEATURE2_ARCH_2_07 | \
PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
- PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR)
+ PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+ PPC_FEATURE2_VEC_CRYPTO)
#define COMMON_USER_PA6T (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
PPC_FEATURE_TRUE_LE | \
PPC_FEATURE_HAS_ALTIVEC_COMP)
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 9ec3fe1..555ae67 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -108,17 +108,19 @@
size_t csize, unsigned long offset, int userbuf)
{
void *vaddr;
+ phys_addr_t paddr;
if (!csize)
return 0;
csize = min_t(size_t, csize, PAGE_SIZE);
+ paddr = pfn << PAGE_SHIFT;
- if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
- vaddr = __va(pfn << PAGE_SHIFT);
+ if (memblock_is_region_memory(paddr, csize)) {
+ vaddr = __va(paddr);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
} else {
- vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+ vaddr = __ioremap(paddr, PAGE_SIZE, 0);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
iounmap(vaddr);
}
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 8741c85..38847767 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -449,15 +449,6 @@
#ifdef CONFIG_PPC_BOOK3S_64
BEGIN_FTR_SECTION
- /*
- * Back up the TAR across context switches. Note that the TAR is not
- * available for use in the kernel. (To provide this, the TAR should
- * be backed up/restored on exception entry/exit instead, and be in
- * pt_regs. FIXME, this should be in pt_regs anyway (for debug).)
- */
- mfspr r0,SPRN_TAR
- std r0,THREAD_TAR(r3)
-
/* Event based branch registers */
mfspr r0, SPRN_BESCR
std r0, THREAD_BESCR(r3)
@@ -584,9 +575,34 @@
ld r7,DSCR_DEFAULT@toc(2)
ld r0,THREAD_DSCR(r4)
cmpwi r6,0
+ li r8, FSCR_DSCR
bne 1f
ld r0,0(r7)
-1: cmpd r0,r25
+ b 3f
+1:
+ BEGIN_FTR_SECTION_NESTED(70)
+ mfspr r6, SPRN_FSCR
+ or r6, r6, r8
+ mtspr SPRN_FSCR, r6
+ BEGIN_FTR_SECTION_NESTED(69)
+ mfspr r6, SPRN_HFSCR
+ or r6, r6, r8
+ mtspr SPRN_HFSCR, r6
+ END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+ b 4f
+ END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+3:
+ BEGIN_FTR_SECTION_NESTED(70)
+ mfspr r6, SPRN_FSCR
+ andc r6, r6, r8
+ mtspr SPRN_FSCR, r6
+ BEGIN_FTR_SECTION_NESTED(69)
+ mfspr r6, SPRN_HFSCR
+ andc r6, r6, r8
+ mtspr SPRN_HFSCR, r6
+ END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+ END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+4: cmpd r0,r25
beq 2f
mtspr SPRN_DSCR,r0
2:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 40e4a17..902ca3c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -341,10 +341,17 @@
EXCEPTION_PROLOG_0(PACA_EXGEN)
b vsx_unavailable_pSeries
+facility_unavailable_trampoline:
. = 0xf60
SET_SCRATCH0(r13)
EXCEPTION_PROLOG_0(PACA_EXGEN)
- b tm_unavailable_pSeries
+ b facility_unavailable_pSeries
+
+hv_facility_unavailable_trampoline:
+ . = 0xf80
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b facility_unavailable_hv
#ifdef CONFIG_CBE_RAS
STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
@@ -522,8 +529,10 @@
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
- STD_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+ STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+ STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
+ KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
/*
* An interrupt came in while soft-disabled. We set paca->irq_happened, then:
@@ -793,14 +802,10 @@
STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step)
. = 0x4e00
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXGEN)
- b h_data_storage_relon_hv
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
. = 0x4e20
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXGEN)
- b h_instr_storage_relon_hv
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
. = 0x4e40
SET_SCRATCH0(r13)
@@ -808,9 +813,7 @@
b emulation_assist_relon_hv
. = 0x4e60
- SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_0(PACA_EXGEN)
- b hmi_exception_relon_hv
+ b . /* Can't happen, see v2.07 Book III-S section 6.5 */
. = 0x4e80
SET_SCRATCH0(r13)
@@ -835,11 +838,17 @@
EXCEPTION_PROLOG_0(PACA_EXGEN)
b vsx_unavailable_relon_pSeries
-tm_unavailable_relon_pSeries_1:
+facility_unavailable_relon_trampoline:
. = 0x4f60
SET_SCRATCH0(r13)
EXCEPTION_PROLOG_0(PACA_EXGEN)
- b tm_unavailable_relon_pSeries
+ b facility_unavailable_relon_pSeries
+
+hv_facility_unavailable_relon_trampoline:
+ . = 0x4f80
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b hv_facility_unavailable_relon_hv
STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
#ifdef CONFIG_PPC_DENORMALISATION
@@ -1165,36 +1174,22 @@
bl .vsx_unavailable_exception
b .ret_from_except
- .align 7
- .globl tm_unavailable_common
-tm_unavailable_common:
- EXCEPTION_PROLOG_COMMON(0xf60, PACA_EXGEN)
- bl .save_nvgprs
- DISABLE_INTS
- addi r3,r1,STACK_FRAME_OVERHEAD
- bl .tm_unavailable_exception
- b .ret_from_except
+ STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
+ STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
.align 7
.globl __end_handlers
__end_handlers:
/* Equivalents to the above handlers for relocation-on interrupt vectors */
- STD_RELON_EXCEPTION_HV_OOL(0xe00, h_data_storage)
- KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00)
- STD_RELON_EXCEPTION_HV_OOL(0xe20, h_instr_storage)
- KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20)
STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
- KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40)
- STD_RELON_EXCEPTION_HV_OOL(0xe60, hmi_exception)
- KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60)
MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
- KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe80)
STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
- STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+ STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
+ STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 2230fd0..7213d93 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -55,9 +55,9 @@
int __init early_init_dt_scan_fw_dump(unsigned long node,
const char *uname, int depth, void *data)
{
- __be32 *sections;
+ const __be32 *sections;
int i, num_sections;
- unsigned long size;
+ int size;
const int *token;
if (depth != 1 || strcmp(uname, "rtas") != 0)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b61363d..192a3f5 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -467,6 +467,7 @@
mtctr r8
bctr
+.balign 8
p_end: .llong _end - _stext
4: /* Now copy the rest of the kernel up to _end */
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index a949bdf..f0b47d1 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -176,7 +176,7 @@
length_max = 512 ; /* 64 doublewords */
/* DAWR region can't cross 512 boundary */
if ((bp->attr.bp_addr >> 10) !=
- ((bp->attr.bp_addr + bp->attr.bp_len) >> 10))
+ ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10))
return -EINVAL;
}
if (info->len >
@@ -250,6 +250,7 @@
* we still need to single-step the instruction, but we don't
* generate an event.
*/
+ info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
if (!((bp->attr.bp_addr <= dar) &&
(dar - bp->attr.bp_addr < bp->attr.bp_len)))
info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c0d0dbd..93d8d96 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -658,7 +658,7 @@
/* number of bytes needed for the bitmap */
sz = BITS_TO_LONGS(tbl->it_size) * sizeof(unsigned long);
- page = alloc_pages_node(nid, GFP_ATOMIC, get_order(sz));
+ page = alloc_pages_node(nid, GFP_KERNEL, get_order(sz));
if (!page)
panic("iommu_init_table: Can't allocate %ld bytes\n", sz);
tbl->it_map = page_address(page);
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index d92f387..e2a0a16 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -35,7 +35,13 @@
#include <asm/vdso_datapage.h>
#include <asm/vio.h>
#include <asm/mmu.h>
+#include <asm/machdep.h>
+
+/*
+ * This isn't a module but we expose that to userspace
+ * via /proc so leave the definitions here
+ */
#define MODULE_VERS "1.9"
#define MODULE_NAME "lparcfg"
@@ -418,7 +424,8 @@
{
unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
- if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+ if (firmware_has_feature(FW_FEATURE_LPAR) &&
+ plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
}
@@ -677,7 +684,6 @@
}
static const struct file_operations lparcfg_fops = {
- .owner = THIS_MODULE,
.read = seq_read,
.write = lparcfg_write,
.open = lparcfg_open,
@@ -699,14 +705,4 @@
}
return 0;
}
-
-static void __exit lparcfg_cleanup(void)
-{
- remove_proc_subtree("powerpc/lparcfg", NULL);
-}
-
-module_init(lparcfg_init);
-module_exit(lparcfg_cleanup);
-MODULE_DESCRIPTION("Interface for LPAR configuration data");
-MODULE_AUTHOR("Dave Engebretsen");
-MODULE_LICENSE("GPL");
+machine_device_initcall(pseries, lparcfg_init);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 076d124..d55357e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -523,6 +523,31 @@
tm_save_sprs(thr);
}
+extern void __tm_recheckpoint(struct thread_struct *thread,
+ unsigned long orig_msr);
+
+void tm_recheckpoint(struct thread_struct *thread,
+ unsigned long orig_msr)
+{
+ unsigned long flags;
+
+ /* We really can't be interrupted here as the TEXASR registers can't
+ * change and later in the trecheckpoint code, we have a userspace R1.
+ * So let's hard disable over this region.
+ */
+ local_irq_save(flags);
+ hard_irq_disable();
+
+ /* The TM SPRs are restored here, so that TEXASR.FS can be set
+ * before the trecheckpoint and no explosion occurs.
+ */
+ tm_restore_sprs(thread);
+
+ __tm_recheckpoint(thread, orig_msr);
+
+ local_irq_restore(flags);
+}
+
static inline void tm_recheckpoint_new_task(struct task_struct *new)
{
unsigned long msr;
@@ -541,13 +566,10 @@
if (!new->thread.regs)
return;
- /* The TM SPRs are restored here, so that TEXASR.FS can be set
- * before the trecheckpoint and no explosion occurs.
- */
- tm_restore_sprs(&new->thread);
-
- if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+ if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+ tm_restore_sprs(&new->thread);
return;
+ }
msr = new->thread.tm_orig_msr;
/* Recheckpoint to restore original checkpointed register state. */
TM_DEBUG("*** tm_recheckpoint of pid %d "
@@ -600,6 +622,16 @@
struct ppc64_tlb_batch *batch;
#endif
+ /* Back up the TAR across context switches.
+ * Note that the TAR is not available for use in the kernel. (To
+ * provide this, the TAR should be backed up/restored on exception
+ * entry/exit instead, and be in pt_regs. FIXME, this should be in
+ * pt_regs anyway (for debug).)
+ * Save the TAR here before we do treclaim/trecheckpoint as these
+ * will change the TAR.
+ */
+ save_tar(&prev->thread);
+
__switch_to_tm(prev);
#ifdef CONFIG_SMP
@@ -916,6 +948,16 @@
flush_altivec_to_thread(src);
flush_vsx_to_thread(src);
flush_spe_to_thread(src);
+ /*
+ * Flush TM state out so we can copy it. __switch_to_tm() does this
+ * flush but it removes the checkpointed state from the current CPU and
+ * transitions the CPU out of TM mode. Hence we need to call
+ * tm_recheckpoint_new_task() (on the same task) to restore the
+ * checkpointed state back and the TM mode.
+ */
+ __switch_to_tm(src);
+ tm_recheckpoint_new_task(src);
+
*dst = *src;
return 0;
}
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 8b6f7a9..bbfd8b7 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -162,7 +162,7 @@
{CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0},
};
-static void __init scan_features(unsigned long node, unsigned char *ftrs,
+static void __init scan_features(unsigned long node, const unsigned char *ftrs,
unsigned long tablelen,
struct ibm_pa_feature *fp,
unsigned long ft_size)
@@ -201,8 +201,8 @@
static void __init check_cpu_pa_features(unsigned long node)
{
- unsigned char *pa_ftrs;
- unsigned long tablelen;
+ const unsigned char *pa_ftrs;
+ int tablelen;
pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
if (pa_ftrs == NULL)
@@ -215,7 +215,7 @@
#ifdef CONFIG_PPC_STD_MMU_64
static void __init check_cpu_slb_size(unsigned long node)
{
- u32 *slb_size_ptr;
+ const __be32 *slb_size_ptr;
slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL);
if (slb_size_ptr != NULL) {
@@ -256,7 +256,7 @@
static inline void identical_pvr_fixup(unsigned long node)
{
unsigned int pvr;
- char *model = of_get_flat_dt_prop(node, "model", NULL);
+ const char *model = of_get_flat_dt_prop(node, "model", NULL);
/*
* Since 440GR(x)/440EP(x) processors have the same pvr,
@@ -294,11 +294,11 @@
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- const u32 *prop;
- const u32 *intserv;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ const __be32 *intserv;
int i, nthreads;
- unsigned long len;
+ int len;
int found = -1;
int found_thread = 0;
@@ -389,7 +389,7 @@
int __init early_init_dt_scan_chosen_ppc(unsigned long node, const char *uname,
int depth, void *data)
{
- unsigned long *lprop;
+ const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */
/* Use common scan routine to determine if this is the chosen node */
if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
@@ -440,8 +440,9 @@
*/
static int __init early_init_dt_scan_drconf_memory(unsigned long node)
{
- __be32 *dm, *ls, *usm;
- unsigned long l, n, flags;
+ const __be32 *dm, *ls, *usm;
+ int l;
+ unsigned long n, flags;
u64 base, size, memblock_size;
unsigned int is_kexec_kdump = 0, rngs;
@@ -550,8 +551,7 @@
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
@@ -757,119 +757,10 @@
return NULL;
}
-#ifdef CONFIG_PPC_PSERIES
-/*
- * Fix up the uninitialized fields in a new device node:
- * name, type and pci-specific fields
- */
-
-static int of_finish_dynamic_node(struct device_node *node)
-{
- struct device_node *parent = of_get_parent(node);
- int err = 0;
- const phandle *ibm_phandle;
-
- node->name = of_get_property(node, "name", NULL);
- node->type = of_get_property(node, "device_type", NULL);
-
- if (!node->name)
- node->name = "<NULL>";
- if (!node->type)
- node->type = "<NULL>";
-
- if (!parent) {
- err = -ENODEV;
- goto out;
- }
-
- /* We don't support that function on PowerMac, at least
- * not yet
- */
- if (machine_is(powermac))
- return -ENODEV;
-
- /* fix up new node's phandle field */
- if ((ibm_phandle = of_get_property(node, "ibm,phandle", NULL)))
- node->phandle = *ibm_phandle;
-
-out:
- of_node_put(parent);
- return err;
-}
-
-static int prom_reconfig_notifier(struct notifier_block *nb,
- unsigned long action, void *node)
-{
- int err;
-
- switch (action) {
- case OF_RECONFIG_ATTACH_NODE:
- err = of_finish_dynamic_node(node);
- if (err < 0)
- printk(KERN_ERR "finish_node returned %d\n", err);
- break;
- default:
- err = 0;
- break;
- }
- return notifier_from_errno(err);
-}
-
-static struct notifier_block prom_reconfig_nb = {
- .notifier_call = prom_reconfig_notifier,
- .priority = 10, /* This one needs to run first */
-};
-
-static int __init prom_reconfig_setup(void)
-{
- return of_reconfig_notifier_register(&prom_reconfig_nb);
-}
-__initcall(prom_reconfig_setup);
-#endif
-
-/* Find the device node for a given logical cpu number, also returns the cpu
- * local thread number (index in ibm,interrupt-server#s) if relevant and
- * asked for (non NULL)
- */
struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
{
- int hardid;
- struct device_node *np;
-
- hardid = get_hard_smp_processor_id(cpu);
-
- for_each_node_by_type(np, "cpu") {
- const u32 *intserv;
- unsigned int plen, t;
-
- /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist
- * fallback to "reg" property and assume no threads
- */
- intserv = of_get_property(np, "ibm,ppc-interrupt-server#s",
- &plen);
- if (intserv == NULL) {
- const u32 *reg = of_get_property(np, "reg", NULL);
- if (reg == NULL)
- continue;
- if (*reg == hardid) {
- if (thread)
- *thread = 0;
- return np;
- }
- } else {
- plen /= sizeof(u32);
- for (t = 0; t < plen; t++) {
- if (hardid == intserv[t]) {
- if (thread)
- *thread = t;
- return np;
- }
- }
- }
- }
- return NULL;
+ return (int)phys_id == get_hard_smp_processor_id(cpu);
}
-EXPORT_SYMBOL(of_get_cpu_node);
#if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
static struct debugfs_blob_wrapper flat_dt_blob;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 98c2fc1..64f7bd5 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1449,7 +1449,9 @@
*/
if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) {
len = bp_info->addr2 - bp_info->addr;
- } else if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+ } else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ len = 1;
+ else {
ptrace_put_breakpoints(child);
return -EINVAL;
}
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index b47a0e1..c712ece 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@
6: blr
+.balign 8
p_dyn: .llong __dynamic_start - 0b
p_rela: .llong __rela_dyn_start - 0b
p_st: .llong _stext - 0b
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 52add6f..2d6f5a8 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1135,7 +1135,7 @@
int __init early_init_dt_scan_rtas(unsigned long node,
const char *uname, int depth, void *data)
{
- u32 *basep, *entryp, *sizep;
+ const u32 *basep, *entryp, *sizep;
if (depth != 1 || strcmp(uname, "rtas") != 0)
return 0;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e379d3f..389fb807 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -76,7 +76,7 @@
#endif
int boot_cpuid = 0;
-int __initdata spinning_secondaries;
+int spinning_secondaries;
u64 ppc64_pft_size;
/* Pick defaults since we might want to patch instructions
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 201385c..81f929f 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -407,7 +407,8 @@
* altivec/spe instructions at some point.
*/
static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
- int sigret, int ctx_has_vsx_region)
+ struct mcontext __user *tm_frame, int sigret,
+ int ctx_has_vsx_region)
{
unsigned long msr = regs->msr;
@@ -441,6 +442,12 @@
#endif /* CONFIG_ALTIVEC */
if (copy_fpr_to_user(&frame->mc_fregs, current))
return 1;
+
+ /*
+ * Clear the MSR VSX bit to indicate there is no valid state attached
+ * to this context, except in the specific case below where we set it.
+ */
+ msr &= ~MSR_VSX;
#ifdef CONFIG_VSX
/*
* Copy VSR 0-31 upper half from thread_struct to local
@@ -475,6 +482,12 @@
if (__put_user(msr, &frame->mc_gregs[PT_MSR]))
return 1;
+ /* We need to write 0 the MSR top 32 bits in the tm frame so that we
+ * can check it on the restore to see if TM is active
+ */
+ if (tm_frame && __put_user(0, &tm_frame->mc_gregs[PT_MSR]))
+ return 1;
+
if (sigret) {
/* Set up the sigreturn trampoline: li r0,sigret; sc */
if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
@@ -747,7 +760,7 @@
struct mcontext __user *tm_sr)
{
long err;
- unsigned long msr;
+ unsigned long msr, msr_hi;
#ifdef CONFIG_VSX
int i;
#endif
@@ -850,10 +863,15 @@
* transactional versions should be loaded.
*/
tm_enable();
+ /* Make sure the transaction is marked as failed */
+ current->thread.tm_texasr |= TEXASR_FS;
/* This loads the checkpointed FP/VEC state, if used */
tm_recheckpoint(¤t->thread, msr);
- /* The task has moved into TM state S, so ensure MSR reflects this */
- regs->msr = (regs->msr & ~MSR_TS_MASK) | MSR_TS_S;
+ /* Get the top half of the MSR */
+ if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+ return 1;
+ /* Pull in MSR TM from user context */
+ regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
/* This loads the speculative FP/VEC state, if used */
if (msr & MSR_FP) {
@@ -952,6 +970,7 @@
{
struct rt_sigframe __user *rt_sf;
struct mcontext __user *frame;
+ struct mcontext __user *tm_frame = NULL;
void __user *addr;
unsigned long newsp = 0;
int sigret;
@@ -985,23 +1004,24 @@
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ tm_frame = &rt_sf->uc_transact.uc_mcontext;
if (MSR_TM_ACTIVE(regs->msr)) {
- if (save_tm_user_regs(regs, &rt_sf->uc.uc_mcontext,
- &rt_sf->uc_transact.uc_mcontext, sigret))
+ if (save_tm_user_regs(regs, frame, tm_frame, sigret))
goto badframe;
}
else
#endif
- if (save_user_regs(regs, frame, sigret, 1))
+ {
+ if (save_user_regs(regs, frame, tm_frame, sigret, 1))
goto badframe;
+ }
regs->link = tramp;
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (MSR_TM_ACTIVE(regs->msr)) {
if (__put_user((unsigned long)&rt_sf->uc_transact,
&rt_sf->uc.uc_link)
- || __put_user(to_user_ptr(&rt_sf->uc_transact.uc_mcontext),
- &rt_sf->uc_transact.uc_regs))
+ || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs))
goto badframe;
}
else
@@ -1170,7 +1190,7 @@
mctx = (struct mcontext __user *)
((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
- || save_user_regs(regs, mctx, 0, ctx_has_vsx_region)
+ || save_user_regs(regs, mctx, NULL, 0, ctx_has_vsx_region)
|| put_sigset_t(&old_ctx->uc_sigmask, ¤t->blocked)
|| __put_user(to_user_ptr(mctx), &old_ctx->uc_regs))
return -EFAULT;
@@ -1233,7 +1253,7 @@
if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
goto bad;
- if (MSR_TM_SUSPENDED(msr_hi<<32)) {
+ if (MSR_TM_ACTIVE(msr_hi<<32)) {
/* We only recheckpoint on return if we're
* transaction.
*/
@@ -1392,6 +1412,7 @@
{
struct sigcontext __user *sc;
struct sigframe __user *frame;
+ struct mcontext __user *tm_mctx = NULL;
unsigned long newsp = 0;
int sigret;
unsigned long tramp;
@@ -1425,6 +1446,7 @@
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ tm_mctx = &frame->mctx_transact;
if (MSR_TM_ACTIVE(regs->msr)) {
if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
sigret))
@@ -1432,8 +1454,10 @@
}
else
#endif
- if (save_user_regs(regs, &frame->mctx, sigret, 1))
+ {
+ if (save_user_regs(regs, &frame->mctx, tm_mctx, sigret, 1))
goto badframe;
+ }
regs->link = tramp;
@@ -1481,16 +1505,22 @@
long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
struct pt_regs *regs)
{
+ struct sigframe __user *sf;
struct sigcontext __user *sc;
struct sigcontext sigctx;
struct mcontext __user *sr;
void __user *addr;
sigset_t set;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ struct mcontext __user *mcp, *tm_mcp;
+ unsigned long msr_hi;
+#endif
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
- sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+ sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+ sc = &sf->sctx;
addr = sc;
if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
goto badframe;
@@ -1507,11 +1537,25 @@
#endif
set_current_blocked(&set);
- sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
- addr = sr;
- if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
- || restore_user_regs(regs, sr, 1))
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ mcp = (struct mcontext __user *)&sf->mctx;
+ tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
+ if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR]))
goto badframe;
+ if (MSR_TM_ACTIVE(msr_hi<<32)) {
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto badframe;
+ if (restore_tm_user_regs(regs, mcp, tm_mcp))
+ goto badframe;
+ } else
+#endif
+ {
+ sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
+ addr = sr;
+ if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
+ || restore_user_regs(regs, sr, 1))
+ goto badframe;
+ }
set_thread_flag(TIF_RESTOREALL);
return 0;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 3459473..74d9615 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -121,6 +121,12 @@
flush_fp_to_thread(current);
/* copy fpr regs and fpscr */
err |= copy_fpr_to_user(&sc->fp_regs, current);
+
+ /*
+ * Clear the MSR VSX bit to indicate there is no valid state attached
+ * to this context, except in the specific case below where we set it.
+ */
+ msr &= ~MSR_VSX;
#ifdef CONFIG_VSX
/*
* Copy VSX low doubleword to local buffer for formatting,
@@ -410,6 +416,10 @@
/* get MSR separately, transfer the LE bit if doing signal return */
err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+ /* pull in MSR TM from user context */
+ regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
+
+ /* pull in MSR LE from user context */
regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
/* The following non-GPR non-FPR non-VR state is also checkpointed: */
@@ -503,10 +513,10 @@
}
#endif
tm_enable();
+ /* Make sure the transaction is marked as failed */
+ current->thread.tm_texasr |= TEXASR_FS;
/* This loads the checkpointed FP/VEC state, if used */
tm_recheckpoint(¤t->thread, msr);
- /* The task has moved into TM state S, so ensure MSR reflects this: */
- regs->msr = (regs->msr & ~MSR_TS_MASK) | __MASK(33);
/* This loads the speculative FP/VEC state, if used */
if (msr & MSR_FP) {
@@ -654,7 +664,7 @@
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
goto badframe;
- if (MSR_TM_SUSPENDED(msr)) {
+ if (MSR_TM_ACTIVE(msr)) {
/* We recheckpoint on return. */
struct ucontext __user *uc_transact;
if (__get_user(uc_transact, &uc->uc_link))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ee7ac5e..c5c6407 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -544,8 +544,8 @@
if (smp_ops->give_timebase)
smp_ops->give_timebase();
- /* Wait until cpu puts itself in the online map */
- while (!cpu_online(cpu))
+ /* Wait until cpu puts itself in the online & active maps */
+ while (!cpu_online(cpu) || !cpu_active(cpu))
cpu_relax();
return 0;
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index 0167d53..a531154 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -9,9 +9,7 @@
#include <linux/mm.h>
#include <asm/page.h>
-
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+#include <asm/sections.h>
/*
* pfn_is_nosave - check if given pfn is in the 'nosave' section
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index e68a845..a15fd1a 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -17,6 +17,7 @@
#include <asm/machdep.h>
#include <asm/smp.h>
#include <asm/pmc.h>
+#include <asm/firmware.h>
#include "cacheinfo.h"
@@ -179,15 +180,25 @@
SYSFS_PMCSETUP(dscr, SPRN_DSCR);
SYSFS_PMCSETUP(pir, SPRN_PIR);
+/*
+ Lets only enable read for phyp resources and
+ enable write when needed with a separate function.
+ Lets be conservative and default to pseries.
+*/
static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-static DEVICE_ATTR(purr, 0600, show_purr, store_purr);
+static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
static DEVICE_ATTR(pir, 0400, show_pir, NULL);
unsigned long dscr_default = 0;
EXPORT_SYMBOL(dscr_default);
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+ attr->attr.mode |= 0200;
+}
+
static ssize_t show_dscr_default(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -394,8 +405,11 @@
if (cpu_has_feature(CPU_FTR_MMCRA))
device_create_file(s, &dev_attr_mmcra);
- if (cpu_has_feature(CPU_FTR_PURR))
+ if (cpu_has_feature(CPU_FTR_PURR)) {
+ if (!firmware_has_feature(FW_FEATURE_LPAR))
+ add_write_permission_dev_attr(&dev_attr_purr);
device_create_file(s, &dev_attr_purr);
+ }
if (cpu_has_feature(CPU_FTR_SPURR))
device_create_file(s, &dev_attr_spurr);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 5fc29ad..57fd5c1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -512,7 +512,7 @@
__get_cpu_var(irq_stat).timer_irqs++;
-#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
if (atomic_read(&ppc_n_lost_interrupts) != 0)
do_IRQ(regs);
#endif
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 2da67e7..1e43ed4 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -79,6 +79,11 @@
TABORT(R3)
blr
+ .section ".toc","aw"
+DSCR_DEFAULT:
+ .tc dscr_default[TC],dscr_default
+
+ .section ".text"
/* void tm_reclaim(struct thread_struct *thread,
* unsigned long orig_msr,
@@ -178,11 +183,18 @@
std r1, PACATMSCRATCH(r13)
ld r1, PACAR1(r13)
+ /* Store the PPR in r11 and reset to decent value */
+ std r11, GPR11(r1) /* Temporary stash */
+ mfspr r11, SPRN_PPR
+ HMT_MEDIUM
+
/* Now get some more GPRS free */
std r7, GPR7(r1) /* Temporary stash */
std r12, GPR12(r1) /* '' '' '' */
ld r12, STACK_PARAM(0)(r1) /* Param 0, thread_struct * */
+ std r11, THREAD_TM_PPR(r12) /* Store PPR and free r11 */
+
addi r7, r12, PT_CKPT_REGS /* Thread's ckpt_regs */
/* Make r7 look like an exception frame so that we
@@ -194,15 +206,19 @@
SAVE_GPR(0, r7) /* user r0 */
SAVE_GPR(2, r7) /* user r2 */
SAVE_4GPRS(3, r7) /* user r3-r6 */
- SAVE_4GPRS(8, r7) /* user r8-r11 */
+ SAVE_GPR(8, r7) /* user r8 */
+ SAVE_GPR(9, r7) /* user r9 */
+ SAVE_GPR(10, r7) /* user r10 */
ld r3, PACATMSCRATCH(r13) /* user r1 */
ld r4, GPR7(r1) /* user r7 */
- ld r5, GPR12(r1) /* user r12 */
- GET_SCRATCH0(6) /* user r13 */
+ ld r5, GPR11(r1) /* user r11 */
+ ld r6, GPR12(r1) /* user r12 */
+ GET_SCRATCH0(8) /* user r13 */
std r3, GPR1(r7)
std r4, GPR7(r7)
- std r5, GPR12(r7)
- std r6, GPR13(r7)
+ std r5, GPR11(r7)
+ std r6, GPR12(r7)
+ std r8, GPR13(r7)
SAVE_NVGPRS(r7) /* user r14-r31 */
@@ -224,6 +240,14 @@
std r5, _CCR(r7)
std r6, _XER(r7)
+
+ /* ******************** TAR, DSCR ********** */
+ mfspr r3, SPRN_TAR
+ mfspr r4, SPRN_DSCR
+
+ std r3, THREAD_TM_TAR(r12)
+ std r4, THREAD_TM_DSCR(r12)
+
/* MSR and flags: We don't change CRs, and we don't need to alter
* MSR.
*/
@@ -239,7 +263,7 @@
std r3, THREAD_TM_TFHAR(r12)
std r4, THREAD_TM_TFIAR(r12)
- /* AMR and PPR are checkpointed too, but are unsupported by Linux. */
+ /* AMR is checkpointed too, but is unsupported by Linux. */
/* Restore original MSR/IRQ state & clear TM mode */
ld r14, TM_FRAME_L0(r1) /* Orig MSR */
@@ -255,6 +279,12 @@
mtcr r4
mtlr r0
ld r2, 40(r1)
+
+ /* Load system default DSCR */
+ ld r4, DSCR_DEFAULT@toc(r2)
+ ld r0, 0(r4)
+ mtspr SPRN_DSCR, r0
+
blr
@@ -266,7 +296,7 @@
* Call with IRQs off, stacks get all out of sync for
* some periods in here!
*/
-_GLOBAL(tm_recheckpoint)
+_GLOBAL(__tm_recheckpoint)
mfcr r5
mflr r0
std r5, 8(r1)
@@ -338,35 +368,51 @@
mtmsr r6 /* FP/Vec off again! */
restore_gprs:
- /* ******************** CR,LR,CCR,MSR ********** */
- ld r3, _CTR(r7)
- ld r4, _LINK(r7)
- ld r5, _CCR(r7)
- ld r6, _XER(r7)
- mtctr r3
- mtlr r4
- mtcr r5
- mtxer r6
+ /* ******************** CR,LR,CCR,MSR ********** */
+ ld r4, _CTR(r7)
+ ld r5, _LINK(r7)
+ ld r6, _CCR(r7)
+ ld r8, _XER(r7)
+
+ mtctr r4
+ mtlr r5
+ mtcr r6
+ mtxer r8
+
+ /* ******************** TAR ******************** */
+ ld r4, THREAD_TM_TAR(r3)
+ mtspr SPRN_TAR, r4
+
+ /* Load up the PPR and DSCR in GPRs only at this stage */
+ ld r5, THREAD_TM_DSCR(r3)
+ ld r6, THREAD_TM_PPR(r3)
/* MSR and flags: We don't change CRs, and we don't need to alter
* MSR.
*/
REST_4GPRS(0, r7) /* GPR0-3 */
- REST_GPR(4, r7) /* GPR4-6 */
- REST_GPR(5, r7)
- REST_GPR(6, r7)
+ REST_GPR(4, r7) /* GPR4 */
REST_4GPRS(8, r7) /* GPR8-11 */
REST_2GPRS(12, r7) /* GPR12-13 */
REST_NVGPRS(r7) /* GPR14-31 */
- ld r7, GPR7(r7) /* GPR7 */
+ /* Load up PPR and DSCR here so we don't run with user values for long
+ */
+ mtspr SPRN_DSCR, r5
+ mtspr SPRN_PPR, r6
+
+ REST_GPR(5, r7) /* GPR5-7 */
+ REST_GPR(6, r7)
+ ld r7, GPR7(r7)
/* Commit register state as checkpointed state: */
TRECHKPT
+ HMT_MEDIUM
+
/* Our transactional state has now changed.
*
* Now just get out of here. Transactional (current) state will be
@@ -385,6 +431,12 @@
mtcr r4
mtlr r0
ld r2, 40(r1)
+
+ /* Load system default DSCR */
+ ld r4, DSCR_DEFAULT@toc(r2)
+ ld r0, 0(r4)
+ mtspr SPRN_DSCR, r0
+
blr
/* ****************************************************************** */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c0e5caf..88929b1 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -44,9 +44,7 @@
#include <asm/machdep.h>
#include <asm/rtas.h>
#include <asm/pmc.h>
-#ifdef CONFIG_PPC32
#include <asm/reg.h>
-#endif
#ifdef CONFIG_PMAC_BACKLIGHT
#include <asm/backlight.h>
#endif
@@ -1282,26 +1280,63 @@
die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
}
-void tm_unavailable_exception(struct pt_regs *regs)
+#ifdef CONFIG_PPC64
+void facility_unavailable_exception(struct pt_regs *regs)
{
+ static char *facility_strings[] = {
+ [FSCR_FP_LG] = "FPU",
+ [FSCR_VECVSX_LG] = "VMX/VSX",
+ [FSCR_DSCR_LG] = "DSCR",
+ [FSCR_PM_LG] = "PMU SPRs",
+ [FSCR_BHRB_LG] = "BHRB",
+ [FSCR_TM_LG] = "TM",
+ [FSCR_EBB_LG] = "EBB",
+ [FSCR_TAR_LG] = "TAR",
+ };
+ char *facility = "unknown";
+ u64 value;
+ u8 status;
+ bool hv;
+
+ hv = (regs->trap == 0xf80);
+ if (hv)
+ value = mfspr(SPRN_HFSCR);
+ else
+ value = mfspr(SPRN_FSCR);
+
+ status = value >> 56;
+ if (status == FSCR_DSCR_LG) {
+ /* User is acessing the DSCR. Set the inherit bit and allow
+ * the user to set it directly in future by setting via the
+ * H/FSCR DSCR bit.
+ */
+ current->thread.dscr_inherit = 1;
+ if (hv)
+ mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
+ else
+ mtspr(SPRN_FSCR, value | FSCR_DSCR);
+ return;
+ }
+
+ if ((status < ARRAY_SIZE(facility_strings)) &&
+ facility_strings[status])
+ facility = facility_strings[status];
+
/* We restore the interrupt state now */
if (!arch_irq_disabled_regs(regs))
local_irq_enable();
- /* Currently we never expect a TMU exception. Catch
- * this and kill the process!
- */
- printk(KERN_EMERG "Unexpected TM unavailable exception at %lx "
- "(msr %lx)\n",
- regs->nip, regs->msr);
+ pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
+ hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
if (user_mode(regs)) {
_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
return;
}
- die("Unexpected TM unavailable exception", regs, SIGABRT);
+ die("Unexpected facility unavailable exception", regs, SIGABRT);
}
+#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 47afd08..fe7e97a 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -30,8 +30,8 @@
V_FUNCTION_BEGIN(__kernel_getcpu)
.cfi_startproc
mfspr r5,SPRN_USPRG3
- cmpdi cr0,r3,0
- cmpdi cr1,r4,0
+ cmpwi cr0,r3,0
+ cmpwi cr1,r4,0
clrlwi r6,r5,16
rlwinm r7,r5,16,31-15,31-0
beq cr0,1f
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 536016d..56d2e72 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1529,11 +1529,15 @@
const char *cp;
dn = dev->of_node;
- if (!dn)
- return -ENODEV;
+ if (!dn) {
+ strcpy(buf, "\n");
+ return strlen(buf);
+ }
cp = of_get_property(dn, "compatible", NULL);
- if (!cp)
- return -ENODEV;
+ if (!cp) {
+ strcpy(buf, "\n");
+ return strlen(buf);
+ }
return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
}
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 654e479..f096e72 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -38,9 +38,6 @@
#endif
SECTIONS
{
- . = 0;
- reloc_start = .;
-
. = KERNELBASE;
/*
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index eb643f8..60019a6 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -155,6 +155,7 @@
bool "KVM in-kernel MPIC emulation"
depends on KVM && E500
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_MSI
help
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 422de3f..008cd85 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -5,9 +5,10 @@
subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
+KVM := ../../../virt/kvm
-common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o \
- eventfd.o)
+common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
+ $(KVM)/eventfd.o
CFLAGS_44x_tlb.o := -I.
CFLAGS_e500_mmu.o := -I.
@@ -53,7 +54,7 @@
kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
- ../../../virt/kvm/coalesced_mmio.o \
+ $(KVM)/coalesced_mmio.o \
fpu.o \
book3s_paired_singles.o \
book3s_pr.o \
@@ -86,8 +87,8 @@
book3s_xics.o
kvm-book3s_64-module-objs := \
- ../../../virt/kvm/kvm_main.o \
- ../../../virt/kvm/eventfd.o \
+ $(KVM)/kvm_main.o \
+ $(KVM)/eventfd.o \
powerpc.o \
emulate.o \
book3s.o \
@@ -111,7 +112,7 @@
kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs)
kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o
-kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(addprefix ../../../virt/kvm/, irqchip.o)
+kvm-objs-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o
kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 5880dfb..b616e364 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -473,11 +473,14 @@
slb_v = vcpu->kvm->arch.vrma_slb_v;
}
+ preempt_disable();
/* Find the HPTE in the hash table */
index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
HPTE_V_VALID | HPTE_V_ABSENT);
- if (index < 0)
+ if (index < 0) {
+ preempt_enable();
return -ENOENT;
+ }
hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
v = hptep[0] & ~HPTE_V_HVLOCK;
gr = kvm->arch.revmap[index].guest_rpte;
@@ -485,6 +488,7 @@
/* Unlock the HPTE */
asm volatile("lwsync" : : : "memory");
hptep[0] = v;
+ preempt_enable();
gpte->eaddr = eaddr;
gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 550f592..a54c59d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -82,10 +82,13 @@
/* CPU points to the first thread of the core */
if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
+#ifdef CONFIG_KVM_XICS
int real_cpu = cpu + vcpu->arch.ptid;
if (paca[real_cpu].kvm_hstate.xics_phys)
xics_wake_cpu(real_cpu);
- else if (cpu_online(cpu))
+ else
+#endif
+ if (cpu_online(cpu))
smp_send_reschedule(cpu);
}
put_cpu();
@@ -1090,7 +1093,9 @@
smp_wmb();
#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
if (vcpu->arch.ptid) {
+#ifdef CONFIG_KVM_XICS
xics_wake_cpu(cpu);
+#endif
++vc->n_woken;
}
#endif
@@ -1253,7 +1258,7 @@
kvm_guest_exit();
preempt_enable();
- kvm_resched(vcpu);
+ cond_resched();
spin_lock(&vc->lock);
now = get_tb();
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6dcbb49..049b899 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -724,6 +724,10 @@
20, /* 1M, unsupported */
};
+/* When called from virtmode, this func should be protected by
+ * preempt_disable(), otherwise, the holding of HPTE_V_HVLOCK
+ * can trigger deadlock issue.
+ */
long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
unsigned long valid)
{
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e..7bcd4d6 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1054,7 +1054,7 @@
BEGIN_FTR_SECTION
mfspr r8, SPRN_DSCR
ld r7, HSTATE_DSCR(r13)
- std r8, VCPU_DSCR(r7)
+ std r8, VCPU_DSCR(r9)
mtspr SPRN_DSCR, r7
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 94c1dd4..a3a5cb8 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,6 +19,7 @@
#include <asm/hvcall.h>
#include <asm/xics.h>
#include <asm/debug.h>
+#include <asm/time.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1a1b511..0a91f47 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1592,12 +1592,12 @@
return -ENOTSUPP;
}
-void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
}
-int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+int kvmppc_core_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned long npages)
{
return 0;
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index 6d6f153..c17600d 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -127,7 +127,7 @@
}
static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
- unsigned int eaddr, int as)
+ gva_t eaddr, int as)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
unsigned int victim, tsized;
diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c
index 2861ae9..b58d610 100644
--- a/arch/powerpc/kvm/mpic.c
+++ b/arch/powerpc/kvm/mpic.c
@@ -1822,8 +1822,7 @@
return 0;
}
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
- struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
int r = -EINVAL;
@@ -1835,7 +1834,6 @@
e->irqchip.pin = ue->u.irqchip.pin;
if (e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS)
goto out;
- rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
break;
case KVM_IRQ_ROUTING_MSI:
e->set = kvm_set_msi;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee3..ea4cfdc 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -246,24 +246,16 @@
return r;
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
int kvm_arch_hardware_setup(void)
{
return 0;
}
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
void kvm_arch_check_processor_compat(void *rtn)
{
*(int *)rtn = kvmppc_core_check_processor_compat();
@@ -296,11 +288,7 @@
mutex_unlock(&kvm->lock);
}
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -409,15 +397,16 @@
return -EINVAL;
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
- kvmppc_core_free_memslot(free, dont);
+ kvmppc_core_free_memslot(kvm, free, dont);
}
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
- return kvmppc_core_create_memslot(slot, npages);
+ return kvmppc_core_create_memslot(kvm, slot, npages);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -436,10 +425,6 @@
kvmppc_core_commit_memory_region(kvm, mem, old);
}
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
@@ -1125,7 +1110,3 @@
{
return 0;
}
-
-void kvm_arch_exit(void)
-{
-}
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 167f725..57a0720 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -226,19 +226,35 @@
blr
- .macro source
+ .macro srcnr
100:
.section __ex_table,"a"
.align 3
- .llong 100b,.Lsrc_error
+ .llong 100b,.Lsrc_error_nr
+ .previous
+ .endm
+
+ .macro source
+150:
+ .section __ex_table,"a"
+ .align 3
+ .llong 150b,.Lsrc_error
+ .previous
+ .endm
+
+ .macro dstnr
+200:
+ .section __ex_table,"a"
+ .align 3
+ .llong 200b,.Ldest_error_nr
.previous
.endm
.macro dest
-200:
+250:
.section __ex_table,"a"
.align 3
- .llong 200b,.Ldest_error
+ .llong 250b,.Ldest_error
.previous
.endm
@@ -269,16 +285,16 @@
rldicl. r6,r3,64-1,64-2 /* r6 = (r3 & 0x3) >> 1 */
beq .Lcopy_aligned
- li r7,4
- sub r6,r7,r6
+ li r9,4
+ sub r6,r9,r6
mtctr r6
1:
-source; lhz r6,0(r3) /* align to doubleword */
+srcnr; lhz r6,0(r3) /* align to doubleword */
subi r5,r5,2
addi r3,r3,2
adde r0,r0,r6
-dest; sth r6,0(r4)
+dstnr; sth r6,0(r4)
addi r4,r4,2
bdnz 1b
@@ -392,10 +408,10 @@
mtctr r6
3:
-source; ld r6,0(r3)
+srcnr; ld r6,0(r3)
addi r3,r3,8
adde r0,r0,r6
-dest; std r6,0(r4)
+dstnr; std r6,0(r4)
addi r4,r4,8
bdnz 3b
@@ -405,10 +421,10 @@
srdi. r6,r5,2
beq .Lcopy_tail_halfword
-source; lwz r6,0(r3)
+srcnr; lwz r6,0(r3)
addi r3,r3,4
adde r0,r0,r6
-dest; stw r6,0(r4)
+dstnr; stw r6,0(r4)
addi r4,r4,4
subi r5,r5,4
@@ -416,10 +432,10 @@
srdi. r6,r5,1
beq .Lcopy_tail_byte
-source; lhz r6,0(r3)
+srcnr; lhz r6,0(r3)
addi r3,r3,2
adde r0,r0,r6
-dest; sth r6,0(r4)
+dstnr; sth r6,0(r4)
addi r4,r4,2
subi r5,r5,2
@@ -427,10 +443,10 @@
andi. r6,r5,1
beq .Lcopy_finish
-source; lbz r6,0(r3)
+srcnr; lbz r6,0(r3)
sldi r9,r6,8 /* Pad the byte out to 16 bits */
adde r0,r0,r9
-dest; stb r6,0(r4)
+dstnr; stb r6,0(r4)
.Lcopy_finish:
addze r0,r0 /* add in final carry */
@@ -440,6 +456,11 @@
blr
.Lsrc_error:
+ ld r14,STK_REG(R14)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r16,STK_REG(R16)(r1)
+ addi r1,r1,STACKFRAMESIZE
+.Lsrc_error_nr:
cmpdi 0,r7,0
beqlr
li r6,-EFAULT
@@ -447,6 +468,11 @@
blr
.Ldest_error:
+ ld r14,STK_REG(R14)(r1)
+ ld r15,STK_REG(R15)(r1)
+ ld r16,STK_REG(R16)(r1)
+ addi r1,r1,STACKFRAMESIZE
+.Ldest_error_nr:
cmpdi 0,r8,0
beqlr
li r6,-EFAULT
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index b2c68ce..a5b30c7 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -231,6 +231,87 @@
mr 1,11
blr
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area. */
+
+_GLOBAL(_savevr_20)
+ li r11,-192
+ stvx vr20,r11,r0
+_GLOBAL(_savevr_21)
+ li r11,-176
+ stvx vr21,r11,r0
+_GLOBAL(_savevr_22)
+ li r11,-160
+ stvx vr22,r11,r0
+_GLOBAL(_savevr_23)
+ li r11,-144
+ stvx vr23,r11,r0
+_GLOBAL(_savevr_24)
+ li r11,-128
+ stvx vr24,r11,r0
+_GLOBAL(_savevr_25)
+ li r11,-112
+ stvx vr25,r11,r0
+_GLOBAL(_savevr_26)
+ li r11,-96
+ stvx vr26,r11,r0
+_GLOBAL(_savevr_27)
+ li r11,-80
+ stvx vr27,r11,r0
+_GLOBAL(_savevr_28)
+ li r11,-64
+ stvx vr28,r11,r0
+_GLOBAL(_savevr_29)
+ li r11,-48
+ stvx vr29,r11,r0
+_GLOBAL(_savevr_30)
+ li r11,-32
+ stvx vr30,r11,r0
+_GLOBAL(_savevr_31)
+ li r11,-16
+ stvx vr31,r11,r0
+ blr
+
+_GLOBAL(_restvr_20)
+ li r11,-192
+ lvx vr20,r11,r0
+_GLOBAL(_restvr_21)
+ li r11,-176
+ lvx vr21,r11,r0
+_GLOBAL(_restvr_22)
+ li r11,-160
+ lvx vr22,r11,r0
+_GLOBAL(_restvr_23)
+ li r11,-144
+ lvx vr23,r11,r0
+_GLOBAL(_restvr_24)
+ li r11,-128
+ lvx vr24,r11,r0
+_GLOBAL(_restvr_25)
+ li r11,-112
+ lvx vr25,r11,r0
+_GLOBAL(_restvr_26)
+ li r11,-96
+ lvx vr26,r11,r0
+_GLOBAL(_restvr_27)
+ li r11,-80
+ lvx vr27,r11,r0
+_GLOBAL(_restvr_28)
+ li r11,-64
+ lvx vr28,r11,r0
+_GLOBAL(_restvr_29)
+ li r11,-48
+ lvx vr29,r11,r0
+_GLOBAL(_restvr_30)
+ li r11,-32
+ lvx vr30,r11,r0
+_GLOBAL(_restvr_31)
+ li r11,-16
+ lvx vr31,r11,r0
+ blr
+
+#endif /* CONFIG_ALTIVEC */
+
#else /* CONFIG_PPC64 */
.section ".text.save.restore","ax",@progbits
@@ -356,6 +437,111 @@
mtlr r0
blr
+#ifdef CONFIG_ALTIVEC
+/* Called with r0 pointing just beyond the end of the vector save area. */
+
+.globl _savevr_20
+_savevr_20:
+ li r12,-192
+ stvx vr20,r12,r0
+.globl _savevr_21
+_savevr_21:
+ li r12,-176
+ stvx vr21,r12,r0
+.globl _savevr_22
+_savevr_22:
+ li r12,-160
+ stvx vr22,r12,r0
+.globl _savevr_23
+_savevr_23:
+ li r12,-144
+ stvx vr23,r12,r0
+.globl _savevr_24
+_savevr_24:
+ li r12,-128
+ stvx vr24,r12,r0
+.globl _savevr_25
+_savevr_25:
+ li r12,-112
+ stvx vr25,r12,r0
+.globl _savevr_26
+_savevr_26:
+ li r12,-96
+ stvx vr26,r12,r0
+.globl _savevr_27
+_savevr_27:
+ li r12,-80
+ stvx vr27,r12,r0
+.globl _savevr_28
+_savevr_28:
+ li r12,-64
+ stvx vr28,r12,r0
+.globl _savevr_29
+_savevr_29:
+ li r12,-48
+ stvx vr29,r12,r0
+.globl _savevr_30
+_savevr_30:
+ li r12,-32
+ stvx vr30,r12,r0
+.globl _savevr_31
+_savevr_31:
+ li r12,-16
+ stvx vr31,r12,r0
+ blr
+
+.globl _restvr_20
+_restvr_20:
+ li r12,-192
+ lvx vr20,r12,r0
+.globl _restvr_21
+_restvr_21:
+ li r12,-176
+ lvx vr21,r12,r0
+.globl _restvr_22
+_restvr_22:
+ li r12,-160
+ lvx vr22,r12,r0
+.globl _restvr_23
+_restvr_23:
+ li r12,-144
+ lvx vr23,r12,r0
+.globl _restvr_24
+_restvr_24:
+ li r12,-128
+ lvx vr24,r12,r0
+.globl _restvr_25
+_restvr_25:
+ li r12,-112
+ lvx vr25,r12,r0
+.globl _restvr_26
+_restvr_26:
+ li r12,-96
+ lvx vr26,r12,r0
+.globl _restvr_27
+_restvr_27:
+ li r12,-80
+ lvx vr27,r12,r0
+.globl _restvr_28
+_restvr_28:
+ li r12,-64
+ lvx vr28,r12,r0
+.globl _restvr_29
+_restvr_29:
+ li r12,-48
+ lvx vr29,r12,r0
+.globl _restvr_30
+_restvr_30:
+ li r12,-32
+ lvx vr30,r12,r0
+.globl _restvr_31
+_restvr_31:
+ li r12,-16
+ lvx vr31,r12,r0
+ blr
+
+#endif /* CONFIG_ALTIVEC */
+
#endif /* CONFIG_PPC64 */
#endif
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e15c521..08490ec 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1395,7 +1395,7 @@
regs->gpr[rd] = byterev_4(val);
goto ldst_done;
-#ifdef CONFIG_PPC_CPU
+#ifdef CONFIG_PPC_FPU
case 535: /* lfsx */
case 567: /* lfsux */
if (!(regs->msr & MSR_FP))
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 8726779..d51a0c1 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -223,9 +223,6 @@
is_write = error_code & ESR_DST;
#endif /* CONFIG_4xx || CONFIG_BOOKE */
- if (is_write)
- flags |= FAULT_FLAG_WRITE;
-
#ifdef CONFIG_PPC_ICSWX
/*
* we need to do this early because this "data storage
@@ -280,6 +277,9 @@
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
@@ -408,6 +408,7 @@
} else if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
@@ -424,6 +425,8 @@
*/
fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+ if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
rc = mm_fault_error(regs, address, fault);
if (rc >= MM_FAULT_RETURN)
goto bail;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index e303a6d..929e3e6 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -250,9 +250,9 @@
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- u32 *prop;
- unsigned long size = 0;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
@@ -306,9 +306,9 @@
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- u32 *prop;
- unsigned long size = 0;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
+ int size = 0;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
@@ -389,9 +389,9 @@
static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
const char *uname, int depth,
void *data) {
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- unsigned long *addr_prop;
- u32 *page_count_prop;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be64 *addr_prop;
+ const __be32 *page_count_prop;
unsigned int expected_pages;
long unsigned int phys_addr;
long unsigned int block_size;
@@ -533,8 +533,8 @@
const char *uname, int depth,
void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- u32 *prop;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *prop;
/* We are scanning "cpu" nodes only */
if (type == NULL || strcmp(type, "cpu") != 0)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 88c0425..5166351 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -27,9 +27,12 @@
#include <linux/seq_file.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
+#include <asm/cputhreads.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/topology.h>
#include <asm/firmware.h>
#include <asm/paca.h>
#include <asm/hvcall.h>
@@ -151,9 +154,22 @@
}
}
-static void map_cpu_to_node(int cpu, int node)
+static void reset_numa_cpu_lookup_table(void)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu)
+ numa_cpu_lookup_table[cpu] = -1;
+}
+
+static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
{
numa_cpu_lookup_table[cpu] = node;
+}
+
+static void map_cpu_to_node(int cpu, int node)
+{
+ update_numa_cpu_lookup_table(cpu, node);
dbg("adding cpu %d to node %d\n", cpu, node);
@@ -518,11 +534,24 @@
*/
static int __cpuinit numa_setup_cpu(unsigned long lcpu)
{
- int nid = 0;
- struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
+ int nid;
+ struct device_node *cpu;
+
+ /*
+ * If a valid cpu-to-node mapping is already available, use it
+ * directly instead of querying the firmware, since it represents
+ * the most recent mapping notified to us by the platform (eg: VPHN).
+ */
+ if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+ map_cpu_to_node(lcpu, nid);
+ return nid;
+ }
+
+ cpu = of_get_cpu_node(lcpu, NULL);
if (!cpu) {
WARN_ON(1);
+ nid = 0;
goto out;
}
@@ -557,8 +586,8 @@
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
unmap_cpu_from_node(lcpu);
- break;
ret = NOTIFY_OK;
+ break;
#endif
}
return ret;
@@ -1065,6 +1094,7 @@
*/
setup_node_to_cpumask_map();
+ reset_numa_cpu_lookup_table();
register_cpu_notifier(&ppc64_numa_nb);
cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
(void *)(unsigned long)boot_cpuid);
@@ -1319,7 +1349,8 @@
}
}
if (changed) {
- cpumask_set_cpu(cpu, changes);
+ cpumask_or(changes, changes, cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
}
}
@@ -1427,17 +1458,42 @@
if (!data)
return -EINVAL;
- cpu = get_cpu();
+ cpu = smp_processor_id();
for (update = data; update; update = update->next) {
if (cpu != update->cpu)
continue;
- unregister_cpu_under_node(update->cpu, update->old_nid);
unmap_cpu_from_node(update->cpu);
map_cpu_to_node(update->cpu, update->new_nid);
vdso_getcpu_init();
- register_cpu_under_node(update->cpu, update->new_nid);
+ }
+
+ return 0;
+}
+
+static int update_lookup_table(void *data)
+{
+ struct topology_update_data *update;
+
+ if (!data)
+ return -EINVAL;
+
+ /*
+ * Upon topology update, the numa-cpu lookup table needs to be updated
+ * for all threads in the core, including offline CPUs, to ensure that
+ * future hotplug operations respect the cpu-to-node associativity
+ * properly.
+ */
+ for (update = data; update; update = update->next) {
+ int nid, base, j;
+
+ nid = update->new_nid;
+ base = cpu_first_thread_sibling(update->cpu);
+
+ for (j = 0; j < threads_per_core; j++) {
+ update_numa_cpu_lookup_table(base + j, nid);
+ }
}
return 0;
@@ -1449,12 +1505,12 @@
*/
int arch_update_cpu_topology(void)
{
- unsigned int cpu, changed = 0;
+ unsigned int cpu, sibling, changed = 0;
struct topology_update_data *updates, *ud;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
cpumask_t updated_cpus;
struct device *dev;
- int weight, i = 0;
+ int weight, new_nid, i = 0;
weight = cpumask_weight(&cpu_associativity_changes_mask);
if (!weight)
@@ -1467,24 +1523,62 @@
cpumask_clear(&updated_cpus);
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
- ud = &updates[i++];
- ud->cpu = cpu;
+ /*
+ * If siblings aren't flagged for changes, updates list
+ * will be too short. Skip on this update and set for next
+ * update.
+ */
+ if (!cpumask_subset(cpu_sibling_mask(cpu),
+ &cpu_associativity_changes_mask)) {
+ pr_info("Sibling bits not set for associativity "
+ "change, cpu%d\n", cpu);
+ cpumask_or(&cpu_associativity_changes_mask,
+ &cpu_associativity_changes_mask,
+ cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
+ continue;
+ }
+
+ /* Use associativity from first thread for all siblings */
vphn_get_associativity(cpu, associativity);
- ud->new_nid = associativity_to_nid(associativity);
+ new_nid = associativity_to_nid(associativity);
+ if (new_nid < 0 || !node_online(new_nid))
+ new_nid = first_online_node;
- if (ud->new_nid < 0 || !node_online(ud->new_nid))
- ud->new_nid = first_online_node;
+ if (new_nid == numa_cpu_lookup_table[cpu]) {
+ cpumask_andnot(&cpu_associativity_changes_mask,
+ &cpu_associativity_changes_mask,
+ cpu_sibling_mask(cpu));
+ cpu = cpu_last_thread_sibling(cpu);
+ continue;
+ }
- ud->old_nid = numa_cpu_lookup_table[cpu];
- cpumask_set_cpu(cpu, &updated_cpus);
-
- if (i < weight)
- ud->next = &updates[i];
+ for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+ ud = &updates[i++];
+ ud->cpu = sibling;
+ ud->new_nid = new_nid;
+ ud->old_nid = numa_cpu_lookup_table[sibling];
+ cpumask_set_cpu(sibling, &updated_cpus);
+ if (i < weight)
+ ud->next = &updates[i];
+ }
+ cpu = cpu_last_thread_sibling(cpu);
}
stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+ /*
+ * Update the numa-cpu lookup table with the new mappings, even for
+ * offline CPUs. It is best to perform this update from the stop-
+ * machine context.
+ */
+ stop_machine(update_lookup_table, &updates[0],
+ cpumask_of(raw_smp_processor_id()));
+
for (ud = &updates[0]; ud; ud = ud->next) {
+ unregister_cpu_under_node(ud->cpu, ud->old_nid);
+ register_cpu_under_node(ud->cpu, ud->new_nid);
+
dev = get_cpu_device(ud->cpu);
if (dev)
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
@@ -1539,12 +1633,11 @@
static int dt_update_callback(struct notifier_block *nb,
unsigned long action, void *data)
{
- struct of_prop_reconfig *update;
+ struct of_reconfig_data *update = data;
int rc = NOTIFY_DONE;
switch (action) {
case OF_RECONFIG_UPDATE_PROPERTY:
- update = (struct of_prop_reconfig *)data;
if (!of_prop_cmp(update->dn->type, "cpu") &&
!of_prop_cmp(update->prop->name, "ibm,associativity")) {
u32 core_id;
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 3e99c14..7ce9cf3 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -258,7 +258,7 @@
slice = GET_HIGH_SLICE_INDEX(addr);
*boundary_addr = (slice + end) ?
((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
- return !!(available.high_slices & (1u << slice));
+ return !!(available.high_slices & (1ul << slice));
}
}
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index c427ae3..a012a97 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -209,10 +209,11 @@
}
PPC_DIVWU(r_A, r_A, r_X);
break;
- case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+ case BPF_S_ALU_DIV_K: /* A /= K */
+ if (K == 1)
+ break;
PPC_LI32(r_scratch1, K);
- /* Top 32 bits of 64bit result -> A */
- PPC_MULHWU(r_A, r_A, r_scratch1);
+ PPC_DIVWU(r_A, r_A, r_scratch1);
break;
case BPF_S_ALU_AND_X:
ctx->seen |= SEEN_XREG;
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e78..ead5535 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -35,7 +35,7 @@
return 0; /* must be 16-byte aligned */
if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
return 0;
- if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+ if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
return 1;
/*
* sp could decrease when we jump off an interrupt stack
@@ -243,7 +243,7 @@
sp = regs->gpr[1];
perf_callchain_store(entry, next_ip);
- for (;;) {
+ while (entry->nr < PERF_MAX_STACK_DEPTH) {
fp = (unsigned long __user *) sp;
if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
return;
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 29c6482..846861a 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -75,6 +75,8 @@
#define MMCR0_FCHV 0
#define MMCR0_PMCjCE MMCR0_PMCnCE
+#define MMCR0_FC56 0
+#define MMCR0_PMAO 0
#define SPRN_MMCRA SPRN_MMCR2
#define MMCRA_SAMPLE_ENABLE 0
@@ -747,7 +749,22 @@
} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
local64_add(delta, &event->count);
- local64_sub(delta, &event->hw.period_left);
+
+ /*
+ * A number of places program the PMC with (0x80000000 - period_left).
+ * We never want period_left to be less than 1 because we will program
+ * the PMC with a value >= 0x800000000 and an edge detected PMC will
+ * roll around to 0 before taking an exception. We have seen this
+ * on POWER8.
+ *
+ * To fix this, clamp the minimum value of period_left to 1.
+ */
+ do {
+ prev = local64_read(&event->hw.period_left);
+ val = prev - delta;
+ if (val < 1)
+ val = 1;
+ } while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev);
}
/*
@@ -852,7 +869,7 @@
static void power_pmu_disable(struct pmu *pmu)
{
struct cpu_hw_events *cpuhw;
- unsigned long flags;
+ unsigned long flags, val;
if (!ppmu)
return;
@@ -860,9 +877,6 @@
cpuhw = &__get_cpu_var(cpu_hw_events);
if (!cpuhw->disabled) {
- cpuhw->disabled = 1;
- cpuhw->n_added = 0;
-
/*
* Check if we ever enabled the PMU on this cpu.
*/
@@ -872,6 +886,21 @@
}
/*
+ * Set the 'freeze counters' bit, clear PMAO/FC56.
+ */
+ val = mfspr(SPRN_MMCR0);
+ val |= MMCR0_FC;
+ val &= ~(MMCR0_PMAO | MMCR0_FC56);
+
+ /*
+ * The barrier is to make sure the mtspr has been
+ * executed and the PMU has frozen the events etc.
+ * before we return.
+ */
+ write_mmcr0(cpuhw, val);
+ mb();
+
+ /*
* Disable instruction sampling if it was enabled
*/
if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) {
@@ -880,14 +909,8 @@
mb();
}
- /*
- * Set the 'freeze counters' bit.
- * The barrier is to make sure the mtspr has been
- * executed and the PMU has frozen the events
- * before we return.
- */
- write_mmcr0(cpuhw, mfspr(SPRN_MMCR0) | MMCR0_FC);
- mb();
+ cpuhw->disabled = 1;
+ cpuhw->n_added = 0;
}
local_irq_restore(flags);
}
@@ -911,12 +934,18 @@
if (!ppmu)
return;
+
local_irq_save(flags);
+
cpuhw = &__get_cpu_var(cpu_hw_events);
- if (!cpuhw->disabled) {
- local_irq_restore(flags);
- return;
+ if (!cpuhw->disabled)
+ goto out;
+
+ if (cpuhw->n_events == 0) {
+ ppc_set_pmu_inuse(0);
+ goto out;
}
+
cpuhw->disabled = 0;
/*
@@ -928,8 +957,6 @@
if (!cpuhw->n_added) {
mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
- if (cpuhw->n_events == 0)
- ppc_set_pmu_inuse(0);
goto out_enable;
}
@@ -1315,6 +1342,9 @@
if (ppmu->limited_pmc_event(ev))
return 1;
+ if (ppmu->flags & PPMU_ARCH_207S)
+ mtspr(SPRN_MMCR2, 0);
+
/*
* The requested event_id isn't on a limited PMC already;
* see if any alternative code goes on a limited PMC.
@@ -1409,7 +1439,7 @@
if (has_branch_stack(event)) {
/* PMU has BHRB enabled */
- if (!(ppmu->flags & PPMU_BHRB))
+ if (!(ppmu->flags & PPMU_ARCH_207S))
return -EOPNOTSUPP;
}
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index f7d1c4f..ee3b404 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -109,6 +109,16 @@
#define EVENT_IS_MARKED (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT)
#define EVENT_PSEL_MASK 0xff /* PMCxSEL value */
+#define EVENT_VALID_MASK \
+ ((EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \
+ (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \
+ (EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \
+ (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \
+ (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \
+ (EVENT_COMBINE_MASK << EVENT_COMBINE_SHIFT) | \
+ (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \
+ EVENT_PSEL_MASK)
+
/* MMCRA IFM bits - POWER8 */
#define POWER8_MMCRA_IFM1 0x0000000040000000UL
#define POWER8_MMCRA_IFM2 0x0000000080000000UL
@@ -184,6 +194,7 @@
#define MMCR1_UNIT_SHIFT(pmc) (60 - (4 * ((pmc) - 1)))
#define MMCR1_COMBINE_SHIFT(pmc) (35 - ((pmc) - 1))
#define MMCR1_PMCSEL_SHIFT(pmc) (24 - (((pmc) - 1)) * 8)
+#define MMCR1_FAB_SHIFT 36
#define MMCR1_DC_QUAL_SHIFT 47
#define MMCR1_IC_QUAL_SHIFT 46
@@ -212,6 +223,9 @@
mask = value = 0;
+ if (event & ~EVENT_VALID_MASK)
+ return -1;
+
pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK;
unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK;
cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK;
@@ -354,8 +368,8 @@
* the threshold bits are used for the match value.
*/
if (event_is_fab_match(event[i])) {
- mmcr1 |= (event[i] >> EVENT_THR_CTL_SHIFT) &
- EVENT_THR_CTL_MASK;
+ mmcr1 |= ((event[i] >> EVENT_THR_CTL_SHIFT) &
+ EVENT_THR_CTL_MASK) << MMCR1_FAB_SHIFT;
} else {
val = (event[i] >> EVENT_THR_CTL_SHIFT) & EVENT_THR_CTL_MASK;
mmcra |= val << MMCRA_THR_CTL_SHIFT;
@@ -378,6 +392,10 @@
if (pmc_inuse & 0x7c)
mmcr[0] |= MMCR0_PMCjCE;
+ /* If we're not using PMC 5 or 6, freeze them */
+ if (!(pmc_inuse & 0x60))
+ mmcr[0] |= MMCR0_FC56;
+
mmcr[1] = mmcr1;
mmcr[2] = mmcra;
@@ -574,7 +592,7 @@
.get_constraint = power8_get_constraint,
.get_alternatives = power8_get_alternatives,
.disable_pmc = power8_disable_pmc,
- .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB,
+ .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
.n_generic = ARRAY_SIZE(power8_generic_events),
.generic_events = power8_generic_events,
.attr_groups = power8_pmu_attr_groups,
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index 90f4496..af54174 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -57,5 +57,5 @@
config PPC_MPC5200_LPBFIFO
tristate "MPC5200 LocalPlus bus FIFO driver"
- depends on PPC_MPC52xx
+ depends on PPC_MPC52xx && PPC_BESTCOMM
select PPC_BESTCOMM_GEN_BD
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 18c1048..6e19b0a 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -199,8 +199,8 @@
static int __init efika_probe(void)
{
- char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
- "model", NULL);
+ const char *model = of_get_flat_dt_prop(of_get_flat_dt_root(),
+ "model", NULL);
if (model == NULL)
return 0;
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c
index 641e727..62f3e4e 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/platforms/cell/spu_fault.c
@@ -75,7 +75,7 @@
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
goto out_unlock;
- } else if (*flt & VM_FAULT_SIGBUS) {
+ } else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
ret = -EFAULT;
goto out_unlock;
}
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 35f77a4..c5c5788 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -164,7 +164,7 @@
struct dentry *dentry, *tmp;
mutex_lock(&dir->d_inode->i_mutex);
- list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+ list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
spin_lock(&dentry->d_lock);
if (!(d_unhashed(dentry)) && dentry->d_inode) {
dget_dlock(dentry);
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index c665d7d..7044fd3 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -574,8 +574,8 @@
static int __init chrp_probe(void)
{
- char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
- "device_type", NULL);
+ const char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
+ "device_type", NULL);
if (dtype == NULL)
return 0;
if (strcmp(dtype, "chrp"))
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 628c564..06620ea 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -35,8 +35,8 @@
int __init early_init_dt_scan_opal(unsigned long node,
const char *uname, int depth, void *data)
{
- const void *basep, *entryp;
- unsigned long basesz, entrysz;
+ const void *basep, *entryp, *sizep;
+ int basesz, entrysz, runtimesz;
if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
return 0;
@@ -50,10 +50,10 @@
opal.base = of_read_number(basep, basesz/4);
opal.entry = of_read_number(entryp, entrysz/4);
- pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%ld)\n",
+ pr_debug("OPAL Base = 0x%llx (basep=%p basesz=%d)\n",
opal.base, basep, basesz);
- pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
- opal.entry, entryp, entrysz);
+ pr_debug("OPAL Entry = 0x%llx (sizep=%p runtimesz=%d)\n",
+ opal.size, sizep, runtimesz);
powerpc_firmware_features |= FW_FEATURE_OPAL;
if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
@@ -105,7 +105,7 @@
opal_poll_events(&evt);
if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
return 0;
- len = count;
+ len = cpu_to_be64(count);
rc = opal_console_read(vtermno, &len, buf);
if (rc == OPAL_SUCCESS)
return len;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 9c9d15e..b2bbb79 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -151,13 +151,23 @@
rid_end = pe->rid + 1;
}
- /* Associate PE in PELT */
+ /*
+ * Associate PE in PELT. We need add the PE into the
+ * corresponding PELT-V as well. Otherwise, the error
+ * originated from the PE might contribute to other
+ * PEs.
+ */
rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
bcomp, dcomp, fcomp, OPAL_MAP_PE);
if (rc) {
pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
return -ENXIO;
}
+
+ rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+ pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
+ if (rc)
+ pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc);
opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
@@ -441,6 +451,17 @@
set_iommu_table_base(&pdev->dev, &pe->tce32_table);
}
+static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ set_iommu_table_base(&dev->dev, &pe->tce32_table);
+ if (dev->subordinate)
+ pnv_ioda_setup_bus_dma(pe, dev->subordinate);
+ }
+}
+
static void pnv_pci_ioda1_tce_invalidate(struct iommu_table *tbl,
u64 *startp, u64 *endp)
{
@@ -596,6 +617,11 @@
}
iommu_init_table(tbl, phb->hose->node);
+ if (pe->pdev)
+ set_iommu_table_base(&pe->pdev->dev, tbl);
+ else
+ pnv_ioda_setup_bus_dma(pe, pe->pbus);
+
return;
fail:
/* XXX Failure: Try to fallback to 64-bit only ? */
@@ -667,6 +693,11 @@
}
iommu_init_table(tbl, phb->hose->node);
+ if (pe->pdev)
+ set_iommu_table_base(&pe->pdev->dev, tbl);
+ else
+ pnv_ioda_setup_bus_dma(pe, pe->pbus);
+
return;
fail:
if (pe->tce32_seg >= 0)
@@ -758,7 +789,6 @@
unsigned int is_64, struct msi_msg *msg)
{
struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
- struct pci_dn *pdn = pci_get_pdn(dev);
struct irq_data *idata;
struct irq_chip *ichip;
unsigned int xive_num = hwirq - phb->msi_base;
@@ -775,7 +805,7 @@
return -ENXIO;
/* Force 32-bit MSI on some broken devices */
- if (pdn && pdn->force_32bit_msi)
+ if (dev->no_64bit_msi)
is_64 = 0;
/* Assign XIVE to PE */
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 277343c..8ee842c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -1,3 +1,4 @@
+
/*
* Support PCI/PCIe on PowerNV platforms
*
@@ -47,9 +48,8 @@
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
struct pnv_phb *phb = hose->private_data;
- struct pci_dn *pdn = pci_get_pdn(pdev);
- if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
+ if (pdev->no_64bit_msi && !phb->msi32_support)
return -ENODEV;
return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a1a7b9a..3d0b622 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -11,7 +11,6 @@
*/
#include <linux/kernel.h>
-#include <linux/kref.h>
#include <linux/notifier.h>
#include <linux/spinlock.h>
#include <linux/cpu.h>
@@ -83,6 +82,8 @@
return NULL;
}
+ of_node_set_flag(dn, OF_DYNAMIC);
+
return dn;
}
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index b456b15..68f97d5 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -400,6 +400,7 @@
} else {
result = EEH_STATE_NOT_SUPPORT;
}
+ break;
default:
result = EEH_STATE_NOT_SUPPORT;
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 217ca5c..adb36f2 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -34,12 +34,7 @@
#include "offline_states.h"
/* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
- .token = RTAS_UNKNOWN_SERVICE,
- .nargs = 0,
- .nret = 1,
- .rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
CPU_STATE_OFFLINE;
@@ -92,15 +87,20 @@
static void rtas_stop_self(void)
{
- struct rtas_args *args = &rtas_stop_self_args;
+ struct rtas_args args = {
+ .token = cpu_to_be32(rtas_stop_self_token),
+ .nargs = 0,
+ .nret = 1,
+ .rets = &args.args[0],
+ };
local_irq_disable();
- BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+ BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
printk("cpu %u (hwid %u) Ready to die...\n",
smp_processor_id(), hard_smp_processor_id());
- enter_rtas(__pa(args));
+ enter_rtas(__pa(&args));
panic("Alas, I survived.\n");
}
@@ -336,16 +336,17 @@
}
static int pseries_smp_notifier(struct notifier_block *nb,
- unsigned long action, void *node)
+ unsigned long action, void *data)
{
+ struct of_reconfig_data *rd = data;
int err = 0;
switch (action) {
case OF_RECONFIG_ATTACH_NODE:
- err = pseries_add_processor(node);
+ err = pseries_add_processor(rd->dn);
break;
case OF_RECONFIG_DETACH_NODE:
- pseries_remove_processor(node);
+ pseries_remove_processor(rd->dn);
break;
}
return notifier_from_errno(err);
@@ -391,10 +392,10 @@
}
}
- rtas_stop_self_args.token = rtas_token("stop-self");
+ rtas_stop_self_token = rtas_token("stop-self");
qcss_tok = rtas_token("query-cpu-stopped-state");
- if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+ if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
qcss_tok == RTAS_UNKNOWN_SERVICE) {
printk(KERN_INFO "CPU Hotplug not supported by firmware "
"- disabling.\n");
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 9a432de..87aa812 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -158,7 +158,7 @@
static inline int pseries_remove_memblock(unsigned long base,
unsigned int memblock_size)
{
- return -EOPNOTSUPP;
+ return 0;
}
static inline int pseries_remove_memory(struct device_node *np)
{
@@ -198,7 +198,7 @@
return (ret < 0) ? -EINVAL : 0;
}
-static int pseries_update_drconf_memory(struct of_prop_reconfig *pr)
+static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
{
struct of_drconf_cell *new_drmem, *old_drmem;
unsigned long memblock_size;
@@ -210,7 +210,7 @@
if (!memblock_size)
return -EINVAL;
- p = (u32 *)of_get_property(pr->dn, "ibm,dynamic-memory", NULL);
+ p = (u32 *) pr->old_prop->value;
if (!p)
return -EINVAL;
@@ -245,9 +245,9 @@
}
static int pseries_memory_notifier(struct notifier_block *nb,
- unsigned long action, void *node)
+ unsigned long action, void *data)
{
- struct of_prop_reconfig *pr;
+ struct of_reconfig_data *rd = data;
int err = 0;
switch (action) {
@@ -258,9 +258,8 @@
err = pseries_remove_memory(node);
break;
case OF_RECONFIG_UPDATE_PROPERTY:
- pr = (struct of_prop_reconfig *)node;
- if (!strcmp(pr->prop->name, "ibm,dynamic-memory"))
- err = pseries_update_drconf_memory(pr);
+ if (!strcmp(rd->prop->name, "ibm,dynamic-memory"))
+ err = pseries_update_drconf_memory(rd);
break;
}
return notifier_from_errno(err);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 86ae364..ed02eb4 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1325,10 +1325,11 @@
.notifier_call = iommu_mem_notifier,
};
-static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
+static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
{
int err = NOTIFY_OK;
- struct device_node *np = node;
+ struct of_reconfig_data *rd = data;
+ struct device_node *np = rd->dn;
struct pci_dn *pci = PCI_DN(np);
struct direct_window *window;
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 6d2f0ab..3b350fb 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -426,7 +426,7 @@
*/
again:
if (type == PCI_CAP_ID_MSI) {
- if (pdn->force_32bit_msi) {
+ if (pdev->no_64bit_msi) {
rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec);
if (rc < 0) {
/*
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index f93cdf5..0435bb6 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -12,7 +12,6 @@
*/
#include <linux/kernel.h>
-#include <linux/kref.h>
#include <linux/notifier.h>
#include <linux/proc_fs.h>
#include <linux/slab.h>
@@ -70,7 +69,6 @@
np->properties = proplist;
of_node_set_flag(np, OF_DYNAMIC);
- kref_init(&np->kref);
np->parent = derive_parent(path);
if (IS_ERR(np->parent)) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c11c823..de3a37d 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -253,9 +253,10 @@
" interrupt-controller\n");
}
-static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
+static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *data)
{
- struct device_node *np = node;
+ struct of_reconfig_data *rd = data;
+ struct device_node *np = rd->dn;
struct pci_dn *pci = NULL;
int err = NOTIFY_OK;
@@ -354,7 +355,7 @@
}
early_initcall(alloc_dispatch_log_kmem_cache);
-static void pSeries_idle(void)
+static void pseries_lpar_idle(void)
{
/* This would call on the cpuidle framework, and the back-end pseries
* driver to go to idle states
@@ -362,10 +363,22 @@
if (cpuidle_idle_call()) {
/* On error, execute default handler
* to go into low thread priority and possibly
- * low power mode.
+ * low power mode by cedeing processor to hypervisor
*/
- HMT_low();
- HMT_very_low();
+
+ /* Indicate to hypervisor that we are idle. */
+ get_lppaca()->idle = 1;
+
+ /*
+ * Yield the processor to the hypervisor. We return if
+ * an external interrupt occurs (which are driven prior
+ * to returning here) or if a prod occurs from another
+ * processor. When returning here, external interrupts
+ * are enabled.
+ */
+ cede_processor();
+
+ get_lppaca()->idle = 0;
}
}
@@ -456,15 +469,14 @@
pSeries_nvram_init();
- if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+ if (firmware_has_feature(FW_FEATURE_LPAR)) {
vpa_init(boot_cpuid);
- ppc_md.power_save = pSeries_idle;
- }
-
- if (firmware_has_feature(FW_FEATURE_LPAR))
+ ppc_md.power_save = pseries_lpar_idle;
ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
- else
+ } else {
+ /* No special idle routine */
ppc_md.enable_pmcs = power4_enable_pmcs;
+ }
ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
@@ -635,7 +647,7 @@
void *data)
{
const char *prop;
- unsigned long len;
+ int len;
static int hypertas_found;
static int vec5_found;
@@ -668,7 +680,7 @@
static int __init pSeries_probe(void)
{
unsigned long root = of_get_flat_dt_root();
- char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+ const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
if (dtype == NULL)
return 0;
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 1c16141..1fea249 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -155,7 +155,7 @@
}
*kaddr = (void *)(bank->ph_addr + offset);
- *pfn = virt_to_phys(kaddr) >> PAGE_SHIFT;
+ *pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
return 0;
}
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 0968b66..8ba6042 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -202,7 +202,7 @@
/* There should really be a struct device_node allocator */
memset(&of_node, 0, sizeof(of_node));
- kref_init(&of_node.kref);
+ kref_init(&of_node.kobj.kref);
of_node.full_name = node_name;
check(0 == msi_bitmap_alloc(&bmp, size, &of_node));
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 96bf5bd..89e5728 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -288,10 +288,11 @@
args.token = rtas_token("set-indicator");
if (args.token == RTAS_UNKNOWN_SERVICE)
return;
- args.nargs = 3;
- args.nret = 1;
+ args.token = cpu_to_be32(args.token);
+ args.nargs = cpu_to_be32(3);
+ args.nret = cpu_to_be32(1);
args.rets = &args.args[3];
- args.args[0] = SURVEILLANCE_TOKEN;
+ args.args[0] = cpu_to_be32(SURVEILLANCE_TOKEN);
args.args[1] = 0;
args.args[2] = 0;
enter_rtas(__pa(&args));
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index da183c5..61ea838 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -62,6 +62,7 @@
def_bool y
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+ select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_INLINE_READ_LOCK
select ARCH_INLINE_READ_LOCK_BH
@@ -116,6 +117,7 @@
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZMA
@@ -227,11 +229,12 @@
not work on older machines.
config MARCH_ZEC12
- bool "IBM zEC12"
+ bool "IBM zBC12 and zEC12"
select HAVE_MARCH_ZEC12_FEATURES if 64BIT
help
- Select this to enable optimizations for IBM zEC12 (2827 series). The
- kernel will be slightly faster but will not work on older machines.
+ Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and
+ 2827 series). The kernel will be slightly faster but will not work on
+ older machines.
endchoice
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index b4dbade8..92eb4d6 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -25,6 +25,7 @@
#include <linux/err.h>
#include <linux/module.h>
#include <linux/init.h>
+#include <linux/spinlock.h>
#include "crypt_s390.h"
#define AES_KEYLEN_128 1
@@ -32,10 +33,10 @@
#define AES_KEYLEN_256 4
static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
static char keylen_flag;
struct s390_aes_ctx {
- u8 iv[AES_BLOCK_SIZE];
u8 key[AES_MAX_KEY_SIZE];
long enc;
long dec;
@@ -56,8 +57,7 @@
struct s390_xts_ctx {
u8 key[32];
- u8 xts_param[16];
- struct pcc_param pcc;
+ u8 pcc_key[32];
long enc;
long dec;
int key_len;
@@ -441,30 +441,36 @@
return aes_set_key(tfm, in_key, key_len);
}
-static int cbc_aes_crypt(struct blkcipher_desc *desc, long func, void *param,
+static int cbc_aes_crypt(struct blkcipher_desc *desc, long func,
struct blkcipher_walk *walk)
{
+ struct s390_aes_ctx *sctx = crypto_blkcipher_ctx(desc->tfm);
int ret = blkcipher_walk_virt(desc, walk);
unsigned int nbytes = walk->nbytes;
+ struct {
+ u8 iv[AES_BLOCK_SIZE];
+ u8 key[AES_MAX_KEY_SIZE];
+ } param;
if (!nbytes)
goto out;
- memcpy(param, walk->iv, AES_BLOCK_SIZE);
+ memcpy(param.iv, walk->iv, AES_BLOCK_SIZE);
+ memcpy(param.key, sctx->key, sctx->key_len);
do {
/* only use complete blocks */
unsigned int n = nbytes & ~(AES_BLOCK_SIZE - 1);
u8 *out = walk->dst.virt.addr;
u8 *in = walk->src.virt.addr;
- ret = crypt_s390_kmc(func, param, out, in, n);
+ ret = crypt_s390_kmc(func, ¶m, out, in, n);
if (ret < 0 || ret != n)
return -EIO;
nbytes &= AES_BLOCK_SIZE - 1;
ret = blkcipher_walk_done(desc, walk, nbytes);
} while ((nbytes = walk->nbytes));
- memcpy(walk->iv, param, AES_BLOCK_SIZE);
+ memcpy(walk->iv, param.iv, AES_BLOCK_SIZE);
out:
return ret;
@@ -481,7 +487,7 @@
return fallback_blk_enc(desc, dst, src, nbytes);
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_aes_crypt(desc, sctx->enc, sctx->iv, &walk);
+ return cbc_aes_crypt(desc, sctx->enc, &walk);
}
static int cbc_aes_decrypt(struct blkcipher_desc *desc,
@@ -495,7 +501,7 @@
return fallback_blk_dec(desc, dst, src, nbytes);
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_aes_crypt(desc, sctx->dec, sctx->iv, &walk);
+ return cbc_aes_crypt(desc, sctx->dec, &walk);
}
static struct crypto_alg cbc_aes_alg = {
@@ -586,7 +592,7 @@
xts_ctx->enc = KM_XTS_128_ENCRYPT;
xts_ctx->dec = KM_XTS_128_DECRYPT;
memcpy(xts_ctx->key + 16, in_key, 16);
- memcpy(xts_ctx->pcc.key + 16, in_key + 16, 16);
+ memcpy(xts_ctx->pcc_key + 16, in_key + 16, 16);
break;
case 48:
xts_ctx->enc = 0;
@@ -597,7 +603,7 @@
xts_ctx->enc = KM_XTS_256_ENCRYPT;
xts_ctx->dec = KM_XTS_256_DECRYPT;
memcpy(xts_ctx->key, in_key, 32);
- memcpy(xts_ctx->pcc.key, in_key + 32, 32);
+ memcpy(xts_ctx->pcc_key, in_key + 32, 32);
break;
default:
*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
@@ -616,29 +622,33 @@
unsigned int nbytes = walk->nbytes;
unsigned int n;
u8 *in, *out;
- void *param;
+ struct pcc_param pcc_param;
+ struct {
+ u8 key[32];
+ u8 init[16];
+ } xts_param;
if (!nbytes)
goto out;
- memset(xts_ctx->pcc.block, 0, sizeof(xts_ctx->pcc.block));
- memset(xts_ctx->pcc.bit, 0, sizeof(xts_ctx->pcc.bit));
- memset(xts_ctx->pcc.xts, 0, sizeof(xts_ctx->pcc.xts));
- memcpy(xts_ctx->pcc.tweak, walk->iv, sizeof(xts_ctx->pcc.tweak));
- param = xts_ctx->pcc.key + offset;
- ret = crypt_s390_pcc(func, param);
+ memset(pcc_param.block, 0, sizeof(pcc_param.block));
+ memset(pcc_param.bit, 0, sizeof(pcc_param.bit));
+ memset(pcc_param.xts, 0, sizeof(pcc_param.xts));
+ memcpy(pcc_param.tweak, walk->iv, sizeof(pcc_param.tweak));
+ memcpy(pcc_param.key, xts_ctx->pcc_key, 32);
+ ret = crypt_s390_pcc(func, &pcc_param.key[offset]);
if (ret < 0)
return -EIO;
- memcpy(xts_ctx->xts_param, xts_ctx->pcc.xts, 16);
- param = xts_ctx->key + offset;
+ memcpy(xts_param.key, xts_ctx->key, 32);
+ memcpy(xts_param.init, pcc_param.xts, 16);
do {
/* only use complete blocks */
n = nbytes & ~(AES_BLOCK_SIZE - 1);
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
- ret = crypt_s390_km(func, param, out, in, n);
+ ret = crypt_s390_km(func, &xts_param.key[offset], out, in, n);
if (ret < 0 || ret != n)
return -EIO;
@@ -748,43 +758,70 @@
return aes_set_key(tfm, in_key, key_len);
}
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+ unsigned int i, n;
+
+ /* only use complete blocks, max. PAGE_SIZE */
+ n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(AES_BLOCK_SIZE - 1);
+ for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
+ memcpy(ctrptr + i, ctrptr + i - AES_BLOCK_SIZE,
+ AES_BLOCK_SIZE);
+ crypto_inc(ctrptr + i, AES_BLOCK_SIZE);
+ }
+ return n;
+}
+
static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
struct s390_aes_ctx *sctx, struct blkcipher_walk *walk)
{
int ret = blkcipher_walk_virt_block(desc, walk, AES_BLOCK_SIZE);
- unsigned int i, n, nbytes;
- u8 buf[AES_BLOCK_SIZE];
- u8 *out, *in;
+ unsigned int n, nbytes;
+ u8 buf[AES_BLOCK_SIZE], ctrbuf[AES_BLOCK_SIZE];
+ u8 *out, *in, *ctrptr = ctrbuf;
if (!walk->nbytes)
return ret;
- memcpy(ctrblk, walk->iv, AES_BLOCK_SIZE);
+ if (spin_trylock(&ctrblk_lock))
+ ctrptr = ctrblk;
+
+ memcpy(ctrptr, walk->iv, AES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= AES_BLOCK_SIZE) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
while (nbytes >= AES_BLOCK_SIZE) {
- /* only use complete blocks, max. PAGE_SIZE */
- n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
- nbytes & ~(AES_BLOCK_SIZE - 1);
- for (i = AES_BLOCK_SIZE; i < n; i += AES_BLOCK_SIZE) {
- memcpy(ctrblk + i, ctrblk + i - AES_BLOCK_SIZE,
- AES_BLOCK_SIZE);
- crypto_inc(ctrblk + i, AES_BLOCK_SIZE);
- }
- ret = crypt_s390_kmctr(func, sctx->key, out, in, n, ctrblk);
- if (ret < 0 || ret != n)
+ if (ctrptr == ctrblk)
+ n = __ctrblk_init(ctrptr, nbytes);
+ else
+ n = AES_BLOCK_SIZE;
+ ret = crypt_s390_kmctr(func, sctx->key, out, in,
+ n, ctrptr);
+ if (ret < 0 || ret != n) {
+ if (ctrptr == ctrblk)
+ spin_unlock(&ctrblk_lock);
return -EIO;
+ }
if (n > AES_BLOCK_SIZE)
- memcpy(ctrblk, ctrblk + n - AES_BLOCK_SIZE,
+ memcpy(ctrptr, ctrptr + n - AES_BLOCK_SIZE,
AES_BLOCK_SIZE);
- crypto_inc(ctrblk, AES_BLOCK_SIZE);
+ crypto_inc(ctrptr, AES_BLOCK_SIZE);
out += n;
in += n;
nbytes -= n;
}
ret = blkcipher_walk_done(desc, walk, nbytes);
}
+ if (ctrptr == ctrblk) {
+ if (nbytes)
+ memcpy(ctrbuf, ctrptr, AES_BLOCK_SIZE);
+ else
+ memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+ spin_unlock(&ctrblk_lock);
+ } else {
+ if (!nbytes)
+ memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
+ }
/*
* final block may be < AES_BLOCK_SIZE, copy only nbytes
*/
@@ -792,14 +829,15 @@
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
ret = crypt_s390_kmctr(func, sctx->key, buf, in,
- AES_BLOCK_SIZE, ctrblk);
+ AES_BLOCK_SIZE, ctrbuf);
if (ret < 0 || ret != AES_BLOCK_SIZE)
return -EIO;
memcpy(out, buf, nbytes);
- crypto_inc(ctrblk, AES_BLOCK_SIZE);
+ crypto_inc(ctrbuf, AES_BLOCK_SIZE);
ret = blkcipher_walk_done(desc, walk, 0);
+ memcpy(walk->iv, ctrbuf, AES_BLOCK_SIZE);
}
- memcpy(walk->iv, ctrblk, AES_BLOCK_SIZE);
+
return ret;
}
@@ -932,7 +970,7 @@
module_init(aes_s390_init);
module_exit(aes_s390_fini);
-MODULE_ALIAS("aes-all");
+MODULE_ALIAS_CRYPTO("aes-all");
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
MODULE_LICENSE("GPL");
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index bcca01c..a89feff 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -25,6 +25,7 @@
#define DES3_KEY_SIZE (3 * DES_KEY_SIZE)
static u8 *ctrblk;
+static DEFINE_SPINLOCK(ctrblk_lock);
struct s390_des_ctx {
u8 iv[DES_BLOCK_SIZE];
@@ -105,29 +106,35 @@
}
static int cbc_desall_crypt(struct blkcipher_desc *desc, long func,
- u8 *iv, struct blkcipher_walk *walk)
+ struct blkcipher_walk *walk)
{
+ struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
int ret = blkcipher_walk_virt(desc, walk);
unsigned int nbytes = walk->nbytes;
+ struct {
+ u8 iv[DES_BLOCK_SIZE];
+ u8 key[DES3_KEY_SIZE];
+ } param;
if (!nbytes)
goto out;
- memcpy(iv, walk->iv, DES_BLOCK_SIZE);
+ memcpy(param.iv, walk->iv, DES_BLOCK_SIZE);
+ memcpy(param.key, ctx->key, DES3_KEY_SIZE);
do {
/* only use complete blocks */
unsigned int n = nbytes & ~(DES_BLOCK_SIZE - 1);
u8 *out = walk->dst.virt.addr;
u8 *in = walk->src.virt.addr;
- ret = crypt_s390_kmc(func, iv, out, in, n);
+ ret = crypt_s390_kmc(func, ¶m, out, in, n);
if (ret < 0 || ret != n)
return -EIO;
nbytes &= DES_BLOCK_SIZE - 1;
ret = blkcipher_walk_done(desc, walk, nbytes);
} while ((nbytes = walk->nbytes));
- memcpy(walk->iv, iv, DES_BLOCK_SIZE);
+ memcpy(walk->iv, param.iv, DES_BLOCK_SIZE);
out:
return ret;
@@ -179,22 +186,20 @@
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_DEA_ENCRYPT, &walk);
}
static int cbc_des_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_DEA_DECRYPT, &walk);
}
static struct crypto_alg cbc_des_alg = {
@@ -327,22 +332,20 @@
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_TDEA_192_ENCRYPT, &walk);
}
static int cbc_des3_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
- struct s390_des_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
struct blkcipher_walk walk;
blkcipher_walk_init(&walk, dst, src, nbytes);
- return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, ctx->iv, &walk);
+ return cbc_desall_crypt(desc, KMC_TDEA_192_DECRYPT, &walk);
}
static struct crypto_alg cbc_des3_alg = {
@@ -366,54 +369,83 @@
}
};
+static unsigned int __ctrblk_init(u8 *ctrptr, unsigned int nbytes)
+{
+ unsigned int i, n;
+
+ /* align to block size, max. PAGE_SIZE */
+ n = (nbytes > PAGE_SIZE) ? PAGE_SIZE : nbytes & ~(DES_BLOCK_SIZE - 1);
+ for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
+ memcpy(ctrptr + i, ctrptr + i - DES_BLOCK_SIZE, DES_BLOCK_SIZE);
+ crypto_inc(ctrptr + i, DES_BLOCK_SIZE);
+ }
+ return n;
+}
+
static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
- struct s390_des_ctx *ctx, struct blkcipher_walk *walk)
+ struct s390_des_ctx *ctx,
+ struct blkcipher_walk *walk)
{
int ret = blkcipher_walk_virt_block(desc, walk, DES_BLOCK_SIZE);
- unsigned int i, n, nbytes;
- u8 buf[DES_BLOCK_SIZE];
- u8 *out, *in;
+ unsigned int n, nbytes;
+ u8 buf[DES_BLOCK_SIZE], ctrbuf[DES_BLOCK_SIZE];
+ u8 *out, *in, *ctrptr = ctrbuf;
- memcpy(ctrblk, walk->iv, DES_BLOCK_SIZE);
+ if (!walk->nbytes)
+ return ret;
+
+ if (spin_trylock(&ctrblk_lock))
+ ctrptr = ctrblk;
+
+ memcpy(ctrptr, walk->iv, DES_BLOCK_SIZE);
while ((nbytes = walk->nbytes) >= DES_BLOCK_SIZE) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
while (nbytes >= DES_BLOCK_SIZE) {
- /* align to block size, max. PAGE_SIZE */
- n = (nbytes > PAGE_SIZE) ? PAGE_SIZE :
- nbytes & ~(DES_BLOCK_SIZE - 1);
- for (i = DES_BLOCK_SIZE; i < n; i += DES_BLOCK_SIZE) {
- memcpy(ctrblk + i, ctrblk + i - DES_BLOCK_SIZE,
- DES_BLOCK_SIZE);
- crypto_inc(ctrblk + i, DES_BLOCK_SIZE);
- }
- ret = crypt_s390_kmctr(func, ctx->key, out, in, n, ctrblk);
- if (ret < 0 || ret != n)
+ if (ctrptr == ctrblk)
+ n = __ctrblk_init(ctrptr, nbytes);
+ else
+ n = DES_BLOCK_SIZE;
+ ret = crypt_s390_kmctr(func, ctx->key, out, in,
+ n, ctrptr);
+ if (ret < 0 || ret != n) {
+ if (ctrptr == ctrblk)
+ spin_unlock(&ctrblk_lock);
return -EIO;
+ }
if (n > DES_BLOCK_SIZE)
- memcpy(ctrblk, ctrblk + n - DES_BLOCK_SIZE,
+ memcpy(ctrptr, ctrptr + n - DES_BLOCK_SIZE,
DES_BLOCK_SIZE);
- crypto_inc(ctrblk, DES_BLOCK_SIZE);
+ crypto_inc(ctrptr, DES_BLOCK_SIZE);
out += n;
in += n;
nbytes -= n;
}
ret = blkcipher_walk_done(desc, walk, nbytes);
}
-
+ if (ctrptr == ctrblk) {
+ if (nbytes)
+ memcpy(ctrbuf, ctrptr, DES_BLOCK_SIZE);
+ else
+ memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+ spin_unlock(&ctrblk_lock);
+ } else {
+ if (!nbytes)
+ memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
+ }
/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
if (nbytes) {
out = walk->dst.virt.addr;
in = walk->src.virt.addr;
ret = crypt_s390_kmctr(func, ctx->key, buf, in,
- DES_BLOCK_SIZE, ctrblk);
+ DES_BLOCK_SIZE, ctrbuf);
if (ret < 0 || ret != DES_BLOCK_SIZE)
return -EIO;
memcpy(out, buf, nbytes);
- crypto_inc(ctrblk, DES_BLOCK_SIZE);
+ crypto_inc(ctrbuf, DES_BLOCK_SIZE);
ret = blkcipher_walk_done(desc, walk, 0);
+ memcpy(walk->iv, ctrbuf, DES_BLOCK_SIZE);
}
- memcpy(walk->iv, ctrblk, DES_BLOCK_SIZE);
return ret;
}
@@ -587,8 +619,8 @@
module_init(des_s390_init);
module_exit(des_s390_exit);
-MODULE_ALIAS("des");
-MODULE_ALIAS("des3_ede");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des3_ede");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index d43485d..7940dc9 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -160,7 +160,7 @@
module_init(ghash_mod_init);
module_exit(ghash_mod_exit);
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation");
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index a1b3a9d..5b2bee3 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -103,6 +103,6 @@
module_init(sha1_s390_init);
module_exit(sha1_s390_fini);
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 9b85380..b74ff15 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -143,7 +143,7 @@
module_init(sha256_s390_init);
module_exit(sha256_s390_fini);
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm");
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 32a8138..0c36989 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -86,7 +86,7 @@
}
};
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha512");
static int sha384_init(struct shash_desc *desc)
{
@@ -126,7 +126,7 @@
}
};
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha384");
static int __init init(void)
{
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 4d8604e..7d46767 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -693,7 +693,7 @@
size -= offset;
p = addr + offset / BITS_PER_LONG;
if (bit) {
- set = __flo_word(0, *p & (~0UL << bit));
+ set = __flo_word(0, *p & (~0UL >> bit));
if (set >= size)
return size + offset;
if (set < BITS_PER_LONG)
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8..31b5ca8 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,7 @@
#define to_ccwdev(n) container_of(n, struct ccw_device, dev)
#define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_probe_console(struct ccw_driver *);
extern void ccw_device_wait_idle(struct ccw_device *);
extern int ccw_device_force_console(struct ccw_device *);
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 6c32190..346b1c8 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -15,7 +15,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("0: brcl 0,0\n"
+ asm_volatile_goto("0: brcl 0,0\n"
".pushsection __jump_table, \"aw\"\n"
ASM_ALIGN "\n"
ASM_PTR " 0b, %l[label], %0\n"
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 16bd5d1..99971df 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -13,8 +13,11 @@
#ifndef ASM_KVM_HOST_H
#define ASM_KVM_HOST_H
+
+#include <linux/types.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
+#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#include <asm/debug.h>
#include <asm/cpu.h>
@@ -266,4 +269,18 @@
};
extern int sie64a(struct kvm_s390_sie_block *, u64 *);
+
+static inline void kvm_arch_hardware_disable(void) {}
+static inline void kvm_arch_check_processor_compat(void *rtn) {}
+static inline void kvm_arch_exit(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
+static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot) {}
+
#endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index bbf8141..2bed4f0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -142,9 +142,9 @@
__u8 pad_0x02fc[0x0300-0x02fc]; /* 0x02fc */
/* Interrupt response block */
- __u8 irb[64]; /* 0x0300 */
+ __u8 irb[96]; /* 0x0300 */
- __u8 pad_0x0340[0x0e00-0x0340]; /* 0x0340 */
+ __u8 pad_0x0360[0x0e00-0x0360]; /* 0x0360 */
/*
* 0xe00 contains the address of the IPL Parameter Information
@@ -288,12 +288,13 @@
__u8 pad_0x03a0[0x0400-0x03a0]; /* 0x03a0 */
/* Interrupt response block. */
- __u8 irb[64]; /* 0x0400 */
+ __u8 irb[96]; /* 0x0400 */
+ __u8 pad_0x0460[0x0480-0x0460]; /* 0x0460 */
/* Per cpu primary space access list */
- __u32 paste[16]; /* 0x0440 */
+ __u32 paste[16]; /* 0x0480 */
- __u8 pad_0x0480[0x0e00-0x0480]; /* 0x0480 */
+ __u8 pad_0x04c0[0x0e00-0x04c0]; /* 0x04c0 */
/*
* 0xe00 contains the address of the IPL Parameter Information
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d6..6d6d92b 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@
struct mm_struct *mm;
struct mmu_table_batch *batch;
unsigned int fullmm;
+ unsigned long start, end;
};
struct mmu_table_batch {
@@ -48,10 +49,13 @@
static inline void tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm,
- unsigned int full_mm_flush)
+ unsigned long start,
+ unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
tlb->batch = NULL;
if (tlb->fullmm)
__tlb_flush_mm(mm);
diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h
index a61d538..471eb09 100644
--- a/arch/s390/include/uapi/asm/statfs.h
+++ b/arch/s390/include/uapi/asm/statfs.h
@@ -35,11 +35,11 @@
struct statfs64 {
unsigned int f_type;
unsigned int f_bsize;
- unsigned long f_blocks;
- unsigned long f_bfree;
- unsigned long f_bavail;
- unsigned long f_files;
- unsigned long f_ffree;
+ unsigned long long f_blocks;
+ unsigned long long f_bfree;
+ unsigned long long f_bavail;
+ unsigned long long f_files;
+ unsigned long long f_ffree;
__kernel_fsid_t f_fsid;
unsigned int f_namelen;
unsigned int f_frsize;
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index 8b6e4f5..a98afed9 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -248,7 +248,7 @@
struct group_info *group_info;
int retval;
- if (!capable(CAP_SETGID))
+ if (!may_setgroups())
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 4d5e6f8..32bb7bf 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -265,6 +265,7 @@
tm __TI_flags+3(%r12),_TIF_SYSCALL
jno sysc_return
lm %r2,%r7,__PT_R2(%r11) # load svc arguments
+ l %r10,__TI_sysc_table(%r12) # 31 bit system call table
xr %r8,%r8 # svc 0 returns -ENOSYS
clc __PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2)
jnl sysc_nr_ok # invalid svc number -> do svc 0
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 4c17eec..2e3befd 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -293,6 +293,7 @@
tm __TI_flags+7(%r12),_TIF_SYSCALL
jno sysc_return
lmg %r2,%r7,__PT_R2(%r11) # load svc arguments
+ lg %r10,__TI_sysc_table(%r12) # address of system call table
lghi %r8,0 # svc 0 returns -ENOSYS
llgh %r1,__PT_INT_CODE+2(%r11) # load new svc number
cghi %r1,NR_syscalls
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index b9e25ae..d7c0050 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -59,7 +59,7 @@
.quad 0 # cr12: tracing off
.quad 0 # cr13: home space segment table
.quad 0xc0000000 # cr14: machine check handling off
- .quad 0 # cr15: linkage stack operations
+ .quad .Llinkage_stack # cr15: linkage stack operations
.Lpcmsk:.quad 0x0000000180000000
.L4malign:.quad 0xffffffffffc00000
.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8
@@ -67,12 +67,15 @@
.Lparmaddr:
.quad PARMAREA
.align 64
-.Lduct: .long 0,0,0,0,.Lduald,0,0,0
+.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0
.long 0,0,0,0,0,0,0,0
+.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0
.align 128
.Lduald:.rept 8
.long 0x80000000,0,0,0 # invalid access-list entries
.endr
+.Llinkage_stack:
+ .long 0,0,0x89000000,0,0,0,0x8a000000,0
ENTRY(_ehead)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index a314c57..9677d93 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -314,7 +314,9 @@
* psw and gprs are stored on the stack
*/
if (addr == (addr_t) &dummy->regs.psw.mask &&
- ((data & ~PSW_MASK_USER) != psw_user_bits ||
+ (((data^psw_user_bits) & ~PSW_MASK_USER) ||
+ (((data^psw_user_bits) & PSW_MASK_ASC) &&
+ ((data|psw_user_bits) & PSW_MASK_ASC) == PSW_MASK_ASC) ||
((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
/* Invalid psw mask. */
return -EINVAL;
@@ -627,7 +629,10 @@
*/
if (addr == (addr_t) &dummy32->regs.psw.mask) {
/* Build a 64 bit psw mask from 31 bit mask. */
- if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits)
+ if (((tmp^psw32_user_bits) & ~PSW32_MASK_USER) ||
+ (((tmp^psw32_user_bits) & PSW32_MASK_ASC) &&
+ ((tmp|psw32_user_bits) & PSW32_MASK_ASC)
+ == PSW32_MASK_ASC))
/* Invalid psw mask. */
return -EINVAL;
regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 0a49095..8ad9413 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -998,6 +998,7 @@
strcpy(elf_platform, "z196");
break;
case 0x2827:
+ case 0x2828:
strcpy(elf_platform, "zEC12");
break;
}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 4f977d0..14647fe 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -933,7 +933,7 @@
idle_count = ACCESS_ONCE(idle->idle_count);
if (ACCESS_ONCE(idle->clock_idle_enter))
idle_count++;
- } while ((sequence & 1) || (idle->sequence != sequence));
+ } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
return sprintf(buf, "%llu\n", idle_count);
}
static DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
@@ -951,7 +951,7 @@
idle_time = ACCESS_ONCE(idle->idle_time);
idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
- } while ((sequence & 1) || (idle->sequence != sequence));
+ } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
return sprintf(buf, "%llu\n", idle_time >> 12);
}
diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c
index c479d2f..58cbb75 100644
--- a/arch/s390/kernel/suspend.c
+++ b/arch/s390/kernel/suspend.c
@@ -9,12 +9,9 @@
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm.h>
+#include <asm/sections.h>
#include <asm/ctl_reg.h>
-
-/*
- * References to section boundaries
- */
-extern const void __nosave_begin, __nosave_end;
+#include <asm/ipl.h>
/*
* The restore of the saved pages in an hibernation image will set
@@ -138,6 +135,8 @@
{
unsigned long nosave_begin_pfn = PFN_DOWN(__pa(&__nosave_begin));
unsigned long nosave_end_pfn = PFN_DOWN(__pa(&__nosave_end));
+ unsigned long eshared_pfn = PFN_DOWN(__pa(&_eshared)) - 1;
+ unsigned long stext_pfn = PFN_DOWN(__pa(&_stext));
/* Always save lowcore pages (LC protection might be enabled). */
if (pfn <= LC_PAGES)
@@ -145,6 +144,8 @@
if (pfn >= nosave_begin_pfn && pfn < nosave_end_pfn)
return 1;
/* Skip memory holes and read-only pages (NSS, DCSS, ...). */
+ if (pfn >= stext_pfn && pfn <= eshared_pfn)
+ return ipl_info.type == IPL_TYPE_NSS ? 1 : 0;
if (tprot(PFN_PHYS(pfn)))
return 1;
return 0;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 3fb0935..737d50c 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -190,7 +190,7 @@
sequence = ACCESS_ONCE(idle->sequence);
idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
- } while ((sequence & 1) || (idle->sequence != sequence));
+ } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence));
return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
}
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 8fe9d65..40b4c64 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -6,7 +6,8 @@
# it under the terms of the GNU General Public License (version 2 only)
# as published by the Free Software Foundation.
-common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o eventfd.o)
+KVM := ../../../virt/kvm
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 1c01a99..6acb24d 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -130,7 +130,7 @@
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
{
- int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+ int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
trace_kvm_s390_handle_diag(vcpu, code);
switch (code) {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5c94817..bc79ab0 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -71,6 +71,7 @@
return 0;
if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
return 1;
+ return 0;
case KVM_S390_INT_EMERGENCY:
if (psw_extint_disabled(vcpu))
return 0;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c1c7c68..412fbc5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -86,16 +86,12 @@
static unsigned long long *facilities;
/* Section: not file related */
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
/* every s390 is virtualization enabled ;-) */
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
int kvm_arch_hardware_setup(void)
{
return 0;
@@ -105,19 +101,11 @@
{
}
-void kvm_arch_check_processor_compat(void *rtn)
-{
-}
-
int kvm_arch_init(void *opaque)
{
return 0;
}
-void kvm_arch_exit(void)
-{
-}
-
/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
@@ -127,7 +115,7 @@
return -EINVAL;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -289,10 +277,6 @@
mutex_unlock(&kvm->lock);
}
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
@@ -320,11 +304,6 @@
return 0;
}
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
- /* Nothing todo */
-}
-
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
save_fp_regs(&vcpu->arch.host_fpregs);
@@ -622,14 +601,25 @@
kvm_s390_deliver_pending_interrupts(vcpu);
vcpu->arch.sie_block->icptcode = 0;
- preempt_disable();
- kvm_guest_enter();
- preempt_enable();
VCPU_EVENT(vcpu, 6, "entering sie flags %x",
atomic_read(&vcpu->arch.sie_block->cpuflags));
trace_kvm_s390_sie_enter(vcpu,
atomic_read(&vcpu->arch.sie_block->cpuflags));
+
+ /*
+ * As PF_VCPU will be used in fault handler, between guest_enter
+ * and guest_exit should be no uaccess.
+ */
+ preempt_disable();
+ kvm_guest_enter();
+ preempt_enable();
rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+ kvm_guest_exit();
+
+ VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+ vcpu->arch.sie_block->icptcode);
+ trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
+
if (rc) {
if (kvm_is_ucontrol(vcpu->kvm)) {
rc = SIE_INTERCEPT_UCONTROL;
@@ -639,10 +629,6 @@
rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
}
}
- VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
- vcpu->arch.sie_block->icptcode);
- trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
- kvm_guest_exit();
memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
return rc;
@@ -964,12 +950,8 @@
return VM_FAULT_SIGBUS;
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
- struct kvm_memory_slot *dont)
-{
-}
-
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
return 0;
}
@@ -1019,15 +1001,6 @@
return;
}
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
-void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
- struct kvm_memory_slot *slot)
-{
-}
-
static int __init kvm_s390_init(void)
{
int ret;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 6bbd7b5..0220c2b 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -328,6 +328,7 @@
for (n = mem->count - 1; n > 0 ; n--)
memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
+ memset(&mem->vm[0], 0, sizeof(mem->vm[0]));
mem->vm[0].cpus_total = cpus;
mem->vm[0].cpus_configured = cpus;
mem->vm[0].cpus_standby = 0;
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 50ea137..1bf40ef 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -78,11 +78,14 @@
* contains the (negative) exception code.
*/
#ifdef CONFIG_64BIT
+
static unsigned long follow_table(struct mm_struct *mm,
unsigned long address, int write)
{
unsigned long *table = (unsigned long *)__pa(mm->pgd);
+ if (unlikely(address > mm->context.asce_limit - 1))
+ return -0x38UL;
switch (mm->context.asce_bits & _ASCE_TYPE_MASK) {
case _ASCE_TYPE_REGION1:
table = table + ((address >> 53) & 0x7ff);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 047c3e4..d214321 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -244,6 +244,12 @@
do_no_context(regs);
else
pagefault_out_of_memory();
+ } else if (fault & VM_FAULT_SIGSEGV) {
+ /* Kernel mode? Handle exceptions or die */
+ if (!user_mode(regs))
+ do_no_context(regs);
+ else
+ do_sigsegv(regs, SEGV_MAPERR);
} else if (fault & VM_FAULT_SIGBUS) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
@@ -302,6 +308,8 @@
address = trans_exc_code & __FAIL_ADDR_MASK;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
flags |= FAULT_FLAG_WRITE;
down_read(&mm->mmap_sem);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 89ebae4..a4dfc0b 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -43,6 +43,7 @@
unsigned long empty_zero_page, zero_page_mask;
EXPORT_SYMBOL(empty_zero_page);
+EXPORT_SYMBOL(zero_page_mask);
static void __init setup_zero_pages(void)
{
@@ -69,6 +70,7 @@
order = 2;
break;
case 0x2827: /* zEC12 */
+ case 0x2828: /* zEC12 */
default:
order = 5;
break;
diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index a90d45e..27c50f4 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -12,6 +12,8 @@
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/init.h>
+#include <asm/setup.h>
+#include <asm/ipl.h>
#define ESSA_SET_STABLE 1
#define ESSA_SET_UNUSED 2
@@ -41,6 +43,14 @@
if (!cmma_flag)
return;
+ /*
+ * Disable CMM for dump, otherwise the tprot based memory
+ * detection can fail because of unstable pages.
+ */
+ if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) {
+ cmma_flag = 0;
+ return;
+ }
asm volatile(
" .insn rrf,0xb9ab0000,%1,%1,0,0\n"
"0: la %0,0\n"
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 82f165f..3bc6b7e 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -243,7 +243,6 @@
case BPF_S_LD_W_IND:
case BPF_S_LD_H_IND:
case BPF_S_LD_B_IND:
- case BPF_S_LDX_B_MSH:
case BPF_S_LD_IMM:
case BPF_S_LD_MEM:
case BPF_S_MISC_TXA:
@@ -335,14 +334,16 @@
EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
/* lhi %r4,0 */
EMIT4(0xa7480000);
- /* dr %r4,%r12 */
- EMIT2(0x1d4c);
+ /* dlr %r4,%r12 */
+ EMIT4(0xb997004c);
break;
- case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
- /* m %r4,<d(K)>(%r13) */
- EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
- /* lr %r5,%r4 */
- EMIT2(0x1854);
+ case BPF_S_ALU_DIV_K: /* A /= K */
+ if (K == 1)
+ break;
+ /* lhi %r4,0 */
+ EMIT4(0xa7480000);
+ /* dl %r4,<d(K)>(%r13) */
+ EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
break;
case BPF_S_ALU_MOD_X: /* A %= X */
jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -352,16 +353,21 @@
EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
/* lhi %r4,0 */
EMIT4(0xa7480000);
- /* dr %r4,%r12 */
- EMIT2(0x1d4c);
+ /* dlr %r4,%r12 */
+ EMIT4(0xb997004c);
/* lr %r5,%r4 */
EMIT2(0x1854);
break;
case BPF_S_ALU_MOD_K: /* A %= K */
+ if (K == 1) {
+ /* lhi %r5,0 */
+ EMIT4(0xa7580000);
+ break;
+ }
/* lhi %r4,0 */
EMIT4(0xa7480000);
- /* d %r4,<d(K)>(%r13) */
- EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+ /* dl %r4,<d(K)>(%r13) */
+ EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
/* lr %r5,%r4 */
EMIT2(0x1854);
break;
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index ffeb17c..930783d 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -440,7 +440,7 @@
switch (id.machine) {
case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
- case 0x2827: ops->cpu_type = "s390/zEC12"; break;
+ case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
default: return -ENODEV;
}
}
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index c8def8b..91182e9 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -109,3 +109,6 @@
source "crypto/Kconfig"
source "lib/Kconfig"
+
+config NO_IOMEM
+ def_bool y
diff --git a/arch/score/Makefile b/arch/score/Makefile
index 974aefe..9e3e060 100644
--- a/arch/score/Makefile
+++ b/arch/score/Makefile
@@ -20,8 +20,8 @@
#
KBUILD_AFLAGS += $(cflags-y)
KBUILD_CFLAGS += $(cflags-y)
-KBUILD_AFLAGS_MODULE += -mlong-calls
-KBUILD_CFLAGS_MODULE += -mlong-calls
+KBUILD_AFLAGS_MODULE +=
+KBUILD_CFLAGS_MODULE +=
LDFLAGS += --oformat elf32-littlescore
LDFLAGS_vmlinux += -G0 -static -nostdlib
diff --git a/arch/score/include/asm/checksum.h b/arch/score/include/asm/checksum.h
index f909ac3..961bd64 100644
--- a/arch/score/include/asm/checksum.h
+++ b/arch/score/include/asm/checksum.h
@@ -184,48 +184,57 @@
__wsum sum)
{
__asm__ __volatile__(
- ".set\tnoreorder\t\t\t# csum_ipv6_magic\n\t"
- ".set\tnoat\n\t"
- "addu\t%0, %5\t\t\t# proto (long in network byte order)\n\t"
- "sltu\t$1, %0, %5\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %6\t\t\t# csum\n\t"
- "sltu\t$1, %0, %6\n\t"
- "lw\t%1, 0(%2)\t\t\t# four words source address\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 4(%2)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 8(%2)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 12(%2)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 0(%3)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 4(%3)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 8(%3)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "lw\t%1, 12(%3)\n\t"
- "addu\t%0, $1\n\t"
- "addu\t%0, %1\n\t"
- "sltu\t$1, %0, %1\n\t"
- "addu\t%0, $1\t\t\t# Add final carry\n\t"
- ".set\tnoat\n\t"
- ".set\tnoreorder"
+ ".set\tvolatile\t\t\t# csum_ipv6_magic\n\t"
+ "add\t%0, %0, %5\t\t\t# proto (long in network byte order)\n\t"
+ "cmp.c\t%5, %0\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %6\t\t\t# csum\n\t"
+ "cmp.c\t%6, %0\n\t"
+ "lw\t%1, [%2, 0]\t\t\t# four words source address\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "1:lw\t%1, [%2, 4]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%2,8]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%2, 12]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0,%1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%3, 0]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%3, 4]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%3, 8]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "lw\t%1, [%3, 12]\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:add\t%0, %0, %1\n\t"
+ "cmp.c\t%1, %0\n\t"
+ "bleu 1f\n\t"
+ "addi\t%0, 0x1\n\t"
+ "1:\n\t"
+ ".set\toptimize"
: "=r" (sum), "=r" (proto)
: "r" (saddr), "r" (daddr),
"0" (htonl(len)), "1" (htonl(proto)), "r" (sum));
diff --git a/arch/score/include/asm/io.h b/arch/score/include/asm/io.h
index fbbfd71..574c8827 100644
--- a/arch/score/include/asm/io.h
+++ b/arch/score/include/asm/io.h
@@ -5,5 +5,4 @@
#define virt_to_bus virt_to_phys
#define bus_to_virt phys_to_virt
-
#endif /* _ASM_SCORE_IO_H */
diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h
index 059a61b..716b3fd 100644
--- a/arch/score/include/asm/pgalloc.h
+++ b/arch/score/include/asm/pgalloc.h
@@ -2,7 +2,7 @@
#define _ASM_SCORE_PGALLOC_H
#include <linux/mm.h>
-
+#include <linux/highmem.h>
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
pte_t *pte)
{
diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S
index 7234ed0..befb87d 100644
--- a/arch/score/kernel/entry.S
+++ b/arch/score/kernel/entry.S
@@ -264,7 +264,7 @@
disable_irq
lw r8, [r28, TI_PRE_COUNT]
cmpz.c r8
- bne r8, restore_all
+ bne restore_all
need_resched:
lw r8, [r28, TI_FLAGS]
andri.c r9, r8, _TIF_NEED_RESCHED
@@ -415,7 +415,7 @@
sw r9, [r0, PT_EPC]
cmpi.c r27, __NR_syscalls # check syscall number
- bgeu illegal_syscall
+ bcs illegal_syscall
slli r8, r27, 2 # get syscall routine
la r11, sys_call_table
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index f4c6d02..a1519ad3 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -78,8 +78,8 @@
p->thread.reg0 = (unsigned long) childregs;
if (unlikely(p->flags & PF_KTHREAD)) {
memset(childregs, 0, sizeof(struct pt_regs));
- p->thread->reg12 = usp;
- p->thread->reg13 = arg;
+ p->thread.reg12 = usp;
+ p->thread.reg13 = arg;
p->thread.reg3 = (unsigned long) ret_from_kernel_thread;
} else {
*childregs = *current_pt_regs();
diff --git a/arch/score/kernel/vmlinux.lds.S b/arch/score/kernel/vmlinux.lds.S
index eebcbaa..7274b5c 100644
--- a/arch/score/kernel/vmlinux.lds.S
+++ b/arch/score/kernel/vmlinux.lds.S
@@ -49,6 +49,7 @@
}
. = ALIGN(16);
+ _sdata = .; /* Start of data section */
RODATA
EXCEPTION_TABLE(16)
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 47b600e..6860beb 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -47,6 +47,7 @@
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
+ unsigned long flags = 0;
siginfo_t info;
int fault;
@@ -75,6 +76,9 @@
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
@@ -95,21 +99,23 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
goto bad_area;
}
-survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(mm, vma, address, write);
+ fault = handle_mm_fault(mm, vma, address, flags);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -167,15 +173,10 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 8c868cf..69c567f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -15,6 +15,7 @@
select HAVE_DEBUG_BUGVERBOSE
select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
+ select ARCH_HAS_GCOV_PROFILE_ALL
select PERF_USE_VMALLOC
select HAVE_DEBUG_KMEMLEAK
select HAVE_KERNEL_GZIP
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 13e9966..e79fb6e 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -40,15 +40,7 @@
/* arch/sh/kernel/return_address.c */
extern void *return_address(unsigned int);
-#define HAVE_ARCH_CALLER_ADDR
-
-#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-#define CALLER_ADDR1 ((unsigned long)return_address(1))
-#define CALLER_ADDR2 ((unsigned long)return_address(2))
-#define CALLER_ADDR3 ((unsigned long)return_address(3))
-#define CALLER_ADDR4 ((unsigned long)return_address(4))
-#define CALLER_ADDR5 ((unsigned long)return_address(5))
-#define CALLER_ADDR6 ((unsigned long)return_address(6))
+#define ftrace_return_address(n) return_address(n)
#endif /* __ASSEMBLY__ */
diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index 1b61997..7a99e6a 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,7 +3,6 @@
#include <asm-generic/sections.h>
-extern long __nosave_begin, __nosave_end;
extern long __machvec_start, __machvec_end;
extern char __uncached_start, __uncached_end;
extern char __start_eh_frame[], __stop_eh_frame[];
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d..362192e 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c
index b959f55..8dfe645 100644
--- a/arch/sh/kernel/dumpstack.c
+++ b/arch/sh/kernel/dumpstack.c
@@ -115,7 +115,7 @@
*/
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
- printk(data);
+ printk("%s", (char *)data);
printk_address(addr, reliable);
}
diff --git a/arch/sh/kernel/kgdb.c b/arch/sh/kernel/kgdb.c
index 38b3139..adad46e 100644
--- a/arch/sh/kernel/kgdb.c
+++ b/arch/sh/kernel/kgdb.c
@@ -13,6 +13,7 @@
#include <linux/kdebug.h>
#include <linux/irq.h>
#include <linux/io.h>
+#include <linux/sched.h>
#include <asm/cacheflush.h>
#include <asm/traps.h>
diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 2a0a596..d77f2f6 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -20,6 +20,11 @@
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(empty_zero_page);
+#ifdef CONFIG_FLATMEM
+/* need in pfn_valid macro */
+EXPORT_SYMBOL(min_low_pfn);
+EXPORT_SYMBOL(max_low_pfn);
+#endif
#define DECLARE_EXPORT(name) \
extern void name(void);EXPORT_SYMBOL(name)
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 7b95f29..3baff31 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -6,7 +6,7 @@
checksum.o strlen.o div64.o div64-generic.o
# Extracted from libgcc
-lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
udiv_qrnnd.o
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 1f49c28a..a58fec9 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@
} else {
if (fault & VM_FAULT_SIGBUS)
do_sigbus(regs, error_code, address);
+ else if (fault & VM_FAULT_SIGSEGV)
+ bad_area(regs, error_code, address);
else
BUG();
}
@@ -400,9 +402,7 @@
struct mm_struct *mm;
struct vm_area_struct * vma;
int fault;
- int write = error_code & FAULT_CODE_WRITE;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -476,6 +476,11 @@
set_thread_fault_code(error_code);
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (error_code & FAULT_CODE_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 9ac9f16..03a1bc3 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,7 +25,7 @@
select RTC_DRV_M48T59
select HAVE_DMA_ATTRS
select HAVE_DMA_API_DEBUG
- select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL if SPARC64
select HAVE_GENERIC_HARDIRQS
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
@@ -77,6 +77,7 @@
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select HAVE_C_RECORDMCOUNT
select NO_BOOTMEM
+ select ARCH_SUPPORTS_ATOMIC_RMW
config ARCH_DEFCONFIG
string
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 503e6d9..ded4cee3 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -499,6 +499,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("AES Secure Hash Algorithm, sparc64 aes opcode accelerated");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/camellia_glue.c b/arch/sparc/crypto/camellia_glue.c
index 888f6260..641f55c 100644
--- a/arch/sparc/crypto/camellia_glue.c
+++ b/arch/sparc/crypto/camellia_glue.c
@@ -322,6 +322,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, sparc64 camellia opcode accelerated");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/crc32c_glue.c b/arch/sparc/crypto/crc32c_glue.c
index 5162fad..d1064e4 100644
--- a/arch/sparc/crypto/crc32c_glue.c
+++ b/arch/sparc/crypto/crc32c_glue.c
@@ -176,6 +176,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CRC32c (Castagnoli), sparc64 crc32c opcode accelerated");
-MODULE_ALIAS("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index 3065bc6..d115009 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -532,6 +532,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms, sparc64 des opcode accelerated");
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index 09a9ea1..64c7ff5 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -185,6 +185,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MD5 Secure Hash Algorithm, sparc64 md5 opcode accelerated");
-MODULE_ALIAS("md5");
+MODULE_ALIAS_CRYPTO("md5");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 6cd5f29..1b3e47a 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -180,6 +180,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, sparc64 sha1 opcode accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 04f555a..41f27cc 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -237,7 +237,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm, sparc64 sha256 opcode accelerated");
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
#include "crop_devid.c"
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index f04d199..9fff885 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -222,7 +222,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-384 and SHA-512 Secure Hash Algorithm, sparc64 sha512 opcode accelerated");
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
#include "crop_devid.c"
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 905832a..a0ed182 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -21,7 +21,7 @@
extern int __atomic_add_return(int, atomic_t *);
extern int atomic_cmpxchg(atomic_t *, int, int);
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+extern int atomic_xchg(atomic_t *, int);
extern int __atomic_add_unless(atomic_t *, int, int);
extern void atomic_set(atomic_t *, int);
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a0..ae0f9a7 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -11,22 +11,14 @@
#ifndef __ARCH_SPARC_CMPXCHG__
#define __ARCH_SPARC_CMPXCHG__
-static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned long val)
-{
- __asm__ __volatile__("swap [%2], %0"
- : "=&r" (val)
- : "0" (val), "r" (m)
- : "memory");
- return val;
-}
-
+extern unsigned long __xchg_u32(volatile u32 *m, u32 new);
extern void __xchg_called_with_bad_pointer(void);
static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
{
switch (size) {
case 4:
- return xchg_u32(ptr, x);
+ return __xchg_u32(ptr, x);
}
__xchg_called_with_bad_pointer();
return x;
diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h
index 5080d16..ec2e2e2 100644
--- a/arch/sparc/include/asm/jump_label.h
+++ b/arch/sparc/include/asm/jump_label.h
@@ -9,7 +9,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:\n\t"
+ asm_volatile_goto("1:\n\t"
"nop\n\t"
"nop\n\t"
".pushsection __jump_table, \"aw\"\n\t"
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 7619f2f..6663604 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@
/* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
* The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
* The PROM resides in an area spanning 0xf0000000 to 0x100000000.
* The vmalloc area spans 0x100000000 to 0x200000000.
* Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
* 0x400000000.
*/
#define TLBTEMP_BASE _AC(0x0000000006000000,UL)
-#define TSBMAP_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL)
+#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL)
#define MODULES_VADDR _AC(0x0000000010000000,UL)
#define MODULES_LEN _AC(0x00000000e0000000,UL)
#define MODULES_END _AC(0x00000000f0000000,UL)
@@ -616,7 +618,7 @@
}
#define pte_accessible pte_accessible
-static inline unsigned long pte_accessible(pte_t a)
+static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
{
return pte_val(a) & _PAGE_VALID;
}
@@ -806,7 +808,7 @@
* SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U
* and SUN4V pte layout, so this inline test is fine.
*/
- if (likely(mm != &init_mm) && pte_accessible(orig))
+ if (likely(mm != &init_mm) && pte_accessible(mm, orig))
tlb_batch_add(mm, addr, ptep, orig, fullmm);
}
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index f0d6a97..1a4bb97 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -35,6 +35,8 @@
{
}
+void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
extern void flush_tlb_pending(void);
@@ -49,11 +51,6 @@
#ifndef CONFIG_SMP
-#define flush_tlb_kernel_range(start,end) \
-do { flush_tsb_kernel_range(start,end); \
- __flush_tlb_kernel_range(start,end); \
-} while (0)
-
static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr)
{
__flush_tlb_page(CTX_HWBITS(mm->context), vaddr);
@@ -64,11 +61,6 @@
extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
-#define flush_tlb_kernel_range(start, end) \
-do { flush_tsb_kernel_range(start,end); \
- smp_flush_tlb_kernel_range(start, end); \
-} while (0)
-
#define global_flush_tlb_page(mm, vaddr) \
smp_flush_tlb_page(mm, vaddr)
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index e562d3c..ad7e178 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -262,8 +262,8 @@
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
struct pt_regs;
extern unsigned long compute_effective_address(struct pt_regs *,
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa8..55841c1 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -118,12 +118,18 @@
u8 vdisk_type;
#define VD_DISK_TYPE_SLICE 0x01 /* Slice in block device */
#define VD_DISK_TYPE_DISK 0x02 /* Entire block device */
- u16 resv1;
+ u8 vdisk_mtype; /* v1.1 */
+#define VD_MEDIA_TYPE_FIXED 0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD 0x02 /* CD Device */
+#define VD_MEDIA_TYPE_DVD 0x03 /* DVD Device */
+ u8 resv1;
u32 vdisk_block_size;
u64 operations;
- u64 vdisk_size;
+ u64 vdisk_size; /* v1.1 */
u64 max_xfer_size;
- u64 resv2[2];
+ u32 phys_block_size; /* v1.2 */
+ u32 resv2;
+ u64 resv3[1];
};
struct vio_disk_desc {
@@ -259,7 +265,7 @@
unsigned int ring_size)
{
return (dr->pending -
- ((dr->prod - dr->cons) & (ring_size - 1)));
+ ((dr->prod - dr->cons) & (ring_size - 1)) - 1);
}
#define VIO_MAX_TYPE_LEN 32
diff --git a/arch/sparc/include/uapi/asm/swab.h b/arch/sparc/include/uapi/asm/swab.h
index a34ad07..4c7c12d 100644
--- a/arch/sparc/include/uapi/asm/swab.h
+++ b/arch/sparc/include/uapi/asm/swab.h
@@ -9,9 +9,9 @@
{
__u16 ret;
- __asm__ __volatile__ ("lduha [%1] %2, %0"
+ __asm__ __volatile__ ("lduha [%2] %3, %0"
: "=r" (ret)
- : "r" (addr), "i" (ASI_PL));
+ : "m" (*addr), "r" (addr), "i" (ASI_PL));
return ret;
}
#define __arch_swab16p __arch_swab16p
@@ -20,9 +20,9 @@
{
__u32 ret;
- __asm__ __volatile__ ("lduwa [%1] %2, %0"
+ __asm__ __volatile__ ("lduwa [%2] %3, %0"
: "=r" (ret)
- : "r" (addr), "i" (ASI_PL));
+ : "m" (*addr), "r" (addr), "i" (ASI_PL));
return ret;
}
#define __arch_swab32p __arch_swab32p
@@ -31,9 +31,9 @@
{
__u64 ret;
- __asm__ __volatile__ ("ldxa [%1] %2, %0"
+ __asm__ __volatile__ ("ldxa [%2] %3, %0"
: "=r" (ret)
- : "r" (addr), "i" (ASI_PL));
+ : "m" (*addr), "r" (addr), "i" (ASI_PL));
return ret;
}
#define __arch_swab64p __arch_swab64p
diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c
index 961b87f9..f76389a 100644
--- a/arch/sparc/kernel/asm-offsets.c
+++ b/arch/sparc/kernel/asm-offsets.c
@@ -49,6 +49,8 @@
DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread));
BLANK();
DEFINE(AOFF_mm_context, offsetof(struct mm_struct, context));
+ BLANK();
+ DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm));
/* DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); */
return 0;
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 5ef48da..252f876 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -842,9 +842,8 @@
if (boot_command && strlen(boot_command)) {
unsigned long len;
- strcpy(full_boot_str, "boot ");
- strlcpy(full_boot_str + strlen("boot "), boot_command,
- sizeof(full_boot_str + strlen("boot ")));
+ snprintf(full_boot_str, sizeof(full_boot_str), "boot %s",
+ boot_command);
len = strlen(full_boot_str);
if (reboot_data_supported) {
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index e2a0300..33c02b1 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -839,7 +839,7 @@
nop
call syscall_trace
- nop
+ mov 1, %o1
1:
/* We don't want to muck with user registers like a
diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index 0746e5e..fde5a41 100644
--- a/arch/sparc/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
@@ -25,11 +25,10 @@
*/
kvmap_itlb_4v:
-kvmap_itlb_nonlinear:
/* Catch kernel NULL pointer calls. */
sethi %hi(PAGE_SIZE), %g5
cmp %g4, %g5
- bleu,pn %xcc, kvmap_dtlb_longpath
+ blu,pn %xcc, kvmap_itlb_longpath
nop
KERN_TSB_LOOKUP_TL1(%g4, %g6, %g5, %g1, %g2, %g3, kvmap_itlb_load)
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 54df554..fa4c900 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1336,7 +1336,7 @@
if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) ||
!(lp->flags & LDC_FLAG_REGISTERED_QUEUES) ||
lp->hs_state != LDC_HS_OPEN)
- err = -EINVAL;
+ err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL);
else
err = start_handshake(lp);
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index baf4366..906cbf0 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -399,8 +399,8 @@
apb_calc_first_last(map, &first, &last);
res = bus->resource[1];
res->flags = IORESOURCE_MEM;
- region.start = (first << 21);
- region.end = (last << 21) + ((1 << 21) - 1);
+ region.start = (first << 29);
+ region.end = (last << 29) + ((1 << 29) - 1);
pcibios_bus_to_resource(dev, res, ®ion);
}
diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 8f76f23..f9c6813 100644
--- a/arch/sparc/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
@@ -581,7 +581,7 @@
{
unsigned long csr_reg, csr, csr_error_bits;
irqreturn_t ret = IRQ_NONE;
- u16 stat;
+ u32 stat;
csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
csr = upa_readq(csr_reg);
@@ -617,7 +617,7 @@
pbm->name);
ret = IRQ_HANDLED;
}
- pci_read_config_word(pbm->pci_bus->self, PCI_STATUS, &stat);
+ pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
if (stat & (PCI_STATUS_PARITY |
PCI_STATUS_SIG_TARGET_ABORT |
PCI_STATUS_REC_TARGET_ABORT |
@@ -625,7 +625,7 @@
PCI_STATUS_SIG_SYSTEM_ERROR)) {
printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
pbm->name, stat);
- pci_write_config_word(pbm->pci_bus->self, PCI_STATUS, 0xffff);
+ pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
ret = IRQ_HANDLED;
}
return ret;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38fa..d461b7d 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -960,6 +960,8 @@
cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
}
+static void sparc_pmu_start(struct perf_event *event, int flags);
+
/* On this PMU each PIC has it's own PCR control register. */
static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
{
@@ -972,20 +974,13 @@
struct perf_event *cp = cpuc->event[i];
struct hw_perf_event *hwc = &cp->hw;
int idx = hwc->idx;
- u64 enc;
if (cpuc->current_idx[i] != PIC_NO_INDEX)
continue;
- sparc_perf_event_set_period(cp, hwc, idx);
cpuc->current_idx[i] = idx;
- enc = perf_event_get_enc(cpuc->events[i]);
- cpuc->pcr[idx] &= ~mask_for_index(idx);
- if (hwc->state & PERF_HES_STOPPED)
- cpuc->pcr[idx] |= nop_for_index(idx);
- else
- cpuc->pcr[idx] |= event_encoding(enc, idx);
+ sparc_pmu_start(cp, PERF_EF_RELOAD);
}
out:
for (i = 0; i < cpuc->n_events; i++) {
@@ -1101,7 +1096,6 @@
int i;
local_irq_save(flags);
- perf_pmu_disable(event->pmu);
for (i = 0; i < cpuc->n_events; i++) {
if (event == cpuc->event[i]) {
@@ -1127,7 +1121,6 @@
}
}
- perf_pmu_enable(event->pmu);
local_irq_restore(flags);
}
@@ -1361,7 +1354,6 @@
unsigned long flags;
local_irq_save(flags);
- perf_pmu_disable(event->pmu);
n0 = cpuc->n_events;
if (n0 >= sparc_pmu->max_hw_events)
@@ -1394,7 +1386,6 @@
ret = 0;
out:
- perf_pmu_enable(event->pmu);
local_irq_restore(flags);
return ret;
}
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index baebab2..036e43c 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -57,9 +57,12 @@
{
if (tlb_type != hypervisor) {
touch_nmi_watchdog();
+ local_irq_enable();
} else {
unsigned long pstate;
+ local_irq_enable();
+
/* The sun4v sleeping code requires that we have PSTATE.IE cleared over
* the cpu sleep hypervisor call.
*/
@@ -81,7 +84,6 @@
: "=&r" (pstate)
: "i" (PSTATE_IE));
}
- local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
@@ -278,6 +280,8 @@
printk(" TPC[%lx] O7[%lx] I7[%lx] RPC[%lx]\n",
gp->tpc, gp->o7, gp->i7, gp->rpc);
}
+
+ touch_nmi_watchdog();
}
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
@@ -350,6 +354,8 @@
(cpu == this_cpu ? '*' : ' '), cpu,
pp->pcr[0], pp->pcr[1], pp->pcr[2], pp->pcr[3],
pp->pic[0], pp->pic[1], pp->pic[2], pp->pic[3]);
+
+ touch_nmi_watchdog();
}
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 77539ed..173964d 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -150,7 +150,7 @@
#define NUM_ROUNDS 64 /* magic value */
#define NUM_ITERS 5 /* likewise */
-static DEFINE_SPINLOCK(itc_sync_lock);
+static DEFINE_RAW_SPINLOCK(itc_sync_lock);
static unsigned long go[SLAVE + 1];
#define DEBUG_TICK_SYNC 0
@@ -258,7 +258,7 @@
go[MASTER] = 0;
membar_safe("#StoreLoad");
- spin_lock_irqsave(&itc_sync_lock, flags);
+ raw_spin_lock_irqsave(&itc_sync_lock, flags);
{
for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) {
while (!go[MASTER])
@@ -269,7 +269,7 @@
membar_safe("#StoreLoad");
}
}
- spin_unlock_irqrestore(&itc_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&itc_sync_lock, flags);
}
#if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
@@ -821,13 +821,17 @@
void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs)
{
clear_softint(1 << irq);
+ irq_enter();
generic_smp_call_function_interrupt();
+ irq_exit();
}
void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs)
{
clear_softint(1 << irq);
+ irq_enter();
generic_smp_call_function_single_interrupt();
+ irq_exit();
}
static void tsb_sync(void *info)
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index f7c72b6..d066eb1 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -44,7 +44,7 @@
SIGN1(sys32_io_submit, compat_sys_io_submit, %o1)
SIGN1(sys32_mq_open, compat_sys_mq_open, %o1)
SIGN1(sys32_select, compat_sys_select, %o0)
-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5)
+SIGN1(sys32_futex, compat_sys_futex, %o1)
SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 2daaaa6..be8db9b 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -336,7 +336,7 @@
long err;
/* No need for backward compatibility. We can start fresh... */
- if (call <= SEMCTL) {
+ if (call <= SEMTIMEDOP) {
switch (call) {
case SEMOP:
err = sys_semtimedop(first, ptr,
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 22a1098..c79c687 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -152,7 +152,7 @@
srl %i4, 0, %o4
srl %i1, 0, %o1
srl %i2, 0, %o2
- ba,pt %xcc, 2f
+ ba,pt %xcc, 5f
srl %i3, 0, %o3
linux_syscall_trace:
@@ -182,14 +182,15 @@
srl %i1, 0, %o1 ! IEU0 Group
ldx [%g6 + TI_FLAGS], %l0 ! Load
- srl %i5, 0, %o5 ! IEU1
+ srl %i3, 0, %o3 ! IEU0
srl %i2, 0, %o2 ! IEU0 Group
andcc %l0, (_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT|_TIF_SYSCALL_TRACEPOINT), %g0
bne,pn %icc, linux_syscall_trace32 ! CTI
mov %i0, %l5 ! IEU1
- call %l7 ! CTI Group brk forced
- srl %i3, 0, %o3 ! IEU0
- ba,a,pt %xcc, 3f
+5: call %l7 ! CTI Group brk forced
+ srl %i5, 0, %o5 ! IEU1
+ ba,pt %xcc, 3f
+ sra %o0, 0, %o0
/* Linux native system calls enter here... */
.align 32
@@ -217,7 +218,6 @@
3: stx %o0, [%sp + PTREGS_OFF + PT_V9_I0]
ret_sys_call:
ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
- sra %o0, 0, %o0
mov %ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
sllx %g2, 32, %g2
diff --git a/arch/sparc/kernel/trampoline_64.S b/arch/sparc/kernel/trampoline_64.S
index 2e973a2..3a43edb 100644
--- a/arch/sparc/kernel/trampoline_64.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -131,7 +131,6 @@
clr %l5
sethi %hi(num_kernel_image_mappings), %l6
lduw [%l6 + %lo(num_kernel_image_mappings)], %l6
- add %l6, 1, %l6
mov 15, %l7
BRANCH_IF_ANY_CHEETAH(g1,g5,2f)
@@ -224,7 +223,6 @@
clr %l5
sethi %hi(num_kernel_image_mappings), %l6
lduw [%l6 + %lo(num_kernel_image_mappings)], %l6
- add %l6, 1, %l6
1:
mov HV_FAST_MMU_MAP_PERM_ADDR, %o5
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 8201c25e..4db8898 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -163,17 +163,23 @@
unsigned long compute_effective_address(struct pt_regs *regs,
unsigned int insn, unsigned int rd)
{
+ int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
unsigned int rs1 = (insn >> 14) & 0x1f;
unsigned int rs2 = insn & 0x1f;
- int from_kernel = (regs->tstate & TSTATE_PRIV) != 0;
+ unsigned long addr;
if (insn & 0x2000) {
maybe_flush_windows(rs1, 0, rd, from_kernel);
- return (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
+ addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn));
} else {
maybe_flush_windows(rs1, rs2, rd, from_kernel);
- return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
+ addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs));
}
+
+ if (!from_kernel && test_thread_flag(TIF_32BIT))
+ addr &= 0xffffffff;
+
+ return addr;
}
/* This is just to make gcc think die_if_kernel does return... */
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 2c20ad6..30eee6e 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@
*/
VISEntryHalf
+ membar #Sync
alignaddr %o1, %g0, %g0
add %o1, (64 - 1), %o4
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 1d32b54..8f2f94d 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -40,6 +40,19 @@
}
EXPORT_SYMBOL(__atomic_add_return);
+int atomic_xchg(atomic_t *v, int new)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(ATOMIC_HASH(v), flags);
+ ret = v->counter;
+ v->counter = new;
+ spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
+ return ret;
+}
+EXPORT_SYMBOL(atomic_xchg);
+
int atomic_cmpxchg(atomic_t *v, int old, int new)
{
int ret;
@@ -132,3 +145,17 @@
return (unsigned long)prev;
}
EXPORT_SYMBOL(__cmpxchg_u32);
+
+unsigned long __xchg_u32(volatile u32 *ptr, u32 new)
+{
+ unsigned long flags;
+ u32 prev;
+
+ spin_lock_irqsave(ATOMIC_HASH(ptr), flags);
+ prev = *ptr;
+ *ptr = new;
+ spin_unlock_irqrestore(ATOMIC_HASH(ptr), flags);
+
+ return (unsigned long)prev;
+}
+EXPORT_SYMBOL(__xchg_u32);
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 0c4e35e..323335b 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -98,15 +98,6 @@
EXPORT_SYMBOL(___copy_in_user);
EXPORT_SYMBOL(__clear_user);
-/* RW semaphores */
-EXPORT_SYMBOL(__down_read);
-EXPORT_SYMBOL(__down_read_trylock);
-EXPORT_SYMBOL(__down_write);
-EXPORT_SYMBOL(__down_write_trylock);
-EXPORT_SYMBOL(__up_read);
-EXPORT_SYMBOL(__up_write);
-EXPORT_SYMBOL(__downgrade_write);
-
/* Atomic counter implementation. */
EXPORT_SYMBOL(atomic_add);
EXPORT_SYMBOL(atomic_add_ret);
diff --git a/arch/sparc/lib/memmove.S b/arch/sparc/lib/memmove.S
index b7f6334..857ad4f 100644
--- a/arch/sparc/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
@@ -8,9 +8,11 @@
.text
ENTRY(memmove) /* o0=dst o1=src o2=len */
- mov %o0, %g1
+ brz,pn %o2, 99f
+ mov %o0, %g1
+
cmp %o0, %o1
- bleu,pt %xcc, memcpy
+ bleu,pt %xcc, 2f
add %o1, %o2, %g7
cmp %g7, %o0
bleu,pt %xcc, memcpy
@@ -24,7 +26,34 @@
stb %g7, [%o0]
bne,pt %icc, 1b
sub %o0, 1, %o0
-
+99:
retl
mov %g1, %o0
+
+ /* We can't just call memcpy for these memmove cases. On some
+ * chips the memcpy uses cache initializing stores and when dst
+ * and src are close enough, those can clobber the source data
+ * before we've loaded it in.
+ */
+2: or %o0, %o1, %g7
+ or %o2, %g7, %g7
+ andcc %g7, 0x7, %g0
+ bne,pn %xcc, 4f
+ nop
+
+3: ldx [%o1], %g7
+ add %o1, 8, %o1
+ subcc %o2, 8, %o2
+ add %o0, 8, %o0
+ bne,pt %icc, 3b
+ stx %g7, [%o0 - 0x8]
+ ba,a,pt %xcc, 99b
+
+4: ldub [%o1], %g7
+ add %o1, 1, %o1
+ subcc %o2, 1, %o2
+ add %o0, 1, %o0
+ bne,pt %icc, 4b
+ stb %g7, [%o0 - 0x1]
+ ba,a,pt %xcc, 99b
ENDPROC(memmove)
diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c
index aa4d55b..5ce8f2f 100644
--- a/arch/sparc/math-emu/math_32.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -499,7 +499,7 @@
case 0: fsr = *pfsr;
if (IR == -1) IR = 2;
/* fcc is always fcc0 */
- fsr &= ~0xc00; fsr |= (IR << 10); break;
+ fsr &= ~0xc00; fsr |= (IR << 10);
*pfsr = fsr;
break;
case 1: rd->s = IR; break;
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index e98bfda..163c787 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -177,8 +177,7 @@
unsigned long g2;
int from_user = !(regs->psr & PSR_PS);
int fault, code;
- unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (text_fault)
address = regs->pc;
@@ -235,6 +234,11 @@
goto bad_area;
}
+ if (from_user)
+ flags |= FAULT_FLAG_USER;
+ if (write)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -248,6 +252,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -383,6 +389,7 @@
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
+ unsigned int flags = FAULT_FLAG_USER;
int code;
code = SEGV_MAPERR;
@@ -402,11 +409,12 @@
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- switch (handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0)) {
+ switch (handle_mm_fault(mm, vma, address, flags)) {
case VM_FAULT_SIGBUS:
case VM_FAULT_OOM:
goto do_sigbus;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 5062ff3..ac2db92 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -95,38 +95,51 @@
pte_t *ptep, pte;
unsigned long pa;
u32 insn = 0;
- unsigned long pstate;
- if (pgd_none(*pgdp))
- goto outret;
+ if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
+ goto out;
pudp = pud_offset(pgdp, tpc);
- if (pud_none(*pudp))
- goto outret;
- pmdp = pmd_offset(pudp, tpc);
- if (pmd_none(*pmdp))
- goto outret;
-
- /* This disables preemption for us as well. */
- __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate));
- __asm__ __volatile__("wrpr %0, %1, %%pstate"
- : : "r" (pstate), "i" (PSTATE_IE));
- ptep = pte_offset_map(pmdp, tpc);
- pte = *ptep;
- if (!pte_present(pte))
+ if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
goto out;
- pa = (pte_pfn(pte) << PAGE_SHIFT);
- pa += (tpc & ~PAGE_MASK);
+ /* This disables preemption for us as well. */
+ local_irq_disable();
- /* Use phys bypass so we don't pollute dtlb/dcache. */
- __asm__ __volatile__("lduwa [%1] %2, %0"
- : "=r" (insn)
- : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ pmdp = pmd_offset(pudp, tpc);
+ if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
+ goto out_irq_enable;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_trans_huge(*pmdp)) {
+ if (pmd_trans_splitting(*pmdp))
+ goto out_irq_enable;
+
+ pa = pmd_pfn(*pmdp) << PAGE_SHIFT;
+ pa += tpc & ~HPAGE_MASK;
+
+ /* Use phys bypass so we don't pollute dtlb/dcache. */
+ __asm__ __volatile__("lduwa [%1] %2, %0"
+ : "=r" (insn)
+ : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ } else
+#endif
+ {
+ ptep = pte_offset_map(pmdp, tpc);
+ pte = *ptep;
+ if (pte_present(pte)) {
+ pa = (pte_pfn(pte) << PAGE_SHIFT);
+ pa += (tpc & ~PAGE_MASK);
+
+ /* Use phys bypass so we don't pollute dtlb/dcache. */
+ __asm__ __volatile__("lduwa [%1] %2, %0"
+ : "=r" (insn)
+ : "r" (pa), "i" (ASI_PHYS_USE_EC));
+ }
+ pte_unmap(ptep);
+ }
+out_irq_enable:
+ local_irq_enable();
out:
- pte_unmap(ptep);
- __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate));
-outret:
return insn;
}
@@ -152,7 +165,8 @@
}
static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
- unsigned int insn, int fault_code)
+ unsigned long fault_addr, unsigned int insn,
+ int fault_code)
{
unsigned long addr;
siginfo_t info;
@@ -160,10 +174,18 @@
info.si_code = code;
info.si_signo = sig;
info.si_errno = 0;
- if (fault_code & FAULT_CODE_ITLB)
+ if (fault_code & FAULT_CODE_ITLB) {
addr = regs->tpc;
- else
- addr = compute_effective_address(regs, insn, 0);
+ } else {
+ /* If we were able to probe the faulting instruction, use it
+ * to compute a precise fault address. Otherwise use the fault
+ * time provided address which may only have page granularity.
+ */
+ if (insn)
+ addr = compute_effective_address(regs, insn, 0);
+ else
+ addr = fault_addr;
+ }
info.si_addr = (void __user *) addr;
info.si_trapno = 0;
@@ -238,7 +260,7 @@
/* The si_code was set to make clear whether
* this was a SEGV_MAPERR or SEGV_ACCERR fault.
*/
- do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code);
+ do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code);
return;
}
@@ -258,18 +280,6 @@
show_regs(regs);
}
-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
- unsigned long addr)
-{
- static int times;
-
- if (times++ < 10)
- printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
- "reports 64-bit fault address [%lx]\n",
- current->comm, current->pid, addr);
- show_regs(regs);
-}
-
asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
{
struct mm_struct *mm = current->mm;
@@ -298,10 +308,8 @@
goto intr_or_no_mm;
}
}
- if (unlikely((address >> 32) != 0)) {
- bogus_32bit_fault_address(regs, address);
+ if (unlikely((address >> 32) != 0))
goto intr_or_no_mm;
- }
}
if (regs->tstate & TSTATE_PRIV) {
@@ -315,7 +323,8 @@
bad_kernel_pc(regs, address);
return;
}
- }
+ } else
+ flags |= FAULT_FLAG_USER;
/*
* If we're in an interrupt or have no user
@@ -418,13 +427,14 @@
vma->vm_file != NULL)
set_thread_fault_code(fault_code |
FAULT_CODE_BLKCOMMIT);
+
+ flags |= FAULT_FLAG_WRITE;
} else {
/* Allow reads even for write-only mappings */
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto bad_area;
}
- flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
fault = handle_mm_fault(mm, vma, address, flags);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
@@ -433,6 +443,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -519,7 +531,7 @@
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code);
+ do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code);
/* Kernel mode? Handle exceptions or die */
if (regs->tstate & TSTATE_PRIV)
diff --git a/arch/sparc/mm/hypersparc.S b/arch/sparc/mm/hypersparc.S
index 44aad32..969f964 100644
--- a/arch/sparc/mm/hypersparc.S
+++ b/arch/sparc/mm/hypersparc.S
@@ -74,7 +74,7 @@
/* The things we do for performance... */
hypersparc_flush_cache_range:
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
#ifndef CONFIG_SMP
ld [%o0 + AOFF_mm_context], %g1
cmp %g1, -1
@@ -163,7 +163,7 @@
*/
/* Verified, my ass... */
hypersparc_flush_cache_page:
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
ld [%o0 + AOFF_mm_context], %g2
#ifndef CONFIG_SMP
cmp %g2, -1
@@ -284,7 +284,7 @@
sta %g5, [%g1] ASI_M_MMUREGS
hypersparc_flush_tlb_range:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
lda [%g1] ASI_M_MMUREGS, %g5
@@ -307,7 +307,7 @@
sta %g5, [%g1] ASI_M_MMUREGS
hypersparc_flush_tlb_page:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
andn %o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 04fd55a..a751023 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -350,6 +350,10 @@
mm = vma->vm_mm;
+ /* Don't insert a non-valid PTE into the TSB, we'll deadlock. */
+ if (!pte_accessible(mm, pte))
+ return;
+
spin_lock_irqsave(&mm->context.lock, flags);
#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -2764,3 +2768,26 @@
}
}
#endif
+
+#ifdef CONFIG_SMP
+#define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range
+#else
+#define do_flush_tlb_kernel_range __flush_tlb_kernel_range
+#endif
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+ if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) {
+ if (start < LOW_OBP_ADDRESS) {
+ flush_tsb_kernel_range(start, LOW_OBP_ADDRESS);
+ do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS);
+ }
+ if (end > HI_OBP_ADDRESS) {
+ flush_tsb_kernel_range(end, HI_OBP_ADDRESS);
+ do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS);
+ }
+ } else {
+ flush_tsb_kernel_range(start, end);
+ do_flush_tlb_kernel_range(start, end);
+ }
+}
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 036c279..f58cb54 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -455,10 +455,12 @@
void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
struct task_struct *tsk)
{
+ unsigned long flags;
+
if (mm->context == NO_CONTEXT) {
- spin_lock(&srmmu_context_spinlock);
+ spin_lock_irqsave(&srmmu_context_spinlock, flags);
alloc_context(old_mm, mm);
- spin_unlock(&srmmu_context_spinlock);
+ spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd);
}
@@ -983,14 +985,15 @@
void destroy_context(struct mm_struct *mm)
{
+ unsigned long flags;
if (mm->context != NO_CONTEXT) {
flush_cache_mm(mm);
srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir);
flush_tlb_mm(mm);
- spin_lock(&srmmu_context_spinlock);
+ spin_lock_irqsave(&srmmu_context_spinlock, flags);
free_context(mm->context);
- spin_unlock(&srmmu_context_spinlock);
+ spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
mm->context = NO_CONTEXT;
}
}
diff --git a/arch/sparc/mm/swift.S b/arch/sparc/mm/swift.S
index c801c39..5d2b88d 100644
--- a/arch/sparc/mm/swift.S
+++ b/arch/sparc/mm/swift.S
@@ -105,7 +105,7 @@
.globl swift_flush_cache_range
swift_flush_cache_range:
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
sub %o2, %o1, %o2
sethi %hi(4096), %o3
cmp %o2, %o3
@@ -116,7 +116,7 @@
.globl swift_flush_cache_page
swift_flush_cache_page:
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
70:
ld [%o0 + AOFF_mm_context], %g2
cmp %g2, -1
@@ -219,7 +219,7 @@
.globl swift_flush_tlb_range
.globl swift_flush_tlb_all
swift_flush_tlb_range:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
swift_flush_tlb_mm:
ld [%o0 + AOFF_mm_context], %g2
cmp %g2, -1
@@ -233,7 +233,7 @@
.globl swift_flush_tlb_page
swift_flush_tlb_page:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
andn %o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 2cc3bce..71d99a6 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@
mm->context.tsb_block[tsb_idx].tsb_nentries =
tsb_bytes / sizeof(struct tsb);
- base = TSBMAP_BASE;
+ switch (tsb_idx) {
+ case MM_TSB_BASE:
+ base = TSBMAP_8K_BASE;
+ break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+ case MM_TSB_HUGE:
+ base = TSBMAP_4M_BASE;
+ break;
+#endif
+ default:
+ BUG();
+ }
+
tte = pgprot_val(PAGE_KERNEL_LOCKED);
tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/sparc/mm/tsunami.S b/arch/sparc/mm/tsunami.S
index 4e55e8f..bf10a34 100644
--- a/arch/sparc/mm/tsunami.S
+++ b/arch/sparc/mm/tsunami.S
@@ -24,7 +24,7 @@
/* Sliiick... */
tsunami_flush_cache_page:
tsunami_flush_cache_range:
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
tsunami_flush_cache_mm:
ld [%o0 + AOFF_mm_context], %g2
cmp %g2, -1
@@ -46,7 +46,7 @@
/* More slick stuff... */
tsunami_flush_tlb_range:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
tsunami_flush_tlb_mm:
ld [%o0 + AOFF_mm_context], %g2
cmp %g2, -1
@@ -65,7 +65,7 @@
/* This one can be done in a fine grained manner... */
tsunami_flush_tlb_page:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
andn %o1, (PAGE_SIZE - 1), %o1
diff --git a/arch/sparc/mm/viking.S b/arch/sparc/mm/viking.S
index bf8ee06..852257f 100644
--- a/arch/sparc/mm/viking.S
+++ b/arch/sparc/mm/viking.S
@@ -108,7 +108,7 @@
viking_flush_cache_page:
viking_flush_cache_range:
#ifndef CONFIG_SMP
- ld [%o0 + 0x0], %o0 /* XXX vma->vm_mm, GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
#endif
viking_flush_cache_mm:
#ifndef CONFIG_SMP
@@ -148,7 +148,7 @@
#endif
viking_flush_tlb_range:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
lda [%g1] ASI_M_MMUREGS, %g5
@@ -173,7 +173,7 @@
#endif
viking_flush_tlb_page:
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
mov SRMMU_CTX_REG, %g1
ld [%o0 + AOFF_mm_context], %o3
lda [%g1] ASI_M_MMUREGS, %g5
@@ -239,7 +239,7 @@
tst %g5
bne 3f
mov SRMMU_CTX_REG, %g1
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
ld [%o0 + AOFF_mm_context], %o3
lda [%g1] ASI_M_MMUREGS, %g5
sethi %hi(~((1 << SRMMU_PGDIR_SHIFT) - 1)), %o4
@@ -265,7 +265,7 @@
tst %g5
bne 2f
mov SRMMU_CTX_REG, %g1
- ld [%o0 + 0x00], %o0 /* XXX vma->vm_mm GROSS XXX */
+ ld [%o0 + VMA_VM_MM], %o0
ld [%o0 + AOFF_mm_context], %o3
lda [%g1] ASI_M_MMUREGS, %g5
and %o1, PAGE_MASK, %o1
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index d36a85e..224fc0c 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -83,9 +83,9 @@
#define BNE (F2(0, 2) | CONDNE)
#ifdef CONFIG_SPARC64
-#define BNE_PTR (F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR (F2(0, 1) | CONDE | (2 << 20))
#else
-#define BNE_PTR BNE
+#define BE_PTR BE
#endif
#define SETHI(K, REG) \
@@ -497,9 +497,20 @@
case BPF_S_ALU_MUL_K: /* A *= K */
emit_alu_K(MUL, K);
break;
- case BPF_S_ALU_DIV_K: /* A /= K */
- emit_alu_K(MUL, K);
- emit_read_y(r_A);
+ case BPF_S_ALU_DIV_K: /* A /= K with K != 0*/
+ if (K == 1)
+ break;
+ emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+ /* The Sparc v8 architecture requires
+ * three instructions between a %y
+ * register write and the first use.
+ */
+ emit_nop();
+ emit_nop();
+ emit_nop();
+#endif
+ emit_alu_K(DIV, K);
break;
case BPF_S_ALU_DIV_X: /* A /= X; */
emit_cmpi(r_X, 0);
@@ -589,7 +600,7 @@
case BPF_S_ANC_IFINDEX:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
- emit_branch(BNE_PTR, cleanup_addr + 4);
+ emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load32(r_A, struct net_device, ifindex, r_A);
break;
@@ -602,7 +613,7 @@
case BPF_S_ANC_HATYPE:
emit_skb_loadptr(dev, r_A);
emit_cmpi(r_A, 0);
- emit_branch(BNE_PTR, cleanup_addr + 4);
+ emit_branch(BE_PTR, cleanup_addr + 4);
emit_nop();
emit_load16(r_A, struct net_device, type, r_A);
break;
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 42b0b8c..17bd2e1 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -9,11 +9,9 @@
#include <asm/hibernate.h>
#include <asm/visasm.h>
#include <asm/page.h>
+#include <asm/sections.h>
#include <asm/tlb.h>
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
struct saved_context saved_context;
/*
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 78f1f2d..ffd4493 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -281,7 +281,6 @@
u32 dummy, u32 low, u32 high);
long compat_sys_pwrite64(unsigned int fd, char __user *ubuf, size_t count,
u32 dummy, u32 low, u32 high);
-long compat_sys_lookup_dcookie(u32 low, u32 high, char __user *buf, size_t len);
long compat_sys_sync_file_range2(int fd, unsigned int flags,
u32 offset_lo, u32 offset_hi,
u32 nbytes_lo, u32 nbytes_hi);
diff --git a/arch/tile/include/asm/percpu.h b/arch/tile/include/asm/percpu.h
index 63294f5..4f7ae39 100644
--- a/arch/tile/include/asm/percpu.h
+++ b/arch/tile/include/asm/percpu.h
@@ -15,9 +15,37 @@
#ifndef _ASM_TILE_PERCPU_H
#define _ASM_TILE_PERCPU_H
-register unsigned long __my_cpu_offset __asm__("tp");
-#define __my_cpu_offset __my_cpu_offset
-#define set_my_cpu_offset(tp) (__my_cpu_offset = (tp))
+register unsigned long my_cpu_offset_reg asm("tp");
+
+#ifdef CONFIG_PREEMPT
+/*
+ * For full preemption, we can't just use the register variable
+ * directly, since we need barrier() to hazard against it, causing the
+ * compiler to reload anything computed from a previous "tp" value.
+ * But we also don't want to use volatile asm, since we'd like the
+ * compiler to be able to cache the value across multiple percpu reads.
+ * So we use a fake stack read as a hazard against barrier().
+ * The 'U' constraint is like 'm' but disallows postincrement.
+ */
+static inline unsigned long __my_cpu_offset(void)
+{
+ unsigned long tp;
+ register unsigned long *sp asm("sp");
+ asm("move %0, tp" : "=r" (tp) : "U" (*sp));
+ return tp;
+}
+#define __my_cpu_offset __my_cpu_offset()
+#else
+/*
+ * We don't need to hazard against barrier() since "tp" doesn't ever
+ * change with PREEMPT_NONE, and with PREEMPT_VOLUNTARY it only
+ * changes at function call points, at which we are already re-reading
+ * the value of "tp" due to "my_cpu_offset_reg" being a global variable.
+ */
+#define __my_cpu_offset my_cpu_offset_reg
+#endif
+
+#define set_my_cpu_offset(tp) (my_cpu_offset_reg = (tp))
#include <asm-generic/percpu.h>
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 3d2b81c..12b732f 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -280,8 +280,7 @@
if (!is_page_fault)
write = 1;
- flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0));
+ flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
is_kernel_mode = (EX1_PL(regs->ex1) != USER_PL);
@@ -365,6 +364,9 @@
goto bad_area_nosemaphore;
}
+ if (!is_kernel_mode)
+ flags |= FAULT_FLAG_USER;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
@@ -425,12 +427,12 @@
#endif
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
+ flags |= FAULT_FLAG_WRITE;
} else {
if (!is_page_fault || !(vma->vm_flags & VM_READ))
goto bad_area;
}
- survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -444,6 +446,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
@@ -568,15 +572,10 @@
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (is_global_init(tsk)) {
- yield();
- down_read(&mm->mmap_sem);
- goto survive;
- }
- pr_alert("VM: killing process %s\n", tsk->comm);
- if (!is_kernel_mode)
- do_group_exit(SIGKILL);
- goto no_context;
+ if (is_kernel_mode)
+ goto no_context;
+ pagefault_out_of_memory();
+ return 0;
do_sigbus:
up_read(&mm->mmap_sem);
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
index bceee66..d1ff46c 100644
--- a/arch/um/Kconfig.common
+++ b/arch/um/Kconfig.common
@@ -8,6 +8,7 @@
default y
select HAVE_GENERIC_HARDIRQS
select HAVE_UID16
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select GENERIC_IRQ_SHOW
select GENERIC_CPU_DEVICES
select GENERIC_IO
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd..29b0301 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@
}
static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = full_mm_flush;
+ tlb->start = start;
+ tlb->end = end;
+ tlb->fullmm = !(start | (end+1));
init_tlb_gather(tlb);
}
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 95feaa4..c70a234 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -200,6 +200,7 @@
extern int os_drop_memory(void *addr, int length);
extern int can_drop_memory(void);
extern void os_flush_stdout(void);
+extern int os_mincore(void *addr, unsigned long len);
/* execvp.c */
extern int execvp_noalloc(char *buf, const char *file, char *const argv[]);
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index babe218..d8b78a0 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -13,7 +13,7 @@
obj-y = config.o exec.o exitcode.o irq.o ksyms.o mem.o \
physmem.o process.o ptrace.o reboot.o sigio.o \
signal.o smp.o syscall.o sysrq.o time.o tlb.o trap.o \
- um_arch.o umid.o skas/
+ um_arch.o umid.o maccess.o skas/
obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o
obj-$(CONFIG_GPROF) += gprof_syms.o
diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c
index 829df49..41ebbfe 100644
--- a/arch/um/kernel/exitcode.c
+++ b/arch/um/kernel/exitcode.c
@@ -40,9 +40,11 @@
const char __user *buffer, size_t count, loff_t *pos)
{
char *end, buf[sizeof("nnnnn\0")];
+ size_t size;
int tmp;
- if (copy_from_user(buf, buffer, count))
+ size = min(count, sizeof(buf));
+ if (copy_from_user(buf, buffer, size))
return -EFAULT;
tmp = simple_strtol(buf, &end, 0);
diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c
new file mode 100644
index 0000000..1f3d5c4
--- /dev/null
+++ b/arch/um/kernel/maccess.c
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2013 Richard Weinberger <richrd@nod.at>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <os.h>
+
+long probe_kernel_read(void *dst, const void *src, size_t size)
+{
+ void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
+
+ if ((unsigned long)src < PAGE_SIZE || size <= 0)
+ return -EFAULT;
+
+ if (os_mincore(psrc, size + src - psrc) <= 0)
+ return -EFAULT;
+
+ return __probe_kernel_read(dst, src, size);
+}
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 089f398..06ab0eb 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -30,8 +30,7 @@
pmd_t *pmd;
pte_t *pte;
int err = -EFAULT;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (is_write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
*code_out = SEGV_MAPERR;
@@ -42,6 +41,8 @@
if (in_atomic())
goto out_nosemaphore;
+ if (is_user)
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -58,12 +59,15 @@
good_area:
*code_out = SEGV_ACCERR;
- if (is_write && !(vma->vm_flags & VM_WRITE))
- goto out;
-
- /* Don't require VM_READ|VM_EXEC for write faults! */
- if (!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
- goto out;
+ if (is_write) {
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out;
+ flags |= FAULT_FLAG_WRITE;
+ } else {
+ /* Don't require VM_READ|VM_EXEC for write faults! */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
+ goto out;
+ }
do {
int fault;
@@ -76,6 +80,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM) {
goto out_of_memory;
+ } else if (fault & VM_FAULT_SIGSEGV) {
+ goto out;
} else if (fault & VM_FAULT_SIGBUS) {
err = -EACCES;
goto out;
@@ -124,6 +130,8 @@
* (which will retry the fault, or kill us if we got oom-killed).
*/
up_read(&mm->mmap_sem);
+ if (!is_user)
+ goto out_nosemaphore;
pagefault_out_of_memory();
return 0;
}
diff --git a/arch/um/os-Linux/process.c b/arch/um/os-Linux/process.c
index b8f34c9..67b9c8f 100644
--- a/arch/um/os-Linux/process.c
+++ b/arch/um/os-Linux/process.c
@@ -4,6 +4,7 @@
*/
#include <stdio.h>
+#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <signal.h>
@@ -232,6 +233,57 @@
return ok;
}
+static int os_page_mincore(void *addr)
+{
+ char vec[2];
+ int ret;
+
+ ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+ if (ret < 0) {
+ if (errno == ENOMEM || errno == EINVAL)
+ return 0;
+ else
+ return -errno;
+ }
+
+ return vec[0] & 1;
+}
+
+int os_mincore(void *addr, unsigned long len)
+{
+ char *vec;
+ int ret, i;
+
+ if (len <= UM_KERN_PAGE_SIZE)
+ return os_page_mincore(addr);
+
+ vec = calloc(1, (len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE);
+ if (!vec)
+ return -ENOMEM;
+
+ ret = mincore(addr, UM_KERN_PAGE_SIZE, vec);
+ if (ret < 0) {
+ if (errno == ENOMEM || errno == EINVAL)
+ ret = 0;
+ else
+ ret = -errno;
+
+ goto out;
+ }
+
+ for (i = 0; i < ((len + UM_KERN_PAGE_SIZE - 1) / UM_KERN_PAGE_SIZE); i++) {
+ if (!(vec[i] & 1)) {
+ ret = 0;
+ goto out;
+ }
+ }
+
+ ret = 1;
+out:
+ free(vec);
+ return ret;
+}
+
void init_new_thread_signals(void)
{
set_handler(SIGSEGV);
diff --git a/arch/unicore32/include/mach/pm.h b/arch/unicore32/include/mach/pm.h
index 4dcd34a..77b5226 100644
--- a/arch/unicore32/include/mach/pm.h
+++ b/arch/unicore32/include/mach/pm.h
@@ -36,8 +36,5 @@
/* Defined in hibernate_asm.S */
extern int restore_image(pgd_t *resume_pg_dir, struct pbe *restore_pblist);
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
extern struct pbe *restore_pblist;
#endif
diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c
index d75ef8b..9969ec3 100644
--- a/arch/unicore32/kernel/hibernate.c
+++ b/arch/unicore32/kernel/hibernate.c
@@ -18,6 +18,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
+#include <asm/sections.h>
#include <asm/suspend.h>
#include "mach/pm.h"
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index de7dc5f..24e8360 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -21,6 +21,7 @@
#include <linux/sched.h>
#include <linux/uaccess.h>
+#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/unaligned.h>
diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c
index f9b5c10..0dc922d 100644
--- a/arch/unicore32/mm/fault.c
+++ b/arch/unicore32/mm/fault.c
@@ -209,8 +209,7 @@
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- ((!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -222,6 +221,11 @@
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (!(fsr ^ 0x12))
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -278,6 +282,13 @@
(VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -288,13 +299,6 @@
return 0;
}
- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fe120da..b2c486f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,6 +21,7 @@
config X86
def_bool y
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+ select ARCH_HAS_GCOV_PROFILE_ALL
select HAVE_AOUT if X86_32
select HAVE_UNSTABLE_SCHED_CLOCK
select ARCH_SUPPORTS_NUMA_BALANCING
@@ -121,6 +122,7 @@
select OLD_SIGACTION if X86_32
select COMPAT_OLD_SIGACTION if IA32_EMULATION
select RTC_LIB
+ select ARCH_SUPPORTS_ATOMIC_RMW
config INSTRUCTION_DECODER
def_bool y
@@ -207,6 +209,12 @@
config ARCH_SUSPEND_POSSIBLE
def_bool y
+config ARCH_WANT_HUGE_PMD_SHARE
+ def_bool y
+
+config ARCH_WANT_GENERAL_HUGETLB
+ def_bool y
+
config ZONE_DMA32
bool
default X86_64
@@ -951,10 +959,27 @@
default y
depends on X86_32
---help---
- This option is required by programs like DOSEMU to run 16-bit legacy
- code on X86 processors. It also may be needed by software like
- XFree86 to initialize some video cards via BIOS. Disabling this
- option saves about 6k.
+ This option is required by programs like DOSEMU to run
+ 16-bit real mode legacy code on x86 processors. It also may
+ be needed by software like XFree86 to initialize some video
+ cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+ bool "Enable support for 16-bit segments" if EXPERT
+ default y
+ ---help---
+ This option is required by programs like Wine to run 16-bit
+ protected mode legacy code on x86 processors. Disabling
+ this option saves about 300 bytes on i386, or around 6K text
+ plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+ def_bool y
+ depends on X86_16BIT && X86_32
+
+config X86_ESPFIX64
+ def_bool y
+ depends on X86_16BIT && X86_64
config TOSHIBA
tristate "Toshiba Laptop support"
@@ -1560,6 +1585,7 @@
config EFI_STUB
bool "EFI stub support"
depends on EFI
+ select RELOCATABLE
---help---
This kernel feature allows a bzImage to be loaded directly
by EFI firmware without the use of a bootloader.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5c47726..412189d 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -31,6 +31,9 @@
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
+ # Don't autogenerate MMX or SSE instructions
+ KBUILD_CFLAGS += -mno-mmx -mno-sse
+
# Never want PIC in a 32-bit kernel, prevent breakage with GCC built
# with nonstandard options
KBUILD_CFLAGS += -fno-pic
@@ -57,8 +60,11 @@
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
+ # Don't autogenerate MMX or SSE instructions
+ KBUILD_CFLAGS += -mno-mmx -mno-sse
+
# Use -mpreferred-stack-boundary=3 if supported.
- KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
+ KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 379814b..6cf0111 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -53,18 +53,18 @@
# How to compile the 16-bit code. Note we always compile for -march=i386,
# that way we can complain to the user if the CPU is insufficient.
-KBUILD_CFLAGS := $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+KBUILD_CFLAGS := $(USERINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ \
-DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes \
-march=i386 -mregparm=3 \
-include $(srctree)/$(src)/code16gcc.h \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+ -mno-mmx -mno-sse \
$(call cc-option, -ffreestanding) \
$(call cc-option, -fno-toplevel-reorder,\
- $(call cc-option, -fno-unit-at-a-time)) \
+ $(call cc-option, -fno-unit-at-a-time)) \
$(call cc-option, -fno-stack-protector) \
$(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS += $(call cc-option, -m32)
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 5ef205c..7194d9f 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -12,6 +12,7 @@
cflags-$(CONFIG_X86_32) := -march=i386
cflags-$(CONFIG_X86_64) := -mcmodel=small
KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mno-mmx -mno-sse
KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c205035..17177e8 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -865,6 +865,9 @@
* Because the x86 boot code expects to be passed a boot_params we
* need to create one ourselves (usually the bootloader would create
* one for us).
+ *
+ * The caller is responsible for filling out ->code32_start in the
+ * returned boot_params.
*/
struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
{
@@ -875,14 +878,15 @@
struct efi_info *efi;
efi_loaded_image_t *image;
void *options;
- u32 load_options_size;
efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
int options_size = 0;
efi_status_t status;
- unsigned long cmdline;
+ char *cmdline_ptr;
u16 *s2;
u8 *s1;
int i;
+ unsigned long ramdisk_addr;
+ unsigned long ramdisk_size;
sys_table = _table;
@@ -893,13 +897,14 @@
status = efi_call_phys3(sys_table->boottime->handle_protocol,
handle, &proto, (void *)&image);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+ efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
return NULL;
}
- status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+ status = efi_low_alloc(sys_table, 0x4000, 1,
+ (unsigned long *)&boot_params);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc lowmem for boot params\n");
+ efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
return NULL;
}
@@ -921,45 +926,13 @@
hdr->vid_mode = 0xffff;
hdr->boot_flag = 0xAA55;
- hdr->code32_start = (__u64)(unsigned long)image->image_base;
-
hdr->type_of_loader = 0x21;
/* Convert unicode cmdline to ascii */
- options = image->load_options;
- load_options_size = image->load_options_size / 2; /* ASCII */
- cmdline = 0;
- s2 = (u16 *)options;
-
- if (s2) {
- while (*s2 && *s2 != '\n' && options_size < load_options_size) {
- s2++;
- options_size++;
- }
-
- if (options_size) {
- if (options_size > hdr->cmdline_size)
- options_size = hdr->cmdline_size;
-
- options_size++; /* NUL termination */
-
- status = low_alloc(options_size, 1, &cmdline);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for cmdline\n");
- goto fail;
- }
-
- s1 = (u8 *)(unsigned long)cmdline;
- s2 = (u16 *)options;
-
- for (i = 0; i < options_size - 1; i++)
- *s1++ = *s2++;
-
- *s1 = '\0';
- }
- }
-
- hdr->cmd_line_ptr = cmdline;
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
+ if (!cmdline_ptr)
+ goto fail;
+ hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
hdr->ramdisk_image = 0;
hdr->ramdisk_size = 0;
@@ -969,16 +942,20 @@
memset(sdt, 0, sizeof(*sdt));
- status = handle_ramdisks(image, hdr);
+ status = handle_cmdline_files(sys_table, image,
+ (char *)(unsigned long)hdr->cmd_line_ptr,
+ "initrd=", hdr->initrd_addr_max,
+ &ramdisk_addr, &ramdisk_size);
if (status != EFI_SUCCESS)
goto fail2;
+ hdr->ramdisk_image = ramdisk_addr;
+ hdr->ramdisk_size = ramdisk_size;
return boot_params;
fail2:
- if (options_size)
- low_free(options_size, hdr->cmd_line_ptr);
+ efi_free(sys_table, options_size, hdr->cmd_line_ptr);
fail:
- low_free(0x4000, (unsigned long)boot_params);
+ efi_free(sys_table, 0x4000, (unsigned long)boot_params);
return NULL;
}
@@ -992,22 +969,24 @@
efi_memory_desc_t *mem_map;
efi_status_t status;
__u32 desc_version;
+ bool called_exit = false;
u8 nr_entries;
int i;
size = sizeof(*mem_map) * 32;
again:
- size += sizeof(*mem_map);
+ size += sizeof(*mem_map) * 2;
_size = size;
- status = low_alloc(size, 1, (unsigned long *)&mem_map);
+ status = efi_low_alloc(sys_table, size, 1, (unsigned long *)&mem_map);
if (status != EFI_SUCCESS)
return status;
+get_map:
status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
mem_map, &key, &desc_size, &desc_version);
if (status == EFI_BUFFER_TOO_SMALL) {
- low_free(_size, (unsigned long)mem_map);
+ efi_free(sys_table, _size, (unsigned long)mem_map);
goto again;
}
@@ -1029,8 +1008,20 @@
/* Might as well exit boot services now */
status = efi_call_phys2(sys_table->boottime->exit_boot_services,
handle, key);
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ if (status != EFI_SUCCESS) {
+ /*
+ * ExitBootServices() will fail if any of the event
+ * handlers change the memory map. In which case, we
+ * must be prepared to retry, but only once so that
+ * we're guaranteed to exit on repeated failures instead
+ * of spinning forever.
+ */
+ if (called_exit)
+ goto free_mem_map;
+
+ called_exit = true;
+ goto get_map;
+ }
/* Historic? */
boot_params->alt_mem_k = 32 * 1024;
@@ -1097,44 +1088,10 @@
return EFI_SUCCESS;
free_mem_map:
- low_free(_size, (unsigned long)mem_map);
+ efi_free(sys_table, _size, (unsigned long)mem_map);
return status;
}
-static efi_status_t relocate_kernel(struct setup_header *hdr)
-{
- unsigned long start, nr_pages;
- efi_status_t status;
-
- /*
- * The EFI firmware loader could have placed the kernel image
- * anywhere in memory, but the kernel has various restrictions
- * on the max physical address it can run at. Attempt to move
- * the kernel to boot_params.pref_address, or as low as
- * possible.
- */
- start = hdr->pref_address;
- nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status != EFI_SUCCESS) {
- status = low_alloc(hdr->init_size, hdr->kernel_alignment,
- &start);
- if (status != EFI_SUCCESS)
- efi_printk("Failed to alloc mem for kernel\n");
- }
-
- if (status == EFI_SUCCESS)
- memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
- hdr->init_size);
-
- hdr->pref_address = hdr->code32_start;
- hdr->code32_start = (__u32)start;
-
- return status;
-}
/*
* On success we return a pointer to a boot_params structure, and NULL
@@ -1163,14 +1120,15 @@
EFI_LOADER_DATA, sizeof(*gdt),
(void **)&gdt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
goto fail;
}
gdt->size = 0x800;
- status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
+ status = efi_low_alloc(sys_table, gdt->size, 8,
+ (unsigned long *)&gdt->address);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt\n");
goto fail;
}
@@ -1178,7 +1136,7 @@
EFI_LOADER_DATA, sizeof(*idt),
(void **)&idt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for idt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for idt structure\n");
goto fail;
}
@@ -1190,10 +1148,16 @@
* address, relocate it.
*/
if (hdr->pref_address != hdr->code32_start) {
- status = relocate_kernel(hdr);
-
+ unsigned long bzimage_addr = hdr->code32_start;
+ status = efi_relocate_kernel(sys_table, &bzimage_addr,
+ hdr->init_size, hdr->init_size,
+ hdr->pref_address,
+ hdr->kernel_alignment);
if (status != EFI_SUCCESS)
goto fail;
+
+ hdr->pref_address = hdr->code32_start;
+ hdr->code32_start = bzimage_addr;
}
status = exit_boot(boot_params, handle);
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f..cc78e2d 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -10,8 +10,6 @@
#define SEG_GRANULARITY_4KB (1 << 0)
#define DESC_TYPE_CODE_DATA (1 << 0)
-
-#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
#define EFI_READ_CHUNK_SIZE (1024 * 1024)
#define EFI_CONSOLE_OUT_DEVICE_GUID \
@@ -40,6 +38,24 @@
u32 pixels_per_scan_line;
} __packed;
+struct efi_graphics_output_protocol_mode_32 {
+ u32 max_mode;
+ u32 mode;
+ u32 info;
+ u32 size_of_info;
+ u64 frame_buffer_base;
+ u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+ u32 max_mode;
+ u32 mode;
+ u64 info;
+ u64 size_of_info;
+ u64 frame_buffer_base;
+ u64 frame_buffer_size;
+} __packed;
+
struct efi_graphics_output_protocol_mode {
u32 max_mode;
u32 mode;
@@ -49,6 +65,20 @@
unsigned long frame_buffer_size;
} __packed;
+struct efi_graphics_output_protocol_32 {
+ u32 query_mode;
+ u32 set_mode;
+ u32 blt;
+ u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+ u64 query_mode;
+ u64 set_mode;
+ u64 blt;
+ u64 mode;
+};
+
struct efi_graphics_output_protocol {
void *query_mode;
unsigned long set_mode;
@@ -56,16 +86,22 @@
struct efi_graphics_output_protocol_mode *mode;
};
+struct efi_uga_draw_protocol_32 {
+ u32 get_mode;
+ u32 set_mode;
+ u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+ u64 get_mode;
+ u64 set_mode;
+ u64 blt;
+};
+
struct efi_uga_draw_protocol {
void *get_mode;
void *set_mode;
void *blt;
};
-struct efi_simple_text_output_protocol {
- void *reset;
- void *output_string;
- void *test_string;
-};
-
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1e3184f..abb988a 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -50,6 +50,13 @@
pushl %eax
pushl %esi
pushl %ecx
+
+ call reloc
+reloc:
+ popl %ecx
+ subl reloc, %ecx
+ movl %ecx, BP_code32_start(%eax)
+
sub $0x4, %esp
ENTRY(efi_stub_entry)
@@ -63,12 +70,7 @@
hlt
jmp 1b
2:
- call 3f
-3:
- popl %eax
- subl $3b, %eax
- subl BP_pref_address(%esi), %eax
- add BP_code32_start(%esi), %eax
+ movl BP_code32_start(%esi), %eax
leal preferred_addr(%eax), %eax
jmp *%eax
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 16f24e6..92059b8 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -217,6 +217,8 @@
cmpq $0,%rax
je 1f
mov %rax, %rdx
+ leaq startup_32(%rip), %rax
+ movl %eax, BP_code32_start(%rdx)
popq %rsi
popq %rdi
@@ -230,12 +232,7 @@
hlt
jmp 1b
2:
- call 3f
-3:
- popq %rax
- subq $3b, %rax
- subq BP_pref_address(%rsi), %rax
- add BP_code32_start(%esi), %eax
+ movl BP_code32_start(%esi), %eax
leaq preferred_addr(%rax), %rax
jmp *%rax
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1..4257124 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct floppy boot is not supported. "
- .ascii "Use a boot loader program instead.\r\n"
+ .ascii "Use a boot loader.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot ...\r\n"
+ .ascii "Remove disk and press any key to reboot...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@
#else
.word 0x8664 # x86-64
#endif
- .word 3 # nr_sections
+ .word 4 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
@@ -250,6 +249,25 @@
.word 0 # NumberOfLineNumbers
.long 0x60500020 # Characteristics (section flags)
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".bss"
+ .byte 0
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0xc8000080 # Characteristics (section flags)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 94c5446..971a0ce0 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -141,7 +141,7 @@
#ifdef CONFIG_EFI_STUB
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
{
unsigned int pe_header;
unsigned short num_sections;
@@ -162,10 +162,10 @@
put_unaligned_le32(size, section + 0x8);
/* section header vma field */
- put_unaligned_le32(offset, section + 0xc);
+ put_unaligned_le32(vma, section + 0xc);
/* section header 'size of initialised data' field */
- put_unaligned_le32(size, section + 0x10);
+ put_unaligned_le32(datasz, section + 0x10);
/* section header 'file offset' field */
put_unaligned_le32(offset, section + 0x14);
@@ -177,6 +177,11 @@
}
}
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
static void update_pecoff_setup_and_reloc(unsigned int size)
{
u32 setup_offset = 0x200;
@@ -201,9 +206,6 @@
pe_header = get_unaligned_le32(&buf[0x3c]);
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
/*
* Size of code: Subtract the size of the first sector (512 bytes)
* which includes the header.
@@ -218,6 +220,22 @@
update_pecoff_section_header(".text", text_start, text_sz);
}
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+ unsigned int pe_header;
+ unsigned int bss_sz = init_sz - file_sz;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of uninitialized data */
+ put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+ /* Size of image */
+ put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+ update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
#endif /* CONFIG_EFI_STUB */
@@ -268,6 +286,9 @@
int fd;
void *kernel;
u32 crc = 0xffffffffUL;
+#ifdef CONFIG_EFI_STUB
+ unsigned int init_sz;
+#endif
/* Defaults for old kernel */
#ifdef CONFIG_X86_32
@@ -338,7 +359,9 @@
put_unaligned_le32(sys_size, &buf[0x1f4]);
#ifdef CONFIG_EFI_STUB
- update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+ update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+ init_sz = get_unaligned_le32(&buf[0x260]);
+ update_pecoff_bss(i + (sys_size * 16), init_sz);
#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
efi_stub_entry -= 0x200;
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index aafe8ce..e26984f 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -66,5 +66,5 @@
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index f80e668..990c969 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -989,7 +989,7 @@
src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
if (!src)
return -ENOMEM;
- assoc = (src + req->cryptlen + auth_tag_len);
+ assoc = (src + req->cryptlen);
scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
scatterwalk_map_and_copy(assoc, req->assoc, 0,
req->assoclen, 0);
@@ -1014,7 +1014,7 @@
scatterwalk_done(&src_sg_walk, 0, 0);
scatterwalk_done(&assoc_sg_walk, 0, 0);
} else {
- scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+ scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
kfree(src);
}
return retval;
@@ -1373,4 +1373,4 @@
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/x86/crypto/blowfish_avx2_glue.c b/arch/x86/crypto/blowfish_avx2_glue.c
index 4417e9a..183395b 100644
--- a/arch/x86/crypto/blowfish_avx2_glue.c
+++ b/arch/x86/crypto/blowfish_avx2_glue.c
@@ -581,5 +581,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Blowfish Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 3548d76..9f7cc6b 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -465,5 +465,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 414fe5d..da710fc 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -582,5 +582,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 37fd0c0..883e1af 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -574,5 +574,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 5cb86cc..16d65b0 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1725,5 +1725,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index c6631813..d416069 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -494,4 +494,4 @@
MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 8d0dfb8..c197562 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -611,4 +611,4 @@
MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 9d014a7..1937fc1 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -197,5 +197,5 @@
MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32");
-MODULE_ALIAS("crc32-pclmul");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 6812ad9..28640c3 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -280,5 +280,5 @@
MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32c");
-MODULE_ALIAS("crc32c-intel");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index 98d7a18..f368ba2 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -17,6 +17,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/crypto.h>
#include <asm/i387.h>
struct crypto_fpu_ctx {
@@ -159,3 +160,5 @@
{
crypto_unregister_template(&crypto_fpu_tmpl);
}
+
+MODULE_ALIAS_CRYPTO("fpu");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 586f41a..185fad4 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -24,10 +24,6 @@
.align 16
.Lbswap_mask:
.octa 0x000102030405060708090a0b0c0d0e0f
-.Lpoly:
- .octa 0xc2000000000000000000000000000001
-.Ltwo_one:
- .octa 0x00000001000000000000000000000001
#define DATA %xmm0
#define SHASH %xmm1
@@ -134,28 +130,3 @@
.Lupdate_just_ret:
ret
ENDPROC(clmul_ghash_update)
-
-/*
- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
- *
- * Calculate hash_key << 1 mod poly
- */
-ENTRY(clmul_ghash_setkey)
- movaps .Lbswap_mask, BSWAP
- movups (%rsi), %xmm0
- PSHUFB_XMM BSWAP %xmm0
- movaps %xmm0, %xmm1
- psllq $1, %xmm0
- psrlq $63, %xmm1
- movaps %xmm1, %xmm2
- pslldq $8, %xmm1
- psrldq $8, %xmm2
- por %xmm1, %xmm0
- # reduction
- pshufd $0b00100100, %xmm2, %xmm1
- pcmpeqd .Ltwo_one, %xmm1
- pand .Lpoly, %xmm1
- pxor %xmm1, %xmm0
- movups %xmm0, (%rdi)
- ret
-ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 6759dd1..a8d6f69 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -30,8 +30,6 @@
void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
const be128 *shash);
-void clmul_ghash_setkey(be128 *shash, const u8 *key);
-
struct ghash_async_ctx {
struct cryptd_ahash *cryptd_tfm;
};
@@ -58,13 +56,23 @@
const u8 *key, unsigned int keylen)
{
struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+ be128 *x = (be128 *)key;
+ u64 a, b;
if (keylen != GHASH_BLOCK_SIZE) {
crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
- clmul_ghash_setkey(&ctx->shash, key);
+ /* perform multiplication by 'x' in GF(2^128) */
+ a = be64_to_cpu(x->a);
+ b = be64_to_cpu(x->b);
+
+ ctx->shash.a = (__be64)((b << 1) | (a >> 63));
+ ctx->shash.b = (__be64)((a << 1) | (b >> 63));
+
+ if (a >> 63)
+ ctx->shash.b ^= cpu_to_be64(0xc2);
return 0;
}
@@ -333,4 +341,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
"acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 5e8e677..399a29d 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -119,5 +119,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS("salsa20");
-MODULE_ALIAS("salsa20-asm");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-asm");
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 23aabc6..cb57caf 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -558,5 +558,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("serpent");
-MODULE_ALIAS("serpent-asm");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-asm");
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 9ae83cf..0a86e8b 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -617,4 +617,4 @@
MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 97a356e..279f389 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -618,4 +618,4 @@
MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 4a11a9d..29e1060 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -237,4 +237,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 597d4da..ceafb01 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -272,4 +272,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha256");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 6cbd8df..d1ee9f6 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -141,7 +141,7 @@
/* save number of bits */
bits[1] = cpu_to_be64(sctx->count[0] << 3);
- bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61;
+ bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
/* Pad out to 112 mod 128 and append length */
index = sctx->count[0] & 0x7f;
@@ -279,4 +279,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha512");
diff --git a/arch/x86/crypto/twofish_avx2_glue.c b/arch/x86/crypto/twofish_avx2_glue.c
index ce33b5b..bb1f0a1 100644
--- a/arch/x86/crypto/twofish_avx2_glue.c
+++ b/arch/x86/crypto/twofish_avx2_glue.c
@@ -580,5 +580,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 2047a56..4a1f944 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -589,4 +589,4 @@
MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 0a52023..77e06c2 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -96,5 +96,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 13e63b3..56d8a08 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -495,5 +495,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index cf1a471..10adb41 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -459,7 +459,7 @@
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+ compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 474dc1b..c9305ef 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
+
+ /*
+ * Sysenter doesn't filter flags, so we need to clear NT
+ * ourselves. To save a few cycles, we can check whether
+ * NT was set instead of doing an unconditional popfq.
+ */
+ testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
@@ -184,6 +194,8 @@
TRACE_IRQS_ON
ENABLE_INTERRUPTS_SYSEXIT32
+ CFI_RESTORE_STATE
+
#ifdef CONFIG_AUDITSYSCALL
.macro auditsys_entry_common
movl %esi,%r9d /* 6th arg: 4th syscall arg */
@@ -226,7 +238,6 @@
.endm
sysenter_auditsys:
- CFI_RESTORE_STATE
auditsys_entry_common
movl %ebp,%r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
@@ -235,6 +246,11 @@
auditsys_exit sysexit_from_sys_call
#endif
+sysenter_fix_flags:
+ pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ popfq_cfi
+ jmp sysenter_flags_fixed
+
sysenter_tracesys:
#ifdef CONFIG_AUDITSYSCALL
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 653668d..4a8cb8d 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -35,9 +35,9 @@
*/
if (boot_params->sentinel) {
/* fields in boot_params are left uninitialized, clear them */
- memset(&boot_params->olpc_ofw_header, 0,
+ memset(&boot_params->ext_ramdisk_image, 0,
(char *)&boot_params->efi_info -
- (char *)&boot_params->olpc_ofw_header);
+ (char *)&boot_params->ext_ramdisk_image);
memset(&boot_params->kbd_status, 0,
(char *)&boot_params->hdr -
(char *)&boot_params->kbd_status);
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474..f50de69 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- return csum_partial_copy_generic((__force void *)src, dst,
- len, sum, err_ptr, NULL);
+ stac();
+ ret = csum_partial_copy_generic((__force void *)src, dst,
+ len, sum, err_ptr, NULL);
+ clac();
+
+ return ret;
}
/*
@@ -176,10 +182,16 @@
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- if (access_ok(VERIFY_WRITE, dst, len))
- return csum_partial_copy_generic(src, (__force void *)dst,
- len, sum, NULL, err_ptr);
+ if (access_ok(VERIFY_WRITE, dst, len)) {
+ stac();
+ ret = csum_partial_copy_generic(src, (__force void *)dst,
+ len, sum, NULL, err_ptr);
+ clac();
+ return ret;
+ }
if (len)
*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e99ac27..4af181d 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -365,7 +365,7 @@
static __always_inline __pure bool __static_cpu_has(u16 bit)
{
#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
- asm goto("1: jmp %l[t_no]\n"
+ asm_volatile_goto("1: jmp %l[t_no]\n"
"2:\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n"
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 8bf1c06..23fb67e 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -251,7 +251,8 @@
gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
}
-#define _LDT_empty(info) \
+/* This intentionally ignores lm, since 32-bit apps don't have that field. */
+#define LDT_empty(info) \
((info)->base_addr == 0 && \
(info)->limit == 0 && \
(info)->contents == 0 && \
@@ -261,11 +262,18 @@
(info)->seg_not_present == 1 && \
(info)->useable == 0)
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
+/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */
+static inline bool LDT_zero(const struct user_desc *info)
+{
+ return (info->base_addr == 0 &&
+ info->limit == 0 &&
+ info->contents == 0 &&
+ info->read_exec_only == 0 &&
+ info->seg_32bit == 0 &&
+ info->limit_in_pages == 0 &&
+ info->seg_not_present == 0 &&
+ info->useable == 0);
+}
static inline void clear_LDT(void)
{
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
index c092416..b4b38ba 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
#ifdef __KERNEL__
#include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
static inline void
dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index cccd07f..779c2ef 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -29,7 +29,7 @@
extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
unsigned long start_addr, unsigned long long end_addr);
struct setup_data;
-extern void parse_e820_ext(struct setup_data *data);
+extern void parse_e820_ext(u64 phys_addr, u32 data_len);
#if defined(CONFIG_X86_64) || \
(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 60c89f3..7a76dc2 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -94,7 +94,7 @@
#endif /* CONFIG_X86_32 */
extern int add_efi_memmap;
-extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9c999c1..01f15b2 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -155,8 +155,9 @@
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
-#define compat_elf_check_arch(x) \
- (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || \
+ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
#if __USER32_DS != __USER_DS
# error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 0000000..99efebb
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0dc7d9e..9d7d36c 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -123,14 +123,14 @@
__end_of_permanent_fixed_addresses,
/*
- * 256 temporary boot-time mappings, used by early_ioremap(),
+ * 512 temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
*
- * If necessary we round it up to the next 256 pages boundary so
+ * If necessary we round it up to the next 512 pages boundary so
* that we can have a single pgd entry and a single pte table:
*/
#define NR_FIX_BTMAPS 64
-#define FIX_BTMAPS_SLOTS 4
+#define FIX_BTMAPS_SLOTS 8
#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
FIX_BTMAP_END =
(__end_of_permanent_fixed_addresses ^
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index e25cc33..1b2fc5c 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -295,12 +295,13 @@
/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
is pending. Clear the x87 state here by setting it to fixed
values. "m" is a random variable that should be in L1 */
- alternative_input(
- ASM_NOP8 ASM_NOP2,
- "emms\n\t" /* clear stack tags */
- "fildl %P[addr]", /* set F?P to defined value */
- X86_FEATURE_FXSAVE_LEAK,
- [addr] "m" (tsk->thread.fpu.has_fpu));
+ if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+ asm volatile(
+ "fnclex\n\t"
+ "emms\n\t"
+ "fildl %P[addr]" /* set F?P to defined value */
+ : : [addr] "m" (tsk->thread.fpu.has_fpu));
+ }
return fpu_restore_checking(&tsk->thread.fpu);
}
@@ -369,7 +370,7 @@
preempt_disable();
tsk->fpu_counter = 0;
__drop_fpu(tsk);
- clear_used_math();
+ clear_stopped_child_used_math(tsk);
preempt_enable();
}
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a809121..68c0539 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
+ ptep_clear_flush(vma, addr, ptep);
}
static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf8..0a8b519 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@
#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */
-#define INTERRUPT_RETURN iretq
+#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
sysretq;
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3a16c14..0297669 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -13,7 +13,7 @@
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:"
+ asm_volatile_goto("1:"
STATIC_KEY_INITIAL_NOP
".pushsection __jump_table, \"aw\" \n\t"
_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 3741c65..b15a6b5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,6 +79,13 @@
#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+ /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+ return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+ (base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03
@@ -96,10 +103,6 @@
#define ASYNC_PF_PER_VCPU 64
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
@@ -445,7 +448,7 @@
bool nmi_injected; /* Trying to inject an NMI this entry */
struct mtrr_state_type mtrr_state;
- u32 pat;
+ u64 pat;
int switch_db_regs;
unsigned long db[KVM_NR_DB_REGS];
@@ -463,6 +466,7 @@
u64 mmio_gva;
unsigned access;
gfn_t mmio_gfn;
+ u64 mmio_gen;
struct kvm_pmu pmu;
@@ -631,8 +635,8 @@
struct kvm_x86_ops {
int (*cpu_has_kvm_support)(void); /* __init */
int (*disabled_by_bios)(void); /* __init */
- int (*hardware_enable)(void *dummy);
- void (*hardware_disable)(void *dummy);
+ int (*hardware_enable)(void);
+ void (*hardware_disable)(void);
void (*check_processor_compatibility)(void *rtn);
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
@@ -952,6 +956,20 @@
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
+static inline u64 get_canonical(u64 la)
+{
+ return ((int64_t)la << 16) >> 16;
+}
+
+static inline bool is_noncanonical_address(u64 la)
+{
+#ifdef CONFIG_X86_64
+ return get_canonical(la) != la;
+#else
+ return false;
+#endif
+}
+
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
@@ -1010,7 +1028,7 @@
void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
void kvm_define_shared_msr(unsigned index, u32 msr);
-void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index fa5f71e..e6833c6 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -32,11 +32,20 @@
#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
-#define MCACOD 0xffff /* MCA Error Code */
+
+/*
+ * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
+ * bits 15:0. But bit 12 is the 'F' bit, defined for corrected
+ * errors to indicate that errors are being filtered by hardware.
+ * We should mask out bit 12 when looking for specific signatures
+ * of uncorrected errors - so the F bit is deliberately skipped
+ * in this #define.
+ */
+#define MCACOD 0xefff /* MCA Error Code */
/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK 0xfff0
+#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */
#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
#define MCACOD_DATA 0x0134 /* Data Load */
#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf367..be12c53 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@
/* Re-load page tables */
load_cr3(next->pgd);
- /* stop flush ipis for the previous mm */
+ /* Stop flush ipis for the previous mm */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
- /*
- * load the LDT, if the LDT is different:
- */
+ /* Load the LDT, if the LDT is different: */
if (unlikely(prev->context.ldt != next->context.ldt))
load_LDT_nolock(&next->context);
}
#ifdef CONFIG_SMP
- else {
+ else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
- if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
- /* We were in lazy tlb mode and leave_mm disabled
+ if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+ /*
+ * On established mms, the mm_cpumask is only changed
+ * from irq context, from ptep_clear_flush() while in
+ * lazy tlb mode, and here. Irqs are blocked during
+ * schedule, protecting us from simultaneous changes.
+ */
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+ /*
+ * We were in lazy tlb mode and leave_mm disabled
* tlb flush IPI delivery. We must reload CR3
* to make sure to use no freed page tables.
*/
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ef17af0..4376b45 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -18,7 +18,6 @@
#define THREAD_SIZE_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define STACKFAULT_STACK 0
#define DOUBLEFAULT_STACK 1
#define NMI_STACK 0
#define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6c896fb..970f309 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
#define IRQ_STACK_ORDER 2
#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */
#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1e67223..5460bf9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -415,9 +415,16 @@
}
#define pte_accessible pte_accessible
-static inline int pte_accessible(pte_t a)
+static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
- return pte_flags(a) & _PAGE_PRESENT;
+ if (pte_flags(a) & _PAGE_PRESENT)
+ return true;
+
+ if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) &&
+ mm_tlb_flush_pending(mm))
+ return true;
+
+ return false;
}
static inline int pte_hidden(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d88344..b1609f2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -61,6 +61,8 @@
#define MODULES_VADDR _AC(0xffffffffa0000000, UL)
#define MODULES_END _AC(0xffffffffff000000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
#define EARLY_DYNAMIC_PAGE_TABLES 64
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 942a086..68e9f00 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -232,6 +232,22 @@
#define ARCH_HAS_USER_SINGLE_STEP_INFO
+/*
+ * When hitting ptrace_stop(), we cannot return using SYSRET because
+ * that does not restore the full CPU state, only a minimal set. The
+ * ptracer can change arbitrary register values, which is usually okay
+ * because the usual ptrace stops run off the signal delivery path which
+ * forces IRET; however, ptrace_event() stops happen in arbitrary places
+ * in the kernel and don't force IRET path.
+ *
+ * So force IRET path after a ptrace stop.
+ */
+#define arch_ptrace_stop_needed(code, info) \
+({ \
+ set_thread_flag(TIF_NOTIFY_RESUME); \
+ false; \
+})
+
struct user_desc;
extern int do_get_thread_area(struct task_struct *p, int idx,
struct user_desc __user *info);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index b7bf350..2e327f1 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -62,6 +62,8 @@
#ifndef _SETUP
+#include <asm/espfix.h>
+
/*
* This is set up by the setup-routine at boot-time
*/
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 33692ea..e3ddd7d 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -233,8 +233,4 @@
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
-/* The {read|write|spin}_lock() on x86 are full memory barriers. */
-static inline void smp_mb__after_lock(void) { }
-#define ARCH_HAS_SMP_MB_AFTER_LOCK
-
#endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a1df6e8..d3e0ff5 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -147,7 +147,7 @@
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \
- _TIF_USER_RETURN_NOTIFY)
+ _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 095b215..60bd274 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@
extern const struct cpumask *cpu_coregroup_mask(int cpu);
-#ifdef ENABLE_TOPO_DEFINES
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca7..2874be9 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -34,7 +34,7 @@
native_read_tscp(&p);
} else {
/* Load per CPU data from GDT */
- asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+ asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
}
return p;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fb..b913915 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@
return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
}
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
{
unsigned long pfn;
- int ret = 0;
+ int ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
- if (unlikely(mfn >= machine_to_phys_nr)) {
- pfn = ~0;
- goto try_override;
- }
- pfn = 0;
+ if (unlikely(mfn >= machine_to_phys_nr))
+ return ~0;
+
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
- /* ret might be < 0 if there are no entries in the m2p for mfn */
if (ret < 0)
- pfn = ~0;
- else if (get_phys_to_machine(pfn) != mfn)
+ return ~0;
+
+ return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+ unsigned long pfn;
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return mfn;
+
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) != mfn) {
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@
* m2p_find_override_pfn returns ~0 if it doesn't find anything.
*/
pfn = m2p_find_override_pfn(mfn, ~0);
+ }
/*
* pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7ea79c5..492b298 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@
#define AVX_XOR_SPEED \
do { \
- if (cpu_has_avx) \
+ if (cpu_has_avx && cpu_has_osxsave) \
xor_speed(&xor_block_avx); \
} while (0)
#define AVX_SELECT(FASTEST) \
- (cpu_has_avx ? &xor_block_avx : FASTEST)
+ (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
#else
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 5d9a303..d3a8778 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -211,9 +211,9 @@
__u32 padding[3];
};
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC 2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT 4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
/* for KVM_SET_CPUID2 */
struct kvm_cpuid2 {
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index 46727eb..6e1aaf7 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@
unsigned int seg_not_present:1;
unsigned int useable:1;
#ifdef __x86_64__
+ /*
+ * Because this bit is not present in 32-bit user code, user
+ * programs can pass uninitialized values here. Therefore, in
+ * any context in which a user_desc comes from a 32-bit program,
+ * the kernel must act as though lm == 0, regardless of the
+ * actual value.
+ */
unsigned int lm:1;
#endif
};
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 2af848d..d3fd447 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -179,6 +179,7 @@
#define MSR_AMD64_PATCH_LOADER 0xc0010020
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD64_LS_CFG 0xc0011020
#define MSR_AMD64_DC_CFG 0xc0011022
#define MSR_AMD64_BU_CFG2 0xc001102a
#define MSR_AMD64_IBSFETCHCTL 0xc0011030
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 54991a7..b16e6d2 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -6,7 +6,7 @@
* EFLAGS bits
*/
#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
-#define X86_EFLAGS_BIT1 0x00000002 /* Bit 1 - always on */
+#define X86_EFLAGS_FIXED 0x00000002 /* Bit 1 - always on */
#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */
#define X86_EFLAGS_AF 0x00000010 /* Auxiliary carry Flag */
#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d651082..dccea7f 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,7 +65,9 @@
#define EXIT_REASON_EOI_INDUCED 45
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_INVEPT 50
#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
#define EXIT_REASON_APIC_WRITE 56
@@ -111,6 +113,7 @@
{ EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
{ EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
{ EXIT_REASON_INVD, "INVD" }, \
+ { EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }, \
{ EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7bd3bd3..111eb35 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -27,6 +27,7 @@
obj-y += syscall_$(BITS).o
obj-$(CONFIG_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index b44577b..ec94e11 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -48,9 +48,20 @@
#ifndef CONFIG_64BIT
native_store_gdt((struct desc_ptr *)&header->pmode_gdt);
+ /*
+ * We have to check that we can write back the value, and not
+ * just read it. At least on 90 nm Pentium M (Family 6, Model
+ * 13), reading an invalid MSR is not guaranteed to trap, see
+ * Erratum X4 in "Intel Pentium M Processor on 90 nm Process
+ * with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90
+ * nm process with 512-KB L2 Cache Specification Update".
+ */
if (!rdmsr_safe(MSR_EFER,
&header->pmode_efer_low,
- &header->pmode_efer_high))
+ &header->pmode_efer_high) &&
+ !wrmsr_safe(MSR_EFER,
+ header->pmode_efer_low,
+ header->pmode_efer_high))
header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER);
#endif /* !CONFIG_64BIT */
@@ -61,7 +72,10 @@
}
if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
&header->pmode_misc_en_low,
- &header->pmode_misc_en_high))
+ &header->pmode_misc_en_high) &&
+ !wrmsr_safe(MSR_IA32_MISC_ENABLE,
+ header->pmode_misc_en_low,
+ header->pmode_misc_en_high))
header->pmode_behavior |=
(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
header->realmode_flags = acpi_realmode_flags;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3048ded..59554dc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,7 @@
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{}
};
@@ -27,6 +28,7 @@
static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{}
};
@@ -81,13 +83,20 @@
next_northbridge(misc, amd_nb_misc_ids);
node_to_amd_nb(i)->link = link =
next_northbridge(link, amd_nb_link_ids);
- }
+ }
+ /* GART present only on Fam15h upto model 0fh */
if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
- boot_cpu_data.x86 == 0x15)
+ (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
amd_northbridges.flags |= AMD_NB_GART;
/*
+ * Check for L3 cache presence.
+ */
+ if (!cpuid_edx(0x80000006))
+ return 0;
+
+ /*
* Some CPU families support L3 Cache Index Disable. There are some
* limitations because of E382 and E388 on family 0x10.
*/
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 904611b..033eb44 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1263,7 +1263,7 @@
unsigned int value, queued;
int i, j, acked = 0;
unsigned long long tsc = 0, ntsc;
- long long max_loops = cpu_khz;
+ long long max_loops = cpu_khz ? cpu_khz : 1000000;
if (cpu_has_tsc)
rdtscll(tsc);
@@ -1360,7 +1360,7 @@
break;
}
if (queued) {
- if (cpu_has_tsc) {
+ if (cpu_has_tsc && cpu_khz) {
rdtscll(ntsc);
max_loops = (cpu_khz << 10) - (ntsc - tsc);
} else
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 794f6eb..b32dbb4 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -98,7 +98,7 @@
break;
case UV3_HUB_PART_NUMBER:
case UV3_HUB_PART_NUMBER_X:
- uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+ uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
break;
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 5013a48..ae177a0 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -508,6 +508,16 @@
set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
}
#endif
+
+ /* F16h erratum 793, CVE-2013-6885 */
+ if (c->x86 == 0x16 && c->x86_model <= 0xf) {
+ u64 val;
+
+ rdmsrl(MSR_AMD64_LS_CFG, val);
+ if (!(val & BIT(15)))
+ wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
+ }
+
}
static const int amd_erratum_383[];
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 22018f7..5641401 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@
static int __init x86_xsave_setup(char *s)
{
+ if (strlen(s))
+ return 0;
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
setup_clear_cpu_cap(X86_FEATURE_AVX);
@@ -284,8 +286,13 @@
raw_local_save_flags(eflags);
BUG_ON(eflags & X86_EFLAGS_AC);
- if (cpu_has(c, X86_FEATURE_SMAP))
+ if (cpu_has(c, X86_FEATURE_SMAP)) {
+#ifdef CONFIG_X86_SMAP
set_in_cr4(X86_CR4_SMAP);
+#else
+ clear_in_cr4(X86_CR4_SMAP);
+#endif
+ }
}
/*
@@ -1129,7 +1136,7 @@
/* Flags to clear on syscall */
wrmsrl(MSR_SYSCALL_MASK,
X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
- X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+ X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
}
/*
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 9b0c441..8533e69 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -154,6 +154,21 @@
setup_clear_cpu_cap(X86_FEATURE_ERMS);
}
}
+
+ /*
+ * Intel Quark Core DevMan_001.pdf section 6.4.11
+ * "The operating system also is required to invalidate (i.e., flush)
+ * the TLB when any changes are made to any of the page table entries.
+ * The operating system must reload CR3 to cause the TLB to be flushed"
+ *
+ * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+ * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+ * to be modified
+ */
+ if (c->x86 == 5 && c->x86_model == 9) {
+ pr_info("Disabling PGE capability bit\n");
+ setup_clear_cpu_cap(X86_FEATURE_PGE);
+ }
}
#ifdef CONFIG_X86_32
@@ -387,7 +402,8 @@
set_cpu_cap(c, X86_FEATURE_PEBS);
}
- if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+ if (c->x86 == 6 && cpu_has_clflush &&
+ (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
#ifdef CONFIG_X86_64
@@ -627,7 +643,7 @@
tlb_flushall_shift = 5;
break;
case 0x63a: /* Ivybridge */
- tlb_flushall_shift = 1;
+ tlb_flushall_shift = 2;
break;
default:
tlb_flushall_shift = 6;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 8f4be53..1853659 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -60,6 +60,7 @@
.rating = 400, /* use this when running on Hyperv*/
.read = read_hv_clock,
.mask = CLOCKSOURCE_MASK(64),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index fa72a39..3982357 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -510,8 +510,9 @@
static void generic_get_mtrr(unsigned int reg, unsigned long *base,
unsigned long *size, mtrr_type *type)
{
- unsigned int mask_lo, mask_hi, base_lo, base_hi;
- unsigned int tmp, hi;
+ u32 mask_lo, mask_hi, base_lo, base_hi;
+ unsigned int hi;
+ u64 tmp, mask;
/*
* get_mtrr doesn't need to update mtrr_state, also it could be called
@@ -532,18 +533,18 @@
rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi);
/* Work out the shifted address mask: */
- tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT;
- mask_lo = size_or_mask | tmp;
+ tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT;
+ mask = size_or_mask | tmp;
/* Expand tmp with high bits to all 1s: */
- hi = fls(tmp);
+ hi = fls64(tmp);
if (hi > 0) {
- tmp |= ~((1<<(hi - 1)) - 1);
+ tmp |= ~((1ULL<<(hi - 1)) - 1);
- if (tmp != mask_lo) {
+ if (tmp != mask) {
printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
- mask_lo = tmp;
+ mask = tmp;
}
}
@@ -551,8 +552,8 @@
* This works correctly if size is a power of two, i.e. a
* contiguous range:
*/
- *size = -mask_lo;
- *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
+ *size = -mask;
+ *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
*type = base_lo & 0xff;
out_put_cpu:
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 726bf96..ca22b73 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -305,7 +305,8 @@
return -EINVAL;
}
- if (base & size_or_mask || size & size_or_mask) {
+ if ((base | (base + size - 1)) >>
+ (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
pr_warning("mtrr: base or size exceeds the MTRR width\n");
return -EINVAL;
}
@@ -583,6 +584,7 @@
int __initdata changed_by_mtrr_cleanup;
+#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1))
/**
* mtrr_bp_init - initialize mtrrs on the boot CPU
*
@@ -600,7 +602,7 @@
if (cpu_has_mtrr) {
mtrr_if = &generic_mtrr_ops;
- size_or_mask = 0xff000000; /* 36 bits */
+ size_or_mask = SIZE_OR_MASK_BITS(36);
size_and_mask = 0x00f00000;
phys_addr = 36;
@@ -619,7 +621,7 @@
boot_cpu_data.x86_mask == 0x4))
phys_addr = 36;
- size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1);
+ size_or_mask = SIZE_OR_MASK_BITS(phys_addr);
size_and_mask = ~size_or_mask & 0xfffff00000ULL;
} else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR &&
boot_cpu_data.x86 == 6) {
@@ -627,7 +629,7 @@
* VIA C* family have Intel style MTRRs,
* but don't support PAE
*/
- size_or_mask = 0xfff00000; /* 32 bits */
+ size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
phys_addr = 32;
}
@@ -637,21 +639,21 @@
if (cpu_has_k6_mtrr) {
/* Pre-Athlon (K6) AMD CPU MTRRs */
mtrr_if = mtrr_ops[X86_VENDOR_AMD];
- size_or_mask = 0xfff00000; /* 32 bits */
+ size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
}
break;
case X86_VENDOR_CENTAUR:
if (cpu_has_centaur_mcr) {
mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR];
- size_or_mask = 0xfff00000; /* 32 bits */
+ size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
}
break;
case X86_VENDOR_CYRIX:
if (cpu_has_cyrix_arr) {
mtrr_if = mtrr_ops[X86_VENDOR_CYRIX];
- size_or_mask = 0xfff00000; /* 32 bits */
+ size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
}
break;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1025f3c..123d9e2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1165,6 +1165,9 @@
for (i = 0; i < cpuc->n_events; i++) {
if (event == cpuc->event_list[i]) {
+ if (i >= cpuc->n_events - cpuc->n_added)
+ --cpuc->n_added;
+
if (x86_pmu.put_event_constraints)
x86_pmu.put_event_constraints(cpuc, event);
@@ -1249,10 +1252,20 @@
static int __kprobes
perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
+ int ret;
+ u64 start_clock;
+ u64 finish_clock;
+
if (!atomic_read(&active_events))
return NMI_DONE;
- return x86_pmu.handle_irq(regs);
+ start_clock = local_clock();
+ ret = x86_pmu.handle_irq(regs);
+ finish_clock = local_clock();
+
+ perf_sample_event_took(finish_clock - start_clock);
+
+ return ret;
}
struct event_constraint emptyconstraint;
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 5f0581e..b46601a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -10,6 +10,7 @@
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/ptrace.h>
+#include <linux/syscore_ops.h>
#include <asm/apic.h>
@@ -816,6 +817,18 @@
return ret;
}
+static void ibs_eilvt_setup(void)
+{
+ /*
+ * Force LVT offset assignment for family 10h: The offsets are
+ * not assigned by the BIOS for this family, so the OS is
+ * responsible for doing it. If the OS assignment fails, fall
+ * back to BIOS settings and try to setup this.
+ */
+ if (boot_cpu_data.x86 == 0x10)
+ force_ibs_eilvt_setup();
+}
+
static inline int get_ibs_lvt_offset(void)
{
u64 val;
@@ -851,6 +864,36 @@
setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
}
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+ clear_APIC_ibs(NULL);
+ return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+ ibs_eilvt_setup();
+ setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+ .resume = perf_ibs_resume,
+ .suspend = perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+ register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
static int __cpuinit
perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
{
@@ -877,18 +920,12 @@
if (!caps)
return -ENODEV; /* ibs not supported by the cpu */
- /*
- * Force LVT offset assignment for family 10h: The offsets are
- * not assigned by the BIOS for this family, so the OS is
- * responsible for doing it. If the OS assignment fails, fall
- * back to BIOS settings and try to setup this.
- */
- if (boot_cpu_data.x86 == 0x10)
- force_ibs_eilvt_setup();
+ ibs_eilvt_setup();
if (!ibs_eilvt_valid())
goto out;
+ perf_ibs_pm_init();
get_online_cpus();
ibs_caps = caps;
/* make ibs_caps visible to other cpus: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a9e2207..6d6bb6f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1199,6 +1199,15 @@
intel_pmu_lbr_read();
/*
+ * CondChgd bit 63 doesn't mean any overflow status. Ignore
+ * and clear the bit.
+ */
+ if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+ if (!status)
+ goto done;
+ }
+
+ /*
* PEBS overflow sets bit 62 in the global status register
*/
if (__test_and_clear_bit(62, (unsigned long *)&status)) {
@@ -2163,6 +2172,9 @@
case 62: /* IvyBridge EP */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ /* dTLB-load-misses on IVB is different than SNB */
+ hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 52441a2..7185af2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@
static struct uncore_event_desc snbep_uncore_qpi_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
- INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
{ /* end: all zeroes */ },
};
@@ -2657,6 +2657,17 @@
return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
}
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+ return event->pmu->event_init == uncore_pmu_event_init;
+}
+
static int
uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
{
@@ -2671,13 +2682,18 @@
return -EINVAL;
n = box->n_events;
- box->event_list[n] = leader;
- n++;
+
+ if (is_uncore_event(leader)) {
+ box->event_list[n] = leader;
+ n++;
+ }
+
if (!dogrp)
return n;
list_for_each_entry(event, &leader->sibling_list, group_entry) {
- if (event->state <= PERF_EVENT_STATE_OFF)
+ if (!is_uncore_event(event) ||
+ event->state <= PERF_EVENT_STATE_OFF)
continue;
if (n >= max_count)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index b158152..2fbad6b 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -52,8 +52,7 @@
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207..66e274a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@
[ DEBUG_STACK-1 ] = "#DB",
[ NMI_STACK-1 ] = "NMI",
[ DOUBLEFAULT_STACK-1 ] = "#DF",
- [ STACKFAULT_STACK-1 ] = "#SS",
[ MCE_STACK-1 ] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d32abea..174da5f 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -658,15 +658,18 @@
* boot_params.e820_map, others are passed via SETUP_E820_EXT node of
* linked list of struct setup_data, which is parsed here.
*/
-void __init parse_e820_ext(struct setup_data *sdata)
+void __init parse_e820_ext(u64 phys_addr, u32 data_len)
{
int entries;
struct e820entry *extmap;
+ struct setup_data *sdata;
+ sdata = early_memremap(phys_addr, data_len);
entries = sdata->len / sizeof(struct e820entry);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ early_iounmap(sdata, data_len);
printk(KERN_INFO "e820: extended physical RAM map:\n");
e820_print_map("extended");
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 94ab6b9..4f7c82c 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -196,16 +196,21 @@
static void __init intel_remapping_check(int num, int slot, int func)
{
u8 revision;
+ u16 device;
+ device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
/*
- * Revision 0x13 of this chipset supports irq remapping
- * but has an erratum that breaks its behavior, flag it as such
+ * Revision <= 13 of all triggering devices id in this quirk
+ * have a problem draining interrupts when irq remapping is
+ * enabled, and should be flagged as broken. Additionally
+ * revision 0x22 of device id 0x3405 has this problem.
*/
- if (revision == 0x13)
+ if (revision <= 0x13)
set_irq_remapping_broken();
-
+ else if (device == 0x3405 && revision == 0x22)
+ set_irq_remapping_broken();
}
#define QFLAG_APPLY_ONCE 0x1
@@ -239,6 +244,8 @@
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
{ PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+ { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST,
+ PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 8f3e2de..5c38e2b 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -434,8 +434,9 @@
jnz sysenter_audit
sysenter_do_call:
cmpl $(NR_syscalls), %eax
- jae syscall_badsys
+ jae sysenter_badsys
call *sys_call_table(,%eax,4)
+sysenter_after_call:
movl %eax,PT_EAX(%esp)
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_ANY)
@@ -516,6 +517,7 @@
jae syscall_badsys
syscall_call:
call *sys_call_table(,%eax,4)
+syscall_after_call:
movl %eax,PT_EAX(%esp) # store the return value
syscall_exit:
LOCKDEP_SYS_EXIT
@@ -530,6 +532,7 @@
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
# are returning to the kernel.
@@ -540,6 +543,7 @@
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
CFI_REMEMBER_STATE
je ldt_ss # returning to user-space with LDT SS
+#endif
restore_nocheck:
RESTORE_REGS 4 # skip orig_eax/error_code
irq_return:
@@ -552,13 +556,9 @@
.previous
_ASM_EXTABLE(irq_return,iret_exc)
+#ifdef CONFIG_X86_ESPFIX32
CFI_RESTORE_STATE
ldt_ss:
- larl PT_OLDSS(%esp), %eax
- jnz restore_nocheck
- testl $0x00400000, %eax # returning to 32bit stack?
- jnz restore_nocheck # allright, normal return
-
#ifdef CONFIG_PARAVIRT
/*
* The kernel can't run on a non-flat stack if paravirt mode
@@ -600,6 +600,7 @@
lss (%esp), %esp /* switch to espfix segment */
CFI_ADJUST_CFA_OFFSET -8
jmp restore_nocheck
+#endif
CFI_ENDPROC
ENDPROC(system_call)
@@ -690,8 +691,13 @@
END(syscall_fault)
syscall_badsys:
- movl $-ENOSYS,PT_EAX(%esp)
- jmp resume_userspace
+ movl $-ENOSYS,%eax
+ jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+ movl $-ENOSYS,%eax
+ jmp sysenter_after_call
END(syscall_badsys)
CFI_ENDPROC
/*
@@ -707,6 +713,7 @@
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
*/
+#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -716,8 +723,10 @@
pushl_cfi %eax
lss (%esp), %esp /* switch to the normal stack segment */
CFI_ADJUST_CFA_OFFSET -8
+#endif
.endm
.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
movl %ss, %eax
/* see if on espfix stack */
cmpw $__ESPFIX_SS, %ax
@@ -728,6 +737,7 @@
/* switch to normal stack */
FIXUP_ESPFIX_STACK
27:
+#endif
.endm
/*
@@ -1075,7 +1085,7 @@
pushl $0 /* Pass NULL as regs pointer */
movl 4*4(%esp), %eax
movl 0x4(%ebp), %edx
- leal function_trace_op, %ecx
+ movl function_trace_op, %ecx
subl $MCOUNT_INSN_SIZE, %eax
.globl ftrace_call
@@ -1133,7 +1143,7 @@
movl 12*4(%esp), %eax /* Load ip (1st parameter) */
subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
- leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
pushl %esp /* Save pt_regs as 4th parameter */
GLOBAL(ftrace_regs_call)
@@ -1335,11 +1345,13 @@
ENTRY(nmi)
RING0_INT_FRAME
ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
pushl_cfi %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
popl_cfi %eax
je nmi_espfix_stack
+#endif
cmpl $ia32_sysenter_target,(%esp)
je nmi_stack_fixup
pushl_cfi %eax
@@ -1379,6 +1391,7 @@
FIX_STACK 24, nmi_stack_correct, 1
jmp nmi_stack_correct
+#ifdef CONFIG_X86_ESPFIX32
nmi_espfix_stack:
/* We have a RING0_INT_FRAME here.
*
@@ -1400,6 +1413,7 @@
lss 12+4(%esp), %esp # back to espfix stack
CFI_ADJUST_CFA_OFFSET -24
jmp irq_return
+#endif
CFI_ENDPROC
END(nmi)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 7272089..6ed8f16 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -58,6 +58,7 @@
#include <asm/asm.h>
#include <asm/context_tracking.h>
#include <asm/smap.h>
+#include <asm/pgtable_types.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -88,7 +89,7 @@
MCOUNT_SAVE_FRAME \skip
/* Load the ftrace_ops into the 3rd parameter */
- leaq function_trace_op, %rdx
+ movq function_trace_op(%rip), %rdx
/* Load ip into the first parameter */
movq RIP(%rsp), %rdi
@@ -365,7 +366,7 @@
/*CFI_REL_OFFSET ss,0*/
pushq_cfi %rax /* rsp */
CFI_REL_OFFSET rsp,0
- pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */
+ pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */
/*CFI_REL_OFFSET rflags,0*/
pushq_cfi $__KERNEL_CS /* cs */
/*CFI_REL_OFFSET cs,0*/
@@ -556,11 +557,14 @@
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
jz 1f
- testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET
- jnz int_ret_from_sys_call
-
- RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
- jmp ret_from_sys_call # go to the SYSRET fastpath
+ /*
+ * By the time we get here, we have no idea whether our pt_regs,
+ * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+ * the slow path, or one of the ia32entry paths.
+ * Use int_ret_from_sys_call to return, since it can safely handle
+ * all of the above.
+ */
+ jmp int_ret_from_sys_call
1:
subq $REST_SKIP, %rsp # leave space for volatiles
@@ -1056,32 +1060,52 @@
irq_return:
INTERRUPT_RETURN
- _ASM_EXTABLE(irq_return, bad_iret)
-#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
- iretq
- _ASM_EXTABLE(native_iret, bad_iret)
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4,(SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
#endif
- .section .fixup,"ax"
-bad_iret:
+.global native_irq_return_iret
+native_irq_return_iret:
/*
- * The iret traps when the %cs or %ss being restored is bogus.
- * We've lost the original trap vector and error code.
- * #GPF is the most likely one to get for an invalid selector.
- * So pretend we completed the iret and took the #GPF in user mode.
- *
- * We are now running with the kernel GS after exception recovery.
- * But error_entry expects us to have user GS to match the user %cs,
- * so swap back.
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
*/
- pushq $0
+ iretq
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq_cfi %rax
+ pushq_cfi %rdi
SWAPGS
- jmp general_protection
-
- .previous
+ movq PER_CPU_VAR(espfix_waddr),%rdi
+ movq %rax,(0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp),%rax /* RIP */
+ movq %rax,(1*8)(%rdi)
+ movq (3*8)(%rsp),%rax /* CS */
+ movq %rax,(2*8)(%rdi)
+ movq (4*8)(%rsp),%rax /* RFLAGS */
+ movq %rax,(3*8)(%rdi)
+ movq (6*8)(%rsp),%rax /* SS */
+ movq %rax,(5*8)(%rdi)
+ movq (5*8)(%rsp),%rax /* RSP */
+ movq %rax,(4*8)(%rdi)
+ andl $0xffff0000,%eax
+ popq_cfi %rdi
+ orq PER_CPU_VAR(espfix_stack),%rax
+ SWAPGS
+ movq %rax,%rsp
+ popq_cfi %rax
+ jmp native_irq_return_iret
+#endif
/* edi: workmask, edx: work */
retint_careful:
@@ -1127,9 +1151,9 @@
call preempt_schedule_irq
jmp exit_intr
#endif
-
CFI_ENDPROC
END(common_interrupt)
+
/*
* End of kprobes section
*/
@@ -1468,7 +1492,7 @@
paranoidzeroentry_ist debug do_debug DEBUG_STACK
paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
#ifdef CONFIG_XEN
zeroentry xen_debug do_debug
zeroentry xen_int3 do_int3
@@ -1578,16 +1602,15 @@
/*
* There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
*/
error_kernelspace:
incl %ebx
- leaq irq_return(%rip),%rcx
+ leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
- je error_swapgs
+ je error_bad_iret
movl %ecx,%eax /* zero extend */
cmpq %rax,RIP+8(%rsp)
je bstep_iret
@@ -1598,7 +1621,15 @@
bstep_iret:
/* Fix truncated RIP */
movq %rcx,RIP+8(%rsp)
- jmp error_swapgs
+ /* fall through */
+
+error_bad_iret:
+ SWAPGS
+ mov %rsp,%rdi
+ call fixup_bad_iret
+ mov %rax,%rsp
+ decl %ebx /* Return to usergs */
+ jmp error_sti
CFI_ENDPROC
END(error_entry)
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 0000000..94d857f
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,208 @@
+/* ----------------------------------------------------------------------- *
+ *
+ * Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer. This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart. When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace. The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables. The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE (8*8UL)
+#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+ __aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+ unsigned long page, slot;
+ unsigned long addr;
+
+ page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+ slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+ addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+ addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+ addr += ESPFIX_BASE_ADDR;
+ return addr;
+}
+
+#define PTE_STRIDE (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+ unsigned long rand;
+
+ /*
+ * This is run before the entropy pools are initialized,
+ * but this is hopefully better than nothing.
+ */
+ if (!arch_get_random_long(&rand)) {
+ /* The constant is an arbitrary large prime */
+ rdtscll(rand);
+ rand *= 0xc345c6b72fd16123UL;
+ }
+
+ slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+ page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+ & (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+ pgd_t *pgd_p;
+ pteval_t ptemask;
+
+ ptemask = __supported_pte_mask;
+
+ /* Install the espfix pud into the kernel page directory */
+ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+ pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+ /* Randomize the locations */
+ init_espfix_random();
+
+ /* The rest is the same as for any other processor */
+ init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+ unsigned int cpu, page;
+ unsigned long addr;
+ pud_t pud, *pud_p;
+ pmd_t pmd, *pmd_p;
+ pte_t pte, *pte_p;
+ int n;
+ void *stack_page;
+ pteval_t ptemask;
+
+ /* We only have to do this once... */
+ if (likely(this_cpu_read(espfix_stack)))
+ return; /* Already initialized */
+
+ cpu = smp_processor_id();
+ addr = espfix_base_addr(cpu);
+ page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+ /* Did another CPU already set this up? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (likely(stack_page))
+ goto done;
+
+ mutex_lock(&espfix_init_mutex);
+
+ /* Did we race on the lock? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (stack_page)
+ goto unlock_done;
+
+ ptemask = __supported_pte_mask;
+
+ pud_p = &espfix_pud_page[pud_index(addr)];
+ pud = *pud_p;
+ if (!pud_present(pud)) {
+ pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+ set_pud(&pud_p[n], pud);
+ }
+
+ pmd_p = pmd_offset(&pud, addr);
+ pmd = *pmd_p;
+ if (!pmd_present(pmd)) {
+ pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+ pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+ set_pmd(&pmd_p[n], pmd);
+ }
+
+ pte_p = pte_offset_kernel(&pmd, addr);
+ stack_page = (void *)__get_free_page(GFP_KERNEL);
+ pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+ for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+ set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+ /* Job is done for this CPU and any CPU which shares this page */
+ ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+ mutex_unlock(&espfix_init_mutex);
+done:
+ this_cpu_write(espfix_stack, addr);
+ this_cpu_write(espfix_waddr, (unsigned long)stack_page
+ + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 42a392a..1ffc32d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -77,8 +77,7 @@
return addr >= start && addr < end;
}
-static int
-do_ftrace_mod_code(unsigned long ip, const void *new_code)
+static unsigned long text_ip_addr(unsigned long ip)
{
/*
* On x86_64, kernel text mappings are mapped read-only with
@@ -91,7 +90,7 @@
if (within(ip, (unsigned long)_text, (unsigned long)_etext))
ip = (unsigned long)__va(__pa_symbol(ip));
- return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
+ return ip;
}
static const unsigned char *ftrace_nop_replace(void)
@@ -123,8 +122,10 @@
if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
return -EINVAL;
+ ip = text_ip_addr(ip);
+
/* replace the text with the new text */
- if (do_ftrace_mod_code(ip, new_code))
+ if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
return -EPERM;
sync_core();
@@ -221,33 +222,56 @@
return -EINVAL;
}
-int ftrace_update_ftrace_func(ftrace_func_t func)
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
{
- unsigned long ip = (unsigned long)(&ftrace_call);
- unsigned char old[MCOUNT_INSN_SIZE], *new;
+ unsigned char old[MCOUNT_INSN_SIZE];
int ret;
- memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
- new = ftrace_call_replace(ip, (unsigned long)func);
+ memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+ ftrace_update_func = ip;
+ /* Make sure the breakpoints see the ftrace_update_func update */
+ smp_wmb();
/* See comment above by declaration of modifying_ftrace_code */
atomic_inc(&modifying_ftrace_code);
ret = ftrace_modify_code(ip, old, new);
- /* Also update the regs callback function */
- if (!ret) {
- ip = (unsigned long)(&ftrace_regs_call);
- memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
- new = ftrace_call_replace(ip, (unsigned long)func);
- ret = ftrace_modify_code(ip, old, new);
- }
-
atomic_dec(&modifying_ftrace_code);
return ret;
}
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+ unsigned long ip = (unsigned long)(&ftrace_call);
+ unsigned char *new;
+ int ret;
+
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = update_ftrace_func(ip, new);
+
+ /* Also update the regs callback function */
+ if (!ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = update_ftrace_func(ip, new);
+ }
+
+ return ret;
+}
+
+static int is_ftrace_caller(unsigned long ip)
+{
+ if (ip == ftrace_update_func)
+ return 1;
+
+ return 0;
+}
+
/*
* A breakpoint was added to the code address we are about to
* modify, and this is the handle that will just skip over it.
@@ -257,10 +281,13 @@
*/
int ftrace_int3_handler(struct pt_regs *regs)
{
+ unsigned long ip;
+
if (WARN_ON_ONCE(!regs))
return 0;
- if (!ftrace_location(regs->ip - 1))
+ ip = regs->ip - 1;
+ if (!ftrace_location(ip) && !is_ftrace_caller(ip))
return 0;
regs->ip += MCOUNT_INSN_SIZE - 1;
@@ -632,8 +659,8 @@
ret = -EPERM;
goto out;
}
- run_sync();
out:
+ run_sync();
return ret;
fail_update:
@@ -665,45 +692,41 @@
#ifdef CONFIG_DYNAMIC_FTRACE
extern void ftrace_graph_call(void);
-static int ftrace_mod_jmp(unsigned long ip,
- int old_offset, int new_offset)
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
{
- unsigned char code[MCOUNT_INSN_SIZE];
+ static union ftrace_code_union calc;
- if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
- return -EFAULT;
+ /* Jmp not a call (ignore the .e8) */
+ calc.e8 = 0xe9;
+ calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
- if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
- return -EINVAL;
+ /*
+ * ftrace external locks synchronize the access to the static variable.
+ */
+ return calc.code;
+}
- *(int *)(&code[1]) = new_offset;
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+ unsigned char *new;
- if (do_ftrace_mod_code(ip, &code))
- return -EPERM;
+ new = ftrace_jmp_replace(ip, (unsigned long)func);
- return 0;
+ return update_ftrace_func(ip, new);
}
int ftrace_enable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
- old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_graph_caller);
}
int ftrace_disable_ftrace_graph_caller(void)
{
unsigned long ip = (unsigned long)(&ftrace_graph_call);
- int old_offset, new_offset;
- old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
- new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-
- return ftrace_mod_jmp(ip, old_offset, new_offset);
+ return ftrace_mod_jmp(ip, &ftrace_stub);
}
#endif /* !CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 73afd11..df63cae 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -566,6 +566,10 @@
/* This is global to keep gas from relaxing the jumps */
ENTRY(early_idt_handler)
cld
+
+ cmpl $2,(%esp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,%ss:early_recursion_flag
je hlt_loop
incl %ss:early_recursion_flag
@@ -616,8 +620,9 @@
pop %edx
pop %ecx
pop %eax
- addl $8,%esp /* drop vector number and error code */
decl %ss:early_recursion_flag
+is_nmi:
+ addl $8,%esp /* drop vector number and error code */
iret
ENDPROC(early_idt_handler)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 321d65e..f2a9a2a 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@
ENTRY(early_idt_handler)
cld
+ cmpl $2,(%rsp) # X86_TRAP_NMI
+ je is_nmi # Ignore NMI
+
cmpl $2,early_recursion_flag(%rip)
jz 1f
incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@
popq %rdx
popq %rcx
popq %rax
- addq $16,%rsp # drop vector number and error code
decl early_recursion_flag(%rip)
+is_nmi:
+ addq $16,%rsp # drop vector number and error code
INTERRUPT_RETURN
ENDPROC(early_idt_handler)
@@ -513,7 +517,7 @@
#include "../../x86/xen/xen-head.S"
.section .bss, "aw", @nobits
- .align L1_CACHE_BYTES
+ .align PAGE_SIZE
ENTRY(idt_table)
.skip IDT_ENTRIES * 16
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index cb33909..b03ff18 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@
void __kernel_fpu_end(void)
{
- if (use_eager_fpu())
- math_state_restore();
- else
+ if (use_eager_fpu()) {
+ /*
+ * For eager fpu, most the time, tsk_used_math() is true.
+ * Restore the user math as we are done with the kernel usage.
+ * At few instances during thread exit, signal handling etc,
+ * tsk_used_math() is false. Those few places will take proper
+ * actions, so we don't need to restore the math here.
+ */
+ if (likely(tsk_used_math(current)))
+ math_state_restore();
+ } else {
stts();
+ }
}
EXPORT_SYMBOL(__kernel_fpu_end);
@@ -116,7 +125,7 @@
if (cpu_has_fxsr) {
memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
- asm volatile("fxsave %0" : : "m" (fx_scratch));
+ asm volatile("fxsave %0" : "+m" (fx_scratch));
mask = fx_scratch.mxcsr_mask;
if (mask == 0)
mask = 0x0000ffbf;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 211bce4..0c6c07c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1017,6 +1017,15 @@
regs->flags &= ~X86_EFLAGS_IF;
trace_hardirqs_off();
regs->ip = (unsigned long)(jp->entry);
+
+ /*
+ * jprobes use jprobe_return() which skips the normal return
+ * path of the function, and this messes up the accounting of the
+ * function graph tracer to get messed up.
+ *
+ * Pause function graph tracing while performing the jprobe function.
+ */
+ pause_graph_tracing();
return 1;
}
@@ -1042,24 +1051,25 @@
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
u8 *addr = (u8 *) (regs->ip - 1);
struct jprobe *jp = container_of(p, struct jprobe, kp);
+ void *saved_sp = kcb->jprobe_saved_sp;
if ((addr > (u8 *) jprobe_return) &&
(addr < (u8 *) jprobe_return_end)) {
- if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+ if (stack_addr(regs) != saved_sp) {
struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
printk(KERN_ERR
"current sp %p does not match saved sp %p\n",
- stack_addr(regs), kcb->jprobe_saved_sp);
+ stack_addr(regs), saved_sp);
printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
show_regs(saved_regs);
printk(KERN_ERR "Current registers\n");
show_regs(regs);
BUG();
}
+ /* It's OK to start function graph tracing again */
+ unpause_graph_tracing();
*regs = kcb->jprobe_saved_regs;
- memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
- kcb->jprobes_stack,
- MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+ memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
preempt_enable_no_resched();
return 1;
}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index cd6d9a5..c4ff2a9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -279,7 +279,14 @@
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
- pv_info.paravirt_enabled = 1;
+
+ /*
+ * KVM isn't paravirt in the sense of paravirt_enabled. A KVM
+ * guest kernel works like a bare metal kernel with additional
+ * features, and paravirt_enabled is about features that are
+ * missing.
+ */
+ pv_info.paravirt_enabled = 0;
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
pv_cpu_ops.io_delay = kvm_io_delay;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 3dd37eb..41514f5 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -265,7 +265,6 @@
#endif
kvm_get_preset_lpj();
clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
- pv_info.paravirt_enabled = 1;
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc9873..c37886d 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,11 @@
}
}
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
fill_ldt(&ldt, &ldt_info);
if (oldmode)
ldt.avl = 0;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index efdec7c..b516dfb 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -430,7 +430,7 @@
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
if (request_firmware(&fw, (const char *)fw_name, device)) {
- pr_err("failed to load file %s\n", fw_name);
+ pr_debug("failed to load file %s\n", fw_name);
goto out;
}
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34..a1da673 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@
DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, iret);
PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 872079a..f7d0672 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,8 +100,10 @@
flag |= __GFP_ZERO;
again:
page = NULL;
- if (!(flag & GFP_ATOMIC))
+ /* CMA can be used only in the context which permits sleeping */
+ if (flag & __GFP_WAIT)
page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ /* fallback */
if (!page)
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 81a5f5e..59b9037 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -391,9 +391,9 @@
* The switch back from broadcast mode needs to be
* called with interrupts disabled.
*/
- local_irq_disable();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
- local_irq_enable();
+ local_irq_disable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ local_irq_enable();
} else
default_idle();
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7305f7d..0339f5c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -147,7 +147,7 @@
childregs->bp = arg;
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
- childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+ childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 355ae06..7099ab1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -176,7 +176,7 @@
childregs->bp = arg;
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
- childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+ childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
return 0;
}
*childregs = *current_pt_regs();
@@ -279,24 +279,9 @@
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
- /*
- * Reload esp0, LDT and the page table pointer:
- */
+ /* Reload esp0 and ss1. */
load_sp0(tss, next);
- /*
- * Switch DS and ES.
- * This won't pick up thread selector changes, but I guess that is ok.
- */
- savesegment(es, prev->es);
- if (unlikely(next->es | prev->es))
- loadsegment(es, next->es);
-
- savesegment(ds, prev->ds);
- if (unlikely(next->ds | prev->ds))
- loadsegment(ds, next->ds);
-
-
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
*
@@ -305,41 +290,101 @@
savesegment(fs, fsindex);
savesegment(gs, gsindex);
+ /*
+ * Load TLS before restoring any segments so that segment loads
+ * reference the correct GDT entries.
+ */
load_TLS(next, cpu);
/*
- * Leave lazy mode, flushing any hypercalls made here.
- * This must be done before restoring TLS segments so
- * the GDT and LDT are properly updated, and must be
- * done before math_state_restore, so the TS bit is up
- * to date.
+ * Leave lazy mode, flushing any hypercalls made here. This
+ * must be done after loading TLS entries in the GDT but before
+ * loading segments that might reference them, and and it must
+ * be done before math_state_restore, so the TS bit is up to
+ * date.
*/
arch_end_context_switch(next_p);
+ /* Switch DS and ES.
+ *
+ * Reading them only returns the selectors, but writing them (if
+ * nonzero) loads the full descriptor from the GDT or LDT. The
+ * LDT for next is loaded in switch_mm, and the GDT is loaded
+ * above.
+ *
+ * We therefore need to write new values to the segment
+ * registers on every context switch unless both the new and old
+ * values are zero.
+ *
+ * Note that we don't need to do anything for CS and SS, as
+ * those are saved and restored as part of pt_regs.
+ */
+ savesegment(es, prev->es);
+ if (unlikely(next->es | prev->es))
+ loadsegment(es, next->es);
+
+ savesegment(ds, prev->ds);
+ if (unlikely(next->ds | prev->ds))
+ loadsegment(ds, next->ds);
+
/*
* Switch FS and GS.
*
- * Segment register != 0 always requires a reload. Also
- * reload when it has changed. When prev process used 64bit
- * base always reload to avoid an information leak.
+ * These are even more complicated than FS and GS: they have
+ * 64-bit bases are that controlled by arch_prctl. Those bases
+ * only differ from the values in the GDT or LDT if the selector
+ * is 0.
+ *
+ * Loading the segment register resets the hidden base part of
+ * the register to 0 or the value from the GDT / LDT. If the
+ * next base address zero, writing 0 to the segment register is
+ * much faster than using wrmsr to explicitly zero the base.
+ *
+ * The thread_struct.fs and thread_struct.gs values are 0
+ * if the fs and gs bases respectively are not overridden
+ * from the values implied by fsindex and gsindex. They
+ * are nonzero, and store the nonzero base addresses, if
+ * the bases are overridden.
+ *
+ * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+ * be impossible.
+ *
+ * Therefore we need to reload the segment registers if either
+ * the old or new selector is nonzero, and we need to override
+ * the base address if next thread expects it to be overridden.
+ *
+ * This code is unnecessarily slow in the case where the old and
+ * new indexes are zero and the new base is nonzero -- it will
+ * unnecessarily write 0 to the selector before writing the new
+ * base address.
+ *
+ * Note: This all depends on arch_prctl being the only way that
+ * user code can override the segment base. Once wrfsbase and
+ * wrgsbase are enabled, most of this code will need to change.
*/
if (unlikely(fsindex | next->fsindex | prev->fs)) {
loadsegment(fs, next->fsindex);
+
/*
- * Check if the user used a selector != 0; if yes
- * clear 64bit base, since overloaded base is always
- * mapped to the Null selector
+ * If user code wrote a nonzero value to FS, then it also
+ * cleared the overridden base address.
+ *
+ * XXX: if user code wrote 0 to FS and cleared the base
+ * address itself, we won't notice and we'll incorrectly
+ * restore the prior base address next time we reschdule
+ * the process.
*/
if (fsindex)
prev->fs = 0;
}
- /* when next process has a 64bit base use it */
if (next->fs)
wrmsrl(MSR_FS_BASE, next->fs);
prev->fsindex = fsindex;
if (unlikely(gsindex | next->gsindex | prev->gs)) {
load_gs_index(next->gsindex);
+
+ /* This works (and fails) the same way as fsindex above. */
if (gsindex)
prev->gs = 0;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 29a8120..baa61e7 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1475,15 +1475,6 @@
force_sig_info(SIGTRAP, &info, tsk);
}
-
-#ifdef CONFIG_X86_32
-# define IS_IA32 1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32 is_compat_task()
-#else
-# define IS_IA32 0
-#endif
-
/*
* We must return the syscall number to actually look up in the table.
* This can be -1L to skip running any syscall at all.
@@ -1521,7 +1512,7 @@
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->orig_ax);
- if (IS_IA32)
+ if (is_ia32_task())
audit_syscall_entry(AUDIT_ARCH_I386,
regs->orig_ax,
regs->bx, regs->cx,
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 04ee1e2..52dbf1e 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@
return;
pci_read_config_dword(nb_ht, 0x60, &val);
- node = val & 7;
+ node = pcibus_to_node(dev->bus) | (val & 7);
/*
* Some hardware may return an invalid node ID,
* so check it first:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 76fa1e9..3876c04 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -36,7 +36,7 @@
EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
-static int reboot_mode;
+static enum reboot_mode reboot_mode;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
@@ -88,11 +88,11 @@
switch (*str) {
case 'w':
- reboot_mode = 0x1234;
+ reboot_mode = REBOOT_WARM;
break;
case 'c':
- reboot_mode = 0;
+ reboot_mode = REBOOT_COLD;
break;
#ifdef CONFIG_SMP
@@ -447,6 +447,22 @@
DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
},
},
+ { /* Handle problems with rebooting on the Dell PowerEdge C6100. */
+ .callback = set_pci_reboot,
+ .ident = "Dell PowerEdge C6100",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+ },
+ },
+ { /* Some C6100 machines were shipped with vendor being 'Dell'. */
+ .callback = set_pci_reboot,
+ .ident = "Dell PowerEdge C6100",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
+ },
+ },
{ }
};
@@ -536,6 +552,7 @@
int i;
int attempt = 0;
int orig_reboot_type = reboot_type;
+ unsigned short mode;
if (reboot_emergency)
emergency_vmx_disable_all();
@@ -543,7 +560,8 @@
tboot_shutdown(TB_SHUTDOWN_REBOOT);
/* Tell the BIOS if we want cold or warm reboot */
- *((unsigned short *)__va(0x472)) = reboot_mode;
+ mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0;
+ *((unsigned short *)__va(0x472)) = mode;
for (;;) {
/* Could also try the reset bit in the Hammer NB */
@@ -585,7 +603,7 @@
case BOOT_EFI:
if (efi_enabled(EFI_RUNTIME_SERVICES))
- efi.reset_system(reboot_mode ?
+ efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819..80eab01 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@
void arch_remove_reservations(struct resource *avail)
{
- /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+ /*
+ * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+ * the low 1MB unconditionally, as this area is needed for some ISA
+ * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+ */
if (avail->flags & IORESOURCE_MEM) {
- if (avail->start < BIOS_END)
- avail->start = BIOS_END;
resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
remove_e820_regions(avail);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 56f7fcf..a3627ad 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -426,25 +426,23 @@
static void __init parse_setup_data(void)
{
struct setup_data *data;
- u64 pa_data;
+ u64 pa_data, pa_next;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
- u32 data_len, map_len;
+ u32 data_len, map_len, data_type;
map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
(u64)sizeof(struct setup_data));
data = early_memremap(pa_data, map_len);
data_len = data->len + sizeof(struct setup_data);
- if (data_len > map_len) {
- early_iounmap(data, map_len);
- data = early_memremap(pa_data, data_len);
- map_len = data_len;
- }
+ data_type = data->type;
+ pa_next = data->next;
+ early_iounmap(data, map_len);
- switch (data->type) {
+ switch (data_type) {
case SETUP_E820_EXT:
- parse_e820_ext(data);
+ parse_e820_ext(pa_data, data_len);
break;
case SETUP_DTB:
add_dtb(pa_data);
@@ -452,8 +450,7 @@
default:
break;
}
- pa_data = data->next;
- early_iounmap(data, map_len);
+ pa_data = pa_next;
}
}
@@ -911,11 +908,11 @@
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL32", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
"EL64", 4)) {
- set_bit(EFI_BOOT, &x86_efi_facility);
- set_bit(EFI_64BIT, &x86_efi_facility);
+ set_bit(EFI_BOOT, &efi.flags);
+ set_bit(EFI_64BIT, &efi.flags);
}
if (efi_enabled(EFI_BOOT))
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 6956299..66deef4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -364,7 +364,7 @@
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ save_altstack_ex(&frame->uc.uc_stack, regs->sp);
/* Set up to return from userspace. */
restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -429,7 +429,7 @@
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ save_altstack_ex(&frame->uc.uc_stack, regs->sp);
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
@@ -496,7 +496,7 @@
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+ compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
put_user_ex(0, &frame->uc.uc__pad0);
if (ksig->ka.sa.sa_flags & SA_RESTORER) {
@@ -677,6 +677,11 @@
* handler too.
*/
regs->flags &= ~X86_EFLAGS_TF;
+ /*
+ * Ensure the signal handler starts with the new fpu state.
+ */
+ if (used_math())
+ drop_init_fpu(current);
}
signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index bfd348e..87084ab 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -265,6 +265,13 @@
check_tsc_sync_target();
/*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap();
+#endif
+
+ /*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
@@ -1277,6 +1284,9 @@
for_each_cpu(sibling, cpu_sibling_mask(cpu))
cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+ for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+ cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+ cpumask_clear(cpu_llc_shared_mask(cpu));
cpumask_clear(cpu_sibling_mask(cpu));
cpumask_clear(cpu_core_mask(cpu));
c->phys_proc_id = 0;
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5a..30277e2 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@
*begin = new_begin;
}
} else {
- *begin = TASK_UNMAPPED_BASE;
+ *begin = current->mm->mmap_legacy_base;
*end = TASK_SIZE;
}
}
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09..7fc5e84 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,58 @@
return -ESRCH;
}
+static bool tls_desc_okay(const struct user_desc *info)
+{
+ /*
+ * For historical reasons (i.e. no one ever documented how any
+ * of the segmentation APIs work), user programs can and do
+ * assume that a struct user_desc that's all zeros except for
+ * entry_number means "no segment at all". This never actually
+ * worked. In fact, up to Linux 3.19, a struct user_desc like
+ * this would create a 16-bit read-write segment with base and
+ * limit both equal to zero.
+ *
+ * That was close enough to "no segment at all" until we
+ * hardened this function to disallow 16-bit TLS segments. Fix
+ * it up by interpreting these zeroed segments the way that they
+ * were almost certainly intended to be interpreted.
+ *
+ * The correct way to ask for "no segment at all" is to specify
+ * a user_desc that satisfies LDT_empty. To keep everything
+ * working, we accept both.
+ *
+ * Note that there's a similar kludge in modify_ldt -- look at
+ * the distinction between modes 1 and 0x11.
+ */
+ if (LDT_empty(info) || LDT_zero(info))
+ return true;
+
+ /*
+ * espfix is required for 16-bit data segments, but espfix
+ * only works for LDT segments.
+ */
+ if (!info->seg_32bit)
+ return false;
+
+ /* Only allow data segments in the TLS array. */
+ if (info->contents > 1)
+ return false;
+
+ /*
+ * Non-present segments with DPL 3 present an interesting attack
+ * surface. The kernel should handle such segments correctly,
+ * but TLS is very difficult to protect in a sandbox, so prevent
+ * such segments from being created.
+ *
+ * If userspace needs to remove a TLS entry, it can still delete
+ * it outright.
+ */
+ if (info->seg_not_present)
+ return false;
+
+ return true;
+}
+
static void set_tls_desc(struct task_struct *p, int idx,
const struct user_desc *info, int n)
{
@@ -40,7 +92,7 @@
cpu = get_cpu();
while (n-- > 0) {
- if (LDT_empty(info))
+ if (LDT_empty(info) || LDT_zero(info))
desc->a = desc->b = 0;
else
fill_ldt(desc, info);
@@ -66,6 +118,9 @@
if (copy_from_user(&info, u_info, sizeof(info)))
return -EFAULT;
+ if (!tls_desc_okay(&info))
+ return -EINVAL;
+
if (idx == -1)
idx = info.entry_number;
@@ -192,6 +247,7 @@
{
struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
const struct user_desc *info;
+ int i;
if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +261,10 @@
else
info = infobuf;
+ for (i = 0; i < count / sizeof(struct user_desc); i++)
+ if (!tls_desc_okay(info + i))
+ return -EINVAL;
+
set_tls_desc(target,
GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 772e2a8..0010ed7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -220,33 +220,41 @@
coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-#ifdef CONFIG_X86_32
DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-#endif
DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
BUS_ADRALN, 0)
#ifdef CONFIG_X86_64
/* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
- enum ctx_state prev_state;
-
- prev_state = exception_enter();
- if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
- preempt_conditional_sti(regs);
- do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
- }
- exception_exit(prev_state);
-}
-
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
+#ifdef CONFIG_X86_ESPFIX64
+ extern unsigned char native_irq_return_iret[];
+
+ /*
+ * If IRET takes a non-IST fault on the espfix64 stack, then we
+ * end up promoting it to a doublefault. In that case, modify
+ * the stack to make it look like we just entered the #GP
+ * handler from user space, similar to bad_iret.
+ */
+ if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ regs->cs == __KERNEL_CS &&
+ regs->ip == (unsigned long)native_irq_return_iret)
+ {
+ struct pt_regs *normal_regs = task_pt_regs(current);
+
+ /* Fake a #GP(0) from userspace. */
+ memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+ normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
+ regs->ip = (unsigned long)general_protection;
+ regs->sp = (unsigned long)&normal_regs->orig_ax;
+ return;
+ }
+#endif
+
exception_enter();
/* Return not checked because double check cannot be ignored */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -354,7 +362,7 @@
* for scheduling or signal handling. The actual stack switch is done in
* entry.S
*/
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
{
struct pt_regs *regs = eregs;
/* Did already sync */
@@ -373,6 +381,35 @@
*regs = *eregs;
return regs;
}
+
+struct bad_iret_stack {
+ void *error_entry_ret;
+ struct pt_regs regs;
+};
+
+asmlinkage __visible notrace __kprobes
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+ /*
+ * This is called from entry_64.S early in handling a fault
+ * caused by a bad iret to user mode. To handle the fault
+ * correctly, we want move our stack frame to task_pt_regs
+ * and we want to pretend that the exception came from the
+ * iret target.
+ */
+ struct bad_iret_stack *new_stack =
+ container_of(task_pt_regs(current),
+ struct bad_iret_stack, regs);
+
+ /* Copy the IRET target to the new stack. */
+ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+ /* Copy the remainder of the stack from the current stack. */
+ memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+ BUG_ON(!user_mode_vm(&new_stack->regs));
+ return new_stack;
+}
#endif
/*
@@ -745,7 +782,7 @@
set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
set_intr_gate(X86_TRAP_TS, &invalid_TSS);
set_intr_gate(X86_TRAP_NP, &segment_not_present);
- set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+ set_intr_gate(X86_TRAP_SS, stack_segment);
set_intr_gate(X86_TRAP_GP, &general_protection);
set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
set_intr_gate(X86_TRAP_MF, &coprocessor_error);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 098b3cf..27e3a14 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -380,7 +380,7 @@
goto success;
}
}
- pr_err("Fast TSC calibration failed\n");
+ pr_info("Fast TSC calibration failed\n");
return 0;
success:
@@ -968,14 +968,17 @@
x86_init.timers.tsc_pre_init();
- if (!cpu_has_tsc)
+ if (!cpu_has_tsc) {
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
+ }
tsc_khz = x86_platform.calibrate_tsc();
cpu_khz = tsc_khz;
if (!tsc_khz) {
mark_tsc_unstable("could not calculate TSC khz");
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
}
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 9a907a6..c52c07e 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -125,10 +125,10 @@
if (!show_unhandled_signals)
return;
- pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
- level, current->comm, task_pid_nr(current),
- message, regs->ip, regs->cs,
- regs->sp, regs->ax, regs->si, regs->di);
+ printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+ level, current->comm, task_pid_nr(current),
+ message, regs->ip, regs->cs,
+ regs->sp, regs->ax, regs->si, regs->di);
}
static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index ada87a3..92f37e7 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -268,8 +268,6 @@
if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
return -1;
- drop_init_fpu(tsk); /* trigger finit */
-
return 0;
}
@@ -378,7 +376,7 @@
* thread's fpu state, reconstruct fxstate from the fsave
* header. Sanitize the copied state etc.
*/
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
@@ -392,16 +390,20 @@
*/
drop_fpu(tsk);
- if (__copy_from_user(xsave, buf_fx, state_size) ||
+ if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
__copy_from_user(&env, buf, sizeof(env))) {
+ fpu_finit(fpu);
err = -1;
} else {
sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
- set_used_math();
}
- if (use_eager_fpu())
+ set_used_math();
+ if (use_eager_fpu()) {
+ preempt_disable();
math_state_restore();
+ preempt_enable();
+ }
return err;
} else {
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e5..bdccfb6 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -27,6 +27,7 @@
select MMU_NOTIFIER
select ANON_INODES
select HAVE_KVM_IRQCHIP
+ select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_EVENTFD
select KVM_APIC_ARCHITECTURE
@@ -38,6 +39,7 @@
select PERF_EVENTS
select HAVE_KVM_MSI
select HAVE_KVM_CPU_RELAX_INTERCEPT
+ select KVM_VFIO
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index d609e1d..25d22b2 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -5,12 +5,13 @@
CFLAGS_svm.o := -I.
CFLAGS_vmx.o := -I.
-kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
- coalesced_mmio.o irq_comm.o eventfd.o \
- irqchip.o)
-kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \
- assigned-dev.o iommu.o)
-kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o)
+KVM := ../../../virt/kvm
+
+kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \
+ $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
+ $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
+kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o
+kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
i8254.o cpuid.o pmu.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5..89d2882 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -187,8 +187,14 @@
#define F(x) bit(X86_FEATURE_##x)
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+ u32 func, u32 index, int *nent, int maxnent)
+{
+ return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+ u32 index, int *nent, int maxnent)
{
int r;
unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -480,6 +486,15 @@
return r;
}
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+ u32 idx, int *nent, int maxnent, unsigned int type)
+{
+ if (type == KVM_GET_EMULATED_CPUID)
+ return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+ return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
#undef F
struct kvm_cpuid_param {
@@ -494,8 +509,34 @@
return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
}
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+ __u32 num_entries, unsigned int ioctl_type)
+{
+ int i;
+
+ if (ioctl_type != KVM_GET_EMULATED_CPUID)
+ return false;
+
+ /*
+ * We want to make sure that ->padding is being passed clean from
+ * userspace in case we want to use it for something in the future.
+ *
+ * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+ * have to give ourselves satisfied only with the emulated side. /me
+ * sheds a tear.
+ */
+ for (i = 0; i < num_entries; i++) {
+ if (entries[i].padding[0] ||
+ entries[i].padding[1] ||
+ entries[i].padding[2])
+ return true;
+ }
+ return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type)
{
struct kvm_cpuid_entry2 *cpuid_entries;
int limit, nent = 0, r = -E2BIG, i;
@@ -512,6 +553,10 @@
goto out;
if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+ if (sanity_check_entries(entries, cpuid->nent, type))
+ return -EINVAL;
+
r = -ENOMEM;
cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
if (!cpuid_entries)
@@ -525,7 +570,7 @@
continue;
r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
@@ -536,7 +581,7 @@
limit = cpuid_entries[nent - 1].eax;
for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
- &nent, cpuid->nent);
+ &nent, cpuid->nent, type);
if (r)
goto out_free;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd079..f1e4895 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
void kvm_update_cpuid(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 __user *entries,
+ unsigned int type);
int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
struct kvm_cpuid *cpuid,
struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5953dce..ddad189 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -663,11 +663,6 @@
masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
}
-static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
-{
- register_address_increment(ctxt, &ctxt->_eip, rel);
-}
-
static u32 desc_limit_scaled(struct desc_struct *desc)
{
u32 limit = get_desc_limit(desc);
@@ -741,6 +736,38 @@
return emulate_exception(ctxt, NM_VECTOR, 0, false);
}
+static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+ int cs_l)
+{
+ switch (ctxt->op_bytes) {
+ case 2:
+ ctxt->_eip = (u16)dst;
+ break;
+ case 4:
+ ctxt->_eip = (u32)dst;
+ break;
+ case 8:
+ if ((cs_l && is_noncanonical_address(dst)) ||
+ (!cs_l && (dst & ~(u32)-1)))
+ return emulate_gp(ctxt, 0);
+ ctxt->_eip = dst;
+ break;
+ default:
+ WARN(1, "unsupported eip assignment size\n");
+ }
+ return X86EMUL_CONTINUE;
+}
+
+static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+{
+ return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64);
+}
+
+static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+{
+ return assign_eip_near(ctxt, ctxt->_eip + rel);
+}
+
static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
{
u16 selector;
@@ -2161,13 +2188,15 @@
case 2: /* call near abs */ {
long int old_eip;
old_eip = ctxt->_eip;
- ctxt->_eip = ctxt->src.val;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
+ if (rc != X86EMUL_CONTINUE)
+ break;
ctxt->src.val = old_eip;
rc = em_push(ctxt);
break;
}
case 4: /* jmp abs */
- ctxt->_eip = ctxt->src.val;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
break;
case 5: /* jmp far */
rc = em_jmp_far(ctxt);
@@ -2199,16 +2228,21 @@
static int em_ret(struct x86_emulate_ctxt *ctxt)
{
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- return em_pop(ctxt);
+ int rc;
+ unsigned long eip;
+
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ return assign_eip_near(ctxt, eip);
}
static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long cs;
+ int cpl = ctxt->ops->cpl(ctxt);
rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
@@ -2218,6 +2252,9 @@
rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
+ /* Outer-privilege level return is not implemented */
+ if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+ return X86EMUL_UNHANDLEABLE;
rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
return rc;
}
@@ -2413,7 +2450,7 @@
* Not recognized on AMD in compat mode (but is recognized in legacy
* mode).
*/
- if ((ctxt->mode == X86EMUL_MODE_PROT32) && (efer & EFER_LMA)
+ if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
&& !vendor_intel(ctxt))
return emulate_ud(ctxt);
@@ -2426,25 +2463,13 @@
setup_syscalls_segments(ctxt, &cs, &ss);
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
- switch (ctxt->mode) {
- case X86EMUL_MODE_PROT32:
- if ((msr_data & 0xfffc) == 0x0)
- return emulate_gp(ctxt, 0);
- break;
- case X86EMUL_MODE_PROT64:
- if (msr_data == 0x0)
- return emulate_gp(ctxt, 0);
- break;
- default:
- break;
- }
+ if ((msr_data & 0xfffc) == 0x0)
+ return emulate_gp(ctxt, 0);
ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
- cs_sel = (u16)msr_data;
- cs_sel &= ~SELECTOR_RPL_MASK;
+ cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK;
ss_sel = cs_sel + 8;
- ss_sel &= ~SELECTOR_RPL_MASK;
- if (ctxt->mode == X86EMUL_MODE_PROT64 || (efer & EFER_LMA)) {
+ if (efer & EFER_LMA) {
cs.d = 0;
cs.l = 1;
}
@@ -2453,10 +2478,11 @@
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
- ctxt->_eip = msr_data;
+ ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
- *reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
+ *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
+ (u32)msr_data;
return X86EMUL_CONTINUE;
}
@@ -2465,7 +2491,7 @@
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
- u64 msr_data;
+ u64 msr_data, rcx, rdx;
int usermode;
u16 cs_sel = 0, ss_sel = 0;
@@ -2481,6 +2507,9 @@
else
usermode = X86EMUL_MODE_PROT32;
+ rcx = reg_read(ctxt, VCPU_REGS_RCX);
+ rdx = reg_read(ctxt, VCPU_REGS_RDX);
+
cs.dpl = 3;
ss.dpl = 3;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
@@ -2498,6 +2527,9 @@
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
+ if (is_noncanonical_address(rcx) ||
+ is_noncanonical_address(rdx))
+ return emulate_gp(ctxt, 0);
break;
}
cs_sel |= SELECTOR_RPL_MASK;
@@ -2506,8 +2538,8 @@
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
- ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
- *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
+ ctxt->_eip = rdx;
+ *reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
}
@@ -3046,10 +3078,13 @@
static int em_call(struct x86_emulate_ctxt *ctxt)
{
+ int rc;
long rel = ctxt->src.val;
ctxt->src.val = (unsigned long)ctxt->_eip;
- jmp_rel(ctxt, rel);
+ rc = jmp_rel(ctxt, rel);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
return em_push(ctxt);
}
@@ -3081,11 +3116,12 @@
static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
{
int rc;
+ unsigned long eip;
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rc = assign_eip_near(ctxt, eip);
if (rc != X86EMUL_CONTINUE)
return rc;
rsp_increment(ctxt, ctxt->src.val);
@@ -3375,20 +3411,24 @@
static int em_loop(struct x86_emulate_ctxt *ctxt)
{
+ int rc = X86EMUL_CONTINUE;
+
register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
(ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
- return X86EMUL_CONTINUE;
+ return rc;
}
static int em_jcxz(struct x86_emulate_ctxt *ctxt)
{
- if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
- jmp_rel(ctxt, ctxt->src.val);
+ int rc = X86EMUL_CONTINUE;
- return X86EMUL_CONTINUE;
+ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
+ rc = jmp_rel(ctxt, ctxt->src.val);
+
+ return rc;
}
static int em_in(struct x86_emulate_ctxt *ctxt)
@@ -4207,7 +4247,10 @@
case OpMem8:
ctxt->memop.bytes = 1;
if (ctxt->memop.type == OP_REG) {
- ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1);
+ int highbyte_regs = ctxt->rex_prefix == 0;
+
+ ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+ highbyte_regs);
fetch_register_operand(&ctxt->memop);
}
goto mem_common;
@@ -4678,7 +4721,8 @@
if (rc != X86EMUL_CONTINUE)
goto done;
}
- ctxt->dst.orig_val = ctxt->dst.val;
+ /* Copy full 64-bit value for CMPXCHG8B. */
+ ctxt->dst.orig_val64 = ctxt->dst.val64;
special_insn:
@@ -4714,7 +4758,7 @@
break;
case 0x70 ... 0x7f: /* jcc (short) */
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x8d: /* lea r16/r32, m */
ctxt->dst.val = ctxt->src.addr.mem.ea;
@@ -4743,7 +4787,7 @@
break;
case 0xe9: /* jmp rel */
case 0xeb: /* jmp rel short */
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
ctxt->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf4: /* hlt */
@@ -4855,7 +4899,7 @@
break;
case 0x80 ... 0x8f: /* jnz rel, etc*/
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x90 ... 0x9f: /* setcc r/m8 */
ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 412a5aa..298781d 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -37,6 +37,7 @@
#include "irq.h"
#include "i8254.h"
+#include "x86.h"
#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -261,8 +262,10 @@
return;
timer = &pit->pit_state.timer;
+ mutex_lock(&pit->pit_state.lock);
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ mutex_unlock(&pit->pit_state.lock);
}
static void destroy_pit_timer(struct kvm_pit *pit)
@@ -349,6 +352,23 @@
atomic_set(&ps->pending, 0);
ps->irq_ack = 1;
+ /*
+ * Do not allow the guest to program periodic timers with small
+ * interval, since the hrtimers are not throttled by the host
+ * scheduler.
+ */
+ if (ps->is_periodic) {
+ s64 min_period = min_timer_period_us * 1000LL;
+
+ if (ps->period < min_period) {
+ pr_info_ratelimited(
+ "kvm: requested %lld ns "
+ "i8254 timer period limited to %lld ns\n",
+ ps->period, min_period);
+ ps->period = min_period;
+ }
+ }
+
hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
HRTIMER_MODE_ABS);
}
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 484bc87..3ec38cb 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@
vector = kvm_cpu_get_extint(v);
- if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+ if (vector != -1)
return vector; /* PIC */
return kvm_get_apic_interrupt(v); /* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0eee2c8..681e4e2 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -71,9 +71,6 @@
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
-static unsigned int min_timer_period_us = 500;
-module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
-
static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
@@ -153,6 +150,8 @@
return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}
+#define KVM_X2APIC_CID_BITS 0
+
static void recalculate_apic_map(struct kvm *kvm)
{
struct kvm_apic_map *new, *old = NULL;
@@ -190,7 +189,8 @@
if (apic_x2apic_mode(apic)) {
new->ldr_bits = 32;
new->cid_shift = 16;
- new->cid_mask = new->lid_mask = 0xffff;
+ new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+ new->lid_mask = 0xffff;
} else if (kvm_apic_sw_enabled(apic) &&
!new->cid_mask /* flat mode */ &&
kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
@@ -362,31 +362,90 @@
static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
{
- apic->irr_pending = false;
+ struct kvm_vcpu *vcpu;
+
+ vcpu = apic->vcpu;
+
apic_clear_vector(vec, apic->regs + APIC_IRR);
- if (apic_search_irr(apic) != -1)
- apic->irr_pending = true;
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ /* try to update RVI */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ else {
+ vec = apic_search_irr(apic);
+ apic->irr_pending = (vec != -1);
+ }
}
static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
{
- if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
- ++apic->isr_count;
- BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+ struct kvm_vcpu *vcpu;
+
+ if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+ return;
+
+ vcpu = apic->vcpu;
+
/*
- * ISR (in service register) bit is set when injecting an interrupt.
- * The highest vector is injected. Thus the latest bit set matches
- * the highest bit in ISR.
+ * With APIC virtualization enabled, all caching is disabled
+ * because the processor can modify ISR under the hood. Instead
+ * just set SVI.
*/
- apic->highest_isr_cache = vec;
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+ else {
+ ++apic->isr_count;
+ BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+ /*
+ * ISR (in service register) bit is set when injecting an interrupt.
+ * The highest vector is injected. Thus the latest bit set matches
+ * the highest bit in ISR.
+ */
+ apic->highest_isr_cache = vec;
+ }
+}
+
+static inline int apic_find_highest_isr(struct kvm_lapic *apic)
+{
+ int result;
+
+ /*
+ * Note that isr_count is always 1, and highest_isr_cache
+ * is always -1, with APIC virtualization enabled.
+ */
+ if (!apic->isr_count)
+ return -1;
+ if (likely(apic->highest_isr_cache != -1))
+ return apic->highest_isr_cache;
+
+ result = find_highest_vector(apic->regs + APIC_ISR);
+ ASSERT(result == -1 || result >= 16);
+
+ return result;
}
static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
{
- if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ struct kvm_vcpu *vcpu;
+ if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ return;
+
+ vcpu = apic->vcpu;
+
+ /*
+ * We do get here for APIC virtualization enabled if the guest
+ * uses the Hyper-V APIC enlightenment. In this case we may need
+ * to trigger a new interrupt delivery by writing the SVI field;
+ * on the other hand isr_count and highest_isr_cache are unused
+ * and must be left alone.
+ */
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ kvm_x86_ops->hwapic_isr_update(vcpu->kvm,
+ apic_find_highest_isr(apic));
+ else {
--apic->isr_count;
- BUG_ON(apic->isr_count < 0);
- apic->highest_isr_cache = -1;
+ BUG_ON(apic->isr_count < 0);
+ apic->highest_isr_cache = -1;
+ }
}
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
@@ -466,22 +525,6 @@
__clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention);
}
-static inline int apic_find_highest_isr(struct kvm_lapic *apic)
-{
- int result;
-
- /* Note that isr_count is always 1 with vid enabled */
- if (!apic->isr_count)
- return -1;
- if (likely(apic->highest_isr_cache != -1))
- return apic->highest_isr_cache;
-
- result = find_highest_vector(apic->regs + APIC_ISR);
- ASSERT(result == -1 || result >= 16);
-
- return result;
-}
-
void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr)
{
struct kvm_lapic *apic = vcpu->arch.apic;
@@ -855,7 +898,8 @@
ASSERT(apic != NULL);
/* if initial count is 0, current count should also be 0 */
- if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
+ if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+ apic->lapic_timer.period == 0)
return 0;
remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -1360,8 +1404,12 @@
return;
}
+ if (!kvm_vcpu_is_bsp(apic->vcpu))
+ value &= ~MSR_IA32_APICBASE_BSP;
+ vcpu->arch.apic_base = value;
+
/* update jump label if enable bit changes */
- if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+ if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
if (value & MSR_IA32_APICBASE_ENABLE)
static_key_slow_dec_deferred(&apic_hw_disabled);
else
@@ -1369,10 +1417,6 @@
recalculate_apic_map(vcpu->kvm);
}
- if (!kvm_vcpu_is_bsp(apic->vcpu))
- value &= ~MSR_IA32_APICBASE_BSP;
-
- vcpu->arch.apic_base = value;
if ((old_value ^ value) & X2APIC_ENABLE) {
if (value & X2APIC_ENABLE) {
u32 id = kvm_apic_id(apic);
@@ -1621,6 +1665,13 @@
if (vector == -1)
return -1;
+ /*
+ * We get here even with APIC virtualization enabled, if doing
+ * nested virtualization and L1 runs with the "acknowledge interrupt
+ * on exit" mode. Then we cannot inject the interrupt via RVI,
+ * because the process would deliver it through the IDT.
+ */
+
apic_set_isr(vector, apic);
apic_update_ppr(apic);
apic_clear_irr(vector, apic);
@@ -1705,7 +1756,6 @@
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
{
u32 data;
- void *vapic;
if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
@@ -1713,9 +1763,8 @@
if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
- vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
- data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
- kunmap_atomic(vapic);
+ kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+ sizeof(u32));
apic_set_tpr(vcpu->arch.apic, data & 0xff);
}
@@ -1751,7 +1800,6 @@
u32 data, tpr;
int max_irr, max_isr;
struct kvm_lapic *apic = vcpu->arch.apic;
- void *vapic;
apic_sync_pv_eoi_to_guest(vcpu, apic);
@@ -1767,18 +1815,24 @@
max_isr = 0;
data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
- vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
- *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
- kunmap_atomic(vapic);
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+ sizeof(u32));
}
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
{
- vcpu->arch.apic->vapic_addr = vapic_addr;
- if (vapic_addr)
+ if (vapic_addr) {
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+ &vcpu->arch.apic->vapic_cache,
+ vapic_addr, sizeof(u32)))
+ return -EINVAL;
__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
- else
+ } else {
__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+ }
+
+ vcpu->arch.apic->vapic_addr = vapic_addr;
+ return 0;
}
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c730ac9..c8b0d0d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -34,7 +34,7 @@
*/
void *regs;
gpa_t vapic_addr;
- struct page *vapic_page;
+ struct gfn_to_hva_cache vapic_cache;
unsigned long pending_events;
unsigned int sipi_vector;
};
@@ -76,7 +76,7 @@
void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 004cc87..0cc34f5 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2585,6 +2585,9 @@
int emulate = 0;
gfn_t pseudo_gfn;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return 0;
+
for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
if (iterator.level == level) {
mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
@@ -2748,6 +2751,9 @@
bool ret = false;
u64 spte = 0ull;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return false;
+
if (!page_fault_can_be_fast(vcpu, error_code))
return false;
@@ -3066,7 +3072,7 @@
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- vcpu_clear_mmio_info(vcpu, ~0ul);
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3139,6 +3145,9 @@
struct kvm_shadow_walk_iterator iterator;
u64 spte = 0ull;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return spte;
+
walk_shadow_page_lockless_begin(vcpu);
for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
if (!is_shadow_present_pte(spte))
@@ -3232,7 +3241,7 @@
arch.direct_map = vcpu->arch.mmu.direct_map;
arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
- return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+ return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
}
static bool can_do_async_pf(struct kvm_vcpu *vcpu)
@@ -4220,7 +4229,7 @@
if (nr_to_scan == 0)
goto out;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
int idx;
@@ -4256,7 +4265,7 @@
break;
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
out:
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
@@ -4329,6 +4338,9 @@
u64 spte;
int nr_sptes = 0;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ return nr_sptes;
+
walk_shadow_page_lockless_begin(vcpu);
for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
sptes[iterator.level-1] = spte;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index da20860..a6a6370 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -69,6 +69,7 @@
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -130,6 +131,22 @@
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -204,7 +221,8 @@
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
@@ -423,6 +441,9 @@
if (FNAME(gpte_changed)(vcpu, gw, top_level))
goto out_gpte_changed;
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+ goto out_gpte_changed;
+
for (shadow_walk_init(&it, vcpu, addr);
shadow_walk_okay(&it) && it.level > gw->level;
shadow_walk_next(&it)) {
@@ -671,6 +692,11 @@
*/
mmu_topup_memory_caches(vcpu);
+ if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) {
+ WARN_ON(1);
+ return;
+ }
+
spin_lock(&vcpu->kvm->mmu_lock);
for_each_shadow_entry(vcpu, gva, iterator) {
level = iterator.level;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a14a6ea..03f7d03 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -606,7 +606,7 @@
return 1;
}
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -617,7 +617,7 @@
amd_pmu_disable_virt();
}
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
@@ -2985,10 +2985,8 @@
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
r = cr_interception(svm);
- if (irqchip_in_kernel(svm->vcpu.kvm)) {
- clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+ if (irqchip_in_kernel(svm->vcpu.kvm))
return r;
- }
if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
return r;
kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3198,7 +3196,7 @@
msr.host_initiated = false;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
- if (svm_set_msr(&svm->vcpu, &msr)) {
+ if (kvm_set_msr(&svm->vcpu, &msr)) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(&svm->vcpu, 0);
} else {
@@ -3480,9 +3478,9 @@
if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
|| !svm_exit_handlers[exit_code]) {
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = exit_code;
- return 0;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
return svm_exit_handlers[exit_code](svm);
@@ -3550,6 +3548,8 @@
if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
return;
+ clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
if (irr == -1)
return;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 260a919..995fcc4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -438,6 +438,7 @@
#endif
int gs_ldt_reload_needed;
int fs_reload_needed;
+ unsigned long vmcs_host_cr4; /* May not match real cr4 */
} host_state;
struct {
int vm86_active;
@@ -2493,12 +2494,15 @@
break;
msr = find_msr_entry(vmx, msr_index);
if (msr) {
+ u64 old_msr_data = msr->data;
msr->data = data;
if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
preempt_disable();
- kvm_set_shared_msr(msr->index, msr->data,
- msr->mask);
+ ret = kvm_set_shared_msr(msr->index, msr->data,
+ msr->mask);
preempt_enable();
+ if (ret)
+ msr->data = old_msr_data;
}
break;
}
@@ -2566,7 +2570,7 @@
: "memory", "cc");
}
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2630,7 +2634,7 @@
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
{
if (vmm_exclusive) {
vmclear_local_loaded_vmcss();
@@ -3399,15 +3403,22 @@
var->limit = vmx_read_guest_seg_limit(vmx, seg);
var->selector = vmx_read_guest_seg_selector(vmx, seg);
ar = vmx_read_guest_seg_ar(vmx, seg);
+ var->unusable = (ar >> 16) & 1;
var->type = ar & 15;
var->s = (ar >> 4) & 1;
var->dpl = (ar >> 5) & 3;
- var->present = (ar >> 7) & 1;
+ /*
+ * Some userspaces do not preserve unusable property. Since usable
+ * segment has to be present according to VMX spec we can use present
+ * property to amend userspace bug by making unusable segment always
+ * nonpresent. vmx_segment_access_rights() already marks nonpresent
+ * segment as unusable.
+ */
+ var->present = !var->unusable;
var->avl = (ar >> 12) & 1;
var->l = (ar >> 13) & 1;
var->db = (ar >> 14) & 1;
var->g = (ar >> 15) & 1;
- var->unusable = (ar >> 16) & 1;
}
static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
@@ -4066,11 +4077,16 @@
u32 low32, high32;
unsigned long tmpl;
struct desc_ptr dt;
+ unsigned long cr4;
vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */
- vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
+ /* Save the most likely value for this task's CR4 in the VMCS. */
+ cr4 = read_cr4();
+ vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */
+ vmx->host_state.vmcs_host_cr4 = cr4;
+
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
#ifdef CONFIG_X86_64
/*
@@ -5055,7 +5071,7 @@
msr.data = data;
msr.index = ecx;
msr.host_initiated = false;
- if (vmx_set_msr(vcpu, &msr) != 0) {
+ if (kvm_set_msr(vcpu, &msr) != 0) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(vcpu, 0);
return 1;
@@ -6232,6 +6248,18 @@
return 1;
}
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
+static int handle_invvpid(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -6276,6 +6304,8 @@
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
+ [EXIT_REASON_INVEPT] = handle_invept,
+ [EXIT_REASON_INVVPID] = handle_invvpid,
};
static const int kvm_vmx_max_exit_handlers =
@@ -6502,6 +6532,7 @@
case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+ case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
/*
* VMX instructions trap unconditionally. This allows L1 to
* emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6644,10 +6675,10 @@
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
- vcpu->run->hw.hardware_exit_reason = exit_reason;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
- return 0;
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
@@ -6946,7 +6977,7 @@
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long debugctlmsr;
+ unsigned long debugctlmsr, cr4;
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -6967,6 +6998,12 @@
if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+ cr4 = read_cr4();
+ if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->host_state.vmcs_host_cr4 = cr4;
+ }
+
/* When single-stepping over STI and MOV SS, we must clear the
* corresponding interruptibility bits in the guest state. Otherwise
* vmentry fails as it then expects bit 14 (BS) in pending debug
@@ -7126,8 +7163,8 @@
struct vcpu_vmx *vmx = to_vmx(vcpu);
free_vpid(vmx);
- free_nested(vmx);
free_loaded_vmcs(vmx->loaded_vmcs);
+ free_nested(vmx);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
@@ -7942,7 +7979,7 @@
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip);
- vmx_set_rflags(vcpu, X86_EFLAGS_BIT1);
+ vmx_set_rflags(vcpu, X86_EFLAGS_FIXED);
/*
* Note that calling vmx_set_cr0 is important, even if cr0 hasn't
* actually changed, because it depends on the current state of
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e8ba99c..88365f2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -94,6 +94,9 @@
static bool ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
+unsigned int min_timer_period_us = 500;
+module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
+
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32 kvm_max_guest_tsc_khz;
@@ -222,24 +225,29 @@
shared_msr_update(i, shared_msrs_global.msrs[i]);
}
-void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+ int err;
if (((value ^ smsr->values[slot].curr) & mask) == 0)
- return;
+ return 0;
smsr->values[slot].curr = value;
- wrmsrl(shared_msrs_global.msrs[slot], value);
+ err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+ if (err)
+ return 1;
+
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
smsr->registered = true;
}
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -917,7 +925,6 @@
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
-
/*
* Writes msr value into into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -925,8 +932,34 @@
*/
int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
+ switch (msr->index) {
+ case MSR_FS_BASE:
+ case MSR_GS_BASE:
+ case MSR_KERNEL_GS_BASE:
+ case MSR_CSTAR:
+ case MSR_LSTAR:
+ if (is_noncanonical_address(msr->data))
+ return 1;
+ break;
+ case MSR_IA32_SYSENTER_EIP:
+ case MSR_IA32_SYSENTER_ESP:
+ /*
+ * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
+ * non-canonical address is written on Intel but not on
+ * AMD (which ignores the top 32-bits, because it does
+ * not implement 64-bit SYSENTER).
+ *
+ * 64-bit code should hence be able to write a non-canonical
+ * value on AMD. Making the address canonical ensures that
+ * vmentry does not fail on Intel after writing a non-canonical
+ * value, and that something deterministic happens if the guest
+ * invokes 64-bit SYSENTER.
+ */
+ msr->data = get_canonical(msr->data);
+ }
return kvm_x86_ops->set_msr(vcpu, msr);
}
+EXPORT_SYMBOL_GPL(kvm_set_msr);
/*
* Adapt set_msr() to msr_io()'s calling convention
@@ -1149,21 +1182,22 @@
{
#ifdef CONFIG_X86_64
bool vcpus_matched;
- bool do_request = false;
struct kvm_arch *ka = &vcpu->kvm->arch;
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
atomic_read(&vcpu->kvm->online_vcpus));
- if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
- if (!ka->use_master_clock)
- do_request = 1;
-
- if (!vcpus_matched && ka->use_master_clock)
- do_request = 1;
-
- if (do_request)
+ /*
+ * Once the masterclock is enabled, always perform request in
+ * order to update it.
+ *
+ * In order to enable masterclock, the host clocksource must be TSC
+ * and the vcpus need to have matched TSCs. When that happens,
+ * perform request to enable masterclock.
+ */
+ if (ka->use_master_clock ||
+ (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -1193,20 +1227,37 @@
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
+ int faulted = 0;
+
/* n.b - signed multiplication and division required */
usdiff = data - kvm->arch.last_tsc_write;
#ifdef CONFIG_X86_64
usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
#else
/* do_div() only does unsigned */
- asm("idivl %2; xor %%edx, %%edx"
- : "=A"(usdiff)
- : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+ asm("1: idivl %[divisor]\n"
+ "2: xor %%edx, %%edx\n"
+ " movl $0, %[faulted]\n"
+ "3:\n"
+ ".section .fixup,\"ax\"\n"
+ "4: movl $1, %[faulted]\n"
+ " jmp 3b\n"
+ ".previous\n"
+
+ _ASM_EXTABLE(1b, 4b)
+
+ : "=A"(usdiff), [faulted] "=r" (faulted)
+ : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz));
+
#endif
do_div(elapsed, 1000);
usdiff -= elapsed;
if (usdiff < 0)
usdiff = -usdiff;
+
+ /* idivl overflow => difference is larger than USEC_PER_SEC */
+ if (faulted)
+ usdiff = USEC_PER_SEC;
} else
usdiff = USEC_PER_SEC; /* disable TSC match window below */
@@ -2500,7 +2551,7 @@
return r;
}
-int kvm_dev_ioctl_check_extension(long ext)
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -2510,6 +2561,7 @@
case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
+ case KVM_CAP_EXT_EMUL_CPUID:
case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
@@ -2619,15 +2671,17 @@
r = 0;
break;
}
- case KVM_GET_SUPPORTED_CPUID: {
+ case KVM_GET_SUPPORTED_CPUID:
+ case KVM_GET_EMULATED_CPUID: {
struct kvm_cpuid2 __user *cpuid_arg = argp;
struct kvm_cpuid2 cpuid;
r = -EFAULT;
if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
goto out;
- r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
- cpuid_arg->entries);
+
+ r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+ ioctl);
if (r)
goto out;
@@ -3138,8 +3192,7 @@
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
- r = 0;
- kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
break;
}
case KVM_X86_SETUP_MCE: {
@@ -4785,7 +4838,7 @@
++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
- if (!is_guest_mode(vcpu)) {
+ if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
@@ -5104,7 +5157,7 @@
smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
@@ -5114,7 +5167,7 @@
send_ipi = 1;
}
}
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
if (freq->old < freq->new && send_ipi) {
/*
@@ -5261,12 +5314,12 @@
struct kvm_vcpu *vcpu;
int i;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
atomic_set(&kvm_guest_has_master_clock, 0);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
}
static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5539,36 +5592,6 @@
!kvm_event_needs_reinjection(vcpu);
}
-static int vapic_enter(struct kvm_vcpu *vcpu)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
- struct page *page;
-
- if (!apic || !apic->vapic_addr)
- return 0;
-
- page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
- if (is_error_page(page))
- return -EFAULT;
-
- vcpu->arch.apic->vapic_page = page;
- return 0;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
- struct kvm_lapic *apic = vcpu->arch.apic;
- int idx;
-
- if (!apic || !apic->vapic_addr)
- return;
-
- idx = srcu_read_lock(&vcpu->kvm->srcu);
- kvm_release_page_dirty(apic->vapic_page);
- mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
static void update_cr8_intercept(struct kvm_vcpu *vcpu)
{
int max_irr, tpr;
@@ -5889,11 +5912,6 @@
struct kvm *kvm = vcpu->kvm;
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- r = vapic_enter(vcpu);
- if (r) {
- srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- return r;
- }
r = 1;
while (r > 0) {
@@ -5944,15 +5962,13 @@
}
if (need_resched()) {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- kvm_resched(vcpu);
+ cond_resched();
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
}
}
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- vapic_exit(vcpu);
-
return r;
}
@@ -6017,7 +6033,7 @@
frag->len -= len;
}
- if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
if (vcpu->mmio_is_write)
return 1;
@@ -6600,7 +6616,7 @@
kvm_rip_write(vcpu, 0);
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
@@ -6611,7 +6627,7 @@
bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- ret = kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable();
if (ret != 0)
return ret;
@@ -6691,10 +6707,10 @@
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
- kvm_x86_ops->hardware_disable(garbage);
- drop_user_return_notifiers(garbage);
+ kvm_x86_ops->hardware_disable();
+ drop_user_return_notifiers();
}
int kvm_arch_hardware_setup(void)
@@ -6806,6 +6822,10 @@
static_key_slow_dec(&kvm_no_apic_vcpu);
}
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
if (type)
@@ -6897,7 +6917,7 @@
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
int i;
@@ -6918,7 +6938,8 @@
}
}
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages)
{
int i;
@@ -6976,6 +6997,10 @@
return -ENOMEM;
}
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -7114,7 +7139,7 @@
int r;
if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
- is_error_page(work->page))
+ work->wakeup_all)
return;
r = kvm_mmu_reload(vcpu);
@@ -7224,7 +7249,7 @@
struct x86_exception fault;
trace_kvm_async_pf_ready(work->arch.token, work->gva);
- if (is_error_page(work->page))
+ if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e224f7a..7626d3e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -78,15 +78,23 @@
vcpu->arch.mmio_gva = gva & PAGE_MASK;
vcpu->arch.access = access;
vcpu->arch.mmio_gfn = gfn;
+ vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
}
/*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
*/
+#define MMIO_GVA_ANY (~(gva_t)0)
+
static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
{
- if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+ if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
return;
vcpu->arch.mmio_gva = 0;
@@ -94,7 +102,8 @@
static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
{
- if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+ vcpu->arch.mmio_gva == (gva & PAGE_MASK))
return true;
return false;
@@ -102,7 +111,8 @@
static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
- if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+ vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
return true;
return false;
@@ -124,5 +134,7 @@
extern u64 host_xcr0;
+extern unsigned int min_timer_period_us;
+
extern struct static_key kvm_no_apic_vcpu;
#endif
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 25b7ae8..7609e0e 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
*/
#include <asm/checksum.h>
#include <linux/module.h>
+#include <asm/smap.h>
/**
* csum_partial_copy_from_user - Copy and checksum from user space.
@@ -52,8 +53,10 @@
len -= 2;
}
}
+ stac();
isum = csum_partial_copy_generic((__force const void *)src,
dst, len, isum, errp, NULL);
+ clac();
if (unlikely(*errp))
goto out_err;
@@ -82,6 +85,8 @@
csum_partial_copy_to_user(const void *src, void __user *dst,
int len, __wsum isum, int *errp)
{
+ __wsum ret;
+
might_sleep();
if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) {
@@ -105,8 +110,11 @@
}
*errp = 0;
- return csum_partial_copy_generic(src, (void __force *)dst,
- len, isum, NULL, errp);
+ stac();
+ ret = csum_partial_copy_generic(src, (void __force *)dst,
+ len, isum, NULL, errp);
+ clac();
+ return ret;
}
EXPORT_SYMBOL(csum_partial_copy_to_user);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a..e04e677 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,11 +30,13 @@
unsigned long start_address;
unsigned long current_address;
const struct addr_marker *marker;
+ unsigned long lines;
};
struct addr_marker {
unsigned long start_address;
const char *name;
+ unsigned long max_lines;
};
/* indices for address_markers; keep sync'd w/ address_markers below */
@@ -45,6 +47,7 @@
LOW_KERNEL_NR,
VMALLOC_START_NR,
VMEMMAP_START_NR,
+ ESPFIX_START_NR,
HIGH_KERNEL_NR,
MODULES_VADDR_NR,
MODULES_END_NR,
@@ -67,6 +70,7 @@
{ PAGE_OFFSET, "Low Kernel Mapping" },
{ VMALLOC_START, "vmalloc() Area" },
{ VMEMMAP_START, "Vmemmap" },
+ { ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
@@ -163,7 +167,7 @@
pgprot_t new_prot, int level)
{
pgprotval_t prot, cur;
- static const char units[] = "KMGTPE";
+ static const char units[] = "BKMGTPE";
/*
* If we have a "break" in the series, we need to flush the state that
@@ -178,6 +182,7 @@
st->current_prot = new_prot;
st->level = level;
st->marker = address_markers;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
} else if (prot != cur || level != st->level ||
st->current_address >= st->marker[1].start_address) {
@@ -188,17 +193,21 @@
/*
* Now print the actual finished series
*/
- seq_printf(m, "0x%0*lx-0x%0*lx ",
- width, st->start_address,
- width, st->current_address);
+ if (!st->marker->max_lines ||
+ st->lines < st->marker->max_lines) {
+ seq_printf(m, "0x%0*lx-0x%0*lx ",
+ width, st->start_address,
+ width, st->current_address);
- delta = (st->current_address - st->start_address) >> 10;
- while (!(delta & 1023) && unit[1]) {
- delta >>= 10;
- unit++;
+ delta = (st->current_address - st->start_address);
+ while (!(delta & 1023) && unit[1]) {
+ delta >>= 10;
+ unit++;
+ }
+ seq_printf(m, "%9lu%c ", delta, *unit);
+ printk_prot(m, st->current_prot, st->level);
}
- seq_printf(m, "%9lu%c ", delta, *unit);
- printk_prot(m, st->current_prot, st->level);
+ st->lines++;
/*
* We print markers for special areas of address space,
@@ -206,7 +215,15 @@
* This helps in the interpretation.
*/
if (st->current_address >= st->marker[1].start_address) {
+ if (st->marker->max_lines &&
+ st->lines > st->marker->max_lines) {
+ unsigned long nskip =
+ st->lines - st->marker->max_lines;
+ seq_printf(m, "... %lu entr%s skipped ... \n",
+ nskip, nskip == 1 ? "y" : "ies");
+ }
st->marker++;
+ st->lines = 0;
seq_printf(m, "---[ %s ]---\n", st->marker->name);
}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4a..e4780b0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -812,11 +812,8 @@
unsigned int fault)
{
struct task_struct *tsk = current;
- struct mm_struct *mm = tsk->mm;
int code = BUS_ADRERR;
- up_read(&mm->mmap_sem);
-
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
@@ -842,35 +839,23 @@
force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}
-static noinline int
+static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
unsigned long address, unsigned int fault)
{
- /*
- * Pagefault was interrupted by SIGKILL. We have no reason to
- * continue pagefault.
- */
- if (fatal_signal_pending(current)) {
- if (!(fault & VM_FAULT_RETRY))
- up_read(¤t->mm->mmap_sem);
- if (!(error_code & PF_USER))
- no_context(regs, error_code, address, 0, 0);
- return 1;
+ if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+ no_context(regs, error_code, address, 0, 0);
+ return;
}
- if (!(fault & VM_FAULT_ERROR))
- return 0;
if (fault & VM_FAULT_OOM) {
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
- up_read(¤t->mm->mmap_sem);
no_context(regs, error_code, address,
SIGSEGV, SEGV_MAPERR);
- return 1;
+ return;
}
- up_read(¤t->mm->mmap_sem);
-
/*
* We ran out of memory, call the OOM killer, and return the
* userspace (which will retry the fault, or kill us if we got
@@ -881,10 +866,11 @@
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
do_sigbus(regs, error_code, address, fault);
+ else if (fault & VM_FAULT_SIGSEGV)
+ bad_area_nosemaphore(regs, error_code, address);
else
BUG();
}
- return 1;
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -989,6 +975,12 @@
static inline bool smap_violation(int error_code, struct pt_regs *regs)
{
+ if (!IS_ENABLED(CONFIG_X86_SMAP))
+ return false;
+
+ if (!static_cpu_has(X86_FEATURE_SMAP))
+ return false;
+
if (error_code & PF_USER)
return false;
@@ -1011,9 +1003,7 @@
unsigned long address;
struct mm_struct *mm;
int fault;
- int write = error_code & PF_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -1083,6 +1073,7 @@
if (user_mode_vm(regs)) {
local_irq_enable();
error_code |= PF_USER;
+ flags |= FAULT_FLAG_USER;
} else {
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
@@ -1091,11 +1082,9 @@
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
- if (static_cpu_has(X86_FEATURE_SMAP)) {
- if (unlikely(smap_violation(error_code, regs))) {
- bad_area_nosemaphore(regs, error_code, address);
- return;
- }
+ if (unlikely(smap_violation(error_code, regs))) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
}
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
@@ -1109,6 +1098,9 @@
return;
}
+ if (error_code & PF_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in
@@ -1187,9 +1179,18 @@
*/
fault = handle_mm_fault(mm, vma, address, flags);
- if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
- if (mm_fault_error(regs, error_code, address, fault))
- return;
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ up_read(&mm->mmap_sem);
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}
/*
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index ae1aa71..7e73e8c 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -16,169 +16,6 @@
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
-static unsigned long page_table_shareable(struct vm_area_struct *svma,
- struct vm_area_struct *vma,
- unsigned long addr, pgoff_t idx)
-{
- unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
- svma->vm_start;
- unsigned long sbase = saddr & PUD_MASK;
- unsigned long s_end = sbase + PUD_SIZE;
-
- /* Allow segments to share if only one is marked locked */
- unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
- unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
-
- /*
- * match the virtual addresses, permission and the alignment of the
- * page table page.
- */
- if (pmd_index(addr) != pmd_index(saddr) ||
- vm_flags != svm_flags ||
- sbase < svma->vm_start || svma->vm_end < s_end)
- return 0;
-
- return saddr;
-}
-
-static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
-{
- unsigned long base = addr & PUD_MASK;
- unsigned long end = base + PUD_SIZE;
-
- /*
- * check on proper vm_flags and page table alignment
- */
- if (vma->vm_flags & VM_MAYSHARE &&
- vma->vm_start <= base && end <= vma->vm_end)
- return 1;
- return 0;
-}
-
-/*
- * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
- * and returns the corresponding pte. While this is not necessary for the
- * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
- */
-static pte_t *
-huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
-{
- struct vm_area_struct *vma = find_vma(mm, addr);
- struct address_space *mapping = vma->vm_file->f_mapping;
- pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
- vma->vm_pgoff;
- struct vm_area_struct *svma;
- unsigned long saddr;
- pte_t *spte = NULL;
- pte_t *pte;
-
- if (!vma_shareable(vma, addr))
- return (pte_t *)pmd_alloc(mm, pud, addr);
-
- mutex_lock(&mapping->i_mmap_mutex);
- vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
- if (svma == vma)
- continue;
-
- saddr = page_table_shareable(svma, vma, addr, idx);
- if (saddr) {
- spte = huge_pte_offset(svma->vm_mm, saddr);
- if (spte) {
- get_page(virt_to_page(spte));
- break;
- }
- }
- }
-
- if (!spte)
- goto out;
-
- spin_lock(&mm->page_table_lock);
- if (pud_none(*pud))
- pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK));
- else
- put_page(virt_to_page(spte));
- spin_unlock(&mm->page_table_lock);
-out:
- pte = (pte_t *)pmd_alloc(mm, pud, addr);
- mutex_unlock(&mapping->i_mmap_mutex);
- return pte;
-}
-
-/*
- * unmap huge page backed by shared pte.
- *
- * Hugetlb pte page is ref counted at the time of mapping. If pte is shared
- * indicated by page_count > 1, unmap is achieved by clearing pud and
- * decrementing the ref count. If count == 1, the pte page is not shared.
- *
- * called with vma->vm_mm->page_table_lock held.
- *
- * returns: 1 successfully unmapped a shared pte page
- * 0 the underlying pte page is not shared, or it is the last user
- */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
- pgd_t *pgd = pgd_offset(mm, *addr);
- pud_t *pud = pud_offset(pgd, *addr);
-
- BUG_ON(page_count(virt_to_page(ptep)) == 0);
- if (page_count(virt_to_page(ptep)) == 1)
- return 0;
-
- pud_clear(pud);
- put_page(virt_to_page(ptep));
- *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
- return 1;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
- unsigned long addr, unsigned long sz)
-{
- pgd_t *pgd;
- pud_t *pud;
- pte_t *pte = NULL;
-
- pgd = pgd_offset(mm, addr);
- pud = pud_alloc(mm, pgd, addr);
- if (pud) {
- if (sz == PUD_SIZE) {
- pte = (pte_t *)pud;
- } else {
- BUG_ON(sz != PMD_SIZE);
- if (pud_none(*pud))
- pte = huge_pmd_share(mm, addr, pud);
- else
- pte = (pte_t *)pmd_alloc(mm, pud, addr);
- }
- }
- BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
-
- return pte;
-}
-
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd = NULL;
-
- pgd = pgd_offset(mm, addr);
- if (pgd_present(*pgd)) {
- pud = pud_offset(pgd, addr);
- if (pud_present(*pud)) {
- if (pud_large(*pud))
- return (pte_t *)pud;
- pmd = pmd_offset(pud, addr);
- }
- }
- return (pte_t *) pmd;
-}
-
#if 0 /* This is just for testing */
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -240,30 +77,6 @@
return !!(pud_val(pud) & _PAGE_PSE);
}
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int write)
-{
- struct page *page;
-
- page = pte_page(*(pte_t *)pmd);
- if (page)
- page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
- return page;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
- pud_t *pud, int write)
-{
- struct page *page;
-
- page = pte_page(*(pte_t *)pud);
- if (page)
- page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
- return page;
-}
-
#endif
/* x86_64 also uses this file */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1f34e92..7a5bf1b 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -78,8 +78,8 @@
return __va(pfn << PAGE_SHIFT);
}
-/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE (5 * PAGE_SIZE)
+/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */
+#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE)
RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
void __init early_alloc_pgt_buf(void)
{
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bb00c46..2db3f30 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1142,7 +1142,7 @@
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
- unsigned long all_end = PFN_ALIGN(&_end);
+ unsigned long all_end;
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
@@ -1153,7 +1153,16 @@
/*
* The rodata/data/bss/brk section (but not the kernel text!)
* should also be not-executable.
+ *
+ * We align all_end to PMD_SIZE because the existing mapping
+ * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+ * split the PMD and the reminder between _brk_end and the end
+ * of the PMD will remain mapped executable.
+ *
+ * Any PMD which was setup after the one which covers _brk_end
+ * has been zapped already via cleanup_highmem().
*/
+ all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
rodata_test();
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9a1e658..86c758de 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -50,6 +50,21 @@
return err;
}
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+ void *arg)
+{
+ unsigned long i;
+
+ for (i = 0; i < nr_pages; ++i)
+ if (pfn_valid(start_pfn + i) &&
+ !PageReserved(pfn_to_page(start_pfn + i)))
+ return 1;
+
+ WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
+
+ return 0;
+}
+
/*
* Remap an arbitrary physical address space into the kernel virtual
* address space. Needed when the kernel wants to access high addresses
@@ -93,14 +108,11 @@
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
+ pfn = phys_addr >> PAGE_SHIFT;
last_pfn = last_addr >> PAGE_SHIFT;
- for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) {
- int is_ram = page_is_ram(pfn);
-
- if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn)))
- return NULL;
- WARN_ON_ONCE(is_ram);
- }
+ if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+ __ioremap_check_ram) == 1)
+ return NULL;
/*
* Mappings have to be page-aligned
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 845df68..75f9e5d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -35,12 +35,12 @@
.flags = -1,
};
-static unsigned int stack_maxrandom_size(void)
+static unsigned long stack_maxrandom_size(void)
{
- unsigned int max = 0;
+ unsigned long max = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
- max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+ max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
}
return max;
@@ -112,12 +112,14 @@
*/
void arch_pick_mmap_layout(struct mm_struct *mm)
{
+ mm->mmap_legacy_base = mmap_legacy_base();
+ mm->mmap_base = mmap_base();
+
if (mmap_is_legacy()) {
- mm->mmap_base = mmap_legacy_base();
+ mm->mmap_base = mm->mmap_legacy_base;
mm->get_unmapped_area = arch_get_unmapped_area;
mm->unmap_area = arch_unmap_area;
} else {
- mm->mmap_base = mmap_base();
mm->get_unmapped_area = arch_get_unmapped_area_topdown;
mm->unmap_area = arch_unmap_area_topdown;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480..aabdf76 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -389,7 +389,7 @@
psize = page_level_size(level);
pmask = page_level_mask(level);
offset = virt_addr & ~pmask;
- phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
return (phys_addr | offset);
}
EXPORT_SYMBOL_GPL(slow_virt_to_phys);
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1..0149575 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@
push %r9; \
push SKBDATA; \
/* rsi already has offset */ \
- mov $SIZE,%ecx; /* size */ \
+ mov $SIZE,%edx; /* size */ \
call bpf_internal_load_pointer_neg_helper; \
test %rax,%rax; \
pop SKBDATA; \
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index f66b540..0c966fe 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -324,15 +324,21 @@
EMIT2(0x89, 0xd0); /* mov %edx,%eax */
break;
case BPF_S_ALU_MOD_K: /* A %= K; */
+ if (K == 1) {
+ CLEAR_A();
+ break;
+ }
EMIT2(0x31, 0xd2); /* xor %edx,%edx */
EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */
EMIT2(0xf7, 0xf1); /* div %ecx */
EMIT2(0x89, 0xd0); /* mov %edx,%eax */
break;
- case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
- EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
- EMIT(K, 4);
- EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+ case BPF_S_ALU_DIV_K: /* A /= K */
+ if (K == 1)
+ break;
+ EMIT2(0x31, 0xd2); /* xor %edx,%edx */
+ EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */
+ EMIT2(0xf7, 0xf1); /* div %ecx */
break;
case BPF_S_ALU_AND_X:
seen |= SEEN_XREG;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 981c2db..88f143d 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -448,6 +448,22 @@
DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
},
},
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+ },
+ },
+ {
+ .callback = set_scan_all,
+ .ident = "Stratus/NEC ftServer",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+ },
+ },
{}
};
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 94919e3..2883f08 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@
return start;
if (start & 0x300)
start = (start + 0x3ff) & ~0x3ff;
+ } else if (res->flags & IORESOURCE_MEM) {
+ /* The low 1MB range is reserved for ISA cards */
+ if (start < BIOS_END)
+ start = BIOS_END;
}
return start;
}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index d2fbced..816e940 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -60,34 +60,19 @@
static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
-struct efi __read_mostly efi = {
- .mps = EFI_INVALID_TABLE_ADDR,
- .acpi = EFI_INVALID_TABLE_ADDR,
- .acpi20 = EFI_INVALID_TABLE_ADDR,
- .smbios = EFI_INVALID_TABLE_ADDR,
- .sal_systab = EFI_INVALID_TABLE_ADDR,
- .boot_info = EFI_INVALID_TABLE_ADDR,
- .hcdp = EFI_INVALID_TABLE_ADDR,
- .uga = EFI_INVALID_TABLE_ADDR,
- .uv_systab = EFI_INVALID_TABLE_ADDR,
-};
-EXPORT_SYMBOL(efi);
-
struct efi_memory_map memmap;
static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;
-unsigned long x86_efi_facility;
+static __initdata efi_config_table_type_t arch_tables[] = {
+#ifdef CONFIG_X86_UV
+ {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+ {NULL_GUID, NULL, 0},
+};
-/*
- * Returns 1 if 'facility' is enabled, 0 otherwise.
- */
-int efi_enabled(int facility)
-{
- return test_bit(facility, &x86_efi_facility) != 0;
-}
-EXPORT_SYMBOL(efi_enabled);
+u64 efi_setup; /* efi setup_data physical address */
static bool __initdata disable_runtime = false;
static int __init setup_noefi(char *arg)
@@ -397,6 +382,8 @@
memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
+ efi.memmap = &memmap;
+
return 0;
}
@@ -438,7 +425,7 @@
* - Not within any part of the kernel
* - Not the bios reserved area
*/
- if ((start+size >= __pa_symbol(_text)
+ if ((start + size > __pa_symbol(_text)
&& start <= __pa_symbol(_end)) ||
!e820_all_mapped(start, start+size, E820_RAM) ||
memblock_is_region_reserved(start, size)) {
@@ -454,7 +441,7 @@
void __init efi_unmap_memmap(void)
{
- clear_bit(EFI_MEMMAP, &x86_efi_facility);
+ clear_bit(EFI_MEMMAP, &efi.flags);
if (memmap.map) {
early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
memmap.map = NULL;
@@ -576,80 +563,6 @@
return 0;
}
-static int __init efi_config_init(u64 tables, int nr_tables)
-{
- void *config_tables, *tablep;
- int i, sz;
-
- if (efi_enabled(EFI_64BIT))
- sz = sizeof(efi_config_table_64_t);
- else
- sz = sizeof(efi_config_table_32_t);
-
- /*
- * Let's see what config tables the firmware passed to us.
- */
- config_tables = early_ioremap(tables, nr_tables * sz);
- if (config_tables == NULL) {
- pr_err("Could not map Configuration table!\n");
- return -ENOMEM;
- }
-
- tablep = config_tables;
- pr_info("");
- for (i = 0; i < efi.systab->nr_tables; i++) {
- efi_guid_t guid;
- unsigned long table;
-
- if (efi_enabled(EFI_64BIT)) {
- u64 table64;
- guid = ((efi_config_table_64_t *)tablep)->guid;
- table64 = ((efi_config_table_64_t *)tablep)->table;
- table = table64;
-#ifdef CONFIG_X86_32
- if (table64 >> 32) {
- pr_cont("\n");
- pr_err("Table located above 4GB, disabling EFI.\n");
- early_iounmap(config_tables,
- efi.systab->nr_tables * sz);
- return -EINVAL;
- }
-#endif
- } else {
- guid = ((efi_config_table_32_t *)tablep)->guid;
- table = ((efi_config_table_32_t *)tablep)->table;
- }
- if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
- efi.mps = table;
- pr_cont(" MPS=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
- efi.acpi20 = table;
- pr_cont(" ACPI 2.0=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
- efi.acpi = table;
- pr_cont(" ACPI=0x%lx ", table);
- } else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
- efi.smbios = table;
- pr_cont(" SMBIOS=0x%lx ", table);
-#ifdef CONFIG_X86_UV
- } else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
- efi.uv_systab = table;
- pr_cont(" UVsystab=0x%lx ", table);
-#endif
- } else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
- efi.hcdp = table;
- pr_cont(" HCDP=0x%lx ", table);
- } else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
- efi.uga = table;
- pr_cont(" UGA=0x%lx ", table);
- }
- tablep += sz;
- }
- pr_cont("\n");
- early_iounmap(config_tables, efi.systab->nr_tables * sz);
- return 0;
-}
-
static int __init efi_runtime_init(void)
{
efi_runtime_services_t *runtime;
@@ -725,7 +638,11 @@
if (efi_systab_init(efi_phys.systab))
return;
- set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
+ set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
+ efi.config_table = (unsigned long)efi.systab->tables;
+ efi.fw_vendor = (unsigned long)efi.systab->fw_vendor;
+ efi.runtime = (unsigned long)efi.systab->runtime;
/*
* Show what we know for posterity
@@ -743,10 +660,10 @@
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff, vendor);
- if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
+ if (efi_config_init(arch_tables))
return;
- set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
+ set_bit(EFI_CONFIG_TABLES, &efi.flags);
/*
* Note: We currently don't support runtime services on an EFI
@@ -758,20 +675,13 @@
else {
if (disable_runtime || efi_runtime_init())
return;
- set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
}
if (efi_memmap_init())
return;
- set_bit(EFI_MEMMAP, &x86_efi_facility);
-
-#ifdef CONFIG_X86_32
- if (efi_is_native()) {
- x86_platform.get_wallclock = efi_get_time;
- x86_platform.set_wallclock = efi_set_rtc_mmss;
- }
-#endif
+ set_bit(EFI_MEMMAP, &efi.flags);
#if EFI_DEBUG
print_efi_memmap();
@@ -814,34 +724,6 @@
}
}
-/*
- * We can't ioremap data in EFI boot services RAM, because we've already mapped
- * it as RAM. So, look it up in the existing EFI memory map instead. Only
- * callable after efi_enter_virtual_mode and before efi_free_boot_services.
- */
-void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
-{
- void *p;
- if (WARN_ON(!memmap.map))
- return NULL;
- for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
- efi_memory_desc_t *md = p;
- u64 size = md->num_pages << EFI_PAGE_SHIFT;
- u64 end = md->phys_addr + size;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
- continue;
- if (!md->virt_addr)
- continue;
- if (phys_addr >= md->phys_addr && phys_addr < end) {
- phys_addr += md->virt_addr - md->phys_addr;
- return (__force void __iomem *)(unsigned long)phys_addr;
- }
- }
- return NULL;
-}
-
void efi_memory_uc(u64 addr, unsigned long size)
{
unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
@@ -910,10 +792,13 @@
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
- continue;
+ if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+ if (md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+ continue;
+ }
size = md->num_pages << EFI_PAGE_SHIFT;
end = md->phys_addr + size;
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 7d28c88..291226b 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -13,13 +13,11 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmzone.h>
+#include <asm/sections.h>
/* Defined in hibernate_asm_32.S */
extern int restore_image(void);
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
/* Pointer to the temporary resume page tables */
pgd_t *resume_pg_dir;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index a0fde91..8ecaed1 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -17,11 +17,9 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mtrr.h>
+#include <asm/sections.h>
#include <asm/suspend.h>
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
/* Defined in hibernate_asm_64.S */
extern int restore_image(void);
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
index 8869287..9cac825 100644
--- a/arch/x86/realmode/rm/Makefile
+++ b/arch/x86/realmode/rm/Makefile
@@ -73,9 +73,10 @@
-march=i386 -mregparm=3 \
-include $(srctree)/$(src)/../../boot/code16gcc.h \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+ -mno-mmx -mno-sse \
$(call cc-option, -ffreestanding) \
$(call cc-option, -fno-toplevel-reorder,\
- $(call cc-option, -fno-unit-at-a-time)) \
+ $(call cc-option, -fno-unit-at-a-time)) \
$(call cc-option, -fno-stack-protector) \
$(call cc-option, -mpreferred-stack-boundary=2)
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65d..63a8993 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -212,10 +212,10 @@
203 common sched_setaffinity sys_sched_setaffinity
204 common sched_getaffinity sys_sched_getaffinity
205 64 set_thread_area
-206 common io_setup sys_io_setup
+206 64 io_setup sys_io_setup
207 common io_destroy sys_io_destroy
208 common io_getevents sys_io_getevents
-209 common io_submit sys_io_submit
+209 64 io_submit sys_io_submit
210 common io_cancel sys_io_cancel
211 64 get_thread_area
212 common lookup_dcookie sys_lookup_dcookie
@@ -356,3 +356,5 @@
540 x32 process_vm_writev compat_sys_process_vm_writev
541 x32 setsockopt compat_sys_setsockopt
542 x32 getsockopt compat_sys_getsockopt
+543 x32 io_setup compat_sys_io_setup
+544 x32 io_submit compat_sys_io_submit
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 531d426..bd16d6c 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -34,7 +34,7 @@
extern asmlinkage void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index f2f0723..9578308 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -46,7 +46,7 @@
extern void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S
index 31776d0..d7ec4e2 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/vdso/vdso32/sigreturn.S
@@ -17,6 +17,7 @@
.text
.globl __kernel_sigreturn
.type __kernel_sigreturn,@function
+ nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
ALIGN
__kernel_sigreturn:
.LSTART_sigreturn:
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 431e875..ab6ba35 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -117,30 +117,45 @@
struct linux_binprm;
-/* Put the vdso above the (randomized) stack with another randomized offset.
- This way there is no hole in the middle of address space.
- To save memory make sure it is still in the same PTE as the stack top.
- This doesn't give that many random bits */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset. This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top. This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
static unsigned long vdso_addr(unsigned long start, unsigned len)
{
unsigned long addr, end;
unsigned offset;
- end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+ /*
+ * Round up the start address. It can start out unaligned as a result
+ * of stack start randomization.
+ */
+ start = PAGE_ALIGN(start);
+
+ /* Round the lowest possible end address up to a PMD boundary. */
+ end = (start + len + PMD_SIZE - 1) & PMD_MASK;
if (end >= TASK_SIZE_MAX)
end = TASK_SIZE_MAX;
end -= len;
- /* This loses some more bits than a modulo, but is cheaper */
- offset = get_random_int() & (PTRS_PER_PTE - 1);
- addr = start + (offset << PAGE_SHIFT);
- if (addr >= end)
- addr = end;
+
+ if (end > start) {
+ offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+ addr = start + (offset << PAGE_SHIFT);
+ } else {
+ addr = start;
+ }
/*
- * page-align it here so that get_unmapped_area doesn't
- * align it wrongfully again to the next page. addr can come in 4K
- * unaligned here as a result of stack start randomization.
+ * Forcibly align the final address in case we have a hardware
+ * issue that requires alignment for performance reasons.
*/
- addr = PAGE_ALIGN(addr);
addr = align_vdso_addr(addr);
return addr;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa..1563444 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -878,7 +878,6 @@
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
if (!PageHighMem(page)) {
@@ -925,8 +924,8 @@
* frontend pages while they are being shared with the backend,
* because mfn_to_pfn (that ends up being called by GUPF) will
* return the backend pfn rather than the frontend pfn. */
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == mfn)
set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
return 0;
@@ -941,7 +940,6 @@
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
mfn = get_phys_to_machine(pfn);
@@ -1019,8 +1017,8 @@
* the original pfn causes mfn_to_pfn(mfn) to return the frontend
* pfn again. */
mfn &= ~FOREIGN_FRAME_BIT;
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
m2p_find_override(mfn) == NULL)
set_phys_to_machine(pfn, mfn);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 94eac5c..0a9fb7a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -313,6 +313,17 @@
e820_add_region(start, end - start, type);
}
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+ struct e820entry *entry;
+ unsigned int i;
+
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ if (entry->type == E820_UNUSABLE)
+ entry->type = E820_RAM;
+ }
+}
+
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
@@ -353,6 +364,17 @@
}
BUG_ON(rc);
+ /*
+ * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+ * regions, so if we're using the machine memory map leave the
+ * region as RAM as it is in the pseudo-physical map.
+ *
+ * UNUSABLE regions in domUs are not handled and will need
+ * a patch in the future.
+ */
+ if (xen_initial_domain())
+ xen_ignore_unusable(map, memmap.nr_entries);
+
/* Make sure the Xen-supplied memory map is well-ordered. */
sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d99cae8..570c9a5 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -245,6 +245,15 @@
old memory can be recycled */
make_lowmem_page_readwrite(xen_initial_gdt);
+#ifdef CONFIG_X86_32
+ /*
+ * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+ * expects __USER_DS
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
+
xen_filter_cpu_maps();
xen_setup_vcpu_info_placement();
}
@@ -667,8 +676,15 @@
static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int rc;
- rc = native_cpu_up(cpu, tidle);
- WARN_ON (xen_smp_intr_init(cpu));
+ /*
+ * xen_smp_intr_init() needs to run before native_cpu_up()
+ * so that IPI vectors are set up on the booting CPU before
+ * it is marked online in native_cpu_up().
+ */
+ rc = xen_smp_intr_init(cpu);
+ WARN_ON(rc);
+ if (!rc)
+ rc = native_cpu_up(cpu, tidle);
return rc;
}
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 3d88bfd..13e8935 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -36,9 +36,8 @@
/* snapshots of runstate info */
static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
-/* unused ns of stolen and blocked time */
+/* unused ns of stolen time */
static DEFINE_PER_CPU(u64, xen_residual_stolen);
-static DEFINE_PER_CPU(u64, xen_residual_blocked);
/* return an consistent snapshot of 64-bit time/counter value */
static u64 get64(const u64 *p)
@@ -115,7 +114,7 @@
{
struct vcpu_runstate_info state;
struct vcpu_runstate_info *snap;
- s64 blocked, runnable, offline, stolen;
+ s64 runnable, offline, stolen;
cputime_t ticks;
get_runstate_snapshot(&state);
@@ -125,7 +124,6 @@
snap = &__get_cpu_var(xen_runstate_snapshot);
/* work out how much time the VCPU has not been runn*ing* */
- blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline];
@@ -141,17 +139,6 @@
ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
__this_cpu_write(xen_residual_stolen, stolen);
account_steal_ticks(ticks);
-
- /* Add the appropriate number of ticks of blocked time,
- including any left-overs from last time. */
- blocked += __this_cpu_read(xen_residual_blocked);
-
- if (blocked < 0)
- blocked = 0;
-
- ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
- __this_cpu_write(xen_residual_blocked, blocked);
- account_idle_ticks(ticks);
}
/* Get the TSC speed from Xen */
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 0a1b95f..2b086a6 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -287,6 +287,36 @@
source "fs/Kconfig.binfmt"
+config XTFPGA_LCD
+ bool "Enable XTFPGA LCD driver"
+ depends on XTENSA_PLATFORM_XTFPGA
+ default n
+ help
+ There's a 2x16 LCD on most of XTFPGA boards, kernel may output
+ progress messages there during bootup/shutdown. It may be useful
+ during board bringup.
+
+ If unsure, say N.
+
+config XTFPGA_LCD_BASE_ADDR
+ hex "XTFPGA LCD base address"
+ depends on XTFPGA_LCD
+ default "0x0d0c0000"
+ help
+ Base address of the LCD controller inside KIO region.
+ Different boards from XTFPGA family have LCD controller at different
+ addresses. Please consult prototyping user guide for your board for
+ the correct address. Wrong address here may lead to hardware lockup.
+
+config XTFPGA_LCD_8BIT_ACCESS
+ bool "Use 8-bit access to XTFPGA LCD"
+ depends on XTFPGA_LCD
+ default n
+ help
+ LCD may be connected with 4- or 8-bit interface, 8-bit access may
+ only be used with 8-bit interface. Please consult prototyping user
+ guide for your board for the correct interface width.
+
endmenu
source "net/Kconfig"
diff --git a/arch/xtensa/include/asm/ftrace.h b/arch/xtensa/include/asm/ftrace.h
deleted file mode 100644
index 36dc7a6..0000000
--- a/arch/xtensa/include/asm/ftrace.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * arch/xtensa/include/asm/ftrace.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2013 Tensilica Inc.
- */
-#ifndef _XTENSA_FTRACE_H
-#define _XTENSA_FTRACE_H
-
-#include <asm/processor.h>
-
-#define HAVE_ARCH_CALLER_ADDR
-#define CALLER_ADDR0 ({ unsigned long a0, a1; \
- __asm__ __volatile__ ( \
- "mov %0, a0\n" \
- "mov %1, a1\n" \
- : "=r"(a0), "=r"(a1) : : ); \
- MAKE_PC_FROM_RA(a0, a1); })
-#ifdef CONFIG_FRAME_POINTER
-extern unsigned long return_address(unsigned level);
-#define CALLER_ADDR1 return_address(1)
-#define CALLER_ADDR2 return_address(2)
-#define CALLER_ADDR3 return_address(3)
-#else
-#define CALLER_ADDR1 (0)
-#define CALLER_ADDR2 (0)
-#define CALLER_ADDR3 (0)
-#endif
-
-#endif /* _XTENSA_FTRACE_H */
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index d7546c9..385efb2 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -68,7 +68,12 @@
#define VMALLOC_START 0xC0000000
#define VMALLOC_END 0xC7FEFFFF
#define TLBTEMP_BASE_1 0xC7FF0000
-#define TLBTEMP_BASE_2 0xC7FF8000
+#define TLBTEMP_BASE_2 (TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
+#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
+#define TLBTEMP_SIZE (2 * DCACHE_WAY_SIZE)
+#else
+#define TLBTEMP_SIZE ICACHE_WAY_SIZE
+#endif
/*
* Xtensa Linux config PTE layout (when present):
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 917488a..f2faa58 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -22,25 +22,37 @@
static inline void spill_registers(void)
{
-
+#if XCHAL_NUM_AREGS > 16
__asm__ __volatile__ (
- "movi a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
- "mov a12, a0\n\t"
- "rsr a13, sar\n\t"
- "xsr a14, ps\n\t"
- "movi a0, _spill_registers\n\t"
- "rsync\n\t"
- "callx0 a0\n\t"
- "mov a0, a12\n\t"
- "wsr a13, sar\n\t"
- "wsr a14, ps\n\t"
- : :
-#if defined(CONFIG_FRAME_POINTER)
- : "a2", "a3", "a4", "a11", "a12", "a13", "a14", "a15",
-#else
- : "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+ " call12 1f\n"
+ " _j 2f\n"
+ " retw\n"
+ " .align 4\n"
+ "1:\n"
+ " _entry a1, 48\n"
+ " addi a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+ " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+ " _entry a1, 48\n"
+ " mov a12, a0\n"
+ " .endr\n"
#endif
- "memory");
+ " _entry a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+ " mov a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+ " mov a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+ " mov a4, a4\n"
+#endif
+ " retw\n"
+ "2:\n"
+ : : : "a12", "a13", "memory");
+#else
+ __asm__ __volatile__ (
+ " mov a12, a12\n"
+ : : : "memory");
+#endif
}
#endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index fd686dc..c7211e7 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -52,7 +52,12 @@
*/
.macro get_fs ad, sp
GET_CURRENT(\ad,\sp)
+#if THREAD_CURRENT_DS > 1020
+ addi \ad, \ad, TASK_THREAD
+ l32i \ad, \ad, THREAD_CURRENT_DS - TASK_THREAD
+#else
l32i \ad, \ad, THREAD_CURRENT_DS
+#endif
.endm
/*
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index b4cb110..a47909f 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -28,17 +28,17 @@
#define TCSETSW 0x5403
#define TCSETSF 0x5404
-#define TCGETA _IOR('t', 23, struct termio)
-#define TCSETA _IOW('t', 24, struct termio)
-#define TCSETAW _IOW('t', 25, struct termio)
-#define TCSETAF _IOW('t', 28, struct termio)
+#define TCGETA 0x80127417 /* _IOR('t', 23, struct termio) */
+#define TCSETA 0x40127418 /* _IOW('t', 24, struct termio) */
+#define TCSETAW 0x40127419 /* _IOW('t', 25, struct termio) */
+#define TCSETAF 0x4012741C /* _IOW('t', 28, struct termio) */
#define TCSBRK _IO('t', 29)
#define TCXONC _IO('t', 30)
#define TCFLSH _IO('t', 31)
-#define TIOCSWINSZ _IOW('t', 103, struct winsize)
-#define TIOCGWINSZ _IOR('t', 104, struct winsize)
+#define TIOCSWINSZ 0x40087467 /* _IOW('t', 103, struct winsize) */
+#define TIOCGWINSZ 0x80087468 /* _IOR('t', 104, struct winsize) */
#define TIOCSTART _IO('t', 110) /* start output, like ^Q */
#define TIOCSTOP _IO('t', 111) /* stop output, like ^S */
#define TIOCOUTQ _IOR('t', 115, int) /* output queue size */
@@ -88,7 +88,6 @@
#define TIOCSETD _IOW('T', 35, int)
#define TIOCGETD _IOR('T', 36, int)
#define TCSBRKP _IOW('T', 37, int) /* Needed for POSIX tcsendbreak()*/
-#define TIOCTTYGSTRUCT _IOR('T', 38, struct tty_struct) /* For debugging only*/
#define TIOCSBRK _IO('T', 39) /* BSD compatibility */
#define TIOCCBRK _IO('T', 40) /* BSD compatibility */
#define TIOCGSID _IOR('T', 41, pid_t) /* Return the session ID of FD*/
@@ -114,8 +113,10 @@
#define TIOCSERGETLSR _IOR('T', 89, unsigned int) /* Get line status reg. */
/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
# define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
-#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config */
-#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */
+#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config */
+ /* _IOR('T', 90, struct serial_multiport_struct) */
+#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */
+ /* _IOW('T', 91, struct serial_multiport_struct) */
#define TIOCMIWAIT _IO('T', 92) /* wait for a change on serial input line(s) */
#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fe..d07c188 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -384,7 +384,8 @@
#define __NR_pivot_root 175
__SYSCALL(175, sys_pivot_root, 2)
#define __NR_umount 176
-__SYSCALL(176, sys_umount, 2)
+__SYSCALL(176, sys_oldumount, 1)
+#define __ARCH_WANT_SYS_OLDUMOUNT
#define __NR_swapoff 177
__SYSCALL(177, sys_swapoff, 1)
#define __NR_sync 178
@@ -714,7 +715,7 @@
__SYSCALL(324, sys_name_to_handle_at, 5)
#define __NR_open_by_handle_at 325
__SYSCALL(325, sys_open_by_handle_at, 3)
-#define __NR_sync_file_range 326
+#define __NR_sync_file_range2 326
__SYSCALL(326, sys_sync_file_range2, 6)
#define __NR_perf_event_open 327
__SYSCALL(327, sys_perf_event_open, 5)
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 5082507..6e53174 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1121,9 +1121,8 @@
movi a7, 4 # sizeof(unsigned int)
access_ok a3, a7, a0, a2, .Leac # a0: scratch reg, a2: sp
- addi a6, a6, -1 # assuming SYS_XTENSA_ATOMIC_SET = 1
- _bgeui a6, SYS_XTENSA_COUNT - 1, .Lill
- _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp
+ _bgeui a6, SYS_XTENSA_COUNT, .Lill
+ _bnei a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp
/* Fall through for ATOMIC_CMP_SWP. */
@@ -1135,27 +1134,26 @@
l32i a7, a2, PT_AREG7 # restore a7
l32i a0, a2, PT_AREG0 # restore a0
movi a2, 1 # and return 1
- addi a6, a6, 1 # restore a6 (really necessary?)
rfe
1: l32i a7, a2, PT_AREG7 # restore a7
l32i a0, a2, PT_AREG0 # restore a0
movi a2, 0 # return 0 (note that we cannot set
- addi a6, a6, 1 # restore a6 (really necessary?)
rfe
.Lnswp: /* Atomic set, add, and exg_add. */
TRY l32i a7, a3, 0 # orig
+ addi a6, a6, -SYS_XTENSA_ATOMIC_SET
add a0, a4, a7 # + arg
moveqz a0, a4, a6 # set
+ addi a6, a6, SYS_XTENSA_ATOMIC_SET
TRY s32i a0, a3, 0 # write new value
mov a0, a2
mov a2, a7
l32i a7, a0, PT_AREG7 # restore a7
l32i a0, a0, PT_AREG0 # restore a0
- addi a6, a6, 1 # restore a6 (really necessary?)
rfe
CATCH
@@ -1164,7 +1162,7 @@
movi a2, -EFAULT
rfe
-.Lill: l32i a7, a2, PT_AREG0 # restore a7
+.Lill: l32i a7, a2, PT_AREG7 # restore a7
l32i a0, a2, PT_AREG0 # restore a0
movi a2, -EINVAL
rfe
@@ -1703,7 +1701,7 @@
rsr a0, excvaddr
bltu a0, a3, 2f
- addi a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT))
+ addi a1, a0, -TLBTEMP_SIZE
bgeu a1, a3, 2f
/* Check if we have to restore an ITLB mapping. */
@@ -1912,6 +1910,43 @@
ENDPROC(system_call)
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+ .macro spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+ call12 1f
+ _j 2f
+ retw
+ .align 4
+1:
+ _entry a1, 48
+ addi a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+ .rept (XCHAL_NUM_AREGS - 32) / 12
+ _entry a1, 48
+ mov a12, a0
+ .endr
+#endif
+ _entry a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+ mov a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+ mov a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+ mov a4, a4
+#endif
+ retw
+2:
+#else
+ mov a12, a12
+#endif
+ .endm
/*
* Task switch.
@@ -1924,21 +1959,25 @@
entry a1, 16
- mov a12, a2 # preserve 'prev' (a2)
- mov a13, a3 # and 'next' (a3)
+ mov a11, a3 # and 'next' (a3)
l32i a4, a2, TASK_THREAD_INFO
l32i a5, a3, TASK_THREAD_INFO
- save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+ save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
- s32i a0, a12, THREAD_RA # save return address
- s32i a1, a12, THREAD_SP # save stack pointer
+#if THREAD_RA > 1020 || THREAD_SP > 1020
+ addi a10, a2, TASK_THREAD
+ s32i a0, a10, THREAD_RA - TASK_THREAD # save return address
+ s32i a1, a10, THREAD_SP - TASK_THREAD # save stack pointer
+#else
+ s32i a0, a2, THREAD_RA # save return address
+ s32i a1, a2, THREAD_SP # save stack pointer
+#endif
/* Disable ints while we manipulate the stack pointer. */
- movi a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
- xsr a14, ps
+ rsil a14, LOCKLEVEL
rsr a3, excsave1
rsync
s32i a3, a3, EXC_TABLE_FIXUP /* enter critical section */
@@ -1953,7 +1992,7 @@
/* Flush register file. */
- call0 _spill_registers # destroys a3, a4, and SAR
+ spill_registers_kernel
/* Set kernel stack (and leave critical section)
* Note: It's save to set it here. The stack will not be overwritten
@@ -1969,13 +2008,12 @@
/* restore context of the task 'next' */
- l32i a0, a13, THREAD_RA # restore return address
- l32i a1, a13, THREAD_SP # restore stack pointer
+ l32i a0, a11, THREAD_RA # restore return address
+ l32i a1, a11, THREAD_SP # restore stack pointer
- load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+ load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
wsr a14, ps
- mov a2, a12 # return 'prev'
rsync
retw
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index ef12c0e..7d740eb 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -68,6 +68,15 @@
#ifdef CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX
initialize_mmu
+#if defined(CONFIG_MMU) && XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY
+ rsr a2, excsave1
+ movi a3, 0x08000000
+ bgeu a2, a3, 1f
+ movi a3, 0xd0000000
+ add a2, a2, a3
+ wsr a2, excsave1
+1:
+#endif
#endif
.end no-absolute-literals
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 2d9cc6d..e8b76b8 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -49,9 +49,8 @@
/* We currently don't support coherent memory outside KSEG */
- if (ret < XCHAL_KSEG_CACHED_VADDR
- || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE)
- BUG();
+ BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
+ ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
if (ret != 0) {
@@ -68,10 +67,11 @@
void dma_free_coherent(struct device *hwdev, size_t size,
void *vaddr, dma_addr_t dma_handle)
{
- long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR;
+ unsigned long addr = (unsigned long)vaddr +
+ XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
- if (addr < 0 || addr >= XCHAL_KSEG_SIZE)
- BUG();
+ BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
+ addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
free_pages(addr, get_order(size));
}
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 6dd25ec..ea9afb6 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -152,8 +152,8 @@
{
meminfo_t* mi;
mi = (meminfo_t*)(tag->data);
- initrd_start = (void*)(mi->start);
- initrd_end = (void*)(mi->end);
+ initrd_start = __va(mi->start);
+ initrd_end = __va(mi->end);
return 0;
}
@@ -164,14 +164,13 @@
static int __init parse_tag_fdt(const bp_tag_t *tag)
{
- dtb_start = (void *)(tag->data[0]);
+ dtb_start = __va(tag->data[0]);
return 0;
}
__tagtable(BP_TAG_FDT, parse_tag_fdt);
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (void *)__va(start);
initrd_end = (void *)__va(end);
@@ -223,6 +222,43 @@
}
#ifdef CONFIG_OF
+bool __initdata dt_memory_scan = false;
+
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY
+unsigned long xtensa_kio_paddr = XCHAL_KIO_DEFAULT_PADDR;
+EXPORT_SYMBOL(xtensa_kio_paddr);
+
+static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ const __be32 *ranges;
+ int len;
+
+ if (depth > 1)
+ return 0;
+
+ if (!of_flat_dt_is_compatible(node, "simple-bus"))
+ return 0;
+
+ ranges = of_get_flat_dt_prop(node, "ranges", &len);
+ if (!ranges)
+ return 1;
+ if (len == 0)
+ return 1;
+
+ xtensa_kio_paddr = of_read_ulong(ranges+1, 1);
+ /* round down to nearest 256MB boundary */
+ xtensa_kio_paddr &= 0xf0000000;
+
+ return 1;
+}
+#else
+static int __init xtensa_dt_io_area(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ return 1;
+}
+#endif
void __init early_init_dt_add_memory_arch(u64 base, u64 size)
{
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 718eca1..98b67d5 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -341,7 +341,7 @@
sp = regs->areg[1];
- if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && ! on_sig_stack(sp)) {
+ if ((ka->sa.sa_flags & SA_ONSTACK) != 0 && sas_ss_flags(sp) == 0) {
sp = current->sas_ss_sp + current->sas_ss_size;
}
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4b7bc8d..3827833 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -72,6 +72,8 @@
address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
#endif
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
@@ -115,6 +117,8 @@
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
+ else if (fault & VM_FAULT_SIGSEGV)
+ goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
diff --git a/arch/xtensa/platforms/xtfpga/Makefile b/arch/xtensa/platforms/xtfpga/Makefile
index b9ae206..7839d38 100644
--- a/arch/xtensa/platforms/xtfpga/Makefile
+++ b/arch/xtensa/platforms/xtfpga/Makefile
@@ -6,4 +6,5 @@
#
# Note 2! The CFLAGS definitions are in the main makefile...
-obj-y = setup.o lcd.o
+obj-y += setup.o
+obj-$(CONFIG_XTFPGA_LCD) += lcd.o
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
index 4416773..b39fbcf 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/hardware.h
@@ -44,9 +44,6 @@
/* UART */
#define DUART16552_PADDR (XCHAL_KIO_PADDR + 0x0D050020)
-/* LCD instruction and data addresses. */
-#define LCD_INSTR_ADDR ((char *)IOADDR(0x0D040000))
-#define LCD_DATA_ADDR ((char *)IOADDR(0x0D040004))
/* Misc. */
#define XTFPGA_FPGAREGS_VADDR IOADDR(0x0D020000)
diff --git a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
index 0e43564..4c8541e 100644
--- a/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
+++ b/arch/xtensa/platforms/xtfpga/include/platform/lcd.h
@@ -11,10 +11,25 @@
#ifndef __XTENSA_XTAVNET_LCD_H
#define __XTENSA_XTAVNET_LCD_H
+#ifdef CONFIG_XTFPGA_LCD
/* Display string STR at position POS on the LCD. */
void lcd_disp_at_pos(char *str, unsigned char pos);
/* Shift the contents of the LCD display left or right. */
void lcd_shiftleft(void);
void lcd_shiftright(void);
+#else
+static inline void lcd_disp_at_pos(char *str, unsigned char pos)
+{
+}
+
+static inline void lcd_shiftleft(void)
+{
+}
+
+static inline void lcd_shiftright(void)
+{
+}
+#endif
+
#endif
diff --git a/arch/xtensa/platforms/xtfpga/lcd.c b/arch/xtensa/platforms/xtfpga/lcd.c
index 2872301..4dc0c1b 100644
--- a/arch/xtensa/platforms/xtfpga/lcd.c
+++ b/arch/xtensa/platforms/xtfpga/lcd.c
@@ -1,50 +1,63 @@
/*
- * Driver for the LCD display on the Tensilica LX60 Board.
+ * Driver for the LCD display on the Tensilica XTFPGA board family.
+ * http://www.mytechcorp.com/cfdata/productFile/File1/MOC-16216B-B-A0A04.pdf
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 2001, 2006 Tensilica Inc.
+ * Copyright (C) 2015 Cadence Design Systems Inc.
*/
-/*
- *
- * FIXME: this code is from the examples from the LX60 user guide.
- *
- * The lcd_pause function does busy waiting, which is probably not
- * great. Maybe the code could be changed to use kernel timers, or
- * change the hardware to not need to wait.
- */
-
+#include <linux/delay.h>
#include <linux/init.h>
#include <linux/io.h>
#include <platform/hardware.h>
#include <platform/lcd.h>
-#include <linux/delay.h>
-#define LCD_PAUSE_ITERATIONS 4000
+/* LCD instruction and data addresses. */
+#define LCD_INSTR_ADDR ((char *)IOADDR(CONFIG_XTFPGA_LCD_BASE_ADDR))
+#define LCD_DATA_ADDR (LCD_INSTR_ADDR + 4)
+
#define LCD_CLEAR 0x1
#define LCD_DISPLAY_ON 0xc
/* 8bit and 2 lines display */
#define LCD_DISPLAY_MODE8BIT 0x38
+#define LCD_DISPLAY_MODE4BIT 0x28
#define LCD_DISPLAY_POS 0x80
#define LCD_SHIFT_LEFT 0x18
#define LCD_SHIFT_RIGHT 0x1c
+static void lcd_put_byte(u8 *addr, u8 data)
+{
+#ifdef CONFIG_XTFPGA_LCD_8BIT_ACCESS
+ ACCESS_ONCE(*addr) = data;
+#else
+ ACCESS_ONCE(*addr) = data & 0xf0;
+ ACCESS_ONCE(*addr) = (data << 4) & 0xf0;
+#endif
+}
+
static int __init lcd_init(void)
{
- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
mdelay(5);
- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
udelay(200);
- *LCD_INSTR_ADDR = LCD_DISPLAY_MODE8BIT;
+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE8BIT;
udelay(50);
- *LCD_INSTR_ADDR = LCD_DISPLAY_ON;
+#ifndef CONFIG_XTFPGA_LCD_8BIT_ACCESS
+ ACCESS_ONCE(*LCD_INSTR_ADDR) = LCD_DISPLAY_MODE4BIT;
udelay(50);
- *LCD_INSTR_ADDR = LCD_CLEAR;
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_MODE4BIT);
+ udelay(50);
+#endif
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_ON);
+ udelay(50);
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_CLEAR);
mdelay(10);
lcd_disp_at_pos("XTENSA LINUX", 0);
return 0;
@@ -52,10 +65,10 @@
void lcd_disp_at_pos(char *str, unsigned char pos)
{
- *LCD_INSTR_ADDR = LCD_DISPLAY_POS | pos;
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_DISPLAY_POS | pos);
udelay(100);
while (*str != 0) {
- *LCD_DATA_ADDR = *str;
+ lcd_put_byte(LCD_DATA_ADDR, *str);
udelay(200);
str++;
}
@@ -63,13 +76,13 @@
void lcd_shiftleft(void)
{
- *LCD_INSTR_ADDR = LCD_SHIFT_LEFT;
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_LEFT);
udelay(50);
}
void lcd_shiftright(void)
{
- *LCD_INSTR_ADDR = LCD_SHIFT_RIGHT;
+ lcd_put_byte(LCD_INSTR_ADDR, LCD_SHIFT_RIGHT);
udelay(50);
}
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 96ef8ee..8a95204 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -195,7 +195,7 @@
* Ethernet -- OpenCores Ethernet MAC (ethoc driver)
*/
-static struct resource ethoc_res[] __initdata = {
+static struct resource ethoc_res[] = {
[0] = { /* register space */
.start = OETH_REGS_PADDR,
.end = OETH_REGS_PADDR + OETH_REGS_SIZE - 1,
@@ -213,7 +213,7 @@
},
};
-static struct ethoc_platform_data ethoc_pdata __initdata = {
+static struct ethoc_platform_data ethoc_pdata = {
/*
* The MAC address for these boards is 00:50:c2:13:6f:xx.
* The last byte (here as zero) is read from the DIP switches on the
@@ -223,7 +223,7 @@
.phy_id = -1,
};
-static struct platform_device ethoc_device __initdata = {
+static struct platform_device ethoc_device = {
.name = "ethoc",
.id = -1,
.num_resources = ARRAY_SIZE(ethoc_res),
@@ -237,13 +237,13 @@
* UART
*/
-static struct resource serial_resource __initdata = {
+static struct resource serial_resource = {
.start = DUART16552_PADDR,
.end = DUART16552_PADDR + 0x1f,
.flags = IORESOURCE_MEM,
};
-static struct plat_serial8250_port serial_platform_data[] __initdata = {
+static struct plat_serial8250_port serial_platform_data[] = {
[0] = {
.mapbase = DUART16552_PADDR,
.irq = DUART16552_INTNUM,
@@ -256,7 +256,7 @@
{ },
};
-static struct platform_device xtavnet_uart __initdata = {
+static struct platform_device xtavnet_uart = {
.name = "serial8250",
.id = PLAT8250_DEV_PLATFORM,
.dev = {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e8918ff..1ff8e97 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -876,6 +876,20 @@
{
lockdep_assert_held(q->queue_lock);
+ /*
+ * @q could be exiting and already have destroyed all blkgs as
+ * indicated by NULL root_blkg. If so, don't confuse policies.
+ */
+ if (!q->root_blkg)
+ return;
+
+ /*
+ * @q could be exiting and already have destroyed all blkgs as
+ * indicated by NULL root_blkg. If so, don't confuse policies.
+ */
+ if (!q->root_blkg)
+ return;
+
blk_throtl_drain(q);
}
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 4e595ee..749afad 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -399,9 +399,9 @@
uint64_t v;
do {
- start = u64_stats_fetch_begin(&stat->syncp);
+ start = u64_stats_fetch_begin_bh(&stat->syncp);
v = stat->cnt;
- } while (u64_stats_fetch_retry(&stat->syncp, start));
+ } while (u64_stats_fetch_retry_bh(&stat->syncp, start));
return v;
}
@@ -467,9 +467,9 @@
struct blkg_rwstat tmp;
do {
- start = u64_stats_fetch_begin(&rwstat->syncp);
+ start = u64_stats_fetch_begin_bh(&rwstat->syncp);
tmp = *rwstat;
- } while (u64_stats_fetch_retry(&rwstat->syncp, start));
+ } while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
return tmp;
}
diff --git a/block/blk-core.c b/block/blk-core.c
index d5745b5..cba537b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -645,10 +645,12 @@
__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
if (blkcg_init_queue(q))
- goto fail_id;
+ goto fail_bdi;
return q;
+fail_bdi:
+ bdi_destroy(&q->backing_dev_info);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
@@ -739,9 +741,17 @@
q->sg_reserved_size = INT_MAX;
+ /* Protect q->elevator from elevator_change */
+ mutex_lock(&q->sysfs_lock);
+
/* init elevator */
- if (elevator_init(q, NULL))
+ if (elevator_init(q, NULL)) {
+ mutex_unlock(&q->sysfs_lock);
return NULL;
+ }
+
+ mutex_unlock(&q->sysfs_lock);
+
return q;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -2229,6 +2239,7 @@
if (unlikely(blk_bidi_rq(req)))
req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+ BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
blk_add_timer(req);
}
EXPORT_SYMBOL(blk_start_request);
@@ -2288,7 +2299,7 @@
if (!req->bio)
return false;
- trace_block_rq_complete(req->q, req);
+ trace_block_rq_complete(req->q, req, nr_bytes);
/*
* For fs requests, rq is just carrier of independent bio's
@@ -3180,7 +3191,8 @@
/* used for unplugging and affects IO latency/throughput - HIGHPRI */
kblockd_workqueue = alloc_workqueue("kblockd",
- WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ WQ_MEM_RECLAIM | WQ_HIGHPRI |
+ WQ_POWER_EFFICIENT, 0);
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 9c4bb82..4464c82 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -144,7 +144,8 @@
if (atomic_long_dec_and_test(&ioc->refcount)) {
spin_lock_irqsave(&ioc->lock, flags);
if (!hlist_empty(&ioc->icq_list))
- schedule_work(&ioc->release_work);
+ queue_work(system_power_efficient_wq,
+ &ioc->release_work);
else
free_ioc = true;
spin_unlock_irqrestore(&ioc->lock, flags);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index d6f50d5..9a32f58 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -121,6 +121,14 @@
atomic_inc(&bb.done);
submit_bio(type, bio);
+
+ /*
+ * We can loop for a long time in here, if someone does
+ * full device discards (like mkfs). Be nice and allow
+ * us to schedule out to avoid softlocking if preempt
+ * is disabled.
+ */
+ cond_resched();
}
blk_finish_plug(&plug);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index c50ecf0..ec00a0f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -144,6 +144,7 @@
lim->discard_zeroes_data = 1;
lim->max_segments = USHRT_MAX;
lim->max_hw_sectors = UINT_MAX;
+ lim->max_segment_size = UINT_MAX;
lim->max_sectors = UINT_MAX;
lim->max_write_same_sectors = UINT_MAX;
}
@@ -552,7 +553,7 @@
bottom = max(b->physical_block_size, b->io_min) + alignment;
/* Verify that top and bottom intervals line up */
- if (max(top, bottom) & (min(top, bottom) - 1)) {
+ if (max(top, bottom) % min(top, bottom)) {
t->misaligned = 1;
ret = -1;
}
@@ -593,7 +594,7 @@
/* Find lowest common alignment_offset */
t->alignment_offset = lcm(t->alignment_offset, alignment)
- & (max(t->physical_block_size, t->io_min) - 1);
+ % max(t->physical_block_size, t->io_min);
/* Verify that new alignment_offset is on a logical block boundary */
if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/block/blk-tag.c b/block/blk-tag.c
index cc345e1..0c51b4b 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@
EXPORT_SYMBOL(blk_queue_find_tag);
/**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
* @bqt: the tag map to free
*
- * Tries to free the specified @bqt. Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
*/
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
{
- int retval;
-
- retval = atomic_dec_and_test(&bqt->refcnt);
- if (retval) {
+ if (atomic_dec_and_test(&bqt->refcnt)) {
BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
bqt->max_depth);
@@ -50,9 +47,8 @@
kfree(bqt);
}
-
- return retval;
}
+EXPORT_SYMBOL(blk_free_tags);
/**
* __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@
if (!bqt)
return;
- __blk_free_tags(bqt);
+ blk_free_tags(bqt);
q->queue_tags = NULL;
queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
}
/**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt: the tag map to free
- *
- * For externally managed @bqt frees the map. Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
- if (unlikely(!__blk_free_tags(bqt)))
- BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
* blk_queue_free_tags - release tag maintenance info
* @q: the request queue for the device
*
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 3114622..7cddfe6 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -942,6 +942,9 @@
struct blkg_rwstat rwstat = { }, tmp;
int i, cpu;
+ if (tg->stats_cpu == NULL)
+ return 0;
+
for_each_possible_cpu(cpu) {
struct tg_stats_cpu *sc = per_cpu_ptr(tg->stats_cpu, cpu);
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 6e4744c..5a6296e 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -90,8 +90,8 @@
__blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
- blk_clear_rq_complete(req);
blk_add_timer(req);
+ blk_clear_rq_complete(req);
break;
case BLK_EH_NOT_HANDLED:
/*
@@ -173,7 +173,6 @@
return;
BUG_ON(!list_empty(&req->timeout_list));
- BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
/*
* Some LLDs, like scsi, peek at the timeout to prevent a
diff --git a/block/blk.h b/block/blk.h
index e837b8f..b3bdeb3 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -96,7 +96,7 @@
q->flush_queue_delayed = 1;
return NULL;
}
- if (unlikely(blk_queue_dying(q)) ||
+ if (unlikely(blk_queue_bypass(q)) ||
!q->elevator->type->ops.elevator_dispatch_fn(q, 0))
return NULL;
}
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index d5cd3131..69111c5 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1275,12 +1275,16 @@
static void
cfq_update_group_weight(struct cfq_group *cfqg)
{
- BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
if (cfqg->new_weight) {
cfqg->weight = cfqg->new_weight;
cfqg->new_weight = 0;
}
+}
+
+static void
+cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+{
+ BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
if (cfqg->new_leaf_weight) {
cfqg->leaf_weight = cfqg->new_leaf_weight;
@@ -1299,7 +1303,7 @@
/* add to the service tree */
BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
- cfq_update_group_weight(cfqg);
+ cfq_update_group_leaf_weight(cfqg);
__cfq_group_service_tree_add(st, cfqg);
/*
@@ -1323,6 +1327,7 @@
*/
while ((parent = cfqg_parent(pos))) {
if (propagate) {
+ cfq_update_group_weight(pos);
propagate = !parent->nr_active++;
parent->children_weight += pos->weight;
}
@@ -1803,7 +1808,7 @@
if (samples) {
v = blkg_stat_read(&cfqg->stats.avg_queue_size_sum);
- do_div(v, samples);
+ v = div64_u64(v, samples);
}
__blkg_prfill_u64(sf, pd, v);
return 0;
@@ -3570,6 +3575,11 @@
blkcg = bio_blkcg(bio);
cfqg = cfq_lookup_create_cfqg(cfqd, blkcg);
+ if (!cfqg) {
+ cfqq = &cfqd->oom_cfqq;
+ goto out;
+ }
+
cfqq = cic_to_cfqq(cic, is_sync);
/*
@@ -3606,7 +3616,7 @@
} else
cfqq = &cfqd->oom_cfqq;
}
-
+out:
if (new_cfqq)
kmem_cache_free(cfq_pool, new_cfqq);
@@ -3636,12 +3646,17 @@
cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
struct bio *bio, gfp_t gfp_mask)
{
- const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
- const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+ int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+ int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
struct cfq_queue **async_cfqq = NULL;
struct cfq_queue *cfqq = NULL;
if (!is_sync) {
+ if (!ioprio_valid(cic->ioprio)) {
+ struct task_struct *tsk = current;
+ ioprio = task_nice_ioprio(tsk);
+ ioprio_class = task_nice_ioclass(tsk);
+ }
async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
cfqq = *async_cfqq;
}
@@ -4347,18 +4362,28 @@
kfree(cfqd);
}
-static int cfq_init_queue(struct request_queue *q)
+static int cfq_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct cfq_data *cfqd;
struct blkcg_gq *blkg __maybe_unused;
int i, ret;
+ struct elevator_queue *eq;
- cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
- if (!cfqd)
+ eq = elevator_alloc(q, e);
+ if (!eq)
return -ENOMEM;
+ cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
+ if (!cfqd) {
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
+ }
+ eq->elevator_data = cfqd;
+
cfqd->queue = q;
- q->elevator->elevator_data = cfqd;
+ spin_lock_irq(q->queue_lock);
+ q->elevator = eq;
+ spin_unlock_irq(q->queue_lock);
/* Init root service tree */
cfqd->grp_service_tree = CFQ_RB_ROOT;
@@ -4433,6 +4458,7 @@
out_free:
kfree(cfqd);
+ kobject_put(&eq->kobj);
return ret;
}
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 7c668c8..21ad686 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -689,6 +689,7 @@
case BLKROSET:
case BLKDISCARD:
case BLKSECDISCARD:
+ case BLKZEROOUT:
/*
* the ones below are implemented in blkdev_locked_ioctl,
* but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index ba19a3a..20614a3 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -337,13 +337,21 @@
/*
* initialize elevator private data (deadline_data).
*/
-static int deadline_init_queue(struct request_queue *q)
+static int deadline_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct deadline_data *dd;
+ struct elevator_queue *eq;
+
+ eq = elevator_alloc(q, e);
+ if (!eq)
+ return -ENOMEM;
dd = kmalloc_node(sizeof(*dd), GFP_KERNEL | __GFP_ZERO, q->node);
- if (!dd)
+ if (!dd) {
+ kobject_put(&eq->kobj);
return -ENOMEM;
+ }
+ eq->elevator_data = dd;
INIT_LIST_HEAD(&dd->fifo_list[READ]);
INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
@@ -355,7 +363,9 @@
dd->front_merges = 1;
dd->fifo_batch = fifo_batch;
- q->elevator->elevator_data = dd;
+ spin_lock_irq(q->queue_lock);
+ q->elevator = eq;
+ spin_unlock_irq(q->queue_lock);
return 0;
}
diff --git a/block/elevator.c b/block/elevator.c
index eba5b04..6d765f7 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -150,7 +150,7 @@
static struct kobj_type elv_ktype;
-static struct elevator_queue *elevator_alloc(struct request_queue *q,
+struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
struct elevator_queue *eq;
@@ -170,6 +170,7 @@
elevator_put(e);
return NULL;
}
+EXPORT_SYMBOL(elevator_alloc);
static void elevator_release(struct kobject *kobj)
{
@@ -185,6 +186,12 @@
struct elevator_type *e = NULL;
int err;
+ /*
+ * q->sysfs_lock must be held to provide mutual exclusion between
+ * elevator_switch() and here.
+ */
+ lockdep_assert_held(&q->sysfs_lock);
+
if (unlikely(q->elevator))
return 0;
@@ -221,16 +228,7 @@
}
}
- q->elevator = elevator_alloc(q, e);
- if (!q->elevator)
- return -ENOMEM;
-
- err = e->ops.elevator_init_fn(q);
- if (err) {
- kobject_put(&q->elevator->kobj);
- return err;
- }
-
+ err = e->ops.elevator_init_fn(q, e);
return 0;
}
EXPORT_SYMBOL(elevator_init);
@@ -935,17 +933,10 @@
spin_unlock_irq(q->queue_lock);
/* allocate, init and register new elevator */
- err = -ENOMEM;
- q->elevator = elevator_alloc(q, new_e);
- if (!q->elevator)
+ err = new_e->ops.elevator_init_fn(q, new_e);
+ if (err)
goto fail_init;
- err = new_e->ops.elevator_init_fn(q);
- if (err) {
- kobject_put(&q->elevator->kobj);
- goto fail_init;
- }
-
if (registered) {
err = elv_register_queue(q);
if (err)
@@ -974,7 +965,7 @@
/*
* Switch this queue to the given IO scheduler.
*/
-int elevator_change(struct request_queue *q, const char *name)
+static int __elevator_change(struct request_queue *q, const char *name)
{
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
@@ -996,6 +987,18 @@
return elevator_switch(q, e);
}
+
+int elevator_change(struct request_queue *q, const char *name)
+{
+ int ret;
+
+ /* Protect q->elevator from elevator_init() */
+ mutex_lock(&q->sysfs_lock);
+ ret = __elevator_change(q, name);
+ mutex_unlock(&q->sysfs_lock);
+
+ return ret;
+}
EXPORT_SYMBOL(elevator_change);
ssize_t elv_iosched_store(struct request_queue *q, const char *name,
@@ -1006,7 +1009,7 @@
if (!q->elevator)
return count;
- ret = elevator_change(q, name);
+ ret = __elevator_change(q, name);
if (!ret)
return count;
diff --git a/block/genhd.c b/block/genhd.c
index 20625ee..ea49f86 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -28,10 +28,10 @@
/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT (1 << MINORBITS)
-/* For extended devt allocation. ext_devt_mutex prevents look up
+/* For extended devt allocation. ext_devt_lock prevents look up
* results from going away underneath its user.
*/
-static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_SPINLOCK(ext_devt_lock);
static DEFINE_IDR(ext_devt_idr);
static struct device_type disk_type;
@@ -420,9 +420,13 @@
}
/* allocate ext devt */
- mutex_lock(&ext_devt_mutex);
- idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
- mutex_unlock(&ext_devt_mutex);
+ idr_preload(GFP_KERNEL);
+
+ spin_lock(&ext_devt_lock);
+ idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
+ spin_unlock(&ext_devt_lock);
+
+ idr_preload_end();
if (idx < 0)
return idx == -ENOSPC ? -EBUSY : idx;
@@ -441,15 +445,13 @@
*/
void blk_free_devt(dev_t devt)
{
- might_sleep();
-
if (devt == MKDEV(0, 0))
return;
if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
- mutex_lock(&ext_devt_mutex);
+ spin_lock(&ext_devt_lock);
idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
- mutex_unlock(&ext_devt_mutex);
+ spin_unlock(&ext_devt_lock);
}
}
@@ -512,7 +514,7 @@
ddev->parent = disk->driverfs_dev;
- dev_set_name(ddev, disk->disk_name);
+ dev_set_name(ddev, "%s", disk->disk_name);
/* delay uevents, until we scanned partition table */
dev_set_uevent_suppress(ddev, 1);
@@ -665,7 +667,6 @@
sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
device_del(disk_to_dev(disk));
- blk_free_devt(disk_to_dev(disk)->devt);
}
EXPORT_SYMBOL(del_gendisk);
@@ -690,13 +691,13 @@
} else {
struct hd_struct *part;
- mutex_lock(&ext_devt_mutex);
+ spin_lock(&ext_devt_lock);
part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
if (part && get_disk(part_to_disk(part))) {
*partno = part->partno;
disk = part_to_disk(part);
}
- mutex_unlock(&ext_devt_mutex);
+ spin_unlock(&ext_devt_lock);
}
return disk;
@@ -1069,9 +1070,16 @@
struct disk_part_tbl *old_ptbl = disk->part_tbl;
struct disk_part_tbl *new_ptbl;
int len = old_ptbl ? old_ptbl->len : 0;
- int target = partno + 1;
+ int i, target;
size_t size;
- int i;
+
+ /*
+ * check for int overflow, since we can get here from blkpg_ioctl()
+ * with a user passed 'partno'.
+ */
+ target = partno + 1;
+ if (target < 0)
+ return -EINVAL;
/* disk_max_parts() is zero during initialization, ignore if so */
if (disk_max_parts(disk) && target > disk_max_parts(disk))
@@ -1098,6 +1106,7 @@
{
struct gendisk *disk = dev_to_disk(dev);
+ blk_free_devt(dev->devt);
disk_release_events(disk);
kfree(disk->random);
disk_replace_part_tbl(disk, NULL);
@@ -1489,9 +1498,11 @@
intv = disk_events_poll_jiffies(disk);
set_timer_slack(&ev->dwork.timer, intv / 4);
if (check_now)
- queue_delayed_work(system_freezable_wq, &ev->dwork, 0);
+ queue_delayed_work(system_freezable_power_efficient_wq,
+ &ev->dwork, 0);
else if (intv)
- queue_delayed_work(system_freezable_wq, &ev->dwork, intv);
+ queue_delayed_work(system_freezable_power_efficient_wq,
+ &ev->dwork, intv);
out_unlock:
spin_unlock_irqrestore(&ev->lock, flags);
}
@@ -1534,7 +1545,8 @@
spin_lock_irq(&ev->lock);
ev->clearing |= mask;
if (!ev->block)
- mod_delayed_work(system_freezable_wq, &ev->dwork, 0);
+ mod_delayed_work(system_freezable_power_efficient_wq,
+ &ev->dwork, 0);
spin_unlock_irq(&ev->lock);
}
@@ -1627,7 +1639,8 @@
intv = disk_events_poll_jiffies(disk);
if (!ev->block && intv)
- queue_delayed_work(system_freezable_wq, &ev->dwork, intv);
+ queue_delayed_work(system_freezable_power_efficient_wq,
+ &ev->dwork, intv);
spin_unlock_irq(&ev->lock);
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 5d1bf70..3de89d4 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -59,16 +59,27 @@
return list_entry(rq->queuelist.next, struct request, queuelist);
}
-static int noop_init_queue(struct request_queue *q)
+static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
{
struct noop_data *nd;
+ struct elevator_queue *eq;
- nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
- if (!nd)
+ eq = elevator_alloc(q, e);
+ if (!eq)
return -ENOMEM;
+ nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
+ if (!nd) {
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
+ }
+ eq->elevator_data = nd;
+
INIT_LIST_HEAD(&nd->queue);
- q->elevator->elevator_data = nd;
+
+ spin_lock_irq(q->queue_lock);
+ q->elevator = eq;
+ spin_unlock_irq(q->queue_lock);
return 0;
}
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 789cdea..0d9e5f9 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -211,6 +211,7 @@
static void part_release(struct device *dev)
{
struct hd_struct *p = dev_to_part(dev);
+ blk_free_devt(dev->devt);
free_part_stats(p);
free_part_info(p);
kfree(p);
@@ -253,7 +254,6 @@
rcu_assign_pointer(ptbl->last_lookup, NULL);
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
- blk_free_devt(part_devt(part));
hd_struct_put(part);
}
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index a5ffcc9..1b4988b 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -506,7 +506,7 @@
if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
err = DRIVER_ERROR << 24;
- goto out;
+ goto error;
}
memset(sense, 0, sizeof(sense));
@@ -516,7 +516,6 @@
blk_execute_rq(q, disk, rq, 0);
-out:
err = rq->errors & 0xff; /* only 8 bit SCSI status */
if (err) {
if (rq->sense_len && rq->sense) {
diff --git a/crypto/842.c b/crypto/842.c
index 65c7a89c..b48f4f1 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -180,3 +180,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("842 Compression Algorithm");
+MODULE_ALIAS_CRYPTO("842");
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bf8148e..a1eba18 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -179,6 +179,10 @@
depends on X86
select CRYPTO_CRYPTD
+config CRYPTO_ABLK_HELPER
+ tristate
+ select CRYPTO_CRYPTD
+
config CRYPTO_GLUE_HELPER_X86
tristate
depends on X86
diff --git a/crypto/Makefile b/crypto/Makefile
index a8e9b0fe..5d0b869 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -101,3 +101,4 @@
obj-$(CONFIG_XOR_BLOCKS) += xor.o
obj-$(CONFIG_ASYNC_CORE) += async_tx/
obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += asymmetric_keys/
+obj-$(CONFIG_CRYPTO_ABLK_HELPER) += ablk_helper.o
diff --git a/crypto/ablk_helper.c b/crypto/ablk_helper.c
new file mode 100644
index 0000000..62568b1
--- /dev/null
+++ b/crypto/ablk_helper.c
@@ -0,0 +1,150 @@
+/*
+ * Shared async block cipher helpers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on aesni-intel_glue.c by:
+ * Copyright (C) 2008, Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
+ * USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <crypto/ablk_helper.h>
+#include <asm/simd.h>
+
+int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+ int err;
+
+ crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+ crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+ & CRYPTO_TFM_REQ_MASK);
+ err = crypto_ablkcipher_setkey(child, key, key_len);
+ crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+ & CRYPTO_TFM_RES_MASK);
+ return err;
+}
+EXPORT_SYMBOL_GPL(ablk_set_key);
+
+int __ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->encrypt(
+ &desc, req->dst, req->src, req->nbytes);
+}
+EXPORT_SYMBOL_GPL(__ablk_encrypt);
+
+int ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!may_use_simd()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ memcpy(cryptd_req, req, sizeof(*req));
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_encrypt(cryptd_req);
+ } else {
+ return __ablk_encrypt(req);
+ }
+}
+EXPORT_SYMBOL_GPL(ablk_encrypt);
+
+int ablk_decrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!may_use_simd()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ memcpy(cryptd_req, req, sizeof(*req));
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_decrypt(cryptd_req);
+ } else {
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->decrypt(
+ &desc, req->dst, req->src, req->nbytes);
+ }
+}
+EXPORT_SYMBOL_GPL(ablk_decrypt);
+
+void ablk_exit(struct crypto_tfm *tfm)
+{
+ struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+EXPORT_SYMBOL_GPL(ablk_exit);
+
+int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
+{
+ struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+
+ ctx->cryptd_tfm = cryptd_tfm;
+ tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+ crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ablk_init_common);
+
+int ablk_init(struct crypto_tfm *tfm)
+{
+ char drv_name[CRYPTO_MAX_ALG_NAME];
+
+ snprintf(drv_name, sizeof(drv_name), "__driver-%s",
+ crypto_tfm_alg_driver_name(tfm));
+
+ return ablk_init_common(tfm, drv_name);
+}
+EXPORT_SYMBOL_GPL(ablk_init);
+
+MODULE_LICENSE("GPL");
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index 47f2e5c..e138ad8 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -1474,4 +1474,5 @@
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-generic");
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index ac33d5f..6ef6e2a 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -21,6 +21,7 @@
#include <linux/module.h>
#include <linux/net.h>
#include <linux/rwsem.h>
+#include <linux/security.h>
struct alg_type_list {
const struct af_alg_type *type;
@@ -243,6 +244,7 @@
sock_init_data(newsock, sk2);
sock_graft(sk2, newsock);
+ security_sk_clone(sk, sk2);
err = type->accept(ask->private, sk2);
if (err) {
@@ -447,6 +449,9 @@
{
struct af_alg_completion *completion = req->data;
+ if (err == -EINPROGRESS)
+ return;
+
completion->err = err;
complete(&completion->completion);
}
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 6149a6e..00d8d93 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -495,7 +495,8 @@
struct crypto_template *crypto_lookup_template(const char *name)
{
- return try_then_request_module(__crypto_lookup_template(name), name);
+ return try_then_request_module(__crypto_lookup_template(name),
+ "crypto-%s", name);
}
EXPORT_SYMBOL_GPL(crypto_lookup_template);
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 0262210..8502462 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -114,6 +114,9 @@
struct hash_ctx *ctx = ask->private;
int err;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
lock_sock(sk);
sg_init_table(ctx->sgl.sg, 1);
sg_set_page(ctx->sgl.sg, page, size, offset);
@@ -161,8 +164,6 @@
else if (len < ds)
msg->msg_flags |= MSG_TRUNC;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (ctx->more) {
ctx->more = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index a1c4f0a..83187f4 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -49,7 +49,7 @@
struct ablkcipher_request req;
};
-#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \
+#define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \
sizeof(struct scatterlist) - 1)
static inline int skcipher_sndbuf(struct sock *sk)
@@ -378,6 +378,9 @@
struct skcipher_sg_list *sgl;
int err = -EINVAL;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
lock_sock(sk);
if (!ctx->more && ctx->used)
goto unlock;
@@ -432,7 +435,6 @@
long copied = 0;
lock_sock(sk);
- msg->msg_namelen = 0;
for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
iovlen--, iov++) {
unsigned long seglen = iov->iov_len;
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index c0bb377..6f5bebc 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -230,11 +230,11 @@
*/
if (byte_count < DEFAULT_BLK_SZ) {
empty_rbuf:
- for (; ctx->rand_data_valid < DEFAULT_BLK_SZ;
- ctx->rand_data_valid++) {
+ while (ctx->rand_data_valid < DEFAULT_BLK_SZ) {
*ptr = ctx->rand_data[ctx->rand_data_valid];
ptr++;
byte_count--;
+ ctx->rand_data_valid++;
if (byte_count == 0)
goto done;
}
@@ -476,4 +476,5 @@
MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)");
module_init(prng_mod_init);
module_exit(prng_mod_fini);
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("ansi_cprng");
diff --git a/crypto/anubis.c b/crypto/anubis.c
index 008c8a4..4bb187c 100644
--- a/crypto/anubis.c
+++ b/crypto/anubis.c
@@ -704,3 +704,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Anubis Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("anubis");
diff --git a/crypto/api.c b/crypto/api.c
index 3b61803..335abea 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -34,6 +34,8 @@
BLOCKING_NOTIFIER_HEAD(crypto_chain);
EXPORT_SYMBOL_GPL(crypto_chain);
+static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
+
struct crypto_alg *crypto_mod_get(struct crypto_alg *alg)
{
return try_module_get(alg->cra_module) ? crypto_alg_get(alg) : NULL;
@@ -144,8 +146,11 @@
}
up_write(&crypto_alg_sem);
- if (alg != &larval->alg)
+ if (alg != &larval->alg) {
kfree(larval);
+ if (crypto_is_larval(alg))
+ alg = crypto_larval_wait(alg);
+ }
return alg;
}
@@ -211,11 +216,11 @@
alg = crypto_alg_lookup(name, type, mask);
if (!alg) {
- request_module("%s", name);
+ request_module("crypto-%s", name);
if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask &
CRYPTO_ALG_NEED_FALLBACK))
- request_module("%s-all", name);
+ request_module("crypto-%s-all", name);
alg = crypto_alg_lookup(name, type, mask);
}
diff --git a/crypto/arc4.c b/crypto/arc4.c
index 5a772c3..f1a8192 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -166,3 +166,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("ARC4 Cipher Algorithm");
MODULE_AUTHOR("Jon Oberheide <jon@oberheide.org>");
+MODULE_ALIAS_CRYPTO("arc4");
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 06007f0..52222a2 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -106,7 +106,6 @@
static int x509_key_preparse(struct key_preparsed_payload *prep)
{
struct x509_certificate *cert;
- struct tm now;
size_t srlen, sulen;
char *desc = NULL;
int ret;
@@ -137,43 +136,6 @@
goto error_free_cert;
}
- time_to_tm(CURRENT_TIME.tv_sec, 0, &now);
- pr_devel("Now: %04ld-%02d-%02d %02d:%02d:%02d\n",
- now.tm_year + 1900, now.tm_mon + 1, now.tm_mday,
- now.tm_hour, now.tm_min, now.tm_sec);
- if (now.tm_year < cert->valid_from.tm_year ||
- (now.tm_year == cert->valid_from.tm_year &&
- (now.tm_mon < cert->valid_from.tm_mon ||
- (now.tm_mon == cert->valid_from.tm_mon &&
- (now.tm_mday < cert->valid_from.tm_mday ||
- (now.tm_mday == cert->valid_from.tm_mday &&
- (now.tm_hour < cert->valid_from.tm_hour ||
- (now.tm_hour == cert->valid_from.tm_hour &&
- (now.tm_min < cert->valid_from.tm_min ||
- (now.tm_min == cert->valid_from.tm_min &&
- (now.tm_sec < cert->valid_from.tm_sec
- ))))))))))) {
- pr_warn("Cert %s is not yet valid\n", cert->fingerprint);
- ret = -EKEYREJECTED;
- goto error_free_cert;
- }
- if (now.tm_year > cert->valid_to.tm_year ||
- (now.tm_year == cert->valid_to.tm_year &&
- (now.tm_mon > cert->valid_to.tm_mon ||
- (now.tm_mon == cert->valid_to.tm_mon &&
- (now.tm_mday > cert->valid_to.tm_mday ||
- (now.tm_mday == cert->valid_to.tm_mday &&
- (now.tm_hour > cert->valid_to.tm_hour ||
- (now.tm_hour == cert->valid_to.tm_hour &&
- (now.tm_min > cert->valid_to.tm_min ||
- (now.tm_min == cert->valid_to.tm_min &&
- (now.tm_sec > cert->valid_to.tm_sec
- ))))))))))) {
- pr_warn("Cert %s has expired\n", cert->fingerprint);
- ret = -EKEYEXPIRED;
- goto error_free_cert;
- }
-
cert->pub->algo = x509_public_key_algorithms[cert->pkey_algo];
cert->pub->id_type = PKEY_ID_X509;
diff --git a/crypto/authenc.c b/crypto/authenc.c
index ffce19d..a2cfae2 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -368,9 +368,10 @@
if (!err) {
struct crypto_aead *authenc = crypto_aead_reqtfm(areq);
struct crypto_authenc_ctx *ctx = crypto_aead_ctx(authenc);
- struct ablkcipher_request *abreq = aead_request_ctx(areq);
- u8 *iv = (u8 *)(abreq + 1) +
- crypto_ablkcipher_reqsize(ctx->enc);
+ struct authenc_request_ctx *areq_ctx = aead_request_ctx(areq);
+ struct ablkcipher_request *abreq = (void *)(areq_ctx->tail
+ + ctx->reqoff);
+ u8 *iv = (u8 *)abreq - crypto_ablkcipher_ivsize(ctx->enc);
err = crypto_authenc_genicv(areq, iv, 0);
}
@@ -708,3 +709,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Simple AEAD wrapper for IPsec");
+MODULE_ALIAS_CRYPTO("authenc");
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index ab53762..16c225c 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -832,3 +832,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
MODULE_DESCRIPTION("AEAD wrapper for IPsec with extended sequence numbers");
+MODULE_ALIAS_CRYPTO("authencesn");
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index a79e7e9..0122bec 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,14 +70,12 @@
return max(start, end_page);
}
-static inline unsigned int blkcipher_done_slow(struct crypto_blkcipher *tfm,
- struct blkcipher_walk *walk,
+static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
unsigned int bsize)
{
u8 *addr;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
- addr = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+ addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
addr = blkcipher_get_spot(addr, bsize);
scatterwalk_copychunks(addr, &walk->out, bsize, 1);
return bsize;
@@ -105,7 +103,6 @@
int blkcipher_walk_done(struct blkcipher_desc *desc,
struct blkcipher_walk *walk, int err)
{
- struct crypto_blkcipher *tfm = desc->tfm;
unsigned int nbytes = 0;
if (likely(err >= 0)) {
@@ -117,7 +114,7 @@
err = -EINVAL;
goto err;
} else
- n = blkcipher_done_slow(tfm, walk, n);
+ n = blkcipher_done_slow(walk, n);
nbytes = walk->total - n;
err = 0;
@@ -136,7 +133,7 @@
}
if (walk->iv != desc->info)
- memcpy(desc->info, walk->iv, crypto_blkcipher_ivsize(tfm));
+ memcpy(desc->info, walk->iv, walk->ivsize);
if (walk->buffer != walk->page)
kfree(walk->buffer);
if (walk->page)
@@ -226,22 +223,20 @@
static int blkcipher_walk_next(struct blkcipher_desc *desc,
struct blkcipher_walk *walk)
{
- struct crypto_blkcipher *tfm = desc->tfm;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
unsigned int bsize;
unsigned int n;
int err;
n = walk->total;
- if (unlikely(n < crypto_blkcipher_blocksize(tfm))) {
+ if (unlikely(n < walk->cipher_blocksize)) {
desc->flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
return blkcipher_walk_done(desc, walk, -EINVAL);
}
walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
BLKCIPHER_WALK_DIFF);
- if (!scatterwalk_aligned(&walk->in, alignmask) ||
- !scatterwalk_aligned(&walk->out, alignmask)) {
+ if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
+ !scatterwalk_aligned(&walk->out, walk->alignmask)) {
walk->flags |= BLKCIPHER_WALK_COPY;
if (!walk->page) {
walk->page = (void *)__get_free_page(GFP_ATOMIC);
@@ -250,12 +245,12 @@
}
}
- bsize = min(walk->blocksize, n);
+ bsize = min(walk->walk_blocksize, n);
n = scatterwalk_clamp(&walk->in, n);
n = scatterwalk_clamp(&walk->out, n);
if (unlikely(n < bsize)) {
- err = blkcipher_next_slow(desc, walk, bsize, alignmask);
+ err = blkcipher_next_slow(desc, walk, bsize, walk->alignmask);
goto set_phys_lowmem;
}
@@ -277,28 +272,26 @@
return err;
}
-static inline int blkcipher_copy_iv(struct blkcipher_walk *walk,
- struct crypto_blkcipher *tfm,
- unsigned int alignmask)
+static inline int blkcipher_copy_iv(struct blkcipher_walk *walk)
{
- unsigned bs = walk->blocksize;
- unsigned int ivsize = crypto_blkcipher_ivsize(tfm);
- unsigned aligned_bs = ALIGN(bs, alignmask + 1);
- unsigned int size = aligned_bs * 2 + ivsize + max(aligned_bs, ivsize) -
- (alignmask + 1);
+ unsigned bs = walk->walk_blocksize;
+ unsigned aligned_bs = ALIGN(bs, walk->alignmask + 1);
+ unsigned int size = aligned_bs * 2 +
+ walk->ivsize + max(aligned_bs, walk->ivsize) -
+ (walk->alignmask + 1);
u8 *iv;
- size += alignmask & ~(crypto_tfm_ctx_alignment() - 1);
+ size += walk->alignmask & ~(crypto_tfm_ctx_alignment() - 1);
walk->buffer = kmalloc(size, GFP_ATOMIC);
if (!walk->buffer)
return -ENOMEM;
- iv = (u8 *)ALIGN((unsigned long)walk->buffer, alignmask + 1);
+ iv = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
iv = blkcipher_get_spot(iv, bs) + aligned_bs;
iv = blkcipher_get_spot(iv, bs) + aligned_bs;
- iv = blkcipher_get_spot(iv, ivsize);
+ iv = blkcipher_get_spot(iv, walk->ivsize);
- walk->iv = memcpy(iv, walk->iv, ivsize);
+ walk->iv = memcpy(iv, walk->iv, walk->ivsize);
return 0;
}
@@ -306,7 +299,10 @@
struct blkcipher_walk *walk)
{
walk->flags &= ~BLKCIPHER_WALK_PHYS;
- walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->cipher_blocksize = walk->walk_blocksize;
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_virt);
@@ -315,7 +311,10 @@
struct blkcipher_walk *walk)
{
walk->flags |= BLKCIPHER_WALK_PHYS;
- walk->blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->walk_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->cipher_blocksize = walk->walk_blocksize;
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_phys);
@@ -323,9 +322,6 @@
static int blkcipher_walk_first(struct blkcipher_desc *desc,
struct blkcipher_walk *walk)
{
- struct crypto_blkcipher *tfm = desc->tfm;
- unsigned int alignmask = crypto_blkcipher_alignmask(tfm);
-
if (WARN_ON_ONCE(in_irq()))
return -EDEADLK;
@@ -335,8 +331,8 @@
walk->buffer = NULL;
walk->iv = desc->info;
- if (unlikely(((unsigned long)walk->iv & alignmask))) {
- int err = blkcipher_copy_iv(walk, tfm, alignmask);
+ if (unlikely(((unsigned long)walk->iv & walk->alignmask))) {
+ int err = blkcipher_copy_iv(walk);
if (err)
return err;
}
@@ -353,11 +349,28 @@
unsigned int blocksize)
{
walk->flags &= ~BLKCIPHER_WALK_PHYS;
- walk->blocksize = blocksize;
+ walk->walk_blocksize = blocksize;
+ walk->cipher_blocksize = crypto_blkcipher_blocksize(desc->tfm);
+ walk->ivsize = crypto_blkcipher_ivsize(desc->tfm);
+ walk->alignmask = crypto_blkcipher_alignmask(desc->tfm);
return blkcipher_walk_first(desc, walk);
}
EXPORT_SYMBOL_GPL(blkcipher_walk_virt_block);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk,
+ struct crypto_aead *tfm,
+ unsigned int blocksize)
+{
+ walk->flags &= ~BLKCIPHER_WALK_PHYS;
+ walk->walk_blocksize = blocksize;
+ walk->cipher_blocksize = crypto_aead_blocksize(tfm);
+ walk->ivsize = crypto_aead_ivsize(tfm);
+ walk->alignmask = crypto_aead_alignmask(tfm);
+ return blkcipher_walk_first(desc, walk);
+}
+EXPORT_SYMBOL_GPL(blkcipher_aead_walk_virt_block);
+
static int setkey_unaligned(struct crypto_tfm *tfm, const u8 *key,
unsigned int keylen)
{
diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c
index 8baf544..87b392a 100644
--- a/crypto/blowfish_generic.c
+++ b/crypto/blowfish_generic.c
@@ -138,4 +138,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Blowfish Cipher Algorithm");
-MODULE_ALIAS("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-generic");
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 75efa20..029587f 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -1098,4 +1098,5 @@
MODULE_DESCRIPTION("Camellia Cipher Algorithm");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("camellia");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-generic");
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index 5558f63..df5c726 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -549,4 +549,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Cast5 Cipher Algorithm");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
+MODULE_ALIAS_CRYPTO("cast5-generic");
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index de73252..058c8d7 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -291,4 +291,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Cast6 Cipher Algorithm");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
+MODULE_ALIAS_CRYPTO("cast6-generic");
diff --git a/crypto/cbc.c b/crypto/cbc.c
index 61ac42e..780ee27 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -289,3 +289,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("cbc");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 499c917..c569c9c 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -271,7 +271,8 @@
}
/* compute plaintext into mac */
- get_data_to_compute(cipher, pctx, plain, cryptlen);
+ if (cryptlen)
+ get_data_to_compute(cipher, pctx, plain, cryptlen);
out:
return err;
@@ -878,5 +879,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Counter with CBC MAC");
-MODULE_ALIAS("ccm_base");
-MODULE_ALIAS("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm_base");
+MODULE_ALIAS_CRYPTO("rfc4309");
+MODULE_ALIAS_CRYPTO("ccm");
diff --git a/crypto/chainiv.c b/crypto/chainiv.c
index 834d8dd..22b7e55 100644
--- a/crypto/chainiv.c
+++ b/crypto/chainiv.c
@@ -359,3 +359,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Chain IV Generator");
+MODULE_ALIAS_CRYPTO("chainiv");
diff --git a/crypto/cmac.c b/crypto/cmac.c
index 50880cf..7a8bfbd 100644
--- a/crypto/cmac.c
+++ b/crypto/cmac.c
@@ -313,3 +313,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CMAC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("cmac");
diff --git a/crypto/crc32.c b/crypto/crc32.c
index 9d1c415..187ded2 100644
--- a/crypto/crc32.c
+++ b/crypto/crc32.c
@@ -156,3 +156,4 @@
MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
MODULE_DESCRIPTION("CRC32 calculations wrapper for lib/crc32");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32");
diff --git a/crypto/crc32c.c b/crypto/crc32c.c
index 06f7018..238f0e6 100644
--- a/crypto/crc32c.c
+++ b/crypto/crc32c.c
@@ -170,3 +170,4 @@
MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("crc32c");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 7bdd61b..75c415d 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -955,3 +955,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Software async crypto daemon");
+MODULE_ALIAS_CRYPTO("cryptd");
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index fee7265..7b39fa3 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -149,9 +149,9 @@
.coa_decompress = null_compress } }
} };
-MODULE_ALIAS("compress_null");
-MODULE_ALIAS("digest_null");
-MODULE_ALIAS("cipher_null");
+MODULE_ALIAS_CRYPTO("compress_null");
+MODULE_ALIAS_CRYPTO("digest_null");
+MODULE_ALIAS_CRYPTO("cipher_null");
static int __init crypto_null_mod_init(void)
{
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index 1512e41..43665d0 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -466,7 +466,7 @@
type -= CRYPTO_MSG_BASE;
link = &crypto_dispatch[type];
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) &&
diff --git a/crypto/crypto_wq.c b/crypto/crypto_wq.c
index adad92a..2f1b8d1 100644
--- a/crypto/crypto_wq.c
+++ b/crypto/crypto_wq.c
@@ -33,7 +33,7 @@
destroy_workqueue(kcrypto_wq);
}
-module_init(crypto_wq_init);
+subsys_initcall(crypto_wq_init);
module_exit(crypto_wq_exit);
MODULE_LICENSE("GPL");
diff --git a/crypto/ctr.c b/crypto/ctr.c
index f2b94f2..2386f73 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -466,4 +466,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CTR Counter block mode");
-MODULE_ALIAS("rfc3686");
+MODULE_ALIAS_CRYPTO("rfc3686");
+MODULE_ALIAS_CRYPTO("ctr");
diff --git a/crypto/cts.c b/crypto/cts.c
index 042223f..60b9da3 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -350,3 +350,4 @@
MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("CTS-CBC CipherText Stealing for CBC");
+MODULE_ALIAS_CRYPTO("cts");
diff --git a/crypto/deflate.c b/crypto/deflate.c
index b57d70e..95d8d37 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -222,4 +222,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Deflate Compression Algorithm for IPCOMP");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
-
+MODULE_ALIAS_CRYPTO("deflate");
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index f6cf63f..3ec6071 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -971,8 +971,6 @@
.cia_decrypt = des3_ede_decrypt } }
} };
-MODULE_ALIAS("des3_ede");
-
static int __init des_generic_mod_init(void)
{
return crypto_register_algs(des_algs, ARRAY_SIZE(des_algs));
@@ -989,4 +987,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms");
MODULE_AUTHOR("Dag Arne Osvik <da@osvik.no>");
-MODULE_ALIAS("des");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-generic");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-generic");
diff --git a/crypto/ecb.c b/crypto/ecb.c
index 935cfef..12011af 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -185,3 +185,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("ECB block cipher algorithm");
+MODULE_ALIAS_CRYPTO("ecb");
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
index 42ce9f5..388f582 100644
--- a/crypto/eseqiv.c
+++ b/crypto/eseqiv.c
@@ -267,3 +267,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Encrypted Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("eseqiv");
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 3b2cf56..300f5b8 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -420,3 +420,4 @@
MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("FCrypt Cipher Algorithm");
MODULE_AUTHOR("David Howells <dhowells@redhat.com>");
+MODULE_ALIAS_CRYPTO("fcrypt");
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 43e1fb0..b4c2520 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -1441,6 +1441,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Galois/Counter Mode");
MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>");
-MODULE_ALIAS("gcm_base");
-MODULE_ALIAS("rfc4106");
-MODULE_ALIAS("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm_base");
+MODULE_ALIAS_CRYPTO("rfc4106");
+MODULE_ALIAS_CRYPTO("rfc4543");
+MODULE_ALIAS_CRYPTO("gcm");
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index 9d3f0c6..bac7099 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -172,4 +172,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("GHASH Message Digest Algorithm");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
+MODULE_ALIAS_CRYPTO("ghash-generic");
diff --git a/crypto/hmac.c b/crypto/hmac.c
index 8d9544c..ade790b 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -271,3 +271,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("HMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("hmac");
diff --git a/crypto/khazad.c b/crypto/khazad.c
index 60e7cd6..873eb5d 100644
--- a/crypto/khazad.c
+++ b/crypto/khazad.c
@@ -880,3 +880,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Khazad Cryptographic Algorithm");
+MODULE_ALIAS_CRYPTO("khazad");
diff --git a/crypto/krng.c b/crypto/krng.c
index a2d2b72..0224841 100644
--- a/crypto/krng.c
+++ b/crypto/krng.c
@@ -62,4 +62,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Kernel Random Number Generator");
-MODULE_ALIAS("stdrng");
+MODULE_ALIAS_CRYPTO("stdrng");
+MODULE_ALIAS_CRYPTO("krng");
diff --git a/crypto/lrw.c b/crypto/lrw.c
index ba42acc..6f9908a 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -400,3 +400,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("LRW block cipher mode");
+MODULE_ALIAS_CRYPTO("lrw");
diff --git a/crypto/lzo.c b/crypto/lzo.c
index 1c2aa69..d1ff694 100644
--- a/crypto/lzo.c
+++ b/crypto/lzo.c
@@ -103,3 +103,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("LZO Compression Algorithm");
+MODULE_ALIAS_CRYPTO("lzo");
diff --git a/crypto/md4.c b/crypto/md4.c
index 0477a6a..3515af4 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -255,4 +255,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MD4 Message Digest Algorithm");
-
+MODULE_ALIAS_CRYPTO("md4");
diff --git a/crypto/md5.c b/crypto/md5.c
index 7febeaa..36f5e5b 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -168,3 +168,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MD5 Message Digest Algorithm");
+MODULE_ALIAS_CRYPTO("md5");
diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c
index 079b761..46195e0 100644
--- a/crypto/michael_mic.c
+++ b/crypto/michael_mic.c
@@ -184,3 +184,4 @@
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Michael MIC");
MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
+MODULE_ALIAS_CRYPTO("michael_mic");
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index d1b8bdf..f654965 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -295,3 +295,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("PCBC block cipher algorithm");
+MODULE_ALIAS_CRYPTO("pcbc");
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index b2c99dc..61ff946 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -565,3 +565,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
MODULE_DESCRIPTION("Parallel crypto wrapper");
+MODULE_ALIAS_CRYPTO("pcrypt");
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
index 8a0f68b..049486e 100644
--- a/crypto/rmd128.c
+++ b/crypto/rmd128.c
@@ -327,3 +327,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-128 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd128");
diff --git a/crypto/rmd160.c b/crypto/rmd160.c
index 525d7bb..de585e5 100644
--- a/crypto/rmd160.c
+++ b/crypto/rmd160.c
@@ -371,3 +371,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-160 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd160");
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index 69293d9..4ec02a7 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -346,3 +346,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-256 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd256");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index 09f97df..770f2cb 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -395,3 +395,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>");
MODULE_DESCRIPTION("RIPEMD-320 Message Digest");
+MODULE_ALIAS_CRYPTO("rmd320");
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index 9a4770c..f550b5d 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -248,4 +248,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm");
-MODULE_ALIAS("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-generic");
diff --git a/crypto/seed.c b/crypto/seed.c
index 9c904d6..c6ba843 100644
--- a/crypto/seed.c
+++ b/crypto/seed.c
@@ -476,3 +476,4 @@
MODULE_DESCRIPTION("SEED Cipher Algorithm");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Hye-Shik Chang <perky@FreeBSD.org>, Kim Hyun <hkim@kisa.or.kr>");
+MODULE_ALIAS_CRYPTO("seed");
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index f2cba4ed..49a4069 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -362,3 +362,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Sequence Number IV Generator");
+MODULE_ALIAS_CRYPTO("seqiv");
diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c
index 7ddbd7e..94970a7 100644
--- a/crypto/serpent_generic.c
+++ b/crypto/serpent_generic.c
@@ -665,5 +665,6 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Serpent and tnepres (kerneli compatible serpent reversed) Cipher Algorithm");
MODULE_AUTHOR("Dag Arne Osvik <osvik@ii.uib.no>");
-MODULE_ALIAS("tnepres");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("tnepres");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-generic");
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 4279480..fdf7c00 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -153,4 +153,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
+MODULE_ALIAS_CRYPTO("sha1-generic");
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 5433667..136381b 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -384,5 +384,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm");
-MODULE_ALIAS("sha224");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha224-generic");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha256-generic");
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 4c58620..fb2d7b8 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -285,5 +285,7 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-512 and SHA-384 Secure Hash Algorithms");
-MODULE_ALIAS("sha384");
-MODULE_ALIAS("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha384-generic");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha512-generic");
diff --git a/crypto/tea.c b/crypto/tea.c
index 0a57232..b70b441 100644
--- a/crypto/tea.c
+++ b/crypto/tea.c
@@ -270,8 +270,9 @@
crypto_unregister_algs(tea_algs, ARRAY_SIZE(tea_algs));
}
-MODULE_ALIAS("xtea");
-MODULE_ALIAS("xeta");
+MODULE_ALIAS_CRYPTO("tea");
+MODULE_ALIAS_CRYPTO("xtea");
+MODULE_ALIAS_CRYPTO("xeta");
module_init(tea_mod_init);
module_exit(tea_mod_fini);
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index 8740355..f7ed2fb 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -676,8 +676,9 @@
crypto_unregister_shashes(tgr_algs, ARRAY_SIZE(tgr_algs));
}
-MODULE_ALIAS("tgr160");
-MODULE_ALIAS("tgr128");
+MODULE_ALIAS_CRYPTO("tgr192");
+MODULE_ALIAS_CRYPTO("tgr160");
+MODULE_ALIAS_CRYPTO("tgr128");
module_init(tgr192_mod_init);
module_exit(tgr192_mod_fini);
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index 2d50005..ebf7a3e 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -211,4 +211,5 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Twofish Cipher Algorithm");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-generic");
diff --git a/crypto/vmac.c b/crypto/vmac.c
index 2eb11a3..bf2d3a8 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -713,3 +713,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("VMAC hash algorithm");
+MODULE_ALIAS_CRYPTO("vmac");
diff --git a/crypto/wp512.c b/crypto/wp512.c
index 180f1d6..253db94 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -1167,8 +1167,9 @@
crypto_unregister_shashes(wp_algs, ARRAY_SIZE(wp_algs));
}
-MODULE_ALIAS("wp384");
-MODULE_ALIAS("wp256");
+MODULE_ALIAS_CRYPTO("wp512");
+MODULE_ALIAS_CRYPTO("wp384");
+MODULE_ALIAS_CRYPTO("wp256");
module_init(wp512_mod_init);
module_exit(wp512_mod_fini);
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index a5fbdf3..df90b33 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -286,3 +286,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("XCBC keyed hash algorithm");
+MODULE_ALIAS_CRYPTO("xcbc");
diff --git a/crypto/xts.c b/crypto/xts.c
index ca1608f..f6fd43f 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -362,3 +362,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("XTS block cipher mode");
+MODULE_ALIAS_CRYPTO("xts");
diff --git a/crypto/zlib.c b/crypto/zlib.c
index 06b62e5..d980788 100644
--- a/crypto/zlib.c
+++ b/crypto/zlib.c
@@ -378,3 +378,4 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Zlib Compression Algorithm");
MODULE_AUTHOR("Sony Corporation");
+MODULE_ALIAS_CRYPTO("zlib");
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 9953a42..d27feb5 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -166,4 +166,6 @@
source "drivers/reset/Kconfig"
+source "drivers/gator/Kconfig"
+
endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 130abc1..292d528 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -152,3 +152,6 @@
obj-$(CONFIG_VME_BUS) += vme/
obj-$(CONFIG_IPACK_BUS) += ipack/
obj-$(CONFIG_NTB) += ntb/
+
+obj-$(CONFIG_GATOR) += gator/
+obj-$(CONFIG_CORESIGHT) += coresight/
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 536562c..97c949a 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -43,6 +43,7 @@
acpi-y += power.o
acpi-y += event.o
acpi-y += sysfs.o
+acpi-$(CONFIG_X86) += acpi_cmos_rtc.o
acpi-$(CONFIG_DEBUG_FS) += debugfs.o
acpi-$(CONFIG_ACPI_NUMA) += numa.o
acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c
new file mode 100644
index 0000000..84190ed
--- /dev/null
+++ b/drivers/acpi/acpi_cmos_rtc.c
@@ -0,0 +1,92 @@
+/*
+ * ACPI support for CMOS RTC Address Space access
+ *
+ * Copyright (C) 2013, Intel Corporation
+ * Authors: Lan Tianyu <tianyu.lan@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <asm-generic/rtc.h>
+
+#include "internal.h"
+
+#define PREFIX "ACPI: "
+
+ACPI_MODULE_NAME("cmos rtc");
+
+static const struct acpi_device_id acpi_cmos_rtc_ids[] = {
+ { "PNP0B00" },
+ { "PNP0B01" },
+ { "PNP0B02" },
+ {}
+};
+
+static acpi_status
+acpi_cmos_rtc_space_handler(u32 function, acpi_physical_address address,
+ u32 bits, u64 *value64,
+ void *handler_context, void *region_context)
+{
+ int i;
+ u8 *value = (u8 *)&value64;
+
+ if (address > 0xff || !value64)
+ return AE_BAD_PARAMETER;
+
+ if (function != ACPI_WRITE && function != ACPI_READ)
+ return AE_BAD_PARAMETER;
+
+ spin_lock_irq(&rtc_lock);
+
+ for (i = 0; i < DIV_ROUND_UP(bits, 8); ++i, ++address, ++value)
+ if (function == ACPI_READ)
+ *value = CMOS_READ(address);
+ else
+ CMOS_WRITE(*value, address);
+
+ spin_unlock_irq(&rtc_lock);
+
+ return AE_OK;
+}
+
+static int acpi_install_cmos_rtc_space_handler(struct acpi_device *adev,
+ const struct acpi_device_id *id)
+{
+ acpi_status status;
+
+ status = acpi_install_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_CMOS,
+ &acpi_cmos_rtc_space_handler,
+ NULL, NULL);
+ if (ACPI_FAILURE(status)) {
+ pr_err(PREFIX "Error installing CMOS-RTC region handler\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static void acpi_remove_cmos_rtc_space_handler(struct acpi_device *adev)
+{
+ if (ACPI_FAILURE(acpi_remove_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_CMOS, &acpi_cmos_rtc_space_handler)))
+ pr_err(PREFIX "Error removing CMOS-RTC region handler\n");
+}
+
+static struct acpi_scan_handler cmos_rtc_handler = {
+ .ids = acpi_cmos_rtc_ids,
+ .attach = acpi_install_cmos_rtc_space_handler,
+ .detach = acpi_remove_cmos_rtc_space_handler,
+};
+
+void __init acpi_cmos_rtc_init(void)
+{
+ acpi_scan_add_handler(&cmos_rtc_handler);
+}
diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c
index f40acef..a6977e1 100644
--- a/drivers/acpi/acpi_ipmi.c
+++ b/drivers/acpi/acpi_ipmi.c
@@ -39,6 +39,7 @@
#include <linux/ipmi.h>
#include <linux/device.h>
#include <linux/pnp.h>
+#include <linux/spinlock.h>
MODULE_AUTHOR("Zhao Yakui");
MODULE_DESCRIPTION("ACPI IPMI Opregion driver");
@@ -57,7 +58,7 @@
struct list_head head;
/* the IPMI request message list */
struct list_head tx_msg_list;
- struct mutex tx_msg_lock;
+ spinlock_t tx_msg_lock;
acpi_handle handle;
struct pnp_dev *pnp_dev;
ipmi_user_t user_interface;
@@ -147,6 +148,7 @@
struct kernel_ipmi_msg *msg;
struct acpi_ipmi_buffer *buffer;
struct acpi_ipmi_device *device;
+ unsigned long flags;
msg = &tx_msg->tx_message;
/*
@@ -177,10 +179,10 @@
/* Get the msgid */
device = tx_msg->device;
- mutex_lock(&device->tx_msg_lock);
+ spin_lock_irqsave(&device->tx_msg_lock, flags);
device->curr_msgid++;
tx_msg->tx_msgid = device->curr_msgid;
- mutex_unlock(&device->tx_msg_lock);
+ spin_unlock_irqrestore(&device->tx_msg_lock, flags);
}
static void acpi_format_ipmi_response(struct acpi_ipmi_msg *msg,
@@ -242,6 +244,7 @@
int msg_found = 0;
struct acpi_ipmi_msg *tx_msg;
struct pnp_dev *pnp_dev = ipmi_device->pnp_dev;
+ unsigned long flags;
if (msg->user != ipmi_device->user_interface) {
dev_warn(&pnp_dev->dev, "Unexpected response is returned. "
@@ -250,7 +253,7 @@
ipmi_free_recv_msg(msg);
return;
}
- mutex_lock(&ipmi_device->tx_msg_lock);
+ spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
list_for_each_entry(tx_msg, &ipmi_device->tx_msg_list, head) {
if (msg->msgid == tx_msg->tx_msgid) {
msg_found = 1;
@@ -258,7 +261,7 @@
}
}
- mutex_unlock(&ipmi_device->tx_msg_lock);
+ spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
if (!msg_found) {
dev_warn(&pnp_dev->dev, "Unexpected response (msg id %ld) is "
"returned.\n", msg->msgid);
@@ -378,6 +381,7 @@
struct acpi_ipmi_device *ipmi_device = handler_context;
int err, rem_time;
acpi_status status;
+ unsigned long flags;
/*
* IPMI opregion message.
* IPMI message is firstly written to the BMC and system software
@@ -395,9 +399,9 @@
return AE_NO_MEMORY;
acpi_format_ipmi_msg(tx_msg, address, value);
- mutex_lock(&ipmi_device->tx_msg_lock);
+ spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
list_add_tail(&tx_msg->head, &ipmi_device->tx_msg_list);
- mutex_unlock(&ipmi_device->tx_msg_lock);
+ spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
err = ipmi_request_settime(ipmi_device->user_interface,
&tx_msg->addr,
tx_msg->tx_msgid,
@@ -413,9 +417,9 @@
status = AE_OK;
end_label:
- mutex_lock(&ipmi_device->tx_msg_lock);
+ spin_lock_irqsave(&ipmi_device->tx_msg_lock, flags);
list_del(&tx_msg->head);
- mutex_unlock(&ipmi_device->tx_msg_lock);
+ spin_unlock_irqrestore(&ipmi_device->tx_msg_lock, flags);
kfree(tx_msg);
return status;
}
@@ -457,7 +461,7 @@
INIT_LIST_HEAD(&ipmi_device->head);
- mutex_init(&ipmi_device->tx_msg_lock);
+ spin_lock_init(&ipmi_device->tx_msg_lock);
INIT_LIST_HEAD(&ipmi_device->tx_msg_list);
ipmi_install_space_handler(ipmi_device);
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index cab13f2..7c451cb 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -155,12 +155,13 @@
pdata->mmio_size = resource_size(&rentry->res);
pdata->mmio_base = ioremap(rentry->res.start,
pdata->mmio_size);
- pdata->dev_desc = dev_desc;
break;
}
acpi_dev_free_resource_list(&resource_list);
+ pdata->dev_desc = dev_desc;
+
if (dev_desc->clk_required) {
ret = register_device_clock(adev, pdata);
if (ret) {
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 5e6301e..2cf0244 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -283,6 +283,7 @@
/* Get the range from the _CRS */
result = acpi_memory_get_device_resources(mem_device);
if (result) {
+ device->driver_data = NULL;
kfree(mem_device);
return result;
}
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index d5bfbd3..9589688 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -254,6 +254,7 @@
u32 field_bit_position;
u32 field_bit_length;
u16 resource_length;
+ u16 pin_number_index;
u8 field_flags;
u8 attribute;
u8 field_type;
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index cc7ab6d..a47cc78f 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -263,6 +263,7 @@
ACPI_OBJECT_COMMON_HEADER ACPI_COMMON_FIELD_INFO u16 resource_length;
union acpi_operand_object *region_obj; /* Containing op_region object */
u8 *resource_buffer; /* resource_template for serial regions/fields */
+ u16 pin_number_index; /* Index relative to previous Connection/Template */
};
struct acpi_object_bank_field {
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index feadeed..e651d4e 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -360,6 +360,7 @@
*/
info->resource_buffer = NULL;
info->connection_node = NULL;
+ info->pin_number_index = 0;
/*
* A Connection() is either an actual resource descriptor (buffer)
@@ -437,6 +438,7 @@
}
info->field_bit_position += info->field_bit_length;
+ info->pin_number_index++; /* Index relative to previous Connection() */
break;
default:
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 6555e35..8fab926 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -141,6 +141,7 @@
union acpi_operand_object *region_obj2;
void *region_context = NULL;
struct acpi_connection_info *context;
+ acpi_physical_address address;
ACPI_FUNCTION_TRACE(ev_address_space_dispatch);
@@ -235,25 +236,23 @@
/* We have everything we need, we can invoke the address space handler */
handler = handler_desc->address_space.handler;
-
- ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
- "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
- ®ion_obj->region.handler->address_space, handler,
- ACPI_FORMAT_NATIVE_UINT(region_obj->region.address +
- region_offset),
- acpi_ut_get_region_name(region_obj->region.
- space_id)));
+ address = (region_obj->region.address + region_offset);
/*
* Special handling for generic_serial_bus and general_purpose_io:
* There are three extra parameters that must be passed to the
* handler via the context:
- * 1) Connection buffer, a resource template from Connection() op.
- * 2) Length of the above buffer.
- * 3) Actual access length from the access_as() op.
+ * 1) Connection buffer, a resource template from Connection() op
+ * 2) Length of the above buffer
+ * 3) Actual access length from the access_as() op
+ *
+ * In addition, for general_purpose_io, the Address and bit_width fields
+ * are defined as follows:
+ * 1) Address is the pin number index of the field (bit offset from
+ * the previous Connection)
+ * 2) bit_width is the actual bit length of the field (number of pins)
*/
- if (((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) ||
- (region_obj->region.space_id == ACPI_ADR_SPACE_GPIO)) &&
+ if ((region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS) &&
context && field_obj) {
/* Get the Connection (resource_template) buffer */
@@ -262,6 +261,24 @@
context->length = field_obj->field.resource_length;
context->access_length = field_obj->field.access_length;
}
+ if ((region_obj->region.space_id == ACPI_ADR_SPACE_GPIO) &&
+ context && field_obj) {
+
+ /* Get the Connection (resource_template) buffer */
+
+ context->connection = field_obj->field.resource_buffer;
+ context->length = field_obj->field.resource_length;
+ context->access_length = field_obj->field.access_length;
+ address = field_obj->field.pin_number_index;
+ bit_width = field_obj->field.bit_length;
+ }
+
+ ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
+ "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
+ ®ion_obj->region.handler->address_space, handler,
+ ACPI_FORMAT_NATIVE_UINT(address),
+ acpi_ut_get_region_name(region_obj->region.
+ space_id)));
if (!(handler_desc->address_space.handler_flags &
ACPI_ADDR_HANDLER_DEFAULT_INSTALLED)) {
@@ -275,9 +292,7 @@
/* Call the handler */
- status = handler(function,
- (region_obj->region.address + region_offset),
- bit_width, value, context,
+ status = handler(function, address, bit_width, value, context,
region_obj2->extra.region_context);
if (ACPI_FAILURE(status)) {
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index 7d4bae7..0108d59 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -178,6 +178,37 @@
buffer = &buffer_desc->integer.value;
}
+ if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+ (obj_desc->field.region_obj->region.space_id ==
+ ACPI_ADR_SPACE_GPIO)) {
+ /*
+ * For GPIO (general_purpose_io), the Address will be the bit offset
+ * from the previous Connection() operator, making it effectively a
+ * pin number index. The bit_length is the length of the field, which
+ * is thus the number of pins.
+ */
+ ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+ "GPIO FieldRead [FROM]: Pin %u Bits %u\n",
+ obj_desc->field.pin_number_index,
+ obj_desc->field.bit_length));
+
+ /* Lock entire transaction if requested */
+
+ acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+ /* Perform the write */
+
+ status = acpi_ex_access_region(obj_desc, 0,
+ (u64 *)buffer, ACPI_READ);
+ acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+ if (ACPI_FAILURE(status)) {
+ acpi_ut_remove_reference(buffer_desc);
+ } else {
+ *ret_buffer_desc = buffer_desc;
+ }
+ return_ACPI_STATUS(status);
+ }
+
ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
"FieldRead [TO]: Obj %p, Type %X, Buf %p, ByteLen %X\n",
obj_desc, obj_desc->common.type, buffer,
@@ -325,6 +356,42 @@
*result_desc = buffer_desc;
return_ACPI_STATUS(status);
+ } else if ((obj_desc->common.type == ACPI_TYPE_LOCAL_REGION_FIELD) &&
+ (obj_desc->field.region_obj->region.space_id ==
+ ACPI_ADR_SPACE_GPIO)) {
+ /*
+ * For GPIO (general_purpose_io), we will bypass the entire field
+ * mechanism and handoff the bit address and bit width directly to
+ * the handler. The Address will be the bit offset
+ * from the previous Connection() operator, making it effectively a
+ * pin number index. The bit_length is the length of the field, which
+ * is thus the number of pins.
+ */
+ if (source_desc->common.type != ACPI_TYPE_INTEGER) {
+ return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
+ }
+
+ ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+ "GPIO FieldWrite [FROM]: (%s:%X), Val %.8X [TO]: Pin %u Bits %u\n",
+ acpi_ut_get_type_name(source_desc->common.
+ type),
+ source_desc->common.type,
+ (u32)source_desc->integer.value,
+ obj_desc->field.pin_number_index,
+ obj_desc->field.bit_length));
+
+ buffer = &source_desc->integer.value;
+
+ /* Lock entire transaction if requested */
+
+ acpi_ex_acquire_global_lock(obj_desc->common_field.field_flags);
+
+ /* Perform the write */
+
+ status = acpi_ex_access_region(obj_desc, 0,
+ (u64 *)buffer, ACPI_WRITE);
+ acpi_ex_release_global_lock(obj_desc->common_field.field_flags);
+ return_ACPI_STATUS(status);
}
/* Get a pointer to the data to be written */
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index b60c877..c3241b1 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -963,10 +963,17 @@
*/
return_desc =
*(operand[0]->reference.where);
- if (return_desc) {
- acpi_ut_add_reference
- (return_desc);
+ if (!return_desc) {
+ /*
+ * Element is NULL, do not allow the dereference.
+ * This provides compatibility with other ACPI
+ * implementations.
+ */
+ return_ACPI_STATUS
+ (AE_AML_UNINITIALIZED_ELEMENT);
}
+
+ acpi_ut_add_reference(return_desc);
break;
default:
@@ -991,11 +998,40 @@
acpi_namespace_node
*)
return_desc);
+ if (!return_desc) {
+ break;
+ }
+
+ /*
+ * June 2013:
+ * buffer_fields/field_units require additional resolution
+ */
+ switch (return_desc->common.type) {
+ case ACPI_TYPE_BUFFER_FIELD:
+ case ACPI_TYPE_LOCAL_REGION_FIELD:
+ case ACPI_TYPE_LOCAL_BANK_FIELD:
+ case ACPI_TYPE_LOCAL_INDEX_FIELD:
+
+ status =
+ acpi_ex_read_data_from_field
+ (walk_state, return_desc,
+ &temp_desc);
+ if (ACPI_FAILURE(status)) {
+ goto cleanup;
+ }
+
+ return_desc = temp_desc;
+ break;
+
+ default:
+
+ /* Add another reference to the object */
+
+ acpi_ut_add_reference
+ (return_desc);
+ break;
+ }
}
-
- /* Add another reference to the object! */
-
- acpi_ut_add_reference(return_desc);
break;
default:
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 6b728ae..df212fe 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -479,6 +479,8 @@
obj_desc->field.resource_length = info->resource_length;
}
+ obj_desc->field.pin_number_index = info->pin_number_index;
+
/* Allow full data read from EC address space */
if ((obj_desc->field.region_obj->region.space_id ==
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index 93c6049..b1ad394 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -57,6 +57,11 @@
union acpi_operand_object *dest_desc,
struct acpi_walk_state *walk_state);
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+ struct acpi_namespace_node *node,
+ struct acpi_walk_state *walk_state);
+
/*******************************************************************************
*
* FUNCTION: acpi_ex_store
@@ -376,7 +381,11 @@
* When storing into an object the data is converted to the
* target object type then stored in the object. This means
* that the target object type (for an initialized target) will
- * not be changed by a store operation.
+ * not be changed by a store operation. A copy_object can change
+ * the target type, however.
+ *
+ * The implicit_conversion flag is set to NO/FALSE only when
+ * storing to an arg_x -- as per the rules of the ACPI spec.
*
* Assumes parameters are already validated.
*
@@ -400,7 +409,7 @@
target_type = acpi_ns_get_type(node);
target_desc = acpi_ns_get_attached_object(node);
- ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p(%s) into node %p(%s)\n",
+ ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Storing %p (%s) to node %p (%s)\n",
source_desc,
acpi_ut_get_object_type_name(source_desc), node,
acpi_ut_get_type_name(target_type)));
@@ -414,46 +423,31 @@
return_ACPI_STATUS(status);
}
- /* If no implicit conversion, drop into the default case below */
-
- if ((!implicit_conversion) ||
- ((walk_state->opcode == AML_COPY_OP) &&
- (target_type != ACPI_TYPE_LOCAL_REGION_FIELD) &&
- (target_type != ACPI_TYPE_LOCAL_BANK_FIELD) &&
- (target_type != ACPI_TYPE_LOCAL_INDEX_FIELD))) {
- /*
- * Force execution of default (no implicit conversion). Note:
- * copy_object does not perform an implicit conversion, as per the ACPI
- * spec -- except in case of region/bank/index fields -- because these
- * objects must retain their original type permanently.
- */
- target_type = ACPI_TYPE_ANY;
- }
-
/* Do the actual store operation */
switch (target_type) {
- case ACPI_TYPE_BUFFER_FIELD:
- case ACPI_TYPE_LOCAL_REGION_FIELD:
- case ACPI_TYPE_LOCAL_BANK_FIELD:
- case ACPI_TYPE_LOCAL_INDEX_FIELD:
-
- /* For fields, copy the source data to the target field. */
-
- status = acpi_ex_write_data_to_field(source_desc, target_desc,
- &walk_state->result_obj);
- break;
-
case ACPI_TYPE_INTEGER:
case ACPI_TYPE_STRING:
case ACPI_TYPE_BUFFER:
/*
- * These target types are all of type Integer/String/Buffer, and
- * therefore support implicit conversion before the store.
- *
- * Copy and/or convert the source object to a new target object
+ * The simple data types all support implicit source operand
+ * conversion before the store.
*/
+
+ if ((walk_state->opcode == AML_COPY_OP) || !implicit_conversion) {
+ /*
+ * However, copy_object and Stores to arg_x do not perform
+ * an implicit conversion, as per the ACPI specification.
+ * A direct store is performed instead.
+ */
+ status = acpi_ex_store_direct_to_node(source_desc, node,
+ walk_state);
+ break;
+ }
+
+ /* Store with implicit source operand conversion support */
+
status =
acpi_ex_store_object_to_object(source_desc, target_desc,
&new_desc, walk_state);
@@ -467,13 +461,12 @@
* the Name's type to that of the value being stored in it.
* source_desc reference count is incremented by attach_object.
*
- * Note: This may change the type of the node if an explicit store
- * has been performed such that the node/object type has been
- * changed.
+ * Note: This may change the type of the node if an explicit
+ * store has been performed such that the node/object type
+ * has been changed.
*/
- status =
- acpi_ns_attach_object(node, new_desc,
- new_desc->common.type);
+ status = acpi_ns_attach_object(node, new_desc,
+ new_desc->common.type);
ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
"Store %s into %s via Convert/Attach\n",
@@ -484,38 +477,83 @@
}
break;
+ case ACPI_TYPE_BUFFER_FIELD:
+ case ACPI_TYPE_LOCAL_REGION_FIELD:
+ case ACPI_TYPE_LOCAL_BANK_FIELD:
+ case ACPI_TYPE_LOCAL_INDEX_FIELD:
+ /*
+ * For all fields, always write the source data to the target
+ * field. Any required implicit source operand conversion is
+ * performed in the function below as necessary. Note, field
+ * objects must retain their original type permanently.
+ */
+ status = acpi_ex_write_data_to_field(source_desc, target_desc,
+ &walk_state->result_obj);
+ break;
+
default:
-
- ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
- "Storing [%s] (%p) directly into node [%s] (%p)"
- " with no implicit conversion\n",
- acpi_ut_get_object_type_name(source_desc),
- source_desc,
- acpi_ut_get_object_type_name(target_desc),
- node));
-
/*
* No conversions for all other types. Directly store a copy of
- * the source object. NOTE: This is a departure from the ACPI
- * spec, which states "If conversion is impossible, abort the
- * running control method".
+ * the source object. This is the ACPI spec-defined behavior for
+ * the copy_object operator.
*
- * This code implements "If conversion is impossible, treat the
- * Store operation as a CopyObject".
+ * NOTE: For the Store operator, this is a departure from the
+ * ACPI spec, which states "If conversion is impossible, abort
+ * the running control method". Instead, this code implements
+ * "If conversion is impossible, treat the Store operation as
+ * a CopyObject".
*/
- status =
- acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc,
- walk_state);
- if (ACPI_FAILURE(status)) {
- return_ACPI_STATUS(status);
- }
-
- status =
- acpi_ns_attach_object(node, new_desc,
- new_desc->common.type);
- acpi_ut_remove_reference(new_desc);
+ status = acpi_ex_store_direct_to_node(source_desc, node,
+ walk_state);
break;
}
return_ACPI_STATUS(status);
}
+
+/*******************************************************************************
+ *
+ * FUNCTION: acpi_ex_store_direct_to_node
+ *
+ * PARAMETERS: source_desc - Value to be stored
+ * node - Named object to receive the value
+ * walk_state - Current walk state
+ *
+ * RETURN: Status
+ *
+ * DESCRIPTION: "Store" an object directly to a node. This involves a copy
+ * and an attach.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ex_store_direct_to_node(union acpi_operand_object *source_desc,
+ struct acpi_namespace_node *node,
+ struct acpi_walk_state *walk_state)
+{
+ acpi_status status;
+ union acpi_operand_object *new_desc;
+
+ ACPI_FUNCTION_TRACE(ex_store_direct_to_node);
+
+ ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+ "Storing [%s] (%p) directly into node [%s] (%p)"
+ " with no implicit conversion\n",
+ acpi_ut_get_object_type_name(source_desc),
+ source_desc, acpi_ut_get_type_name(node->type),
+ node));
+
+ /* Copy the source object to a new object */
+
+ status =
+ acpi_ut_copy_iobject_to_iobject(source_desc, &new_desc, walk_state);
+ if (ACPI_FAILURE(status)) {
+ return_ACPI_STATUS(status);
+ }
+
+ /* Attach the new object to the node */
+
+ status = acpi_ns_attach_object(node, new_desc, new_desc->common.type);
+ acpi_ut_remove_reference(new_desc);
+ return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 35eebda..09b06e2 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -240,12 +240,14 @@
&acpi_sleep_dispatch[function_id];
#if (!ACPI_REDUCED_HARDWARE)
-
/*
* If the Hardware Reduced flag is set (from the FADT), we must
- * use the extended sleep registers
+ * use the extended sleep registers (FADT). Note: As per the ACPI
+ * specification, these extended registers are to be used for HW-reduced
+ * platforms only. They are not general-purpose replacements for the
+ * legacy PM register sleep support.
*/
- if (acpi_gbl_reduced_hardware || acpi_gbl_FADT.sleep_control.address) {
+ if (acpi_gbl_reduced_hardware) {
status = sleep_functions->extended_function(sleep_state);
} else {
/* Legacy sleep */
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index e4c9291..a63a4cd 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -998,5 +998,11 @@
status = acpi_ut_copy_simple_object(source_desc, *dest_desc);
}
+ /* Delete the allocated object if copy failed */
+
+ if (ACPI_FAILURE(status)) {
+ acpi_ut_remove_reference(*dest_desc);
+ }
+
return_ACPI_STATUS(status);
}
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index b3e36a8..ca6d2aca 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -349,7 +349,7 @@
}
acpi_os_printf("\"");
- for (i = 0; string[i] && (i < max_length); i++) {
+ for (i = 0; (i < max_length) && string[i]; i++) {
/* Escape sequences */
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index e710045..7ae5ebd 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -34,6 +34,7 @@
#include <linux/dmi.h>
#include <linux/slab.h>
#include <linux/suspend.h>
+#include <linux/delay.h>
#include <asm/unaligned.h>
#ifdef CONFIG_ACPI_PROCFS_POWER
@@ -68,6 +69,7 @@
MODULE_DESCRIPTION("ACPI Battery Driver");
MODULE_LICENSE("GPL");
+static int battery_bix_broken_package;
static unsigned int cache_time = 1000;
module_param(cache_time, uint, 0644);
MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -117,6 +119,7 @@
struct acpi_device *device;
struct notifier_block pm_nb;
unsigned long update_time;
+ int revision;
int rate_now;
int capacity_now;
int voltage_now;
@@ -359,6 +362,7 @@
};
static struct acpi_offsets extended_info_offsets[] = {
+ {offsetof(struct acpi_battery, revision), 0},
{offsetof(struct acpi_battery, power_unit), 0},
{offsetof(struct acpi_battery, design_capacity), 0},
{offsetof(struct acpi_battery, full_charge_capacity), 0},
@@ -441,7 +445,12 @@
ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", name));
return -ENODEV;
}
- if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
+
+ if (battery_bix_broken_package)
+ result = extract_package(battery, buffer.pointer,
+ extended_info_offsets + 1,
+ ARRAY_SIZE(extended_info_offsets) - 1);
+ else if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
result = extract_package(battery, buffer.pointer,
extended_info_offsets,
ARRAY_SIZE(extended_info_offsets));
@@ -1062,6 +1071,39 @@
return 0;
}
+static struct dmi_system_id bat_dmi_table[] = {
+ {
+ .ident = "NEC LZ750/LS",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
+ },
+ },
+ {},
+};
+
+/*
+ * Some machines'(E,G Lenovo Z480) ECs are not stable
+ * during boot up and this causes battery driver fails to be
+ * probed due to failure of getting battery information
+ * from EC sometimes. After several retries, the operation
+ * may work. So add retry code here and 20ms sleep between
+ * every retries.
+ */
+static int acpi_battery_update_retry(struct acpi_battery *battery)
+{
+ int retry, ret;
+
+ for (retry = 5; retry; retry--) {
+ ret = acpi_battery_update(battery);
+ if (!ret)
+ break;
+
+ msleep(20);
+ }
+ return ret;
+}
+
static int acpi_battery_add(struct acpi_device *device)
{
int result = 0;
@@ -1081,9 +1123,11 @@
if (ACPI_SUCCESS(acpi_get_handle(battery->device->handle,
"_BIX", &handle)))
set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
- result = acpi_battery_update(battery);
+
+ result = acpi_battery_update_retry(battery);
if (result)
goto fail;
+
#ifdef CONFIG_ACPI_PROCFS_POWER
result = acpi_battery_add_fs(device);
#endif
@@ -1172,6 +1216,8 @@
if (!acpi_battery_dir)
return;
#endif
+ if (dmi_check_system(bat_dmi_table))
+ battery_bix_broken_package = 1;
if (acpi_bus_register_driver(&acpi_battery_driver) < 0) {
#ifdef CONFIG_ACPI_PROCFS_POWER
acpi_unlock_battery_dir(acpi_battery_dir);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index cb96296..76da257 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -327,6 +327,19 @@
DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"),
},
},
+ /*
+ * Without this this EEEpc exports a non working WMI interface, with
+ * this it exports a working "good old" eeepc_laptop interface, fixing
+ * both brightness control, and rfkill not working.
+ */
+ {
+ .callback = dmi_enable_osi_linux,
+ .ident = "Asus EEE PC 1015PX",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"),
+ },
+ },
{}
};
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 292de3c..b62207a 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -33,6 +33,7 @@
#include <linux/proc_fs.h>
#include <linux/acpi.h>
#include <linux/slab.h>
+#include <linux/regulator/machine.h>
#ifdef CONFIG_X86
#include <asm/mpspec.h>
#endif
@@ -56,6 +57,12 @@
#ifdef CONFIG_X86
+#ifdef CONFIG_ACPI_CUSTOM_DSDT
+static inline int set_copy_dsdt(const struct dmi_system_id *id)
+{
+ return 0;
+}
+#else
static int set_copy_dsdt(const struct dmi_system_id *id)
{
printk(KERN_NOTICE "%s detected - "
@@ -63,6 +70,7 @@
acpi_gbl_copy_dsdt_locally = 1;
return 0;
}
+#endif
static struct dmi_system_id dsdt_dmi_table[] __initdata = {
/*
@@ -705,6 +713,14 @@
goto error0;
}
+ /*
+ * If the system is using ACPI then we can be reasonably
+ * confident that any regulators are managed by the firmware
+ * so tell the regulator core it has everything it needs to
+ * know.
+ */
+ regulator_has_full_constraints();
+
return;
error0:
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 31c217a..3e865d2 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -324,14 +324,27 @@
if (result)
return result;
- if (state == ACPI_STATE_UNKNOWN)
+ if (state == ACPI_STATE_UNKNOWN) {
state = ACPI_STATE_D0;
-
- result = acpi_device_set_power(device, state);
- if (!result && state_p)
+ result = acpi_device_set_power(device, state);
+ if (result)
+ return result;
+ } else {
+ if (device->power.flags.power_resources) {
+ /*
+ * We don't need to really switch the state, bu we need
+ * to update the power resources' reference counters.
+ */
+ result = acpi_power_transition(device, state);
+ if (result)
+ return result;
+ }
+ device->power.state = state;
+ }
+ if (state_p)
*state_p = state;
- return result;
+ return 0;
}
EXPORT_SYMBOL_GPL(acpi_bus_update_power);
@@ -952,6 +965,8 @@
acpi_dev_pm_full_power(adev);
__acpi_device_run_wake(adev, false);
}
+
+ dev->pm_domain->detach = acpi_dev_pm_detach;
return 0;
}
EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index edc0081..1ad5a4f 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -175,9 +175,10 @@
static void advance_transaction(struct acpi_ec *ec, u8 status)
{
unsigned long flags;
- struct transaction *t = ec->curr;
+ struct transaction *t;
spin_lock_irqsave(&ec->lock, flags);
+ t = ec->curr;
if (!t)
goto unlock;
if (t->wlen > t->wi) {
@@ -983,6 +984,14 @@
ec_enlarge_storm_threshold, "CLEVO hardware", {
DMI_MATCH(DMI_SYS_VENDOR, "CLEVO Co."),
DMI_MATCH(DMI_PRODUCT_NAME, "M720T/M730T"),}, NULL},
+ {
+ ec_skip_dsdt_scan, "HP Folio 13", {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Folio 13"),}, NULL},
+ {
+ ec_validate_ecdt, "ASUS hardware", {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
{},
};
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 40a84cc..2384120 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -78,32 +78,99 @@
return ret;
}
-static acpi_status do_acpi_find_child(acpi_handle handle, u32 lvl_not_used,
- void *addr_p, void **ret_p)
+static acpi_status acpi_dev_present(acpi_handle handle, u32 lvl_not_used,
+ void *not_used, void **ret_p)
{
- unsigned long long addr;
- acpi_status status;
+ struct acpi_device *adev = NULL;
- status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
- if (ACPI_SUCCESS(status) && addr == *((u64 *)addr_p)) {
+ acpi_bus_get_device(handle, &adev);
+ if (adev) {
*ret_p = handle;
return AE_CTRL_TERMINATE;
}
return AE_OK;
}
-acpi_handle acpi_get_child(acpi_handle parent, u64 address)
+static bool acpi_extra_checks_passed(acpi_handle handle, bool is_bridge)
{
- void *ret = NULL;
+ unsigned long long sta;
+ acpi_status status;
- if (!parent)
- return NULL;
+ status = acpi_bus_get_status_handle(handle, &sta);
+ if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
+ return false;
- acpi_walk_namespace(ACPI_TYPE_DEVICE, parent, 1, NULL,
- do_acpi_find_child, &address, &ret);
- return (acpi_handle)ret;
+ if (is_bridge) {
+ void *test = NULL;
+
+ /* Check if this object has at least one child device. */
+ acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+ acpi_dev_present, NULL, NULL, &test);
+ return !!test;
+ }
+ return true;
}
-EXPORT_SYMBOL(acpi_get_child);
+
+struct find_child_context {
+ u64 addr;
+ bool is_bridge;
+ acpi_handle ret;
+ bool ret_checked;
+};
+
+static acpi_status do_find_child(acpi_handle handle, u32 lvl_not_used,
+ void *data, void **not_used)
+{
+ struct find_child_context *context = data;
+ unsigned long long addr;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &addr);
+ if (ACPI_FAILURE(status) || addr != context->addr)
+ return AE_OK;
+
+ if (!context->ret) {
+ /* This is the first matching object. Save its handle. */
+ context->ret = handle;
+ return AE_OK;
+ }
+ /*
+ * There is more than one matching object with the same _ADR value.
+ * That really is unexpected, so we are kind of beyond the scope of the
+ * spec here. We have to choose which one to return, though.
+ *
+ * First, check if the previously found object is good enough and return
+ * its handle if so. Second, check the same for the object that we've
+ * just found.
+ */
+ if (!context->ret_checked) {
+ if (acpi_extra_checks_passed(context->ret, context->is_bridge))
+ return AE_CTRL_TERMINATE;
+ else
+ context->ret_checked = true;
+ }
+ if (acpi_extra_checks_passed(handle, context->is_bridge)) {
+ context->ret = handle;
+ return AE_CTRL_TERMINATE;
+ }
+ return AE_OK;
+}
+
+acpi_handle acpi_find_child(acpi_handle parent, u64 addr, bool is_bridge)
+{
+ if (parent) {
+ struct find_child_context context = {
+ .addr = addr,
+ .is_bridge = is_bridge,
+ };
+
+ acpi_walk_namespace(ACPI_TYPE_DEVICE, parent, 1, do_find_child,
+ NULL, &context, NULL);
+ return context.ret;
+ }
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(acpi_find_child);
static int acpi_bind_one(struct device *dev, acpi_handle handle)
{
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index c610a76..63a0854 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -50,6 +50,11 @@
#else
static inline void acpi_memory_hotplug_init(void) {}
#endif
+#ifdef CONFIG_X86
+void acpi_cmos_rtc_init(void);
+#else
+static inline void acpi_cmos_rtc_init(void) {}
+#endif
void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
const char *name);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 41c5e1b..f658e09 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -432,6 +432,7 @@
pin_name(pin));
}
+ kfree(entry);
return 0;
}
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index e427dc5..a02a91c 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -63,6 +63,9 @@
.ids = root_device_ids,
.attach = acpi_pci_root_add,
.detach = acpi_pci_root_remove,
+ .hotplug = {
+ .ignore = true,
+ },
};
/* Lock to protect both acpi_pci_roots lists */
@@ -614,9 +617,12 @@
ej_event->device = device;
ej_event->event = ACPI_NOTIFY_EJECT_REQUEST;
+ get_device(&device->dev);
status = acpi_os_hotplug_execute(acpi_bus_hot_remove_device, ej_event);
- if (ACPI_FAILURE(status))
+ if (ACPI_FAILURE(status)) {
+ put_device(&device->dev);
kfree(ej_event);
+ }
}
static void _handle_hotplug_event_root(struct work_struct *work)
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index aa1227a..04a1378 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -311,6 +311,8 @@
dev->pnp.bus_id,
(u32) dev->wakeup.sleep_state);
+ mutex_lock(&dev->physical_node_lock);
+
if (!dev->physical_node_count) {
seq_printf(seq, "%c%-8s\n",
dev->wakeup.flags.run_wake ? '*' : ' ',
@@ -338,6 +340,8 @@
put_device(ldev);
}
}
+
+ mutex_unlock(&dev->physical_node_lock);
}
mutex_unlock(&acpi_device_lock);
return 0;
@@ -347,12 +351,16 @@
{
struct acpi_device_physical_node *entry;
+ mutex_lock(&adev->physical_node_lock);
+
list_for_each_entry(entry,
&adev->physical_node_list, node)
if (entry->dev && device_can_wakeup(entry->dev)) {
bool enable = !device_may_wakeup(entry->dev);
device_set_wakeup_enable(entry->dev, enable);
}
+
+ mutex_unlock(&adev->physical_node_lock);
}
static ssize_t
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index eb133c7..c991fe68 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -121,17 +121,10 @@
*/
static void acpi_safe_halt(void)
{
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we
- * test NEED_RESCHED:
- */
- smp_mb();
- if (!need_resched()) {
+ if (!tif_need_resched()) {
safe_halt();
local_irq_disable();
}
- current_thread_info()->status |= TS_POLLING;
}
#ifdef ARCH_APICTIMER_STOPS_ON_C3
@@ -739,6 +732,11 @@
if (unlikely(!pr))
return -EINVAL;
+ if (cx->entry_method == ACPI_CSTATE_FFH) {
+ if (current_set_polling_and_test())
+ return -EINVAL;
+ }
+
lapic_timer_state_broadcast(pr, cx, 1);
acpi_idle_do_entry(cx);
@@ -792,18 +790,9 @@
if (unlikely(!pr))
return -EINVAL;
- if (cx->entry_method != ACPI_CSTATE_FFH) {
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we test
- * NEED_RESCHED:
- */
- smp_mb();
-
- if (unlikely(need_resched())) {
- current_thread_info()->status |= TS_POLLING;
+ if (cx->entry_method == ACPI_CSTATE_FFH) {
+ if (current_set_polling_and_test())
return -EINVAL;
- }
}
/*
@@ -821,9 +810,6 @@
sched_clock_idle_wakeup_event(0);
- if (cx->entry_method != ACPI_CSTATE_FFH)
- current_thread_info()->status |= TS_POLLING;
-
lapic_timer_state_broadcast(pr, cx, 0);
return index;
}
@@ -860,18 +846,9 @@
}
}
- if (cx->entry_method != ACPI_CSTATE_FFH) {
- current_thread_info()->status &= ~TS_POLLING;
- /*
- * TS_POLLING-cleared state must be visible before we test
- * NEED_RESCHED:
- */
- smp_mb();
-
- if (unlikely(need_resched())) {
- current_thread_info()->status |= TS_POLLING;
+ if (cx->entry_method == ACPI_CSTATE_FFH) {
+ if (current_set_polling_and_test())
return -EINVAL;
- }
}
acpi_unlazy_tlb(smp_processor_id());
@@ -917,9 +894,6 @@
sched_clock_idle_wakeup_event(0);
- if (cx->entry_method != ACPI_CSTATE_FFH)
- current_thread_info()->status |= TS_POLLING;
-
lapic_timer_state_broadcast(pr, cx, 0);
return index;
}
@@ -1004,7 +978,7 @@
return -EINVAL;
drv->safe_state_index = -1;
- for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
+ for (i = CPUIDLE_DRIVER_STATE_START; i < CPUIDLE_STATE_MAX; i++) {
drv->states[i].name[0] = '\0';
drv->states[i].desc[0] = '\0';
}
@@ -1127,9 +1101,9 @@
if (pr->id == 0 && cpuidle_get_driver() == &acpi_idle_driver) {
- cpuidle_pause_and_lock();
/* Protect against cpu-hotplug */
get_online_cpus();
+ cpuidle_pause_and_lock();
/* Disable all cpuidle devices */
for_each_online_cpu(cpu) {
@@ -1156,8 +1130,8 @@
cpuidle_enable_device(dev);
}
}
- put_online_cpus();
cpuidle_resume_and_unlock();
+ put_online_cpus();
}
return 0;
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index e7dd2c1..5e47d7b 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -59,6 +59,12 @@
int target_state; /* target T-state */
};
+struct acpi_processor_throttling_arg {
+ struct acpi_processor *pr;
+ int target_state;
+ bool force;
+};
+
#define THROTTLING_PRECHANGE (1)
#define THROTTLING_POSTCHANGE (2)
@@ -1063,16 +1069,24 @@
return 0;
}
+static long acpi_processor_throttling_fn(void *data)
+{
+ struct acpi_processor_throttling_arg *arg = data;
+ struct acpi_processor *pr = arg->pr;
+
+ return pr->throttling.acpi_processor_set_throttling(pr,
+ arg->target_state, arg->force);
+}
+
int acpi_processor_set_throttling(struct acpi_processor *pr,
int state, bool force)
{
- cpumask_var_t saved_mask;
int ret = 0;
unsigned int i;
struct acpi_processor *match_pr;
struct acpi_processor_throttling *p_throttling;
+ struct acpi_processor_throttling_arg arg;
struct throttling_tstate t_state;
- cpumask_var_t online_throttling_cpus;
if (!pr)
return -EINVAL;
@@ -1083,14 +1097,6 @@
if ((state < 0) || (state > (pr->throttling.state_count - 1)))
return -EINVAL;
- if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
- return -ENOMEM;
-
- if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
- free_cpumask_var(saved_mask);
- return -ENOMEM;
- }
-
if (cpu_is_offline(pr->id)) {
/*
* the cpu pointed by pr->id is offline. Unnecessary to change
@@ -1099,17 +1105,15 @@
return -ENODEV;
}
- cpumask_copy(saved_mask, ¤t->cpus_allowed);
t_state.target_state = state;
p_throttling = &(pr->throttling);
- cpumask_and(online_throttling_cpus, cpu_online_mask,
- p_throttling->shared_cpu_map);
+
/*
* The throttling notifier will be called for every
* affected cpu in order to get one proper T-state.
* The notifier event is THROTTLING_PRECHANGE.
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
t_state.cpu = i;
acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
&t_state);
@@ -1121,21 +1125,18 @@
* it can be called only for the cpu pointed by pr.
*/
if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
- /* FIXME: use work_on_cpu() */
- if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
- /* Can't migrate to the pr->id CPU. Exit */
- ret = -ENODEV;
- goto exit;
- }
- ret = p_throttling->acpi_processor_set_throttling(pr,
- t_state.target_state, force);
+ arg.pr = pr;
+ arg.target_state = state;
+ arg.force = force;
+ ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
} else {
/*
* When the T-state coordination is SW_ALL or HW_ALL,
* it is necessary to set T-state for every affected
* cpus.
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask,
+ p_throttling->shared_cpu_map) {
match_pr = per_cpu(processors, i);
/*
* If the pointer is invalid, we will report the
@@ -1156,13 +1157,12 @@
"on CPU %d\n", i));
continue;
}
- t_state.cpu = i;
- /* FIXME: use work_on_cpu() */
- if (set_cpus_allowed_ptr(current, cpumask_of(i)))
- continue;
- ret = match_pr->throttling.
- acpi_processor_set_throttling(
- match_pr, t_state.target_state, force);
+
+ arg.pr = match_pr;
+ arg.target_state = state;
+ arg.force = force;
+ ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
+ &arg);
}
}
/*
@@ -1171,17 +1171,12 @@
* affected cpu to update the T-states.
* The notifier event is THROTTLING_POSTCHANGE
*/
- for_each_cpu(i, online_throttling_cpus) {
+ for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) {
t_state.cpu = i;
acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
&t_state);
}
- /* restore the previous state */
- /* FIXME: use work_on_cpu() */
- set_cpus_allowed_ptr(current, saved_mask);
-exit:
- free_cpumask_var(online_throttling_cpus);
- free_cpumask_var(saved_mask);
+
return ret;
}
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3322b47..b9cfaf1 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,18 +77,24 @@
switch (ares->type) {
case ACPI_RESOURCE_TYPE_MEMORY24:
memory24 = &ares->data.memory24;
+ if (!memory24->minimum && !memory24->address_length)
+ return false;
acpi_dev_get_memresource(res, memory24->minimum,
memory24->address_length,
memory24->write_protect);
break;
case ACPI_RESOURCE_TYPE_MEMORY32:
memory32 = &ares->data.memory32;
+ if (!memory32->minimum && !memory32->address_length)
+ return false;
acpi_dev_get_memresource(res, memory32->minimum,
memory32->address_length,
memory32->write_protect);
break;
case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
fixed_memory32 = &ares->data.fixed_memory32;
+ if (!fixed_memory32->address && !fixed_memory32->address_length)
+ return false;
acpi_dev_get_memresource(res, fixed_memory32->address,
fixed_memory32->address_length,
fixed_memory32->write_protect);
@@ -144,12 +150,16 @@
switch (ares->type) {
case ACPI_RESOURCE_TYPE_IO:
io = &ares->data.io;
+ if (!io->minimum && !io->address_length)
+ return false;
acpi_dev_get_ioresource(res, io->minimum,
io->address_length,
io->io_decode);
break;
case ACPI_RESOURCE_TYPE_FIXED_IO:
fixed_io = &ares->data.fixed_io;
+ if (!fixed_io->address && !fixed_io->address_length)
+ return false;
acpi_dev_get_ioresource(res, fixed_io->address,
fixed_io->address_length,
ACPI_DECODE_10);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 27da630..091682f 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -237,13 +237,13 @@
mutex_lock(&acpi_scan_lock);
- acpi_bus_get_device(handle, &device);
- if (device) {
- dev_warn(&device->dev, "Attempt to re-insert\n");
- goto out;
+ if (ost_source != ACPI_NOTIFY_BUS_CHECK) {
+ acpi_bus_get_device(handle, &device);
+ if (device) {
+ dev_warn(&device->dev, "Attempt to re-insert\n");
+ goto out;
+ }
}
- acpi_evaluate_hotplug_ost(handle, ost_source,
- ACPI_OST_SC_INSERT_IN_PROGRESS, NULL);
error = acpi_bus_scan(handle);
if (error) {
acpi_handle_warn(handle, "Namespace scan failure\n");
@@ -769,12 +769,17 @@
device->driver->ops.notify(device, event);
}
-static acpi_status acpi_device_notify_fixed(void *data)
+static void acpi_device_notify_fixed(void *data)
{
struct acpi_device *device = data;
/* Fixed hardware devices have no handles */
acpi_device_notify(NULL, ACPI_FIXED_HARDWARE_EVENT, device);
+}
+
+static acpi_status acpi_device_fixed_event(void *data)
+{
+ acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_device_notify_fixed, data);
return AE_OK;
}
@@ -785,12 +790,12 @@
if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
status =
acpi_install_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
- acpi_device_notify_fixed,
+ acpi_device_fixed_event,
device);
else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
status =
acpi_install_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
- acpi_device_notify_fixed,
+ acpi_device_fixed_event,
device);
else
status = acpi_install_notify_handler(device->handle,
@@ -807,10 +812,10 @@
{
if (device->device_type == ACPI_BUS_TYPE_POWER_BUTTON)
acpi_remove_fixed_event_handler(ACPI_EVENT_POWER_BUTTON,
- acpi_device_notify_fixed);
+ acpi_device_fixed_event);
else if (device->device_type == ACPI_BUS_TYPE_SLEEP_BUTTON)
acpi_remove_fixed_event_handler(ACPI_EVENT_SLEEP_BUTTON,
- acpi_device_notify_fixed);
+ acpi_device_fixed_event);
else
acpi_remove_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
acpi_device_notify);
@@ -1790,7 +1795,7 @@
*/
list_for_each_entry(hwid, &pnp.ids, list) {
handler = acpi_scan_match_handler(hwid->id, NULL);
- if (handler) {
+ if (handler && !handler->hotplug.ignore) {
acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
acpi_hotplug_notify_cb, handler);
break;
@@ -1890,6 +1895,9 @@
if (acpi_bus_get_device(handle, &device))
return AE_CTRL_DEPTH;
+ if (device->handler)
+ return AE_OK;
+
ret = acpi_scan_attach_handler(device);
if (ret)
return ret > 0 ? AE_OK : AE_CTRL_DEPTH;
@@ -2040,6 +2048,7 @@
acpi_pci_link_init();
acpi_platform_init();
acpi_lpss_init();
+ acpi_cmos_rtc_init();
acpi_container_init();
acpi_memory_hotplug_init();
acpi_dock_init();
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9c1a435..035920f 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -78,6 +78,17 @@
return 0;
}
+static bool acpi_sleep_state_supported(u8 sleep_state)
+{
+ acpi_status status;
+ u8 type_a, type_b;
+
+ status = acpi_get_sleep_type_data(sleep_state, &type_a, &type_b);
+ return ACPI_SUCCESS(status) && (!acpi_gbl_reduced_hardware
+ || (acpi_gbl_FADT.sleep_control.address
+ && acpi_gbl_FADT.sleep_status.address));
+}
+
#ifdef CONFIG_ACPI_SLEEP
static u32 acpi_target_sleep_state = ACPI_STATE_S0;
@@ -600,15 +611,9 @@
{
int i;
- for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++) {
- acpi_status status;
- u8 type_a, type_b;
-
- status = acpi_get_sleep_type_data(i, &type_a, &type_b);
- if (ACPI_SUCCESS(status)) {
+ for (i = ACPI_STATE_S1; i < ACPI_STATE_S4; i++)
+ if (acpi_sleep_state_supported(i))
sleep_states[i] = 1;
- }
- }
suspend_set_ops(old_suspend_ordering ?
&acpi_suspend_ops_old : &acpi_suspend_ops);
@@ -739,11 +744,7 @@
static void acpi_sleep_hibernate_setup(void)
{
- acpi_status status;
- u8 type_a, type_b;
-
- status = acpi_get_sleep_type_data(ACPI_STATE_S4, &type_a, &type_b);
- if (ACPI_FAILURE(status))
+ if (!acpi_sleep_state_supported(ACPI_STATE_S4))
return;
hibernation_set_ops(old_suspend_ordering ?
@@ -792,8 +793,6 @@
int __init acpi_sleep_init(void)
{
- acpi_status status;
- u8 type_a, type_b;
char supported[ACPI_S_STATE_COUNT * 3 + 1];
char *pos = supported;
int i;
@@ -808,8 +807,7 @@
acpi_sleep_suspend_setup();
acpi_sleep_hibernate_setup();
- status = acpi_get_sleep_type_data(ACPI_STATE_S5, &type_a, &type_b);
- if (ACPI_SUCCESS(status)) {
+ if (acpi_sleep_state_supported(ACPI_STATE_S5)) {
sleep_states[ACPI_STATE_S5] = 1;
pm_power_off_prepare = acpi_power_off_prepare;
pm_power_off = acpi_power_off;
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 440eadf..0dc9ff6 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -450,6 +450,14 @@
},
{
.callback = video_ignore_initial_backlight,
+ .ident = "Fujitsu E753",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E753"),
+ },
+ },
+ {
+ .callback = video_ignore_initial_backlight,
.ident = "HP Pavilion dm4",
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
@@ -725,6 +733,7 @@
union acpi_object *o;
struct acpi_video_device_brightness *br = NULL;
int result = -EINVAL;
+ u32 value;
if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device, &obj))) {
ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available "
@@ -755,7 +764,12 @@
printk(KERN_ERR PREFIX "Invalid data\n");
continue;
}
- br->levels[count] = (u32) o->integer.value;
+ value = (u32) o->integer.value;
+ /* Skip duplicate entries */
+ if (count > 2 && br->levels[count - 1] == value)
+ continue;
+
+ br->levels[count] = value;
if (br->levels[count] > max_level)
max_level = br->levels[count];
@@ -838,7 +852,7 @@
for (i = 2; i < br->count; i++)
if (level_old == br->levels[i])
break;
- if (i == br->count)
+ if (i == br->count || !level)
level = max_level;
}
@@ -1939,6 +1953,17 @@
static int __init acpi_video_init(void)
{
+ /*
+ * Let the module load even if ACPI is disabled (e.g. due to
+ * a broken BIOS) so that i915.ko can still be loaded on such
+ * old systems without an AcpiOpRegion.
+ *
+ * acpi_video_register() will report -ENODEV later as well due
+ * to acpi_disabled when i915.ko tries to register itself afterwards.
+ */
+ if (acpi_disabled)
+ return 0;
+
dmi_check_system(video_dmi_table);
if (intel_opregion_present())
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index cdbad3a..4144a3a 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -506,7 +506,7 @@
amba_put_disable_pclk(dev);
- if (cid == AMBA_CID)
+ if (cid == AMBA_CID || cid == CORESIGHT_CID)
dev->periphid = pid;
if (!dev->periphid)
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index a5a3ebc..78eabff 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -107,7 +107,7 @@
If unsure, say N.
config SATA_INIC162X
- tristate "Initio 162x SATA support"
+ tristate "Initio 162x SATA support (Very Experimental)"
depends on PCI
help
This option enables support for Initio 162x Serial ATA.
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 2b50dfd..9064a2f 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -61,6 +61,8 @@
/* board IDs by feature in alphabetical order */
board_ahci,
board_ahci_ign_iferr,
+ board_ahci_nomsi,
+ board_ahci_noncq,
board_ahci_nosntf,
board_ahci_yes_fbs,
@@ -119,6 +121,20 @@
.udma_mask = ATA_UDMA6,
.port_ops = &ahci_ops,
},
+ [board_ahci_nomsi] = {
+ AHCI_HFLAGS (AHCI_HFLAG_NO_MSI),
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_ops,
+ },
+ [board_ahci_noncq] = {
+ AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ),
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_ops,
+ },
[board_ahci_nosntf] = {
AHCI_HFLAGS (AHCI_HFLAG_NO_SNTF),
.flags = AHCI_FLAG_COMMON,
@@ -291,6 +307,27 @@
{ PCI_VDEVICE(INTEL, 0x8d64), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x8d66), board_ahci }, /* Wellsburg RAID */
{ PCI_VDEVICE(INTEL, 0x8d6e), board_ahci }, /* Wellsburg RAID */
+ { PCI_VDEVICE(INTEL, 0x23a3), board_ahci }, /* Coleto Creek AHCI */
+ { PCI_VDEVICE(INTEL, 0x9c83), board_ahci }, /* Wildcat Point-LP AHCI */
+ { PCI_VDEVICE(INTEL, 0x9c85), board_ahci }, /* Wildcat Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0x9c87), board_ahci }, /* Wildcat Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0x9c8f), board_ahci }, /* Wildcat Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0x8c82), board_ahci }, /* 9 Series AHCI */
+ { PCI_VDEVICE(INTEL, 0x8c83), board_ahci }, /* 9 Series AHCI */
+ { PCI_VDEVICE(INTEL, 0x8c84), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x8c85), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x8c86), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */
+ { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
+ { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
+ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -310,6 +347,7 @@
/* AMD */
{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
+ { PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
/* AMD is using RAID class only for ahci controllers */
{ PCI_VENDOR_ID_AMD, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
PCI_CLASS_STORAGE_RAID << 8, 0xffffff, board_ahci },
@@ -421,17 +459,29 @@
.driver_data = board_ahci_yes_fbs }, /* 88se9128 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9125),
.driver_data = board_ahci_yes_fbs }, /* 88se9125 */
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_MARVELL_EXT, 0x9178,
+ PCI_VENDOR_ID_MARVELL_EXT, 0x9170),
+ .driver_data = board_ahci_yes_fbs }, /* 88se9170 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a),
.driver_data = board_ahci_yes_fbs }, /* 88se9172 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172),
+ .driver_data = board_ahci_yes_fbs }, /* 88se9182 */
+ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9182),
.driver_data = board_ahci_yes_fbs }, /* 88se9172 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192),
.driver_data = board_ahci_yes_fbs }, /* 88se9172 on some Gigabyte */
+ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0),
+ .driver_data = board_ahci_yes_fbs },
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
.driver_data = board_ahci_yes_fbs },
+ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
+ .driver_data = board_ahci_yes_fbs },
+ { PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642),
+ .driver_data = board_ahci_yes_fbs },
/* Promise */
{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */
+ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */
/* Asmedia */
{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */
@@ -439,6 +489,13 @@
{ PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */
{ PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */
+ /*
+ * Samsung SSDs found on some macbooks. NCQ times out if MSI is
+ * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731
+ */
+ { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi },
+ { PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi },
+
/* Enmotus */
{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 9a8a674..82aa7b5 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -330,7 +330,7 @@
/* SATA Controller IDE (Wellsburg) */
{ 0x8086, 0x8d00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
/* SATA Controller IDE (Wellsburg) */
- { 0x8086, 0x8d08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+ { 0x8086, 0x8d08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
/* SATA Controller IDE (Wellsburg) */
{ 0x8086, 0x8d60, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
/* SATA Controller IDE (Wellsburg) */
@@ -338,6 +338,16 @@
/* SATA Controller IDE (BayTrail) */
{ 0x8086, 0x0F20, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt },
{ 0x8086, 0x0F21, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_byt },
+ /* SATA Controller IDE (Coleto Creek) */
+ { 0x8086, 0x23a6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata },
+ /* SATA Controller IDE (9 Series) */
+ { 0x8086, 0x8c88, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+ /* SATA Controller IDE (9 Series) */
+ { 0x8086, 0x8c89, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata_snb },
+ /* SATA Controller IDE (9 Series) */
+ { 0x8086, 0x8c80, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
+ /* SATA Controller IDE (9 Series) */
+ { 0x8086, 0x8c81, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb },
{ } /* terminate list */
};
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index a70ff15..8905e03 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1266,9 +1266,11 @@
{
struct ata_port *ap = link->ap;
struct ahci_host_priv *hpriv = ap->host->private_data;
+ struct ahci_port_priv *pp = ap->private_data;
const char *reason = NULL;
unsigned long now, msecs;
struct ata_taskfile tf;
+ bool fbs_disabled = false;
int rc;
DPRINTK("ENTER\n");
@@ -1278,6 +1280,16 @@
if (rc && rc != -EOPNOTSUPP)
ata_link_warn(link, "failed to reset engine (errno=%d)\n", rc);
+ /*
+ * According to AHCI-1.2 9.3.9: if FBS is enable, software shall
+ * clear PxFBS.EN to '0' prior to issuing software reset to devices
+ * that is attached to port multiplier.
+ */
+ if (!ata_is_host_link(link) && pp->fbs_enabled) {
+ ahci_disable_fbs(ap);
+ fbs_disabled = true;
+ }
+
ata_tf_init(link->device, &tf);
/* issue the first D2H Register FIS */
@@ -1318,6 +1330,10 @@
} else
*class = ahci_dev_classify(ap);
+ /* re-enable FBS if disabled before */
+ if (fbs_disabled)
+ ahci_enable_fbs(ap);
+
DPRINTK("EXIT, class=%u\n", *class);
return 0;
@@ -1560,8 +1576,7 @@
u32 fbs = readl(port_mmio + PORT_FBS);
int pmp = fbs >> PORT_FBS_DWE_OFFSET;
- if ((fbs & PORT_FBS_SDE) && (pmp < ap->nr_pmp_links) &&
- ata_link_online(&ap->pmp_link[pmp])) {
+ if ((fbs & PORT_FBS_SDE) && (pmp < ap->nr_pmp_links)) {
link = &ap->pmp_link[pmp];
fbs_need_dec = true;
}
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index adf002a3..ca7c23d 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2199,6 +2199,16 @@
if (rc)
return rc;
+ /* some WD SATA-1 drives have issues with LPM, turn on NOLPM for them */
+ if ((dev->horkage & ATA_HORKAGE_WD_BROKEN_LPM) &&
+ (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
+ dev->horkage |= ATA_HORKAGE_NOLPM;
+
+ if (dev->horkage & ATA_HORKAGE_NOLPM) {
+ ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
+ dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
+ }
+
/* let ACPI work its magic */
rc = ata_acpi_on_devcfg(dev);
if (rc)
@@ -2401,7 +2411,7 @@
cdb_intr_string = ", CDB intr";
}
- if (atapi_dmadir || atapi_id_dmadir(dev->id)) {
+ if (atapi_dmadir || (dev->horkage & ATA_HORKAGE_ATAPI_DMADIR) || atapi_id_dmadir(dev->id)) {
dev->flags |= ATA_DFLAG_DMADIR;
dma_dir_string = ", DMADIR";
}
@@ -4110,6 +4120,7 @@
{ "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 },
{ "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA },
{ "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 },
+ { "Slimtype DVD A DS8A9SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 },
/* Devices we expect to fail diagnostics */
@@ -4139,6 +4150,10 @@
{ "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ |
ATA_HORKAGE_FIRMWARE_WARN },
+ /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+ { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA },
+ { "ST1000LM024 HN-M101MBB", "2BA30001", ATA_HORKAGE_BROKEN_FPDMA_AA },
+
/* Blacklist entries taken from Silicon Image 3124/3132
Windows driver .inf file - also several Linux problem reports */
{ "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, },
@@ -4185,6 +4200,23 @@
{ "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER },
{ "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER },
+ /*
+ * Some WD SATA-I drives spin up and down erratically when the link
+ * is put into the slumber mode. We don't have full list of the
+ * affected devices. Disable LPM if the device matches one of the
+ * known prefixes and is SATA-1. As a side effect LPM partial is
+ * lost too.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=57211
+ */
+ { "WDC WD800JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD1200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD1600JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD2000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD2500JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+ { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM },
+
/* End Marker */
{ }
};
@@ -4726,6 +4758,10 @@
* ata_qc_new - Request an available ATA command, for queueing
* @ap: target port
*
+ * Some ATA host controllers may implement a queue depth which is less
+ * than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ * the hardware limitation.
+ *
* LOCKING:
* None.
*/
@@ -4733,21 +4769,27 @@
static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
{
struct ata_queued_cmd *qc = NULL;
- unsigned int i;
+ unsigned int max_queue = ap->host->n_tags;
+ unsigned int i, tag;
/* no command while frozen */
if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
return NULL;
- /* the last tag is reserved for internal command. */
- for (i = 0; i < ATA_MAX_QUEUE - 1; i++)
- if (!test_and_set_bit(i, &ap->qc_allocated)) {
- qc = __ata_qc_from_tag(ap, i);
+ for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+ tag = tag < max_queue ? tag : 0;
+
+ /* the last tag is reserved for internal command. */
+ if (tag == ATA_TAG_INTERNAL)
+ continue;
+
+ if (!test_and_set_bit(tag, &ap->qc_allocated)) {
+ qc = __ata_qc_from_tag(ap, tag);
+ qc->tag = tag;
+ ap->last_tag = tag;
break;
}
-
- if (qc)
- qc->tag = i;
+ }
return qc;
}
@@ -6036,6 +6078,7 @@
{
spin_lock_init(&host->lock);
mutex_init(&host->eh_mutex);
+ host->n_tags = ATA_MAX_QUEUE - 1;
host->dev = dev;
host->ops = ops;
}
@@ -6117,6 +6160,8 @@
{
int i, rc;
+ host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
/* host must have been started */
if (!(host->flags & ATA_HOST_STARTED)) {
dev_err(host->dev, "BUG: trying to register unstarted host\n");
@@ -6263,6 +6308,8 @@
static void ata_port_detach(struct ata_port *ap)
{
unsigned long flags;
+ struct ata_link *link;
+ struct ata_device *dev;
if (!ap->ops->error_handler)
goto skip_eh;
@@ -6282,6 +6329,13 @@
cancel_delayed_work_sync(&ap->hotplug_task);
skip_eh:
+ /* clean up zpodd on port removal */
+ ata_for_each_link(link, ap, HOST_FIRST) {
+ ata_for_each_dev(dev, link, ALL) {
+ if (zpodd_dev_enabled(dev))
+ zpodd_exit(dev);
+ }
+ }
if (ap->pmp_link) {
int i;
for (i = 0; i < SATA_PMP_MAX_PORTS; i++)
@@ -6502,6 +6556,8 @@
{ "nosrst", .lflags = ATA_LFLAG_NO_SRST },
{ "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST },
{ "rstonce", .lflags = ATA_LFLAG_RST_ONCE },
+ { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR },
+ { "disable", .horkage_on = ATA_HORKAGE_DISABLE },
};
char *start = *cur, *p = *cur;
char *id, *val, *endp;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index c69fcce..370462f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1322,14 +1322,14 @@
* should be retried. To be used from EH.
*
* SCSI midlayer limits the number of retries to scmd->allowed.
- * scmd->retries is decremented for commands which get retried
+ * scmd->allowed is incremented for commands which get retried
* due to unrelated failures (qc->err_mask is zero).
*/
void ata_eh_qc_retry(struct ata_queued_cmd *qc)
{
struct scsi_cmnd *scmd = qc->scsicmd;
- if (!qc->err_mask && scmd->retries)
- scmd->retries--;
+ if (!qc->err_mask)
+ scmd->allowed++;
__ata_eh_qc_complete(qc);
}
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 61c59ee..7ccc084 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -289,24 +289,24 @@
/* Disable sending Early R_OK.
* With "cached read" HDD testing and multiple ports busy on a SATA
- * host controller, 3726 PMP will very rarely drop a deferred
+ * host controller, 3x26 PMP will very rarely drop a deferred
* R_OK that was intended for the host. Symptom will be all
* 5 drives under test will timeout, get reset, and recover.
*/
- if (vendor == 0x1095 && devid == 0x3726) {
+ if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
u32 reg;
err_mask = sata_pmp_read(&ap->link, PMP_GSCR_SII_POL, ®);
if (err_mask) {
rc = -EIO;
- reason = "failed to read Sil3726 Private Register";
+ reason = "failed to read Sil3x26 Private Register";
goto fail;
}
reg &= ~0x1;
err_mask = sata_pmp_write(&ap->link, PMP_GSCR_SII_POL, reg);
if (err_mask) {
rc = -EIO;
- reason = "failed to write Sil3726 Private Register";
+ reason = "failed to write Sil3x26 Private Register";
goto fail;
}
}
@@ -383,15 +383,19 @@
u16 devid = sata_pmp_gscr_devid(gscr);
struct ata_link *link;
- if (vendor == 0x1095 && devid == 0x3726) {
- /* sil3726 quirks */
+ if (vendor == 0x1095 && (devid == 0x3726 || devid == 0x3826)) {
+ /* sil3x26 quirks */
ata_for_each_link(link, ap, EDGE) {
/* link reports offline after LPM */
link->flags |= ATA_LFLAG_NO_LPM;
- /* Class code report is unreliable. */
+ /*
+ * Class code report is unreliable and SRST times
+ * out under certain configurations.
+ */
if (link->pmp < 5)
- link->flags |= ATA_LFLAG_ASSUME_ATA;
+ link->flags |= ATA_LFLAG_NO_SRST |
+ ATA_LFLAG_ASSUME_ATA;
/* port 5 is for SEMB device and it doesn't like SRST */
if (link->pmp == 5)
@@ -399,20 +403,17 @@
ATA_LFLAG_ASSUME_SEMB;
}
} else if (vendor == 0x1095 && devid == 0x4723) {
- /* sil4723 quirks */
- ata_for_each_link(link, ap, EDGE) {
- /* link reports offline after LPM */
- link->flags |= ATA_LFLAG_NO_LPM;
-
- /* class code report is unreliable */
- if (link->pmp < 2)
- link->flags |= ATA_LFLAG_ASSUME_ATA;
-
- /* the config device at port 2 locks up on SRST */
- if (link->pmp == 2)
- link->flags |= ATA_LFLAG_NO_SRST |
- ATA_LFLAG_ASSUME_ATA;
- }
+ /*
+ * sil4723 quirks
+ *
+ * Link reports offline after LPM. Class code report is
+ * unreliable. SIMG PMPs never got SRST reliable and the
+ * config device at port 2 locks up on SRST.
+ */
+ ata_for_each_link(link, ap, EDGE)
+ link->flags |= ATA_LFLAG_NO_LPM |
+ ATA_LFLAG_NO_SRST |
+ ATA_LFLAG_ASSUME_ATA;
} else if (vendor == 0x1095 && devid == 0x4726) {
/* sil4726 quirks */
ata_for_each_link(link, ap, EDGE) {
@@ -446,8 +447,11 @@
* otherwise. Don't try hard to recover it.
*/
ap->pmp_link[ap->nr_pmp_links - 1].flags |= ATA_LFLAG_NO_RETRY;
- } else if (vendor == 0x197b && devid == 0x2352) {
- /* chip found in Thermaltake BlackX Duet, jmicron JMB350? */
+ } else if (vendor == 0x197b && (devid == 0x2352 || devid == 0x0325)) {
+ /*
+ * 0x2352: found in Thermaltake BlackX Duet, jmicron JMB350?
+ * 0x0325: jmicron JMB394.
+ */
ata_for_each_link(link, ap, EDGE) {
/* SRST breaks detection and disks get misclassified
* LPM disabled to avoid potential problems
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 0101af5..9933b4d 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -112,12 +112,14 @@
[ATA_LPM_MIN_POWER] = "min_power",
};
-static ssize_t ata_scsi_lpm_store(struct device *dev,
+static ssize_t ata_scsi_lpm_store(struct device *device,
struct device_attribute *attr,
const char *buf, size_t count)
{
- struct Scsi_Host *shost = class_to_shost(dev);
+ struct Scsi_Host *shost = class_to_shost(device);
struct ata_port *ap = ata_shost_to_port(shost);
+ struct ata_link *link;
+ struct ata_device *dev;
enum ata_lpm_policy policy;
unsigned long flags;
@@ -133,10 +135,20 @@
return -EINVAL;
spin_lock_irqsave(ap->lock, flags);
+
+ ata_for_each_link(link, ap, EDGE) {
+ ata_for_each_dev(dev, &ap->link, ENABLED) {
+ if (dev->horkage & ATA_HORKAGE_NOLPM) {
+ count = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+ }
+ }
+
ap->target_lpm_policy = policy;
ata_port_schedule_eh(ap);
+out_unlock:
spin_unlock_irqrestore(ap->lock, flags);
-
return count;
}
@@ -3614,6 +3626,7 @@
shost->max_lun = 1;
shost->max_channel = 1;
shost->max_cmd_len = 16;
+ shost->no_write_same = 1;
/* Schedule policy is determined by ->qc_defer()
* callback and it needs to see every deferred qc.
@@ -3863,6 +3876,27 @@
return;
}
+ /*
+ * XXX - UGLY HACK
+ *
+ * The block layer suspend/resume path is fundamentally broken due
+ * to freezable kthreads and workqueue and may deadlock if a block
+ * device gets removed while resume is in progress. I don't know
+ * what the solution is short of removing freezable kthreads and
+ * workqueues altogether.
+ *
+ * The following is an ugly hack to avoid kicking off device
+ * removal while freezer is active. This is a joke but does avoid
+ * this particular deadlock scenario.
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=62801
+ * http://marc.info/?l=linux-kernel&m=138695698516487
+ */
+#ifdef CONFIG_FREEZER
+ while (pm_freezing)
+ msleep(10);
+#endif
+
DPRINTK("ENTER\n");
mutex_lock(&ap->scsi_scan_mutex);
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index b603720..136803c 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -1333,7 +1333,19 @@
DPRINTK("ENTER\n");
cancel_delayed_work_sync(&ap->sff_pio_task);
+
+ /*
+ * We wanna reset the HSM state to IDLE. If we do so without
+ * grabbing the port lock, critical sections protected by it which
+ * expect the HSM state to stay stable may get surprised. For
+ * example, we may set IDLE in between the time
+ * __ata_sff_port_intr() checks for HSM_ST_IDLE and before it calls
+ * ata_sff_hsm_move() causing ata_sff_hsm_move() to BUG().
+ */
+ spin_lock_irq(ap->lock);
ap->hsm_task_state = HSM_ST_IDLE;
+ spin_unlock_irq(ap->lock);
+
ap->sff_pio_task_link = NULL;
if (ata_msg_ctl(ap))
@@ -2008,13 +2020,15 @@
DPRINTK("ata%u: bus reset via SRST\n", ap->print_id);
- /* software reset. causes dev0 to be selected */
- iowrite8(ap->ctl, ioaddr->ctl_addr);
- udelay(20); /* FIXME: flush */
- iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
- udelay(20); /* FIXME: flush */
- iowrite8(ap->ctl, ioaddr->ctl_addr);
- ap->last_ctl = ap->ctl;
+ if (ap->ioaddr.ctl_addr) {
+ /* software reset. causes dev0 to be selected */
+ iowrite8(ap->ctl, ioaddr->ctl_addr);
+ udelay(20); /* FIXME: flush */
+ iowrite8(ap->ctl | ATA_SRST, ioaddr->ctl_addr);
+ udelay(20); /* FIXME: flush */
+ iowrite8(ap->ctl, ioaddr->ctl_addr);
+ ap->last_ctl = ap->ctl;
+ }
/* wait the port to become ready */
return ata_sff_wait_after_reset(&ap->link, devmask, deadline);
@@ -2215,10 +2229,6 @@
spin_unlock_irqrestore(ap->lock, flags);
- /* ignore ata_sff_softreset if ctl isn't accessible */
- if (softreset == ata_sff_softreset && !ap->ioaddr.ctl_addr)
- softreset = NULL;
-
/* ignore built-in hardresets if SCR access is not available */
if ((hardreset == sata_std_hardreset ||
hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link))
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index c04d393..08e6728 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -319,25 +319,25 @@
/*
* ATA link attributes
*/
+static int noop(int x) { return x; }
-
-#define ata_link_show_linkspeed(field) \
+#define ata_link_show_linkspeed(field, format) \
static ssize_t \
show_ata_link_##field(struct device *dev, \
struct device_attribute *attr, char *buf) \
{ \
struct ata_link *link = transport_class_to_link(dev); \
\
- return sprintf(buf,"%s\n", sata_spd_string(fls(link->field))); \
+ return sprintf(buf, "%s\n", sata_spd_string(format(link->field))); \
}
-#define ata_link_linkspeed_attr(field) \
- ata_link_show_linkspeed(field) \
+#define ata_link_linkspeed_attr(field, format) \
+ ata_link_show_linkspeed(field, format) \
static DEVICE_ATTR(field, S_IRUGO, show_ata_link_##field, NULL)
-ata_link_linkspeed_attr(hw_sata_spd_limit);
-ata_link_linkspeed_attr(sata_spd_limit);
-ata_link_linkspeed_attr(sata_spd);
+ata_link_linkspeed_attr(hw_sata_spd_limit, fls);
+ata_link_linkspeed_attr(sata_spd_limit, fls);
+ata_link_linkspeed_attr(sata_spd, noop);
static DECLARE_TRANSPORT_CLASS(ata_link_class,
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index 90b159b..cd8daf4 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -32,13 +32,14 @@
static int eject_tray(struct ata_device *dev)
{
- struct ata_taskfile tf = {};
+ struct ata_taskfile tf;
const char cdb[] = { GPCMD_START_STOP_UNIT,
0, 0, 0,
0x02, /* LoEj */
0, 0, 0, 0, 0, 0, 0,
};
+ ata_tf_init(dev, &tf);
tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
tf.command = ATA_CMD_PACKET;
tf.protocol = ATAPI_PROT_NODATA;
@@ -52,8 +53,7 @@
char buf[16];
unsigned int ret;
struct rm_feature_desc *desc = (void *)(buf + 8);
- struct ata_taskfile tf = {};
-
+ struct ata_taskfile tf;
char cdb[] = { GPCMD_GET_CONFIGURATION,
2, /* only 1 feature descriptor requested */
0, 3, /* 3, removable medium feature */
@@ -62,6 +62,7 @@
0, 0, 0,
};
+ ata_tf_init(dev, &tf);
tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
tf.command = ATA_CMD_PACKET;
tf.protocol = ATAPI_PROT_PIO;
diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c
index 033f3f4..fa28859 100644
--- a/drivers/ata/pata_at91.c
+++ b/drivers/ata/pata_at91.c
@@ -408,12 +408,13 @@
host->private_data = info;
- return ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
- gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
- irq_flags, &pata_at91_sht);
+ ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
+ gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
+ irq_flags, &pata_at91_sht);
+ if (ret)
+ goto err_put;
- if (!ret)
- return 0;
+ return 0;
err_put:
clk_put(info->mck);
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index f35f15f..f7badaa 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -586,7 +586,7 @@
* Note: Original code is ata_bus_softreset().
*/
-static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
+static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask,
unsigned long deadline)
{
struct ata_ioports *ioaddr = &ap->ioaddr;
@@ -600,9 +600,7 @@
udelay(20);
out_be32(ioaddr->ctl_addr, ap->ctl);
- scc_wait_after_reset(&ap->link, devmask, deadline);
-
- return 0;
+ return scc_wait_after_reset(&ap->link, devmask, deadline);
}
/**
@@ -619,7 +617,8 @@
{
struct ata_port *ap = link->ap;
unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS;
- unsigned int devmask = 0, err_mask;
+ unsigned int devmask = 0;
+ int rc;
u8 err;
DPRINTK("ENTER\n");
@@ -635,9 +634,9 @@
/* issue bus reset */
DPRINTK("about to softreset, devmask=%x\n", devmask);
- err_mask = scc_bus_softreset(ap, devmask, deadline);
- if (err_mask) {
- ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask);
+ rc = scc_bus_softreset(ap, devmask, deadline);
+ if (rc) {
+ ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc);
return -EIO;
}
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index f3febbc..34c91ac 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -252,12 +252,18 @@
pci_write_config_byte(pdev, 0x54, ultra_cfg);
}
-static struct scsi_host_template serverworks_sht = {
+static struct scsi_host_template serverworks_osb4_sht = {
+ ATA_BMDMA_SHT(DRV_NAME),
+ .sg_tablesize = LIBATA_DUMB_MAX_PRD,
+};
+
+static struct scsi_host_template serverworks_csb_sht = {
ATA_BMDMA_SHT(DRV_NAME),
};
static struct ata_port_operations serverworks_osb4_port_ops = {
.inherits = &ata_bmdma_port_ops,
+ .qc_prep = ata_bmdma_dumb_qc_prep,
.cable_detect = serverworks_cable_detect,
.mode_filter = serverworks_osb4_filter,
.set_piomode = serverworks_set_piomode,
@@ -266,6 +272,7 @@
static struct ata_port_operations serverworks_csb_port_ops = {
.inherits = &serverworks_osb4_port_ops,
+ .qc_prep = ata_bmdma_qc_prep,
.mode_filter = serverworks_csb_filter,
};
@@ -405,6 +412,7 @@
}
};
const struct ata_port_info *ppi[] = { &info[id->driver_data], NULL };
+ struct scsi_host_template *sht = &serverworks_csb_sht;
int rc;
rc = pcim_enable_device(pdev);
@@ -418,6 +426,7 @@
/* Select non UDMA capable OSB4 if we can't do fixups */
if (rc < 0)
ppi[0] = &info[1];
+ sht = &serverworks_osb4_sht;
}
/* setup CSB5/CSB6 : South Bridge and IDE option RAID */
else if ((pdev->device == PCI_DEVICE_ID_SERVERWORKS_CSB5IDE) ||
@@ -434,7 +443,7 @@
ppi[1] = &ata_dummy_port_info;
}
- return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0);
+ return ata_pci_bmdma_init_one(pdev, ppi, sht, NULL, 0);
}
#ifdef CONFIG_PM
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 2e39173..776b59f 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -797,7 +797,7 @@
if (err) {
dev_err(host_pvt.dwc_dev, "%s: dma_request_interrupts returns"
" %d\n", __func__, err);
- goto error_out;
+ return err;
}
/* Enabe DMA */
@@ -808,11 +808,6 @@
sata_dma_regs);
return 0;
-
-error_out:
- dma_dwc_exit(hsdev);
-
- return err;
}
static int sata_dwc_scr_read(struct ata_link *link, unsigned int scr, u32 *val)
@@ -1662,7 +1657,7 @@
char *ver = (char *)&versionr;
u8 *base = NULL;
int err = 0;
- int irq, rc;
+ int irq;
struct ata_host *host;
struct ata_port_info pi = sata_dwc_port_info[0];
const struct ata_port_info *ppi[] = { &pi, NULL };
@@ -1725,7 +1720,7 @@
if (irq == NO_IRQ) {
dev_err(&ofdev->dev, "no SATA DMA irq\n");
err = -ENODEV;
- goto error_out;
+ goto error_iomap;
}
/* Get physical SATA DMA register base address */
@@ -1734,14 +1729,16 @@
dev_err(&ofdev->dev, "ioremap failed for AHBDMA register"
" address\n");
err = -ENODEV;
- goto error_out;
+ goto error_iomap;
}
/* Save dev for later use in dev_xxx() routines */
host_pvt.dwc_dev = &ofdev->dev;
/* Initialize AHB DMAC */
- dma_dwc_init(hsdev, irq);
+ err = dma_dwc_init(hsdev, irq);
+ if (err)
+ goto error_dma_iomap;
/* Enable SATA Interrupts */
sata_dwc_enable_interrupts(hsdev);
@@ -1759,9 +1756,8 @@
* device discovery process, invoking our port_start() handler &
* error_handler() to execute a dummy Softreset EH session
*/
- rc = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
-
- if (rc != 0)
+ err = ata_host_activate(host, irq, sata_dwc_isr, 0, &sata_dwc_sht);
+ if (err)
dev_err(&ofdev->dev, "failed to activate host");
dev_set_drvdata(&ofdev->dev, host);
@@ -1770,7 +1766,8 @@
error_out:
/* Free SATA DMA resources */
dma_dwc_exit(hsdev);
-
+error_dma_iomap:
+ iounmap((void __iomem *)host_pvt.sata_dma_regs);
error_iomap:
iounmap(base);
error_kmalloc:
@@ -1791,6 +1788,7 @@
/* Free SATA DMA resources */
dma_dwc_exit(hsdev);
+ iounmap((void __iomem *)host_pvt.sata_dma_regs);
iounmap(hsdev->reg_base);
kfree(hsdev);
kfree(host);
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index d40e403..38a2389 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -293,6 +293,7 @@
{
struct sata_fsl_host_priv *host_priv = host->private_data;
void __iomem *hcr_base = host_priv->hcr_base;
+ unsigned long flags;
if (count > ICC_MAX_INT_COUNT_THRESHOLD)
count = ICC_MAX_INT_COUNT_THRESHOLD;
@@ -305,12 +306,12 @@
(count > ICC_MIN_INT_COUNT_THRESHOLD))
ticks = ICC_SAFE_INT_TICKS;
- spin_lock(&host->lock);
+ spin_lock_irqsave(&host->lock, flags);
iowrite32((count << 24 | ticks), hcr_base + ICC);
intr_coalescing_count = count;
intr_coalescing_ticks = ticks;
- spin_unlock(&host->lock);
+ spin_unlock_irqrestore(&host->lock, flags);
DPRINTK("interrupt coalescing, count = 0x%x, ticks = %x\n",
intr_coalescing_count, intr_coalescing_ticks);
@@ -1500,7 +1501,7 @@
host_priv->csr_base = csr_base;
irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
- if (irq < 0) {
+ if (!irq) {
dev_err(&ofdev->dev, "invalid irq from platform\n");
goto error_exit_with_cleanup;
}
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index b20aa96..c846fd3 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -196,10 +196,26 @@
return 0;
}
+/*
+ * The Calxeda SATA phy intermittently fails to bring up a link with Gen3
+ * Retrying the phy hard reset can work around the issue, but the drive
+ * may fail again. In less than 150 out of 15000 test runs, it took more
+ * than 10 tries for the link to be established (but never more than 35).
+ * Triple the maximum observed retry count to provide plenty of margin for
+ * rare events and to guarantee that the link is established.
+ *
+ * Also, the default 2 second time-out on a failed drive is too long in
+ * this situation. The uboot implementation of the same driver function
+ * uses a much shorter time-out period and never experiences a time out
+ * issue. Reducing the time-out to 500ms improves the responsiveness.
+ * The other timing constants were kept the same as the stock AHCI driver.
+ * This change was also tested 15000 times on 24 drives and none of them
+ * experienced a time out.
+ */
static int ahci_highbank_hardreset(struct ata_link *link, unsigned int *class,
unsigned long deadline)
{
- const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context);
+ static const unsigned long timing[] = { 5, 100, 500};
struct ata_port *ap = link->ap;
struct ahci_port_priv *pp = ap->private_data;
u8 *d2h_fis = pp->rx_fis + RX_FIS_D2H_REG;
@@ -207,7 +223,7 @@
bool online;
u32 sstatus;
int rc;
- int retry = 10;
+ int retry = 100;
ahci_stop_engine(ap);
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index 1e6827c..74456fa 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -6,6 +6,18 @@
*
* This file is released under GPL v2.
*
+ * **** WARNING ****
+ *
+ * This driver never worked properly and unfortunately data corruption is
+ * relatively common. There isn't anyone working on the driver and there's
+ * no support from the vendor. Do not use this driver in any production
+ * environment.
+ *
+ * http://thread.gmane.org/gmane.linux.debian.devel.bugs.rc/378525/focus=54491
+ * https://bugzilla.kernel.org/show_bug.cgi?id=60565
+ *
+ * *****************
+ *
* This controller is eccentric and easily locks up if something isn't
* right. Documentation is available at initio's website but it only
* documents registers (not programming model).
@@ -807,6 +819,8 @@
ata_print_version_once(&pdev->dev, DRV_VERSION);
+ dev_alert(&pdev->dev, "inic162x support is broken with common data corruption issues and will be disabled by default, contact linux-ide@vger.kernel.org if in production use\n");
+
/* alloc host */
host = ata_host_alloc_pinfo(&pdev->dev, ppi, NR_PORTS);
hpriv = devm_kzalloc(&pdev->dev, sizeof(*hpriv), GFP_KERNEL);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 35c6b6d..b256ff5 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -304,6 +304,7 @@
MV5_LTMODE = 0x30,
MV5_PHY_CTL = 0x0C,
SATA_IFCFG = 0x050,
+ LP_PHY_CTL = 0x058,
MV_M2_PREAMP_MASK = 0x7e0,
@@ -431,6 +432,7 @@
MV_HP_CUT_THROUGH = (1 << 10), /* can use EDMA cut-through */
MV_HP_FLAG_SOC = (1 << 11), /* SystemOnChip, no PCI */
MV_HP_QUIRK_LED_BLINK_EN = (1 << 12), /* is led blinking enabled? */
+ MV_HP_FIX_LP_PHY_CTL = (1 << 13), /* fix speed in LP_PHY_CTL ? */
/* Port private flags (pp_flags) */
MV_PP_FLAG_EDMA_EN = (1 << 0), /* is EDMA engine enabled? */
@@ -1353,6 +1355,7 @@
if (ofs != 0xffffffffU) {
void __iomem *addr = mv_ap_base(link->ap) + ofs;
+ struct mv_host_priv *hpriv = link->ap->host->private_data;
if (sc_reg_in == SCR_CONTROL) {
/*
* Workaround for 88SX60x1 FEr SATA#26:
@@ -1369,6 +1372,18 @@
*/
if ((val & 0xf) == 1 || (readl(addr) & 0xf) == 1)
val |= 0xf000;
+
+ if (hpriv->hp_flags & MV_HP_FIX_LP_PHY_CTL) {
+ void __iomem *lp_phy_addr =
+ mv_ap_base(link->ap) + LP_PHY_CTL;
+ /*
+ * Set PHY speed according to SControl speed.
+ */
+ if ((val & 0xf0) == 0x10)
+ writelfl(0x7, lp_phy_addr);
+ else
+ writelfl(0x227, lp_phy_addr);
+ }
}
writelfl(val, addr);
return 0;
@@ -4111,6 +4126,15 @@
if (rc)
goto err;
+ /*
+ * To allow disk hotplug on Armada 370/XP SoCs, the PHY speed must be
+ * updated in the LP_PHY_CTL register.
+ */
+ if (pdev->dev.of_node &&
+ of_device_is_compatible(pdev->dev.of_node,
+ "marvell,armada-370-sata"))
+ hpriv->hp_flags |= MV_HP_FIX_LP_PHY_CTL;
+
/* initialize adapter */
rc = mv_init_host(host);
if (rc)
@@ -4216,6 +4240,7 @@
#ifdef CONFIG_OF
static struct of_device_id mv_sata_dt_ids[] = {
+ { .compatible = "marvell,armada-370-sata", },
{ .compatible = "marvell,orion-sata", },
{},
};
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 0ae3ca4..dd1faa5 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -157,6 +157,7 @@
{ "ST380011ASL", SIL_QUIRK_MOD15WRITE },
{ "ST3120022ASL", SIL_QUIRK_MOD15WRITE },
{ "ST3160021ASL", SIL_QUIRK_MOD15WRITE },
+ { "TOSHIBA MK2561GSYN", SIL_QUIRK_MOD15WRITE },
{ "Maxtor 4D060H3", SIL_QUIRK_UDMA5MAX },
{ }
};
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 272f009..1bdf104 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -3511,7 +3511,7 @@
tmp = dev_get_by_name(&init_net, tname); /* jhs: was "tmp = dev_get(tname);" */
if (tmp) {
memcpy(card->atmdev->esi, tmp->dev_addr, 6);
-
+ dev_put(tmp);
printk("%s: ESI %pM\n", card->name, card->atmdev->esi);
}
/*
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 07abd9d..4fe77b8 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -187,6 +187,14 @@
bool
default n
+config HAVE_CPU_AUTOPROBE
+ def_bool ARCH_HAS_CPU_AUTOPROBE
+
+config GENERIC_CPU_AUTOPROBE
+ bool
+ depends on !ARCH_HAS_CPU_AUTOPROBE
+ select HAVE_CPU_AUTOPROBE
+
config SOC_BUS
bool
@@ -202,11 +210,9 @@
APIs extension; the file's descriptor can then be passed on to other
driver.
-config CMA
- bool "Contiguous Memory Allocator"
- depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK
- select MIGRATION
- select MEMORY_ISOLATION
+config DMA_CMA
+ bool "DMA Contiguous Memory Allocator"
+ depends on HAVE_DMA_CONTIGUOUS && CMA
help
This enables the Contiguous Memory Allocator which allows drivers
to allocate big physically-contiguous blocks of memory for use with
@@ -215,17 +221,7 @@
For more information see <include/linux/dma-contiguous.h>.
If unsure, say "n".
-if CMA
-
-config CMA_DEBUG
- bool "CMA debug messages (DEVELOPMENT)"
- depends on DEBUG_KERNEL
- help
- Turns on debug messages in CMA. This produces KERN_DEBUG
- messages for every CMA call as well as various messages while
- processing calls such as dma_alloc_from_contiguous().
- This option does not affect warning and error messages.
-
+if DMA_CMA
comment "Default contiguous memory area size:"
config CMA_SIZE_MBYTES
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 4e22ce3..5d93bb5 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@
attribute_container.o transport_class.o \
topology.o
obj-$(CONFIG_DEVTMPFS) += devtmpfs.o
-obj-$(CONFIG_CMA) += dma-contiguous.o
+obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
obj-y += power/
obj-$(CONFIG_HAS_DMA) += dma-mapping.o
obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index d414331..558d562 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -242,13 +242,15 @@
const char *buf, size_t count)
{
struct device *dev;
+ int err = -EINVAL;
dev = bus_find_device_by_name(bus, NULL, buf);
if (!dev)
return -ENODEV;
- if (bus_rescan_devices_helper(dev, NULL) != 0)
- return -EINVAL;
- return count;
+ if (bus_rescan_devices_helper(dev, NULL) == 0)
+ err = count;
+ put_device(dev);
+ return err;
}
static struct device *next_device(struct klist_iter *i)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2499cef..2a19097 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -765,12 +765,12 @@
return &dir->kobj;
}
+static DEFINE_MUTEX(gdp_mutex);
static struct kobject *get_device_parent(struct device *dev,
struct device *parent)
{
if (dev->class) {
- static DEFINE_MUTEX(gdp_mutex);
struct kobject *kobj = NULL;
struct kobject *parent_kobj;
struct kobject *k;
@@ -834,7 +834,9 @@
glue_dir->kset != &dev->class->p->glue_dirs)
return;
+ mutex_lock(&gdp_mutex);
kobject_put(glue_dir);
+ mutex_unlock(&gdp_mutex);
}
static void cleanup_device_parent(struct device *dev)
@@ -1839,7 +1841,7 @@
*/
void device_shutdown(void)
{
- struct device *dev;
+ struct device *dev, *parent;
spin_lock(&devices_kset->list_lock);
/*
@@ -1856,7 +1858,7 @@
* prevent it from being freed because parent's
* lock is to be held
*/
- get_device(dev->parent);
+ parent = get_device(dev->parent);
get_device(dev);
/*
* Make sure the device is off the kset list, in the
@@ -1866,8 +1868,8 @@
spin_unlock(&devices_kset->list_lock);
/* hold lock to avoid race with probe/release */
- if (dev->parent)
- device_lock(dev->parent);
+ if (parent)
+ device_lock(parent);
device_lock(dev);
/* Don't allow any more runtime suspends */
@@ -1885,11 +1887,11 @@
}
device_unlock(dev);
- if (dev->parent)
- device_unlock(dev->parent);
+ if (parent)
+ device_unlock(parent);
put_device(dev);
- put_device(dev->parent);
+ put_device(parent);
spin_lock(&devices_kset->list_lock);
}
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 3d48fc8..607efe6 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -13,6 +13,9 @@
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/percpu.h>
+#include <linux/acpi.h>
+#include <linux/of.h>
+#include <linux/cpufeature.h>
#include "base.h"
@@ -260,6 +263,45 @@
*/
}
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+static ssize_t print_cpu_modalias(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ ssize_t n;
+ u32 i;
+
+ n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
+ CPU_FEATURE_TYPEVAL);
+
+ for (i = 0; i < MAX_CPU_FEATURES; i++)
+ if (cpu_have_feature(i)) {
+ if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
+ WARN(1, "CPU features overflow page\n");
+ break;
+ }
+ n += sprintf(&buf[n], ",%04X", i);
+ }
+ buf[n++] = '\n';
+ return n;
+}
+#else
+#define print_cpu_modalias arch_print_cpu_modalias
+#endif
+
+static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+ char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ if (buf) {
+ print_cpu_modalias(NULL, NULL, buf);
+ add_uevent_var(env, "MODALIAS=%s", buf);
+ kfree(buf);
+ }
+ return 0;
+}
+#endif
+
/*
* register_cpu - Setup a sysfs device for a CPU.
* @cpu - cpu->hotpluggable field set to 1 will generate a control file in
@@ -277,8 +319,8 @@
cpu->dev.id = num;
cpu->dev.bus = &cpu_subsys;
cpu->dev.release = cpu_device_release;
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
- cpu->dev.bus->uevent = arch_cpu_uevent;
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+ cpu->dev.bus->uevent = cpu_uevent;
#endif
error = device_register(&cpu->dev);
if (!error && cpu->hotpluggable)
@@ -307,8 +349,8 @@
}
EXPORT_SYMBOL_GPL(get_cpu_device);
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
#endif
static struct attribute *cpu_root_attrs[] = {
@@ -321,7 +363,7 @@
&cpu_attrs[2].attr.attr,
&dev_attr_kernel_max.attr,
&dev_attr_offline.attr,
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
&dev_attr_modalias.attr,
#endif
NULL
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 35fa368..8a8d611 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -52,6 +52,7 @@
static LIST_HEAD(deferred_probe_pending_list);
static LIST_HEAD(deferred_probe_active_list);
static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
/**
* deferred_probe_work_func() - Retry probing devices in the active list.
@@ -135,6 +136,17 @@
* This functions moves all devices from the pending list to the active
* list and schedules the deferred probe workqueue to process them. It
* should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
*/
static void driver_deferred_probe_trigger(void)
{
@@ -147,6 +159,7 @@
* into the active list so they can be retried by the workqueue
*/
mutex_lock(&deferred_probe_mutex);
+ atomic_inc(&deferred_trigger_count);
list_splice_tail_init(&deferred_probe_pending_list,
&deferred_probe_active_list);
mutex_unlock(&deferred_probe_mutex);
@@ -265,6 +278,7 @@
static int really_probe(struct device *dev, struct device_driver *drv)
{
int ret = 0;
+ int local_trigger_count = atomic_read(&deferred_trigger_count);
atomic_inc(&probe_count);
pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
@@ -310,6 +324,9 @@
/* Driver requested deferred probing */
dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
driver_deferred_probe_add(dev);
+ /* Did a trigger occur while probing? Need to re-trigger if yes */
+ if (local_trigger_count != atomic_read(&deferred_trigger_count))
+ driver_deferred_probe_trigger();
} else if (ret != -ENODEV && ret != -ENXIO) {
/* driver matched but the probe failed */
printk(KERN_WARNING
@@ -499,7 +516,7 @@
BUS_NOTIFY_UNBIND_DRIVER,
dev);
- pm_runtime_put(dev);
+ pm_runtime_put_sync(dev);
if (dev->bus && dev->bus->remove)
dev->bus->remove(dev);
diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 507379e..545c4de 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -91,7 +91,8 @@
if (unlikely(!dr))
return NULL;
- memset(dr, 0, tot_size);
+ memset(dr, 0, offsetof(struct devres, data));
+
INIT_LIST_HEAD(&dr->node.entry);
dr->node.release = release;
return dr;
@@ -110,7 +111,7 @@
{
struct devres *dr;
- dr = alloc_dr(release, size, gfp);
+ dr = alloc_dr(release, size, gfp | __GFP_ZERO);
if (unlikely(!dr))
return NULL;
set_node_dbginfo(&dr->node, name, size);
@@ -135,7 +136,7 @@
{
struct devres *dr;
- dr = alloc_dr(release, size, gfp);
+ dr = alloc_dr(release, size, gfp | __GFP_ZERO);
if (unlikely(!dr))
return NULL;
return dr->data;
@@ -745,58 +746,62 @@
EXPORT_SYMBOL_GPL(devm_remove_action);
/*
- * Managed kzalloc/kfree
+ * Managed kmalloc/kfree
*/
-static void devm_kzalloc_release(struct device *dev, void *res)
+static void devm_kmalloc_release(struct device *dev, void *res)
{
/* noop */
}
-static int devm_kzalloc_match(struct device *dev, void *res, void *data)
+static int devm_kmalloc_match(struct device *dev, void *res, void *data)
{
return res == data;
}
/**
- * devm_kzalloc - Resource-managed kzalloc
+ * devm_kmalloc - Resource-managed kmalloc
* @dev: Device to allocate memory for
* @size: Allocation size
* @gfp: Allocation gfp flags
*
- * Managed kzalloc. Memory allocated with this function is
+ * Managed kmalloc. Memory allocated with this function is
* automatically freed on driver detach. Like all other devres
* resources, guaranteed alignment is unsigned long long.
*
* RETURNS:
* Pointer to allocated memory on success, NULL on failure.
*/
-void * devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
{
struct devres *dr;
/* use raw alloc_dr for kmalloc caller tracing */
- dr = alloc_dr(devm_kzalloc_release, size, gfp);
+ dr = alloc_dr(devm_kmalloc_release, size, gfp);
if (unlikely(!dr))
return NULL;
+ /*
+ * This is named devm_kzalloc_release for historical reasons
+ * The initial implementation did not support kmalloc, only kzalloc
+ */
set_node_dbginfo(&dr->node, "devm_kzalloc_release", size);
devres_add(dev, dr->data);
return dr->data;
}
-EXPORT_SYMBOL_GPL(devm_kzalloc);
+EXPORT_SYMBOL_GPL(devm_kmalloc);
/**
* devm_kfree - Resource-managed kfree
* @dev: Device this memory belongs to
* @p: Memory to free
*
- * Free memory allocated with devm_kzalloc().
+ * Free memory allocated with devm_kmalloc().
*/
void devm_kfree(struct device *dev, void *p)
{
int rc;
- rc = devres_destroy(dev, devm_kzalloc_release, devm_kzalloc_match, p);
+ rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, p);
WARN_ON(rc);
}
EXPORT_SYMBOL_GPL(devm_kfree);
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 0ca5442..99802d6f 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -96,7 +96,7 @@
#endif
/**
- * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
* @limit: End address of the reserved memory (optional, 0 for any).
*
* This function reserves memory from early allocator. It should be
@@ -124,22 +124,29 @@
#endif
}
- if (selected_size) {
+ if (selected_size && !dma_contiguous_default_area) {
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
(unsigned long)selected_size / SZ_1M);
- dma_declare_contiguous(NULL, selected_size, 0, limit);
+ dma_contiguous_reserve_area(selected_size, 0, limit,
+ &dma_contiguous_default_area);
}
};
static DEFINE_MUTEX(cma_mutex);
-static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+static int __init cma_activate_area(struct cma *cma)
{
- unsigned long pfn = base_pfn;
- unsigned i = count >> pageblock_order;
+ int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+ unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
+ unsigned i = cma->count >> pageblock_order;
struct zone *zone;
+ cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+ if (!cma->bitmap)
+ return -ENOMEM;
+
WARN_ON_ONCE(!pfn_valid(pfn));
zone = page_zone(pfn_to_page(pfn));
@@ -153,92 +160,53 @@
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
+
return 0;
}
-static __init struct cma *cma_create_area(unsigned long base_pfn,
- unsigned long count)
-{
- int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
- struct cma *cma;
- int ret = -ENOMEM;
-
- pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
-
- cma = kmalloc(sizeof *cma, GFP_KERNEL);
- if (!cma)
- return ERR_PTR(-ENOMEM);
-
- cma->base_pfn = base_pfn;
- cma->count = count;
- cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-
- if (!cma->bitmap)
- goto no_mem;
-
- ret = cma_activate_area(base_pfn, count);
- if (ret)
- goto error;
-
- pr_debug("%s: returned %p\n", __func__, (void *)cma);
- return cma;
-
-error:
- kfree(cma->bitmap);
-no_mem:
- kfree(cma);
- return ERR_PTR(ret);
-}
-
-static struct cma_reserved {
- phys_addr_t start;
- unsigned long size;
- struct device *dev;
-} cma_reserved[MAX_CMA_AREAS] __initdata;
-static unsigned cma_reserved_count __initdata;
+static struct cma cma_areas[MAX_CMA_AREAS];
+static unsigned cma_area_count;
static int __init cma_init_reserved_areas(void)
{
- struct cma_reserved *r = cma_reserved;
- unsigned i = cma_reserved_count;
+ int i;
- pr_debug("%s()\n", __func__);
-
- for (; i; --i, ++r) {
- struct cma *cma;
- cma = cma_create_area(PFN_DOWN(r->start),
- r->size >> PAGE_SHIFT);
- if (!IS_ERR(cma))
- dev_set_cma_area(r->dev, cma);
+ for (i = 0; i < cma_area_count; i++) {
+ int ret = cma_activate_area(&cma_areas[i]);
+ if (ret)
+ return ret;
}
+
return 0;
}
core_initcall(cma_init_reserved_areas);
/**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- * for particular device
- * @dev: Pointer to device structure.
- * @size: Size of the reserved memory.
- * @base: Start address of the reserved memory (optional, 0 for any).
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
* @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
*
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
*/
-int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
- phys_addr_t base, phys_addr_t limit)
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+ phys_addr_t limit, struct cma **res_cma)
{
- struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+ struct cma *cma = &cma_areas[cma_area_count];
phys_addr_t alignment;
+ int ret = 0;
pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
(unsigned long)size, (unsigned long)base,
(unsigned long)limit);
/* Sanity checks */
- if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+ if (cma_area_count == ARRAY_SIZE(cma_areas)) {
pr_err("Not enough slots for CMA reserved regions!\n");
return -ENOSPC;
}
@@ -256,7 +224,7 @@
if (base) {
if (memblock_is_region_reserved(base, size) ||
memblock_reserve(base, size) < 0) {
- base = -EBUSY;
+ ret = -EBUSY;
goto err;
}
} else {
@@ -266,7 +234,7 @@
*/
phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
if (!addr) {
- base = -ENOMEM;
+ ret = -ENOMEM;
goto err;
} else {
base = addr;
@@ -277,10 +245,11 @@
* Each reserved area must be initialised later, when more kernel
* subsystems (like slab allocator) are available.
*/
- r->start = base;
- r->size = size;
- r->dev = dev;
- cma_reserved_count++;
+ cma->base_pfn = PFN_DOWN(base);
+ cma->count = size >> PAGE_SHIFT;
+ *res_cma = cma;
+ cma_area_count++;
+
pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
(unsigned long)base);
@@ -289,7 +258,7 @@
return 0;
err:
pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
- return base;
+ return ret;
}
/**
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index 0ce39a3..dd302ea 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -10,6 +10,8 @@
#include <linux/dma-mapping.h>
#include <linux/export.h>
#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm-generic/dma-coherent.h>
/*
@@ -267,3 +269,73 @@
return ret;
}
EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+ unsigned long vm_flags, pgprot_t prot,
+ const void *caller)
+{
+ struct vm_struct *area;
+
+ area = get_vm_area_caller(size, vm_flags, caller);
+ if (!area)
+ return NULL;
+
+ area->pages = pages;
+
+ if (map_vm_area(area, prot, &pages)) {
+ vunmap(area->addr);
+ return NULL;
+ }
+
+ return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+ unsigned long vm_flags,
+ pgprot_t prot, const void *caller)
+{
+ int i;
+ struct page **pages;
+ void *ptr;
+ unsigned long pfn;
+
+ pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+
+ for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++)
+ pages[i] = pfn_to_page(pfn + i);
+
+ ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+ kfree(pages);
+
+ return ptr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (!area || (area->flags & vm_flags) != vm_flags) {
+ WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+ return;
+ }
+
+ unmap_kernel_range((unsigned long)cpu_addr, size);
+ vunmap(cpu_addr);
+}
+#endif
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 01e2103..00a5656 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -1021,6 +1021,9 @@
if (!firmware_p)
return -EINVAL;
+ if (!name || name[0] == '\0')
+ return -EINVAL;
+
ret = _request_firmware_prepare(&fw, name, device);
if (ret <= 0) /* error or already assigned */
goto out;
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 14f8a69..86abbff 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -152,6 +152,8 @@
container_of(dev, struct memory_block, dev);
for (i = 0; i < sections_per_block; i++) {
+ if (!present_section_nr(mem->start_section_nr + i))
+ continue;
pfn = section_nr_to_pfn(mem->start_section_nr + i);
ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
}
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 9eda842..2fb6e98 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -913,6 +913,7 @@
error = bus_register(&platform_bus_type);
if (error)
device_unregister(&platform_bus);
+ of_platform_register_reconfig_notifier();
return error;
}
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 7072404..723b425 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -9,6 +9,7 @@
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/io.h>
+#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/pm_domain.h>
#include <linux/pm_qos.h>
@@ -2178,3 +2179,291 @@
list_add(&genpd->gpd_list_node, &gpd_list);
mutex_unlock(&gpd_list_lock);
}
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+/*
+ * Device Tree based PM domain providers.
+ *
+ * The code below implements generic device tree based PM domain providers that
+ * bind device tree nodes with generic PM domains registered in the system.
+ *
+ * Any driver that registers generic PM domains and needs to support binding of
+ * devices to these domains is supposed to register a PM domain provider, which
+ * maps a PM domain specifier retrieved from the device tree to a PM domain.
+ *
+ * Two simple mapping functions have been provided for convenience:
+ * - __of_genpd_xlate_simple() for 1:1 device tree node to PM domain mapping.
+ * - __of_genpd_xlate_onecell() for mapping of multiple PM domains per node by
+ * index.
+ */
+
+/**
+ * struct of_genpd_provider - PM domain provider registration structure
+ * @link: Entry in global list of PM domain providers
+ * @node: Pointer to device tree node of PM domain provider
+ * @xlate: Provider-specific xlate callback mapping a set of specifier cells
+ * into a PM domain.
+ * @data: context pointer to be passed into @xlate callback
+ */
+struct of_genpd_provider {
+ struct list_head link;
+ struct device_node *node;
+ genpd_xlate_t xlate;
+ void *data;
+};
+
+/* List of registered PM domain providers. */
+static LIST_HEAD(of_genpd_providers);
+/* Mutex to protect the list above. */
+static DEFINE_MUTEX(of_genpd_mutex);
+
+/**
+ * __of_genpd_xlate_simple() - Xlate function for direct node-domain mapping
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct generic_pm_domain
+ *
+ * This is a generic xlate function that can be used to model PM domains that
+ * have their own device tree nodes. The private data of xlate function needs
+ * to be a valid pointer to struct generic_pm_domain.
+ */
+struct generic_pm_domain *__of_genpd_xlate_simple(
+ struct of_phandle_args *genpdspec,
+ void *data)
+{
+ if (genpdspec->args_count != 0)
+ return ERR_PTR(-EINVAL);
+ return data;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_simple);
+
+/**
+ * __of_genpd_xlate_onecell() - Xlate function using a single index.
+ * @genpdspec: OF phandle args to map into a PM domain
+ * @data: xlate function private data - pointer to struct genpd_onecell_data
+ *
+ * This is a generic xlate function that can be used to model simple PM domain
+ * controllers that have one device tree node and provide multiple PM domains.
+ * A single cell is used as an index into an array of PM domains specified in
+ * the genpd_onecell_data struct when registering the provider.
+ */
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+ struct of_phandle_args *genpdspec,
+ void *data)
+{
+ struct genpd_onecell_data *genpd_data = data;
+ unsigned int idx = genpdspec->args[0];
+
+ if (genpdspec->args_count != 1)
+ return ERR_PTR(-EINVAL);
+
+ if (idx >= genpd_data->num_domains) {
+ pr_err("%s: invalid domain index %u\n", __func__, idx);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!genpd_data->domains[idx])
+ return ERR_PTR(-ENOENT);
+
+ return genpd_data->domains[idx];
+}
+EXPORT_SYMBOL_GPL(__of_genpd_xlate_onecell);
+
+/**
+ * __of_genpd_add_provider() - Register a PM domain provider for a node
+ * @np: Device node pointer associated with the PM domain provider.
+ * @xlate: Callback for decoding PM domain from phandle arguments.
+ * @data: Context pointer for @xlate callback.
+ */
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+ void *data)
+{
+ struct of_genpd_provider *cp;
+
+ cp = kzalloc(sizeof(*cp), GFP_KERNEL);
+ if (!cp)
+ return -ENOMEM;
+
+ cp->node = of_node_get(np);
+ cp->data = data;
+ cp->xlate = xlate;
+
+ mutex_lock(&of_genpd_mutex);
+ list_add(&cp->link, &of_genpd_providers);
+ mutex_unlock(&of_genpd_mutex);
+ pr_debug("Added domain provider from %s\n", np->full_name);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__of_genpd_add_provider);
+
+/**
+ * of_genpd_del_provider() - Remove a previously registered PM domain provider
+ * @np: Device node pointer associated with the PM domain provider
+ */
+void of_genpd_del_provider(struct device_node *np)
+{
+ struct of_genpd_provider *cp;
+
+ mutex_lock(&of_genpd_mutex);
+ list_for_each_entry(cp, &of_genpd_providers, link) {
+ if (cp->node == np) {
+ list_del(&cp->link);
+ of_node_put(cp->node);
+ kfree(cp);
+ break;
+ }
+ }
+ mutex_unlock(&of_genpd_mutex);
+}
+EXPORT_SYMBOL_GPL(of_genpd_del_provider);
+
+/**
+ * of_genpd_get_from_provider() - Look-up PM domain
+ * @genpdspec: OF phandle args to use for look-up
+ *
+ * Looks for a PM domain provider under the node specified by @genpdspec and if
+ * found, uses xlate function of the provider to map phandle args to a PM
+ * domain.
+ *
+ * Returns a valid pointer to struct generic_pm_domain on success or ERR_PTR()
+ * on failure.
+ */
+static struct generic_pm_domain *of_genpd_get_from_provider(
+ struct of_phandle_args *genpdspec)
+{
+ struct generic_pm_domain *genpd = ERR_PTR(-ENOENT);
+ struct of_genpd_provider *provider;
+
+ mutex_lock(&of_genpd_mutex);
+
+ /* Check if we have such a provider in our array */
+ list_for_each_entry(provider, &of_genpd_providers, link) {
+ if (provider->node == genpdspec->np)
+ genpd = provider->xlate(genpdspec, provider->data);
+ if (!IS_ERR(genpd))
+ break;
+ }
+
+ mutex_unlock(&of_genpd_mutex);
+
+ return genpd;
+}
+
+/**
+ * genpd_dev_pm_detach - Detach a device from its PM domain.
+ * @dev: Device to attach.
+ * @power_off: Currently not used
+ *
+ * Try to locate a corresponding generic PM domain, which the device was
+ * attached to previously. If such is found, the device is detached from it.
+ */
+static void genpd_dev_pm_detach(struct device *dev, bool power_off)
+{
+ struct generic_pm_domain *pd = NULL, *gpd;
+ int ret = 0;
+
+ if (!dev->pm_domain)
+ return;
+
+ mutex_lock(&gpd_list_lock);
+ list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+ if (&gpd->domain == dev->pm_domain) {
+ pd = gpd;
+ break;
+ }
+ }
+ mutex_unlock(&gpd_list_lock);
+
+ if (!pd)
+ return;
+
+ dev_dbg(dev, "removing from PM domain %s\n", pd->name);
+
+ while (1) {
+ ret = pm_genpd_remove_device(pd, dev);
+ if (ret != -EAGAIN)
+ break;
+ cond_resched();
+ }
+
+ if (ret < 0) {
+ dev_err(dev, "failed to remove from PM domain %s: %d",
+ pd->name, ret);
+ return;
+ }
+
+ /* Check if PM domain can be powered off after removing this device. */
+ genpd_queue_power_off_work(pd);
+}
+
+/**
+ * genpd_dev_pm_attach - Attach a device to its PM domain using DT.
+ * @dev: Device to attach.
+ *
+ * Parse device's OF node to find a PM domain specifier. If such is found,
+ * attaches the device to retrieved pm_domain ops.
+ *
+ * Both generic and legacy Samsung-specific DT bindings are supported to keep
+ * backwards compatibility with existing DTBs.
+ *
+ * Returns 0 on successfully attached PM domain or negative error code.
+ */
+int genpd_dev_pm_attach(struct device *dev)
+{
+ struct of_phandle_args pd_args;
+ struct generic_pm_domain *pd;
+ int ret;
+
+ if (!dev->of_node)
+ return -ENODEV;
+
+ if (dev->pm_domain)
+ return -EEXIST;
+
+ ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
+ "#power-domain-cells", 0, &pd_args);
+ if (ret < 0) {
+ if (ret != -ENOENT)
+ return ret;
+
+ /*
+ * Try legacy Samsung-specific bindings
+ * (for backwards compatibility of DT ABI)
+ */
+ pd_args.args_count = 0;
+ pd_args.np = of_parse_phandle(dev->of_node,
+ "samsung,power-domain", 0);
+ if (!pd_args.np)
+ return -ENOENT;
+ }
+
+ pd = of_genpd_get_from_provider(&pd_args);
+ if (IS_ERR(pd)) {
+ dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
+ __func__, PTR_ERR(pd));
+ of_node_put(dev->of_node);
+ return PTR_ERR(pd);
+ }
+
+ dev_dbg(dev, "adding to PM domain %s\n", pd->name);
+
+ while (1) {
+ ret = pm_genpd_add_device(pd, dev);
+ if (ret != -EAGAIN)
+ break;
+ cond_resched();
+ }
+
+ if (ret < 0) {
+ dev_err(dev, "failed to add to PM domain %s: %d",
+ pd->name, ret);
+ of_node_put(dev->of_node);
+ return ret;
+ }
+
+ dev->pm_domain->detach = genpd_dev_pm_detach;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
+#endif
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 02f490b..bb8c3bb 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -362,7 +362,7 @@
rbnode = kzalloc(sizeof *rbnode, GFP_KERNEL);
if (!rbnode)
return -ENOMEM;
- rbnode->blklen = sizeof(*rbnode);
+ rbnode->blklen = 1;
rbnode->base_reg = reg;
rbnode->block = kmalloc(rbnode->blklen * map->cache_word_size,
GFP_KERNEL);
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 507ee2d..46283fd 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -644,7 +644,8 @@
}
}
- return regcache_sync_block_raw_flush(map, &data, base, regtmp);
+ return regcache_sync_block_raw_flush(map, &data, base, regtmp +
+ map->reg_stride);
}
int regcache_sync_block(struct regmap *map, void *block,
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 975719b..b41994f 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -460,16 +460,20 @@
{
struct rb_node *next;
struct regmap_range_node *range_node;
+ const char *devname = "dummy";
INIT_LIST_HEAD(&map->debugfs_off_cache);
mutex_init(&map->cache_lock);
+ if (map->dev)
+ devname = dev_name(map->dev);
+
if (name) {
map->debugfs_name = kasprintf(GFP_KERNEL, "%s-%s",
- dev_name(map->dev), name);
+ devname, name);
name = map->debugfs_name;
} else {
- name = dev_name(map->dev);
+ name = devname;
}
map->debugfs = debugfs_create_dir(name, regmap_debugfs_root);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index a941dcf..6a66f0b 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -114,7 +114,7 @@
bool regmap_volatile(struct regmap *map, unsigned int reg)
{
- if (!regmap_readable(map, reg))
+ if (!map->format.format_write && !regmap_readable(map, reg))
return false;
if (map->volatile_reg)
@@ -1177,7 +1177,7 @@
}
#ifdef LOG_DEVICE
- if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+ if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
dev_info(map->dev, "%x <= %x\n", reg, val);
#endif
@@ -1437,7 +1437,7 @@
ret = map->reg_read(context, reg, val);
if (ret == 0) {
#ifdef LOG_DEVICE
- if (strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
+ if (map->dev && strcmp(dev_name(map->dev), LOG_DEVICE) == 0)
dev_info(map->dev, "%x => %x\n", reg, *val);
#endif
@@ -1717,7 +1717,7 @@
int ret;
/* Nothing to do with no async support */
- if (!map->bus->async_write)
+ if (!map->bus || !map->bus->async_write)
return 0;
trace_regmap_async_complete_start(map->dev);
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index ae989c5..bcd1988 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -40,8 +40,7 @@
static ssize_t show_##name(struct device *dev, \
struct device_attribute *attr, char *buf) \
{ \
- unsigned int cpu = dev->id; \
- return sprintf(buf, "%d\n", topology_##name(cpu)); \
+ return sprintf(buf, "%d\n", topology_##name(dev->id)); \
}
#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b81ddfe..9da952c 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -105,6 +105,8 @@
source "drivers/block/mtip32xx/Kconfig"
+source "drivers/block/zram/Kconfig"
+
config BLK_CPQ_DA
tristate "Compaq SMART2 support"
depends on PCI && VIRT_TO_BUS
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index ca07399..3675937 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -41,6 +41,7 @@
obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX) += mtip32xx/
obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
+obj-$(CONFIG_ZRAM) += zram/
nvme-y := nvme-core.o nvme-scsi.o
swim_mod-y := swim.o swim_asm.o
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index fc803ec..3126273 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -899,7 +899,7 @@
* but this has never been seen here.
*/
if (unlikely(PageCompound(page)))
- if (compound_trans_head(page) != page) {
+ if (compound_head(page) != page) {
pr_crit("page tail used for block I/O\n");
BUG();
}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 9bf4371..d91f1a5 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -545,7 +545,7 @@
mutex_lock(&brd_devices_mutex);
brd = brd_init_one(MINOR(dev) >> part_shift);
- kobj = brd ? get_disk(brd->brd_disk) : ERR_PTR(-ENOMEM);
+ kobj = brd ? get_disk(brd->brd_disk) : NULL;
mutex_unlock(&brd_devices_mutex);
*part = 0;
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 62b6c2c..90a4e6b 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1189,6 +1189,7 @@
int err;
u32 cp;
+ memset(&arg64, 0, sizeof(arg64));
err = 0;
err |=
copy_from_user(&arg64.LUN_info, &arg32->LUN_info,
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 639d26b..2b94403 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -1193,6 +1193,7 @@
ida_pci_info_struct pciinfo;
if (!arg) return -EINVAL;
+ memset(&pciinfo, 0, sizeof(pciinfo));
pciinfo.bus = host->pci_dev->bus->number;
pciinfo.dev_fn = host->pci_dev->devfn;
pciinfo.board_id = host->board_id;
diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c
index 89c497c..04a14e0 100644
--- a/drivers/block/drbd/drbd_interval.c
+++ b/drivers/block/drbd/drbd_interval.c
@@ -79,6 +79,7 @@
drbd_insert_interval(struct rb_root *root, struct drbd_interval *this)
{
struct rb_node **new = &root->rb_node, *parent = NULL;
+ sector_t this_end = this->sector + (this->size >> 9);
BUG_ON(!IS_ALIGNED(this->size, 512));
@@ -87,6 +88,8 @@
rb_entry(*new, struct drbd_interval, rb);
parent = *new;
+ if (here->end < this_end)
+ here->end = this_end;
if (this->sector < here->sector)
new = &(*new)->rb_left;
else if (this->sector > here->sector)
@@ -99,6 +102,7 @@
return false;
}
+ this->end = this_end;
rb_link_node(&this->rb, parent, new);
rb_insert_augmented(&this->rb, root, &augment_callbacks);
return true;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 9e3f441..9c37f3d 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -514,6 +514,12 @@
struct task_struct *opa;
kref_get(&tconn->kref);
+ /* We may just have force_sig()'ed this thread
+ * to get it out of some blocking network function.
+ * Clear signals; otherwise kthread_run(), which internally uses
+ * wait_on_completion_killable(), will mistake our pending signal
+ * for a new fatal signal and fail. */
+ flush_signals(current);
opa = kthread_run(_try_outdate_peer_async, tconn, "drbd_async_h");
if (IS_ERR(opa)) {
conn_err(tconn, "out of mem, failed to invoke fence-peer helper\n");
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c24379f..b2ae184 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1309,6 +1309,7 @@
struct request_queue * const b =
mdev->ldev->backing_bdev->bd_disk->queue;
if (b->merge_bvec_fn) {
+ bvm->bi_bdev = mdev->ldev->backing_bdev;
backing_limit = b->merge_bvec_fn(b, bvm, bvec);
limit = min(limit, backing_limit);
}
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 04ceb7e..eb3575b 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3053,7 +3053,10 @@
int ret;
while (ptr) {
- ret = copy_to_user(param, ptr, sizeof(*ptr));
+ struct floppy_raw_cmd cmd = *ptr;
+ cmd.next = NULL;
+ cmd.kernel_data = NULL;
+ ret = copy_to_user(param, &cmd, sizeof(cmd));
if (ret)
return -EFAULT;
param += sizeof(struct floppy_raw_cmd);
@@ -3107,10 +3110,11 @@
return -ENOMEM;
*rcmd = ptr;
ret = copy_from_user(ptr, param, sizeof(*ptr));
- if (ret)
- return -EFAULT;
ptr->next = NULL;
ptr->buffer_length = 0;
+ ptr->kernel_data = NULL;
+ if (ret)
+ return -EFAULT;
param += sizeof(struct floppy_raw_cmd);
if (ptr->cmd_count > 33)
/* the command may now also take up the space
@@ -3126,7 +3130,6 @@
for (i = 0; i < 16; i++)
ptr->reply[i] = 0;
ptr->resultcode = 0;
- ptr->kernel_data = NULL;
if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) {
if (ptr->length <= 0)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d92d50f..4a81165 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -894,13 +894,6 @@
bio_list_init(&lo->lo_bio_list);
- /*
- * set queue make_request_fn, and add limits based on lower level
- * device
- */
- blk_queue_make_request(lo->lo_queue, loop_make_request);
- lo->lo_queue->queuedata = lo;
-
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_flush(lo->lo_queue, REQ_FLUSH);
@@ -1618,6 +1611,8 @@
if (!lo)
goto out;
+ lo->lo_state = Lo_unbound;
+
/* allocate id, if @id >= 0, we're requesting that specific id */
if (i >= 0) {
err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
@@ -1633,7 +1628,13 @@
err = -ENOMEM;
lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
if (!lo->lo_queue)
- goto out_free_dev;
+ goto out_free_idr;
+
+ /*
+ * set queue make_request_fn
+ */
+ blk_queue_make_request(lo->lo_queue, loop_make_request);
+ lo->lo_queue->queuedata = lo;
disk = lo->lo_disk = alloc_disk(1 << part_shift);
if (!disk)
@@ -1678,6 +1679,8 @@
out_free_queue:
blk_cleanup_queue(lo->lo_queue);
+out_free_idr:
+ idr_remove(&loop_index_idr, i);
out_free_dev:
kfree(lo);
out:
@@ -1741,7 +1744,7 @@
if (err < 0)
err = loop_add(&lo, MINOR(dev) >> part_shift);
if (err < 0)
- kobj = ERR_PTR(err);
+ kobj = NULL;
else
kobj = get_disk(lo->lo_disk);
mutex_unlock(&loop_index_mutex);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 20dd52a..0d94e09 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -1493,6 +1493,37 @@
be16_to_cpus(&buf[i]);
}
+static void mtip_set_timeout(struct driver_data *dd,
+ struct host_to_dev_fis *fis,
+ unsigned int *timeout, u8 erasemode)
+{
+ switch (fis->command) {
+ case ATA_CMD_DOWNLOAD_MICRO:
+ *timeout = 120000; /* 2 minutes */
+ break;
+ case ATA_CMD_SEC_ERASE_UNIT:
+ case 0xFC:
+ if (erasemode)
+ *timeout = ((*(dd->port->identify + 90) * 2) * 60000);
+ else
+ *timeout = ((*(dd->port->identify + 89) * 2) * 60000);
+ break;
+ case ATA_CMD_STANDBYNOW1:
+ *timeout = 120000; /* 2 minutes */
+ break;
+ case 0xF7:
+ case 0xFA:
+ *timeout = 60000; /* 60 seconds */
+ break;
+ case ATA_CMD_SMART:
+ *timeout = 15000; /* 15 seconds */
+ break;
+ default:
+ *timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
+ break;
+ }
+}
+
/*
* Request the device identity information.
*
@@ -1602,6 +1633,7 @@
int rv;
struct host_to_dev_fis fis;
unsigned long start;
+ unsigned int timeout;
/* Build the FIS. */
memset(&fis, 0, sizeof(struct host_to_dev_fis));
@@ -1609,6 +1641,8 @@
fis.opts = 1 << 7;
fis.command = ATA_CMD_STANDBYNOW1;
+ mtip_set_timeout(port->dd, &fis, &timeout, 0);
+
start = jiffies;
rv = mtip_exec_internal_command(port,
&fis,
@@ -1617,7 +1651,7 @@
0,
0,
GFP_ATOMIC,
- 15000);
+ timeout);
dbg_printk(MTIP_DRV_NAME "Time taken to complete standby cmd: %d ms\n",
jiffies_to_msecs(jiffies - start));
if (rv)
@@ -2156,36 +2190,6 @@
}
return rv;
}
-static void mtip_set_timeout(struct driver_data *dd,
- struct host_to_dev_fis *fis,
- unsigned int *timeout, u8 erasemode)
-{
- switch (fis->command) {
- case ATA_CMD_DOWNLOAD_MICRO:
- *timeout = 120000; /* 2 minutes */
- break;
- case ATA_CMD_SEC_ERASE_UNIT:
- case 0xFC:
- if (erasemode)
- *timeout = ((*(dd->port->identify + 90) * 2) * 60000);
- else
- *timeout = ((*(dd->port->identify + 89) * 2) * 60000);
- break;
- case ATA_CMD_STANDBYNOW1:
- *timeout = 120000; /* 2 minutes */
- break;
- case 0xF7:
- case 0xFA:
- *timeout = 60000; /* 60 seconds */
- break;
- case ATA_CMD_SMART:
- *timeout = 15000; /* 15 seconds */
- break;
- default:
- *timeout = MTIP_IOCTL_COMMAND_TIMEOUT_MS;
- break;
- }
-}
/*
* Executes a taskfile
@@ -4040,6 +4044,7 @@
blk_queue_max_hw_sectors(dd->queue, 0xffff);
blk_queue_max_segment_size(dd->queue, 0x400000);
blk_queue_io_min(dd->queue, 4096);
+ blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask);
/*
* write back cache is not supported in the device. FUA depends on
@@ -4283,6 +4288,57 @@
static DEFINE_HANDLER(6);
static DEFINE_HANDLER(7);
+static void mtip_disable_link_opts(struct driver_data *dd, struct pci_dev *pdev)
+{
+ int pos;
+ unsigned short pcie_dev_ctrl;
+
+ pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+ if (pos) {
+ pci_read_config_word(pdev,
+ pos + PCI_EXP_DEVCTL,
+ &pcie_dev_ctrl);
+ if (pcie_dev_ctrl & (1 << 11) ||
+ pcie_dev_ctrl & (1 << 4)) {
+ dev_info(&dd->pdev->dev,
+ "Disabling ERO/No-Snoop on bridge device %04x:%04x\n",
+ pdev->vendor, pdev->device);
+ pcie_dev_ctrl &= ~(PCI_EXP_DEVCTL_NOSNOOP_EN |
+ PCI_EXP_DEVCTL_RELAX_EN);
+ pci_write_config_word(pdev,
+ pos + PCI_EXP_DEVCTL,
+ pcie_dev_ctrl);
+ }
+ }
+}
+
+static void mtip_fix_ero_nosnoop(struct driver_data *dd, struct pci_dev *pdev)
+{
+ /*
+ * This workaround is specific to AMD/ATI chipset with a PCI upstream
+ * device with device id 0x5aXX
+ */
+ if (pdev->bus && pdev->bus->self) {
+ if (pdev->bus->self->vendor == PCI_VENDOR_ID_ATI &&
+ ((pdev->bus->self->device & 0xff00) == 0x5a00)) {
+ mtip_disable_link_opts(dd, pdev->bus->self);
+ } else {
+ /* Check further up the topology */
+ struct pci_dev *parent_dev = pdev->bus->self;
+ if (parent_dev->bus &&
+ parent_dev->bus->parent &&
+ parent_dev->bus->parent->self &&
+ parent_dev->bus->parent->self->vendor ==
+ PCI_VENDOR_ID_ATI &&
+ (parent_dev->bus->parent->self->device &
+ 0xff00) == 0x5a00) {
+ mtip_disable_link_opts(dd,
+ parent_dev->bus->parent->self);
+ }
+ }
+ }
+}
+
/*
* Called for each supported PCI device detected.
*
@@ -4434,6 +4490,8 @@
goto block_initialize_err;
}
+ mtip_fix_ero_nosnoop(dd, pdev);
+
/* Initialize the block layer. */
rv = mtip_block_initialize(dd);
if (rv < 0) {
@@ -4726,13 +4784,13 @@
*/
static void __exit mtip_exit(void)
{
- debugfs_remove_recursive(dfs_parent);
-
/* Release the allocated major block device number. */
unregister_blkdev(mtip_major, MTIP_DRV_NAME);
/* Unregister the PCI driver. */
pci_unregister_driver(&mtip_pci_driver);
+
+ debugfs_remove_recursive(dfs_parent);
}
MODULE_AUTHOR("Micron Technology, Inc");
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 037288e..a5c987a 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -623,8 +623,10 @@
if (!nbd->sock)
return -EINVAL;
+ nbd->disconnect = 1;
+
nbd_send_req(nbd, &sreq);
- return 0;
+ return 0;
}
case NBD_CLEAR_SOCK: {
@@ -654,6 +656,7 @@
nbd->sock = SOCKET_I(inode);
if (max_part > 0)
bdev->bd_invalidated = 1;
+ nbd->disconnect = 0; /* we're connected now */
return 0;
} else {
fput(file);
@@ -714,7 +717,8 @@
else
blk_queue_flush(nbd->disk->queue, 0);
- thread = kthread_create(nbd_thread, nbd, nbd->disk->disk_name);
+ thread = kthread_create(nbd_thread, nbd, "%s",
+ nbd->disk->disk_name);
if (IS_ERR(thread)) {
mutex_lock(&nbd->tx_lock);
return PTR_ERR(thread);
@@ -742,6 +746,8 @@
set_capacity(nbd->disk, 0);
if (max_part > 0)
ioctl_by_bdev(bdev, BLKRRPART, 0);
+ if (nbd->disconnect) /* user requested, ignore socket errors */
+ return 0;
return nbd->harderror;
}
@@ -809,10 +815,6 @@
return -EINVAL;
}
- nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
- if (!nbd_dev)
- return -ENOMEM;
-
part_shift = 0;
if (max_part > 0) {
part_shift = fls(max_part);
@@ -834,6 +836,10 @@
if (nbds_max > 1UL << (MINORBITS - part_shift))
return -EINVAL;
+ nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
+ if (!nbd_dev)
+ return -ENOMEM;
+
for (i = 0; i < nbds_max; i++) {
struct gendisk *disk = alloc_disk(1 << part_shift);
if (!disk)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index aff789d..7e3f451 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -937,12 +937,14 @@
u64 snap_id)
{
u32 which;
+ const char *snap_name;
which = rbd_dev_snap_index(rbd_dev, snap_id);
if (which == BAD_SNAP_INDEX)
- return NULL;
+ return ERR_PTR(-ENOENT);
- return _rbd_dev_v1_snap_name(rbd_dev, which);
+ snap_name = _rbd_dev_v1_snap_name(rbd_dev, which);
+ return snap_name ? snap_name : ERR_PTR(-ENOMEM);
}
static const char *rbd_snap_name(struct rbd_device *rbd_dev, u64 snap_id)
@@ -1126,6 +1128,7 @@
buf = bvec_kmap_irq(bv, &flags);
memset(buf + remainder, 0,
bv->bv_len - remainder);
+ flush_dcache_page(bv->bv_page);
bvec_kunmap_irq(buf, &flags);
}
pos += bv->bv_len;
@@ -1158,6 +1161,7 @@
local_irq_save(flags);
kaddr = kmap_atomic(*page);
memset(kaddr + page_offset, 0, length);
+ flush_dcache_page(*page);
kunmap_atomic(kaddr);
local_irq_restore(flags);
@@ -1381,6 +1385,14 @@
return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
}
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+ struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+ return obj_request->img_offset <
+ round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
{
dout("%s: obj %p (was %d)\n", __func__, obj_request,
@@ -1397,6 +1409,13 @@
kref_put(&obj_request->kref, rbd_obj_request_destroy);
}
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+ dout("%s: img %p (was %d)\n", __func__, img_request,
+ atomic_read(&img_request->kref.refcount));
+ kref_get(&img_request->kref);
+}
+
static bool img_request_child_test(struct rbd_img_request *img_request);
static void rbd_parent_request_destroy(struct kref *kref);
static void rbd_img_request_destroy(struct kref *kref);
@@ -1565,11 +1584,12 @@
obj_request, obj_request->img_request, obj_request->result,
xferred, length);
/*
- * ENOENT means a hole in the image. We zero-fill the
- * entire length of the request. A short read also implies
- * zero-fill to the end of the request. Either way we
- * update the xferred count to indicate the whole request
- * was satisfied.
+ * ENOENT means a hole in the image. We zero-fill the entire
+ * length of the request. A short read also implies zero-fill
+ * to the end of the request. An error requires the whole
+ * length of the request to be reported finished with an error
+ * to the block layer. In each case we update the xferred
+ * count to indicate the whole request was satisfied.
*/
rbd_assert(obj_request->type != OBJ_REQUEST_NODATA);
if (obj_request->result == -ENOENT) {
@@ -1578,14 +1598,13 @@
else
zero_pages(obj_request->pages, 0, length);
obj_request->result = 0;
- obj_request->xferred = length;
} else if (xferred < length && !obj_request->result) {
if (obj_request->type == OBJ_REQUEST_BIO)
zero_bio_chain(obj_request->bio_list, xferred);
else
zero_pages(obj_request->pages, xferred, length);
- obj_request->xferred = length;
}
+ obj_request->xferred = length;
obj_request_done_set(obj_request);
}
@@ -2130,7 +2149,6 @@
rbd_assert(img_request->obj_request_count > 0);
rbd_assert(which != BAD_WHICH);
rbd_assert(which < img_request->obj_request_count);
- rbd_assert(which >= img_request->next_completion);
spin_lock_irq(&img_request->completion_lock);
if (which != img_request->next_completion)
@@ -2150,6 +2168,7 @@
img_request->next_completion = which;
out:
spin_unlock_irq(&img_request->completion_lock);
+ rbd_img_request_put(img_request);
if (!more)
rbd_img_request_complete(img_request);
@@ -2171,9 +2190,9 @@
struct rbd_obj_request *obj_request = NULL;
struct rbd_obj_request *next_obj_request;
bool write_request = img_request_write_test(img_request);
- struct bio *bio_list;
+ struct bio *bio_list = 0;
unsigned int bio_offset = 0;
- struct page **pages;
+ struct page **pages = 0;
u64 img_offset;
u64 resid;
u16 opcode;
@@ -2211,6 +2230,11 @@
rbd_segment_name_free(object_name);
if (!obj_request)
goto out_unwind;
+ /*
+ * set obj_request->img_request before creating the
+ * osd_request so that it gets the right snapc
+ */
+ rbd_img_obj_request_add(img_request, obj_request);
if (type == OBJ_REQUEST_BIO) {
unsigned int clone_size;
@@ -2241,6 +2265,7 @@
goto out_partial;
obj_request->osd_req = osd_req;
obj_request->callback = rbd_img_obj_callback;
+ rbd_img_request_get(img_request);
osd_req_op_extent_init(osd_req, 0, opcode, offset, length,
0, 0);
@@ -2252,11 +2277,6 @@
obj_request->pages, length,
offset & ~PAGE_MASK, false, false);
- /*
- * set obj_request->img_request before formatting
- * the osd_request so that it gets the right snapc
- */
- rbd_img_obj_request_add(img_request, obj_request);
if (write_request)
rbd_osd_req_format_write(obj_request);
else
@@ -2274,7 +2294,7 @@
rbd_obj_request_put(obj_request);
out_unwind:
for_each_obj_request_safe(img_request, obj_request, next_obj_request)
- rbd_obj_request_put(obj_request);
+ rbd_img_obj_request_del(img_request, obj_request);
return -ENOMEM;
}
@@ -2669,7 +2689,7 @@
*/
if (!img_request_write_test(img_request) ||
!img_request_layered_test(img_request) ||
- rbd_dev->parent_overlap <= obj_request->img_offset ||
+ !obj_request_overlaps_parent(obj_request) ||
((known = obj_request_known_test(obj_request)) &&
obj_request_exists_test(obj_request))) {
@@ -2817,7 +2837,7 @@
obj_request_done_set(obj_request);
}
-static int rbd_obj_notify_ack(struct rbd_device *rbd_dev, u64 notify_id)
+static int rbd_obj_notify_ack_sync(struct rbd_device *rbd_dev, u64 notify_id)
{
struct rbd_obj_request *obj_request;
struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
@@ -2832,16 +2852,17 @@
obj_request->osd_req = rbd_osd_req_create(rbd_dev, false, obj_request);
if (!obj_request->osd_req)
goto out;
- obj_request->callback = rbd_obj_request_put;
osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_NOTIFY_ACK,
notify_id, 0, 0);
rbd_osd_req_format_read(obj_request);
ret = rbd_obj_request_submit(osdc, obj_request);
-out:
if (ret)
- rbd_obj_request_put(obj_request);
+ goto out;
+ ret = rbd_obj_request_wait(obj_request);
+out:
+ rbd_obj_request_put(obj_request);
return ret;
}
@@ -2861,7 +2882,7 @@
if (ret)
rbd_warn(rbd_dev, ": header refresh error (%d)\n", ret);
- rbd_obj_notify_ack(rbd_dev, notify_id);
+ rbd_obj_notify_ack_sync(rbd_dev, notify_id);
}
/*
@@ -3205,7 +3226,7 @@
page_count = (u32) calc_pages_for(offset, length);
pages = ceph_alloc_page_vector(page_count, GFP_KERNEL);
if (IS_ERR(pages))
- ret = PTR_ERR(pages);
+ return PTR_ERR(pages);
ret = -ENOMEM;
obj_request = rbd_obj_request_create(object_name, offset, length,
@@ -3333,6 +3354,31 @@
clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
}
+static void rbd_dev_update_size(struct rbd_device *rbd_dev)
+{
+ sector_t size;
+ bool removing;
+
+ /*
+ * Don't hold the lock while doing disk operations,
+ * or lock ordering will conflict with the bdev mutex via:
+ * rbd_add() -> blkdev_get() -> rbd_open()
+ */
+ spin_lock_irq(&rbd_dev->lock);
+ removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
+ spin_unlock_irq(&rbd_dev->lock);
+ /*
+ * If the device is being removed, rbd_dev->disk has
+ * been destroyed, so don't try to update its size
+ */
+ if (!removing) {
+ size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
+ dout("setting size to %llu sectors", (unsigned long long)size);
+ set_capacity(rbd_dev->disk, size);
+ revalidate_disk(rbd_dev->disk);
+ }
+}
+
static int rbd_dev_refresh(struct rbd_device *rbd_dev)
{
u64 mapping_size;
@@ -3351,12 +3397,7 @@
rbd_exists_validate(rbd_dev);
mutex_unlock(&ctl_mutex);
if (mapping_size != rbd_dev->mapping.size) {
- sector_t size;
-
- size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE;
- dout("setting size to %llu sectors", (unsigned long long)size);
- set_capacity(rbd_dev->disk, size);
- revalidate_disk(rbd_dev->disk);
+ rbd_dev_update_size(rbd_dev);
}
return ret;
@@ -3710,12 +3751,14 @@
if (ret < sizeof (size_buf))
return -ERANGE;
- if (order)
+ if (order) {
*order = size_buf.order;
+ dout(" order %u", (unsigned int)*order);
+ }
*snap_size = le64_to_cpu(size_buf.size);
- dout(" snap_id 0x%016llx order = %u, snap_size = %llu\n",
- (unsigned long long)snap_id, (unsigned int)*order,
+ dout(" snap_id 0x%016llx snap_size = %llu\n",
+ (unsigned long long)snap_id,
(unsigned long long)*snap_size);
return 0;
@@ -4030,8 +4073,13 @@
snap_id = snapc->snaps[which];
snap_name = rbd_dev_v2_snap_name(rbd_dev, snap_id);
- if (IS_ERR(snap_name))
- break;
+ if (IS_ERR(snap_name)) {
+ /* ignore no-longer existing snapshots */
+ if (PTR_ERR(snap_name) == -ENOENT)
+ continue;
+ else
+ break;
+ }
found = !strcmp(name, snap_name);
kfree(snap_name);
}
@@ -4110,8 +4158,8 @@
/* Look up the snapshot name, and make a copy */
snap_name = rbd_snap_name(rbd_dev, spec->snap_id);
- if (!snap_name) {
- ret = -ENOMEM;
+ if (IS_ERR(snap_name)) {
+ ret = PTR_ERR(snap_name);
goto out_err;
}
@@ -5059,23 +5107,6 @@
return (ssize_t)rc;
}
-static struct rbd_device *__rbd_get_dev(unsigned long dev_id)
-{
- struct list_head *tmp;
- struct rbd_device *rbd_dev;
-
- spin_lock(&rbd_dev_list_lock);
- list_for_each(tmp, &rbd_dev_list) {
- rbd_dev = list_entry(tmp, struct rbd_device, node);
- if (rbd_dev->dev_id == dev_id) {
- spin_unlock(&rbd_dev_list_lock);
- return rbd_dev;
- }
- }
- spin_unlock(&rbd_dev_list_lock);
- return NULL;
-}
-
static void rbd_dev_device_release(struct device *dev)
{
struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
@@ -5120,8 +5151,10 @@
size_t count)
{
struct rbd_device *rbd_dev = NULL;
- int target_id;
+ struct list_head *tmp;
+ int dev_id;
unsigned long ul;
+ bool already = false;
int ret;
ret = strict_strtoul(buf, 10, &ul);
@@ -5129,30 +5162,51 @@
return ret;
/* convert to int; abort if we lost anything in the conversion */
- target_id = (int) ul;
- if (target_id != ul)
+ dev_id = (int)ul;
+ if (dev_id != ul)
return -EINVAL;
mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
- rbd_dev = __rbd_get_dev(target_id);
- if (!rbd_dev) {
- ret = -ENOENT;
- goto done;
+ ret = -ENOENT;
+ spin_lock(&rbd_dev_list_lock);
+ list_for_each(tmp, &rbd_dev_list) {
+ rbd_dev = list_entry(tmp, struct rbd_device, node);
+ if (rbd_dev->dev_id == dev_id) {
+ ret = 0;
+ break;
+ }
}
-
- spin_lock_irq(&rbd_dev->lock);
- if (rbd_dev->open_count)
- ret = -EBUSY;
- else
- set_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags);
- spin_unlock_irq(&rbd_dev->lock);
- if (ret < 0)
+ if (!ret) {
+ spin_lock_irq(&rbd_dev->lock);
+ if (rbd_dev->open_count)
+ ret = -EBUSY;
+ else
+ already = test_and_set_bit(RBD_DEV_FLAG_REMOVING,
+ &rbd_dev->flags);
+ spin_unlock_irq(&rbd_dev->lock);
+ }
+ spin_unlock(&rbd_dev_list_lock);
+ if (ret < 0 || already)
goto done;
- rbd_bus_del_dev(rbd_dev);
+
ret = rbd_dev_header_watch_sync(rbd_dev, false);
if (ret)
rbd_warn(rbd_dev, "failed to cancel watch event (%d)\n", ret);
+
+ /*
+ * flush remaining watch callbacks - these must be complete
+ * before the osd_client is shutdown
+ */
+ dout("%s: flushing notifies", __func__);
+ ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
+ /*
+ * Don't free anything from rbd_dev->disk until after all
+ * notifies are completely processed. Otherwise
+ * rbd_bus_del_dev() will race with rbd_watch_cb(), resulting
+ * in a potential use after free of rbd_dev->disk or rbd_dev.
+ */
+ rbd_bus_del_dev(rbd_dev);
rbd_dev_image_release(rbd_dev);
module_put(THIS_MODULE);
ret = count;
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb..0ebadf9 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/genhd.h>
+#include <linux/cdrom.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
@@ -22,8 +23,8 @@
#define DRV_MODULE_NAME "sunvdc"
#define PFX DRV_MODULE_NAME ": "
-#define DRV_MODULE_VERSION "1.0"
-#define DRV_MODULE_RELDATE "June 25, 2007"
+#define DRV_MODULE_VERSION "1.1"
+#define DRV_MODULE_RELDATE "February 13, 2013"
static char version[] =
DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -32,7 +33,7 @@
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_MODULE_VERSION);
-#define VDC_TX_RING_SIZE 256
+#define VDC_TX_RING_SIZE 512
#define WAITING_FOR_LINK_UP 0x01
#define WAITING_FOR_TX_SPACE 0x02
@@ -65,11 +66,9 @@
u64 operations;
u32 vdisk_size;
u8 vdisk_type;
+ u8 vdisk_mtype;
char disk_name[32];
-
- struct vio_disk_geom geom;
- struct vio_disk_vtoc label;
};
static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
@@ -79,9 +78,16 @@
/* Ordered from largest major to lowest */
static struct vio_version vdc_versions[] = {
+ { .major = 1, .minor = 1 },
{ .major = 1, .minor = 0 },
};
+static inline int vdc_version_supported(struct vdc_port *port,
+ u16 major, u16 minor)
+{
+ return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
#define VDCBLK_NAME "vdisk"
static int vdc_major;
#define PARTITION_SHIFT 3
@@ -94,18 +100,54 @@
static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct gendisk *disk = bdev->bd_disk;
- struct vdc_port *port = disk->private_data;
+ sector_t nsect = get_capacity(disk);
+ sector_t cylinders = nsect;
- geo->heads = (u8) port->geom.num_hd;
- geo->sectors = (u8) port->geom.num_sec;
- geo->cylinders = port->geom.num_cyl;
+ geo->heads = 0xff;
+ geo->sectors = 0x3f;
+ sector_div(cylinders, geo->heads * geo->sectors);
+ geo->cylinders = cylinders;
+ if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+ geo->cylinders = 0xffff;
return 0;
}
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned command, unsigned long argument)
+{
+ int i;
+ struct gendisk *disk;
+
+ switch (command) {
+ case CDROMMULTISESSION:
+ pr_debug(PFX "Multisession CDs not supported\n");
+ for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+ if (put_user(0, (char __user *)(argument + i)))
+ return -EFAULT;
+ return 0;
+
+ case CDROM_GET_CAPABILITY:
+ disk = bdev->bd_disk;
+
+ if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+ return 0;
+ return -EINVAL;
+
+ default:
+ pr_debug(PFX "ioctl %08x not supported\n", command);
+ return -EINVAL;
+ }
+}
+
static const struct block_device_operations vdc_fops = {
.owner = THIS_MODULE,
.getgeo = vdc_getgeo,
+ .ioctl = vdc_ioctl,
};
static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +207,9 @@
struct vio_disk_attr_info *pkt = arg;
viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
- "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+ "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
pkt->tag.stype, pkt->operations,
- pkt->vdisk_size, pkt->vdisk_type,
+ pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
pkt->xfer_mode, pkt->vdisk_block_size,
pkt->max_xfer_size);
@@ -192,8 +234,11 @@
}
port->operations = pkt->operations;
- port->vdisk_size = pkt->vdisk_size;
port->vdisk_type = pkt->vdisk_type;
+ if (vdc_version_supported(port, 1, 1)) {
+ port->vdisk_size = pkt->vdisk_size;
+ port->vdisk_mtype = pkt->vdisk_mtype;
+ }
if (pkt->max_xfer_size < port->max_xfer_size)
port->max_xfer_size = pkt->max_xfer_size;
port->vdisk_block_size = pkt->vdisk_block_size;
@@ -236,7 +281,9 @@
__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
- if (blk_queue_stopped(port->disk->queue))
+ /* restart blk queue when ring is half emptied */
+ if (blk_queue_stopped(port->disk->queue) &&
+ vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
blk_start_queue(port->disk->queue);
}
@@ -388,12 +435,6 @@
for (i = 0; i < nsg; i++)
len += sg[i].length;
- if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
- blk_stop_queue(port->disk->queue);
- err = -ENOMEM;
- goto out;
- }
-
desc = vio_dring_cur(dr);
err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -433,21 +474,32 @@
port->req_id++;
dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
}
-out:
return err;
}
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
{
- while (1) {
- struct request *req = blk_fetch_request(q);
+ struct request *req;
- if (!req)
+ while ((req = blk_peek_request(rq)) != NULL) {
+ struct vdc_port *port;
+ struct vio_dring_state *dr;
+
+ port = req->rq_disk->private_data;
+ dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+ if (unlikely(vdc_tx_dring_avail(dr) < 1))
+ goto wait;
+
+ blk_start_request(req);
+
+ if (__send_request(req) < 0) {
+ blk_requeue_request(rq, req);
+wait:
+ /* Avoid pointless unplugs. */
+ blk_stop_queue(rq);
break;
-
- if (__send_request(req) < 0)
- __blk_end_request_all(req, -EIO);
+ }
}
}
@@ -656,25 +708,27 @@
if (comp.err)
return comp.err;
- err = generic_request(port, VD_OP_GET_VTOC,
- &port->label, sizeof(port->label));
- if (err < 0) {
- printk(KERN_ERR PFX "VD_OP_GET_VTOC returns error %d\n", err);
- return err;
- }
+ if (vdc_version_supported(port, 1, 1)) {
+ /* vdisk_size should be set during the handshake, if it wasn't
+ * then the underlying disk is reserved by another system
+ */
+ if (port->vdisk_size == -1)
+ return -ENODEV;
+ } else {
+ struct vio_disk_geom geom;
- err = generic_request(port, VD_OP_GET_DISKGEOM,
- &port->geom, sizeof(port->geom));
- if (err < 0) {
- printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
- "error %d\n", err);
- return err;
+ err = generic_request(port, VD_OP_GET_DISKGEOM,
+ &geom, sizeof(geom));
+ if (err < 0) {
+ printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+ "error %d\n", err);
+ return err;
+ }
+ port->vdisk_size = ((u64)geom.num_cyl *
+ (u64)geom.num_hd *
+ (u64)geom.num_sec);
}
- port->vdisk_size = ((u64)port->geom.num_cyl *
- (u64)port->geom.num_hd *
- (u64)port->geom.num_sec);
-
q = blk_init_queue(do_vdc_request, &port->vio.lock);
if (!q) {
printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -691,6 +745,10 @@
port->disk = g;
+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(q, PAGE_SIZE);
+
blk_queue_max_segments(q, port->ring_cookies);
blk_queue_max_hw_sectors(q, port->max_xfer_size);
g->major = vdc_major;
@@ -704,9 +762,32 @@
set_capacity(g, port->vdisk_size);
- printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+ if (vdc_version_supported(port, 1, 1)) {
+ switch (port->vdisk_mtype) {
+ case VD_MEDIA_TYPE_CD:
+ pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_DVD:
+ pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+ g->flags |= GENHD_FL_CD;
+ g->flags |= GENHD_FL_REMOVABLE;
+ set_disk_ro(g, 1);
+ break;
+
+ case VD_MEDIA_TYPE_FIXED:
+ pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+ break;
+ }
+ }
+
+ pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
g->disk_name,
- port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+ port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+ port->vio.ver.major, port->vio.ver.minor);
add_disk(g);
@@ -765,6 +846,7 @@
else
snprintf(port->disk_name, sizeof(port->disk_name),
VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+ port->vdisk_size = -1;
err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
vdc_versions, ARRAY_SIZE(vdc_versions),
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index dd5b2fe..03dd4aa 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -647,10 +647,22 @@
int status = BLKIF_RSP_OKAY;
struct block_device *bdev = blkif->vbd.bdev;
unsigned long secure;
-
- blkif->st_ds_req++;
+ struct phys_req preq;
xen_blkif_get(blkif);
+
+ preq.sector_number = req->u.discard.sector_number;
+ preq.nr_sects = req->u.discard.nr_sectors;
+
+ err = xen_vbd_translate(&preq, blkif, WRITE);
+ if (err) {
+ pr_warn(DRV_PFX "access denied: DISCARD [%llu->%llu] on dev=%04x\n",
+ preq.sector_number,
+ preq.sector_number + preq.nr_sects, blkif->vbd.pdevice);
+ goto fail_response;
+ }
+ blkif->st_ds_req++;
+
secure = (blkif->vbd.discard_secure &&
(req->u.discard.flag & BLKIF_DISCARD_SECURE)) ?
BLKDEV_DISCARD_SECURE : 0;
@@ -658,7 +670,7 @@
err = blkdev_issue_discard(bdev, req->u.discard.sector_number,
req->u.discard.nr_sectors,
GFP_KERNEL, secure);
-
+fail_response:
if (err == -EOPNOTSUPP) {
pr_debug(DRV_PFX "discard op failed, not supported\n");
status = BLKIF_RSP_EOPNOTSUPP;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index d89ef86..ddd9a09 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -75,6 +75,7 @@
struct blkif_request req;
struct request *request;
struct grant *grants_used[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
};
static DEFINE_MUTEX(blkfront_mutex);
@@ -98,13 +99,12 @@
enum blkif_state connected;
int ring_ref;
struct blkif_front_ring ring;
- struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
unsigned int evtchn, irq;
struct request_queue *rq;
struct work_struct work;
struct gnttab_free_callback callback;
struct blk_shadow shadow[BLK_RING_SIZE];
- struct list_head persistent_gnts;
+ struct list_head grants;
unsigned int persistent_gnts_c;
unsigned long shadow_free;
unsigned int feature_flush;
@@ -175,15 +175,17 @@
if (!gnt_list_entry)
goto out_of_memory;
- granted_page = alloc_page(GFP_NOIO);
- if (!granted_page) {
- kfree(gnt_list_entry);
- goto out_of_memory;
+ if (info->feature_persistent) {
+ granted_page = alloc_page(GFP_NOIO);
+ if (!granted_page) {
+ kfree(gnt_list_entry);
+ goto out_of_memory;
+ }
+ gnt_list_entry->pfn = page_to_pfn(granted_page);
}
- gnt_list_entry->pfn = page_to_pfn(granted_page);
gnt_list_entry->gref = GRANT_INVALID_REF;
- list_add(&gnt_list_entry->node, &info->persistent_gnts);
+ list_add(&gnt_list_entry->node, &info->grants);
i++;
}
@@ -191,9 +193,10 @@
out_of_memory:
list_for_each_entry_safe(gnt_list_entry, n,
- &info->persistent_gnts, node) {
+ &info->grants, node) {
list_del(&gnt_list_entry->node);
- __free_page(pfn_to_page(gnt_list_entry->pfn));
+ if (info->feature_persistent)
+ __free_page(pfn_to_page(gnt_list_entry->pfn));
kfree(gnt_list_entry);
i--;
}
@@ -202,14 +205,14 @@
}
static struct grant *get_grant(grant_ref_t *gref_head,
+ unsigned long pfn,
struct blkfront_info *info)
{
struct grant *gnt_list_entry;
unsigned long buffer_mfn;
- BUG_ON(list_empty(&info->persistent_gnts));
- gnt_list_entry = list_first_entry(&info->persistent_gnts, struct grant,
- node);
+ BUG_ON(list_empty(&info->grants));
+ gnt_list_entry = list_first_entry(&info->grants, struct grant, node);
list_del(&gnt_list_entry->node);
if (gnt_list_entry->gref != GRANT_INVALID_REF) {
@@ -220,6 +223,10 @@
/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
+ if (!info->feature_persistent) {
+ BUG_ON(!pfn);
+ gnt_list_entry->pfn = pfn;
+ }
buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
info->xbdev->otherend_id,
@@ -422,20 +429,20 @@
ring_req->u.discard.flag = 0;
} else {
ring_req->u.rw.nr_segments = blk_rq_map_sg(req->q, req,
- info->sg);
+ info->shadow[id].sg);
BUG_ON(ring_req->u.rw.nr_segments >
BLKIF_MAX_SEGMENTS_PER_REQUEST);
- for_each_sg(info->sg, sg, ring_req->u.rw.nr_segments, i) {
+ for_each_sg(info->shadow[id].sg, sg, ring_req->u.rw.nr_segments, i) {
fsect = sg->offset >> 9;
lsect = fsect + (sg->length >> 9) - 1;
- gnt_list_entry = get_grant(&gref_head, info);
+ gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
ref = gnt_list_entry->gref;
info->shadow[id].grants_used[i] = gnt_list_entry;
- if (rq_data_dir(req)) {
+ if (rq_data_dir(req) && info->feature_persistent) {
char *bvec_data;
void *shared_data;
@@ -828,16 +835,17 @@
blk_stop_queue(info->rq);
/* Remove all persistent grants */
- if (!list_empty(&info->persistent_gnts)) {
+ if (!list_empty(&info->grants)) {
list_for_each_entry_safe(persistent_gnt, n,
- &info->persistent_gnts, node) {
+ &info->grants, node) {
list_del(&persistent_gnt->node);
if (persistent_gnt->gref != GRANT_INVALID_REF) {
gnttab_end_foreign_access(persistent_gnt->gref,
0, 0UL);
info->persistent_gnts_c--;
}
- __free_page(pfn_to_page(persistent_gnt->pfn));
+ if (info->feature_persistent)
+ __free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
}
}
@@ -867,39 +875,57 @@
struct blkif_response *bret)
{
int i = 0;
- struct bio_vec *bvec;
- struct req_iterator iter;
- unsigned long flags;
+ struct scatterlist *sg;
char *bvec_data;
void *shared_data;
- unsigned int offset = 0;
+ int nseg;
- if (bret->operation == BLKIF_OP_READ) {
+ nseg = s->req.u.rw.nr_segments;
+
+ if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
/*
* Copy the data received from the backend into the bvec.
* Since bv_offset can be different than 0, and bv_len different
* than PAGE_SIZE, we have to keep track of the current offset,
* to be sure we are copying the data from the right shared page.
*/
- rq_for_each_segment(bvec, s->request, iter) {
- BUG_ON((bvec->bv_offset + bvec->bv_len) > PAGE_SIZE);
- if (bvec->bv_offset < offset)
- i++;
- BUG_ON(i >= s->req.u.rw.nr_segments);
+ for_each_sg(s->sg, sg, nseg, i) {
+ BUG_ON(sg->offset + sg->length > PAGE_SIZE);
shared_data = kmap_atomic(
pfn_to_page(s->grants_used[i]->pfn));
- bvec_data = bvec_kmap_irq(bvec, &flags);
- memcpy(bvec_data, shared_data + bvec->bv_offset,
- bvec->bv_len);
- bvec_kunmap_irq(bvec_data, &flags);
+ bvec_data = kmap_atomic(sg_page(sg));
+ memcpy(bvec_data + sg->offset,
+ shared_data + sg->offset,
+ sg->length);
+ kunmap_atomic(bvec_data);
kunmap_atomic(shared_data);
- offset = bvec->bv_offset + bvec->bv_len;
}
}
/* Add the persistent grant into the list of free grants */
- for (i = 0; i < s->req.u.rw.nr_segments; i++) {
- list_add(&s->grants_used[i]->node, &info->persistent_gnts);
- info->persistent_gnts_c++;
+ for (i = 0; i < nseg; i++) {
+ if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
+ /*
+ * If the grant is still mapped by the backend (the
+ * backend has chosen to make this grant persistent)
+ * we add it at the head of the list, so it will be
+ * reused first.
+ */
+ if (!info->feature_persistent)
+ pr_alert_ratelimited("backed has not unmapped grant: %u\n",
+ s->grants_used[i]->gref);
+ list_add(&s->grants_used[i]->node, &info->grants);
+ info->persistent_gnts_c++;
+ } else {
+ /*
+ * If the grant is not mapped by the backend we end the
+ * foreign access and add it to the tail of the list,
+ * so it will not be picked again unless we run out of
+ * persistent grants.
+ */
+ gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL);
+ s->grants_used[i]->gref = GRANT_INVALID_REF;
+ list_add_tail(&s->grants_used[i]->node, &info->grants);
+ }
}
}
@@ -1022,7 +1048,7 @@
struct blkfront_info *info)
{
struct blkif_sring *sring;
- int err;
+ int err, i;
info->ring_ref = GRANT_INVALID_REF;
@@ -1034,13 +1060,8 @@
SHARED_RING_INIT(sring);
FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);
- sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
-
- /* Allocate memory for grants */
- err = fill_grant_buffer(info, BLK_RING_SIZE *
- BLKIF_MAX_SEGMENTS_PER_REQUEST);
- if (err)
- goto fail;
+ for (i = 0; i < BLK_RING_SIZE; i++)
+ sg_init_table(info->shadow[i].sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);
err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
if (err < 0) {
@@ -1200,7 +1221,7 @@
spin_lock_init(&info->io_lock);
info->xbdev = dev;
info->vdevice = vdevice;
- INIT_LIST_HEAD(&info->persistent_gnts);
+ INIT_LIST_HEAD(&info->grants);
info->persistent_gnts_c = 0;
info->connected = BLKIF_STATE_DISCONNECTED;
INIT_WORK(&info->work, blkif_restart_queue);
@@ -1229,7 +1250,8 @@
int i;
struct blkif_request *req;
struct blk_shadow *copy;
- int j;
+ unsigned int persistent;
+ int j, rc;
/* Stage 1: Make a safe copy of the shadow state. */
copy = kmemdup(info->shadow, sizeof(info->shadow),
@@ -1244,6 +1266,24 @@
info->shadow_free = info->ring.req_prod_pvt;
info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff;
+ /* Check if the backend supports persistent grants */
+ rc = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-persistent", "%u", &persistent,
+ NULL);
+ if (rc)
+ info->feature_persistent = 0;
+ else
+ info->feature_persistent = persistent;
+
+ /* Allocate memory for grants */
+ rc = fill_grant_buffer(info, BLK_RING_SIZE *
+ BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ if (rc) {
+ xenbus_dev_fatal(info->xbdev, rc, "setting grant buffer failed");
+ kfree(copy);
+ return rc;
+ }
+
/* Stage 3: Find pending requests and requeue them. */
for (i = 0; i < BLK_RING_SIZE; i++) {
/* Not in use? */
@@ -1308,8 +1348,12 @@
blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);
err = talk_to_blkback(dev, info);
- if (info->connected == BLKIF_STATE_SUSPENDED && !err)
- err = blkif_recover(info);
+
+ /*
+ * We have to wait for the backend to switch to
+ * connected state, since we want to read which
+ * features it supports.
+ */
return err;
}
@@ -1413,9 +1457,16 @@
sectors);
set_capacity(info->gd, sectors);
revalidate_disk(info->gd);
+ return;
- /* fall through */
case BLKIF_STATE_SUSPENDED:
+ /*
+ * If we are recovering from suspension, we need to wait
+ * for the backend to announce it's features before
+ * reconnecting, we need to know if the backend supports
+ * persistent grants.
+ */
+ blkif_recover(info);
return;
default:
@@ -1483,6 +1534,14 @@
else
info->feature_persistent = persistent;
+ /* Allocate memory for grants */
+ err = fill_grant_buffer(info, BLK_RING_SIZE *
+ BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ if (err) {
+ xenbus_dev_fatal(info->xbdev, err, "setting grant buffer failed");
+ return;
+ }
+
err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
if (err) {
xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
@@ -1520,13 +1579,16 @@
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
case XenbusStateUnknown:
- case XenbusStateClosed:
break;
case XenbusStateConnected:
blkfront_connect(info);
break;
+ case XenbusStateClosed:
+ if (dev->state == XenbusStateClosed)
+ break;
+ /* Missed the backend's Closing state -- fallthrough */
case XenbusStateClosing:
blkfront_closing(info);
break;
diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
new file mode 100644
index 0000000..6489c0f
--- /dev/null
+++ b/drivers/block/zram/Kconfig
@@ -0,0 +1,34 @@
+config ZRAM
+ tristate "Compressed RAM block device support"
+ depends on BLOCK && SYSFS && ZSMALLOC
+ select LZO_COMPRESS
+ select LZO_DECOMPRESS
+ default n
+ help
+ Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
+ Pages written to these disks are compressed and stored in memory
+ itself. These disks allow very fast I/O and compression provides
+ good amounts of memory savings.
+
+ It has several use cases, for example: /tmp storage, use as swap
+ disks and maybe many more.
+
+ See zram.txt for more information.
+
+config ZRAM_LZ4_COMPRESS
+ bool "Enable LZ4 algorithm support"
+ depends on ZRAM
+ select LZ4_COMPRESS
+ select LZ4_DECOMPRESS
+ default n
+ help
+ This option enables LZ4 compression algorithm support. Compression
+ algorithm can be changed using `comp_algorithm' device attribute.
+
+config ZRAM_DEBUG
+ bool "Compressed RAM block device debug support"
+ depends on ZRAM
+ default n
+ help
+ This option adds additional debugging code to the compressed
+ RAM block device driver.
diff --git a/drivers/block/zram/Makefile b/drivers/block/zram/Makefile
new file mode 100644
index 0000000..be0763f
--- /dev/null
+++ b/drivers/block/zram/Makefile
@@ -0,0 +1,5 @@
+zram-y := zcomp_lzo.o zcomp.o zram_drv.o
+
+zram-$(CONFIG_ZRAM_LZ4_COMPRESS) += zcomp_lz4.o
+
+obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
new file mode 100644
index 0000000..f1ff39a
--- /dev/null
+++ b/drivers/block/zram/zcomp.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+
+#include "zcomp.h"
+#include "zcomp_lzo.h"
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+#include "zcomp_lz4.h"
+#endif
+
+/*
+ * single zcomp_strm backend
+ */
+struct zcomp_strm_single {
+ struct mutex strm_lock;
+ struct zcomp_strm *zstrm;
+};
+
+/*
+ * multi zcomp_strm backend
+ */
+struct zcomp_strm_multi {
+ /* protect strm list */
+ spinlock_t strm_lock;
+ /* max possible number of zstrm streams */
+ int max_strm;
+ /* number of available zstrm streams */
+ int avail_strm;
+ /* list of available strms */
+ struct list_head idle_strm;
+ wait_queue_head_t strm_wait;
+};
+
+static struct zcomp_backend *backends[] = {
+ &zcomp_lzo,
+#ifdef CONFIG_ZRAM_LZ4_COMPRESS
+ &zcomp_lz4,
+#endif
+ NULL
+};
+
+static struct zcomp_backend *find_backend(const char *compress)
+{
+ int i = 0;
+ while (backends[i]) {
+ if (sysfs_streq(compress, backends[i]->name))
+ break;
+ i++;
+ }
+ return backends[i];
+}
+
+static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ if (zstrm->private)
+ comp->backend->destroy(zstrm->private);
+ free_pages((unsigned long)zstrm->buffer, 1);
+ kfree(zstrm);
+}
+
+/*
+ * allocate new zcomp_strm structure with ->private initialized by
+ * backend, return NULL on error
+ */
+static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
+{
+ struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL);
+ if (!zstrm)
+ return NULL;
+
+ zstrm->private = comp->backend->create();
+ /*
+ * allocate 2 pages. 1 for compressed data, plus 1 extra for the
+ * case when compressed size is larger than the original one
+ */
+ zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
+ if (!zstrm->private || !zstrm->buffer) {
+ zcomp_strm_free(comp, zstrm);
+ zstrm = NULL;
+ }
+ return zstrm;
+}
+
+/*
+ * get idle zcomp_strm or wait until other process release
+ * (zcomp_strm_release()) one for us
+ */
+static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ while (1) {
+ spin_lock(&zs->strm_lock);
+ if (!list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ spin_unlock(&zs->strm_lock);
+ return zstrm;
+ }
+ /* zstrm streams limit reached, wait for idle stream */
+ if (zs->avail_strm >= zs->max_strm) {
+ spin_unlock(&zs->strm_lock);
+ wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+ continue;
+ }
+ /* allocate new zstrm stream */
+ zs->avail_strm++;
+ spin_unlock(&zs->strm_lock);
+
+ zstrm = zcomp_strm_alloc(comp);
+ if (!zstrm) {
+ spin_lock(&zs->strm_lock);
+ zs->avail_strm--;
+ spin_unlock(&zs->strm_lock);
+ wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+ continue;
+ }
+ break;
+ }
+ return zstrm;
+}
+
+/* add stream back to idle list and wake up waiter or free the stream */
+static void zcomp_strm_multi_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+
+ spin_lock(&zs->strm_lock);
+ if (zs->avail_strm <= zs->max_strm) {
+ list_add(&zstrm->list, &zs->idle_strm);
+ spin_unlock(&zs->strm_lock);
+ wake_up(&zs->strm_wait);
+ return;
+ }
+
+ zs->avail_strm--;
+ spin_unlock(&zs->strm_lock);
+ zcomp_strm_free(comp, zstrm);
+}
+
+/* change max_strm limit */
+static bool zcomp_strm_multi_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ spin_lock(&zs->strm_lock);
+ zs->max_strm = num_strm;
+ /*
+ * if user has lowered the limit and there are idle streams,
+ * immediately free as much streams (and memory) as we can.
+ */
+ while (zs->avail_strm > num_strm && !list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ zcomp_strm_free(comp, zstrm);
+ zs->avail_strm--;
+ }
+ spin_unlock(&zs->strm_lock);
+ return true;
+}
+
+static void zcomp_strm_multi_destroy(struct zcomp *comp)
+{
+ struct zcomp_strm_multi *zs = comp->stream;
+ struct zcomp_strm *zstrm;
+
+ while (!list_empty(&zs->idle_strm)) {
+ zstrm = list_entry(zs->idle_strm.next,
+ struct zcomp_strm, list);
+ list_del(&zstrm->list);
+ zcomp_strm_free(comp, zstrm);
+ }
+ kfree(zs);
+}
+
+static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm)
+{
+ struct zcomp_strm *zstrm;
+ struct zcomp_strm_multi *zs;
+
+ comp->destroy = zcomp_strm_multi_destroy;
+ comp->strm_find = zcomp_strm_multi_find;
+ comp->strm_release = zcomp_strm_multi_release;
+ comp->set_max_streams = zcomp_strm_multi_set_max_streams;
+ zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL);
+ if (!zs)
+ return -ENOMEM;
+
+ comp->stream = zs;
+ spin_lock_init(&zs->strm_lock);
+ INIT_LIST_HEAD(&zs->idle_strm);
+ init_waitqueue_head(&zs->strm_wait);
+ zs->max_strm = max_strm;
+ zs->avail_strm = 1;
+
+ zstrm = zcomp_strm_alloc(comp);
+ if (!zstrm) {
+ kfree(zs);
+ return -ENOMEM;
+ }
+ list_add(&zstrm->list, &zs->idle_strm);
+ return 0;
+}
+
+static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ mutex_lock(&zs->strm_lock);
+ return zs->zstrm;
+}
+
+static void zcomp_strm_single_release(struct zcomp *comp,
+ struct zcomp_strm *zstrm)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ mutex_unlock(&zs->strm_lock);
+}
+
+static bool zcomp_strm_single_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ /* zcomp_strm_single support only max_comp_streams == 1 */
+ return false;
+}
+
+static void zcomp_strm_single_destroy(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs = comp->stream;
+ zcomp_strm_free(comp, zs->zstrm);
+ kfree(zs);
+}
+
+static int zcomp_strm_single_create(struct zcomp *comp)
+{
+ struct zcomp_strm_single *zs;
+
+ comp->destroy = zcomp_strm_single_destroy;
+ comp->strm_find = zcomp_strm_single_find;
+ comp->strm_release = zcomp_strm_single_release;
+ comp->set_max_streams = zcomp_strm_single_set_max_streams;
+ zs = kmalloc(sizeof(struct zcomp_strm_single), GFP_KERNEL);
+ if (!zs)
+ return -ENOMEM;
+
+ comp->stream = zs;
+ mutex_init(&zs->strm_lock);
+ zs->zstrm = zcomp_strm_alloc(comp);
+ if (!zs->zstrm) {
+ kfree(zs);
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+/* show available compressors */
+ssize_t zcomp_available_show(const char *comp, char *buf)
+{
+ ssize_t sz = 0;
+ int i = 0;
+
+ while (backends[i]) {
+ if (sysfs_streq(comp, backends[i]->name))
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+ "[%s] ", backends[i]->name);
+ else
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz - 2,
+ "%s ", backends[i]->name);
+ i++;
+ }
+ sz += scnprintf(buf + sz, PAGE_SIZE - sz, "\n");
+ return sz;
+}
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm)
+{
+ return comp->set_max_streams(comp, num_strm);
+}
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp)
+{
+ return comp->strm_find(comp);
+}
+
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+ comp->strm_release(comp, zstrm);
+}
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+ const unsigned char *src, size_t *dst_len)
+{
+ return comp->backend->compress(src, zstrm->buffer, dst_len,
+ zstrm->private);
+}
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+ size_t src_len, unsigned char *dst)
+{
+ return comp->backend->decompress(src, src_len, dst);
+}
+
+void zcomp_destroy(struct zcomp *comp)
+{
+ comp->destroy(comp);
+ kfree(comp);
+}
+
+/*
+ * search available compressors for requested algorithm.
+ * allocate new zcomp and initialize it. return compressing
+ * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
+ * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
+ * case of allocation error.
+ */
+struct zcomp *zcomp_create(const char *compress, int max_strm)
+{
+ struct zcomp *comp;
+ struct zcomp_backend *backend;
+
+ backend = find_backend(compress);
+ if (!backend)
+ return ERR_PTR(-EINVAL);
+
+ comp = kzalloc(sizeof(struct zcomp), GFP_KERNEL);
+ if (!comp)
+ return ERR_PTR(-ENOMEM);
+
+ comp->backend = backend;
+ if (max_strm > 1)
+ zcomp_strm_multi_create(comp, max_strm);
+ else
+ zcomp_strm_single_create(comp);
+ if (!comp->stream) {
+ kfree(comp);
+ return ERR_PTR(-ENOMEM);
+ }
+ return comp;
+}
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
new file mode 100644
index 0000000..c59d1fc
--- /dev/null
+++ b/drivers/block/zram/zcomp.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_H_
+#define _ZCOMP_H_
+
+#include <linux/mutex.h>
+
+struct zcomp_strm {
+ /* compression/decompression buffer */
+ void *buffer;
+ /*
+ * The private data of the compression stream, only compression
+ * stream backend can touch this (e.g. compression algorithm
+ * working memory)
+ */
+ void *private;
+ /* used in multi stream backend, protected by backend strm_lock */
+ struct list_head list;
+};
+
+/* static compression backend */
+struct zcomp_backend {
+ int (*compress)(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private);
+
+ int (*decompress)(const unsigned char *src, size_t src_len,
+ unsigned char *dst);
+
+ void *(*create)(void);
+ void (*destroy)(void *private);
+
+ const char *name;
+};
+
+/* dynamic per-device compression frontend */
+struct zcomp {
+ void *stream;
+ struct zcomp_backend *backend;
+
+ struct zcomp_strm *(*strm_find)(struct zcomp *comp);
+ void (*strm_release)(struct zcomp *comp, struct zcomp_strm *zstrm);
+ bool (*set_max_streams)(struct zcomp *comp, int num_strm);
+ void (*destroy)(struct zcomp *comp);
+};
+
+ssize_t zcomp_available_show(const char *comp, char *buf);
+
+struct zcomp *zcomp_create(const char *comp, int max_strm);
+void zcomp_destroy(struct zcomp *comp);
+
+struct zcomp_strm *zcomp_strm_find(struct zcomp *comp);
+void zcomp_strm_release(struct zcomp *comp, struct zcomp_strm *zstrm);
+
+int zcomp_compress(struct zcomp *comp, struct zcomp_strm *zstrm,
+ const unsigned char *src, size_t *dst_len);
+
+int zcomp_decompress(struct zcomp *comp, const unsigned char *src,
+ size_t src_len, unsigned char *dst);
+
+bool zcomp_set_max_streams(struct zcomp *comp, int num_strm);
+#endif /* _ZCOMP_H_ */
diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c
new file mode 100644
index 0000000..f2afb7e
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lz4.h>
+
+#include "zcomp_lz4.h"
+
+static void *zcomp_lz4_create(void)
+{
+ return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void zcomp_lz4_destroy(void *private)
+{
+ kfree(private);
+}
+
+static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private)
+{
+ /* return : Success if return 0 */
+ return lz4_compress(src, PAGE_SIZE, dst, dst_len, private);
+}
+
+static int zcomp_lz4_decompress(const unsigned char *src, size_t src_len,
+ unsigned char *dst)
+{
+ size_t dst_len = PAGE_SIZE;
+ /* return : Success if return 0 */
+ return lz4_decompress_unknownoutputsize(src, src_len, dst, &dst_len);
+}
+
+struct zcomp_backend zcomp_lz4 = {
+ .compress = zcomp_lz4_compress,
+ .decompress = zcomp_lz4_decompress,
+ .create = zcomp_lz4_create,
+ .destroy = zcomp_lz4_destroy,
+ .name = "lz4",
+};
diff --git a/drivers/block/zram/zcomp_lz4.h b/drivers/block/zram/zcomp_lz4.h
new file mode 100644
index 0000000..60613fb
--- /dev/null
+++ b/drivers/block/zram/zcomp_lz4.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZ4_H_
+#define _ZCOMP_LZ4_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lz4;
+
+#endif /* _ZCOMP_LZ4_H_ */
diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c
new file mode 100644
index 0000000..da1bc47
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/lzo.h>
+
+#include "zcomp_lzo.h"
+
+static void *lzo_create(void)
+{
+ return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+}
+
+static void lzo_destroy(void *private)
+{
+ kfree(private);
+}
+
+static int lzo_compress(const unsigned char *src, unsigned char *dst,
+ size_t *dst_len, void *private)
+{
+ int ret = lzo1x_1_compress(src, PAGE_SIZE, dst, dst_len, private);
+ return ret == LZO_E_OK ? 0 : ret;
+}
+
+static int lzo_decompress(const unsigned char *src, size_t src_len,
+ unsigned char *dst)
+{
+ size_t dst_len = PAGE_SIZE;
+ int ret = lzo1x_decompress_safe(src, src_len, dst, &dst_len);
+ return ret == LZO_E_OK ? 0 : ret;
+}
+
+struct zcomp_backend zcomp_lzo = {
+ .compress = lzo_compress,
+ .decompress = lzo_decompress,
+ .create = lzo_create,
+ .destroy = lzo_destroy,
+ .name = "lzo",
+};
diff --git a/drivers/block/zram/zcomp_lzo.h b/drivers/block/zram/zcomp_lzo.h
new file mode 100644
index 0000000..128c580
--- /dev/null
+++ b/drivers/block/zram/zcomp_lzo.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2014 Sergey Senozhatsky.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ZCOMP_LZO_H_
+#define _ZCOMP_LZO_H_
+
+#include "zcomp.h"
+
+extern struct zcomp_backend zcomp_lzo;
+
+#endif /* _ZCOMP_LZO_H_ */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
new file mode 100644
index 0000000..45e2e85
--- /dev/null
+++ b/drivers/block/zram/zram_drv.c
@@ -0,0 +1,1162 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#define KMSG_COMPONENT "zram"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#ifdef CONFIG_ZRAM_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bio.h>
+#include <linux/bitops.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/device.h>
+#include <linux/genhd.h>
+#include <linux/highmem.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+#include <linux/err.h>
+
+#include "zram_drv.h"
+
+/* Globals */
+static int zram_major;
+static struct zram *zram_devices;
+static const char *default_compressor = "lzo";
+
+/* Module params (documentation at end) */
+static unsigned int num_devices = 1;
+
+#define ZRAM_ATTR_RO(name) \
+static ssize_t zram_attr_##name##_show(struct device *d, \
+ struct device_attribute *attr, char *b) \
+{ \
+ struct zram *zram = dev_to_zram(d); \
+ return scnprintf(b, PAGE_SIZE, "%llu\n", \
+ (u64)atomic64_read(&zram->stats.name)); \
+} \
+static struct device_attribute dev_attr_##name = \
+ __ATTR(name, S_IRUGO, zram_attr_##name##_show, NULL);
+
+static inline int init_done(struct zram *zram)
+{
+ return zram->meta != NULL;
+}
+
+static inline struct zram *dev_to_zram(struct device *dev)
+{
+ return (struct zram *)dev_to_disk(dev)->private_data;
+}
+
+static ssize_t disksize_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", zram->disksize);
+}
+
+static ssize_t initstate_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u32 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = init_done(zram);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t orig_data_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct zram *zram = dev_to_zram(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n",
+ (u64)(atomic64_read(&zram->stats.pages_stored)) << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_total_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ if (init_done(zram)) {
+ struct zram_meta *meta = zram->meta;
+ val = zs_get_total_pages(meta->mem_pool);
+ }
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t max_comp_streams_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = zram->max_comp_streams;
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t mem_limit_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ val = zram->limit_pages;
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_limit_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 limit;
+ char *tmp;
+ struct zram *zram = dev_to_zram(dev);
+
+ limit = memparse(buf, &tmp);
+ if (buf == tmp) /* no chars parsed, invalid input */
+ return -EINVAL;
+
+ down_write(&zram->init_lock);
+ zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+ up_write(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t mem_used_max_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u64 val = 0;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ if (init_done(zram))
+ val = atomic_long_read(&zram->stats.max_used_pages);
+ up_read(&zram->init_lock);
+
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT);
+}
+
+static ssize_t mem_used_max_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int err;
+ unsigned long val;
+ struct zram *zram = dev_to_zram(dev);
+
+ err = kstrtoul(buf, 10, &val);
+ if (err || val != 0)
+ return -EINVAL;
+
+ down_read(&zram->init_lock);
+ if (init_done(zram)) {
+ struct zram_meta *meta = zram->meta;
+ atomic_long_set(&zram->stats.max_used_pages,
+ zs_get_total_pages(meta->mem_pool));
+ }
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
+static ssize_t max_comp_streams_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int num;
+ struct zram *zram = dev_to_zram(dev);
+ int ret;
+
+ ret = kstrtoint(buf, 0, &num);
+ if (ret < 0)
+ return ret;
+ if (num < 1)
+ return -EINVAL;
+
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ if (!zcomp_set_max_streams(zram->comp, num)) {
+ pr_info("Cannot change max compression streams\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+ zram->max_comp_streams = num;
+ ret = len;
+out:
+ up_write(&zram->init_lock);
+ return ret;
+}
+
+static ssize_t comp_algorithm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ size_t sz;
+ struct zram *zram = dev_to_zram(dev);
+
+ down_read(&zram->init_lock);
+ sz = zcomp_available_show(zram->compressor, buf);
+ up_read(&zram->init_lock);
+
+ return sz;
+}
+
+static ssize_t comp_algorithm_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct zram *zram = dev_to_zram(dev);
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ up_write(&zram->init_lock);
+ pr_info("Can't change algorithm for initialized device\n");
+ return -EBUSY;
+ }
+ strlcpy(zram->compressor, buf, sizeof(zram->compressor));
+ up_write(&zram->init_lock);
+ return len;
+}
+
+/* flag operations needs meta->tb_lock */
+static int zram_test_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ return meta->table[index].value & BIT(flag);
+}
+
+static void zram_set_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].value |= BIT(flag);
+}
+
+static void zram_clear_flag(struct zram_meta *meta, u32 index,
+ enum zram_pageflags flag)
+{
+ meta->table[index].value &= ~BIT(flag);
+}
+
+static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
+{
+ return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+}
+
+static void zram_set_obj_size(struct zram_meta *meta,
+ u32 index, size_t size)
+{
+ unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;
+
+ meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
+}
+
+static inline int is_partial_io(struct bio_vec *bvec)
+{
+ return bvec->bv_len != PAGE_SIZE;
+}
+
+/*
+ * Check if request is within bounds and aligned on zram logical blocks.
+ */
+static inline int valid_io_request(struct zram *zram, struct bio *bio)
+{
+ u64 start, end, bound;
+
+ /* unaligned request */
+ if (unlikely(bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+ return 0;
+ if (unlikely(bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+ return 0;
+
+ start = bio->bi_sector;
+ end = start + (bio->bi_size >> SECTOR_SHIFT);
+ bound = zram->disksize >> SECTOR_SHIFT;
+ /* out of range range */
+ if (unlikely(start >= bound || end >= bound || start > end))
+ return 0;
+
+ /* I/O request is valid */
+ return 1;
+}
+
+static void zram_meta_free(struct zram_meta *meta, u64 disksize)
+{
+ size_t num_pages = disksize >> PAGE_SHIFT;
+ size_t index;
+
+ /* Free all pages that are still in this zram device */
+ for (index = 0; index < num_pages; index++) {
+ unsigned long handle = meta->table[index].handle;
+
+ if (!handle)
+ continue;
+
+ zs_free(meta->mem_pool, handle);
+ }
+
+ zs_destroy_pool(meta->mem_pool);
+ vfree(meta->table);
+ kfree(meta);
+}
+
+static struct zram_meta *zram_meta_alloc(u64 disksize)
+{
+ size_t num_pages;
+ struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
+ if (!meta)
+ goto out;
+
+ num_pages = disksize >> PAGE_SHIFT;
+ meta->table = vzalloc(num_pages * sizeof(*meta->table));
+ if (!meta->table) {
+ pr_err("Error allocating zram address table\n");
+ goto free_meta;
+ }
+
+ meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
+ if (!meta->mem_pool) {
+ pr_err("Error creating memory pool\n");
+ goto free_table;
+ }
+
+ return meta;
+
+free_table:
+ vfree(meta->table);
+free_meta:
+ kfree(meta);
+ meta = NULL;
+out:
+ return meta;
+}
+
+static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
+{
+ if (*offset + bvec->bv_len >= PAGE_SIZE)
+ (*index)++;
+ *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
+}
+
+static int page_zero_filled(void *ptr)
+{
+ unsigned int pos;
+ unsigned long *page;
+
+ page = (unsigned long *)ptr;
+
+ for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
+ if (page[pos])
+ return 0;
+ }
+
+ return 1;
+}
+
+static void handle_zero_page(struct bio_vec *bvec)
+{
+ struct page *page = bvec->bv_page;
+ void *user_mem;
+
+ user_mem = kmap_atomic(page);
+ if (is_partial_io(bvec))
+ memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
+ else
+ clear_page(user_mem);
+ kunmap_atomic(user_mem);
+
+ flush_dcache_page(page);
+}
+
+
+/*
+ * To protect concurrent access to the same index entry,
+ * caller should hold this table index entry's bit_spinlock to
+ * indicate this index entry is accessing.
+ */
+static void zram_free_page(struct zram *zram, size_t index)
+{
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle = meta->table[index].handle;
+
+ if (unlikely(!handle)) {
+ /*
+ * No memory is allocated for zero filled pages.
+ * Simply clear zero page flag.
+ */
+ if (zram_test_flag(meta, index, ZRAM_ZERO)) {
+ zram_clear_flag(meta, index, ZRAM_ZERO);
+ atomic64_dec(&zram->stats.zero_pages);
+ }
+ return;
+ }
+
+ zs_free(meta->mem_pool, handle);
+
+ atomic64_sub(zram_get_obj_size(meta, index),
+ &zram->stats.compr_data_size);
+ atomic64_dec(&zram->stats.pages_stored);
+
+ meta->table[index].handle = 0;
+ zram_set_obj_size(meta, index, 0);
+}
+
+static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
+{
+ int ret = 0;
+ unsigned char *cmem;
+ struct zram_meta *meta = zram->meta;
+ unsigned long handle;
+ size_t size;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ handle = meta->table[index].handle;
+ size = zram_get_obj_size(meta, index);
+
+ if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ clear_page(mem);
+ return 0;
+ }
+
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
+ if (size == PAGE_SIZE)
+ copy_page(mem, cmem);
+ else
+ ret = zcomp_decompress(zram->comp, cmem, size, mem);
+ zs_unmap_object(meta->mem_pool, handle);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret)) {
+ pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
+ u32 index, int offset, struct bio *bio)
+{
+ int ret;
+ struct page *page;
+ unsigned char *user_mem, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ page = bvec->bv_page;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ if (unlikely(!meta->table[index].handle) ||
+ zram_test_flag(meta, index, ZRAM_ZERO)) {
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ handle_zero_page(bvec);
+ return 0;
+ }
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ if (is_partial_io(bvec))
+ /* Use a temporary buffer to decompress the page */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+
+ user_mem = kmap_atomic(page);
+ if (!is_partial_io(bvec))
+ uncmem = user_mem;
+
+ if (!uncmem) {
+ pr_info("Unable to allocate temp memory\n");
+ ret = -ENOMEM;
+ goto out_cleanup;
+ }
+
+ ret = zram_decompress_page(zram, uncmem, index);
+ /* Should NEVER happen. Return bio error if it does. */
+ if (unlikely(ret))
+ goto out_cleanup;
+
+ if (is_partial_io(bvec))
+ memcpy(user_mem + bvec->bv_offset, uncmem + offset,
+ bvec->bv_len);
+
+ flush_dcache_page(page);
+ ret = 0;
+out_cleanup:
+ kunmap_atomic(user_mem);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+ return ret;
+}
+
+static inline void update_used_max(struct zram *zram,
+ const unsigned long pages)
+{
+ int old_max, cur_max;
+
+ old_max = atomic_long_read(&zram->stats.max_used_pages);
+
+ do {
+ cur_max = old_max;
+ if (pages > cur_max)
+ old_max = atomic_long_cmpxchg(
+ &zram->stats.max_used_pages, cur_max, pages);
+ } while (old_max != cur_max);
+}
+
+static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset)
+{
+ int ret = 0;
+ size_t clen;
+ unsigned long handle;
+ struct page *page;
+ unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
+ struct zram_meta *meta = zram->meta;
+ struct zcomp_strm *zstrm;
+ bool locked = false;
+ unsigned long alloced_pages;
+
+ page = bvec->bv_page;
+ if (is_partial_io(bvec)) {
+ /*
+ * This is a partial IO. We need to read the full page
+ * before to write the changes.
+ */
+ uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
+ if (!uncmem) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = zram_decompress_page(zram, uncmem, index);
+ if (ret)
+ goto out;
+ }
+
+ zstrm = zcomp_strm_find(zram->comp);
+ locked = true;
+ user_mem = kmap_atomic(page);
+
+ if (is_partial_io(bvec)) {
+ memcpy(uncmem + offset, user_mem + bvec->bv_offset,
+ bvec->bv_len);
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ } else {
+ uncmem = user_mem;
+ }
+
+ if (page_zero_filled(uncmem)) {
+ if (user_mem)
+ kunmap_atomic(user_mem);
+ /* Free memory associated with this sector now. */
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ zram_set_flag(meta, index, ZRAM_ZERO);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ atomic64_inc(&zram->stats.zero_pages);
+ ret = 0;
+ goto out;
+ }
+
+ ret = zcomp_compress(zram->comp, zstrm, uncmem, &clen);
+ if (!is_partial_io(bvec)) {
+ kunmap_atomic(user_mem);
+ user_mem = NULL;
+ uncmem = NULL;
+ }
+
+ if (unlikely(ret)) {
+ pr_err("Compression failed! err=%d\n", ret);
+ goto out;
+ }
+ src = zstrm->buffer;
+ if (unlikely(clen > max_zpage_size)) {
+ clen = PAGE_SIZE;
+ if (is_partial_io(bvec))
+ src = uncmem;
+ }
+
+ handle = zs_malloc(meta->mem_pool, clen);
+ if (!handle) {
+ pr_info("Error allocating memory for compressed page: %u, size=%zu\n",
+ index, clen);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ alloced_pages = zs_get_total_pages(meta->mem_pool);
+ if (zram->limit_pages && alloced_pages > zram->limit_pages) {
+ zs_free(meta->mem_pool, handle);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ update_used_max(zram, alloced_pages);
+
+ cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
+
+ if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
+ src = kmap_atomic(page);
+ copy_page(cmem, src);
+ kunmap_atomic(src);
+ } else {
+ memcpy(cmem, src, clen);
+ }
+
+ zcomp_strm_release(zram->comp, zstrm);
+ locked = false;
+ zs_unmap_object(meta->mem_pool, handle);
+
+ /*
+ * Free memory associated with this sector
+ * before overwriting unused sectors.
+ */
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+
+ meta->table[index].handle = handle;
+ zram_set_obj_size(meta, index, clen);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+
+ /* Update stats */
+ atomic64_add(clen, &zram->stats.compr_data_size);
+ atomic64_inc(&zram->stats.pages_stored);
+out:
+ if (locked)
+ zcomp_strm_release(zram->comp, zstrm);
+ if (is_partial_io(bvec))
+ kfree(uncmem);
+ return ret;
+}
+
+static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
+ int offset, struct bio *bio)
+{
+ int ret;
+ int rw = bio_data_dir(bio);
+
+ if (rw == READ) {
+ atomic64_inc(&zram->stats.num_reads);
+ ret = zram_bvec_read(zram, bvec, index, offset, bio);
+ } else {
+ atomic64_inc(&zram->stats.num_writes);
+ ret = zram_bvec_write(zram, bvec, index, offset);
+ }
+
+ if (unlikely(ret)) {
+ if (rw == READ)
+ atomic64_inc(&zram->stats.failed_reads);
+ else
+ atomic64_inc(&zram->stats.failed_writes);
+ }
+
+ return ret;
+}
+
+/*
+ * zram_bio_discard - handler on discard request
+ * @index: physical block index in PAGE_SIZE units
+ * @offset: byte offset within physical block
+ */
+static void zram_bio_discard(struct zram *zram, u32 index,
+ int offset, struct bio *bio)
+{
+ size_t n = bio->bi_size;
+ struct zram_meta *meta = zram->meta;
+
+ /*
+ * zram manages data in physical block size units. Because logical block
+ * size isn't identical with physical block size on some arch, we
+ * could get a discard request pointing to a specific offset within a
+ * certain physical block. Although we can handle this request by
+ * reading that physiclal block and decompressing and partially zeroing
+ * and re-compressing and then re-storing it, this isn't reasonable
+ * because our intent with a discard request is to save memory. So
+ * skipping this logical block is appropriate here.
+ */
+ if (offset) {
+ if (n <= (PAGE_SIZE - offset))
+ return;
+
+ n -= (PAGE_SIZE - offset);
+ index++;
+ }
+
+ while (n >= PAGE_SIZE) {
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ atomic64_inc(&zram->stats.notify_free);
+ index++;
+ n -= PAGE_SIZE;
+ }
+}
+
+static void zram_reset_device(struct zram *zram)
+{
+ down_write(&zram->init_lock);
+
+ zram->limit_pages = 0;
+
+ if (!init_done(zram)) {
+ up_write(&zram->init_lock);
+ return;
+ }
+
+ zcomp_destroy(zram->comp);
+ zram->max_comp_streams = 1;
+ zram_meta_free(zram->meta, zram->disksize);
+ zram->meta = NULL;
+ /* Reset stats */
+ memset(&zram->stats, 0, sizeof(zram->stats));
+
+ zram->disksize = 0;
+ up_write(&zram->init_lock);
+}
+
+static ssize_t disksize_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ u64 disksize;
+ struct zcomp *comp;
+ struct zram_meta *meta;
+ struct zram *zram = dev_to_zram(dev);
+ int err;
+
+ disksize = memparse(buf, NULL);
+ if (!disksize)
+ return -EINVAL;
+
+ disksize = PAGE_ALIGN(disksize);
+ meta = zram_meta_alloc(disksize);
+ if (!meta)
+ return -ENOMEM;
+
+ comp = zcomp_create(zram->compressor, zram->max_comp_streams);
+ if (IS_ERR(comp)) {
+ pr_info("Cannot initialise %s compressing backend\n",
+ zram->compressor);
+ err = PTR_ERR(comp);
+ goto out_free_meta;
+ }
+
+ down_write(&zram->init_lock);
+ if (init_done(zram)) {
+ pr_info("Cannot change disksize for initialized device\n");
+ err = -EBUSY;
+ goto out_destroy_comp;
+ }
+
+ zram->meta = meta;
+ zram->comp = comp;
+ zram->disksize = disksize;
+ set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
+ up_write(&zram->init_lock);
+
+ /*
+ * Revalidate disk out of the init_lock to avoid lockdep splat.
+ * It's okay because disk's capacity is protected by init_lock
+ * so that revalidate_disk always sees up-to-date capacity.
+ */
+ revalidate_disk(zram->disk);
+
+ return len;
+
+out_destroy_comp:
+ up_write(&zram->init_lock);
+ zcomp_destroy(comp);
+out_free_meta:
+ zram_meta_free(meta, disksize);
+ return err;
+}
+
+static ssize_t reset_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ int ret;
+ unsigned short do_reset;
+ struct zram *zram;
+ struct block_device *bdev;
+
+ zram = dev_to_zram(dev);
+ bdev = bdget_disk(zram->disk, 0);
+
+ if (!bdev)
+ return -ENOMEM;
+
+ mutex_lock(&bdev->bd_mutex);
+ /* Do not reset an active device! */
+ if (bdev->bd_holders) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ ret = kstrtou16(buf, 10, &do_reset);
+ if (ret)
+ goto out;
+
+ if (!do_reset) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* Make sure all pending I/O is finished */
+ fsync_bdev(bdev);
+ zram_reset_device(zram);
+ set_capacity(zram->disk, 0);
+
+ mutex_unlock(&bdev->bd_mutex);
+ revalidate_disk(zram->disk);
+ bdput(bdev);
+
+ return len;
+
+out:
+ mutex_unlock(&bdev->bd_mutex);
+ bdput(bdev);
+ return ret;
+}
+
+static void __zram_make_request(struct zram *zram, struct bio *bio)
+{
+ int i, offset;
+ u32 index;
+ struct bio_vec *bvec;
+
+
+ index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
+ offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
+
+ if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+ zram_bio_discard(zram, index, offset, bio);
+ bio_endio(bio, 0);
+ return;
+ }
+
+ bio_for_each_segment(bvec, bio, i) {
+ int max_transfer_size = PAGE_SIZE - offset;
+
+ if (bvec->bv_len > max_transfer_size) {
+ /*
+ * zram_bvec_rw() can only make operation on a single
+ * zram page. Split the bio vector.
+ */
+ struct bio_vec bv;
+
+ bv.bv_page = bvec->bv_page;
+ bv.bv_len = max_transfer_size;
+ bv.bv_offset = bvec->bv_offset;
+
+ if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
+ goto out;
+
+ bv.bv_len = bvec->bv_len - max_transfer_size;
+ bv.bv_offset += max_transfer_size;
+ if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
+ goto out;
+ } else
+ if (zram_bvec_rw(zram, bvec, index, offset, bio) < 0)
+ goto out;
+
+ update_position(&index, &offset, bvec);
+ }
+
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
+ bio_endio(bio, 0);
+ return;
+
+out:
+ bio_io_error(bio);
+}
+
+/*
+ * Handler function for all zram I/O requests.
+ */
+static void zram_make_request(struct request_queue *queue, struct bio *bio)
+{
+ struct zram *zram = queue->queuedata;
+
+ down_read(&zram->init_lock);
+ if (unlikely(!init_done(zram)))
+ goto error;
+
+ if (!valid_io_request(zram, bio)) {
+ atomic64_inc(&zram->stats.invalid_io);
+ goto error;
+ }
+
+ __zram_make_request(zram, bio);
+ up_read(&zram->init_lock);
+
+ return;
+
+error:
+ up_read(&zram->init_lock);
+ bio_io_error(bio);
+}
+
+static void zram_slot_free_notify(struct block_device *bdev,
+ unsigned long index)
+{
+ struct zram *zram;
+ struct zram_meta *meta;
+
+ zram = bdev->bd_disk->private_data;
+ meta = zram->meta;
+
+ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+ zram_free_page(zram, index);
+ bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+ atomic64_inc(&zram->stats.notify_free);
+}
+
+static const struct block_device_operations zram_devops = {
+ .swap_slot_free_notify = zram_slot_free_notify,
+ .owner = THIS_MODULE
+};
+
+static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
+ disksize_show, disksize_store);
+static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
+static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
+static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
+static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show,
+ mem_limit_store);
+static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show,
+ mem_used_max_store);
+static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
+ max_comp_streams_show, max_comp_streams_store);
+static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR,
+ comp_algorithm_show, comp_algorithm_store);
+
+ZRAM_ATTR_RO(num_reads);
+ZRAM_ATTR_RO(num_writes);
+ZRAM_ATTR_RO(failed_reads);
+ZRAM_ATTR_RO(failed_writes);
+ZRAM_ATTR_RO(invalid_io);
+ZRAM_ATTR_RO(notify_free);
+ZRAM_ATTR_RO(zero_pages);
+ZRAM_ATTR_RO(compr_data_size);
+
+static struct attribute *zram_disk_attrs[] = {
+ &dev_attr_disksize.attr,
+ &dev_attr_initstate.attr,
+ &dev_attr_reset.attr,
+ &dev_attr_num_reads.attr,
+ &dev_attr_num_writes.attr,
+ &dev_attr_failed_reads.attr,
+ &dev_attr_failed_writes.attr,
+ &dev_attr_invalid_io.attr,
+ &dev_attr_notify_free.attr,
+ &dev_attr_zero_pages.attr,
+ &dev_attr_orig_data_size.attr,
+ &dev_attr_compr_data_size.attr,
+ &dev_attr_mem_used_total.attr,
+ &dev_attr_mem_limit.attr,
+ &dev_attr_mem_used_max.attr,
+ &dev_attr_max_comp_streams.attr,
+ &dev_attr_comp_algorithm.attr,
+ NULL,
+};
+
+static struct attribute_group zram_disk_attr_group = {
+ .attrs = zram_disk_attrs,
+};
+
+static int create_device(struct zram *zram, int device_id)
+{
+ int ret = -ENOMEM;
+
+ init_rwsem(&zram->init_lock);
+
+ zram->queue = blk_alloc_queue(GFP_KERNEL);
+ if (!zram->queue) {
+ pr_err("Error allocating disk queue for device %d\n",
+ device_id);
+ goto out;
+ }
+
+ blk_queue_make_request(zram->queue, zram_make_request);
+ zram->queue->queuedata = zram;
+
+ /* gendisk structure */
+ zram->disk = alloc_disk(1);
+ if (!zram->disk) {
+ pr_warn("Error allocating disk structure for device %d\n",
+ device_id);
+ goto out_free_queue;
+ }
+
+ zram->disk->major = zram_major;
+ zram->disk->first_minor = device_id;
+ zram->disk->fops = &zram_devops;
+ zram->disk->queue = zram->queue;
+ zram->disk->private_data = zram;
+ snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
+
+ /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
+ set_capacity(zram->disk, 0);
+ /* zram devices sort of resembles non-rotational disks */
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
+ /*
+ * To ensure that we always get PAGE_SIZE aligned
+ * and n*PAGE_SIZED sized I/O requests.
+ */
+ blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
+ blk_queue_logical_block_size(zram->disk->queue,
+ ZRAM_LOGICAL_BLOCK_SIZE);
+ blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
+ blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
+ zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
+ zram->disk->queue->limits.max_discard_sectors = UINT_MAX;
+ /*
+ * zram_bio_discard() will clear all logical blocks if logical block
+ * size is identical with physical block size(PAGE_SIZE). But if it is
+ * different, we will skip discarding some parts of logical blocks in
+ * the part of the request range which isn't aligned to physical block
+ * size. So we can't ensure that all discarded logical blocks are
+ * zeroed.
+ */
+ if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
+ zram->disk->queue->limits.discard_zeroes_data = 1;
+ else
+ zram->disk->queue->limits.discard_zeroes_data = 0;
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
+ add_disk(zram->disk);
+
+ ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+ if (ret < 0) {
+ pr_warn("Error creating sysfs group");
+ goto out_free_disk;
+ }
+ strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));
+ zram->meta = NULL;
+ zram->max_comp_streams = 1;
+ return 0;
+
+out_free_disk:
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+out_free_queue:
+ blk_cleanup_queue(zram->queue);
+out:
+ return ret;
+}
+
+static void destroy_device(struct zram *zram)
+{
+ sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
+ &zram_disk_attr_group);
+
+ del_gendisk(zram->disk);
+ put_disk(zram->disk);
+
+ blk_cleanup_queue(zram->queue);
+}
+
+static int __init zram_init(void)
+{
+ int ret, dev_id;
+
+ if (num_devices > max_num_devices) {
+ pr_warn("Invalid value for num_devices: %u\n",
+ num_devices);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ zram_major = register_blkdev(0, "zram");
+ if (zram_major <= 0) {
+ pr_warn("Unable to get major number\n");
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Allocate the device array and initialize each one */
+ zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
+ if (!zram_devices) {
+ ret = -ENOMEM;
+ goto unregister;
+ }
+
+ for (dev_id = 0; dev_id < num_devices; dev_id++) {
+ ret = create_device(&zram_devices[dev_id], dev_id);
+ if (ret)
+ goto free_devices;
+ }
+
+ pr_info("Created %u device(s) ...\n", num_devices);
+
+ return 0;
+
+free_devices:
+ while (dev_id)
+ destroy_device(&zram_devices[--dev_id]);
+ kfree(zram_devices);
+unregister:
+ unregister_blkdev(zram_major, "zram");
+out:
+ return ret;
+}
+
+static void __exit zram_exit(void)
+{
+ int i;
+ struct zram *zram;
+
+ for (i = 0; i < num_devices; i++) {
+ zram = &zram_devices[i];
+
+ destroy_device(zram);
+ /*
+ * Shouldn't access zram->disk after destroy_device
+ * because destroy_device already released zram->disk.
+ */
+ zram_reset_device(zram);
+ }
+
+ unregister_blkdev(zram_major, "zram");
+
+ kfree(zram_devices);
+ pr_debug("Cleanup done!\n");
+}
+
+module_init(zram_init);
+module_exit(zram_exit);
+
+module_param(num_devices, uint, 0);
+MODULE_PARM_DESC(num_devices, "Number of zram devices");
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
+MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
new file mode 100644
index 0000000..b05a816
--- /dev/null
+++ b/drivers/block/zram/zram_drv.h
@@ -0,0 +1,123 @@
+/*
+ * Compressed RAM block device
+ *
+ * Copyright (C) 2008, 2009, 2010 Nitin Gupta
+ * 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the licence that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ *
+ */
+
+#ifndef _ZRAM_DRV_H_
+#define _ZRAM_DRV_H_
+
+#include <linux/spinlock.h>
+#include <linux/zsmalloc.h>
+
+#include "zcomp.h"
+
+/*
+ * Some arbitrary value. This is just to catch
+ * invalid value for num_devices module parameter.
+ */
+static const unsigned max_num_devices = 32;
+
+/*-- Configurable parameters */
+
+/*
+ * Pages that compress to size greater than this are stored
+ * uncompressed in memory.
+ */
+static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
+
+/*
+ * NOTE: max_zpage_size must be less than or equal to:
+ * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
+ * always return failure.
+ */
+
+/*-- End of configurable params */
+
+#define SECTOR_SHIFT 9
+#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
+#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
+#define ZRAM_LOGICAL_BLOCK_SHIFT 12
+#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
+#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
+ (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
+
+
+/*
+ * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * object size (excluding header), the higher bits is for
+ * zram_pageflags.
+ *
+ * zram is mainly used for memory efficiency so we want to keep memory
+ * footprint small so we can squeeze size and flags into a field.
+ * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
+ * the higher bits is for zram_pageflags.
+ */
+#define ZRAM_FLAG_SHIFT 24
+
+/* Flags for zram pages (table[page_no].value) */
+enum zram_pageflags {
+ /* Page consists entirely of zeros */
+ ZRAM_ZERO = ZRAM_FLAG_SHIFT,
+ ZRAM_ACCESS, /* page is now accessed */
+
+ __NR_ZRAM_PAGEFLAGS,
+};
+
+/*-- Data structures */
+
+/* Allocated for each disk page */
+struct zram_table_entry {
+ unsigned long handle;
+ unsigned long value;
+};
+
+struct zram_stats {
+ atomic64_t compr_data_size; /* compressed size of pages stored */
+ atomic64_t num_reads; /* failed + successful */
+ atomic64_t num_writes; /* --do-- */
+ atomic64_t failed_reads; /* can happen when memory is too low */
+ atomic64_t failed_writes; /* can happen when memory is too low */
+ atomic64_t invalid_io; /* non-page-aligned I/O requests */
+ atomic64_t notify_free; /* no. of swap slot free notifications */
+ atomic64_t zero_pages; /* no. of zero filled pages */
+ atomic64_t pages_stored; /* no. of pages currently stored */
+ atomic_long_t max_used_pages; /* no. of maximum pages stored */
+};
+
+struct zram_meta {
+ struct zram_table_entry *table;
+ struct zs_pool *mem_pool;
+};
+
+struct zram {
+ struct zram_meta *meta;
+ struct request_queue *queue;
+ struct gendisk *disk;
+ struct zcomp *comp;
+
+ /* Prevent concurrent execution of device init, reset and R/W request */
+ struct rw_semaphore init_lock;
+ /*
+ * This is the limit on amount of *uncompressed* worth of data
+ * we can store in a disk.
+ */
+ u64 disksize; /* bytes */
+ int max_comp_streams;
+ struct zram_stats stats;
+ /*
+ * the number of pages zram can consume for storing compressed data
+ */
+ unsigned long limit_pages;
+
+ char compressor[10];
+};
+#endif
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 11f467c..9c2c4ec 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -77,20 +77,28 @@
{ USB_DEVICE(0x0CF3, 0x3004) },
{ USB_DEVICE(0x0CF3, 0x3008) },
{ USB_DEVICE(0x0CF3, 0x311D) },
+ { USB_DEVICE(0x0CF3, 0x311E) },
+ { USB_DEVICE(0x0CF3, 0x311F) },
{ USB_DEVICE(0x0CF3, 0x817a) },
{ USB_DEVICE(0x13d3, 0x3375) },
{ USB_DEVICE(0x04CA, 0x3004) },
{ USB_DEVICE(0x04CA, 0x3005) },
{ USB_DEVICE(0x04CA, 0x3006) },
+ { USB_DEVICE(0x04CA, 0x3007) },
{ USB_DEVICE(0x04CA, 0x3008) },
{ USB_DEVICE(0x13d3, 0x3362) },
{ USB_DEVICE(0x0CF3, 0xE004) },
+ { USB_DEVICE(0x0CF3, 0xE005) },
{ USB_DEVICE(0x0930, 0x0219) },
{ USB_DEVICE(0x0489, 0xe057) },
{ USB_DEVICE(0x13d3, 0x3393) },
{ USB_DEVICE(0x0489, 0xe04e) },
{ USB_DEVICE(0x0489, 0xe056) },
{ USB_DEVICE(0x0489, 0xe04d) },
+ { USB_DEVICE(0x04c5, 0x1330) },
+ { USB_DEVICE(0x13d3, 0x3402) },
+ { USB_DEVICE(0x0cf3, 0x3121) },
+ { USB_DEVICE(0x0cf3, 0xe003) },
/* Atheros AR5BBU12 with sflash firmware */
{ USB_DEVICE(0x0489, 0xE02C) },
@@ -114,20 +122,28 @@
{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x311E), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x311F), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
/* Atheros AR5BBU22 with sflash firmware */
{ USB_DEVICE(0x0489, 0xE03C), .driver_info = BTUSB_ATH3012 },
@@ -139,6 +155,8 @@
#define USB_REQ_DFU_DNLOAD 1
#define BULK_SIZE 4096
#define FW_HDR_SIZE 20
+#define TIMEGAP_USEC_MIN 50
+#define TIMEGAP_USEC_MAX 100
static int ath3k_load_firmware(struct usb_device *udev,
const struct firmware *firmware)
@@ -169,6 +187,9 @@
count -= 20;
while (count) {
+ /* workaround the compatibility issue with xHCI controller*/
+ usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
size = min_t(uint, count, BULK_SIZE);
pipe = usb_sndbulkpipe(udev, 0x02);
memcpy(send_buf, firmware->data + sent, size);
@@ -193,24 +214,44 @@
static int ath3k_get_state(struct usb_device *udev, unsigned char *state)
{
- int pipe = 0;
+ int ret, pipe = 0;
+ char *buf;
+
+ buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
pipe = usb_rcvctrlpipe(udev, 0);
- return usb_control_msg(udev, pipe, ATH3K_GETSTATE,
- USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
- state, 0x01, USB_CTRL_SET_TIMEOUT);
+ ret = usb_control_msg(udev, pipe, ATH3K_GETSTATE,
+ USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
+ buf, sizeof(*buf), USB_CTRL_SET_TIMEOUT);
+
+ *state = *buf;
+ kfree(buf);
+
+ return ret;
}
static int ath3k_get_version(struct usb_device *udev,
struct ath3k_version *version)
{
- int pipe = 0;
+ int ret, pipe = 0;
+ struct ath3k_version *buf;
+ const int size = sizeof(*buf);
+
+ buf = kmalloc(size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
pipe = usb_rcvctrlpipe(udev, 0);
- return usb_control_msg(udev, pipe, ATH3K_GETVERSION,
- USB_TYPE_VENDOR | USB_DIR_IN, 0, 0, version,
- sizeof(struct ath3k_version),
- USB_CTRL_SET_TIMEOUT);
+ ret = usb_control_msg(udev, pipe, ATH3K_GETVERSION,
+ USB_TYPE_VENDOR | USB_DIR_IN, 0, 0,
+ buf, size, USB_CTRL_SET_TIMEOUT);
+
+ memcpy(version, buf, size);
+ kfree(buf);
+
+ return ret;
}
static int ath3k_load_fwfile(struct usb_device *udev,
@@ -245,6 +286,9 @@
count -= size;
while (count) {
+ /* workaround the compatibility issue with xHCI controller*/
+ usleep_range(TIMEGAP_USEC_MIN, TIMEGAP_USEC_MAX);
+
size = min_t(uint, count, BULK_SIZE);
pipe = usb_sndbulkpipe(udev, 0x02);
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 7a7e5f8..92b9853 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -49,6 +49,7 @@
#define BTUSB_WRONG_SCO_MTU 0x40
#define BTUSB_ATH3012 0x80
#define BTUSB_INTEL 0x100
+#define BTUSB_INTEL_BOOT 0x200
static struct usb_device_id btusb_table[] = {
/* Generic Bluetooth USB device */
@@ -57,6 +58,9 @@
/* Apple-specific (Broadcom) devices */
{ USB_VENDOR_AND_INTERFACE_INFO(0x05ac, 0xff, 0x01, 0x01) },
+ /* MediaTek MT76x0E */
+ { USB_DEVICE(0x0e8d, 0x763f) },
+
/* Broadcom SoftSailing reporting vendor specific */
{ USB_DEVICE(0x0a5c, 0x21e1) },
@@ -99,6 +103,7 @@
/* Broadcom BCM20702A0 */
{ USB_DEVICE(0x0b05, 0x17b5) },
+ { USB_DEVICE(0x0b05, 0x17cb) },
{ USB_DEVICE(0x04ca, 0x2003) },
{ USB_DEVICE(0x0489, 0xe042) },
{ USB_DEVICE(0x413c, 0x8197) },
@@ -109,6 +114,13 @@
/*Broadcom devices with vendor specific id */
{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) },
+ /* IMC Networks - Broadcom based */
+ { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01) },
+
+ /* Intel Bluetooth USB Bootloader (RAM module) */
+ { USB_DEVICE(0x8087, 0x0a5a),
+ .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC },
+
{ } /* Terminating entry */
};
@@ -137,20 +149,28 @@
{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x311f), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0x817a), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3006), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe056), .driver_info = BTUSB_ATH3012 },
{ USB_DEVICE(0x0489, 0xe04d), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0x3121), .driver_info = BTUSB_ATH3012 },
+ { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 },
/* Atheros AR5BBU12 with sflash firmware */
{ USB_DEVICE(0x0489, 0xe02c), .driver_info = BTUSB_IGNORE },
@@ -292,6 +312,9 @@
BT_ERR("%s corrupted event packet", hdev->name);
hdev->stat.err_rx++;
}
+ } else if (urb->status == -ENOENT) {
+ /* Avoid suspend failed when usb_kill_urb */
+ return;
}
if (!test_bit(BTUSB_INTR_RUNNING, &data->flags))
@@ -380,6 +403,9 @@
BT_ERR("%s corrupted ACL packet", hdev->name);
hdev->stat.err_rx++;
}
+ } else if (urb->status == -ENOENT) {
+ /* Avoid suspend failed when usb_kill_urb */
+ return;
}
if (!test_bit(BTUSB_BULK_RUNNING, &data->flags))
@@ -474,6 +500,9 @@
hdev->stat.err_rx++;
}
}
+ } else if (urb->status == -ENOENT) {
+ /* Avoid suspend failed when usb_kill_urb */
+ return;
}
if (!test_bit(BTUSB_ISOC_RUNNING, &data->flags))
@@ -1092,7 +1121,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s sending Intel patch command (0x%4.4x) failed (%ld)",
hdev->name, cmd->opcode, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
/* It ensures that the returned event matches the event data read from
@@ -1144,7 +1173,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s sending initial HCI reset command failed (%ld)",
hdev->name, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
kfree_skb(skb);
@@ -1158,7 +1187,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s reading Intel fw version command failed (%ld)",
hdev->name, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
if (skb->len != sizeof(*ver)) {
@@ -1216,7 +1245,7 @@
BT_ERR("%s entering Intel manufacturer mode failed (%ld)",
hdev->name, PTR_ERR(skb));
release_firmware(fw);
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
if (skb->data[0]) {
@@ -1273,7 +1302,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
hdev->name, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
kfree_skb(skb);
@@ -1289,7 +1318,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
hdev->name, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
kfree_skb(skb);
@@ -1307,7 +1336,7 @@
if (IS_ERR(skb)) {
BT_ERR("%s exiting Intel manufacturer mode failed (%ld)",
hdev->name, PTR_ERR(skb));
- return -PTR_ERR(skb);
+ return PTR_ERR(skb);
}
kfree_skb(skb);
@@ -1425,6 +1454,9 @@
if (id->driver_info & BTUSB_INTEL)
hdev->setup = btusb_setup_intel;
+ if (id->driver_info & BTUSB_INTEL_BOOT)
+ set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);
+
/* Interface numbers are hardcoded in the specification */
data->isoc = usb_ifnum_to_if(data->udev, 1);
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index b6154d5..db35c54 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -237,7 +237,7 @@
break;
to_remove--;
- seq = (seq - 1) % 8;
+ seq = (seq - 1) & 0x07;
}
if (seq != h5->rx_ack)
@@ -406,6 +406,7 @@
H5_HDR_PKT_TYPE(hdr) != HCI_3WIRE_LINK_PKT) {
BT_ERR("Non-link packet received in non-active state");
h5_reset_rx(h5);
+ return 0;
}
h5->rx_func = h5_rx_payload;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index bc68a44..c4d2f0e 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -118,10 +118,6 @@
int hci_uart_tx_wakeup(struct hci_uart *hu)
{
- struct tty_struct *tty = hu->tty;
- struct hci_dev *hdev = hu->hdev;
- struct sk_buff *skb;
-
if (test_and_set_bit(HCI_UART_SENDING, &hu->tx_state)) {
set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
return 0;
@@ -129,6 +125,22 @@
BT_DBG("");
+ schedule_work(&hu->write_work);
+
+ return 0;
+}
+
+static void hci_uart_write_work(struct work_struct *work)
+{
+ struct hci_uart *hu = container_of(work, struct hci_uart, write_work);
+ struct tty_struct *tty = hu->tty;
+ struct hci_dev *hdev = hu->hdev;
+ struct sk_buff *skb;
+
+ /* REVISIT: should we cope with bad skbs or ->write() returning
+ * and error value ?
+ */
+
restart:
clear_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
@@ -153,7 +165,6 @@
goto restart;
clear_bit(HCI_UART_SENDING, &hu->tx_state);
- return 0;
}
static void hci_uart_init_work(struct work_struct *work)
@@ -289,6 +300,7 @@
tty->receive_room = 65536;
INIT_WORK(&hu->init_ready, hci_uart_init_work);
+ INIT_WORK(&hu->write_work, hci_uart_write_work);
spin_lock_init(&hu->rx_lock);
@@ -326,6 +338,8 @@
if (hdev)
hci_uart_close(hdev);
+ cancel_work_sync(&hu->write_work);
+
if (test_and_clear_bit(HCI_UART_PROTO_SET, &hu->flags)) {
if (hdev) {
if (test_bit(HCI_UART_REGISTERED, &hu->flags))
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fffa61f..12df101 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -68,6 +68,7 @@
unsigned long hdev_flags;
struct work_struct init_ready;
+ struct work_struct write_work;
struct hci_uart_proto *proto;
void *priv;
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index b05ecab..5286e2d 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -26,4 +26,11 @@
help
Driver to enable OMAP interconnect error handling driver.
+
+config ARM_CCI
+ bool "ARM CCI driver support"
+ depends on ARM
+ help
+ Driver supporting the CCI cache coherent interconnect for ARM
+ platforms.
endmenu
diff --git a/drivers/bus/Makefile b/drivers/bus/Makefile
index 3c7b53c..670cea4 100644
--- a/drivers/bus/Makefile
+++ b/drivers/bus/Makefile
@@ -7,3 +7,5 @@
# Interconnect bus driver for OMAP SoCs.
obj-$(CONFIG_OMAP_INTERCONNECT) += omap_l3_smx.o omap_l3_noc.o
+# CCI cache coherent interconnect for ARM platforms
+obj-$(CONFIG_ARM_CCI) += arm-cci.o
diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
new file mode 100644
index 0000000..d9d954e
--- /dev/null
+++ b/drivers/bus/arm-cci.c
@@ -0,0 +1,947 @@
+/*
+ * CCI cache coherent interconnect driver
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/arm-cci.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+#include <asm/cacheflush.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+#include <asm/smp_plat.h>
+
+#define DRIVER_NAME "CCI"
+
+#define CCI_PORT_CTRL 0x0
+#define CCI_CTRL_STATUS 0xc
+
+#define CCI_ENABLE_SNOOP_REQ 0x1
+#define CCI_ENABLE_DVM_REQ 0x2
+#define CCI_ENABLE_REQ (CCI_ENABLE_SNOOP_REQ | CCI_ENABLE_DVM_REQ)
+
+struct cci_nb_ports {
+ unsigned int nb_ace;
+ unsigned int nb_ace_lite;
+};
+
+enum cci_ace_port_type {
+ ACE_INVALID_PORT = 0x0,
+ ACE_PORT,
+ ACE_LITE_PORT,
+};
+
+struct cci_ace_port {
+ void __iomem *base;
+ unsigned long phys;
+ enum cci_ace_port_type type;
+ struct device_node *dn;
+};
+
+static struct cci_ace_port *ports;
+static unsigned int nb_cci_ports;
+
+static void __iomem *cci_ctrl_base;
+static unsigned long cci_ctrl_phys;
+
+#ifdef CONFIG_HW_PERF_EVENTS
+
+static void __iomem *cci_pmu_base;
+
+#define CCI400_PMCR 0x0100
+
+#define CCI400_PMU_CYCLE_CNTR_BASE 0x0000
+#define CCI400_PMU_CNTR_BASE(idx) (CCI400_PMU_CYCLE_CNTR_BASE + (idx) * 0x1000)
+
+#define CCI400_PMCR_CEN 0x00000001
+#define CCI400_PMCR_RST 0x00000002
+#define CCI400_PMCR_CCR 0x00000004
+#define CCI400_PMCR_CCD 0x00000008
+#define CCI400_PMCR_EX 0x00000010
+#define CCI400_PMCR_DP 0x00000020
+#define CCI400_PMCR_NCNT_MASK 0x0000F800
+#define CCI400_PMCR_NCNT_SHIFT 11
+
+#define CCI400_PMU_EVT_SEL 0x000
+#define CCI400_PMU_CNTR 0x004
+#define CCI400_PMU_CNTR_CTRL 0x008
+#define CCI400_PMU_OVERFLOW 0x00C
+
+#define CCI400_PMU_OVERFLOW_FLAG 1
+
+enum cci400_perf_events {
+ CCI400_PMU_CYCLES = 0xFF
+};
+
+#define CCI400_PMU_EVENT_MASK 0xff
+#define CCI400_PMU_EVENT_SOURCE(event) ((event >> 5) & 0x7)
+#define CCI400_PMU_EVENT_CODE(event) (event & 0x1f)
+
+#define CCI400_PMU_EVENT_SOURCE_S0 0
+#define CCI400_PMU_EVENT_SOURCE_S4 4
+#define CCI400_PMU_EVENT_SOURCE_M0 5
+#define CCI400_PMU_EVENT_SOURCE_M2 7
+
+#define CCI400_PMU_EVENT_SLAVE_MIN 0x0
+#define CCI400_PMU_EVENT_SLAVE_MAX 0x13
+
+#define CCI400_PMU_EVENT_MASTER_MIN 0x14
+#define CCI400_PMU_EVENT_MASTER_MAX 0x1A
+
+#define CCI400_PMU_MAX_HW_EVENTS 5 /* CCI PMU has 4 counters + 1 cycle counter */
+
+#define CCI400_PMU_CYCLE_COUNTER_IDX 0
+#define CCI400_PMU_COUNTER0_IDX 1
+#define CCI400_PMU_COUNTER_LAST(cci_pmu) (CCI400_PMU_CYCLE_COUNTER_IDX + cci_pmu->num_events - 1)
+
+
+static struct perf_event *events[CCI400_PMU_MAX_HW_EVENTS];
+static unsigned long used_mask[BITS_TO_LONGS(CCI400_PMU_MAX_HW_EVENTS)];
+static struct pmu_hw_events cci_hw_events = {
+ .events = events,
+ .used_mask = used_mask,
+};
+
+static int cci_pmu_validate_hw_event(u8 hw_event)
+{
+ u8 ev_source = CCI400_PMU_EVENT_SOURCE(hw_event);
+ u8 ev_code = CCI400_PMU_EVENT_CODE(hw_event);
+
+ if (ev_source <= CCI400_PMU_EVENT_SOURCE_S4 &&
+ ev_code <= CCI400_PMU_EVENT_SLAVE_MAX)
+ return hw_event;
+ else if (CCI400_PMU_EVENT_SOURCE_M0 <= ev_source &&
+ ev_source <= CCI400_PMU_EVENT_SOURCE_M2 &&
+ CCI400_PMU_EVENT_MASTER_MIN <= ev_code &&
+ ev_code <= CCI400_PMU_EVENT_MASTER_MAX)
+ return hw_event;
+
+ return -EINVAL;
+}
+
+static inline int cci_pmu_counter_is_valid(struct arm_pmu *cci_pmu, int idx)
+{
+ return CCI400_PMU_CYCLE_COUNTER_IDX <= idx &&
+ idx <= CCI400_PMU_COUNTER_LAST(cci_pmu);
+}
+
+static inline u32 cci_pmu_read_register(int idx, unsigned int offset)
+{
+ return readl_relaxed(cci_pmu_base + CCI400_PMU_CNTR_BASE(idx) + offset);
+}
+
+static inline void cci_pmu_write_register(u32 value, int idx, unsigned int offset)
+{
+ return writel_relaxed(value, cci_pmu_base + CCI400_PMU_CNTR_BASE(idx) + offset);
+}
+
+static inline void cci_pmu_disable_counter(int idx)
+{
+ cci_pmu_write_register(0, idx, CCI400_PMU_CNTR_CTRL);
+}
+
+static inline void cci_pmu_enable_counter(int idx)
+{
+ cci_pmu_write_register(1, idx, CCI400_PMU_CNTR_CTRL);
+}
+
+static inline void cci_pmu_select_event(int idx, unsigned long event)
+{
+ event &= CCI400_PMU_EVENT_MASK;
+ cci_pmu_write_register(event, idx, CCI400_PMU_EVT_SEL);
+}
+
+static u32 cci_pmu_get_max_counters(void)
+{
+ u32 n_cnts = (readl_relaxed(cci_ctrl_base + CCI400_PMCR) &
+ CCI400_PMCR_NCNT_MASK) >> CCI400_PMCR_NCNT_SHIFT;
+
+ /* add 1 for cycle counter */
+ return n_cnts + 1;
+}
+
+static struct pmu_hw_events *cci_pmu_get_hw_events(void)
+{
+ return &cci_hw_events;
+}
+
+static int cci_pmu_get_event_idx(struct pmu_hw_events *hw, struct perf_event *event)
+{
+ struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hw_event = &event->hw;
+ unsigned long cci_event = hw_event->config_base & CCI400_PMU_EVENT_MASK;
+ int idx;
+
+ if (cci_event == CCI400_PMU_CYCLES) {
+ if (test_and_set_bit(CCI400_PMU_CYCLE_COUNTER_IDX, hw->used_mask))
+ return -EAGAIN;
+
+ return CCI400_PMU_CYCLE_COUNTER_IDX;
+ }
+
+ for (idx = CCI400_PMU_COUNTER0_IDX; idx <= CCI400_PMU_COUNTER_LAST(cci_pmu); ++idx) {
+ if (!test_and_set_bit(idx, hw->used_mask))
+ return idx;
+ }
+
+ /* No counters available */
+ return -EAGAIN;
+}
+
+static int cci_pmu_map_event(struct perf_event *event)
+{
+ int mapping;
+ u8 config = event->attr.config & CCI400_PMU_EVENT_MASK;
+
+ if (event->attr.type < PERF_TYPE_MAX)
+ return -ENOENT;
+
+ /* 0xff is used to represent CCI Cycles */
+ if (config == 0xff)
+ mapping = config;
+ else
+ mapping = cci_pmu_validate_hw_event(config);
+
+ return mapping;
+}
+
+static int cci_pmu_request_irq(struct arm_pmu *cci_pmu, irq_handler_t handler)
+{
+ int irq, err, i = 0;
+ struct platform_device *pmu_device = cci_pmu->plat_device;
+
+ if (unlikely(!pmu_device))
+ return -ENODEV;
+
+ /* CCI exports 6 interrupts - 1 nERRORIRQ + 5 nEVNTCNTOVERFLOW (PMU)
+ nERRORIRQ will be handled by secure firmware on TC2. So we
+ assume that all CCI interrupts listed in the linux device
+ tree are PMU interrupts.
+
+ The following code should then be able to handle different routing
+ of the CCI PMU interrupts.
+ */
+ while ((irq = platform_get_irq(pmu_device, i)) > 0) {
+ err = request_irq(irq, handler, 0, "arm-cci-pmu", cci_pmu);
+ if (err) {
+ dev_err(&pmu_device->dev, "unable to request IRQ%d for ARM CCI PMU counters\n",
+ irq);
+ return err;
+ }
+ i++;
+ }
+
+ return 0;
+}
+
+static irqreturn_t cci_pmu_handle_irq(int irq_num, void *dev)
+{
+ struct arm_pmu *cci_pmu = (struct arm_pmu *)dev;
+ struct pmu_hw_events *events = cci_pmu->get_hw_events();
+ struct perf_sample_data data;
+ struct pt_regs *regs;
+ int idx;
+
+ regs = get_irq_regs();
+
+ /* Iterate over counters and update the corresponding perf events.
+ This should work regardless of whether we have per-counter overflow
+ interrupt or a combined overflow interrupt. */
+ for (idx = CCI400_PMU_CYCLE_COUNTER_IDX; idx <= CCI400_PMU_COUNTER_LAST(cci_pmu); idx++) {
+ struct perf_event *event = events->events[idx];
+ struct hw_perf_event *hw_counter;
+
+ if (!event)
+ continue;
+
+ hw_counter = &event->hw;
+
+ /* Did this counter overflow? */
+ if (!(cci_pmu_read_register(idx, CCI400_PMU_OVERFLOW) & CCI400_PMU_OVERFLOW_FLAG))
+ continue;
+ cci_pmu_write_register(CCI400_PMU_OVERFLOW_FLAG, idx, CCI400_PMU_OVERFLOW);
+
+ armpmu_event_update(event);
+ perf_sample_data_init(&data, 0, hw_counter->last_period);
+ if (!armpmu_event_set_period(event))
+ continue;
+
+ if (perf_event_overflow(event, &data, regs))
+ cci_pmu->disable(event);
+ }
+
+ irq_work_run();
+ return IRQ_HANDLED;
+}
+
+static void cci_pmu_free_irq(struct arm_pmu *cci_pmu)
+{
+ int irq, i = 0;
+ struct platform_device *pmu_device = cci_pmu->plat_device;
+
+ while ((irq = platform_get_irq(pmu_device, i)) > 0) {
+ free_irq(irq, cci_pmu);
+ i++;
+ }
+}
+
+static void cci_pmu_enable_event(struct perf_event *event)
+{
+ unsigned long flags;
+ struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = cci_pmu->get_hw_events();
+ struct hw_perf_event *hw_counter = &event->hw;
+ int idx = hw_counter->idx;
+
+ if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+ dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+ /* Configure the event to count, unless you are counting cycles */
+ if (idx != CCI400_PMU_CYCLE_COUNTER_IDX)
+ cci_pmu_select_event(idx, hw_counter->config_base);
+
+ cci_pmu_enable_counter(idx);
+
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_disable_event(struct perf_event *event)
+{
+ unsigned long flags;
+ struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+ struct pmu_hw_events *events = cci_pmu->get_hw_events();
+ struct hw_perf_event *hw_counter = &event->hw;
+ int idx = hw_counter->idx;
+
+ if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+ dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+ cci_pmu_disable_counter(idx);
+
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_start(struct arm_pmu *cci_pmu)
+{
+ u32 val;
+ unsigned long flags;
+ struct pmu_hw_events *events = cci_pmu->get_hw_events();
+
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+ /* Enable all the PMU counters. */
+ val = readl(cci_ctrl_base + CCI400_PMCR) | CCI400_PMCR_CEN;
+ writel(val, cci_ctrl_base + CCI400_PMCR);
+
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void cci_pmu_stop(struct arm_pmu *cci_pmu)
+{
+ u32 val;
+ unsigned long flags;
+ struct pmu_hw_events *events = cci_pmu->get_hw_events();
+
+ raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+ /* Disable all the PMU counters. */
+ val = readl(cci_ctrl_base + CCI400_PMCR) & ~CCI400_PMCR_CEN;
+ writel(val, cci_ctrl_base + CCI400_PMCR);
+
+ raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static u32 cci_pmu_read_counter(struct perf_event *event)
+{
+ struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hw_counter = &event->hw;
+ int idx = hw_counter->idx;
+ u32 value;
+
+ if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx))) {
+ dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+ return 0;
+ }
+ value = cci_pmu_read_register(idx, CCI400_PMU_CNTR);
+
+ return value;
+}
+
+static void cci_pmu_write_counter(struct perf_event *event, u32 value)
+{
+ struct arm_pmu *cci_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hw_counter = &event->hw;
+ int idx = hw_counter->idx;
+
+ if (unlikely(!cci_pmu_counter_is_valid(cci_pmu, idx)))
+ dev_err(&cci_pmu->plat_device->dev, "Invalid CCI PMU counter %d\n", idx);
+ else
+ cci_pmu_write_register(value, idx, CCI400_PMU_CNTR);
+}
+
+static struct arm_pmu cci_pmu = {
+ .name = DRIVER_NAME,
+ .max_period = (1LLU << 32) - 1,
+ .get_hw_events = cci_pmu_get_hw_events,
+ .get_event_idx = cci_pmu_get_event_idx,
+ .map_event = cci_pmu_map_event,
+ .request_irq = cci_pmu_request_irq,
+ .handle_irq = cci_pmu_handle_irq,
+ .free_irq = cci_pmu_free_irq,
+ .enable = cci_pmu_enable_event,
+ .disable = cci_pmu_disable_event,
+ .start = cci_pmu_start,
+ .stop = cci_pmu_stop,
+ .read_counter = cci_pmu_read_counter,
+ .write_counter = cci_pmu_write_counter,
+};
+
+static int cci_pmu_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ cci_pmu_base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(cci_pmu_base))
+ return PTR_ERR(cci_pmu_base);
+
+ cci_pmu.plat_device = pdev;
+ cci_pmu.num_events = cci_pmu_get_max_counters();
+ raw_spin_lock_init(&cci_hw_events.pmu_lock);
+ cpumask_setall(&cci_pmu.valid_cpus);
+
+ return armpmu_register(&cci_pmu, -1);
+}
+
+static const struct of_device_id arm_cci_pmu_matches[] = {
+ {.compatible = "arm,cci-400-pmu"},
+ {},
+};
+
+static struct platform_driver cci_pmu_platform_driver = {
+ .driver = {
+ .name = DRIVER_NAME,
+ .of_match_table = arm_cci_pmu_matches,
+ },
+ .probe = cci_pmu_probe,
+};
+
+static int __init cci_pmu_init(void)
+{
+ if (platform_driver_register(&cci_pmu_platform_driver))
+ WARN(1, "unable to register CCI platform driver\n");
+ return 0;
+}
+
+#else
+
+static int __init cci_pmu_init(void)
+{
+ return 0;
+}
+
+#endif /* CONFIG_HW_PERF_EVENTS */
+
+struct cpu_port {
+ u64 mpidr;
+ u32 port;
+};
+
+/*
+ * Use the port MSB as valid flag, shift can be made dynamic
+ * by computing number of bits required for port indexes.
+ * Code disabling CCI cpu ports runs with D-cache invalidated
+ * and SCTLR bit clear so data accesses must be kept to a minimum
+ * to improve performance; for now shift is left static to
+ * avoid one more data access while disabling the CCI port.
+ */
+#define PORT_VALID_SHIFT 31
+#define PORT_VALID (0x1 << PORT_VALID_SHIFT)
+
+static inline void init_cpu_port(struct cpu_port *port, u32 index, u64 mpidr)
+{
+ port->port = PORT_VALID | index;
+ port->mpidr = mpidr;
+}
+
+static inline bool cpu_port_is_valid(struct cpu_port *port)
+{
+ return !!(port->port & PORT_VALID);
+}
+
+static inline bool cpu_port_match(struct cpu_port *port, u64 mpidr)
+{
+ return port->mpidr == (mpidr & MPIDR_HWID_BITMASK);
+}
+
+static struct cpu_port cpu_port[NR_CPUS];
+
+/**
+ * __cci_ace_get_port - Function to retrieve the port index connected to
+ * a cpu or device.
+ *
+ * @dn: device node of the device to look-up
+ * @type: port type
+ *
+ * Return value:
+ * - CCI port index if success
+ * - -ENODEV if failure
+ */
+static int __cci_ace_get_port(struct device_node *dn, int type)
+{
+ int i;
+ bool ace_match;
+ struct device_node *cci_portn;
+
+ cci_portn = of_parse_phandle(dn, "cci-control-port", 0);
+ for (i = 0; i < nb_cci_ports; i++) {
+ ace_match = ports[i].type == type;
+ if (ace_match && cci_portn == ports[i].dn)
+ return i;
+ }
+ return -ENODEV;
+}
+
+int cci_ace_get_port(struct device_node *dn)
+{
+ return __cci_ace_get_port(dn, ACE_LITE_PORT);
+}
+EXPORT_SYMBOL_GPL(cci_ace_get_port);
+
+static void __init cci_ace_init_ports(void)
+{
+ int port, ac, cpu;
+ u64 hwid;
+ const u32 *cell;
+ struct device_node *cpun, *cpus;
+
+ cpus = of_find_node_by_path("/cpus");
+ if (WARN(!cpus, "Missing cpus node, bailing out\n"))
+ return;
+
+ if (WARN_ON(of_property_read_u32(cpus, "#address-cells", &ac)))
+ ac = of_n_addr_cells(cpus);
+
+ /*
+ * Port index look-up speeds up the function disabling ports by CPU,
+ * since the logical to port index mapping is done once and does
+ * not change after system boot.
+ * The stashed index array is initialized for all possible CPUs
+ * at probe time.
+ */
+ for_each_child_of_node(cpus, cpun) {
+ if (of_node_cmp(cpun->type, "cpu"))
+ continue;
+ cell = of_get_property(cpun, "reg", NULL);
+ if (WARN(!cell, "%s: missing reg property\n", cpun->full_name))
+ continue;
+
+ hwid = of_read_number(cell, ac);
+ cpu = get_logical_index(hwid & MPIDR_HWID_BITMASK);
+
+ if (cpu < 0 || !cpu_possible(cpu))
+ continue;
+ port = __cci_ace_get_port(cpun, ACE_PORT);
+ if (port < 0)
+ continue;
+
+ init_cpu_port(&cpu_port[cpu], port, cpu_logical_map(cpu));
+ }
+
+ for_each_possible_cpu(cpu) {
+ WARN(!cpu_port_is_valid(&cpu_port[cpu]),
+ "CPU %u does not have an associated CCI port\n",
+ cpu);
+ }
+}
+/*
+ * Functions to enable/disable a CCI interconnect slave port
+ *
+ * They are called by low-level power management code to disable slave
+ * interfaces snoops and DVM broadcast.
+ * Since they may execute with cache data allocation disabled and
+ * after the caches have been cleaned and invalidated the functions provide
+ * no explicit locking since they may run with D-cache disabled, so normal
+ * cacheable kernel locks based on ldrex/strex may not work.
+ * Locking has to be provided by BSP implementations to ensure proper
+ * operations.
+ */
+
+/**
+ * cci_port_control() - function to control a CCI port
+ *
+ * @port: index of the port to setup
+ * @enable: if true enables the port, if false disables it
+ */
+static void notrace cci_port_control(unsigned int port, bool enable)
+{
+ void __iomem *base = ports[port].base;
+
+ writel_relaxed(enable ? CCI_ENABLE_REQ : 0, base + CCI_PORT_CTRL);
+ /*
+ * This function is called from power down procedures
+ * and must not execute any instruction that might
+ * cause the processor to be put in a quiescent state
+ * (eg wfi). Hence, cpu_relax() can not be added to this
+ * read loop to optimize power, since it might hide possibly
+ * disruptive operations.
+ */
+ while (readl_relaxed(cci_ctrl_base + CCI_CTRL_STATUS) & 0x1)
+ ;
+}
+
+/**
+ * cci_disable_port_by_cpu() - function to disable a CCI port by CPU
+ * reference
+ *
+ * @mpidr: mpidr of the CPU whose CCI port should be disabled
+ *
+ * Disabling a CCI port for a CPU implies disabling the CCI port
+ * controlling that CPU cluster. Code disabling CPU CCI ports
+ * must make sure that the CPU running the code is the last active CPU
+ * in the cluster ie all other CPUs are quiescent in a low power state.
+ *
+ * Return:
+ * 0 on success
+ * -ENODEV on port look-up failure
+ */
+int notrace cci_disable_port_by_cpu(u64 mpidr)
+{
+ int cpu;
+ bool is_valid;
+ for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
+ is_valid = cpu_port_is_valid(&cpu_port[cpu]);
+ if (is_valid && cpu_port_match(&cpu_port[cpu], mpidr)) {
+ cci_port_control(cpu_port[cpu].port, false);
+ return 0;
+ }
+ }
+ return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(cci_disable_port_by_cpu);
+
+/**
+ * cci_enable_port_for_self() - enable a CCI port for calling CPU
+ *
+ * Enabling a CCI port for the calling CPU implies enabling the CCI
+ * port controlling that CPU's cluster. Caller must make sure that the
+ * CPU running the code is the first active CPU in the cluster and all
+ * other CPUs are quiescent in a low power state or waiting for this CPU
+ * to complete the CCI initialization.
+ *
+ * Because this is called when the MMU is still off and with no stack,
+ * the code must be position independent and ideally rely on callee
+ * clobbered registers only. To achieve this we must code this function
+ * entirely in assembler.
+ *
+ * On success this returns with the proper CCI port enabled. In case of
+ * any failure this never returns as the inability to enable the CCI is
+ * fatal and there is no possible recovery at this stage.
+ */
+asmlinkage void __naked cci_enable_port_for_self(void)
+{
+ asm volatile ("\n"
+
+" mrc p15, 0, r0, c0, c0, 5 @ get MPIDR value \n"
+" and r0, r0, #"__stringify(MPIDR_HWID_BITMASK)" \n"
+" adr r1, 5f \n"
+" ldr r2, [r1] \n"
+" add r1, r1, r2 @ &cpu_port \n"
+" add ip, r1, %[sizeof_cpu_port] \n"
+
+ /* Loop over the cpu_port array looking for a matching MPIDR */
+"1: ldr r2, [r1, %[offsetof_cpu_port_mpidr_lsb]] \n"
+" cmp r2, r0 @ compare MPIDR \n"
+" bne 2f \n"
+
+ /* Found a match, now test port validity */
+" ldr r3, [r1, %[offsetof_cpu_port_port]] \n"
+" tst r3, #"__stringify(PORT_VALID)" \n"
+" bne 3f \n"
+
+ /* no match, loop with the next cpu_port entry */
+"2: add r1, r1, %[sizeof_struct_cpu_port] \n"
+" cmp r1, ip @ done? \n"
+" blo 1b \n"
+
+ /* CCI port not found -- cheaply try to stall this CPU */
+"cci_port_not_found: \n"
+" wfi \n"
+" wfe \n"
+" b cci_port_not_found \n"
+
+ /* Use matched port index to look up the corresponding ports entry */
+"3: bic r3, r3, #"__stringify(PORT_VALID)" \n"
+" adr r0, 6f \n"
+" ldmia r0, {r1, r2} \n"
+" sub r1, r1, r0 @ virt - phys \n"
+" ldr r0, [r0, r2] @ *(&ports) \n"
+" mov r2, %[sizeof_struct_ace_port] \n"
+" mla r0, r2, r3, r0 @ &ports[index] \n"
+" sub r0, r0, r1 @ virt_to_phys() \n"
+
+ /* Enable the CCI port */
+" ldr r0, [r0, %[offsetof_port_phys]] \n"
+" mov r3, %[cci_enable_req]\n"
+" str r3, [r0, #"__stringify(CCI_PORT_CTRL)"] \n"
+
+ /* poll the status reg for completion */
+" adr r1, 7f \n"
+" ldr r0, [r1] \n"
+" ldr r0, [r0, r1] @ cci_ctrl_base \n"
+"4: ldr r1, [r0, #"__stringify(CCI_CTRL_STATUS)"] \n"
+" tst r1, %[cci_control_status_bits] \n"
+" bne 4b \n"
+
+" mov r0, #0 \n"
+" bx lr \n"
+
+" .align 2 \n"
+"5: .word cpu_port - . \n"
+"6: .word . \n"
+" .word ports - 6b \n"
+"7: .word cci_ctrl_phys - . \n"
+ : :
+ [sizeof_cpu_port] "i" (sizeof(cpu_port)),
+ [cci_enable_req] "i" cpu_to_le32(CCI_ENABLE_REQ),
+ [cci_control_status_bits] "i" cpu_to_le32(1),
+#ifndef __ARMEB__
+ [offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)),
+#else
+ [offsetof_cpu_port_mpidr_lsb] "i" (offsetof(struct cpu_port, mpidr)+4),
+#endif
+ [offsetof_cpu_port_port] "i" (offsetof(struct cpu_port, port)),
+ [sizeof_struct_cpu_port] "i" (sizeof(struct cpu_port)),
+ [sizeof_struct_ace_port] "i" (sizeof(struct cci_ace_port)),
+ [offsetof_port_phys] "i" (offsetof(struct cci_ace_port, phys)) );
+
+ unreachable();
+}
+
+/**
+ * __cci_control_port_by_device() - function to control a CCI port by device
+ * reference
+ *
+ * @dn: device node pointer of the device whose CCI port should be
+ * controlled
+ * @enable: if true enables the port, if false disables it
+ *
+ * Return:
+ * 0 on success
+ * -ENODEV on port look-up failure
+ */
+int notrace __cci_control_port_by_device(struct device_node *dn, bool enable)
+{
+ int port;
+
+ if (!dn)
+ return -ENODEV;
+
+ port = __cci_ace_get_port(dn, ACE_LITE_PORT);
+ if (WARN_ONCE(port < 0, "node %s ACE lite port look-up failure\n",
+ dn->full_name))
+ return -ENODEV;
+ cci_port_control(port, enable);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__cci_control_port_by_device);
+
+/**
+ * __cci_control_port_by_index() - function to control a CCI port by port index
+ *
+ * @port: port index previously retrieved with cci_ace_get_port()
+ * @enable: if true enables the port, if false disables it
+ *
+ * Return:
+ * 0 on success
+ * -ENODEV on port index out of range
+ * -EPERM if operation carried out on an ACE PORT
+ */
+int notrace __cci_control_port_by_index(u32 port, bool enable)
+{
+ if (port >= nb_cci_ports || ports[port].type == ACE_INVALID_PORT)
+ return -ENODEV;
+ /*
+ * CCI control for ports connected to CPUS is extremely fragile
+ * and must be made to go through a specific and controlled
+ * interface (ie cci_disable_port_by_cpu(); control by general purpose
+ * indexing is therefore disabled for ACE ports.
+ */
+ if (ports[port].type == ACE_PORT)
+ return -EPERM;
+
+ cci_port_control(port, enable);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(__cci_control_port_by_index);
+
+static const struct cci_nb_ports cci400_ports = {
+ .nb_ace = 2,
+ .nb_ace_lite = 3
+};
+
+static const struct of_device_id arm_cci_matches[] = {
+ {.compatible = "arm,cci-400", .data = &cci400_ports },
+ {},
+};
+
+static const struct of_device_id arm_cci_ctrl_if_matches[] = {
+ {.compatible = "arm,cci-400-ctrl-if", },
+ {},
+};
+
+static int __init cci_probe(void)
+{
+ struct cci_nb_ports const *cci_config;
+ int ret, i, nb_ace = 0, nb_ace_lite = 0;
+ struct device_node *np, *cp;
+ struct resource res;
+ const char *match_str;
+ bool is_ace;
+
+ np = of_find_matching_node(NULL, arm_cci_matches);
+ if (!np)
+ return -ENODEV;
+
+ cci_config = of_match_node(arm_cci_matches, np)->data;
+ if (!cci_config)
+ return -ENODEV;
+
+ nb_cci_ports = cci_config->nb_ace + cci_config->nb_ace_lite;
+
+ ports = kcalloc(sizeof(*ports), nb_cci_ports, GFP_KERNEL);
+ if (!ports)
+ return -ENOMEM;
+
+ ret = of_address_to_resource(np, 0, &res);
+ if (!ret) {
+ cci_ctrl_base = ioremap(res.start, resource_size(&res));
+ cci_ctrl_phys = res.start;
+ }
+ if (ret || !cci_ctrl_base) {
+ WARN(1, "unable to ioremap CCI ctrl\n");
+ ret = -ENXIO;
+ goto memalloc_err;
+ }
+
+ for_each_child_of_node(np, cp) {
+ if (!of_match_node(arm_cci_ctrl_if_matches, cp))
+ continue;
+
+ i = nb_ace + nb_ace_lite;
+
+ if (i >= nb_cci_ports)
+ break;
+
+ if (of_property_read_string(cp, "interface-type",
+ &match_str)) {
+ WARN(1, "node %s missing interface-type property\n",
+ cp->full_name);
+ continue;
+ }
+ is_ace = strcmp(match_str, "ace") == 0;
+ if (!is_ace && strcmp(match_str, "ace-lite")) {
+ WARN(1, "node %s containing invalid interface-type property, skipping it\n",
+ cp->full_name);
+ continue;
+ }
+
+ ret = of_address_to_resource(cp, 0, &res);
+ if (!ret) {
+ ports[i].base = ioremap(res.start, resource_size(&res));
+ ports[i].phys = res.start;
+ }
+ if (ret || !ports[i].base) {
+ WARN(1, "unable to ioremap CCI port %d\n", i);
+ continue;
+ }
+
+ if (is_ace) {
+ if (WARN_ON(nb_ace >= cci_config->nb_ace))
+ continue;
+ ports[i].type = ACE_PORT;
+ ++nb_ace;
+ } else {
+ if (WARN_ON(nb_ace_lite >= cci_config->nb_ace_lite))
+ continue;
+ ports[i].type = ACE_LITE_PORT;
+ ++nb_ace_lite;
+ }
+ ports[i].dn = cp;
+ }
+
+ /* initialize a stashed array of ACE ports to speed-up look-up */
+ cci_ace_init_ports();
+
+ /*
+ * Multi-cluster systems may need this data when non-coherent, during
+ * cluster power-up/power-down. Make sure it reaches main memory.
+ */
+ sync_cache_w(&cci_ctrl_base);
+ sync_cache_w(&cci_ctrl_phys);
+ sync_cache_w(&ports);
+ sync_cache_w(&cpu_port);
+ __sync_cache_range_w(ports, sizeof(*ports) * nb_cci_ports);
+ pr_info("ARM CCI driver probed\n");
+ return 0;
+
+memalloc_err:
+
+ kfree(ports);
+ return ret;
+}
+
+static int cci_init_status = -EAGAIN;
+static DEFINE_MUTEX(cci_probing);
+
+static int __init cci_init(void)
+{
+ if (cci_init_status != -EAGAIN)
+ return cci_init_status;
+
+ mutex_lock(&cci_probing);
+ if (cci_init_status == -EAGAIN)
+ cci_init_status = cci_probe();
+ mutex_unlock(&cci_probing);
+ return cci_init_status;
+}
+
+/*
+ * To sort out early init calls ordering a helper function is provided to
+ * check if the CCI driver has beed initialized. Function check if the driver
+ * has been initialized, if not it calls the init function that probes
+ * the driver and updates the return value.
+ */
+bool __init cci_probed(void)
+{
+ return cci_init() == 0;
+}
+EXPORT_SYMBOL_GPL(cci_probed);
+
+early_initcall(cci_init);
+core_initcall(cci_pmu_init);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ARM CCI support");
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 8740f46..711dcf4 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -209,12 +209,25 @@
}
/* Checks whether the given window number is available */
+
+/* On Armada XP, 375 and 38x the MBus window 13 has the remap
+ * capability, like windows 0 to 7. However, the mvebu-mbus driver
+ * isn't currently taking into account this special case, which means
+ * that when window 13 is actually used, the remap registers are left
+ * to 0, making the device using this MBus window unavailable. The
+ * quick fix for stable is to not use window 13. A follow up patch
+ * will correctly handle this window.
+*/
static int mvebu_mbus_window_is_free(struct mvebu_mbus_state *mbus,
const int win)
{
void __iomem *addr = mbus->mbuswins_base +
mbus->soc->win_cfg_offset(win);
u32 ctrl = readl(addr + WIN_CTRL_OFF);
+
+ if (win == 13)
+ return false;
+
return !(ctrl & WIN_CTRL_ENABLE);
}
@@ -250,12 +263,6 @@
*/
if ((u64)base < wend && end > wbase)
return 0;
-
- /*
- * Check if target/attribute conflicts
- */
- if (target == wtarget && attr == wattr)
- return 0;
}
return 1;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index d620b44..8a3aff7 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2882,7 +2882,7 @@
if (lba < 0)
return -EINVAL;
- cgc->buffer = kmalloc(blocksize, GFP_KERNEL);
+ cgc->buffer = kzalloc(blocksize, GFP_KERNEL);
if (cgc->buffer == NULL)
return -ENOMEM;
diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c
index 94821ab..9576fad 100644
--- a/drivers/char/agp/parisc-agp.c
+++ b/drivers/char/agp/parisc-agp.c
@@ -129,7 +129,8 @@
off_t j, io_pg_start;
int io_pg_count;
- if (type != 0 || mem->type != 0) {
+ if (type != mem->type ||
+ agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
return -EINVAL;
}
@@ -175,7 +176,8 @@
struct _parisc_agp_info *info = &parisc_agp_info;
int i, io_pg_start, io_pg_count;
- if (type != 0 || mem->type != 0) {
+ if (type != mem->type ||
+ agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type)) {
return -EINVAL;
}
diff --git a/drivers/char/applicom.c b/drivers/char/applicom.c
index 974321a..1479030 100644
--- a/drivers/char/applicom.c
+++ b/drivers/char/applicom.c
@@ -345,7 +345,6 @@
free_irq(apbs[i].irq, &dummy);
iounmap(apbs[i].RamIO);
}
- pci_disable_device(dev);
return ret;
}
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index eb7f147..43577ca 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -110,4 +110,4 @@
MODULE_AUTHOR("Lubomir Rintel <lkundrak@v3.sk>");
MODULE_DESCRIPTION("BCM2835 Random Number Generator (RNG) driver");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index 40cc0cf2..e6939e1 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -664,6 +664,13 @@
DMI_MATCH(DMI_PRODUCT_NAME, "Vostro"),
},
},
+ {
+ .ident = "Dell XPS421",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS L421X"),
+ },
+ },
{ }
};
diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
index a22a7a5..8156caf 100644
--- a/drivers/char/ipmi/ipmi_bt_sm.c
+++ b/drivers/char/ipmi/ipmi_bt_sm.c
@@ -352,7 +352,7 @@
static inline int read_all_bytes(struct si_sm_data *bt)
{
- unsigned char i;
+ unsigned int i;
/*
* length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
diff --git a/drivers/char/ipmi/ipmi_kcs_sm.c b/drivers/char/ipmi/ipmi_kcs_sm.c
index e53fc24..e1ddcf9 100644
--- a/drivers/char/ipmi/ipmi_kcs_sm.c
+++ b/drivers/char/ipmi/ipmi_kcs_sm.c
@@ -251,8 +251,9 @@
if (!GET_STATUS_OBF(status)) {
kcs->obf_timeout -= time;
if (kcs->obf_timeout < 0) {
- start_error_recovery(kcs, "OBF not ready in time");
- return 1;
+ kcs->obf_timeout = OBF_RETRY_TIMEOUT;
+ start_error_recovery(kcs, "OBF not ready in time");
+ return 1;
}
return 0;
}
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index af4b23f..40b3f75 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -244,6 +244,9 @@
/* The timer for this si. */
struct timer_list si_timer;
+ /* This flag is set, if the timer is running (timer_pending() isn't enough) */
+ bool timer_running;
+
/* The time (in jiffies) the last timeout occurred at. */
unsigned long last_timeout_jiffies;
@@ -427,6 +430,13 @@
smi_info->si_state = SI_CLEARING_FLAGS;
}
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+ smi_info->last_timeout_jiffies = jiffies;
+ mod_timer(&smi_info->si_timer, new_val);
+ smi_info->timer_running = true;
+}
+
/*
* When we have a situtaion where we run out of memory and cannot
* allocate messages, we just leave them in the BMC and run the system
@@ -439,8 +449,7 @@
start_disable_irq(smi_info);
smi_info->interrupt_disabled = 1;
if (!atomic_read(&smi_info->stop_operation))
- mod_timer(&smi_info->si_timer,
- jiffies + SI_TIMEOUT_JIFFIES);
+ smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
}
}
@@ -900,15 +909,7 @@
list_add_tail(&msg->link, &smi_info->xmit_msgs);
if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) {
- /*
- * last_timeout_jiffies is updated here to avoid
- * smi_timeout() handler passing very large time_diff
- * value to smi_event_handler() that causes
- * the send command to abort.
- */
- smi_info->last_timeout_jiffies = jiffies;
-
- mod_timer(&smi_info->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+ smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
if (smi_info->thread)
wake_up_process(smi_info->thread);
@@ -997,6 +998,17 @@
spin_lock_irqsave(&(smi_info->si_lock), flags);
smi_result = smi_event_handler(smi_info, 0);
+
+ /*
+ * If the driver is doing something, there is a possible
+ * race with the timer. If the timer handler see idle,
+ * and the thread here sees something else, the timer
+ * handler won't restart the timer even though it is
+ * required. So start it here if necessary.
+ */
+ if (smi_result != SI_SM_IDLE && !smi_info->timer_running)
+ smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
spin_unlock_irqrestore(&(smi_info->si_lock), flags);
busy_wait = ipmi_thread_busy_wait(smi_result, smi_info,
&busy_until);
@@ -1066,10 +1078,6 @@
* SI_USEC_PER_JIFFY);
smi_result = smi_event_handler(smi_info, time_diff);
- spin_unlock_irqrestore(&(smi_info->si_lock), flags);
-
- smi_info->last_timeout_jiffies = jiffies_now;
-
if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
/* Running with interrupts, only do long timeouts. */
timeout = jiffies + SI_TIMEOUT_JIFFIES;
@@ -1091,7 +1099,10 @@
do_mod_timer:
if (smi_result != SI_SM_IDLE)
- mod_timer(&(smi_info->si_timer), timeout);
+ smi_mod_timer(smi_info, timeout);
+ else
+ smi_info->timer_running = false;
+ spin_unlock_irqrestore(&(smi_info->si_lock), flags);
}
static irqreturn_t si_irq_handler(int irq, void *data)
@@ -1139,8 +1150,7 @@
/* Set up the timer that drives the interface. */
setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi);
- new_smi->last_timeout_jiffies = jiffies;
- mod_timer(&new_smi->si_timer, jiffies + SI_TIMEOUT_JIFFIES);
+ smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
/*
* Check if the user forcefully enabled the daemon.
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 35487e8..aee3464 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -933,8 +933,8 @@
* pool while mixing, and hash one final time.
*/
sha_transform(hash.w, extract, workspace);
- memset(extract, 0, sizeof(extract));
- memset(workspace, 0, sizeof(workspace));
+ memzero_explicit(extract, sizeof(extract));
+ memzero_explicit(workspace, sizeof(workspace));
/*
* In case the hash function has some recognizable output
@@ -957,7 +957,7 @@
}
memcpy(out, &hash, EXTRACT_SIZE);
- memset(&hash, 0, sizeof(hash));
+ memzero_explicit(&hash, sizeof(hash));
}
static ssize_t extract_entropy(struct entropy_store *r, void *buf,
@@ -1005,7 +1005,7 @@
}
/* Wipe data just returned from memory */
- memset(tmp, 0, sizeof(tmp));
+ memzero_explicit(tmp, sizeof(tmp));
return ret;
}
@@ -1043,7 +1043,7 @@
}
/* Wipe data just returned from memory */
- memset(tmp, 0, sizeof(tmp));
+ memzero_explicit(tmp, sizeof(tmp));
return ret;
}
@@ -1462,12 +1462,11 @@
static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
-static int __init random_int_secret_init(void)
+int random_int_secret_init(void)
{
get_random_bytes(random_int_secret, sizeof(random_int_secret));
return 0;
}
-late_initcall(random_int_secret_init);
/*
* Get a random word for internal kernel use only. Similar to urandom but
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index f3223aa..6e8d65e 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -190,7 +190,7 @@
struct raw_device_data *rawdev;
struct block_device *bdev;
- if (number <= 0 || number >= MAX_RAW_MINORS)
+ if (number <= 0 || number >= max_raw_minors)
return -EINVAL;
rawdev = &raw_devices[number];
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index 7c3b3dc..f659a57 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -533,11 +533,10 @@
int tpm_get_timeouts(struct tpm_chip *chip)
{
struct tpm_cmd_t tpm_cmd;
- struct timeout_t *timeout_cap;
+ unsigned long new_timeout[4];
+ unsigned long old_timeout[4];
struct duration_t *duration_cap;
ssize_t rc;
- u32 timeout;
- unsigned int scale = 1;
tpm_cmd.header.in = tpm_getcap_header;
tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP;
@@ -571,25 +570,46 @@
!= sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32))
return -EINVAL;
- timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout;
- /* Don't overwrite default if value is 0 */
- timeout = be32_to_cpu(timeout_cap->a);
- if (timeout && timeout < 1000) {
- /* timeouts in msec rather usec */
- scale = 1000;
- chip->vendor.timeout_adjusted = true;
+ old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a);
+ old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b);
+ old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c);
+ old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d);
+ memcpy(new_timeout, old_timeout, sizeof(new_timeout));
+
+ /*
+ * Provide ability for vendor overrides of timeout values in case
+ * of misreporting.
+ */
+ if (chip->vendor.update_timeouts != NULL)
+ chip->vendor.timeout_adjusted =
+ chip->vendor.update_timeouts(chip, new_timeout);
+
+ if (!chip->vendor.timeout_adjusted) {
+ /* Don't overwrite default if value is 0 */
+ if (new_timeout[0] != 0 && new_timeout[0] < 1000) {
+ int i;
+
+ /* timeouts in msec rather usec */
+ for (i = 0; i != ARRAY_SIZE(new_timeout); i++)
+ new_timeout[i] *= 1000;
+ chip->vendor.timeout_adjusted = true;
+ }
}
- if (timeout)
- chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->b);
- if (timeout)
- chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->c);
- if (timeout)
- chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale);
- timeout = be32_to_cpu(timeout_cap->d);
- if (timeout)
- chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale);
+
+ /* Report adjusted timeouts */
+ if (chip->vendor.timeout_adjusted) {
+ dev_info(chip->dev,
+ HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n",
+ old_timeout[0], new_timeout[0],
+ old_timeout[1], new_timeout[1],
+ old_timeout[2], new_timeout[2],
+ old_timeout[3], new_timeout[3]);
+ }
+
+ chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]);
+ chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]);
+ chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]);
+ chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]);
duration:
tpm_cmd.header.in = tpm_getcap_header;
@@ -1423,13 +1443,13 @@
int err, total = 0, retries = 5;
u8 *dest = out;
+ if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
+ return -EINVAL;
+
chip = tpm_chip_find_get(chip_num);
if (chip == NULL)
return -ENODEV;
- if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
- return -EINVAL;
-
do {
tpm_cmd.header.in = tpm_getrandom_header;
tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes);
@@ -1448,6 +1468,7 @@
num_bytes -= recd;
} while (retries-- && total < max);
+ tpm_chip_put(chip);
return total ? total : -EIO;
}
EXPORT_SYMBOL_GPL(tpm_get_random);
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 0770d1d..deffda7 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -95,6 +95,9 @@
int (*send) (struct tpm_chip *, u8 *, size_t);
void (*cancel) (struct tpm_chip *);
u8 (*status) (struct tpm_chip *);
+ bool (*update_timeouts)(struct tpm_chip *chip,
+ unsigned long *timeout_cap);
+
void (*release) (struct device *);
struct miscdevice miscdev;
struct attribute_group *attr_group;
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 5bb8e2d..3925f7b 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -410,6 +410,8 @@
&chip->vendor.read_queue)
== 0) {
burstcnt = get_burstcount(chip);
+ if (burstcnt < 0)
+ return burstcnt;
len = min_t(int, burstcnt, count - size);
I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
size += len;
@@ -451,7 +453,8 @@
static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
size_t len)
{
- u32 status, burstcnt = 0, i, size;
+ u32 status, i, size;
+ int burstcnt = 0;
int ret;
u8 data;
struct i2c_client *client;
@@ -482,8 +485,10 @@
for (i = 0; i < len - 1;) {
burstcnt = get_burstcount(chip);
+ if (burstcnt < 0)
+ return burstcnt;
size = min_t(int, len - i - 1, burstcnt);
- ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf, size);
+ ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size);
if (ret < 0)
goto out_err;
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 56b07c3..09df26f 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -124,7 +124,7 @@
{
struct ibmvtpm_dev *ibmvtpm;
struct ibmvtpm_crq crq;
- u64 *word = (u64 *) &crq;
+ __be64 *word = (__be64 *)&crq;
int rc;
ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip);
@@ -145,10 +145,11 @@
memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
crq.valid = (u8)IBMVTPM_VALID_CMD;
crq.msg = (u8)VTPM_TPM_COMMAND;
- crq.len = (u16)count;
- crq.data = ibmvtpm->rtce_dma_handle;
+ crq.len = cpu_to_be16(count);
+ crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, word[0], word[1]);
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
+ be64_to_cpu(word[1]));
if (rc != H_SUCCESS) {
dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
rc = 0;
@@ -186,7 +187,8 @@
crq.valid = (u8)IBMVTPM_VALID_CMD;
crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+ cpu_to_be64(buf[1]));
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
@@ -212,7 +214,8 @@
crq.valid = (u8)IBMVTPM_VALID_CMD;
crq.msg = (u8)VTPM_GET_VERSION;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+ cpu_to_be64(buf[1]));
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_version failed rc=%d\n", rc);
@@ -307,6 +310,14 @@
static unsigned long tpm_ibmvtpm_get_desired_dma(struct vio_dev *vdev)
{
struct ibmvtpm_dev *ibmvtpm = ibmvtpm_get_data(&vdev->dev);
+
+ /* ibmvtpm initializes at probe time, so the data we are
+ * asking for may not be set yet. Estimate that 4K required
+ * for TCE-mapped buffer in addition to CRQ.
+ */
+ if (!ibmvtpm)
+ return CRQ_RES_BUF_SIZE + PAGE_SIZE;
+
return CRQ_RES_BUF_SIZE + ibmvtpm->rtce_size;
}
@@ -327,7 +338,8 @@
crq.valid = (u8)IBMVTPM_VALID_CMD;
crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, buf[0], buf[1]);
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
+ cpu_to_be64(buf[1]));
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
@@ -511,11 +523,11 @@
case IBMVTPM_VALID_CMD:
switch (crq->msg) {
case VTPM_GET_RTCE_BUFFER_SIZE_RES:
- if (crq->len <= 0) {
+ if (be16_to_cpu(crq->len) <= 0) {
dev_err(ibmvtpm->dev, "Invalid rtce size\n");
return;
}
- ibmvtpm->rtce_size = crq->len;
+ ibmvtpm->rtce_size = be16_to_cpu(crq->len);
ibmvtpm->rtce_buf = kmalloc(ibmvtpm->rtce_size,
GFP_KERNEL);
if (!ibmvtpm->rtce_buf) {
@@ -536,11 +548,11 @@
return;
case VTPM_GET_VERSION_RES:
- ibmvtpm->vtpm_version = crq->data;
+ ibmvtpm->vtpm_version = be32_to_cpu(crq->data);
return;
case VTPM_TPM_COMMAND_RES:
/* len of the data in rtce buffer */
- ibmvtpm->res_len = crq->len;
+ ibmvtpm->res_len = be16_to_cpu(crq->len);
wake_up_interruptible(&ibmvtpm->wq);
return;
default:
diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h
index bd82a79..b2c231b 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.h
+++ b/drivers/char/tpm/tpm_ibmvtpm.h
@@ -22,9 +22,9 @@
struct ibmvtpm_crq {
u8 valid;
u8 msg;
- u16 len;
- u32 data;
- u64 reserved;
+ __be16 len;
+ __be32 data;
+ __be64 reserved;
} __attribute__((packed, aligned(8)));
struct ibmvtpm_crq_queue {
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index 2168d15..811ad1e 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -27,15 +27,18 @@
static acpi_status ppi_callback(acpi_handle handle, u32 level, void *context,
void **return_value)
{
- acpi_status status;
+ acpi_status status = AE_OK;
struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
- status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
- if (strstr(buffer.pointer, context) != NULL) {
- *return_value = handle;
+
+ if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) {
+ if (strstr(buffer.pointer, context) != NULL) {
+ *return_value = handle;
+ status = AE_CTRL_TERMINATE;
+ }
kfree(buffer.pointer);
- return AE_CTRL_TERMINATE;
}
- return AE_OK;
+
+ return status;
}
static inline void ppi_assign_params(union acpi_object params[4],
@@ -169,7 +172,7 @@
* is updated with function index from SUBREQ to SUBREQ2 since PPI
* version 1.1
*/
- if (strcmp(version, "1.1") == -1)
+ if (strcmp(version, "1.1") < 0)
params[2].integer.value = TPM_PPI_FN_SUBREQ;
else
params[2].integer.value = TPM_PPI_FN_SUBREQ2;
@@ -179,7 +182,7 @@
* string/package type. For PPI version 1.0 and 1.1, use buffer type
* for compatibility, and use package type since 1.2 according to spec.
*/
- if (strcmp(version, "1.2") == -1) {
+ if (strcmp(version, "1.2") < 0) {
params[3].type = ACPI_TYPE_BUFFER;
params[3].buffer.length = sizeof(req);
sscanf(buf, "%d", &req);
@@ -245,7 +248,7 @@
* (e.g. Capella with PPI 1.0) need integer/string/buffer type, so for
* compatibility, define params[3].type as buffer, if PPI version < 1.2
*/
- if (strcmp(version, "1.2") == -1) {
+ if (strcmp(version, "1.2") < 0) {
params[3].type = ACPI_TYPE_BUFFER;
params[3].buffer.length = 0;
params[3].buffer.pointer = NULL;
@@ -387,7 +390,7 @@
kfree(output.pointer);
output.length = ACPI_ALLOCATE_BUFFER;
output.pointer = NULL;
- if (strcmp(version, "1.2") == -1)
+ if (strcmp(version, "1.2") < 0)
return -EPERM;
params[2].integer.value = TPM_PPI_FN_GETOPR;
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 8a41b6b..323d02d 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -75,6 +75,10 @@
#define TPM_DID_VID(l) (0x0F00 | ((l) << 12))
#define TPM_RID(l) (0x0F04 | ((l) << 12))
+struct priv_data {
+ bool irq_tested;
+};
+
static LIST_HEAD(tis_chips);
static DEFINE_MUTEX(tis_lock);
@@ -338,12 +342,27 @@
return rc;
}
+static void disable_interrupts(struct tpm_chip *chip)
+{
+ u32 intmask;
+
+ intmask =
+ ioread32(chip->vendor.iobase +
+ TPM_INT_ENABLE(chip->vendor.locality));
+ intmask &= ~TPM_GLOBAL_INT_ENABLE;
+ iowrite32(intmask,
+ chip->vendor.iobase +
+ TPM_INT_ENABLE(chip->vendor.locality));
+ free_irq(chip->vendor.irq, chip);
+ chip->vendor.irq = 0;
+}
+
/*
* If interrupts are used (signaled by an irq set in the vendor structure)
* tpm.c can skip polling for the data to be available as the interrupt is
* waited for here
*/
-static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send_main(struct tpm_chip *chip, u8 *buf, size_t len)
{
int rc;
u32 ordinal;
@@ -373,6 +392,60 @@
return rc;
}
+static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+{
+ int rc, irq;
+ struct priv_data *priv = chip->vendor.priv;
+
+ if (!chip->vendor.irq || priv->irq_tested)
+ return tpm_tis_send_main(chip, buf, len);
+
+ /* Verify receipt of the expected IRQ */
+ irq = chip->vendor.irq;
+ chip->vendor.irq = 0;
+ rc = tpm_tis_send_main(chip, buf, len);
+ chip->vendor.irq = irq;
+ if (!priv->irq_tested)
+ msleep(1);
+ if (!priv->irq_tested) {
+ disable_interrupts(chip);
+ dev_err(chip->dev,
+ FW_BUG "TPM interrupt not working, polling instead\n");
+ }
+ priv->irq_tested = true;
+ return rc;
+}
+
+struct tis_vendor_timeout_override {
+ u32 did_vid;
+ unsigned long timeout_us[4];
+};
+
+static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = {
+ /* Atmel 3204 */
+ { 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000),
+ (TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } },
+};
+
+static bool tpm_tis_update_timeouts(struct tpm_chip *chip,
+ unsigned long *timeout_cap)
+{
+ int i;
+ u32 did_vid;
+
+ did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0));
+
+ for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) {
+ if (vendor_timeout_overrides[i].did_vid != did_vid)
+ continue;
+ memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us,
+ sizeof(vendor_timeout_overrides[i].timeout_us));
+ return true;
+ }
+
+ return false;
+}
+
/*
* Early probing for iTPM with STS_DATA_EXPECT flaw.
* Try sending command without itpm flag set and if that
@@ -475,6 +548,7 @@
.recv = tpm_tis_recv,
.send = tpm_tis_send,
.cancel = tpm_tis_ready,
+ .update_timeouts = tpm_tis_update_timeouts,
.req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
.req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID,
.req_canceled = tpm_tis_req_canceled,
@@ -515,6 +589,7 @@
if (interrupt == 0)
return IRQ_NONE;
+ ((struct priv_data *)chip->vendor.priv)->irq_tested = true;
if (interrupt & TPM_INTF_DATA_AVAIL_INT)
wake_up_interruptible(&chip->vendor.read_queue);
if (interrupt & TPM_INTF_LOCALITY_CHANGE_INT)
@@ -544,9 +619,14 @@
u32 vendor, intfcaps, intmask;
int rc, i, irq_s, irq_e, probe;
struct tpm_chip *chip;
+ struct priv_data *priv;
+ priv = devm_kzalloc(dev, sizeof(struct priv_data), GFP_KERNEL);
+ if (priv == NULL)
+ return -ENOMEM;
if (!(chip = tpm_register_hardware(dev, &tpm_tis)))
return -ENODEV;
+ chip->vendor.priv = priv;
chip->vendor.iobase = ioremap(start, len);
if (!chip->vendor.iobase) {
@@ -615,19 +695,6 @@
if (intfcaps & TPM_INTF_DATA_AVAIL_INT)
dev_dbg(dev, "\tData Avail Int Support\n");
- /* get the timeouts before testing for irqs */
- if (tpm_get_timeouts(chip)) {
- dev_err(dev, "Could not get TPM timeouts and durations\n");
- rc = -ENODEV;
- goto out_err;
- }
-
- if (tpm_do_selftest(chip)) {
- dev_err(dev, "TPM self test failed\n");
- rc = -ENODEV;
- goto out_err;
- }
-
/* INTERRUPT Setup */
init_waitqueue_head(&chip->vendor.read_queue);
init_waitqueue_head(&chip->vendor.int_queue);
@@ -729,6 +796,18 @@
}
}
+ if (tpm_get_timeouts(chip)) {
+ dev_err(dev, "Could not get TPM timeouts and durations\n");
+ rc = -ENODEV;
+ goto out_err;
+ }
+
+ if (tpm_do_selftest(chip)) {
+ dev_err(dev, "TPM self test failed\n");
+ rc = -ENODEV;
+ goto out_err;
+ }
+
INIT_LIST_HEAD(&chip->vendor.list);
mutex_lock(&tis_lock);
list_add(&chip->vendor.list, &tis_chips);
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 1b456fe..ec3bd62 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -272,9 +272,12 @@
unsigned long flags;
spin_lock_irqsave(&portdev->ports_lock, flags);
- list_for_each_entry(port, &portdev->ports, list)
- if (port->cdev->dev == dev)
+ list_for_each_entry(port, &portdev->ports, list) {
+ if (port->cdev->dev == dev) {
+ kref_get(&port->kref);
goto out;
+ }
+ }
port = NULL;
out:
spin_unlock_irqrestore(&portdev->ports_lock, flags);
@@ -746,6 +749,10 @@
port = filp->private_data;
+ /* Port is hot-unplugged. */
+ if (!port->guest_connected)
+ return -ENODEV;
+
if (!port_has_data(port)) {
/*
* If nothing's connected on the host just return 0 in
@@ -762,7 +769,7 @@
if (ret < 0)
return ret;
}
- /* Port got hot-unplugged. */
+ /* Port got hot-unplugged while we were waiting above. */
if (!port->guest_connected)
return -ENODEV;
/*
@@ -932,13 +939,25 @@
if (is_rproc_serial(port->out_vq->vdev))
return -EINVAL;
+ /*
+ * pipe->nrbufs == 0 means there are no data to transfer,
+ * so this returns just 0 for no data.
+ */
+ pipe_lock(pipe);
+ if (!pipe->nrbufs) {
+ ret = 0;
+ goto error_out;
+ }
+
ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
if (ret < 0)
- return ret;
+ goto error_out;
buf = alloc_buf(port->out_vq, 0, pipe->nrbufs);
- if (!buf)
- return -ENOMEM;
+ if (!buf) {
+ ret = -ENOMEM;
+ goto error_out;
+ }
sgl.n = 0;
sgl.len = 0;
@@ -946,12 +965,17 @@
sgl.sg = buf->sg;
sg_init_table(sgl.sg, sgl.size);
ret = __splice_from_pipe(pipe, &sd, pipe_to_sg);
+ pipe_unlock(pipe);
if (likely(ret > 0))
ret = __send_to_port(port, buf->sg, sgl.n, sgl.len, buf, true);
if (unlikely(ret <= 0))
free_buf(buf, true);
return ret;
+
+error_out:
+ pipe_unlock(pipe);
+ return ret;
}
static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
@@ -1019,14 +1043,14 @@
struct port *port;
int ret;
+ /* We get the port with a kref here */
port = find_port_by_devt(cdev->dev);
+ if (!port) {
+ /* Port was unplugged before we could proceed */
+ return -ENXIO;
+ }
filp->private_data = port;
- /* Prevent against a port getting hot-unplugged at the same time */
- spin_lock_irq(&port->portdev->ports_lock);
- kref_get(&port->kref);
- spin_unlock_irq(&port->portdev->ports_lock);
-
/*
* Don't allow opening of console port devices -- that's done
* via /dev/hvc
@@ -1498,14 +1522,6 @@
port = container_of(kref, struct port, kref);
- sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
- device_destroy(pdrvdata.class, port->dev->devt);
- cdev_del(port->cdev);
-
- kfree(port->name);
-
- debugfs_remove(port->debugfs_file);
-
kfree(port);
}
@@ -1539,12 +1555,14 @@
spin_unlock_irq(&port->portdev->ports_lock);
if (port->guest_connected) {
- port->guest_connected = false;
- port->host_connected = false;
- wake_up_interruptible(&port->waitqueue);
-
/* Let the app know the port is going down. */
send_sigio_to_port(port);
+
+ /* Do this after sigio is actually sent */
+ port->guest_connected = false;
+ port->host_connected = false;
+
+ wake_up_interruptible(&port->waitqueue);
}
if (is_console_port(port)) {
@@ -1563,6 +1581,14 @@
*/
port->portdev = NULL;
+ sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+ device_destroy(pdrvdata.class, port->dev->devt);
+ cdev_del(port->cdev);
+
+ kfree(port->name);
+
+ debugfs_remove(port->debugfs_file);
+
/*
* Locks around here are not necessary - a port can't be
* opened after we removed the port struct from ports_list
@@ -1997,12 +2023,13 @@
spin_lock_init(&portdev->ports_lock);
INIT_LIST_HEAD(&portdev->ports);
+ INIT_WORK(&portdev->control_work, &control_work_handler);
+
if (multiport) {
unsigned int nr_added_bufs;
spin_lock_init(&portdev->c_ivq_lock);
spin_lock_init(&portdev->c_ovq_lock);
- INIT_WORK(&portdev->control_work, &control_work_handler);
nr_added_bufs = fill_queue(portdev->c_ivq,
&portdev->c_ivq_lock);
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 0357ac4..d0d9b21 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -42,7 +42,7 @@
config COMMON_CLK_VERSATILE
bool "Clock driver for ARM Reference designs"
- depends on ARCH_INTEGRATOR || ARCH_REALVIEW || ARCH_VEXPRESS
+ depends on ARCH_INTEGRATOR || ARCH_REALVIEW || ARCH_VEXPRESS || ARM64
---help---
Supports clocking on ARM Reference designs:
- Integrator/AP and Integrator/CP
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 6d96741..a885284 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -24,7 +24,7 @@
* Traits of this clock:
* prepare - clk_prepare only ensures that parents are prepared
* enable - clk_enable only ensures that parents are enabled
- * rate - rate is adjustable. clk->rate = parent->rate / divisor
+ * rate - rate is adjustable. clk->rate = DIV_ROUND_UP(parent->rate / divisor)
* parent - fixed parent. No clk_set_parent support
*/
@@ -43,6 +43,17 @@
return maxdiv;
}
+static unsigned int _get_table_mindiv(const struct clk_div_table *table)
+{
+ unsigned int mindiv = UINT_MAX;
+ const struct clk_div_table *clkt;
+
+ for (clkt = table; clkt->div; clkt++)
+ if (clkt->div < mindiv)
+ mindiv = clkt->div;
+ return mindiv;
+}
+
static unsigned int _get_maxdiv(struct clk_divider *divider)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
@@ -87,7 +98,7 @@
return 0;
}
-static unsigned int _get_val(struct clk_divider *divider, u8 div)
+static unsigned int _get_val(struct clk_divider *divider, unsigned int div)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
return div;
@@ -115,7 +126,7 @@
return parent_rate;
}
- return parent_rate / div;
+ return DIV_ROUND_UP(parent_rate, div);
}
/*
@@ -144,6 +155,91 @@
return true;
}
+static int _round_up_table(const struct clk_div_table *table, int div)
+{
+ const struct clk_div_table *clkt;
+ int up = INT_MAX;
+
+ for (clkt = table; clkt->div; clkt++) {
+ if (clkt->div == div)
+ return clkt->div;
+ else if (clkt->div < div)
+ continue;
+
+ if ((clkt->div - div) < (up - div))
+ up = clkt->div;
+ }
+
+ return up;
+}
+
+static int _round_down_table(const struct clk_div_table *table, int div)
+{
+ const struct clk_div_table *clkt;
+ int down = _get_table_mindiv(table);
+
+ for (clkt = table; clkt->div; clkt++) {
+ if (clkt->div == div)
+ return clkt->div;
+ else if (clkt->div > div)
+ continue;
+
+ if ((div - clkt->div) < (div - down))
+ down = clkt->div;
+ }
+
+ return down;
+}
+
+static int _div_round_up(struct clk_divider *divider,
+ unsigned long parent_rate, unsigned long rate)
+{
+ int div = DIV_ROUND_UP(parent_rate, rate);
+
+ if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+ div = __roundup_pow_of_two(div);
+ if (divider->table)
+ div = _round_up_table(divider->table, div);
+
+ return div;
+}
+
+static int _div_round_closest(struct clk_divider *divider,
+ unsigned long parent_rate, unsigned long rate)
+{
+ int up, down, div;
+
+ up = down = div = DIV_ROUND_CLOSEST(parent_rate, rate);
+
+ if (divider->flags & CLK_DIVIDER_POWER_OF_TWO) {
+ up = __roundup_pow_of_two(div);
+ down = __rounddown_pow_of_two(div);
+ } else if (divider->table) {
+ up = _round_up_table(divider->table, div);
+ down = _round_down_table(divider->table, div);
+ }
+
+ return (up - div) <= (div - down) ? up : down;
+}
+
+static int _div_round(struct clk_divider *divider, unsigned long parent_rate,
+ unsigned long rate)
+{
+ if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+ return _div_round_closest(divider, parent_rate, rate);
+
+ return _div_round_up(divider, parent_rate, rate);
+}
+
+static bool _is_best_div(struct clk_divider *divider,
+ unsigned long rate, unsigned long now, unsigned long best)
+{
+ if (divider->flags & CLK_DIVIDER_ROUND_CLOSEST)
+ return abs(rate - now) < abs(rate - best);
+
+ return now <= rate && now > best;
+}
+
static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
unsigned long *best_parent_rate)
{
@@ -158,7 +254,7 @@
if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
parent_rate = *best_parent_rate;
- bestdiv = DIV_ROUND_UP(parent_rate, rate);
+ bestdiv = _div_round(divider, parent_rate, rate);
bestdiv = bestdiv == 0 ? 1 : bestdiv;
bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
return bestdiv;
@@ -175,8 +271,8 @@
continue;
parent_rate = __clk_round_rate(__clk_get_parent(hw->clk),
MULT_ROUND_UP(rate, i));
- now = parent_rate / i;
- if (now <= rate && now > best) {
+ now = DIV_ROUND_UP(parent_rate, i);
+ if (_is_best_div(divider, rate, now, best)) {
bestdiv = i;
best = now;
*best_parent_rate = parent_rate;
@@ -197,7 +293,7 @@
int div;
div = clk_divider_bestdiv(hw, rate, prate);
- return *prate / div;
+ return DIV_ROUND_UP(*prate, div);
}
static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
@@ -208,7 +304,11 @@
unsigned long flags = 0;
u32 val;
- div = parent_rate / rate;
+ div = DIV_ROUND_UP(parent_rate, rate);
+
+ if (!_is_valid_div(divider, div))
+ return -EINVAL;
+
value = _get_val(divider, div);
if (value > div_mask(divider))
diff --git a/drivers/clk/clk-wm831x.c b/drivers/clk/clk-wm831x.c
index 16ed068..917a3ab 100644
--- a/drivers/clk/clk-wm831x.c
+++ b/drivers/clk/clk-wm831x.c
@@ -360,6 +360,8 @@
if (!clkdata)
return -ENOMEM;
+ clkdata->wm831x = wm831x;
+
/* XTAL_ENA can only be set via OTP/InstantConfig so just read once */
ret = wm831x_reg_read(wm831x, WM831X_CLOCK_CONTROL_2);
if (ret < 0) {
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 1144e8c..fccac4a 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2084,6 +2084,12 @@
return clk;
}
+int of_clk_get_parent_count(struct device_node *np)
+{
+ return of_count_phandle_with_args(np, "clocks", "#clock-cells");
+}
+EXPORT_SYMBOL_GPL(of_clk_get_parent_count);
+
const char *of_clk_get_parent_name(struct device_node *np, int index)
{
struct of_phandle_args clkspec;
diff --git a/drivers/clk/mvebu/clk-core.c b/drivers/clk/mvebu/clk-core.c
index 0a53edb..e5c477b 100644
--- a/drivers/clk/mvebu/clk-core.c
+++ b/drivers/clk/mvebu/clk-core.c
@@ -126,8 +126,8 @@
#define SARH_AXP_FAB_FREQ_OPT_SHIFT 4
static const u32 __initconst armada_370_tclk_frequencies[] = {
- 16600000,
- 20000000,
+ 166000000,
+ 200000000,
};
static u32 __init armada_370_get_tclk_freq(void __iomem *sar)
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 3c1f888..b4b283b 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -40,7 +40,7 @@
#define SRC_TOP1 0xc214
#define SRC_CAM 0xc220
#define SRC_TV 0xc224
-#define SRC_MFC 0xcc28
+#define SRC_MFC 0xc228
#define SRC_G3D 0xc22c
#define E4210_SRC_IMAGE 0xc230
#define SRC_LCD0 0xc234
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 22d7699..92afc06 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -325,8 +325,8 @@
GATE(smmu_gscl2, "smmu_gscl2", "aclk266", GATE_IP_GSCL, 9, 0, 0),
GATE(smmu_gscl3, "smmu_gscl3", "aclk266", GATE_IP_GSCL, 10, 0, 0),
GATE(mfc, "mfc", "aclk333", GATE_IP_MFC, 0, 0, 0),
- GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 1, 0, 0),
- GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 2, 0, 0),
+ GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 2, 0, 0),
+ GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 1, 0, 0),
GATE(rotator, "rotator", "aclk266", GATE_IP_GEN, 1, 0, 0),
GATE(jpeg, "jpeg", "aclk166", GATE_IP_GEN, 2, 0, 0),
GATE(mdma1, "mdma1", "aclk266", GATE_IP_GEN, 4, 0, 0),
@@ -377,7 +377,8 @@
GATE(hsi2c2, "hsi2c2", "aclk66", GATE_IP_PERIC, 30, 0, 0),
GATE(hsi2c3, "hsi2c3", "aclk66", GATE_IP_PERIC, 31, 0, 0),
GATE(chipid, "chipid", "aclk66", GATE_IP_PERIS, 0, 0, 0),
- GATE(sysreg, "sysreg", "aclk66", GATE_IP_PERIS, 1, 0, 0),
+ GATE(sysreg, "sysreg", "aclk66",
+ GATE_IP_PERIS, 1, CLK_IGNORE_UNUSED, 0),
GATE(pmu, "pmu", "aclk66", GATE_IP_PERIS, 2, CLK_IGNORE_UNUSED, 0),
GATE(tzpc0, "tzpc0", "aclk66", GATE_IP_PERIS, 6, 0, 0),
GATE(tzpc1, "tzpc1", "aclk66", GATE_IP_PERIS, 7, 0, 0),
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index 080c3c5..1fe2590 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -211,7 +211,7 @@
/* array of all spear 320 clock lookups */
#ifdef CONFIG_MACH_SPEAR320
-#define SPEAR320_CONTROL_REG (soc_config_base + 0x0000)
+#define SPEAR320_CONTROL_REG (soc_config_base + 0x0010)
#define SPEAR320_EXT_CTRL_REG (soc_config_base + 0x0018)
#define SPEAR320_UARTX_PCLK_MASK 0x1
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 88523f9..7555793 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -70,7 +70,7 @@
p = FACTOR_GET(config->pshift, config->pwidth, reg);
/* Calculate the rate */
- rate = (parent_rate * n * (k + 1) >> p) / (m + 1);
+ rate = (parent_rate * (n + config->n_start) * (k + 1) >> p) / (m + 1);
return rate;
}
diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h
index f49851c..441fdc3 100644
--- a/drivers/clk/sunxi/clk-factors.h
+++ b/drivers/clk/sunxi/clk-factors.h
@@ -15,6 +15,7 @@
u8 mwidth;
u8 pshift;
u8 pwidth;
+ u8 n_start;
};
struct clk *clk_register_factors(struct device *dev, const char *name,
diff --git a/drivers/clk/versatile/Makefile b/drivers/clk/versatile/Makefile
index c16ca78..6e76bf8 100644
--- a/drivers/clk/versatile/Makefile
+++ b/drivers/clk/versatile/Makefile
@@ -4,4 +4,4 @@
obj-$(CONFIG_INTEGRATOR_IMPD1) += clk-impd1.o
obj-$(CONFIG_ARCH_REALVIEW) += clk-realview.o
obj-$(CONFIG_ARCH_VEXPRESS) += clk-vexpress.o clk-sp810.o
-obj-$(CONFIG_VEXPRESS_CONFIG) += clk-vexpress-osc.o
+obj-$(CONFIG_VEXPRESS_CONFIG) += clk-vexpress-osc.o clk-vexpress-spc.o
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index 67ccf4a..f5e4c21 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -107,7 +107,7 @@
vco = icst_hz_to_vco(icst->params, rate);
icst->rate = icst_hz(icst->params, vco);
- vco_set(icst->vcoreg, icst->lockreg, vco);
+ vco_set(icst->lockreg, icst->vcoreg, vco);
return 0;
}
diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c
index 256c8be..a535c7b 100644
--- a/drivers/clk/versatile/clk-vexpress-osc.c
+++ b/drivers/clk/versatile/clk-vexpress-osc.c
@@ -102,12 +102,12 @@
osc = kzalloc(sizeof(*osc), GFP_KERNEL);
if (!osc)
- goto error;
+ return;
osc->func = vexpress_config_func_get_by_node(node);
if (!osc->func) {
pr_err("Failed to obtain config func for node '%s'!\n",
- node->name);
+ node->full_name);
goto error;
}
@@ -119,7 +119,7 @@
of_property_read_string(node, "clock-output-names", &init.name);
if (!init.name)
- init.name = node->name;
+ init.name = node->full_name;
init.ops = &vexpress_osc_ops;
init.flags = CLK_IS_ROOT;
diff --git a/drivers/clk/versatile/clk-vexpress-spc.c b/drivers/clk/versatile/clk-vexpress-spc.c
new file mode 100644
index 0000000..bb566e2
--- /dev/null
+++ b/drivers/clk/versatile/clk-vexpress-spc.c
@@ -0,0 +1,131 @@
+/*
+ * Copyright (C) 2012 ARM Limited
+ * Copyright (C) 2012 Linaro
+ *
+ * Author: Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+/* SPC clock programming interface for Vexpress cpus */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/vexpress.h>
+
+struct clk_spc {
+ struct clk_hw hw;
+ spinlock_t *lock;
+ int cluster;
+};
+
+#define to_clk_spc(spc) container_of(spc, struct clk_spc, hw)
+
+static unsigned long spc_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct clk_spc *spc = to_clk_spc(hw);
+ u32 freq;
+
+ if (vexpress_spc_get_performance(spc->cluster, &freq)) {
+ return -EIO;
+ pr_err("%s: Failed", __func__);
+ }
+
+ return freq * 1000;
+}
+
+static long spc_round_rate(struct clk_hw *hw, unsigned long drate,
+ unsigned long *parent_rate)
+{
+ return drate;
+}
+
+static int spc_set_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long parent_rate)
+{
+ struct clk_spc *spc = to_clk_spc(hw);
+
+ return vexpress_spc_set_performance(spc->cluster, rate / 1000);
+}
+
+static struct clk_ops clk_spc_ops = {
+ .recalc_rate = spc_recalc_rate,
+ .round_rate = spc_round_rate,
+ .set_rate = spc_set_rate,
+};
+
+struct clk *vexpress_clk_register_spc(const char *name, int cluster_id)
+{
+ struct clk_init_data init;
+ struct clk_spc *spc;
+ struct clk *clk;
+
+ if (!name) {
+ pr_err("Invalid name passed");
+ return ERR_PTR(-EINVAL);
+ }
+
+ spc = kzalloc(sizeof(*spc), GFP_KERNEL);
+ if (!spc) {
+ pr_err("could not allocate spc clk\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ spc->hw.init = &init;
+ spc->cluster = cluster_id;
+
+ init.name = name;
+ init.ops = &clk_spc_ops;
+ init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE;
+ init.num_parents = 0;
+
+ clk = clk_register(NULL, &spc->hw);
+ if (!IS_ERR_OR_NULL(clk))
+ return clk;
+
+ pr_err("clk register failed\n");
+ kfree(spc);
+
+ return NULL;
+}
+
+#if defined(CONFIG_OF)
+void __init vexpress_clk_of_register_spc(void)
+{
+ char name[14] = "cpu-cluster.X";
+ struct device_node *node = NULL;
+ struct clk *clk;
+ const u32 *val;
+ int cluster_id = 0, len;
+
+ if (!of_find_compatible_node(NULL, NULL, "arm,vexpress-spc")) {
+ pr_debug("%s: No SPC found, Exiting!!\n", __func__);
+ return;
+ }
+
+ while ((node = of_find_node_by_name(node, "cluster"))) {
+ val = of_get_property(node, "reg", &len);
+ if (val && len == 4)
+ cluster_id = be32_to_cpup(val);
+
+ name[12] = cluster_id + '0';
+ clk = vexpress_clk_register_spc(name, cluster_id);
+ if (IS_ERR(clk))
+ return;
+
+ pr_debug("Registered clock '%s'\n", name);
+ clk_register_clkdev(clk, NULL, name);
+ }
+}
+CLK_OF_DECLARE(spc, "arm,vexpress-spc", vexpress_clk_of_register_spc);
+#endif
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index f151c6c..593485b0 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -67,6 +67,21 @@
bool
select CLKSRC_OF if OF
+config ARM_ARCH_TIMER_EVTSTREAM
+ bool "Support for ARM architected timer event stream generation"
+ default y if ARM_ARCH_TIMER
+ help
+ This option enables support for event stream generation based on
+ the ARM architected timer. It is used for waking up CPUs executing
+ the wfe instruction at a frequency represented as a power-of-2
+ divisor of the clock rate.
+ The main use of the event stream is wfe-based timeouts of userspace
+ locking implementations. It might also be useful for imposing timeout
+ on wfe to safeguard against any programming errors in case an expected
+ event is not generated.
+ This must be disabled for hardware validation purposes to detect any
+ hardware anomalies of missing events.
+
config CLKSRC_METAG_GENERIC
def_bool y if METAG
help
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index a2b2541..67bbbd8 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -13,16 +13,43 @@
#include <linux/device.h>
#include <linux/smp.h>
#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/of_irq.h>
+#include <linux/of_address.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <asm/arch_timer.h>
#include <asm/virt.h>
#include <clocksource/arm_arch_timer.h>
+#define CNTTIDR 0x08
+#define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4))
+
+#define CNTVCT_LO 0x08
+#define CNTVCT_HI 0x0c
+#define CNTFRQ 0x10
+#define CNTP_TVAL 0x28
+#define CNTP_CTL 0x2c
+#define CNTV_TVAL 0x38
+#define CNTV_CTL 0x3c
+
+#define ARCH_CP15_TIMER BIT(0)
+#define ARCH_MEM_TIMER BIT(1)
+static unsigned arch_timers_present __initdata;
+
+static void __iomem *arch_counter_base;
+
+struct arch_timer {
+ void __iomem *base;
+ struct clock_event_device evt;
+};
+
+#define to_arch_timer(e) container_of(e, struct arch_timer, evt)
+
static u32 arch_timer_rate;
enum ppi_nr {
@@ -38,19 +65,82 @@
static struct clock_event_device __percpu *arch_timer_evt;
static bool arch_timer_use_virtual = true;
+static bool arch_timer_mem_use_virtual;
/*
* Architected system timer support.
*/
-static inline irqreturn_t timer_handler(const int access,
+static __always_inline
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+ struct clock_event_device *clk)
+{
+ if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ writel_relaxed(val, timer->base + CNTP_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ writel_relaxed(val, timer->base + CNTP_TVAL);
+ break;
+ }
+ } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ writel_relaxed(val, timer->base + CNTV_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ writel_relaxed(val, timer->base + CNTV_TVAL);
+ break;
+ }
+ } else {
+ arch_timer_reg_write_cp15(access, reg, val);
+ }
+}
+
+static __always_inline
+u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
+ struct clock_event_device *clk)
+{
+ u32 val;
+
+ if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ val = readl_relaxed(timer->base + CNTP_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ val = readl_relaxed(timer->base + CNTP_TVAL);
+ break;
+ }
+ } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ val = readl_relaxed(timer->base + CNTV_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ val = readl_relaxed(timer->base + CNTV_TVAL);
+ break;
+ }
+ } else {
+ val = arch_timer_reg_read_cp15(access, reg);
+ }
+
+ return val;
+}
+
+static __always_inline irqreturn_t timer_handler(const int access,
struct clock_event_device *evt)
{
unsigned long ctrl;
- ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+ ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, evt);
if (ctrl & ARCH_TIMER_CTRL_IT_STAT) {
ctrl |= ARCH_TIMER_CTRL_IT_MASK;
- arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, evt);
evt->event_handler(evt);
return IRQ_HANDLED;
}
@@ -72,15 +162,30 @@
return timer_handler(ARCH_TIMER_PHYS_ACCESS, evt);
}
-static inline void timer_set_mode(const int access, int mode)
+static irqreturn_t arch_timer_handler_phys_mem(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = dev_id;
+
+ return timer_handler(ARCH_TIMER_MEM_PHYS_ACCESS, evt);
+}
+
+static irqreturn_t arch_timer_handler_virt_mem(int irq, void *dev_id)
+{
+ struct clock_event_device *evt = dev_id;
+
+ return timer_handler(ARCH_TIMER_MEM_VIRT_ACCESS, evt);
+}
+
+static __always_inline void timer_set_mode(const int access, int mode,
+ struct clock_event_device *clk)
{
unsigned long ctrl;
switch (mode) {
case CLOCK_EVT_MODE_UNUSED:
case CLOCK_EVT_MODE_SHUTDOWN:
- ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+ ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
- arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
break;
default:
break;
@@ -90,60 +195,121 @@
static void arch_timer_set_mode_virt(enum clock_event_mode mode,
struct clock_event_device *clk)
{
- timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode);
+ timer_set_mode(ARCH_TIMER_VIRT_ACCESS, mode, clk);
}
static void arch_timer_set_mode_phys(enum clock_event_mode mode,
struct clock_event_device *clk)
{
- timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode);
+ timer_set_mode(ARCH_TIMER_PHYS_ACCESS, mode, clk);
}
-static inline void set_next_event(const int access, unsigned long evt)
+static void arch_timer_set_mode_virt_mem(enum clock_event_mode mode,
+ struct clock_event_device *clk)
+{
+ timer_set_mode(ARCH_TIMER_MEM_VIRT_ACCESS, mode, clk);
+}
+
+static void arch_timer_set_mode_phys_mem(enum clock_event_mode mode,
+ struct clock_event_device *clk)
+{
+ timer_set_mode(ARCH_TIMER_MEM_PHYS_ACCESS, mode, clk);
+}
+
+static __always_inline void set_next_event(const int access, unsigned long evt,
+ struct clock_event_device *clk)
{
unsigned long ctrl;
- ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL);
+ ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
ctrl |= ARCH_TIMER_CTRL_ENABLE;
ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
- arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt);
- arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl);
+ arch_timer_reg_write(access, ARCH_TIMER_REG_TVAL, evt, clk);
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
}
static int arch_timer_set_next_event_virt(unsigned long evt,
- struct clock_event_device *unused)
+ struct clock_event_device *clk)
{
- set_next_event(ARCH_TIMER_VIRT_ACCESS, evt);
+ set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
return 0;
}
static int arch_timer_set_next_event_phys(unsigned long evt,
- struct clock_event_device *unused)
+ struct clock_event_device *clk)
{
- set_next_event(ARCH_TIMER_PHYS_ACCESS, evt);
+ set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
return 0;
}
+static void arch_timer_configure_evtstream(void)
+{
+ int evt_stream_div, pos;
+
+ /* Find the closest power of two to the divisor */
+ evt_stream_div = arch_timer_rate / ARCH_TIMER_EVT_STREAM_FREQ;
+ pos = fls(evt_stream_div);
+ if (pos > 1 && !(evt_stream_div & (1 << (pos - 2))))
+ pos--;
+ /* enable event stream */
+ arch_timer_evtstrm_enable(min(pos, 15));
+}
+
+static int arch_timer_set_next_event_virt_mem(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ set_next_event(ARCH_TIMER_MEM_VIRT_ACCESS, evt, clk);
+ return 0;
+}
+
+static int arch_timer_set_next_event_phys_mem(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ set_next_event(ARCH_TIMER_MEM_PHYS_ACCESS, evt, clk);
+ return 0;
+}
+
+static void __cpuinit __arch_timer_setup(unsigned type,
+ struct clock_event_device *clk)
+{
+ clk->features = CLOCK_EVT_FEAT_ONESHOT;
+
+ if (type == ARCH_CP15_TIMER) {
+ clk->features |= CLOCK_EVT_FEAT_C3STOP;
+ clk->name = "arch_sys_timer";
+ clk->rating = 450;
+ clk->cpumask = cpumask_of(smp_processor_id());
+ if (arch_timer_use_virtual) {
+ clk->irq = arch_timer_ppi[VIRT_PPI];
+ clk->set_mode = arch_timer_set_mode_virt;
+ clk->set_next_event = arch_timer_set_next_event_virt;
+ } else {
+ clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
+ clk->set_mode = arch_timer_set_mode_phys;
+ clk->set_next_event = arch_timer_set_next_event_phys;
+ }
+ } else {
+ clk->name = "arch_mem_timer";
+ clk->rating = 400;
+ clk->cpumask = cpu_all_mask;
+ if (arch_timer_mem_use_virtual) {
+ clk->set_mode = arch_timer_set_mode_virt_mem;
+ clk->set_next_event =
+ arch_timer_set_next_event_virt_mem;
+ } else {
+ clk->set_mode = arch_timer_set_mode_phys_mem;
+ clk->set_next_event =
+ arch_timer_set_next_event_phys_mem;
+ }
+ }
+
+ clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, clk);
+
+ clockevents_config_and_register(clk, arch_timer_rate, 0xf, 0x7fffffff);
+}
+
static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
{
- clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
- clk->name = "arch_sys_timer";
- clk->rating = 450;
- if (arch_timer_use_virtual) {
- clk->irq = arch_timer_ppi[VIRT_PPI];
- clk->set_mode = arch_timer_set_mode_virt;
- clk->set_next_event = arch_timer_set_next_event_virt;
- } else {
- clk->irq = arch_timer_ppi[PHYS_SECURE_PPI];
- clk->set_mode = arch_timer_set_mode_phys;
- clk->set_next_event = arch_timer_set_next_event_phys;
- }
-
- clk->cpumask = cpumask_of(smp_processor_id());
-
- clk->set_mode(CLOCK_EVT_MODE_SHUTDOWN, NULL);
-
- clockevents_config_and_register(clk, arch_timer_rate,
- 0xf, 0x7fffffff);
+ __arch_timer_setup(ARCH_CP15_TIMER, clk);
if (arch_timer_use_virtual)
enable_percpu_irq(arch_timer_ppi[VIRT_PPI], 0);
@@ -154,31 +320,47 @@
}
arch_counter_set_user_access();
+ if (IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM))
+ arch_timer_configure_evtstream();
return 0;
}
-static int arch_timer_available(void)
+static void
+arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np)
{
- u32 freq;
+ /* Who has more than one independent system counter? */
+ if (arch_timer_rate)
+ return;
- if (arch_timer_rate == 0) {
- freq = arch_timer_get_cntfrq();
-
- /* Check the timer frequency. */
- if (freq == 0) {
- pr_warn("Architected timer frequency not available\n");
- return -EINVAL;
- }
-
- arch_timer_rate = freq;
+ /* Try to determine the frequency from the device tree or CNTFRQ */
+ if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) {
+ if (cntbase)
+ arch_timer_rate = readl_relaxed(cntbase + CNTFRQ);
+ else
+ arch_timer_rate = arch_timer_get_cntfrq();
}
- pr_info_once("Architected local timer running at %lu.%02luMHz (%s).\n",
+ /* Check the timer frequency. */
+ if (arch_timer_rate == 0)
+ pr_warn("Architected timer frequency not available\n");
+}
+
+static void arch_timer_banner(unsigned type)
+{
+ pr_info("Architected %s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
+ type & ARCH_CP15_TIMER ? "cp15" : "",
+ type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ? " and " : "",
+ type & ARCH_MEM_TIMER ? "mmio" : "",
(unsigned long)arch_timer_rate / 1000000,
(unsigned long)(arch_timer_rate / 10000) % 100,
- arch_timer_use_virtual ? "virt" : "phys");
- return 0;
+ type & ARCH_CP15_TIMER ?
+ arch_timer_use_virtual ? "virt" : "phys" :
+ "",
+ type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ? "/" : "",
+ type & ARCH_MEM_TIMER ?
+ arch_timer_mem_use_virtual ? "virt" : "phys" :
+ "");
}
u32 arch_timer_get_rate(void)
@@ -186,27 +368,35 @@
return arch_timer_rate;
}
-/*
- * Some external users of arch_timer_read_counter (e.g. sched_clock) may try to
- * call it before it has been initialised. Rather than incur a performance
- * penalty checking for initialisation, provide a default implementation that
- * won't lead to time appearing to jump backwards.
- */
-static u64 arch_timer_read_zero(void)
+static u64 arch_counter_get_cntvct_mem(void)
{
- return 0;
+ u32 vct_lo, vct_hi, tmp_hi;
+
+ do {
+ vct_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+ vct_lo = readl_relaxed(arch_counter_base + CNTVCT_LO);
+ tmp_hi = readl_relaxed(arch_counter_base + CNTVCT_HI);
+ } while (vct_hi != tmp_hi);
+
+ return ((u64) vct_hi << 32) | vct_lo;
}
-u64 (*arch_timer_read_counter)(void) = arch_timer_read_zero;
+/*
+ * Default to cp15 based access because arm64 uses this function for
+ * sched_clock() before DT is probed and the cp15 method is guaranteed
+ * to exist on arm64. arm doesn't use this before DT is probed so even
+ * if we don't have the cp15 accessors we won't have a problem.
+ */
+u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
static cycle_t arch_counter_read(struct clocksource *cs)
{
- return arch_timer_read_counter();
+ return arch_counter_get_cntvct();
}
static cycle_t arch_counter_read_cc(const struct cyclecounter *cc)
{
- return arch_timer_read_counter();
+ return arch_counter_get_cntvct();
}
static struct clocksource clocksource_counter = {
@@ -229,6 +419,23 @@
return &timecounter;
}
+static void __init arch_counter_register(unsigned type)
+{
+ u64 start_count;
+
+ /* Register the CP15 based counter if we have one */
+ if (type & ARCH_CP15_TIMER)
+ arch_timer_read_counter = arch_counter_get_cntvct;
+ else
+ arch_timer_read_counter = arch_counter_get_cntvct_mem;
+
+ start_count = arch_timer_read_counter();
+ clocksource_register_hz(&clocksource_counter, arch_timer_rate);
+ cyclecounter.mult = clocksource_counter.mult;
+ cyclecounter.shift = clocksource_counter.shift;
+ timecounter_init(&timecounter, &cyclecounter, start_count);
+}
+
static void __cpuinit arch_timer_stop(struct clock_event_device *clk)
{
pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
@@ -268,27 +475,44 @@
.notifier_call = arch_timer_cpu_notify,
};
+#ifdef CONFIG_CPU_PM
+static unsigned int saved_cntkctl;
+static int arch_timer_cpu_pm_notify(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ if (action == CPU_PM_ENTER)
+ saved_cntkctl = arch_timer_get_cntkctl();
+ else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
+ arch_timer_set_cntkctl(saved_cntkctl);
+ return NOTIFY_OK;
+}
+
+static struct notifier_block arch_timer_cpu_pm_notifier = {
+ .notifier_call = arch_timer_cpu_pm_notify,
+};
+
+static int __init arch_timer_cpu_pm_init(void)
+{
+ return cpu_pm_register_notifier(&arch_timer_cpu_pm_notifier);
+}
+#else
+static int __init arch_timer_cpu_pm_init(void)
+{
+ return 0;
+}
+#endif
+
static int __init arch_timer_register(void)
{
int err;
int ppi;
- err = arch_timer_available();
- if (err)
- goto out;
-
arch_timer_evt = alloc_percpu(struct clock_event_device);
if (!arch_timer_evt) {
err = -ENOMEM;
goto out;
}
- clocksource_register_hz(&clocksource_counter, arch_timer_rate);
- cyclecounter.mult = clocksource_counter.mult;
- cyclecounter.shift = clocksource_counter.shift;
- timecounter_init(&timecounter, &cyclecounter,
- arch_counter_get_cntpct());
-
if (arch_timer_use_virtual) {
ppi = arch_timer_ppi[VIRT_PPI];
err = request_percpu_irq(ppi, arch_timer_handler_virt,
@@ -317,11 +541,17 @@
if (err)
goto out_free_irq;
+ err = arch_timer_cpu_pm_init();
+ if (err)
+ goto out_unreg_notify;
+
/* Immediately configure the timer on the boot CPU */
arch_timer_setup(this_cpu_ptr(arch_timer_evt));
return 0;
+out_unreg_notify:
+ unregister_cpu_notifier(&arch_timer_cpu_nb);
out_free_irq:
if (arch_timer_use_virtual)
free_percpu_irq(arch_timer_ppi[VIRT_PPI], arch_timer_evt);
@@ -339,24 +569,77 @@
return err;
}
+static int __init arch_timer_mem_register(void __iomem *base, unsigned int irq)
+{
+ int ret;
+ irq_handler_t func;
+ struct arch_timer *t;
+
+ t = kzalloc(sizeof(*t), GFP_KERNEL);
+ if (!t)
+ return -ENOMEM;
+
+ t->base = base;
+ t->evt.irq = irq;
+ __arch_timer_setup(ARCH_MEM_TIMER, &t->evt);
+
+ if (arch_timer_mem_use_virtual)
+ func = arch_timer_handler_virt_mem;
+ else
+ func = arch_timer_handler_phys_mem;
+
+ ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
+ if (ret) {
+ pr_err("arch_timer: Failed to request mem timer irq\n");
+ kfree(t);
+ }
+
+ return ret;
+}
+
+static const struct of_device_id arch_timer_of_match[] __initconst = {
+ { .compatible = "arm,armv7-timer", },
+ { .compatible = "arm,armv8-timer", },
+ {},
+};
+
+static const struct of_device_id arch_timer_mem_of_match[] __initconst = {
+ { .compatible = "arm,armv7-timer-mem", },
+ {},
+};
+
+static void __init arch_timer_common_init(void)
+{
+ unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
+
+ /* Wait until both nodes are probed if we have two timers */
+ if ((arch_timers_present & mask) != mask) {
+ if (of_find_matching_node(NULL, arch_timer_mem_of_match) &&
+ !(arch_timers_present & ARCH_MEM_TIMER))
+ return;
+ if (of_find_matching_node(NULL, arch_timer_of_match) &&
+ !(arch_timers_present & ARCH_CP15_TIMER))
+ return;
+ }
+
+ arch_timer_banner(arch_timers_present);
+ arch_counter_register(arch_timers_present);
+ arch_timer_arch_init();
+}
+
static void __init arch_timer_init(struct device_node *np)
{
- u32 freq;
int i;
- if (arch_timer_get_rate()) {
+ if (arch_timers_present & ARCH_CP15_TIMER) {
pr_warn("arch_timer: multiple nodes in dt, skipping\n");
return;
}
- /* Try to determine the frequency from the device tree or CNTFRQ */
- if (!of_property_read_u32(np, "clock-frequency", &freq))
- arch_timer_rate = freq;
-
+ arch_timers_present |= ARCH_CP15_TIMER;
for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
-
- of_node_put(np);
+ arch_timer_detect_rate(NULL, np);
/*
* If HYP mode is available, we know that the physical timer
@@ -376,13 +659,74 @@
}
}
- if (arch_timer_use_virtual)
- arch_timer_read_counter = arch_counter_get_cntvct;
- else
- arch_timer_read_counter = arch_counter_get_cntpct;
-
arch_timer_register();
- arch_timer_arch_init();
+ arch_timer_common_init();
}
CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_init);
CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_init);
+
+static void __init arch_timer_mem_init(struct device_node *np)
+{
+ struct device_node *frame, *best_frame = NULL;
+ void __iomem *cntctlbase, *base;
+ unsigned int irq;
+ u32 cnttidr;
+
+ arch_timers_present |= ARCH_MEM_TIMER;
+ cntctlbase = of_iomap(np, 0);
+ if (!cntctlbase) {
+ pr_err("arch_timer: Can't find CNTCTLBase\n");
+ return;
+ }
+
+ cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
+ iounmap(cntctlbase);
+
+ /*
+ * Try to find a virtual capable frame. Otherwise fall back to a
+ * physical capable frame.
+ */
+ for_each_available_child_of_node(np, frame) {
+ int n;
+
+ if (of_property_read_u32(frame, "frame-number", &n)) {
+ pr_err("arch_timer: Missing frame-number\n");
+ of_node_put(best_frame);
+ of_node_put(frame);
+ return;
+ }
+
+ if (cnttidr & CNTTIDR_VIRT(n)) {
+ of_node_put(best_frame);
+ best_frame = frame;
+ arch_timer_mem_use_virtual = true;
+ break;
+ }
+ of_node_put(best_frame);
+ best_frame = of_node_get(frame);
+ }
+
+ base = arch_counter_base = of_iomap(best_frame, 0);
+ if (!base) {
+ pr_err("arch_timer: Can't map frame's registers\n");
+ of_node_put(best_frame);
+ return;
+ }
+
+ if (arch_timer_mem_use_virtual)
+ irq = irq_of_parse_and_map(best_frame, 1);
+ else
+ irq = irq_of_parse_and_map(best_frame, 0);
+ of_node_put(best_frame);
+ if (!irq) {
+ pr_err("arch_timer: Frame missing %s irq",
+ arch_timer_mem_use_virtual ? "virt" : "phys");
+ return;
+ }
+
+ arch_timer_detect_rate(base, np);
+ arch_timer_mem_register(base, irq);
+ arch_timer_common_init();
+}
+CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
+ arch_timer_mem_init);
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index ab09ed3..f22417c 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -44,7 +44,7 @@
u32 irq, rate;
irq = irq_of_parse_and_map(event_timer, 0);
- if (irq == NO_IRQ)
+ if (irq == 0)
panic("No IRQ for clock event timer");
timer_get_base_and_rate(event_timer, &iobase, &rate);
@@ -77,7 +77,7 @@
static u32 read_sched_clock(void)
{
- return __raw_readl(sched_io_base);
+ return ~__raw_readl(sched_io_base);
}
static const struct of_device_id sptimer_ids[] __initconst = {
diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c
index 4329a29..3141849 100644
--- a/drivers/clocksource/em_sti.c
+++ b/drivers/clocksource/em_sti.c
@@ -301,7 +301,7 @@
ced->name = dev_name(&p->pdev->dev);
ced->features = CLOCK_EVT_FEAT_ONESHOT;
ced->rating = 200;
- ced->cpumask = cpumask_of(0);
+ ced->cpumask = cpu_possible_mask;
ced->set_next_event = em_sti_clock_event_next;
ced->set_mode = em_sti_clock_event_mode;
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 662fcc0..3dfa3e5 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -94,8 +94,8 @@
__raw_writel(value, reg_base + offset);
if (likely(offset >= EXYNOS4_MCT_L_BASE(0))) {
- stat_addr = (offset & ~EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
- switch (offset & EXYNOS4_MCT_L_MASK) {
+ stat_addr = (offset & EXYNOS4_MCT_L_MASK) + MCT_L_WSTAT_OFFSET;
+ switch (offset & ~EXYNOS4_MCT_L_MASK) {
case MCT_L_TCON_OFFSET:
mask = 1 << 3; /* L_TCON write status */
break;
@@ -429,8 +429,6 @@
evt->set_mode = exynos4_tick_set_mode;
evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
evt->rating = 450;
- clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
- 0xf, 0x7fffffff);
exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
@@ -448,6 +446,8 @@
} else {
enable_percpu_irq(mct_irqs[MCT_L0_IRQ], 0);
}
+ clockevents_config_and_register(evt, clk_rate / (TICK_BASE_CNT + 1),
+ 0xf, 0x7fffffff);
return 0;
}
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 08ae128..3165811 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -32,11 +32,23 @@
#include <linux/atomic.h>
#include <linux/pid_namespace.h>
-#include <asm/unaligned.h>
-
#include <linux/cn_proc.h>
-#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
+/*
+ * Size of a cn_msg followed by a proc_event structure. Since the
+ * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we
+ * add one 4-byte word to the size here, and then start the actual
+ * cn_msg structure 4 bytes into the stack buffer. The result is that
+ * the immediately following proc_event structure is aligned to 8 bytes.
+ */
+#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4)
+
+/* See comment above; we test our assumption about sizeof struct cn_msg here. */
+static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
+{
+ BUILD_BUG_ON(sizeof(struct cn_msg) != 20);
+ return (struct cn_msg *)(buffer + 4);
+}
static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
@@ -56,18 +68,19 @@
{
struct cn_msg *msg;
struct proc_event *ev;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
struct timespec ts;
struct task_struct *parent;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_FORK;
rcu_read_lock();
parent = rcu_dereference(task->real_parent);
@@ -80,6 +93,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
/* If cn_netlink_send() failed, the data is not sent */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -89,16 +103,17 @@
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_EXEC;
ev->event_data.exec.process_pid = task->pid;
ev->event_data.exec.process_tgid = task->tgid;
@@ -106,6 +121,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -113,15 +129,16 @@
{
struct cn_msg *msg;
struct proc_event *ev;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
struct timespec ts;
const struct cred *cred;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
ev->what = which_id;
ev->event_data.id.process_pid = task->pid;
ev->event_data.id.process_tgid = task->tgid;
@@ -140,11 +157,12 @@
rcu_read_unlock();
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -153,16 +171,17 @@
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_SID;
ev->event_data.sid.process_pid = task->pid;
ev->event_data.sid.process_tgid = task->tgid;
@@ -170,6 +189,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -178,16 +198,17 @@
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_PTRACE;
ev->event_data.ptrace.process_pid = task->pid;
ev->event_data.ptrace.process_tgid = task->tgid;
@@ -203,6 +224,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -211,16 +233,17 @@
struct cn_msg *msg;
struct proc_event *ev;
struct timespec ts;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_COMM;
ev->event_data.comm.process_pid = task->pid;
ev->event_data.comm.process_tgid = task->tgid;
@@ -229,6 +252,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -236,17 +260,18 @@
{
struct cn_msg *msg;
struct proc_event *ev;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
struct timespec ts;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_COREDUMP;
ev->event_data.coredump.process_pid = task->pid;
ev->event_data.coredump.process_tgid = task->tgid;
@@ -254,6 +279,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -261,17 +287,18 @@
{
struct cn_msg *msg;
struct proc_event *ev;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
struct timespec ts;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
get_seq(&msg->seq, &ev->cpu);
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->what = PROC_EVENT_EXIT;
ev->event_data.exit.process_pid = task->pid;
ev->event_data.exit.process_tgid = task->tgid;
@@ -281,6 +308,7 @@
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = 0; /* not used */
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -296,23 +324,25 @@
{
struct cn_msg *msg;
struct proc_event *ev;
- __u8 buffer[CN_PROC_MSG_SIZE];
+ __u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
struct timespec ts;
if (atomic_read(&proc_event_num_listeners) < 1)
return;
- msg = (struct cn_msg *)buffer;
+ msg = buffer_to_cn_msg(buffer);
ev = (struct proc_event *)msg->data;
+ memset(&ev->event_data, 0, sizeof(ev->event_data));
msg->seq = rcvd_seq;
ktime_get_ts(&ts); /* get high res monotonic timestamp */
- put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+ ev->timestamp_ns = timespec_to_ns(&ts);
ev->cpu = -1;
ev->what = PROC_EVENT_NONE;
ev->event_data.ack.err = err;
memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
msg->ack = rcvd_ack + 1;
msg->len = sizeof(*ev);
+ msg->flags = 0; /* not used */
cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
}
@@ -339,7 +369,7 @@
return;
/* Can only change if privileged. */
- if (!capable(CAP_NET_ADMIN)) {
+ if (!__netlink_ns_capable(nsp, &init_user_ns, CAP_NET_ADMIN)) {
err = EPERM;
goto out;
}
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index 6ecfa75..0daa11e 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -157,17 +157,18 @@
static void cn_rx_skb(struct sk_buff *__skb)
{
struct nlmsghdr *nlh;
- int err;
struct sk_buff *skb;
+ int len, err;
skb = skb_get(__skb);
if (skb->len >= NLMSG_HDRLEN) {
nlh = nlmsg_hdr(skb);
+ len = nlmsg_len(nlh);
- if (nlh->nlmsg_len < sizeof(struct cn_msg) ||
+ if (len < (int)sizeof(struct cn_msg) ||
skb->len < nlh->nlmsg_len ||
- nlh->nlmsg_len > CONNECTOR_MAX_MSG_SIZE) {
+ len > CONNECTOR_MAX_MSG_SIZE) {
kfree_skb(skb);
return;
}
diff --git a/drivers/coresight/Makefile b/drivers/coresight/Makefile
new file mode 100644
index 0000000..4b4bec8
--- /dev/null
+++ b/drivers/coresight/Makefile
@@ -0,0 +1,11 @@
+#
+# Makefile for CoreSight drivers.
+#
+obj-$(CONFIG_CORESIGHT) += coresight.o
+obj-$(CONFIG_OF) += of_coresight.o
+obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o
+obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o
+obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o
+obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \
+ coresight-replicator.o
+obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o
diff --git a/drivers/coresight/coresight-etb10.c b/drivers/coresight/coresight-etb10.c
new file mode 100644
index 0000000..c9acd40
--- /dev/null
+++ b/drivers/coresight/coresight-etb10.c
@@ -0,0 +1,527 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/seq_file.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define ETB_RAM_DEPTH_REG 0x004
+#define ETB_STATUS_REG 0x00c
+#define ETB_RAM_READ_DATA_REG 0x010
+#define ETB_RAM_READ_POINTER 0x014
+#define ETB_RAM_WRITE_POINTER 0x018
+#define ETB_TRG 0x01c
+#define ETB_CTL_REG 0x020
+#define ETB_RWD_REG 0x024
+#define ETB_FFSR 0x300
+#define ETB_FFCR 0x304
+#define ETB_ITMISCOP0 0xee0
+#define ETB_ITTRFLINACK 0xee4
+#define ETB_ITTRFLIN 0xee8
+#define ETB_ITATBDATA0 0xeeC
+#define ETB_ITATBCTR2 0xef0
+#define ETB_ITATBCTR1 0xef4
+#define ETB_ITATBCTR0 0xef8
+
+/* register description */
+/* STS - 0x00C */
+#define ETB_STATUS_RAM_FULL BIT(0)
+/* CTL - 0x020 */
+#define ETB_CTL_CAPT_EN BIT(0)
+/* FFCR - 0x304 */
+#define ETB_FFCR_EN_FTC BIT(0)
+#define ETB_FFCR_FON_MAN BIT(6)
+#define ETB_FFCR_STOP_FI BIT(12)
+#define ETB_FFCR_STOP_TRIGGER BIT(13)
+
+#define ETB_FFCR_BIT 6
+#define ETB_FFSR_BIT 1
+#define ETB_FRAME_SIZE_WORDS 4
+
+/**
+ * struct etb_drvdata - specifics associated to an ETB component
+ * @base: memory mapped base address for this component.
+ * @dev: the device entity associated to this component.
+ * @csdev: component vitals needed by the framework.
+ * @miscdev: specifics to handle "/dev/xyz.etb" entry.
+ * @clk: the clock this component is associated to.
+ * @spinlock: only one at a time pls.
+ * @in_use: synchronise user space access to etb buffer.
+ * @buf: area of memory where ETB buffer content gets sent.
+ * @buffer_depth: size of @buf.
+ * @enable: this ETB is being used.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct etb_drvdata {
+ void __iomem *base;
+ struct device *dev;
+ struct coresight_device *csdev;
+ struct miscdevice miscdev;
+ struct clk *clk;
+ spinlock_t spinlock;
+ atomic_t in_use;
+ u8 *buf;
+ u32 buffer_depth;
+ bool enable;
+ u32 trigger_cntr;
+};
+
+static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata)
+{
+ int ret;
+ u32 depth = 0;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ /* RO registers don't need locking */
+ depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+
+ clk_disable_unprepare(drvdata->clk);
+ return depth;
+}
+
+static void etb_enable_hw(struct etb_drvdata *drvdata)
+{
+ int i;
+ u32 depth;
+
+ CS_UNLOCK(drvdata->base);
+
+ depth = drvdata->buffer_depth;
+ /* reset write RAM pointer address */
+ writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+ /* clear entire RAM buffer */
+ for (i = 0; i < depth; i++)
+ writel_relaxed(0x0, drvdata->base + ETB_RWD_REG);
+
+ /* reset write RAM pointer address */
+ writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER);
+ /* reset read RAM pointer address */
+ writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+
+ writel_relaxed(drvdata->trigger_cntr, drvdata->base + ETB_TRG);
+ writel_relaxed(ETB_FFCR_EN_FTC | ETB_FFCR_STOP_TRIGGER,
+ drvdata->base + ETB_FFCR);
+ /* ETB trace capture enable */
+ writel_relaxed(ETB_CTL_CAPT_EN, drvdata->base + ETB_CTL_REG);
+
+ CS_LOCK(drvdata->base);
+}
+
+static int etb_enable(struct coresight_device *csdev)
+{
+ struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ int ret;
+ unsigned long flags;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ etb_enable_hw(drvdata);
+ drvdata->enable = true;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ dev_info(drvdata->dev, "ETB enabled\n");
+ return 0;
+}
+
+static void etb_disable_hw(struct etb_drvdata *drvdata)
+{
+ u32 ffcr;
+
+ CS_UNLOCK(drvdata->base);
+
+ ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+ /* stop formatter when a stop has completed */
+ ffcr |= ETB_FFCR_STOP_FI;
+ writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+ /* manually generate a flush of the system */
+ ffcr |= ETB_FFCR_FON_MAN;
+ writel_relaxed(ffcr, drvdata->base + ETB_FFCR);
+
+ if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n",
+ ETB_FFCR);
+ }
+
+ /* disable trace capture */
+ writel_relaxed(0x0, drvdata->base + ETB_CTL_REG);
+
+ if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n",
+ ETB_FFCR);
+ }
+
+ CS_LOCK(drvdata->base);
+}
+
+static void etb_dump_hw(struct etb_drvdata *drvdata)
+{
+ int i;
+ u8 *buf_ptr;
+ u32 read_data, depth;
+ u32 read_ptr, write_ptr;
+ u32 frame_off, frame_endoff;
+
+ CS_UNLOCK(drvdata->base);
+
+ read_ptr = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+ write_ptr = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+
+ frame_off = write_ptr % ETB_FRAME_SIZE_WORDS;
+ frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off;
+ if (frame_off) {
+ dev_err(drvdata->dev,
+ "write_ptr: %lu not aligned to formatter frame size\n",
+ (unsigned long)write_ptr);
+ dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n",
+ (unsigned long)frame_off, (unsigned long)frame_endoff);
+ write_ptr += frame_endoff;
+ }
+
+ if ((readl_relaxed(drvdata->base + ETB_STATUS_REG)
+ & ETB_STATUS_RAM_FULL) == 0)
+ writel_relaxed(0x0, drvdata->base + ETB_RAM_READ_POINTER);
+ else
+ writel_relaxed(write_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+ depth = drvdata->buffer_depth;
+ buf_ptr = drvdata->buf;
+ for (i = 0; i < depth; i++) {
+ read_data = readl_relaxed(drvdata->base +
+ ETB_RAM_READ_DATA_REG);
+ *buf_ptr++ = read_data >> 0;
+ *buf_ptr++ = read_data >> 8;
+ *buf_ptr++ = read_data >> 16;
+ *buf_ptr++ = read_data >> 24;
+ }
+
+ if (frame_off) {
+ buf_ptr -= (frame_endoff * 4);
+ for (i = 0; i < frame_endoff; i++) {
+ *buf_ptr++ = 0x0;
+ *buf_ptr++ = 0x0;
+ *buf_ptr++ = 0x0;
+ *buf_ptr++ = 0x0;
+ }
+ }
+
+ writel_relaxed(read_ptr, drvdata->base + ETB_RAM_READ_POINTER);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void etb_disable(struct coresight_device *csdev)
+{
+ struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ unsigned long flags;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ etb_disable_hw(drvdata);
+ etb_dump_hw(drvdata);
+ drvdata->enable = false;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ dev_info(drvdata->dev, "ETB disabled\n");
+}
+
+static const struct coresight_ops_sink etb_sink_ops = {
+ .enable = etb_enable,
+ .disable = etb_disable,
+};
+
+static const struct coresight_ops etb_cs_ops = {
+ .sink_ops = &etb_sink_ops,
+};
+
+static void etb_dump(struct etb_drvdata *drvdata)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ if (drvdata->enable) {
+ etb_disable_hw(drvdata);
+ etb_dump_hw(drvdata);
+ etb_enable_hw(drvdata);
+ }
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ dev_info(drvdata->dev, "ETB dumped\n");
+}
+
+static int etb_open(struct inode *inode, struct file *file)
+{
+ struct etb_drvdata *drvdata = container_of(file->private_data,
+ struct etb_drvdata, miscdev);
+
+ if (atomic_cmpxchg(&drvdata->in_use, 0, 1))
+ return -EBUSY;
+
+ dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+ return 0;
+}
+
+static ssize_t etb_read(struct file *file, char __user *data,
+ size_t len, loff_t *ppos)
+{
+ u32 depth;
+ struct etb_drvdata *drvdata = container_of(file->private_data,
+ struct etb_drvdata, miscdev);
+
+ etb_dump(drvdata);
+
+ depth = drvdata->buffer_depth;
+ if (*ppos + len > depth * 4)
+ len = depth * 4 - *ppos;
+
+ if (copy_to_user(data, drvdata->buf + *ppos, len)) {
+ dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+ return -EFAULT;
+ }
+
+ *ppos += len;
+
+ dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+ __func__, len, (int) (depth * 4 - *ppos));
+ return len;
+}
+
+static int etb_release(struct inode *inode, struct file *file)
+{
+ struct etb_drvdata *drvdata = container_of(file->private_data,
+ struct etb_drvdata, miscdev);
+ atomic_set(&drvdata->in_use, 0);
+
+ dev_dbg(drvdata->dev, "%s: released\n", __func__);
+ return 0;
+}
+
+static const struct file_operations etb_fops = {
+ .owner = THIS_MODULE,
+ .open = etb_open,
+ .read = etb_read,
+ .release = etb_release,
+ .llseek = no_llseek,
+};
+
+static ssize_t status_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ unsigned long flags;
+ u32 etb_rdr, etb_sr, etb_rrp, etb_rwp;
+ u32 etb_trg, etb_cr, etb_ffsr, etb_ffcr;
+ struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ goto out;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ CS_UNLOCK(drvdata->base);
+
+ etb_rdr = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG);
+ etb_sr = readl_relaxed(drvdata->base + ETB_STATUS_REG);
+ etb_rrp = readl_relaxed(drvdata->base + ETB_RAM_READ_POINTER);
+ etb_rwp = readl_relaxed(drvdata->base + ETB_RAM_WRITE_POINTER);
+ etb_trg = readl_relaxed(drvdata->base + ETB_TRG);
+ etb_cr = readl_relaxed(drvdata->base + ETB_CTL_REG);
+ etb_ffsr = readl_relaxed(drvdata->base + ETB_FFSR);
+ etb_ffcr = readl_relaxed(drvdata->base + ETB_FFCR);
+
+ CS_LOCK(drvdata->base);
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ return sprintf(buf,
+ "Depth:\t\t0x%x\n"
+ "Status:\t\t0x%x\n"
+ "RAM read ptr:\t0x%x\n"
+ "RAM wrt ptr:\t0x%x\n"
+ "Trigger cnt:\t0x%x\n"
+ "Control:\t0x%x\n"
+ "Flush status:\t0x%x\n"
+ "Flush ctrl:\t0x%x\n",
+ etb_rdr, etb_sr, etb_rrp, etb_rwp,
+ etb_trg, etb_cr, etb_ffsr, etb_ffcr);
+out:
+ return -EINVAL;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t trigger_cntr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+ unsigned long val = drvdata->trigger_cntr;
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etb_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->trigger_cntr = val;
+ return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+ &dev_attr_trigger_cntr.attr,
+ &dev_attr_status.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static int etb_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ int ret;
+ void __iomem *base;
+ struct device *dev = &adev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct etb_drvdata *drvdata;
+ struct resource *res = &adev->res;
+ struct coresight_desc *desc;
+ struct device_node *np = adev->dev.of_node;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+ adev->dev.platform_data = pdata;
+ }
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->dev = &adev->dev;
+ dev_set_drvdata(dev, drvdata);
+
+ /* validity for the resource is already checked by the AMBA core */
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ drvdata->base = base;
+
+ spin_lock_init(&drvdata->spinlock);
+
+ drvdata->clk = adev->pclk;
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ drvdata->buffer_depth = etb_get_buffer_depth(drvdata);
+ clk_disable_unprepare(drvdata->clk);
+
+ if (drvdata->buffer_depth < 0)
+ return -EINVAL;
+
+ drvdata->buf = devm_kzalloc(dev,
+ drvdata->buffer_depth * 4, GFP_KERNEL);
+ if (!drvdata->buf)
+ return -ENOMEM;
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ desc->type = CORESIGHT_DEV_TYPE_SINK;
+ desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+ desc->ops = &etb_cs_ops;
+ desc->pdata = pdata;
+ desc->dev = dev;
+ desc->groups = coresight_etb_groups;
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev))
+ return PTR_ERR(drvdata->csdev);
+
+ drvdata->miscdev.name = pdata->name;
+ drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+ drvdata->miscdev.fops = &etb_fops;
+ ret = misc_register(&drvdata->miscdev);
+ if (ret)
+ goto err_misc_register;
+
+ dev_info(dev, "ETB initialized\n");
+ return 0;
+
+err_misc_register:
+ coresight_unregister(drvdata->csdev);
+ return ret;
+}
+
+static int etb_remove(struct amba_device *adev)
+{
+ struct etb_drvdata *drvdata = amba_get_drvdata(adev);
+
+ misc_deregister(&drvdata->miscdev);
+ coresight_unregister(drvdata->csdev);
+ return 0;
+}
+
+static struct amba_id etb_ids[] = {
+ {
+ .id = 0x0003b907,
+ .mask = 0x0003ffff,
+ },
+ { 0, 0},
+};
+
+static struct amba_driver etb_driver = {
+ .drv = {
+ .name = "coresight-etb10",
+ .owner = THIS_MODULE,
+ },
+ .probe = etb_probe,
+ .remove = etb_remove,
+ .id_table = etb_ids,
+};
+
+module_amba_driver(etb_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Embedded Trace Buffer driver");
diff --git a/drivers/coresight/coresight-etm-cp14.c b/drivers/coresight/coresight-etm-cp14.c
new file mode 100644
index 0000000..12a2206
--- /dev/null
+++ b/drivers/coresight/coresight-etm-cp14.c
@@ -0,0 +1,591 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <asm/hardware/cp14.h>
+
+#include "coresight-etm.h"
+
+int etm_readl_cp14(u32 reg, unsigned int *val)
+{
+ switch (reg) {
+ case ETMCR:
+ *val = etm_read(ETMCR);
+ return 0;
+ case ETMCCR:
+ *val = etm_read(ETMCCR);
+ return 0;
+ case ETMTRIGGER:
+ *val = etm_read(ETMTRIGGER);
+ return 0;
+ case ETMSR:
+ *val = etm_read(ETMSR);
+ return 0;
+ case ETMSCR:
+ *val = etm_read(ETMSCR);
+ return 0;
+ case ETMTSSCR:
+ *val = etm_read(ETMTSSCR);
+ return 0;
+ case ETMTEEVR:
+ *val = etm_read(ETMTEEVR);
+ return 0;
+ case ETMTECR1:
+ *val = etm_read(ETMTECR1);
+ return 0;
+ case ETMFFLR:
+ *val = etm_read(ETMFFLR);
+ return 0;
+ case ETMACVRn(0):
+ *val = etm_read(ETMACVR0);
+ return 0;
+ case ETMACVRn(1):
+ *val = etm_read(ETMACVR1);
+ return 0;
+ case ETMACVRn(2):
+ *val = etm_read(ETMACVR2);
+ return 0;
+ case ETMACVRn(3):
+ *val = etm_read(ETMACVR3);
+ return 0;
+ case ETMACVRn(4):
+ *val = etm_read(ETMACVR4);
+ return 0;
+ case ETMACVRn(5):
+ *val = etm_read(ETMACVR5);
+ return 0;
+ case ETMACVRn(6):
+ *val = etm_read(ETMACVR6);
+ return 0;
+ case ETMACVRn(7):
+ *val = etm_read(ETMACVR7);
+ return 0;
+ case ETMACVRn(8):
+ *val = etm_read(ETMACVR8);
+ return 0;
+ case ETMACVRn(9):
+ *val = etm_read(ETMACVR9);
+ return 0;
+ case ETMACVRn(10):
+ *val = etm_read(ETMACVR10);
+ return 0;
+ case ETMACVRn(11):
+ *val = etm_read(ETMACVR11);
+ return 0;
+ case ETMACVRn(12):
+ *val = etm_read(ETMACVR12);
+ return 0;
+ case ETMACVRn(13):
+ *val = etm_read(ETMACVR13);
+ return 0;
+ case ETMACVRn(14):
+ *val = etm_read(ETMACVR14);
+ return 0;
+ case ETMACVRn(15):
+ *val = etm_read(ETMACVR15);
+ return 0;
+ case ETMACTRn(0):
+ *val = etm_read(ETMACTR0);
+ return 0;
+ case ETMACTRn(1):
+ *val = etm_read(ETMACTR1);
+ return 0;
+ case ETMACTRn(2):
+ *val = etm_read(ETMACTR2);
+ return 0;
+ case ETMACTRn(3):
+ *val = etm_read(ETMACTR3);
+ return 0;
+ case ETMACTRn(4):
+ *val = etm_read(ETMACTR4);
+ return 0;
+ case ETMACTRn(5):
+ *val = etm_read(ETMACTR5);
+ return 0;
+ case ETMACTRn(6):
+ *val = etm_read(ETMACTR6);
+ return 0;
+ case ETMACTRn(7):
+ *val = etm_read(ETMACTR7);
+ return 0;
+ case ETMACTRn(8):
+ *val = etm_read(ETMACTR8);
+ return 0;
+ case ETMACTRn(9):
+ *val = etm_read(ETMACTR9);
+ return 0;
+ case ETMACTRn(10):
+ *val = etm_read(ETMACTR10);
+ return 0;
+ case ETMACTRn(11):
+ *val = etm_read(ETMACTR11);
+ return 0;
+ case ETMACTRn(12):
+ *val = etm_read(ETMACTR12);
+ return 0;
+ case ETMACTRn(13):
+ *val = etm_read(ETMACTR13);
+ return 0;
+ case ETMACTRn(14):
+ *val = etm_read(ETMACTR14);
+ return 0;
+ case ETMACTRn(15):
+ *val = etm_read(ETMACTR15);
+ return 0;
+ case ETMCNTRLDVRn(0):
+ *val = etm_read(ETMCNTRLDVR0);
+ return 0;
+ case ETMCNTRLDVRn(1):
+ *val = etm_read(ETMCNTRLDVR1);
+ return 0;
+ case ETMCNTRLDVRn(2):
+ *val = etm_read(ETMCNTRLDVR2);
+ return 0;
+ case ETMCNTRLDVRn(3):
+ *val = etm_read(ETMCNTRLDVR3);
+ return 0;
+ case ETMCNTENRn(0):
+ *val = etm_read(ETMCNTENR0);
+ return 0;
+ case ETMCNTENRn(1):
+ *val = etm_read(ETMCNTENR1);
+ return 0;
+ case ETMCNTENRn(2):
+ *val = etm_read(ETMCNTENR2);
+ return 0;
+ case ETMCNTENRn(3):
+ *val = etm_read(ETMCNTENR3);
+ return 0;
+ case ETMCNTRLDEVRn(0):
+ *val = etm_read(ETMCNTRLDEVR0);
+ return 0;
+ case ETMCNTRLDEVRn(1):
+ *val = etm_read(ETMCNTRLDEVR1);
+ return 0;
+ case ETMCNTRLDEVRn(2):
+ *val = etm_read(ETMCNTRLDEVR2);
+ return 0;
+ case ETMCNTRLDEVRn(3):
+ *val = etm_read(ETMCNTRLDEVR3);
+ return 0;
+ case ETMCNTVRn(0):
+ *val = etm_read(ETMCNTVR0);
+ return 0;
+ case ETMCNTVRn(1):
+ *val = etm_read(ETMCNTVR1);
+ return 0;
+ case ETMCNTVRn(2):
+ *val = etm_read(ETMCNTVR2);
+ return 0;
+ case ETMCNTVRn(3):
+ *val = etm_read(ETMCNTVR3);
+ return 0;
+ case ETMSQ12EVR:
+ *val = etm_read(ETMSQ12EVR);
+ return 0;
+ case ETMSQ21EVR:
+ *val = etm_read(ETMSQ21EVR);
+ return 0;
+ case ETMSQ23EVR:
+ *val = etm_read(ETMSQ23EVR);
+ return 0;
+ case ETMSQ31EVR:
+ *val = etm_read(ETMSQ31EVR);
+ return 0;
+ case ETMSQ32EVR:
+ *val = etm_read(ETMSQ32EVR);
+ return 0;
+ case ETMSQ13EVR:
+ *val = etm_read(ETMSQ13EVR);
+ return 0;
+ case ETMSQR:
+ *val = etm_read(ETMSQR);
+ return 0;
+ case ETMEXTOUTEVRn(0):
+ *val = etm_read(ETMEXTOUTEVR0);
+ return 0;
+ case ETMEXTOUTEVRn(1):
+ *val = etm_read(ETMEXTOUTEVR1);
+ return 0;
+ case ETMEXTOUTEVRn(2):
+ *val = etm_read(ETMEXTOUTEVR2);
+ return 0;
+ case ETMEXTOUTEVRn(3):
+ *val = etm_read(ETMEXTOUTEVR3);
+ return 0;
+ case ETMCIDCVRn(0):
+ *val = etm_read(ETMCIDCVR0);
+ return 0;
+ case ETMCIDCVRn(1):
+ *val = etm_read(ETMCIDCVR1);
+ return 0;
+ case ETMCIDCVRn(2):
+ *val = etm_read(ETMCIDCVR2);
+ return 0;
+ case ETMCIDCMR:
+ *val = etm_read(ETMCIDCMR);
+ return 0;
+ case ETMIMPSPEC0:
+ *val = etm_read(ETMIMPSPEC0);
+ return 0;
+ case ETMIMPSPEC1:
+ *val = etm_read(ETMIMPSPEC1);
+ return 0;
+ case ETMIMPSPEC2:
+ *val = etm_read(ETMIMPSPEC2);
+ return 0;
+ case ETMIMPSPEC3:
+ *val = etm_read(ETMIMPSPEC3);
+ return 0;
+ case ETMIMPSPEC4:
+ *val = etm_read(ETMIMPSPEC4);
+ return 0;
+ case ETMIMPSPEC5:
+ *val = etm_read(ETMIMPSPEC5);
+ return 0;
+ case ETMIMPSPEC6:
+ *val = etm_read(ETMIMPSPEC6);
+ return 0;
+ case ETMIMPSPEC7:
+ *val = etm_read(ETMIMPSPEC7);
+ return 0;
+ case ETMSYNCFR:
+ *val = etm_read(ETMSYNCFR);
+ return 0;
+ case ETMIDR:
+ *val = etm_read(ETMIDR);
+ return 0;
+ case ETMCCER:
+ *val = etm_read(ETMCCER);
+ return 0;
+ case ETMEXTINSELR:
+ *val = etm_read(ETMEXTINSELR);
+ return 0;
+ case ETMTESSEICR:
+ *val = etm_read(ETMTESSEICR);
+ return 0;
+ case ETMEIBCR:
+ *val = etm_read(ETMEIBCR);
+ return 0;
+ case ETMTSEVR:
+ *val = etm_read(ETMTSEVR);
+ return 0;
+ case ETMAUXCR:
+ *val = etm_read(ETMAUXCR);
+ return 0;
+ case ETMTRACEIDR:
+ *val = etm_read(ETMTRACEIDR);
+ return 0;
+ case ETMVMIDCVR:
+ *val = etm_read(ETMVMIDCVR);
+ return 0;
+ case ETMOSLSR:
+ *val = etm_read(ETMOSLSR);
+ return 0;
+ case ETMOSSRR:
+ *val = etm_read(ETMOSSRR);
+ return 0;
+ case ETMPDCR:
+ *val = etm_read(ETMPDCR);
+ return 0;
+ case ETMPDSR:
+ *val = etm_read(ETMPDSR);
+ return 0;
+ default:
+ *val = 0;
+ return -EINVAL;
+ }
+}
+
+int etm_writel_cp14(u32 reg, u32 val)
+{
+ switch (reg) {
+ case ETMCR:
+ etm_write(val, ETMCR);
+ break;
+ case ETMTRIGGER:
+ etm_write(val, ETMTRIGGER);
+ break;
+ case ETMSR:
+ etm_write(val, ETMSR);
+ break;
+ case ETMTSSCR:
+ etm_write(val, ETMTSSCR);
+ break;
+ case ETMTEEVR:
+ etm_write(val, ETMTEEVR);
+ break;
+ case ETMTECR1:
+ etm_write(val, ETMTECR1);
+ break;
+ case ETMFFLR:
+ etm_write(val, ETMFFLR);
+ break;
+ case ETMACVRn(0):
+ etm_write(val, ETMACVR0);
+ break;
+ case ETMACVRn(1):
+ etm_write(val, ETMACVR1);
+ break;
+ case ETMACVRn(2):
+ etm_write(val, ETMACVR2);
+ break;
+ case ETMACVRn(3):
+ etm_write(val, ETMACVR3);
+ break;
+ case ETMACVRn(4):
+ etm_write(val, ETMACVR4);
+ break;
+ case ETMACVRn(5):
+ etm_write(val, ETMACVR5);
+ break;
+ case ETMACVRn(6):
+ etm_write(val, ETMACVR6);
+ break;
+ case ETMACVRn(7):
+ etm_write(val, ETMACVR7);
+ break;
+ case ETMACVRn(8):
+ etm_write(val, ETMACVR8);
+ break;
+ case ETMACVRn(9):
+ etm_write(val, ETMACVR9);
+ break;
+ case ETMACVRn(10):
+ etm_write(val, ETMACVR10);
+ break;
+ case ETMACVRn(11):
+ etm_write(val, ETMACVR11);
+ break;
+ case ETMACVRn(12):
+ etm_write(val, ETMACVR12);
+ break;
+ case ETMACVRn(13):
+ etm_write(val, ETMACVR13);
+ break;
+ case ETMACVRn(14):
+ etm_write(val, ETMACVR14);
+ break;
+ case ETMACVRn(15):
+ etm_write(val, ETMACVR15);
+ break;
+ case ETMACTRn(0):
+ etm_write(val, ETMACTR0);
+ break;
+ case ETMACTRn(1):
+ etm_write(val, ETMACTR1);
+ break;
+ case ETMACTRn(2):
+ etm_write(val, ETMACTR2);
+ break;
+ case ETMACTRn(3):
+ etm_write(val, ETMACTR3);
+ break;
+ case ETMACTRn(4):
+ etm_write(val, ETMACTR4);
+ break;
+ case ETMACTRn(5):
+ etm_write(val, ETMACTR5);
+ break;
+ case ETMACTRn(6):
+ etm_write(val, ETMACTR6);
+ break;
+ case ETMACTRn(7):
+ etm_write(val, ETMACTR7);
+ break;
+ case ETMACTRn(8):
+ etm_write(val, ETMACTR8);
+ break;
+ case ETMACTRn(9):
+ etm_write(val, ETMACTR9);
+ break;
+ case ETMACTRn(10):
+ etm_write(val, ETMACTR10);
+ break;
+ case ETMACTRn(11):
+ etm_write(val, ETMACTR11);
+ break;
+ case ETMACTRn(12):
+ etm_write(val, ETMACTR12);
+ break;
+ case ETMACTRn(13):
+ etm_write(val, ETMACTR13);
+ break;
+ case ETMACTRn(14):
+ etm_write(val, ETMACTR14);
+ break;
+ case ETMACTRn(15):
+ etm_write(val, ETMACTR15);
+ break;
+ case ETMCNTRLDVRn(0):
+ etm_write(val, ETMCNTRLDVR0);
+ break;
+ case ETMCNTRLDVRn(1):
+ etm_write(val, ETMCNTRLDVR1);
+ break;
+ case ETMCNTRLDVRn(2):
+ etm_write(val, ETMCNTRLDVR2);
+ break;
+ case ETMCNTRLDVRn(3):
+ etm_write(val, ETMCNTRLDVR3);
+ break;
+ case ETMCNTENRn(0):
+ etm_write(val, ETMCNTENR0);
+ break;
+ case ETMCNTENRn(1):
+ etm_write(val, ETMCNTENR1);
+ break;
+ case ETMCNTENRn(2):
+ etm_write(val, ETMCNTENR2);
+ break;
+ case ETMCNTENRn(3):
+ etm_write(val, ETMCNTENR3);
+ break;
+ case ETMCNTRLDEVRn(0):
+ etm_write(val, ETMCNTRLDEVR0);
+ break;
+ case ETMCNTRLDEVRn(1):
+ etm_write(val, ETMCNTRLDEVR1);
+ break;
+ case ETMCNTRLDEVRn(2):
+ etm_write(val, ETMCNTRLDEVR2);
+ break;
+ case ETMCNTRLDEVRn(3):
+ etm_write(val, ETMCNTRLDEVR3);
+ break;
+ case ETMCNTVRn(0):
+ etm_write(val, ETMCNTVR0);
+ break;
+ case ETMCNTVRn(1):
+ etm_write(val, ETMCNTVR1);
+ break;
+ case ETMCNTVRn(2):
+ etm_write(val, ETMCNTVR2);
+ break;
+ case ETMCNTVRn(3):
+ etm_write(val, ETMCNTVR3);
+ break;
+ case ETMSQ12EVR:
+ etm_write(val, ETMSQ12EVR);
+ break;
+ case ETMSQ21EVR:
+ etm_write(val, ETMSQ21EVR);
+ break;
+ case ETMSQ23EVR:
+ etm_write(val, ETMSQ23EVR);
+ break;
+ case ETMSQ31EVR:
+ etm_write(val, ETMSQ31EVR);
+ break;
+ case ETMSQ32EVR:
+ etm_write(val, ETMSQ32EVR);
+ break;
+ case ETMSQ13EVR:
+ etm_write(val, ETMSQ13EVR);
+ break;
+ case ETMSQR:
+ etm_write(val, ETMSQR);
+ break;
+ case ETMEXTOUTEVRn(0):
+ etm_write(val, ETMEXTOUTEVR0);
+ break;
+ case ETMEXTOUTEVRn(1):
+ etm_write(val, ETMEXTOUTEVR1);
+ break;
+ case ETMEXTOUTEVRn(2):
+ etm_write(val, ETMEXTOUTEVR2);
+ break;
+ case ETMEXTOUTEVRn(3):
+ etm_write(val, ETMEXTOUTEVR3);
+ break;
+ case ETMCIDCVRn(0):
+ etm_write(val, ETMCIDCVR0);
+ break;
+ case ETMCIDCVRn(1):
+ etm_write(val, ETMCIDCVR1);
+ break;
+ case ETMCIDCVRn(2):
+ etm_write(val, ETMCIDCVR2);
+ break;
+ case ETMCIDCMR:
+ etm_write(val, ETMCIDCMR);
+ break;
+ case ETMIMPSPEC0:
+ etm_write(val, ETMIMPSPEC0);
+ break;
+ case ETMIMPSPEC1:
+ etm_write(val, ETMIMPSPEC1);
+ break;
+ case ETMIMPSPEC2:
+ etm_write(val, ETMIMPSPEC2);
+ break;
+ case ETMIMPSPEC3:
+ etm_write(val, ETMIMPSPEC3);
+ break;
+ case ETMIMPSPEC4:
+ etm_write(val, ETMIMPSPEC4);
+ break;
+ case ETMIMPSPEC5:
+ etm_write(val, ETMIMPSPEC5);
+ break;
+ case ETMIMPSPEC6:
+ etm_write(val, ETMIMPSPEC6);
+ break;
+ case ETMIMPSPEC7:
+ etm_write(val, ETMIMPSPEC7);
+ break;
+ case ETMSYNCFR:
+ etm_write(val, ETMSYNCFR);
+ break;
+ case ETMEXTINSELR:
+ etm_write(val, ETMEXTINSELR);
+ break;
+ case ETMTESSEICR:
+ etm_write(val, ETMTESSEICR);
+ break;
+ case ETMEIBCR:
+ etm_write(val, ETMEIBCR);
+ break;
+ case ETMTSEVR:
+ etm_write(val, ETMTSEVR);
+ break;
+ case ETMAUXCR:
+ etm_write(val, ETMAUXCR);
+ break;
+ case ETMTRACEIDR:
+ etm_write(val, ETMTRACEIDR);
+ break;
+ case ETMVMIDCVR:
+ etm_write(val, ETMVMIDCVR);
+ break;
+ case ETMOSLAR:
+ etm_write(val, ETMOSLAR);
+ break;
+ case ETMOSSRR:
+ etm_write(val, ETMOSSRR);
+ break;
+ case ETMPDCR:
+ etm_write(val, ETMPDCR);
+ break;
+ case ETMPDSR:
+ etm_write(val, ETMPDSR);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/drivers/coresight/coresight-etm.h b/drivers/coresight/coresight-etm.h
new file mode 100644
index 0000000..501c5fa
--- /dev/null
+++ b/drivers/coresight/coresight-etm.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_CORESIGHT_ETM_H
+#define _CORESIGHT_CORESIGHT_ETM_H
+
+#include <linux/spinlock.h>
+#include "coresight-priv.h"
+
+/*
+ * Device registers:
+ * 0x000 - 0x2FC: Trace registers
+ * 0x300 - 0x314: Management registers
+ * 0x318 - 0xEFC: Trace registers
+ *
+ * Coresight registers
+ * 0xF00 - 0xF9C: Management registers
+ * 0xFA0 - 0xFA4: Management registers in PFTv1.0
+ * Trace registers in PFTv1.1
+ * 0xFA8 - 0xFFC: Management registers
+ */
+
+/* Trace registers (0x000-0x2FC) */
+#define ETMCR 0x000
+#define ETMCCR 0x004
+#define ETMTRIGGER 0x008
+#define ETMSR 0x010
+#define ETMSCR 0x014
+#define ETMTSSCR 0x018
+#define ETMTECR2 0x01c
+#define ETMTEEVR 0x020
+#define ETMTECR1 0x024
+#define ETMFFLR 0x02c
+#define ETMACVRn(n) (0x040 + (n * 4))
+#define ETMACTRn(n) (0x080 + (n * 4))
+#define ETMCNTRLDVRn(n) (0x140 + (n * 4))
+#define ETMCNTENRn(n) (0x150 + (n * 4))
+#define ETMCNTRLDEVRn(n) (0x160 + (n * 4))
+#define ETMCNTVRn(n) (0x170 + (n * 4))
+#define ETMSQ12EVR 0x180
+#define ETMSQ21EVR 0x184
+#define ETMSQ23EVR 0x188
+#define ETMSQ31EVR 0x18c
+#define ETMSQ32EVR 0x190
+#define ETMSQ13EVR 0x194
+#define ETMSQR 0x19c
+#define ETMEXTOUTEVRn(n) (0x1a0 + (n * 4))
+#define ETMCIDCVRn(n) (0x1b0 + (n * 4))
+#define ETMCIDCMR 0x1bc
+#define ETMIMPSPEC0 0x1c0
+#define ETMIMPSPEC1 0x1c4
+#define ETMIMPSPEC2 0x1c8
+#define ETMIMPSPEC3 0x1cc
+#define ETMIMPSPEC4 0x1d0
+#define ETMIMPSPEC5 0x1d4
+#define ETMIMPSPEC6 0x1d8
+#define ETMIMPSPEC7 0x1dc
+#define ETMSYNCFR 0x1e0
+#define ETMIDR 0x1e4
+#define ETMCCER 0x1e8
+#define ETMEXTINSELR 0x1ec
+#define ETMTESSEICR 0x1f0
+#define ETMEIBCR 0x1f4
+#define ETMTSEVR 0x1f8
+#define ETMAUXCR 0x1fc
+#define ETMTRACEIDR 0x200
+#define ETMVMIDCVR 0x240
+/* Management registers (0x300-0x314) */
+#define ETMOSLAR 0x300
+#define ETMOSLSR 0x304
+#define ETMOSSRR 0x308
+#define ETMPDCR 0x310
+#define ETMPDSR 0x314
+#define ETM_MAX_ADDR_CMP 16
+#define ETM_MAX_CNTR 4
+#define ETM_MAX_CTXID_CMP 3
+
+/* Register definition */
+/* ETMCR - 0x00 */
+#define ETMCR_PWD_DWN BIT(0)
+#define ETMCR_STALL_MODE BIT(7)
+#define ETMCR_ETM_PRG BIT(10)
+#define ETMCR_ETM_EN BIT(11)
+#define ETMCR_CYC_ACC BIT(12)
+#define ETMCR_CTXID_SIZE (BIT(14)|BIT(15))
+#define ETMCR_TIMESTAMP_EN BIT(28)
+/* ETMCCR - 0x04 */
+#define ETMCCR_FIFOFULL BIT(23)
+/* ETMPDCR - 0x310 */
+#define ETMPDCR_PWD_UP BIT(3)
+/* ETMTECR1 - 0x024 */
+#define ETMTECR1_ADDR_COMP_1 BIT(0)
+#define ETMTECR1_INC_EXC BIT(24)
+#define ETMTECR1_START_STOP BIT(25)
+/* ETMCCER - 0x1E8 */
+#define ETMCCER_TIMESTAMP BIT(22)
+
+#define ETM_MODE_EXCLUDE BIT(0)
+#define ETM_MODE_CYCACC BIT(1)
+#define ETM_MODE_STALL BIT(2)
+#define ETM_MODE_TIMESTAMP BIT(3)
+#define ETM_MODE_CTXID BIT(4)
+#define ETM_MODE_ALL 0x1f
+
+#define ETM_SQR_MASK 0x3
+#define ETM_TRACEID_MASK 0x3f
+#define ETM_EVENT_MASK 0x1ffff
+#define ETM_SYNC_MASK 0xfff
+#define ETM_ALL_MASK 0xffffffff
+
+#define ETMSR_PROG_BIT 1
+#define ETM_SEQ_STATE_MAX_VAL (0x2)
+#define PORT_SIZE_MASK (GENMASK(21, 21) | GENMASK(6, 4))
+
+#define ETM_HARD_WIRE_RES_A /* Hard wired, always true */ \
+ ((0x0f << 0) | \
+ /* Resource index A */ \
+ (0x06 << 4))
+
+#define ETM_ADD_COMP_0 /* Single addr comparator 1 */ \
+ ((0x00 << 7) | \
+ /* Resource index B */ \
+ (0x00 << 11))
+
+#define ETM_EVENT_NOT_A BIT(14) /* NOT(A) */
+
+#define ETM_DEFAULT_EVENT_VAL (ETM_HARD_WIRE_RES_A | \
+ ETM_ADD_COMP_0 | \
+ ETM_EVENT_NOT_A)
+/**
+ * struct etm_drvdata - specifics associated to an ETM component
+ * @base: memory mapped base address for this component.
+ * @dev: the device entity associated to this component.
+ * @csdev: component vitals needed by the framework.
+ * @clk: the clock this component is associated to.
+ * @spinlock: only one at a time pls.
+ * @cpu: the cpu this component is affined to.
+ * @port_size: port size as reported by ETMCR bit 4-6 and 21.
+ * @arch: ETM/PTM version number.
+ * @use_cpu14: true if management registers need to be accessed via CP14.
+ * @enable: is this ETM/PTM currently tracing.
+ * @sticky_enable: true if ETM base configuration has been done.
+ * @boot_enable:true if we should start tracing at boot time.
+ * @os_unlock: true if access to management registers is allowed.
+ * @nr_addr_cmp:Number of pairs of address comparators as found in ETMCCR.
+ * @nr_cntr: Number of counters as found in ETMCCR bit 13-15.
+ * @nr_ext_inp: Number of external input as found in ETMCCR bit 17-19.
+ * @nr_ext_out: Number of external output as found in ETMCCR bit 20-22.
+ * @nr_ctxid_cmp: Number of contextID comparators as found in ETMCCR bit 24-25.
+ * @etmccr: value of register ETMCCR.
+ * @etmccer: value of register ETMCCER.
+ * @traceid: value of the current ID for this component.
+ * @mode: controls various modes supported by this ETM/PTM.
+ * @ctrl: used in conjunction with @mode.
+ * @trigger_event: setting for register ETMTRIGGER.
+ * @startstop_ctrl: setting for register ETMTSSCR.
+ * @enable_event: setting for register ETMTEEVR.
+ * @enable_ctrl1: setting for register ETMTECR1.
+ * @fifofull_level: setting for register ETMFFLR.
+ * @addr_idx: index for the address comparator selection.
+ * @addr_val: value for address comparator register.
+ * @addr_acctype: access type for address comparator register.
+ * @addr_type: current status of the comparator register.
+ * @cntr_idx: index for the counter register selection.
+ * @cntr_rld_val: reload value of a counter register.
+ * @cntr_event: control for counter enable register.
+ * @cntr_rld_event: value for counter reload event register.
+ * @cntr_val: counter value register.
+ * @seq_12_event: event causing the transition from 1 to 2.
+ * @seq_21_event: event causing the transition from 2 to 1.
+ * @seq_23_event: event causing the transition from 2 to 3.
+ * @seq_31_event: event causing the transition from 3 to 1.
+ * @seq_32_event: event causing the transition from 3 to 2.
+ * @seq_13_event: event causing the transition from 1 to 3.
+ * @seq_curr_state: current value of the sequencer register.
+ * @ctxid_idx: index for the context ID registers.
+ * @ctxid_val: value for the context ID to trigger on.
+ * @ctxid_mask: mask applicable to all the context IDs.
+ * @sync_freq: Synchronisation frequency.
+ * @timestamp_event: Defines an event that requests the insertion
+ of a timestamp into the trace stream.
+ */
+struct etm_drvdata {
+ void __iomem *base;
+ struct device *dev;
+ struct coresight_device *csdev;
+ struct clk *clk;
+ spinlock_t spinlock;
+ int cpu;
+ int port_size;
+ u8 arch;
+ bool use_cp14;
+ bool enable;
+ bool sticky_enable;
+ bool boot_enable;
+ bool os_unlock;
+ u8 nr_addr_cmp;
+ u8 nr_cntr;
+ u8 nr_ext_inp;
+ u8 nr_ext_out;
+ u8 nr_ctxid_cmp;
+ u32 etmccr;
+ u32 etmccer;
+ u32 traceid;
+ u32 mode;
+ u32 ctrl;
+ u32 trigger_event;
+ u32 startstop_ctrl;
+ u32 enable_event;
+ u32 enable_ctrl1;
+ u32 fifofull_level;
+ u8 addr_idx;
+ u32 addr_val[ETM_MAX_ADDR_CMP];
+ u32 addr_acctype[ETM_MAX_ADDR_CMP];
+ u32 addr_type[ETM_MAX_ADDR_CMP];
+ u8 cntr_idx;
+ u32 cntr_rld_val[ETM_MAX_CNTR];
+ u32 cntr_event[ETM_MAX_CNTR];
+ u32 cntr_rld_event[ETM_MAX_CNTR];
+ u32 cntr_val[ETM_MAX_CNTR];
+ u32 seq_12_event;
+ u32 seq_21_event;
+ u32 seq_23_event;
+ u32 seq_31_event;
+ u32 seq_32_event;
+ u32 seq_13_event;
+ u32 seq_curr_state;
+ u8 ctxid_idx;
+ u32 ctxid_val[ETM_MAX_CTXID_CMP];
+ u32 ctxid_mask;
+ u32 sync_freq;
+ u32 timestamp_event;
+};
+
+enum etm_addr_type {
+ ETM_ADDR_TYPE_NONE,
+ ETM_ADDR_TYPE_SINGLE,
+ ETM_ADDR_TYPE_RANGE,
+ ETM_ADDR_TYPE_START,
+ ETM_ADDR_TYPE_STOP,
+};
+#endif
diff --git a/drivers/coresight/coresight-etm3x.c b/drivers/coresight/coresight-etm3x.c
new file mode 100644
index 0000000..c965f57
--- /dev/null
+++ b/drivers/coresight/coresight-etm3x.c
@@ -0,0 +1,1932 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/stat.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <asm/sections.h>
+
+#include "coresight-etm.h"
+
+static int boot_enable;
+module_param_named(boot_enable, boot_enable, int, S_IRUGO);
+
+/* The number of ETM/PTM currently registered */
+static int etm_count;
+static struct etm_drvdata *etmdrvdata[NR_CPUS];
+
+static inline void etm_writel(struct etm_drvdata *drvdata,
+ u32 val, u32 off)
+{
+ if (drvdata->use_cp14) {
+ if (etm_writel_cp14(off, val)) {
+ dev_err(drvdata->dev,
+ "invalid CP14 access to ETM reg: %#x", off);
+ }
+ } else {
+ writel_relaxed(val, drvdata->base + off);
+ }
+}
+
+static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off)
+{
+ u32 val;
+
+ if (drvdata->use_cp14) {
+ if (etm_readl_cp14(off, &val)) {
+ dev_err(drvdata->dev,
+ "invalid CP14 access to ETM reg: %#x", off);
+ }
+ } else {
+ val = readl_relaxed(drvdata->base + off);
+ }
+
+ return val;
+}
+
+/*
+ * Memory mapped writes to clear os lock are not supported on some processors
+ * and OS lock must be unlocked before any memory mapped access on such
+ * processors, otherwise memory mapped reads/writes will be invalid.
+ */
+static void etm_os_unlock(void *info)
+{
+ struct etm_drvdata *drvdata = (struct etm_drvdata *)info;
+ /* Writing any value to ETMOSLAR unlocks the trace registers */
+ etm_writel(drvdata, 0x0, ETMOSLAR);
+ isb();
+}
+
+static void etm_set_pwrdwn(struct etm_drvdata *drvdata)
+{
+ u32 etmcr;
+
+ /* Ensure pending cp14 accesses complete before setting pwrdwn */
+ mb();
+ isb();
+ etmcr = etm_readl(drvdata, ETMCR);
+ etmcr |= ETMCR_PWD_DWN;
+ etm_writel(drvdata, etmcr, ETMCR);
+}
+
+static void etm_clr_pwrdwn(struct etm_drvdata *drvdata)
+{
+ u32 etmcr;
+
+ etmcr = etm_readl(drvdata, ETMCR);
+ etmcr &= ~ETMCR_PWD_DWN;
+ etm_writel(drvdata, etmcr, ETMCR);
+ /* Ensure pwrup completes before subsequent cp14 accesses */
+ mb();
+ isb();
+}
+
+static void etm_set_pwrup(struct etm_drvdata *drvdata)
+{
+ u32 etmpdcr;
+
+ etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+ etmpdcr |= ETMPDCR_PWD_UP;
+ writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+ /* Ensure pwrup completes before subsequent cp14 accesses */
+ mb();
+ isb();
+}
+
+static void etm_clr_pwrup(struct etm_drvdata *drvdata)
+{
+ u32 etmpdcr;
+
+ /* Ensure pending cp14 accesses complete before clearing pwrup */
+ mb();
+ isb();
+ etmpdcr = readl_relaxed(drvdata->base + ETMPDCR);
+ etmpdcr &= ~ETMPDCR_PWD_UP;
+ writel_relaxed(etmpdcr, drvdata->base + ETMPDCR);
+}
+
+/**
+ * coresight_timeout_etm - loop until a bit has changed to a specific state.
+ * @drvdata: etm's private data structure.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Basically the same as @coresight_timeout except for the register access
+ * method where we have to account for CP14 configurations.
+
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+static int coresight_timeout_etm(struct etm_drvdata *drvdata, u32 offset,
+ int position, int value)
+{
+ int i;
+ u32 val;
+
+ for (i = TIMEOUT_US; i > 0; i--) {
+ val = etm_readl(drvdata, offset);
+ /* Waiting on the bit to go from 0 to 1 */
+ if (value) {
+ if (val & BIT(position))
+ return 0;
+ /* Waiting on the bit to go from 1 to 0 */
+ } else {
+ if (!(val & BIT(position)))
+ return 0;
+ }
+
+ /*
+ * Delay is arbitrary - the specification doesn't say how long
+ * we are expected to wait. Extra check required to make sure
+ * we don't wait needlessly on the last iteration.
+ */
+ if (i - 1)
+ udelay(1);
+ }
+
+ return -EAGAIN;
+}
+
+
+static void etm_set_prog(struct etm_drvdata *drvdata)
+{
+ u32 etmcr;
+
+ etmcr = etm_readl(drvdata, ETMCR);
+ etmcr |= ETMCR_ETM_PRG;
+ etm_writel(drvdata, etmcr, ETMCR);
+ /*
+ * Recommended by spec for cp14 accesses to ensure etmcr write is
+ * complete before polling etmsr
+ */
+ isb();
+ if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n", ETMSR);
+ }
+}
+
+static void etm_clr_prog(struct etm_drvdata *drvdata)
+{
+ u32 etmcr;
+
+ etmcr = etm_readl(drvdata, ETMCR);
+ etmcr &= ~ETMCR_ETM_PRG;
+ etm_writel(drvdata, etmcr, ETMCR);
+ /*
+ * Recommended by spec for cp14 accesses to ensure etmcr write is
+ * complete before polling etmsr
+ */
+ isb();
+ if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n", ETMSR);
+ }
+}
+
+static void etm_set_default(struct etm_drvdata *drvdata)
+{
+ int i;
+
+ drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->enable_event = ETM_HARD_WIRE_RES_A;
+
+ drvdata->seq_12_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->seq_21_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->seq_23_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->seq_31_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->seq_32_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->seq_13_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->timestamp_event = ETM_DEFAULT_EVENT_VAL;
+
+ for (i = 0; i < drvdata->nr_cntr; i++) {
+ drvdata->cntr_rld_val[i] = 0x0;
+ drvdata->cntr_event[i] = ETM_DEFAULT_EVENT_VAL;
+ drvdata->cntr_rld_event[i] = ETM_DEFAULT_EVENT_VAL;
+ drvdata->cntr_val[i] = 0x0;
+ }
+
+ drvdata->seq_curr_state = 0x0;
+ drvdata->ctxid_idx = 0x0;
+ for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+ drvdata->ctxid_val[i] = 0x0;
+ drvdata->ctxid_mask = 0x0;
+}
+
+static void etm_enable_hw(void *info)
+{
+ int i;
+ u32 etmcr;
+ struct etm_drvdata *drvdata = info;
+
+ CS_UNLOCK(drvdata->base);
+
+ /* Turn engine on */
+ etm_clr_pwrdwn(drvdata);
+ /* Apply power to trace registers */
+ etm_set_pwrup(drvdata);
+ /* Make sure all registers are accessible */
+ etm_os_unlock(drvdata);
+
+ etm_set_prog(drvdata);
+
+ etmcr = etm_readl(drvdata, ETMCR);
+ etmcr &= (ETMCR_PWD_DWN | ETMCR_ETM_PRG);
+ etmcr |= drvdata->port_size;
+ etm_writel(drvdata, drvdata->ctrl | etmcr, ETMCR);
+ etm_writel(drvdata, drvdata->trigger_event, ETMTRIGGER);
+ etm_writel(drvdata, drvdata->startstop_ctrl, ETMTSSCR);
+ etm_writel(drvdata, drvdata->enable_event, ETMTEEVR);
+ etm_writel(drvdata, drvdata->enable_ctrl1, ETMTECR1);
+ etm_writel(drvdata, drvdata->fifofull_level, ETMFFLR);
+ for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+ etm_writel(drvdata, drvdata->addr_val[i], ETMACVRn(i));
+ etm_writel(drvdata, drvdata->addr_acctype[i], ETMACTRn(i));
+ }
+ for (i = 0; i < drvdata->nr_cntr; i++) {
+ etm_writel(drvdata, drvdata->cntr_rld_val[i], ETMCNTRLDVRn(i));
+ etm_writel(drvdata, drvdata->cntr_event[i], ETMCNTENRn(i));
+ etm_writel(drvdata, drvdata->cntr_rld_event[i],
+ ETMCNTRLDEVRn(i));
+ etm_writel(drvdata, drvdata->cntr_val[i], ETMCNTVRn(i));
+ }
+ etm_writel(drvdata, drvdata->seq_12_event, ETMSQ12EVR);
+ etm_writel(drvdata, drvdata->seq_21_event, ETMSQ21EVR);
+ etm_writel(drvdata, drvdata->seq_23_event, ETMSQ23EVR);
+ etm_writel(drvdata, drvdata->seq_31_event, ETMSQ31EVR);
+ etm_writel(drvdata, drvdata->seq_32_event, ETMSQ32EVR);
+ etm_writel(drvdata, drvdata->seq_13_event, ETMSQ13EVR);
+ etm_writel(drvdata, drvdata->seq_curr_state, ETMSQR);
+ for (i = 0; i < drvdata->nr_ext_out; i++)
+ etm_writel(drvdata, ETM_DEFAULT_EVENT_VAL, ETMEXTOUTEVRn(i));
+ for (i = 0; i < drvdata->nr_ctxid_cmp; i++)
+ etm_writel(drvdata, drvdata->ctxid_val[i], ETMCIDCVRn(i));
+ etm_writel(drvdata, drvdata->ctxid_mask, ETMCIDCMR);
+ etm_writel(drvdata, drvdata->sync_freq, ETMSYNCFR);
+ /* No external input selected */
+ etm_writel(drvdata, 0x0, ETMEXTINSELR);
+ etm_writel(drvdata, drvdata->timestamp_event, ETMTSEVR);
+ /* No auxiliary control selected */
+ etm_writel(drvdata, 0x0, ETMAUXCR);
+ etm_writel(drvdata, drvdata->traceid, ETMTRACEIDR);
+ /* No VMID comparator value selected */
+ etm_writel(drvdata, 0x0, ETMVMIDCVR);
+
+ /* Ensures trace output is enabled from this ETM */
+ etm_writel(drvdata, drvdata->ctrl | ETMCR_ETM_EN | etmcr, ETMCR);
+
+ etm_clr_prog(drvdata);
+ CS_LOCK(drvdata->base);
+
+ dev_dbg(drvdata->dev, "cpu: %d enable smp call done\n", drvdata->cpu);
+}
+
+static int etm_trace_id_simple(struct etm_drvdata *drvdata)
+{
+ if (!drvdata->enable)
+ return drvdata->traceid;
+
+ return (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+}
+
+static int etm_trace_id(struct coresight_device *csdev)
+{
+ struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ unsigned long flags;
+ int trace_id = -1;
+
+ if (!drvdata->enable)
+ return drvdata->traceid;
+
+ if (clk_prepare_enable(drvdata->clk))
+ goto out;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+
+ CS_UNLOCK(drvdata->base);
+ trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+ CS_LOCK(drvdata->base);
+
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+out:
+ return trace_id;
+}
+
+static int etm_enable(struct coresight_device *csdev)
+{
+ struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ int ret;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ goto err_clk;
+
+ spin_lock(&drvdata->spinlock);
+
+ /*
+ * Configure the ETM only if the CPU is online. If it isn't online
+ * hw configuration will take place when 'CPU_STARTING' is received
+ * in @etm_cpu_callback.
+ */
+ if (cpu_online(drvdata->cpu)) {
+ ret = smp_call_function_single(drvdata->cpu,
+ etm_enable_hw, drvdata, 1);
+ if (ret)
+ goto err;
+ }
+
+ drvdata->enable = true;
+ drvdata->sticky_enable = true;
+
+ spin_unlock(&drvdata->spinlock);
+
+ dev_info(drvdata->dev, "ETM tracing enabled\n");
+ return 0;
+err:
+ spin_unlock(&drvdata->spinlock);
+ clk_disable_unprepare(drvdata->clk);
+err_clk:
+ return ret;
+}
+
+static void etm_disable_hw(void *info)
+{
+ int i;
+ struct etm_drvdata *drvdata = info;
+
+ CS_UNLOCK(drvdata->base);
+ etm_set_prog(drvdata);
+
+ /* Program trace enable to low by using always false event */
+ etm_writel(drvdata, ETM_HARD_WIRE_RES_A | ETM_EVENT_NOT_A, ETMTEEVR);
+
+ /* Read back sequencer and counters for post trace analysis */
+ drvdata->seq_curr_state = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+
+ for (i = 0; i < drvdata->nr_cntr; i++)
+ drvdata->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i));
+
+ etm_set_pwrdwn(drvdata);
+ CS_LOCK(drvdata->base);
+
+ dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu);
+}
+
+static void etm_disable(struct coresight_device *csdev)
+{
+ struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ /*
+ * Taking hotplug lock here protects from clocks getting disabled
+ * with tracing being left on (crash scenario) if user disable occurs
+ * after cpu online mask indicates the cpu is offline but before the
+ * DYING hotplug callback is serviced by the ETM driver.
+ */
+ get_online_cpus();
+ spin_lock(&drvdata->spinlock);
+
+ /*
+ * Executing etm_disable_hw on the cpu whose ETM is being disabled
+ * ensures that register writes occur when cpu is powered.
+ */
+ smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
+ drvdata->enable = false;
+
+ spin_unlock(&drvdata->spinlock);
+ put_online_cpus();
+
+ clk_disable_unprepare(drvdata->clk);
+
+ dev_info(drvdata->dev, "ETM tracing disabled\n");
+}
+
+static const struct coresight_ops_source etm_source_ops = {
+ .trace_id = etm_trace_id,
+ .enable = etm_enable,
+ .disable = etm_disable,
+};
+
+static const struct coresight_ops etm_cs_ops = {
+ .source_ops = &etm_source_ops,
+};
+
+static ssize_t nr_addr_cmp_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->nr_addr_cmp;
+ return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_addr_cmp);
+
+static ssize_t nr_cntr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->nr_cntr;
+ return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_cntr);
+
+static ssize_t nr_ctxid_cmp_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->nr_ctxid_cmp;
+ return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(nr_ctxid_cmp);
+
+static ssize_t etmsr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ unsigned long flags, val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ CS_UNLOCK(drvdata->base);
+
+ val = etm_readl(drvdata, ETMSR);
+
+ CS_LOCK(drvdata->base);
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+static DEVICE_ATTR_RO(etmsr);
+
+static ssize_t reset_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int i, ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ if (val) {
+ spin_lock(&drvdata->spinlock);
+ drvdata->mode = ETM_MODE_EXCLUDE;
+ drvdata->ctrl = 0x0;
+ drvdata->trigger_event = ETM_DEFAULT_EVENT_VAL;
+ drvdata->startstop_ctrl = 0x0;
+ drvdata->addr_idx = 0x0;
+ for (i = 0; i < drvdata->nr_addr_cmp; i++) {
+ drvdata->addr_val[i] = 0x0;
+ drvdata->addr_acctype[i] = 0x0;
+ drvdata->addr_type[i] = ETM_ADDR_TYPE_NONE;
+ }
+ drvdata->cntr_idx = 0x0;
+
+ etm_set_default(drvdata);
+ spin_unlock(&drvdata->spinlock);
+ }
+
+ return size;
+}
+static DEVICE_ATTR_WO(reset);
+
+static ssize_t mode_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->mode;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t mode_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->mode = val & ETM_MODE_ALL;
+
+ if (drvdata->mode & ETM_MODE_EXCLUDE)
+ drvdata->enable_ctrl1 |= ETMTECR1_INC_EXC;
+ else
+ drvdata->enable_ctrl1 &= ~ETMTECR1_INC_EXC;
+
+ if (drvdata->mode & ETM_MODE_CYCACC)
+ drvdata->ctrl |= ETMCR_CYC_ACC;
+ else
+ drvdata->ctrl &= ~ETMCR_CYC_ACC;
+
+ if (drvdata->mode & ETM_MODE_STALL) {
+ if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) {
+ dev_warn(drvdata->dev, "stall mode not supported\n");
+ ret = -EINVAL;
+ goto err_unlock;
+ }
+ drvdata->ctrl |= ETMCR_STALL_MODE;
+ } else
+ drvdata->ctrl &= ~ETMCR_STALL_MODE;
+
+ if (drvdata->mode & ETM_MODE_TIMESTAMP) {
+ if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) {
+ dev_warn(drvdata->dev, "timestamp not supported\n");
+ ret = -EINVAL;
+ goto err_unlock;
+ }
+ drvdata->ctrl |= ETMCR_TIMESTAMP_EN;
+ } else
+ drvdata->ctrl &= ~ETMCR_TIMESTAMP_EN;
+
+ if (drvdata->mode & ETM_MODE_CTXID)
+ drvdata->ctrl |= ETMCR_CTXID_SIZE;
+ else
+ drvdata->ctrl &= ~ETMCR_CTXID_SIZE;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+
+err_unlock:
+ spin_unlock(&drvdata->spinlock);
+ return ret;
+}
+static DEVICE_ATTR_RW(mode);
+
+static ssize_t trigger_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->trigger_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->trigger_event = val & ETM_EVENT_MASK;
+
+ return size;
+}
+static DEVICE_ATTR_RW(trigger_event);
+
+static ssize_t enable_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->enable_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t enable_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->enable_event = val & ETM_EVENT_MASK;
+
+ return size;
+}
+static DEVICE_ATTR_RW(enable_event);
+
+static ssize_t fifofull_level_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->fifofull_level;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t fifofull_level_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->fifofull_level = val;
+
+ return size;
+}
+static DEVICE_ATTR_RW(fifofull_level);
+
+static ssize_t addr_idx_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->addr_idx;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_idx_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ if (val >= drvdata->nr_addr_cmp)
+ return -EINVAL;
+
+ /*
+ * Use spinlock to ensure index doesn't change while it gets
+ * dereferenced multiple times within a spinlock block elsewhere.
+ */
+ spin_lock(&drvdata->spinlock);
+ drvdata->addr_idx = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_idx);
+
+static ssize_t addr_single_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u8 idx;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EINVAL;
+ }
+
+ val = drvdata->addr_val[idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_single_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ u8 idx;
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EINVAL;
+ }
+
+ drvdata->addr_val[idx] = val;
+ drvdata->addr_type[idx] = ETM_ADDR_TYPE_SINGLE;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_single);
+
+static ssize_t addr_range_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u8 idx;
+ unsigned long val1, val2;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (idx % 2 != 0) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+ if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+ drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+ (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+ drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ val1 = drvdata->addr_val[idx];
+ val2 = drvdata->addr_val[idx + 1];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx %#lx\n", val1, val2);
+}
+
+static ssize_t addr_range_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ u8 idx;
+ unsigned long val1, val2;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ if (sscanf(buf, "%lx %lx", &val1, &val2) != 2)
+ return -EINVAL;
+ /* Lower address comparator cannot have a higher address value */
+ if (val1 > val2)
+ return -EINVAL;
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (idx % 2 != 0) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+ if (!((drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE &&
+ drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) ||
+ (drvdata->addr_type[idx] == ETM_ADDR_TYPE_RANGE &&
+ drvdata->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ drvdata->addr_val[idx] = val1;
+ drvdata->addr_type[idx] = ETM_ADDR_TYPE_RANGE;
+ drvdata->addr_val[idx + 1] = val2;
+ drvdata->addr_type[idx + 1] = ETM_ADDR_TYPE_RANGE;
+ drvdata->enable_ctrl1 |= (1 << (idx/2));
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_range);
+
+static ssize_t addr_start_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u8 idx;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ val = drvdata->addr_val[idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_start_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ u8 idx;
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_START)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ drvdata->addr_val[idx] = val;
+ drvdata->addr_type[idx] = ETM_ADDR_TYPE_START;
+ drvdata->startstop_ctrl |= (1 << idx);
+ drvdata->enable_ctrl1 |= BIT(25);
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_start);
+
+static ssize_t addr_stop_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ u8 idx;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ val = drvdata->addr_val[idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_stop_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ u8 idx;
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ idx = drvdata->addr_idx;
+ if (!(drvdata->addr_type[idx] == ETM_ADDR_TYPE_NONE ||
+ drvdata->addr_type[idx] == ETM_ADDR_TYPE_STOP)) {
+ spin_unlock(&drvdata->spinlock);
+ return -EPERM;
+ }
+
+ drvdata->addr_val[idx] = val;
+ drvdata->addr_type[idx] = ETM_ADDR_TYPE_STOP;
+ drvdata->startstop_ctrl |= (1 << (idx + 16));
+ drvdata->enable_ctrl1 |= ETMTECR1_START_STOP;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_stop);
+
+static ssize_t addr_acctype_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ val = drvdata->addr_acctype[drvdata->addr_idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t addr_acctype_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->addr_acctype[drvdata->addr_idx] = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(addr_acctype);
+
+static ssize_t cntr_idx_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->cntr_idx;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_idx_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ if (val >= drvdata->nr_cntr)
+ return -EINVAL;
+ /*
+ * Use spinlock to ensure index doesn't change while it gets
+ * dereferenced multiple times within a spinlock block elsewhere.
+ */
+ spin_lock(&drvdata->spinlock);
+ drvdata->cntr_idx = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(cntr_idx);
+
+static ssize_t cntr_rld_val_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ val = drvdata->cntr_rld_val[drvdata->cntr_idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_val_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->cntr_rld_val[drvdata->cntr_idx] = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_val);
+
+static ssize_t cntr_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ val = drvdata->cntr_event[drvdata->cntr_idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->cntr_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(cntr_event);
+
+static ssize_t cntr_rld_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ val = drvdata->cntr_rld_event[drvdata->cntr_idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t cntr_rld_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->cntr_rld_event[drvdata->cntr_idx] = val & ETM_EVENT_MASK;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(cntr_rld_event);
+
+static ssize_t cntr_val_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int i, ret = 0;
+ u32 val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ if (!drvdata->enable) {
+ spin_lock(&drvdata->spinlock);
+ for (i = 0; i < drvdata->nr_cntr; i++)
+ ret += sprintf(buf, "counter %d: %x\n",
+ i, drvdata->cntr_val[i]);
+ spin_unlock(&drvdata->spinlock);
+ return ret;
+ }
+
+ for (i = 0; i < drvdata->nr_cntr; i++) {
+ val = etm_readl(drvdata, ETMCNTVRn(i));
+ ret += sprintf(buf, "counter %d: %x\n", i, val);
+ }
+
+ return ret;
+}
+
+static ssize_t cntr_val_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->cntr_val[drvdata->cntr_idx] = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(cntr_val);
+
+static ssize_t seq_12_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_12_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_12_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_12_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_12_event);
+
+static ssize_t seq_21_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_21_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_21_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_21_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_21_event);
+
+static ssize_t seq_23_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_23_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_23_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_23_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_23_event);
+
+static ssize_t seq_31_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_31_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_31_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_31_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_31_event);
+
+static ssize_t seq_32_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_32_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_32_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_32_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_32_event);
+
+static ssize_t seq_13_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->seq_13_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_13_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->seq_13_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(seq_13_event);
+
+static ssize_t seq_curr_state_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ unsigned long val, flags;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ if (!drvdata->enable) {
+ val = drvdata->seq_curr_state;
+ goto out;
+ }
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+
+ CS_UNLOCK(drvdata->base);
+ val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK);
+ CS_LOCK(drvdata->base);
+
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+out:
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t seq_curr_state_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ if (val > ETM_SEQ_STATE_MAX_VAL)
+ return -EINVAL;
+
+ drvdata->seq_curr_state = val;
+
+ return size;
+}
+static DEVICE_ATTR_RW(seq_curr_state);
+
+static ssize_t ctxid_idx_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->ctxid_idx;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_idx_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ if (val >= drvdata->nr_ctxid_cmp)
+ return -EINVAL;
+
+ /*
+ * Use spinlock to ensure index doesn't change while it gets
+ * dereferenced multiple times within a spinlock block elsewhere.
+ */
+ spin_lock(&drvdata->spinlock);
+ drvdata->ctxid_idx = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(ctxid_idx);
+
+static ssize_t ctxid_val_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ spin_lock(&drvdata->spinlock);
+ val = drvdata->ctxid_val[drvdata->ctxid_idx];
+ spin_unlock(&drvdata->spinlock);
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_val_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ spin_lock(&drvdata->spinlock);
+ drvdata->ctxid_val[drvdata->ctxid_idx] = val;
+ spin_unlock(&drvdata->spinlock);
+
+ return size;
+}
+static DEVICE_ATTR_RW(ctxid_val);
+
+static ssize_t ctxid_mask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->ctxid_mask;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t ctxid_mask_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->ctxid_mask = val;
+ return size;
+}
+static DEVICE_ATTR_RW(ctxid_mask);
+
+static ssize_t sync_freq_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->sync_freq;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t sync_freq_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->sync_freq = val & ETM_SYNC_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(sync_freq);
+
+static ssize_t timestamp_event_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ val = drvdata->timestamp_event;
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t timestamp_event_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->timestamp_event = val & ETM_EVENT_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(timestamp_event);
+
+static ssize_t status_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ unsigned long flags;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+
+ CS_UNLOCK(drvdata->base);
+ ret = sprintf(buf,
+ "ETMCCR: 0x%08x\n"
+ "ETMCCER: 0x%08x\n"
+ "ETMSCR: 0x%08x\n"
+ "ETMIDR: 0x%08x\n"
+ "ETMCR: 0x%08x\n"
+ "ETMTRACEIDR: 0x%08x\n"
+ "Enable event: 0x%08x\n"
+ "Enable start/stop: 0x%08x\n"
+ "Enable control: CR1 0x%08x CR2 0x%08x\n"
+ "CPU affinity: %d\n",
+ drvdata->etmccr, drvdata->etmccer,
+ etm_readl(drvdata, ETMSCR), etm_readl(drvdata, ETMIDR),
+ etm_readl(drvdata, ETMCR), etm_trace_id_simple(drvdata),
+ etm_readl(drvdata, ETMTEEVR),
+ etm_readl(drvdata, ETMTSSCR),
+ etm_readl(drvdata, ETMTECR1),
+ etm_readl(drvdata, ETMTECR2),
+ drvdata->cpu);
+ CS_LOCK(drvdata->base);
+
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+
+ return ret;
+}
+static DEVICE_ATTR_RO(status);
+
+static ssize_t traceid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ unsigned long val, flags;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ if (!drvdata->enable) {
+ val = drvdata->traceid;
+ goto out;
+ }
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ CS_UNLOCK(drvdata->base);
+
+ val = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK);
+
+ CS_LOCK(drvdata->base);
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+out:
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t traceid_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->traceid = val & ETM_TRACEID_MASK;
+ return size;
+}
+static DEVICE_ATTR_RW(traceid);
+
+static struct attribute *coresight_etm_attrs[] = {
+ &dev_attr_nr_addr_cmp.attr,
+ &dev_attr_nr_cntr.attr,
+ &dev_attr_nr_ctxid_cmp.attr,
+ &dev_attr_etmsr.attr,
+ &dev_attr_reset.attr,
+ &dev_attr_mode.attr,
+ &dev_attr_trigger_event.attr,
+ &dev_attr_enable_event.attr,
+ &dev_attr_fifofull_level.attr,
+ &dev_attr_addr_idx.attr,
+ &dev_attr_addr_single.attr,
+ &dev_attr_addr_range.attr,
+ &dev_attr_addr_start.attr,
+ &dev_attr_addr_stop.attr,
+ &dev_attr_addr_acctype.attr,
+ &dev_attr_cntr_idx.attr,
+ &dev_attr_cntr_rld_val.attr,
+ &dev_attr_cntr_event.attr,
+ &dev_attr_cntr_rld_event.attr,
+ &dev_attr_cntr_val.attr,
+ &dev_attr_seq_12_event.attr,
+ &dev_attr_seq_21_event.attr,
+ &dev_attr_seq_23_event.attr,
+ &dev_attr_seq_31_event.attr,
+ &dev_attr_seq_32_event.attr,
+ &dev_attr_seq_13_event.attr,
+ &dev_attr_seq_curr_state.attr,
+ &dev_attr_ctxid_idx.attr,
+ &dev_attr_ctxid_val.attr,
+ &dev_attr_ctxid_mask.attr,
+ &dev_attr_sync_freq.attr,
+ &dev_attr_timestamp_event.attr,
+ &dev_attr_status.attr,
+ &dev_attr_traceid.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etm);
+
+static int etm_cpu_callback(struct notifier_block *nfb, unsigned long action,
+ void *hcpu)
+{
+ unsigned int cpu = (unsigned long)hcpu;
+
+ if (!etmdrvdata[cpu])
+ goto out;
+
+ switch (action & (~CPU_TASKS_FROZEN)) {
+ case CPU_STARTING:
+ spin_lock(&etmdrvdata[cpu]->spinlock);
+ if (!etmdrvdata[cpu]->os_unlock) {
+ etm_os_unlock(etmdrvdata[cpu]);
+ etmdrvdata[cpu]->os_unlock = true;
+ }
+
+ if (etmdrvdata[cpu]->enable)
+ etm_enable_hw(etmdrvdata[cpu]);
+ spin_unlock(&etmdrvdata[cpu]->spinlock);
+ break;
+
+ case CPU_ONLINE:
+ if (etmdrvdata[cpu]->boot_enable &&
+ !etmdrvdata[cpu]->sticky_enable)
+ coresight_enable(etmdrvdata[cpu]->csdev);
+ break;
+
+ case CPU_DYING:
+ spin_lock(&etmdrvdata[cpu]->spinlock);
+ if (etmdrvdata[cpu]->enable)
+ etm_disable_hw(etmdrvdata[cpu]);
+ spin_unlock(&etmdrvdata[cpu]->spinlock);
+ break;
+ }
+out:
+ return NOTIFY_OK;
+}
+
+static struct notifier_block etm_cpu_notifier = {
+ .notifier_call = etm_cpu_callback,
+};
+
+static bool etm_arch_supported(u8 arch)
+{
+ switch (arch) {
+ case ETM_ARCH_V3_3:
+ break;
+ case ETM_ARCH_V3_5:
+ break;
+ case PFT_ARCH_V1_0:
+ break;
+ case PFT_ARCH_V1_1:
+ break;
+ default:
+ return false;
+ }
+ return true;
+}
+
+static void etm_init_arch_data(void *info)
+{
+ u32 etmidr;
+ u32 etmccr;
+ struct etm_drvdata *drvdata = info;
+
+ CS_UNLOCK(drvdata->base);
+
+ /* First dummy read */
+ (void)etm_readl(drvdata, ETMPDSR);
+ /* Provide power to ETM: ETMPDCR[3] == 1 */
+ etm_set_pwrup(drvdata);
+ /*
+ * Clear power down bit since when this bit is set writes to
+ * certain registers might be ignored.
+ */
+ etm_clr_pwrdwn(drvdata);
+ /*
+ * Set prog bit. It will be set from reset but this is included to
+ * ensure it is set
+ */
+ etm_set_prog(drvdata);
+
+ /* Find all capabilities */
+ etmidr = etm_readl(drvdata, ETMIDR);
+ drvdata->arch = BMVAL(etmidr, 4, 11);
+ drvdata->port_size = etm_readl(drvdata, ETMCR) & PORT_SIZE_MASK;
+
+ drvdata->etmccer = etm_readl(drvdata, ETMCCER);
+ etmccr = etm_readl(drvdata, ETMCCR);
+ drvdata->etmccr = etmccr;
+ drvdata->nr_addr_cmp = BMVAL(etmccr, 0, 3) * 2;
+ drvdata->nr_cntr = BMVAL(etmccr, 13, 15);
+ drvdata->nr_ext_inp = BMVAL(etmccr, 17, 19);
+ drvdata->nr_ext_out = BMVAL(etmccr, 20, 22);
+ drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25);
+
+ etm_set_pwrdwn(drvdata);
+ etm_clr_pwrup(drvdata);
+ CS_LOCK(drvdata->base);
+}
+
+static void etm_init_default_data(struct etm_drvdata *drvdata)
+{
+ /*
+ * A trace ID of value 0 is invalid, so let's start at some
+ * random value that fits in 7 bits and will be just as good.
+ */
+ static int etm3x_traceid = 0x10;
+
+ u32 flags = (1 << 0 | /* instruction execute*/
+ 3 << 3 | /* ARM instruction */
+ 0 << 5 | /* No data value comparison */
+ 0 << 7 | /* No exact mach */
+ 0 << 8 | /* Ignore context ID */
+ 0 << 10); /* Security ignored */
+
+ /*
+ * Initial configuration only - guarantees sources handled by
+ * this driver have a unique ID at startup time but not between
+ * all other types of sources. For that we lean on the core
+ * framework.
+ */
+ drvdata->traceid = etm3x_traceid++;
+ drvdata->ctrl = (ETMCR_CYC_ACC | ETMCR_TIMESTAMP_EN);
+ drvdata->enable_ctrl1 = ETMTECR1_ADDR_COMP_1;
+ if (drvdata->nr_addr_cmp >= 2) {
+ drvdata->addr_val[0] = (u32) _stext;
+ drvdata->addr_val[1] = (u32) _etext;
+ drvdata->addr_acctype[0] = flags;
+ drvdata->addr_acctype[1] = flags;
+ drvdata->addr_type[0] = ETM_ADDR_TYPE_RANGE;
+ drvdata->addr_type[1] = ETM_ADDR_TYPE_RANGE;
+ }
+
+ etm_set_default(drvdata);
+}
+
+static int etm_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ int ret;
+ void __iomem *base;
+ struct device *dev = &adev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct etm_drvdata *drvdata;
+ struct resource *res = &adev->res;
+ struct coresight_desc *desc;
+ struct device_node *np = adev->dev.of_node;
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+
+ adev->dev.platform_data = pdata;
+ drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14");
+ }
+
+ drvdata->dev = &adev->dev;
+ dev_set_drvdata(dev, drvdata);
+
+ /* Validity for the resource is already checked by the AMBA core */
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ drvdata->base = base;
+
+ spin_lock_init(&drvdata->spinlock);
+
+ drvdata->clk = adev->pclk;
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ drvdata->cpu = pdata ? pdata->cpu : 0;
+
+ get_online_cpus();
+ etmdrvdata[drvdata->cpu] = drvdata;
+
+ if (!smp_call_function_single(drvdata->cpu, etm_os_unlock, drvdata, 1))
+ drvdata->os_unlock = true;
+
+ if (smp_call_function_single(drvdata->cpu,
+ etm_init_arch_data, drvdata, 1))
+ dev_err(dev, "ETM arch init failed\n");
+
+ if (!etm_count++)
+ register_hotcpu_notifier(&etm_cpu_notifier);
+
+ put_online_cpus();
+
+ if (etm_arch_supported(drvdata->arch) == false) {
+ ret = -EINVAL;
+ goto err_arch_supported;
+ }
+ etm_init_default_data(drvdata);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ desc->type = CORESIGHT_DEV_TYPE_SOURCE;
+ desc->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC;
+ desc->ops = &etm_cs_ops;
+ desc->pdata = pdata;
+ desc->dev = dev;
+ desc->groups = coresight_etm_groups;
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev)) {
+ ret = PTR_ERR(drvdata->csdev);
+ goto err_arch_supported;
+ }
+
+ dev_info(dev, "ETM initialized\n");
+
+ if (boot_enable) {
+ coresight_enable(drvdata->csdev);
+ drvdata->boot_enable = true;
+ }
+
+ return 0;
+
+err_arch_supported:
+ clk_disable_unprepare(drvdata->clk);
+ if (--etm_count == 0)
+ unregister_hotcpu_notifier(&etm_cpu_notifier);
+ return ret;
+}
+
+static int etm_remove(struct amba_device *adev)
+{
+ struct etm_drvdata *drvdata = amba_get_drvdata(adev);
+
+ coresight_unregister(drvdata->csdev);
+ if (--etm_count == 0)
+ unregister_hotcpu_notifier(&etm_cpu_notifier);
+
+ return 0;
+}
+
+static struct amba_id etm_ids[] = {
+ { /* ETM 3.3 */
+ .id = 0x0003b921,
+ .mask = 0x0003ffff,
+ },
+ { /* ETM 3.5 */
+ .id = 0x0003b956,
+ .mask = 0x0003ffff,
+ },
+ { /* PTM 1.0 */
+ .id = 0x0003b950,
+ .mask = 0x0003ffff,
+ },
+ { /* PTM 1.1 */
+ .id = 0x0003b95f,
+ .mask = 0x0003ffff,
+ },
+ { 0, 0},
+};
+
+static struct amba_driver etm_driver = {
+ .drv = {
+ .name = "coresight-etm3x",
+ .owner = THIS_MODULE,
+ },
+ .probe = etm_probe,
+ .remove = etm_remove,
+ .id_table = etm_ids,
+};
+
+int __init etm_init(void)
+{
+ return amba_driver_register(&etm_driver);
+}
+module_init(etm_init);
+
+void __exit etm_exit(void)
+{
+ amba_driver_unregister(&etm_driver);
+}
+module_exit(etm_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Program Flow Trace driver");
diff --git a/drivers/coresight/coresight-funnel.c b/drivers/coresight/coresight-funnel.c
new file mode 100644
index 0000000..3db36f7
--- /dev/null
+++ b/drivers/coresight/coresight-funnel.c
@@ -0,0 +1,258 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define FUNNEL_FUNCTL 0x000
+#define FUNNEL_PRICTL 0x004
+
+#define FUNNEL_HOLDTIME_MASK 0xf00
+#define FUNNEL_HOLDTIME_SHFT 0x8
+#define FUNNEL_HOLDTIME (0x7 << FUNNEL_HOLDTIME_SHFT)
+
+/**
+ * struct funnel_drvdata - specifics associated to a funnel component
+ * @base: memory mapped base address for this component.
+ * @dev: the device entity associated to this component.
+ * @csdev: component vitals needed by the framework.
+ * @clk: the clock this component is associated to.
+ * @priority: port selection order.
+ */
+struct funnel_drvdata {
+ void __iomem *base;
+ struct device *dev;
+ struct coresight_device *csdev;
+ struct clk *clk;
+ unsigned long priority;
+};
+
+static void funnel_enable_hw(struct funnel_drvdata *drvdata, int port)
+{
+ u32 functl;
+
+ CS_UNLOCK(drvdata->base);
+
+ functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+ functl &= ~FUNNEL_HOLDTIME_MASK;
+ functl |= FUNNEL_HOLDTIME;
+ functl |= (1 << port);
+ writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+ writel_relaxed(drvdata->priority, drvdata->base + FUNNEL_PRICTL);
+
+ CS_LOCK(drvdata->base);
+}
+
+static int funnel_enable(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ int ret;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ funnel_enable_hw(drvdata, inport);
+
+ dev_info(drvdata->dev, "FUNNEL inport %d enabled\n", inport);
+ return 0;
+}
+
+static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport)
+{
+ u32 functl;
+
+ CS_UNLOCK(drvdata->base);
+
+ functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+ functl &= ~(1 << inport);
+ writel_relaxed(functl, drvdata->base + FUNNEL_FUNCTL);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void funnel_disable(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ funnel_disable_hw(drvdata, inport);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ dev_info(drvdata->dev, "FUNNEL inport %d disabled\n", inport);
+}
+
+static const struct coresight_ops_link funnel_link_ops = {
+ .enable = funnel_enable,
+ .disable = funnel_disable,
+};
+
+static const struct coresight_ops funnel_cs_ops = {
+ .link_ops = &funnel_link_ops,
+};
+
+static ssize_t priority_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+ unsigned long val = drvdata->priority;
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t priority_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->priority = val;
+ return size;
+}
+static DEVICE_ATTR_RW(priority);
+
+static u32 get_funnel_ctrl_hw(struct funnel_drvdata *drvdata)
+{
+ u32 functl;
+
+ CS_UNLOCK(drvdata->base);
+ functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL);
+ CS_LOCK(drvdata->base);
+
+ return functl;
+}
+
+static ssize_t funnel_ctrl_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int ret;
+ u32 val;
+ struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ val = get_funnel_ctrl_hw(drvdata);
+ clk_disable_unprepare(drvdata->clk);
+
+ return sprintf(buf, "%#x\n", val);
+}
+static DEVICE_ATTR_RO(funnel_ctrl);
+
+static struct attribute *coresight_funnel_attrs[] = {
+ &dev_attr_funnel_ctrl.attr,
+ &dev_attr_priority.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_funnel);
+
+static int funnel_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ void __iomem *base;
+ struct device *dev = &adev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct funnel_drvdata *drvdata;
+ struct resource *res = &adev->res;
+ struct coresight_desc *desc;
+ struct device_node *np = adev->dev.of_node;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+ adev->dev.platform_data = pdata;
+ }
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->dev = &adev->dev;
+ dev_set_drvdata(dev, drvdata);
+
+ /* Validity for the resource is already checked by the AMBA core */
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ drvdata->base = base;
+
+ drvdata->clk = adev->pclk;
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ desc->type = CORESIGHT_DEV_TYPE_LINK;
+ desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG;
+ desc->ops = &funnel_cs_ops;
+ desc->pdata = pdata;
+ desc->dev = dev;
+ desc->groups = coresight_funnel_groups;
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev))
+ return PTR_ERR(drvdata->csdev);
+
+ dev_info(dev, "FUNNEL initialized\n");
+ return 0;
+}
+
+static int funnel_remove(struct amba_device *adev)
+{
+ struct funnel_drvdata *drvdata = amba_get_drvdata(adev);
+
+ coresight_unregister(drvdata->csdev);
+ return 0;
+}
+
+static struct amba_id funnel_ids[] = {
+ {
+ .id = 0x0003b908,
+ .mask = 0x0003ffff,
+ },
+ { 0, 0},
+};
+
+static struct amba_driver funnel_driver = {
+ .drv = {
+ .name = "coresight-funnel",
+ .owner = THIS_MODULE,
+ },
+ .probe = funnel_probe,
+ .remove = funnel_remove,
+ .id_table = funnel_ids,
+};
+
+module_amba_driver(funnel_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Funnel driver");
diff --git a/drivers/coresight/coresight-priv.h b/drivers/coresight/coresight-priv.h
new file mode 100644
index 0000000..62fcd98
--- /dev/null
+++ b/drivers/coresight/coresight-priv.h
@@ -0,0 +1,63 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORESIGHT_PRIV_H
+#define _CORESIGHT_PRIV_H
+
+#include <linux/bitops.h>
+#include <linux/io.h>
+#include <linux/coresight.h>
+
+/*
+ * Coresight management registers (0xf00-0xfcc)
+ * 0xfa0 - 0xfa4: Management registers in PFTv1.0
+ * Trace registers in PFTv1.1
+ */
+#define CORESIGHT_ITCTRL 0xf00
+#define CORESIGHT_CLAIMSET 0xfa0
+#define CORESIGHT_CLAIMCLR 0xfa4
+#define CORESIGHT_LAR 0xfb0
+#define CORESIGHT_LSR 0xfb4
+#define CORESIGHT_AUTHSTATUS 0xfb8
+#define CORESIGHT_DEVID 0xfc8
+#define CORESIGHT_DEVTYPE 0xfcc
+
+#define TIMEOUT_US 100
+#define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb)
+
+static inline void CS_LOCK(void __iomem *addr)
+{
+ do {
+ /* Wait for things to settle */
+ mb();
+ writel_relaxed(0x0, addr + CORESIGHT_LAR);
+ } while (0);
+}
+
+static inline void CS_UNLOCK(void __iomem *addr)
+{
+ do {
+ writel_relaxed(CORESIGHT_UNLOCK, addr + CORESIGHT_LAR);
+ /* Make sure everyone has seen this */
+ mb();
+ } while (0);
+}
+
+#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X
+extern int etm_readl_cp14(u32 off, unsigned int *val);
+extern int etm_writel_cp14(u32 off, u32 val);
+#else
+static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; }
+static inline int etm_writel_cp14(u32 off, u32 val) { return 0; }
+#endif
+
+#endif
diff --git a/drivers/coresight/coresight-replicator.c b/drivers/coresight/coresight-replicator.c
new file mode 100644
index 0000000..cdf0553
--- /dev/null
+++ b/drivers/coresight/coresight-replicator.c
@@ -0,0 +1,137 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+
+#include "coresight-priv.h"
+
+/**
+ * struct replicator_drvdata - specifics associated to a replicator component
+ * @dev: the device entity associated with this component
+ * @csdev: component vitals needed by the framework
+ */
+struct replicator_drvdata {
+ struct device *dev;
+ struct coresight_device *csdev;
+};
+
+static int replicator_enable(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ dev_info(drvdata->dev, "REPLICATOR enabled\n");
+ return 0;
+}
+
+static void replicator_disable(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ dev_info(drvdata->dev, "REPLICATOR disabled\n");
+}
+
+static const struct coresight_ops_link replicator_link_ops = {
+ .enable = replicator_enable,
+ .disable = replicator_disable,
+};
+
+static const struct coresight_ops replicator_cs_ops = {
+ .link_ops = &replicator_link_ops,
+};
+
+static int replicator_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct replicator_drvdata *drvdata;
+ struct coresight_desc *desc;
+ struct device_node *np = pdev->dev.of_node;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+ pdev->dev.platform_data = pdata;
+ }
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->dev = &pdev->dev;
+ platform_set_drvdata(pdev, drvdata);
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ desc->type = CORESIGHT_DEV_TYPE_LINK;
+ desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT;
+ desc->ops = &replicator_cs_ops;
+ desc->pdata = pdev->dev.platform_data;
+ desc->dev = &pdev->dev;
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev))
+ return PTR_ERR(drvdata->csdev);
+
+ dev_info(dev, "REPLICATOR initialized\n");
+ return 0;
+}
+
+static int replicator_remove(struct platform_device *pdev)
+{
+ struct replicator_drvdata *drvdata = platform_get_drvdata(pdev);
+
+ coresight_unregister(drvdata->csdev);
+ return 0;
+}
+
+static struct of_device_id replicator_match[] = {
+ {.compatible = "arm,coresight-replicator"},
+ {}
+};
+
+static struct platform_driver replicator_driver = {
+ .probe = replicator_probe,
+ .remove = replicator_remove,
+ .driver = {
+ .name = "coresight-replicator",
+ .of_match_table = replicator_match,
+ },
+};
+
+static int __init replicator_init(void)
+{
+ return platform_driver_register(&replicator_driver);
+}
+module_init(replicator_init);
+
+static void __exit replicator_exit(void)
+{
+ platform_driver_unregister(&replicator_driver);
+}
+module_exit(replicator_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Replicator driver");
diff --git a/drivers/coresight/coresight-tmc.c b/drivers/coresight/coresight-tmc.c
new file mode 100644
index 0000000..3ff232f
--- /dev/null
+++ b/drivers/coresight/coresight-tmc.c
@@ -0,0 +1,766 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/dma-mapping.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TMC_RSZ 0x004
+#define TMC_STS 0x00c
+#define TMC_RRD 0x010
+#define TMC_RRP 0x014
+#define TMC_RWP 0x018
+#define TMC_TRG 0x01c
+#define TMC_CTL 0x020
+#define TMC_RWD 0x024
+#define TMC_MODE 0x028
+#define TMC_LBUFLEVEL 0x02c
+#define TMC_CBUFLEVEL 0x030
+#define TMC_BUFWM 0x034
+#define TMC_RRPHI 0x038
+#define TMC_RWPHI 0x03c
+#define TMC_AXICTL 0x110
+#define TMC_DBALO 0x118
+#define TMC_DBAHI 0x11c
+#define TMC_FFSR 0x300
+#define TMC_FFCR 0x304
+#define TMC_PSCR 0x308
+#define TMC_ITMISCOP0 0xee0
+#define TMC_ITTRFLIN 0xee8
+#define TMC_ITATBDATA0 0xeec
+#define TMC_ITATBCTR2 0xef0
+#define TMC_ITATBCTR1 0xef4
+#define TMC_ITATBCTR0 0xef8
+
+/* register description */
+/* TMC_CTL - 0x020 */
+#define TMC_CTL_CAPT_EN BIT(0)
+/* TMC_STS - 0x00C */
+#define TMC_STS_TRIGGERED BIT(1)
+/* TMC_AXICTL - 0x110 */
+#define TMC_AXICTL_PROT_CTL_B0 BIT(0)
+#define TMC_AXICTL_PROT_CTL_B1 BIT(1)
+#define TMC_AXICTL_SCT_GAT_MODE BIT(7)
+#define TMC_AXICTL_WR_BURST_LEN 0xF00
+/* TMC_FFCR - 0x304 */
+#define TMC_FFCR_EN_FMT BIT(0)
+#define TMC_FFCR_EN_TI BIT(1)
+#define TMC_FFCR_FON_FLIN BIT(4)
+#define TMC_FFCR_FON_TRIG_EVT BIT(5)
+#define TMC_FFCR_FLUSHMAN BIT(6)
+#define TMC_FFCR_TRIGON_TRIGIN BIT(8)
+#define TMC_FFCR_STOP_ON_FLUSH BIT(12)
+
+#define TMC_STS_TRIGGERED_BIT 2
+#define TMC_FFCR_FLUSHMAN_BIT 6
+
+enum tmc_config_type {
+ TMC_CONFIG_TYPE_ETB,
+ TMC_CONFIG_TYPE_ETR,
+ TMC_CONFIG_TYPE_ETF,
+};
+
+enum tmc_mode {
+ TMC_MODE_CIRCULAR_BUFFER,
+ TMC_MODE_SOFTWARE_FIFO,
+ TMC_MODE_HARDWARE_FIFO,
+};
+
+enum tmc_mem_intf_width {
+ TMC_MEM_INTF_WIDTH_32BITS = 0x2,
+ TMC_MEM_INTF_WIDTH_64BITS = 0x3,
+ TMC_MEM_INTF_WIDTH_128BITS = 0x4,
+ TMC_MEM_INTF_WIDTH_256BITS = 0x5,
+};
+
+/**
+ * struct tmc_drvdata - specifics associated to an TMC component
+ * @base: memory mapped base address for this component.
+ * @dev: the device entity associated to this component.
+ * @csdev: component vitals needed by the framework.
+ * @miscdev: specifics to handle "/dev/xyz.tmc" entry.
+ * @clk: the clock this component is associated to.
+ * @spinlock: only one at a time pls.
+ * @read_count: manages preparation of buffer for reading.
+ * @buf: area of memory where trace data get sent.
+ * @paddr: DMA start location in RAM.
+ * @vaddr: virtual representation of @paddr.
+ * @size: @buf size.
+ * @enable: this TMC is being used.
+ * @config_type: TMC variant, must be of type @tmc_config_type.
+ * @trigger_cntr: amount of words to store after a trigger.
+ */
+struct tmc_drvdata {
+ void __iomem *base;
+ struct device *dev;
+ struct coresight_device *csdev;
+ struct miscdevice miscdev;
+ struct clk *clk;
+ spinlock_t spinlock;
+ int read_count;
+ bool reading;
+ char *buf;
+ dma_addr_t paddr;
+ void __iomem *vaddr;
+ u32 size;
+ bool enable;
+ enum tmc_config_type config_type;
+ u32 trigger_cntr;
+};
+
+static void tmc_wait_for_ready(struct tmc_drvdata *drvdata)
+{
+ /* Ensure formatter, unformatter and hardware fifo are empty */
+ if (coresight_timeout(drvdata->base,
+ TMC_STS, TMC_STS_TRIGGERED_BIT, 1)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n",
+ TMC_STS);
+ }
+}
+
+static void tmc_flush_and_stop(struct tmc_drvdata *drvdata)
+{
+ u32 ffcr;
+
+ ffcr = readl_relaxed(drvdata->base + TMC_FFCR);
+ ffcr |= TMC_FFCR_STOP_ON_FLUSH;
+ writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+ ffcr |= TMC_FFCR_FLUSHMAN;
+ writel_relaxed(ffcr, drvdata->base + TMC_FFCR);
+ /* Ensure flush completes */
+ if (coresight_timeout(drvdata->base,
+ TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) {
+ dev_err(drvdata->dev,
+ "timeout observed when probing at offset %#x\n",
+ TMC_FFCR);
+ }
+
+ tmc_wait_for_ready(drvdata);
+}
+
+static void tmc_enable_hw(struct tmc_drvdata *drvdata)
+{
+ writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL);
+}
+
+static void tmc_disable_hw(struct tmc_drvdata *drvdata)
+{
+ writel_relaxed(0x0, drvdata->base + TMC_CTL);
+}
+
+static void tmc_etb_enable_hw(struct tmc_drvdata *drvdata)
+{
+ /* Zero out the memory to help with debug */
+ memset(drvdata->buf, 0, drvdata->size);
+
+ CS_UNLOCK(drvdata->base);
+
+ writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+ writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+ TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+ TMC_FFCR_TRIGON_TRIGIN,
+ drvdata->base + TMC_FFCR);
+
+ writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+ tmc_enable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_enable_hw(struct tmc_drvdata *drvdata)
+{
+ u32 axictl;
+
+ /* Zero out the memory to help with debug */
+ memset(drvdata->vaddr, 0, drvdata->size);
+
+ CS_UNLOCK(drvdata->base);
+
+ writel_relaxed(drvdata->size / 4, drvdata->base + TMC_RSZ);
+ writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE);
+
+ axictl = readl_relaxed(drvdata->base + TMC_AXICTL);
+ axictl |= TMC_AXICTL_WR_BURST_LEN;
+ writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+ axictl &= ~TMC_AXICTL_SCT_GAT_MODE;
+ writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+ axictl = (axictl &
+ ~(TMC_AXICTL_PROT_CTL_B0 | TMC_AXICTL_PROT_CTL_B1)) |
+ TMC_AXICTL_PROT_CTL_B1;
+ writel_relaxed(axictl, drvdata->base + TMC_AXICTL);
+
+ writel_relaxed(drvdata->paddr, drvdata->base + TMC_DBALO);
+ writel_relaxed(0x0, drvdata->base + TMC_DBAHI);
+ writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI |
+ TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT |
+ TMC_FFCR_TRIGON_TRIGIN,
+ drvdata->base + TMC_FFCR);
+ writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG);
+ tmc_enable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_enable_hw(struct tmc_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE);
+ writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI,
+ drvdata->base + TMC_FFCR);
+ writel_relaxed(0x0, drvdata->base + TMC_BUFWM);
+ tmc_enable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static int tmc_enable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+ int ret;
+ unsigned long flags;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ if (drvdata->reading) {
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ clk_disable_unprepare(drvdata->clk);
+ return -EBUSY;
+ }
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+ tmc_etb_enable_hw(drvdata);
+ } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ tmc_etr_enable_hw(drvdata);
+ } else {
+ if (mode == TMC_MODE_CIRCULAR_BUFFER)
+ tmc_etb_enable_hw(drvdata);
+ else
+ tmc_etf_enable_hw(drvdata);
+ }
+ drvdata->enable = true;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ dev_info(drvdata->dev, "TMC enabled\n");
+ return 0;
+}
+
+static int tmc_enable_sink(struct coresight_device *csdev)
+{
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ return tmc_enable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static int tmc_enable_link(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ return tmc_enable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata)
+{
+ enum tmc_mem_intf_width memwidth;
+ u8 memwords;
+ char *bufp;
+ u32 read_data;
+ int i;
+
+ memwidth = BMVAL(readl_relaxed(drvdata->base + CORESIGHT_DEVID), 8, 10);
+ if (memwidth == TMC_MEM_INTF_WIDTH_32BITS)
+ memwords = 1;
+ else if (memwidth == TMC_MEM_INTF_WIDTH_64BITS)
+ memwords = 2;
+ else if (memwidth == TMC_MEM_INTF_WIDTH_128BITS)
+ memwords = 4;
+ else
+ memwords = 8;
+
+ bufp = drvdata->buf;
+ while (1) {
+ for (i = 0; i < memwords; i++) {
+ read_data = readl_relaxed(drvdata->base + TMC_RRD);
+ if (read_data == 0xFFFFFFFF)
+ return;
+ memcpy(bufp, &read_data, 4);
+ bufp += 4;
+ }
+ }
+}
+
+static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ tmc_flush_and_stop(drvdata);
+ tmc_etb_dump_hw(drvdata);
+ tmc_disable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tmc_etr_dump_hw(struct tmc_drvdata *drvdata)
+{
+ u32 rwp, val;
+
+ rwp = readl_relaxed(drvdata->base + TMC_RWP);
+ val = readl_relaxed(drvdata->base + TMC_STS);
+
+ /* How much memory do we still have */
+ if (val & BIT(0))
+ drvdata->buf = drvdata->vaddr + rwp - drvdata->paddr;
+ else
+ drvdata->buf = drvdata->vaddr;
+}
+
+static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ tmc_flush_and_stop(drvdata);
+ tmc_etr_dump_hw(drvdata);
+ tmc_disable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ tmc_flush_and_stop(drvdata);
+ tmc_disable_hw(drvdata);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tmc_disable(struct tmc_drvdata *drvdata, enum tmc_mode mode)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ if (drvdata->reading)
+ goto out;
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+ tmc_etb_disable_hw(drvdata);
+ } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ tmc_etr_disable_hw(drvdata);
+ } else {
+ if (mode == TMC_MODE_CIRCULAR_BUFFER)
+ tmc_etb_disable_hw(drvdata);
+ else
+ tmc_etf_disable_hw(drvdata);
+ }
+out:
+ drvdata->enable = false;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ dev_info(drvdata->dev, "TMC disabled\n");
+}
+
+static void tmc_disable_sink(struct coresight_device *csdev)
+{
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ tmc_disable(drvdata, TMC_MODE_CIRCULAR_BUFFER);
+}
+
+static void tmc_disable_link(struct coresight_device *csdev, int inport,
+ int outport)
+{
+ struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ tmc_disable(drvdata, TMC_MODE_HARDWARE_FIFO);
+}
+
+static const struct coresight_ops_sink tmc_sink_ops = {
+ .enable = tmc_enable_sink,
+ .disable = tmc_disable_sink,
+};
+
+static const struct coresight_ops_link tmc_link_ops = {
+ .enable = tmc_enable_link,
+ .disable = tmc_disable_link,
+};
+
+static const struct coresight_ops tmc_etb_cs_ops = {
+ .sink_ops = &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etr_cs_ops = {
+ .sink_ops = &tmc_sink_ops,
+};
+
+static const struct coresight_ops tmc_etf_cs_ops = {
+ .sink_ops = &tmc_sink_ops,
+ .link_ops = &tmc_link_ops,
+};
+
+static int tmc_read_prepare(struct tmc_drvdata *drvdata)
+{
+ int ret;
+ unsigned long flags;
+ enum tmc_mode mode;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ if (!drvdata->enable)
+ goto out;
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+ tmc_etb_disable_hw(drvdata);
+ } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ tmc_etr_disable_hw(drvdata);
+ } else {
+ mode = readl_relaxed(drvdata->base + TMC_MODE);
+ if (mode == TMC_MODE_CIRCULAR_BUFFER) {
+ tmc_etb_disable_hw(drvdata);
+ } else {
+ ret = -ENODEV;
+ goto err;
+ }
+ }
+out:
+ drvdata->reading = true;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ dev_info(drvdata->dev, "TMC read start\n");
+ return 0;
+err:
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+ return ret;
+}
+
+static void tmc_read_unprepare(struct tmc_drvdata *drvdata)
+{
+ unsigned long flags;
+ enum tmc_mode mode;
+
+ spin_lock_irqsave(&drvdata->spinlock, flags);
+ if (!drvdata->enable)
+ goto out;
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+ tmc_etb_enable_hw(drvdata);
+ } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ tmc_etr_enable_hw(drvdata);
+ } else {
+ mode = readl_relaxed(drvdata->base + TMC_MODE);
+ if (mode == TMC_MODE_CIRCULAR_BUFFER)
+ tmc_etb_enable_hw(drvdata);
+ }
+out:
+ drvdata->reading = false;
+ spin_unlock_irqrestore(&drvdata->spinlock, flags);
+
+ dev_info(drvdata->dev, "TMC read end\n");
+}
+
+static int tmc_open(struct inode *inode, struct file *file)
+{
+ struct tmc_drvdata *drvdata = container_of(file->private_data,
+ struct tmc_drvdata, miscdev);
+ int ret = 0;
+
+ if (drvdata->read_count++)
+ goto out;
+
+ ret = tmc_read_prepare(drvdata);
+ if (ret)
+ return ret;
+out:
+ nonseekable_open(inode, file);
+
+ dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__);
+ return 0;
+}
+
+static ssize_t tmc_read(struct file *file, char __user *data, size_t len,
+ loff_t *ppos)
+{
+ struct tmc_drvdata *drvdata = container_of(file->private_data,
+ struct tmc_drvdata, miscdev);
+ char *bufp = drvdata->buf + *ppos;
+
+ if (*ppos + len > drvdata->size)
+ len = drvdata->size - *ppos;
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ if (bufp == (char *)(drvdata->vaddr + drvdata->size))
+ bufp = drvdata->vaddr;
+ else if (bufp > (char *)(drvdata->vaddr + drvdata->size))
+ bufp -= drvdata->size;
+ if ((bufp + len) > (char *)(drvdata->vaddr + drvdata->size))
+ len = (char *)(drvdata->vaddr + drvdata->size) - bufp;
+ }
+
+ if (copy_to_user(data, bufp, len)) {
+ dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__);
+ return -EFAULT;
+ }
+
+ *ppos += len;
+
+ dev_dbg(drvdata->dev, "%s: %d bytes copied, %d bytes left\n",
+ __func__, len, (int) (drvdata->size - *ppos));
+ return len;
+}
+
+static int tmc_release(struct inode *inode, struct file *file)
+{
+ struct tmc_drvdata *drvdata = container_of(file->private_data,
+ struct tmc_drvdata, miscdev);
+
+ if (--drvdata->read_count) {
+ if (drvdata->read_count < 0) {
+ dev_err(drvdata->dev, "mismatched close\n");
+ drvdata->read_count = 0;
+ }
+ goto out;
+ }
+
+ tmc_read_unprepare(drvdata);
+out:
+ dev_dbg(drvdata->dev, "%s: released\n", __func__);
+ return 0;
+}
+
+static const struct file_operations tmc_fops = {
+ .owner = THIS_MODULE,
+ .open = tmc_open,
+ .read = tmc_read,
+ .release = tmc_release,
+ .llseek = no_llseek,
+};
+
+static ssize_t trigger_cntr_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+ unsigned long val = drvdata->trigger_cntr;
+
+ return sprintf(buf, "%#lx\n", val);
+}
+
+static ssize_t trigger_cntr_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent);
+
+ ret = kstrtoul(buf, 16, &val);
+ if (ret)
+ return ret;
+
+ drvdata->trigger_cntr = val;
+ return size;
+}
+static DEVICE_ATTR_RW(trigger_cntr);
+
+static struct attribute *coresight_etb_attrs[] = {
+ &dev_attr_trigger_cntr.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etb);
+
+static struct attribute *coresight_etr_attrs[] = {
+ &dev_attr_trigger_cntr.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etr);
+
+static struct attribute *coresight_etf_attrs[] = {
+ &dev_attr_trigger_cntr.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_etf);
+
+static int tmc_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ int ret = 0;
+ u32 devid;
+ void __iomem *base;
+ struct device *dev = &adev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct tmc_drvdata *drvdata;
+ struct resource *res = &adev->res;
+ struct coresight_desc *desc;
+ struct device_node *np = adev->dev.of_node;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+ adev->dev.platform_data = pdata;
+ }
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->dev = &adev->dev;
+ dev_set_drvdata(dev, drvdata);
+
+ /* Validity for the resource is already checked by the AMBA core */
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ drvdata->base = base;
+
+ spin_lock_init(&drvdata->spinlock);
+
+ drvdata->clk = adev->pclk;
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID);
+ drvdata->config_type = BMVAL(devid, 6, 7);
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ if (np)
+ ret = of_property_read_u32(np,
+ "arm,buffer-size",
+ &drvdata->size);
+ if (ret)
+ drvdata->size = SZ_1M;
+ } else {
+ drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4;
+ }
+
+ clk_disable_unprepare(drvdata->clk);
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ drvdata->vaddr = dma_alloc_coherent(dev, drvdata->size,
+ &drvdata->paddr, GFP_KERNEL);
+ if (!drvdata->vaddr)
+ return -ENOMEM;
+
+ memset(drvdata->vaddr, 0, drvdata->size);
+ drvdata->buf = drvdata->vaddr;
+ } else {
+ drvdata->buf = devm_kzalloc(dev, drvdata->size, GFP_KERNEL);
+ if (!drvdata->buf)
+ return -ENOMEM;
+ }
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc) {
+ ret = -ENOMEM;
+ goto err_devm_kzalloc;
+ }
+
+ desc->pdata = pdata;
+ desc->dev = dev;
+ desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER;
+
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETB) {
+ desc->type = CORESIGHT_DEV_TYPE_SINK;
+ desc->ops = &tmc_etb_cs_ops;
+ desc->groups = coresight_etb_groups;
+ } else if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) {
+ desc->type = CORESIGHT_DEV_TYPE_SINK;
+ desc->ops = &tmc_etr_cs_ops;
+ desc->groups = coresight_etr_groups;
+ } else {
+ desc->type = CORESIGHT_DEV_TYPE_LINKSINK;
+ desc->subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO;
+ desc->ops = &tmc_etf_cs_ops;
+ desc->groups = coresight_etf_groups;
+ }
+
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev)) {
+ ret = PTR_ERR(drvdata->csdev);
+ goto err_devm_kzalloc;
+ }
+
+ drvdata->miscdev.name = pdata->name;
+ drvdata->miscdev.minor = MISC_DYNAMIC_MINOR;
+ drvdata->miscdev.fops = &tmc_fops;
+ ret = misc_register(&drvdata->miscdev);
+ if (ret)
+ goto err_misc_register;
+
+ dev_info(dev, "TMC initialized\n");
+ return 0;
+
+err_misc_register:
+ coresight_unregister(drvdata->csdev);
+err_devm_kzalloc:
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+ dma_free_coherent(dev, drvdata->size,
+ &drvdata->paddr, GFP_KERNEL);
+ return ret;
+}
+
+static int tmc_remove(struct amba_device *adev)
+{
+ struct tmc_drvdata *drvdata = amba_get_drvdata(adev);
+
+ misc_deregister(&drvdata->miscdev);
+ coresight_unregister(drvdata->csdev);
+ if (drvdata->config_type == TMC_CONFIG_TYPE_ETR)
+ dma_free_coherent(drvdata->dev, drvdata->size,
+ &drvdata->paddr, GFP_KERNEL);
+
+ return 0;
+}
+
+static struct amba_id tmc_ids[] = {
+ {
+ .id = 0x0003b961,
+ .mask = 0x0003ffff,
+ },
+ { 0, 0},
+};
+
+static struct amba_driver tmc_driver = {
+ .drv = {
+ .name = "coresight-tmc",
+ .owner = THIS_MODULE,
+ },
+ .probe = tmc_probe,
+ .remove = tmc_remove,
+ .id_table = tmc_ids,
+};
+
+module_amba_driver(tmc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Memory Controller driver");
diff --git a/drivers/coresight/coresight-tpiu.c b/drivers/coresight/coresight-tpiu.c
new file mode 100644
index 0000000..3b33af2
--- /dev/null
+++ b/drivers/coresight/coresight-tpiu.c
@@ -0,0 +1,207 @@
+/* Copyright (c) 2011-2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/amba/bus.h>
+
+#include "coresight-priv.h"
+
+#define TPIU_SUPP_PORTSZ 0x000
+#define TPIU_CURR_PORTSZ 0x004
+#define TPIU_SUPP_TRIGMODES 0x100
+#define TPIU_TRIG_CNTRVAL 0x104
+#define TPIU_TRIG_MULT 0x108
+#define TPIU_SUPP_TESTPATM 0x200
+#define TPIU_CURR_TESTPATM 0x204
+#define TPIU_TEST_PATREPCNTR 0x208
+#define TPIU_FFSR 0x300
+#define TPIU_FFCR 0x304
+#define TPIU_FSYNC_CNTR 0x308
+#define TPIU_EXTCTL_INPORT 0x400
+#define TPIU_EXTCTL_OUTPORT 0x404
+#define TPIU_ITTRFLINACK 0xee4
+#define TPIU_ITTRFLIN 0xee8
+#define TPIU_ITATBDATA0 0xeec
+#define TPIU_ITATBCTR2 0xef0
+#define TPIU_ITATBCTR1 0xef4
+#define TPIU_ITATBCTR0 0xef8
+
+/** register definition **/
+/* FFCR - 0x304 */
+#define FFCR_FON_MAN BIT(6)
+
+/**
+ * @base: memory mapped base address for this component.
+ * @dev: the device entity associated to this component.
+ * @csdev: component vitals needed by the framework.
+ * @clk: the clock this component is associated to.
+ */
+struct tpiu_drvdata {
+ void __iomem *base;
+ struct device *dev;
+ struct coresight_device *csdev;
+ struct clk *clk;
+};
+
+static void tpiu_enable_hw(struct tpiu_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ /* TODO: fill this up */
+
+ CS_LOCK(drvdata->base);
+}
+
+static int tpiu_enable(struct coresight_device *csdev)
+{
+ struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+ int ret;
+
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ tpiu_enable_hw(drvdata);
+
+ dev_info(drvdata->dev, "TPIU enabled\n");
+ return 0;
+}
+
+static void tpiu_disable_hw(struct tpiu_drvdata *drvdata)
+{
+ CS_UNLOCK(drvdata->base);
+
+ /* Clear formatter controle reg. */
+ writel_relaxed(0x0, drvdata->base + TPIU_FFCR);
+ /* Generate manual flush */
+ writel_relaxed(FFCR_FON_MAN, drvdata->base + TPIU_FFCR);
+
+ CS_LOCK(drvdata->base);
+}
+
+static void tpiu_disable(struct coresight_device *csdev)
+{
+ struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);
+
+ tpiu_disable_hw(drvdata);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ dev_info(drvdata->dev, "TPIU disabled\n");
+}
+
+static const struct coresight_ops_sink tpiu_sink_ops = {
+ .enable = tpiu_enable,
+ .disable = tpiu_disable,
+};
+
+static const struct coresight_ops tpiu_cs_ops = {
+ .sink_ops = &tpiu_sink_ops,
+};
+
+static int tpiu_probe(struct amba_device *adev, const struct amba_id *id)
+{
+ int ret;
+ void __iomem *base;
+ struct device *dev = &adev->dev;
+ struct coresight_platform_data *pdata = NULL;
+ struct tpiu_drvdata *drvdata;
+ struct resource *res = &adev->res;
+ struct coresight_desc *desc;
+ struct device_node *np = adev->dev.of_node;
+
+ if (np) {
+ pdata = of_get_coresight_platform_data(dev, np);
+ if (IS_ERR(pdata))
+ return PTR_ERR(pdata);
+ adev->dev.platform_data = pdata;
+ }
+
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->dev = &adev->dev;
+ dev_set_drvdata(dev, drvdata);
+
+ /* Validity for the resource is already checked by the AMBA core */
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ drvdata->base = base;
+
+ drvdata->clk = adev->pclk;
+ ret = clk_prepare_enable(drvdata->clk);
+ if (ret)
+ return ret;
+
+ /* Disable tpiu to support older devices */
+ tpiu_disable_hw(drvdata);
+
+ clk_disable_unprepare(drvdata->clk);
+
+ desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return -ENOMEM;
+
+ desc->type = CORESIGHT_DEV_TYPE_SINK;
+ desc->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT;
+ desc->ops = &tpiu_cs_ops;
+ desc->pdata = pdata;
+ desc->dev = dev;
+ drvdata->csdev = coresight_register(desc);
+ if (IS_ERR(drvdata->csdev))
+ return PTR_ERR(drvdata->csdev);
+
+ dev_info(dev, "TPIU initialized\n");
+ return 0;
+}
+
+static int tpiu_remove(struct amba_device *adev)
+{
+ struct tpiu_drvdata *drvdata = amba_get_drvdata(adev);
+
+ coresight_unregister(drvdata->csdev);
+ return 0;
+}
+
+static struct amba_id tpiu_ids[] = {
+ {
+ .id = 0x0003b912,
+ .mask = 0x0003ffff,
+ },
+ { 0, 0},
+};
+
+static struct amba_driver tpiu_driver = {
+ .drv = {
+ .name = "coresight-tpiu",
+ .owner = THIS_MODULE,
+ },
+ .probe = tpiu_probe,
+ .remove = tpiu_remove,
+ .id_table = tpiu_ids,
+};
+
+module_amba_driver(tpiu_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("CoreSight Trace Port Interface Unit driver");
diff --git a/drivers/coresight/coresight.c b/drivers/coresight/coresight.c
new file mode 100644
index 0000000..c5def93
--- /dev/null
+++ b/drivers/coresight/coresight.c
@@ -0,0 +1,718 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/coresight.h>
+#include <linux/of_platform.h>
+#include <linux/delay.h>
+
+#include "coresight-priv.h"
+
+static DEFINE_MUTEX(coresight_mutex);
+
+static int coresight_id_match(struct device *dev, void *data)
+{
+ int trace_id, i_trace_id;
+ struct coresight_device *csdev, *i_csdev;
+
+ csdev = data;
+ i_csdev = to_coresight_device(dev);
+
+ /*
+ * No need to care about oneself and components that are not
+ * sources or not enabled
+ */
+ if (i_csdev == csdev || !i_csdev->enable ||
+ i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE)
+ return 0;
+
+ /* Get the source ID for both compoment */
+ trace_id = source_ops(csdev)->trace_id(csdev);
+ i_trace_id = source_ops(i_csdev)->trace_id(i_csdev);
+
+ /* All you need is one */
+ if (trace_id == i_trace_id)
+ return 1;
+
+ return 0;
+}
+
+static int coresight_source_is_unique(struct coresight_device *csdev)
+{
+ int trace_id = source_ops(csdev)->trace_id(csdev);
+
+ /* this shouldn't happen */
+ if (trace_id < 0)
+ return 0;
+
+ return !bus_for_each_dev(&coresight_bustype, NULL,
+ csdev, coresight_id_match);
+}
+
+static int coresight_find_link_inport(struct coresight_device *csdev)
+{
+ int i;
+ struct coresight_device *parent;
+ struct coresight_connection *conn;
+
+ parent = container_of(csdev->path_link.next,
+ struct coresight_device, path_link);
+
+ for (i = 0; i < parent->nr_outport; i++) {
+ conn = &parent->conns[i];
+ if (conn->child_dev == csdev)
+ return conn->child_port;
+ }
+
+ dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n",
+ dev_name(&parent->dev), dev_name(&csdev->dev));
+
+ return 0;
+}
+
+static int coresight_find_link_outport(struct coresight_device *csdev)
+{
+ int i;
+ struct coresight_device *child;
+ struct coresight_connection *conn;
+
+ child = container_of(csdev->path_link.prev,
+ struct coresight_device, path_link);
+
+ for (i = 0; i < csdev->nr_outport; i++) {
+ conn = &csdev->conns[i];
+ if (conn->child_dev == child)
+ return conn->outport;
+ }
+
+ dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n",
+ dev_name(&csdev->dev), dev_name(&child->dev));
+
+ return 0;
+}
+
+static int coresight_enable_sink(struct coresight_device *csdev)
+{
+ int ret;
+
+ if (!csdev->enable) {
+ if (sink_ops(csdev)->enable) {
+ ret = sink_ops(csdev)->enable(csdev);
+ if (ret)
+ return ret;
+ }
+ csdev->enable = true;
+ }
+
+ atomic_inc(csdev->refcnt);
+
+ return 0;
+}
+
+static void coresight_disable_sink(struct coresight_device *csdev)
+{
+ if (atomic_dec_return(csdev->refcnt) == 0) {
+ if (sink_ops(csdev)->disable) {
+ sink_ops(csdev)->disable(csdev);
+ csdev->enable = false;
+ }
+ }
+}
+
+static int coresight_enable_link(struct coresight_device *csdev)
+{
+ int ret;
+ int link_subtype;
+ int refport, inport, outport;
+
+ inport = coresight_find_link_inport(csdev);
+ outport = coresight_find_link_outport(csdev);
+ link_subtype = csdev->subtype.link_subtype;
+
+ if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+ refport = inport;
+ else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+ refport = outport;
+ else
+ refport = 0;
+
+ if (atomic_inc_return(&csdev->refcnt[refport]) == 1) {
+ if (link_ops(csdev)->enable) {
+ ret = link_ops(csdev)->enable(csdev, inport, outport);
+ if (ret)
+ return ret;
+ }
+ }
+
+ csdev->enable = true;
+
+ return 0;
+}
+
+static void coresight_disable_link(struct coresight_device *csdev)
+{
+ int i, nr_conns;
+ int link_subtype;
+ int refport, inport, outport;
+
+ inport = coresight_find_link_inport(csdev);
+ outport = coresight_find_link_outport(csdev);
+ link_subtype = csdev->subtype.link_subtype;
+
+ if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) {
+ refport = inport;
+ nr_conns = csdev->nr_inport;
+ } else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) {
+ refport = outport;
+ nr_conns = csdev->nr_outport;
+ } else {
+ refport = 0;
+ nr_conns = 1;
+ }
+
+ if (atomic_dec_return(&csdev->refcnt[refport]) == 0) {
+ if (link_ops(csdev)->disable)
+ link_ops(csdev)->disable(csdev, inport, outport);
+ }
+
+ for (i = 0; i < nr_conns; i++)
+ if (atomic_read(&csdev->refcnt[i]) != 0)
+ return;
+
+ csdev->enable = false;
+}
+
+static int coresight_enable_source(struct coresight_device *csdev)
+{
+ int ret;
+
+ if (!coresight_source_is_unique(csdev)) {
+ dev_warn(&csdev->dev, "traceID %d not unique\n",
+ source_ops(csdev)->trace_id(csdev));
+ return -EINVAL;
+ }
+
+ if (!csdev->enable) {
+ if (source_ops(csdev)->enable) {
+ ret = source_ops(csdev)->enable(csdev);
+ if (ret)
+ return ret;
+ }
+ csdev->enable = true;
+ }
+
+ atomic_inc(csdev->refcnt);
+
+ return 0;
+}
+
+static void coresight_disable_source(struct coresight_device *csdev)
+{
+ if (atomic_dec_return(csdev->refcnt) == 0) {
+ if (source_ops(csdev)->disable) {
+ source_ops(csdev)->disable(csdev);
+ csdev->enable = false;
+ }
+ }
+}
+
+static int coresight_enable_path(struct list_head *path)
+{
+ int ret = 0;
+ struct coresight_device *cd;
+
+ list_for_each_entry(cd, path, path_link) {
+ if (cd == list_first_entry(path, struct coresight_device,
+ path_link)) {
+ ret = coresight_enable_sink(cd);
+ } else if (list_is_last(&cd->path_link, path)) {
+ /*
+ * Don't enable the source just yet - this needs to
+ * happen at the very end when all links and sink
+ * along the path have been configured properly.
+ */
+ ;
+ } else {
+ ret = coresight_enable_link(cd);
+ }
+ if (ret)
+ goto err;
+ }
+
+ return 0;
+err:
+ list_for_each_entry_continue_reverse(cd, path, path_link) {
+ if (cd == list_first_entry(path, struct coresight_device,
+ path_link)) {
+ coresight_disable_sink(cd);
+ } else if (list_is_last(&cd->path_link, path)) {
+ ;
+ } else {
+ coresight_disable_link(cd);
+ }
+ }
+
+ return ret;
+}
+
+static int coresight_disable_path(struct list_head *path)
+{
+ struct coresight_device *cd;
+
+ list_for_each_entry_reverse(cd, path, path_link) {
+ if (cd == list_first_entry(path, struct coresight_device,
+ path_link)) {
+ coresight_disable_sink(cd);
+ } else if (list_is_last(&cd->path_link, path)) {
+ /*
+ * The source has already been stopped, no need
+ * to do it again here.
+ */
+ ;
+ } else {
+ coresight_disable_link(cd);
+ }
+ }
+
+ return 0;
+}
+
+static int coresight_build_paths(struct coresight_device *csdev,
+ struct list_head *path,
+ bool enable)
+{
+ int i, ret = -EINVAL;
+ struct coresight_connection *conn;
+
+ list_add(&csdev->path_link, path);
+
+ if (csdev->type == CORESIGHT_DEV_TYPE_SINK && csdev->activated) {
+ if (enable)
+ ret = coresight_enable_path(path);
+ else
+ ret = coresight_disable_path(path);
+ } else {
+ for (i = 0; i < csdev->nr_outport; i++) {
+ conn = &csdev->conns[i];
+ if (coresight_build_paths(conn->child_dev,
+ path, enable) == 0)
+ ret = 0;
+ }
+ }
+
+ if (list_first_entry(path, struct coresight_device, path_link) != csdev)
+ dev_err(&csdev->dev, "wrong device in %s\n", __func__);
+
+ list_del(&csdev->path_link);
+
+ return ret;
+}
+
+int coresight_enable(struct coresight_device *csdev)
+{
+ int ret = 0;
+ LIST_HEAD(path);
+
+ mutex_lock(&coresight_mutex);
+ if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+ ret = -EINVAL;
+ dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+ goto out;
+ }
+ if (csdev->enable)
+ goto out;
+
+ if (coresight_build_paths(csdev, &path, true)) {
+ dev_err(&csdev->dev, "building path(s) failed\n");
+ goto out;
+ }
+
+ if (coresight_enable_source(csdev))
+ dev_err(&csdev->dev, "source enable failed\n");
+out:
+ mutex_unlock(&coresight_mutex);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(coresight_enable);
+
+void coresight_disable(struct coresight_device *csdev)
+{
+ LIST_HEAD(path);
+
+ mutex_lock(&coresight_mutex);
+ if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE) {
+ dev_err(&csdev->dev, "wrong device type in %s\n", __func__);
+ goto out;
+ }
+ if (!csdev->enable)
+ goto out;
+
+ coresight_disable_source(csdev);
+ if (coresight_build_paths(csdev, &path, false))
+ dev_err(&csdev->dev, "releasing path(s) failed\n");
+
+out:
+ mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_disable);
+
+static ssize_t enable_sink_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->activated);
+}
+
+static ssize_t enable_sink_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret;
+ unsigned long val;
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ ret = kstrtoul(buf, 10, &val);
+ if (ret)
+ return ret;
+
+ if (val)
+ csdev->activated = true;
+ else
+ csdev->activated = false;
+
+ return size;
+
+}
+static DEVICE_ATTR_RW(enable_sink);
+
+static ssize_t enable_source_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ return scnprintf(buf, PAGE_SIZE, "%u\n", (unsigned)csdev->enable);
+}
+
+static ssize_t enable_source_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int ret = 0;
+ unsigned long val;
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ ret = kstrtoul(buf, 10, &val);
+ if (ret)
+ return ret;
+
+ if (val) {
+ ret = coresight_enable(csdev);
+ if (ret)
+ return ret;
+ } else {
+ coresight_disable(csdev);
+ }
+
+ return size;
+}
+static DEVICE_ATTR_RW(enable_source);
+
+static struct attribute *coresight_sink_attrs[] = {
+ &dev_attr_enable_sink.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_sink);
+
+static struct attribute *coresight_source_attrs[] = {
+ &dev_attr_enable_source.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(coresight_source);
+
+static struct device_type coresight_dev_type[] = {
+ {
+ .name = "none",
+ },
+ {
+ .name = "sink",
+ .groups = coresight_sink_groups,
+ },
+ {
+ .name = "link",
+ },
+ {
+ .name = "linksink",
+ .groups = coresight_sink_groups,
+ },
+ {
+ .name = "source",
+ .groups = coresight_source_groups,
+ },
+};
+
+static void coresight_device_release(struct device *dev)
+{
+ struct coresight_device *csdev = to_coresight_device(dev);
+
+ kfree(csdev);
+}
+
+static int coresight_orphan_match(struct device *dev, void *data)
+{
+ int i;
+ bool still_orphan = false;
+ struct coresight_device *csdev, *i_csdev;
+ struct coresight_connection *conn;
+
+ csdev = data;
+ i_csdev = to_coresight_device(dev);
+
+ /* No need to check oneself */
+ if (csdev == i_csdev)
+ return 0;
+
+ /* Move on to another component if no connection is orphan */
+ if (!i_csdev->orphan)
+ return 0;
+ /*
+ * Circle throuch all the connection of that component. If we find
+ * an orphan connection whose name matches @csdev, link it.
+ */
+ for (i = 0; i < i_csdev->nr_outport; i++) {
+ conn = &i_csdev->conns[i];
+
+ /* We have found at least one orphan connection */
+ if (conn->child_dev == NULL) {
+ /* Does it match this newly added device? */
+ if (!strcmp(dev_name(&csdev->dev), conn->child_name)) {
+ conn->child_dev = csdev;
+ } else {
+ /* This component still has an orphan */
+ still_orphan = true;
+ }
+ }
+ }
+
+ i_csdev->orphan = still_orphan;
+
+ /*
+ * Returning '0' ensures that all known component on the
+ * bus will be checked.
+ */
+ return 0;
+}
+
+static void coresight_fixup_orphan_conns(struct coresight_device *csdev)
+{
+ /*
+ * No need to check for a return value as orphan connection(s)
+ * are hooked-up with each newly added component.
+ */
+ bus_for_each_dev(&coresight_bustype, NULL,
+ csdev, coresight_orphan_match);
+}
+
+
+static int coresight_name_match(struct device *dev, void *data)
+{
+ char *to_match;
+ struct coresight_device *i_csdev;
+
+ to_match = data;
+ i_csdev = to_coresight_device(dev);
+
+ if (!strcmp(to_match, dev_name(&i_csdev->dev)))
+ return 1;
+
+ return 0;
+}
+
+static void coresight_fixup_device_conns(struct coresight_device *csdev)
+{
+ int i;
+ struct device *dev = NULL;
+ struct coresight_connection *conn;
+
+ for (i = 0; i < csdev->nr_outport; i++) {
+ conn = &csdev->conns[i];
+ dev = bus_find_device(&coresight_bustype, NULL,
+ (void *)conn->child_name,
+ coresight_name_match);
+
+ if (dev) {
+ conn->child_dev = to_coresight_device(dev);
+ } else {
+ csdev->orphan = true;
+ conn->child_dev = NULL;
+ }
+ }
+}
+
+/**
+ * coresight_timeout - loop until a bit has changed to a specific state.
+ * @addr: base address of the area of interest.
+ * @offset: address of a register, starting from @addr.
+ * @position: the position of the bit of interest.
+ * @value: the value the bit should have.
+ *
+ * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if
+ * TIMEOUT_US has elapsed, which ever happens first.
+ */
+
+int coresight_timeout(void __iomem *addr, u32 offset, int position, int value)
+{
+ int i;
+ u32 val;
+
+ for (i = TIMEOUT_US; i > 0; i--) {
+ val = __raw_readl(addr + offset);
+ /* waiting on the bit to go from 0 to 1 */
+ if (value) {
+ if (val & BIT(position))
+ return 0;
+ /* waiting on the bit to go from 1 to 0 */
+ } else {
+ if (!(val & BIT(position)))
+ return 0;
+ }
+
+ /*
+ * Delay is arbitrary - the specification doesn't say how long
+ * we are expected to wait. Extra check required to make sure
+ * we don't wait needlessly on the last iteration.
+ */
+ if (i - 1)
+ udelay(1);
+ }
+
+ return -EAGAIN;
+}
+
+struct bus_type coresight_bustype = {
+ .name = "coresight",
+};
+
+static int __init coresight_init(void)
+{
+ return bus_register(&coresight_bustype);
+}
+postcore_initcall(coresight_init);
+
+struct coresight_device *coresight_register(struct coresight_desc *desc)
+{
+ int i;
+ int ret;
+ int link_subtype;
+ int nr_refcnts = 1;
+ atomic_t *refcnts = NULL;
+ struct coresight_device *csdev;
+ struct coresight_connection *conns;
+
+ csdev = kzalloc(sizeof(*csdev), GFP_KERNEL);
+ if (!csdev) {
+ ret = -ENOMEM;
+ goto err_kzalloc_csdev;
+ }
+
+ if (desc->type == CORESIGHT_DEV_TYPE_LINK ||
+ desc->type == CORESIGHT_DEV_TYPE_LINKSINK) {
+ link_subtype = desc->subtype.link_subtype;
+
+ if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG)
+ nr_refcnts = desc->pdata->nr_inport;
+ else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT)
+ nr_refcnts = desc->pdata->nr_outport;
+ }
+
+ refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL);
+ if (!refcnts) {
+ ret = -ENOMEM;
+ goto err_kzalloc_refcnts;
+ }
+
+ csdev->refcnt = refcnts;
+
+ csdev->nr_inport = desc->pdata->nr_inport;
+ csdev->nr_outport = desc->pdata->nr_outport;
+ conns = kcalloc(csdev->nr_outport, sizeof(*conns), GFP_KERNEL);
+ if (!conns) {
+ ret = -ENOMEM;
+ goto err_kzalloc_conns;
+ }
+
+ for (i = 0; i < csdev->nr_outport; i++) {
+ conns[i].outport = desc->pdata->outports[i];
+ conns[i].child_name = desc->pdata->child_names[i];
+ conns[i].child_port = desc->pdata->child_ports[i];
+ }
+
+ csdev->conns = conns;
+
+ csdev->type = desc->type;
+ csdev->subtype = desc->subtype;
+ csdev->ops = desc->ops;
+ csdev->orphan = false;
+
+ csdev->dev.type = &coresight_dev_type[desc->type];
+ csdev->dev.groups = desc->groups;
+ csdev->dev.parent = desc->dev;
+ csdev->dev.release = coresight_device_release;
+ csdev->dev.bus = &coresight_bustype;
+ dev_set_name(&csdev->dev, "%s", desc->pdata->name);
+
+ ret = device_register(&csdev->dev);
+ if (ret)
+ goto err_device_register;
+
+ mutex_lock(&coresight_mutex);
+
+ coresight_fixup_device_conns(csdev);
+ coresight_fixup_orphan_conns(csdev);
+
+ mutex_unlock(&coresight_mutex);
+
+ return csdev;
+
+err_device_register:
+ kfree(conns);
+err_kzalloc_conns:
+ kfree(refcnts);
+err_kzalloc_refcnts:
+ kfree(csdev);
+err_kzalloc_csdev:
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(coresight_register);
+
+void coresight_unregister(struct coresight_device *csdev)
+{
+ mutex_lock(&coresight_mutex);
+
+ kfree(csdev->conns);
+ device_unregister(&csdev->dev);
+
+ mutex_unlock(&coresight_mutex);
+}
+EXPORT_SYMBOL_GPL(coresight_unregister);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/coresight/of_coresight.c b/drivers/coresight/of_coresight.c
new file mode 100644
index 0000000..c3efa41
--- /dev/null
+++ b/drivers/coresight/of_coresight.c
@@ -0,0 +1,206 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/amba/bus.h>
+#include <linux/coresight.h>
+#include <asm/smp_plat.h>
+
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+ return dev->of_node == data;
+}
+
+static struct device *
+of_coresight_get_endpoint_device(struct device_node *endpoint)
+{
+ struct device *dev = NULL;
+
+ /*
+ * If we have a non-configuable replicator, it will be found on the
+ * platform bus.
+ */
+ dev = bus_find_device(&platform_bus_type, NULL,
+ endpoint, of_dev_node_match);
+ if (dev)
+ return dev;
+
+ /*
+ * We have a configurable component - circle through the AMBA bus
+ * looking for the device that matches the endpoint node.
+ */
+ return bus_find_device(&amba_bustype, NULL,
+ endpoint, of_dev_node_match);
+}
+
+static struct device_node *of_get_coresight_endpoint(
+ const struct device_node *parent, struct device_node *prev)
+{
+ struct device_node *node = of_graph_get_next_endpoint(parent, prev);
+
+ of_node_put(prev);
+ return node;
+}
+
+static void of_coresight_get_ports(struct device_node *node,
+ int *nr_inport, int *nr_outport)
+{
+ struct device_node *ep = NULL;
+ int in = 0, out = 0;
+
+ do {
+ ep = of_get_coresight_endpoint(node, ep);
+ if (!ep)
+ break;
+
+ if (of_property_read_bool(ep, "slave-mode"))
+ in++;
+ else
+ out++;
+
+ } while (ep);
+
+ *nr_inport = in;
+ *nr_outport = out;
+}
+
+static int of_coresight_alloc_memory(struct device *dev,
+ struct coresight_platform_data *pdata)
+{
+ /* List of output port on this component */
+ pdata->outports = devm_kzalloc(dev, pdata->nr_outport *
+ sizeof(*pdata->outports),
+ GFP_KERNEL);
+ if (!pdata->outports)
+ return -ENOMEM;
+
+ /* Children connected to this component via @outports */
+ pdata->child_names = devm_kzalloc(dev, pdata->nr_outport *
+ sizeof(*pdata->child_names),
+ GFP_KERNEL);
+ if (!pdata->child_names)
+ return -ENOMEM;
+
+ /* Port number on the child this component is connected to */
+ pdata->child_ports = devm_kzalloc(dev, pdata->nr_outport *
+ sizeof(*pdata->child_ports),
+ GFP_KERNEL);
+ if (!pdata->child_ports)
+ return -ENOMEM;
+
+ return 0;
+}
+
+struct coresight_platform_data *of_get_coresight_platform_data(
+ struct device *dev, struct device_node *node)
+{
+ int i = 0, ret = 0;
+ struct coresight_platform_data *pdata;
+ struct of_endpoint endpoint, rendpoint;
+ struct device *rdev;
+ struct device_node *dn;
+ struct device_node *ep = NULL;
+ struct device_node *rparent = NULL;
+ struct device_node *rport = NULL;
+
+ pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+ if (!pdata)
+ return ERR_PTR(-ENOMEM);
+
+ /* Use device name as sysfs handle */
+ pdata->name = dev_name(dev);
+
+ /* Get the number of input and output port for this component */
+ of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport);
+
+ if (pdata->nr_outport) {
+ ret = of_coresight_alloc_memory(dev, pdata);
+ if (ret)
+ return ERR_PTR(ret);
+
+ /* Iterate through each port to discover topology */
+ do {
+ /* Get a handle on a port */
+ ep = of_get_coresight_endpoint(node, ep);
+ if (!ep)
+ break;
+
+ /*
+ * No need to deal with input ports, processing for as
+ * processing for output ports will deal with them.
+ */
+ if (of_find_property(ep, "slave-mode", NULL))
+ continue;
+
+ /* Get a handle on the local endpoint */
+ ret = of_graph_parse_endpoint(ep, &endpoint);
+
+ if (ret)
+ continue;
+
+ /* The local out port number */
+ pdata->outports[i] = endpoint.id;
+
+ /*
+ * Get a handle on the remote port and parent
+ * attached to it.
+ */
+ rparent = of_graph_get_remote_port_parent(ep);
+ rport = of_graph_get_remote_port(ep);
+
+ if (!rparent || !rport)
+ continue;
+
+ if (of_graph_parse_endpoint(rport, &rendpoint))
+ continue;
+
+ rdev = of_coresight_get_endpoint_device(rparent);
+ if (!rdev)
+ continue;
+
+ pdata->child_names[i] = dev_name(rdev);
+ pdata->child_ports[i] = rendpoint.id;
+
+ i++;
+ } while (ep);
+ }
+
+ /* Affinity defaults to CPU0 */
+ pdata->cpu = 0;
+ dn = of_parse_phandle(node, "cpu", 0);
+ if (dn) {
+ const u32 *cell;
+ int len, index;
+ u64 hwid;
+
+ cell = of_get_property(dn, "reg", &len);
+ if (cell) {
+ hwid = of_read_number(cell, of_n_addr_cells(dn));
+ index = get_logical_index(hwid);
+ if (index != -EINVAL)
+ pdata->cpu = index;
+ }
+ }
+
+ return pdata;
+}
+EXPORT_SYMBOL_GPL(of_get_coresight_platform_data);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 534fcb8..a9c1324 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -201,7 +201,7 @@
endmenu
menu "ARM CPU frequency scaling drivers"
-depends on ARM
+depends on ARM || ARM64
source "drivers/cpufreq/Kconfig.arm"
endmenu
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 6e57543..2272779 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -4,7 +4,8 @@
config ARM_BIG_LITTLE_CPUFREQ
tristate "Generic ARM big LITTLE CPUfreq driver"
- depends on ARM_CPU_TOPOLOGY && PM_OPP && HAVE_CLK
+ depends on (ARM_CPU_TOPOLOGY && BIG_LITTLE) || (ARM64 && SMP)
+ depends on PM_OPP && HAVE_CLK
help
This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -15,6 +16,14 @@
This enables probing via DT for Generic CPUfreq driver for ARM
big.LITTLE platform. This gets frequency tables from DT.
+config ARM_VEXPRESS_BL_CPUFREQ
+ tristate "ARM Vexpress big LITTLE CPUfreq driver"
+ select ARM_BIG_LITTLE_CPUFREQ
+ depends on VEXPRESS_SPC
+ help
+ This enables the CPUfreq driver for ARM Vexpress big.LITTLE platform.
+ If in doubt, say N.
+
config ARM_EXYNOS_CPUFREQ
bool "SAMSUNG EXYNOS SoCs"
depends on ARCH_EXYNOS
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 315b923..505c62b 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -48,9 +48,10 @@
obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ) += arm_big_little.o
# big LITTLE per platform glues. Keep DT_BL_CPUFREQ as the last entry in all big
# LITTLE drivers, so that it is probed last.
+obj-$(CONFIG_ARM_VEXPRESS_BL_CPUFREQ) += vexpress_big_little.o
obj-$(CONFIG_ARM_DT_BL_CPUFREQ) += arm_big_little_dt.o
-obj-$(CONFIG_ARCH_DAVINCI_DA850) += davinci-cpufreq.o
+obj-$(CONFIG_ARCH_DAVINCI) += davinci-cpufreq.o
obj-$(CONFIG_UX500_SOC_DB8500) += dbx500-cpufreq.o
obj-$(CONFIG_ARM_EXYNOS_CPUFREQ) += exynos-cpufreq.o
obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ) += exynos4210-cpufreq.o
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 5d7f53f..eaee6e2 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -24,27 +24,148 @@
#include <linux/cpufreq.h>
#include <linux/cpumask.h>
#include <linux/export.h>
+#include <linux/mutex.h>
#include <linux/of_platform.h>
#include <linux/opp.h>
#include <linux/slab.h>
#include <linux/topology.h>
#include <linux/types.h>
+#include <asm/bL_switcher.h>
#include "arm_big_little.h"
-/* Currently we support only two clusters */
-#define MAX_CLUSTERS 2
+#ifdef CONFIG_BL_SWITCHER
+bool bL_switching_enabled;
+#endif
+
+#define ACTUAL_FREQ(cluster, freq) ((cluster == A7_CLUSTER) ? freq << 1 : freq)
+#define VIRT_FREQ(cluster, freq) ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
static struct cpufreq_arm_bL_ops *arm_bL_ops;
static struct clk *clk[MAX_CLUSTERS];
-static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS];
-static atomic_t cluster_usage[MAX_CLUSTERS] = {ATOMIC_INIT(0), ATOMIC_INIT(0)};
+static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
+static atomic_t cluster_usage[MAX_CLUSTERS + 1] = {ATOMIC_INIT(0),
+ ATOMIC_INIT(0)};
-static unsigned int bL_cpufreq_get(unsigned int cpu)
+static unsigned int clk_big_min; /* (Big) clock frequencies */
+static unsigned int clk_little_max; /* Maximum clock frequency (Little) */
+
+static DEFINE_PER_CPU(unsigned int, physical_cluster);
+static DEFINE_PER_CPU(unsigned int, cpu_last_req_freq);
+
+static struct mutex cluster_lock[MAX_CLUSTERS];
+
+static unsigned int find_cluster_maxfreq(int cluster)
{
- u32 cur_cluster = cpu_to_cluster(cpu);
+ int j;
+ u32 max_freq = 0, cpu_freq;
- return clk_get_rate(clk[cur_cluster]) / 1000;
+ for_each_online_cpu(j) {
+ cpu_freq = per_cpu(cpu_last_req_freq, j);
+
+ if ((cluster == per_cpu(physical_cluster, j)) &&
+ (max_freq < cpu_freq))
+ max_freq = cpu_freq;
+ }
+
+ pr_debug("%s: cluster: %d, max freq: %d\n", __func__, cluster,
+ max_freq);
+
+ return max_freq;
+}
+
+static unsigned int clk_get_cpu_rate(unsigned int cpu)
+{
+ u32 cur_cluster = per_cpu(physical_cluster, cpu);
+ u32 rate = clk_get_rate(clk[cur_cluster]) / 1000;
+
+ /* For switcher we use virtual A15 clock rates */
+ if (is_bL_switching_enabled())
+ rate = VIRT_FREQ(cur_cluster, rate);
+
+ pr_debug("%s: cpu: %d, cluster: %d, freq: %u\n", __func__, cpu,
+ cur_cluster, rate);
+
+ return rate;
+}
+
+static unsigned int bL_cpufreq_get_rate(unsigned int cpu)
+{
+ if (is_bL_switching_enabled()) {
+ pr_debug("%s: freq: %d\n", __func__, per_cpu(cpu_last_req_freq,
+ cpu));
+
+ return per_cpu(cpu_last_req_freq, cpu);
+ } else {
+ return clk_get_cpu_rate(cpu);
+ }
+}
+
+static unsigned int
+bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
+{
+ u32 new_rate, prev_rate;
+ int ret;
+ bool bLs = is_bL_switching_enabled();
+
+ mutex_lock(&cluster_lock[new_cluster]);
+
+ if (bLs) {
+ prev_rate = per_cpu(cpu_last_req_freq, cpu);
+ per_cpu(cpu_last_req_freq, cpu) = rate;
+ per_cpu(physical_cluster, cpu) = new_cluster;
+
+ new_rate = find_cluster_maxfreq(new_cluster);
+ new_rate = ACTUAL_FREQ(new_cluster, new_rate);
+ } else {
+ new_rate = rate;
+ }
+
+ pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d, freq: %d\n",
+ __func__, cpu, old_cluster, new_cluster, new_rate);
+
+ ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+ if (WARN_ON(ret)) {
+ pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret,
+ new_cluster);
+ if (bLs) {
+ per_cpu(cpu_last_req_freq, cpu) = prev_rate;
+ per_cpu(physical_cluster, cpu) = old_cluster;
+ }
+
+ mutex_unlock(&cluster_lock[new_cluster]);
+
+ return ret;
+ }
+
+ mutex_unlock(&cluster_lock[new_cluster]);
+
+ /* Recalc freq for old cluster when switching clusters */
+ if (old_cluster != new_cluster) {
+ pr_debug("%s: cpu: %d, old cluster: %d, new cluster: %d\n",
+ __func__, cpu, old_cluster, new_cluster);
+
+ /* Switch cluster */
+ bL_switch_request(cpu, new_cluster);
+
+ mutex_lock(&cluster_lock[old_cluster]);
+
+ /* Set freq of old cluster if there are cpus left on it */
+ new_rate = find_cluster_maxfreq(old_cluster);
+ new_rate = ACTUAL_FREQ(old_cluster, new_rate);
+
+ if (new_rate) {
+ pr_debug("%s: Updating rate of old cluster: %d, to freq: %d\n",
+ __func__, old_cluster, new_rate);
+
+ if (clk_set_rate(clk[old_cluster], new_rate * 1000))
+ pr_err("%s: clk_set_rate failed: %d, old cluster: %d\n",
+ __func__, ret, old_cluster);
+ }
+ mutex_unlock(&cluster_lock[old_cluster]);
+ }
+
+ return 0;
}
/* Validate policy frequency range */
@@ -60,12 +181,14 @@
unsigned int target_freq, unsigned int relation)
{
struct cpufreq_freqs freqs;
- u32 cpu = policy->cpu, freq_tab_idx, cur_cluster;
+ u32 cpu = policy->cpu, freq_tab_idx, cur_cluster, new_cluster,
+ actual_cluster;
int ret = 0;
- cur_cluster = cpu_to_cluster(policy->cpu);
+ cur_cluster = cpu_to_cluster(cpu);
+ new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
- freqs.old = bL_cpufreq_get(policy->cpu);
+ freqs.old = bL_cpufreq_get_rate(cpu);
/* Determine valid target frequency using freq_table */
cpufreq_frequency_table_target(policy, freq_table[cur_cluster],
@@ -79,13 +202,21 @@
if (freqs.old == freqs.new)
return 0;
+ if (is_bL_switching_enabled()) {
+ if ((actual_cluster == A15_CLUSTER) &&
+ (freqs.new < clk_big_min)) {
+ new_cluster = A7_CLUSTER;
+ } else if ((actual_cluster == A7_CLUSTER) &&
+ (freqs.new > clk_little_max)) {
+ new_cluster = A15_CLUSTER;
+ }
+ }
+
cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
- ret = clk_set_rate(clk[cur_cluster], freqs.new * 1000);
- if (ret) {
- pr_err("clk_set_rate failed: %d\n", ret);
+ ret = bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs.new);
+ if (ret)
return ret;
- }
policy->cur = freqs.new;
@@ -94,7 +225,73 @@
return ret;
}
-static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
+static inline u32 get_table_count(struct cpufreq_frequency_table *table)
+{
+ int count;
+
+ for (count = 0; table[count].frequency != CPUFREQ_TABLE_END; count++)
+ ;
+
+ return count;
+}
+
+/* get the minimum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_min(struct cpufreq_frequency_table *table)
+{
+ int i;
+ uint32_t min_freq = ~0;
+ for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+ if (table[i].frequency < min_freq)
+ min_freq = table[i].frequency;
+ return min_freq;
+}
+
+/* get the maximum frequency in the cpufreq_frequency_table */
+static inline u32 get_table_max(struct cpufreq_frequency_table *table)
+{
+ int i;
+ uint32_t max_freq = 0;
+ for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++)
+ if (table[i].frequency > max_freq)
+ max_freq = table[i].frequency;
+ return max_freq;
+}
+
+static int merge_cluster_tables(void)
+{
+ int i, j, k = 0, count = 1;
+ struct cpufreq_frequency_table *table;
+
+ for (i = 0; i < MAX_CLUSTERS; i++)
+ count += get_table_count(freq_table[i]);
+
+ table = kzalloc(sizeof(*table) * count, GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ freq_table[MAX_CLUSTERS] = table;
+
+ /* Add in reverse order to get freqs in increasing order */
+ for (i = MAX_CLUSTERS - 1; i >= 0; i--) {
+ for (j = 0; freq_table[i][j].frequency != CPUFREQ_TABLE_END;
+ j++) {
+ table[k].frequency = VIRT_FREQ(i,
+ freq_table[i][j].frequency);
+ pr_debug("%s: index: %d, freq: %d\n", __func__, k,
+ table[k].frequency);
+ k++;
+ }
+ }
+
+ table[k].index = k;
+ table[k].frequency = CPUFREQ_TABLE_END;
+
+ pr_debug("%s: End, table: %p, count: %d\n", __func__, table, k);
+
+ return 0;
+}
+
+static void _put_cluster_clk_and_freq_table(struct device *cpu_dev)
{
u32 cluster = cpu_to_cluster(cpu_dev->id);
@@ -105,10 +302,35 @@
}
}
-static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
{
u32 cluster = cpu_to_cluster(cpu_dev->id);
- char name[14] = "cpu-cluster.";
+ int i;
+
+ if (cluster < MAX_CLUSTERS)
+ return _put_cluster_clk_and_freq_table(cpu_dev);
+
+ if (atomic_dec_return(&cluster_usage[MAX_CLUSTERS]))
+ return;
+
+ for (i = 0; i < MAX_CLUSTERS; i++) {
+ struct device *cdev = get_cpu_device(i);
+ if (!cdev) {
+ pr_err("%s: failed to get cpu%d device\n", __func__, i);
+ return;
+ }
+
+ _put_cluster_clk_and_freq_table(cdev);
+ }
+
+ /* free virtual table */
+ kfree(freq_table[MAX_CLUSTERS]);
+}
+
+static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+ u32 cluster = cpu_to_cluster(cpu_dev->id);
+ char name[14] = "cpu-cluster.X";
int ret;
if (atomic_inc_return(&cluster_usage[cluster]) != 1)
@@ -149,6 +371,62 @@
return ret;
}
+static int get_cluster_clk_and_freq_table(struct device *cpu_dev)
+{
+ u32 cluster = cpu_to_cluster(cpu_dev->id);
+ int i, ret;
+
+ if (cluster < MAX_CLUSTERS)
+ return _get_cluster_clk_and_freq_table(cpu_dev);
+
+ if (atomic_inc_return(&cluster_usage[MAX_CLUSTERS]) != 1)
+ return 0;
+
+ /*
+ * Get data for all clusters and fill virtual cluster with a merge of
+ * both
+ */
+ for (i = 0; i < MAX_CLUSTERS; i++) {
+ struct device *cdev = get_cpu_device(i);
+ if (!cdev) {
+ pr_err("%s: failed to get cpu%d device\n", __func__, i);
+ return -ENODEV;
+ }
+
+ ret = _get_cluster_clk_and_freq_table(cdev);
+ if (ret)
+ goto put_clusters;
+ }
+
+ ret = merge_cluster_tables();
+ if (ret)
+ goto put_clusters;
+
+ /* Assuming 2 cluster, set clk_big_min and clk_little_max */
+ clk_big_min = get_table_min(freq_table[0]);
+ clk_little_max = VIRT_FREQ(1, get_table_max(freq_table[1]));
+
+ pr_debug("%s: cluster: %d, clk_big_min: %d, clk_little_max: %d\n",
+ __func__, cluster, clk_big_min, clk_little_max);
+
+ return 0;
+
+put_clusters:
+ while (i--) {
+ struct device *cdev = get_cpu_device(i);
+ if (!cdev) {
+ pr_err("%s: failed to get cpu%d device\n", __func__, i);
+ return -ENODEV;
+ }
+
+ _put_cluster_clk_and_freq_table(cdev);
+ }
+
+ atomic_dec(&cluster_usage[MAX_CLUSTERS]);
+
+ return ret;
+}
+
/* Per-CPU initialization */
static int bL_cpufreq_init(struct cpufreq_policy *policy)
{
@@ -177,37 +455,33 @@
cpufreq_frequency_table_get_attr(freq_table[cur_cluster], policy->cpu);
+ if (cur_cluster < MAX_CLUSTERS) {
+ int cpu;
+
+ cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+
+ for_each_cpu(cpu, policy->cpus)
+ per_cpu(physical_cluster, cpu) = cur_cluster;
+ } else {
+ /* Assumption: during init, we are always running on A15 */
+ per_cpu(physical_cluster, policy->cpu) = A15_CLUSTER;
+ }
+
if (arm_bL_ops->get_transition_latency)
policy->cpuinfo.transition_latency =
arm_bL_ops->get_transition_latency(cpu_dev);
else
policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
- policy->cur = bL_cpufreq_get(policy->cpu);
+ policy->cur = clk_get_cpu_rate(policy->cpu);
- cpumask_copy(policy->cpus, topology_core_cpumask(policy->cpu));
+ if (is_bL_switching_enabled())
+ per_cpu(cpu_last_req_freq, policy->cpu) = policy->cur;
dev_info(cpu_dev, "%s: CPU %d initialized\n", __func__, policy->cpu);
return 0;
}
-static int bL_cpufreq_exit(struct cpufreq_policy *policy)
-{
- struct device *cpu_dev;
-
- cpu_dev = get_cpu_device(policy->cpu);
- if (!cpu_dev) {
- pr_err("%s: failed to get cpu%d device\n", __func__,
- policy->cpu);
- return -ENODEV;
- }
-
- put_cluster_clk_and_freq_table(cpu_dev);
- dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
-
- return 0;
-}
-
/* Export freq_table to sysfs */
static struct freq_attr *bL_cpufreq_attr[] = {
&cpufreq_freq_attr_scaling_available_freqs,
@@ -219,16 +493,47 @@
.flags = CPUFREQ_STICKY,
.verify = bL_cpufreq_verify_policy,
.target = bL_cpufreq_set_target,
- .get = bL_cpufreq_get,
+ .get = bL_cpufreq_get_rate,
.init = bL_cpufreq_init,
- .exit = bL_cpufreq_exit,
.have_governor_per_policy = true,
.attr = bL_cpufreq_attr,
};
+static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
+ unsigned long action, void *_arg)
+{
+ pr_debug("%s: action: %ld\n", __func__, action);
+
+ switch (action) {
+ case BL_NOTIFY_PRE_ENABLE:
+ case BL_NOTIFY_PRE_DISABLE:
+ cpufreq_unregister_driver(&bL_cpufreq_driver);
+ break;
+
+ case BL_NOTIFY_POST_ENABLE:
+ set_switching_enabled(true);
+ cpufreq_register_driver(&bL_cpufreq_driver);
+ break;
+
+ case BL_NOTIFY_POST_DISABLE:
+ set_switching_enabled(false);
+ cpufreq_register_driver(&bL_cpufreq_driver);
+ break;
+
+ default:
+ return NOTIFY_DONE;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block bL_switcher_notifier = {
+ .notifier_call = bL_cpufreq_switcher_notifier,
+};
+
int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
{
- int ret;
+ int ret, i;
if (arm_bL_ops) {
pr_debug("%s: Already registered: %s, exiting\n", __func__,
@@ -243,16 +548,29 @@
arm_bL_ops = ops;
+ ret = bL_switcher_get_enabled();
+ set_switching_enabled(ret);
+
+ for (i = 0; i < MAX_CLUSTERS; i++)
+ mutex_init(&cluster_lock[i]);
+
ret = cpufreq_register_driver(&bL_cpufreq_driver);
if (ret) {
pr_info("%s: Failed registering platform driver: %s, err: %d\n",
__func__, ops->name, ret);
arm_bL_ops = NULL;
} else {
- pr_info("%s: Registered platform driver: %s\n", __func__,
- ops->name);
+ ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+ if (ret) {
+ cpufreq_unregister_driver(&bL_cpufreq_driver);
+ arm_bL_ops = NULL;
+ } else {
+ pr_info("%s: Registered platform driver: %s\n",
+ __func__, ops->name);
+ }
}
+ bL_switcher_put_enabled();
return ret;
}
EXPORT_SYMBOL_GPL(bL_cpufreq_register);
@@ -265,9 +583,31 @@
return;
}
+ bL_switcher_get_enabled();
+ bL_switcher_unregister_notifier(&bL_switcher_notifier);
cpufreq_unregister_driver(&bL_cpufreq_driver);
+ bL_switcher_put_enabled();
pr_info("%s: Un-registered platform driver: %s\n", __func__,
arm_bL_ops->name);
+
+ /* For saving table get/put on every cpu in/out */
+ if (is_bL_switching_enabled()) {
+ put_cluster_clk_and_freq_table(get_cpu_device(0));
+ } else {
+ int i;
+
+ for (i = 0; i < MAX_CLUSTERS; i++) {
+ struct device *cdev = get_cpu_device(i);
+ if (!cdev) {
+ pr_err("%s: failed to get cpu%d device\n",
+ __func__, i);
+ return;
+ }
+
+ put_cluster_clk_and_freq_table(cdev);
+ }
+ }
+
arm_bL_ops = NULL;
}
EXPORT_SYMBOL_GPL(bL_cpufreq_unregister);
diff --git a/drivers/cpufreq/arm_big_little.h b/drivers/cpufreq/arm_big_little.h
index 79b2ce1..4f5a03d 100644
--- a/drivers/cpufreq/arm_big_little.h
+++ b/drivers/cpufreq/arm_big_little.h
@@ -23,6 +23,20 @@
#include <linux/device.h>
#include <linux/types.h>
+/* Currently we support only two clusters */
+#define A15_CLUSTER 0
+#define A7_CLUSTER 1
+#define MAX_CLUSTERS 2
+
+#ifdef CONFIG_BL_SWITCHER
+extern bool bL_switching_enabled;
+#define is_bL_switching_enabled() bL_switching_enabled
+#define set_switching_enabled(x) (bL_switching_enabled = (x))
+#else
+#define is_bL_switching_enabled() false
+#define set_switching_enabled(x) do { } while (0)
+#endif
+
struct cpufreq_arm_bL_ops {
char name[CPUFREQ_NAME_LEN];
int (*get_transition_latency)(struct device *cpu_dev);
@@ -36,7 +50,8 @@
static inline int cpu_to_cluster(int cpu)
{
- return topology_physical_package_id(cpu);
+ return is_bL_switching_enabled() ? MAX_CLUSTERS:
+ topology_physical_package_id(cpu);
}
int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2d53f47..66f6cf5 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -46,6 +46,7 @@
static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
#endif
static DEFINE_RWLOCK(cpufreq_driver_lock);
+static DEFINE_MUTEX(cpufreq_governor_lock);
/*
* cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
@@ -1075,14 +1076,11 @@
__func__, cpu_dev->id, cpu);
}
- if ((cpus == 1) && (cpufreq_driver->target))
- __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
-
- pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
- cpufreq_cpu_put(data);
-
/* If cpu is last user of policy, free policy */
if (cpus == 1) {
+ if (cpufreq_driver->target)
+ __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
+
lock_policy_rwsem_read(cpu);
kobj = &data->kobj;
cmp = &data->kobj_unregister;
@@ -1103,9 +1101,13 @@
free_cpumask_var(data->related_cpus);
free_cpumask_var(data->cpus);
kfree(data);
- } else if (cpufreq_driver->target) {
- __cpufreq_governor(data, CPUFREQ_GOV_START);
- __cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+ } else {
+ pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
+ cpufreq_cpu_put(data);
+ if (cpufreq_driver->target) {
+ __cpufreq_governor(data, CPUFREQ_GOV_START);
+ __cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+ }
}
per_cpu(cpufreq_policy_cpu, cpu) = -1;
@@ -1562,6 +1564,21 @@
pr_debug("__cpufreq_governor for CPU %u, event %u\n",
policy->cpu, event);
+
+ mutex_lock(&cpufreq_governor_lock);
+ if ((!policy->governor_enabled && (event == CPUFREQ_GOV_STOP)) ||
+ (policy->governor_enabled && (event == CPUFREQ_GOV_START))) {
+ mutex_unlock(&cpufreq_governor_lock);
+ return -EBUSY;
+ }
+
+ if (event == CPUFREQ_GOV_STOP)
+ policy->governor_enabled = false;
+ else if (event == CPUFREQ_GOV_START)
+ policy->governor_enabled = true;
+
+ mutex_unlock(&cpufreq_governor_lock);
+
ret = policy->governor->governor(policy, event);
if (!ret) {
@@ -1569,6 +1586,14 @@
policy->governor->initialized++;
else if (event == CPUFREQ_GOV_POLICY_EXIT)
policy->governor->initialized--;
+ } else {
+ /* Restore original values */
+ mutex_lock(&cpufreq_governor_lock);
+ if (event == CPUFREQ_GOV_STOP)
+ policy->governor_enabled = true;
+ else if (event == CPUFREQ_GOV_START)
+ policy->governor_enabled = false;
+ mutex_unlock(&cpufreq_governor_lock);
}
/* we keep one module reference alive for
@@ -1837,13 +1862,15 @@
if (dev) {
switch (action) {
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
cpufreq_add_dev(dev, NULL);
break;
case CPU_DOWN_PREPARE:
- case CPU_UP_CANCELED_FROZEN:
+ case CPU_DOWN_PREPARE_FROZEN:
__cpufreq_remove_dev(dev, NULL);
break;
case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
cpufreq_add_dev(dev, NULL);
break;
}
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 0ceb2ef..f97cb3d 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -221,8 +221,8 @@
return count;
}
-static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
- size_t count)
+static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
+ const char *buf, size_t count)
{
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
unsigned int input, j;
@@ -235,10 +235,10 @@
if (input > 1)
input = 1;
- if (input == cs_tuners->ignore_nice) /* nothing to do */
+ if (input == cs_tuners->ignore_nice_load) /* nothing to do */
return count;
- cs_tuners->ignore_nice = input;
+ cs_tuners->ignore_nice_load = input;
/* we need to re-evaluate prev_cpu_idle */
for_each_online_cpu(j) {
@@ -246,7 +246,7 @@
dbs_info = &per_cpu(cs_cpu_dbs_info, j);
dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
&dbs_info->cdbs.prev_cpu_wall, 0);
- if (cs_tuners->ignore_nice)
+ if (cs_tuners->ignore_nice_load)
dbs_info->cdbs.prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
}
@@ -279,7 +279,7 @@
show_store_one(cs, sampling_down_factor);
show_store_one(cs, up_threshold);
show_store_one(cs, down_threshold);
-show_store_one(cs, ignore_nice);
+show_store_one(cs, ignore_nice_load);
show_store_one(cs, freq_step);
declare_show_sampling_rate_min(cs);
@@ -287,7 +287,7 @@
gov_sys_pol_attr_rw(sampling_down_factor);
gov_sys_pol_attr_rw(up_threshold);
gov_sys_pol_attr_rw(down_threshold);
-gov_sys_pol_attr_rw(ignore_nice);
+gov_sys_pol_attr_rw(ignore_nice_load);
gov_sys_pol_attr_rw(freq_step);
gov_sys_pol_attr_ro(sampling_rate_min);
@@ -297,7 +297,7 @@
&sampling_down_factor_gov_sys.attr,
&up_threshold_gov_sys.attr,
&down_threshold_gov_sys.attr,
- &ignore_nice_gov_sys.attr,
+ &ignore_nice_load_gov_sys.attr,
&freq_step_gov_sys.attr,
NULL
};
@@ -313,7 +313,7 @@
&sampling_down_factor_gov_pol.attr,
&up_threshold_gov_pol.attr,
&down_threshold_gov_pol.attr,
- &ignore_nice_gov_pol.attr,
+ &ignore_nice_load_gov_pol.attr,
&freq_step_gov_pol.attr,
NULL
};
@@ -338,7 +338,7 @@
tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
tuners->down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD;
tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
- tuners->ignore_nice = 0;
+ tuners->ignore_nice_load = 0;
tuners->freq_step = DEF_FREQUENCY_STEP;
dbs_data->tuners = tuners;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index dc9b72e..27b0e2a 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -26,7 +26,6 @@
#include <linux/tick.h>
#include <linux/types.h>
#include <linux/workqueue.h>
-#include <linux/cpu.h>
#include "cpufreq_governor.h"
@@ -92,13 +91,13 @@
unsigned int j;
if (dbs_data->cdata->governor == GOV_ONDEMAND)
- ignore_nice = od_tuners->ignore_nice;
+ ignore_nice = od_tuners->ignore_nice_load;
else
- ignore_nice = cs_tuners->ignore_nice;
+ ignore_nice = cs_tuners->ignore_nice_load;
policy = cdbs->cur_policy;
- /* Get Absolute Load (in terms of freq for ondemand gov) */
+ /* Get Absolute Load */
for_each_cpu(j, policy->cpus) {
struct cpu_dbs_common_info *j_cdbs;
u64 cur_wall_time, cur_idle_time;
@@ -149,14 +148,6 @@
load = 100 * (wall_time - idle_time) / wall_time;
- if (dbs_data->cdata->governor == GOV_ONDEMAND) {
- int freq_avg = __cpufreq_driver_getavg(policy, j);
- if (freq_avg <= 0)
- freq_avg = policy->cur;
-
- load *= freq_avg;
- }
-
if (load > max_load)
max_load = load;
}
@@ -178,13 +169,14 @@
{
int i;
+ if (!policy->governor_enabled)
+ return;
+
if (!all_cpus) {
__gov_queue_work(smp_processor_id(), dbs_data, delay);
} else {
- get_online_cpus();
for_each_cpu(i, policy->cpus)
__gov_queue_work(i, dbs_data, delay);
- put_online_cpus();
}
}
EXPORT_SYMBOL_GPL(gov_queue_work);
@@ -339,12 +331,12 @@
cs_tuners = dbs_data->tuners;
cs_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
sampling_rate = cs_tuners->sampling_rate;
- ignore_nice = cs_tuners->ignore_nice;
+ ignore_nice = cs_tuners->ignore_nice_load;
} else {
od_tuners = dbs_data->tuners;
od_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
sampling_rate = od_tuners->sampling_rate;
- ignore_nice = od_tuners->ignore_nice;
+ ignore_nice = od_tuners->ignore_nice_load;
od_ops = dbs_data->cdata->gov_ops;
io_busy = od_tuners->io_is_busy;
}
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index e16a961..4a9058a 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -165,17 +165,16 @@
/* Per policy Governers sysfs tunables */
struct od_dbs_tuners {
- unsigned int ignore_nice;
+ unsigned int ignore_nice_load;
unsigned int sampling_rate;
unsigned int sampling_down_factor;
unsigned int up_threshold;
- unsigned int adj_up_threshold;
unsigned int powersave_bias;
unsigned int io_is_busy;
};
struct cs_dbs_tuners {
- unsigned int ignore_nice;
+ unsigned int ignore_nice_load;
unsigned int sampling_rate;
unsigned int sampling_down_factor;
unsigned int up_threshold;
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 93eb5cb..25438bb 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -29,11 +29,9 @@
#include "cpufreq_governor.h"
/* On-demand governor macros */
-#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10)
#define DEF_FREQUENCY_UP_THRESHOLD (80)
#define DEF_SAMPLING_DOWN_FACTOR (1)
#define MAX_SAMPLING_DOWN_FACTOR (100000)
-#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3)
#define MICRO_FREQUENCY_UP_THRESHOLD (95)
#define MICRO_FREQUENCY_MIN_SAMPLE_RATE (10000)
#define MIN_FREQUENCY_UP_THRESHOLD (11)
@@ -161,14 +159,10 @@
/*
* Every sampling_rate, we check, if current idle time is less than 20%
- * (default), then we try to increase frequency. Every sampling_rate, we look
- * for the lowest frequency which can sustain the load while keeping idle time
- * over 30%. If such a frequency exist, we try to decrease to this frequency.
- *
- * Any frequency increase takes it to the maximum frequency. Frequency reduction
- * happens at minimum steps of 5% (default) of current frequency
+ * (default), then we try to increase frequency. Else, we adjust the frequency
+ * proportional to load.
*/
-static void od_check_cpu(int cpu, unsigned int load_freq)
+static void od_check_cpu(int cpu, unsigned int load)
{
struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
@@ -178,29 +172,17 @@
dbs_info->freq_lo = 0;
/* Check for frequency increase */
- if (load_freq > od_tuners->up_threshold * policy->cur) {
+ if (load > od_tuners->up_threshold) {
/* If switching to max speed, apply sampling_down_factor */
if (policy->cur < policy->max)
dbs_info->rate_mult =
od_tuners->sampling_down_factor;
dbs_freq_increase(policy, policy->max);
return;
- }
-
- /* Check for frequency decrease */
- /* if we cannot reduce the frequency anymore, break out early */
- if (policy->cur == policy->min)
- return;
-
- /*
- * The optimal frequency is the frequency that is the lowest that can
- * support the current CPU usage without triggering the up policy. To be
- * safe, we focus 10 points under the threshold.
- */
- if (load_freq < od_tuners->adj_up_threshold
- * policy->cur) {
+ } else {
+ /* Calculate the next frequency proportional to load */
unsigned int freq_next;
- freq_next = load_freq / od_tuners->adj_up_threshold;
+ freq_next = load * policy->cpuinfo.max_freq / 100;
/* No longer fully busy, reset rate_mult */
dbs_info->rate_mult = 1;
@@ -374,9 +356,6 @@
input < MIN_FREQUENCY_UP_THRESHOLD) {
return -EINVAL;
}
- /* Calculate the new adj_up_threshold */
- od_tuners->adj_up_threshold += input;
- od_tuners->adj_up_threshold -= od_tuners->up_threshold;
od_tuners->up_threshold = input;
return count;
@@ -403,8 +382,8 @@
return count;
}
-static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
- size_t count)
+static ssize_t store_ignore_nice_load(struct dbs_data *dbs_data,
+ const char *buf, size_t count)
{
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
unsigned int input;
@@ -419,10 +398,10 @@
if (input > 1)
input = 1;
- if (input == od_tuners->ignore_nice) { /* nothing to do */
+ if (input == od_tuners->ignore_nice_load) { /* nothing to do */
return count;
}
- od_tuners->ignore_nice = input;
+ od_tuners->ignore_nice_load = input;
/* we need to re-evaluate prev_cpu_idle */
for_each_online_cpu(j) {
@@ -430,7 +409,7 @@
dbs_info = &per_cpu(od_cpu_dbs_info, j);
dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
- if (od_tuners->ignore_nice)
+ if (od_tuners->ignore_nice_load)
dbs_info->cdbs.prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
@@ -461,7 +440,7 @@
show_store_one(od, io_is_busy);
show_store_one(od, up_threshold);
show_store_one(od, sampling_down_factor);
-show_store_one(od, ignore_nice);
+show_store_one(od, ignore_nice_load);
show_store_one(od, powersave_bias);
declare_show_sampling_rate_min(od);
@@ -469,7 +448,7 @@
gov_sys_pol_attr_rw(io_is_busy);
gov_sys_pol_attr_rw(up_threshold);
gov_sys_pol_attr_rw(sampling_down_factor);
-gov_sys_pol_attr_rw(ignore_nice);
+gov_sys_pol_attr_rw(ignore_nice_load);
gov_sys_pol_attr_rw(powersave_bias);
gov_sys_pol_attr_ro(sampling_rate_min);
@@ -478,7 +457,7 @@
&sampling_rate_gov_sys.attr,
&up_threshold_gov_sys.attr,
&sampling_down_factor_gov_sys.attr,
- &ignore_nice_gov_sys.attr,
+ &ignore_nice_load_gov_sys.attr,
&powersave_bias_gov_sys.attr,
&io_is_busy_gov_sys.attr,
NULL
@@ -494,7 +473,7 @@
&sampling_rate_gov_pol.attr,
&up_threshold_gov_pol.attr,
&sampling_down_factor_gov_pol.attr,
- &ignore_nice_gov_pol.attr,
+ &ignore_nice_load_gov_pol.attr,
&powersave_bias_gov_pol.attr,
&io_is_busy_gov_pol.attr,
NULL
@@ -525,8 +504,6 @@
if (idle_time != -1ULL) {
/* Idle micro accounting is supported. Use finer thresholds */
tuners->up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
- tuners->adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
- MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
/*
* In nohz/micro accounting case we set the minimum frequency
* not depending on HZ, but fixed (very low). The deferred
@@ -535,8 +512,6 @@
dbs_data->min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
} else {
tuners->up_threshold = DEF_FREQUENCY_UP_THRESHOLD;
- tuners->adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
- DEF_FREQUENCY_DOWN_DIFFERENTIAL;
/* For correct statistics, we need 10 ticks for each measure */
dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
@@ -544,7 +519,7 @@
}
tuners->sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR;
- tuners->ignore_nice = 0;
+ tuners->ignore_nice_load = 0;
tuners->powersave_bias = default_powersave_bias;
tuners->io_is_busy = should_io_be_busy();
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index fb65dec..9823037 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -21,6 +21,9 @@
#include <linux/spinlock.h>
#include <linux/notifier.h>
#include <asm/cputime.h>
+#ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
+#endif
static spinlock_t cpufreq_stats_lock;
@@ -81,7 +84,7 @@
for (i = 0; i < stat->state_num; i++) {
len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
(unsigned long long)
- cputime64_to_clock_t(stat->time_in_state[i]));
+ jiffies_64_to_clock_t(stat->time_in_state[i]));
}
return len;
}
@@ -349,16 +352,15 @@
switch (action) {
case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
cpufreq_update_policy(cpu);
break;
case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
cpufreq_stats_free_sysfs(cpu);
break;
case CPU_DEAD:
- cpufreq_stats_free_table(cpu);
- break;
- case CPU_UP_CANCELED_FROZEN:
- cpufreq_stats_free_sysfs(cpu);
+ case CPU_DEAD_FROZEN:
cpufreq_stats_free_table(cpu);
break;
}
@@ -379,7 +381,7 @@
.notifier_call = cpufreq_stat_notifier_trans
};
-static int __init cpufreq_stats_init(void)
+static int cpufreq_stats_setup(void)
{
int ret;
unsigned int cpu;
@@ -407,7 +409,8 @@
return 0;
}
-static void __exit cpufreq_stats_exit(void)
+
+static void cpufreq_stats_cleanup(void)
{
unsigned int cpu;
@@ -422,6 +425,54 @@
}
}
+#ifdef CONFIG_BL_SWITCHER
+static int cpufreq_stats_switcher_notifier(struct notifier_block *nfb,
+ unsigned long action, void *_arg)
+{
+ switch (action) {
+ case BL_NOTIFY_PRE_ENABLE:
+ case BL_NOTIFY_PRE_DISABLE:
+ cpufreq_stats_cleanup();
+ break;
+
+ case BL_NOTIFY_POST_ENABLE:
+ case BL_NOTIFY_POST_DISABLE:
+ cpufreq_stats_setup();
+ break;
+
+ default:
+ return NOTIFY_DONE;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block switcher_notifier = {
+ .notifier_call = cpufreq_stats_switcher_notifier,
+};
+#endif
+
+static int __init cpufreq_stats_init(void)
+{
+ int ret;
+ spin_lock_init(&cpufreq_stats_lock);
+
+ ret = cpufreq_stats_setup();
+#ifdef CONFIG_BL_SWITCHER
+ if (!ret)
+ bL_switcher_register_notifier(&switcher_notifier);
+#endif
+ return ret;
+}
+
+static void __exit cpufreq_stats_exit(void)
+{
+#ifdef CONFIG_BL_SWITCHER
+ bL_switcher_unregister_notifier(&switcher_notifier);
+#endif
+ cpufreq_stats_cleanup();
+}
+
MODULE_AUTHOR("Zou Nan hai <nanhai.zou@intel.com>");
MODULE_DESCRIPTION("'cpufreq_stats' - A driver to export cpufreq stats "
"through sysfs filesystem");
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
index b61b5a3..9216c20 100644
--- a/drivers/cpufreq/highbank-cpufreq.c
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -19,7 +19,7 @@
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/of.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
#include <linux/platform_device.h>
#define HB_CPUFREQ_CHANGE_NOTE 0x80000001
@@ -66,7 +66,8 @@
struct device_node *np;
int ret;
- if (!of_machine_is_compatible("calxeda,highbank"))
+ if ((!of_machine_is_compatible("calxeda,highbank")) &&
+ (!of_machine_is_compatible("calxeda,ecx-2000")))
return -ENODEV;
for_each_child_of_node(of_find_node_by_path("/cpus"), np)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 07f2840..decf84e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -48,7 +48,7 @@
}
struct sample {
- int core_pct_busy;
+ int32_t core_pct_busy;
u64 aperf;
u64 mperf;
int freq;
@@ -68,7 +68,7 @@
int32_t i_gain;
int32_t d_gain;
int deadband;
- int last_err;
+ int32_t last_err;
};
struct cpudata {
@@ -103,10 +103,10 @@
static struct pstate_adjust_policy default_policy = {
.sample_rate_ms = 10,
.deadband = 0,
- .setpoint = 109,
- .p_gain_pct = 17,
+ .setpoint = 97,
+ .p_gain_pct = 20,
.d_gain_pct = 0,
- .i_gain_pct = 4,
+ .i_gain_pct = 0,
};
struct perf_limits {
@@ -153,16 +153,15 @@
pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
}
-static signed int pid_calc(struct _pid *pid, int busy)
+static signed int pid_calc(struct _pid *pid, int32_t busy)
{
- signed int err, result;
+ signed int result;
int32_t pterm, dterm, fp_error;
int32_t integral_limit;
- err = pid->setpoint - busy;
- fp_error = int_tofp(err);
+ fp_error = int_tofp(pid->setpoint) - busy;
- if (abs(err) <= pid->deadband)
+ if (abs(fp_error) <= int_tofp(pid->deadband))
return 0;
pterm = mul_fp(pid->p_gain, fp_error);
@@ -176,8 +175,8 @@
if (pid->integral < -integral_limit)
pid->integral = -integral_limit;
- dterm = mul_fp(pid->d_gain, (err - pid->last_err));
- pid->last_err = err;
+ dterm = mul_fp(pid->d_gain, fp_error - pid->last_err);
+ pid->last_err = fp_error;
result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
@@ -367,12 +366,13 @@
static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
{
int max_perf = cpu->pstate.turbo_pstate;
+ int max_perf_adj;
int min_perf;
if (limits.no_turbo)
max_perf = cpu->pstate.max_pstate;
- max_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
- *max = clamp_t(int, max_perf,
+ max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
+ *max = clamp_t(int, max_perf_adj,
cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
@@ -394,7 +394,10 @@
trace_cpu_frequency(pstate * 100000, cpu->cpu);
cpu->pstate.current_pstate = pstate;
- wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
+ if (limits.no_turbo)
+ wrmsrl(MSR_IA32_PERF_CTL, BIT(32) | (pstate << 8));
+ else
+ wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
}
@@ -432,8 +435,9 @@
struct sample *sample)
{
u64 core_pct;
- core_pct = div64_u64(sample->aperf * 100, sample->mperf);
- sample->freq = cpu->pstate.max_pstate * core_pct * 1000;
+ core_pct = div64_u64(int_tofp(sample->aperf * 100),
+ sample->mperf);
+ sample->freq = fp_toint(cpu->pstate.max_pstate * core_pct * 1000);
sample->core_pct_busy = core_pct;
}
@@ -465,22 +469,19 @@
mod_timer_pinned(&cpu->timer, jiffies + delay);
}
-static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
+static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
{
- int32_t busy_scaled;
- int32_t core_busy, turbo_pstate, current_pstate;
+ int32_t core_busy, max_pstate, current_pstate;
- core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy);
- turbo_pstate = int_tofp(cpu->pstate.turbo_pstate);
+ core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy;
+ max_pstate = int_tofp(cpu->pstate.max_pstate);
current_pstate = int_tofp(cpu->pstate.current_pstate);
- busy_scaled = mul_fp(core_busy, div_fp(turbo_pstate, current_pstate));
-
- return fp_toint(busy_scaled);
+ return mul_fp(core_busy, div_fp(max_pstate, current_pstate));
}
static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
{
- int busy_scaled;
+ int32_t busy_scaled;
struct _pid *pid;
signed int ctl = 0;
int steps;
@@ -516,12 +517,18 @@
}
#define ICPU(model, policy) \
- { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
+ (unsigned long)&policy }
static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(0x2a, default_policy),
ICPU(0x2d, default_policy),
ICPU(0x3a, default_policy),
+ ICPU(0x3c, default_policy),
+ ICPU(0x3e, default_policy),
+ ICPU(0x3f, default_policy),
+ ICPU(0x45, default_policy),
+ ICPU(0x46, default_policy),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -543,6 +550,11 @@
cpu = all_cpu_data[cpunum];
intel_pstate_get_cpu_pstates(cpu);
+ if (!cpu->pstate.current_pstate) {
+ all_cpu_data[cpunum] = NULL;
+ kfree(cpu);
+ return -ENODATA;
+ }
cpu->cpu = cpunum;
cpu->pstate_policy =
@@ -587,6 +599,7 @@
if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
limits.min_perf_pct = 100;
limits.min_perf = int_tofp(1);
+ limits.max_policy_pct = 100;
limits.max_perf_pct = 100;
limits.max_perf = int_tofp(1);
limits.no_turbo = 0;
@@ -629,8 +642,8 @@
static int __cpuinit intel_pstate_cpu_init(struct cpufreq_policy *policy)
{
- int rc, min_pstate, max_pstate;
struct cpudata *cpu;
+ int rc;
rc = intel_pstate_init_cpu(policy->cpu);
if (rc)
@@ -644,9 +657,8 @@
else
policy->policy = CPUFREQ_POLICY_POWERSAVE;
- intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
- policy->min = min_pstate * 100000;
- policy->max = max_pstate * 100000;
+ policy->min = cpu->pstate.min_pstate * 100000;
+ policy->max = cpu->pstate.turbo_pstate * 100000;
/* cpuinfo and default policy values */
policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index d539127..f92b02a 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -118,11 +118,6 @@
clk_put(cpuclk);
return -EINVAL;
}
- ret = clk_set_rate(cpuclk, rate);
- if (ret) {
- clk_put(cpuclk);
- return ret;
- }
/* clock table init */
for (i = 2;
@@ -130,6 +125,12 @@
i++)
loongson2_clockmod_table[i].frequency = (rate * i) / 8;
+ ret = clk_set_rate(cpuclk, rate);
+ if (ret) {
+ clk_put(cpuclk);
+ return ret;
+ }
+
policy->cur = loongson2_cpufreq_get(policy->cpu);
cpufreq_frequency_table_get_attr(&loongson2_clockmod_table[0],
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index ea0222a..b07ca0d 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -26,41 +26,108 @@
static unsigned int busfreq; /* FSB, in 10 kHz */
static unsigned int max_multiplier;
+static unsigned int param_busfreq = 0;
+static unsigned int param_max_multiplier = 0;
+
+module_param_named(max_multiplier, param_max_multiplier, uint, S_IRUGO);
+MODULE_PARM_DESC(max_multiplier, "Maximum multiplier (allowed values: 20 30 35 40 45 50 55 60)");
+
+module_param_named(bus_frequency, param_busfreq, uint, S_IRUGO);
+MODULE_PARM_DESC(bus_frequency, "Bus frequency in kHz");
/* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
static struct cpufreq_frequency_table clock_ratio[] = {
- {45, /* 000 -> 4.5x */ 0},
- {50, /* 001 -> 5.0x */ 0},
- {40, /* 010 -> 4.0x */ 0},
- {55, /* 011 -> 5.5x */ 0},
- {20, /* 100 -> 2.0x */ 0},
- {30, /* 101 -> 3.0x */ 0},
{60, /* 110 -> 6.0x */ 0},
+ {55, /* 011 -> 5.5x */ 0},
+ {50, /* 001 -> 5.0x */ 0},
+ {45, /* 000 -> 4.5x */ 0},
+ {40, /* 010 -> 4.0x */ 0},
{35, /* 111 -> 3.5x */ 0},
+ {30, /* 101 -> 3.0x */ 0},
+ {20, /* 100 -> 2.0x */ 0},
{0, CPUFREQ_TABLE_END}
};
+static const u8 index_to_register[8] = { 6, 3, 1, 0, 2, 7, 5, 4 };
+static const u8 register_to_index[8] = { 3, 2, 4, 1, 7, 6, 0, 5 };
+
+static const struct {
+ unsigned freq;
+ unsigned mult;
+} usual_frequency_table[] = {
+ { 400000, 40 }, // 100 * 4
+ { 450000, 45 }, // 100 * 4.5
+ { 475000, 50 }, // 95 * 5
+ { 500000, 50 }, // 100 * 5
+ { 506250, 45 }, // 112.5 * 4.5
+ { 533500, 55 }, // 97 * 5.5
+ { 550000, 55 }, // 100 * 5.5
+ { 562500, 50 }, // 112.5 * 5
+ { 570000, 60 }, // 95 * 6
+ { 600000, 60 }, // 100 * 6
+ { 618750, 55 }, // 112.5 * 5.5
+ { 660000, 55 }, // 120 * 5.5
+ { 675000, 60 }, // 112.5 * 6
+ { 720000, 60 }, // 120 * 6
+};
+
+#define FREQ_RANGE 3000
/**
* powernow_k6_get_cpu_multiplier - returns the current FSB multiplier
*
- * Returns the current setting of the frequency multiplier. Core clock
+ * Returns the current setting of the frequency multiplier. Core clock
* speed is frequency of the Front-Side Bus multiplied with this value.
*/
static int powernow_k6_get_cpu_multiplier(void)
{
- u64 invalue = 0;
+ unsigned long invalue = 0;
u32 msrval;
+ local_irq_disable();
+
msrval = POWERNOW_IOPORT + 0x1;
wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
invalue = inl(POWERNOW_IOPORT + 0x8);
msrval = POWERNOW_IOPORT + 0x0;
wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
- return clock_ratio[(invalue >> 5)&7].index;
+ local_irq_enable();
+
+ return clock_ratio[register_to_index[(invalue >> 5)&7]].index;
}
+static void powernow_k6_set_cpu_multiplier(unsigned int best_i)
+{
+ unsigned long outvalue, invalue;
+ unsigned long msrval;
+ unsigned long cr0;
+
+ /* we now need to transform best_i to the BVC format, see AMD#23446 */
+
+ /*
+ * The processor doesn't respond to inquiry cycles while changing the
+ * frequency, so we must disable cache.
+ */
+ local_irq_disable();
+ cr0 = read_cr0();
+ write_cr0(cr0 | X86_CR0_CD);
+ wbinvd();
+
+ outvalue = (1<<12) | (1<<10) | (1<<9) | (index_to_register[best_i]<<5);
+
+ msrval = POWERNOW_IOPORT + 0x1;
+ wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
+ invalue = inl(POWERNOW_IOPORT + 0x8);
+ invalue = invalue & 0x1f;
+ outvalue = outvalue | invalue;
+ outl(outvalue, (POWERNOW_IOPORT + 0x8));
+ msrval = POWERNOW_IOPORT + 0x0;
+ wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+
+ write_cr0(cr0);
+ local_irq_enable();
+}
/**
* powernow_k6_set_state - set the PowerNow! multiplier
@@ -71,8 +138,6 @@
static void powernow_k6_set_state(struct cpufreq_policy *policy,
unsigned int best_i)
{
- unsigned long outvalue = 0, invalue = 0;
- unsigned long msrval;
struct cpufreq_freqs freqs;
if (clock_ratio[best_i].index > max_multiplier) {
@@ -85,18 +150,7 @@
cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
- /* we now need to transform best_i to the BVC format, see AMD#23446 */
-
- outvalue = (1<<12) | (1<<10) | (1<<9) | (best_i<<5);
-
- msrval = POWERNOW_IOPORT + 0x1;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */
- invalue = inl(POWERNOW_IOPORT + 0x8);
- invalue = invalue & 0xf;
- outvalue = outvalue | invalue;
- outl(outvalue , (POWERNOW_IOPORT + 0x8));
- msrval = POWERNOW_IOPORT + 0x0;
- wrmsr(MSR_K6_EPMR, msrval, 0); /* disable it again */
+ powernow_k6_set_cpu_multiplier(best_i);
cpufreq_notify_transition(policy, &freqs, CPUFREQ_POSTCHANGE);
@@ -141,18 +195,57 @@
return 0;
}
-
static int powernow_k6_cpu_init(struct cpufreq_policy *policy)
{
unsigned int i, f;
int result;
+ unsigned khz;
if (policy->cpu != 0)
return -ENODEV;
- /* get frequencies */
- max_multiplier = powernow_k6_get_cpu_multiplier();
- busfreq = cpu_khz / max_multiplier;
+ max_multiplier = 0;
+ khz = cpu_khz;
+ for (i = 0; i < ARRAY_SIZE(usual_frequency_table); i++) {
+ if (khz >= usual_frequency_table[i].freq - FREQ_RANGE &&
+ khz <= usual_frequency_table[i].freq + FREQ_RANGE) {
+ khz = usual_frequency_table[i].freq;
+ max_multiplier = usual_frequency_table[i].mult;
+ break;
+ }
+ }
+ if (param_max_multiplier) {
+ for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
+ if (clock_ratio[i].index == param_max_multiplier) {
+ max_multiplier = param_max_multiplier;
+ goto have_max_multiplier;
+ }
+ }
+ printk(KERN_ERR "powernow-k6: invalid max_multiplier parameter, valid parameters 20, 30, 35, 40, 45, 50, 55, 60\n");
+ return -EINVAL;
+ }
+
+ if (!max_multiplier) {
+ printk(KERN_WARNING "powernow-k6: unknown frequency %u, cannot determine current multiplier\n", khz);
+ printk(KERN_WARNING "powernow-k6: use module parameters max_multiplier and bus_frequency\n");
+ return -EOPNOTSUPP;
+ }
+
+have_max_multiplier:
+ param_max_multiplier = max_multiplier;
+
+ if (param_busfreq) {
+ if (param_busfreq >= 50000 && param_busfreq <= 150000) {
+ busfreq = param_busfreq / 10;
+ goto have_busfreq;
+ }
+ printk(KERN_ERR "powernow-k6: invalid bus_frequency parameter, allowed range 50000 - 150000 kHz\n");
+ return -EINVAL;
+ }
+
+ busfreq = khz / max_multiplier;
+have_busfreq:
+ param_busfreq = busfreq * 10;
/* table init */
for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
@@ -164,7 +257,7 @@
}
/* cpuinfo and default policy values */
- policy->cpuinfo.transition_latency = 200000;
+ policy->cpuinfo.transition_latency = 500000;
policy->cur = busfreq * max_multiplier;
result = cpufreq_frequency_table_cpuinfo(policy, clock_ratio);
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index b828efe..9b963ce 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1100,7 +1100,7 @@
{
struct powernow_k8_data *data;
struct init_on_cpu init_on_cpu;
- int rc;
+ int rc, cpu;
smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
if (rc)
@@ -1169,7 +1169,9 @@
pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n",
data->currfid, data->currvid);
- per_cpu(powernow_data, pol->cpu) = data;
+ /* Point all the CPUs in this policy to the same data */
+ for_each_cpu(cpu, pol->cpus)
+ per_cpu(powernow_data, cpu) = data;
return 0;
@@ -1184,6 +1186,7 @@
static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
{
struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
+ int cpu;
if (!data)
return -EINVAL;
@@ -1194,7 +1197,8 @@
kfree(data->powernow_table);
kfree(data);
- per_cpu(powernow_data, pol->cpu) = NULL;
+ for_each_cpu(cpu, pol->cpus)
+ per_cpu(powernow_data, cpu) = NULL;
return 0;
}
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 7047821..4ab7a21 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -400,6 +400,7 @@
pr_debug("previous speed is %u\n", prev_speed);
+ preempt_disable();
local_irq_save(flags);
/* switch to low state */
@@ -464,6 +465,8 @@
out:
local_irq_restore(flags);
+ preempt_enable();
+
return ret;
}
EXPORT_SYMBOL_GPL(speedstep_get_freqs);
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index f5a6b70..2844009 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -188,6 +188,7 @@
return;
/* Disable IRQs */
+ preempt_disable();
local_irq_save(flags);
command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
@@ -198,9 +199,19 @@
do {
if (retry) {
+ /*
+ * We need to enable interrupts, otherwise the blockage
+ * won't resolve.
+ *
+ * We disable preemption so that other processes don't
+ * run. If other processes were running, they could
+ * submit more DMA requests, making the blockage worse.
+ */
pr_debug("retry %u, previous result %u, waiting...\n",
retry, result);
+ local_irq_enable();
mdelay(retry * 50);
+ local_irq_disable();
}
retry++;
__asm__ __volatile__(
@@ -217,6 +228,7 @@
/* enable IRQs */
local_irq_restore(flags);
+ preempt_enable();
if (new_state == state)
pr_debug("change to %u MHz succeeded after %u tries "
diff --git a/drivers/cpufreq/vexpress_big_little.c b/drivers/cpufreq/vexpress_big_little.c
new file mode 100644
index 0000000..1abb883
--- /dev/null
+++ b/drivers/cpufreq/vexpress_big_little.c
@@ -0,0 +1,86 @@
+/*
+ * Vexpress big.LITTLE CPUFreq Interface driver
+ *
+ * It provides necessary ops to arm_big_little cpufreq driver and gets
+ * Frequency information from Device Tree. Freq table in DT must be in KHz.
+ *
+ * Copyright (C) 2013 Linaro.
+ * Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/export.h>
+#include <linux/opp.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/vexpress.h>
+#include "arm_big_little.h"
+
+static int vexpress_init_opp_table(struct device *cpu_dev)
+{
+ int i = -1, count, cluster = cpu_to_cluster(cpu_dev->id);
+ u32 *table;
+ int ret;
+
+ count = vexpress_spc_get_freq_table(cluster, &table);
+ if (!table || !count) {
+ pr_err("SPC controller returned invalid freq table");
+ return -EINVAL;
+ }
+
+ while (++i < count) {
+ /* FIXME: Voltage value */
+ ret = opp_add(cpu_dev, table[i] * 1000, 900000);
+ if (ret) {
+ dev_warn(cpu_dev, "%s: Failed to add OPP %d, err: %d\n",
+ __func__, table[i] * 1000, ret);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int vexpress_get_transition_latency(struct device *cpu_dev)
+{
+ /* 1 ms */
+ return 1000000;
+}
+
+static struct cpufreq_arm_bL_ops vexpress_bL_ops = {
+ .name = "vexpress-bL",
+ .get_transition_latency = vexpress_get_transition_latency,
+ .init_opp_table = vexpress_init_opp_table,
+};
+
+static int vexpress_bL_init(void)
+{
+ if (!vexpress_spc_check_loaded()) {
+ pr_info("%s: No SPC found\n", __func__);
+ return -ENOENT;
+ }
+
+ return bL_cpufreq_register(&vexpress_bL_ops);
+}
+module_init(vexpress_bL_init);
+
+static void vexpress_bL_exit(void)
+{
+ return bL_cpufreq_unregister(&vexpress_bL_ops);
+}
+module_exit(vexpress_bL_exit);
+
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
+MODULE_DESCRIPTION("ARM Vexpress big LITTLE cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index c4cc27e..9625ce7 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -31,8 +31,16 @@
config ARCH_NEEDS_CPU_IDLE_COUPLED
def_bool n
+config DT_IDLE_STATES
+ bool
+
if CPU_IDLE
+menu "ARM64 CPU Idle Drivers"
+depends on ARM64
+source "drivers/cpuidle/Kconfig.arm64"
+endmenu
+
config CPU_IDLE_CALXEDA
bool "CPU Idle Driver for Calxeda processors"
depends on ARCH_HIGHBANK
diff --git a/drivers/cpuidle/Kconfig.arm64 b/drivers/cpuidle/Kconfig.arm64
new file mode 100644
index 0000000..d0a08ed
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.arm64
@@ -0,0 +1,14 @@
+#
+# ARM64 CPU Idle drivers
+#
+
+config ARM64_CPUIDLE
+ bool "Generic ARM64 CPU idle Driver"
+ select ARM64_CPU_SUSPEND
+ select DT_IDLE_STATES
+ help
+ Select this to enable generic cpuidle driver for ARM64.
+ It provides a generic idle driver whose idle states are configured
+ at run-time through DT nodes. The CPUidle suspend backend is
+ initialized by calling the CPU operations init idle hook
+ provided by architecture code.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 0d8bd55..0bd32cd 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -4,6 +4,12 @@
obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
+obj-$(CONFIG_BIG_LITTLE) += arm_big_little.o
+obj-$(CONFIG_DT_IDLE_STATES) += dt_idle_states.o
obj-$(CONFIG_CPU_IDLE_CALXEDA) += cpuidle-calxeda.o
obj-$(CONFIG_ARCH_KIRKWOOD) += cpuidle-kirkwood.o
+
+###############################################################################
+# ARM64 drivers
+obj-$(CONFIG_ARM64_CPUIDLE) += cpuidle-arm64.o
diff --git a/drivers/cpuidle/arm_big_little.c b/drivers/cpuidle/arm_big_little.c
new file mode 100644
index 0000000..e537889
--- /dev/null
+++ b/drivers/cpuidle/arm_big_little.c
@@ -0,0 +1,183 @@
+/*
+ * big.LITTLE CPU idle driver.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/arm-cci.h>
+#include <linux/bitmap.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
+#include <linux/clockchips.h>
+#include <linux/debugfs.h>
+#include <linux/hrtimer.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/tick.h>
+#include <linux/vexpress.h>
+#include <asm/mcpm.h>
+#include <asm/cpuidle.h>
+#include <asm/cputype.h>
+#include <asm/idmap.h>
+#include <asm/proc-fns.h>
+#include <asm/suspend.h>
+#include <linux/of.h>
+
+static int bl_cpuidle_simple_enter(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
+{
+ ktime_t time_start, time_end;
+ s64 diff;
+
+ time_start = ktime_get();
+
+ cpu_do_idle();
+
+ time_end = ktime_get();
+
+ local_irq_enable();
+
+ diff = ktime_to_us(ktime_sub(time_end, time_start));
+ if (diff > INT_MAX)
+ diff = INT_MAX;
+
+ dev->last_residency = (int) diff;
+
+ return index;
+}
+
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int idx);
+
+static struct cpuidle_state bl_cpuidle_set[] __initdata = {
+ [0] = {
+ .enter = bl_cpuidle_simple_enter,
+ .exit_latency = 1,
+ .target_residency = 1,
+ .power_usage = UINT_MAX,
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .name = "WFI",
+ .desc = "ARM WFI",
+ },
+ [1] = {
+ .enter = bl_enter_powerdown,
+ .exit_latency = 300,
+ .target_residency = 1000,
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .name = "C1",
+ .desc = "ARM power down",
+ },
+};
+
+struct cpuidle_driver bl_idle_driver = {
+ .name = "bl_idle",
+ .owner = THIS_MODULE,
+ .safe_state_index = 0
+};
+
+static DEFINE_PER_CPU(struct cpuidle_device, bl_idle_dev);
+
+static int notrace bl_powerdown_finisher(unsigned long arg)
+{
+ unsigned int mpidr = read_cpuid_mpidr();
+ unsigned int cluster = (mpidr >> 8) & 0xf;
+ unsigned int cpu = mpidr & 0xf;
+
+ mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+ mcpm_cpu_suspend(0); /* 0 should be replaced with better value here */
+ return 1;
+}
+
+/*
+ * bl_enter_powerdown - Programs CPU to enter the specified state
+ * @dev: cpuidle device
+ * @drv: The target state to be programmed
+ * @idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int bl_enter_powerdown(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int idx)
+{
+ struct timespec ts_preidle, ts_postidle, ts_idle;
+ int ret;
+
+ /* Used to keep track of the total time in idle */
+ getnstimeofday(&ts_preidle);
+
+ BUG_ON(!irqs_disabled());
+
+ cpu_pm_enter();
+
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu);
+
+ ret = cpu_suspend((unsigned long) dev, bl_powerdown_finisher);
+ if (ret)
+ BUG();
+
+ mcpm_cpu_powered_up();
+
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+ cpu_pm_exit();
+
+ getnstimeofday(&ts_postidle);
+ local_irq_enable();
+ ts_idle = timespec_sub(ts_postidle, ts_preidle);
+
+ dev->last_residency = ts_idle.tv_nsec / NSEC_PER_USEC +
+ ts_idle.tv_sec * USEC_PER_SEC;
+ return idx;
+}
+
+/*
+ * bl_idle_init
+ *
+ * Registers the bl specific cpuidle driver with the cpuidle
+ * framework with the valid set of states.
+ */
+int __init bl_idle_init(void)
+{
+ struct cpuidle_device *dev;
+ int i, cpu_id;
+ struct cpuidle_driver *drv = &bl_idle_driver;
+
+ if (!of_find_compatible_node(NULL, NULL, "arm,generic")) {
+ pr_info("%s: No compatible node found\n", __func__);
+ return -ENODEV;
+ }
+
+ drv->state_count = (sizeof(bl_cpuidle_set) /
+ sizeof(struct cpuidle_state));
+
+ for (i = 0; i < drv->state_count; i++) {
+ memcpy(&drv->states[i], &bl_cpuidle_set[i],
+ sizeof(struct cpuidle_state));
+ }
+
+ cpuidle_register_driver(drv);
+
+ for_each_cpu(cpu_id, cpu_online_mask) {
+ pr_err("CPUidle for CPU%d registered\n", cpu_id);
+ dev = &per_cpu(bl_idle_dev, cpu_id);
+ dev->cpu = cpu_id;
+
+ dev->state_count = drv->state_count;
+
+ if (cpuidle_register_device(dev)) {
+ printk(KERN_ERR "%s: Cpuidle register device failed\n",
+ __func__);
+ return -EIO;
+ }
+ }
+
+ return 0;
+}
+
+device_initcall(bl_idle_init);
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 2a297f8..fe853903 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -106,6 +106,7 @@
cpumask_t coupled_cpus;
int requested_state[NR_CPUS];
atomic_t ready_waiting_counts;
+ atomic_t abort_barrier;
int online_count;
int refcnt;
int prevent;
@@ -122,12 +123,19 @@
static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
/*
- * The cpuidle_coupled_poked_mask mask is used to avoid calling
+ * The cpuidle_coupled_poke_pending mask is used to avoid calling
* __smp_call_function_single with the per cpu call_single_data struct already
* in use. This prevents a deadlock where two cpus are waiting for each others
* call_single_data struct to be available
*/
-static cpumask_t cpuidle_coupled_poked_mask;
+static cpumask_t cpuidle_coupled_poke_pending;
+
+/*
+ * The cpuidle_coupled_poked mask is used to ensure that each cpu has been poked
+ * once to minimize entering the ready loop with a poke pending, which would
+ * require aborting and retrying.
+ */
+static cpumask_t cpuidle_coupled_poked;
/**
* cpuidle_coupled_parallel_barrier - synchronize all online coupled cpus
@@ -291,10 +299,11 @@
return state;
}
-static void cpuidle_coupled_poked(void *info)
+static void cpuidle_coupled_handle_poke(void *info)
{
int cpu = (unsigned long)info;
- cpumask_clear_cpu(cpu, &cpuidle_coupled_poked_mask);
+ cpumask_set_cpu(cpu, &cpuidle_coupled_poked);
+ cpumask_clear_cpu(cpu, &cpuidle_coupled_poke_pending);
}
/**
@@ -313,7 +322,7 @@
{
struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
- if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poked_mask))
+ if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
__smp_call_function_single(cpu, csd, 0);
}
@@ -340,30 +349,19 @@
* @coupled: the struct coupled that contains the current cpu
* @next_state: the index in drv->states of the requested state for this cpu
*
- * Updates the requested idle state for the specified cpuidle device,
- * poking all coupled cpus out of idle if necessary to let them see the new
- * state.
+ * Updates the requested idle state for the specified cpuidle device.
+ * Returns the number of waiting cpus.
*/
-static void cpuidle_coupled_set_waiting(int cpu,
+static int cpuidle_coupled_set_waiting(int cpu,
struct cpuidle_coupled *coupled, int next_state)
{
- int w;
-
coupled->requested_state[cpu] = next_state;
/*
- * If this is the last cpu to enter the waiting state, poke
- * all the other cpus out of their waiting state so they can
- * enter a deeper state. This can race with one of the cpus
- * exiting the waiting state due to an interrupt and
- * decrementing waiting_count, see comment below.
- *
* The atomic_inc_return provides a write barrier to order the write
* to requested_state with the later write that increments ready_count.
*/
- w = atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK;
- if (w == coupled->online_count)
- cpuidle_coupled_poke_others(cpu, coupled);
+ return atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK;
}
/**
@@ -410,19 +408,33 @@
* been processed and the poke bit has been cleared.
*
* Other interrupts may also be processed while interrupts are enabled, so
- * need_resched() must be tested after turning interrupts off again to make sure
+ * need_resched() must be tested after this function returns to make sure
* the interrupt didn't schedule work that should take the cpu out of idle.
*
- * Returns 0 if need_resched was false, -EINTR if need_resched was true.
+ * Returns 0 if no poke was pending, 1 if a poke was cleared.
*/
static int cpuidle_coupled_clear_pokes(int cpu)
{
+ if (!cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
+ return 0;
+
local_irq_enable();
- while (cpumask_test_cpu(cpu, &cpuidle_coupled_poked_mask))
+ while (cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending))
cpu_relax();
local_irq_disable();
- return need_resched() ? -EINTR : 0;
+ return 1;
+}
+
+static bool cpuidle_coupled_any_pokes_pending(struct cpuidle_coupled *coupled)
+{
+ cpumask_t cpus;
+ int ret;
+
+ cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus);
+ ret = cpumask_and(&cpus, &cpuidle_coupled_poke_pending, &cpus);
+
+ return ret;
}
/**
@@ -449,12 +461,14 @@
{
int entered_state = -1;
struct cpuidle_coupled *coupled = dev->coupled;
+ int w;
if (!coupled)
return -EINVAL;
while (coupled->prevent) {
- if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+ cpuidle_coupled_clear_pokes(dev->cpu);
+ if (need_resched()) {
local_irq_enable();
return entered_state;
}
@@ -465,15 +479,37 @@
/* Read barrier ensures online_count is read after prevent is cleared */
smp_rmb();
- cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state);
+reset:
+ cpumask_clear_cpu(dev->cpu, &cpuidle_coupled_poked);
+
+ w = cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state);
+ /*
+ * If this is the last cpu to enter the waiting state, poke
+ * all the other cpus out of their waiting state so they can
+ * enter a deeper state. This can race with one of the cpus
+ * exiting the waiting state due to an interrupt and
+ * decrementing waiting_count, see comment below.
+ */
+ if (w == coupled->online_count) {
+ cpumask_set_cpu(dev->cpu, &cpuidle_coupled_poked);
+ cpuidle_coupled_poke_others(dev->cpu, coupled);
+ }
retry:
/*
* Wait for all coupled cpus to be idle, using the deepest state
- * allowed for a single cpu.
+ * allowed for a single cpu. If this was not the poking cpu, wait
+ * for at least one poke before leaving to avoid a race where
+ * two cpus could arrive at the waiting loop at the same time,
+ * but the first of the two to arrive could skip the loop without
+ * processing the pokes from the last to arrive.
*/
- while (!cpuidle_coupled_cpus_waiting(coupled)) {
- if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+ while (!cpuidle_coupled_cpus_waiting(coupled) ||
+ !cpumask_test_cpu(dev->cpu, &cpuidle_coupled_poked)) {
+ if (cpuidle_coupled_clear_pokes(dev->cpu))
+ continue;
+
+ if (need_resched()) {
cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
goto out;
}
@@ -487,12 +523,19 @@
dev->safe_state_index);
}
- if (cpuidle_coupled_clear_pokes(dev->cpu)) {
+ cpuidle_coupled_clear_pokes(dev->cpu);
+ if (need_resched()) {
cpuidle_coupled_set_not_waiting(dev->cpu, coupled);
goto out;
}
/*
+ * Make sure final poke status for this cpu is visible before setting
+ * cpu as ready.
+ */
+ smp_wmb();
+
+ /*
* All coupled cpus are probably idle. There is a small chance that
* one of the other cpus just became active. Increment the ready count,
* and spin until all coupled cpus have incremented the counter. Once a
@@ -511,6 +554,28 @@
cpu_relax();
}
+ /*
+ * Make sure read of all cpus ready is done before reading pending pokes
+ */
+ smp_rmb();
+
+ /*
+ * There is a small chance that a cpu left and reentered idle after this
+ * cpu saw that all cpus were waiting. The cpu that reentered idle will
+ * have sent this cpu a poke, which will still be pending after the
+ * ready loop. The pending interrupt may be lost by the interrupt
+ * controller when entering the deep idle state. It's not possible to
+ * clear a pending interrupt without turning interrupts on and handling
+ * it, and it's too late to turn on interrupts here, so reset the
+ * coupled idle state of all cpus and retry.
+ */
+ if (cpuidle_coupled_any_pokes_pending(coupled)) {
+ cpuidle_coupled_set_done(dev->cpu, coupled);
+ /* Wait for all cpus to see the pending pokes */
+ cpuidle_coupled_parallel_barrier(dev, &coupled->abort_barrier);
+ goto reset;
+ }
+
/* all cpus have acked the coupled state */
next_state = cpuidle_coupled_get_state(dev, coupled);
@@ -596,7 +661,7 @@
coupled->refcnt++;
csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu);
- csd->func = cpuidle_coupled_poked;
+ csd->func = cpuidle_coupled_handle_poke;
csd->info = (void *)(unsigned long)dev->cpu;
return 0;
diff --git a/drivers/cpuidle/cpuidle-arm64.c b/drivers/cpuidle/cpuidle-arm64.c
new file mode 100644
index 0000000..50997ea
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-arm64.c
@@ -0,0 +1,133 @@
+/*
+ * ARM64 generic CPU idle driver.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "CPUidle arm64: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_pm.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+#include <asm/cpuidle.h>
+#include <asm/suspend.h>
+
+#include "dt_idle_states.h"
+
+/*
+ * arm64_enter_idle_state - Programs CPU to enter the specified state
+ *
+ * dev: cpuidle device
+ * drv: cpuidle driver
+ * idx: state index
+ *
+ * Called from the CPUidle framework to program the device to the
+ * specified target state selected by the governor.
+ */
+static int arm64_enter_idle_state(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int idx)
+{
+ int ret;
+
+ if (!idx) {
+ cpu_do_idle();
+ return idx;
+ }
+
+ ret = cpu_pm_enter();
+ if (!ret) {
+ /*
+ * Pass idle state index to cpu_suspend which in turn will
+ * call the CPU ops suspend protocol with idle index as a
+ * parameter.
+ */
+ ret = cpu_suspend(idx);
+
+ cpu_pm_exit();
+ }
+
+ return ret ? -1 : idx;
+}
+
+static struct cpuidle_driver arm64_idle_driver = {
+ .name = "arm64_idle",
+ .owner = THIS_MODULE,
+ /*
+ * State at index 0 is standby wfi and considered standard
+ * on all ARM platforms. If in some platforms simple wfi
+ * can't be used as "state 0", DT bindings must be implemented
+ * to work around this issue and allow installing a special
+ * handler for idle state index 0.
+ */
+ .states[0] = {
+ .enter = arm64_enter_idle_state,
+ .exit_latency = 1,
+ .target_residency = 1,
+ .power_usage = UINT_MAX,
+ .flags = CPUIDLE_FLAG_TIME_VALID,
+ .name = "WFI",
+ .desc = "ARM64 WFI",
+ }
+};
+
+static const struct of_device_id arm64_idle_state_match[] __initconst = {
+ { .compatible = "arm,idle-state",
+ .data = arm64_enter_idle_state },
+ { },
+};
+
+/*
+ * arm64_idle_init
+ *
+ * Registers the arm64 specific cpuidle driver with the cpuidle
+ * framework. It relies on core code to parse the idle states
+ * and initialize them using driver data structures accordingly.
+ */
+static int __init arm64_idle_init(void)
+{
+ int cpu, ret;
+ struct cpuidle_driver *drv = &arm64_idle_driver;
+
+ /*
+ * Initialize idle states data, starting at index 1.
+ * This driver is DT only, if no DT idle states are detected (ret == 0)
+ * let the driver initialization fail accordingly since there is no
+ * reason to initialize the idle driver if only wfi is supported.
+ */
+ ret = dt_init_idle_driver(drv, arm64_idle_state_match, 1);
+ if (ret <= 0) {
+ if (ret)
+ pr_err("failed to initialize idle states\n");
+ return ret ? : -ENODEV;
+ }
+
+ /*
+ * Call arch CPU operations in order to initialize
+ * idle states suspend back-end specific data
+ */
+ for_each_possible_cpu(cpu) {
+ ret = cpu_init_idle(cpu);
+ if (ret) {
+ pr_err("CPU %d failed to init idle CPU ops\n", cpu);
+ return ret;
+ }
+ }
+
+ ret = cpuidle_register(drv, NULL);
+ if (ret) {
+ pr_err("failed to register cpuidle driver\n");
+ return ret;
+ }
+
+ return 0;
+}
+device_initcall(arm64_idle_init);
diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 2233791..0e6e408 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -37,20 +37,6 @@
extern void highbank_set_cpu_jump(int cpu, void *jump_addr);
extern void *scu_base_addr;
-static inline unsigned int get_auxcr(void)
-{
- unsigned int val;
- asm("mrc p15, 0, %0, c1, c0, 1 @ get AUXCR" : "=r" (val) : : "cc");
- return val;
-}
-
-static inline void set_auxcr(unsigned int val)
-{
- asm volatile("mcr p15, 0, %0, c1, c0, 1 @ set AUXCR"
- : : "r" (val) : "cc");
- isb();
-}
-
static noinline void calxeda_idle_restore(void)
{
set_cr(get_cr() | CR_C);
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 8dfaaae..2253271 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -251,7 +251,8 @@
spin_lock(&cpuidle_driver_lock);
drv = cpuidle_get_driver();
- drv->refcnt++;
+ if (drv)
+ drv->refcnt++;
spin_unlock(&cpuidle_driver_lock);
return drv;
diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c
new file mode 100644
index 0000000..52f4d11
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.c
@@ -0,0 +1,213 @@
+/*
+ * DT idle states parsing code.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "DT idle-states: " fmt
+
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include "dt_idle_states.h"
+
+static int init_state_node(struct cpuidle_state *idle_state,
+ const struct of_device_id *matches,
+ struct device_node *state_node)
+{
+ int err;
+ const struct of_device_id *match_id;
+
+ match_id = of_match_node(matches, state_node);
+ if (!match_id)
+ return -ENODEV;
+ /*
+ * CPUidle drivers are expected to initialize the const void *data
+ * pointer of the passed in struct of_device_id array to the idle
+ * state enter function.
+ */
+ idle_state->enter = match_id->data;
+
+ err = of_property_read_u32(state_node, "wakeup-latency-us",
+ &idle_state->exit_latency);
+ if (err) {
+ u32 entry_latency, exit_latency;
+
+ err = of_property_read_u32(state_node, "entry-latency-us",
+ &entry_latency);
+ if (err) {
+ pr_debug(" * %s missing entry-latency-us property\n",
+ state_node->full_name);
+ return -EINVAL;
+ }
+
+ err = of_property_read_u32(state_node, "exit-latency-us",
+ &exit_latency);
+ if (err) {
+ pr_debug(" * %s missing exit-latency-us property\n",
+ state_node->full_name);
+ return -EINVAL;
+ }
+ /*
+ * If wakeup-latency-us is missing, default to entry+exit
+ * latencies as defined in idle states bindings
+ */
+ idle_state->exit_latency = entry_latency + exit_latency;
+ }
+
+ err = of_property_read_u32(state_node, "min-residency-us",
+ &idle_state->target_residency);
+ if (err) {
+ pr_debug(" * %s missing min-residency-us property\n",
+ state_node->full_name);
+ return -EINVAL;
+ }
+
+ idle_state->flags = CPUIDLE_FLAG_TIME_VALID;
+ if (of_property_read_bool(state_node, "local-timer-stop"))
+ idle_state->flags |= CPUIDLE_FLAG_TIMER_STOP;
+ /*
+ * TODO:
+ * replace with kstrdup and pointer assignment when name
+ * and desc become string pointers
+ */
+ strncpy(idle_state->name, state_node->name, CPUIDLE_NAME_LEN - 1);
+ strncpy(idle_state->desc, state_node->name, CPUIDLE_DESC_LEN - 1);
+ return 0;
+}
+
+/*
+ * Check that the idle state is uniform across all CPUs in the CPUidle driver
+ * cpumask
+ */
+static bool idle_state_valid(struct device_node *state_node, unsigned int idx,
+ const cpumask_t *cpumask)
+{
+ int cpu;
+ struct device_node *cpu_node, *curr_state_node;
+ bool valid = true;
+
+ /*
+ * Compare idle state phandles for index idx on all CPUs in the
+ * CPUidle driver cpumask. Start from next logical cpu following
+ * cpumask_first(cpumask) since that's the CPU state_node was
+ * retrieved from. If a mismatch is found bail out straight
+ * away since we certainly hit a firmware misconfiguration.
+ */
+ for (cpu = cpumask_next(cpumask_first(cpumask), cpumask);
+ cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpumask)) {
+ cpu_node = of_cpu_device_node_get(cpu);
+ curr_state_node = of_parse_phandle(cpu_node, "cpu-idle-states",
+ idx);
+ if (state_node != curr_state_node)
+ valid = false;
+
+ of_node_put(curr_state_node);
+ of_node_put(cpu_node);
+ if (!valid)
+ break;
+ }
+
+ return valid;
+}
+
+/**
+ * dt_init_idle_driver() - Parse the DT idle states and initialize the
+ * idle driver states array
+ * @drv: Pointer to CPU idle driver to be initialized
+ * @matches: Array of of_device_id match structures to search in for
+ * compatible idle state nodes. The data pointer for each valid
+ * struct of_device_id entry in the matches array must point to
+ * a function with the following signature, that corresponds to
+ * the CPUidle state enter function signature:
+ *
+ * int (*)(struct cpuidle_device *dev,
+ * struct cpuidle_driver *drv,
+ * int index);
+ *
+ * @start_idx: First idle state index to be initialized
+ *
+ * If DT idle states are detected and are valid the state count and states
+ * array entries in the cpuidle driver are initialized accordingly starting
+ * from index start_idx.
+ *
+ * Return: number of valid DT idle states parsed, <0 on failure
+ */
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+ const struct of_device_id *matches,
+ unsigned int start_idx)
+{
+ struct cpuidle_state *idle_state;
+ struct device_node *state_node, *cpu_node;
+ int i, err = 0;
+ const cpumask_t *cpumask;
+ unsigned int state_idx = start_idx;
+
+ if (state_idx >= CPUIDLE_STATE_MAX)
+ return -EINVAL;
+ /*
+ * We get the idle states for the first logical cpu in the
+ * driver mask (or cpu_possible_mask if the driver cpumask is not set)
+ * and we check through idle_state_valid() if they are uniform
+ * across CPUs, otherwise we hit a firmware misconfiguration.
+ */
+ cpumask = drv->cpumask ? : cpu_possible_mask;
+ cpu_node = of_cpu_device_node_get(cpumask_first(cpumask));
+
+ for (i = 0; ; i++) {
+ state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+ if (!state_node)
+ break;
+
+ if (!idle_state_valid(state_node, i, cpumask)) {
+ pr_warn("%s idle state not valid, bailing out\n",
+ state_node->full_name);
+ err = -EINVAL;
+ break;
+ }
+
+ if (state_idx == CPUIDLE_STATE_MAX) {
+ pr_warn("State index reached static CPU idle driver states array size\n");
+ break;
+ }
+
+ idle_state = &drv->states[state_idx++];
+ err = init_state_node(idle_state, matches, state_node);
+ if (err) {
+ pr_err("Parsing idle state node %s failed with err %d\n",
+ state_node->full_name, err);
+ err = -EINVAL;
+ break;
+ }
+ of_node_put(state_node);
+ }
+
+ of_node_put(state_node);
+ of_node_put(cpu_node);
+ if (err)
+ return err;
+ /*
+ * Update the driver state count only if some valid DT idle states
+ * were detected
+ */
+ if (i)
+ drv->state_count = state_idx;
+
+ /*
+ * Return the number of present and valid DT idle states, which can
+ * also be 0 on platforms with missing DT idle states or legacy DT
+ * configuration predating the DT idle states bindings.
+ */
+ return i;
+}
+EXPORT_SYMBOL_GPL(dt_init_idle_driver);
diff --git a/drivers/cpuidle/dt_idle_states.h b/drivers/cpuidle/dt_idle_states.h
new file mode 100644
index 0000000..4818134
--- /dev/null
+++ b/drivers/cpuidle/dt_idle_states.h
@@ -0,0 +1,7 @@
+#ifndef __DT_IDLE_STATES
+#define __DT_IDLE_STATES
+
+int dt_init_idle_driver(struct cpuidle_driver *drv,
+ const struct of_device_id *matches,
+ unsigned int start_idx);
+#endif
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index fe343a0..bc580b6 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -28,13 +28,6 @@
#define MAX_INTERESTING 50000
#define STDDEV_THRESH 400
-/* 60 * 60 > STDDEV_THRESH * INTERVALS = 400 * 8 */
-#define MAX_DEVIATION 60
-
-static DEFINE_PER_CPU(struct hrtimer, menu_hrtimer);
-static DEFINE_PER_CPU(int, hrtimer_status);
-/* menu hrtimer mode */
-enum {MENU_HRTIMER_STOP, MENU_HRTIMER_REPEAT, MENU_HRTIMER_GENERAL};
/*
* Concepts and ideas behind the menu governor
@@ -116,13 +109,6 @@
*
*/
-/*
- * The C-state residency is so long that is is worthwhile to exit
- * from the shallow C-state and re-enter into a deeper C-state.
- */
-static unsigned int perfect_cstate_ms __read_mostly = 30;
-module_param(perfect_cstate_ms, uint, 0000);
-
struct menu_device {
int last_state_idx;
int needs_update;
@@ -205,52 +191,17 @@
return div_u64(dividend + (divisor / 2), divisor);
}
-/* Cancel the hrtimer if it is not triggered yet */
-void menu_hrtimer_cancel(void)
-{
- int cpu = smp_processor_id();
- struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
-
- /* The timer is still not time out*/
- if (per_cpu(hrtimer_status, cpu)) {
- hrtimer_cancel(hrtmr);
- per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
- }
-}
-EXPORT_SYMBOL_GPL(menu_hrtimer_cancel);
-
-/* Call back for hrtimer is triggered */
-static enum hrtimer_restart menu_hrtimer_notify(struct hrtimer *hrtimer)
-{
- int cpu = smp_processor_id();
- struct menu_device *data = &per_cpu(menu_devices, cpu);
-
- /* In general case, the expected residency is much larger than
- * deepest C-state target residency, but prediction logic still
- * predicts a small predicted residency, so the prediction
- * history is totally broken if the timer is triggered.
- * So reset the correction factor.
- */
- if (per_cpu(hrtimer_status, cpu) == MENU_HRTIMER_GENERAL)
- data->correction_factor[data->bucket] = RESOLUTION * DECAY;
-
- per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_STOP;
-
- return HRTIMER_NORESTART;
-}
-
/*
* Try detecting repeating patterns by keeping track of the last 8
* intervals, and checking if the standard deviation of that set
* of points is below a threshold. If it is... then use the
* average of these 8 points as the estimated value.
*/
-static u32 get_typical_interval(struct menu_device *data)
+static void get_typical_interval(struct menu_device *data)
{
int i = 0, divisor = 0;
uint64_t max = 0, avg = 0, stddev = 0;
int64_t thresh = LLONG_MAX; /* Discard outliers above this value. */
- unsigned int ret = 0;
again:
@@ -291,16 +242,13 @@
if (((avg > stddev * 6) && (divisor * 4 >= INTERVALS * 3))
|| stddev <= 20) {
data->predicted_us = avg;
- ret = 1;
- return ret;
+ return;
} else if ((divisor * 4) > INTERVALS * 3) {
/* Exclude the max interval */
thresh = max - 1;
goto again;
}
-
- return ret;
}
/**
@@ -315,9 +263,6 @@
int i;
int multiplier;
struct timespec t;
- int repeat = 0, low_predicted = 0;
- int cpu = smp_processor_id();
- struct hrtimer *hrtmr = &per_cpu(menu_hrtimer, cpu);
if (data->needs_update) {
menu_update(drv, dev);
@@ -352,7 +297,7 @@
data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket],
RESOLUTION * DECAY);
- repeat = get_typical_interval(data);
+ get_typical_interval(data);
/*
* We want to default to C1 (hlt), not to busy polling
@@ -373,10 +318,8 @@
if (s->disabled || su->disable)
continue;
- if (s->target_residency > data->predicted_us) {
- low_predicted = 1;
+ if (s->target_residency > data->predicted_us)
continue;
- }
if (s->exit_latency > latency_req)
continue;
if (s->exit_latency * multiplier > data->predicted_us)
@@ -386,44 +329,6 @@
data->exit_us = s->exit_latency;
}
- /* not deepest C-state chosen for low predicted residency */
- if (low_predicted) {
- unsigned int timer_us = 0;
- unsigned int perfect_us = 0;
-
- /*
- * Set a timer to detect whether this sleep is much
- * longer than repeat mode predicted. If the timer
- * triggers, the code will evaluate whether to put
- * the CPU into a deeper C-state.
- * The timer is cancelled on CPU wakeup.
- */
- timer_us = 2 * (data->predicted_us + MAX_DEVIATION);
-
- perfect_us = perfect_cstate_ms * 1000;
-
- if (repeat && (4 * timer_us < data->expected_us)) {
- RCU_NONIDLE(hrtimer_start(hrtmr,
- ns_to_ktime(1000 * timer_us),
- HRTIMER_MODE_REL_PINNED));
- /* In repeat case, menu hrtimer is started */
- per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_REPEAT;
- } else if (perfect_us < data->expected_us) {
- /*
- * The next timer is long. This could be because
- * we did not make a useful prediction.
- * In that case, it makes sense to re-enter
- * into a deeper C-state after some time.
- */
- RCU_NONIDLE(hrtimer_start(hrtmr,
- ns_to_ktime(1000 * timer_us),
- HRTIMER_MODE_REL_PINNED));
- /* In general case, menu hrtimer is started */
- per_cpu(hrtimer_status, cpu) = MENU_HRTIMER_GENERAL;
- }
-
- }
-
return data->last_state_idx;
}
@@ -514,9 +419,6 @@
struct cpuidle_device *dev)
{
struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
- struct hrtimer *t = &per_cpu(menu_hrtimer, dev->cpu);
- hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- t->function = menu_hrtimer_notify;
memset(data, 0, sizeof(struct menu_device));
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 5996521..84573b4 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -429,7 +429,7 @@
dma_addr_t src_dma, dst_dma;
int ret = 0;
- desc = kmalloc(CAAM_CMD_SZ * 6 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
+ desc = kmalloc(CAAM_CMD_SZ * 8 + CAAM_PTR_SZ * 2, GFP_KERNEL | GFP_DMA);
if (!desc) {
dev_err(jrdev, "unable to allocate key input memory\n");
return -ENOMEM;
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 9f25f52..0eabd81 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -16,9 +16,13 @@
char *tmp; \
\
tmp = kmalloc(sizeof(format) + max_alloc, GFP_ATOMIC); \
- sprintf(tmp, format, param); \
- strcat(str, tmp); \
- kfree(tmp); \
+ if (likely(tmp)) { \
+ sprintf(tmp, format, param); \
+ strcat(str, tmp); \
+ kfree(tmp); \
+ } else { \
+ strcat(str, "kmalloc failure in SPRINTFCAT"); \
+ } \
}
static void report_jump_idx(u32 status, char *outstr)
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 6c4c000..01783e4 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -927,28 +927,14 @@
goto error_out;
}
- /* Set ptr to new property if provided */
- if (new_prop) {
- /* Single property */
- if (!strncmp(new_prop->name, "status", new_prop->length)) {
- status = new_prop;
-
- } else if (!strncmp(new_prop->name, "ibm,max-sg-len",
- new_prop->length)) {
- maxsglen = new_prop;
-
- } else if (!strncmp(new_prop->name, "ibm,max-sync-cop",
- new_prop->length)) {
- maxsyncop = new_prop;
-
- } else {
- /*
- * Skip the update, the property being updated
- * has no impact.
- */
- goto out;
- }
- }
+ /*
+ * If this is a property update, there are only certain properties that
+ * we care about. Bail if it isn't in the below list
+ */
+ if (new_prop && (strncmp(new_prop->name, "status", new_prop->length) ||
+ strncmp(new_prop->name, "ibm,max-sg-len", new_prop->length) ||
+ strncmp(new_prop->name, "ibm,max-sync-cop", new_prop->length)))
+ goto out;
/* Perform property updates */
ret = nx842_OF_upd_status(new_devdata, status);
@@ -1014,9 +1000,9 @@
* notifier_to_errno() to decode this value
*/
static int nx842_OF_notifier(struct notifier_block *np, unsigned long action,
- void *update)
+ void *data)
{
- struct of_prop_reconfig *upd = update;
+ struct of_reconfig_data *upd = data;
struct nx842_devdata *local_devdata;
struct device_node *node = NULL;
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 633ba94..c178ed8 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -563,4 +563,4 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Michal Ludvig");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 9266c0e..93d7753 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -593,7 +593,7 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Michal Ludvig");
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("sha1-padlock");
-MODULE_ALIAS("sha256-padlock");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-padlock");
+MODULE_ALIAS_CRYPTO("sha256-padlock");
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 32f4806..e08275d 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@
static irqreturn_t cryp_interrupt_handler(int irq, void *param)
{
struct cryp_ctx *ctx;
- int i;
+ int count;
struct cryp_device_data *device_data;
if (param == NULL) {
@@ -215,12 +215,11 @@
if (cryp_pending_irq_src(device_data,
CRYP_IRQ_SRC_OUTPUT_FIFO)) {
if (ctx->outlen / ctx->blocksize > 0) {
- for (i = 0; i < ctx->blocksize / 4; i++) {
- *(ctx->outdata) = readl_relaxed(
- &device_data->base->dout);
- ctx->outdata += 4;
- ctx->outlen -= 4;
- }
+ count = ctx->blocksize / 4;
+
+ readsl(&device_data->base->dout, ctx->outdata, count);
+ ctx->outdata += count;
+ ctx->outlen -= count;
if (ctx->outlen == 0) {
cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@
} else if (cryp_pending_irq_src(device_data,
CRYP_IRQ_SRC_INPUT_FIFO)) {
if (ctx->datalen / ctx->blocksize > 0) {
- for (i = 0 ; i < ctx->blocksize / 4; i++) {
- writel_relaxed(ctx->indata,
- &device_data->base->din);
- ctx->indata += 4;
- ctx->datalen -= 4;
- }
+ count = ctx->blocksize / 4;
+
+ writesl(&device_data->base->din, ctx->indata, count);
+
+ ctx->indata += count;
+ ctx->datalen -= count;
if (ctx->datalen == 0)
cryp_disable_irq_src(device_data,
@@ -1776,7 +1775,7 @@
module_param(cryp_mode, int, 0);
MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 CRYP crypto engine.");
-MODULE_ALIAS("aes-all");
-MODULE_ALIAS("des-all");
+MODULE_ALIAS_CRYPTO("aes-all");
+MODULE_ALIAS_CRYPTO("des-all");
MODULE_LICENSE("GPL");
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index cf55089..6789c16 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1998,7 +1998,7 @@
MODULE_DESCRIPTION("Driver for ST-Ericsson UX500 HASH engine.");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("sha1-all");
-MODULE_ALIAS("sha256-all");
-MODULE_ALIAS("hmac-sha1-all");
-MODULE_ALIAS("hmac-sha256-all");
+MODULE_ALIAS_CRYPTO("sha1-all");
+MODULE_ALIAS_CRYPTO("sha256-all");
+MODULE_ALIAS_CRYPTO("hmac-sha1-all");
+MODULE_ALIAS_CRYPTO("hmac-sha256-all");
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index e992489..0ba5a95 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -333,6 +333,7 @@
bool "Network: TCP receive copy offload"
depends on DMA_ENGINE && NET
default (INTEL_IOATDMA || FSL_DMA)
+ depends on BROKEN
help
This enables the use of DMA engines in the network stack to
offload receive copy-to-user operations, freeing CPU cycles.
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index f285833..617d170 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -414,17 +414,18 @@
struct imxdma_engine *imxdma = imxdmac->imxdma;
int chno = imxdmac->channel;
struct imxdma_desc *desc;
+ unsigned long flags;
- spin_lock(&imxdma->lock);
+ spin_lock_irqsave(&imxdma->lock, flags);
if (list_empty(&imxdmac->ld_active)) {
- spin_unlock(&imxdma->lock);
+ spin_unlock_irqrestore(&imxdma->lock, flags);
goto out;
}
desc = list_first_entry(&imxdmac->ld_active,
struct imxdma_desc,
node);
- spin_unlock(&imxdma->lock);
+ spin_unlock_irqrestore(&imxdma->lock, flags);
if (desc->sg) {
u32 tmp;
@@ -496,7 +497,6 @@
{
struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
struct imxdma_engine *imxdma = imxdmac->imxdma;
- unsigned long flags;
int slot = -1;
int i;
@@ -504,7 +504,6 @@
switch (d->type) {
case IMXDMA_DESC_INTERLEAVED:
/* Try to get a free 2D slot */
- spin_lock_irqsave(&imxdma->lock, flags);
for (i = 0; i < IMX_DMA_2D_SLOTS; i++) {
if ((imxdma->slots_2d[i].count > 0) &&
((imxdma->slots_2d[i].xsr != d->x) ||
@@ -514,10 +513,8 @@
slot = i;
break;
}
- if (slot < 0) {
- spin_unlock_irqrestore(&imxdma->lock, flags);
+ if (slot < 0)
return -EBUSY;
- }
imxdma->slots_2d[slot].xsr = d->x;
imxdma->slots_2d[slot].ysr = d->y;
@@ -526,7 +523,6 @@
imxdmac->slot_2d = slot;
imxdmac->enabled_2d = true;
- spin_unlock_irqrestore(&imxdma->lock, flags);
if (slot == IMX_DMA_2D_SLOT_A) {
d->config_mem &= ~CCR_MSEL_B;
@@ -602,18 +598,17 @@
struct imxdma_channel *imxdmac = (void *)data;
struct imxdma_engine *imxdma = imxdmac->imxdma;
struct imxdma_desc *desc;
+ unsigned long flags;
- spin_lock(&imxdma->lock);
+ spin_lock_irqsave(&imxdma->lock, flags);
if (list_empty(&imxdmac->ld_active)) {
/* Someone might have called terminate all */
- goto out;
+ spin_unlock_irqrestore(&imxdma->lock, flags);
+ return;
}
desc = list_first_entry(&imxdmac->ld_active, struct imxdma_desc, node);
- if (desc->desc.callback)
- desc->desc.callback(desc->desc.callback_param);
-
/* If we are dealing with a cyclic descriptor, keep it on ld_active
* and dont mark the descriptor as complete.
* Only in non-cyclic cases it would be marked as complete
@@ -640,7 +635,11 @@
__func__, imxdmac->channel);
}
out:
- spin_unlock(&imxdma->lock);
+ spin_unlock_irqrestore(&imxdma->lock, flags);
+
+ if (desc->desc.callback)
+ desc->desc.callback(desc->desc.callback_param);
+
}
static int imxdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -862,7 +861,7 @@
kfree(imxdmac->sg_list);
imxdmac->sg_list = kcalloc(periods + 1,
- sizeof(struct scatterlist), GFP_KERNEL);
+ sizeof(struct scatterlist), GFP_ATOMIC);
if (!imxdmac->sg_list)
return NULL;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 17a2393..533e187 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -77,7 +77,8 @@
attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
chan = ioat_chan_by_index(instance, bit);
- tasklet_schedule(&chan->cleanup_task);
+ if (test_bit(IOAT_RUN, &chan->state))
+ tasklet_schedule(&chan->cleanup_task);
}
writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -93,7 +94,8 @@
{
struct ioat_chan_common *chan = data;
- tasklet_schedule(&chan->cleanup_task);
+ if (test_bit(IOAT_RUN, &chan->state))
+ tasklet_schedule(&chan->cleanup_task);
return IRQ_HANDLED;
}
@@ -116,7 +118,6 @@
chan->timer.function = device->timer_fn;
chan->timer.data = data;
tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
- tasklet_disable(&chan->cleanup_task);
}
/**
@@ -354,13 +355,49 @@
writel(((u64) chan->completion_dma) >> 32,
chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
- tasklet_enable(&chan->cleanup_task);
+ set_bit(IOAT_RUN, &chan->state);
ioat1_dma_start_null_desc(ioat); /* give chain to dma device */
dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
__func__, ioat->desccount);
return ioat->desccount;
}
+void ioat_stop(struct ioat_chan_common *chan)
+{
+ struct ioatdma_device *device = chan->device;
+ struct pci_dev *pdev = device->pdev;
+ int chan_id = chan_num(chan);
+ struct msix_entry *msix;
+
+ /* 1/ stop irq from firing tasklets
+ * 2/ stop the tasklet from re-arming irqs
+ */
+ clear_bit(IOAT_RUN, &chan->state);
+
+ /* flush inflight interrupts */
+ switch (device->irq_mode) {
+ case IOAT_MSIX:
+ msix = &device->msix_entries[chan_id];
+ synchronize_irq(msix->vector);
+ break;
+ case IOAT_MSI:
+ case IOAT_INTX:
+ synchronize_irq(pdev->irq);
+ break;
+ default:
+ break;
+ }
+
+ /* flush inflight timers */
+ del_timer_sync(&chan->timer);
+
+ /* flush inflight tasklet runs */
+ tasklet_kill(&chan->cleanup_task);
+
+ /* final cleanup now that everything is quiesced and can't re-arm */
+ device->cleanup_fn((unsigned long) &chan->common);
+}
+
/**
* ioat1_dma_free_chan_resources - release all the descriptors
* @chan: the channel to be cleaned
@@ -379,9 +416,7 @@
if (ioat->desccount == 0)
return;
- tasklet_disable(&chan->cleanup_task);
- del_timer_sync(&chan->timer);
- ioat1_cleanup(ioat);
+ ioat_stop(chan);
/* Delay 100ms after reset to allow internal DMA logic to quiesce
* before removing DMA descriptor resources.
@@ -526,8 +561,11 @@
static void ioat1_cleanup_event(unsigned long data)
{
struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat1_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index 54fb7b9..a1d7884 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -370,6 +370,7 @@
void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
void ioat_kobject_del(struct ioatdma_device *device);
int ioat_dma_setup_interrupts(struct ioatdma_device *device);
+void ioat_stop(struct ioat_chan_common *chan);
extern const struct sysfs_ops ioat_sysfs_ops;
extern struct ioat_sysfs_entry ioat_version_attr;
extern struct ioat_sysfs_entry ioat_cap_attr;
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index b925e1b..1cd7610 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -190,8 +190,11 @@
void ioat2_cleanup_event(unsigned long data)
{
struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat2_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
@@ -553,10 +556,10 @@
ioat->issued = 0;
ioat->tail = 0;
ioat->alloc_order = order;
+ set_bit(IOAT_RUN, &chan->state);
spin_unlock_bh(&ioat->prep_lock);
spin_unlock_bh(&chan->cleanup_lock);
- tasklet_enable(&chan->cleanup_task);
ioat2_start_null_desc(ioat);
/* check that we got off the ground */
@@ -566,7 +569,6 @@
} while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
if (is_ioat_active(status) || is_ioat_idle(status)) {
- set_bit(IOAT_RUN, &chan->state);
return 1 << ioat->alloc_order;
} else {
u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET);
@@ -809,11 +811,8 @@
if (!ioat->ring)
return;
- tasklet_disable(&chan->cleanup_task);
- del_timer_sync(&chan->timer);
- device->cleanup_fn((unsigned long) c);
+ ioat_stop(chan);
device->reset_hw(chan);
- clear_bit(IOAT_RUN, &chan->state);
spin_lock_bh(&chan->cleanup_lock);
spin_lock_bh(&ioat->prep_lock);
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c
index ca6ea9b..38b94b3 100644
--- a/drivers/dma/ioat/dma_v3.c
+++ b/drivers/dma/ioat/dma_v3.c
@@ -87,13 +87,6 @@
static const u8 pq16_idx_to_field[] = { 1, 4, 1, 2, 3, 4, 5, 6, 7,
0, 1, 2, 3, 4, 5, 6 };
-/*
- * technically sources 1 and 2 do not require SED, but the op will have
- * at least 9 descriptors so that's irrelevant.
- */
-static const u8 pq16_idx_to_sed[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 1, 1, 1, 1, 1, 1, 1 };
-
static void ioat3_eh(struct ioat2_dma_chan *ioat);
static dma_addr_t xor_get_src(struct ioat_raw_descriptor *descs[2], int idx)
@@ -135,12 +128,6 @@
pq->coef[idx] = coef;
}
-static int sed_get_pq16_pool_idx(int src_cnt)
-{
-
- return pq16_idx_to_sed[src_cnt];
-}
-
static bool is_jf_ioat(struct pci_dev *pdev)
{
switch (pdev->device) {
@@ -648,8 +635,11 @@
static void ioat3_cleanup_event(unsigned long data)
{
struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data);
+ struct ioat_chan_common *chan = &ioat->base;
ioat3_cleanup(ioat);
+ if (!test_bit(IOAT_RUN, &chan->state))
+ return;
writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
}
@@ -1182,9 +1172,6 @@
u8 op;
int i, s, idx, num_descs;
- /* this function only handles src_cnt 9 - 16 */
- BUG_ON(src_cnt < 9);
-
/* this function is only called with 9-16 sources */
op = result ? IOAT_OP_PQ_VAL_16S : IOAT_OP_PQ_16S;
@@ -1212,8 +1199,7 @@
descs[0] = (struct ioat_raw_descriptor *) pq;
- desc->sed = ioat3_alloc_sed(device,
- sed_get_pq16_pool_idx(src_cnt));
+ desc->sed = ioat3_alloc_sed(device, (src_cnt-2) >> 3);
if (!desc->sed) {
dev_err(to_dev(chan),
"%s: no free sed entries\n", __func__);
@@ -1271,13 +1257,21 @@
return &desc->txd;
}
+static int src_cnt_flags(unsigned int src_cnt, unsigned long flags)
+{
+ if (dmaf_p_disabled_continue(flags))
+ return src_cnt + 1;
+ else if (dmaf_continue(flags))
+ return src_cnt + 3;
+ else
+ return src_cnt;
+}
+
static struct dma_async_tx_descriptor *
ioat3_prep_pq(struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src,
unsigned int src_cnt, const unsigned char *scf, size_t len,
unsigned long flags)
{
- struct dma_device *dma = chan->device;
-
/* specify valid address for disabled result */
if (flags & DMA_PREP_PQ_DISABLE_P)
dst[0] = dst[1];
@@ -1297,7 +1291,7 @@
single_source_coef[0] = scf[0];
single_source_coef[1] = 0;
- return (src_cnt > 8) && (dma->max_pq > 8) ?
+ return src_cnt_flags(src_cnt, flags) > 8 ?
__ioat3_prep_pq16_lock(chan, NULL, dst, single_source,
2, single_source_coef, len,
flags) :
@@ -1305,7 +1299,7 @@
single_source_coef, len, flags);
} else {
- return (src_cnt > 8) && (dma->max_pq > 8) ?
+ return src_cnt_flags(src_cnt, flags) > 8 ?
__ioat3_prep_pq16_lock(chan, NULL, dst, src, src_cnt,
scf, len, flags) :
__ioat3_prep_pq_lock(chan, NULL, dst, src, src_cnt,
@@ -1318,8 +1312,6 @@
unsigned int src_cnt, const unsigned char *scf, size_t len,
enum sum_check_flags *pqres, unsigned long flags)
{
- struct dma_device *dma = chan->device;
-
/* specify valid address for disabled result */
if (flags & DMA_PREP_PQ_DISABLE_P)
pq[0] = pq[1];
@@ -1331,7 +1323,7 @@
*/
*pqres = 0;
- return (src_cnt > 8) && (dma->max_pq > 8) ?
+ return src_cnt_flags(src_cnt, flags) > 8 ?
__ioat3_prep_pq16_lock(chan, pqres, pq, src, src_cnt, scf, len,
flags) :
__ioat3_prep_pq_lock(chan, pqres, pq, src, src_cnt, scf, len,
@@ -1342,7 +1334,6 @@
ioat3_prep_pqxor(struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src,
unsigned int src_cnt, size_t len, unsigned long flags)
{
- struct dma_device *dma = chan->device;
unsigned char scf[src_cnt];
dma_addr_t pq[2];
@@ -1351,7 +1342,7 @@
flags |= DMA_PREP_PQ_DISABLE_Q;
pq[1] = dst; /* specify valid address for disabled result */
- return (src_cnt > 8) && (dma->max_pq > 8) ?
+ return src_cnt_flags(src_cnt, flags) > 8 ?
__ioat3_prep_pq16_lock(chan, NULL, pq, src, src_cnt, scf, len,
flags) :
__ioat3_prep_pq_lock(chan, NULL, pq, src, src_cnt, scf, len,
@@ -1363,7 +1354,6 @@
unsigned int src_cnt, size_t len,
enum sum_check_flags *result, unsigned long flags)
{
- struct dma_device *dma = chan->device;
unsigned char scf[src_cnt];
dma_addr_t pq[2];
@@ -1377,8 +1367,7 @@
flags |= DMA_PREP_PQ_DISABLE_Q;
pq[1] = pq[0]; /* specify valid address for disabled result */
-
- return (src_cnt > 8) && (dma->max_pq > 8) ?
+ return src_cnt_flags(src_cnt, flags) > 8 ?
__ioat3_prep_pq16_lock(chan, result, pq, &src[1], src_cnt - 1,
scf, len, flags) :
__ioat3_prep_pq_lock(chan, result, pq, &src[1], src_cnt - 1,
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index ec3fc4f..b94a376 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -487,6 +487,7 @@
* c->desc is NULL and exit.)
*/
if (c->desc) {
+ omap_dma_desc_free(&c->desc->vd);
c->desc = NULL;
/* Avoid stopping the dma twice */
if (!c->paused)
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index a17553f..4c2f465 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2485,10 +2485,10 @@
struct dma_pl330_chan *pch = to_pchan(chan);
unsigned long flags;
- spin_lock_irqsave(&pch->lock, flags);
-
tasklet_kill(&pch->task);
+ spin_lock_irqsave(&pch->lock, flags);
+
pl330_release_channel(pch->pl330_chid);
pch->pl330_chid = NULL;
@@ -2527,6 +2527,10 @@
/* Assign cookies to all nodes */
while (!list_empty(&last->node)) {
desc = list_entry(last->node.next, struct dma_pl330_desc, node);
+ if (pch->cyclic) {
+ desc->txd.callback = last->txd.callback;
+ desc->txd.callback_param = last->txd.callback_param;
+ }
dma_cookie_assign(&desc->txd);
@@ -2710,45 +2714,82 @@
size_t period_len, enum dma_transfer_direction direction,
unsigned long flags, void *context)
{
- struct dma_pl330_desc *desc;
+ struct dma_pl330_desc *desc = NULL, *first = NULL;
struct dma_pl330_chan *pch = to_pchan(chan);
+ struct dma_pl330_dmac *pdmac = pch->dmac;
+ unsigned int i;
dma_addr_t dst;
dma_addr_t src;
- desc = pl330_get_desc(pch);
- if (!desc) {
- dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n",
- __func__, __LINE__);
+ if (len % period_len != 0)
return NULL;
- }
- switch (direction) {
- case DMA_MEM_TO_DEV:
- desc->rqcfg.src_inc = 1;
- desc->rqcfg.dst_inc = 0;
- desc->req.rqtype = MEMTODEV;
- src = dma_addr;
- dst = pch->fifo_addr;
- break;
- case DMA_DEV_TO_MEM:
- desc->rqcfg.src_inc = 0;
- desc->rqcfg.dst_inc = 1;
- desc->req.rqtype = DEVTOMEM;
- src = pch->fifo_addr;
- dst = dma_addr;
- break;
- default:
+ if (!is_slave_direction(direction)) {
dev_err(pch->dmac->pif.dev, "%s:%d Invalid dma direction\n",
__func__, __LINE__);
return NULL;
}
- desc->rqcfg.brst_size = pch->burst_sz;
- desc->rqcfg.brst_len = 1;
+ for (i = 0; i < len / period_len; i++) {
+ desc = pl330_get_desc(pch);
+ if (!desc) {
+ dev_err(pch->dmac->pif.dev, "%s:%d Unable to fetch desc\n",
+ __func__, __LINE__);
+
+ if (!first)
+ return NULL;
+
+ spin_lock_irqsave(&pdmac->pool_lock, flags);
+
+ while (!list_empty(&first->node)) {
+ desc = list_entry(first->node.next,
+ struct dma_pl330_desc, node);
+ list_move_tail(&desc->node, &pdmac->desc_pool);
+ }
+
+ list_move_tail(&first->node, &pdmac->desc_pool);
+
+ spin_unlock_irqrestore(&pdmac->pool_lock, flags);
+
+ return NULL;
+ }
+
+ switch (direction) {
+ case DMA_MEM_TO_DEV:
+ desc->rqcfg.src_inc = 1;
+ desc->rqcfg.dst_inc = 0;
+ desc->req.rqtype = MEMTODEV;
+ src = dma_addr;
+ dst = pch->fifo_addr;
+ break;
+ case DMA_DEV_TO_MEM:
+ desc->rqcfg.src_inc = 0;
+ desc->rqcfg.dst_inc = 1;
+ desc->req.rqtype = DEVTOMEM;
+ src = pch->fifo_addr;
+ dst = dma_addr;
+ break;
+ default:
+ break;
+ }
+
+ desc->rqcfg.brst_size = pch->burst_sz;
+ desc->rqcfg.brst_len = 1;
+ fill_px(&desc->px, dst, src, period_len);
+
+ if (!first)
+ first = desc;
+ else
+ list_add_tail(&desc->node, &first->node);
+
+ dma_addr += period_len;
+ }
+
+ if (!desc)
+ return NULL;
pch->cyclic = true;
-
- fill_px(&desc->px, dst, src, period_len);
+ desc->txd.flags = flags;
return &desc->txd;
}
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 71bf4ec..ca78044 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1587,6 +1587,7 @@
struct d40_chan *d40c = (struct d40_chan *) data;
struct d40_desc *d40d;
unsigned long flags;
+ bool callback_active;
dma_async_tx_callback callback;
void *callback_param;
@@ -1614,6 +1615,7 @@
}
/* Callback to client */
+ callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT);
callback = d40d->txd.callback;
callback_param = d40d->txd.callback_param;
@@ -1636,7 +1638,7 @@
spin_unlock_irqrestore(&d40c->lock, flags);
- if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT))
+ if (callback_active && callback)
callback(callback_param);
return;
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 8b6a034..8b3d901 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2470,8 +2470,15 @@
layers[0].size = pvt->csels[0].b_cnt;
layers[0].is_virt_csrow = true;
layers[1].type = EDAC_MC_LAYER_CHANNEL;
- layers[1].size = pvt->channel_count;
+
+ /*
+ * Always allocate two channels since we can have setups with DIMMs on
+ * only one channel. Also, this simplifies handling later for the price
+ * of a couple of KBs tops.
+ */
+ layers[1].size = 2;
layers[1].is_virt_csrow = false;
+
mci = edac_mc_alloc(nid, ARRAY_SIZE(layers), layers, 0);
if (!mci)
goto err_siblings;
diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
index 7f3c571..1e08ce7 100644
--- a/drivers/edac/cpc925_edac.c
+++ b/drivers/edac/cpc925_edac.c
@@ -562,7 +562,7 @@
if (apiexcp & UECC_EXCP_DETECTED) {
cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n");
- edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+ edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
pfn, offset, 0,
csrow, -1, -1,
mci->ctl_name, "");
diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
index 644fec5..f1e9d7b 100644
--- a/drivers/edac/e752x_edac.c
+++ b/drivers/edac/e752x_edac.c
@@ -1182,9 +1182,11 @@
pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
pvt->dev_info->err_dev, pvt->bridge_ck);
- if (pvt->bridge_ck == NULL)
+ if (pvt->bridge_ck == NULL) {
pvt->bridge_ck = pci_scan_single_device(pdev->bus,
PCI_DEVFN(0, 1));
+ pci_dev_get(pvt->bridge_ck);
+ }
if (pvt->bridge_ck == NULL) {
e752x_printk(KERN_ERR, "error reporting device not found:"
diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
index 1c4056a..2697dea 100644
--- a/drivers/edac/e7xxx_edac.c
+++ b/drivers/edac/e7xxx_edac.c
@@ -226,7 +226,7 @@
static void process_ce_no_info(struct mem_ctl_info *mci)
{
edac_dbg(3, "\n");
- edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
+ edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
"e7xxx CE log register overflow", "");
}
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 27e86d9..a9d98cd 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -48,6 +48,8 @@
*/
static void const *edac_mc_owner;
+static struct bus_type mc_bus[EDAC_MAX_MCS];
+
unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned len)
{
@@ -557,7 +559,8 @@
*
* called with the mem_ctls_mutex held
*/
-static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec)
+static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
+ bool init)
{
edac_dbg(0, "\n");
@@ -565,7 +568,9 @@
if (mci->op_state != OP_RUNNING_POLL)
return;
- INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+ if (init)
+ INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function);
+
mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec));
}
@@ -599,7 +604,7 @@
* user space has updated our poll period value, need to
* reset our workq delays
*/
-void edac_mc_reset_delay_period(int value)
+void edac_mc_reset_delay_period(unsigned long value)
{
struct mem_ctl_info *mci;
struct list_head *item;
@@ -609,7 +614,7 @@
list_for_each(item, &mc_devices) {
mci = list_entry(item, struct mem_ctl_info, link);
- edac_mc_workq_setup(mci, (unsigned long) value);
+ edac_mc_workq_setup(mci, value, false);
}
mutex_unlock(&mem_ctls_mutex);
@@ -723,6 +728,11 @@
int ret = -EINVAL;
edac_dbg(0, "\n");
+ if (mci->mc_idx >= EDAC_MAX_MCS) {
+ pr_warn_once("Too many memory controllers: %d\n", mci->mc_idx);
+ return -ENODEV;
+ }
+
#ifdef CONFIG_EDAC_DEBUG
if (edac_debug_level >= 3)
edac_mc_dump_mci(mci);
@@ -762,6 +772,8 @@
/* set load time so that error rate can be tracked */
mci->start_time = jiffies;
+ mci->bus = &mc_bus[mci->mc_idx];
+
if (edac_create_sysfs_mci_device(mci)) {
edac_mc_printk(mci, KERN_WARNING,
"failed to create sysfs device\n");
@@ -773,7 +785,7 @@
/* This instance is NOW RUNNING */
mci->op_state = OP_RUNNING_POLL;
- edac_mc_workq_setup(mci, edac_mc_get_poll_msec());
+ edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true);
} else {
mci->op_state = OP_RUNNING_INTERRUPT;
}
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 67610a6..88cd940 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -52,16 +52,20 @@
static int edac_set_poll_msec(const char *val, struct kernel_param *kp)
{
- long l;
+ unsigned long l;
int ret;
if (!val)
return -EINVAL;
- ret = strict_strtol(val, 0, &l);
- if (ret == -EINVAL || ((int)l != l))
+ ret = kstrtoul(val, 0, &l);
+ if (ret)
+ return ret;
+
+ if (l < 1000)
return -EINVAL;
- *((int *)kp->arg) = l;
+
+ *((unsigned long *)kp->arg) = l;
/* notify edac_mc engine to reset the poll period */
edac_mc_reset_delay_period(l);
@@ -370,7 +374,7 @@
return -ENODEV;
csrow->dev.type = &csrow_attr_type;
- csrow->dev.bus = &mci->bus;
+ csrow->dev.bus = mci->bus;
device_initialize(&csrow->dev);
csrow->dev.parent = &mci->dev;
csrow->mci = mci;
@@ -605,7 +609,7 @@
dimm->mci = mci;
dimm->dev.type = &dimm_attr_type;
- dimm->dev.bus = &mci->bus;
+ dimm->dev.bus = mci->bus;
device_initialize(&dimm->dev);
dimm->dev.parent = &mci->dev;
@@ -975,11 +979,13 @@
* The memory controller needs its own bus, in order to avoid
* namespace conflicts at /sys/bus/edac.
*/
- mci->bus.name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
- if (!mci->bus.name)
+ mci->bus->name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx);
+ if (!mci->bus->name)
return -ENOMEM;
- edac_dbg(0, "creating bus %s\n", mci->bus.name);
- err = bus_register(&mci->bus);
+
+ edac_dbg(0, "creating bus %s\n", mci->bus->name);
+
+ err = bus_register(mci->bus);
if (err < 0)
return err;
@@ -988,7 +994,7 @@
device_initialize(&mci->dev);
mci->dev.parent = mci_pdev;
- mci->dev.bus = &mci->bus;
+ mci->dev.bus = mci->bus;
dev_set_name(&mci->dev, "mc%d", mci->mc_idx);
dev_set_drvdata(&mci->dev, mci);
pm_runtime_forbid(&mci->dev);
@@ -997,8 +1003,8 @@
err = device_add(&mci->dev);
if (err < 0) {
edac_dbg(1, "failure: create device %s\n", dev_name(&mci->dev));
- bus_unregister(&mci->bus);
- kfree(mci->bus.name);
+ bus_unregister(mci->bus);
+ kfree(mci->bus->name);
return err;
}
@@ -1064,8 +1070,8 @@
}
fail2:
device_unregister(&mci->dev);
- bus_unregister(&mci->bus);
- kfree(mci->bus.name);
+ bus_unregister(mci->bus);
+ kfree(mci->bus->name);
return err;
}
@@ -1098,8 +1104,8 @@
{
edac_dbg(1, "Unregistering device %s\n", dev_name(&mci->dev));
device_unregister(&mci->dev);
- bus_unregister(&mci->bus);
- kfree(mci->bus.name);
+ bus_unregister(mci->bus);
+ kfree(mci->bus->name);
}
static void mc_attr_release(struct device *dev)
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 3d139c6..f2118bf 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -52,7 +52,7 @@
extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev);
extern void edac_device_reset_delay_period(struct edac_device_ctl_info
*edac_dev, unsigned long value);
-extern void edac_mc_reset_delay_period(int value);
+extern void edac_mc_reset_delay_period(unsigned long value);
extern void *edac_align_ptr(void **p, unsigned size, int n_elems);
diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c
index c2bd8c6..10d3d29 100644
--- a/drivers/edac/highbank_l2_edac.c
+++ b/drivers/edac/highbank_l2_edac.c
@@ -90,28 +90,30 @@
goto err;
}
- drvdata->db_irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev, drvdata->db_irq,
- highbank_l2_err_handler,
- 0, dev_name(&pdev->dev), dci);
- if (res < 0)
- goto err;
-
- drvdata->sb_irq = platform_get_irq(pdev, 1);
- res = devm_request_irq(&pdev->dev, drvdata->sb_irq,
- highbank_l2_err_handler,
- 0, dev_name(&pdev->dev), dci);
- if (res < 0)
- goto err;
-
dci->mod_name = dev_name(&pdev->dev);
dci->dev_name = dev_name(&pdev->dev);
if (edac_device_add_device(dci))
goto err;
+ drvdata->db_irq = platform_get_irq(pdev, 0);
+ res = devm_request_irq(&pdev->dev, drvdata->db_irq,
+ highbank_l2_err_handler,
+ 0, dev_name(&pdev->dev), dci);
+ if (res < 0)
+ goto err2;
+
+ drvdata->sb_irq = platform_get_irq(pdev, 1);
+ res = devm_request_irq(&pdev->dev, drvdata->sb_irq,
+ highbank_l2_err_handler,
+ 0, dev_name(&pdev->dev), dci);
+ if (res < 0)
+ goto err2;
+
devres_close_group(&pdev->dev, NULL);
return 0;
+err2:
+ edac_device_del_device(&pdev->dev);
err:
devres_release_group(&pdev->dev, NULL);
edac_device_free_ctl_info(dci);
diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c
index 4695dd2..7a78307 100644
--- a/drivers/edac/highbank_mc_edac.c
+++ b/drivers/edac/highbank_mc_edac.c
@@ -189,14 +189,6 @@
goto err;
}
- irq = platform_get_irq(pdev, 0);
- res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler,
- 0, dev_name(&pdev->dev), mci);
- if (res < 0) {
- dev_err(&pdev->dev, "Unable to request irq %d\n", irq);
- goto err;
- }
-
mci->mtype_cap = MEM_FLAG_DDR3;
mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
mci->edac_cap = EDAC_FLAG_SECDED;
@@ -217,10 +209,20 @@
if (res < 0)
goto err;
+ irq = platform_get_irq(pdev, 0);
+ res = devm_request_irq(&pdev->dev, irq, highbank_mc_err_handler,
+ 0, dev_name(&pdev->dev), mci);
+ if (res < 0) {
+ dev_err(&pdev->dev, "Unable to request irq %d\n", irq);
+ goto err2;
+ }
+
highbank_mc_create_debugfs_nodes(mci);
devres_close_group(&pdev->dev, NULL);
return 0;
+err2:
+ edac_mc_del_mc(&pdev->dev);
err:
devres_release_group(&pdev->dev, NULL);
edac_mc_free(mci);
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index aa44c17..71b2651 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -242,11 +242,11 @@
-1, -1,
"i3000 UE", "");
} else if (log & I3200_ECCERRLOG_CE) {
- edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+ edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
0, 0, eccerrlog_syndrome(log),
eccerrlog_row(channel, log),
-1, -1,
- "i3000 UE", "");
+ "i3000 CE", "");
}
}
}
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 1b63517..157b934 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -974,7 +974,7 @@
if (!i5100_debugfs)
return -ENODEV;
- priv->debugfs = debugfs_create_dir(mci->bus.name, i5100_debugfs);
+ priv->debugfs = debugfs_create_dir(mci->bus->name, i5100_debugfs);
if (!priv->debugfs)
return -ENOMEM;
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 9004c64..841eee3 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -943,33 +943,35 @@
/* Attempt to 'get' the MCH register we want */
pdev = NULL;
- while (!pvt->pci_dev_16_1_fsb_addr_map ||
- !pvt->pci_dev_16_2_fsb_err_regs) {
- pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev);
- if (!pdev) {
- /* End of list, leave */
- i7300_printk(KERN_ERR,
- "'system address,Process Bus' "
- "device not found:"
- "vendor 0x%x device 0x%x ERR funcs "
- "(broken BIOS?)\n",
- PCI_VENDOR_ID_INTEL,
- PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
- goto error;
- }
-
+ while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_I7300_MCH_ERR,
+ pdev))) {
/* Store device 16 funcs 1 and 2 */
switch (PCI_FUNC(pdev->devfn)) {
case 1:
- pvt->pci_dev_16_1_fsb_addr_map = pdev;
+ if (!pvt->pci_dev_16_1_fsb_addr_map)
+ pvt->pci_dev_16_1_fsb_addr_map =
+ pci_dev_get(pdev);
break;
case 2:
- pvt->pci_dev_16_2_fsb_err_regs = pdev;
+ if (!pvt->pci_dev_16_2_fsb_err_regs)
+ pvt->pci_dev_16_2_fsb_err_regs =
+ pci_dev_get(pdev);
break;
}
}
+ if (!pvt->pci_dev_16_1_fsb_addr_map ||
+ !pvt->pci_dev_16_2_fsb_err_regs) {
+ /* At least one device was not found */
+ i7300_printk(KERN_ERR,
+ "'system address,Process Bus' device not found:"
+ "vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n",
+ PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_I7300_MCH_ERR);
+ goto error;
+ }
+
edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s %x:%x\n",
pci_name(pvt->pci_dev_16_0_fsb_ctlr),
pvt->pci_dev_16_0_fsb_ctlr->vendor,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 0ec3e95..271818a 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1334,14 +1334,19 @@
* is at addr 8086:2c40, instead of 8086:2c41. So, we need
* to probe for the alternate address in case of failure
*/
- if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev)
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) {
+ pci_dev_get(*prev); /* pci_get_device will put it */
pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev);
+ }
- if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev)
+ if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE &&
+ !pdev) {
+ pci_dev_get(*prev); /* pci_get_device will put it */
pdev = pci_get_device(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT,
*prev);
+ }
if (!pdev) {
if (*prev) {
diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c
index 3e3e431..b93b0d0 100644
--- a/drivers/edac/i82860_edac.c
+++ b/drivers/edac/i82860_edac.c
@@ -124,7 +124,7 @@
dimm->location[0], dimm->location[1], -1,
"i82860 UE", "");
else
- edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+ edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
info->eap, 0, info->derrsyn,
dimm->location[0], dimm->location[1], -1,
"i82860 CE", "");
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index e04462b..f505e4c 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -270,8 +270,9 @@
* sbridge structs
*/
-#define NUM_CHANNELS 4
-#define MAX_DIMMS 3 /* Max DIMMS per channel */
+#define NUM_CHANNELS 4
+#define MAX_DIMMS 3 /* Max DIMMS per channel */
+#define CHANNEL_UNSPECIFIED 0xf /* Intel IA32 SDM 15-14 */
struct sbridge_info {
u32 mcmtr;
@@ -1451,6 +1452,9 @@
/* FIXME: need support for channel mask */
+ if (channel == CHANNEL_UNSPECIFIED)
+ channel = -1;
+
/* Call the helper to output message */
edac_mc_handle_error(tp_event, mci, core_err_cnt,
m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
diff --git a/drivers/eisa/eisa-bus.c b/drivers/eisa/eisa-bus.c
index 272a3ec..0314dde 100644
--- a/drivers/eisa/eisa-bus.c
+++ b/drivers/eisa/eisa-bus.c
@@ -275,11 +275,13 @@
}
if (slot) {
+ edev->res[i].name = NULL;
edev->res[i].start = SLOT_ADDRESS(root, slot)
+ (i * 0x400);
edev->res[i].end = edev->res[i].start + 0xff;
edev->res[i].flags = IORESOURCE_IO;
} else {
+ edev->res[i].name = NULL;
edev->res[i].start = SLOT_ADDRESS(root, slot)
+ EISA_VENDOR_ID_OFFSET;
edev->res[i].end = edev->res[i].start + 3;
@@ -326,13 +328,6 @@
return -ENOMEM;
}
- if (eisa_init_device(root, edev, 0)) {
- kfree(edev);
- if (!root->force_probe)
- return -ENODEV;
- goto force_probe;
- }
-
if (eisa_request_resources(root, edev, 0)) {
dev_warn(root->dev,
"EISA: Cannot allocate resource for mainboard\n");
@@ -342,6 +337,14 @@
goto force_probe;
}
+ if (eisa_init_device(root, edev, 0)) {
+ eisa_release_resources(edev);
+ kfree(edev);
+ if (!root->force_probe)
+ return -ENODEV;
+ goto force_probe;
+ }
+
dev_info(&edev->dev, "EISA: Mainboard %s detected\n", edev->id.sig);
if (eisa_register_device(edev)) {
@@ -361,11 +364,6 @@
continue;
}
- if (eisa_init_device(root, edev, i)) {
- kfree(edev);
- continue;
- }
-
if (eisa_request_resources(root, edev, i)) {
dev_warn(root->dev,
"Cannot allocate resource for EISA slot %d\n",
@@ -374,6 +372,12 @@
continue;
}
+ if (eisa_init_device(root, edev, i)) {
+ eisa_release_resources(edev);
+ kfree(edev);
+ continue;
+ }
+
if (edev->state == (EISA_CONFIG_ENABLED | EISA_CONFIG_FORCED))
enabled_str = " (forced enabled)";
else if (edev->state == EISA_CONFIG_FORCED)
diff --git a/drivers/extcon/extcon-adc-jack.c b/drivers/extcon/extcon-adc-jack.c
index d0233cd..5985807 100644
--- a/drivers/extcon/extcon-adc-jack.c
+++ b/drivers/extcon/extcon-adc-jack.c
@@ -87,7 +87,8 @@
{
struct adc_jack_data *data = _data;
- schedule_delayed_work(&data->handler, data->handling_delay);
+ queue_delayed_work(system_power_efficient_wq,
+ &data->handler, data->handling_delay);
return IRQ_HANDLED;
}
diff --git a/drivers/extcon/extcon-gpio.c b/drivers/extcon/extcon-gpio.c
index 02bec32..f874c30 100644
--- a/drivers/extcon/extcon-gpio.c
+++ b/drivers/extcon/extcon-gpio.c
@@ -56,7 +56,7 @@
{
struct gpio_extcon_data *extcon_data = dev_id;
- schedule_delayed_work(&extcon_data->work,
+ queue_delayed_work(system_power_efficient_wq, &extcon_data->work,
extcon_data->debounce_jiffies);
return IRQ_HANDLED;
}
diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index b56bdaa..9966fc0 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -1180,7 +1180,7 @@
/* Initialize MUIC register by using platform data or default data */
- if (pdata->muic_data) {
+ if (pdata && pdata->muic_data) {
init_data = pdata->muic_data->init_data;
num_init_data = pdata->muic_data->num_init_data;
} else {
@@ -1213,7 +1213,7 @@
= init_data[i].data;
}
- if (pdata->muic_data) {
+ if (pdata && pdata->muic_data) {
struct max77693_muic_platform_data *muic_pdata = pdata->muic_data;
/*
diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c
index 67d6738..09f4a93 100644
--- a/drivers/extcon/extcon-max8997.c
+++ b/drivers/extcon/extcon-max8997.c
@@ -712,7 +712,7 @@
goto err_irq;
}
- if (pdata->muic_pdata) {
+ if (pdata && pdata->muic_pdata) {
struct max8997_muic_platform_data *muic_pdata
= pdata->muic_pdata;
diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
index 7ef316f..4f73c72 100644
--- a/drivers/firewire/core-cdev.c
+++ b/drivers/firewire/core-cdev.c
@@ -54,6 +54,7 @@
#define FW_CDEV_KERNEL_VERSION 5
#define FW_CDEV_VERSION_EVENT_REQUEST2 4
#define FW_CDEV_VERSION_ALLOCATE_REGION_END 4
+#define FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW 5
struct client {
u32 version;
@@ -1005,6 +1006,8 @@
a->channel, a->speed, a->header_size, cb, client);
if (IS_ERR(context))
return PTR_ERR(context);
+ if (client->version < FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW)
+ context->drop_overflow_headers = true;
/* We only support one context at this time. */
spin_lock_irq(&client->lock);
@@ -1634,8 +1637,7 @@
_IOC_SIZE(cmd) > sizeof(buffer))
return -ENOTTY;
- if (_IOC_DIR(cmd) == _IOC_READ)
- memset(&buffer, 0, _IOC_SIZE(cmd));
+ memset(&buffer, 0, sizeof(buffer));
if (_IOC_DIR(cmd) & _IOC_WRITE)
if (copy_from_user(&buffer, arg, _IOC_SIZE(cmd)))
diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c
index 664a6ff..392ad51 100644
--- a/drivers/firewire/core-device.c
+++ b/drivers/firewire/core-device.c
@@ -895,7 +895,7 @@
old->config_rom_retries = 0;
fw_notice(card, "rediscovered device %s\n", dev_name(dev));
- PREPARE_DELAYED_WORK(&old->work, fw_device_update);
+ old->workfn = fw_device_update;
fw_schedule_device_work(old, 0);
if (current_node == card->root_node)
@@ -1054,7 +1054,7 @@
if (atomic_cmpxchg(&device->state,
FW_DEVICE_INITIALIZING,
FW_DEVICE_RUNNING) == FW_DEVICE_GONE) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device, SHUTDOWN_DELAY);
} else {
fw_notice(card, "created device %s: GUID %08x%08x, S%d00\n",
@@ -1175,13 +1175,20 @@
dev_name(&device->device), fw_rcode_string(ret));
gone:
atomic_set(&device->state, FW_DEVICE_GONE);
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device, SHUTDOWN_DELAY);
out:
if (node_id == card->root_node->node_id)
fw_schedule_bm_work(card, 0);
}
+static void fw_device_workfn(struct work_struct *work)
+{
+ struct fw_device *device = container_of(to_delayed_work(work),
+ struct fw_device, work);
+ device->workfn(work);
+}
+
void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
{
struct fw_device *device;
@@ -1231,7 +1238,8 @@
* power-up after getting plugged in. We schedule the
* first config rom scan half a second after bus reset.
*/
- INIT_DELAYED_WORK(&device->work, fw_device_init);
+ device->workfn = fw_device_init;
+ INIT_DELAYED_WORK(&device->work, fw_device_workfn);
fw_schedule_device_work(device, INITIAL_DELAY);
break;
@@ -1247,7 +1255,7 @@
if (atomic_cmpxchg(&device->state,
FW_DEVICE_RUNNING,
FW_DEVICE_INITIALIZING) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_refresh);
+ device->workfn = fw_device_refresh;
fw_schedule_device_work(device,
device->is_local ? 0 : INITIAL_DELAY);
}
@@ -1262,7 +1270,7 @@
smp_wmb(); /* update node_id before generation */
device->generation = card->generation;
if (atomic_read(&device->state) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_update);
+ device->workfn = fw_device_update;
fw_schedule_device_work(device, 0);
}
break;
@@ -1287,7 +1295,7 @@
device = node->data;
if (atomic_xchg(&device->state,
FW_DEVICE_GONE) == FW_DEVICE_RUNNING) {
- PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown);
+ device->workfn = fw_device_shutdown;
fw_schedule_device_work(device,
list_empty(&card->link) ? 0 : SHUTDOWN_DELAY);
}
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 815b0fc..7bdb6fe6 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -929,8 +929,6 @@
if (rcode == RCODE_COMPLETE) {
fwnet_transmit_packet_done(ptask);
} else {
- fwnet_transmit_packet_failed(ptask);
-
if (printk_timed_ratelimit(&j, 1000) || rcode != last_rcode) {
dev_err(&ptask->dev->netdev->dev,
"fwnet_write_complete failed: %x (skipped %d)\n",
@@ -938,8 +936,10 @@
errors_skipped = 0;
last_rcode = rcode;
- } else
+ } else {
errors_skipped++;
+ }
+ fwnet_transmit_packet_failed(ptask);
}
}
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 9e1db64..0f3e304 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -271,6 +271,7 @@
static char ohci_driver_name[] = KBUILD_MODNAME;
+#define PCI_VENDOR_ID_PINNACLE_SYSTEMS 0x11bd
#define PCI_DEVICE_ID_AGERE_FW643 0x5901
#define PCI_DEVICE_ID_CREATIVE_SB1394 0x4001
#define PCI_DEVICE_ID_JMICRON_JMB38X_FW 0x2380
@@ -278,17 +279,15 @@
#define PCI_DEVICE_ID_TI_TSB12LV26 0x8020
#define PCI_DEVICE_ID_TI_TSB82AA2 0x8025
#define PCI_DEVICE_ID_VIA_VT630X 0x3044
-#define PCI_VENDOR_ID_PINNACLE_SYSTEMS 0x11bd
#define PCI_REV_ID_VIA_VT6306 0x46
-#define QUIRK_CYCLE_TIMER 1
-#define QUIRK_RESET_PACKET 2
-#define QUIRK_BE_HEADERS 4
-#define QUIRK_NO_1394A 8
-#define QUIRK_NO_MSI 16
-#define QUIRK_TI_SLLZ059 32
-#define QUIRK_IR_WAKE 64
-#define QUIRK_PHY_LCTRL_TIMEOUT 128
+#define QUIRK_CYCLE_TIMER 0x1
+#define QUIRK_RESET_PACKET 0x2
+#define QUIRK_BE_HEADERS 0x4
+#define QUIRK_NO_1394A 0x8
+#define QUIRK_NO_MSI 0x10
+#define QUIRK_TI_SLLZ059 0x20
+#define QUIRK_IR_WAKE 0x40
/* In case of multiple matches in ohci_quirks[], only the first one is used. */
static const struct {
@@ -301,10 +300,7 @@
QUIRK_BE_HEADERS},
{PCI_VENDOR_ID_ATT, PCI_DEVICE_ID_AGERE_FW643, 6,
- QUIRK_PHY_LCTRL_TIMEOUT | QUIRK_NO_MSI},
-
- {PCI_VENDOR_ID_ATT, PCI_ANY_ID, PCI_ANY_ID,
- QUIRK_PHY_LCTRL_TIMEOUT},
+ QUIRK_NO_MSI},
{PCI_VENDOR_ID_CREATIVE, PCI_DEVICE_ID_CREATIVE_SB1394, PCI_ANY_ID,
QUIRK_RESET_PACKET},
@@ -351,7 +347,6 @@
", disable MSI = " __stringify(QUIRK_NO_MSI)
", TI SLLZ059 erratum = " __stringify(QUIRK_TI_SLLZ059)
", IR wake unreliable = " __stringify(QUIRK_IR_WAKE)
- ", phy LCtrl timeout = " __stringify(QUIRK_PHY_LCTRL_TIMEOUT)
")");
#define OHCI_PARAM_DEBUG_AT_AR 1
@@ -2293,9 +2288,6 @@
* TI TSB82AA2 + TSB81BA3(A) cards signal LPS enabled early but
* cannot actually use the phy at that time. These need tens of
* millisecods pause between LPS write and first phy access too.
- *
- * But do not wait for 50msec on Agere/LSI cards. Their phy
- * arbitration state machine may time out during such a long wait.
*/
reg_write(ohci, OHCI1394_HCControlSet,
@@ -2303,11 +2295,8 @@
OHCI1394_HCControl_postedWriteEnable);
flush_writes(ohci);
- if (!(ohci->quirks & QUIRK_PHY_LCTRL_TIMEOUT))
+ for (lps = 0, i = 0; !lps && i < 3; i++) {
msleep(50);
-
- for (lps = 0, i = 0; !lps && i < 150; i++) {
- msleep(1);
lps = reg_read(ohci, OHCI1394_HCControlSet) &
OHCI1394_HCControl_LPS;
}
@@ -2749,8 +2738,11 @@
{
u32 *ctx_hdr;
- if (ctx->header_length + ctx->base.header_size > PAGE_SIZE)
+ if (ctx->header_length + ctx->base.header_size > PAGE_SIZE) {
+ if (ctx->base.drop_overflow_headers)
+ return;
flush_iso_completions(ctx);
+ }
ctx_hdr = ctx->header + ctx->header_length;
ctx->last_timestamp = (u16)le32_to_cpu((__force __le32)dma_hdr[0]);
@@ -2910,8 +2902,11 @@
sync_it_packet_for_cpu(context, d);
- if (ctx->header_length + 4 > PAGE_SIZE)
+ if (ctx->header_length + 4 > PAGE_SIZE) {
+ if (ctx->base.drop_overflow_headers)
+ return 1;
flush_iso_completions(ctx);
+ }
ctx_hdr = ctx->header + ctx->header_length;
ctx->last_timestamp = le16_to_cpu(last->res_count);
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index 47674b9..1b1c37d 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -146,6 +146,7 @@
*/
int generation;
int retries;
+ work_func_t workfn;
struct delayed_work work;
bool has_sdev;
bool blocked;
@@ -864,7 +865,7 @@
/* set appropriate retry limit(s) in BUSY_TIMEOUT register */
sbp2_set_busy_timeout(lu);
- PREPARE_DELAYED_WORK(&lu->work, sbp2_reconnect);
+ lu->workfn = sbp2_reconnect;
sbp2_agent_reset(lu);
/* This was a re-login. */
@@ -918,7 +919,7 @@
* If a bus reset happened, sbp2_update will have requeued
* lu->work already. Reset the work from reconnect to login.
*/
- PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
}
static void sbp2_reconnect(struct work_struct *work)
@@ -952,7 +953,7 @@
lu->retries++ >= 5) {
dev_err(tgt_dev(tgt), "failed to reconnect\n");
lu->retries = 0;
- PREPARE_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
}
sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5));
@@ -972,6 +973,13 @@
sbp2_conditionally_unblock(lu);
}
+static void sbp2_lu_workfn(struct work_struct *work)
+{
+ struct sbp2_logical_unit *lu = container_of(to_delayed_work(work),
+ struct sbp2_logical_unit, work);
+ lu->workfn(work);
+}
+
static int sbp2_add_logical_unit(struct sbp2_target *tgt, int lun_entry)
{
struct sbp2_logical_unit *lu;
@@ -998,7 +1006,8 @@
lu->blocked = false;
++tgt->dont_block;
INIT_LIST_HEAD(&lu->orb_list);
- INIT_DELAYED_WORK(&lu->work, sbp2_login);
+ lu->workfn = sbp2_login;
+ INIT_DELAYED_WORK(&lu->work, sbp2_lu_workfn);
list_add_tail(&lu->link, &tgt->lu_list);
return 0;
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index b95159b..eb760a2 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -551,9 +551,15 @@
int s = dmi->matches[i].slot;
if (s == DMI_NONE)
break;
- if (dmi_ident[s]
- && strstr(dmi_ident[s], dmi->matches[i].substr))
- continue;
+ if (dmi_ident[s]) {
+ if (!dmi->matches[i].exact_match &&
+ strstr(dmi_ident[s], dmi->matches[i].substr))
+ continue;
+ else if (dmi->matches[i].exact_match &&
+ !strcmp(dmi_ident[s], dmi->matches[i].substr))
+ continue;
+ }
+
/* No match */
return false;
}
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index b0fc7c7..0d32596 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -36,4 +36,11 @@
backend for pstore by default. This setting can be overridden
using the efivars module's pstore_disable parameter.
+config EFI_PARAMS_FROM_FDT
+ bool
+ help
+ Select this config option from the architecture Kconfig if
+ the EFI runtime support gets system table address, memory
+ map address, and other parameters from the device tree.
+
endmenu
diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/arm-stub.c
new file mode 100644
index 0000000..41114ce
--- /dev/null
+++ b/drivers/firmware/efi/arm-stub.c
@@ -0,0 +1,278 @@
+/*
+ * EFI stub implementation that is shared by arm and arm64 architectures.
+ * This should be #included by the EFI stub implementation files.
+ *
+ * Copyright (C) 2013,2014 Linaro Limited
+ * Roy Franz <roy.franz@linaro.org
+ * Copyright (C) 2013 Red Hat, Inc.
+ * Mark Salter <msalter@redhat.com>
+ *
+ * This file is part of the Linux kernel, and is made available under the
+ * terms of the GNU General Public License version 2.
+ *
+ */
+
+static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg)
+{
+ static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID;
+ static efi_char16_t const var_name[] __initconst = {
+ 'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 };
+
+ efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable;
+ unsigned long size = sizeof(u8);
+ efi_status_t status;
+ u8 val;
+
+ status = f_getvar((efi_char16_t *)var_name, (efi_guid_t *)&var_guid,
+ NULL, &size, &val);
+
+ switch (status) {
+ case EFI_SUCCESS:
+ return val;
+ case EFI_NOT_FOUND:
+ return 0;
+ default:
+ return 1;
+ }
+}
+
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+ void *__image, void **__fh)
+{
+ efi_file_io_interface_t *io;
+ efi_loaded_image_t *image = __image;
+ efi_file_handle_t *fh;
+ efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+ efi_status_t status;
+ void *handle = (void *)(unsigned long)image->device_handle;
+
+ status = sys_table_arg->boottime->handle_protocol(handle,
+ &fs_proto, (void **)&io);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+ return status;
+ }
+
+ status = io->open_volume(io, &fh);
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table_arg, "Failed to open volume\n");
+
+ *__fh = fh;
+ return status;
+}
+static efi_status_t efi_file_close(void *handle)
+{
+ efi_file_handle_t *fh = handle;
+
+ return fh->close(handle);
+}
+
+static efi_status_t
+efi_file_read(void *handle, unsigned long *size, void *addr)
+{
+ efi_file_handle_t *fh = handle;
+
+ return fh->read(handle, size, addr);
+}
+
+
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
+ efi_char16_t *filename_16, void **handle, u64 *file_sz)
+{
+ efi_file_handle_t *h, *fh = __fh;
+ efi_file_info_t *info;
+ efi_status_t status;
+ efi_guid_t info_guid = EFI_FILE_INFO_ID;
+ unsigned long info_sz;
+
+ status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to open file: ");
+ efi_char16_printk(sys_table_arg, filename_16);
+ efi_printk(sys_table_arg, "\n");
+ return status;
+ }
+
+ *handle = h;
+
+ info_sz = 0;
+ status = h->get_info(h, &info_guid, &info_sz, NULL);
+ if (status != EFI_BUFFER_TOO_SMALL) {
+ efi_printk(sys_table_arg, "Failed to get file info size\n");
+ return status;
+ }
+
+grow:
+ status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA,
+ info_sz, (void **)&info);
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
+ return status;
+ }
+
+ status = h->get_info(h, &info_guid, &info_sz,
+ info);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ sys_table_arg->boottime->free_pool(info);
+ goto grow;
+ }
+
+ *file_sz = info->file_size;
+ sys_table_arg->boottime->free_pool(info);
+
+ if (status != EFI_SUCCESS)
+ efi_printk(sys_table_arg, "Failed to get initrd info\n");
+
+ return status;
+}
+
+
+
+static void efi_char16_printk(efi_system_table_t *sys_table_arg,
+ efi_char16_t *str)
+{
+ struct efi_simple_text_output_protocol *out;
+
+ out = (struct efi_simple_text_output_protocol *)sys_table_arg->con_out;
+ out->output_string(out, str);
+}
+
+
+/*
+ * This function handles the architcture specific differences between arm and
+ * arm64 regarding where the kernel image must be loaded and any memory that
+ * must be reserved. On failure it is required to free all
+ * all allocations it has made.
+ */
+static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+ unsigned long *image_addr,
+ unsigned long *image_size,
+ unsigned long *reserve_addr,
+ unsigned long *reserve_size,
+ unsigned long dram_base,
+ efi_loaded_image_t *image);
+/*
+ * EFI entry point for the arm/arm64 EFI stubs. This is the entrypoint
+ * that is described in the PE/COFF header. Most of the code is the same
+ * for both archictectures, with the arch-specific code provided in the
+ * handle_kernel_image() function.
+ */
+unsigned long __init efi_entry(void *handle, efi_system_table_t *sys_table,
+ unsigned long *image_addr)
+{
+ efi_loaded_image_t *image;
+ efi_status_t status;
+ unsigned long image_size = 0;
+ unsigned long dram_base;
+ /* addr/point and size pairs for memory management*/
+ unsigned long initrd_addr;
+ u64 initrd_size = 0;
+ unsigned long fdt_addr = 0; /* Original DTB */
+ u64 fdt_size = 0; /* We don't get size from configuration table */
+ char *cmdline_ptr = NULL;
+ int cmdline_size = 0;
+ unsigned long new_fdt_addr;
+ efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID;
+ unsigned long reserve_addr = 0;
+ unsigned long reserve_size = 0;
+
+ /* Check if we were booted by the EFI firmware */
+ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+ goto fail;
+
+ pr_efi(sys_table, "Booting Linux Kernel...\n");
+
+ /*
+ * Get a handle to the loaded image protocol. This is used to get
+ * information about the running image, such as size and the command
+ * line.
+ */
+ status = sys_table->boottime->handle_protocol(handle,
+ &loaded_image_proto, (void *)&image);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Failed to get loaded image protocol\n");
+ goto fail;
+ }
+
+ dram_base = get_dram_base(sys_table);
+ if (dram_base == EFI_ERROR) {
+ pr_efi_err(sys_table, "Failed to find DRAM base\n");
+ goto fail;
+ }
+ status = handle_kernel_image(sys_table, image_addr, &image_size,
+ &reserve_addr,
+ &reserve_size,
+ dram_base, image);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Failed to relocate kernel\n");
+ goto fail;
+ }
+
+ /*
+ * Get the command line from EFI, using the LOADED_IMAGE
+ * protocol. We are going to copy the command line into the
+ * device tree, so this can be allocated anywhere.
+ */
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size);
+ if (!cmdline_ptr) {
+ pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n");
+ goto fail_free_image;
+ }
+
+ /*
+ * Unauthenticated device tree data is a security hazard, so
+ * ignore 'dtb=' unless UEFI Secure Boot is disabled.
+ */
+ if (efi_secureboot_enabled(sys_table)) {
+ pr_efi(sys_table, "UEFI Secure Boot is enabled.\n");
+ } else {
+ status = handle_cmdline_files(sys_table, image, cmdline_ptr,
+ "dtb=",
+ ~0UL, (unsigned long *)&fdt_addr,
+ (unsigned long *)&fdt_size);
+
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Failed to load device tree!\n");
+ goto fail_free_cmdline;
+ }
+ }
+ if (!fdt_addr)
+ /* Look for a device tree configuration table entry. */
+ fdt_addr = (uintptr_t)get_fdt(sys_table);
+
+ status = handle_cmdline_files(sys_table, image, cmdline_ptr,
+ "initrd=", dram_base + SZ_512M,
+ (unsigned long *)&initrd_addr,
+ (unsigned long *)&initrd_size);
+ if (status != EFI_SUCCESS)
+ pr_efi_err(sys_table, "Failed initrd from command line!\n");
+
+ new_fdt_addr = fdt_addr;
+ status = allocate_new_fdt_and_exit_boot(sys_table, handle,
+ &new_fdt_addr, dram_base + MAX_FDT_OFFSET,
+ initrd_addr, initrd_size, cmdline_ptr,
+ fdt_addr, fdt_size);
+
+ /*
+ * If all went well, we need to return the FDT address to the
+ * calling function so it can be passed to kernel as part of
+ * the kernel boot protocol.
+ */
+ if (status == EFI_SUCCESS)
+ return new_fdt_addr;
+
+ pr_efi_err(sys_table, "Failed to update FDT and exit boot services\n");
+
+ efi_free(sys_table, initrd_size, initrd_addr);
+ efi_free(sys_table, fdt_size, fdt_addr);
+
+fail_free_cmdline:
+ efi_free(sys_table, cmdline_size, (unsigned long)cmdline_ptr);
+
+fail_free_image:
+ efi_free(sys_table, image_size, *image_addr);
+ efi_free(sys_table, reserve_size, reserve_addr);
+fail:
+ return EFI_ERROR;
+}
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 202d2c8..fb3a2c1f 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -18,14 +18,12 @@
static int efi_pstore_open(struct pstore_info *psi)
{
- efivar_entry_iter_begin();
psi->data = NULL;
return 0;
}
static int efi_pstore_close(struct pstore_info *psi)
{
- efivar_entry_iter_end();
psi->data = NULL;
return 0;
}
@@ -38,6 +36,12 @@
char **buf;
};
+static inline u64 generic_id(unsigned long timestamp,
+ unsigned int part, int count)
+{
+ return (timestamp * 100 + part) * 1000 + count;
+}
+
static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
{
efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
@@ -56,7 +60,7 @@
if (sscanf(name, "dump-type%u-%u-%d-%lu",
cb_data->type, &part, &cnt, &time) == 4) {
- *cb_data->id = part;
+ *cb_data->id = generic_id(time, part, cnt);
*cb_data->count = cnt;
cb_data->timespec->tv_sec = time;
cb_data->timespec->tv_nsec = 0;
@@ -67,7 +71,7 @@
* which doesn't support holding
* multiple logs, remains.
*/
- *cb_data->id = part;
+ *cb_data->id = generic_id(time, part, 0);
*cb_data->count = 0;
cb_data->timespec->tv_sec = time;
cb_data->timespec->tv_nsec = 0;
@@ -78,19 +82,124 @@
__efivar_entry_get(entry, &entry->var.Attributes,
&entry->var.DataSize, entry->var.Data);
size = entry->var.DataSize;
+ memcpy(*cb_data->buf, entry->var.Data,
+ (size_t)min_t(unsigned long, EFIVARS_DATA_SIZE_MAX, size));
- *cb_data->buf = kmalloc(size, GFP_KERNEL);
- if (*cb_data->buf == NULL)
- return -ENOMEM;
- memcpy(*cb_data->buf, entry->var.Data, size);
return size;
}
+/**
+ * efi_pstore_scan_sysfs_enter
+ * @entry: scanning entry
+ * @next: next entry
+ * @head: list head
+ */
+static void efi_pstore_scan_sysfs_enter(struct efivar_entry *pos,
+ struct efivar_entry *next,
+ struct list_head *head)
+{
+ pos->scanning = true;
+ if (&next->list != head)
+ next->scanning = true;
+}
+
+/**
+ * __efi_pstore_scan_sysfs_exit
+ * @entry: deleting entry
+ * @turn_off_scanning: Check if a scanning flag should be turned off
+ */
+static inline void __efi_pstore_scan_sysfs_exit(struct efivar_entry *entry,
+ bool turn_off_scanning)
+{
+ if (entry->deleting) {
+ list_del(&entry->list);
+ efivar_entry_iter_end();
+ efivar_unregister(entry);
+ efivar_entry_iter_begin();
+ } else if (turn_off_scanning)
+ entry->scanning = false;
+}
+
+/**
+ * efi_pstore_scan_sysfs_exit
+ * @pos: scanning entry
+ * @next: next entry
+ * @head: list head
+ * @stop: a flag checking if scanning will stop
+ */
+static void efi_pstore_scan_sysfs_exit(struct efivar_entry *pos,
+ struct efivar_entry *next,
+ struct list_head *head, bool stop)
+{
+ __efi_pstore_scan_sysfs_exit(pos, true);
+ if (stop)
+ __efi_pstore_scan_sysfs_exit(next, &next->list != head);
+}
+
+/**
+ * efi_pstore_sysfs_entry_iter
+ *
+ * @data: function-specific data to pass to callback
+ * @pos: entry to begin iterating from
+ *
+ * You MUST call efivar_enter_iter_begin() before this function, and
+ * efivar_entry_iter_end() afterwards.
+ *
+ * It is possible to begin iteration from an arbitrary entry within
+ * the list by passing @pos. @pos is updated on return to point to
+ * the next entry of the last one passed to efi_pstore_read_func().
+ * To begin iterating from the beginning of the list @pos must be %NULL.
+ */
+static int efi_pstore_sysfs_entry_iter(void *data, struct efivar_entry **pos)
+{
+ struct efivar_entry *entry, *n;
+ struct list_head *head = &efivar_sysfs_list;
+ int size = 0;
+
+ if (!*pos) {
+ list_for_each_entry_safe(entry, n, head, list) {
+ efi_pstore_scan_sysfs_enter(entry, n, head);
+
+ size = efi_pstore_read_func(entry, data);
+ efi_pstore_scan_sysfs_exit(entry, n, head, size < 0);
+ if (size)
+ break;
+ }
+ *pos = n;
+ return size;
+ }
+
+ list_for_each_entry_safe_from((*pos), n, head, list) {
+ efi_pstore_scan_sysfs_enter((*pos), n, head);
+
+ size = efi_pstore_read_func((*pos), data);
+ efi_pstore_scan_sysfs_exit((*pos), n, head, size < 0);
+ if (size)
+ break;
+ }
+ *pos = n;
+ return size;
+}
+
+/**
+ * efi_pstore_read
+ *
+ * This function returns a size of NVRAM entry logged via efi_pstore_write().
+ * The meaning and behavior of efi_pstore/pstore are as below.
+ *
+ * size > 0: Got data of an entry logged via efi_pstore_write() successfully,
+ * and pstore filesystem will continue reading subsequent entries.
+ * size == 0: Entry was not logged via efi_pstore_write(),
+ * and efi_pstore driver will continue reading subsequent entries.
+ * size < 0: Failed to get data of entry logging via efi_pstore_write(),
+ * and pstore will stop reading entry.
+ */
static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
int *count, struct timespec *timespec,
char **buf, struct pstore_info *psi)
{
struct pstore_read_data data;
+ ssize_t size;
data.id = id;
data.type = type;
@@ -98,8 +207,17 @@
data.timespec = timespec;
data.buf = buf;
- return __efivar_entry_iter(efi_pstore_read_func, &efivar_sysfs_list, &data,
- (struct efivar_entry **)&psi->data);
+ *data.buf = kzalloc(EFIVARS_DATA_SIZE_MAX, GFP_KERNEL);
+ if (!*data.buf)
+ return -ENOMEM;
+
+ efivar_entry_iter_begin();
+ size = efi_pstore_sysfs_entry_iter(&data,
+ (struct efivar_entry **)&psi->data);
+ efivar_entry_iter_end();
+ if (size <= 0)
+ kfree(*data.buf);
+ return size;
}
static int efi_pstore_write(enum pstore_type_id type,
@@ -170,9 +288,17 @@
return 0;
}
+ if (entry->scanning) {
+ /*
+ * Skip deletion because this entry will be deleted
+ * after scanning is completed.
+ */
+ entry->deleting = true;
+ } else
+ list_del(&entry->list);
+
/* found */
__efivar_entry_delete(entry);
- list_del(&entry->list);
return 1;
}
@@ -185,14 +311,16 @@
char name[DUMP_NAME_LEN];
efi_char16_t efi_name[DUMP_NAME_LEN];
int found, i;
+ unsigned int part;
- sprintf(name, "dump-type%u-%u-%d-%lu", type, (unsigned int)id, count,
- time.tv_sec);
+ do_div(id, 1000);
+ part = do_div(id, 100);
+ sprintf(name, "dump-type%u-%u-%d-%lu", type, part, count, time.tv_sec);
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
- edata.id = id;
+ edata.id = part;
edata.type = type;
edata.count = count;
edata.time = time;
@@ -200,10 +328,12 @@
efivar_entry_iter_begin();
found = __efivar_entry_iter(efi_pstore_erase_func, &efivar_sysfs_list, &edata, &entry);
- efivar_entry_iter_end();
- if (found)
+ if (found && !entry->scanning) {
+ efivar_entry_iter_end();
efivar_unregister(entry);
+ } else
+ efivar_entry_iter_end();
return 0;
}
@@ -236,7 +366,11 @@
efi_pstore_info.bufsize = 1024;
spin_lock_init(&efi_pstore_info.buf_lock);
- pstore_register(&efi_pstore_info);
+ if (pstore_register(&efi_pstore_info)) {
+ kfree(efi_pstore_info.buf);
+ efi_pstore_info.buf = NULL;
+ efi_pstore_info.bufsize = 0;
+ }
return 0;
}
diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c
new file mode 100644
index 0000000..eb6d4be
--- /dev/null
+++ b/drivers/firmware/efi/efi-stub-helper.c
@@ -0,0 +1,634 @@
+/*
+ * Helper functions used by the EFI stub on multiple
+ * architectures. This should be #included by the EFI stub
+ * implementation files.
+ *
+ * Copyright 2011 Intel Corporation; author Matt Fleming
+ *
+ * This file is part of the Linux kernel, and is made available
+ * under the terms of the GNU General Public License version 2.
+ *
+ */
+#define EFI_READ_CHUNK_SIZE (1024 * 1024)
+
+/* error code which can't be mistaken for valid address */
+#define EFI_ERROR (~0UL)
+
+
+struct file_info {
+ efi_file_handle_t *handle;
+ u64 size;
+};
+
+static void efi_printk(efi_system_table_t *sys_table_arg, char *str)
+{
+ char *s8;
+
+ for (s8 = str; *s8; s8++) {
+ efi_char16_t ch[2] = { 0 };
+
+ ch[0] = *s8;
+ if (*s8 == '\n') {
+ efi_char16_t nl[2] = { '\r', 0 };
+ efi_char16_printk(sys_table_arg, nl);
+ }
+
+ efi_char16_printk(sys_table_arg, ch);
+ }
+}
+
+#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg)
+#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
+
+
+static efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
+ efi_memory_desc_t **map,
+ unsigned long *map_size,
+ unsigned long *desc_size,
+ u32 *desc_ver,
+ unsigned long *key_ptr)
+{
+ efi_memory_desc_t *m = NULL;
+ efi_status_t status;
+ unsigned long key;
+ u32 desc_version;
+
+ *map_size = sizeof(*m) * 32;
+again:
+ /*
+ * Add an additional efi_memory_desc_t because we're doing an
+ * allocation which may be in a new descriptor region.
+ */
+ *map_size += sizeof(*m);
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ *map_size, (void **)&m);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ *desc_size = 0;
+ key = 0;
+ status = efi_call_early(get_memory_map, map_size, m,
+ &key, desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_early(free_pool, m);
+ goto again;
+ }
+
+ if (status != EFI_SUCCESS)
+ efi_call_early(free_pool, m);
+
+ if (key_ptr && status == EFI_SUCCESS)
+ *key_ptr = key;
+ if (desc_ver && status == EFI_SUCCESS)
+ *desc_ver = desc_version;
+
+fail:
+ *map = m;
+ return status;
+}
+
+
+static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg)
+{
+ efi_status_t status;
+ unsigned long map_size;
+ unsigned long membase = EFI_ERROR;
+ struct efi_memory_map map;
+ efi_memory_desc_t *md;
+
+ status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
+ &map_size, &map.desc_size, NULL, NULL);
+ if (status != EFI_SUCCESS)
+ return membase;
+
+ map.map_end = map.map + map_size;
+
+ for_each_efi_memory_desc(&map, md)
+ if (md->attribute & EFI_MEMORY_WB)
+ if (membase > md->phys_addr)
+ membase = md->phys_addr;
+
+ efi_call_early(free_pool, map.map);
+
+ return membase;
+}
+
+/*
+ * Allocate at the highest possible address that is not above 'max'.
+ */
+static efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
+ unsigned long size, unsigned long align,
+ unsigned long *addr, unsigned long max)
+{
+ unsigned long map_size, desc_size;
+ efi_memory_desc_t *map;
+ efi_status_t status;
+ unsigned long nr_pages;
+ u64 max_addr = 0;
+ int i;
+
+ status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
+ NULL, NULL);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ /*
+ * Enforce minimum alignment that EFI requires when requesting
+ * a specific address. We are doing page-based allocations,
+ * so we must be aligned to a page.
+ */
+ if (align < EFI_PAGE_SIZE)
+ align = EFI_PAGE_SIZE;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+again:
+ for (i = 0; i < map_size / desc_size; i++) {
+ efi_memory_desc_t *desc;
+ unsigned long m = (unsigned long)map;
+ u64 start, end;
+
+ desc = (efi_memory_desc_t *)(m + (i * desc_size));
+ if (desc->type != EFI_CONVENTIONAL_MEMORY)
+ continue;
+
+ if (desc->num_pages < nr_pages)
+ continue;
+
+ start = desc->phys_addr;
+ end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+ if ((start + size) > end || (start + size) > max)
+ continue;
+
+ if (end - size > max)
+ end = max;
+
+ if (round_down(end - size, align) < start)
+ continue;
+
+ start = round_down(end - size, align);
+
+ /*
+ * Don't allocate at 0x0. It will confuse code that
+ * checks pointers against NULL.
+ */
+ if (start == 0x0)
+ continue;
+
+ if (start > max_addr)
+ max_addr = start;
+ }
+
+ if (!max_addr)
+ status = EFI_NOT_FOUND;
+ else {
+ status = efi_call_early(allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &max_addr);
+ if (status != EFI_SUCCESS) {
+ max = max_addr;
+ max_addr = 0;
+ goto again;
+ }
+
+ *addr = max_addr;
+ }
+
+ efi_call_early(free_pool, map);
+fail:
+ return status;
+}
+
+/*
+ * Allocate at the lowest possible address.
+ */
+static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
+ unsigned long size, unsigned long align,
+ unsigned long *addr)
+{
+ unsigned long map_size, desc_size;
+ efi_memory_desc_t *map;
+ efi_status_t status;
+ unsigned long nr_pages;
+ int i;
+
+ status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
+ NULL, NULL);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ /*
+ * Enforce minimum alignment that EFI requires when requesting
+ * a specific address. We are doing page-based allocations,
+ * so we must be aligned to a page.
+ */
+ if (align < EFI_PAGE_SIZE)
+ align = EFI_PAGE_SIZE;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ for (i = 0; i < map_size / desc_size; i++) {
+ efi_memory_desc_t *desc;
+ unsigned long m = (unsigned long)map;
+ u64 start, end;
+
+ desc = (efi_memory_desc_t *)(m + (i * desc_size));
+
+ if (desc->type != EFI_CONVENTIONAL_MEMORY)
+ continue;
+
+ if (desc->num_pages < nr_pages)
+ continue;
+
+ start = desc->phys_addr;
+ end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+ /*
+ * Don't allocate at 0x0. It will confuse code that
+ * checks pointers against NULL. Skip the first 8
+ * bytes so we start at a nice even number.
+ */
+ if (start == 0x0)
+ start += 8;
+
+ start = round_up(start, align);
+ if ((start + size) > end)
+ continue;
+
+ status = efi_call_early(allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &start);
+ if (status == EFI_SUCCESS) {
+ *addr = start;
+ break;
+ }
+ }
+
+ if (i == map_size / desc_size)
+ status = EFI_NOT_FOUND;
+
+ efi_call_early(free_pool, map);
+fail:
+ return status;
+}
+
+static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
+ unsigned long addr)
+{
+ unsigned long nr_pages;
+
+ if (!size)
+ return;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ efi_call_early(free_pages, addr, nr_pages);
+}
+
+
+/*
+ * Check the cmdline for a LILO-style file= arguments.
+ *
+ * We only support loading a file from the same filesystem as
+ * the kernel image.
+ */
+static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
+ efi_loaded_image_t *image,
+ char *cmd_line, char *option_string,
+ unsigned long max_addr,
+ unsigned long *load_addr,
+ unsigned long *load_size)
+{
+ struct file_info *files;
+ unsigned long file_addr;
+ u64 file_size_total;
+ efi_file_handle_t *fh = NULL;
+ efi_status_t status;
+ int nr_files;
+ char *str;
+ int i, j, k;
+
+ file_addr = 0;
+ file_size_total = 0;
+
+ str = cmd_line;
+
+ j = 0; /* See close_handles */
+
+ if (!load_addr || !load_size)
+ return EFI_INVALID_PARAMETER;
+
+ *load_addr = 0;
+ *load_size = 0;
+
+ if (!str || !*str)
+ return EFI_SUCCESS;
+
+ for (nr_files = 0; *str; nr_files++) {
+ str = strstr(str, option_string);
+ if (!str)
+ break;
+
+ str += strlen(option_string);
+
+ /* Skip any leading slashes */
+ while (*str == '/' || *str == '\\')
+ str++;
+
+ while (*str && *str != ' ' && *str != '\n')
+ str++;
+ }
+
+ if (!nr_files)
+ return EFI_SUCCESS;
+
+ status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+ nr_files * sizeof(*files), (void **)&files);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg, "Failed to alloc mem for file handle list\n");
+ goto fail;
+ }
+
+ str = cmd_line;
+ for (i = 0; i < nr_files; i++) {
+ struct file_info *file;
+ efi_char16_t filename_16[256];
+ efi_char16_t *p;
+
+ str = strstr(str, option_string);
+ if (!str)
+ break;
+
+ str += strlen(option_string);
+
+ file = &files[i];
+ p = filename_16;
+
+ /* Skip any leading slashes */
+ while (*str == '/' || *str == '\\')
+ str++;
+
+ while (*str && *str != ' ' && *str != '\n') {
+ if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16))
+ break;
+
+ if (*str == '/') {
+ *p++ = '\\';
+ str++;
+ } else {
+ *p++ = *str++;
+ }
+ }
+
+ *p = '\0';
+
+ /* Only open the volume once. */
+ if (!i) {
+ status = efi_open_volume(sys_table_arg, image,
+ (void **)&fh);
+ if (status != EFI_SUCCESS)
+ goto free_files;
+ }
+
+ status = efi_file_size(sys_table_arg, fh, filename_16,
+ (void **)&file->handle, &file->size);
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ file_size_total += file->size;
+ }
+
+ if (file_size_total) {
+ unsigned long addr;
+
+ /*
+ * Multiple files need to be at consecutive addresses in memory,
+ * so allocate enough memory for all the files. This is used
+ * for loading multiple files.
+ */
+ status = efi_high_alloc(sys_table_arg, file_size_total, 0x1000,
+ &file_addr, max_addr);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg, "Failed to alloc highmem for files\n");
+ goto close_handles;
+ }
+
+ /* We've run out of free low memory. */
+ if (file_addr > max_addr) {
+ pr_efi_err(sys_table_arg, "We've run out of free low memory\n");
+ status = EFI_INVALID_PARAMETER;
+ goto free_file_total;
+ }
+
+ addr = file_addr;
+ for (j = 0; j < nr_files; j++) {
+ unsigned long size;
+
+ size = files[j].size;
+ while (size) {
+ unsigned long chunksize;
+ if (size > EFI_READ_CHUNK_SIZE)
+ chunksize = EFI_READ_CHUNK_SIZE;
+ else
+ chunksize = size;
+
+ status = efi_file_read(files[j].handle,
+ &chunksize,
+ (void *)addr);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg, "Failed to read file\n");
+ goto free_file_total;
+ }
+ addr += chunksize;
+ size -= chunksize;
+ }
+
+ efi_file_close(files[j].handle);
+ }
+
+ }
+
+ efi_call_early(free_pool, files);
+
+ *load_addr = file_addr;
+ *load_size = file_size_total;
+
+ return status;
+
+free_file_total:
+ efi_free(sys_table_arg, file_size_total, file_addr);
+
+close_handles:
+ for (k = j; k < i; k++)
+ efi_file_close(files[k].handle);
+free_files:
+ efi_call_early(free_pool, files);
+fail:
+ *load_addr = 0;
+ *load_size = 0;
+
+ return status;
+}
+/*
+ * Relocate a kernel image, either compressed or uncompressed.
+ * In the ARM64 case, all kernel images are currently
+ * uncompressed, and as such when we relocate it we need to
+ * allocate additional space for the BSS segment. Any low
+ * memory that this function should avoid needs to be
+ * unavailable in the EFI memory map, as if the preferred
+ * address is not available the lowest available address will
+ * be used.
+ */
+static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
+ unsigned long *image_addr,
+ unsigned long image_size,
+ unsigned long alloc_size,
+ unsigned long preferred_addr,
+ unsigned long alignment)
+{
+ unsigned long cur_image_addr;
+ unsigned long new_addr = 0;
+ efi_status_t status;
+ unsigned long nr_pages;
+ efi_physical_addr_t efi_addr = preferred_addr;
+
+ if (!image_addr || !image_size || !alloc_size)
+ return EFI_INVALID_PARAMETER;
+ if (alloc_size < image_size)
+ return EFI_INVALID_PARAMETER;
+
+ cur_image_addr = *image_addr;
+
+ /*
+ * The EFI firmware loader could have placed the kernel image
+ * anywhere in memory, but the kernel has restrictions on the
+ * max physical address it can run at. Some architectures
+ * also have a prefered address, so first try to relocate
+ * to the preferred address. If that fails, allocate as low
+ * as possible while respecting the required alignment.
+ */
+ nr_pages = round_up(alloc_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ status = efi_call_early(allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &efi_addr);
+ new_addr = efi_addr;
+ /*
+ * If preferred address allocation failed allocate as low as
+ * possible.
+ */
+ if (status != EFI_SUCCESS) {
+ status = efi_low_alloc(sys_table_arg, alloc_size, alignment,
+ &new_addr);
+ }
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n");
+ return status;
+ }
+
+ /*
+ * We know source/dest won't overlap since both memory ranges
+ * have been allocated by UEFI, so we can safely use memcpy.
+ */
+ memcpy((void *)new_addr, (void *)cur_image_addr, image_size);
+
+ /* Return the new address of the relocated image. */
+ *image_addr = new_addr;
+
+ return status;
+}
+
+/*
+ * Get the number of UTF-8 bytes corresponding to an UTF-16 character.
+ * This overestimates for surrogates, but that is okay.
+ */
+static int efi_utf8_bytes(u16 c)
+{
+ return 1 + (c >= 0x80) + (c >= 0x800);
+}
+
+/*
+ * Convert an UTF-16 string, not necessarily null terminated, to UTF-8.
+ */
+static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
+{
+ unsigned int c;
+
+ while (n--) {
+ c = *src++;
+ if (n && c >= 0xd800 && c <= 0xdbff &&
+ *src >= 0xdc00 && *src <= 0xdfff) {
+ c = 0x10000 + ((c & 0x3ff) << 10) + (*src & 0x3ff);
+ src++;
+ n--;
+ }
+ if (c >= 0xd800 && c <= 0xdfff)
+ c = 0xfffd; /* Unmatched surrogate */
+ if (c < 0x80) {
+ *dst++ = c;
+ continue;
+ }
+ if (c < 0x800) {
+ *dst++ = 0xc0 + (c >> 6);
+ goto t1;
+ }
+ if (c < 0x10000) {
+ *dst++ = 0xe0 + (c >> 12);
+ goto t2;
+ }
+ *dst++ = 0xf0 + (c >> 18);
+ *dst++ = 0x80 + ((c >> 12) & 0x3f);
+ t2:
+ *dst++ = 0x80 + ((c >> 6) & 0x3f);
+ t1:
+ *dst++ = 0x80 + (c & 0x3f);
+ }
+
+ return dst;
+}
+
+/*
+ * Convert the unicode UEFI command line to ASCII to pass to kernel.
+ * Size of memory allocated return in *cmd_line_len.
+ * Returns NULL on error.
+ */
+static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
+ efi_loaded_image_t *image,
+ int *cmd_line_len)
+{
+ const u16 *s2;
+ u8 *s1 = NULL;
+ unsigned long cmdline_addr = 0;
+ int load_options_chars = image->load_options_size / 2; /* UTF-16 */
+ const u16 *options = image->load_options;
+ int options_bytes = 0; /* UTF-8 bytes */
+ int options_chars = 0; /* UTF-16 chars */
+ efi_status_t status;
+ u16 zero = 0;
+
+ if (options) {
+ s2 = options;
+ while (*s2 && *s2 != '\n'
+ && options_chars < load_options_chars) {
+ options_bytes += efi_utf8_bytes(*s2++);
+ options_chars++;
+ }
+ }
+
+ if (!options_chars) {
+ /* No command line options, so return empty string*/
+ options = &zero;
+ }
+
+ options_bytes++; /* NUL termination */
+
+ status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr);
+ if (status != EFI_SUCCESS)
+ return NULL;
+
+ s1 = (u8 *)cmdline_addr;
+ s2 = (const u16 *)options;
+
+ s1 = efi_utf16_to_utf8(s1, s2, options_chars);
+ *s1 = '\0';
+
+ *cmd_line_len = options_bytes;
+ return (char *)cmdline_addr;
+}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5145fa3..87f2890 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -13,11 +13,29 @@
* This file is released under the GPLv2.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kobject.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/device.h>
#include <linux/efi.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/io.h>
+
+struct efi __read_mostly efi = {
+ .mps = EFI_INVALID_TABLE_ADDR,
+ .acpi = EFI_INVALID_TABLE_ADDR,
+ .acpi20 = EFI_INVALID_TABLE_ADDR,
+ .smbios = EFI_INVALID_TABLE_ADDR,
+ .sal_systab = EFI_INVALID_TABLE_ADDR,
+ .boot_info = EFI_INVALID_TABLE_ADDR,
+ .hcdp = EFI_INVALID_TABLE_ADDR,
+ .uga = EFI_INVALID_TABLE_ADDR,
+ .uv_systab = EFI_INVALID_TABLE_ADDR,
+};
+EXPORT_SYMBOL(efi);
static struct kobject *efi_kobj;
static struct kobject *efivars_kobj;
@@ -132,3 +150,212 @@
}
subsys_initcall(efisubsys_init);
+
+
+/*
+ * We can't ioremap data in EFI boot services RAM, because we've already mapped
+ * it as RAM. So, look it up in the existing EFI memory map instead. Only
+ * callable after efi_enter_virtual_mode and before efi_free_boot_services.
+ */
+void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
+{
+ struct efi_memory_map *map;
+ void *p;
+ map = efi.memmap;
+ if (!map)
+ return NULL;
+ if (WARN_ON(!map->map))
+ return NULL;
+ for (p = map->map; p < map->map_end; p += map->desc_size) {
+ efi_memory_desc_t *md = p;
+ u64 size = md->num_pages << EFI_PAGE_SHIFT;
+ u64 end = md->phys_addr + size;
+ if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+ md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA)
+ continue;
+ if (!md->virt_addr)
+ continue;
+ if (phys_addr >= md->phys_addr && phys_addr < end) {
+ phys_addr += md->virt_addr - md->phys_addr;
+ return (__force void __iomem *)(unsigned long)phys_addr;
+ }
+ }
+ return NULL;
+}
+
+static __initdata efi_config_table_type_t common_tables[] = {
+ {ACPI_20_TABLE_GUID, "ACPI 2.0", &efi.acpi20},
+ {ACPI_TABLE_GUID, "ACPI", &efi.acpi},
+ {HCDP_TABLE_GUID, "HCDP", &efi.hcdp},
+ {MPS_TABLE_GUID, "MPS", &efi.mps},
+ {SAL_SYSTEM_TABLE_GUID, "SALsystab", &efi.sal_systab},
+ {SMBIOS_TABLE_GUID, "SMBIOS", &efi.smbios},
+ {UGA_IO_PROTOCOL_GUID, "UGA", &efi.uga},
+ {NULL_GUID, NULL, NULL},
+};
+
+static __init int match_config_table(efi_guid_t *guid,
+ unsigned long table,
+ efi_config_table_type_t *table_types)
+{
+ u8 str[EFI_VARIABLE_GUID_LEN + 1];
+ int i;
+
+ if (table_types) {
+ efi_guid_unparse(guid, str);
+
+ for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
+ efi_guid_unparse(&table_types[i].guid, str);
+
+ if (!efi_guidcmp(*guid, table_types[i].guid)) {
+ *(table_types[i].ptr) = table;
+ pr_cont(" %s=0x%lx ",
+ table_types[i].name, table);
+ return 1;
+ }
+ }
+ }
+
+ return 0;
+}
+
+int __init efi_config_init(efi_config_table_type_t *arch_tables)
+{
+ void *config_tables, *tablep;
+ int i, sz;
+
+ if (efi_enabled(EFI_64BIT))
+ sz = sizeof(efi_config_table_64_t);
+ else
+ sz = sizeof(efi_config_table_32_t);
+
+ /*
+ * Let's see what config tables the firmware passed to us.
+ */
+ config_tables = early_memremap(efi.systab->tables,
+ efi.systab->nr_tables * sz);
+ if (config_tables == NULL) {
+ pr_err("Could not map Configuration table!\n");
+ return -ENOMEM;
+ }
+
+ tablep = config_tables;
+ pr_info("");
+ for (i = 0; i < efi.systab->nr_tables; i++) {
+ efi_guid_t guid;
+ unsigned long table;
+
+ if (efi_enabled(EFI_64BIT)) {
+ u64 table64;
+ guid = ((efi_config_table_64_t *)tablep)->guid;
+ table64 = ((efi_config_table_64_t *)tablep)->table;
+ table = table64;
+#ifndef CONFIG_64BIT
+ if (table64 >> 32) {
+ pr_cont("\n");
+ pr_err("Table located above 4GB, disabling EFI.\n");
+ early_iounmap(config_tables,
+ efi.systab->nr_tables * sz);
+ return -EINVAL;
+ }
+#endif
+ } else {
+ guid = ((efi_config_table_32_t *)tablep)->guid;
+ table = ((efi_config_table_32_t *)tablep)->table;
+ }
+
+ if (!match_config_table(&guid, table, common_tables))
+ match_config_table(&guid, table, arch_tables);
+
+ tablep += sz;
+ }
+ pr_cont("\n");
+ early_iounmap(config_tables, efi.systab->nr_tables * sz);
+ return 0;
+}
+
+#ifdef CONFIG_EFI_PARAMS_FROM_FDT
+
+#define UEFI_PARAM(name, prop, field) \
+ { \
+ { name }, \
+ { prop }, \
+ offsetof(struct efi_fdt_params, field), \
+ FIELD_SIZEOF(struct efi_fdt_params, field) \
+ }
+
+static __initdata struct {
+ const char name[32];
+ const char propname[32];
+ int offset;
+ int size;
+} dt_params[] = {
+ UEFI_PARAM("System Table", "linux,uefi-system-table", system_table),
+ UEFI_PARAM("MemMap Address", "linux,uefi-mmap-start", mmap),
+ UEFI_PARAM("MemMap Size", "linux,uefi-mmap-size", mmap_size),
+ UEFI_PARAM("MemMap Desc. Size", "linux,uefi-mmap-desc-size", desc_size),
+ UEFI_PARAM("MemMap Desc. Version", "linux,uefi-mmap-desc-ver", desc_ver)
+};
+
+struct param_info {
+ int verbose;
+ int found;
+ void *params;
+};
+
+static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ struct param_info *info = data;
+ const void *prop;
+ void *dest;
+ u64 val;
+ int i, len;
+
+ if (depth != 1 ||
+ (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
+ return 0;
+
+ for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
+ prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len);
+ if (!prop)
+ return 0;
+ dest = info->params + dt_params[i].offset;
+ info->found++;
+
+ val = of_read_number(prop, len / sizeof(u32));
+
+ if (dt_params[i].size == sizeof(u32))
+ *(u32 *)dest = val;
+ else
+ *(u64 *)dest = val;
+
+ if (info->verbose)
+ pr_info(" %s: 0x%0*llx\n", dt_params[i].name,
+ dt_params[i].size * 2, val);
+ }
+ return 1;
+}
+
+int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose)
+{
+ struct param_info info;
+ int ret;
+
+ pr_info("Getting EFI parameters from FDT:\n");
+
+ info.verbose = verbose;
+ info.found = 0;
+ info.params = params;
+
+ ret = of_scan_flat_dt(fdt_find_uefi_params, &info);
+ if (!info.found)
+ pr_info("UEFI not found.\n");
+ else if (!ret)
+ pr_err("Can't find '%s' in device tree!\n",
+ dt_params[info.found].name);
+
+ return ret;
+}
+#endif /* CONFIG_EFI_PARAMS_FROM_FDT */
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 8bd1bb6..463c565 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -69,6 +69,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/ucs2_string.h>
+#include <linux/compat.h>
#define EFIVARS_VERSION "0.08"
#define EFIVARS_DATE "2004-May-17"
@@ -86,6 +87,15 @@
static struct bin_attribute *efivars_new_var;
static struct bin_attribute *efivars_del_var;
+struct compat_efi_variable {
+ efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)];
+ efi_guid_t VendorGuid;
+ __u32 DataSize;
+ __u8 Data[1024];
+ __u32 Status;
+ __u32 Attributes;
+} __packed;
+
struct efivar_attribute {
struct attribute attr;
ssize_t (*show) (struct efivar_entry *entry, char *buf);
@@ -189,6 +199,54 @@
memcpy(buf, var->Data, var->DataSize);
return var->DataSize;
}
+
+static inline int
+sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
+ unsigned long size, u32 attributes, u8 *data)
+{
+ /*
+ * If only updating the variable data, then the name
+ * and guid should remain the same
+ */
+ if (memcmp(name, var->VariableName, sizeof(var->VariableName)) ||
+ efi_guidcmp(vendor, var->VendorGuid)) {
+ printk(KERN_ERR "efivars: Cannot edit the wrong variable!\n");
+ return -EINVAL;
+ }
+
+ if ((size <= 0) || (attributes == 0)){
+ printk(KERN_ERR "efivars: DataSize & Attributes must be valid!\n");
+ return -EINVAL;
+ }
+
+ if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
+ efivar_validate(name, data, size) == false) {
+ printk(KERN_ERR "efivars: Malformed variable content\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static inline bool is_compat(void)
+{
+ if (IS_ENABLED(CONFIG_COMPAT) && is_compat_task())
+ return true;
+
+ return false;
+}
+
+static void
+copy_out_compat(struct efi_variable *dst, struct compat_efi_variable *src)
+{
+ memcpy(dst->VariableName, src->VariableName, EFI_VAR_NAME_LEN);
+ memcpy(dst->Data, src->Data, sizeof(src->Data));
+
+ dst->VendorGuid = src->VendorGuid;
+ dst->DataSize = src->DataSize;
+ dst->Attributes = src->Attributes;
+}
+
/*
* We allow each variable to be edited via rewriting the
* entire efi variable structure.
@@ -197,37 +255,51 @@
efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count)
{
struct efi_variable *new_var, *var = &entry->var;
+ efi_char16_t *name;
+ unsigned long size;
+ efi_guid_t vendor;
+ u32 attributes;
+ u8 *data;
int err;
- if (count != sizeof(struct efi_variable))
- return -EINVAL;
+ if (is_compat()) {
+ struct compat_efi_variable *compat;
- new_var = (struct efi_variable *)buf;
- /*
- * If only updating the variable data, then the name
- * and guid should remain the same
- */
- if (memcmp(new_var->VariableName, var->VariableName, sizeof(var->VariableName)) ||
- efi_guidcmp(new_var->VendorGuid, var->VendorGuid)) {
- printk(KERN_ERR "efivars: Cannot edit the wrong variable!\n");
- return -EINVAL;
+ if (count != sizeof(*compat))
+ return -EINVAL;
+
+ compat = (struct compat_efi_variable *)buf;
+ attributes = compat->Attributes;
+ vendor = compat->VendorGuid;
+ name = compat->VariableName;
+ size = compat->DataSize;
+ data = compat->Data;
+
+ err = sanity_check(var, name, vendor, size, attributes, data);
+ if (err)
+ return err;
+
+ copy_out_compat(&entry->var, compat);
+ } else {
+ if (count != sizeof(struct efi_variable))
+ return -EINVAL;
+
+ new_var = (struct efi_variable *)buf;
+
+ attributes = new_var->Attributes;
+ vendor = new_var->VendorGuid;
+ name = new_var->VariableName;
+ size = new_var->DataSize;
+ data = new_var->Data;
+
+ err = sanity_check(var, name, vendor, size, attributes, data);
+ if (err)
+ return err;
+
+ memcpy(&entry->var, new_var, count);
}
- if ((new_var->DataSize <= 0) || (new_var->Attributes == 0)){
- printk(KERN_ERR "efivars: DataSize & Attributes must be valid!\n");
- return -EINVAL;
- }
-
- if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 ||
- efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) {
- printk(KERN_ERR "efivars: Malformed variable content\n");
- return -EINVAL;
- }
-
- memcpy(&entry->var, new_var, count);
-
- err = efivar_entry_set(entry, new_var->Attributes,
- new_var->DataSize, new_var->Data, false);
+ err = efivar_entry_set(entry, attributes, size, data, NULL);
if (err) {
printk(KERN_WARNING "efivars: set_variable() failed: status=%d\n", err);
return -EIO;
@@ -240,6 +312,8 @@
efivar_show_raw(struct efivar_entry *entry, char *buf)
{
struct efi_variable *var = &entry->var;
+ struct compat_efi_variable *compat;
+ size_t size;
if (!entry || !buf)
return 0;
@@ -249,9 +323,23 @@
&entry->var.DataSize, entry->var.Data))
return -EIO;
- memcpy(buf, var, sizeof(*var));
+ if (is_compat()) {
+ compat = (struct compat_efi_variable *)buf;
- return sizeof(*var);
+ size = sizeof(*compat);
+ memcpy(compat->VariableName, var->VariableName,
+ EFI_VAR_NAME_LEN);
+ memcpy(compat->Data, var->Data, sizeof(compat->Data));
+
+ compat->VendorGuid = var->VendorGuid;
+ compat->DataSize = var->DataSize;
+ compat->Attributes = var->Attributes;
+ } else {
+ size = sizeof(*var);
+ memcpy(buf, var, size);
+ }
+
+ return size;
}
/*
@@ -326,15 +414,39 @@
struct bin_attribute *bin_attr,
char *buf, loff_t pos, size_t count)
{
+ struct compat_efi_variable *compat = (struct compat_efi_variable *)buf;
struct efi_variable *new_var = (struct efi_variable *)buf;
struct efivar_entry *new_entry;
+ bool need_compat = is_compat();
+ efi_char16_t *name;
+ unsigned long size;
+ u32 attributes;
+ u8 *data;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
- if ((new_var->Attributes & ~EFI_VARIABLE_MASK) != 0 ||
- efivar_validate(new_var, new_var->Data, new_var->DataSize) == false) {
+ if (need_compat) {
+ if (count != sizeof(*compat))
+ return -EINVAL;
+
+ attributes = compat->Attributes;
+ name = compat->VariableName;
+ size = compat->DataSize;
+ data = compat->Data;
+ } else {
+ if (count != sizeof(*new_var))
+ return -EINVAL;
+
+ attributes = new_var->Attributes;
+ name = new_var->VariableName;
+ size = new_var->DataSize;
+ data = new_var->Data;
+ }
+
+ if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
+ efivar_validate(name, data, size) == false) {
printk(KERN_ERR "efivars: Malformed variable content\n");
return -EINVAL;
}
@@ -343,10 +455,13 @@
if (!new_entry)
return -ENOMEM;
- memcpy(&new_entry->var, new_var, sizeof(*new_var));
+ if (need_compat)
+ copy_out_compat(&new_entry->var, compat);
+ else
+ memcpy(&new_entry->var, new_var, sizeof(*new_var));
- err = efivar_entry_set(new_entry, new_var->Attributes, new_var->DataSize,
- new_var->Data, &efivar_sysfs_list);
+ err = efivar_entry_set(new_entry, attributes, size,
+ data, &efivar_sysfs_list);
if (err) {
if (err == -EEXIST)
err = -EINVAL;
@@ -369,26 +484,47 @@
char *buf, loff_t pos, size_t count)
{
struct efi_variable *del_var = (struct efi_variable *)buf;
+ struct compat_efi_variable *compat;
struct efivar_entry *entry;
+ efi_char16_t *name;
+ efi_guid_t vendor;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
+ if (is_compat()) {
+ if (count != sizeof(*compat))
+ return -EINVAL;
+
+ compat = (struct compat_efi_variable *)buf;
+ name = compat->VariableName;
+ vendor = compat->VendorGuid;
+ } else {
+ if (count != sizeof(*del_var))
+ return -EINVAL;
+
+ name = del_var->VariableName;
+ vendor = del_var->VendorGuid;
+ }
+
efivar_entry_iter_begin();
- entry = efivar_entry_find(del_var->VariableName, del_var->VendorGuid,
- &efivar_sysfs_list, true);
+ entry = efivar_entry_find(name, vendor, &efivar_sysfs_list, true);
if (!entry)
err = -EINVAL;
else if (__efivar_entry_delete(entry))
err = -EIO;
- efivar_entry_iter_end();
-
- if (err)
+ if (err) {
+ efivar_entry_iter_end();
return err;
+ }
- efivar_unregister(entry);
+ if (!entry->scanning) {
+ efivar_entry_iter_end();
+ efivar_unregister(entry);
+ } else
+ efivar_entry_iter_end();
/* It's dead Jim.... */
return count;
@@ -564,7 +700,7 @@
return 0;
}
-void efivars_sysfs_exit(void)
+static void efivars_sysfs_exit(void)
{
/* Remove all entries and destroy */
__efivar_entry_iter(efivar_sysfs_destroy, &efivar_sysfs_list, NULL, NULL);
@@ -583,6 +719,9 @@
struct kobject *parent_kobj = efivars_kobject();
int error = 0;
+ if (!efi_enabled(EFI_RUNTIME_SERVICES))
+ return -ENODEV;
+
/* No efivars has been registered yet */
if (!parent_kobj)
return 0;
diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/fdt.c
new file mode 100644
index 0000000..507a3df
--- /dev/null
+++ b/drivers/firmware/efi/fdt.c
@@ -0,0 +1,275 @@
+/*
+ * FDT related Helper functions used by the EFI stub on multiple
+ * architectures. This should be #included by the EFI stub
+ * implementation files.
+ *
+ * Copyright 2013 Linaro Limited; author Roy Franz
+ *
+ * This file is part of the Linux kernel, and is made available
+ * under the terms of the GNU General Public License version 2.
+ *
+ */
+
+static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+ unsigned long orig_fdt_size,
+ void *fdt, int new_fdt_size, char *cmdline_ptr,
+ u64 initrd_addr, u64 initrd_size,
+ efi_memory_desc_t *memory_map,
+ unsigned long map_size, unsigned long desc_size,
+ u32 desc_ver)
+{
+ int node, prev;
+ int status;
+ u32 fdt_val32;
+ u64 fdt_val64;
+
+ /* Do some checks on provided FDT, if it exists*/
+ if (orig_fdt) {
+ if (fdt_check_header(orig_fdt)) {
+ pr_efi_err(sys_table, "Device Tree header not valid!\n");
+ return EFI_LOAD_ERROR;
+ }
+ /*
+ * We don't get the size of the FDT if we get if from a
+ * configuration table.
+ */
+ if (orig_fdt_size && fdt_totalsize(orig_fdt) > orig_fdt_size) {
+ pr_efi_err(sys_table, "Truncated device tree! foo!\n");
+ return EFI_LOAD_ERROR;
+ }
+ }
+
+ if (orig_fdt)
+ status = fdt_open_into(orig_fdt, fdt, new_fdt_size);
+ else
+ status = fdt_create_empty_tree(fdt, new_fdt_size);
+
+ if (status != 0)
+ goto fdt_set_fail;
+
+ /*
+ * Delete any memory nodes present. We must delete nodes which
+ * early_init_dt_scan_memory may try to use.
+ */
+ prev = 0;
+ for (;;) {
+ const char *type;
+ int len;
+
+ node = fdt_next_node(fdt, prev, NULL);
+ if (node < 0)
+ break;
+
+ type = fdt_getprop(fdt, node, "device_type", &len);
+ if (type && strncmp(type, "memory", len) == 0) {
+ fdt_del_node(fdt, node);
+ continue;
+ }
+
+ prev = node;
+ }
+
+ node = fdt_subnode_offset(fdt, 0, "chosen");
+ if (node < 0) {
+ node = fdt_add_subnode(fdt, 0, "chosen");
+ if (node < 0) {
+ status = node; /* node is error code when negative */
+ goto fdt_set_fail;
+ }
+ }
+
+ if ((cmdline_ptr != NULL) && (strlen(cmdline_ptr) > 0)) {
+ status = fdt_setprop(fdt, node, "bootargs", cmdline_ptr,
+ strlen(cmdline_ptr) + 1);
+ if (status)
+ goto fdt_set_fail;
+ }
+
+ /* Set initrd address/end in device tree, if present */
+ if (initrd_size != 0) {
+ u64 initrd_image_end;
+ u64 initrd_image_start = cpu_to_fdt64(initrd_addr);
+
+ status = fdt_setprop(fdt, node, "linux,initrd-start",
+ &initrd_image_start, sizeof(u64));
+ if (status)
+ goto fdt_set_fail;
+ initrd_image_end = cpu_to_fdt64(initrd_addr + initrd_size);
+ status = fdt_setprop(fdt, node, "linux,initrd-end",
+ &initrd_image_end, sizeof(u64));
+ if (status)
+ goto fdt_set_fail;
+ }
+
+ /* Add FDT entries for EFI runtime services in chosen node. */
+ node = fdt_subnode_offset(fdt, 0, "chosen");
+ fdt_val64 = cpu_to_fdt64((u64)(unsigned long)sys_table);
+ status = fdt_setprop(fdt, node, "linux,uefi-system-table",
+ &fdt_val64, sizeof(fdt_val64));
+ if (status)
+ goto fdt_set_fail;
+
+ fdt_val64 = cpu_to_fdt64((u64)(unsigned long)memory_map);
+ status = fdt_setprop(fdt, node, "linux,uefi-mmap-start",
+ &fdt_val64, sizeof(fdt_val64));
+ if (status)
+ goto fdt_set_fail;
+
+ fdt_val32 = cpu_to_fdt32(map_size);
+ status = fdt_setprop(fdt, node, "linux,uefi-mmap-size",
+ &fdt_val32, sizeof(fdt_val32));
+ if (status)
+ goto fdt_set_fail;
+
+ fdt_val32 = cpu_to_fdt32(desc_size);
+ status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-size",
+ &fdt_val32, sizeof(fdt_val32));
+ if (status)
+ goto fdt_set_fail;
+
+ fdt_val32 = cpu_to_fdt32(desc_ver);
+ status = fdt_setprop(fdt, node, "linux,uefi-mmap-desc-ver",
+ &fdt_val32, sizeof(fdt_val32));
+ if (status)
+ goto fdt_set_fail;
+
+ /*
+ * Add kernel version banner so stub/kernel match can be
+ * verified.
+ */
+ status = fdt_setprop_string(fdt, node, "linux,uefi-stub-kern-ver",
+ linux_banner);
+ if (status)
+ goto fdt_set_fail;
+
+ return EFI_SUCCESS;
+
+fdt_set_fail:
+ if (status == -FDT_ERR_NOSPACE)
+ return EFI_BUFFER_TOO_SMALL;
+
+ return EFI_LOAD_ERROR;
+}
+
+#ifndef EFI_FDT_ALIGN
+#define EFI_FDT_ALIGN EFI_PAGE_SIZE
+#endif
+
+/*
+ * Allocate memory for a new FDT, then add EFI, commandline, and
+ * initrd related fields to the FDT. This routine increases the
+ * FDT allocation size until the allocated memory is large
+ * enough. EFI allocations are in EFI_PAGE_SIZE granules,
+ * which are fixed at 4K bytes, so in most cases the first
+ * allocation should succeed.
+ * EFI boot services are exited at the end of this function.
+ * There must be no allocations between the get_memory_map()
+ * call and the exit_boot_services() call, so the exiting of
+ * boot services is very tightly tied to the creation of the FDT
+ * with the final memory map in it.
+ */
+
+efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
+ void *handle,
+ unsigned long *new_fdt_addr,
+ unsigned long max_addr,
+ u64 initrd_addr, u64 initrd_size,
+ char *cmdline_ptr,
+ unsigned long fdt_addr,
+ unsigned long fdt_size)
+{
+ unsigned long map_size, desc_size;
+ u32 desc_ver;
+ unsigned long mmap_key;
+ efi_memory_desc_t *memory_map;
+ unsigned long new_fdt_size;
+ efi_status_t status;
+
+ /*
+ * Estimate size of new FDT, and allocate memory for it. We
+ * will allocate a bigger buffer if this ends up being too
+ * small, so a rough guess is OK here.
+ */
+ new_fdt_size = fdt_size + EFI_PAGE_SIZE;
+ while (1) {
+ status = efi_high_alloc(sys_table, new_fdt_size, EFI_FDT_ALIGN,
+ new_fdt_addr, max_addr);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Unable to allocate memory for new device tree.\n");
+ goto fail;
+ }
+
+ /*
+ * Now that we have done our final memory allocation (and free)
+ * we can get the memory map key needed for
+ * exit_boot_services().
+ */
+ status = efi_get_memory_map(sys_table, &memory_map, &map_size,
+ &desc_size, &desc_ver, &mmap_key);
+ if (status != EFI_SUCCESS)
+ goto fail_free_new_fdt;
+
+ status = update_fdt(sys_table,
+ (void *)fdt_addr, fdt_size,
+ (void *)*new_fdt_addr, new_fdt_size,
+ cmdline_ptr, initrd_addr, initrd_size,
+ memory_map, map_size, desc_size, desc_ver);
+
+ /* Succeeding the first time is the expected case. */
+ if (status == EFI_SUCCESS)
+ break;
+
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ /*
+ * We need to allocate more space for the new
+ * device tree, so free existing buffer that is
+ * too small. Also free memory map, as we will need
+ * to get new one that reflects the free/alloc we do
+ * on the device tree buffer.
+ */
+ efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+ sys_table->boottime->free_pool(memory_map);
+ new_fdt_size += EFI_PAGE_SIZE;
+ } else {
+ pr_efi_err(sys_table, "Unable to constuct new device tree.\n");
+ goto fail_free_mmap;
+ }
+ }
+
+ /* Now we are ready to exit_boot_services.*/
+ status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+
+
+ if (status == EFI_SUCCESS)
+ return status;
+
+ pr_efi_err(sys_table, "Exit boot services failed.\n");
+
+fail_free_mmap:
+ sys_table->boottime->free_pool(memory_map);
+
+fail_free_new_fdt:
+ efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+
+fail:
+ return EFI_LOAD_ERROR;
+}
+
+static void *get_fdt(efi_system_table_t *sys_table)
+{
+ efi_guid_t fdt_guid = DEVICE_TREE_GUID;
+ efi_config_table_t *tables;
+ void *fdt;
+ int i;
+
+ tables = (efi_config_table_t *) sys_table->tables;
+ fdt = NULL;
+
+ for (i = 0; i < sys_table->nr_tables; i++)
+ if (efi_guidcmp(tables[i].guid, fdt_guid) == 0) {
+ fdt = (void *) tables[i].table;
+ break;
+ }
+
+ return fdt;
+}
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 391c67b..5abe943 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -42,7 +42,7 @@
EXPORT_SYMBOL_GPL(efivar_work);
static bool
-validate_device_path(struct efi_variable *var, int match, u8 *buffer,
+validate_device_path(efi_char16_t *var_name, int match, u8 *buffer,
unsigned long len)
{
struct efi_generic_dev_path *node;
@@ -75,7 +75,7 @@
}
static bool
-validate_boot_order(struct efi_variable *var, int match, u8 *buffer,
+validate_boot_order(efi_char16_t *var_name, int match, u8 *buffer,
unsigned long len)
{
/* An array of 16-bit integers */
@@ -86,18 +86,18 @@
}
static bool
-validate_load_option(struct efi_variable *var, int match, u8 *buffer,
+validate_load_option(efi_char16_t *var_name, int match, u8 *buffer,
unsigned long len)
{
u16 filepathlength;
int i, desclength = 0, namelen;
- namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName));
+ namelen = ucs2_strnlen(var_name, EFI_VAR_NAME_LEN);
/* Either "Boot" or "Driver" followed by four digits of hex */
for (i = match; i < match+4; i++) {
- if (var->VariableName[i] > 127 ||
- hex_to_bin(var->VariableName[i] & 0xff) < 0)
+ if (var_name[i] > 127 ||
+ hex_to_bin(var_name[i] & 0xff) < 0)
return true;
}
@@ -132,12 +132,12 @@
/*
* And, finally, check the filepath
*/
- return validate_device_path(var, match, buffer + desclength + 6,
+ return validate_device_path(var_name, match, buffer + desclength + 6,
filepathlength);
}
static bool
-validate_uint16(struct efi_variable *var, int match, u8 *buffer,
+validate_uint16(efi_char16_t *var_name, int match, u8 *buffer,
unsigned long len)
{
/* A single 16-bit integer */
@@ -148,7 +148,7 @@
}
static bool
-validate_ascii_string(struct efi_variable *var, int match, u8 *buffer,
+validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
unsigned long len)
{
int i;
@@ -166,7 +166,7 @@
struct variable_validate {
char *name;
- bool (*validate)(struct efi_variable *var, int match, u8 *data,
+ bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
unsigned long len);
};
@@ -189,10 +189,10 @@
};
bool
-efivar_validate(struct efi_variable *var, u8 *data, unsigned long len)
+efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
{
int i;
- u16 *unicode_name = var->VariableName;
+ u16 *unicode_name = var_name;
for (i = 0; variable_validate[i].validate != NULL; i++) {
const char *name = variable_validate[i].name;
@@ -208,7 +208,7 @@
/* Wildcard in the matching name means we've matched */
if (c == '*')
- return variable_validate[i].validate(var,
+ return variable_validate[i].validate(var_name,
match, data, len);
/* Case sensitive match */
@@ -217,7 +217,7 @@
/* Reached the end of the string while matching */
if (!c)
- return variable_validate[i].validate(var,
+ return variable_validate[i].validate(var_name,
match, data, len);
}
}
@@ -481,7 +481,7 @@
*/
static void efivar_entry_list_del_unlock(struct efivar_entry *entry)
{
- WARN_ON(!spin_is_locked(&__efivars->lock));
+ lockdep_assert_held(&__efivars->lock);
list_del(&entry->list);
spin_unlock_irq(&__efivars->lock);
@@ -507,7 +507,7 @@
const struct efivar_operations *ops = __efivars->ops;
efi_status_t status;
- WARN_ON(!spin_is_locked(&__efivars->lock));
+ lockdep_assert_held(&__efivars->lock);
status = ops->set_variable(entry->var.VariableName,
&entry->var.VendorGuid,
@@ -667,7 +667,7 @@
int strsize1, strsize2;
bool found = false;
- WARN_ON(!spin_is_locked(&__efivars->lock));
+ lockdep_assert_held(&__efivars->lock);
list_for_each_entry_safe(entry, n, head, list) {
strsize1 = ucs2_strsize(name, 1024);
@@ -683,8 +683,16 @@
if (!found)
return NULL;
- if (remove)
- list_del(&entry->list);
+ if (remove) {
+ if (entry->scanning) {
+ /*
+ * The entry will be deleted
+ * after scanning is completed.
+ */
+ entry->deleting = true;
+ } else
+ list_del(&entry->list);
+ }
return entry;
}
@@ -731,7 +739,7 @@
const struct efivar_operations *ops = __efivars->ops;
efi_status_t status;
- WARN_ON(!spin_is_locked(&__efivars->lock));
+ lockdep_assert_held(&__efivars->lock);
status = ops->get_variable(entry->var.VariableName,
&entry->var.VendorGuid,
@@ -797,7 +805,7 @@
*set = false;
- if (efivar_validate(&entry->var, data, *size) == false)
+ if (efivar_validate(name, data, *size) == false)
return -EINVAL;
/*
diff --git a/drivers/gator/COPYING b/drivers/gator/COPYING
new file mode 100644
index 0000000..d159169
--- /dev/null
+++ b/drivers/gator/COPYING
@@ -0,0 +1,339 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License along
+ with this program; if not, write to the Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/drivers/gator/Kconfig b/drivers/gator/Kconfig
new file mode 100644
index 0000000..b2358bb
--- /dev/null
+++ b/drivers/gator/Kconfig
@@ -0,0 +1,39 @@
+config GATOR
+ tristate "Gator module for ARM's Streamline Performance Analyzer"
+ default m if (ARM || ARM64)
+ depends on PROFILING
+ depends on HIGH_RES_TIMERS
+ depends on LOCAL_TIMERS || !(ARM && SMP)
+ depends on PERF_EVENTS
+ depends on HW_PERF_EVENTS || !(ARM || ARM64)
+ select TRACING
+ help
+ Gator module for ARM's Streamline Performance Analyzer
+
+config GATOR_WITH_MALI_SUPPORT
+ bool
+
+choice
+ prompt "Enable Mali GPU support in Gator"
+ depends on GATOR
+ optional
+ help
+ Enable Mali GPU support in Gator
+
+config GATOR_MALI_4XXMP
+ bool "Mali-400MP or Mali-450MP"
+ select GATOR_WITH_MALI_SUPPORT
+
+config GATOR_MALI_MIDGARD
+ bool "Mali-T60x, Mali-T62x, Mali-T72x or Mali-T76x"
+ select GATOR_WITH_MALI_SUPPORT
+
+endchoice
+
+config GATOR_MALI_PATH
+ string "Path to Mali driver"
+ depends on GATOR_WITH_MALI_SUPPORT
+ default "drivers/gpu/arm/mali400mp"
+ help
+ The gator code adds this to its include path so it can get the Mali
+ trace headers with: #include "linux/mali_linux_trace.h"
diff --git a/drivers/gator/Makefile b/drivers/gator/Makefile
new file mode 100644
index 0000000..d14e2a0
--- /dev/null
+++ b/drivers/gator/Makefile
@@ -0,0 +1,95 @@
+ifneq ($(KERNELRELEASE),)
+
+# Uncomment the following line to enable kernel stack unwinding within gator, or update gator_backtrace.c
+# EXTRA_CFLAGS += -DGATOR_KERNEL_STACK_UNWINDING
+
+CONFIG_GATOR ?= m
+obj-$(CONFIG_GATOR) := gator.o
+
+gator-y := gator_main.o \
+ gator_events_block.o \
+ gator_events_irq.o \
+ gator_events_meminfo.o \
+ gator_events_mmapped.o \
+ gator_events_net.o \
+ gator_events_perf_pmu.o \
+ gator_events_sched.o \
+
+# Convert the old GATOR_WITH_MALI_SUPPORT to the new kernel flags
+ifneq ($(GATOR_WITH_MALI_SUPPORT),)
+ CONFIG_GATOR_WITH_MALI_SUPPORT := y
+ ifeq ($(GATOR_WITH_MALI_SUPPORT),MALI_MIDGARD)
+ CONFIG_GATOR_MALI_4XXMP := n
+ CONFIG_GATOR_MALI_MIDGARD := y
+ else
+ CONFIG_GATOR_MALI_4XXMP := y
+ CONFIG_GATOR_MALI_MIDGARD := n
+ endif
+ EXTRA_CFLAGS += -DMALI_SUPPORT=$(GATOR_WITH_MALI_SUPPORT)
+ ifneq ($(GATOR_MALI_INTERFACE_STYLE),)
+ EXTRA_CFLAGS += -DGATOR_MALI_INTERFACE_STYLE=$(GATOR_MALI_INTERFACE_STYLE)
+ endif
+endif
+
+ifeq ($(CONFIG_GATOR_WITH_MALI_SUPPORT),y)
+ ifeq ($(CONFIG_GATOR_MALI_MIDGARD),y)
+ gator-y += gator_events_mali_midgard.o \
+ gator_events_mali_midgard_hw.o
+ include $(src)/mali_midgard.mk
+ else
+ gator-y += gator_events_mali_4xx.o
+ endif
+ gator-y += gator_events_mali_common.o
+
+ ifneq ($(CONFIG_GATOR_MALI_PATH),)
+ ccflags-y += -I$(CONFIG_GATOR_MALI_PATH)
+ endif
+ ccflags-$(CONFIG_GATOR_MALI_4XXMP) += -DMALI_SUPPORT=MALI_4xx
+ ccflags-$(CONFIG_GATOR_MALI_MIDGARD) += -DMALI_SUPPORT=MALI_MIDGARD
+endif
+
+# GATOR_TEST controls whether to include (=1) or exclude (=0) test code.
+GATOR_TEST ?= 0
+EXTRA_CFLAGS += -DGATOR_TEST=$(GATOR_TEST)
+
+# Should the original or new block_rq_complete API be used?
+OLD_BLOCK_RQ_COMPLETE := $(shell grep -A3 block_rq_complete $(srctree)/include/trace/events/block.h | grep nr_bytes -q; echo $$?)
+EXTRA_CFLAGS += -DOLD_BLOCK_RQ_COMPLETE=$(OLD_BLOCK_RQ_COMPLETE)
+
+gator-$(CONFIG_ARM) += gator_events_armv6.o \
+ gator_events_armv7.o \
+ gator_events_l2c-310.o \
+ gator_events_scorpion.o
+
+gator-$(CONFIG_ARM64) +=
+
+$(obj)/gator_main.o: $(obj)/gator_src_md5.h
+
+clean-files := gator_src_md5.h
+
+# Note, in the recipe below we use "cd $(srctree) && cd $(src)" rather than
+# "cd $(srctree)/$(src)" because under DKMS $(src) is an absolute path, and we
+# can't just use $(src) because for normal kernel builds this is relative to
+# $(srctree)
+
+ chk_events.h = :
+ quiet_chk_events.h = echo ' CHK $@'
+silent_chk_events.h = :
+$(obj)/gator_src_md5.h: FORCE
+ @$($(quiet)chk_events.h)
+ $(Q)cd $(srctree) && cd $(src) ; $(CONFIG_SHELL) -c "echo 'static char *gator_src_md5 = \"'\`ls *.c *.h mali/*.h | grep -Ev '^(gator_src_md5\.c|gator\.mod\.c)$$' | LC_ALL=C sort | xargs cat | md5sum | cut -b 1-32\`'\";'" > $(abspath $@)
+
+else
+
+all:
+ @echo
+ @echo "usage:"
+ @echo " make -C <kernel_build_dir> M=\`pwd\` ARCH=arm CROSS_COMPILE=<...> modules"
+ @echo
+ $(error)
+
+clean:
+ rm -f *.o .*.cmd gator_src_md5.h modules.order Module.symvers gator.ko gator.mod.c
+ rm -rf .tmp_versions
+
+endif
diff --git a/drivers/gator/gator.h b/drivers/gator/gator.h
new file mode 100644
index 0000000..202eb41
--- /dev/null
+++ b/drivers/gator/gator.h
@@ -0,0 +1,153 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef GATOR_H_
+#define GATOR_H_
+
+#include <linux/version.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/list.h>
+
+#define GATOR_PERF_SUPPORT (LINUX_VERSION_CODE >= KERNEL_VERSION(3, 0, 0))
+#define GATOR_PERF_PMU_SUPPORT (GATOR_PERF_SUPPORT && defined(CONFIG_PERF_EVENTS) && (!(defined(__arm__) || defined(__aarch64__)) || defined(CONFIG_HW_PERF_EVENTS)))
+#define GATOR_NO_PERF_SUPPORT (!(GATOR_PERF_SUPPORT))
+#define GATOR_CPU_FREQ_SUPPORT ((LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)) && defined(CONFIG_CPU_FREQ))
+#define GATOR_IKS_SUPPORT defined(CONFIG_BL_SWITCHER)
+
+/* cpu ids */
+#define ARM1136 0x41b36
+#define ARM1156 0x41b56
+#define ARM1176 0x41b76
+#define ARM11MPCORE 0x41b02
+#define CORTEX_A5 0x41c05
+#define CORTEX_A7 0x41c07
+#define CORTEX_A8 0x41c08
+#define CORTEX_A9 0x41c09
+#define CORTEX_A15 0x41c0f
+#define CORTEX_A12 0x41c0d
+#define CORTEX_A17 0x41c0e
+#define SCORPION 0x5100f
+#define SCORPIONMP 0x5102d
+#define KRAITSIM 0x51049
+#define KRAIT 0x5104d
+#define KRAIT_S4_PRO 0x5106f
+#define CORTEX_A53 0x41d03
+#define CORTEX_A57 0x41d07
+#define CORTEX_A72 0x41d08
+#define OTHER 0xfffff
+
+/* gpu enums */
+#define MALI_4xx 1
+#define MALI_MIDGARD 2
+
+#define MAXSIZE_CORE_NAME 32
+
+struct gator_cpu {
+ const int cpuid;
+ /* Human readable name */
+ const char core_name[MAXSIZE_CORE_NAME];
+ /* gatorfs event and Perf PMU name */
+ const char *const pmnc_name;
+ /* compatible from Documentation/devicetree/bindings/arm/cpus.txt */
+ const char *const dt_name;
+ const int pmnc_counters;
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid);
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name);
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+struct dentry *gatorfs_mkdir(struct super_block *sb, struct dentry *root,
+ char const *name);
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+ char const *name, unsigned long *val);
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+ char const *name, unsigned long *val);
+
+/******************************************************************************
+ * Tracepoints
+ ******************************************************************************/
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+# error Kernels prior to 2.6.32 not supported
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+# define GATOR_DEFINE_PROBE(probe_name, proto) \
+ static void probe_##probe_name(PARAMS(proto))
+# define GATOR_REGISTER_TRACE(probe_name) \
+ register_trace_##probe_name(probe_##probe_name)
+# define GATOR_UNREGISTER_TRACE(probe_name) \
+ unregister_trace_##probe_name(probe_##probe_name)
+#elif LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+# define GATOR_DEFINE_PROBE(probe_name, proto) \
+ static void probe_##probe_name(void *data, PARAMS(proto))
+# define GATOR_REGISTER_TRACE(probe_name) \
+ register_trace_##probe_name(probe_##probe_name, NULL)
+# define GATOR_UNREGISTER_TRACE(probe_name) \
+ unregister_trace_##probe_name(probe_##probe_name, NULL)
+#else
+# define GATOR_DEFINE_PROBE(probe_name, proto) \
+ extern struct tracepoint *gator_tracepoint_##probe_name; \
+ static void probe_##probe_name(void *data, PARAMS(proto))
+# define GATOR_REGISTER_TRACE(probe_name) \
+ ((gator_tracepoint_##probe_name == NULL) || tracepoint_probe_register(gator_tracepoint_##probe_name, probe_##probe_name, NULL))
+# define GATOR_UNREGISTER_TRACE(probe_name) \
+ tracepoint_probe_unregister(gator_tracepoint_##probe_name, probe_##probe_name, NULL)
+#endif
+
+/******************************************************************************
+ * Events
+ ******************************************************************************/
+struct gator_interface {
+ /* Complementary function to init */
+ void (*shutdown)(void);
+ int (*create_files)(struct super_block *sb, struct dentry *root);
+ int (*start)(void);
+ /* Complementary function to start */
+ void (*stop)(void);
+ int (*online)(int **buffer, bool migrate);
+ int (*offline)(int **buffer, bool migrate);
+ /* called in process context but may not be running on core 'cpu' */
+ void (*online_dispatch)(int cpu, bool migrate);
+ /* called in process context but may not be running on core 'cpu' */
+ void (*offline_dispatch)(int cpu, bool migrate);
+ int (*read)(int **buffer, bool sched_switch);
+ int (*read64)(long long **buffer);
+ int (*read_proc)(long long **buffer, struct task_struct *);
+ struct list_head list;
+};
+
+int gator_events_install(struct gator_interface *interface);
+int gator_events_get_key(void);
+u32 gator_cpuid(void);
+
+void gator_backtrace_handler(struct pt_regs *const regs);
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid);
+
+#if !GATOR_IKS_SUPPORT
+
+#define get_physical_cpu() smp_processor_id()
+#define lcpu_to_pcpu(lcpu) lcpu
+#define pcpu_to_lcpu(pcpu) pcpu
+
+#else
+
+#define get_physical_cpu() lcpu_to_pcpu(get_logical_cpu())
+int lcpu_to_pcpu(const int lcpu);
+int pcpu_to_lcpu(const int pcpu);
+
+#endif
+
+#define get_logical_cpu() smp_processor_id()
+#define on_primary_core() (get_logical_cpu() == 0)
+
+#endif /* GATOR_H_ */
diff --git a/drivers/gator/gator_annotate.c b/drivers/gator/gator_annotate.c
new file mode 100644
index 0000000..cc9ae02
--- /dev/null
+++ b/drivers/gator/gator_annotate.c
@@ -0,0 +1,189 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <asm/current.h>
+#include <linux/spinlock.h>
+
+static DEFINE_SPINLOCK(annotate_lock);
+static bool collect_annotations;
+
+static int annotate_copy(struct file *file, char const __user *buf, size_t count)
+{
+ int cpu = 0;
+ int write = per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF];
+
+ if (file == NULL) {
+ /* copy from kernel */
+ memcpy(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count);
+ } else {
+ /* copy from user space */
+ if (copy_from_user(&per_cpu(gator_buffer, cpu)[ANNOTATE_BUF][write], buf, count) != 0)
+ return -1;
+ }
+ per_cpu(gator_buffer_write, cpu)[ANNOTATE_BUF] = (write + count) & gator_buffer_mask[ANNOTATE_BUF];
+
+ return 0;
+}
+
+static ssize_t annotate_write(struct file *file, char const __user *buf, size_t count_orig, loff_t *offset)
+{
+ int pid, cpu, header_size, available, contiguous, length1, length2, size, count = count_orig & 0x7fffffff;
+ bool interrupt_context;
+
+ if (*offset)
+ return -EINVAL;
+
+ interrupt_context = in_interrupt();
+ /* Annotations are not supported in interrupt context, but may work
+ * if you comment out the the next four lines of code. By doing so,
+ * annotations in interrupt context can result in deadlocks and lost
+ * data.
+ */
+ if (interrupt_context) {
+ pr_warning("gator: Annotations are not supported in interrupt context. Edit gator_annotate.c in the gator driver to enable annotations in interrupt context.\n");
+ return -EINVAL;
+ }
+
+ retry:
+ /* synchronize between cores and with collect_annotations */
+ spin_lock(&annotate_lock);
+
+ if (!collect_annotations) {
+ /* Not collecting annotations, tell the caller everything was written */
+ size = count_orig;
+ goto annotate_write_out;
+ }
+
+ /* Annotation only uses a single per-cpu buffer as the data must be in order to the engine */
+ cpu = 0;
+
+ if (current == NULL)
+ pid = 0;
+ else
+ pid = current->pid;
+
+ /* determine total size of the payload */
+ header_size = MAXSIZE_PACK32 * 3 + MAXSIZE_PACK64;
+ available = buffer_bytes_available(cpu, ANNOTATE_BUF) - header_size;
+ size = count < available ? count : available;
+
+ if (size <= 0) {
+ /* Buffer is full, wait until space is available */
+ spin_unlock(&annotate_lock);
+
+ /* Drop the annotation as blocking is not allowed in interrupt context */
+ if (interrupt_context)
+ return -EINVAL;
+
+ wait_event_interruptible(gator_annotate_wait, buffer_bytes_available(cpu, ANNOTATE_BUF) > header_size || !collect_annotations);
+
+ /* Check to see if a signal is pending */
+ if (signal_pending(current))
+ return -EINTR;
+
+ goto retry;
+ }
+
+ /* synchronize shared variables annotateBuf and annotatePos */
+ if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF]) {
+ u64 time = gator_get_time();
+
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+ gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, time);
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, size);
+
+ /* determine the sizes to capture, length1 + length2 will equal size */
+ contiguous = contiguous_space_available(cpu, ANNOTATE_BUF);
+ if (size < contiguous) {
+ length1 = size;
+ length2 = 0;
+ } else {
+ length1 = contiguous;
+ length2 = size - contiguous;
+ }
+
+ if (annotate_copy(file, buf, length1) != 0) {
+ size = -EINVAL;
+ goto annotate_write_out;
+ }
+
+ if (length2 > 0 && annotate_copy(file, &buf[length1], length2) != 0) {
+ size = -EINVAL;
+ goto annotate_write_out;
+ }
+
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, ANNOTATE_BUF, time);
+ }
+
+annotate_write_out:
+ spin_unlock(&annotate_lock);
+
+ /* return the number of bytes written */
+ return size;
+}
+
+#include "gator_annotate_kernel.c"
+
+static int annotate_release(struct inode *inode, struct file *file)
+{
+ int cpu = 0;
+
+ /* synchronize between cores */
+ spin_lock(&annotate_lock);
+
+ if (per_cpu(gator_buffer, cpu)[ANNOTATE_BUF] && buffer_check_space(cpu, ANNOTATE_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+ uint32_t pid = current->pid;
+
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, get_physical_cpu());
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, pid);
+ /* time */
+ gator_buffer_write_packed_int64(cpu, ANNOTATE_BUF, 0);
+ /* size */
+ gator_buffer_write_packed_int(cpu, ANNOTATE_BUF, 0);
+ }
+
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, ANNOTATE_BUF, gator_get_time());
+
+ spin_unlock(&annotate_lock);
+
+ return 0;
+}
+
+static const struct file_operations annotate_fops = {
+ .write = annotate_write,
+ .release = annotate_release
+};
+
+static int gator_annotate_create_files(struct super_block *sb, struct dentry *root)
+{
+ return gatorfs_create_file_perm(sb, root, "annotate", &annotate_fops, 0666);
+}
+
+static int gator_annotate_start(void)
+{
+ collect_annotations = true;
+ return 0;
+}
+
+static void gator_annotate_stop(void)
+{
+ /* the spinlock here will ensure that when this function exits, we are not in the middle of an annotation */
+ spin_lock(&annotate_lock);
+ collect_annotations = false;
+ wake_up(&gator_annotate_wait);
+ spin_unlock(&annotate_lock);
+}
diff --git a/drivers/gator/gator_annotate_kernel.c b/drivers/gator/gator_annotate_kernel.c
new file mode 100644
index 0000000..54e8e86
--- /dev/null
+++ b/drivers/gator/gator_annotate_kernel.c
@@ -0,0 +1,200 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define ESCAPE_CODE 0x1c
+#define STRING_ANNOTATION 0x06
+#define NAME_CHANNEL_ANNOTATION 0x07
+#define NAME_GROUP_ANNOTATION 0x08
+#define VISUAL_ANNOTATION 0x04
+#define MARKER_ANNOTATION 0x05
+
+static void kannotate_write(const char *ptr, unsigned int size)
+{
+ int retval;
+ int pos = 0;
+ loff_t offset = 0;
+
+ while (pos < size) {
+ retval = annotate_write(NULL, &ptr[pos], size - pos, &offset);
+ if (retval < 0) {
+ pr_warning("gator: kannotate_write failed with return value %d\n", retval);
+ return;
+ }
+ pos += retval;
+ }
+}
+
+static void marshal_u16(char *buf, u16 val)
+{
+ buf[0] = val & 0xff;
+ buf[1] = (val >> 8) & 0xff;
+}
+
+static void marshal_u32(char *buf, u32 val)
+{
+ buf[0] = val & 0xff;
+ buf[1] = (val >> 8) & 0xff;
+ buf[2] = (val >> 16) & 0xff;
+ buf[3] = (val >> 24) & 0xff;
+}
+
+void gator_annotate_channel(int channel, const char *str)
+{
+ const u16 str_size = strlen(str) & 0xffff;
+ char header[8];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = STRING_ANNOTATION;
+ marshal_u32(header + 2, channel);
+ marshal_u16(header + 6, str_size);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_channel);
+
+void gator_annotate(const char *str)
+{
+ gator_annotate_channel(0, str);
+}
+EXPORT_SYMBOL(gator_annotate);
+
+void gator_annotate_channel_color(int channel, int color, const char *str)
+{
+ const u16 str_size = (strlen(str) + 4) & 0xffff;
+ char header[12];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = STRING_ANNOTATION;
+ marshal_u32(header + 2, channel);
+ marshal_u16(header + 6, str_size);
+ marshal_u32(header + 8, color);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_channel_color);
+
+void gator_annotate_color(int color, const char *str)
+{
+ gator_annotate_channel_color(0, color, str);
+}
+EXPORT_SYMBOL(gator_annotate_color);
+
+void gator_annotate_channel_end(int channel)
+{
+ char header[8];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = STRING_ANNOTATION;
+ marshal_u32(header + 2, channel);
+ marshal_u16(header + 6, 0);
+ kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_channel_end);
+
+void gator_annotate_end(void)
+{
+ gator_annotate_channel_end(0);
+}
+EXPORT_SYMBOL(gator_annotate_end);
+
+void gator_annotate_name_channel(int channel, int group, const char *str)
+{
+ const u16 str_size = strlen(str) & 0xffff;
+ char header[12];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = NAME_CHANNEL_ANNOTATION;
+ marshal_u32(header + 2, channel);
+ marshal_u32(header + 6, group);
+ marshal_u16(header + 10, str_size);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_channel);
+
+void gator_annotate_name_group(int group, const char *str)
+{
+ const u16 str_size = strlen(str) & 0xffff;
+ char header[8];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = NAME_GROUP_ANNOTATION;
+ marshal_u32(header + 2, group);
+ marshal_u16(header + 6, str_size);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_name_group);
+
+void gator_annotate_visual(const char *data, unsigned int length, const char *str)
+{
+ const u16 str_size = strlen(str) & 0xffff;
+ char header[4];
+ char header_length[4];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = VISUAL_ANNOTATION;
+ marshal_u16(header + 2, str_size);
+ marshal_u32(header_length, length);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size);
+ kannotate_write(header_length, sizeof(header_length));
+ kannotate_write(data, length);
+}
+EXPORT_SYMBOL(gator_annotate_visual);
+
+void gator_annotate_marker(void)
+{
+ char header[4];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = MARKER_ANNOTATION;
+ marshal_u16(header + 2, 0);
+ kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker);
+
+void gator_annotate_marker_str(const char *str)
+{
+ const u16 str_size = strlen(str) & 0xffff;
+ char header[4];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = MARKER_ANNOTATION;
+ marshal_u16(header + 2, str_size);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size);
+}
+EXPORT_SYMBOL(gator_annotate_marker_str);
+
+void gator_annotate_marker_color(int color)
+{
+ char header[8];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = MARKER_ANNOTATION;
+ marshal_u16(header + 2, 4);
+ marshal_u32(header + 4, color);
+ kannotate_write(header, sizeof(header));
+}
+EXPORT_SYMBOL(gator_annotate_marker_color);
+
+void gator_annotate_marker_color_str(int color, const char *str)
+{
+ const u16 str_size = (strlen(str) + 4) & 0xffff;
+ char header[8];
+
+ header[0] = ESCAPE_CODE;
+ header[1] = MARKER_ANNOTATION;
+ marshal_u16(header + 2, str_size);
+ marshal_u32(header + 4, color);
+ kannotate_write(header, sizeof(header));
+ kannotate_write(str, str_size - 4);
+}
+EXPORT_SYMBOL(gator_annotate_marker_color_str);
diff --git a/drivers/gator/gator_backtrace.c b/drivers/gator/gator_backtrace.c
new file mode 100644
index 0000000..5557ec0b
--- /dev/null
+++ b/drivers/gator/gator_backtrace.c
@@ -0,0 +1,208 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * EABI backtrace stores {fp,lr} on the stack.
+ */
+struct stack_frame_eabi {
+ union {
+ struct {
+ unsigned long fp;
+ /* May be the fp in the case of a leaf function or clang */
+ unsigned long lr;
+ /* If lr is really the fp, lr2 is the corresponding lr */
+ unsigned long lr2;
+ };
+ /* Used to read 32 bit fp/lr from a 64 bit kernel */
+ struct {
+ u32 fp_32;
+ /* same as lr above */
+ u32 lr_32;
+ /* same as lr2 above */
+ u32 lr2_32;
+ };
+ };
+};
+
+static void gator_add_trace(int cpu, unsigned long address)
+{
+ off_t offset = 0;
+ unsigned long cookie = get_address_cookie(cpu, current, address & ~1, &offset);
+
+ if (cookie == NO_COOKIE || cookie == UNRESOLVED_COOKIE)
+ offset = address;
+
+ marshal_backtrace(offset & ~1, cookie, 0);
+}
+
+static void arm_backtrace_eabi(int cpu, struct pt_regs *const regs, unsigned int depth)
+{
+#if defined(__arm__) || defined(__aarch64__)
+ struct stack_frame_eabi *curr;
+ struct stack_frame_eabi bufcurr;
+#if defined(__arm__)
+ const bool is_compat = false;
+ unsigned long fp = regs->ARM_fp;
+ unsigned long sp = regs->ARM_sp;
+ unsigned long lr = regs->ARM_lr;
+ const int gcc_frame_offset = sizeof(unsigned long);
+#else
+ /* Is userspace aarch32 (32 bit) */
+ const bool is_compat = compat_user_mode(regs);
+ unsigned long fp = (is_compat ? regs->regs[11] : regs->regs[29]);
+ unsigned long sp = (is_compat ? regs->compat_sp : regs->sp);
+ unsigned long lr = (is_compat ? regs->compat_lr : regs->regs[30]);
+ const int gcc_frame_offset = (is_compat ? sizeof(u32) : 0);
+#endif
+ /* clang frame offset is always zero */
+ int is_user_mode = user_mode(regs);
+
+ /* pc (current function) has already been added */
+
+ if (!is_user_mode)
+ return;
+
+ /* Add the lr (parent function), entry preamble may not have
+ * executed
+ */
+ gator_add_trace(cpu, lr);
+
+ /* check fp is valid */
+ if (fp == 0 || fp < sp)
+ return;
+
+ /* Get the current stack frame */
+ curr = (struct stack_frame_eabi *)(fp - gcc_frame_offset);
+ if ((unsigned long)curr & 3)
+ return;
+
+ while (depth-- && curr) {
+ if (!access_ok(VERIFY_READ, curr, sizeof(struct stack_frame_eabi)) ||
+ __copy_from_user_inatomic(&bufcurr, curr, sizeof(struct stack_frame_eabi))) {
+ return;
+ }
+
+ fp = (is_compat ? bufcurr.fp_32 : bufcurr.fp);
+ lr = (is_compat ? bufcurr.lr_32 : bufcurr.lr);
+
+#define calc_next(reg) ((reg) - gcc_frame_offset)
+ /* Returns true if reg is a valid fp */
+#define validate_next(reg, curr) \
+ ((reg) != 0 && (calc_next(reg) & 3) == 0 && (unsigned long)(curr) < calc_next(reg))
+
+ /* Try lr from the stack as the fp because gcc leaf functions do
+ * not push lr. If gcc_frame_offset is non-zero, the lr will also
+ * be the clang fp. This assumes code is at a lower address than
+ * the stack
+ */
+ if (validate_next(lr, curr)) {
+ fp = lr;
+ lr = (is_compat ? bufcurr.lr2_32 : bufcurr.lr2);
+ }
+
+ gator_add_trace(cpu, lr);
+
+ if (!validate_next(fp, curr))
+ return;
+
+ /* Move to the next stack frame */
+ curr = (struct stack_frame_eabi *)calc_next(fp);
+ }
+#endif
+}
+
+#if defined(__arm__) || defined(__aarch64__)
+static int report_trace(struct stackframe *frame, void *d)
+{
+ unsigned int *depth = d, cookie = NO_COOKIE;
+ unsigned long addr = frame->pc;
+
+ if (*depth) {
+#if defined(MODULE)
+ unsigned int cpu = get_physical_cpu();
+ struct module *mod = __module_address(addr);
+
+ if (mod) {
+ cookie = get_cookie(cpu, current, mod->name, false);
+ addr = addr - (unsigned long)mod->module_core;
+ }
+#endif
+ marshal_backtrace(addr & ~1, cookie, 1);
+ (*depth)--;
+ }
+
+ return *depth == 0;
+}
+#endif
+
+/* Uncomment the following line to enable kernel stack unwinding within gator, note it can also be defined from the Makefile */
+/* #define GATOR_KERNEL_STACK_UNWINDING */
+
+#if (defined(__arm__) || defined(__aarch64__)) && !defined(GATOR_KERNEL_STACK_UNWINDING)
+/* Disabled by default */
+MODULE_PARM_DESC(kernel_stack_unwinding, "Allow kernel stack unwinding.");
+static bool kernel_stack_unwinding;
+module_param(kernel_stack_unwinding, bool, 0644);
+#endif
+
+static void kernel_backtrace(int cpu, struct pt_regs *const regs)
+{
+#if defined(__arm__) || defined(__aarch64__)
+#ifdef GATOR_KERNEL_STACK_UNWINDING
+ int depth = gator_backtrace_depth;
+#else
+ int depth = (kernel_stack_unwinding ? gator_backtrace_depth : 1);
+#endif
+ struct stackframe frame;
+
+ if (depth == 0)
+ depth = 1;
+#if defined(__arm__)
+ frame.fp = regs->ARM_fp;
+ frame.sp = regs->ARM_sp;
+ frame.lr = regs->ARM_lr;
+ frame.pc = regs->ARM_pc;
+#else
+ frame.fp = regs->regs[29];
+ frame.sp = regs->sp;
+ frame.pc = regs->pc;
+#endif
+ walk_stackframe(&frame, report_trace, &depth);
+#else
+ marshal_backtrace(PC_REG & ~1, NO_COOKIE, 1);
+#endif
+}
+
+static void gator_add_sample(int cpu, struct pt_regs *const regs, u64 time)
+{
+ bool in_kernel;
+ unsigned long exec_cookie;
+
+ if (!regs)
+ return;
+
+ in_kernel = !user_mode(regs);
+ exec_cookie = get_exec_cookie(cpu, current);
+
+ if (!marshal_backtrace_header(exec_cookie, current->tgid, current->pid, time))
+ return;
+
+ if (in_kernel) {
+ kernel_backtrace(cpu, regs);
+ } else {
+ /* Cookie+PC */
+ gator_add_trace(cpu, PC_REG);
+
+ /* Backtrace */
+ if (gator_backtrace_depth)
+ arm_backtrace_eabi(cpu, regs, gator_backtrace_depth);
+ }
+
+ marshal_backtrace_footer(time);
+}
diff --git a/drivers/gator/gator_buffer.c b/drivers/gator/gator_buffer.c
new file mode 100644
index 0000000..f335457
--- /dev/null
+++ b/drivers/gator/gator_buffer.c
@@ -0,0 +1,171 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void marshal_frame(int cpu, int buftype)
+{
+ int frame;
+ bool write_cpu;
+
+ if (!per_cpu(gator_buffer, cpu)[buftype])
+ return;
+
+ switch (buftype) {
+ case SUMMARY_BUF:
+ write_cpu = false;
+ frame = FRAME_SUMMARY;
+ break;
+ case BACKTRACE_BUF:
+ write_cpu = true;
+ frame = FRAME_BACKTRACE;
+ break;
+ case NAME_BUF:
+ write_cpu = true;
+ frame = FRAME_NAME;
+ break;
+ case COUNTER_BUF:
+ write_cpu = false;
+ frame = FRAME_COUNTER;
+ break;
+ case BLOCK_COUNTER_BUF:
+ write_cpu = true;
+ frame = FRAME_BLOCK_COUNTER;
+ break;
+ case ANNOTATE_BUF:
+ write_cpu = false;
+ frame = FRAME_ANNOTATE;
+ break;
+ case SCHED_TRACE_BUF:
+ write_cpu = true;
+ frame = FRAME_SCHED_TRACE;
+ break;
+ case IDLE_BUF:
+ write_cpu = false;
+ frame = FRAME_IDLE;
+ break;
+ case ACTIVITY_BUF:
+ write_cpu = false;
+ frame = FRAME_ACTIVITY;
+ break;
+ default:
+ write_cpu = false;
+ frame = -1;
+ break;
+ }
+
+ /* add response type */
+ if (gator_response_type > 0)
+ gator_buffer_write_packed_int(cpu, buftype, gator_response_type);
+
+ /* leave space for 4-byte unpacked length */
+ per_cpu(gator_buffer_write, cpu)[buftype] = (per_cpu(gator_buffer_write, cpu)[buftype] + sizeof(s32)) & gator_buffer_mask[buftype];
+
+ /* add frame type and core number */
+ gator_buffer_write_packed_int(cpu, buftype, frame);
+ if (write_cpu)
+ gator_buffer_write_packed_int(cpu, buftype, cpu);
+}
+
+static int buffer_bytes_available(int cpu, int buftype)
+{
+ int remaining, filled;
+
+ filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_read, cpu)[buftype];
+ if (filled < 0)
+ filled += gator_buffer_size[buftype];
+
+ remaining = gator_buffer_size[buftype] - filled;
+
+ if (per_cpu(buffer_space_available, cpu)[buftype])
+ /* Give some extra room; also allows space to insert the overflow error packet */
+ remaining -= 200;
+ else
+ /* Hysteresis, prevents multiple overflow messages */
+ remaining -= 2000;
+
+ return remaining;
+}
+
+static bool buffer_check_space(int cpu, int buftype, int bytes)
+{
+ int remaining = buffer_bytes_available(cpu, buftype);
+
+ if (remaining < bytes)
+ per_cpu(buffer_space_available, cpu)[buftype] = false;
+ else
+ per_cpu(buffer_space_available, cpu)[buftype] = true;
+
+ return per_cpu(buffer_space_available, cpu)[buftype];
+}
+
+static int contiguous_space_available(int cpu, int buftype)
+{
+ int remaining = buffer_bytes_available(cpu, buftype);
+ int contiguous = gator_buffer_size[buftype] - per_cpu(gator_buffer_write, cpu)[buftype];
+
+ if (remaining < contiguous)
+ return remaining;
+ return contiguous;
+}
+
+static void gator_commit_buffer(int cpu, int buftype, u64 time)
+{
+ int type_length, commit, length, byte;
+ unsigned long flags;
+
+ if (!per_cpu(gator_buffer, cpu)[buftype])
+ return;
+
+ /* post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload */
+ local_irq_save(flags);
+ type_length = gator_response_type ? 1 : 0;
+ commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+ length = per_cpu(gator_buffer_write, cpu)[buftype] - commit;
+ if (length < 0)
+ length += gator_buffer_size[buftype];
+ length = length - type_length - sizeof(s32);
+
+ if (length <= FRAME_HEADER_SIZE) {
+ /* Nothing to write, only the frame header is present */
+ local_irq_restore(flags);
+ return;
+ }
+
+ for (byte = 0; byte < sizeof(s32); byte++)
+ per_cpu(gator_buffer, cpu)[buftype][(commit + type_length + byte) & gator_buffer_mask[buftype]] = (length >> byte * 8) & 0xFF;
+
+ per_cpu(gator_buffer_commit, cpu)[buftype] = per_cpu(gator_buffer_write, cpu)[buftype];
+
+ if (gator_live_rate > 0) {
+ while (time > per_cpu(gator_buffer_commit_time, cpu))
+ per_cpu(gator_buffer_commit_time, cpu) += gator_live_rate;
+ }
+
+ marshal_frame(cpu, buftype);
+ local_irq_restore(flags);
+
+ /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+ if (per_cpu(in_scheduler_context, cpu)) {
+#ifndef CONFIG_PREEMPT_RT_FULL
+ /* mod_timer can not be used in interrupt context in RT-Preempt full */
+ mod_timer(&gator_buffer_wake_up_timer, jiffies + 1);
+#endif
+ } else {
+ up(&gator_buffer_wake_sem);
+ }
+}
+
+static void buffer_check(int cpu, int buftype, u64 time)
+{
+ int filled = per_cpu(gator_buffer_write, cpu)[buftype] - per_cpu(gator_buffer_commit, cpu)[buftype];
+
+ if (filled < 0)
+ filled += gator_buffer_size[buftype];
+ if (filled >= ((gator_buffer_size[buftype] * 3) / 4))
+ gator_commit_buffer(cpu, buftype, time);
+}
diff --git a/drivers/gator/gator_buffer_write.c b/drivers/gator/gator_buffer_write.c
new file mode 100644
index 0000000..b731e6a
--- /dev/null
+++ b/drivers/gator/gator_buffer_write.c
@@ -0,0 +1,83 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+static void gator_buffer_write_packed_int(int cpu, int buftype, int x)
+{
+ uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+ uint32_t mask = gator_buffer_mask[buftype];
+ char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+ int packedBytes = 0;
+ int more = true;
+
+ while (more) {
+ /* low order 7 bits of x */
+ char b = x & 0x7f;
+
+ x >>= 7;
+
+ if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+ more = false;
+ else
+ b |= 0x80;
+
+ buffer[(write + packedBytes) & mask] = b;
+ packedBytes++;
+ }
+
+ per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_packed_int64(int cpu, int buftype, long long x)
+{
+ uint32_t write = per_cpu(gator_buffer_write, cpu)[buftype];
+ uint32_t mask = gator_buffer_mask[buftype];
+ char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+ int packedBytes = 0;
+ int more = true;
+
+ while (more) {
+ /* low order 7 bits of x */
+ char b = x & 0x7f;
+
+ x >>= 7;
+
+ if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0))
+ more = false;
+ else
+ b |= 0x80;
+
+ buffer[(write + packedBytes) & mask] = b;
+ packedBytes++;
+ }
+
+ per_cpu(gator_buffer_write, cpu)[buftype] = (write + packedBytes) & mask;
+}
+
+static void gator_buffer_write_bytes(int cpu, int buftype, const char *x, int len)
+{
+ int i;
+ u32 write = per_cpu(gator_buffer_write, cpu)[buftype];
+ u32 mask = gator_buffer_mask[buftype];
+ char *buffer = per_cpu(gator_buffer, cpu)[buftype];
+
+ for (i = 0; i < len; i++) {
+ buffer[write] = x[i];
+ write = (write + 1) & mask;
+ }
+
+ per_cpu(gator_buffer_write, cpu)[buftype] = write;
+}
+
+static void gator_buffer_write_string(int cpu, int buftype, const char *x)
+{
+ int len = strlen(x);
+
+ gator_buffer_write_packed_int(cpu, buftype, len);
+ gator_buffer_write_bytes(cpu, buftype, x, len);
+}
diff --git a/drivers/gator/gator_cookies.c b/drivers/gator/gator_cookies.c
new file mode 100644
index 0000000..9bd4c8b
--- /dev/null
+++ b/drivers/gator/gator_cookies.c
@@ -0,0 +1,446 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* must be power of 2 */
+#define COOKIEMAP_ENTRIES 1024
+/* must be a power of 2 - 512/4 = 128 entries */
+#define TRANSLATE_BUFFER_SIZE 512
+#define TRANSLATE_TEXT_SIZE 256
+#define MAX_COLLISIONS 2
+
+static uint32_t *gator_crc32_table;
+static unsigned int translate_buffer_mask;
+
+struct cookie_args {
+ struct task_struct *task;
+ const char *text;
+};
+
+static DEFINE_PER_CPU(char *, translate_text);
+static DEFINE_PER_CPU(uint32_t, cookie_next_key);
+static DEFINE_PER_CPU(uint64_t *, cookie_keys);
+static DEFINE_PER_CPU(uint32_t *, cookie_values);
+static DEFINE_PER_CPU(int, translate_buffer_read);
+static DEFINE_PER_CPU(int, translate_buffer_write);
+static DEFINE_PER_CPU(struct cookie_args *, translate_buffer);
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq);
+static void wq_cookie_handler(struct work_struct *unused);
+static DECLARE_WORK(cookie_work, wq_cookie_handler);
+static struct timer_list app_process_wake_up_timer;
+static void app_process_wake_up_handler(unsigned long unused_data);
+
+static uint32_t cookiemap_code(uint64_t value64)
+{
+ uint32_t value = (uint32_t)((value64 >> 32) + value64);
+ uint32_t cookiecode = (value >> 24) & 0xff;
+
+ cookiecode = cookiecode * 31 + ((value >> 16) & 0xff);
+ cookiecode = cookiecode * 31 + ((value >> 8) & 0xff);
+ cookiecode = cookiecode * 31 + ((value >> 0) & 0xff);
+ cookiecode &= (COOKIEMAP_ENTRIES - 1);
+ return cookiecode * MAX_COLLISIONS;
+}
+
+static uint32_t gator_chksum_crc32(const char *data)
+{
+ register unsigned long crc;
+ const unsigned char *block = data;
+ int i, length = strlen(data);
+
+ crc = 0xFFFFFFFF;
+ for (i = 0; i < length; i++)
+ crc = ((crc >> 8) & 0x00FFFFFF) ^ gator_crc32_table[(crc ^ *block++) & 0xFF];
+
+ return (crc ^ 0xFFFFFFFF);
+}
+
+/*
+ * Exists
+ * Pre: [0][1][v][3]..[n-1]
+ * Post: [v][0][1][3]..[n-1]
+ */
+static uint32_t cookiemap_exists(uint64_t key)
+{
+ unsigned long x, flags, retval = 0;
+ int cpu = get_physical_cpu();
+ uint32_t cookiecode = cookiemap_code(key);
+ uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+ uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+
+ /* Can be called from interrupt handler or from work queue */
+ local_irq_save(flags);
+ for (x = 0; x < MAX_COLLISIONS; x++) {
+ if (keys[x] == key) {
+ uint32_t value = values[x];
+
+ for (; x > 0; x--) {
+ keys[x] = keys[x - 1];
+ values[x] = values[x - 1];
+ }
+ keys[0] = key;
+ values[0] = value;
+ retval = value;
+ break;
+ }
+ }
+ local_irq_restore(flags);
+
+ return retval;
+}
+
+/*
+ * Add
+ * Pre: [0][1][2][3]..[n-1]
+ * Post: [v][0][1][2]..[n-2]
+ */
+static void cookiemap_add(uint64_t key, uint32_t value)
+{
+ int cpu = get_physical_cpu();
+ int cookiecode = cookiemap_code(key);
+ uint64_t *keys = &(per_cpu(cookie_keys, cpu)[cookiecode]);
+ uint32_t *values = &(per_cpu(cookie_values, cpu)[cookiecode]);
+ int x;
+
+ for (x = MAX_COLLISIONS - 1; x > 0; x--) {
+ keys[x] = keys[x - 1];
+ values[x] = values[x - 1];
+ }
+ keys[0] = key;
+ values[0] = value;
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+static void translate_buffer_write_args(int cpu, struct task_struct *task, const char *text)
+{
+ unsigned long flags;
+ int write;
+ int next_write;
+ struct cookie_args *args;
+
+ local_irq_save(flags);
+
+ write = per_cpu(translate_buffer_write, cpu);
+ next_write = (write + 1) & translate_buffer_mask;
+
+ /* At least one entry must always remain available as when read == write, the queue is empty not full */
+ if (next_write != per_cpu(translate_buffer_read, cpu)) {
+ args = &per_cpu(translate_buffer, cpu)[write];
+ args->task = task;
+ args->text = text;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+ get_task_struct(task);
+#endif
+ per_cpu(translate_buffer_write, cpu) = next_write;
+ }
+
+ local_irq_restore(flags);
+}
+#endif
+
+static void translate_buffer_read_args(int cpu, struct cookie_args *args)
+{
+ unsigned long flags;
+ int read;
+
+ local_irq_save(flags);
+
+ read = per_cpu(translate_buffer_read, cpu);
+ *args = per_cpu(translate_buffer, cpu)[read];
+ per_cpu(translate_buffer_read, cpu) = (read + 1) & translate_buffer_mask;
+
+ local_irq_restore(flags);
+}
+
+static void wq_cookie_handler(struct work_struct *unused)
+{
+ struct cookie_args args;
+ int cpu = get_physical_cpu(), cookie;
+
+ mutex_lock(&start_mutex);
+
+ if (gator_started != 0) {
+ while (per_cpu(translate_buffer_read, cpu) != per_cpu(translate_buffer_write, cpu)) {
+ translate_buffer_read_args(cpu, &args);
+ cookie = get_cookie(cpu, args.task, args.text, true);
+ marshal_link(cookie, args.task->tgid, args.task->pid);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 39)
+ put_task_struct(args.task);
+#endif
+ }
+ }
+
+ mutex_unlock(&start_mutex);
+}
+
+static void app_process_wake_up_handler(unsigned long unused_data)
+{
+ /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+ schedule_work(&cookie_work);
+}
+
+/* Retrieve full name from proc/pid/cmdline for java processes on Android */
+static int translate_app_process(const char **text, int cpu, struct task_struct *task, bool from_wq)
+{
+ void *maddr;
+ unsigned int len;
+ unsigned long addr;
+ struct mm_struct *mm;
+ struct page *page = NULL;
+ struct vm_area_struct *page_vma;
+ int bytes, offset, retval = 0;
+ char *buf = per_cpu(translate_text, cpu);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+ /* Push work into a work queue if in atomic context as the kernel
+ * functions below might sleep. Rely on the in_interrupt variable
+ * rather than in_irq() or in_interrupt() kernel functions, as the
+ * value of these functions seems inconsistent during a context
+ * switch between android/linux versions
+ */
+ if (!from_wq) {
+ /* Check if already in buffer */
+ int pos = per_cpu(translate_buffer_read, cpu);
+
+ while (pos != per_cpu(translate_buffer_write, cpu)) {
+ if (per_cpu(translate_buffer, cpu)[pos].task == task)
+ goto out;
+ pos = (pos + 1) & translate_buffer_mask;
+ }
+
+ translate_buffer_write_args(cpu, task, *text);
+
+ /* Not safe to call in RT-Preempt full in schedule switch context */
+ mod_timer(&app_process_wake_up_timer, jiffies + 1);
+ goto out;
+ }
+#endif
+
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out;
+ if (!mm->arg_end)
+ goto outmm;
+ addr = mm->arg_start;
+ len = mm->arg_end - mm->arg_start;
+
+ if (len > TRANSLATE_TEXT_SIZE)
+ len = TRANSLATE_TEXT_SIZE;
+
+ down_read(&mm->mmap_sem);
+ while (len) {
+ if (get_user_pages(task, mm, addr, 1, 0, 1, &page, &page_vma) <= 0)
+ goto outsem;
+
+ maddr = kmap(page);
+ offset = addr & (PAGE_SIZE - 1);
+ bytes = len;
+ if (bytes > PAGE_SIZE - offset)
+ bytes = PAGE_SIZE - offset;
+
+ copy_from_user_page(page_vma, page, addr, buf, maddr + offset, bytes);
+
+ /* release page allocated by get_user_pages() */
+ kunmap(page);
+ page_cache_release(page);
+
+ len -= bytes;
+ buf += bytes;
+ addr += bytes;
+
+ *text = per_cpu(translate_text, cpu);
+ retval = 1;
+ }
+
+ /* On app_process startup, /proc/pid/cmdline is initially "zygote" then "<pre-initialized>" but changes after an initial startup period */
+ if (strcmp(*text, "zygote") == 0 || strcmp(*text, "<pre-initialized>") == 0)
+ retval = 0;
+
+outsem:
+ up_read(&mm->mmap_sem);
+outmm:
+ mmput(mm);
+out:
+ return retval;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static uint32_t get_cookie(int cpu, struct task_struct *task, const char *text, bool from_wq)
+{
+ unsigned long flags, cookie;
+ uint64_t key;
+
+ key = gator_chksum_crc32(text);
+ key = (key << 32) | (uint32_t)task->tgid;
+
+ cookie = cookiemap_exists(key);
+ if (cookie)
+ return cookie;
+
+ /* On 64-bit android app_process can be app_process32 or app_process64 */
+ if (strncmp(text, APP_PROCESS, sizeof(APP_PROCESS) - 1) == 0) {
+ if (!translate_app_process(&text, cpu, task, from_wq))
+ return UNRESOLVED_COOKIE;
+ }
+
+ /* Can be called from interrupt handler or from work queue or from scheduler trace */
+ local_irq_save(flags);
+
+ cookie = UNRESOLVED_COOKIE;
+ if (marshal_cookie_header(text)) {
+ cookie = per_cpu(cookie_next_key, cpu) += nr_cpu_ids;
+ cookiemap_add(key, cookie);
+ marshal_cookie(cookie, text);
+ }
+
+ local_irq_restore(flags);
+
+ return cookie;
+}
+
+static int get_exec_cookie(int cpu, struct task_struct *task)
+{
+ struct mm_struct *mm = task->mm;
+ const char *text;
+
+ /* kernel threads have no address space */
+ if (!mm)
+ return NO_COOKIE;
+
+ if (task && task->mm && task->mm->exe_file) {
+ text = task->mm->exe_file->f_path.dentry->d_name.name;
+ return get_cookie(cpu, task, text, false);
+ }
+
+ return UNRESOLVED_COOKIE;
+}
+
+static unsigned long get_address_cookie(int cpu, struct task_struct *task, unsigned long addr, off_t *offset)
+{
+ unsigned long cookie = NO_COOKIE;
+ struct mm_struct *mm = task->mm;
+ struct vm_area_struct *vma;
+ const char *text;
+
+ if (!mm)
+ return cookie;
+
+ for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
+ if (addr < vma->vm_start || addr >= vma->vm_end)
+ continue;
+
+ if (vma->vm_file) {
+ text = vma->vm_file->f_path.dentry->d_name.name;
+ cookie = get_cookie(cpu, task, text, false);
+ *offset = (vma->vm_pgoff << PAGE_SHIFT) + addr - vma->vm_start;
+ } else {
+ /* must be an anonymous map */
+ *offset = addr;
+ }
+
+ break;
+ }
+
+ if (!vma)
+ cookie = UNRESOLVED_COOKIE;
+
+ return cookie;
+}
+
+static int cookies_initialize(void)
+{
+ uint32_t crc, poly;
+ int i, j, cpu, size, err = 0;
+
+ translate_buffer_mask = TRANSLATE_BUFFER_SIZE / sizeof(per_cpu(translate_buffer, 0)[0]) - 1;
+
+ for_each_present_cpu(cpu) {
+ per_cpu(cookie_next_key, cpu) = nr_cpu_ids + cpu;
+
+ size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint64_t);
+ per_cpu(cookie_keys, cpu) = kmalloc(size, GFP_KERNEL);
+ if (!per_cpu(cookie_keys, cpu)) {
+ err = -ENOMEM;
+ goto cookie_setup_error;
+ }
+ memset(per_cpu(cookie_keys, cpu), 0, size);
+
+ size = COOKIEMAP_ENTRIES * MAX_COLLISIONS * sizeof(uint32_t);
+ per_cpu(cookie_values, cpu) = kmalloc(size, GFP_KERNEL);
+ if (!per_cpu(cookie_values, cpu)) {
+ err = -ENOMEM;
+ goto cookie_setup_error;
+ }
+ memset(per_cpu(cookie_values, cpu), 0, size);
+
+ per_cpu(translate_buffer, cpu) = kmalloc(TRANSLATE_BUFFER_SIZE, GFP_KERNEL);
+ if (!per_cpu(translate_buffer, cpu)) {
+ err = -ENOMEM;
+ goto cookie_setup_error;
+ }
+
+ per_cpu(translate_buffer_write, cpu) = 0;
+ per_cpu(translate_buffer_read, cpu) = 0;
+
+ per_cpu(translate_text, cpu) = kmalloc(TRANSLATE_TEXT_SIZE, GFP_KERNEL);
+ if (!per_cpu(translate_text, cpu)) {
+ err = -ENOMEM;
+ goto cookie_setup_error;
+ }
+ }
+
+ /* build CRC32 table */
+ poly = 0x04c11db7;
+ gator_crc32_table = kmalloc(256 * sizeof(*gator_crc32_table), GFP_KERNEL);
+ if (!gator_crc32_table) {
+ err = -ENOMEM;
+ goto cookie_setup_error;
+ }
+ for (i = 0; i < 256; i++) {
+ crc = i;
+ for (j = 8; j > 0; j--) {
+ if (crc & 1)
+ crc = (crc >> 1) ^ poly;
+ else
+ crc >>= 1;
+ }
+ gator_crc32_table[i] = crc;
+ }
+
+ setup_timer(&app_process_wake_up_timer, app_process_wake_up_handler, 0);
+
+cookie_setup_error:
+ return err;
+}
+
+static void cookies_release(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kfree(per_cpu(cookie_keys, cpu));
+ per_cpu(cookie_keys, cpu) = NULL;
+
+ kfree(per_cpu(cookie_values, cpu));
+ per_cpu(cookie_values, cpu) = NULL;
+
+ kfree(per_cpu(translate_buffer, cpu));
+ per_cpu(translate_buffer, cpu) = NULL;
+ per_cpu(translate_buffer_read, cpu) = 0;
+ per_cpu(translate_buffer_write, cpu) = 0;
+
+ kfree(per_cpu(translate_text, cpu));
+ per_cpu(translate_text, cpu) = NULL;
+ }
+
+ del_timer_sync(&app_process_wake_up_timer);
+ kfree(gator_crc32_table);
+ gator_crc32_table = NULL;
+}
diff --git a/drivers/gator/gator_events_armv6.c b/drivers/gator/gator_events_armv6.c
new file mode 100644
index 0000000..1783970
--- /dev/null
+++ b/drivers/gator/gator_events_armv6.c
@@ -0,0 +1,234 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+
+/*
+ * Per-CPU PMCR
+ */
+#define PMCR_E (1 << 0) /* Enable */
+#define PMCR_P (1 << 1) /* Count reset */
+#define PMCR_C (1 << 2) /* Cycle counter reset */
+#define PMCR_OFL_PMN0 (1 << 8) /* Count reg 0 overflow */
+#define PMCR_OFL_PMN1 (1 << 9) /* Count reg 1 overflow */
+#define PMCR_OFL_CCNT (1 << 10) /* Cycle counter overflow */
+
+#define PMN0 0
+#define PMN1 1
+#define CCNT 2
+#define CNTMAX (CCNT+1)
+
+static int pmnc_counters;
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+static inline void armv6_pmnc_write(u32 val)
+{
+ /* upper 4bits and 7, 11 are write-as-0 */
+ val &= 0x0ffff77f;
+ asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r" (val));
+}
+
+static inline u32 armv6_pmnc_read(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r" (val));
+ return val;
+}
+
+static void armv6_pmnc_reset_counter(unsigned int cnt)
+{
+ u32 val = 0;
+
+ switch (cnt) {
+ case CCNT:
+ asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r" (val));
+ break;
+ case PMN0:
+ asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r" (val));
+ break;
+ case PMN1:
+ asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r" (val));
+ break;
+ }
+}
+
+int gator_events_armv6_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ int i;
+
+ pmnc_counters = 3;
+
+ for (i = PMN0; i <= CCNT; i++) {
+ char buf[40];
+
+ if (i == CCNT)
+ snprintf(buf, sizeof(buf), "ARM_%s_ccnt", pmnc_name);
+ else
+ snprintf(buf, sizeof(buf), "ARM_%s_cnt%d", pmnc_name, i);
+ dir = gatorfs_mkdir(sb, root, buf);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+ if (i != CCNT)
+ gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+ }
+
+ return 0;
+}
+
+static int gator_events_armv6_online(int **buffer, bool migrate)
+{
+ unsigned int cnt, len = 0, cpu = smp_processor_id();
+ u32 pmnc;
+
+ if (armv6_pmnc_read() & PMCR_E)
+ armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+
+ /* initialize PMNC, reset overflow, D bit, C bit and P bit. */
+ armv6_pmnc_write(PMCR_OFL_PMN0 | PMCR_OFL_PMN1 | PMCR_OFL_CCNT |
+ PMCR_C | PMCR_P);
+
+ /* configure control register */
+ for (pmnc = 0, cnt = PMN0; cnt <= CCNT; cnt++) {
+ unsigned long event;
+
+ if (!pmnc_enabled[cnt])
+ continue;
+
+ event = pmnc_event[cnt] & 255;
+
+ /* Set event (if destined for PMNx counters) */
+ if (cnt == PMN0)
+ pmnc |= event << 20;
+ else if (cnt == PMN1)
+ pmnc |= event << 12;
+
+ /* Reset counter */
+ armv6_pmnc_reset_counter(cnt);
+ }
+ armv6_pmnc_write(pmnc | PMCR_E);
+
+ /* return zero values, no need to read as the counters were just reset */
+ for (cnt = PMN0; cnt <= CCNT; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = 0;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static int gator_events_armv6_offline(int **buffer, bool migrate)
+{
+ unsigned int cnt;
+
+ armv6_pmnc_write(armv6_pmnc_read() & ~PMCR_E);
+ for (cnt = PMN0; cnt <= CCNT; cnt++)
+ armv6_pmnc_reset_counter(cnt);
+
+ return 0;
+}
+
+static void gator_events_armv6_stop(void)
+{
+ unsigned int cnt;
+
+ for (cnt = PMN0; cnt <= CCNT; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ }
+}
+
+static int gator_events_armv6_read(int **buffer, bool sched_switch)
+{
+ int cnt, len = 0;
+ int cpu = smp_processor_id();
+
+ /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+ if (!(armv6_pmnc_read() & PMCR_E))
+ return 0;
+
+ for (cnt = PMN0; cnt <= CCNT; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ u32 value = 0;
+
+ switch (cnt) {
+ case CCNT:
+ asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r" (value));
+ break;
+ case PMN0:
+ asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r" (value));
+ break;
+ case PMN1:
+ asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r" (value));
+ break;
+ }
+ armv6_pmnc_reset_counter(cnt);
+
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = value;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_armv6_interface = {
+ .create_files = gator_events_armv6_create_files,
+ .stop = gator_events_armv6_stop,
+ .online = gator_events_armv6_online,
+ .offline = gator_events_armv6_offline,
+ .read = gator_events_armv6_read,
+};
+
+int gator_events_armv6_init(void)
+{
+ unsigned int cnt;
+
+ switch (gator_cpuid()) {
+ case ARM1136:
+ case ARM1156:
+ case ARM1176:
+ pmnc_name = "ARM11";
+ break;
+ case ARM11MPCORE:
+ pmnc_name = "ARM11MPCore";
+ break;
+ default:
+ return -1;
+ }
+
+ for (cnt = PMN0; cnt <= CCNT; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ pmnc_key[cnt] = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_armv6_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_armv7.c b/drivers/gator/gator_events_armv7.c
new file mode 100644
index 0000000..e1f6a5f
--- /dev/null
+++ b/drivers/gator/gator_events_armv7.c
@@ -0,0 +1,314 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Disabling interrupts
+ * Many of the functions below disable interrupts via local_irq_save(). This disabling of interrupts is done to prevent any race conditions
+ * between multiple entities (e.g. hrtimer interrupts and event based interrupts) calling the same functions. As accessing the pmu involves
+ * several steps (disable, select, read, enable), these steps must be performed atomically. Normal synchronization routines cannot be used
+ * as these functions are being called from interrupt context.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E (1 << 0) /* Enable all counters */
+#define PMNC_P (1 << 1) /* Reset all counters */
+#define PMNC_C (1 << 2) /* Cycle counter reset */
+#define PMNC_MASK 0x3f /* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG (1 << 31)
+
+#define CCNT 0
+#define CNT0 1
+#define CNTMAX (6+1)
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+inline void armv7_pmnc_write(u32 val)
+{
+ val &= PMNC_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_read(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+ return val;
+}
+
+inline u32 armv7_ccnt_read(u32 reset_value)
+{
+ unsigned long flags;
+ u32 newval = -reset_value;
+ u32 den = CCNT_REG;
+ u32 val;
+
+ local_irq_save(flags);
+ asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); /* disable */
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); /* read */
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (newval)); /* new value */
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); /* enable */
+ local_irq_restore(flags);
+
+ return val;
+}
+
+inline u32 armv7_cntn_read(unsigned int cnt, u32 reset_value)
+{
+ unsigned long flags;
+ u32 newval = -reset_value;
+ u32 sel = (cnt - CNT0);
+ u32 den = 1 << sel;
+ u32 oldval;
+
+ local_irq_save(flags);
+ asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (den)); /* disable */
+ asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (sel)); /* select */
+ asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (oldval)); /* read */
+ asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (newval)); /* new value */
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (den)); /* enable */
+ local_irq_restore(flags);
+
+ return oldval;
+}
+
+static inline void armv7_pmnc_disable_interrupt(unsigned int cnt)
+{
+ u32 val = cnt ? (1 << (cnt - CNT0)) : (1 << 31);
+
+ asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+}
+
+inline u32 armv7_pmnc_reset_interrupt(void)
+{
+ /* Get and reset overflow status flags */
+ u32 flags;
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (flags));
+ flags &= 0x8000003f;
+ asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (flags));
+ return flags;
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int cnt)
+{
+ u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+ return cnt;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int cnt)
+{
+ u32 val = cnt ? (1 << (cnt - CNT0)) : CCNT_REG;
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+ return cnt;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int cnt)
+{
+ u32 val = (cnt - CNT0);
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+ return cnt;
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+ if (armv7_pmnc_select_counter(cnt) == cnt)
+ asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+}
+
+static int gator_events_armv7_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ int i;
+
+ for (i = 0; i < pmnc_counters; i++) {
+ char buf[40];
+
+ if (i == 0)
+ snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+ else
+ snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+ dir = gatorfs_mkdir(sb, root, buf);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+ if (i > 0)
+ gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+ }
+
+ return 0;
+}
+
+static int gator_events_armv7_online(int **buffer, bool migrate)
+{
+ unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+ if (armv7_pmnc_read() & PMNC_E)
+ armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+ /* Initialize & Reset PMNC: C bit and P bit */
+ armv7_pmnc_write(PMNC_P | PMNC_C);
+
+ /* Reset overflow flags */
+ armv7_pmnc_reset_interrupt();
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ unsigned long event;
+
+ if (!pmnc_enabled[cnt])
+ continue;
+
+ /* Disable counter */
+ armv7_pmnc_disable_counter(cnt);
+
+ event = pmnc_event[cnt] & 255;
+
+ /* Set event (if destined for PMNx counters), we don't need to set the event if it's a cycle count */
+ if (cnt != CCNT)
+ armv7_pmnc_write_evtsel(cnt, event);
+
+ armv7_pmnc_disable_interrupt(cnt);
+
+ /* Reset counter */
+ cnt ? armv7_cntn_read(cnt, 0) : armv7_ccnt_read(0);
+
+ /* Enable counter */
+ armv7_pmnc_enable_counter(cnt);
+ }
+
+ /* enable */
+ armv7_pmnc_write(armv7_pmnc_read() | PMNC_E);
+
+ /* return zero values, no need to read as the counters were just reset */
+ for (cnt = 0; cnt < pmnc_counters; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = 0;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static int gator_events_armv7_offline(int **buffer, bool migrate)
+{
+ /* disable all counters, including PMCCNTR; overflow IRQs will not be signaled */
+ armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+
+ return 0;
+}
+
+static void gator_events_armv7_stop(void)
+{
+ unsigned int cnt;
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ }
+}
+
+static int gator_events_armv7_read(int **buffer, bool sched_switch)
+{
+ int cnt, len = 0;
+ int cpu = smp_processor_id();
+
+ /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+ if (!(armv7_pmnc_read() & PMNC_E))
+ return 0;
+
+ for (cnt = 0; cnt < pmnc_counters; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ int value;
+
+ if (cnt == CCNT)
+ value = armv7_ccnt_read(0);
+ else
+ value = armv7_cntn_read(cnt, 0);
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = value;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_armv7_interface = {
+ .create_files = gator_events_armv7_create_files,
+ .stop = gator_events_armv7_stop,
+ .online = gator_events_armv7_online,
+ .offline = gator_events_armv7_offline,
+ .read = gator_events_armv7_read,
+};
+
+int gator_events_armv7_init(void)
+{
+ unsigned int cnt;
+
+ switch (gator_cpuid()) {
+ case CORTEX_A5:
+ pmnc_name = "ARMv7_Cortex_A5";
+ pmnc_counters = 2;
+ break;
+ case CORTEX_A7:
+ pmnc_name = "ARMv7_Cortex_A7";
+ pmnc_counters = 4;
+ break;
+ case CORTEX_A8:
+ pmnc_name = "ARMv7_Cortex_A8";
+ pmnc_counters = 4;
+ break;
+ case CORTEX_A9:
+ pmnc_name = "ARMv7_Cortex_A9";
+ pmnc_counters = 6;
+ break;
+ case CORTEX_A15:
+ pmnc_name = "ARMv7_Cortex_A15";
+ pmnc_counters = 6;
+ break;
+ /* ARM Cortex A17 is not supported by version of Linux before 3.0 */
+ default:
+ return -1;
+ }
+
+ pmnc_counters++; /* CNT[n] + CCNT */
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ pmnc_key[cnt] = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_armv7_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_block.c b/drivers/gator/gator_events_block.c
new file mode 100644
index 0000000..b3467b1
--- /dev/null
+++ b/drivers/gator/gator_events_block.c
@@ -0,0 +1,160 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/block.h>
+
+#define BLOCK_RQ_WR 0
+#define BLOCK_RQ_RD 1
+
+#define BLOCK_TOTAL (BLOCK_RQ_RD+1)
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+#define EVENTWRITE REQ_RW
+#else
+#define EVENTWRITE REQ_WRITE
+#endif
+
+static ulong block_rq_wr_enabled;
+static ulong block_rq_rd_enabled;
+static ulong block_rq_wr_key;
+static ulong block_rq_rd_key;
+static atomic_t blockCnt[BLOCK_TOTAL];
+static int blockGet[BLOCK_TOTAL * 4];
+
+/* Tracepoint changed in 3.15 backported to older kernels. The Makefile tries to autodetect the correct value, but if it fails change the #if below */
+#if OLD_BLOCK_RQ_COMPLETE
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq))
+#else
+GATOR_DEFINE_PROBE(block_rq_complete, TP_PROTO(struct request_queue *q, struct request *rq, unsigned int nr_bytes))
+#endif
+{
+ int write;
+ unsigned int size;
+
+ if (!rq)
+ return;
+
+ write = rq->cmd_flags & EVENTWRITE;
+#if OLD_BLOCK_RQ_COMPLETE
+ size = rq->resid_len;
+#else
+ size = nr_bytes;
+#endif
+
+ if (!size)
+ return;
+
+ if (write) {
+ if (block_rq_wr_enabled)
+ atomic_add(size, &blockCnt[BLOCK_RQ_WR]);
+ } else {
+ if (block_rq_rd_enabled)
+ atomic_add(size, &blockCnt[BLOCK_RQ_RD]);
+ }
+}
+
+static int gator_events_block_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+
+ /* block_complete_wr */
+ dir = gatorfs_mkdir(sb, root, "Linux_block_rq_wr");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &block_rq_wr_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_wr_key);
+
+ /* block_complete_rd */
+ dir = gatorfs_mkdir(sb, root, "Linux_block_rq_rd");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &block_rq_rd_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &block_rq_rd_key);
+
+ return 0;
+}
+
+static int gator_events_block_start(void)
+{
+ /* register tracepoints */
+ if (block_rq_wr_enabled || block_rq_rd_enabled)
+ if (GATOR_REGISTER_TRACE(block_rq_complete))
+ goto fail_block_rq_exit;
+ pr_debug("gator: registered block event tracepoints\n");
+
+ return 0;
+
+ /* unregister tracepoints on error */
+fail_block_rq_exit:
+ pr_err("gator: block event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+ return -1;
+}
+
+static void gator_events_block_stop(void)
+{
+ if (block_rq_wr_enabled || block_rq_rd_enabled)
+ GATOR_UNREGISTER_TRACE(block_rq_complete);
+ pr_debug("gator: unregistered block event tracepoints\n");
+
+ block_rq_wr_enabled = 0;
+ block_rq_rd_enabled = 0;
+}
+
+static int gator_events_block_read(int **buffer, bool sched_switch)
+{
+ int len, value, data = 0;
+
+ if (!on_primary_core())
+ return 0;
+
+ len = 0;
+ if (block_rq_wr_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_WR])) > 0) {
+ atomic_sub(value, &blockCnt[BLOCK_RQ_WR]);
+ blockGet[len++] = block_rq_wr_key;
+ /* Indicates to Streamline that value bytes were written now, not since the last message */
+ blockGet[len++] = 0;
+ blockGet[len++] = block_rq_wr_key;
+ blockGet[len++] = value;
+ data += value;
+ }
+ if (block_rq_rd_enabled && (value = atomic_read(&blockCnt[BLOCK_RQ_RD])) > 0) {
+ atomic_sub(value, &blockCnt[BLOCK_RQ_RD]);
+ blockGet[len++] = block_rq_rd_key;
+ /* Indicates to Streamline that value bytes were read now, not since the last message */
+ blockGet[len++] = 0;
+ blockGet[len++] = block_rq_rd_key;
+ blockGet[len++] = value;
+ data += value;
+ }
+
+ if (buffer)
+ *buffer = blockGet;
+
+ return len;
+}
+
+static struct gator_interface gator_events_block_interface = {
+ .create_files = gator_events_block_create_files,
+ .start = gator_events_block_start,
+ .stop = gator_events_block_stop,
+ .read = gator_events_block_read,
+};
+
+int gator_events_block_init(void)
+{
+ block_rq_wr_enabled = 0;
+ block_rq_rd_enabled = 0;
+
+ block_rq_wr_key = gator_events_get_key();
+ block_rq_rd_key = gator_events_get_key();
+
+ return gator_events_install(&gator_events_block_interface);
+}
diff --git a/drivers/gator/gator_events_irq.c b/drivers/gator/gator_events_irq.c
new file mode 100644
index 0000000..81b976a
--- /dev/null
+++ b/drivers/gator/gator_events_irq.c
@@ -0,0 +1,163 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/irq.h>
+
+#define HARDIRQ 0
+#define SOFTIRQ 1
+#define TOTALIRQ (SOFTIRQ+1)
+
+static ulong hardirq_enabled;
+static ulong softirq_enabled;
+static ulong hardirq_key;
+static ulong softirq_key;
+static DEFINE_PER_CPU(atomic_t[TOTALIRQ], irqCnt);
+static DEFINE_PER_CPU(int[TOTALIRQ * 2], irqGet);
+
+GATOR_DEFINE_PROBE(irq_handler_exit,
+ TP_PROTO(int irq, struct irqaction *action, int ret))
+{
+ atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[HARDIRQ]);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 37)
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(struct softirq_action *h, struct softirq_action *vec))
+#else
+GATOR_DEFINE_PROBE(softirq_exit, TP_PROTO(unsigned int vec_nr))
+#endif
+{
+ atomic_inc(&per_cpu(irqCnt, get_physical_cpu())[SOFTIRQ]);
+}
+
+static int gator_events_irq_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+
+ /* irq */
+ dir = gatorfs_mkdir(sb, root, "Linux_irq_irq");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &hardirq_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &hardirq_key);
+
+ /* soft irq */
+ dir = gatorfs_mkdir(sb, root, "Linux_irq_softirq");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &softirq_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &softirq_key);
+
+ return 0;
+}
+
+static int gator_events_irq_online(int **buffer, bool migrate)
+{
+ int len = 0, cpu = get_physical_cpu();
+
+ /* synchronization with the irq_exit functions is not necessary as the values are being reset */
+ if (hardirq_enabled) {
+ atomic_set(&per_cpu(irqCnt, cpu)[HARDIRQ], 0);
+ per_cpu(irqGet, cpu)[len++] = hardirq_key;
+ per_cpu(irqGet, cpu)[len++] = 0;
+ }
+
+ if (softirq_enabled) {
+ atomic_set(&per_cpu(irqCnt, cpu)[SOFTIRQ], 0);
+ per_cpu(irqGet, cpu)[len++] = softirq_key;
+ per_cpu(irqGet, cpu)[len++] = 0;
+ }
+
+ if (buffer)
+ *buffer = per_cpu(irqGet, cpu);
+
+ return len;
+}
+
+static int gator_events_irq_start(void)
+{
+ /* register tracepoints */
+ if (hardirq_enabled)
+ if (GATOR_REGISTER_TRACE(irq_handler_exit))
+ goto fail_hardirq_exit;
+ if (softirq_enabled)
+ if (GATOR_REGISTER_TRACE(softirq_exit))
+ goto fail_softirq_exit;
+ pr_debug("gator: registered irq tracepoints\n");
+
+ return 0;
+
+ /* unregister tracepoints on error */
+fail_softirq_exit:
+ if (hardirq_enabled)
+ GATOR_UNREGISTER_TRACE(irq_handler_exit);
+fail_hardirq_exit:
+ pr_err("gator: irq tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+ return -1;
+}
+
+static void gator_events_irq_stop(void)
+{
+ if (hardirq_enabled)
+ GATOR_UNREGISTER_TRACE(irq_handler_exit);
+ if (softirq_enabled)
+ GATOR_UNREGISTER_TRACE(softirq_exit);
+ pr_debug("gator: unregistered irq tracepoints\n");
+
+ hardirq_enabled = 0;
+ softirq_enabled = 0;
+}
+
+static int gator_events_irq_read(int **buffer, bool sched_switch)
+{
+ int len, value;
+ int cpu = get_physical_cpu();
+
+ len = 0;
+ if (hardirq_enabled) {
+ value = atomic_read(&per_cpu(irqCnt, cpu)[HARDIRQ]);
+ atomic_sub(value, &per_cpu(irqCnt, cpu)[HARDIRQ]);
+
+ per_cpu(irqGet, cpu)[len++] = hardirq_key;
+ per_cpu(irqGet, cpu)[len++] = value;
+ }
+
+ if (softirq_enabled) {
+ value = atomic_read(&per_cpu(irqCnt, cpu)[SOFTIRQ]);
+ atomic_sub(value, &per_cpu(irqCnt, cpu)[SOFTIRQ]);
+
+ per_cpu(irqGet, cpu)[len++] = softirq_key;
+ per_cpu(irqGet, cpu)[len++] = value;
+ }
+
+ if (buffer)
+ *buffer = per_cpu(irqGet, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_irq_interface = {
+ .create_files = gator_events_irq_create_files,
+ .online = gator_events_irq_online,
+ .start = gator_events_irq_start,
+ .stop = gator_events_irq_stop,
+ .read = gator_events_irq_read,
+};
+
+int gator_events_irq_init(void)
+{
+ hardirq_key = gator_events_get_key();
+ softirq_key = gator_events_get_key();
+
+ hardirq_enabled = 0;
+ softirq_enabled = 0;
+
+ return gator_events_install(&gator_events_irq_interface);
+}
diff --git a/drivers/gator/gator_events_l2c-310.c b/drivers/gator/gator_events_l2c-310.c
new file mode 100644
index 0000000..063a060
--- /dev/null
+++ b/drivers/gator/gator_events_l2c-310.c
@@ -0,0 +1,208 @@
+/**
+ * l2c310 (L2 Cache Controller) event counters for gator
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#if defined(CONFIG_OF)
+#include <linux/of.h>
+#include <linux/of_address.h>
+#endif
+#include <asm/hardware/cache-l2x0.h>
+
+#include "gator.h"
+
+#define L2C310_COUNTERS_NUM 2
+
+static struct {
+ unsigned long enabled;
+ unsigned long event;
+ unsigned long key;
+} l2c310_counters[L2C310_COUNTERS_NUM];
+
+static int l2c310_buffer[L2C310_COUNTERS_NUM * 2];
+
+static void __iomem *l2c310_base;
+
+static void gator_events_l2c310_reset_counters(void)
+{
+ u32 val = readl(l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+ val |= ((1 << L2C310_COUNTERS_NUM) - 1) << 1;
+
+ writel(val, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_create_files(struct super_block *sb,
+ struct dentry *root)
+{
+ int i;
+
+ for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+ char buf[16];
+ struct dentry *dir;
+
+ snprintf(buf, sizeof(buf), "L2C-310_cnt%d", i);
+ dir = gatorfs_mkdir(sb, root, buf);
+ if (WARN_ON(!dir))
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled",
+ &l2c310_counters[i].enabled);
+ gatorfs_create_ulong(sb, dir, "event",
+ &l2c310_counters[i].event);
+ gatorfs_create_ro_ulong(sb, dir, "key",
+ &l2c310_counters[i].key);
+ }
+
+ return 0;
+}
+
+static int gator_events_l2c310_start(void)
+{
+ static const unsigned long l2x0_event_cntx_cfg[L2C310_COUNTERS_NUM] = {
+ L2X0_EVENT_CNT0_CFG,
+ L2X0_EVENT_CNT1_CFG,
+ };
+ int i;
+
+ /* Counter event sources */
+ for (i = 0; i < L2C310_COUNTERS_NUM; i++)
+ writel((l2c310_counters[i].event & 0xf) << 2,
+ l2c310_base + l2x0_event_cntx_cfg[i]);
+
+ gator_events_l2c310_reset_counters();
+
+ /* Event counter enable */
+ writel(1, l2c310_base + L2X0_EVENT_CNT_CTRL);
+
+ return 0;
+}
+
+static void gator_events_l2c310_stop(void)
+{
+ /* Event counter disable */
+ writel(0, l2c310_base + L2X0_EVENT_CNT_CTRL);
+}
+
+static int gator_events_l2c310_read(int **buffer, bool sched_switch)
+{
+ static const unsigned long l2x0_event_cntx_val[L2C310_COUNTERS_NUM] = {
+ L2X0_EVENT_CNT0_VAL,
+ L2X0_EVENT_CNT1_VAL,
+ };
+ int i;
+ int len = 0;
+
+ if (!on_primary_core())
+ return 0;
+
+ for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+ if (l2c310_counters[i].enabled) {
+ l2c310_buffer[len++] = l2c310_counters[i].key;
+ l2c310_buffer[len++] = readl(l2c310_base +
+ l2x0_event_cntx_val[i]);
+ }
+ }
+
+ /* l2c310 counters are saturating, not wrapping in case of overflow */
+ gator_events_l2c310_reset_counters();
+
+ if (buffer)
+ *buffer = l2c310_buffer;
+
+ return len;
+}
+
+static struct gator_interface gator_events_l2c310_interface = {
+ .create_files = gator_events_l2c310_create_files,
+ .start = gator_events_l2c310_start,
+ .stop = gator_events_l2c310_stop,
+ .read = gator_events_l2c310_read,
+};
+
+#define L2C310_ADDR_PROBE (~0)
+
+MODULE_PARM_DESC(l2c310_addr, "L2C310 physical base address (0 to disable)");
+static unsigned long l2c310_addr = L2C310_ADDR_PROBE;
+module_param(l2c310_addr, ulong, 0444);
+
+static void __iomem *gator_events_l2c310_probe(void)
+{
+ phys_addr_t variants[] = {
+#if defined(CONFIG_ARCH_EXYNOS4) || defined(CONFIG_ARCH_S5PV310)
+ 0x10502000,
+#endif
+#if defined(CONFIG_ARCH_OMAP4)
+ 0x48242000,
+#endif
+#if defined(CONFIG_ARCH_TEGRA)
+ 0x50043000,
+#endif
+#if defined(CONFIG_ARCH_U8500)
+ 0xa0412000,
+#endif
+#if defined(CONFIG_ARCH_VEXPRESS)
+ 0x1e00a000, /* A9x4 core tile (HBI-0191) */
+ 0x2c0f0000, /* New memory map tiles */
+#endif
+ };
+ int i;
+ void __iomem *base;
+#if defined(CONFIG_OF)
+ struct device_node *node = of_find_all_nodes(NULL);
+
+ if (node) {
+ of_node_put(node);
+
+ node = of_find_compatible_node(NULL, NULL, "arm,pl310-cache");
+ base = of_iomap(node, 0);
+ of_node_put(node);
+
+ return base;
+ }
+#endif
+
+ for (i = 0; i < ARRAY_SIZE(variants); i++) {
+ base = ioremap(variants[i], SZ_4K);
+ if (base) {
+ u32 cache_id = readl(base + L2X0_CACHE_ID);
+
+ if ((cache_id & 0xff0003c0) == 0x410000c0)
+ return base;
+
+ iounmap(base);
+ }
+ }
+
+ return NULL;
+}
+
+int gator_events_l2c310_init(void)
+{
+ int i;
+
+ if (gator_cpuid() != CORTEX_A5 && gator_cpuid() != CORTEX_A9)
+ return -1;
+
+ if (l2c310_addr == L2C310_ADDR_PROBE)
+ l2c310_base = gator_events_l2c310_probe();
+ else if (l2c310_addr)
+ l2c310_base = ioremap(l2c310_addr, SZ_4K);
+
+ if (!l2c310_base)
+ return -1;
+
+ for (i = 0; i < L2C310_COUNTERS_NUM; i++) {
+ l2c310_counters[i].enabled = 0;
+ l2c310_counters[i].key = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_l2c310_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.c b/drivers/gator/gator_events_mali_4xx.c
new file mode 100644
index 0000000..423b4e0
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.c
@@ -0,0 +1,622 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#include "linux/mali_linux_trace.h"
+
+#include "gator_events_mali_common.h"
+#include "gator_events_mali_4xx.h"
+
+/*
+* There have been four different variants of the comms between gator and Mali depending on driver version:
+* # | DDK vsn range | Support | Notes
+*
+* 1 | (obsolete) | No software counter support | Obsolete patches
+* 2 | (obsolete) | Tracepoint called for each separate s/w counter value as it appears | Obsolete patches
+* 3 | r3p0-04rel0 - r3p2-01rel2 | Single tracepoint for all s/w counters in a bundle. |
+* 4 | r3p2-01rel3 - date | As above but with extensions for MP devices (Mali-450) | At least r4p0-00rel1
+*/
+
+#if !defined(GATOR_MALI_INTERFACE_STYLE)
+#define GATOR_MALI_INTERFACE_STYLE (4)
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE == 1
+#error GATOR_MALI_INTERFACE_STYLE 1 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE == 2
+#error GATOR_MALI_INTERFACE_STYLE 2 is obsolete
+#elif GATOR_MALI_INTERFACE_STYLE >= 3
+/* Valid GATOR_MALI_INTERFACE_STYLE */
+#else
+#error Unknown GATOR_MALI_INTERFACE_STYLE option.
+#endif
+
+#if GATOR_MALI_INTERFACE_STYLE < 4
+#include "mali/mali_mjollnir_profiling_gator_api.h"
+#else
+#include "mali/mali_utgard_profiling_gator_api.h"
+#endif
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_4xx)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_4xx
+#endif
+
+static const char mali_name[] = "4xx";
+
+/* gatorfs variables for counter enable state,
+ * the event the counter should count and the
+ * 'key' (a unique id set by gatord and returned
+ * by gator.ko)
+ */
+static unsigned long counter_enabled[NUMBER_OF_EVENTS];
+static unsigned long counter_event[NUMBER_OF_EVENTS];
+static unsigned long counter_key[NUMBER_OF_EVENTS];
+
+/* The data we have recorded */
+static u32 counter_data[NUMBER_OF_EVENTS];
+/* The address to sample (or 0 if samples are sent to us) */
+static u32 *counter_address[NUMBER_OF_EVENTS];
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+static int counter_prev[NUMBER_OF_EVENTS];
+static bool prev_set[NUMBER_OF_EVENTS];
+
+/* Note whether tracepoints have been registered */
+static int trace_registered;
+
+/*
+ * These numbers define the actual numbers of each block type that exist in the system. Initially
+ * these are set to the maxima defined above; if the driver is capable of being queried (newer
+ * drivers only) then the values may be revised.
+ */
+static unsigned int n_vp_cores = MAX_NUM_VP_CORES;
+static unsigned int n_l2_cores = MAX_NUM_L2_CACHE_CORES;
+static unsigned int n_fp_cores = MAX_NUM_FP_CORES;
+
+extern struct mali_counter mali_activity[2];
+static const char *const mali_activity_names[] = {
+ "fragment",
+ "vertex",
+};
+
+/**
+ * Returns non-zero if the given counter ID is an activity counter.
+ */
+static inline int is_activity_counter(unsigned int event_id)
+{
+ return (event_id >= FIRST_ACTIVITY_EVENT &&
+ event_id <= LAST_ACTIVITY_EVENT);
+}
+
+/**
+ * Returns non-zero if the given counter ID is a hardware counter.
+ */
+static inline int is_hw_counter(unsigned int event_id)
+{
+ return (event_id >= FIRST_HW_COUNTER && event_id <= LAST_HW_COUNTER);
+}
+
+/* Probe for hardware counter events */
+GATOR_DEFINE_PROBE(mali_hw_counter, TP_PROTO(unsigned int event_id, unsigned int value))
+{
+ if (is_hw_counter(event_id))
+ counter_data[event_id] = value;
+}
+
+GATOR_DEFINE_PROBE(mali_sw_counters, TP_PROTO(pid_t pid, pid_t tid, void *surface_id, unsigned int *counters))
+{
+ u32 i;
+
+ /* Copy over the values for those counters which are enabled. */
+ for (i = FIRST_SW_COUNTER; i <= LAST_SW_COUNTER; i++) {
+ if (counter_enabled[i])
+ counter_data[i] = (u32)(counters[i - FIRST_SW_COUNTER]);
+ }
+}
+
+/**
+ * Create a single filesystem entry for a specified event.
+ * @param sb the superblock
+ * @param root Filesystem root
+ * @param name The name of the entry to create
+ * @param event The ID of the event
+ * @param create_event_item boolean indicating whether to create an 'event' filesystem entry. True to create.
+ *
+ * @return 0 if ok, non-zero if the create failed.
+ */
+static int create_fs_entry(struct super_block *sb, struct dentry *root, const char *name, int event, int create_event_item)
+{
+ struct dentry *dir;
+
+ dir = gatorfs_mkdir(sb, root, name);
+
+ if (!dir)
+ return -1;
+
+ if (create_event_item)
+ gatorfs_create_ulong(sb, dir, "event", &counter_event[event]);
+
+ gatorfs_create_ulong(sb, dir, "enabled", &counter_enabled[event]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &counter_key[event]);
+
+ return 0;
+}
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+/*
+ * Read the version info structure if available
+ */
+static void initialise_version_info(void)
+{
+ void (*mali_profiling_get_mali_version_symbol)(struct _mali_profiling_mali_version *values);
+
+ mali_profiling_get_mali_version_symbol = symbol_get(_mali_profiling_get_mali_version);
+
+ if (mali_profiling_get_mali_version_symbol) {
+ struct _mali_profiling_mali_version version_info;
+
+ pr_debug("gator: mali online _mali_profiling_get_mali_version symbol @ %p\n",
+ mali_profiling_get_mali_version_symbol);
+
+ /*
+ * Revise the number of each different core type using information derived from the DDK.
+ */
+ mali_profiling_get_mali_version_symbol(&version_info);
+
+ n_fp_cores = version_info.num_of_fp_cores;
+ n_vp_cores = version_info.num_of_vp_cores;
+ n_l2_cores = version_info.num_of_l2_cores;
+
+ /* Release the function - we're done with it. */
+ symbol_put(_mali_profiling_get_mali_version);
+ } else {
+ pr_err("gator: mali online _mali_profiling_get_mali_version symbol not found\n");
+ pr_err("gator: check your Mali DDK version versus the GATOR_MALI_INTERFACE_STYLE setting\n");
+ }
+}
+#endif
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+ int event;
+
+ char buf[40];
+ int core_id;
+ int counter_number;
+
+ pr_debug("gator: Initialising counters with style = %d\n", GATOR_MALI_INTERFACE_STYLE);
+
+#if GATOR_MALI_INTERFACE_STYLE > 3
+ /*
+ * Initialise first: this sets up the number of cores available (on compatible DDK versions).
+ * Ideally this would not need guarding but other parts of the code depend on the interface style being set
+ * correctly; if it is not then the system can enter an inconsistent state.
+ */
+ initialise_version_info();
+#endif
+
+ mali_activity[0].cores = n_fp_cores;
+ mali_activity[1].cores = n_vp_cores;
+ for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+ if (gator_mali_create_file_system(mali_name, mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+ return -1;
+ }
+
+ /* Vertex processor counters */
+ for (core_id = 0; core_id < n_vp_cores; core_id++) {
+ int activity_counter_id = ACTIVITY_VP_0;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_active", mali_name, core_id);
+ if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+ return -1;
+
+ for (counter_number = 0; counter_number < 2; counter_number++) {
+ int counter_id = COUNTER_VP_0_C0 + (2 * core_id) + counter_number;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_VP_%d_cnt%d", mali_name, core_id, counter_number);
+ if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+ return -1;
+ }
+ }
+
+ /* Fragment processors' counters */
+ for (core_id = 0; core_id < n_fp_cores; core_id++) {
+ int activity_counter_id = ACTIVITY_FP_0 + core_id;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_active", mali_name, core_id);
+ if (create_fs_entry(sb, root, buf, activity_counter_id, 0) != 0)
+ return -1;
+
+ for (counter_number = 0; counter_number < 2; counter_number++) {
+ int counter_id = COUNTER_FP_0_C0 + (2 * core_id) + counter_number;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_FP_%d_cnt%d", mali_name, core_id, counter_number);
+ if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+ return -1;
+ }
+ }
+
+ /* L2 Cache counters */
+ for (core_id = 0; core_id < n_l2_cores; core_id++) {
+ for (counter_number = 0; counter_number < 2; counter_number++) {
+ int counter_id = COUNTER_L2_0_C0 + (2 * core_id) + counter_number;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_L2_%d_cnt%d", mali_name, core_id, counter_number);
+ if (create_fs_entry(sb, root, buf, counter_id, 1) != 0)
+ return -1;
+ }
+ }
+
+ /* Now set up the software counter entries */
+ for (event = FIRST_SW_COUNTER; event <= LAST_SW_COUNTER; event++) {
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_SW_%d", mali_name, event - FIRST_SW_COUNTER);
+
+ if (create_fs_entry(sb, root, buf, event, 0) != 0)
+ return -1;
+ }
+
+ /* Now set up the special counter entries */
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_Filmstrip_cnt0", mali_name);
+ if (create_fs_entry(sb, root, buf, COUNTER_FILMSTRIP, 1) != 0)
+ return -1;
+
+#ifdef DVFS_REPORTED_BY_DDK
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_Frequency", mali_name);
+ if (create_fs_entry(sb, root, buf, COUNTER_FREQUENCY, 1) != 0)
+ return -1;
+
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_Voltage", mali_name);
+ if (create_fs_entry(sb, root, buf, COUNTER_VOLTAGE, 1) != 0)
+ return -1;
+#endif
+
+ return 0;
+}
+
+/*
+ * Local store for the get_counters entry point into the DDK.
+ * This is stored here since it is used very regularly.
+ */
+static void (*mali_get_counters)(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+static u32 (*mali_get_l2_counters)(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * Examine list of counters between two index limits and determine if any one is enabled.
+ * Returns 1 if any counter is enabled, 0 if none is.
+ */
+static int is_any_counter_enabled(unsigned int first_counter, unsigned int last_counter)
+{
+ unsigned int i;
+
+ for (i = first_counter; i <= last_counter; i++) {
+ if (counter_enabled[i])
+ return 1; /* At least one counter is enabled */
+ }
+
+ return 0; /* No s/w counters enabled */
+}
+
+static void init_counters(unsigned int from_counter, unsigned int to_counter)
+{
+ unsigned int counter_id;
+
+ /* If a Mali driver is present and exporting the appropriate symbol
+ * then we can request the HW counters (of which there are only 2)
+ * be configured to count the desired events
+ */
+ mali_profiling_set_event_type *mali_set_hw_event;
+
+ mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+ if (mali_set_hw_event) {
+ pr_debug("gator: mali online _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+
+ for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+ if (counter_enabled[counter_id])
+ mali_set_hw_event(counter_id, counter_event[counter_id]);
+ else
+ mali_set_hw_event(counter_id, 0xFFFFFFFF);
+ }
+
+ symbol_put(_mali_profiling_set_event);
+ } else {
+ pr_err("gator: mali online _mali_profiling_set_event symbol not found\n");
+ }
+}
+
+static void mali_counter_initialize(void)
+{
+ int i;
+
+ mali_profiling_control_type *mali_control;
+
+ init_counters(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores) - 1);
+ init_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1);
+ init_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1);
+
+ /* Generic control interface for Mali DDK. */
+ mali_control = symbol_get(_mali_profiling_control);
+ if (mali_control) {
+ /* The event attribute in the XML file keeps the actual frame rate. */
+ unsigned int rate = counter_event[COUNTER_FILMSTRIP] & 0xff;
+ unsigned int resize_factor = (counter_event[COUNTER_FILMSTRIP] >> 8) & 0xff;
+
+ pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+ mali_control(SW_COUNTER_ENABLE, (is_any_counter_enabled(FIRST_SW_COUNTER, LAST_SW_COUNTER) ? 1 : 0));
+ mali_control(FBDUMP_CONTROL_ENABLE, (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0));
+ mali_control(FBDUMP_CONTROL_RATE, rate);
+ mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+ pr_debug("gator: sent mali_control enabled=%d, rate=%d\n", (counter_enabled[COUNTER_FILMSTRIP] ? 1 : 0), rate);
+
+ symbol_put(_mali_profiling_control);
+ } else {
+ pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+ }
+
+ mali_get_counters = symbol_get(_mali_profiling_get_counters);
+ if (mali_get_counters)
+ pr_debug("gator: mali online _mali_profiling_get_counters symbol @ %p\n", mali_get_counters);
+ else
+ pr_debug("gator WARNING: mali _mali_profiling_get_counters symbol not defined\n");
+
+ mali_get_l2_counters = symbol_get(_mali_profiling_get_l2_counters);
+ if (mali_get_l2_counters)
+ pr_debug("gator: mali online _mali_profiling_get_l2_counters symbol @ %p\n", mali_get_l2_counters);
+ else
+ pr_debug("gator WARNING: mali _mali_profiling_get_l2_counters symbol not defined\n");
+
+ if (!mali_get_counters && !mali_get_l2_counters) {
+ pr_debug("gator: WARNING: no L2 counters available\n");
+ n_l2_cores = 0;
+ }
+
+ /* Clear counters in the start */
+ for (i = 0; i < NUMBER_OF_EVENTS; i++) {
+ counter_data[i] = 0;
+ prev_set[i] = false;
+ }
+}
+
+static void mali_counter_deinitialize(void)
+{
+ mali_profiling_set_event_type *mali_set_hw_event;
+ mali_profiling_control_type *mali_control;
+
+ mali_set_hw_event = symbol_get(_mali_profiling_set_event);
+
+ if (mali_set_hw_event) {
+ int i;
+
+ pr_debug("gator: mali offline _mali_profiling_set_event symbol @ %p\n", mali_set_hw_event);
+ for (i = FIRST_HW_COUNTER; i <= LAST_HW_COUNTER; i++)
+ mali_set_hw_event(i, 0xFFFFFFFF);
+
+ symbol_put(_mali_profiling_set_event);
+ } else {
+ pr_err("gator: mali offline _mali_profiling_set_event symbol not found\n");
+ }
+
+ /* Generic control interface for Mali DDK. */
+ mali_control = symbol_get(_mali_profiling_control);
+
+ if (mali_control) {
+ pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+ /* Reset the DDK state - disable counter collection */
+ mali_control(SW_COUNTER_ENABLE, 0);
+
+ mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+ symbol_put(_mali_profiling_control);
+ } else {
+ pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+ }
+
+ if (mali_get_counters)
+ symbol_put(_mali_profiling_get_counters);
+
+ if (mali_get_l2_counters)
+ symbol_put(_mali_profiling_get_l2_counters);
+}
+
+static int start(void)
+{
+ /* register tracepoints */
+ if (GATOR_REGISTER_TRACE(mali_hw_counter)) {
+ pr_err("gator: mali_hw_counter tracepoint failed to activate\n");
+ return -1;
+ }
+
+ /* For Mali drivers with built-in support. */
+ if (GATOR_REGISTER_TRACE(mali_sw_counters)) {
+ pr_err("gator: mali_sw_counters tracepoint failed to activate\n");
+ return -1;
+ }
+
+ trace_registered = 1;
+
+ mali_counter_initialize();
+ return 0;
+}
+
+static void stop(void)
+{
+ unsigned int cnt;
+
+ pr_debug("gator: mali stop\n");
+
+ if (trace_registered) {
+ GATOR_UNREGISTER_TRACE(mali_hw_counter);
+
+ /* For Mali drivers with built-in support. */
+ GATOR_UNREGISTER_TRACE(mali_sw_counters);
+
+ pr_debug("gator: mali timeline tracepoint deactivated\n");
+
+ trace_registered = 0;
+ }
+
+ for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+ counter_enabled[cnt] = 0;
+ counter_event[cnt] = 0;
+ counter_address[cnt] = NULL;
+ }
+
+ mali_counter_deinitialize();
+}
+
+static void dump_counters(unsigned int from_counter, unsigned int to_counter, unsigned int *len)
+{
+ unsigned int counter_id;
+
+ for (counter_id = from_counter; counter_id <= to_counter; counter_id++) {
+ if (counter_enabled[counter_id]) {
+ counter_dump[(*len)++] = counter_key[counter_id];
+ counter_dump[(*len)++] = counter_data[counter_id];
+
+ counter_data[counter_id] = 0;
+ }
+ }
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+ int len = 0;
+
+ if (!on_primary_core())
+ return 0;
+
+ /* Read the L2 C0 and C1 here. */
+ if (n_l2_cores > 0 && is_any_counter_enabled(COUNTER_L2_0_C0, COUNTER_L2_0_C0 + (2 * n_l2_cores))) {
+ unsigned int unavailable_l2_caches = 0;
+ struct _mali_profiling_l2_counter_values cache_values;
+ unsigned int cache_id;
+ struct _mali_profiling_core_counters *per_core;
+
+ /* Poke the driver to get the counter values - older style; only one L2 cache */
+ if (mali_get_l2_counters) {
+ unavailable_l2_caches = mali_get_l2_counters(&cache_values);
+ } else if (mali_get_counters) {
+ per_core = &cache_values.cores[0];
+ mali_get_counters(&per_core->source0, &per_core->value0, &per_core->source1, &per_core->value1);
+ } else {
+ /* This should never happen, as n_l2_caches is only set > 0 if one of the above functions is found. */
+ }
+
+ /* Fill in the two cache counter values for each cache block. */
+ for (cache_id = 0; cache_id < n_l2_cores; cache_id++) {
+ unsigned int counter_id_0 = COUNTER_L2_0_C0 + (2 * cache_id);
+ unsigned int counter_id_1 = counter_id_0 + 1;
+
+ if ((1 << cache_id) & unavailable_l2_caches)
+ continue; /* This cache is unavailable (powered-off, possibly). */
+
+ per_core = &cache_values.cores[cache_id];
+
+ if (counter_enabled[counter_id_0] && prev_set[counter_id_0]) {
+ /* Calculate and save src0's counter val0 */
+ counter_dump[len++] = counter_key[counter_id_0];
+ counter_dump[len++] = per_core->value0 - counter_prev[counter_id_0];
+ }
+
+ if (counter_enabled[counter_id_1] && prev_set[counter_id_1]) {
+ /* Calculate and save src1's counter val1 */
+ counter_dump[len++] = counter_key[counter_id_1];
+ counter_dump[len++] = per_core->value1 - counter_prev[counter_id_1];
+ }
+
+ /* Save the previous values for the counters. */
+ counter_prev[counter_id_0] = per_core->value0;
+ prev_set[counter_id_0] = true;
+ counter_prev[counter_id_1] = per_core->value1;
+ prev_set[counter_id_1] = true;
+ }
+ }
+
+ /* Process other (non-timeline) counters. */
+ dump_counters(COUNTER_VP_0_C0, COUNTER_VP_0_C0 + (2 * n_vp_cores) - 1, &len);
+ dump_counters(COUNTER_FP_0_C0, COUNTER_FP_0_C0 + (2 * n_fp_cores) - 1, &len);
+
+ dump_counters(FIRST_SW_COUNTER, LAST_SW_COUNTER, &len);
+
+#ifdef DVFS_REPORTED_BY_DDK
+ {
+ int cnt;
+ /*
+ * Add in the voltage and frequency counters if enabled. Note
+ * that, since these are actually passed as events, the counter
+ * value should not be cleared.
+ */
+ cnt = COUNTER_FREQUENCY;
+ if (counter_enabled[cnt]) {
+ counter_dump[len++] = counter_key[cnt];
+ counter_dump[len++] = counter_data[cnt];
+ }
+
+ cnt = COUNTER_VOLTAGE;
+ if (counter_enabled[cnt]) {
+ counter_dump[len++] = counter_key[cnt];
+ counter_dump[len++] = counter_data[cnt];
+ }
+ }
+#endif
+
+ if (buffer)
+ *buffer = counter_dump;
+
+ return len;
+}
+
+static struct gator_interface gator_events_mali_interface = {
+ .create_files = create_files,
+ .start = start,
+ .stop = stop,
+ .read = read,
+};
+
+extern void gator_events_mali_log_dvfs_event(unsigned int frequency_mhz, unsigned int voltage_mv)
+{
+#ifdef DVFS_REPORTED_BY_DDK
+ counter_data[COUNTER_FREQUENCY] = frequency_mhz;
+ counter_data[COUNTER_VOLTAGE] = voltage_mv;
+#endif
+}
+
+int gator_events_mali_init(void)
+{
+ unsigned int cnt;
+
+ pr_debug("gator: mali init\n");
+
+ gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+
+ for (cnt = 0; cnt < NUMBER_OF_EVENTS; cnt++) {
+ counter_enabled[cnt] = 0;
+ counter_event[cnt] = 0;
+ counter_key[cnt] = gator_events_get_key();
+ counter_address[cnt] = NULL;
+ counter_data[cnt] = 0;
+ }
+
+ trace_registered = 0;
+
+ return gator_events_install(&gator_events_mali_interface);
+}
diff --git a/drivers/gator/gator_events_mali_4xx.h b/drivers/gator/gator_events_mali_4xx.h
new file mode 100644
index 0000000..8f6a870
--- /dev/null
+++ b/drivers/gator/gator_events_mali_4xx.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/*
+ * Header contains common definitions for the Mali-4xx processors.
+ */
+#if !defined(GATOR_EVENTS_MALI_4xx_H)
+#define GATOR_EVENTS_MALI_4xx_H
+
+extern void gator_events_mali_log_dvfs_event(unsigned int d0, unsigned int d1);
+
+#endif /* GATOR_EVENTS_MALI_4xx_H */
diff --git a/drivers/gator/gator_events_mali_common.c b/drivers/gator/gator_events_mali_common.c
new file mode 100644
index 0000000..7741f25
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.c
@@ -0,0 +1,72 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include "gator_events_mali_common.h"
+
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event)
+{
+ int err;
+ char buf[255];
+ struct dentry *dir;
+
+ /* If the counter name is empty ignore it */
+ if (strlen(event_name) != 0) {
+ /* Set up the filesystem entry for this event. */
+ if (mali_name == NULL)
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s", event_name);
+ else
+ snprintf(buf, sizeof(buf), "ARM_Mali-%s_%s", mali_name, event_name);
+
+ dir = gatorfs_mkdir(sb, root, buf);
+
+ if (dir == NULL) {
+ pr_debug("gator: %s: error creating file system for: %s (%s)\n", mali_name, event_name, buf);
+ return -1;
+ }
+
+ err = gatorfs_create_ulong(sb, dir, "enabled", &counter->enabled);
+ if (err != 0) {
+ pr_debug("gator: %s: error calling gatorfs_create_ulong for: %s (%s)\n", mali_name, event_name, buf);
+ return -1;
+ }
+ err = gatorfs_create_ro_ulong(sb, dir, "key", &counter->key);
+ if (err != 0) {
+ pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+ return -1;
+ }
+ if (counter->cores != -1) {
+ err = gatorfs_create_ro_ulong(sb, dir, "cores", &counter->cores);
+ if (err != 0) {
+ pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+ return -1;
+ }
+ }
+ if (event != NULL) {
+ err = gatorfs_create_ulong(sb, dir, "event", event);
+ if (err != 0) {
+ pr_debug("gator: %s: error calling gatorfs_create_ro_ulong for: %s (%s)\n", mali_name, event_name, buf);
+ return -1;
+ }
+ }
+ }
+
+ return 0;
+}
+
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters)
+{
+ unsigned int cnt;
+
+ for (cnt = 0; cnt < n_counters; cnt++) {
+ struct mali_counter *counter = &counters[cnt];
+
+ counter->key = gator_events_get_key();
+ counter->enabled = 0;
+ counter->cores = -1;
+ }
+}
diff --git a/drivers/gator/gator_events_mali_common.h b/drivers/gator/gator_events_mali_common.h
new file mode 100644
index 0000000..a4fc9d7
--- /dev/null
+++ b/drivers/gator/gator_events_mali_common.h
@@ -0,0 +1,77 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if !defined(GATOR_EVENTS_MALI_COMMON_H)
+#define GATOR_EVENTS_MALI_COMMON_H
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Ensure that MALI_SUPPORT has been defined to something. */
+#ifndef MALI_SUPPORT
+#error MALI_SUPPORT not defined!
+#endif
+
+/* Values for the supported activity event types */
+#define ACTIVITY_START (1)
+#define ACTIVITY_STOP (2)
+
+/*
+ * Runtime state information for a counter.
+ */
+struct mali_counter {
+ /* 'key' (a unique id set by gatord and returned by gator.ko) */
+ unsigned long key;
+ /* counter enable state */
+ unsigned long enabled;
+ /* for activity counters, the number of cores, otherwise -1 */
+ unsigned long cores;
+};
+
+/*
+ * Mali-4xx
+ */
+typedef int mali_profiling_set_event_type(unsigned int, int);
+typedef void mali_profiling_control_type(unsigned int, unsigned int);
+
+/*
+ * Driver entry points for functions called directly by gator.
+ */
+extern int _mali_profiling_set_event(unsigned int, int);
+extern void _mali_profiling_control(unsigned int, unsigned int);
+extern void _mali_profiling_get_counters(unsigned int *, unsigned int *, unsigned int *, unsigned int *);
+
+/**
+ * Creates a filesystem entry under /dev/gator relating to the specified event name and key, and
+ * associate the key/enable values with this entry point.
+ *
+ * @param event_name The name of the event.
+ * @param sb Linux super block
+ * @param root Directory under which the entry will be created.
+ * @param counter_key Ptr to location which will be associated with the counter key.
+ * @param counter_enabled Ptr to location which will be associated with the counter enable state.
+ *
+ * @return 0 if entry point was created, non-zero if not.
+ */
+extern int gator_mali_create_file_system(const char *mali_name, const char *event_name, struct super_block *sb, struct dentry *root, struct mali_counter *counter, unsigned long *event);
+
+/**
+ * Initializes the counter array.
+ *
+ * @param keys The array of counters
+ * @param n_counters The number of entries in each of the arrays.
+ */
+extern void gator_mali_initialise_counters(struct mali_counter counters[], unsigned int n_counters);
+
+#endif /* GATOR_EVENTS_MALI_COMMON_H */
diff --git a/drivers/gator/gator_events_mali_midgard.c b/drivers/gator/gator_events_mali_midgard.c
new file mode 100644
index 0000000..3b0963a
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard.c
@@ -0,0 +1,562 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Check that the MALI_SUPPORT define is set to one of the allowable device codes.
+ */
+#if (MALI_SUPPORT != MALI_MIDGARD)
+#error MALI_SUPPORT set to an invalid device code: expecting MALI_MIDGARD
+#endif
+
+static const char mali_name[] = "Midgard";
+
+/* Counters for Mali-Midgard:
+ *
+ * - Timeline events
+ * They are tracepoints, but instead of reporting a number they report a START/STOP event.
+ * They are reported in Streamline as number of microseconds while that particular counter was active.
+ *
+ * - SW counters
+ * They are tracepoints reporting a particular number.
+ * They are accumulated in sw_counter_data array until they are passed to Streamline, then they are zeroed.
+ *
+ * - Accumulators
+ * They are the same as software counters but their value is not zeroed.
+ */
+
+/* Timeline (start/stop) activity */
+static const char *const timeline_event_names[] = {
+ "PM_SHADER_0",
+ "PM_SHADER_1",
+ "PM_SHADER_2",
+ "PM_SHADER_3",
+ "PM_SHADER_4",
+ "PM_SHADER_5",
+ "PM_SHADER_6",
+ "PM_SHADER_7",
+ "PM_TILER_0",
+ "PM_L2_0",
+ "PM_L2_1",
+ "MMU_AS_0",
+ "MMU_AS_1",
+ "MMU_AS_2",
+ "MMU_AS_3"
+};
+
+enum {
+ PM_SHADER_0 = 0,
+ PM_SHADER_1,
+ PM_SHADER_2,
+ PM_SHADER_3,
+ PM_SHADER_4,
+ PM_SHADER_5,
+ PM_SHADER_6,
+ PM_SHADER_7,
+ PM_TILER_0,
+ PM_L2_0,
+ PM_L2_1,
+ MMU_AS_0,
+ MMU_AS_1,
+ MMU_AS_2,
+ MMU_AS_3
+};
+/* The number of shader blocks in the enum above */
+#define NUM_PM_SHADER (8)
+
+/* Software Counters */
+static const char *const software_counter_names[] = {
+ "MMU_PAGE_FAULT_0",
+ "MMU_PAGE_FAULT_1",
+ "MMU_PAGE_FAULT_2",
+ "MMU_PAGE_FAULT_3"
+};
+
+enum {
+ MMU_PAGE_FAULT_0 = 0,
+ MMU_PAGE_FAULT_1,
+ MMU_PAGE_FAULT_2,
+ MMU_PAGE_FAULT_3
+};
+
+/* Software Counters */
+static const char *const accumulators_names[] = {
+ "TOTAL_ALLOC_PAGES"
+};
+
+enum {
+ TOTAL_ALLOC_PAGES = 0
+};
+
+#define FIRST_TIMELINE_EVENT (0)
+#define NUMBER_OF_TIMELINE_EVENTS (sizeof(timeline_event_names) / sizeof(timeline_event_names[0]))
+#define FIRST_SOFTWARE_COUNTER (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS)
+#define NUMBER_OF_SOFTWARE_COUNTERS (sizeof(software_counter_names) / sizeof(software_counter_names[0]))
+#define FIRST_ACCUMULATOR (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS)
+#define NUMBER_OF_ACCUMULATORS (sizeof(accumulators_names) / sizeof(accumulators_names[0]))
+#define FILMSTRIP (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS)
+#define NUMBER_OF_EVENTS (NUMBER_OF_TIMELINE_EVENTS + NUMBER_OF_SOFTWARE_COUNTERS + NUMBER_OF_ACCUMULATORS + 1)
+
+/*
+ * gatorfs variables for counter enable state
+ */
+static struct mali_counter counters[NUMBER_OF_EVENTS];
+static unsigned long filmstrip_event;
+
+/* An array used to return the data we recorded
+ * as key,value pairs hence the *2
+ */
+static int counter_dump[NUMBER_OF_EVENTS * 2];
+
+/*
+ * Array holding counter start times (in ns) for each counter. A zero
+ * here indicates that the activity monitored by this counter is not
+ * running.
+ */
+static struct timespec timeline_event_starttime[NUMBER_OF_TIMELINE_EVENTS];
+
+/* The data we have recorded */
+static unsigned int timeline_data[NUMBER_OF_TIMELINE_EVENTS];
+static unsigned int sw_counter_data[NUMBER_OF_SOFTWARE_COUNTERS];
+static unsigned int accumulators_data[NUMBER_OF_ACCUMULATORS];
+
+/* Hold the previous timestamp, used to calculate the sample interval. */
+static struct timespec prev_timestamp;
+
+/**
+ * Returns the timespan (in microseconds) between the two specified timestamps.
+ *
+ * @param start Ptr to the start timestamp
+ * @param end Ptr to the end timestamp
+ *
+ * @return Number of microseconds between the two timestamps (can be negative if start follows end).
+ */
+static inline long get_duration_us(const struct timespec *start, const struct timespec *end)
+{
+ long event_duration_us = (end->tv_nsec - start->tv_nsec) / 1000;
+
+ event_duration_us += (end->tv_sec - start->tv_sec) * 1000000;
+
+ return event_duration_us;
+}
+
+static void record_timeline_event(unsigned int timeline_index, unsigned int type)
+{
+ struct timespec event_timestamp;
+ struct timespec *event_start = &timeline_event_starttime[timeline_index];
+
+ switch (type) {
+ case ACTIVITY_START:
+ /* Get the event time... */
+ getnstimeofday(&event_timestamp);
+
+ /* Remember the start time if the activity is not already started */
+ if (event_start->tv_sec == 0)
+ *event_start = event_timestamp; /* Structure copy */
+ break;
+
+ case ACTIVITY_STOP:
+ /* if the counter was started... */
+ if (event_start->tv_sec != 0) {
+ /* Get the event time... */
+ getnstimeofday(&event_timestamp);
+
+ /* Accumulate the duration in us */
+ timeline_data[timeline_index] += get_duration_us(event_start, &event_timestamp);
+
+ /* Reset the start time to indicate the activity is stopped. */
+ event_start->tv_sec = 0;
+ }
+ break;
+
+ default:
+ /* Other activity events are ignored. */
+ break;
+ }
+}
+
+/*
+ * Documentation about the following tracepoints is in mali_linux_trace.h
+ */
+
+GATOR_DEFINE_PROBE(mali_pm_status, TP_PROTO(unsigned int event_id, unsigned long long value))
+{
+#define SHADER_PRESENT_LO 0x100 /* (RO) Shader core present bitmap, low word */
+#define TILER_PRESENT_LO 0x110 /* (RO) Tiler core present bitmap, low word */
+#define L2_PRESENT_LO 0x120 /* (RO) Level 2 cache present bitmap, low word */
+#define BIT_AT(value, pos) ((value >> pos) & 1)
+
+ static unsigned long long previous_shader_bitmask;
+ static unsigned long long previous_tiler_bitmask;
+ static unsigned long long previous_l2_bitmask;
+
+ switch (event_id) {
+ case SHADER_PRESENT_LO:
+ {
+ unsigned long long changed_bitmask = previous_shader_bitmask ^ value;
+ int pos;
+
+ for (pos = 0; pos < NUM_PM_SHADER; ++pos) {
+ if (BIT_AT(changed_bitmask, pos))
+ record_timeline_event(PM_SHADER_0 + pos, BIT_AT(value, pos) ? ACTIVITY_START : ACTIVITY_STOP);
+ }
+
+ previous_shader_bitmask = value;
+ break;
+ }
+
+ case TILER_PRESENT_LO:
+ {
+ unsigned long long changed = previous_tiler_bitmask ^ value;
+
+ if (BIT_AT(changed, 0))
+ record_timeline_event(PM_TILER_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+
+ previous_tiler_bitmask = value;
+ break;
+ }
+
+ case L2_PRESENT_LO:
+ {
+ unsigned long long changed = previous_l2_bitmask ^ value;
+
+ if (BIT_AT(changed, 0))
+ record_timeline_event(PM_L2_0, BIT_AT(value, 0) ? ACTIVITY_START : ACTIVITY_STOP);
+ if (BIT_AT(changed, 4))
+ record_timeline_event(PM_L2_1, BIT_AT(value, 4) ? ACTIVITY_START : ACTIVITY_STOP);
+
+ previous_l2_bitmask = value;
+ break;
+ }
+
+ default:
+ /* No other blocks are supported at present */
+ break;
+ }
+
+#undef SHADER_PRESENT_LO
+#undef TILER_PRESENT_LO
+#undef L2_PRESENT_LO
+#undef BIT_AT
+}
+
+GATOR_DEFINE_PROBE(mali_page_fault_insert_pages, TP_PROTO(int event_id, unsigned long value))
+{
+ /* We add to the previous since we may receive many tracepoints in one sample period */
+ sw_counter_data[MMU_PAGE_FAULT_0 + event_id] += value;
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_in_use, TP_PROTO(int event_id))
+{
+ record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_START);
+}
+
+GATOR_DEFINE_PROBE(mali_mmu_as_released, TP_PROTO(int event_id))
+{
+ record_timeline_event(MMU_AS_0 + event_id, ACTIVITY_STOP);
+}
+
+GATOR_DEFINE_PROBE(mali_total_alloc_pages_change, TP_PROTO(long long int event_id))
+{
+ accumulators_data[TOTAL_ALLOC_PAGES] = event_id;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+ int event;
+ /*
+ * Create the filesystem for all events
+ */
+ int counter_index = 0;
+ mali_profiling_control_type *mali_control;
+
+ for (event = FIRST_TIMELINE_EVENT; event < FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS; event++) {
+ if (gator_mali_create_file_system(mali_name, timeline_event_names[counter_index], sb, root, &counters[event], NULL) != 0)
+ return -1;
+ counter_index++;
+ }
+ counter_index = 0;
+ for (event = FIRST_SOFTWARE_COUNTER; event < FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS; event++) {
+ if (gator_mali_create_file_system(mali_name, software_counter_names[counter_index], sb, root, &counters[event], NULL) != 0)
+ return -1;
+ counter_index++;
+ }
+ counter_index = 0;
+ for (event = FIRST_ACCUMULATOR; event < FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS; event++) {
+ if (gator_mali_create_file_system(mali_name, accumulators_names[counter_index], sb, root, &counters[event], NULL) != 0)
+ return -1;
+ counter_index++;
+ }
+
+ mali_control = symbol_get(_mali_profiling_control);
+ if (mali_control) {
+ if (gator_mali_create_file_system(mali_name, "Filmstrip_cnt0", sb, root, &counters[FILMSTRIP], &filmstrip_event) != 0)
+ return -1;
+ symbol_put(_mali_profiling_control);
+ }
+
+ return 0;
+}
+
+static int register_tracepoints(void)
+{
+ if (GATOR_REGISTER_TRACE(mali_pm_status)) {
+ pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint failed to activate\n");
+ return 0;
+ }
+
+ if (GATOR_REGISTER_TRACE(mali_page_fault_insert_pages)) {
+ pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint failed to activate\n");
+ return 0;
+ }
+
+ if (GATOR_REGISTER_TRACE(mali_mmu_as_in_use)) {
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint failed to activate\n");
+ return 0;
+ }
+
+ if (GATOR_REGISTER_TRACE(mali_mmu_as_released)) {
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint failed to activate\n");
+ return 0;
+ }
+
+ if (GATOR_REGISTER_TRACE(mali_total_alloc_pages_change)) {
+ pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint failed to activate\n");
+ return 0;
+ }
+
+ pr_debug("gator: Mali-Midgard: start\n");
+ pr_debug("gator: Mali-Midgard: mali_pm_status probe is at %p\n", &probe_mali_pm_status);
+ pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages probe is at %p\n", &probe_mali_page_fault_insert_pages);
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use probe is at %p\n", &probe_mali_mmu_as_in_use);
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_released probe is at %p\n", &probe_mali_mmu_as_released);
+ pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change probe is at %p\n", &probe_mali_total_alloc_pages_change);
+
+ return 1;
+}
+
+static int start(void)
+{
+ unsigned int cnt;
+ mali_profiling_control_type *mali_control;
+
+ /* Clean all data for the next capture */
+ for (cnt = 0; cnt < NUMBER_OF_TIMELINE_EVENTS; cnt++) {
+ timeline_event_starttime[cnt].tv_sec = timeline_event_starttime[cnt].tv_nsec = 0;
+ timeline_data[cnt] = 0;
+ }
+
+ for (cnt = 0; cnt < NUMBER_OF_SOFTWARE_COUNTERS; cnt++)
+ sw_counter_data[cnt] = 0;
+
+ for (cnt = 0; cnt < NUMBER_OF_ACCUMULATORS; cnt++)
+ accumulators_data[cnt] = 0;
+
+ /* Register tracepoints */
+ if (register_tracepoints() == 0)
+ return -1;
+
+ /* Generic control interface for Mali DDK. */
+ mali_control = symbol_get(_mali_profiling_control);
+ if (mali_control) {
+ /* The event attribute in the XML file keeps the actual frame rate. */
+ unsigned int enabled = counters[FILMSTRIP].enabled ? 1 : 0;
+ unsigned int rate = filmstrip_event & 0xff;
+ unsigned int resize_factor = (filmstrip_event >> 8) & 0xff;
+
+ pr_debug("gator: mali online _mali_profiling_control symbol @ %p\n", mali_control);
+
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+ mali_control(FBDUMP_CONTROL_ENABLE, enabled);
+ mali_control(FBDUMP_CONTROL_RATE, rate);
+ mali_control(FBDUMP_CONTROL_RESIZE_FACTOR, resize_factor);
+
+ pr_debug("gator: sent mali_control enabled=%d, rate=%d, resize_factor=%d\n", enabled, rate, resize_factor);
+
+ symbol_put(_mali_profiling_control);
+ } else {
+ pr_err("gator: mali online _mali_profiling_control symbol not found\n");
+ }
+
+ /*
+ * Set the first timestamp for calculating the sample interval. The first interval could be quite long,
+ * since it will be the time between 'start' and the first 'read'.
+ * This means that timeline values will be divided by a big number for the first sample.
+ */
+ getnstimeofday(&prev_timestamp);
+
+ return 0;
+}
+
+static void stop(void)
+{
+ mali_profiling_control_type *mali_control;
+
+ pr_debug("gator: Mali-Midgard: stop\n");
+
+ /*
+ * It is safe to unregister traces even if they were not successfully
+ * registered, so no need to check.
+ */
+ GATOR_UNREGISTER_TRACE(mali_pm_status);
+ pr_debug("gator: Mali-Midgard: mali_pm_status tracepoint deactivated\n");
+
+ GATOR_UNREGISTER_TRACE(mali_page_fault_insert_pages);
+ pr_debug("gator: Mali-Midgard: mali_page_fault_insert_pages tracepoint deactivated\n");
+
+ GATOR_UNREGISTER_TRACE(mali_mmu_as_in_use);
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_in_use tracepoint deactivated\n");
+
+ GATOR_UNREGISTER_TRACE(mali_mmu_as_released);
+ pr_debug("gator: Mali-Midgard: mali_mmu_as_released tracepoint deactivated\n");
+
+ GATOR_UNREGISTER_TRACE(mali_total_alloc_pages_change);
+ pr_debug("gator: Mali-Midgard: mali_total_alloc_pages_change tracepoint deactivated\n");
+
+ /* Generic control interface for Mali DDK. */
+ mali_control = symbol_get(_mali_profiling_control);
+ if (mali_control) {
+ pr_debug("gator: mali offline _mali_profiling_control symbol @ %p\n", mali_control);
+
+ mali_control(FBDUMP_CONTROL_ENABLE, 0);
+
+ symbol_put(_mali_profiling_control);
+ } else {
+ pr_err("gator: mali offline _mali_profiling_control symbol not found\n");
+ }
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+ int cnt;
+ int len = 0;
+ long sample_interval_us = 0;
+ struct timespec read_timestamp;
+
+ if (!on_primary_core())
+ return 0;
+
+ /* Get the start of this sample period. */
+ getnstimeofday(&read_timestamp);
+
+ /*
+ * Calculate the sample interval if the previous sample time is valid.
+ * We use tv_sec since it will not be 0.
+ */
+ if (prev_timestamp.tv_sec != 0)
+ sample_interval_us = get_duration_us(&prev_timestamp, &read_timestamp);
+
+ /* Structure copy. Update the previous timestamp. */
+ prev_timestamp = read_timestamp;
+
+ /*
+ * Report the timeline counters (ACTIVITY_START/STOP)
+ */
+ for (cnt = FIRST_TIMELINE_EVENT; cnt < (FIRST_TIMELINE_EVENT + NUMBER_OF_TIMELINE_EVENTS); cnt++) {
+ struct mali_counter *counter = &counters[cnt];
+
+ if (counter->enabled) {
+ const int index = cnt - FIRST_TIMELINE_EVENT;
+ unsigned int value;
+
+ /* If the activity is still running, reset its start time to the
+ * start of this sample period to correct the count. Add the
+ * time up to the end of the sample onto the count.
+ */
+ if (timeline_event_starttime[index].tv_sec != 0) {
+ const long event_duration = get_duration_us(&timeline_event_starttime[index], &read_timestamp);
+
+ timeline_data[index] += event_duration;
+ timeline_event_starttime[index] = read_timestamp; /* Activity is still running. */
+ }
+
+ if (sample_interval_us != 0) {
+ /* Convert the counter to a percent-of-sample value */
+ value = (timeline_data[index] * 100) / sample_interval_us;
+ } else {
+ pr_debug("gator: Mali-Midgard: setting value to zero\n");
+ value = 0;
+ }
+
+ /* Clear the counter value ready for the next sample. */
+ timeline_data[index] = 0;
+
+ counter_dump[len++] = counter->key;
+ counter_dump[len++] = value;
+ }
+ }
+
+ /* Report the software counters */
+ for (cnt = FIRST_SOFTWARE_COUNTER; cnt < (FIRST_SOFTWARE_COUNTER + NUMBER_OF_SOFTWARE_COUNTERS); cnt++) {
+ const struct mali_counter *counter = &counters[cnt];
+
+ if (counter->enabled) {
+ const int index = cnt - FIRST_SOFTWARE_COUNTER;
+
+ counter_dump[len++] = counter->key;
+ counter_dump[len++] = sw_counter_data[index];
+ /* Set the value to zero for the next time */
+ sw_counter_data[index] = 0;
+ }
+ }
+
+ /* Report the accumulators */
+ for (cnt = FIRST_ACCUMULATOR; cnt < (FIRST_ACCUMULATOR + NUMBER_OF_ACCUMULATORS); cnt++) {
+ const struct mali_counter *counter = &counters[cnt];
+
+ if (counter->enabled) {
+ const int index = cnt - FIRST_ACCUMULATOR;
+
+ counter_dump[len++] = counter->key;
+ counter_dump[len++] = accumulators_data[index];
+ /* Do not zero the accumulator */
+ }
+ }
+
+ /* Update the buffer */
+ if (buffer)
+ *buffer = counter_dump;
+
+ return len;
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+ .create_files = create_files,
+ .start = start,
+ .stop = stop,
+ .read = read
+};
+
+extern int gator_events_mali_midgard_init(void)
+{
+ pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+ gator_mali_initialise_counters(counters, NUMBER_OF_EVENTS);
+
+ return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw.c b/drivers/gator/gator_events_mali_midgard_hw.c
new file mode 100644
index 0000000..7e1eee3
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw.c
@@ -0,0 +1,978 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+
+/* Mali Midgard DDK includes */
+#if defined(MALI_SIMPLE_API)
+/* Header with wrapper functions to kbase structures and functions */
+#include "mali_kbase_gator_api.h"
+#elif defined(MALI_DIR_MIDGARD)
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard */
+#include "mali_linux_trace.h"
+#include "mali_kbase.h"
+#include "mali_kbase_mem_linux.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx */
+#include "linux/mali_linux_trace.h"
+#include "kbase/src/common/mali_kbase.h"
+#include "kbase/src/linux/mali_kbase_mem_linux.h"
+#endif
+
+/* If API version is not specified then assume API version 1. */
+#ifndef MALI_DDK_GATOR_API_VERSION
+#define MALI_DDK_GATOR_API_VERSION 1
+#endif
+
+#if (MALI_DDK_GATOR_API_VERSION != 1) && (MALI_DDK_GATOR_API_VERSION != 2) && (MALI_DDK_GATOR_API_VERSION != 3)
+#error MALI_DDK_GATOR_API_VERSION is invalid (must be 1 for r1/r2 DDK, or 2 for r3/r4 DDK, or 3 for r5 and later DDK).
+#endif
+
+#if !defined(CONFIG_MALI_GATOR_SUPPORT)
+#error CONFIG_MALI_GATOR_SUPPORT is required for GPU activity and software counters
+#endif
+
+#include "gator_events_mali_common.h"
+
+/*
+ * Mali-Midgard
+ */
+#if MALI_DDK_GATOR_API_VERSION == 3
+static uint32_t (*kbase_gator_instr_hwcnt_dump_irq_symbol)(struct kbase_gator_hwcnt_handles *);
+static uint32_t (*kbase_gator_instr_hwcnt_dump_complete_symbol)(struct kbase_gator_hwcnt_handles *, uint32_t *const);
+static struct kbase_gator_hwcnt_handles *(*kbase_gator_hwcnt_init_symbol)(struct kbase_gator_hwcnt_info *);
+static void (*kbase_gator_hwcnt_term_symbol)(struct kbase_gator_hwcnt_info *, struct kbase_gator_hwcnt_handles *);
+
+#else
+static struct kbase_device *(*kbase_find_device_symbol)(int);
+static struct kbase_context *(*kbase_create_context_symbol)(struct kbase_device *);
+static void (*kbase_destroy_context_symbol)(struct kbase_context *);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32);
+static void (*kbase_va_free_symbol)(struct kbase_context *, void *);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+static void *(*kbase_va_alloc_symbol)(struct kbase_context *, u32, struct kbase_hwc_dma_mapping *);
+static void (*kbase_va_free_symbol)(struct kbase_context *, struct kbase_hwc_dma_mapping *);
+#endif
+
+static mali_error (*kbase_instr_hwcnt_enable_symbol)(struct kbase_context *, struct kbase_uk_hwcnt_setup *);
+static mali_error (*kbase_instr_hwcnt_disable_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_clear_symbol)(struct kbase_context *);
+static mali_error (*kbase_instr_hwcnt_dump_irq_symbol)(struct kbase_context *);
+static mali_bool (*kbase_instr_hwcnt_dump_complete_symbol)(struct kbase_context *, mali_bool *);
+
+static long shader_present_low;
+#endif
+
+/** The interval between reads, in ns.
+ *
+ * Earlier we introduced a 'hold off for 1ms after last read' to
+ * resolve MIDBASE-2178 and MALINE-724. However, the 1ms hold off is
+ * too long if no context switches occur as there is a race between
+ * this value and the tick of the read clock in gator which is also
+ * 1ms. If we 'miss' the current read, the counter values are
+ * effectively 'spread' over 2ms and the values seen are half what
+ * they should be (since Streamline averages over sample time). In the
+ * presence of context switches this spread can vary and markedly
+ * affect the counters. Currently there is no 'proper' solution to
+ * this, but empirically we have found that reducing the minimum read
+ * interval to 950us causes the counts to be much more stable.
+ */
+static const int READ_INTERVAL_NSEC = 950000;
+
+#if GATOR_TEST
+#include "gator_events_mali_midgard_hw_test.c"
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION != 3
+/* Blocks for HW counters */
+enum {
+ JM_BLOCK = 0,
+ TILER_BLOCK,
+ SHADER_BLOCK,
+ MMU_BLOCK
+};
+#endif
+
+static const char *mali_name;
+
+/* Counters for Mali-Midgard:
+ *
+ * For HW counters we need strings to create /dev/gator/events files.
+ * Enums are not needed because the position of the HW name in the array is the same
+ * of the corresponding value in the received block of memory.
+ * HW counters are requested by calculating a bitmask, passed then to the driver.
+ * Every millisecond a HW counters dump is requested, and if the previous has been completed they are read.
+ */
+
+/* Hardware Counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+
+static const char *const *hardware_counter_names;
+static int number_of_hardware_counters;
+
+#else
+
+static const char *const hardware_counter_names[] = {
+ /* Job Manager */
+ "",
+ "",
+ "",
+ "",
+ "MESSAGES_SENT",
+ "MESSAGES_RECEIVED",
+ "GPU_ACTIVE", /* 6 */
+ "IRQ_ACTIVE",
+ "JS0_JOBS",
+ "JS0_TASKS",
+ "JS0_ACTIVE",
+ "",
+ "JS0_WAIT_READ",
+ "JS0_WAIT_ISSUE",
+ "JS0_WAIT_DEPEND",
+ "JS0_WAIT_FINISH",
+ "JS1_JOBS",
+ "JS1_TASKS",
+ "JS1_ACTIVE",
+ "",
+ "JS1_WAIT_READ",
+ "JS1_WAIT_ISSUE",
+ "JS1_WAIT_DEPEND",
+ "JS1_WAIT_FINISH",
+ "JS2_JOBS",
+ "JS2_TASKS",
+ "JS2_ACTIVE",
+ "",
+ "JS2_WAIT_READ",
+ "JS2_WAIT_ISSUE",
+ "JS2_WAIT_DEPEND",
+ "JS2_WAIT_FINISH",
+ "JS3_JOBS",
+ "JS3_TASKS",
+ "JS3_ACTIVE",
+ "",
+ "JS3_WAIT_READ",
+ "JS3_WAIT_ISSUE",
+ "JS3_WAIT_DEPEND",
+ "JS3_WAIT_FINISH",
+ "JS4_JOBS",
+ "JS4_TASKS",
+ "JS4_ACTIVE",
+ "",
+ "JS4_WAIT_READ",
+ "JS4_WAIT_ISSUE",
+ "JS4_WAIT_DEPEND",
+ "JS4_WAIT_FINISH",
+ "JS5_JOBS",
+ "JS5_TASKS",
+ "JS5_ACTIVE",
+ "",
+ "JS5_WAIT_READ",
+ "JS5_WAIT_ISSUE",
+ "JS5_WAIT_DEPEND",
+ "JS5_WAIT_FINISH",
+ "JS6_JOBS",
+ "JS6_TASKS",
+ "JS6_ACTIVE",
+ "",
+ "JS6_WAIT_READ",
+ "JS6_WAIT_ISSUE",
+ "JS6_WAIT_DEPEND",
+ "JS6_WAIT_FINISH",
+
+ /*Tiler */
+ "",
+ "",
+ "",
+ "JOBS_PROCESSED",
+ "TRIANGLES",
+ "QUADS",
+ "POLYGONS",
+ "POINTS",
+ "LINES",
+ "VCACHE_HIT",
+ "VCACHE_MISS",
+ "FRONT_FACING",
+ "BACK_FACING",
+ "PRIM_VISIBLE",
+ "PRIM_CULLED",
+ "PRIM_CLIPPED",
+ "LEVEL0",
+ "LEVEL1",
+ "LEVEL2",
+ "LEVEL3",
+ "LEVEL4",
+ "LEVEL5",
+ "LEVEL6",
+ "LEVEL7",
+ "COMMAND_1",
+ "COMMAND_2",
+ "COMMAND_3",
+ "COMMAND_4",
+ "COMMAND_4_7",
+ "COMMAND_8_15",
+ "COMMAND_16_63",
+ "COMMAND_64",
+ "COMPRESS_IN",
+ "COMPRESS_OUT",
+ "COMPRESS_FLUSH",
+ "TIMESTAMPS",
+ "PCACHE_HIT",
+ "PCACHE_MISS",
+ "PCACHE_LINE",
+ "PCACHE_STALL",
+ "WRBUF_HIT",
+ "WRBUF_MISS",
+ "WRBUF_LINE",
+ "WRBUF_PARTIAL",
+ "WRBUF_STALL",
+ "ACTIVE",
+ "LOADING_DESC",
+ "INDEX_WAIT",
+ "INDEX_RANGE_WAIT",
+ "VERTEX_WAIT",
+ "PCACHE_WAIT",
+ "WRBUF_WAIT",
+ "BUS_READ",
+ "BUS_WRITE",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "UTLB_STALL",
+ "UTLB_REPLAY_MISS",
+ "UTLB_REPLAY_FULL",
+ "UTLB_NEW_MISS",
+ "UTLB_HIT",
+
+ /* Shader Core */
+ "",
+ "",
+ "",
+ "SHADER_CORE_ACTIVE",
+ "FRAG_ACTIVE",
+ "FRAG_PRIMATIVES",
+ "FRAG_PRIMATIVES_DROPPED",
+ "FRAG_CYCLE_DESC",
+ "FRAG_CYCLES_PLR",
+ "FRAG_CYCLES_VERT",
+ "FRAG_CYCLES_TRISETUP",
+ "FRAG_CYCLES_RAST",
+ "FRAG_THREADS",
+ "FRAG_DUMMY_THREADS",
+ "FRAG_QUADS_RAST",
+ "FRAG_QUADS_EZS_TEST",
+ "FRAG_QUADS_EZS_KILLED",
+ "FRAG_QUADS_LZS_TEST",
+ "FRAG_QUADS_LZS_KILLED",
+ "FRAG_CYCLE_NO_TILE",
+ "FRAG_NUM_TILES",
+ "FRAG_TRANS_ELIM",
+ "COMPUTE_ACTIVE",
+ "COMPUTE_TASKS",
+ "COMPUTE_THREADS",
+ "COMPUTE_CYCLES_DESC",
+ "TRIPIPE_ACTIVE",
+ "ARITH_WORDS",
+ "ARITH_CYCLES_REG",
+ "ARITH_CYCLES_L0",
+ "ARITH_FRAG_DEPEND",
+ "LS_WORDS",
+ "LS_ISSUES",
+ "LS_RESTARTS",
+ "LS_REISSUES_MISS",
+ "LS_REISSUES_VD",
+ "LS_REISSUE_ATTRIB_MISS",
+ "LS_NO_WB",
+ "TEX_WORDS",
+ "TEX_BUBBLES",
+ "TEX_WORDS_L0",
+ "TEX_WORDS_DESC",
+ "TEX_THREADS",
+ "TEX_RECIRC_FMISS",
+ "TEX_RECIRC_DESC",
+ "TEX_RECIRC_MULTI",
+ "TEX_RECIRC_PMISS",
+ "TEX_RECIRC_CONF",
+ "LSC_READ_HITS",
+ "LSC_READ_MISSES",
+ "LSC_WRITE_HITS",
+ "LSC_WRITE_MISSES",
+ "LSC_ATOMIC_HITS",
+ "LSC_ATOMIC_MISSES",
+ "LSC_LINE_FETCHES",
+ "LSC_DIRTY_LINE",
+ "LSC_SNOOPS",
+ "AXI_TLB_STALL",
+ "AXI_TLB_MIESS",
+ "AXI_TLB_TRANSACTION",
+ "LS_TLB_MISS",
+ "LS_TLB_HIT",
+ "AXI_BEATS_READ",
+ "AXI_BEATS_WRITTEN",
+
+ /*L2 and MMU */
+ "",
+ "",
+ "",
+ "",
+ "MMU_HIT",
+ "MMU_NEW_MISS",
+ "MMU_REPLAY_FULL",
+ "MMU_REPLAY_MISS",
+ "MMU_TABLE_WALK",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "UTLB_HIT",
+ "UTLB_NEW_MISS",
+ "UTLB_REPLAY_FULL",
+ "UTLB_REPLAY_MISS",
+ "UTLB_STALL",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "",
+ "L2_WRITE_BEATS",
+ "L2_READ_BEATS",
+ "L2_ANY_LOOKUP",
+ "L2_READ_LOOKUP",
+ "L2_SREAD_LOOKUP",
+ "L2_READ_REPLAY",
+ "L2_READ_SNOOP",
+ "L2_READ_HIT",
+ "L2_CLEAN_MISS",
+ "L2_WRITE_LOOKUP",
+ "L2_SWRITE_LOOKUP",
+ "L2_WRITE_REPLAY",
+ "L2_WRITE_SNOOP",
+ "L2_WRITE_HIT",
+ "L2_EXT_READ_FULL",
+ "L2_EXT_READ_HALF",
+ "L2_EXT_WRITE_FULL",
+ "L2_EXT_WRITE_HALF",
+ "L2_EXT_READ",
+ "L2_EXT_READ_LINE",
+ "L2_EXT_WRITE",
+ "L2_EXT_WRITE_LINE",
+ "L2_EXT_WRITE_SMALL",
+ "L2_EXT_BARRIER",
+ "L2_EXT_AR_STALL",
+ "L2_EXT_R_BUF_FULL",
+ "L2_EXT_RD_BUF_FULL",
+ "L2_EXT_R_RAW",
+ "L2_EXT_W_STALL",
+ "L2_EXT_W_BUF_FULL",
+ "L2_EXT_R_W_HAZARD",
+ "L2_TAG_HAZARD",
+ "L2_SNOOP_FULL",
+ "L2_REPLAY_FULL"
+};
+
+static const int number_of_hardware_counters = ARRAY_SIZE(hardware_counter_names);
+
+#endif
+
+#define GET_HW_BLOCK(c) (((c) >> 6) & 0x3)
+#define GET_COUNTER_OFFSET(c) ((c) & 0x3f)
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+/* Opaque handles for kbase_context and kbase_hwc_dma_mapping */
+static struct kbase_gator_hwcnt_handles *handles;
+
+/* Information about hardware counters */
+static struct kbase_gator_hwcnt_info *in_out_info;
+
+#else
+/* Memory to dump hardware counters into */
+static void *kernel_dump_buffer;
+
+#if MALI_DDK_GATOR_API_VERSION == 2
+/* DMA state used to manage lifetime of the buffer */
+struct kbase_hwc_dma_mapping kernel_dump_buffer_handle;
+#endif
+
+/* kbase context and device */
+static struct kbase_context *kbcontext;
+static struct kbase_device *kbdevice;
+
+/*
+ * The following function has no external prototype in older DDK
+ * revisions. When the DDK is updated then this should be removed.
+ */
+struct kbase_device *kbase_find_device(int minor);
+#endif
+
+static volatile bool kbase_device_busy;
+static unsigned int num_hardware_counters_enabled;
+
+/* gatorfs variables for counter enable state */
+static struct mali_counter *counters;
+
+/* An array used to return the data we recorded as key,value pairs */
+static int *counter_dump;
+
+extern struct mali_counter mali_activity[3];
+
+static const char *const mali_activity_names[] = {
+ "fragment",
+ "vertex",
+ "opencl",
+};
+
+#define SYMBOL_GET(FUNCTION, ERROR_COUNT) \
+ do { \
+ if (FUNCTION ## _symbol) { \
+ pr_err("gator: mali " #FUNCTION " symbol was already registered\n"); \
+ (ERROR_COUNT)++; \
+ } else { \
+ FUNCTION ## _symbol = symbol_get(FUNCTION); \
+ if (!FUNCTION ## _symbol) { \
+ pr_err("gator: mali online " #FUNCTION " symbol not found\n"); \
+ (ERROR_COUNT)++; \
+ } \
+ } \
+ } while (0)
+
+#define SYMBOL_CLEANUP(FUNCTION) \
+ do { \
+ if (FUNCTION ## _symbol) { \
+ symbol_put(FUNCTION); \
+ FUNCTION ## _symbol = NULL; \
+ } \
+ } while (0)
+
+/**
+ * Execute symbol_get for all the Mali symbols and check for success.
+ * @return the number of symbols not loaded.
+ */
+static int init_symbols(void)
+{
+ int error_count = 0;
+#if MALI_DDK_GATOR_API_VERSION == 3
+ SYMBOL_GET(kbase_gator_instr_hwcnt_dump_irq, error_count);
+ SYMBOL_GET(kbase_gator_instr_hwcnt_dump_complete, error_count);
+ SYMBOL_GET(kbase_gator_hwcnt_init, error_count);
+ SYMBOL_GET(kbase_gator_hwcnt_term, error_count);
+#else
+ SYMBOL_GET(kbase_find_device, error_count);
+ SYMBOL_GET(kbase_create_context, error_count);
+ SYMBOL_GET(kbase_va_alloc, error_count);
+ SYMBOL_GET(kbase_instr_hwcnt_enable, error_count);
+ SYMBOL_GET(kbase_instr_hwcnt_clear, error_count);
+ SYMBOL_GET(kbase_instr_hwcnt_dump_irq, error_count);
+ SYMBOL_GET(kbase_instr_hwcnt_dump_complete, error_count);
+ SYMBOL_GET(kbase_instr_hwcnt_disable, error_count);
+ SYMBOL_GET(kbase_va_free, error_count);
+ SYMBOL_GET(kbase_destroy_context, error_count);
+#endif
+
+ return error_count;
+}
+
+/**
+ * Execute symbol_put for all the registered Mali symbols.
+ */
+static void clean_symbols(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+ SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_irq);
+ SYMBOL_CLEANUP(kbase_gator_instr_hwcnt_dump_complete);
+ SYMBOL_CLEANUP(kbase_gator_hwcnt_init);
+ SYMBOL_CLEANUP(kbase_gator_hwcnt_term);
+#else
+ SYMBOL_CLEANUP(kbase_find_device);
+ SYMBOL_CLEANUP(kbase_create_context);
+ SYMBOL_CLEANUP(kbase_va_alloc);
+ SYMBOL_CLEANUP(kbase_instr_hwcnt_enable);
+ SYMBOL_CLEANUP(kbase_instr_hwcnt_clear);
+ SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_irq);
+ SYMBOL_CLEANUP(kbase_instr_hwcnt_dump_complete);
+ SYMBOL_CLEANUP(kbase_instr_hwcnt_disable);
+ SYMBOL_CLEANUP(kbase_va_free);
+ SYMBOL_CLEANUP(kbase_destroy_context);
+#endif
+}
+
+/**
+ * Determines whether a read should take place
+ * @param current_time The current time, obtained from getnstimeofday()
+ * @param prev_time_s The number of seconds at the previous read attempt.
+ * @param next_read_time_ns The time (in ns) when the next read should be allowed.
+ *
+ * Note that this function has been separated out here to allow it to be tested.
+ */
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns)
+{
+ /* If the current ns count rolls over a second, roll the next read time too. */
+ if (current_time->tv_sec != *prev_time_s)
+ *next_read_time_ns = *next_read_time_ns - NSEC_PER_SEC;
+
+ /* Abort the read if the next read time has not arrived. */
+ if (current_time->tv_nsec < *next_read_time_ns)
+ return 0;
+
+ /* Set the next read some fixed time after this one, and update the read timestamp. */
+ *next_read_time_ns = current_time->tv_nsec + READ_INTERVAL_NSEC;
+
+ *prev_time_s = current_time->tv_sec;
+ return 1;
+}
+
+static int start(void)
+{
+#if MALI_DDK_GATOR_API_VERSION != 3
+ struct kbase_uk_hwcnt_setup setup;
+ unsigned long long shadersPresent = 0;
+ u16 bitmask[] = { 0, 0, 0, 0 };
+ mali_error err;
+#endif
+ int cnt;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+ /* Setup HW counters */
+ num_hardware_counters_enabled = 0;
+
+ /* Declare and initialise kbase_gator_hwcnt_info structure */
+ in_out_info = kmalloc(sizeof(*in_out_info), GFP_KERNEL);
+ for (cnt = 0; cnt < ARRAY_SIZE(in_out_info->bitmask); cnt++)
+ in_out_info->bitmask[cnt] = 0;
+
+ /* Calculate enable bitmasks based on counters_enabled array */
+ for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+ if (counters[cnt].enabled) {
+ int block = GET_HW_BLOCK(cnt);
+ int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+ in_out_info->bitmask[block] |= (1 << enable_bit);
+ pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+ num_hardware_counters_enabled++;
+ }
+ }
+
+ /* Create a kbase context for HW counters */
+ if (num_hardware_counters_enabled > 0) {
+ if (init_symbols() > 0) {
+ clean_symbols();
+ /* No Mali driver code entrypoints found - not a fault. */
+ return 0;
+ }
+
+ handles = kbase_gator_hwcnt_init_symbol(in_out_info);
+
+ if (handles == NULL)
+ goto out;
+
+ kbase_device_busy = false;
+ }
+
+ return 0;
+#else
+ /* Setup HW counters */
+ num_hardware_counters_enabled = 0;
+
+ /* Calculate enable bitmasks based on counters_enabled array */
+ for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+ const struct mali_counter *counter = &counters[cnt];
+
+ if (counter->enabled) {
+ int block = GET_HW_BLOCK(cnt);
+ int enable_bit = GET_COUNTER_OFFSET(cnt) / 4;
+
+ bitmask[block] |= (1 << enable_bit);
+ pr_debug("gator: Mali-Midgard: hardware counter %s selected [%d]\n", hardware_counter_names[cnt], cnt);
+ num_hardware_counters_enabled++;
+ }
+ }
+
+ /* Create a kbase context for HW counters */
+ if (num_hardware_counters_enabled > 0) {
+ if (init_symbols() > 0) {
+ clean_symbols();
+ /* No Mali driver code entrypoints found - not a fault. */
+ return 0;
+ }
+
+ kbdevice = kbase_find_device_symbol(-1);
+
+ /* If we already got a context, fail */
+ if (kbcontext) {
+ pr_debug("gator: Mali-Midgard: error context already present\n");
+ goto out;
+ }
+
+ /* kbcontext will only be valid after all the Mali symbols are loaded successfully */
+ kbcontext = kbase_create_context_symbol(kbdevice);
+ if (!kbcontext) {
+ pr_debug("gator: Mali-Midgard: error creating kbase context\n");
+ goto out;
+ }
+
+ /* See if we can get the number of shader cores */
+ shadersPresent = kbdevice->shader_present_bitmap;
+ shader_present_low = (unsigned long)shadersPresent;
+
+ /*
+ * The amount of memory needed to store the dump (bytes)
+ * DUMP_SIZE = number of core groups
+ * * number of blocks (always 8 for midgard)
+ * * number of counters per block (always 64 for midgard)
+ * * number of bytes per counter (always 4 in midgard)
+ * For a Mali-Midgard with a single core group = 1 * 8 * 64 * 4 = 2048
+ * For a Mali-Midgard with a dual core group = 2 * 8 * 64 * 4 = 4096
+ */
+#if MALI_DDK_GATOR_API_VERSION == 1
+ kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+ kernel_dump_buffer = kbase_va_alloc_symbol(kbcontext, 4096, &kernel_dump_buffer_handle);
+#endif
+ if (!kernel_dump_buffer) {
+ pr_debug("gator: Mali-Midgard: error trying to allocate va\n");
+ goto destroy_context;
+ }
+
+ setup.dump_buffer = (uintptr_t)kernel_dump_buffer;
+ setup.jm_bm = bitmask[JM_BLOCK];
+ setup.tiler_bm = bitmask[TILER_BLOCK];
+ setup.shader_bm = bitmask[SHADER_BLOCK];
+ setup.mmu_l2_bm = bitmask[MMU_BLOCK];
+ /* These counters do not exist on Mali-T60x */
+ setup.l3_cache_bm = 0;
+
+ /* Use kbase API to enable hardware counters and provide dump buffer */
+ err = kbase_instr_hwcnt_enable_symbol(kbcontext, &setup);
+ if (err != MALI_ERROR_NONE) {
+ pr_debug("gator: Mali-Midgard: can't setup hardware counters\n");
+ goto free_buffer;
+ }
+ pr_debug("gator: Mali-Midgard: hardware counters enabled\n");
+ kbase_instr_hwcnt_clear_symbol(kbcontext);
+ pr_debug("gator: Mali-Midgard: hardware counters cleared\n");
+
+ kbase_device_busy = false;
+ }
+
+ return 0;
+
+free_buffer:
+#if MALI_DDK_GATOR_API_VERSION == 1
+ kbase_va_free_symbol(kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+ kbase_va_free_symbol(kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+destroy_context:
+ kbase_destroy_context_symbol(kbcontext);
+#endif
+
+out:
+ clean_symbols();
+ return -1;
+}
+
+static void stop(void)
+{
+ unsigned int cnt;
+#if MALI_DDK_GATOR_API_VERSION == 3
+ struct kbase_gator_hwcnt_handles *temp_hand;
+#else
+ struct kbase_context *temp_kbcontext;
+#endif
+
+ pr_debug("gator: Mali-Midgard: stop\n");
+
+ /* Set all counters as disabled */
+ for (cnt = 0; cnt < number_of_hardware_counters; cnt++)
+ counters[cnt].enabled = 0;
+
+ /* Destroy the context for HW counters */
+#if MALI_DDK_GATOR_API_VERSION == 3
+ if (num_hardware_counters_enabled > 0 && handles != NULL) {
+ /*
+ * Set the global variable to NULL before destroying it, because
+ * other function will check this before using it.
+ */
+ temp_hand = handles;
+ handles = NULL;
+
+ kbase_gator_hwcnt_term_symbol(in_out_info, temp_hand);
+
+ kfree(in_out_info);
+
+#else
+ if (num_hardware_counters_enabled > 0 && kbcontext != NULL) {
+ /*
+ * Set the global variable to NULL before destroying it, because
+ * other function will check this before using it.
+ */
+ temp_kbcontext = kbcontext;
+ kbcontext = NULL;
+
+ kbase_instr_hwcnt_disable_symbol(temp_kbcontext);
+
+#if MALI_DDK_GATOR_API_VERSION == 1
+ kbase_va_free_symbol(temp_kbcontext, kernel_dump_buffer);
+#elif MALI_DDK_GATOR_API_VERSION == 2
+ kbase_va_free_symbol(temp_kbcontext, &kernel_dump_buffer_handle);
+#endif
+
+ kbase_destroy_context_symbol(temp_kbcontext);
+#endif
+
+ pr_debug("gator: Mali-Midgard: hardware counters stopped\n");
+
+ clean_symbols();
+ }
+}
+
+static int read_counter(const int cnt, const int len, const struct mali_counter *counter)
+{
+ const int block = GET_HW_BLOCK(cnt);
+ const int counter_offset = GET_COUNTER_OFFSET(cnt);
+ u32 value = 0;
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+ const char *block_base_address = (char *)in_out_info->kernel_dump_buffer;
+ int i;
+ int shader_core_count = 0;
+
+ for (i = 0; i < in_out_info->nr_hwc_blocks; i++) {
+ if (block == in_out_info->hwc_layout[i]) {
+ value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+ if (block == SHADER_BLOCK)
+ ++shader_core_count;
+ }
+ }
+
+ if (shader_core_count > 1)
+ value /= shader_core_count;
+#else
+ const unsigned int vithar_blocks[] = {
+ 0x700, /* VITHAR_JOB_MANAGER, Block 0 */
+ 0x400, /* VITHAR_TILER, Block 1 */
+ 0x000, /* VITHAR_SHADER_CORE, Block 2 */
+ 0x500 /* VITHAR_MEMORY_SYSTEM, Block 3 */
+ };
+ const char *block_base_address = (char *)kernel_dump_buffer + vithar_blocks[block];
+
+ /* If counter belongs to shader block need to take into account all cores */
+ if (block == SHADER_BLOCK) {
+ int i = 0;
+ int shader_core_count = 0;
+
+ value = 0;
+
+ for (i = 0; i < 4; i++) {
+ if ((shader_present_low >> i) & 1) {
+ value += *((u32 *)(block_base_address + (0x100 * i)) + counter_offset);
+ shader_core_count++;
+ }
+ }
+
+ for (i = 0; i < 4; i++) {
+ if ((shader_present_low >> (i+4)) & 1) {
+ value += *((u32 *)(block_base_address + (0x100 * i) + 0x800) + counter_offset);
+ shader_core_count++;
+ }
+ }
+
+ /* Need to total by number of cores to produce an average */
+ if (shader_core_count != 0)
+ value /= shader_core_count;
+ } else {
+ value = *((u32 *)block_base_address + counter_offset);
+ }
+#endif
+
+ counter_dump[len + 0] = counter->key;
+ counter_dump[len + 1] = value;
+
+ return 2;
+}
+
+static int read(int **buffer, bool sched_switch)
+{
+ int cnt;
+ int len = 0;
+ uint32_t success;
+
+ struct timespec current_time;
+ static u32 prev_time_s;
+ static s32 next_read_time_ns;
+
+ if (!on_primary_core() || sched_switch)
+ return 0;
+
+ getnstimeofday(¤t_time);
+
+ /*
+ * Discard reads unless a respectable time has passed. This
+ * reduces the load on the GPU without sacrificing accuracy on
+ * the Streamline display.
+ */
+ if (!is_read_scheduled(¤t_time, &prev_time_s, &next_read_time_ns))
+ return 0;
+
+ /*
+ * Report the HW counters
+ * Only process hardware counters if at least one of the hardware counters is enabled.
+ */
+ if (num_hardware_counters_enabled > 0) {
+#if MALI_DDK_GATOR_API_VERSION == 3
+ if (!handles)
+ return -1;
+
+ /* Mali symbols can be called safely since a kbcontext is valid */
+ if (kbase_gator_instr_hwcnt_dump_complete_symbol(handles, &success)) {
+#else
+ if (!kbcontext)
+ return -1;
+
+ /* Mali symbols can be called safely since a kbcontext is valid */
+ if (kbase_instr_hwcnt_dump_complete_symbol(kbcontext, &success)) {
+#endif
+ kbase_device_busy = false;
+
+ if (success) {
+ /* Cycle through hardware counters and accumulate totals */
+ for (cnt = 0; cnt < number_of_hardware_counters; cnt++) {
+ const struct mali_counter *counter = &counters[cnt];
+
+ if (counter->enabled)
+ len += read_counter(cnt, len, counter);
+ }
+ }
+ }
+
+ if (!kbase_device_busy) {
+ kbase_device_busy = true;
+#if MALI_DDK_GATOR_API_VERSION == 3
+ kbase_gator_instr_hwcnt_dump_irq_symbol(handles);
+#else
+ kbase_instr_hwcnt_dump_irq_symbol(kbcontext);
+#endif
+ }
+ }
+
+ /* Update the buffer */
+ if (buffer)
+ *buffer = counter_dump;
+
+ return len;
+}
+
+static int create_files(struct super_block *sb, struct dentry *root)
+{
+ unsigned int event;
+ /*
+ * Create the filesystem for all events
+ */
+ for (event = 0; event < ARRAY_SIZE(mali_activity); event++) {
+ if (gator_mali_create_file_system("Midgard", mali_activity_names[event], sb, root, &mali_activity[event], NULL) != 0)
+ return -1;
+ }
+
+ for (event = 0; event < number_of_hardware_counters; event++) {
+ if (gator_mali_create_file_system(mali_name, hardware_counter_names[event], sb, root, &counters[event], NULL) != 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+static void shutdown(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+ void (*kbase_gator_hwcnt_term_names_symbol)(void) = NULL;
+ int error_count = 0;
+#endif
+
+ kfree(counters);
+ kfree(counter_dump);
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+ SYMBOL_GET(kbase_gator_hwcnt_term_names, error_count);
+
+ number_of_hardware_counters = -1;
+ hardware_counter_names = NULL;
+ if (kbase_gator_hwcnt_term_names_symbol != NULL) {
+ kbase_gator_hwcnt_term_names_symbol();
+ pr_err("Released symbols\n");
+ }
+
+ SYMBOL_CLEANUP(kbase_gator_hwcnt_term_names);
+#endif
+}
+
+static struct gator_interface gator_events_mali_midgard_interface = {
+ .shutdown = shutdown,
+ .create_files = create_files,
+ .start = start,
+ .stop = stop,
+ .read = read
+};
+
+int gator_events_mali_midgard_hw_init(void)
+{
+#if MALI_DDK_GATOR_API_VERSION == 3
+ const char *const *(*kbase_gator_hwcnt_init_names_symbol)(uint32_t *) = NULL;
+ int error_count = 0;
+#endif
+
+ pr_debug("gator: Mali-Midgard: sw_counters init\n");
+
+#if GATOR_TEST
+ test_all_is_read_scheduled();
+#endif
+
+#if MALI_DDK_GATOR_API_VERSION == 3
+ SYMBOL_GET(kbase_gator_hwcnt_init_names, error_count);
+ if (error_count > 0) {
+ SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+ return 1;
+ }
+
+ number_of_hardware_counters = -1;
+ hardware_counter_names = kbase_gator_hwcnt_init_names_symbol(&number_of_hardware_counters);
+
+ SYMBOL_CLEANUP(kbase_gator_hwcnt_init_names);
+
+ if ((hardware_counter_names == NULL) || (number_of_hardware_counters <= 0)) {
+ pr_err("gator: Error reading hardware counters names: got %d names\n", number_of_hardware_counters);
+ return -1;
+ }
+#else
+ mali_name = "Midgard";
+#endif
+
+ counters = kmalloc(sizeof(*counters)*number_of_hardware_counters, GFP_KERNEL);
+ counter_dump = kmalloc(sizeof(*counter_dump)*number_of_hardware_counters*2, GFP_KERNEL);
+
+ gator_mali_initialise_counters(mali_activity, ARRAY_SIZE(mali_activity));
+ gator_mali_initialise_counters(counters, number_of_hardware_counters);
+
+ return gator_events_install(&gator_events_mali_midgard_interface);
+}
diff --git a/drivers/gator/gator_events_mali_midgard_hw_test.c b/drivers/gator/gator_events_mali_midgard_hw_test.c
new file mode 100644
index 0000000..87c569c
--- /dev/null
+++ b/drivers/gator/gator_events_mali_midgard_hw_test.c
@@ -0,0 +1,55 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/**
+ * Test functions for mali_t600_hw code.
+ */
+
+static int is_read_scheduled(const struct timespec *current_time, u32 *prev_time_s, s32 *next_read_time_ns);
+
+static int test_is_read_scheduled(u32 s, u32 ns, u32 prev_s, s32 next_ns, int expected_result, s32 expected_next_ns)
+{
+ struct timespec current_time;
+ u32 prev_time_s = prev_s;
+ s32 next_read_time_ns = next_ns;
+
+ current_time.tv_sec = s;
+ current_time.tv_nsec = ns;
+
+ if (is_read_scheduled(¤t_time, &prev_time_s, &next_read_time_ns) != expected_result) {
+ pr_err("Failed do_read(%u, %u, %u, %d): expected %d\n", s, ns, prev_s, next_ns, expected_result);
+ return 0;
+ }
+
+ if (next_read_time_ns != expected_next_ns) {
+ pr_err("Failed: next_read_ns expected=%d, actual=%d\n", expected_next_ns, next_read_time_ns);
+ return 0;
+ }
+
+ return 1;
+}
+
+static void test_all_is_read_scheduled(void)
+{
+ const int HIGHEST_NS = 999999999;
+ int n_tests_passed = 0;
+
+ pr_err("gator: running tests on %s\n", __FILE__);
+
+ n_tests_passed += test_is_read_scheduled(0, 0, 0, 0, 1, READ_INTERVAL_NSEC); /* Null time */
+ n_tests_passed += test_is_read_scheduled(100, 1000, 0, 0, 1, READ_INTERVAL_NSEC + 1000); /* Initial values */
+
+ n_tests_passed += test_is_read_scheduled(100, HIGHEST_NS, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500);
+ n_tests_passed += test_is_read_scheduled(101, 0001, 100, HIGHEST_NS + 500, 0, HIGHEST_NS + 500 - NSEC_PER_SEC);
+ n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500 - NSEC_PER_SEC, 1, 600 + READ_INTERVAL_NSEC);
+
+ n_tests_passed += test_is_read_scheduled(101, 600, 100, HIGHEST_NS + 500, 1, 600 + READ_INTERVAL_NSEC);
+
+ pr_err("gator: %d tests passed\n", n_tests_passed);
+}
diff --git a/drivers/gator/gator_events_meminfo.c b/drivers/gator/gator_events_meminfo.c
new file mode 100644
index 0000000..985b312
--- /dev/null
+++ b/drivers/gator/gator_events_meminfo.c
@@ -0,0 +1,473 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+
+#include <linux/hardirq.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/workqueue.h>
+#include <trace/events/kmem.h>
+
+#define USE_THREAD defined(CONFIG_PREEMPT_RT_FULL)
+
+enum {
+ MEMINFO_MEMFREE,
+ MEMINFO_MEMUSED,
+ MEMINFO_BUFFERRAM,
+ MEMINFO_TOTAL,
+};
+
+enum {
+ PROC_SIZE,
+ PROC_SHARE,
+ PROC_TEXT,
+ PROC_DATA,
+ PROC_COUNT,
+};
+
+static const char * const meminfo_names[] = {
+ "Linux_meminfo_memfree",
+ "Linux_meminfo_memused",
+ "Linux_meminfo_bufferram",
+};
+
+static const char * const proc_names[] = {
+ "Linux_proc_statm_size",
+ "Linux_proc_statm_share",
+ "Linux_proc_statm_text",
+ "Linux_proc_statm_data",
+};
+
+static bool meminfo_global_enabled;
+static ulong meminfo_enabled[MEMINFO_TOTAL];
+static ulong meminfo_keys[MEMINFO_TOTAL];
+static long long meminfo_buffer[2 * (MEMINFO_TOTAL + 2)];
+static int meminfo_length;
+static bool new_data_avail;
+
+static bool proc_global_enabled;
+static ulong proc_enabled[PROC_COUNT];
+static ulong proc_keys[PROC_COUNT];
+static DEFINE_PER_CPU(long long, proc_buffer[2 * (PROC_COUNT + 3)]);
+
+static void do_read(void);
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data);
+static bool gator_meminfo_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_meminfo_sem);
+#else
+static DEFINE_SEMAPHORE(gator_meminfo_sem);
+#endif
+
+static void notify(void)
+{
+ up(&gator_meminfo_sem);
+}
+
+#else
+
+static unsigned int mem_event;
+static void wq_sched_handler(struct work_struct *wsptr);
+DECLARE_WORK(work, wq_sched_handler);
+static struct timer_list meminfo_wake_up_timer;
+static void meminfo_wake_up_handler(unsigned long unused_data);
+
+static void notify(void)
+{
+ mem_event++;
+}
+
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_page_free_direct, TP_PROTO(struct page *page, unsigned int order))
+#else
+GATOR_DEFINE_PROBE(mm_page_free, TP_PROTO(struct page *page, unsigned int order))
+#endif
+{
+ notify();
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+GATOR_DEFINE_PROBE(mm_pagevec_free, TP_PROTO(struct page *page, int cold))
+#else
+GATOR_DEFINE_PROBE(mm_page_free_batched, TP_PROTO(struct page *page, int cold))
+#endif
+{
+ notify();
+}
+
+GATOR_DEFINE_PROBE(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype))
+{
+ notify();
+}
+
+static int gator_events_meminfo_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ int i;
+
+ for (i = 0; i < MEMINFO_TOTAL; i++) {
+ dir = gatorfs_mkdir(sb, root, meminfo_names[i]);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &meminfo_enabled[i]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &meminfo_keys[i]);
+ }
+
+ for (i = 0; i < PROC_COUNT; ++i) {
+ dir = gatorfs_mkdir(sb, root, proc_names[i]);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &proc_enabled[i]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &proc_keys[i]);
+ }
+
+ return 0;
+}
+
+static int gator_events_meminfo_start(void)
+{
+ int i;
+
+ new_data_avail = false;
+ meminfo_global_enabled = 0;
+ for (i = 0; i < MEMINFO_TOTAL; i++) {
+ if (meminfo_enabled[i]) {
+ meminfo_global_enabled = 1;
+ break;
+ }
+ }
+
+ proc_global_enabled = 0;
+ for (i = 0; i < PROC_COUNT; ++i) {
+ if (proc_enabled[i]) {
+ proc_global_enabled = 1;
+ break;
+ }
+ }
+ if (meminfo_enabled[MEMINFO_MEMUSED])
+ proc_global_enabled = 1;
+
+ if (meminfo_global_enabled == 0)
+ return 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+ if (GATOR_REGISTER_TRACE(mm_page_free_direct))
+#else
+ if (GATOR_REGISTER_TRACE(mm_page_free))
+#endif
+ goto mm_page_free_exit;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+ if (GATOR_REGISTER_TRACE(mm_pagevec_free))
+#else
+ if (GATOR_REGISTER_TRACE(mm_page_free_batched))
+#endif
+ goto mm_page_free_batched_exit;
+ if (GATOR_REGISTER_TRACE(mm_page_alloc))
+ goto mm_page_alloc_exit;
+
+ do_read();
+#if USE_THREAD
+ /* Start worker thread */
+ gator_meminfo_run = true;
+ /* Since the mutex starts unlocked, memory values will be initialized */
+ if (IS_ERR(kthread_run(gator_meminfo_func, NULL, "gator_meminfo")))
+ goto kthread_run_exit;
+#else
+ setup_timer(&meminfo_wake_up_timer, meminfo_wake_up_handler, 0);
+#endif
+
+ return 0;
+
+#if USE_THREAD
+kthread_run_exit:
+ GATOR_UNREGISTER_TRACE(mm_page_alloc);
+#endif
+mm_page_alloc_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+ GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+ GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+mm_page_free_batched_exit:
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+ GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+#else
+ GATOR_UNREGISTER_TRACE(mm_page_free);
+#endif
+mm_page_free_exit:
+ return -1;
+}
+
+static void gator_events_meminfo_stop(void)
+{
+ if (meminfo_global_enabled) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 3, 0)
+ GATOR_UNREGISTER_TRACE(mm_page_free_direct);
+ GATOR_UNREGISTER_TRACE(mm_pagevec_free);
+#else
+ GATOR_UNREGISTER_TRACE(mm_page_free);
+ GATOR_UNREGISTER_TRACE(mm_page_free_batched);
+#endif
+ GATOR_UNREGISTER_TRACE(mm_page_alloc);
+
+#if USE_THREAD
+ /* Stop worker thread */
+ gator_meminfo_run = false;
+ up(&gator_meminfo_sem);
+#else
+ del_timer_sync(&meminfo_wake_up_timer);
+#endif
+ }
+}
+
+static void do_read(void)
+{
+ struct sysinfo info;
+ int i, len;
+ unsigned long long value;
+
+ meminfo_length = len = 0;
+
+ si_meminfo(&info);
+ for (i = 0; i < MEMINFO_TOTAL; i++) {
+ if (meminfo_enabled[i]) {
+ switch (i) {
+ case MEMINFO_MEMFREE:
+ value = info.freeram * PAGE_SIZE;
+ break;
+ case MEMINFO_MEMUSED:
+ /* pid -1 means system wide */
+ meminfo_buffer[len++] = 1;
+ meminfo_buffer[len++] = -1;
+ /* Emit value */
+ meminfo_buffer[len++] = meminfo_keys[MEMINFO_MEMUSED];
+ meminfo_buffer[len++] = (info.totalram - info.freeram) * PAGE_SIZE;
+ /* Clear pid */
+ meminfo_buffer[len++] = 1;
+ meminfo_buffer[len++] = 0;
+ continue;
+ case MEMINFO_BUFFERRAM:
+ value = info.bufferram * PAGE_SIZE;
+ break;
+ default:
+ value = 0;
+ break;
+ }
+ meminfo_buffer[len++] = meminfo_keys[i];
+ meminfo_buffer[len++] = value;
+ }
+ }
+
+ meminfo_length = len;
+ new_data_avail = true;
+}
+
+#if USE_THREAD
+
+static int gator_meminfo_func(void *data)
+{
+ for (;;) {
+ if (down_killable(&gator_meminfo_sem))
+ break;
+
+ /* Eat up any pending events */
+ while (!down_trylock(&gator_meminfo_sem))
+ ;
+
+ if (!gator_meminfo_run)
+ break;
+
+ do_read();
+ }
+
+ return 0;
+}
+
+#else
+
+/* Must be run in process context as the kernel function si_meminfo() can sleep */
+static void wq_sched_handler(struct work_struct *wsptr)
+{
+ do_read();
+}
+
+static void meminfo_wake_up_handler(unsigned long unused_data)
+{
+ /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+ schedule_work(&work);
+}
+
+#endif
+
+static int gator_events_meminfo_read(long long **buffer)
+{
+#if !USE_THREAD
+ static unsigned int last_mem_event;
+#endif
+
+ if (!on_primary_core() || !meminfo_global_enabled)
+ return 0;
+
+#if !USE_THREAD
+ if (last_mem_event != mem_event) {
+ last_mem_event = mem_event;
+ mod_timer(&meminfo_wake_up_timer, jiffies + 1);
+ }
+#endif
+
+ if (!new_data_avail)
+ return 0;
+
+ new_data_avail = false;
+
+ if (buffer)
+ *buffer = meminfo_buffer;
+
+ return meminfo_length;
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 34) && LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+
+static inline unsigned long gator_get_mm_counter(struct mm_struct *mm, int member)
+{
+#ifdef SPLIT_RSS_COUNTING
+ long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+ if (val < 0)
+ val = 0;
+ return (unsigned long)val;
+#else
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 0, 0)
+ return mm->rss_stat.count[member];
+#else
+ return atomic_long_read(&mm->rss_stat.count[member]);
+#endif
+#endif
+}
+
+#define get_mm_counter(mm, member) gator_get_mm_counter(mm, member)
+
+#endif
+
+static int gator_events_meminfo_read_proc(long long **buffer, struct task_struct *task)
+{
+ struct mm_struct *mm;
+ u64 share = 0;
+ int i;
+ long long value;
+ int len = 0;
+ int cpu = get_physical_cpu();
+ long long *buf = per_cpu(proc_buffer, cpu);
+
+ if (!proc_global_enabled)
+ return 0;
+
+ /* Collect the memory stats of the process instead of the thread */
+ if (task->group_leader != NULL)
+ task = task->group_leader;
+
+ /* get_task_mm/mmput is not needed in this context because the task and it's mm are required as part of the sched_switch */
+ mm = task->mm;
+ if (mm == NULL)
+ return 0;
+
+ /* Derived from task_statm in fs/proc/task_mmu.c */
+ if (meminfo_enabled[MEMINFO_MEMUSED] || proc_enabled[PROC_SHARE]) {
+ share = get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+ file_rss
+#else
+ MM_FILEPAGES
+#endif
+ );
+ }
+
+ /* key of 1 indicates a pid */
+ buf[len++] = 1;
+ buf[len++] = task->pid;
+
+ for (i = 0; i < PROC_COUNT; ++i) {
+ if (proc_enabled[i]) {
+ switch (i) {
+ case PROC_SIZE:
+ value = mm->total_vm;
+ break;
+ case PROC_SHARE:
+ value = share;
+ break;
+ case PROC_TEXT:
+ value = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT;
+ break;
+ case PROC_DATA:
+ value = mm->total_vm - mm->shared_vm;
+ break;
+ }
+
+ buf[len++] = proc_keys[i];
+ buf[len++] = value * PAGE_SIZE;
+ }
+ }
+
+ if (meminfo_enabled[MEMINFO_MEMUSED]) {
+ value = share + get_mm_counter(mm,
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 32) && LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 34)
+ anon_rss
+#else
+ MM_ANONPAGES
+#endif
+ );
+ /* Send resident for this pid */
+ buf[len++] = meminfo_keys[MEMINFO_MEMUSED];
+ buf[len++] = value * PAGE_SIZE;
+ }
+
+ /* Clear pid */
+ buf[len++] = 1;
+ buf[len++] = 0;
+
+ if (buffer)
+ *buffer = buf;
+
+ return len;
+}
+
+static struct gator_interface gator_events_meminfo_interface = {
+ .create_files = gator_events_meminfo_create_files,
+ .start = gator_events_meminfo_start,
+ .stop = gator_events_meminfo_stop,
+ .read64 = gator_events_meminfo_read,
+ .read_proc = gator_events_meminfo_read_proc,
+};
+
+int gator_events_meminfo_init(void)
+{
+ int i;
+
+ meminfo_global_enabled = 0;
+ for (i = 0; i < MEMINFO_TOTAL; i++) {
+ meminfo_enabled[i] = 0;
+ meminfo_keys[i] = gator_events_get_key();
+ }
+
+ proc_global_enabled = 0;
+ for (i = 0; i < PROC_COUNT; ++i) {
+ proc_enabled[i] = 0;
+ proc_keys[i] = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_meminfo_interface);
+}
diff --git a/drivers/gator/gator_events_mmapped.c b/drivers/gator/gator_events_mmapped.c
new file mode 100644
index 0000000..7b51761
--- /dev/null
+++ b/drivers/gator/gator_events_mmapped.c
@@ -0,0 +1,209 @@
+/*
+ * Example events provider
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Similar entries to those below must be present in the events.xml file.
+ * To add them to the events.xml, create an events-mmap.xml with the
+ * following contents and rebuild gatord:
+ *
+ * <category name="mmapped">
+ * <event counter="mmapped_cnt0" title="Simulated1" name="Sine" display="maximum" class="absolute" description="Sort-of-sine"/>
+ * <event counter="mmapped_cnt1" title="Simulated2" name="Triangle" display="maximum" class="absolute" description="Triangular wave"/>
+ * <event counter="mmapped_cnt2" title="Simulated3" name="PWM" display="maximum" class="absolute" description="PWM Signal"/>
+ * </category>
+ *
+ * When adding custom events, be sure to do the following:
+ * - add any needed .c files to the gator driver Makefile
+ * - call gator_events_install in the events init function
+ * - add the init function to GATOR_EVENTS_LIST in gator_main.c
+ * - add a new events-*.xml file to the gator daemon and rebuild
+ *
+ * Troubleshooting:
+ * - verify the new events are part of events.xml, which is created when building the daemon
+ * - verify the new events exist at /dev/gator/events/ once gatord is launched
+ * - verify the counter name in the XML matches the name at /dev/gator/events
+ */
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ratelimit.h>
+
+#include "gator.h"
+
+#define MMAPPED_COUNTERS_NUM 3
+
+static int mmapped_global_enabled;
+
+static struct {
+ unsigned long enabled;
+ unsigned long key;
+} mmapped_counters[MMAPPED_COUNTERS_NUM];
+
+static int mmapped_buffer[MMAPPED_COUNTERS_NUM * 2];
+
+static s64 prev_time;
+
+/* Adds mmapped_cntX directories and enabled, event, and key files to /dev/gator/events */
+static int gator_events_mmapped_create_files(struct super_block *sb,
+ struct dentry *root)
+{
+ int i;
+
+ for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+ char buf[16];
+ struct dentry *dir;
+
+ snprintf(buf, sizeof(buf), "mmapped_cnt%d", i);
+ dir = gatorfs_mkdir(sb, root, buf);
+ if (WARN_ON(!dir))
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled",
+ &mmapped_counters[i].enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key",
+ &mmapped_counters[i].key);
+ }
+
+ return 0;
+}
+
+static int gator_events_mmapped_start(void)
+{
+ int i;
+ struct timespec ts;
+
+ getnstimeofday(&ts);
+ prev_time = timespec_to_ns(&ts);
+
+ mmapped_global_enabled = 0;
+ for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+ if (mmapped_counters[i].enabled) {
+ mmapped_global_enabled = 1;
+ break;
+ }
+ }
+
+ return 0;
+}
+
+static void gator_events_mmapped_stop(void)
+{
+}
+
+/* This function "simulates" counters, generating values of fancy
+ * functions like sine or triangle... */
+static int mmapped_simulate(int counter, int delta_in_us)
+{
+ int result = 0;
+
+ switch (counter) {
+ case 0: /* sort-of-sine */
+ {
+ static int t;
+ int x;
+
+ t += delta_in_us;
+ if (t > 2048000)
+ t = 0;
+
+ if (t % 1024000 < 512000)
+ x = 512000 - (t % 512000);
+ else
+ x = t % 512000;
+
+ result = 32 * x / 512000;
+ result = result * result;
+
+ if (t < 1024000)
+ result = 1922 - result;
+ }
+ break;
+ case 1: /* triangle */
+ {
+ static int v, d = 1;
+
+ v = v + d * delta_in_us;
+ if (v < 0) {
+ v = 0;
+ d = 1;
+ } else if (v > 1000000) {
+ v = 1000000;
+ d = -1;
+ }
+
+ result = v;
+ }
+ break;
+ case 2: /* PWM signal */
+ {
+ static int dc, x, t;
+
+ t += delta_in_us;
+ if (t > 1000000)
+ t = 0;
+ if (x / 1000000 != (x + delta_in_us) / 1000000)
+ dc = (dc + 100000) % 1000000;
+ x += delta_in_us;
+
+ result = t < dc ? 0 : 10;
+ }
+ break;
+ }
+
+ return result;
+}
+
+static int gator_events_mmapped_read(int **buffer, bool sched_switch)
+{
+ int i;
+ int len = 0;
+ int delta_in_us;
+ struct timespec ts;
+ s64 time;
+
+ /* System wide counters - read from one core only */
+ if (!on_primary_core() || !mmapped_global_enabled)
+ return 0;
+
+ getnstimeofday(&ts);
+ time = timespec_to_ns(&ts);
+ delta_in_us = (int)(time - prev_time) / 1000;
+ prev_time = time;
+
+ for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+ if (mmapped_counters[i].enabled) {
+ mmapped_buffer[len++] = mmapped_counters[i].key;
+ mmapped_buffer[len++] =
+ mmapped_simulate(i, delta_in_us);
+ }
+ }
+
+ if (buffer)
+ *buffer = mmapped_buffer;
+
+ return len;
+}
+
+static struct gator_interface gator_events_mmapped_interface = {
+ .create_files = gator_events_mmapped_create_files,
+ .start = gator_events_mmapped_start,
+ .stop = gator_events_mmapped_stop,
+ .read = gator_events_mmapped_read,
+};
+
+/* Must not be static! */
+int __init gator_events_mmapped_init(void)
+{
+ int i;
+
+ for (i = 0; i < MMAPPED_COUNTERS_NUM; i++) {
+ mmapped_counters[i].enabled = 0;
+ mmapped_counters[i].key = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_mmapped_interface);
+}
diff --git a/drivers/gator/gator_events_net.c b/drivers/gator/gator_events_net.c
new file mode 100644
index 0000000..1e36731
--- /dev/null
+++ b/drivers/gator/gator_events_net.c
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <linux/netdevice.h>
+#include <linux/hardirq.h>
+
+#define NETRX 0
+#define NETTX 1
+#define TOTALNET 2
+
+static ulong netrx_enabled;
+static ulong nettx_enabled;
+static ulong netrx_key;
+static ulong nettx_key;
+static int rx_total, tx_total;
+static ulong netPrev[TOTALNET];
+static int netGet[TOTALNET * 4];
+
+static struct timer_list net_wake_up_timer;
+
+/* Must be run in process context as the kernel function dev_get_stats() can sleep */
+static void get_network_stats(struct work_struct *wsptr)
+{
+ int rx = 0, tx = 0;
+ struct net_device *dev;
+
+ for_each_netdev(&init_net, dev) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+ const struct net_device_stats *stats = dev_get_stats(dev);
+#else
+ struct rtnl_link_stats64 temp;
+ const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+#endif
+ rx += stats->rx_bytes;
+ tx += stats->tx_bytes;
+ }
+ rx_total = rx;
+ tx_total = tx;
+}
+
+DECLARE_WORK(wq_get_stats, get_network_stats);
+
+static void net_wake_up_handler(unsigned long unused_data)
+{
+ /* had to delay scheduling work as attempting to schedule work during the context switch is illegal in kernel versions 3.5 and greater */
+ schedule_work(&wq_get_stats);
+}
+
+static void calculate_delta(int *rx, int *tx)
+{
+ int rx_calc, tx_calc;
+
+ rx_calc = (int)(rx_total - netPrev[NETRX]);
+ if (rx_calc < 0)
+ rx_calc = 0;
+ netPrev[NETRX] += rx_calc;
+
+ tx_calc = (int)(tx_total - netPrev[NETTX]);
+ if (tx_calc < 0)
+ tx_calc = 0;
+ netPrev[NETTX] += tx_calc;
+
+ *rx = rx_calc;
+ *tx = tx_calc;
+}
+
+static int gator_events_net_create_files(struct super_block *sb, struct dentry *root)
+{
+ /* Network counters are not currently supported in RT-Preempt full because mod_timer is used */
+#ifndef CONFIG_PREEMPT_RT_FULL
+ struct dentry *dir;
+
+ dir = gatorfs_mkdir(sb, root, "Linux_net_rx");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &netrx_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &netrx_key);
+
+ dir = gatorfs_mkdir(sb, root, "Linux_net_tx");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &nettx_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &nettx_key);
+#endif
+
+ return 0;
+}
+
+static int gator_events_net_start(void)
+{
+ get_network_stats(0);
+ netPrev[NETRX] = rx_total;
+ netPrev[NETTX] = tx_total;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+ setup_timer(&net_wake_up_timer, net_wake_up_handler, 0);
+#else
+ setup_deferrable_timer_on_stack(&net_wake_up_timer, net_wake_up_handler, 0);
+#endif
+ return 0;
+}
+
+static void gator_events_net_stop(void)
+{
+ del_timer_sync(&net_wake_up_timer);
+ netrx_enabled = 0;
+ nettx_enabled = 0;
+}
+
+static int gator_events_net_read(int **buffer, bool sched_switch)
+{
+ int len, rx_delta, tx_delta;
+ static int last_rx_delta, last_tx_delta;
+
+ if (!on_primary_core())
+ return 0;
+
+ if (!netrx_enabled && !nettx_enabled)
+ return 0;
+
+ mod_timer(&net_wake_up_timer, jiffies + 1);
+
+ calculate_delta(&rx_delta, &tx_delta);
+
+ len = 0;
+ if (netrx_enabled && last_rx_delta != rx_delta) {
+ last_rx_delta = rx_delta;
+ netGet[len++] = netrx_key;
+ /* indicates to Streamline that rx_delta bytes were transmitted now, not since the last message */
+ netGet[len++] = 0;
+ netGet[len++] = netrx_key;
+ netGet[len++] = rx_delta;
+ }
+
+ if (nettx_enabled && last_tx_delta != tx_delta) {
+ last_tx_delta = tx_delta;
+ netGet[len++] = nettx_key;
+ /* indicates to Streamline that tx_delta bytes were transmitted now, not since the last message */
+ netGet[len++] = 0;
+ netGet[len++] = nettx_key;
+ netGet[len++] = tx_delta;
+ }
+
+ if (buffer)
+ *buffer = netGet;
+
+ return len;
+}
+
+static struct gator_interface gator_events_net_interface = {
+ .create_files = gator_events_net_create_files,
+ .start = gator_events_net_start,
+ .stop = gator_events_net_stop,
+ .read = gator_events_net_read,
+};
+
+int gator_events_net_init(void)
+{
+ netrx_key = gator_events_get_key();
+ nettx_key = gator_events_get_key();
+
+ netrx_enabled = 0;
+ nettx_enabled = 0;
+
+ return gator_events_install(&gator_events_net_interface);
+}
diff --git a/drivers/gator/gator_events_perf_pmu.c b/drivers/gator/gator_events_perf_pmu.c
new file mode 100644
index 0000000..f6b4f18
--- /dev/null
+++ b/drivers/gator/gator_events_perf_pmu.c
@@ -0,0 +1,583 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_armvX.c is used for Linux 2.6.x */
+#if GATOR_PERF_PMU_SUPPORT
+
+#include <linux/io.h>
+#ifdef CONFIG_OF
+#include <linux/of_address.h>
+#endif
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+
+extern bool event_based_sampling;
+
+/* Maximum number of per-core counters - currently reserves enough space for two full hardware PMUs for big.LITTLE */
+#define CNTMAX 16
+#define CCI_400 4
+#define CCI_500 8
+#define CCN_5XX 8
+/* Maximum number of uncore counters */
+/* + 1 for the cci-400 cycles counter */
+/* cci-500 has no cycles counter */
+/* + 1 for the CCN-5xx cycles counter */
+#define UCCNT (CCI_400 + 1 + CCI_500 + CCN_5XX + 1)
+
+/* Default to 0 if unable to probe the revision which was the previous behavior */
+#define DEFAULT_CCI_REVISION 0
+
+/* A gator_attr is needed for every counter */
+struct gator_attr {
+ /* Set once in gator_events_perf_pmu_*_init - the name of the event in the gatorfs */
+ char name[40];
+ /* Exposed in gatorfs - set by gatord to enable this counter */
+ unsigned long enabled;
+ /* Set once in gator_events_perf_pmu_*_init - the perf type to use, see perf_type_id in the perf_event.h header file. */
+ unsigned long type;
+ /* Exposed in gatorfs - set by gatord to select the event to collect */
+ unsigned long event;
+ /* Exposed in gatorfs - set by gatord with the sample period to use and enable EBS for this counter */
+ unsigned long count;
+ /* Exposed as read only in gatorfs - set once in __attr_init as the key to use in the APC data */
+ unsigned long key;
+};
+
+/* Per-core counter attributes */
+static struct gator_attr attrs[CNTMAX];
+/* Number of initialized per-core counters */
+static int attr_count;
+/* Uncore counter attributes */
+static struct gator_attr uc_attrs[UCCNT];
+/* Number of initialized uncore counters */
+static int uc_attr_count;
+
+struct gator_event {
+ uint32_t curr;
+ uint32_t prev;
+ uint32_t prev_delta;
+ bool zero;
+ struct perf_event *pevent;
+ struct perf_event_attr *pevent_attr;
+};
+
+static DEFINE_PER_CPU(struct gator_event[CNTMAX], events);
+static struct gator_event uc_events[UCCNT];
+static DEFINE_PER_CPU(int[(CNTMAX + UCCNT)*2], perf_cnt);
+
+static void gator_events_perf_pmu_stop(void);
+
+static int __create_files(struct super_block *sb, struct dentry *root, struct gator_attr *const attr)
+{
+ struct dentry *dir;
+
+ if (attr->name[0] == '\0')
+ return 0;
+ dir = gatorfs_mkdir(sb, root, attr->name);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &attr->enabled);
+ gatorfs_create_ulong(sb, dir, "count", &attr->count);
+ gatorfs_create_ro_ulong(sb, dir, "key", &attr->key);
+ gatorfs_create_ulong(sb, dir, "event", &attr->event);
+
+ return 0;
+}
+
+static int gator_events_perf_pmu_create_files(struct super_block *sb, struct dentry *root)
+{
+ int cnt;
+
+ for (cnt = 0; cnt < attr_count; cnt++) {
+ if (__create_files(sb, root, &attrs[cnt]) != 0)
+ return -1;
+ }
+
+ for (cnt = 0; cnt < uc_attr_count; cnt++) {
+ if (__create_files(sb, root, &uc_attrs[cnt]) != 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void ebs_overflow_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void ebs_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+ gator_backtrace_handler(regs);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+static void dummy_handler(struct perf_event *event, int unused, struct perf_sample_data *data, struct pt_regs *regs)
+#else
+static void dummy_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs)
+#endif
+{
+ /* Required as perf_event_create_kernel_counter() requires an overflow handler, even though all we do is poll */
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch);
+
+static int gator_events_perf_pmu_online(int **buffer, bool migrate)
+{
+ return gator_events_perf_pmu_read(buffer, false);
+}
+
+static void __online_dispatch(int cpu, bool migrate, struct gator_attr *const attr, struct gator_event *const event)
+{
+ perf_overflow_handler_t handler;
+
+ event->zero = true;
+
+ if (event->pevent != NULL || event->pevent_attr == 0 || migrate)
+ return;
+
+ if (attr->count > 0)
+ handler = ebs_overflow_handler;
+ else
+ handler = dummy_handler;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+ event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler);
+#else
+ event->pevent = perf_event_create_kernel_counter(event->pevent_attr, cpu, 0, handler, 0);
+#endif
+ if (IS_ERR(event->pevent)) {
+ pr_debug("gator: unable to online a counter on cpu %d\n", cpu);
+ event->pevent = NULL;
+ return;
+ }
+
+ if (event->pevent->state != PERF_EVENT_STATE_ACTIVE) {
+ pr_debug("gator: inactive counter on cpu %d\n", cpu);
+ perf_event_release_kernel(event->pevent);
+ event->pevent = NULL;
+ return;
+ }
+}
+
+static void gator_events_perf_pmu_online_dispatch(int cpu, bool migrate)
+{
+ int cnt;
+
+ cpu = pcpu_to_lcpu(cpu);
+
+ for (cnt = 0; cnt < attr_count; cnt++)
+ __online_dispatch(cpu, migrate, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+ if (cpu == 0) {
+ for (cnt = 0; cnt < uc_attr_count; cnt++)
+ __online_dispatch(cpu, migrate, &uc_attrs[cnt], &uc_events[cnt]);
+ }
+}
+
+static void __offline_dispatch(int cpu, struct gator_event *const event)
+{
+ struct perf_event *pe = NULL;
+
+ if (event->pevent) {
+ pe = event->pevent;
+ event->pevent = NULL;
+ }
+
+ if (pe)
+ perf_event_release_kernel(pe);
+}
+
+static void gator_events_perf_pmu_offline_dispatch(int cpu, bool migrate)
+{
+ int cnt;
+
+ if (migrate)
+ return;
+ cpu = pcpu_to_lcpu(cpu);
+
+ for (cnt = 0; cnt < attr_count; cnt++)
+ __offline_dispatch(cpu, &per_cpu(events, cpu)[cnt]);
+
+ if (cpu == 0) {
+ for (cnt = 0; cnt < uc_attr_count; cnt++)
+ __offline_dispatch(cpu, &uc_events[cnt]);
+ }
+}
+
+static int __check_ebs(struct gator_attr *const attr)
+{
+ if (attr->count > 0) {
+ if (!event_based_sampling) {
+ event_based_sampling = true;
+ } else {
+ pr_warning("gator: Only one ebs counter is allowed\n");
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int __start(struct gator_attr *const attr, struct gator_event *const event)
+{
+ u32 size = sizeof(struct perf_event_attr);
+
+ event->pevent = NULL;
+ /* Skip disabled counters */
+ if (!attr->enabled)
+ return 0;
+
+ event->prev = 0;
+ event->curr = 0;
+ event->prev_delta = 0;
+ event->pevent_attr = kmalloc(size, GFP_KERNEL);
+ if (!event->pevent_attr) {
+ gator_events_perf_pmu_stop();
+ return -1;
+ }
+
+ memset(event->pevent_attr, 0, size);
+ event->pevent_attr->type = attr->type;
+ event->pevent_attr->size = size;
+ event->pevent_attr->config = attr->event;
+ event->pevent_attr->sample_period = attr->count;
+ event->pevent_attr->pinned = 1;
+
+ return 0;
+}
+
+static int gator_events_perf_pmu_start(void)
+{
+ int cnt, cpu;
+
+ event_based_sampling = false;
+ for (cnt = 0; cnt < attr_count; cnt++) {
+ if (__check_ebs(&attrs[cnt]) != 0)
+ return -1;
+ }
+
+ for (cnt = 0; cnt < uc_attr_count; cnt++) {
+ if (__check_ebs(&uc_attrs[cnt]) != 0)
+ return -1;
+ }
+
+ for_each_present_cpu(cpu) {
+ for (cnt = 0; cnt < attr_count; cnt++) {
+ if (__start(&attrs[cnt], &per_cpu(events, cpu)[cnt]) != 0)
+ return -1;
+ }
+ }
+
+ for (cnt = 0; cnt < uc_attr_count; cnt++) {
+ if (__start(&uc_attrs[cnt], &uc_events[cnt]) != 0)
+ return -1;
+ }
+
+ return 0;
+}
+
+static void __event_stop(struct gator_event *const event)
+{
+ kfree(event->pevent_attr);
+ event->pevent_attr = NULL;
+}
+
+static void __attr_stop(struct gator_attr *const attr)
+{
+ attr->enabled = 0;
+ attr->event = 0;
+ attr->count = 0;
+}
+
+static void gator_events_perf_pmu_stop(void)
+{
+ unsigned int cnt, cpu;
+
+ for_each_present_cpu(cpu) {
+ for (cnt = 0; cnt < attr_count; cnt++)
+ __event_stop(&per_cpu(events, cpu)[cnt]);
+ }
+
+ for (cnt = 0; cnt < uc_attr_count; cnt++)
+ __event_stop(&uc_events[cnt]);
+
+ for (cnt = 0; cnt < attr_count; cnt++)
+ __attr_stop(&attrs[cnt]);
+
+ for (cnt = 0; cnt < uc_attr_count; cnt++)
+ __attr_stop(&uc_attrs[cnt]);
+}
+
+static void __read(int *const len, int cpu, struct gator_attr *const attr, struct gator_event *const event)
+{
+ uint32_t delta;
+ struct perf_event *const ev = event->pevent;
+
+ if (ev != NULL && ev->state == PERF_EVENT_STATE_ACTIVE) {
+ /* After creating the perf counter in __online_dispatch, there
+ * is a race condition between gator_events_perf_pmu_online and
+ * gator_events_perf_pmu_read. So have
+ * gator_events_perf_pmu_online call gator_events_perf_pmu_read
+ * and in __read check to see if it's the first call after
+ * __online_dispatch and if so, run the online code.
+ */
+ if (event->zero) {
+ ev->pmu->read(ev);
+ event->prev = event->curr = local64_read(&ev->count);
+ event->prev_delta = 0;
+ per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+ per_cpu(perf_cnt, cpu)[(*len)++] = 0;
+ event->zero = false;
+ } else {
+ ev->pmu->read(ev);
+ event->curr = local64_read(&ev->count);
+ delta = event->curr - event->prev;
+ if (delta != 0 || delta != event->prev_delta) {
+ event->prev_delta = delta;
+ event->prev = event->curr;
+ per_cpu(perf_cnt, cpu)[(*len)++] = attr->key;
+ per_cpu(perf_cnt, cpu)[(*len)++] = delta;
+ }
+ }
+ }
+}
+
+static int gator_events_perf_pmu_read(int **buffer, bool sched_switch)
+{
+ int cnt, len = 0;
+ const int cpu = get_logical_cpu();
+
+ for (cnt = 0; cnt < attr_count; cnt++)
+ __read(&len, cpu, &attrs[cnt], &per_cpu(events, cpu)[cnt]);
+
+ if (cpu == 0) {
+ for (cnt = 0; cnt < uc_attr_count; cnt++)
+ __read(&len, cpu, &uc_attrs[cnt], &uc_events[cnt]);
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perf_cnt, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_perf_pmu_interface = {
+ .create_files = gator_events_perf_pmu_create_files,
+ .start = gator_events_perf_pmu_start,
+ .stop = gator_events_perf_pmu_stop,
+ .online = gator_events_perf_pmu_online,
+ .online_dispatch = gator_events_perf_pmu_online_dispatch,
+ .offline_dispatch = gator_events_perf_pmu_offline_dispatch,
+ .read = gator_events_perf_pmu_read,
+};
+
+static void __attr_init(struct gator_attr *const attr)
+{
+ attr->name[0] = '\0';
+ attr->enabled = 0;
+ attr->type = 0;
+ attr->event = 0;
+ attr->count = 0;
+ attr->key = gator_events_get_key();
+}
+
+#ifdef CONFIG_OF
+
+static const struct of_device_id arm_cci_matches[] = {
+ {.compatible = "arm,cci-400" },
+ {},
+};
+
+static int probe_cci_revision(void)
+{
+ struct device_node *np;
+ struct resource res;
+ void __iomem *cci_ctrl_base;
+ int rev;
+ int ret = DEFAULT_CCI_REVISION;
+
+ np = of_find_matching_node(NULL, arm_cci_matches);
+ if (!np)
+ return ret;
+
+ if (of_address_to_resource(np, 0, &res))
+ goto node_put;
+
+ cci_ctrl_base = ioremap(res.start, resource_size(&res));
+
+ rev = (readl_relaxed(cci_ctrl_base + 0xfe8) >> 4) & 0xf;
+
+ if (rev <= 4)
+ ret = 0;
+ else if (rev <= 6)
+ ret = 1;
+
+ iounmap(cci_ctrl_base);
+
+ node_put:
+ of_node_put(np);
+
+ return ret;
+}
+
+#else
+
+static int probe_cci_revision(void)
+{
+ return DEFAULT_CCI_REVISION;
+}
+
+#endif
+
+static void gator_events_perf_pmu_uncore_init(const char *const name, const int type, const int count, const bool has_cycles_counter)
+{
+ int cnt;
+
+ if (has_cycles_counter) {
+ snprintf(uc_attrs[uc_attr_count].name, sizeof(uc_attrs[uc_attr_count].name), "%s_ccnt", name);
+ uc_attrs[uc_attr_count].type = type;
+ ++uc_attr_count;
+ }
+
+ for (cnt = 0; cnt < count; ++cnt, ++uc_attr_count) {
+ struct gator_attr *const attr = &uc_attrs[uc_attr_count];
+
+ snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", name, cnt);
+ attr->type = type;
+ }
+}
+
+static void gator_events_perf_pmu_cci_400_init(const int type)
+{
+ const char *cci_name;
+
+ switch (probe_cci_revision()) {
+ case 0:
+ cci_name = "CCI_400";
+ break;
+ case 1:
+ cci_name = "CCI_400-r1";
+ break;
+ default:
+ pr_debug("gator: unrecognized cci-400 revision\n");
+ return;
+ }
+
+ gator_events_perf_pmu_uncore_init(cci_name, type, CCI_400, true);
+}
+
+static void gator_events_perf_pmu_cpu_init(const struct gator_cpu *const gator_cpu, const int type)
+{
+ int cnt;
+
+ snprintf(attrs[attr_count].name, sizeof(attrs[attr_count].name), "%s_ccnt", gator_cpu->pmnc_name);
+ attrs[attr_count].type = type;
+ ++attr_count;
+
+ for (cnt = 0; cnt < gator_cpu->pmnc_counters; ++cnt, ++attr_count) {
+ struct gator_attr *const attr = &attrs[attr_count];
+
+ snprintf(attr->name, sizeof(attr->name), "%s_cnt%d", gator_cpu->pmnc_name, cnt);
+ attr->type = type;
+ }
+}
+
+int gator_events_perf_pmu_init(void)
+{
+ struct perf_event_attr pea;
+ struct perf_event *pe;
+ const struct gator_cpu *gator_cpu;
+ int type;
+ int cpu;
+ int cnt;
+ bool found_cpu = false;
+
+ for (cnt = 0; cnt < CNTMAX; cnt++)
+ __attr_init(&attrs[cnt]);
+ for (cnt = 0; cnt < UCCNT; cnt++)
+ __attr_init(&uc_attrs[cnt]);
+
+ memset(&pea, 0, sizeof(pea));
+ pea.size = sizeof(pea);
+ pea.config = 0xFF;
+ attr_count = 0;
+ uc_attr_count = 0;
+ for (type = PERF_TYPE_MAX; type < 0x20; ++type) {
+ pea.type = type;
+
+ /* A particular PMU may work on some but not all cores, so try on each core */
+ pe = NULL;
+ for_each_present_cpu(cpu) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+ pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler);
+#else
+ pe = perf_event_create_kernel_counter(&pea, cpu, 0, dummy_handler, 0);
+#endif
+ if (!IS_ERR(pe))
+ break;
+ }
+ /* Assume that valid PMUs are contiguous */
+ if (IS_ERR(pe)) {
+ pea.config = 0xff00;
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 1, 0)
+ pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler);
+#else
+ pe = perf_event_create_kernel_counter(&pea, 0, 0, dummy_handler, 0);
+#endif
+ if (IS_ERR(pe))
+ break;
+ }
+
+ if (pe->pmu != NULL && type == pe->pmu->type) {
+ if (strcmp("CCI", pe->pmu->name) == 0 || strcmp("CCI_400", pe->pmu->name) == 0 || strcmp("CCI_400-r1", pe->pmu->name) == 0) {
+ gator_events_perf_pmu_cci_400_init(type);
+ } else if (strcmp("CCI_500", pe->pmu->name) == 0) {
+ gator_events_perf_pmu_uncore_init("CCI_500", type, CCI_500, false);
+ } else if (strcmp("ccn", pe->pmu->name) == 0) {
+ gator_events_perf_pmu_uncore_init("ARM_CCN_5XX", type, CCN_5XX, true);
+ } else if ((gator_cpu = gator_find_cpu_by_pmu_name(pe->pmu->name)) != NULL) {
+ found_cpu = true;
+ gator_events_perf_pmu_cpu_init(gator_cpu, type);
+ }
+ /* Initialize gator_attrs for dynamic PMUs here */
+ }
+
+ perf_event_release_kernel(pe);
+ }
+
+ if (!found_cpu) {
+ const struct gator_cpu *gator_cpu = gator_find_cpu_by_cpuid(gator_cpuid());
+
+ if (gator_cpu == NULL) {
+ gator_cpu = gator_find_cpu_by_cpuid(OTHER);
+ if (gator_cpu == NULL) {
+ pr_err("gator: Didn't find cpu\n");
+ return -1;
+ }
+ }
+ gator_events_perf_pmu_cpu_init(gator_cpu, PERF_TYPE_RAW);
+ }
+
+ /* Initialize gator_attrs for non-dynamic PMUs here */
+
+ if (attr_count > CNTMAX) {
+ pr_err("gator: Too many perf counters\n");
+ return -1;
+ }
+
+ if (uc_attr_count > UCCNT) {
+ pr_err("gator: Too many perf uncore counters\n");
+ return -1;
+ }
+
+ return gator_events_install(&gator_events_perf_pmu_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_events_sched.c b/drivers/gator/gator_events_sched.c
new file mode 100644
index 0000000..463d834
--- /dev/null
+++ b/drivers/gator/gator_events_sched.c
@@ -0,0 +1,113 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include "gator.h"
+#include <trace/events/sched.h>
+
+#define SCHED_SWITCH 0
+#define SCHED_TOTAL (SCHED_SWITCH+1)
+
+static ulong sched_switch_enabled;
+static ulong sched_switch_key;
+static DEFINE_PER_CPU(int[SCHED_TOTAL], schedCnt);
+static DEFINE_PER_CPU(int[SCHED_TOTAL * 2], schedGet);
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+ unsigned long flags;
+
+ /* disable interrupts to synchronize with gator_events_sched_read()
+ * spinlocks not needed since percpu buffers are used
+ */
+ local_irq_save(flags);
+ per_cpu(schedCnt, get_physical_cpu())[SCHED_SWITCH]++;
+ local_irq_restore(flags);
+}
+
+static int gator_events_sched_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+
+ /* switch */
+ dir = gatorfs_mkdir(sb, root, "Linux_sched_switch");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &sched_switch_enabled);
+ gatorfs_create_ro_ulong(sb, dir, "key", &sched_switch_key);
+
+ return 0;
+}
+
+static int gator_events_sched_start(void)
+{
+ /* register tracepoints */
+ if (sched_switch_enabled)
+ if (GATOR_REGISTER_TRACE(sched_switch))
+ goto sched_switch_exit;
+ pr_debug("gator: registered scheduler event tracepoints\n");
+
+ return 0;
+
+ /* unregister tracepoints on error */
+sched_switch_exit:
+ pr_err("gator: scheduler event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+ return -1;
+}
+
+static void gator_events_sched_stop(void)
+{
+ if (sched_switch_enabled)
+ GATOR_UNREGISTER_TRACE(sched_switch);
+ pr_debug("gator: unregistered scheduler event tracepoints\n");
+
+ sched_switch_enabled = 0;
+}
+
+static int gator_events_sched_read(int **buffer, bool sched_switch)
+{
+ unsigned long flags;
+ int len, value;
+ int cpu = get_physical_cpu();
+
+ len = 0;
+ if (sched_switch_enabled) {
+ local_irq_save(flags);
+ value = per_cpu(schedCnt, cpu)[SCHED_SWITCH];
+ per_cpu(schedCnt, cpu)[SCHED_SWITCH] = 0;
+ local_irq_restore(flags);
+ per_cpu(schedGet, cpu)[len++] = sched_switch_key;
+ per_cpu(schedGet, cpu)[len++] = value;
+ }
+
+ if (buffer)
+ *buffer = per_cpu(schedGet, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_sched_interface = {
+ .create_files = gator_events_sched_create_files,
+ .start = gator_events_sched_start,
+ .stop = gator_events_sched_stop,
+ .read = gator_events_sched_read,
+};
+
+int gator_events_sched_init(void)
+{
+ sched_switch_enabled = 0;
+
+ sched_switch_key = gator_events_get_key();
+
+ return gator_events_install(&gator_events_sched_interface);
+}
diff --git a/drivers/gator/gator_events_scorpion.c b/drivers/gator/gator_events_scorpion.c
new file mode 100644
index 0000000..b51dcd3
--- /dev/null
+++ b/drivers/gator/gator_events_scorpion.c
@@ -0,0 +1,674 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+/* gator_events_perf_pmu.c is used if perf is supported */
+#if GATOR_NO_PERF_SUPPORT
+
+static const char *pmnc_name;
+static int pmnc_counters;
+
+/* Per-CPU PMNC: config reg */
+#define PMNC_E (1 << 0) /* Enable all counters */
+#define PMNC_P (1 << 1) /* Reset all counters */
+#define PMNC_C (1 << 2) /* Cycle counter reset */
+#define PMNC_D (1 << 3) /* CCNT counts every 64th cpu cycle */
+#define PMNC_X (1 << 4) /* Export to ETM */
+#define PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug */
+#define PMNC_MASK 0x3f /* Mask for writable bits */
+
+/* ccnt reg */
+#define CCNT_REG (1 << 31)
+
+#define CCNT 0
+#define CNT0 1
+#define CNTMAX (4+1)
+
+static unsigned long pmnc_enabled[CNTMAX];
+static unsigned long pmnc_event[CNTMAX];
+static unsigned long pmnc_key[CNTMAX];
+
+static DEFINE_PER_CPU(int[CNTMAX * 2], perfCnt);
+
+enum scorpion_perf_types {
+ SCORPION_ICACHE_EXPL_INV = 0x4c,
+ SCORPION_ICACHE_MISS = 0x4d,
+ SCORPION_ICACHE_ACCESS = 0x4e,
+ SCORPION_ICACHE_CACHEREQ_L2 = 0x4f,
+ SCORPION_ICACHE_NOCACHE_L2 = 0x50,
+ SCORPION_HIQUP_NOPED = 0x51,
+ SCORPION_DATA_ABORT = 0x52,
+ SCORPION_IRQ = 0x53,
+ SCORPION_FIQ = 0x54,
+ SCORPION_ALL_EXCPT = 0x55,
+ SCORPION_UNDEF = 0x56,
+ SCORPION_SVC = 0x57,
+ SCORPION_SMC = 0x58,
+ SCORPION_PREFETCH_ABORT = 0x59,
+ SCORPION_INDEX_CHECK = 0x5a,
+ SCORPION_NULL_CHECK = 0x5b,
+ SCORPION_EXPL_ICIALLU = 0x5c,
+ SCORPION_IMPL_ICIALLU = 0x5d,
+ SCORPION_NONICIALLU_BTAC_INV = 0x5e,
+ SCORPION_ICIMVAU_IMPL_ICIALLU = 0x5f,
+ SCORPION_SPIPE_ONLY_CYCLES = 0x60,
+ SCORPION_XPIPE_ONLY_CYCLES = 0x61,
+ SCORPION_DUAL_CYCLES = 0x62,
+ SCORPION_DISPATCH_ANY_CYCLES = 0x63,
+ SCORPION_FIFO_FULLBLK_CMT = 0x64,
+ SCORPION_FAIL_COND_INST = 0x65,
+ SCORPION_PASS_COND_INST = 0x66,
+ SCORPION_ALLOW_VU_CLK = 0x67,
+ SCORPION_VU_IDLE = 0x68,
+ SCORPION_ALLOW_L2_CLK = 0x69,
+ SCORPION_L2_IDLE = 0x6a,
+ SCORPION_DTLB_IMPL_INV_SCTLR_DACR = 0x6b,
+ SCORPION_DTLB_EXPL_INV = 0x6c,
+ SCORPION_DTLB_MISS = 0x6d,
+ SCORPION_DTLB_ACCESS = 0x6e,
+ SCORPION_ITLB_MISS = 0x6f,
+ SCORPION_ITLB_IMPL_INV = 0x70,
+ SCORPION_ITLB_EXPL_INV = 0x71,
+ SCORPION_UTLB_D_MISS = 0x72,
+ SCORPION_UTLB_D_ACCESS = 0x73,
+ SCORPION_UTLB_I_MISS = 0x74,
+ SCORPION_UTLB_I_ACCESS = 0x75,
+ SCORPION_UTLB_INV_ASID = 0x76,
+ SCORPION_UTLB_INV_MVA = 0x77,
+ SCORPION_UTLB_INV_ALL = 0x78,
+ SCORPION_S2_HOLD_RDQ_UNAVAIL = 0x79,
+ SCORPION_S2_HOLD = 0x7a,
+ SCORPION_S2_HOLD_DEV_OP = 0x7b,
+ SCORPION_S2_HOLD_ORDER = 0x7c,
+ SCORPION_S2_HOLD_BARRIER = 0x7d,
+ SCORPION_VIU_DUAL_CYCLE = 0x7e,
+ SCORPION_VIU_SINGLE_CYCLE = 0x7f,
+ SCORPION_VX_PIPE_WAR_STALL_CYCLES = 0x80,
+ SCORPION_VX_PIPE_WAW_STALL_CYCLES = 0x81,
+ SCORPION_VX_PIPE_RAW_STALL_CYCLES = 0x82,
+ SCORPION_VX_PIPE_LOAD_USE_STALL = 0x83,
+ SCORPION_VS_PIPE_WAR_STALL_CYCLES = 0x84,
+ SCORPION_VS_PIPE_WAW_STALL_CYCLES = 0x85,
+ SCORPION_VS_PIPE_RAW_STALL_CYCLES = 0x86,
+ SCORPION_EXCEPTIONS_INV_OPERATION = 0x87,
+ SCORPION_EXCEPTIONS_DIV_BY_ZERO = 0x88,
+ SCORPION_COND_INST_FAIL_VX_PIPE = 0x89,
+ SCORPION_COND_INST_FAIL_VS_PIPE = 0x8a,
+ SCORPION_EXCEPTIONS_OVERFLOW = 0x8b,
+ SCORPION_EXCEPTIONS_UNDERFLOW = 0x8c,
+ SCORPION_EXCEPTIONS_DENORM = 0x8d,
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+ SCORPIONMP_NUM_BARRIERS = 0x8e,
+ SCORPIONMP_BARRIER_CYCLES = 0x8f,
+#else
+ SCORPION_BANK_AB_HIT = 0x8e,
+ SCORPION_BANK_AB_ACCESS = 0x8f,
+ SCORPION_BANK_CD_HIT = 0x90,
+ SCORPION_BANK_CD_ACCESS = 0x91,
+ SCORPION_BANK_AB_DSIDE_HIT = 0x92,
+ SCORPION_BANK_AB_DSIDE_ACCESS = 0x93,
+ SCORPION_BANK_CD_DSIDE_HIT = 0x94,
+ SCORPION_BANK_CD_DSIDE_ACCESS = 0x95,
+ SCORPION_BANK_AB_ISIDE_HIT = 0x96,
+ SCORPION_BANK_AB_ISIDE_ACCESS = 0x97,
+ SCORPION_BANK_CD_ISIDE_HIT = 0x98,
+ SCORPION_BANK_CD_ISIDE_ACCESS = 0x99,
+ SCORPION_ISIDE_RD_WAIT = 0x9a,
+ SCORPION_DSIDE_RD_WAIT = 0x9b,
+ SCORPION_BANK_BYPASS_WRITE = 0x9c,
+ SCORPION_BANK_AB_NON_CASTOUT = 0x9d,
+ SCORPION_BANK_AB_L2_CASTOUT = 0x9e,
+ SCORPION_BANK_CD_NON_CASTOUT = 0x9f,
+ SCORPION_BANK_CD_L2_CASTOUT = 0xa0,
+#endif
+ MSM_MAX_EVT
+};
+
+struct scorp_evt {
+ u32 evt_type;
+ u32 val;
+ u8 grp;
+ u32 evt_type_act;
+};
+
+static const struct scorp_evt sc_evt[] = {
+ {SCORPION_ICACHE_EXPL_INV, 0x80000500, 0, 0x4d},
+ {SCORPION_ICACHE_MISS, 0x80050000, 0, 0x4e},
+ {SCORPION_ICACHE_ACCESS, 0x85000000, 0, 0x4f},
+ {SCORPION_ICACHE_CACHEREQ_L2, 0x86000000, 0, 0x4f},
+ {SCORPION_ICACHE_NOCACHE_L2, 0x87000000, 0, 0x4f},
+ {SCORPION_HIQUP_NOPED, 0x80080000, 0, 0x4e},
+ {SCORPION_DATA_ABORT, 0x8000000a, 0, 0x4c},
+ {SCORPION_IRQ, 0x80000a00, 0, 0x4d},
+ {SCORPION_FIQ, 0x800a0000, 0, 0x4e},
+ {SCORPION_ALL_EXCPT, 0x8a000000, 0, 0x4f},
+ {SCORPION_UNDEF, 0x8000000b, 0, 0x4c},
+ {SCORPION_SVC, 0x80000b00, 0, 0x4d},
+ {SCORPION_SMC, 0x800b0000, 0, 0x4e},
+ {SCORPION_PREFETCH_ABORT, 0x8b000000, 0, 0x4f},
+ {SCORPION_INDEX_CHECK, 0x8000000c, 0, 0x4c},
+ {SCORPION_NULL_CHECK, 0x80000c00, 0, 0x4d},
+ {SCORPION_EXPL_ICIALLU, 0x8000000d, 0, 0x4c},
+ {SCORPION_IMPL_ICIALLU, 0x80000d00, 0, 0x4d},
+ {SCORPION_NONICIALLU_BTAC_INV, 0x800d0000, 0, 0x4e},
+ {SCORPION_ICIMVAU_IMPL_ICIALLU, 0x8d000000, 0, 0x4f},
+
+ {SCORPION_SPIPE_ONLY_CYCLES, 0x80000600, 1, 0x51},
+ {SCORPION_XPIPE_ONLY_CYCLES, 0x80060000, 1, 0x52},
+ {SCORPION_DUAL_CYCLES, 0x86000000, 1, 0x53},
+ {SCORPION_DISPATCH_ANY_CYCLES, 0x89000000, 1, 0x53},
+ {SCORPION_FIFO_FULLBLK_CMT, 0x8000000d, 1, 0x50},
+ {SCORPION_FAIL_COND_INST, 0x800d0000, 1, 0x52},
+ {SCORPION_PASS_COND_INST, 0x8d000000, 1, 0x53},
+ {SCORPION_ALLOW_VU_CLK, 0x8000000e, 1, 0x50},
+ {SCORPION_VU_IDLE, 0x80000e00, 1, 0x51},
+ {SCORPION_ALLOW_L2_CLK, 0x800e0000, 1, 0x52},
+ {SCORPION_L2_IDLE, 0x8e000000, 1, 0x53},
+
+ {SCORPION_DTLB_IMPL_INV_SCTLR_DACR, 0x80000001, 2, 0x54},
+ {SCORPION_DTLB_EXPL_INV, 0x80000100, 2, 0x55},
+ {SCORPION_DTLB_MISS, 0x80010000, 2, 0x56},
+ {SCORPION_DTLB_ACCESS, 0x81000000, 2, 0x57},
+ {SCORPION_ITLB_MISS, 0x80000200, 2, 0x55},
+ {SCORPION_ITLB_IMPL_INV, 0x80020000, 2, 0x56},
+ {SCORPION_ITLB_EXPL_INV, 0x82000000, 2, 0x57},
+ {SCORPION_UTLB_D_MISS, 0x80000003, 2, 0x54},
+ {SCORPION_UTLB_D_ACCESS, 0x80000300, 2, 0x55},
+ {SCORPION_UTLB_I_MISS, 0x80030000, 2, 0x56},
+ {SCORPION_UTLB_I_ACCESS, 0x83000000, 2, 0x57},
+ {SCORPION_UTLB_INV_ASID, 0x80000400, 2, 0x55},
+ {SCORPION_UTLB_INV_MVA, 0x80040000, 2, 0x56},
+ {SCORPION_UTLB_INV_ALL, 0x84000000, 2, 0x57},
+ {SCORPION_S2_HOLD_RDQ_UNAVAIL, 0x80000800, 2, 0x55},
+ {SCORPION_S2_HOLD, 0x88000000, 2, 0x57},
+ {SCORPION_S2_HOLD_DEV_OP, 0x80000900, 2, 0x55},
+ {SCORPION_S2_HOLD_ORDER, 0x80090000, 2, 0x56},
+ {SCORPION_S2_HOLD_BARRIER, 0x89000000, 2, 0x57},
+
+ {SCORPION_VIU_DUAL_CYCLE, 0x80000001, 4, 0x5c},
+ {SCORPION_VIU_SINGLE_CYCLE, 0x80000100, 4, 0x5d},
+ {SCORPION_VX_PIPE_WAR_STALL_CYCLES, 0x80000005, 4, 0x5c},
+ {SCORPION_VX_PIPE_WAW_STALL_CYCLES, 0x80000500, 4, 0x5d},
+ {SCORPION_VX_PIPE_RAW_STALL_CYCLES, 0x80050000, 4, 0x5e},
+ {SCORPION_VX_PIPE_LOAD_USE_STALL, 0x80000007, 4, 0x5c},
+ {SCORPION_VS_PIPE_WAR_STALL_CYCLES, 0x80000008, 4, 0x5c},
+ {SCORPION_VS_PIPE_WAW_STALL_CYCLES, 0x80000800, 4, 0x5d},
+ {SCORPION_VS_PIPE_RAW_STALL_CYCLES, 0x80080000, 4, 0x5e},
+ {SCORPION_EXCEPTIONS_INV_OPERATION, 0x8000000b, 4, 0x5c},
+ {SCORPION_EXCEPTIONS_DIV_BY_ZERO, 0x80000b00, 4, 0x5d},
+ {SCORPION_COND_INST_FAIL_VX_PIPE, 0x800b0000, 4, 0x5e},
+ {SCORPION_COND_INST_FAIL_VS_PIPE, 0x8b000000, 4, 0x5f},
+ {SCORPION_EXCEPTIONS_OVERFLOW, 0x8000000c, 4, 0x5c},
+ {SCORPION_EXCEPTIONS_UNDERFLOW, 0x80000c00, 4, 0x5d},
+ {SCORPION_EXCEPTIONS_DENORM, 0x8c000000, 4, 0x5f},
+
+#ifdef CONFIG_ARCH_MSM_SCORPIONMP
+ {SCORPIONMP_NUM_BARRIERS, 0x80000e00, 3, 0x59},
+ {SCORPIONMP_BARRIER_CYCLES, 0x800e0000, 3, 0x5a},
+#else
+ {SCORPION_BANK_AB_HIT, 0x80000001, 3, 0x58},
+ {SCORPION_BANK_AB_ACCESS, 0x80000100, 3, 0x59},
+ {SCORPION_BANK_CD_HIT, 0x80010000, 3, 0x5a},
+ {SCORPION_BANK_CD_ACCESS, 0x81000000, 3, 0x5b},
+ {SCORPION_BANK_AB_DSIDE_HIT, 0x80000002, 3, 0x58},
+ {SCORPION_BANK_AB_DSIDE_ACCESS, 0x80000200, 3, 0x59},
+ {SCORPION_BANK_CD_DSIDE_HIT, 0x80020000, 3, 0x5a},
+ {SCORPION_BANK_CD_DSIDE_ACCESS, 0x82000000, 3, 0x5b},
+ {SCORPION_BANK_AB_ISIDE_HIT, 0x80000003, 3, 0x58},
+ {SCORPION_BANK_AB_ISIDE_ACCESS, 0x80000300, 3, 0x59},
+ {SCORPION_BANK_CD_ISIDE_HIT, 0x80030000, 3, 0x5a},
+ {SCORPION_BANK_CD_ISIDE_ACCESS, 0x83000000, 3, 0x5b},
+ {SCORPION_ISIDE_RD_WAIT, 0x80000009, 3, 0x58},
+ {SCORPION_DSIDE_RD_WAIT, 0x80090000, 3, 0x5a},
+ {SCORPION_BANK_BYPASS_WRITE, 0x8000000a, 3, 0x58},
+ {SCORPION_BANK_AB_NON_CASTOUT, 0x8000000c, 3, 0x58},
+ {SCORPION_BANK_AB_L2_CASTOUT, 0x80000c00, 3, 0x59},
+ {SCORPION_BANK_CD_NON_CASTOUT, 0x800c0000, 3, 0x5a},
+ {SCORPION_BANK_CD_L2_CASTOUT, 0x8c000000, 3, 0x5b},
+#endif
+};
+
+static inline void scorpion_pmnc_write(u32 val)
+{
+ val &= PMNC_MASK;
+ asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+static inline u32 scorpion_pmnc_read(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+ return val;
+}
+
+static inline u32 scorpion_ccnt_read(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+ return val;
+}
+
+static inline u32 scorpion_cntn_read(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+ return val;
+}
+
+static inline u32 scorpion_pmnc_enable_counter(unsigned int cnt)
+{
+ u32 val;
+
+ if (cnt >= CNTMAX) {
+ pr_err("gator: CPU%u enabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+ return -1;
+ }
+
+ if (cnt == CCNT)
+ val = CCNT_REG;
+ else
+ val = (1 << (cnt - CNT0));
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+ return cnt;
+}
+
+static inline u32 scorpion_pmnc_disable_counter(unsigned int cnt)
+{
+ u32 val;
+
+ if (cnt >= CNTMAX) {
+ pr_err("gator: CPU%u disabling wrong PMNC counter %d\n", smp_processor_id(), cnt);
+ return -1;
+ }
+
+ if (cnt == CCNT)
+ val = CCNT_REG;
+ else
+ val = (1 << (cnt - CNT0));
+
+ asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+ return cnt;
+}
+
+static inline int scorpion_pmnc_select_counter(unsigned int cnt)
+{
+ u32 val;
+
+ if ((cnt == CCNT) || (cnt >= CNTMAX)) {
+ pr_err("gator: CPU%u selecting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+ return -1;
+ }
+
+ val = (cnt - CNT0);
+ asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+ return cnt;
+}
+
+static u32 scorpion_read_lpm0(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val));
+ return val;
+}
+
+static void scorpion_write_lpm0(u32 val)
+{
+ asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm1(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val));
+ return val;
+}
+
+static void scorpion_write_lpm1(u32 val)
+{
+ asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_lpm2(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val));
+ return val;
+}
+
+static void scorpion_write_lpm2(u32 val)
+{
+ asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_l2lpm(void)
+{
+ u32 val;
+
+ asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val));
+ return val;
+}
+
+static void scorpion_write_l2lpm(u32 val)
+{
+ asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val));
+}
+
+static u32 scorpion_read_vlpm(void)
+{
+ u32 val;
+
+ asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+ return val;
+}
+
+static void scorpion_write_vlpm(u32 val)
+{
+ asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+struct scorpion_access_funcs {
+ u32 (*read)(void);
+ void (*write)(u32);
+};
+
+struct scorpion_access_funcs scor_func[] = {
+ {scorpion_read_lpm0, scorpion_write_lpm0},
+ {scorpion_read_lpm1, scorpion_write_lpm1},
+ {scorpion_read_lpm2, scorpion_write_lpm2},
+ {scorpion_read_l2lpm, scorpion_write_l2lpm},
+ {scorpion_read_vlpm, scorpion_write_vlpm},
+};
+
+u32 venum_orig_val;
+u32 fp_orig_val;
+
+static void scorpion_pre_vlpm(void)
+{
+ u32 venum_new_val;
+ u32 fp_new_val;
+
+ /* CPACR Enable CP10 access */
+ asm volatile("mrc p15, 0, %0, c1, c0, 2" : "=r" (venum_orig_val));
+ venum_new_val = venum_orig_val | 0x00300000;
+ asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_new_val));
+ /* Enable FPEXC */
+ asm volatile("mrc p10, 7, %0, c8, c0, 0" : "=r" (fp_orig_val));
+ fp_new_val = fp_orig_val | 0x40000000;
+ asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_new_val));
+}
+
+static void scorpion_post_vlpm(void)
+{
+ /* Restore FPEXC */
+ asm volatile("mcr p10, 7, %0, c8, c0, 0" : : "r" (fp_orig_val));
+ /* Restore CPACR */
+ asm volatile("mcr p15, 0, %0, c1, c0, 2" : : "r" (venum_orig_val));
+}
+
+#define COLMN0MASK 0x000000ff
+#define COLMN1MASK 0x0000ff00
+#define COLMN2MASK 0x00ff0000
+static u32 scorpion_get_columnmask(u32 setval)
+{
+ if (setval & COLMN0MASK)
+ return 0xffffff00;
+ if (setval & COLMN1MASK)
+ return 0xffff00ff;
+ if (setval & COLMN2MASK)
+ return 0xff00ffff;
+ return 0x80ffffff;
+}
+
+static void scorpion_evt_setup(u32 gr, u32 setval)
+{
+ u32 val;
+
+ if (gr == 4)
+ scorpion_pre_vlpm();
+ val = scorpion_get_columnmask(setval) & scor_func[gr].read();
+ val = val | setval;
+ scor_func[gr].write(val);
+ if (gr == 4)
+ scorpion_post_vlpm();
+}
+
+static int get_scorpion_evtinfo(unsigned int evt_type, struct scorp_evt *evtinfo)
+{
+ u32 idx;
+
+ if ((evt_type < 0x4c) || (evt_type >= MSM_MAX_EVT))
+ return 0;
+ idx = evt_type - 0x4c;
+ if (sc_evt[idx].evt_type == evt_type) {
+ evtinfo->val = sc_evt[idx].val;
+ evtinfo->grp = sc_evt[idx].grp;
+ evtinfo->evt_type_act = sc_evt[idx].evt_type_act;
+ return 1;
+ }
+ return 0;
+}
+
+static inline void scorpion_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+ if (scorpion_pmnc_select_counter(cnt) == cnt) {
+ if (val < 0x40) {
+ asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+ } else {
+ u32 zero = 0;
+ struct scorp_evt evtinfo;
+ /* extract evtinfo.grp and evtinfo.tevt_type_act from val */
+ if (get_scorpion_evtinfo(val, &evtinfo) == 0)
+ return;
+ asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (evtinfo.evt_type_act));
+ asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (zero));
+ scorpion_evt_setup(evtinfo.grp, val);
+ }
+ }
+}
+
+static void scorpion_pmnc_reset_counter(unsigned int cnt)
+{
+ u32 val = 0;
+
+ if (cnt == CCNT) {
+ scorpion_pmnc_disable_counter(cnt);
+
+ asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (val));
+
+ if (pmnc_enabled[cnt] != 0)
+ scorpion_pmnc_enable_counter(cnt);
+
+ } else if (cnt >= CNTMAX) {
+ pr_err("gator: CPU%u resetting wrong PMNC counter %d\n", smp_processor_id(), cnt);
+ } else {
+ scorpion_pmnc_disable_counter(cnt);
+
+ if (scorpion_pmnc_select_counter(cnt) == cnt)
+ asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (val));
+
+ if (pmnc_enabled[cnt] != 0)
+ scorpion_pmnc_enable_counter(cnt);
+ }
+}
+
+static int gator_events_scorpion_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ int i;
+
+ for (i = 0; i < pmnc_counters; i++) {
+ char buf[40];
+
+ if (i == 0)
+ snprintf(buf, sizeof(buf), "%s_ccnt", pmnc_name);
+ else
+ snprintf(buf, sizeof(buf), "%s_cnt%d", pmnc_name, i - 1);
+ dir = gatorfs_mkdir(sb, root, buf);
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &pmnc_enabled[i]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &pmnc_key[i]);
+ if (i > 0)
+ gatorfs_create_ulong(sb, dir, "event", &pmnc_event[i]);
+ }
+
+ return 0;
+}
+
+static int gator_events_scorpion_online(int **buffer, bool migrate)
+{
+ unsigned int cnt, len = 0, cpu = smp_processor_id();
+
+ if (scorpion_pmnc_read() & PMNC_E)
+ scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+
+ /* Initialize & Reset PMNC: C bit and P bit */
+ scorpion_pmnc_write(PMNC_P | PMNC_C);
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ unsigned long event;
+
+ if (!pmnc_enabled[cnt])
+ continue;
+
+ /* disable counter */
+ scorpion_pmnc_disable_counter(cnt);
+
+ event = pmnc_event[cnt] & 255;
+
+ /* Set event (if destined for PMNx counters), We don't need to set the event if it's a cycle count */
+ if (cnt != CCNT)
+ scorpion_pmnc_write_evtsel(cnt, event);
+
+ /* reset counter */
+ scorpion_pmnc_reset_counter(cnt);
+
+ /* Enable counter, do not enable interrupt for this counter */
+ scorpion_pmnc_enable_counter(cnt);
+ }
+
+ /* enable */
+ scorpion_pmnc_write(scorpion_pmnc_read() | PMNC_E);
+
+ /* read the counters and toss the invalid data, return zero instead */
+ for (cnt = 0; cnt < pmnc_counters; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ if (cnt == CCNT)
+ scorpion_ccnt_read();
+ else if (scorpion_pmnc_select_counter(cnt) == cnt)
+ scorpion_cntn_read();
+ scorpion_pmnc_reset_counter(cnt);
+
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = 0;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static int gator_events_scorpion_offline(int **buffer, bool migrate)
+{
+ scorpion_pmnc_write(scorpion_pmnc_read() & ~PMNC_E);
+ return 0;
+}
+
+static void gator_events_scorpion_stop(void)
+{
+ unsigned int cnt;
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ }
+}
+
+static int gator_events_scorpion_read(int **buffer, bool sched_switch)
+{
+ int cnt, len = 0;
+ int cpu = smp_processor_id();
+
+ /* a context switch may occur before the online hotplug event, thus need to check that the pmu is enabled */
+ if (!(scorpion_pmnc_read() & PMNC_E))
+ return 0;
+
+ for (cnt = 0; cnt < pmnc_counters; cnt++) {
+ if (pmnc_enabled[cnt]) {
+ int value;
+
+ if (cnt == CCNT)
+ value = scorpion_ccnt_read();
+ else if (scorpion_pmnc_select_counter(cnt) == cnt)
+ value = scorpion_cntn_read();
+ else
+ value = 0;
+ scorpion_pmnc_reset_counter(cnt);
+
+ per_cpu(perfCnt, cpu)[len++] = pmnc_key[cnt];
+ per_cpu(perfCnt, cpu)[len++] = value;
+ }
+ }
+
+ if (buffer)
+ *buffer = per_cpu(perfCnt, cpu);
+
+ return len;
+}
+
+static struct gator_interface gator_events_scorpion_interface = {
+ .create_files = gator_events_scorpion_create_files,
+ .stop = gator_events_scorpion_stop,
+ .online = gator_events_scorpion_online,
+ .offline = gator_events_scorpion_offline,
+ .read = gator_events_scorpion_read,
+};
+
+int gator_events_scorpion_init(void)
+{
+ unsigned int cnt;
+
+ switch (gator_cpuid()) {
+ case SCORPION:
+ pmnc_name = "Scorpion";
+ pmnc_counters = 4;
+ break;
+ case SCORPIONMP:
+ pmnc_name = "ScorpionMP";
+ pmnc_counters = 4;
+ break;
+ default:
+ return -1;
+ }
+
+ /* CNT[n] + CCNT */
+ pmnc_counters++;
+
+ for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+ pmnc_enabled[cnt] = 0;
+ pmnc_event[cnt] = 0;
+ pmnc_key[cnt] = gator_events_get_key();
+ }
+
+ return gator_events_install(&gator_events_scorpion_interface);
+}
+
+#endif
diff --git a/drivers/gator/gator_fs.c b/drivers/gator/gator_fs.c
new file mode 100644
index 0000000..d8fb357
--- /dev/null
+++ b/drivers/gator/gator_fs.c
@@ -0,0 +1,370 @@
+/**
+ * @file gatorfs.c
+ *
+ * @remark Copyright 2002 OProfile authors
+ * @remark Read the file COPYING
+ *
+ * @author John Levon
+ *
+ * A simple filesystem for configuration and
+ * access of oprofile.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/uaccess.h>
+
+#define gatorfs_MAGIC 0x24051020
+#define TMPBUFSIZE 50
+DEFINE_SPINLOCK(gatorfs_lock);
+
+static struct inode *gatorfs_get_inode(struct super_block *sb, int mode)
+{
+ struct inode *inode = new_inode(sb);
+
+ if (inode) {
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 37)
+ inode->i_ino = get_next_ino();
+#endif
+ inode->i_mode = mode;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ }
+ return inode;
+}
+
+static const struct super_operations s_ops = {
+ .statfs = simple_statfs,
+ .drop_inode = generic_delete_inode,
+};
+
+static ssize_t gatorfs_ulong_to_user(unsigned long val, char __user *buf, size_t count, loff_t *offset)
+{
+ char tmpbuf[TMPBUFSIZE];
+ size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%lu\n", val);
+
+ if (maxlen > TMPBUFSIZE)
+ maxlen = TMPBUFSIZE;
+ return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static ssize_t gatorfs_u64_to_user(u64 val, char __user *buf, size_t count, loff_t *offset)
+{
+ char tmpbuf[TMPBUFSIZE];
+ size_t maxlen = snprintf(tmpbuf, TMPBUFSIZE, "%llu\n", val);
+
+ if (maxlen > TMPBUFSIZE)
+ maxlen = TMPBUFSIZE;
+ return simple_read_from_buffer(buf, count, offset, tmpbuf, maxlen);
+}
+
+static int gatorfs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count)
+{
+ char tmpbuf[TMPBUFSIZE];
+ unsigned long flags;
+
+ if (!count)
+ return 0;
+
+ if (count > TMPBUFSIZE - 1)
+ return -EINVAL;
+
+ memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+ if (copy_from_user(tmpbuf, buf, count))
+ return -EFAULT;
+
+ spin_lock_irqsave(&gatorfs_lock, flags);
+ *val = simple_strtoul(tmpbuf, NULL, 0);
+ spin_unlock_irqrestore(&gatorfs_lock, flags);
+ return 0;
+}
+
+static int gatorfs_u64_from_user(u64 *val, char const __user *buf, size_t count)
+{
+ char tmpbuf[TMPBUFSIZE];
+ unsigned long flags;
+
+ if (!count)
+ return 0;
+
+ if (count > TMPBUFSIZE - 1)
+ return -EINVAL;
+
+ memset(tmpbuf, 0x0, TMPBUFSIZE);
+
+ if (copy_from_user(tmpbuf, buf, count))
+ return -EFAULT;
+
+ spin_lock_irqsave(&gatorfs_lock, flags);
+ *val = simple_strtoull(tmpbuf, NULL, 0);
+ spin_unlock_irqrestore(&gatorfs_lock, flags);
+ return 0;
+}
+
+static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ unsigned long *val = file->private_data;
+
+ return gatorfs_ulong_to_user(*val, buf, count, offset);
+}
+
+static ssize_t u64_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ u64 *val = file->private_data;
+
+ return gatorfs_u64_to_user(*val, buf, count, offset);
+}
+
+static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+ unsigned long *value = file->private_data;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = gatorfs_ulong_from_user(value, buf, count);
+
+ if (retval)
+ return retval;
+ return count;
+}
+
+static ssize_t u64_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+ u64 *value = file->private_data;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = gatorfs_u64_from_user(value, buf, count);
+
+ if (retval)
+ return retval;
+ return count;
+}
+
+static int default_open(struct inode *inode, struct file *filp)
+{
+ if (inode->i_private)
+ filp->private_data = inode->i_private;
+ return 0;
+}
+
+static const struct file_operations ulong_fops = {
+ .read = ulong_read_file,
+ .write = ulong_write_file,
+ .open = default_open,
+};
+
+static const struct file_operations u64_fops = {
+ .read = u64_read_file,
+ .write = u64_write_file,
+ .open = default_open,
+};
+
+static const struct file_operations ulong_ro_fops = {
+ .read = ulong_read_file,
+ .open = default_open,
+};
+
+static const struct file_operations u64_ro_fops = {
+ .read = u64_read_file,
+ .open = default_open,
+};
+
+static struct dentry *__gatorfs_create_file(struct super_block *sb,
+ struct dentry *root,
+ char const *name,
+ const struct file_operations *fops,
+ int perm)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+
+ dentry = d_alloc_name(root, name);
+ if (!dentry)
+ return NULL;
+ inode = gatorfs_get_inode(sb, S_IFREG | perm);
+ if (!inode) {
+ dput(dentry);
+ return NULL;
+ }
+ inode->i_fop = fops;
+ d_add(dentry, inode);
+ return dentry;
+}
+
+int gatorfs_create_ulong(struct super_block *sb, struct dentry *root,
+ char const *name, unsigned long *val)
+{
+ struct dentry *d = __gatorfs_create_file(sb, root, name,
+ &ulong_fops, 0644);
+ if (!d)
+ return -EFAULT;
+
+ d->d_inode->i_private = val;
+ return 0;
+}
+
+static int gatorfs_create_u64(struct super_block *sb, struct dentry *root,
+ char const *name, u64 *val)
+{
+ struct dentry *d = __gatorfs_create_file(sb, root, name,
+ &u64_fops, 0644);
+ if (!d)
+ return -EFAULT;
+
+ d->d_inode->i_private = val;
+ return 0;
+}
+
+int gatorfs_create_ro_ulong(struct super_block *sb, struct dentry *root,
+ char const *name, unsigned long *val)
+{
+ struct dentry *d = __gatorfs_create_file(sb, root, name,
+ &ulong_ro_fops, 0444);
+ if (!d)
+ return -EFAULT;
+
+ d->d_inode->i_private = val;
+ return 0;
+}
+
+static int gatorfs_create_ro_u64(struct super_block *sb, struct dentry *root,
+ char const *name, u64 *val)
+{
+ struct dentry *d =
+ __gatorfs_create_file(sb, root, name, &u64_ro_fops, 0444);
+ if (!d)
+ return -EFAULT;
+
+ d->d_inode->i_private = val;
+ return 0;
+}
+
+static ssize_t atomic_read_file(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ atomic_t *val = file->private_data;
+
+ return gatorfs_ulong_to_user(atomic_read(val), buf, count, offset);
+}
+
+static const struct file_operations atomic_ro_fops = {
+ .read = atomic_read_file,
+ .open = default_open,
+};
+
+static int gatorfs_create_file(struct super_block *sb, struct dentry *root,
+ char const *name, const struct file_operations *fops)
+{
+ if (!__gatorfs_create_file(sb, root, name, fops, 0644))
+ return -EFAULT;
+ return 0;
+}
+
+static int gatorfs_create_file_perm(struct super_block *sb, struct dentry *root,
+ char const *name,
+ const struct file_operations *fops, int perm)
+{
+ if (!__gatorfs_create_file(sb, root, name, fops, perm))
+ return -EFAULT;
+ return 0;
+}
+
+struct dentry *gatorfs_mkdir(struct super_block *sb,
+ struct dentry *root, char const *name)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+
+ dentry = d_alloc_name(root, name);
+ if (!dentry)
+ return NULL;
+ inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+ if (!inode) {
+ dput(dentry);
+ return NULL;
+ }
+ inode->i_op = &simple_dir_inode_operations;
+ inode->i_fop = &simple_dir_operations;
+ d_add(dentry, inode);
+ return dentry;
+}
+
+static int gatorfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+ struct inode *root_inode;
+ struct dentry *root_dentry;
+
+ sb->s_blocksize = PAGE_CACHE_SIZE;
+ sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ sb->s_magic = gatorfs_MAGIC;
+ sb->s_op = &s_ops;
+ sb->s_time_gran = 1;
+
+ root_inode = gatorfs_get_inode(sb, S_IFDIR | 0755);
+ if (!root_inode)
+ return -ENOMEM;
+ root_inode->i_op = &simple_dir_inode_operations;
+ root_inode->i_fop = &simple_dir_operations;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+ root_dentry = d_alloc_root(root_inode);
+#else
+ root_dentry = d_make_root(root_inode);
+#endif
+
+ if (!root_dentry) {
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+ iput(root_inode);
+#endif
+ return -ENOMEM;
+ }
+
+ sb->s_root = root_dentry;
+
+ gator_op_create_files(sb, root_dentry);
+
+ return 0;
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+static int gatorfs_get_sb(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data,
+ struct vfsmount *mnt)
+{
+ return get_sb_single(fs_type, flags, data, gatorfs_fill_super, mnt);
+}
+#else
+static struct dentry *gatorfs_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
+{
+ return mount_nodev(fs_type, flags, data, gatorfs_fill_super);
+}
+#endif
+
+static struct file_system_type gatorfs_type = {
+ .owner = THIS_MODULE,
+ .name = "gatorfs",
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 39)
+ .get_sb = gatorfs_get_sb,
+#else
+ .mount = gatorfs_mount,
+#endif
+
+ .kill_sb = kill_litter_super,
+};
+
+static int __init gatorfs_register(void)
+{
+ return register_filesystem(&gatorfs_type);
+}
+
+static void gatorfs_unregister(void)
+{
+ unregister_filesystem(&gatorfs_type);
+}
diff --git a/drivers/gator/gator_hrtimer_gator.c b/drivers/gator/gator_hrtimer_gator.c
new file mode 100644
index 0000000..36961f8
--- /dev/null
+++ b/drivers/gator/gator_hrtimer_gator.c
@@ -0,0 +1,80 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+void (*callback)(void);
+DEFINE_PER_CPU(struct hrtimer, percpu_hrtimer);
+DEFINE_PER_CPU(ktime_t, hrtimer_expire);
+DEFINE_PER_CPU(int, hrtimer_is_active);
+static ktime_t profiling_interval;
+static void gator_hrtimer_online(void);
+static void gator_hrtimer_offline(void);
+
+static enum hrtimer_restart gator_hrtimer_notify(struct hrtimer *hrtimer)
+{
+ int cpu = get_logical_cpu();
+
+ hrtimer_forward(hrtimer, per_cpu(hrtimer_expire, cpu), profiling_interval);
+ per_cpu(hrtimer_expire, cpu) = ktime_add(per_cpu(hrtimer_expire, cpu), profiling_interval);
+ (*callback)();
+ return HRTIMER_RESTART;
+}
+
+static void gator_hrtimer_online(void)
+{
+ int cpu = get_logical_cpu();
+ struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+ if (per_cpu(hrtimer_is_active, cpu) || profiling_interval.tv64 == 0)
+ return;
+
+ per_cpu(hrtimer_is_active, cpu) = 1;
+ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer->function = gator_hrtimer_notify;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ hrtimer->irqsafe = 1;
+#endif
+ per_cpu(hrtimer_expire, cpu) = ktime_add(hrtimer->base->get_time(), profiling_interval);
+ hrtimer_start(hrtimer, per_cpu(hrtimer_expire, cpu), HRTIMER_MODE_ABS_PINNED);
+}
+
+static void gator_hrtimer_offline(void)
+{
+ int cpu = get_logical_cpu();
+ struct hrtimer *hrtimer = &per_cpu(percpu_hrtimer, cpu);
+
+ if (!per_cpu(hrtimer_is_active, cpu))
+ return;
+
+ per_cpu(hrtimer_is_active, cpu) = 0;
+ hrtimer_cancel(hrtimer);
+}
+
+static int gator_hrtimer_init(int interval, void (*func)(void))
+{
+ int cpu;
+
+ (callback) = (func);
+
+ for_each_present_cpu(cpu) {
+ per_cpu(hrtimer_is_active, cpu) = 0;
+ }
+
+ /* calculate profiling interval */
+ if (interval > 0)
+ profiling_interval = ns_to_ktime(1000000000UL / interval);
+ else
+ profiling_interval.tv64 = 0;
+
+ return 0;
+}
+
+static void gator_hrtimer_shutdown(void)
+{
+ /* empty */
+}
diff --git a/drivers/gator/gator_iks.c b/drivers/gator/gator_iks.c
new file mode 100644
index 0000000..80535c7
--- /dev/null
+++ b/drivers/gator/gator_iks.c
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#if GATOR_IKS_SUPPORT
+
+#include <linux/of.h>
+#include <asm/bL_switcher.h>
+#include <asm/smp_plat.h>
+#include <trace/events/power_cpu_migrate.h>
+
+static bool map_cpuids;
+static int mpidr_cpuids[NR_CPUS];
+static const struct gator_cpu *mpidr_cpus[NR_CPUS];
+static int __lcpu_to_pcpu[NR_CPUS];
+
+static const struct gator_cpu *gator_find_cpu_by_dt_name(const char *const name)
+{
+ int i;
+
+ for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+ const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+ if (gator_cpu->dt_name != NULL && strcmp(gator_cpu->dt_name, name) == 0)
+ return gator_cpu;
+ }
+
+ return NULL;
+}
+
+static void calc_first_cluster_size(void)
+{
+ int len;
+ const u32 *val;
+ const char *compatible;
+ struct device_node *cn = NULL;
+ int mpidr_cpuids_count = 0;
+
+ /* Zero is a valid cpuid, so initialize the array to 0xff's */
+ memset(&mpidr_cpuids, 0xff, sizeof(mpidr_cpuids));
+ memset(&mpidr_cpus, 0, sizeof(mpidr_cpus));
+
+ while ((cn = of_find_node_by_type(cn, "cpu"))) {
+ BUG_ON(mpidr_cpuids_count >= NR_CPUS);
+
+ val = of_get_property(cn, "reg", &len);
+ if (!val || len != 4) {
+ pr_err("%s missing reg property\n", cn->full_name);
+ continue;
+ }
+ compatible = of_get_property(cn, "compatible", NULL);
+ if (compatible == NULL) {
+ pr_err("%s missing compatible property\n", cn->full_name);
+ continue;
+ }
+
+ mpidr_cpuids[mpidr_cpuids_count] = be32_to_cpup(val);
+ mpidr_cpus[mpidr_cpuids_count] = gator_find_cpu_by_dt_name(compatible);
+ ++mpidr_cpuids_count;
+ }
+
+ map_cpuids = (mpidr_cpuids_count == nr_cpu_ids);
+}
+
+static int linearize_mpidr(int mpidr)
+{
+ int i;
+
+ for (i = 0; i < nr_cpu_ids; ++i) {
+ if (mpidr_cpuids[i] == mpidr)
+ return i;
+ }
+
+ BUG();
+}
+
+int lcpu_to_pcpu(const int lcpu)
+{
+ int pcpu;
+
+ if (!map_cpuids)
+ return lcpu;
+
+ BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+ pcpu = __lcpu_to_pcpu[lcpu];
+ BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+ return pcpu;
+}
+
+int pcpu_to_lcpu(const int pcpu)
+{
+ int lcpu;
+
+ if (!map_cpuids)
+ return pcpu;
+
+ BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+ for (lcpu = 0; lcpu < nr_cpu_ids; ++lcpu) {
+ if (__lcpu_to_pcpu[lcpu] == pcpu) {
+ BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+ return lcpu;
+ }
+ }
+ BUG();
+}
+
+static void gator_update_cpu_mapping(u32 cpu_hwid)
+{
+ int lcpu = smp_processor_id();
+ int pcpu = linearize_mpidr(cpu_hwid & MPIDR_HWID_BITMASK);
+
+ BUG_ON(lcpu >= nr_cpu_ids || lcpu < 0);
+ BUG_ON(pcpu >= nr_cpu_ids || pcpu < 0);
+ __lcpu_to_pcpu[lcpu] = pcpu;
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_begin, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+ const int cpu = get_physical_cpu();
+
+ gator_timer_offline((void *)1);
+ gator_timer_offline_dispatch(cpu, true);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_finish, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+ int cpu;
+
+ gator_update_cpu_mapping(cpu_hwid);
+
+ /* get_physical_cpu must be called after gator_update_cpu_mapping */
+ cpu = get_physical_cpu();
+ gator_timer_online_dispatch(cpu, true);
+ gator_timer_online((void *)1);
+}
+
+GATOR_DEFINE_PROBE(cpu_migrate_current, TP_PROTO(u64 timestamp, u32 cpu_hwid))
+{
+ gator_update_cpu_mapping(cpu_hwid);
+}
+
+static void gator_send_iks_core_names(void)
+{
+ int cpu;
+ /* Send the cpu names */
+ preempt_disable();
+ for (cpu = 0; cpu < nr_cpu_ids; ++cpu) {
+ if (mpidr_cpus[cpu] != NULL)
+ gator_send_core_name(cpu, mpidr_cpus[cpu]->cpuid);
+ }
+ preempt_enable();
+}
+
+static int gator_migrate_start(void)
+{
+ int retval = 0;
+
+ if (!map_cpuids)
+ return retval;
+
+ if (retval == 0)
+ retval = GATOR_REGISTER_TRACE(cpu_migrate_begin);
+ if (retval == 0)
+ retval = GATOR_REGISTER_TRACE(cpu_migrate_finish);
+ if (retval == 0)
+ retval = GATOR_REGISTER_TRACE(cpu_migrate_current);
+ if (retval == 0) {
+ /* Initialize the logical to physical cpu mapping */
+ memset(&__lcpu_to_pcpu, 0xff, sizeof(__lcpu_to_pcpu));
+ bL_switcher_trace_trigger();
+ }
+ return retval;
+}
+
+static void gator_migrate_stop(void)
+{
+ if (!map_cpuids)
+ return;
+
+ GATOR_UNREGISTER_TRACE(cpu_migrate_current);
+ GATOR_UNREGISTER_TRACE(cpu_migrate_finish);
+ GATOR_UNREGISTER_TRACE(cpu_migrate_begin);
+}
+
+#else
+
+#define calc_first_cluster_size()
+#define gator_send_iks_core_names()
+#define gator_migrate_start() 0
+#define gator_migrate_stop()
+
+#endif
diff --git a/drivers/gator/gator_main.c b/drivers/gator/gator_main.c
new file mode 100644
index 0000000..affa1dc
--- /dev/null
+++ b/drivers/gator/gator_main.c
@@ -0,0 +1,1501 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/* This version must match the gator daemon version */
+#define PROTOCOL_VERSION 21
+static unsigned long gator_protocol_version = PROTOCOL_VERSION;
+
+#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/irq.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/perf_event.h>
+#include <linux/utsname.h>
+#include <linux/kthread.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
+
+#include "gator.h"
+#include "gator_src_md5.h"
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 32)
+#error kernels prior to 2.6.32 are not supported
+#endif
+
+#if defined(MODULE) && !defined(CONFIG_MODULES)
+#error Cannot build a module against a kernel that does not support modules. To resolve, either rebuild the kernel to support modules or build gator as part of the kernel.
+#endif
+
+#if !defined(CONFIG_GENERIC_TRACER) && !defined(CONFIG_TRACING)
+#error gator requires the kernel to have CONFIG_GENERIC_TRACER or CONFIG_TRACING defined
+#endif
+
+#ifndef CONFIG_PROFILING
+#error gator requires the kernel to have CONFIG_PROFILING defined
+#endif
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+#error gator requires the kernel to have CONFIG_HIGH_RES_TIMERS defined to support PC sampling
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 12, 0) && defined(__arm__) && defined(CONFIG_SMP) && !defined(CONFIG_LOCAL_TIMERS)
+#error gator requires the kernel to have CONFIG_LOCAL_TIMERS defined on SMP systems
+#endif
+
+#if (GATOR_PERF_SUPPORT) && (!(GATOR_PERF_PMU_SUPPORT))
+#ifndef CONFIG_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_PERF_EVENTS defined to support pmu hardware counters
+#elif !defined CONFIG_HW_PERF_EVENTS
+#error gator requires the kernel to have CONFIG_HW_PERF_EVENTS defined to support pmu hardware counters
+#endif
+#endif
+
+/******************************************************************************
+ * DEFINES
+ ******************************************************************************/
+#define SUMMARY_BUFFER_SIZE (1*1024)
+#define BACKTRACE_BUFFER_SIZE (128*1024)
+#define NAME_BUFFER_SIZE (64*1024)
+#define COUNTER_BUFFER_SIZE (64*1024) /* counters have the core as part of the data and the core value in the frame header may be discarded */
+#define BLOCK_COUNTER_BUFFER_SIZE (128*1024)
+#define ANNOTATE_BUFFER_SIZE (128*1024) /* annotate counters have the core as part of the data and the core value in the frame header may be discarded */
+#define SCHED_TRACE_BUFFER_SIZE (128*1024)
+#define IDLE_BUFFER_SIZE (32*1024) /* idle counters have the core as part of the data and the core value in the frame header may be discarded */
+#define ACTIVITY_BUFFER_SIZE (128*1024)
+
+#define NO_COOKIE 0U
+#define UNRESOLVED_COOKIE ~0U
+
+#define FRAME_SUMMARY 1
+#define FRAME_BACKTRACE 2
+#define FRAME_NAME 3
+#define FRAME_COUNTER 4
+#define FRAME_BLOCK_COUNTER 5
+#define FRAME_ANNOTATE 6
+#define FRAME_SCHED_TRACE 7
+#define FRAME_IDLE 9
+#define FRAME_ACTIVITY 13
+
+#define MESSAGE_END_BACKTRACE 1
+
+/* Name Frame Messages */
+#define MESSAGE_COOKIE 1
+#define MESSAGE_THREAD_NAME 2
+
+/* Scheduler Trace Frame Messages */
+#define MESSAGE_SCHED_SWITCH 1
+#define MESSAGE_SCHED_EXIT 2
+
+/* Summary Frame Messages */
+#define MESSAGE_SUMMARY 1
+#define MESSAGE_CORE_NAME 3
+
+/* Activity Frame Messages */
+#define MESSAGE_LINK 1
+#define MESSAGE_SWITCH 2
+#define MESSAGE_EXIT 3
+
+#define MAXSIZE_PACK32 5
+#define MAXSIZE_PACK64 10
+
+#define FRAME_HEADER_SIZE 3
+
+#if defined(__arm__)
+#define PC_REG regs->ARM_pc
+#elif defined(__aarch64__)
+#define PC_REG regs->pc
+#else
+#define PC_REG regs->ip
+#endif
+
+enum {
+ SUMMARY_BUF,
+ BACKTRACE_BUF,
+ NAME_BUF,
+ COUNTER_BUF,
+ BLOCK_COUNTER_BUF,
+ ANNOTATE_BUF,
+ SCHED_TRACE_BUF,
+ IDLE_BUF,
+ ACTIVITY_BUF,
+ NUM_GATOR_BUFS
+};
+
+/******************************************************************************
+ * Globals
+ ******************************************************************************/
+static unsigned long gator_cpu_cores;
+/* Size of the largest buffer. Effectively constant, set in gator_op_create_files */
+static unsigned long userspace_buffer_size;
+static unsigned long gator_backtrace_depth;
+/* How often to commit the buffers for live in nanoseconds */
+static u64 gator_live_rate;
+
+static unsigned long gator_started;
+static u64 gator_monotonic_started;
+static u64 gator_sync_time;
+static u64 gator_hibernate_time;
+static unsigned long gator_buffer_opened;
+static unsigned long gator_timer_count;
+static unsigned long gator_response_type;
+static DEFINE_MUTEX(start_mutex);
+static DEFINE_MUTEX(gator_buffer_mutex);
+
+bool event_based_sampling;
+
+static DECLARE_WAIT_QUEUE_HEAD(gator_buffer_wait);
+static DECLARE_WAIT_QUEUE_HEAD(gator_annotate_wait);
+static struct timer_list gator_buffer_wake_up_timer;
+static bool gator_buffer_wake_run;
+/* Initialize semaphore unlocked to initialize memory values */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 36)
+static DECLARE_MUTEX(gator_buffer_wake_sem);
+#else
+static DEFINE_SEMAPHORE(gator_buffer_wake_sem);
+#endif
+static struct task_struct *gator_buffer_wake_thread;
+static LIST_HEAD(gator_events);
+
+static DEFINE_PER_CPU(u64, last_timestamp);
+
+static bool printed_monotonic_warning;
+
+static u32 gator_cpuids[NR_CPUS];
+static bool sent_core_name[NR_CPUS];
+
+static DEFINE_PER_CPU(bool, in_scheduler_context);
+
+/******************************************************************************
+ * Prototypes
+ ******************************************************************************/
+static u64 gator_get_time(void);
+static void gator_emit_perf_time(u64 time);
+static void gator_op_create_files(struct super_block *sb, struct dentry *root);
+
+/* gator_buffer is protected by being per_cpu and by having IRQs
+ * disabled when writing to it. Most marshal_* calls take care of this
+ * except for marshal_cookie*, marshal_backtrace* and marshal_frame
+ * where the caller is responsible for doing so. No synchronization is
+ * needed with the backtrace buffer as it is per cpu and is only used
+ * from the hrtimer. The annotate_lock must be held when using the
+ * annotation buffer as it is not per cpu. collect_counters which is
+ * the sole writer to the block counter frame is additionally
+ * protected by the per cpu collecting flag.
+ */
+
+/* Size of the buffer, must be a power of 2. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_size[NUM_GATOR_BUFS];
+/* gator_buffer_size - 1, bitwise and with pos to get offset into the array. Effectively constant, set in gator_op_setup. */
+static uint32_t gator_buffer_mask[NUM_GATOR_BUFS];
+/* Read position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are read by userspace in userspace_buffer_read */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_read);
+/* Write position in the buffer. Initialized to zero in gator_op_setup and incremented after bytes are written to the buffer */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_write);
+/* Commit position in the buffer. Initialized to zero in gator_op_setup and incremented after a frame is ready to be read by userspace */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], gator_buffer_commit);
+/* If set to false, decreases the number of bytes returned by
+ * buffer_bytes_available. Set in buffer_check_space if no space is
+ * remaining. Initialized to true in gator_op_setup. This means that
+ * if we run out of space, continue to report that no space is
+ * available until bytes are read by userspace
+ */
+static DEFINE_PER_CPU(int[NUM_GATOR_BUFS], buffer_space_available);
+/* The buffer. Allocated in gator_op_setup */
+static DEFINE_PER_CPU(char *[NUM_GATOR_BUFS], gator_buffer);
+/* The time after which the buffer should be committed for live display */
+static DEFINE_PER_CPU(u64, gator_buffer_commit_time);
+
+/* List of all gator events - new events must be added to this list */
+#define GATOR_EVENTS_LIST \
+ GATOR_EVENT(gator_events_armv6_init) \
+ GATOR_EVENT(gator_events_armv7_init) \
+ GATOR_EVENT(gator_events_block_init) \
+ GATOR_EVENT(gator_events_ccn504_init) \
+ GATOR_EVENT(gator_events_irq_init) \
+ GATOR_EVENT(gator_events_l2c310_init) \
+ GATOR_EVENT(gator_events_mali_init) \
+ GATOR_EVENT(gator_events_mali_midgard_hw_init) \
+ GATOR_EVENT(gator_events_mali_midgard_init) \
+ GATOR_EVENT(gator_events_meminfo_init) \
+ GATOR_EVENT(gator_events_mmapped_init) \
+ GATOR_EVENT(gator_events_net_init) \
+ GATOR_EVENT(gator_events_perf_pmu_init) \
+ GATOR_EVENT(gator_events_sched_init) \
+ GATOR_EVENT(gator_events_scorpion_init) \
+
+#define GATOR_EVENT(EVENT_INIT) __weak int EVENT_INIT(void);
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+
+static int (*gator_events_list[])(void) = {
+#define GATOR_EVENT(EVENT_INIT) EVENT_INIT,
+GATOR_EVENTS_LIST
+#undef GATOR_EVENT
+};
+
+/******************************************************************************
+ * Application Includes
+ ******************************************************************************/
+#include "gator_fs.c"
+#include "gator_buffer_write.c"
+#include "gator_buffer.c"
+#include "gator_marshaling.c"
+#include "gator_hrtimer_gator.c"
+#include "gator_cookies.c"
+#include "gator_annotate.c"
+#include "gator_trace_sched.c"
+#include "gator_trace_power.c"
+#include "gator_trace_gpu.c"
+#include "gator_backtrace.c"
+
+/******************************************************************************
+ * Misc
+ ******************************************************************************/
+
+MODULE_PARM_DESC(gator_src_md5, "Gator driver source code md5sum");
+module_param_named(src_md5, gator_src_md5, charp, 0444);
+
+static const struct gator_cpu gator_cpus[] = {
+ {
+ .cpuid = ARM1136,
+ .core_name = "ARM1136",
+ .pmnc_name = "ARM_ARM11",
+ .dt_name = "arm,arm1136",
+ .pmnc_counters = 3,
+ },
+ {
+ .cpuid = ARM1156,
+ .core_name = "ARM1156",
+ .pmnc_name = "ARM_ARM11",
+ .dt_name = "arm,arm1156",
+ .pmnc_counters = 3,
+ },
+ {
+ .cpuid = ARM1176,
+ .core_name = "ARM1176",
+ .pmnc_name = "ARM_ARM11",
+ .dt_name = "arm,arm1176",
+ .pmnc_counters = 3,
+ },
+ {
+ .cpuid = ARM11MPCORE,
+ .core_name = "ARM11MPCore",
+ .pmnc_name = "ARM_ARM11MPCore",
+ .dt_name = "arm,arm11mpcore",
+ .pmnc_counters = 3,
+ },
+ {
+ .cpuid = CORTEX_A5,
+ .core_name = "Cortex-A5",
+ .pmnc_name = "ARMv7_Cortex_A5",
+ .dt_name = "arm,cortex-a5",
+ .pmnc_counters = 2,
+ },
+ {
+ .cpuid = CORTEX_A7,
+ .core_name = "Cortex-A7",
+ .pmnc_name = "ARMv7_Cortex_A7",
+ .dt_name = "arm,cortex-a7",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = CORTEX_A8,
+ .core_name = "Cortex-A8",
+ .pmnc_name = "ARMv7_Cortex_A8",
+ .dt_name = "arm,cortex-a8",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = CORTEX_A9,
+ .core_name = "Cortex-A9",
+ .pmnc_name = "ARMv7_Cortex_A9",
+ .dt_name = "arm,cortex-a9",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = CORTEX_A15,
+ .core_name = "Cortex-A15",
+ .pmnc_name = "ARMv7_Cortex_A15",
+ .dt_name = "arm,cortex-a15",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = CORTEX_A12,
+ .core_name = "Cortex-A17",
+ .pmnc_name = "ARMv7_Cortex_A17",
+ .dt_name = "arm,cortex-a17",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = CORTEX_A17,
+ .core_name = "Cortex-A17",
+ .pmnc_name = "ARMv7_Cortex_A17",
+ .dt_name = "arm,cortex-a17",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = SCORPION,
+ .core_name = "Scorpion",
+ .pmnc_name = "Scorpion",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = SCORPIONMP,
+ .core_name = "ScorpionMP",
+ .pmnc_name = "ScorpionMP",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = KRAITSIM,
+ .core_name = "KraitSIM",
+ .pmnc_name = "Krait",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = KRAIT,
+ .core_name = "Krait",
+ .pmnc_name = "Krait",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = KRAIT_S4_PRO,
+ .core_name = "Krait S4 Pro",
+ .pmnc_name = "Krait",
+ .pmnc_counters = 4,
+ },
+ {
+ .cpuid = CORTEX_A53,
+ .core_name = "Cortex-A53",
+ .pmnc_name = "ARM_Cortex-A53",
+ .dt_name = "arm,cortex-a53",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = CORTEX_A57,
+ .core_name = "Cortex-A57",
+ .pmnc_name = "ARM_Cortex-A57",
+ .dt_name = "arm,cortex-a57",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = CORTEX_A72,
+ .core_name = "Cortex-A72",
+ .pmnc_name = "ARM_Cortex-A72",
+ .dt_name = "arm,cortex-a72",
+ .pmnc_counters = 6,
+ },
+ {
+ .cpuid = OTHER,
+ .core_name = "Other",
+ .pmnc_name = "Other",
+ .pmnc_counters = 6,
+ },
+ {}
+};
+
+const struct gator_cpu *gator_find_cpu_by_cpuid(const u32 cpuid)
+{
+ int i;
+
+ for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+ const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+ if (gator_cpu->cpuid == cpuid)
+ return gator_cpu;
+ }
+
+ return NULL;
+}
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+const struct gator_cpu *gator_find_cpu_by_pmu_name(const char *const name)
+{
+ int i;
+
+ for (i = 0; gator_cpus[i].cpuid != 0; ++i) {
+ const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+ if (gator_cpu->pmnc_name != NULL &&
+ /* Do the names match exactly? */
+ (strcasecmp(gator_cpu->pmnc_name, name) == 0 ||
+ /* Do these names match but have the old vs new prefix? */
+ ((strncasecmp(name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) == 0 &&
+ strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) == 0 &&
+ strcasecmp(name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) == 0))))
+ return gator_cpu;
+ }
+
+ return NULL;
+}
+
+u32 gator_cpuid(void)
+{
+#if defined(__arm__) || defined(__aarch64__)
+ u32 val;
+#if !defined(__aarch64__)
+ asm volatile("mrc p15, 0, %0, c0, c0, 0" : "=r" (val));
+#else
+ asm volatile("mrs %0, midr_el1" : "=r" (val));
+#endif
+ return ((val & 0xff000000) >> 12) | ((val & 0xfff0) >> 4);
+#else
+ return OTHER;
+#endif
+}
+
+static void gator_buffer_wake_up(unsigned long data)
+{
+ wake_up(&gator_buffer_wait);
+}
+
+static int gator_buffer_wake_func(void *data)
+{
+ for (;;) {
+ if (down_killable(&gator_buffer_wake_sem))
+ break;
+
+ /* Eat up any pending events */
+ while (!down_trylock(&gator_buffer_wake_sem))
+ ;
+
+ if (!gator_buffer_wake_run)
+ break;
+
+ gator_buffer_wake_up(0);
+ }
+
+ return 0;
+}
+
+/******************************************************************************
+ * Commit interface
+ ******************************************************************************/
+static bool buffer_commit_ready(int *cpu, int *buftype)
+{
+ int cpu_x, x;
+
+ for_each_present_cpu(cpu_x) {
+ for (x = 0; x < NUM_GATOR_BUFS; x++)
+ if (per_cpu(gator_buffer_commit, cpu_x)[x] != per_cpu(gator_buffer_read, cpu_x)[x]) {
+ *cpu = cpu_x;
+ *buftype = x;
+ return true;
+ }
+ }
+ *cpu = -1;
+ *buftype = -1;
+ return false;
+}
+
+/******************************************************************************
+ * hrtimer interrupt processing
+ ******************************************************************************/
+static void gator_timer_interrupt(void)
+{
+ struct pt_regs *const regs = get_irq_regs();
+
+ gator_backtrace_handler(regs);
+}
+
+void gator_backtrace_handler(struct pt_regs *const regs)
+{
+ u64 time = gator_get_time();
+ int cpu = get_physical_cpu();
+
+ /* Output backtrace */
+ gator_add_sample(cpu, regs, time);
+
+ /* Collect counters */
+ if (!per_cpu(collecting, cpu))
+ collect_counters(time, current, false);
+
+ /* No buffer flushing occurs during sched switch for RT-Preempt full. The block counter frame will be flushed by collect_counters, but the sched buffer needs to be explicitly flushed */
+#ifdef CONFIG_PREEMPT_RT_FULL
+ buffer_check(cpu, SCHED_TRACE_BUF, time);
+#endif
+}
+
+static int gator_running;
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_offline(void *migrate)
+{
+ struct gator_interface *gi;
+ int i, len, cpu = get_physical_cpu();
+ int *buffer;
+ u64 time;
+
+ gator_trace_sched_offline();
+ gator_trace_power_offline();
+
+ if (!migrate)
+ gator_hrtimer_offline();
+
+ /* Offline any events and output counters */
+ time = gator_get_time();
+ if (marshal_event_header(time)) {
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->offline) {
+ len = gi->offline(&buffer, migrate);
+ marshal_event(len, buffer);
+ }
+ }
+ /* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+ buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+ }
+
+ /* Flush all buffers on this core */
+ for (i = 0; i < NUM_GATOR_BUFS; i++)
+ gator_commit_buffer(cpu, i, time);
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_offline_dispatch(int cpu, bool migrate)
+{
+ struct gator_interface *gi;
+
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->offline_dispatch)
+ gi->offline_dispatch(cpu, migrate);
+ }
+}
+
+static void gator_timer_stop(void)
+{
+ int cpu;
+
+ if (gator_running) {
+ on_each_cpu(gator_timer_offline, NULL, 1);
+ for_each_online_cpu(cpu) {
+ gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+ }
+
+ gator_running = 0;
+ gator_hrtimer_shutdown();
+ }
+}
+
+static void gator_send_core_name(const int cpu, const u32 cpuid)
+{
+#if defined(__arm__) || defined(__aarch64__)
+ if (!sent_core_name[cpu] || (cpuid != gator_cpuids[cpu])) {
+ const struct gator_cpu *const gator_cpu = gator_find_cpu_by_cpuid(cpuid);
+ const char *core_name = NULL;
+ char core_name_buf[32];
+
+ /* Save off this cpuid */
+ gator_cpuids[cpu] = cpuid;
+ if (gator_cpu != NULL) {
+ core_name = gator_cpu->core_name;
+ } else {
+ if (cpuid == -1)
+ snprintf(core_name_buf, sizeof(core_name_buf), "Unknown");
+ else
+ snprintf(core_name_buf, sizeof(core_name_buf), "Unknown (0x%.5x)", cpuid);
+ core_name = core_name_buf;
+ }
+
+ marshal_core_name(cpu, cpuid, core_name);
+ sent_core_name[cpu] = true;
+ }
+#endif
+}
+
+static void gator_read_cpuid(void *arg)
+{
+ gator_cpuids[get_physical_cpu()] = gator_cpuid();
+}
+
+/* This function runs in interrupt context and on the appropriate core */
+static void gator_timer_online(void *migrate)
+{
+ struct gator_interface *gi;
+ int len, cpu = get_physical_cpu();
+ int *buffer;
+ u64 time;
+
+ /* Send what is currently running on this core */
+ marshal_sched_trace_switch(current->pid, 0);
+
+ gator_trace_power_online();
+
+ /* online any events and output counters */
+ time = gator_get_time();
+ if (marshal_event_header(time)) {
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->online) {
+ len = gi->online(&buffer, migrate);
+ marshal_event(len, buffer);
+ }
+ }
+ /* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+ buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+ }
+
+ if (!migrate)
+ gator_hrtimer_online();
+
+ gator_send_core_name(cpu, gator_cpuid());
+}
+
+/* This function runs in interrupt context and may be running on a core other than core 'cpu' */
+static void gator_timer_online_dispatch(int cpu, bool migrate)
+{
+ struct gator_interface *gi;
+
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->online_dispatch)
+ gi->online_dispatch(cpu, migrate);
+ }
+}
+
+#include "gator_iks.c"
+
+static int gator_timer_start(unsigned long sample_rate)
+{
+ int cpu;
+
+ if (gator_running) {
+ pr_notice("gator: already running\n");
+ return 0;
+ }
+
+ gator_running = 1;
+
+ /* event based sampling trumps hr timer based sampling */
+ if (event_based_sampling)
+ sample_rate = 0;
+
+ if (gator_hrtimer_init(sample_rate, gator_timer_interrupt) == -1)
+ return -1;
+
+ /* Send off the previously saved cpuids */
+ for_each_present_cpu(cpu) {
+ preempt_disable();
+ gator_send_core_name(cpu, gator_cpuids[cpu]);
+ preempt_enable();
+ }
+
+ gator_send_iks_core_names();
+ for_each_online_cpu(cpu) {
+ gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+ }
+ on_each_cpu(gator_timer_online, NULL, 1);
+
+ return 0;
+}
+
+static u64 gator_get_time(void)
+{
+ struct timespec ts;
+ u64 timestamp;
+ u64 prev_timestamp;
+ u64 delta;
+ int cpu = smp_processor_id();
+
+ /* Match clock_gettime(CLOCK_MONOTONIC_RAW, &ts) from userspace */
+ getrawmonotonic(&ts);
+ timestamp = timespec_to_ns(&ts);
+
+ /* getrawmonotonic is not monotonic on all systems. Detect and
+ * attempt to correct these cases. up to 0.5ms delta has been seen
+ * on some systems, which can skew Streamline data when viewing at
+ * high resolution. This doesn't work well with interrupts, but that
+ * it's OK - the real concern is to catch big jumps in time
+ */
+ prev_timestamp = per_cpu(last_timestamp, cpu);
+ if (prev_timestamp <= timestamp) {
+ per_cpu(last_timestamp, cpu) = timestamp;
+ } else {
+ delta = prev_timestamp - timestamp;
+ /* Log the error once */
+ if (!printed_monotonic_warning && delta > 500000) {
+ pr_err("%s: getrawmonotonic is not monotonic cpu: %i delta: %lli\nSkew in Streamline data may be present at the fine zoom levels\n", __func__, cpu, delta);
+ printed_monotonic_warning = true;
+ }
+ timestamp = prev_timestamp;
+ }
+
+ return timestamp - gator_monotonic_started;
+}
+
+static void gator_emit_perf_time(u64 time)
+{
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 10, 0)
+ if (time >= gator_sync_time) {
+ marshal_event_single64(0, -1, local_clock());
+ gator_sync_time += NSEC_PER_SEC;
+ if (gator_live_rate <= 0) {
+ gator_commit_buffer(get_physical_cpu(), COUNTER_BUF, time);
+ }
+ }
+#endif
+}
+
+/******************************************************************************
+ * cpu hotplug and pm notifiers
+ ******************************************************************************/
+static int __cpuinit gator_hotcpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+ int cpu = lcpu_to_pcpu((long)hcpu);
+
+ switch (action) {
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ smp_call_function_single(cpu, gator_timer_offline, NULL, 1);
+ gator_timer_offline_dispatch(cpu, false);
+ break;
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ gator_timer_online_dispatch(cpu, false);
+ smp_call_function_single(cpu, gator_timer_online, NULL, 1);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata gator_hotcpu_notifier = {
+ .notifier_call = gator_hotcpu_notify,
+};
+
+/* n.b. calling "on_each_cpu" only runs on those that are online.
+ * Registered linux events are not disabled, so their counters will
+ * continue to collect
+ */
+static int gator_pm_notify(struct notifier_block *nb, unsigned long event, void *dummy)
+{
+ int cpu;
+ struct timespec ts;
+
+ switch (event) {
+ case PM_HIBERNATION_PREPARE:
+ case PM_SUSPEND_PREPARE:
+ unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+ unregister_scheduler_tracepoints();
+ on_each_cpu(gator_timer_offline, NULL, 1);
+ for_each_online_cpu(cpu) {
+ gator_timer_offline_dispatch(lcpu_to_pcpu(cpu), false);
+ }
+
+ /* Record the wallclock hibernate time */
+ getnstimeofday(&ts);
+ gator_hibernate_time = timespec_to_ns(&ts) - gator_get_time();
+ break;
+ case PM_POST_HIBERNATION:
+ case PM_POST_SUSPEND:
+ /* Adjust gator_monotonic_started for the time spent sleeping, as gator_get_time does not account for it */
+ if (gator_hibernate_time > 0) {
+ getnstimeofday(&ts);
+ gator_monotonic_started += gator_hibernate_time + gator_get_time() - timespec_to_ns(&ts);
+ gator_hibernate_time = 0;
+ }
+
+ for_each_online_cpu(cpu) {
+ gator_timer_online_dispatch(lcpu_to_pcpu(cpu), false);
+ }
+ on_each_cpu(gator_timer_online, NULL, 1);
+ register_scheduler_tracepoints();
+ register_hotcpu_notifier(&gator_hotcpu_notifier);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block gator_pm_notifier = {
+ .notifier_call = gator_pm_notify,
+};
+
+static int gator_notifier_start(void)
+{
+ int retval;
+
+ retval = register_hotcpu_notifier(&gator_hotcpu_notifier);
+ if (retval == 0)
+ retval = register_pm_notifier(&gator_pm_notifier);
+ return retval;
+}
+
+static void gator_notifier_stop(void)
+{
+ unregister_pm_notifier(&gator_pm_notifier);
+ unregister_hotcpu_notifier(&gator_hotcpu_notifier);
+}
+
+/******************************************************************************
+ * Main
+ ******************************************************************************/
+static void gator_summary(void)
+{
+ u64 timestamp, uptime;
+ struct timespec ts;
+ char uname_buf[512];
+
+ snprintf(uname_buf, sizeof(uname_buf), "%s %s %s %s %s GNU/Linux", utsname()->sysname, utsname()->nodename, utsname()->release, utsname()->version, utsname()->machine);
+
+ getnstimeofday(&ts);
+ timestamp = timespec_to_ns(&ts);
+
+ /* Similar to reading /proc/uptime from fs/proc/uptime.c, calculate uptime */
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 11, 0)
+ {
+ void (*m2b)(struct timespec *ts);
+
+ do_posix_clock_monotonic_gettime(&ts);
+ /* monotonic_to_bootbased is not defined for some versions of Android */
+ m2b = symbol_get(monotonic_to_bootbased);
+ if (m2b)
+ m2b(&ts);
+ }
+#else
+ get_monotonic_boottime(&ts);
+#endif
+ uptime = timespec_to_ns(&ts);
+
+ /* Disable preemption as gator_get_time calls smp_processor_id to verify time is monotonic */
+ preempt_disable();
+ /* Set monotonic_started to zero as gator_get_time is uptime minus monotonic_started */
+ gator_monotonic_started = 0;
+ gator_monotonic_started = gator_get_time();
+
+ marshal_summary(timestamp, uptime, gator_monotonic_started, uname_buf);
+ gator_sync_time = 0;
+ gator_emit_perf_time(gator_monotonic_started);
+ /* Always flush COUNTER_BUF so that the initial perf_time is received before it's used */
+ gator_commit_buffer(get_physical_cpu(), COUNTER_BUF, 0);
+ preempt_enable();
+}
+
+int gator_events_install(struct gator_interface *interface)
+{
+ list_add_tail(&interface->list, &gator_events);
+
+ return 0;
+}
+
+int gator_events_get_key(void)
+{
+ /* key 0 is reserved as a timestamp. key 1 is reserved as the marker
+ * for thread specific counters. key 2 is reserved as the marker for
+ * core. Odd keys are assigned by the driver, even keys by the
+ * daemon.
+ */
+ static int key = 3;
+ const int ret = key;
+
+ key += 2;
+ return ret;
+}
+
+static int gator_init(void)
+{
+ int i;
+
+ calc_first_cluster_size();
+
+ /* events sources */
+ for (i = 0; i < ARRAY_SIZE(gator_events_list); i++)
+ if (gator_events_list[i])
+ gator_events_list[i]();
+
+ gator_trace_sched_init();
+ gator_trace_power_init();
+
+ return 0;
+}
+
+static void gator_exit(void)
+{
+ struct gator_interface *gi;
+
+ list_for_each_entry(gi, &gator_events, list)
+ if (gi->shutdown)
+ gi->shutdown();
+}
+
+static int gator_start(void)
+{
+ unsigned long cpu, i;
+ struct gator_interface *gi;
+
+ gator_buffer_wake_run = true;
+ gator_buffer_wake_thread = kthread_run(gator_buffer_wake_func, NULL, "gator_bwake");
+ if (IS_ERR(gator_buffer_wake_thread))
+ goto bwake_failure;
+
+ if (gator_migrate_start())
+ goto migrate_failure;
+
+ /* Initialize the buffer with the frame type and core */
+ for_each_present_cpu(cpu) {
+ for (i = 0; i < NUM_GATOR_BUFS; i++)
+ marshal_frame(cpu, i);
+ per_cpu(last_timestamp, cpu) = 0;
+ }
+ printed_monotonic_warning = false;
+
+ /* Capture the start time */
+ gator_summary();
+
+ /* start all events */
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->start && gi->start() != 0) {
+ struct list_head *ptr = gi->list.prev;
+
+ while (ptr != &gator_events) {
+ gi = list_entry(ptr, struct gator_interface, list);
+
+ if (gi->stop)
+ gi->stop();
+
+ ptr = ptr->prev;
+ }
+ goto events_failure;
+ }
+ }
+
+ /* cookies shall be initialized before trace_sched_start() and gator_timer_start() */
+ if (cookies_initialize())
+ goto cookies_failure;
+ if (gator_annotate_start())
+ goto annotate_failure;
+ if (gator_trace_sched_start())
+ goto sched_failure;
+ if (gator_trace_power_start())
+ goto power_failure;
+ if (gator_trace_gpu_start())
+ goto gpu_failure;
+ if (gator_timer_start(gator_timer_count))
+ goto timer_failure;
+ if (gator_notifier_start())
+ goto notifier_failure;
+
+ return 0;
+
+notifier_failure:
+ gator_timer_stop();
+timer_failure:
+ gator_trace_gpu_stop();
+gpu_failure:
+ gator_trace_power_stop();
+power_failure:
+ gator_trace_sched_stop();
+sched_failure:
+ gator_annotate_stop();
+annotate_failure:
+ cookies_release();
+cookies_failure:
+ /* stop all events */
+ list_for_each_entry(gi, &gator_events, list)
+ if (gi->stop)
+ gi->stop();
+events_failure:
+ gator_migrate_stop();
+migrate_failure:
+ gator_buffer_wake_run = false;
+ up(&gator_buffer_wake_sem);
+ gator_buffer_wake_thread = NULL;
+bwake_failure:
+
+ return -1;
+}
+
+static void gator_stop(void)
+{
+ struct gator_interface *gi;
+
+ gator_annotate_stop();
+ gator_trace_sched_stop();
+ gator_trace_power_stop();
+ gator_trace_gpu_stop();
+
+ /* stop all interrupt callback reads before tearing down other interfaces */
+ gator_notifier_stop(); /* should be called before gator_timer_stop to avoid re-enabling the hrtimer after it has been offlined */
+ gator_timer_stop();
+
+ /* stop all events */
+ list_for_each_entry(gi, &gator_events, list)
+ if (gi->stop)
+ gi->stop();
+
+ gator_migrate_stop();
+
+ gator_buffer_wake_run = false;
+ up(&gator_buffer_wake_sem);
+ gator_buffer_wake_thread = NULL;
+}
+
+/******************************************************************************
+ * Filesystem
+ ******************************************************************************/
+/* fopen("buffer") */
+static int gator_op_setup(void)
+{
+ int err = 0;
+ int cpu, i;
+
+ mutex_lock(&start_mutex);
+
+ gator_buffer_size[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE;
+ gator_buffer_mask[SUMMARY_BUF] = SUMMARY_BUFFER_SIZE - 1;
+
+ gator_buffer_size[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE;
+ gator_buffer_mask[BACKTRACE_BUF] = BACKTRACE_BUFFER_SIZE - 1;
+
+ gator_buffer_size[NAME_BUF] = NAME_BUFFER_SIZE;
+ gator_buffer_mask[NAME_BUF] = NAME_BUFFER_SIZE - 1;
+
+ gator_buffer_size[COUNTER_BUF] = COUNTER_BUFFER_SIZE;
+ gator_buffer_mask[COUNTER_BUF] = COUNTER_BUFFER_SIZE - 1;
+
+ gator_buffer_size[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE;
+ gator_buffer_mask[BLOCK_COUNTER_BUF] = BLOCK_COUNTER_BUFFER_SIZE - 1;
+
+ gator_buffer_size[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE;
+ gator_buffer_mask[ANNOTATE_BUF] = ANNOTATE_BUFFER_SIZE - 1;
+
+ gator_buffer_size[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE;
+ gator_buffer_mask[SCHED_TRACE_BUF] = SCHED_TRACE_BUFFER_SIZE - 1;
+
+ gator_buffer_size[IDLE_BUF] = IDLE_BUFFER_SIZE;
+ gator_buffer_mask[IDLE_BUF] = IDLE_BUFFER_SIZE - 1;
+
+ gator_buffer_size[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE;
+ gator_buffer_mask[ACTIVITY_BUF] = ACTIVITY_BUFFER_SIZE - 1;
+
+ /* Initialize percpu per buffer variables */
+ for (i = 0; i < NUM_GATOR_BUFS; i++) {
+ /* Verify buffers are a power of 2 */
+ if (gator_buffer_size[i] & (gator_buffer_size[i] - 1)) {
+ err = -ENOEXEC;
+ goto setup_error;
+ }
+
+ for_each_present_cpu(cpu) {
+ per_cpu(gator_buffer_read, cpu)[i] = 0;
+ per_cpu(gator_buffer_write, cpu)[i] = 0;
+ per_cpu(gator_buffer_commit, cpu)[i] = 0;
+ per_cpu(buffer_space_available, cpu)[i] = true;
+ per_cpu(gator_buffer_commit_time, cpu) = gator_live_rate;
+
+ /* Annotation is a special case that only uses a single buffer */
+ if (cpu > 0 && i == ANNOTATE_BUF) {
+ per_cpu(gator_buffer, cpu)[i] = NULL;
+ continue;
+ }
+
+ per_cpu(gator_buffer, cpu)[i] = vmalloc(gator_buffer_size[i]);
+ if (!per_cpu(gator_buffer, cpu)[i]) {
+ err = -ENOMEM;
+ goto setup_error;
+ }
+ }
+ }
+
+setup_error:
+ mutex_unlock(&start_mutex);
+ return err;
+}
+
+/* Actually start profiling (echo 1>/dev/gator/enable) */
+static int gator_op_start(void)
+{
+ int err = 0;
+
+ mutex_lock(&start_mutex);
+
+ if (gator_started || gator_start())
+ err = -EINVAL;
+ else
+ gator_started = 1;
+
+ mutex_unlock(&start_mutex);
+
+ return err;
+}
+
+/* echo 0>/dev/gator/enable */
+static void gator_op_stop(void)
+{
+ mutex_lock(&start_mutex);
+
+ if (gator_started) {
+ gator_stop();
+
+ mutex_lock(&gator_buffer_mutex);
+
+ gator_started = 0;
+ gator_monotonic_started = 0;
+ cookies_release();
+ wake_up(&gator_buffer_wait);
+
+ mutex_unlock(&gator_buffer_mutex);
+ }
+
+ mutex_unlock(&start_mutex);
+}
+
+static void gator_shutdown(void)
+{
+ int cpu, i;
+
+ mutex_lock(&start_mutex);
+
+ for_each_present_cpu(cpu) {
+ mutex_lock(&gator_buffer_mutex);
+ for (i = 0; i < NUM_GATOR_BUFS; i++) {
+ vfree(per_cpu(gator_buffer, cpu)[i]);
+ per_cpu(gator_buffer, cpu)[i] = NULL;
+ per_cpu(gator_buffer_read, cpu)[i] = 0;
+ per_cpu(gator_buffer_write, cpu)[i] = 0;
+ per_cpu(gator_buffer_commit, cpu)[i] = 0;
+ per_cpu(buffer_space_available, cpu)[i] = true;
+ per_cpu(gator_buffer_commit_time, cpu) = 0;
+ }
+ mutex_unlock(&gator_buffer_mutex);
+ }
+
+ memset(&sent_core_name, 0, sizeof(sent_core_name));
+
+ mutex_unlock(&start_mutex);
+}
+
+static int gator_set_backtrace(unsigned long val)
+{
+ int err = 0;
+
+ mutex_lock(&start_mutex);
+
+ if (gator_started)
+ err = -EBUSY;
+ else
+ gator_backtrace_depth = val;
+
+ mutex_unlock(&start_mutex);
+
+ return err;
+}
+
+static ssize_t enable_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ return gatorfs_ulong_to_user(gator_started, buf, count, offset);
+}
+
+static ssize_t enable_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = gatorfs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ if (val)
+ retval = gator_op_start();
+ else
+ gator_op_stop();
+
+ if (retval)
+ return retval;
+ return count;
+}
+
+static const struct file_operations enable_fops = {
+ .read = enable_read,
+ .write = enable_write,
+};
+
+static int userspace_buffer_open(struct inode *inode, struct file *file)
+{
+ int err = -EPERM;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (test_and_set_bit_lock(0, &gator_buffer_opened))
+ return -EBUSY;
+
+ err = gator_op_setup();
+ if (err)
+ goto fail;
+
+ /* NB: the actual start happens from userspace
+ * echo 1 >/dev/gator/enable
+ */
+
+ return 0;
+
+fail:
+ __clear_bit_unlock(0, &gator_buffer_opened);
+ return err;
+}
+
+static int userspace_buffer_release(struct inode *inode, struct file *file)
+{
+ gator_op_stop();
+ gator_shutdown();
+ __clear_bit_unlock(0, &gator_buffer_opened);
+ return 0;
+}
+
+static ssize_t userspace_buffer_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ int commit, length1, length2, read;
+ char *buffer1;
+ char *buffer2;
+ int cpu, buftype;
+ int written = 0;
+
+ /* ensure there is enough space for a whole frame */
+ if (count < userspace_buffer_size || *offset)
+ return -EINVAL;
+
+ /* sleep until the condition is true or a signal is received the
+ * condition is checked each time gator_buffer_wait is woken up
+ */
+ wait_event_interruptible(gator_buffer_wait, buffer_commit_ready(&cpu, &buftype) || !gator_started);
+
+ if (signal_pending(current))
+ return -EINTR;
+
+ if (buftype == -1 || cpu == -1)
+ return 0;
+
+ mutex_lock(&gator_buffer_mutex);
+
+ do {
+ read = per_cpu(gator_buffer_read, cpu)[buftype];
+ commit = per_cpu(gator_buffer_commit, cpu)[buftype];
+
+ /* May happen if the buffer is freed during pending reads. */
+ if (!per_cpu(gator_buffer, cpu)[buftype])
+ break;
+
+ /* determine the size of two halves */
+ length1 = commit - read;
+ length2 = 0;
+ buffer1 = &(per_cpu(gator_buffer, cpu)[buftype][read]);
+ buffer2 = &(per_cpu(gator_buffer, cpu)[buftype][0]);
+ if (length1 < 0) {
+ length1 = gator_buffer_size[buftype] - read;
+ length2 = commit;
+ }
+
+ if (length1 + length2 > count - written)
+ break;
+
+ /* start, middle or end */
+ if (length1 > 0 && copy_to_user(&buf[written], buffer1, length1))
+ break;
+
+ /* possible wrap around */
+ if (length2 > 0 && copy_to_user(&buf[written + length1], buffer2, length2))
+ break;
+
+ per_cpu(gator_buffer_read, cpu)[buftype] = commit;
+ written += length1 + length2;
+
+ /* Wake up annotate_write if more space is available */
+ if (buftype == ANNOTATE_BUF)
+ wake_up(&gator_annotate_wait);
+ } while (buffer_commit_ready(&cpu, &buftype));
+
+ mutex_unlock(&gator_buffer_mutex);
+
+ /* kick just in case we've lost an SMP event */
+ wake_up(&gator_buffer_wait);
+
+ return written > 0 ? written : -EFAULT;
+}
+
+static const struct file_operations gator_event_buffer_fops = {
+ .open = userspace_buffer_open,
+ .release = userspace_buffer_release,
+ .read = userspace_buffer_read,
+};
+
+static ssize_t depth_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
+{
+ return gatorfs_ulong_to_user(gator_backtrace_depth, buf, count, offset);
+}
+
+static ssize_t depth_write(struct file *file, char const __user *buf, size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = gatorfs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ retval = gator_set_backtrace(val);
+
+ if (retval)
+ return retval;
+ return count;
+}
+
+static const struct file_operations depth_fops = {
+ .read = depth_read,
+ .write = depth_write
+};
+
+static void gator_op_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ struct gator_interface *gi;
+ int cpu;
+
+ /* reinitialize default values */
+ gator_cpu_cores = 0;
+ for_each_present_cpu(cpu) {
+ gator_cpu_cores++;
+ }
+ userspace_buffer_size = BACKTRACE_BUFFER_SIZE;
+ gator_response_type = 1;
+ gator_live_rate = 0;
+
+ gatorfs_create_file(sb, root, "enable", &enable_fops);
+ gatorfs_create_file(sb, root, "buffer", &gator_event_buffer_fops);
+ gatorfs_create_file(sb, root, "backtrace_depth", &depth_fops);
+ gatorfs_create_ro_ulong(sb, root, "cpu_cores", &gator_cpu_cores);
+ gatorfs_create_ro_ulong(sb, root, "buffer_size", &userspace_buffer_size);
+ gatorfs_create_ulong(sb, root, "tick", &gator_timer_count);
+ gatorfs_create_ulong(sb, root, "response_type", &gator_response_type);
+ gatorfs_create_ro_ulong(sb, root, "version", &gator_protocol_version);
+ gatorfs_create_ro_u64(sb, root, "started", &gator_monotonic_started);
+ gatorfs_create_u64(sb, root, "live_rate", &gator_live_rate);
+
+ /* Annotate interface */
+ gator_annotate_create_files(sb, root);
+
+ /* Linux Events */
+ dir = gatorfs_mkdir(sb, root, "events");
+ list_for_each_entry(gi, &gator_events, list)
+ if (gi->create_files)
+ gi->create_files(sb, dir);
+
+ /* Sched Events */
+ sched_trace_create_files(sb, dir);
+
+ /* Power interface */
+ gator_trace_power_create_files(sb, dir);
+}
+
+/******************************************************************************
+ * Module
+ ******************************************************************************/
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 15, 0)
+
+#define GATOR_TRACEPOINTS \
+ GATOR_HANDLE_TRACEPOINT(block_rq_complete); \
+ GATOR_HANDLE_TRACEPOINT(cpu_frequency); \
+ GATOR_HANDLE_TRACEPOINT(cpu_idle); \
+ GATOR_HANDLE_TRACEPOINT(cpu_migrate_begin); \
+ GATOR_HANDLE_TRACEPOINT(cpu_migrate_current); \
+ GATOR_HANDLE_TRACEPOINT(cpu_migrate_finish); \
+ GATOR_HANDLE_TRACEPOINT(irq_handler_exit); \
+ GATOR_HANDLE_TRACEPOINT(mali_hw_counter); \
+ GATOR_HANDLE_TRACEPOINT(mali_job_slots_event); \
+ GATOR_HANDLE_TRACEPOINT(mali_mmu_as_in_use); \
+ GATOR_HANDLE_TRACEPOINT(mali_mmu_as_released); \
+ GATOR_HANDLE_TRACEPOINT(mali_page_fault_insert_pages); \
+ GATOR_HANDLE_TRACEPOINT(mali_pm_status); \
+ GATOR_HANDLE_TRACEPOINT(mali_sw_counter); \
+ GATOR_HANDLE_TRACEPOINT(mali_sw_counters); \
+ GATOR_HANDLE_TRACEPOINT(mali_timeline_event); \
+ GATOR_HANDLE_TRACEPOINT(mali_total_alloc_pages_change); \
+ GATOR_HANDLE_TRACEPOINT(mm_page_alloc); \
+ GATOR_HANDLE_TRACEPOINT(mm_page_free); \
+ GATOR_HANDLE_TRACEPOINT(mm_page_free_batched); \
+ GATOR_HANDLE_TRACEPOINT(sched_process_exec); \
+ GATOR_HANDLE_TRACEPOINT(sched_process_fork); \
+ GATOR_HANDLE_TRACEPOINT(sched_process_free); \
+ GATOR_HANDLE_TRACEPOINT(sched_switch); \
+ GATOR_HANDLE_TRACEPOINT(softirq_exit); \
+ GATOR_HANDLE_TRACEPOINT(task_rename); \
+
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+ struct tracepoint *gator_tracepoint_##probe_name
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+
+static void gator_save_tracepoint(struct tracepoint *tp, void *priv)
+{
+#define GATOR_HANDLE_TRACEPOINT(probe_name) \
+ do { \
+ if (strcmp(tp->name, #probe_name) == 0) { \
+ gator_tracepoint_##probe_name = tp; \
+ return; \
+ } \
+ } while (0)
+GATOR_TRACEPOINTS;
+#undef GATOR_HANDLE_TRACEPOINT
+}
+
+#else
+
+#define for_each_kernel_tracepoint(fct, priv)
+
+#endif
+
+static int __init gator_module_init(void)
+{
+ for_each_kernel_tracepoint(gator_save_tracepoint, NULL);
+
+ if (gatorfs_register())
+ return -1;
+
+ if (gator_init()) {
+ gatorfs_unregister();
+ return -1;
+ }
+
+ setup_timer(&gator_buffer_wake_up_timer, gator_buffer_wake_up, 0);
+
+ /* Initialize the list of cpuids */
+ memset(gator_cpuids, -1, sizeof(gator_cpuids));
+ on_each_cpu(gator_read_cpuid, NULL, 1);
+
+ return 0;
+}
+
+static void __exit gator_module_exit(void)
+{
+ del_timer_sync(&gator_buffer_wake_up_timer);
+ tracepoint_synchronize_unregister();
+ gator_exit();
+ gatorfs_unregister();
+}
+
+module_init(gator_module_init);
+module_exit(gator_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ARM Ltd");
+MODULE_DESCRIPTION("Gator system profiler");
+#define STRIFY2(ARG) #ARG
+#define STRIFY(ARG) STRIFY2(ARG)
+MODULE_VERSION(STRIFY(PROTOCOL_VERSION));
diff --git a/drivers/gator/gator_marshaling.c b/drivers/gator/gator_marshaling.c
new file mode 100644
index 0000000..f5b8184
--- /dev/null
+++ b/drivers/gator/gator_marshaling.c
@@ -0,0 +1,371 @@
+/**
+ * Copyright (C) ARM Limited 2012-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define NEWLINE_CANARY \
+ /* Unix */ \
+ "1\n" \
+ /* Windows */ \
+ "2\r\n" \
+ /* Mac OS */ \
+ "3\r" \
+ /* RISC OS */ \
+ "4\n\r" \
+ /* Add another character so the length isn't 0x0a bytes */ \
+ "5"
+
+#ifdef MALI_SUPPORT
+#include "gator_events_mali_common.h"
+#endif
+
+static void marshal_summary(long long timestamp, long long uptime, long long monotonic_delta, const char *uname)
+{
+ unsigned long flags;
+ int cpu = 0;
+
+ local_irq_save(flags);
+ gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_SUMMARY);
+ gator_buffer_write_string(cpu, SUMMARY_BUF, NEWLINE_CANARY);
+ gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, timestamp);
+ gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, uptime);
+ gator_buffer_write_packed_int64(cpu, SUMMARY_BUF, monotonic_delta);
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "uname");
+ gator_buffer_write_string(cpu, SUMMARY_BUF, uname);
+#if GATOR_IKS_SUPPORT
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "iks");
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RTB
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rtb");
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "preempt_rt_full");
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+#endif
+ /* Let Streamline know which GPU is used so that it can label the GPU Activity appropriately. This is a temporary fix, to be improved in a future release. */
+#ifdef MALI_SUPPORT
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "mali_type");
+#if (MALI_SUPPORT == MALI_4xx)
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "4xx");
+#elif (MALI_SUPPORT == MALI_MIDGARD)
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "6xx");
+#else
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "unknown");
+#endif
+#endif
+ gator_buffer_write_string(cpu, SUMMARY_BUF, "");
+ /* Commit the buffer now so it can be one of the first frames read by Streamline */
+ local_irq_restore(flags);
+ gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+
+static bool marshal_cookie_header(const char *text)
+{
+ int cpu = get_physical_cpu();
+
+ return buffer_check_space(cpu, NAME_BUF, strlen(text) + 3 * MAXSIZE_PACK32);
+}
+
+static void marshal_cookie(int cookie, const char *text)
+{
+ int cpu = get_physical_cpu();
+ /* buffer_check_space already called by marshal_cookie_header */
+ gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_COOKIE);
+ gator_buffer_write_packed_int(cpu, NAME_BUF, cookie);
+ gator_buffer_write_string(cpu, NAME_BUF, text);
+ buffer_check(cpu, NAME_BUF, gator_get_time());
+}
+
+static void marshal_thread_name(int pid, char *name)
+{
+ unsigned long flags, cpu;
+ u64 time;
+
+ local_irq_save(flags);
+ cpu = get_physical_cpu();
+ time = gator_get_time();
+ if (buffer_check_space(cpu, NAME_BUF, TASK_COMM_LEN + 3 * MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ gator_buffer_write_packed_int(cpu, NAME_BUF, MESSAGE_THREAD_NAME);
+ gator_buffer_write_packed_int64(cpu, NAME_BUF, time);
+ gator_buffer_write_packed_int(cpu, NAME_BUF, pid);
+ gator_buffer_write_string(cpu, NAME_BUF, name);
+ }
+ local_irq_restore(flags);
+ buffer_check(cpu, NAME_BUF, time);
+}
+
+static void marshal_link(int cookie, int tgid, int pid)
+{
+ unsigned long cpu = get_physical_cpu(), flags;
+ u64 time;
+
+ local_irq_save(flags);
+ time = gator_get_time();
+ if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_LINK);
+ gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, cookie);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, tgid);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+static bool marshal_backtrace_header(int exec_cookie, int tgid, int pid, u64 time)
+{
+ int cpu = get_physical_cpu();
+
+ if (!buffer_check_space(cpu, BACKTRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32 + gator_backtrace_depth * 2 * MAXSIZE_PACK32)) {
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, BACKTRACE_BUF, time);
+
+ return false;
+ }
+
+ gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, time);
+ gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, exec_cookie);
+ gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, tgid);
+ gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, pid);
+
+ return true;
+}
+
+static void marshal_backtrace(unsigned long address, int cookie, int in_kernel)
+{
+ int cpu = get_physical_cpu();
+
+ if (cookie == 0 && !in_kernel)
+ cookie = UNRESOLVED_COOKIE;
+ gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, cookie);
+ gator_buffer_write_packed_int64(cpu, BACKTRACE_BUF, address);
+}
+
+static void marshal_backtrace_footer(u64 time)
+{
+ int cpu = get_physical_cpu();
+
+ gator_buffer_write_packed_int(cpu, BACKTRACE_BUF, MESSAGE_END_BACKTRACE);
+
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, BACKTRACE_BUF, time);
+}
+
+static bool marshal_event_header(u64 time)
+{
+ unsigned long flags, cpu = get_physical_cpu();
+ bool retval = false;
+
+ local_irq_save(flags);
+ if (buffer_check_space(cpu, BLOCK_COUNTER_BUF, MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, 0); /* key of zero indicates a timestamp */
+ gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, time);
+ retval = true;
+ }
+ local_irq_restore(flags);
+
+ return retval;
+}
+
+static void marshal_event(int len, int *buffer)
+{
+ unsigned long i, flags, cpu = get_physical_cpu();
+
+ if (len <= 0)
+ return;
+
+ /* length must be even since all data is a (key, value) pair */
+ if (len & 0x1) {
+ pr_err("gator: invalid counter data detected and discarded\n");
+ return;
+ }
+
+ /* events must be written in key,value pairs */
+ local_irq_save(flags);
+ for (i = 0; i < len; i += 2) {
+ if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK32))
+ break;
+ gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i]);
+ gator_buffer_write_packed_int(cpu, BLOCK_COUNTER_BUF, buffer[i + 1]);
+ }
+ local_irq_restore(flags);
+}
+
+static void marshal_event64(int len, long long *buffer64)
+{
+ unsigned long i, flags, cpu = get_physical_cpu();
+
+ if (len <= 0)
+ return;
+
+ /* length must be even since all data is a (key, value) pair */
+ if (len & 0x1) {
+ pr_err("gator: invalid counter data detected and discarded\n");
+ return;
+ }
+
+ /* events must be written in key,value pairs */
+ local_irq_save(flags);
+ for (i = 0; i < len; i += 2) {
+ if (!buffer_check_space(cpu, BLOCK_COUNTER_BUF, 2 * MAXSIZE_PACK64))
+ break;
+ gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i]);
+ gator_buffer_write_packed_int64(cpu, BLOCK_COUNTER_BUF, buffer64[i + 1]);
+ }
+ local_irq_restore(flags);
+}
+
+static void __maybe_unused marshal_event_single(int core, int key, int value)
+{
+ unsigned long flags, cpu;
+ u64 time;
+
+ local_irq_save(flags);
+ cpu = get_physical_cpu();
+ time = gator_get_time();
+ if (buffer_check_space(cpu, COUNTER_BUF, MAXSIZE_PACK64 + 3 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+ gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+ gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+ gator_buffer_write_packed_int(cpu, COUNTER_BUF, value);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void __maybe_unused marshal_event_single64(int core, int key, long long value)
+{
+ unsigned long flags, cpu;
+ u64 time;
+
+ local_irq_save(flags);
+ cpu = get_physical_cpu();
+ time = gator_get_time();
+ if (buffer_check_space(cpu, COUNTER_BUF, 2 * MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int64(cpu, COUNTER_BUF, time);
+ gator_buffer_write_packed_int(cpu, COUNTER_BUF, core);
+ gator_buffer_write_packed_int(cpu, COUNTER_BUF, key);
+ gator_buffer_write_packed_int64(cpu, COUNTER_BUF, value);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, COUNTER_BUF, time);
+}
+
+static void marshal_sched_trace_switch(int pid, int state)
+{
+ unsigned long cpu = get_physical_cpu(), flags;
+ u64 time;
+
+ if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+ return;
+
+ local_irq_save(flags);
+ time = gator_get_time();
+ if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_SWITCH);
+ gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+ gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+ gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, state);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+static void marshal_sched_trace_exit(int tgid, int pid)
+{
+ unsigned long cpu = get_physical_cpu(), flags;
+ u64 time;
+
+ if (!per_cpu(gator_buffer, cpu)[SCHED_TRACE_BUF])
+ return;
+
+ local_irq_save(flags);
+ time = gator_get_time();
+ if (buffer_check_space(cpu, SCHED_TRACE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, MESSAGE_SCHED_EXIT);
+ gator_buffer_write_packed_int64(cpu, SCHED_TRACE_BUF, time);
+ gator_buffer_write_packed_int(cpu, SCHED_TRACE_BUF, pid);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, SCHED_TRACE_BUF, time);
+}
+
+#if GATOR_CPU_FREQ_SUPPORT
+static void marshal_idle(int core, int state)
+{
+ unsigned long flags, cpu;
+ u64 time;
+
+ local_irq_save(flags);
+ cpu = get_physical_cpu();
+ time = gator_get_time();
+ if (buffer_check_space(cpu, IDLE_BUF, MAXSIZE_PACK64 + 2 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int(cpu, IDLE_BUF, state);
+ gator_buffer_write_packed_int64(cpu, IDLE_BUF, time);
+ gator_buffer_write_packed_int(cpu, IDLE_BUF, core);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, IDLE_BUF, time);
+}
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+static void marshal_core_name(const int core, const int cpuid, const char *name)
+{
+ int cpu = get_physical_cpu();
+ unsigned long flags;
+
+ local_irq_save(flags);
+ if (buffer_check_space(cpu, SUMMARY_BUF, MAXSIZE_PACK32 + MAXSIZE_CORE_NAME)) {
+ gator_buffer_write_packed_int(cpu, SUMMARY_BUF, MESSAGE_CORE_NAME);
+ gator_buffer_write_packed_int(cpu, SUMMARY_BUF, core);
+ gator_buffer_write_packed_int(cpu, SUMMARY_BUF, cpuid);
+ gator_buffer_write_string(cpu, SUMMARY_BUF, name);
+ }
+ /* Commit core names now so that they can show up in live */
+ local_irq_restore(flags);
+ gator_commit_buffer(cpu, SUMMARY_BUF, gator_get_time());
+}
+#endif
+
+static void marshal_activity_switch(int core, int key, int activity, int pid, int state)
+{
+ unsigned long cpu = get_physical_cpu(), flags;
+ u64 time;
+
+ if (!per_cpu(gator_buffer, cpu)[ACTIVITY_BUF])
+ return;
+
+ local_irq_save(flags);
+ time = gator_get_time();
+ if (buffer_check_space(cpu, ACTIVITY_BUF, MAXSIZE_PACK64 + 5 * MAXSIZE_PACK32)) {
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, MESSAGE_SWITCH);
+ gator_buffer_write_packed_int64(cpu, ACTIVITY_BUF, time);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, core);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, key);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, activity);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, pid);
+ gator_buffer_write_packed_int(cpu, ACTIVITY_BUF, state);
+ }
+ local_irq_restore(flags);
+ /* Check and commit; commit is set to occur once buffer is 3/4 full */
+ buffer_check(cpu, ACTIVITY_BUF, time);
+}
+
+void gator_marshal_activity_switch(int core, int key, int activity, int pid)
+{
+ /* state is reserved for cpu use only */
+ marshal_activity_switch(core, key, activity, pid, 0);
+}
diff --git a/drivers/gator/gator_trace_gpu.c b/drivers/gator/gator_trace_gpu.c
new file mode 100644
index 0000000..d9b82ee
--- /dev/null
+++ b/drivers/gator/gator_trace_gpu.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "gator.h"
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/math64.h>
+
+#ifdef MALI_SUPPORT
+#ifdef MALI_DIR_MIDGARD
+/* New DDK Directory structure with kernel/drivers/gpu/arm/midgard*/
+#include "mali_linux_trace.h"
+#else
+/* Old DDK Directory structure with kernel/drivers/gpu/arm/t6xx*/
+#include "linux/mali_linux_trace.h"
+#endif
+#endif
+
+/*
+ * Taken from MALI_PROFILING_EVENT_TYPE_* items in Mali DDK.
+ */
+#define EVENT_TYPE_SINGLE 0
+#define EVENT_TYPE_START 1
+#define EVENT_TYPE_STOP 2
+#define EVENT_TYPE_SUSPEND 3
+#define EVENT_TYPE_RESUME 4
+
+/* Note whether tracepoints have been registered */
+static int mali_timeline_trace_registered;
+static int mali_job_slots_trace_registered;
+
+enum {
+ GPU_UNIT_NONE = 0,
+ GPU_UNIT_VP,
+ GPU_UNIT_FP,
+ GPU_UNIT_CL,
+ NUMBER_OF_GPU_UNITS
+};
+
+#if defined(MALI_SUPPORT)
+
+struct mali_activity {
+ int core;
+ int key;
+ int count;
+ int last_activity;
+ int last_pid;
+};
+
+#define NUMBER_OF_GPU_CORES 16
+static struct mali_activity mali_activities[NUMBER_OF_GPU_UNITS*NUMBER_OF_GPU_CORES];
+static DEFINE_SPINLOCK(mali_activities_lock);
+
+/* Only one event should be running on a unit and core at a time (ie,
+ * a start event can only be followed by a stop and vice versa), but
+ * because the kernel only knows when a job is enqueued and not
+ * started, it is possible for a start1, start2, stop1, stop2. Change
+ * it back into start1, stop1, start2, stop2 by queueing up start2 and
+ * releasing it when stop1 is received.
+ */
+
+static int mali_activity_index(int core, int key)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mali_activities); ++i) {
+ if ((mali_activities[i].core == core) && (mali_activities[i].key == key))
+ break;
+ if ((mali_activities[i].core == 0) && (mali_activities[i].key == 0)) {
+ mali_activities[i].core = core;
+ mali_activities[i].key = key;
+ break;
+ }
+ }
+ BUG_ON(i >= ARRAY_SIZE(mali_activities));
+
+ return i;
+}
+
+static void mali_activity_enqueue(int core, int key, int activity, int pid)
+{
+ int i;
+ int count;
+
+ spin_lock(&mali_activities_lock);
+ i = mali_activity_index(core, key);
+
+ count = mali_activities[i].count;
+ BUG_ON(count < 0);
+ ++mali_activities[i].count;
+ if (count) {
+ mali_activities[i].last_activity = activity;
+ mali_activities[i].last_pid = pid;
+ }
+ spin_unlock(&mali_activities_lock);
+
+ if (!count)
+ gator_marshal_activity_switch(core, key, activity, pid);
+}
+
+static void mali_activity_stop(int core, int key)
+{
+ int i;
+ int count;
+ int last_activity = 0;
+ int last_pid = 0;
+
+ spin_lock(&mali_activities_lock);
+ i = mali_activity_index(core, key);
+
+ if (mali_activities[i].count == 0) {
+ spin_unlock(&mali_activities_lock);
+ return;
+ }
+ --mali_activities[i].count;
+ count = mali_activities[i].count;
+ if (count) {
+ last_activity = mali_activities[i].last_activity;
+ last_pid = mali_activities[i].last_pid;
+ }
+ spin_unlock(&mali_activities_lock);
+
+ gator_marshal_activity_switch(core, key, 0, 0);
+ if (count)
+ gator_marshal_activity_switch(core, key, last_activity, last_pid);
+}
+
+void mali_activity_clear(struct mali_counter mali_activity[], size_t mali_activity_size)
+{
+ int activity;
+ int cores;
+ int core;
+
+ for (activity = 0; activity < mali_activity_size; ++activity) {
+ cores = mali_activity[activity].cores;
+ if (cores < 0)
+ cores = 1;
+ for (core = 0; core < cores; ++core) {
+ if (mali_activity[activity].enabled) {
+ preempt_disable();
+ gator_marshal_activity_switch(core, mali_activity[activity].key, 0, 0);
+ preempt_enable();
+ }
+ }
+ }
+}
+
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+#include "gator_events_mali_4xx.h"
+
+/*
+ * Taken from MALI_PROFILING_EVENT_CHANNEL_* in Mali DDK.
+ */
+enum {
+ EVENT_CHANNEL_SOFTWARE = 0,
+ EVENT_CHANNEL_VP0 = 1,
+ EVENT_CHANNEL_FP0 = 5,
+ EVENT_CHANNEL_FP1,
+ EVENT_CHANNEL_FP2,
+ EVENT_CHANNEL_FP3,
+ EVENT_CHANNEL_FP4,
+ EVENT_CHANNEL_FP5,
+ EVENT_CHANNEL_FP6,
+ EVENT_CHANNEL_FP7,
+ EVENT_CHANNEL_GPU = 21
+};
+
+/**
+ * These events are applicable when the type MALI_PROFILING_EVENT_TYPE_SINGLE is used from the GPU channel
+ */
+enum {
+ EVENT_REASON_SINGLE_GPU_NONE = 0,
+ EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE = 1,
+};
+
+struct mali_counter mali_activity[2];
+
+GATOR_DEFINE_PROBE(mali_timeline_event, TP_PROTO(unsigned int event_id, unsigned int d0, unsigned int d1, unsigned int d2, unsigned int d3, unsigned int d4))
+{
+ unsigned int component, state;
+
+ /* do as much work as possible before disabling interrupts */
+ component = (event_id >> 16) & 0xFF; /* component is an 8-bit field */
+ state = (event_id >> 24) & 0xF; /* state is a 4-bit field */
+
+ switch (state) {
+ case EVENT_TYPE_START:
+ if (component == EVENT_CHANNEL_VP0) {
+ /* tgid = d0; pid = d1; */
+ if (mali_activity[1].enabled)
+ mali_activity_enqueue(0, mali_activity[1].key, 1, d1);
+ } else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+ /* tgid = d0; pid = d1; */
+ if (mali_activity[0].enabled)
+ mali_activity_enqueue(component - EVENT_CHANNEL_FP0, mali_activity[0].key, 1, d1);
+ }
+ break;
+
+ case EVENT_TYPE_STOP:
+ if (component == EVENT_CHANNEL_VP0) {
+ if (mali_activity[1].enabled)
+ mali_activity_stop(0, mali_activity[1].key);
+ } else if (component >= EVENT_CHANNEL_FP0 && component <= EVENT_CHANNEL_FP7) {
+ if (mali_activity[0].enabled)
+ mali_activity_stop(component - EVENT_CHANNEL_FP0, mali_activity[0].key);
+ }
+ break;
+
+ case EVENT_TYPE_SINGLE:
+ if (component == EVENT_CHANNEL_GPU) {
+ unsigned int reason = (event_id & 0xffff);
+
+ if (reason == EVENT_REASON_SINGLE_GPU_FREQ_VOLT_CHANGE)
+ gator_events_mali_log_dvfs_event(d0, d1);
+ }
+ break;
+
+ default:
+ break;
+ }
+}
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+
+struct mali_counter mali_activity[3];
+
+#if defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid, unsigned char job_id))
+#else
+GATOR_DEFINE_PROBE(mali_job_slots_event, TP_PROTO(unsigned int event_id, unsigned int tgid, unsigned int pid))
+#endif
+{
+ unsigned int component, state, unit;
+#if !defined(MALI_JOB_SLOTS_EVENT_CHANGED)
+ unsigned char job_id = 0;
+#endif
+
+ component = (event_id >> 16) & 0xFF; /* component is an 8-bit field */
+ state = (event_id >> 24) & 0xF; /* state is a 4-bit field */
+
+ switch (component) {
+ case 0:
+ unit = GPU_UNIT_FP;
+ break;
+ case 1:
+ unit = GPU_UNIT_VP;
+ break;
+ case 2:
+ unit = GPU_UNIT_CL;
+ break;
+ default:
+ unit = GPU_UNIT_NONE;
+ }
+
+ if (unit != GPU_UNIT_NONE) {
+ switch (state) {
+ case EVENT_TYPE_START:
+ if (mali_activity[component].enabled)
+ mali_activity_enqueue(0, mali_activity[component].key, 1, (pid != 0 ? pid : tgid));
+ break;
+ case EVENT_TYPE_STOP:
+ default: /* Some jobs can be soft-stopped, so ensure that this terminates the activity trace. */
+ if (mali_activity[component].enabled)
+ mali_activity_stop(0, mali_activity[component].key);
+ break;
+ }
+ }
+}
+#endif
+
+static int gator_trace_gpu_start(void)
+{
+ /*
+ * Returns nonzero for installation failed
+ * Absence of gpu trace points is not an error
+ */
+
+#if defined(MALI_SUPPORT)
+ memset(&mali_activities, 0, sizeof(mali_activities));
+#endif
+ mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+ mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+ if (!GATOR_REGISTER_TRACE(mali_timeline_event))
+ mali_timeline_trace_registered = 1;
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+ mali_activity_clear(mali_activity, ARRAY_SIZE(mali_activity));
+ if (!GATOR_REGISTER_TRACE(mali_job_slots_event))
+ mali_job_slots_trace_registered = 1;
+#endif
+
+ return 0;
+}
+
+static void gator_trace_gpu_stop(void)
+{
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT != MALI_MIDGARD)
+ if (mali_timeline_trace_registered)
+ GATOR_UNREGISTER_TRACE(mali_timeline_event);
+#endif
+
+#if defined(MALI_SUPPORT) && (MALI_SUPPORT == MALI_MIDGARD)
+ if (mali_job_slots_trace_registered)
+ GATOR_UNREGISTER_TRACE(mali_job_slots_event);
+#endif
+
+ mali_timeline_trace_registered = mali_job_slots_trace_registered = 0;
+}
diff --git a/drivers/gator/gator_trace_power.c b/drivers/gator/gator_trace_power.c
new file mode 100644
index 0000000..aaa8f86
--- /dev/null
+++ b/drivers/gator/gator_trace_power.c
@@ -0,0 +1,186 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpufreq.h>
+#include <trace/events/power.h>
+
+#if defined(__arm__)
+
+#include <asm/mach-types.h>
+
+#define implements_wfi() (!machine_is_omap3_beagle())
+
+#else
+
+#define implements_wfi() false
+
+#endif
+
+/* cpu_frequency and cpu_idle trace points were introduced in Linux
+ * kernel v2.6.38 the now deprecated power_frequency trace point was
+ * available prior to 2.6.38, but only for x86
+ */
+#if GATOR_CPU_FREQ_SUPPORT
+enum {
+ POWER_CPU_FREQ,
+ POWER_TOTAL
+};
+
+static DEFINE_PER_CPU(ulong, idle_prev_state);
+static ulong power_cpu_enabled[POWER_TOTAL];
+static ulong power_cpu_key[POWER_TOTAL];
+static ulong power_cpu_cores;
+
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+ int cpu;
+ bool found_nonzero_freq = false;
+
+ /* Even if CONFIG_CPU_FREQ is defined, it still may not be
+ * used. Check for non-zero values from cpufreq_quick_get
+ */
+ for_each_online_cpu(cpu) {
+ if (cpufreq_quick_get(cpu) > 0) {
+ found_nonzero_freq = true;
+ break;
+ }
+ }
+
+ if (found_nonzero_freq) {
+ /* cpu_frequency */
+ dir = gatorfs_mkdir(sb, root, "Linux_power_cpu_freq");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &power_cpu_enabled[POWER_CPU_FREQ]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &power_cpu_key[POWER_CPU_FREQ]);
+ }
+
+ return 0;
+}
+
+/* 'cpu' may not equal smp_processor_id(), i.e. may not be running on the core that is having the freq/idle state change */
+GATOR_DEFINE_PROBE(cpu_frequency, TP_PROTO(unsigned int frequency, unsigned int cpu))
+{
+ cpu = lcpu_to_pcpu(cpu);
+ marshal_event_single64(cpu, power_cpu_key[POWER_CPU_FREQ], frequency * 1000L);
+}
+
+GATOR_DEFINE_PROBE(cpu_idle, TP_PROTO(unsigned int state, unsigned int cpu))
+{
+ cpu = lcpu_to_pcpu(cpu);
+
+ if (state == per_cpu(idle_prev_state, cpu))
+ return;
+
+ if (implements_wfi()) {
+ marshal_idle(cpu, state);
+ }
+
+ per_cpu(idle_prev_state, cpu) = state;
+}
+
+static void gator_trace_power_online(void)
+{
+ int pcpu = get_physical_cpu();
+ int lcpu = get_logical_cpu();
+
+ if (power_cpu_enabled[POWER_CPU_FREQ])
+ marshal_event_single64(pcpu, power_cpu_key[POWER_CPU_FREQ], cpufreq_quick_get(lcpu) * 1000L);
+}
+
+static void gator_trace_power_offline(void)
+{
+ /* Set frequency to zero on an offline */
+ int cpu = get_physical_cpu();
+
+ if (power_cpu_enabled[POWER_CPU_FREQ])
+ marshal_event_single(cpu, power_cpu_key[POWER_CPU_FREQ], 0);
+}
+
+static int gator_trace_power_start(void)
+{
+ int cpu;
+
+ /* register tracepoints */
+ if (power_cpu_enabled[POWER_CPU_FREQ])
+ if (GATOR_REGISTER_TRACE(cpu_frequency))
+ goto fail_cpu_frequency_exit;
+
+ /* Always register for cpu_idle for detecting WFI */
+ if (GATOR_REGISTER_TRACE(cpu_idle))
+ goto fail_cpu_idle_exit;
+ pr_debug("gator: registered power event tracepoints\n");
+
+ for_each_present_cpu(cpu) {
+ per_cpu(idle_prev_state, cpu) = 0;
+ }
+
+ return 0;
+
+ /* unregister tracepoints on error */
+fail_cpu_idle_exit:
+ if (power_cpu_enabled[POWER_CPU_FREQ])
+ GATOR_UNREGISTER_TRACE(cpu_frequency);
+fail_cpu_frequency_exit:
+ pr_err("gator: power event tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+ return -1;
+}
+
+static void gator_trace_power_stop(void)
+{
+ int i;
+
+ if (power_cpu_enabled[POWER_CPU_FREQ])
+ GATOR_UNREGISTER_TRACE(cpu_frequency);
+ GATOR_UNREGISTER_TRACE(cpu_idle);
+ pr_debug("gator: unregistered power event tracepoints\n");
+
+ for (i = 0; i < POWER_TOTAL; i++)
+ power_cpu_enabled[i] = 0;
+}
+
+static void gator_trace_power_init(void)
+{
+ int i;
+
+ power_cpu_cores = nr_cpu_ids;
+ for (i = 0; i < POWER_TOTAL; i++) {
+ power_cpu_enabled[i] = 0;
+ power_cpu_key[i] = gator_events_get_key();
+ }
+}
+#else
+static int gator_trace_power_create_files(struct super_block *sb, struct dentry *root)
+{
+ return 0;
+}
+
+static void gator_trace_power_online(void)
+{
+}
+
+static void gator_trace_power_offline(void)
+{
+}
+
+static int gator_trace_power_start(void)
+{
+ return 0;
+}
+
+static void gator_trace_power_stop(void)
+{
+}
+
+static void gator_trace_power_init(void)
+{
+}
+#endif
diff --git a/drivers/gator/gator_trace_sched.c b/drivers/gator/gator_trace_sched.c
new file mode 100644
index 0000000..ad7c39e
--- /dev/null
+++ b/drivers/gator/gator_trace_sched.c
@@ -0,0 +1,321 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <trace/events/sched.h>
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+#include <trace/events/task.h>
+#endif
+
+#include "gator.h"
+
+#define TASK_MAP_ENTRIES 1024 /* must be power of 2 */
+#define TASK_MAX_COLLISIONS 2
+
+enum {
+ STATE_WAIT_ON_OTHER = 0,
+ STATE_CONTENTION,
+ STATE_WAIT_ON_IO,
+ CPU_WAIT_TOTAL
+};
+
+static DEFINE_PER_CPU(uint64_t *, taskname_keys);
+static DEFINE_PER_CPU(int, collecting);
+
+/* this array is never read as the cpu wait charts are derived
+ * counters the files are needed, nonetheless, to show that these
+ * counters are available
+ */
+static ulong cpu_wait_enabled[CPU_WAIT_TOTAL];
+static ulong sched_cpu_key[CPU_WAIT_TOTAL];
+
+static int sched_trace_create_files(struct super_block *sb, struct dentry *root)
+{
+ struct dentry *dir;
+
+ /* CPU Wait - Contention */
+ dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_contention");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_CONTENTION]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_CONTENTION]);
+
+ /* CPU Wait - I/O */
+ dir = gatorfs_mkdir(sb, root, "Linux_cpu_wait_io");
+ if (!dir)
+ return -1;
+ gatorfs_create_ulong(sb, dir, "enabled", &cpu_wait_enabled[STATE_WAIT_ON_IO]);
+ gatorfs_create_ro_ulong(sb, dir, "key", &sched_cpu_key[STATE_WAIT_ON_IO]);
+
+ return 0;
+}
+
+static void emit_pid_name(const char *comm, struct task_struct *task)
+{
+ bool found = false;
+ char taskcomm[TASK_COMM_LEN + 3];
+ unsigned long x, cpu = get_physical_cpu();
+ uint64_t *keys = &(per_cpu(taskname_keys, cpu)[(task->pid & 0xFF) * TASK_MAX_COLLISIONS]);
+ uint64_t value;
+
+ value = gator_chksum_crc32(comm);
+ value = (value << 32) | (uint32_t)task->pid;
+
+ /* determine if the thread name was emitted already */
+ for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+ if (keys[x] == value) {
+ found = true;
+ break;
+ }
+ }
+
+ if (!found) {
+ /* shift values, new value always in front */
+ uint64_t oldv, newv = value;
+
+ for (x = 0; x < TASK_MAX_COLLISIONS; x++) {
+ oldv = keys[x];
+ keys[x] = newv;
+ newv = oldv;
+ }
+
+ /* emit pid names, cannot use get_task_comm, as it's not exported on all kernel versions */
+ if (strlcpy(taskcomm, comm, TASK_COMM_LEN) == TASK_COMM_LEN - 1) {
+ /* append ellipses if comm has length of TASK_COMM_LEN - 1 */
+ strcat(taskcomm, "...");
+ }
+
+ marshal_thread_name(task->pid, taskcomm);
+ }
+}
+
+static void collect_counters(u64 time, struct task_struct *task, bool sched_switch)
+{
+ int *buffer, len, cpu = get_physical_cpu();
+ long long *buffer64;
+ struct gator_interface *gi;
+
+ if (marshal_event_header(time)) {
+ list_for_each_entry(gi, &gator_events, list) {
+ if (gi->read) {
+ len = gi->read(&buffer, sched_switch);
+ marshal_event(len, buffer);
+ } else if (gi->read64) {
+ len = gi->read64(&buffer64);
+ marshal_event64(len, buffer64);
+ }
+ if (gi->read_proc && task != NULL) {
+ len = gi->read_proc(&buffer64, task);
+ marshal_event64(len, buffer64);
+ }
+ }
+ if (cpu == 0)
+ gator_emit_perf_time(time);
+ /* Only check after writing all counters so that time and corresponding counters appear in the same frame */
+ buffer_check(cpu, BLOCK_COUNTER_BUF, time);
+
+ /* Commit buffers on timeout */
+ if (gator_live_rate > 0 && time >= per_cpu(gator_buffer_commit_time, cpu)) {
+ static const int buftypes[] = { NAME_BUF, COUNTER_BUF, BLOCK_COUNTER_BUF, SCHED_TRACE_BUF, ACTIVITY_BUF };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(buftypes); ++i)
+ gator_commit_buffer(cpu, buftypes[i], time);
+
+ /* spinlocks are noops on uniprocessor machines and mutexes do
+ * not work in sched_switch context in RT-Preempt full, so
+ * disable proactive flushing of the annotate frame on
+ * uniprocessor machines.
+ */
+#ifdef CONFIG_SMP
+ /* Try to preemptively flush the annotate buffer to reduce the chance of the buffer being full */
+ if (on_primary_core() && spin_trylock(&annotate_lock)) {
+ gator_commit_buffer(0, ANNOTATE_BUF, time);
+ spin_unlock(&annotate_lock);
+ }
+#endif
+ }
+ }
+}
+
+/* special case used during a suspend of the system */
+static void trace_sched_insert_idle(void)
+{
+ marshal_sched_trace_switch(0, 0);
+}
+
+static void gator_trace_emit_link(struct task_struct *p)
+{
+ int cookie;
+ int cpu = get_physical_cpu();
+
+ cookie = get_exec_cookie(cpu, p);
+ emit_pid_name(p->comm, p);
+
+ marshal_link(cookie, p->tgid, p->pid);
+}
+
+GATOR_DEFINE_PROBE(sched_process_fork, TP_PROTO(struct task_struct *parent, struct task_struct *child))
+{
+ gator_trace_emit_link(child);
+}
+
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+GATOR_DEFINE_PROBE(sched_process_exec, TP_PROTO(struct task_struct *p, pid_t old_pid, struct linux_binprm *bprm))
+{
+ gator_trace_emit_link(p);
+}
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 15, 0)
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, char *comm))
+#else
+GATOR_DEFINE_PROBE(task_rename, TP_PROTO(struct task_struct *task, const char *comm))
+#endif
+{
+ emit_pid_name(comm, task);
+}
+#endif
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 35)
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct rq *rq, struct task_struct *prev, struct task_struct *next))
+#else
+GATOR_DEFINE_PROBE(sched_switch, TP_PROTO(struct task_struct *prev, struct task_struct *next))
+#endif
+{
+ int state;
+ int cpu = get_physical_cpu();
+
+ per_cpu(in_scheduler_context, cpu) = true;
+
+ /* do as much work as possible before disabling interrupts */
+ if (prev->state == TASK_RUNNING)
+ state = STATE_CONTENTION;
+ else if (prev->in_iowait)
+ state = STATE_WAIT_ON_IO;
+ else
+ state = STATE_WAIT_ON_OTHER;
+
+ per_cpu(collecting, cpu) = 1;
+ collect_counters(gator_get_time(), prev, true);
+ per_cpu(collecting, cpu) = 0;
+
+#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 4, 0)
+ gator_trace_emit_link(next);
+#endif
+ marshal_sched_trace_switch(next->pid, state);
+
+ per_cpu(in_scheduler_context, cpu) = false;
+}
+
+GATOR_DEFINE_PROBE(sched_process_free, TP_PROTO(struct task_struct *p))
+{
+ marshal_sched_trace_exit(p->tgid, p->pid);
+}
+
+static void do_nothing(void *info)
+{
+ /* Intentionally do nothing */
+ (void)info;
+}
+
+static int register_scheduler_tracepoints(void)
+{
+ /* register tracepoints */
+ if (GATOR_REGISTER_TRACE(sched_process_fork))
+ goto fail_sched_process_fork;
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+ if (GATOR_REGISTER_TRACE(sched_process_exec))
+ goto fail_sched_process_exec;
+ if (GATOR_REGISTER_TRACE(task_rename))
+ goto fail_task_rename;
+#endif
+ if (GATOR_REGISTER_TRACE(sched_switch))
+ goto fail_sched_switch;
+ if (GATOR_REGISTER_TRACE(sched_process_free))
+ goto fail_sched_process_free;
+ pr_debug("gator: registered tracepoints\n");
+
+ /* Now that the scheduler tracepoint is registered, force a context
+ * switch on all cpus to capture what is currently running.
+ */
+ on_each_cpu(do_nothing, NULL, 0);
+
+ return 0;
+
+ /* unregister tracepoints on error */
+fail_sched_process_free:
+ GATOR_UNREGISTER_TRACE(sched_switch);
+fail_sched_switch:
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+ GATOR_UNREGISTER_TRACE(task_rename);
+fail_task_rename:
+ GATOR_UNREGISTER_TRACE(sched_process_exec);
+fail_sched_process_exec:
+#endif
+ GATOR_UNREGISTER_TRACE(sched_process_fork);
+fail_sched_process_fork:
+ pr_err("gator: tracepoints failed to activate, please verify that tracepoints are enabled in the linux kernel\n");
+
+ return -1;
+}
+
+static void unregister_scheduler_tracepoints(void)
+{
+ GATOR_UNREGISTER_TRACE(sched_process_fork);
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(3, 4, 0)
+ GATOR_UNREGISTER_TRACE(sched_process_exec);
+ GATOR_UNREGISTER_TRACE(task_rename);
+#endif
+ GATOR_UNREGISTER_TRACE(sched_switch);
+ GATOR_UNREGISTER_TRACE(sched_process_free);
+ pr_debug("gator: unregistered tracepoints\n");
+}
+
+static void gator_trace_sched_stop(void)
+{
+ int cpu;
+
+ unregister_scheduler_tracepoints();
+
+ for_each_present_cpu(cpu) {
+ kfree(per_cpu(taskname_keys, cpu));
+ }
+}
+
+static int gator_trace_sched_start(void)
+{
+ int cpu, size;
+ int ret;
+
+ for_each_present_cpu(cpu) {
+ size = TASK_MAP_ENTRIES * TASK_MAX_COLLISIONS * sizeof(uint64_t);
+ per_cpu(taskname_keys, cpu) = kmalloc(size, GFP_KERNEL);
+ if (!per_cpu(taskname_keys, cpu))
+ return -1;
+ memset(per_cpu(taskname_keys, cpu), 0, size);
+ }
+
+ ret = register_scheduler_tracepoints();
+
+ return ret;
+}
+
+static void gator_trace_sched_offline(void)
+{
+ trace_sched_insert_idle();
+}
+
+static void gator_trace_sched_init(void)
+{
+ int i;
+
+ for (i = 0; i < CPU_WAIT_TOTAL; i++) {
+ cpu_wait_enabled[i] = 0;
+ sched_cpu_key[i] = gator_events_get_key();
+ }
+}
diff --git a/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
new file mode 100644
index 0000000..a5d1651
--- /dev/null
+++ b/drivers/gator/mali/mali_mjollnir_profiling_gator_api.h
@@ -0,0 +1,159 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+#define __MALI_MJOLLNIR_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+
+/*
+ * The number of processor cores. Update to suit your hardware implementation.
+ */
+#define MAX_NUM_FP_CORES (4)
+#define MAX_NUM_VP_CORES (1)
+#define MAX_NUM_L2_CACHE_CORES (1)
+
+enum counters {
+ /* Timeline activity */
+ ACTIVITY_VP_0 = 0,
+ ACTIVITY_FP_0,
+ ACTIVITY_FP_1,
+ ACTIVITY_FP_2,
+ ACTIVITY_FP_3,
+
+ /* L2 cache counters */
+ COUNTER_L2_0_C0,
+ COUNTER_L2_0_C1,
+
+ /* Vertex processor counters */
+ COUNTER_VP_0_C0,
+ COUNTER_VP_0_C1,
+
+ /* Fragment processor counters */
+ COUNTER_FP_0_C0,
+ COUNTER_FP_0_C1,
+ COUNTER_FP_1_C0,
+ COUNTER_FP_1_C1,
+ COUNTER_FP_2_C0,
+ COUNTER_FP_2_C1,
+ COUNTER_FP_3_C0,
+ COUNTER_FP_3_C1,
+
+ /* EGL Software Counters */
+ COUNTER_EGL_BLIT_TIME,
+
+ /* GLES Software Counters */
+ COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+ COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+ COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+ COUNTER_GLES_DRAW_ARRAYS_CALLS,
+ COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+ COUNTER_GLES_DRAW_POINTS,
+ COUNTER_GLES_DRAW_LINES,
+ COUNTER_GLES_DRAW_LINE_LOOP,
+ COUNTER_GLES_DRAW_LINE_STRIP,
+ COUNTER_GLES_DRAW_TRIANGLES,
+ COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+ COUNTER_GLES_DRAW_TRIANGLE_FAN,
+ COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+ COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+ COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+ COUNTER_GLES_UPLOAD_VBO_TIME,
+ COUNTER_GLES_NUM_FLUSHES,
+ COUNTER_GLES_NUM_VSHADERS_GENERATED,
+ COUNTER_GLES_NUM_FSHADERS_GENERATED,
+ COUNTER_GLES_VSHADER_GEN_TIME,
+ COUNTER_GLES_FSHADER_GEN_TIME,
+ COUNTER_GLES_INPUT_TRIANGLES,
+ COUNTER_GLES_VXCACHE_HIT,
+ COUNTER_GLES_VXCACHE_MISS,
+ COUNTER_GLES_VXCACHE_COLLISION,
+ COUNTER_GLES_CULLED_TRIANGLES,
+ COUNTER_GLES_CULLED_LINES,
+ COUNTER_GLES_BACKFACE_TRIANGLES,
+ COUNTER_GLES_GBCLIP_TRIANGLES,
+ COUNTER_GLES_GBCLIP_LINES,
+ COUNTER_GLES_TRIANGLES_DRAWN,
+ COUNTER_GLES_DRAWCALL_TIME,
+ COUNTER_GLES_TRIANGLES_COUNT,
+ COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+ COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+ COUNTER_GLES_FAN_TRIANGLES_COUNT,
+ COUNTER_GLES_LINES_COUNT,
+ COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+ COUNTER_GLES_STRIP_LINES_COUNT,
+ COUNTER_GLES_LOOP_LINES_COUNT,
+
+ COUNTER_FILMSTRIP,
+ COUNTER_FREQUENCY,
+ COUNTER_VOLTAGE,
+
+ NUMBER_OF_EVENTS
+};
+
+#define FIRST_ACTIVITY_EVENT ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT ACTIVITY_FP_3
+
+#define FIRST_HW_COUNTER COUNTER_L2_0_C0
+#define LAST_HW_COUNTER COUNTER_FP_3_C1
+
+#define FIRST_SW_COUNTER COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER COUNTER_GLES_LOOP_LINES_COUNT
+
+/* Signifies that the system is able to report voltage and frequency numbers. */
+#define DVFS_REPORTED_BY_DDK 1
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+ u32 source0;
+ u32 value0;
+ u32 source1;
+ u32 value1;
+};
+
+/*
+ * For compatibility with utgard.
+ */
+struct _mali_profiling_l2_counter_values {
+ struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+struct _mali_profiling_mali_version {
+ u32 mali_product_id;
+ u32 mali_version_major;
+ u32 mali_version_minor;
+ u32 num_of_l2_cores;
+ u32 num_of_fp_cores;
+ u32 num_of_vp_cores;
+};
+
+extern void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+extern u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+/*
+ * List of possible actions allowing DDK to be controlled by Streamline.
+ * The following numbers are used by DDK to control the frame buffer dumping.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_MJOLLNIR_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali/mali_utgard_profiling_gator_api.h b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
new file mode 100644
index 0000000..f550490
--- /dev/null
+++ b/drivers/gator/mali/mali_utgard_profiling_gator_api.h
@@ -0,0 +1,197 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __MALI_UTGARD_PROFILING_GATOR_API_H__
+#define __MALI_UTGARD_PROFILING_GATOR_API_H__
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+#define MALI_PROFILING_API_VERSION 4
+
+#define MAX_NUM_L2_CACHE_CORES 3
+#define MAX_NUM_FP_CORES 8
+#define MAX_NUM_VP_CORES 1
+
+/** The list of events supported by the Mali DDK. */
+enum {
+ /* Vertex processor activity */
+ ACTIVITY_VP_0 = 0,
+
+ /* Fragment processor activity */
+ ACTIVITY_FP_0, /* 1 */
+ ACTIVITY_FP_1,
+ ACTIVITY_FP_2,
+ ACTIVITY_FP_3,
+ ACTIVITY_FP_4,
+ ACTIVITY_FP_5,
+ ACTIVITY_FP_6,
+ ACTIVITY_FP_7,
+
+ /* L2 cache counters */
+ COUNTER_L2_0_C0,
+ COUNTER_L2_0_C1,
+ COUNTER_L2_1_C0,
+ COUNTER_L2_1_C1,
+ COUNTER_L2_2_C0,
+ COUNTER_L2_2_C1,
+
+ /* Vertex processor counters */
+ COUNTER_VP_0_C0, /*15*/
+ COUNTER_VP_0_C1,
+
+ /* Fragment processor counters */
+ COUNTER_FP_0_C0,
+ COUNTER_FP_0_C1,
+ COUNTER_FP_1_C0,
+ COUNTER_FP_1_C1,
+ COUNTER_FP_2_C0,
+ COUNTER_FP_2_C1,
+ COUNTER_FP_3_C0,
+ COUNTER_FP_3_C1,
+ COUNTER_FP_4_C0,
+ COUNTER_FP_4_C1,
+ COUNTER_FP_5_C0,
+ COUNTER_FP_5_C1,
+ COUNTER_FP_6_C0,
+ COUNTER_FP_6_C1,
+ COUNTER_FP_7_C0,
+ COUNTER_FP_7_C1, /* 32 */
+
+ /*
+ * If more hardware counters are added, the _mali_osk_hw_counter_table
+ * below should also be updated.
+ */
+
+ /* EGL software counters */
+ COUNTER_EGL_BLIT_TIME,
+
+ /* GLES software counters */
+ COUNTER_GLES_DRAW_ELEMENTS_CALLS,
+ COUNTER_GLES_DRAW_ELEMENTS_NUM_INDICES,
+ COUNTER_GLES_DRAW_ELEMENTS_NUM_TRANSFORMED,
+ COUNTER_GLES_DRAW_ARRAYS_CALLS,
+ COUNTER_GLES_DRAW_ARRAYS_NUM_TRANSFORMED,
+ COUNTER_GLES_DRAW_POINTS,
+ COUNTER_GLES_DRAW_LINES,
+ COUNTER_GLES_DRAW_LINE_LOOP,
+ COUNTER_GLES_DRAW_LINE_STRIP,
+ COUNTER_GLES_DRAW_TRIANGLES,
+ COUNTER_GLES_DRAW_TRIANGLE_STRIP,
+ COUNTER_GLES_DRAW_TRIANGLE_FAN,
+ COUNTER_GLES_NON_VBO_DATA_COPY_TIME,
+ COUNTER_GLES_UNIFORM_BYTES_COPIED_TO_MALI,
+ COUNTER_GLES_UPLOAD_TEXTURE_TIME,
+ COUNTER_GLES_UPLOAD_VBO_TIME,
+ COUNTER_GLES_NUM_FLUSHES,
+ COUNTER_GLES_NUM_VSHADERS_GENERATED,
+ COUNTER_GLES_NUM_FSHADERS_GENERATED,
+ COUNTER_GLES_VSHADER_GEN_TIME,
+ COUNTER_GLES_FSHADER_GEN_TIME,
+ COUNTER_GLES_INPUT_TRIANGLES,
+ COUNTER_GLES_VXCACHE_HIT,
+ COUNTER_GLES_VXCACHE_MISS,
+ COUNTER_GLES_VXCACHE_COLLISION,
+ COUNTER_GLES_CULLED_TRIANGLES,
+ COUNTER_GLES_CULLED_LINES,
+ COUNTER_GLES_BACKFACE_TRIANGLES,
+ COUNTER_GLES_GBCLIP_TRIANGLES,
+ COUNTER_GLES_GBCLIP_LINES,
+ COUNTER_GLES_TRIANGLES_DRAWN,
+ COUNTER_GLES_DRAWCALL_TIME,
+ COUNTER_GLES_TRIANGLES_COUNT,
+ COUNTER_GLES_INDEPENDENT_TRIANGLES_COUNT,
+ COUNTER_GLES_STRIP_TRIANGLES_COUNT,
+ COUNTER_GLES_FAN_TRIANGLES_COUNT,
+ COUNTER_GLES_LINES_COUNT,
+ COUNTER_GLES_INDEPENDENT_LINES_COUNT,
+ COUNTER_GLES_STRIP_LINES_COUNT,
+ COUNTER_GLES_LOOP_LINES_COUNT,
+
+ /* Framebuffer capture pseudo-counter */
+ COUNTER_FILMSTRIP,
+
+ NUMBER_OF_EVENTS
+} _mali_osk_counter_id;
+
+#define FIRST_ACTIVITY_EVENT ACTIVITY_VP_0
+#define LAST_ACTIVITY_EVENT ACTIVITY_FP_7
+
+#define FIRST_HW_COUNTER COUNTER_L2_0_C0
+#define LAST_HW_COUNTER COUNTER_FP_7_C1
+
+#define FIRST_SW_COUNTER COUNTER_EGL_BLIT_TIME
+#define LAST_SW_COUNTER COUNTER_GLES_LOOP_LINES_COUNT
+
+#define FIRST_SPECIAL_COUNTER COUNTER_FILMSTRIP
+#define LAST_SPECIAL_COUNTER COUNTER_FILMSTRIP
+
+/**
+ * Structure to pass performance counter data of a Mali core
+ */
+struct _mali_profiling_core_counters {
+ u32 source0;
+ u32 value0;
+ u32 source1;
+ u32 value1;
+};
+
+/**
+ * Structure to pass performance counter data of Mali L2 cache cores
+ */
+struct _mali_profiling_l2_counter_values {
+ struct _mali_profiling_core_counters cores[MAX_NUM_L2_CACHE_CORES];
+};
+
+/**
+ * Structure to pass data defining Mali instance in use:
+ *
+ * mali_product_id - Mali product id
+ * mali_version_major - Mali version major number
+ * mali_version_minor - Mali version minor number
+ * num_of_l2_cores - number of L2 cache cores
+ * num_of_fp_cores - number of fragment processor cores
+ * num_of_vp_cores - number of vertex processor cores
+ */
+struct _mali_profiling_mali_version {
+ u32 mali_product_id;
+ u32 mali_version_major;
+ u32 mali_version_minor;
+ u32 num_of_l2_cores;
+ u32 num_of_fp_cores;
+ u32 num_of_vp_cores;
+};
+
+/*
+ * List of possible actions to be controlled by Streamline.
+ * The following numbers are used by gator to control the frame buffer dumping and s/w counter reporting.
+ * We cannot use the enums in mali_uk_types.h because they are unknown inside gator.
+ */
+#define FBDUMP_CONTROL_ENABLE (1)
+#define FBDUMP_CONTROL_RATE (2)
+#define SW_COUNTER_ENABLE (3)
+#define FBDUMP_CONTROL_RESIZE_FACTOR (4)
+
+void _mali_profiling_control(u32 action, u32 value);
+
+u32 _mali_profiling_get_l2_counters(struct _mali_profiling_l2_counter_values *values);
+
+int _mali_profiling_set_event(u32 counter_id, s32 event_id);
+
+u32 _mali_profiling_get_api_version(void);
+
+void _mali_profiling_get_mali_version(struct _mali_profiling_mali_version *values);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MALI_UTGARD_PROFILING_GATOR_API_H__ */
diff --git a/drivers/gator/mali_midgard.mk b/drivers/gator/mali_midgard.mk
new file mode 100644
index 0000000..b0076c2
--- /dev/null
+++ b/drivers/gator/mali_midgard.mk
@@ -0,0 +1,40 @@
+# Defines for Mali-Midgard driver
+EXTRA_CFLAGS += -DMALI_USE_UMP=1 \
+ -DMALI_LICENSE_IS_GPL=1 \
+ -DMALI_BASE_TRACK_MEMLEAK=0 \
+ -DMALI_DEBUG=0 \
+ -DMALI_ERROR_INJECT_ON=0 \
+ -DMALI_CUSTOMER_RELEASE=1 \
+ -DMALI_UNIT_TEST=0 \
+ -DMALI_BACKEND_KERNEL=1 \
+ -DMALI_NO_MALI=0
+
+DDK_DIR ?= .
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/t6xx),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/t6xx/kbase/osk
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard),)
+KBASE_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard
+OSK_DIR = $(DDK_DIR)/drivers/gpu/arm/midgard/osk
+EXTRA_CFLAGS += -DMALI_DIR_MIDGARD=1
+endif
+
+ifneq ($(wildcard $(DDK_DIR)/drivers/gpu/arm/midgard/mali_kbase_gator_api.h),)
+EXTRA_CFLAGS += -DMALI_SIMPLE_API=1
+EXTRA_CFLAGS += -I$(DDK_DIR)/drivers/gpu/arm/midgard
+endif
+
+UMP_DIR = $(DDK_DIR)/include/linux
+
+# Include directories in the DDK
+EXTRA_CFLAGS += -I$(KBASE_DIR)/ \
+ -I$(KBASE_DIR)/.. \
+ -I$(OSK_DIR)/.. \
+ -I$(UMP_DIR)/.. \
+ -I$(DDK_DIR)/include \
+ -I$(KBASE_DIR)/osk/src/linux/include \
+ -I$(KBASE_DIR)/platform_dummy \
+ -I$(KBASE_DIR)/src
+
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 86c17de..71d8614 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -248,14 +248,15 @@
struct lp_gpio *lg = irq_data_get_irq_handler_data(data);
struct irq_chip *chip = irq_data_get_irq_chip(data);
u32 base, pin, mask;
- unsigned long reg, pending;
+ unsigned long reg, ena, pending;
unsigned virq;
/* check from GPIO controller which pin triggered the interrupt */
for (base = 0; base < lg->chip.ngpio; base += 32) {
reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
+ ena = lp_gpio_reg(&lg->chip, base, LP_INT_ENABLE);
- while ((pending = inl(reg))) {
+ while ((pending = (inl(reg) & inl(ena)))) {
pin = __ffs(pending);
mask = BIT(pin);
/* Clear before handling so we don't lose an edge */
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index a0b33a2..2aa3ca2 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -69,10 +69,14 @@
u32 val;
struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
+ u32 out_mask, out_shadow;
- val = in_be32(mm->regs + GPIO_DAT) & ~in_be32(mm->regs + GPIO_DIR);
+ out_mask = in_be32(mm->regs + GPIO_DIR);
- return (val | mpc8xxx_gc->data) & mpc8xxx_gpio2mask(gpio);
+ val = in_be32(mm->regs + GPIO_DAT) & ~out_mask;
+ out_shadow = mpc8xxx_gc->data & out_mask;
+
+ return (val | out_shadow) & mpc8xxx_gpio2mask(gpio);
}
static int mpc8xxx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index dd2edde..500c4d1 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -248,7 +248,7 @@
spin_lock_irqsave(&tlmm_lock, irq_flags);
writel(TARGET_PROC_NONE, GPIO_INTR_CFG_SU(gpio));
- clear_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+ clear_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
__clear_bit(gpio, msm_gpio.enabled_irqs);
spin_unlock_irqrestore(&tlmm_lock, irq_flags);
}
@@ -260,7 +260,7 @@
spin_lock_irqsave(&tlmm_lock, irq_flags);
__set_bit(gpio, msm_gpio.enabled_irqs);
- set_gpio_bits(INTR_RAW_STATUS_EN | INTR_ENABLE, GPIO_INTR_CFG(gpio));
+ set_gpio_bits(BIT(INTR_RAW_STATUS_EN) | BIT(INTR_ENABLE), GPIO_INTR_CFG(gpio));
writel(TARGET_PROC_SCORPION, GPIO_INTR_CFG_SU(gpio));
spin_unlock_irqrestore(&tlmm_lock, irq_flags);
}
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 3a4816a..5c27da6 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -79,7 +79,7 @@
spinlock_t lock;
void __iomem *membase;
void __iomem *percpu_membase;
- unsigned int irqbase;
+ int irqbase;
struct irq_domain *domain;
int soc_variant;
};
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index f8e6af2..d599fc4 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -214,7 +214,8 @@
ct->regs.ack = PINCTRL_IRQSTAT(port) + MXS_CLR;
ct->regs.mask = PINCTRL_IRQEN(port);
- irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+ irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+ IRQ_NOREQUEST, 0);
}
static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 4a43036..5405212 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -63,6 +63,7 @@
struct gpio_chip chip;
struct clk *dbck;
u32 mod_usage;
+ u32 irq_usage;
u32 dbck_enable_mask;
bool dbck_enabled;
struct device *dev;
@@ -86,6 +87,9 @@
#define GPIO_BIT(bank, gpio) (1 << GPIO_INDEX(bank, gpio))
#define GPIO_MOD_CTRL_BIT BIT(0)
+#define BANK_USED(bank) (bank->mod_usage || bank->irq_usage)
+#define LINE_USED(line, offset) (line & (1 << offset))
+
static int irq_to_gpio(struct gpio_bank *bank, unsigned int gpio_irq)
{
return bank->chip.base + gpio_irq;
@@ -420,15 +424,69 @@
return 0;
}
+static void _enable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+ if (bank->regs->pinctrl) {
+ void __iomem *reg = bank->base + bank->regs->pinctrl;
+
+ /* Claim the pin for MPU */
+ __raw_writel(__raw_readl(reg) | (1 << offset), reg);
+ }
+
+ if (bank->regs->ctrl && !BANK_USED(bank)) {
+ void __iomem *reg = bank->base + bank->regs->ctrl;
+ u32 ctrl;
+
+ ctrl = __raw_readl(reg);
+ /* Module is enabled, clocks are not gated */
+ ctrl &= ~GPIO_MOD_CTRL_BIT;
+ __raw_writel(ctrl, reg);
+ bank->context.ctrl = ctrl;
+ }
+}
+
+static void _disable_gpio_module(struct gpio_bank *bank, unsigned offset)
+{
+ void __iomem *base = bank->base;
+
+ if (bank->regs->wkup_en &&
+ !LINE_USED(bank->mod_usage, offset) &&
+ !LINE_USED(bank->irq_usage, offset)) {
+ /* Disable wake-up during idle for dynamic tick */
+ _gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
+ bank->context.wake_en =
+ __raw_readl(bank->base + bank->regs->wkup_en);
+ }
+
+ if (bank->regs->ctrl && !BANK_USED(bank)) {
+ void __iomem *reg = bank->base + bank->regs->ctrl;
+ u32 ctrl;
+
+ ctrl = __raw_readl(reg);
+ /* Module is disabled, clocks are gated */
+ ctrl |= GPIO_MOD_CTRL_BIT;
+ __raw_writel(ctrl, reg);
+ bank->context.ctrl = ctrl;
+ }
+}
+
+static int gpio_is_input(struct gpio_bank *bank, int mask)
+{
+ void __iomem *reg = bank->base + bank->regs->direction;
+
+ return __raw_readl(reg) & mask;
+}
+
static int gpio_irq_type(struct irq_data *d, unsigned type)
{
struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
unsigned gpio = 0;
int retval;
unsigned long flags;
+ unsigned offset;
- if (WARN_ON(!bank->mod_usage))
- return -EINVAL;
+ if (!BANK_USED(bank))
+ pm_runtime_get_sync(bank->dev);
#ifdef CONFIG_ARCH_OMAP1
if (d->irq > IH_MPUIO_BASE)
@@ -446,7 +504,17 @@
return -EINVAL;
spin_lock_irqsave(&bank->lock, flags);
- retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type);
+ offset = GPIO_INDEX(bank, gpio);
+ retval = _set_gpio_triggering(bank, offset, type);
+ if (!LINE_USED(bank->mod_usage, offset)) {
+ _enable_gpio_module(bank, offset);
+ _set_gpio_direction(bank, offset, 1);
+ } else if (!gpio_is_input(bank, 1 << offset)) {
+ spin_unlock_irqrestore(&bank->lock, flags);
+ return -EINVAL;
+ }
+
+ bank->irq_usage |= 1 << GPIO_INDEX(bank, gpio);
spin_unlock_irqrestore(&bank->lock, flags);
if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
@@ -603,35 +671,19 @@
* If this is the first gpio_request for the bank,
* enable the bank module.
*/
- if (!bank->mod_usage)
+ if (!BANK_USED(bank))
pm_runtime_get_sync(bank->dev);
spin_lock_irqsave(&bank->lock, flags);
/* Set trigger to none. You need to enable the desired trigger with
- * request_irq() or set_irq_type().
+ * request_irq() or set_irq_type(). Only do this if the IRQ line has
+ * not already been requested.
*/
- _set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
-
- if (bank->regs->pinctrl) {
- void __iomem *reg = bank->base + bank->regs->pinctrl;
-
- /* Claim the pin for MPU */
- __raw_writel(__raw_readl(reg) | (1 << offset), reg);
+ if (!LINE_USED(bank->irq_usage, offset)) {
+ _set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+ _enable_gpio_module(bank, offset);
}
-
- if (bank->regs->ctrl && !bank->mod_usage) {
- void __iomem *reg = bank->base + bank->regs->ctrl;
- u32 ctrl;
-
- ctrl = __raw_readl(reg);
- /* Module is enabled, clocks are not gated */
- ctrl &= ~GPIO_MOD_CTRL_BIT;
- __raw_writel(ctrl, reg);
- bank->context.ctrl = ctrl;
- }
-
bank->mod_usage |= 1 << offset;
-
spin_unlock_irqrestore(&bank->lock, flags);
return 0;
@@ -640,31 +692,11 @@
static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
{
struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
- void __iomem *base = bank->base;
unsigned long flags;
spin_lock_irqsave(&bank->lock, flags);
-
- if (bank->regs->wkup_en) {
- /* Disable wake-up during idle for dynamic tick */
- _gpio_rmw(base, bank->regs->wkup_en, 1 << offset, 0);
- bank->context.wake_en =
- __raw_readl(bank->base + bank->regs->wkup_en);
- }
-
bank->mod_usage &= ~(1 << offset);
-
- if (bank->regs->ctrl && !bank->mod_usage) {
- void __iomem *reg = bank->base + bank->regs->ctrl;
- u32 ctrl;
-
- ctrl = __raw_readl(reg);
- /* Module is disabled, clocks are gated */
- ctrl |= GPIO_MOD_CTRL_BIT;
- __raw_writel(ctrl, reg);
- bank->context.ctrl = ctrl;
- }
-
+ _disable_gpio_module(bank, offset);
_reset_gpio(bank, bank->chip.base + offset);
spin_unlock_irqrestore(&bank->lock, flags);
@@ -672,7 +704,7 @@
* If this is the last gpio to be freed in the bank,
* disable the bank module.
*/
- if (!bank->mod_usage)
+ if (!BANK_USED(bank))
pm_runtime_put(bank->dev);
}
@@ -762,10 +794,20 @@
struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
unsigned int gpio = irq_to_gpio(bank, d->hwirq);
unsigned long flags;
+ unsigned offset = GPIO_INDEX(bank, gpio);
spin_lock_irqsave(&bank->lock, flags);
+ bank->irq_usage &= ~(1 << offset);
+ _disable_gpio_module(bank, offset);
_reset_gpio(bank, gpio);
spin_unlock_irqrestore(&bank->lock, flags);
+
+ /*
+ * If this is the last IRQ to be freed in the bank,
+ * disable the bank module.
+ */
+ if (!BANK_USED(bank))
+ pm_runtime_put(bank->dev);
}
static void gpio_ack_irq(struct irq_data *d)
@@ -897,13 +939,6 @@
return 0;
}
-static int gpio_is_input(struct gpio_bank *bank, int mask)
-{
- void __iomem *reg = bank->base + bank->regs->direction;
-
- return __raw_readl(reg) & mask;
-}
-
static int gpio_get(struct gpio_chip *chip, unsigned offset)
{
struct gpio_bank *bank;
@@ -922,13 +957,22 @@
{
struct gpio_bank *bank;
unsigned long flags;
+ int retval = 0;
bank = container_of(chip, struct gpio_bank, chip);
spin_lock_irqsave(&bank->lock, flags);
+
+ if (LINE_USED(bank->irq_usage, offset)) {
+ retval = -EINVAL;
+ goto exit;
+ }
+
bank->set_dataout(bank, offset, value);
_set_gpio_direction(bank, offset, 0);
+
+exit:
spin_unlock_irqrestore(&bank->lock, flags);
- return 0;
+ return retval;
}
static int gpio_debounce(struct gpio_chip *chip, unsigned offset,
@@ -1400,7 +1444,7 @@
struct gpio_bank *bank;
list_for_each_entry(bank, &omap_gpio_list, node) {
- if (!bank->mod_usage || !bank->loses_context)
+ if (!BANK_USED(bank) || !bank->loses_context)
continue;
bank->power_mode = pwr_mode;
@@ -1414,7 +1458,7 @@
struct gpio_bank *bank;
list_for_each_entry(bank, &omap_gpio_list, node) {
- if (!bank->mod_usage || !bank->loses_context)
+ if (!BANK_USED(bank) || !bank->loses_context)
continue;
pm_runtime_get_sync(bank->dev);
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 6a4bd0d..4fbe12d 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -286,11 +286,6 @@
if (!chip->base)
return -ENOMEM;
- chip->domain = irq_domain_add_simple(adev->dev.of_node, PL061_GPIO_NR,
- irq_base, &pl061_domain_ops, chip);
- if (!chip->domain)
- return -ENODEV;
-
spin_lock_init(&chip->lock);
chip->gc.request = pl061_gpio_request;
@@ -320,6 +315,11 @@
irq_set_chained_handler(irq, pl061_irq_handler);
irq_set_handler_data(irq, chip);
+ chip->domain = irq_domain_add_simple(adev->dev.of_node, PL061_GPIO_NR,
+ irq_base, &pl061_domain_ops, chip);
+ if (!chip->domain)
+ return -ENODEV;
+
for (i = 0; i < PL061_GPIO_NR; i++) {
if (pdata) {
if (pdata->directions & (1 << i))
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index b4ca450..f3c5d39 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -329,11 +329,11 @@
if (!p->irq_domain) {
ret = -ENXIO;
dev_err(&pdev->dev, "cannot initialize irq domain\n");
- goto err1;
+ goto err0;
}
if (devm_request_irq(&pdev->dev, irq->start,
- gpio_rcar_irq_handler, 0, name, p)) {
+ gpio_rcar_irq_handler, IRQF_SHARED, name, p)) {
dev_err(&pdev->dev, "failed to request IRQ\n");
ret = -ENOENT;
goto err1;
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index 30a5844..8457304 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -26,9 +26,12 @@
struct gpio_chip gpio_chip;
};
+#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip)
+
static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset)
{
- struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+ struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+ struct tps65912 *tps65912 = tps65912_gpio->tps65912;
int val;
val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset);
@@ -42,7 +45,8 @@
static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset,
int value)
{
- struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+ struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+ struct tps65912 *tps65912 = tps65912_gpio->tps65912;
if (value)
tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset,
@@ -55,7 +59,8 @@
static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset,
int value)
{
- struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+ struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+ struct tps65912 *tps65912 = tps65912_gpio->tps65912;
/* Set the initial value */
tps65912_gpio_set(gc, offset, value);
@@ -66,7 +71,8 @@
static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset)
{
- struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio);
+ struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc);
+ struct tps65912 *tps65912 = tps65912_gpio->tps65912;
return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset,
GPIO_CFG_MASK);
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index 4d330e3..28d9876 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -300,7 +300,7 @@
if (offset < TWL4030_GPIO_MAX)
ret = twl4030_set_gpio_direction(offset, 1);
else
- ret = -EINVAL;
+ ret = -EINVAL; /* LED outputs can't be set as input */
if (!ret)
priv->direction &= ~BIT(offset);
@@ -354,17 +354,27 @@
static int twl_direction_out(struct gpio_chip *chip, unsigned offset, int value)
{
struct gpio_twl4030_priv *priv = to_gpio_twl4030(chip);
+ int ret = 0;
mutex_lock(&priv->mutex);
- if (offset < TWL4030_GPIO_MAX)
- twl4030_set_gpio_dataout(offset, value);
+ if (offset < TWL4030_GPIO_MAX) {
+ ret = twl4030_set_gpio_direction(offset, 0);
+ if (ret) {
+ mutex_unlock(&priv->mutex);
+ return ret;
+ }
+ }
+
+ /*
+ * LED gpios i.e. offset >= TWL4030_GPIO_MAX are always output
+ */
priv->direction |= BIT(offset);
mutex_unlock(&priv->mutex);
twl_set(chip, offset, value);
- return 0;
+ return ret;
}
static int twl_to_irq(struct gpio_chip *chip, unsigned offset)
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 665f953..7476972 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -12,6 +12,7 @@
*/
#include <linux/device.h>
+#include <linux/err.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/io.h>
@@ -42,8 +43,14 @@
return false;
ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags);
- if (ret < 0)
- return false;
+ if (ret < 0) {
+ /* We've found the gpio chip, but the translation failed.
+ * Return true to stop looking and return the translation
+ * error via out_gpio
+ */
+ gg_data->out_gpio = ret;
+ return true;
+ }
gg_data->out_gpio = ret + gc->base;
return true;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c2534d6..ca1cb2d7 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -362,7 +362,7 @@
return status;
}
-static const DEVICE_ATTR(value, 0644,
+static DEVICE_ATTR(value, 0644,
gpio_value_show, gpio_value_store);
static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
@@ -580,17 +580,17 @@
return status ? : size;
}
-static const DEVICE_ATTR(active_low, 0644,
+static DEVICE_ATTR(active_low, 0644,
gpio_active_low_show, gpio_active_low_store);
-static const struct attribute *gpio_attrs[] = {
+static struct attribute *gpio_attrs[] = {
&dev_attr_value.attr,
&dev_attr_active_low.attr,
NULL,
};
static const struct attribute_group gpio_attr_group = {
- .attrs = (struct attribute **) gpio_attrs,
+ .attrs = gpio_attrs,
};
/*
@@ -627,7 +627,7 @@
}
static DEVICE_ATTR(ngpio, 0444, chip_ngpio_show, NULL);
-static const struct attribute *gpiochip_attrs[] = {
+static struct attribute *gpiochip_attrs[] = {
&dev_attr_base.attr,
&dev_attr_label.attr,
&dev_attr_ngpio.attr,
@@ -635,7 +635,7 @@
};
static const struct attribute_group gpiochip_attr_group = {
- .attrs = (struct attribute **) gpiochip_attrs,
+ .attrs = gpiochip_attrs,
};
/*
@@ -806,20 +806,24 @@
if (direction_may_change) {
status = device_create_file(dev, &dev_attr_direction);
if (status)
- goto fail_unregister_device;
+ goto fail_remove_attr_group;
}
if (gpiod_to_irq(desc) >= 0 && (direction_may_change ||
!test_bit(FLAG_IS_OUT, &desc->flags))) {
status = device_create_file(dev, &dev_attr_edge);
if (status)
- goto fail_unregister_device;
+ goto fail_remove_attr_direction;
}
set_bit(FLAG_EXPORT, &desc->flags);
mutex_unlock(&sysfs_lock);
return 0;
+fail_remove_attr_direction:
+ device_remove_file(dev, &dev_attr_direction);
+fail_remove_attr_group:
+ sysfs_remove_group(&dev->kobj, &gpio_attr_group);
fail_unregister_device:
device_unregister(dev);
fail_unlock:
@@ -870,6 +874,7 @@
if (tdev != NULL) {
status = sysfs_create_link(&dev->kobj, &tdev->kobj,
name);
+ put_device(tdev);
} else {
status = -ENODEV;
}
@@ -923,7 +928,7 @@
}
status = sysfs_set_active_low(desc, dev, value);
-
+ put_device(dev);
unlock:
mutex_unlock(&sysfs_lock);
@@ -971,6 +976,9 @@
mutex_unlock(&sysfs_lock);
if (dev) {
+ device_remove_file(dev, &dev_attr_edge);
+ device_remove_file(dev, &dev_attr_direction);
+ sysfs_remove_group(&dev->kobj, &gpio_attr_group);
device_unregister(dev);
put_device(dev);
}
@@ -1036,6 +1044,7 @@
mutex_lock(&sysfs_lock);
dev = class_find_device(&gpio_class, NULL, chip, match_export);
if (dev) {
+ sysfs_remove_group(&dev->kobj, &gpiochip_attr_group);
put_device(dev);
device_unregister(dev);
chip->exported = 0;
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 02e52d5..b6b7d70 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -177,7 +177,7 @@
static inline void ast_open_key(struct ast_private *ast)
{
- ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xA1, 0xFF, 0x04);
+ ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x80, 0xA8);
}
#define AST_VIDMEM_SIZE_8M 0x00800000
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f60fd7b..96f874a 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -100,7 +100,7 @@
}
ast->vga2_clone = false;
} else {
- ast->chip = 2000;
+ ast->chip = AST2000;
DRM_INFO("AST 2000 detected\n");
}
}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 7fc9f72..e8f6418 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1012,8 +1012,8 @@
srcdata32[1].ul = *((u32 *)(srcxor + 4)) & 0xf0f0f0f0;
data32.b[0] = srcdata32[0].b[1] | (srcdata32[0].b[0] >> 4);
data32.b[1] = srcdata32[0].b[3] | (srcdata32[0].b[2] >> 4);
- data32.b[2] = srcdata32[0].b[1] | (srcdata32[1].b[0] >> 4);
- data32.b[3] = srcdata32[0].b[3] | (srcdata32[1].b[2] >> 4);
+ data32.b[2] = srcdata32[1].b[1] | (srcdata32[1].b[0] >> 4);
+ data32.b[3] = srcdata32[1].b[3] | (srcdata32[1].b[2] >> 4);
writel(data32.ul, dstxor);
csum += data32.ul;
diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c
index 09da339..d5902e2 100644
--- a/drivers/gpu/drm/ast/ast_ttm.c
+++ b/drivers/gpu/drm/ast/ast_ttm.c
@@ -348,6 +348,7 @@
astbo->gem.driver_private = NULL;
astbo->bo.bdev = &ast->ttm.bdev;
+ astbo->bo.bdev->dev_mapping = dev->dev_mapping;
ast_ttm_placement(astbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 8ecb601..64bfc23 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -11,6 +11,7 @@
#include <linux/module.h>
#include <linux/console.h>
#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
#include "cirrus_drv.h"
@@ -75,6 +76,41 @@
drm_put_dev(dev);
}
+static int cirrus_pm_suspend(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct drm_device *drm_dev = pci_get_drvdata(pdev);
+ struct cirrus_device *cdev = drm_dev->dev_private;
+
+ drm_kms_helper_poll_disable(drm_dev);
+
+ if (cdev->mode_info.gfbdev) {
+ console_lock();
+ fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 1);
+ console_unlock();
+ }
+
+ return 0;
+}
+
+static int cirrus_pm_resume(struct device *dev)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ struct drm_device *drm_dev = pci_get_drvdata(pdev);
+ struct cirrus_device *cdev = drm_dev->dev_private;
+
+ drm_helper_resume_force_mode(drm_dev);
+
+ if (cdev->mode_info.gfbdev) {
+ console_lock();
+ fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 0);
+ console_unlock();
+ }
+
+ drm_kms_helper_poll_enable(drm_dev);
+ return 0;
+}
+
static const struct file_operations cirrus_driver_fops = {
.owner = THIS_MODULE,
.open = drm_open,
@@ -105,11 +141,17 @@
.dumb_destroy = cirrus_dumb_destroy,
};
+static const struct dev_pm_ops cirrus_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(cirrus_pm_suspend,
+ cirrus_pm_resume)
+};
+
static struct pci_driver cirrus_pci_driver = {
.name = DRIVER_NAME,
.id_table = pciidlist,
.probe = cirrus_pci_probe,
.remove = cirrus_pci_remove,
+ .driver.pm = &cirrus_pm_ops,
};
static int __init cirrus_init(void)
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 60685b2..b86f68d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -273,8 +273,8 @@
sr07 |= 0x11;
break;
case 16:
- sr07 |= 0xc1;
- hdr = 0xc0;
+ sr07 |= 0x17;
+ hdr = 0xc1;
break;
case 24:
sr07 |= 0x15;
@@ -308,6 +308,9 @@
WREG_HDR(hdr);
cirrus_crtc_do_set_base(crtc, old_fb, x, y, 0);
+
+ /* Unblank (needed on S3 resume, vgabios doesn't do it then) */
+ outb(0x20, 0x3c0);
return 0;
}
diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c
index 2ed8cfc..c18faff 100644
--- a/drivers/gpu/drm/cirrus/cirrus_ttm.c
+++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c
@@ -353,6 +353,7 @@
cirrusbo->gem.driver_private = NULL;
cirrusbo->bo.bdev = &cirrus->ttm.bdev;
+ cirrusbo->bo.bdev->dev_mapping = dev->dev_mapping;
cirrus_ttm_placement(cirrusbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index e7e9242..8759d69 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2501,10 +2501,22 @@
r->depth = fb->depth;
r->bpp = fb->bits_per_pixel;
r->pitch = fb->pitches[0];
- if (fb->funcs->create_handle)
- ret = fb->funcs->create_handle(fb, file_priv, &r->handle);
- else
+ if (fb->funcs->create_handle) {
+ if (file_priv->is_master || capable(CAP_SYS_ADMIN)) {
+ ret = fb->funcs->create_handle(fb, file_priv,
+ &r->handle);
+ } else {
+ /* GET_FB() is an unprivileged ioctl so we must not
+ * return a buffer-handle to non-master processes! For
+ * backwards-compatibility reasons, we cannot make
+ * GET_FB() privileged, so just return an invalid handle
+ * for non-masters. */
+ r->handle = 0;
+ ret = 0;
+ }
+ } else {
ret = -ENODEV;
+ }
drm_framebuffer_unreference(fb);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 9cc247f..2ab782c 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -406,9 +406,16 @@
cmd = ioctl->cmd_drv;
}
else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) {
+ u32 drv_size;
+
ioctl = &drm_ioctls[nr];
- cmd = ioctl->cmd;
+
+ drv_size = _IOC_SIZE(ioctl->cmd);
usize = asize = _IOC_SIZE(cmd);
+ if (drv_size > asize)
+ asize = drv_size;
+
+ cmd = ioctl->cmd;
} else
goto err_i1;
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 9e62bbe..83f0ba5 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -68,6 +68,8 @@
#define EDID_QUIRK_DETAILED_SYNC_PP (1 << 6)
/* Force reduced-blanking timings for detailed modes */
#define EDID_QUIRK_FORCE_REDUCED_BLANKING (1 << 7)
+/* Force 8bpc */
+#define EDID_QUIRK_FORCE_8BPC (1 << 8)
struct detailed_mode_closure {
struct drm_connector *connector;
@@ -125,6 +127,12 @@
/* ViewSonic VA2026w */
{ "VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING },
+
+ /* Medion MD 30217 PG */
+ { "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
+
+ /* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
+ { "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
};
/*
@@ -2952,6 +2960,9 @@
drm_add_display_info(edid, &connector->display_info);
+ if (quirks & EDID_QUIRK_FORCE_8BPC)
+ connector->display_info.bpc = 8;
+
return num_modes;
}
EXPORT_SYMBOL(drm_add_edid_modes);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index cf919e3..239ef30 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -453,25 +453,21 @@
spin_lock(&dev->object_name_lock);
if (!obj->name) {
ret = idr_alloc(&dev->object_name_idr, obj, 1, 0, GFP_NOWAIT);
- obj->name = ret;
- args->name = (uint64_t) obj->name;
- spin_unlock(&dev->object_name_lock);
- idr_preload_end();
-
if (ret < 0)
goto err;
- ret = 0;
+
+ obj->name = ret;
/* Allocate a reference for the name table. */
drm_gem_object_reference(obj);
- } else {
- args->name = (uint64_t) obj->name;
- spin_unlock(&dev->object_name_lock);
- idr_preload_end();
- ret = 0;
}
+ args->name = (uint64_t) obj->name;
+ ret = 0;
+
err:
+ spin_unlock(&dev->object_name_lock);
+ idr_preload_end();
drm_gem_object_unreference_unlocked(obj);
return ret;
}
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 0a7e011..c25b7a0 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -262,9 +262,9 @@
if (obj->map_list.map)
off = (uint64_t)obj->map_list.hash.key;
- seq_printf(m, "%2d (%2d) %08llx %08Zx %p %d",
+ seq_printf(m, "%2d (%2d) %08llx %pad %p %zd",
obj->name, obj->refcount.refcount.counter,
- off, cma_obj->paddr, cma_obj->vaddr, obj->size);
+ off, &cma_obj->paddr, cma_obj->vaddr, obj->size);
seq_printf(m, "\n");
}
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 8bcce78..f92da0a 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -708,7 +708,10 @@
/* Subtract time delta from raw timestamp to get final
* vblank_time timestamp for end of vblank.
*/
- etime = ktime_sub_ns(etime, delta_ns);
+ if (delta_ns < 0)
+ etime = ktime_add_ns(etime, -delta_ns);
+ else
+ etime = ktime_sub_ns(etime, delta_ns);
*vblank_time = ktime_to_timeval(etime);
DRM_DEBUG("crtc %d : v %d p(%d,%d)@ %ld.%ld -> %ld.%ld [e %d us, %d rep]\n",
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 3b315ba..ccfc636 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -84,6 +84,14 @@
drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_master_private *master_priv;
+ /*
+ * The dri breadcrumb update races against the drm master disappearing.
+ * Instead of trying to fix this (this is by far not the only ums issue)
+ * just don't do the update in kms mode.
+ */
+ if (drm_core_check_feature(dev, DRIVER_MODESET))
+ return;
+
if (dev->primary->master) {
master_priv = dev->primary->master->driver_priv;
if (master_priv->sarea_priv)
@@ -1511,6 +1519,14 @@
dev_priv->dev = dev;
dev_priv->info = info;
+ spin_lock_init(&dev_priv->irq_lock);
+ spin_lock_init(&dev_priv->gpu_error.lock);
+ spin_lock_init(&dev_priv->rps.lock);
+ spin_lock_init(&dev_priv->gt_lock);
+ mutex_init(&dev_priv->dpio_lock);
+ mutex_init(&dev_priv->rps.hw_lock);
+ mutex_init(&dev_priv->modeset_restore_lock);
+
i915_dump_device_info(dev_priv);
if (i915_get_bridge_dev(dev)) {
@@ -1601,6 +1617,8 @@
intel_detect_pch(dev);
intel_irq_init(dev);
+ intel_pm_init(dev);
+ intel_gt_sanitize(dev);
intel_gt_init(dev);
/* Try to make sure MCHBAR is enabled before poking at it */
@@ -1626,14 +1644,6 @@
if (!IS_I945G(dev) && !IS_I945GM(dev))
pci_enable_msi(dev->pdev);
- spin_lock_init(&dev_priv->irq_lock);
- spin_lock_init(&dev_priv->gpu_error.lock);
- spin_lock_init(&dev_priv->rps.lock);
- mutex_init(&dev_priv->dpio_lock);
-
- mutex_init(&dev_priv->rps.hw_lock);
- mutex_init(&dev_priv->modeset_restore_lock);
-
dev_priv->num_plane = 1;
if (IS_VALLEYVIEW(dev))
dev_priv->num_plane = 2;
@@ -1677,6 +1687,7 @@
intel_teardown_gmbus(dev);
intel_teardown_mchbar(dev);
+ pm_qos_remove_request(&dev_priv->pm_qos);
destroy_workqueue(dev_priv->wq);
out_mtrrfree:
if (dev_priv->mm.gtt_mtrr >= 0) {
@@ -1845,8 +1856,10 @@
void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
{
+ mutex_lock(&dev->struct_mutex);
i915_gem_context_close(dev, file_priv);
i915_gem_release(dev, file_priv);
+ mutex_unlock(&dev->struct_mutex);
}
void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a2e4953..bc6cd31 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -685,7 +685,7 @@
{
int error = 0;
- intel_gt_reset(dev);
+ intel_gt_sanitize(dev);
if (drm_core_check_feature(dev, DRIVER_MODESET)) {
mutex_lock(&dev->struct_mutex);
@@ -711,7 +711,7 @@
pci_set_master(dev->pdev);
- intel_gt_reset(dev);
+ intel_gt_sanitize(dev);
/*
* Platforms with opregion should have sane BIOS, older ones (gen3 and
@@ -1247,21 +1247,21 @@
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
+ unsigned long irqflags; \
u##x val = 0; \
+ spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
if (IS_GEN5(dev_priv->dev)) \
ilk_dummy_write(dev_priv); \
if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
- unsigned long irqflags; \
- spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
if (dev_priv->forcewake_count == 0) \
dev_priv->gt.force_wake_get(dev_priv); \
val = read##y(dev_priv->regs + reg); \
if (dev_priv->forcewake_count == 0) \
dev_priv->gt.force_wake_put(dev_priv); \
- spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
} else { \
val = read##y(dev_priv->regs + reg); \
} \
+ spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
trace_i915_reg_rw(false, reg, val, sizeof(val)); \
return val; \
}
@@ -1274,8 +1274,10 @@
#define __i915_write(x, y) \
void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \
+ unsigned long irqflags; \
u32 __fifo_ret = 0; \
trace_i915_reg_rw(true, reg, val, sizeof(val)); \
+ spin_lock_irqsave(&dev_priv->gt_lock, irqflags); \
if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \
__fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \
} \
@@ -1287,6 +1289,7 @@
gen6_gt_check_fifodbg(dev_priv); \
} \
hsw_unclaimed_reg_check(dev_priv, reg); \
+ spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \
}
__i915_write(8, b)
__i915_write(16, w)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9669a0b..47d8b68 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -491,6 +491,7 @@
#define QUIRK_PIPEA_FORCE (1<<0)
#define QUIRK_LVDS_SSC_DISABLE (1<<1)
#define QUIRK_INVERT_BRIGHTNESS (1<<2)
+#define QUIRK_NO_PCH_PWM_ENABLE (1<<3)
struct intel_fbdev;
struct intel_fbc_work;
@@ -1474,9 +1475,10 @@
void i915_handle_error(struct drm_device *dev, bool wedged);
extern void intel_irq_init(struct drm_device *dev);
+extern void intel_pm_init(struct drm_device *dev);
extern void intel_hpd_init(struct drm_device *dev);
extern void intel_gt_init(struct drm_device *dev);
-extern void intel_gt_reset(struct drm_device *dev);
+extern void intel_gt_sanitize(struct drm_device *dev);
void i915_error_state_free(struct kref *error_ref);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9e35daf..0b71a0a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1160,7 +1160,8 @@
/* Manually manage the write flush as we may have not yet
* retired the buffer.
*/
- if (obj->last_write_seqno &&
+ if (ret == 0 &&
+ obj->last_write_seqno &&
i915_seqno_passed(seqno, obj->last_write_seqno)) {
obj->last_write_seqno = 0;
obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
@@ -1880,6 +1881,10 @@
u32 seqno = intel_ring_get_seqno(ring);
BUG_ON(ring == NULL);
+ if (obj->ring != ring && obj->last_write_seqno) {
+ /* Keep the seqno relative to the current ring */
+ obj->last_write_seqno = seqno;
+ }
obj->ring = ring;
/* Add a reference if we're newly entering the active list. */
@@ -2133,7 +2138,17 @@
for (i = 0; i < dev_priv->num_fence_regs; i++) {
struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
- i915_gem_write_fence(dev, i, reg->obj);
+
+ /*
+ * Commit delayed tiling changes if we have an object still
+ * attached to the fence, otherwise just clear the fence.
+ */
+ if (reg->obj) {
+ i915_gem_object_update_fence(reg->obj, reg,
+ reg->obj->tiling_mode);
+ } else {
+ i915_gem_write_fence(dev, i, NULL);
+ }
}
}
@@ -2533,7 +2548,6 @@
drm_i915_private_t *dev_priv = dev->dev_private;
int fence_reg;
int fence_pitch_shift;
- uint64_t val;
if (INTEL_INFO(dev)->gen >= 6) {
fence_reg = FENCE_REG_SANDYBRIDGE_0;
@@ -2543,8 +2557,23 @@
fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
}
+ fence_reg += reg * 8;
+
+ /* To w/a incoherency with non-atomic 64-bit register updates,
+ * we split the 64-bit update into two 32-bit writes. In order
+ * for a partial fence not to be evaluated between writes, we
+ * precede the update with write to turn off the fence register,
+ * and only enable the fence as the last step.
+ *
+ * For extra levels of paranoia, we make sure each step lands
+ * before applying the next step.
+ */
+ I915_WRITE(fence_reg, 0);
+ POSTING_READ(fence_reg);
+
if (obj) {
u32 size = obj->gtt_space->size;
+ uint64_t val;
val = (uint64_t)((obj->gtt_offset + size - 4096) &
0xfffff000) << 32;
@@ -2553,12 +2582,16 @@
if (obj->tiling_mode == I915_TILING_Y)
val |= 1 << I965_FENCE_TILING_Y_SHIFT;
val |= I965_FENCE_REG_VALID;
- } else
- val = 0;
- fence_reg += reg * 8;
- I915_WRITE64(fence_reg, val);
- POSTING_READ(fence_reg);
+ I915_WRITE(fence_reg + 4, val >> 32);
+ POSTING_READ(fence_reg + 4);
+
+ I915_WRITE(fence_reg + 0, val);
+ POSTING_READ(fence_reg);
+ } else {
+ I915_WRITE(fence_reg + 4, 0);
+ POSTING_READ(fence_reg + 4);
+ }
}
static void i915_write_fence_reg(struct drm_device *dev, int reg,
@@ -2653,6 +2686,10 @@
if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj))
mb();
+ WARN(obj && (!obj->stride || !obj->tiling_mode),
+ "bogus fence setup with stride: 0x%x, tiling mode: %i\n",
+ obj->stride, obj->tiling_mode);
+
switch (INTEL_INFO(dev)->gen) {
case 7:
case 6:
@@ -2712,6 +2749,7 @@
fence->obj = NULL;
list_del_init(&fence->lru_list);
}
+ obj->fence_dirty = false;
}
static int
@@ -2841,7 +2879,6 @@
return 0;
i915_gem_object_update_fence(obj, reg, enable);
- obj->fence_dirty = false;
return 0;
}
@@ -4412,7 +4449,7 @@
if (!mutex_is_locked(mutex))
return false;
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if defined(CONFIG_SMP) && !defined(CONFIG_DEBUG_MUTEXES)
return mutex->owner == task;
#else
/* Since UP may be pre-empted, we cannot assume that we own the lock */
@@ -4456,7 +4493,7 @@
list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
if (obj->pages_pin_count == 0)
cnt += obj->base.size >> PAGE_SHIFT;
- list_for_each_entry(obj, &dev_priv->mm.inactive_list, gtt_list)
+ list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
if (obj->pin_count == 0 && obj->pages_pin_count == 0)
cnt += obj->base.size >> PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index a1e8ecb..b10b1b1 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -113,7 +113,7 @@
case 7:
reg = I915_READ(GEN7_CXT_SIZE);
if (IS_HASWELL(dev))
- ret = HSW_CXT_TOTAL_SIZE(reg) * 64;
+ ret = HSW_CXT_TOTAL_SIZE;
else
ret = GEN7_CXT_TOTAL_SIZE(reg) * 64;
break;
@@ -291,10 +291,8 @@
{
struct drm_i915_file_private *file_priv = file->driver_priv;
- mutex_lock(&dev->struct_mutex);
idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
idr_destroy(&file_priv->context_idr);
- mutex_unlock(&dev->struct_mutex);
}
static struct i915_hw_context *
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 117ce38..6416d0d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -635,9 +635,9 @@
* relocations were valid.
*/
for (j = 0; j < exec[i].relocation_count; j++) {
- if (copy_to_user(&user_relocs[j].presumed_offset,
- &invalid_offset,
- sizeof(invalid_offset))) {
+ if (__copy_to_user(&user_relocs[j].presumed_offset,
+ &invalid_offset,
+ sizeof(invalid_offset))) {
ret = -EFAULT;
mutex_lock(&dev->struct_mutex);
goto err;
@@ -1151,18 +1151,21 @@
ret = i915_gem_do_execbuffer(dev, data, file, &exec2, exec2_list);
if (!ret) {
+ struct drm_i915_gem_exec_object __user *user_exec_list =
+ to_user_ptr(args->buffers_ptr);
+
/* Copy the new buffer offsets back to the user's exec list. */
- for (i = 0; i < args->buffer_count; i++)
- exec_list[i].offset = exec2_list[i].offset;
- /* ... and back out to userspace */
- ret = copy_to_user(to_user_ptr(args->buffers_ptr),
- exec_list,
- sizeof(*exec_list) * args->buffer_count);
- if (ret) {
- ret = -EFAULT;
- DRM_DEBUG("failed to copy %d exec entries "
- "back to user (%d)\n",
- args->buffer_count, ret);
+ for (i = 0; i < args->buffer_count; i++) {
+ ret = __copy_to_user(&user_exec_list[i].offset,
+ &exec2_list[i].offset,
+ sizeof(user_exec_list[i].offset));
+ if (ret) {
+ ret = -EFAULT;
+ DRM_DEBUG("failed to copy %d exec entries "
+ "back to user (%d)\n",
+ args->buffer_count, ret);
+ break;
+ }
}
}
@@ -1208,14 +1211,21 @@
ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
if (!ret) {
/* Copy the new buffer offsets back to the user's exec list. */
- ret = copy_to_user(to_user_ptr(args->buffers_ptr),
- exec2_list,
- sizeof(*exec2_list) * args->buffer_count);
- if (ret) {
- ret = -EFAULT;
- DRM_DEBUG("failed to copy %d exec entries "
- "back to user (%d)\n",
- args->buffer_count, ret);
+ struct drm_i915_gem_exec_object2 *user_exec_list =
+ to_user_ptr(args->buffers_ptr);
+ int i;
+
+ for (i = 0; i < args->buffer_count; i++) {
+ ret = __copy_to_user(&user_exec_list[i].offset,
+ &exec2_list[i].offset,
+ sizeof(user_exec_list[i].offset));
+ if (ret) {
+ ret = -EFAULT;
+ DRM_DEBUG("failed to copy %d exec entries "
+ "back to user\n",
+ args->buffer_count);
+ break;
+ }
}
}
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 130d1db..fa2d15b 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -222,7 +222,7 @@
}
sg = st->sgl;
- sg->offset = offset;
+ sg->offset = 0;
sg->length = size;
sg_dma_address(sg) = (dma_addr_t)dev_priv->mm.stolen_base + offset;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0aa2ef0..c8d16a6 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -70,15 +70,6 @@
[HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS
};
-static const u32 hpd_status_i965[] = {
- [HPD_CRT] = CRT_HOTPLUG_INT_STATUS,
- [HPD_SDVO_B] = SDVOB_HOTPLUG_INT_STATUS_I965,
- [HPD_SDVO_C] = SDVOC_HOTPLUG_INT_STATUS_I965,
- [HPD_PORT_B] = PORTB_HOTPLUG_INT_STATUS,
- [HPD_PORT_C] = PORTC_HOTPLUG_INT_STATUS,
- [HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS
-};
-
static const u32 hpd_status_i915[] = { /* i915 and valleyview are the same */
[HPD_CRT] = CRT_HOTPLUG_INT_STATUS,
[HPD_SDVO_B] = SDVOB_HOTPLUG_INT_STATUS_I915,
@@ -1018,6 +1009,34 @@
return ret;
}
+static void i915_error_wake_up(struct drm_i915_private *dev_priv,
+ bool reset_completed)
+{
+ struct intel_ring_buffer *ring;
+ int i;
+
+ /*
+ * Notify all waiters for GPU completion events that reset state has
+ * been changed, and that they need to restart their wait after
+ * checking for potential errors (and bail out to drop locks if there is
+ * a gpu reset pending so that i915_error_work_func can acquire them).
+ */
+
+ /* Wake up __wait_seqno, potentially holding dev->struct_mutex. */
+ for_each_ring(ring, dev_priv, i)
+ wake_up_all(&ring->irq_queue);
+
+ /* Wake up intel_crtc_wait_for_pending_flips, holding crtc->mutex. */
+ wake_up_all(&dev_priv->pending_flip_queue);
+
+ /*
+ * Signal tasks blocked in i915_gem_wait_for_error that the pending
+ * reset state is cleared.
+ */
+ if (reset_completed)
+ wake_up_all(&dev_priv->gpu_error.reset_queue);
+}
+
/**
* i915_error_work_func - do process context error handling work
* @work: work struct
@@ -1032,11 +1051,10 @@
drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t,
gpu_error);
struct drm_device *dev = dev_priv->dev;
- struct intel_ring_buffer *ring;
char *error_event[] = { "ERROR=1", NULL };
char *reset_event[] = { "RESET=1", NULL };
char *reset_done_event[] = { "ERROR=0", NULL };
- int i, ret;
+ int ret;
kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event);
@@ -1055,8 +1073,16 @@
kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE,
reset_event);
+ /*
+ * All state reset _must_ be completed before we update the
+ * reset counter, for otherwise waiters might miss the reset
+ * pending state and not properly drop locks, resulting in
+ * deadlocks with the reset work.
+ */
ret = i915_reset(dev);
+ intel_display_handle_reset(dev);
+
if (ret == 0) {
/*
* After all the gem state is reset, increment the reset
@@ -1077,12 +1103,11 @@
atomic_set(&error->reset_counter, I915_WEDGED);
}
- for_each_ring(ring, dev_priv, i)
- wake_up_all(&ring->irq_queue);
-
- intel_display_handle_reset(dev);
-
- wake_up_all(&dev_priv->gpu_error.reset_queue);
+ /*
+ * Note: The wake_up also serves as a memory barrier so that
+ * waiters see the update value of the reset counter atomic_t.
+ */
+ i915_error_wake_up(dev_priv, true);
}
}
@@ -1718,8 +1743,6 @@
void i915_handle_error(struct drm_device *dev, bool wedged)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- struct intel_ring_buffer *ring;
- int i;
i915_capture_error_state(dev);
i915_report_and_clear_eir(dev);
@@ -1729,14 +1752,28 @@
&dev_priv->gpu_error.reset_counter);
/*
- * Wakeup waiting processes so that the reset work item
- * doesn't deadlock trying to grab various locks.
+ * Wakeup waiting processes so that the reset work function
+ * i915_error_work_func doesn't deadlock trying to grab various
+ * locks. By bumping the reset counter first, the woken
+ * processes will see a reset in progress and back off,
+ * releasing their locks and then wait for the reset completion.
+ * We must do this for _all_ gpu waiters that might hold locks
+ * that the reset work needs to acquire.
+ *
+ * Note: The wake_up serves as the required memory barrier to
+ * ensure that the waiters see the updated value of the reset
+ * counter atomic_t.
*/
- for_each_ring(ring, dev_priv, i)
- wake_up_all(&ring->irq_queue);
+ i915_error_wake_up(dev_priv, false);
}
- queue_work(dev_priv->wq, &dev_priv->gpu_error.work);
+ /*
+ * Our reset work can grab modeset locks (since it needs to reset the
+ * state of outstanding pagelips). Hence it must not be run on our own
+ * dev-priv->wq work queue for otherwise the flush_work in the pageflip
+ * code will deadlock.
+ */
+ schedule_work(&dev_priv->gpu_error.work);
}
static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, int pipe)
@@ -2952,13 +2989,13 @@
u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
u32 hotplug_trigger = hotplug_status & (IS_G4X(dev) ?
HOTPLUG_INT_STATUS_G4X :
- HOTPLUG_INT_STATUS_I965);
+ HOTPLUG_INT_STATUS_I915);
DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x\n",
hotplug_status);
if (hotplug_trigger) {
if (hotplug_irq_storm_detect(dev, hotplug_trigger,
- IS_G4X(dev) ? hpd_status_gen4 : hpd_status_i965))
+ IS_G4X(dev) ? hpd_status_gen4 : hpd_status_i915))
i915_hpd_irq_setup(dev);
queue_work(dev_priv->wq,
&dev_priv->hotplug_work);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2d6b62e..35287ab 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -317,6 +317,7 @@
#define PIPE_CONTROL_GLOBAL_GTT_IVB (1<<24) /* gen7+ */
#define PIPE_CONTROL_CS_STALL (1<<20)
#define PIPE_CONTROL_TLB_INVALIDATE (1<<18)
+#define PIPE_CONTROL_MEDIA_STATE_CLEAR (1<<16)
#define PIPE_CONTROL_QW_WRITE (1<<14)
#define PIPE_CONTROL_DEPTH_STALL (1<<13)
#define PIPE_CONTROL_WRITE_FLUSH (1<<12)
@@ -617,6 +618,8 @@
will not assert AGPBUSY# and will only
be delivered when out of C3. */
#define INSTPM_FORCE_ORDERING (1<<7) /* GEN6+ */
+#define INSTPM_TLB_INVALIDATE (1<<9)
+#define INSTPM_SYNC_FLUSH (1<<5)
#define ACTHD 0x020c8
#define FW_BLC 0x020d8
#define FW_BLC2 0x020dc
@@ -906,6 +909,7 @@
#define GMBUS_CYCLE_INDEX (2<<25)
#define GMBUS_CYCLE_STOP (4<<25)
#define GMBUS_BYTE_COUNT_SHIFT 16
+#define GMBUS_BYTE_COUNT_MAX 256U
#define GMBUS_SLAVE_INDEX_SHIFT 8
#define GMBUS_SLAVE_ADDR_SHIFT 1
#define GMBUS_SLAVE_READ (1<<0)
@@ -1535,14 +1539,13 @@
GEN7_CXT_EXTENDED_SIZE(ctx_reg) + \
GEN7_CXT_GT1_SIZE(ctx_reg) + \
GEN7_CXT_VFSTATE_SIZE(ctx_reg))
-#define HSW_CXT_POWER_SIZE(ctx_reg) ((ctx_reg >> 26) & 0x3f)
-#define HSW_CXT_RING_SIZE(ctx_reg) ((ctx_reg >> 23) & 0x7)
-#define HSW_CXT_RENDER_SIZE(ctx_reg) ((ctx_reg >> 15) & 0xff)
-#define HSW_CXT_TOTAL_SIZE(ctx_reg) (HSW_CXT_POWER_SIZE(ctx_reg) + \
- HSW_CXT_RING_SIZE(ctx_reg) + \
- HSW_CXT_RENDER_SIZE(ctx_reg) + \
- GEN7_CXT_VFSTATE_SIZE(ctx_reg))
-
+/* Haswell does have the CXT_SIZE register however it does not appear to be
+ * valid. Now, docs explain in dwords what is in the context object. The full
+ * size is 70720 bytes, however, the power context and execlist context will
+ * never be saved (power context is stored elsewhere, and execlists don't work
+ * on HSW) - so the final size is 66944 bytes, which rounds to 17 pages.
+ */
+#define HSW_CXT_TOTAL_SIZE (17 * PAGE_SIZE)
/*
* Overlay regs
@@ -1674,10 +1677,20 @@
#define CRT_HOTPLUG_DETECT_VOLTAGE_475MV (1 << 2)
#define PORT_HOTPLUG_STAT (dev_priv->info->display_mmio_offset + 0x61114)
-/* HDMI/DP bits are gen4+ */
-#define PORTB_HOTPLUG_LIVE_STATUS (1 << 29)
-#define PORTC_HOTPLUG_LIVE_STATUS (1 << 28)
-#define PORTD_HOTPLUG_LIVE_STATUS (1 << 27)
+/*
+ * HDMI/DP bits are gen4+
+ *
+ * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused.
+ * Please check the detailed lore in the commit message for for experimental
+ * evidence.
+ */
+#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 29)
+#define PORTC_HOTPLUG_LIVE_STATUS_G4X (1 << 28)
+#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 27)
+/* VLV DP/HDMI bits again match Bspec */
+#define PORTD_HOTPLUG_LIVE_STATUS_VLV (1 << 27)
+#define PORTC_HOTPLUG_LIVE_STATUS_VLV (1 << 28)
+#define PORTB_HOTPLUG_LIVE_STATUS_VLV (1 << 29)
#define PORTD_HOTPLUG_INT_STATUS (3 << 21)
#define PORTC_HOTPLUG_INT_STATUS (3 << 19)
#define PORTB_HOTPLUG_INT_STATUS (3 << 17)
@@ -1691,6 +1704,12 @@
/* SDVO is different across gen3/4 */
#define SDVOC_HOTPLUG_INT_STATUS_G4X (1 << 3)
#define SDVOB_HOTPLUG_INT_STATUS_G4X (1 << 2)
+/*
+ * Bspec seems to be seriously misleaded about the SDVO hpd bits on i965g/gm,
+ * since reality corrobates that they're the same as on gen3. But keep these
+ * bits here (and the comment!) to help any other lost wanderers back onto the
+ * right tracks.
+ */
#define SDVOC_HOTPLUG_INT_STATUS_I965 (3 << 4)
#define SDVOB_HOTPLUG_INT_STATUS_I965 (3 << 2)
#define SDVOC_HOTPLUG_INT_STATUS_I915 (1 << 7)
@@ -1702,13 +1721,6 @@
PORTC_HOTPLUG_INT_STATUS | \
PORTD_HOTPLUG_INT_STATUS)
-#define HOTPLUG_INT_STATUS_I965 (CRT_HOTPLUG_INT_STATUS | \
- SDVOB_HOTPLUG_INT_STATUS_I965 | \
- SDVOC_HOTPLUG_INT_STATUS_I965 | \
- PORTB_HOTPLUG_INT_STATUS | \
- PORTC_HOTPLUG_INT_STATUS | \
- PORTD_HOTPLUG_INT_STATUS)
-
#define HOTPLUG_INT_STATUS_I915 (CRT_HOTPLUG_INT_STATUS | \
SDVOB_HOTPLUG_INT_STATUS_I915 | \
SDVOC_HOTPLUG_INT_STATUS_I915 | \
@@ -4246,7 +4258,7 @@
#define EDP_LINK_TRAIN_600MV_0DB_IVB (0x30 <<22)
#define EDP_LINK_TRAIN_600MV_3_5DB_IVB (0x36 <<22)
#define EDP_LINK_TRAIN_800MV_0DB_IVB (0x38 <<22)
-#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x33 <<22)
+#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x3e <<22)
/* legacy values */
#define EDP_LINK_TRAIN_500MV_0DB_IVB (0x00 <<22)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 95070b2..49acec1 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -657,7 +657,7 @@
DRM_DEBUG_KMS("Set default to SSC at %dMHz\n", dev_priv->lvds_ssc_freq);
}
-static int __init intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
+static int intel_no_opregion_vbt_callback(const struct dmi_system_id *id)
{
DRM_DEBUG_KMS("Falling back to manually reading VBT from "
"VBIOS ROM for %s\n",
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 58b4a53..53435a9 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -702,7 +702,7 @@
.destroy = intel_encoder_destroy,
};
-static int __init intel_no_crt_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_crt_dmi_callback(const struct dmi_system_id *id)
{
DRM_INFO("Skipping CRT initialization for %s\n", id->ident);
return 1;
@@ -717,6 +717,14 @@
DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"),
},
},
+ {
+ .callback = intel_no_crt_dmi_callback,
+ .ident = "DELL XPS 8700",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"),
+ },
+ },
{ }
};
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index fb961bb..7ce3834 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -684,7 +684,7 @@
struct intel_digital_port *intel_dig_port =
enc_to_dig_port(encoder);
- intel_dp->DP = intel_dig_port->port_reversal |
+ intel_dp->DP = intel_dig_port->saved_port_bits |
DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
switch (intel_dp->lane_count) {
case 1:
@@ -1193,12 +1193,18 @@
enum pipe pipe;
struct intel_crtc *intel_crtc;
+ dev_priv->ddi_plls.spll_refcount = 0;
+ dev_priv->ddi_plls.wrpll1_refcount = 0;
+ dev_priv->ddi_plls.wrpll2_refcount = 0;
+
for_each_pipe(pipe) {
intel_crtc =
to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
- if (!intel_crtc->active)
+ if (!intel_crtc->active) {
+ intel_crtc->ddi_pll_sel = PORT_CLK_SEL_NONE;
continue;
+ }
intel_crtc->ddi_pll_sel = intel_ddi_get_crtc_pll(dev_priv,
pipe);
@@ -1324,7 +1330,8 @@
* enabling the port.
*/
I915_WRITE(DDI_BUF_CTL(port),
- intel_dig_port->port_reversal | DDI_BUF_CTL_ENABLE);
+ intel_dig_port->saved_port_bits |
+ DDI_BUF_CTL_ENABLE);
} else if (type == INTEL_OUTPUT_EDP) {
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
@@ -1543,8 +1550,9 @@
intel_encoder->get_hw_state = intel_ddi_get_hw_state;
intel_dig_port->port = port;
- intel_dig_port->port_reversal = I915_READ(DDI_BUF_CTL(port)) &
- DDI_BUF_PORT_REVERSAL;
+ intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
+ (DDI_BUF_PORT_REVERSAL |
+ DDI_A_4_LANES);
if (hdmi_connector)
intel_dig_port->hdmi.hdmi_reg = DDI_BUF_CTL(port);
intel_dig_port->dp.output_reg = DDI_BUF_CTL(port);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 56746dc..8814b0d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3946,8 +3946,6 @@
* consider. */
void intel_connector_dpms(struct drm_connector *connector, int mode)
{
- struct intel_encoder *encoder = intel_attached_encoder(connector);
-
/* All the simple cases only support two dpms states. */
if (mode != DRM_MODE_DPMS_ON)
mode = DRM_MODE_DPMS_OFF;
@@ -3958,10 +3956,8 @@
connector->dpms = mode;
/* Only need to change hw state when actually enabled */
- if (encoder->base.crtc)
- intel_encoder_dpms(encoder, mode);
- else
- WARN_ON(encoder->connectors_active != false);
+ if (connector->encoder)
+ intel_encoder_dpms(to_intel_encoder(connector->encoder), mode);
intel_modeset_check_state(connector->dev);
}
@@ -4333,7 +4329,8 @@
static void i9xx_update_pll(struct intel_crtc *crtc,
intel_clock_t *reduced_clock,
- int num_connectors)
+ int num_connectors,
+ bool needs_tv_clock)
{
struct drm_device *dev = crtc->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4391,7 +4388,7 @@
if (INTEL_INFO(dev)->gen >= 4)
dpll |= (6 << PLL_LOAD_PULSE_PHASE_SHIFT);
- if (is_sdvo && intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_TVOUT))
+ if (is_sdvo && needs_tv_clock)
dpll |= PLL_REF_INPUT_TVCLKINBC;
else if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_TVOUT))
/* XXX: just matching BIOS for now */
@@ -4563,6 +4560,10 @@
pipeconf = I915_READ(PIPECONF(intel_crtc->pipe));
+ if (dev_priv->quirks & QUIRK_PIPEA_FORCE &&
+ I915_READ(PIPECONF(intel_crtc->pipe)) & PIPECONF_ENABLE)
+ pipeconf |= PIPECONF_ENABLE;
+
if (intel_crtc->pipe == 0 && INTEL_INFO(dev)->gen < 4) {
/* Enable pixel doubling when the dot clock is > 90% of the (display)
* core speed.
@@ -4716,7 +4717,8 @@
else
i9xx_update_pll(intel_crtc,
has_reduced_clock ? &reduced_clock : NULL,
- num_connectors);
+ num_connectors,
+ is_sdvo && is_tv);
/* Set up the display plane register */
dspcntr = DISPPLANE_GAMMA_ENABLE;
@@ -5223,7 +5225,7 @@
uint16_t postoff = 0;
if (intel_crtc->config.limited_color_range)
- postoff = (16 * (1 << 13) / 255) & 0x1fff;
+ postoff = (16 * (1 << 12) / 255) & 0x1fff;
I915_WRITE(PIPE_CSC_POSTOFF_HI(pipe), postoff);
I915_WRITE(PIPE_CSC_POSTOFF_ME(pipe), postoff);
@@ -6260,7 +6262,9 @@
intel_crtc->cursor_visible = visible;
}
/* and commit changes on next vblank */
+ POSTING_READ(CURCNTR(pipe));
I915_WRITE(CURBASE(pipe), base);
+ POSTING_READ(CURBASE(pipe));
}
static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
@@ -6287,7 +6291,9 @@
intel_crtc->cursor_visible = visible;
}
/* and commit changes on next vblank */
+ POSTING_READ(CURCNTR_IVB(pipe));
I915_WRITE(CURBASE_IVB(pipe), base);
+ POSTING_READ(CURBASE_IVB(pipe));
}
/* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
@@ -8146,15 +8152,20 @@
}
static bool
-is_crtc_connector_off(struct drm_crtc *crtc, struct drm_connector *connectors,
- int num_connectors)
+is_crtc_connector_off(struct drm_mode_set *set)
{
int i;
- for (i = 0; i < num_connectors; i++)
- if (connectors[i].encoder &&
- connectors[i].encoder->crtc == crtc &&
- connectors[i].dpms != DRM_MODE_DPMS_ON)
+ if (set->num_connectors == 0)
+ return false;
+
+ if (WARN_ON(set->connectors == NULL))
+ return false;
+
+ for (i = 0; i < set->num_connectors; i++)
+ if (set->connectors[i]->encoder &&
+ set->connectors[i]->encoder->crtc == set->crtc &&
+ set->connectors[i]->dpms != DRM_MODE_DPMS_ON)
return true;
return false;
@@ -8167,10 +8178,8 @@
/* We should be able to check here if the fb has the same properties
* and then just flip_or_move it */
- if (set->connectors != NULL &&
- is_crtc_connector_off(set->crtc, *set->connectors,
- set->num_connectors)) {
- config->mode_changed = true;
+ if (is_crtc_connector_off(set)) {
+ config->mode_changed = true;
} else if (set->crtc->fb != set->fb) {
/* If we have no fb then treat it as a full mode set */
if (set->crtc->fb == NULL) {
@@ -8914,6 +8923,17 @@
DRM_INFO("applying inverted panel brightness quirk\n");
}
+/*
+ * Some machines (Dell XPS13) suffer broken backlight controls if
+ * BLM_PCH_PWM_ENABLE is set.
+ */
+static void quirk_no_pcm_pwm_enable(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ dev_priv->quirks |= QUIRK_NO_PCH_PWM_ENABLE;
+ DRM_INFO("applying no-PCH_PWM_ENABLE quirk\n");
+}
+
struct intel_quirk {
int device;
int subsystem_vendor;
@@ -8983,6 +9003,11 @@
/* Acer Aspire 4736Z */
{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
+
+ /* Dell XPS13 HD Sandy Bridge */
+ { 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
+ /* Dell XPS13 HD and XPS13 FHD Ivy Bridge */
+ { 0x0166, 0x1028, 0x058b, quirk_no_pcm_pwm_enable },
};
static void intel_init_quirks(struct drm_device *dev)
@@ -9098,15 +9123,6 @@
intel_disable_fbc(dev);
}
-static void
-intel_connector_break_all_links(struct intel_connector *connector)
-{
- connector->base.dpms = DRM_MODE_DPMS_OFF;
- connector->base.encoder = NULL;
- connector->encoder->connectors_active = false;
- connector->encoder->base.crtc = NULL;
-}
-
static void intel_enable_pipe_a(struct drm_device *dev)
{
struct intel_connector *connector;
@@ -9188,8 +9204,17 @@
if (connector->encoder->base.crtc != &crtc->base)
continue;
- intel_connector_break_all_links(connector);
+ connector->base.dpms = DRM_MODE_DPMS_OFF;
+ connector->base.encoder = NULL;
}
+ /* multiple connectors may have the same encoder:
+ * handle them and break crtc link separately */
+ list_for_each_entry(connector, &dev->mode_config.connector_list,
+ base.head)
+ if (connector->encoder->base.crtc == &crtc->base) {
+ connector->encoder->base.crtc = NULL;
+ connector->encoder->connectors_active = false;
+ }
WARN_ON(crtc->active);
crtc->base.enabled = false;
@@ -9260,6 +9285,8 @@
drm_get_encoder_name(&encoder->base));
encoder->disable(encoder);
}
+ encoder->base.crtc = NULL;
+ encoder->connectors_active = false;
/* Inconsistent output/port/pipe state happens presumably due to
* a bug in one of the get_hw_state functions. Or someplace else
@@ -9270,8 +9297,8 @@
base.head) {
if (connector->encoder != encoder)
continue;
-
- intel_connector_break_all_links(connector);
+ connector->base.dpms = DRM_MODE_DPMS_OFF;
+ connector->base.encoder = NULL;
}
}
/* Enabled encoders without active connectors will be fixed in
@@ -9431,7 +9458,9 @@
intel_setup_overlay(dev);
+ mutex_lock(&dev->mode_config.mutex);
intel_modeset_setup_hw_state(dev, false);
+ mutex_unlock(&dev->mode_config.mutex);
}
void intel_modeset_cleanup(struct drm_device *dev)
@@ -9505,14 +9534,15 @@
int intel_modeset_vga_set_state(struct drm_device *dev, bool state)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
u16 gmch_ctrl;
- pci_read_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, &gmch_ctrl);
+ pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl);
if (state)
gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
else
gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
- pci_write_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, gmch_ctrl);
+ pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl);
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 70789b1..cfd327c 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -604,7 +604,18 @@
DRM_DEBUG_KMS("aux_ch native nack\n");
return -EREMOTEIO;
case AUX_NATIVE_REPLY_DEFER:
- udelay(100);
+ /*
+ * For now, just give more slack to branch devices. We
+ * could check the DPCD for I2C bit rate capabilities,
+ * and if available, adjust the interval. We could also
+ * be more careful with DP-to-Legacy adapters where a
+ * long legacy cable may force very low I2C bit rates.
+ */
+ if (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] &
+ DP_DWN_STRM_PORT_PRESENT)
+ usleep_range(500, 600);
+ else
+ usleep_range(300, 400);
continue;
default:
DRM_ERROR("aux_ch invalid native reply 0x%02x\n",
@@ -2266,18 +2277,34 @@
return status;
}
- switch (intel_dig_port->port) {
- case PORT_B:
- bit = PORTB_HOTPLUG_LIVE_STATUS;
- break;
- case PORT_C:
- bit = PORTC_HOTPLUG_LIVE_STATUS;
- break;
- case PORT_D:
- bit = PORTD_HOTPLUG_LIVE_STATUS;
- break;
- default:
- return connector_status_unknown;
+ if (IS_VALLEYVIEW(dev)) {
+ switch (intel_dig_port->port) {
+ case PORT_B:
+ bit = PORTB_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ case PORT_C:
+ bit = PORTC_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ case PORT_D:
+ bit = PORTD_HOTPLUG_LIVE_STATUS_VLV;
+ break;
+ default:
+ return connector_status_unknown;
+ }
+ } else {
+ switch (intel_dig_port->port) {
+ case PORT_B:
+ bit = PORTB_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ case PORT_C:
+ bit = PORTC_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ case PORT_D:
+ bit = PORTD_HOTPLUG_LIVE_STATUS_G4X;
+ break;
+ default:
+ return connector_status_unknown;
+ }
}
if ((I915_READ(PORT_HOTPLUG_STAT) & bit) == 0)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 624a9e6..7cd5584 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -426,7 +426,7 @@
struct intel_digital_port {
struct intel_encoder base;
enum port port;
- u32 port_reversal;
+ u32 saved_port_bits;
struct intel_dp dp;
struct intel_hdmi hdmi;
};
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 639fe19..4a21e13 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -276,18 +276,17 @@
}
static int
-gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
- u32 gmbus1_index)
+gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
+ unsigned short addr, u8 *buf, unsigned int len,
+ u32 gmbus1_index)
{
int reg_offset = dev_priv->gpio_mmio_base;
- u16 len = msg->len;
- u8 *buf = msg->buf;
I915_WRITE(GMBUS1 + reg_offset,
gmbus1_index |
GMBUS_CYCLE_WAIT |
(len << GMBUS_BYTE_COUNT_SHIFT) |
- (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) |
+ (addr << GMBUS_SLAVE_ADDR_SHIFT) |
GMBUS_SLAVE_READ | GMBUS_SW_RDY);
while (len) {
int ret;
@@ -309,11 +308,35 @@
}
static int
-gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
+gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
+ u32 gmbus1_index)
+{
+ u8 *buf = msg->buf;
+ unsigned int rx_size = msg->len;
+ unsigned int len;
+ int ret;
+
+ do {
+ len = min(rx_size, GMBUS_BYTE_COUNT_MAX);
+
+ ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
+ buf, len, gmbus1_index);
+ if (ret)
+ return ret;
+
+ rx_size -= len;
+ buf += len;
+ } while (rx_size != 0);
+
+ return 0;
+}
+
+static int
+gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv,
+ unsigned short addr, u8 *buf, unsigned int len)
{
int reg_offset = dev_priv->gpio_mmio_base;
- u16 len = msg->len;
- u8 *buf = msg->buf;
+ unsigned int chunk_size = len;
u32 val, loop;
val = loop = 0;
@@ -325,8 +348,8 @@
I915_WRITE(GMBUS3 + reg_offset, val);
I915_WRITE(GMBUS1 + reg_offset,
GMBUS_CYCLE_WAIT |
- (msg->len << GMBUS_BYTE_COUNT_SHIFT) |
- (msg->addr << GMBUS_SLAVE_ADDR_SHIFT) |
+ (chunk_size << GMBUS_BYTE_COUNT_SHIFT) |
+ (addr << GMBUS_SLAVE_ADDR_SHIFT) |
GMBUS_SLAVE_WRITE | GMBUS_SW_RDY);
while (len) {
int ret;
@@ -343,6 +366,29 @@
if (ret)
return ret;
}
+
+ return 0;
+}
+
+static int
+gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg)
+{
+ u8 *buf = msg->buf;
+ unsigned int tx_size = msg->len;
+ unsigned int len;
+ int ret;
+
+ do {
+ len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
+
+ ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len);
+ if (ret)
+ return ret;
+
+ buf += len;
+ tx_size -= len;
+ } while (tx_size != 0);
+
return 0;
}
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 29412cc..f5d1dc5 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -694,7 +694,7 @@
.destroy = intel_encoder_destroy,
};
-static int __init intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
+static int intel_no_lvds_dmi_callback(const struct dmi_system_id *id)
{
DRM_INFO("Skipping LVDS initialization for %s\n", id->ident);
return 1;
@@ -869,6 +869,30 @@
DMI_MATCH(DMI_PRODUCT_NAME, "ESPRIMO Q900"),
},
},
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Intel D410PT",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+ DMI_MATCH(DMI_BOARD_NAME, "D410PT"),
+ },
+ },
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Intel D425KT",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "D425KT"),
+ },
+ },
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Intel D510MO",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Intel"),
+ DMI_EXACT_MATCH(DMI_BOARD_NAME, "D510MO"),
+ },
+ },
{ } /* terminating entry */
};
@@ -1073,6 +1097,17 @@
int pipe;
u8 pin;
+ /*
+ * Unlock registers and just leave them unlocked. Do this before
+ * checking quirk lists to avoid bogus WARNINGs.
+ */
+ if (HAS_PCH_SPLIT(dev)) {
+ I915_WRITE(PCH_PP_CONTROL,
+ I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
+ } else {
+ I915_WRITE(PP_CONTROL,
+ I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
+ }
if (!intel_lvds_supported(dev))
return false;
@@ -1256,17 +1291,6 @@
DRM_DEBUG_KMS("detected %s-link lvds configuration\n",
lvds_encoder->is_dual_link ? "dual" : "single");
- /*
- * Unlock registers and just
- * leave them unlocked
- */
- if (HAS_PCH_SPLIT(dev)) {
- I915_WRITE(PCH_PP_CONTROL,
- I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS);
- } else {
- I915_WRITE(PP_CONTROL,
- I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS);
- }
lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
DRM_DEBUG_KMS("lid notifier registration failed\n");
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index eb5e6e9..33cb87f 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -354,7 +354,8 @@
POSTING_READ(reg);
I915_WRITE(reg, tmp | BLM_PWM_ENABLE);
- if (HAS_PCH_SPLIT(dev)) {
+ if (HAS_PCH_SPLIT(dev) &&
+ !(dev_priv->quirks & QUIRK_NO_PCH_PWM_ENABLE)) {
tmp = I915_READ(BLC_PWM_PCH_CTL1);
tmp |= BLM_PCH_PWM_ENABLE;
tmp &= ~BLM_PCH_OVERRIDE_ENABLE;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index aa01128..94ad6bc 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4486,7 +4486,7 @@
gen6_gt_check_fifodbg(dev_priv);
}
-void intel_gt_reset(struct drm_device *dev)
+void intel_gt_sanitize(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4497,26 +4497,61 @@
if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev))
__gen6_gt_force_wake_mt_reset(dev_priv);
}
+
+ /* BIOS often leaves RC6 enabled, but disable it for hw init */
+ if (INTEL_INFO(dev)->gen >= 6)
+ intel_disable_gt_powersave(dev);
}
void intel_gt_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- spin_lock_init(&dev_priv->gt_lock);
-
- intel_gt_reset(dev);
-
if (IS_VALLEYVIEW(dev)) {
dev_priv->gt.force_wake_get = vlv_force_wake_get;
dev_priv->gt.force_wake_put = vlv_force_wake_put;
- } else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
+ } else if (IS_HASWELL(dev)) {
dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get;
dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put;
+ } else if (IS_IVYBRIDGE(dev)) {
+ u32 ecobus;
+
+ /* IVB configs may use multi-threaded forcewake */
+
+ /* A small trick here - if the bios hasn't configured
+ * MT forcewake, and if the device is in RC6, then
+ * force_wake_mt_get will not wake the device and the
+ * ECOBUS read will return zero. Which will be
+ * (correctly) interpreted by the test below as MT
+ * forcewake being disabled.
+ */
+ mutex_lock(&dev->struct_mutex);
+ __gen6_gt_force_wake_mt_get(dev_priv);
+ ecobus = I915_READ_NOTRACE(ECOBUS);
+ __gen6_gt_force_wake_mt_put(dev_priv);
+ mutex_unlock(&dev->struct_mutex);
+
+ if (ecobus & FORCEWAKE_MT_ENABLE) {
+ dev_priv->gt.force_wake_get =
+ __gen6_gt_force_wake_mt_get;
+ dev_priv->gt.force_wake_put =
+ __gen6_gt_force_wake_mt_put;
+ } else {
+ DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
+ DRM_INFO("when using vblank-synced partial screen updates.\n");
+ dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
+ dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
+ }
} else if (IS_GEN6(dev)) {
dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
}
+}
+
+void intel_pm_init(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
intel_gen6_powersave_work);
}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 1d5d613..ef4cde1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -314,12 +314,15 @@
flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+ flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
/*
* TLB invalidate requires a post-sync write.
*/
flags |= PIPE_CONTROL_QW_WRITE;
flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+ flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
+
/* Workaround: we must issue a pipe_control with CS-stall bit
* set before a pipe_control command that has the state cache
* invalidate bit set. */
@@ -396,6 +399,9 @@
}
}
+ /* Enforce ordering by reading HEAD register back */
+ I915_READ_HEAD(ring);
+
/* Initialize the ring. This must happen _after_ we've cleared the ring
* registers with the above sequence (the readback of the HEAD registers
* also enforces ordering), otherwise the hw might lose the new ring
@@ -490,9 +496,6 @@
struct pipe_control *pc = ring->private;
struct drm_i915_gem_object *obj;
- if (!ring->private)
- return;
-
obj = pc->obj;
kunmap(sg_page(obj->pages->sgl));
@@ -500,7 +503,6 @@
drm_gem_object_unreference(&obj->base);
kfree(pc);
- ring->private = NULL;
}
static int init_render_ring(struct intel_ring_buffer *ring)
@@ -571,7 +573,10 @@
if (HAS_BROKEN_CS_TLB(dev))
drm_gem_object_unreference(to_gem_object(ring->private));
- cleanup_pipe_control(ring);
+ if (INTEL_INFO(dev)->gen >= 5)
+ cleanup_pipe_control(ring);
+
+ ring->private = NULL;
}
static void
@@ -908,6 +913,18 @@
I915_WRITE(mmio, (u32)ring->status_page.gfx_addr);
POSTING_READ(mmio);
+
+ /* Flush the TLB for this page */
+ if (INTEL_INFO(dev)->gen >= 6) {
+ u32 reg = RING_INSTPM(ring->mmio_base);
+ I915_WRITE(reg,
+ _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE |
+ INSTPM_SYNC_FLUSH));
+ if (wait_for((I915_READ(reg) & INSTPM_SYNC_FLUSH) == 0,
+ 1000))
+ DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n",
+ ring->name);
+ }
}
static int
@@ -1448,8 +1465,8 @@
return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_request);
}
-static int __intel_ring_begin(struct intel_ring_buffer *ring,
- int bytes)
+static int __intel_ring_prepare(struct intel_ring_buffer *ring,
+ int bytes)
{
int ret;
@@ -1465,7 +1482,6 @@
return ret;
}
- ring->space -= bytes;
return 0;
}
@@ -1480,12 +1496,17 @@
if (ret)
return ret;
+ ret = __intel_ring_prepare(ring, num_dwords * sizeof(uint32_t));
+ if (ret)
+ return ret;
+
/* Preallocate the olr before touching the ring */
ret = intel_ring_alloc_seqno(ring);
if (ret)
return ret;
- return __intel_ring_begin(ring, num_dwords * sizeof(uint32_t));
+ ring->space -= num_dwords * sizeof(uint32_t);
+ return 0;
}
void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index b945bc5..7c4e312 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -856,6 +856,10 @@
struct drm_device *dev = encoder->base.dev;
struct drm_i915_private *dev_priv = dev->dev_private;
+ /* Prevents vblank waits from timing out in intel_tv_detect_type() */
+ intel_wait_for_vblank(encoder->base.dev,
+ to_intel_crtc(encoder->base.crtc)->pipe);
+
I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
}
@@ -921,6 +925,14 @@
DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
pipe_config->pipe_bpp = 8*3;
+ /* TV has it's own notion of sync and other mode flags, so clear them. */
+ pipe_config->adjusted_mode.flags = 0;
+
+ /*
+ * FIXME: We don't check whether the input mode is actually what we want
+ * or whether userspace is doing something stupid.
+ */
+
return true;
}
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index bf29b2f..988911a 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -198,7 +198,8 @@
struct ttm_bo_device bdev;
} ttm;
- u32 reg_1e24; /* SE model number */
+ /* SE model number stored in reg 0x1e24 */
+ u32 unique_rev_id;
};
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 9905923..dafe049 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -176,7 +176,7 @@
/* stash G200 SE model number for later use */
if (IS_G200_SE(mdev))
- mdev->reg_1e24 = RREG32(0x1e24);
+ mdev->unique_rev_id = RREG32(0x1e24);
ret = mga_vram_init(mdev);
if (ret)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index ee66bad..f6341e8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1008,7 +1008,7 @@
if (IS_G200_SE(mdev)) {
- if (mdev->reg_1e24 >= 0x02) {
+ if (mdev->unique_rev_id >= 0x02) {
u8 hi_pri_lvl;
u32 bpp;
u32 mb;
@@ -1038,7 +1038,7 @@
WREG8(MGAREG_CRTCEXT_DATA, hi_pri_lvl);
} else {
WREG8(MGAREG_CRTCEXT_INDEX, 0x06);
- if (mdev->reg_1e24 >= 0x01)
+ if (mdev->unique_rev_id >= 0x01)
WREG8(MGAREG_CRTCEXT_DATA, 0x03);
else
WREG8(MGAREG_CRTCEXT_DATA, 0x04);
@@ -1410,6 +1410,32 @@
return ret;
}
+static uint32_t mga_vga_calculate_mode_bandwidth(struct drm_display_mode *mode,
+ int bits_per_pixel)
+{
+ uint32_t total_area, divisor;
+ int64_t active_area, pixels_per_second, bandwidth;
+ uint64_t bytes_per_pixel = (bits_per_pixel + 7) / 8;
+
+ divisor = 1024;
+
+ if (!mode->htotal || !mode->vtotal || !mode->clock)
+ return 0;
+
+ active_area = mode->hdisplay * mode->vdisplay;
+ total_area = mode->htotal * mode->vtotal;
+
+ pixels_per_second = active_area * mode->clock * 1000;
+ do_div(pixels_per_second, total_area);
+
+ bandwidth = pixels_per_second * bytes_per_pixel * 100;
+ do_div(bandwidth, divisor);
+
+ return (uint32_t)(bandwidth);
+}
+
+#define MODE_BANDWIDTH MODE_BAD
+
static int mga_vga_mode_valid(struct drm_connector *connector,
struct drm_display_mode *mode)
{
@@ -1421,7 +1447,45 @@
int bpp = 32;
int i = 0;
- /* FIXME: Add bandwidth and g200se limitations */
+ if (IS_G200_SE(mdev)) {
+ if (mdev->unique_rev_id == 0x01) {
+ if (mode->hdisplay > 1600)
+ return MODE_VIRTUAL_X;
+ if (mode->vdisplay > 1200)
+ return MODE_VIRTUAL_Y;
+ if (mga_vga_calculate_mode_bandwidth(mode, bpp)
+ > (24400 * 1024))
+ return MODE_BANDWIDTH;
+ } else if (mdev->unique_rev_id >= 0x02) {
+ if (mode->hdisplay > 1920)
+ return MODE_VIRTUAL_X;
+ if (mode->vdisplay > 1200)
+ return MODE_VIRTUAL_Y;
+ if (mga_vga_calculate_mode_bandwidth(mode, bpp)
+ > (30100 * 1024))
+ return MODE_BANDWIDTH;
+ }
+ } else if (mdev->type == G200_WB) {
+ if (mode->hdisplay > 1280)
+ return MODE_VIRTUAL_X;
+ if (mode->vdisplay > 1024)
+ return MODE_VIRTUAL_Y;
+ if (mga_vga_calculate_mode_bandwidth(mode,
+ bpp > (31877 * 1024)))
+ return MODE_BANDWIDTH;
+ } else if (mdev->type == G200_EV &&
+ (mga_vga_calculate_mode_bandwidth(mode, bpp)
+ > (32700 * 1024))) {
+ return MODE_BANDWIDTH;
+ } else if (mdev->type == G200_EH &&
+ (mga_vga_calculate_mode_bandwidth(mode, bpp)
+ > (37500 * 1024))) {
+ return MODE_BANDWIDTH;
+ } else if (mdev->type == G200_ER &&
+ (mga_vga_calculate_mode_bandwidth(mode,
+ bpp) > (55000 * 1024))) {
+ return MODE_BANDWIDTH;
+ }
if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 401c989..d2cb32f 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -347,6 +347,7 @@
mgabo->gem.driver_private = NULL;
mgabo->bo.bdev = &mdev->ttm.bdev;
+ mgabo->bo.bdev->dev_mapping = dev->dev_mapping;
mgag200_ttm_placement(mgabo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
index f02fd9f..a66b27c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dacnv50.c
@@ -49,18 +49,23 @@
nv50_dac_sense(struct nv50_disp_priv *priv, int or, u32 loadval)
{
const u32 doff = (or * 0x800);
- int load = -EINVAL;
+
nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80150000);
nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
+
nv_wr32(priv, 0x61a00c + doff, 0x00100000 | loadval);
mdelay(9);
udelay(500);
- nv_wr32(priv, 0x61a00c + doff, 0x80000000);
- load = (nv_rd32(priv, 0x61a00c + doff) & 0x38000000) >> 27;
- nv_wr32(priv, 0x61a00c + doff, 0x00000000);
+ loadval = nv_mask(priv, 0x61a00c + doff, 0xffffffff, 0x00000000);
+
nv_mask(priv, 0x61a004 + doff, 0x807f0000, 0x80550000);
nv_wait(priv, 0x61a004 + doff, 0x80000000, 0x00000000);
- return load;
+
+ nv_debug(priv, "DAC%d sense: 0x%08x\n", or, loadval);
+ if (!(loadval & 0x80000000))
+ return -ETIMEDOUT;
+
+ return (loadval & 0x38000000) >> 27;
}
int
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
index 373dbcc5..a19e7d7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanva3.c
@@ -36,6 +36,8 @@
if (data && data[0]) {
for (i = 0; i < size; i++)
nv_wr32(priv, 0x61c440 + soff, (i << 8) | data[i]);
+ for (; i < 0x60; i++)
+ nv_wr32(priv, 0x61c440 + soff, (i << 8));
nv_mask(priv, 0x61c448 + soff, 0x80000003, 0x80000003);
} else
if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
index dc57e24..7176393 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdanvd0.c
@@ -41,6 +41,8 @@
if (data && data[0]) {
for (i = 0; i < size; i++)
nv_wr32(priv, 0x10ec00 + soff, (i << 8) | data[i]);
+ for (; i < 0x60; i++)
+ nv_wr32(priv, 0x10ec00 + soff, (i << 8));
nv_mask(priv, 0x10ec10 + soff, 0x80000003, 0x80000003);
} else
if (data) {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c
index f065fc2..db8c6fd 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/hdminva3.c
@@ -55,6 +55,10 @@
nv_wr32(priv, 0x61c510 + soff, 0x00000000);
nv_mask(priv, 0x61c500 + soff, 0x00000001, 0x00000001);
+ nv_mask(priv, 0x61c5d0 + soff, 0x00070001, 0x00010001); /* SPARE, HW_CTS */
+ nv_mask(priv, 0x61c568 + soff, 0x00010101, 0x00000000); /* ACR_CTRL, ?? */
+ nv_mask(priv, 0x61c578 + soff, 0x80000000, 0x80000000); /* ACR_0441_ENABLE */
+
/* ??? */
nv_mask(priv, 0x61733c, 0x00100000, 0x00100000); /* RESETF */
nv_mask(priv, 0x61733c, 0x10000000, 0x10000000); /* LOOKUP_EN */
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 6a38402..4b7d434 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -1107,11 +1107,12 @@
u32 pclk = nv_rd32(priv, 0x610ad0 + (head * 0x540)) & 0x3fffff;
u32 hval, hreg = 0x614200 + (head * 0x800);
u32 oval, oreg;
+ u32 mask;
u32 conf = exec_clkcmp(priv, head, 0xff, pclk, &outp);
if (conf != ~0) {
if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) {
u32 soff = (ffs(outp.or) - 1) * 0x08;
- u32 ctrl = nv_rd32(priv, 0x610798 + soff);
+ u32 ctrl = nv_rd32(priv, 0x610794 + soff);
u32 datarate;
switch ((ctrl & 0x000f0000) >> 16) {
@@ -1133,6 +1134,7 @@
oreg = 0x614280 + (ffs(outp.or) - 1) * 0x800;
oval = 0x00000000;
hval = 0x00000000;
+ mask = 0xffffffff;
} else
if (!outp.location) {
if (outp.type == DCB_OUTPUT_DP)
@@ -1140,14 +1142,16 @@
oreg = 0x614300 + (ffs(outp.or) - 1) * 0x800;
oval = (conf & 0x0100) ? 0x00000101 : 0x00000000;
hval = 0x00000000;
+ mask = 0x00000707;
} else {
oreg = 0x614380 + (ffs(outp.or) - 1) * 0x800;
oval = 0x00000001;
hval = 0x00000001;
+ mask = 0x00000707;
}
nv_mask(priv, hreg, 0x0000000f, hval);
- nv_mask(priv, oreg, 0x00000707, oval);
+ nv_mask(priv, oreg, mask, oval);
}
}
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index 019eacd8..9ee4004 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -679,7 +679,7 @@
}
if (outp == 8)
- return false;
+ return conf;
data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1);
if (data == 0x0000)
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
index ab1e918..526b752 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
@@ -47,14 +47,8 @@
nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
{
struct nv50_disp_priv *priv = (void *)object->engine;
- struct nouveau_bios *bios = nouveau_bios(priv);
- const u16 type = (mthd & NV50_DISP_SOR_MTHD_TYPE) >> 12;
const u8 head = (mthd & NV50_DISP_SOR_MTHD_HEAD) >> 3;
- const u8 link = (mthd & NV50_DISP_SOR_MTHD_LINK) >> 2;
const u8 or = (mthd & NV50_DISP_SOR_MTHD_OR);
- const u16 mask = (0x0100 << head) | (0x0040 << link) | (0x0001 << or);
- struct dcb_output outp;
- u8 ver, hdr;
u32 data;
int ret = -EINVAL;
@@ -62,8 +56,6 @@
return -EINVAL;
data = *(u32 *)args;
- if (type && !dcb_outp_match(bios, type, mask, &ver, &hdr, &outp))
- return -ENODEV;
switch (mthd & ~0x3f) {
case NV50_DISP_SOR_PWR:
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
index d550226..9d2cd20 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h
@@ -20,8 +20,8 @@
return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_MC];
}
-#define nouveau_mc_create(p,e,o,d) \
- nouveau_mc_create_((p), (e), (o), sizeof(**d), (void **)d)
+#define nouveau_mc_create(p,e,o,m,d) \
+ nouveau_mc_create_((p), (e), (o), (m), sizeof(**d), (void **)d)
#define nouveau_mc_destroy(p) ({ \
struct nouveau_mc *pmc = (p); _nouveau_mc_dtor(nv_object(pmc)); \
})
@@ -33,7 +33,8 @@
})
int nouveau_mc_create_(struct nouveau_object *, struct nouveau_object *,
- struct nouveau_oclass *, int, void **);
+ struct nouveau_oclass *, const struct nouveau_mc_intr *,
+ int, void **);
void _nouveau_mc_dtor(struct nouveau_object *);
int _nouveau_mc_init(struct nouveau_object *);
int _nouveau_mc_fini(struct nouveau_object *, bool);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
index 2d9b9d7..f3edd28 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dcb.c
@@ -124,6 +124,7 @@
struct dcb_output *outp)
{
u16 dcb = dcb_outp(bios, idx, ver, len);
+ memset(outp, 0x00, sizeof(*outp));
if (dcb) {
if (*ver >= 0x20) {
u32 conn = nv_ro32(bios, dcb + 0x00);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index c434d39..c7bf974 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -366,13 +366,13 @@
init_script(struct nouveau_bios *bios, int index)
{
struct nvbios_init init = { .bios = bios };
- u16 data;
+ u16 bmp_ver = bmp_version(bios), data;
- if (bmp_version(bios) && bmp_version(bios) < 0x0510) {
- if (index > 1)
+ if (bmp_ver && bmp_ver < 0x0510) {
+ if (index > 1 || bmp_ver < 0x0100)
return 0x0000;
- data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18);
+ data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18);
return nv_ro16(bios, data + (index * 2));
}
@@ -580,8 +580,22 @@
init_reserved(struct nvbios_init *init)
{
u8 opcode = nv_ro08(init->bios, init->offset);
- trace("RESERVED\t0x%02x\n", opcode);
- init->offset += 1;
+ u8 length, i;
+
+ switch (opcode) {
+ case 0xaa:
+ length = 4;
+ break;
+ default:
+ length = 1;
+ break;
+ }
+
+ trace("RESERVED 0x%02x\t", opcode);
+ for (i = 1; i < length; i++)
+ cont(" 0x%02x", nv_ro08(init->bios, init->offset + i));
+ cont("\n");
+ init->offset += length;
}
/**
@@ -1281,7 +1295,11 @@
u16 offset = nv_ro16(bios, init->offset + 1);
trace("JUMP\t0x%04x\n", offset);
- init->offset = offset;
+
+ if (init_exec(init))
+ init->offset = offset;
+ else
+ init->offset += 3;
}
/**
@@ -2136,6 +2154,7 @@
[0x99] = { init_zm_auxch },
[0x9a] = { init_i2c_long_if },
[0xa9] = { init_gpio_ne },
+ [0xaa] = { init_reserved },
};
#define init_opcode_nr (sizeof(init_opcode) / sizeof(init_opcode[0]))
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
index 1c0330b..ec9cd6f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
@@ -80,7 +80,9 @@
int
nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
- struct nouveau_oclass *oclass, int length, void **pobject)
+ struct nouveau_oclass *oclass,
+ const struct nouveau_mc_intr *intr_map,
+ int length, void **pobject)
{
struct nouveau_device *device = nv_device(parent);
struct nouveau_mc *pmc;
@@ -92,6 +94,8 @@
if (ret)
return ret;
+ pmc->intr_map = intr_map;
+
ret = request_irq(device->pdev->irq, nouveau_mc_intr,
IRQF_SHARED, "nouveau", pmc);
if (ret < 0)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
index 8c76971..64aa4ed 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.c
@@ -50,12 +50,11 @@
struct nv04_mc_priv *priv;
int ret;
- ret = nouveau_mc_create(parent, engine, oclass, &priv);
+ ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
- priv->base.intr_map = nv04_mc_intr;
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
index 5191937..d989178 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c
@@ -36,12 +36,11 @@
struct nv44_mc_priv *priv;
int ret;
- ret = nouveau_mc_create(parent, engine, oclass, &priv);
+ ret = nouveau_mc_create(parent, engine, oclass, nv04_mc_intr, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
- priv->base.intr_map = nv04_mc_intr;
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
index d796924..732d810 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
@@ -52,12 +52,11 @@
struct nv50_mc_priv *priv;
int ret;
- ret = nouveau_mc_create(parent, engine, oclass, &priv);
+ ret = nouveau_mc_create(parent, engine, oclass, nv50_mc_intr, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
- priv->base.intr_map = nv50_mc_intr;
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index e82fd21..0d57b4d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -54,12 +54,11 @@
struct nv98_mc_priv *priv;
int ret;
- ret = nouveau_mc_create(parent, engine, oclass, &priv);
+ ret = nouveau_mc_create(parent, engine, oclass, nv98_mc_intr, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
- priv->base.intr_map = nv98_mc_intr;
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
index 737bd4b..4c97cd2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
@@ -56,12 +56,11 @@
struct nvc0_mc_priv *priv;
int ret;
- ret = nouveau_mc_create(parent, engine, oclass, &priv);
+ ret = nouveau_mc_create(parent, engine, oclass, nvc0_mc_intr, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
- priv->base.intr_map = nvc0_mc_intr;
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
index c728380..ea19acd 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/fan.c
@@ -54,8 +54,10 @@
/* check that we're not already at the target duty cycle */
duty = fan->get(therm);
- if (duty == target)
- goto done;
+ if (duty == target) {
+ spin_unlock_irqrestore(&fan->lock, flags);
+ return 0;
+ }
/* smooth out the fanspeed increase/decrease */
if (!immediate && duty >= 0) {
@@ -73,8 +75,15 @@
nv_debug(therm, "FAN update: %d\n", duty);
ret = fan->set(therm, duty);
- if (ret)
- goto done;
+ if (ret) {
+ spin_unlock_irqrestore(&fan->lock, flags);
+ return ret;
+ }
+
+ /* fan speed updated, drop the fan lock before grabbing the
+ * alarm-scheduling lock and risking a deadlock
+ */
+ spin_unlock_irqrestore(&fan->lock, flags);
/* schedule next fan update, if not at target speed already */
if (list_empty(&fan->alarm.head) && target != duty) {
@@ -92,8 +101,6 @@
ptimer->alarm(ptimer, delay * 1000 * 1000, &fan->alarm);
}
-done:
- spin_unlock_irqrestore(&fan->lock, flags);
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
index 77c67fc..e66fb77 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/vm/base.c
@@ -362,7 +362,7 @@
vm->fpde = offset >> (vmm->pgt_bits + 12);
vm->lpde = (offset + length - 1) >> (vmm->pgt_bits + 12);
- vm->pgt = kcalloc(vm->lpde - vm->fpde + 1, sizeof(*vm->pgt), GFP_KERNEL);
+ vm->pgt = vzalloc((vm->lpde - vm->fpde + 1) * sizeof(*vm->pgt));
if (!vm->pgt) {
kfree(vm);
return -ENOMEM;
@@ -371,7 +371,7 @@
ret = nouveau_mm_init(&vm->mm, mm_offset >> 12, mm_length >> 12,
block >> 12);
if (ret) {
- kfree(vm->pgt);
+ vfree(vm->pgt);
kfree(vm);
return ret;
}
@@ -446,7 +446,7 @@
}
nouveau_mm_fini(&vm->mm);
- kfree(vm->pgt);
+ vfree(vm->pgt);
kfree(vm);
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index d97f200..5cec3a0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -372,9 +372,6 @@
acpi_status status;
acpi_handle dhandle, rom_handle;
- if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
- return false;
-
dhandle = DEVICE_ACPI_HANDLE(&pdev->dev);
if (!dhandle)
return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 7ff1071..5a5f021 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -788,25 +788,25 @@
struct ttm_mem_reg *old_mem, struct ttm_mem_reg *new_mem)
{
struct nouveau_mem *node = old_mem->mm_node;
- struct nouveau_bo *nvbo = nouveau_bo(bo);
u64 length = (new_mem->num_pages << PAGE_SHIFT);
u64 src_offset = node->vma[0].offset;
u64 dst_offset = node->vma[1].offset;
+ int src_tiled = !!node->memtype;
+ int dst_tiled = !!((struct nouveau_mem *)new_mem->mm_node)->memtype;
int ret;
while (length) {
u32 amount, stride, height;
+ ret = RING_SPACE(chan, 18 + 6 * (src_tiled + dst_tiled));
+ if (ret)
+ return ret;
+
amount = min(length, (u64)(4 * 1024 * 1024));
stride = 16 * 4;
height = amount / stride;
- if (old_mem->mem_type == TTM_PL_VRAM &&
- nouveau_bo_tile_layout(nvbo)) {
- ret = RING_SPACE(chan, 8);
- if (ret)
- return ret;
-
+ if (src_tiled) {
BEGIN_NV04(chan, NvSubCopy, 0x0200, 7);
OUT_RING (chan, 0);
OUT_RING (chan, 0);
@@ -816,19 +816,10 @@
OUT_RING (chan, 0);
OUT_RING (chan, 0);
} else {
- ret = RING_SPACE(chan, 2);
- if (ret)
- return ret;
-
BEGIN_NV04(chan, NvSubCopy, 0x0200, 1);
OUT_RING (chan, 1);
}
- if (new_mem->mem_type == TTM_PL_VRAM &&
- nouveau_bo_tile_layout(nvbo)) {
- ret = RING_SPACE(chan, 8);
- if (ret)
- return ret;
-
+ if (dst_tiled) {
BEGIN_NV04(chan, NvSubCopy, 0x021c, 7);
OUT_RING (chan, 0);
OUT_RING (chan, 0);
@@ -838,18 +829,10 @@
OUT_RING (chan, 0);
OUT_RING (chan, 0);
} else {
- ret = RING_SPACE(chan, 2);
- if (ret)
- return ret;
-
BEGIN_NV04(chan, NvSubCopy, 0x021c, 1);
OUT_RING (chan, 1);
}
- ret = RING_SPACE(chan, 14);
- if (ret)
- return ret;
-
BEGIN_NV04(chan, NvSubCopy, 0x0238, 2);
OUT_RING (chan, upper_32_bits(src_offset));
OUT_RING (chan, upper_32_bits(dst_offset));
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 383f4e6..4598a6a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -339,6 +339,8 @@
if (ret)
goto fail_device;
+ dev->irq_enabled = true;
+
/* workaround an odd issue on nvc1 by disabling the device's
* nosnoop capability. hopefully won't cause issues until a
* better fix is found - assuming there is one...
@@ -426,6 +428,7 @@
struct nouveau_drm *drm = nouveau_drm(dev);
struct nouveau_object *device;
+ dev->irq_enabled = false;
device = drm->client.base.device;
drm_put_dev(dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index b4b4d0c..5bccf31 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -287,7 +287,8 @@
list_for_each_safe(entry, tmp, list) {
nvbo = list_entry(entry, struct nouveau_bo, entry);
- nouveau_bo_fence(nvbo, fence);
+ if (likely(fence))
+ nouveau_bo_fence(nvbo, fence);
if (unlikely(nvbo->validate_mapped)) {
ttm_bo_kunmap(&nvbo->kmap);
diff --git a/drivers/gpu/drm/nouveau/nv17_fence.c b/drivers/gpu/drm/nouveau/nv17_fence.c
index 8e47a9b..22aa996 100644
--- a/drivers/gpu/drm/nouveau/nv17_fence.c
+++ b/drivers/gpu/drm/nouveau/nv17_fence.c
@@ -76,7 +76,7 @@
struct ttm_mem_reg *mem = &priv->bo->bo.mem;
struct nouveau_object *object;
u32 start = mem->start * PAGE_SIZE;
- u32 limit = mem->start + mem->size - 1;
+ u32 limit = start + mem->size - 1;
int ret = 0;
fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL);
diff --git a/drivers/gpu/drm/nouveau/nv50_fence.c b/drivers/gpu/drm/nouveau/nv50_fence.c
index f9701e5..0ee3638 100644
--- a/drivers/gpu/drm/nouveau/nv50_fence.c
+++ b/drivers/gpu/drm/nouveau/nv50_fence.c
@@ -39,6 +39,8 @@
struct nv10_fence_chan *fctx;
struct ttm_mem_reg *mem = &priv->bo->bo.mem;
struct nouveau_object *object;
+ u32 start = mem->start * PAGE_SIZE;
+ u32 limit = start + mem->size - 1;
int ret, i;
fctx = chan->fence = kzalloc(sizeof(*fctx), GFP_KERNEL);
@@ -51,26 +53,28 @@
fctx->base.sync = nv17_fence_sync;
ret = nouveau_object_new(nv_object(chan->cli), chan->handle,
- NvSema, 0x0002,
+ NvSema, 0x003d,
&(struct nv_dma_class) {
.flags = NV_DMA_TARGET_VRAM |
NV_DMA_ACCESS_RDWR,
- .start = mem->start * PAGE_SIZE,
- .limit = mem->size - 1,
+ .start = start,
+ .limit = limit,
}, sizeof(struct nv_dma_class),
&object);
/* dma objects for display sync channel semaphore blocks */
for (i = 0; !ret && i < dev->mode_config.num_crtc; i++) {
struct nouveau_bo *bo = nv50_display_crtc_sema(dev, i);
+ u32 start = bo->bo.mem.start * PAGE_SIZE;
+ u32 limit = start + bo->bo.mem.size - 1;
ret = nouveau_object_new(nv_object(chan->cli), chan->handle,
NvEvoSema0 + i, 0x003d,
&(struct nv_dma_class) {
.flags = NV_DMA_TARGET_VRAM |
NV_DMA_ACCESS_RDWR,
- .start = bo->bo.offset,
- .limit = bo->bo.offset + 0xfff,
+ .start = start,
+ .limit = limit,
}, sizeof(struct nv_dma_class),
&object);
}
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index 9b794c9..b5df614 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -199,7 +199,7 @@
static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
struct page **pages, uint32_t npages, uint32_t roll)
{
- dma_addr_t pat_pa = 0;
+ dma_addr_t pat_pa = 0, data_pa = 0;
uint32_t *data;
struct pat *pat;
struct refill_engine *engine = txn->engine_handle;
@@ -223,7 +223,9 @@
.lut_id = engine->tcm->lut_id,
};
- data = alloc_dma(txn, 4*i, &pat->data_pa);
+ data = alloc_dma(txn, 4*i, &data_pa);
+ /* FIXME: what if data_pa is more than 32-bit ? */
+ pat->data_pa = data_pa;
while (i--) {
int n = i + roll;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index ebbdf41..2272c66 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -806,7 +806,7 @@
omap_obj->paddr = tiler_ssptr(block);
omap_obj->block = block;
- DBG("got paddr: %08x", omap_obj->paddr);
+ DBG("got paddr: %pad", &omap_obj->paddr);
}
omap_obj->paddr_cnt++;
@@ -1004,9 +1004,9 @@
if (obj->map_list.map)
off = (uint64_t)obj->map_list.hash.key;
- seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d",
+ seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
omap_obj->flags, obj->name, obj->refcount.refcount.counter,
- off, omap_obj->paddr, omap_obj->paddr_cnt,
+ off, &omap_obj->paddr, omap_obj->paddr_cnt,
omap_obj->vaddr, omap_obj->roll);
if (omap_obj->flags & OMAP_BO_TILED) {
@@ -1489,8 +1489,8 @@
entry->paddr = tiler_ssptr(block);
entry->block = block;
- DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h,
- entry->paddr,
+ DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h,
+ &entry->paddr,
usergart[i].stride_pfn << PAGE_SHIFT);
}
}
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 8d225d7..6d01c2a 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -146,8 +146,8 @@
DBG("%dx%d -> %dx%d (%d)", info->width, info->height,
info->out_width, info->out_height,
info->screen_width);
- DBG("%d,%d %08x %08x", info->pos_x, info->pos_y,
- info->paddr, info->p_uv_addr);
+ DBG("%d,%d %pad %pad", info->pos_x, info->pos_y,
+ &info->paddr, &info->p_uv_addr);
/* TODO: */
ilace = false;
diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c
index b3c5127..7002de7 100644
--- a/drivers/gpu/drm/qxl/qxl_fb.c
+++ b/drivers/gpu/drm/qxl/qxl_fb.c
@@ -91,7 +91,7 @@
u32 x1, x2, y1, y2;
/* TODO: hard coding 32 bpp */
- int stride = qfbdev->qfb.base.pitches[0] * 4;
+ int stride = qfbdev->qfb.base.pitches[0];
x1 = qfbdev->dirty.x1;
x2 = qfbdev->dirty.x2;
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index 21393dc..f4b6b89 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -33,6 +33,9 @@
pending = xchg(&qdev->ram_header->int_pending, 0);
+ if (!pending)
+ return IRQ_NONE;
+
atomic_inc(&qdev->irq_received);
if (pending & QXL_INTERRUPT_DISPLAY) {
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 489cb8c..3401eb8 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -431,6 +431,7 @@
static void qxl_sync_obj_unref(void **sync_obj)
{
+ *sync_obj = NULL;
}
static void *qxl_sync_obj_ref(void *sync_obj)
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index fb441a7..15da7ef 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -1222,12 +1222,17 @@
int r;
mutex_lock(&ctx->mutex);
+ /* reset data block */
+ ctx->data_block = 0;
/* reset reg block */
ctx->reg_block = 0;
/* reset fb window */
ctx->fb_base = 0;
/* reset io mode */
ctx->io_mode = ATOM_IO_MM;
+ /* reset divmul */
+ ctx->divmul[0] = 0;
+ ctx->divmul[1] = 0;
r = atom_execute_table_locked(ctx, index, params);
mutex_unlock(&ctx->mutex);
return r;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index d5df8fd..8ac3330 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -312,8 +312,10 @@
misc |= ATOM_COMPOSITESYNC;
if (mode->flags & DRM_MODE_FLAG_INTERLACE)
misc |= ATOM_INTERLACE;
- if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ if (mode->flags & DRM_MODE_FLAG_DBLCLK)
misc |= ATOM_DOUBLE_CLOCK_MODE;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2;
args.susModeMiscInfo.usAccess = cpu_to_le16(misc);
args.ucCRTC = radeon_crtc->crtc_id;
@@ -356,8 +358,10 @@
misc |= ATOM_COMPOSITESYNC;
if (mode->flags & DRM_MODE_FLAG_INTERLACE)
misc |= ATOM_INTERLACE;
- if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ if (mode->flags & DRM_MODE_FLAG_DBLCLK)
misc |= ATOM_DOUBLE_CLOCK_MODE;
+ if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+ misc |= ATOM_H_REPLICATIONBY2 | ATOM_V_REPLICATIONBY2;
args.susModeMiscInfo.usAccess = cpu_to_le16(misc);
args.ucCRTC = radeon_crtc->crtc_id;
@@ -839,14 +843,16 @@
args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */
if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC;
- switch (bpc) {
- case 8:
- default:
- args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
- break;
- case 10:
- args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
- break;
+ if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+ switch (bpc) {
+ case 8:
+ default:
+ args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
+ break;
+ case 10:
+ args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+ break;
+ }
}
args.v5.ucTransmitterID = encoder_id;
args.v5.ucEncoderMode = encoder_mode;
@@ -861,20 +867,22 @@
args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */
if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC;
- switch (bpc) {
- case 8:
- default:
- args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
- break;
- case 10:
- args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
- break;
- case 12:
- args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
- break;
- case 16:
- args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
- break;
+ if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+ switch (bpc) {
+ case 8:
+ default:
+ args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
+ break;
+ case 10:
+ args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
+ break;
+ case 12:
+ args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
+ break;
+ case 16:
+ args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+ break;
+ }
}
args.v6.ucTransmitterID = encoder_id;
args.v6.ucEncoderMode = encoder_mode;
@@ -938,11 +946,14 @@
radeon_atombios_get_ppll_ss_info(rdev,
&radeon_crtc->ss,
ATOM_DP_SS_ID1);
- } else
+ } else {
radeon_crtc->ss_enabled =
radeon_atombios_get_ppll_ss_info(rdev,
&radeon_crtc->ss,
ATOM_DP_SS_ID1);
+ }
+ /* disable spread spectrum on DCE3 DP */
+ radeon_crtc->ss_enabled = false;
}
break;
case ATOM_ENCODER_MODE_LVDS:
@@ -1176,7 +1187,9 @@
if ((rdev->family == CHIP_TAHITI) ||
(rdev->family == CHIP_PITCAIRN))
fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
- else if (rdev->family == CHIP_VERDE)
+ else if ((rdev->family == CHIP_VERDE) ||
+ (rdev->family == CHIP_OLAND) ||
+ (rdev->family == CHIP_HAINAN)) /* for completeness. HAINAN has no display hw */
fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P4_8x16);
switch (radeon_crtc->crtc_id) {
@@ -1656,6 +1669,20 @@
return ATOM_PPLL1;
DRM_ERROR("unable to allocate a PPLL\n");
return ATOM_PPLL_INVALID;
+ } else if (ASIC_IS_DCE41(rdev)) {
+ /* Don't share PLLs on DCE4.1 chips */
+ if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) {
+ if (rdev->clock.dp_extclk)
+ /* skip PPLL programming if using ext clock */
+ return ATOM_PPLL_INVALID;
+ }
+ pll_in_use = radeon_get_pll_use_mask(crtc);
+ if (!(pll_in_use & (1 << ATOM_PPLL1)))
+ return ATOM_PPLL1;
+ if (!(pll_in_use & (1 << ATOM_PPLL2)))
+ return ATOM_PPLL2;
+ DRM_ERROR("unable to allocate a PPLL\n");
+ return ATOM_PPLL_INVALID;
} else if (ASIC_IS_DCE4(rdev)) {
/* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock,
* depending on the asic:
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 064023b..d4a5118 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -44,6 +44,41 @@
};
/***** radeon AUX functions *****/
+
+/* Atom needs data in little endian format
+ * so swap as appropriate when copying data to
+ * or from atom. Note that atom operates on
+ * dw units.
+ */
+void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le)
+{
+#ifdef __BIG_ENDIAN
+ u8 src_tmp[20], dst_tmp[20]; /* used for byteswapping */
+ u32 *dst32, *src32;
+ int i;
+
+ memcpy(src_tmp, src, num_bytes);
+ src32 = (u32 *)src_tmp;
+ dst32 = (u32 *)dst_tmp;
+ if (to_le) {
+ for (i = 0; i < ((num_bytes + 3) / 4); i++)
+ dst32[i] = cpu_to_le32(src32[i]);
+ memcpy(dst, dst_tmp, num_bytes);
+ } else {
+ u8 dws = num_bytes & ~3;
+ for (i = 0; i < ((num_bytes + 3) / 4); i++)
+ dst32[i] = le32_to_cpu(src32[i]);
+ memcpy(dst, dst_tmp, dws);
+ if (num_bytes % 4) {
+ for (i = 0; i < (num_bytes % 4); i++)
+ dst[dws+i] = dst_tmp[dws+i];
+ }
+ }
+#else
+ memcpy(dst, src, num_bytes);
+#endif
+}
+
union aux_channel_transaction {
PROCESS_AUX_CHANNEL_TRANSACTION_PS_ALLOCATION v1;
PROCESS_AUX_CHANNEL_TRANSACTION_PARAMETERS_V2 v2;
@@ -65,10 +100,10 @@
base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
- memcpy(base, send, send_bytes);
+ radeon_atom_copy_swap(base, send, send_bytes, true);
- args.v1.lpAuxRequest = 0 + 4;
- args.v1.lpDataOut = 16 + 4;
+ args.v1.lpAuxRequest = cpu_to_le16((u16)(0 + 4));
+ args.v1.lpDataOut = cpu_to_le16((u16)(16 + 4));
args.v1.ucDataOutLen = 0;
args.v1.ucChannelID = chan->rec.i2c_id;
args.v1.ucDelay = delay / 10;
@@ -102,7 +137,7 @@
recv_bytes = recv_size;
if (recv && recv_size)
- memcpy(recv, base + 16, recv_bytes);
+ radeon_atom_copy_swap(recv, base + 16, recv_bytes, false);
return recv_bytes;
}
@@ -349,6 +384,19 @@
/***** radeon specific DP functions *****/
+static int radeon_dp_get_max_link_rate(struct drm_connector *connector,
+ u8 dpcd[DP_DPCD_SIZE])
+{
+ int max_link_rate;
+
+ if (radeon_connector_is_dp12_capable(connector))
+ max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
+ else
+ max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
+
+ return max_link_rate;
+}
+
/* First get the min lane# when low rate is used according to pixel clock
* (prefer low rate), second check max lane# supported by DP panel,
* if the max lane# < low rate lane# then use max lane# instead.
@@ -358,7 +406,7 @@
int pix_clock)
{
int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
- int max_link_rate = drm_dp_max_link_rate(dpcd);
+ int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
int max_lane_num = drm_dp_max_lane_count(dpcd);
int lane_num;
int max_dp_pix_clock;
@@ -396,7 +444,7 @@
return 540000;
}
- return drm_dp_max_link_rate(dpcd);
+ return radeon_dp_get_max_link_rate(connector, dpcd);
}
static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -526,6 +574,10 @@
struct radeon_connector_atom_dig *dig_connector;
int dp_clock;
+ if ((mode->clock > 340000) &&
+ (!radeon_connector_is_dp12_capable(connector)))
+ return MODE_CLOCK_HIGH;
+
if (!radeon_connector->con_priv)
return MODE_CLOCK_HIGH;
dig_connector = radeon_connector->con_priv;
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 8406c82..1b564d7 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -183,9 +183,15 @@
struct backlight_properties props;
struct radeon_backlight_privdata *pdata;
struct radeon_encoder_atom_dig *dig;
- u8 backlight_level;
char bl_name[16];
+ /* Mac laptops with multiple GPUs use the gmux driver for backlight
+ * so don't register a backlight device
+ */
+ if ((rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE) &&
+ (rdev->pdev->device == 0x6741))
+ return;
+
if (!radeon_encoder->enc_priv)
return;
@@ -215,12 +221,17 @@
pdata->encoder = radeon_encoder;
- backlight_level = radeon_atom_get_backlight_level_from_reg(rdev);
-
dig = radeon_encoder->enc_priv;
dig->bl_dev = bd;
bd->props.brightness = radeon_atom_backlight_get_brightness(bd);
+ /* Set a reasonable default here if the level is 0 otherwise
+ * fbdev will attempt to turn the backlight on after console
+ * unblanking and it will try and restore 0 which turns the backlight
+ * off again.
+ */
+ if (bd->props.brightness == 0)
+ bd->props.brightness = RADEON_MAX_BL_LEVEL;
bd->props.power = FB_BLANK_UNBLANK;
backlight_update_status(bd);
@@ -1274,7 +1285,7 @@
}
if (is_dp)
args.v5.ucLaneNum = dp_lane_count;
- else if (radeon_encoder->pixel_clock > 165000)
+ else if (radeon_dig_monitor_is_duallink(encoder, radeon_encoder->pixel_clock))
args.v5.ucLaneNum = 8;
else
args.v5.ucLaneNum = 4;
@@ -1629,8 +1640,12 @@
atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0);
atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0);
atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0);
- /* some early dce3.2 boards have a bug in their transmitter control table */
- if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730))
+ /* some dce3.x boards have a bug in their transmitter control table.
+ * ACTION_ENABLE_OUTPUT can probably be dropped since ACTION_ENABLE
+ * does the same thing and more.
+ */
+ if ((rdev->family != CHIP_RV710) && (rdev->family != CHIP_RV730) &&
+ (rdev->family != CHIP_RS780) && (rdev->family != CHIP_RS880))
atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0);
}
if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) {
@@ -1866,8 +1881,11 @@
args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT;
else
args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
- } else
+ } else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+ args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS;
+ } else {
args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
+ }
switch (radeon_encoder->encoder_id) {
case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index 082338d..2ca389d 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -27,6 +27,8 @@
#include "radeon.h"
#include "atom.h"
+extern void radeon_atom_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
+
#define TARGET_HW_I2C_CLOCK 50
/* these are a limitation of ProcessI2cChannelTransaction not the hw */
@@ -77,7 +79,7 @@
}
if (!(flags & HW_I2C_WRITE))
- memcpy(buf, base, num);
+ radeon_atom_copy_swap(buf, base, num, false);
return 0;
}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 0f89ce3..59ea654 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -94,7 +94,7 @@
0x8c1c, 0xffffffff, 0x00001010,
0x28350, 0xffffffff, 0x00000000,
0xa008, 0xffffffff, 0x00010000,
- 0x5cc, 0xffffffff, 0x00000001,
+ 0x5c4, 0xffffffff, 0x00000001,
0x9508, 0xffffffff, 0x00000002,
0x913c, 0x0000000f, 0x0000000a
};
@@ -381,7 +381,7 @@
0x8c1c, 0xffffffff, 0x00001010,
0x28350, 0xffffffff, 0x00000000,
0xa008, 0xffffffff, 0x00010000,
- 0x5cc, 0xffffffff, 0x00000001,
+ 0x5c4, 0xffffffff, 0x00000001,
0x9508, 0xffffffff, 0x00000002
};
@@ -540,7 +540,7 @@
static const u32 supersumo_golden_registers[] =
{
0x5eb4, 0xffffffff, 0x00000002,
- 0x5cc, 0xffffffff, 0x00000001,
+ 0x5c4, 0xffffffff, 0x00000001,
0x7030, 0xffffffff, 0x00000011,
0x7c30, 0xffffffff, 0x00000011,
0x6104, 0x01000300, 0x00000000,
@@ -624,7 +624,7 @@
static const u32 wrestler_golden_registers[] =
{
0x5eb4, 0xffffffff, 0x00000002,
- 0x5cc, 0xffffffff, 0x00000001,
+ 0x5c4, 0xffffffff, 0x00000001,
0x7030, 0xffffffff, 0x00000011,
0x7c30, 0xffffffff, 0x00000011,
0x6104, 0x01000300, 0x00000000,
@@ -1718,7 +1718,8 @@
struct drm_display_mode *mode,
struct drm_display_mode *other_mode)
{
- u32 tmp;
+ u32 tmp, buffer_alloc, i;
+ u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
/*
* Line Buffer Setup
* There are 3 line buffers, each one shared by 2 display controllers.
@@ -1741,18 +1742,34 @@
* non-linked crtcs for maximum line buffer allocation.
*/
if (radeon_crtc->base.enabled && mode) {
- if (other_mode)
+ if (other_mode) {
tmp = 0; /* 1/2 */
- else
+ buffer_alloc = 1;
+ } else {
tmp = 2; /* whole */
- } else
+ buffer_alloc = 2;
+ }
+ } else {
tmp = 0;
+ buffer_alloc = 0;
+ }
/* second controller of the pair uses second half of the lb */
if (radeon_crtc->crtc_id % 2)
tmp += 4;
WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset, tmp);
+ if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) {
+ WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+ DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+ DMIF_BUFFERS_ALLOCATED_COMPLETED)
+ break;
+ udelay(1);
+ }
+ }
+
if (radeon_crtc->base.enabled && mode) {
switch (tmp) {
case 0:
@@ -2362,6 +2379,7 @@
WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1);
tmp |= EVERGREEN_CRTC_BLANK_DATA_EN;
WREG32(EVERGREEN_CRTC_BLANK_CONTROL + crtc_offsets[i], tmp);
+ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 0);
}
} else {
tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]);
@@ -2973,7 +2991,7 @@
rdev->config.evergreen.sx_max_export_size = 256;
rdev->config.evergreen.sx_max_export_pos_size = 64;
rdev->config.evergreen.sx_max_export_smx_size = 192;
- rdev->config.evergreen.max_hw_contexts = 8;
+ rdev->config.evergreen.max_hw_contexts = 4;
rdev->config.evergreen.sq_num_cf_insts = 2;
rdev->config.evergreen.sc_prim_fifo_size = 0x40;
@@ -3775,8 +3793,8 @@
WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
}
- /* only one DAC on DCE6 */
- if (!ASIC_IS_DCE6(rdev))
+ /* only one DAC on DCE5 */
+ if (!ASIC_IS_DCE5(rdev))
WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
WREG32(DACB_AUTODETECT_INT_CONTROL, 0);
@@ -3998,6 +4016,9 @@
WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5);
WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6);
+ /* posting read */
+ RREG32(SRBM_STATUS);
+
return 0;
}
@@ -4681,6 +4702,8 @@
/* enable pcie gen2 link */
evergreen_pcie_gen2_enable(rdev);
+ evergreen_mc_program(rdev);
+
if (ASIC_IS_DCE5(rdev)) {
if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw || !rdev->mc_fw) {
r = ni_init_microcode(rdev);
@@ -4708,7 +4731,6 @@
if (r)
return r;
- evergreen_mc_program(rdev);
if (rdev->flags & RADEON_IS_AGP) {
evergreen_agp_enable(rdev);
} else {
@@ -4854,10 +4876,10 @@
int evergreen_suspend(struct radeon_device *rdev)
{
r600_audio_fini(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_suspend(rdev);
r700_cp_stop(rdev);
r600_dma_stop(rdev);
- r600_uvd_rbc_stop(rdev);
evergreen_irq_suspend(rdev);
radeon_wb_disable(rdev);
evergreen_pcie_gart_disable(rdev);
@@ -4988,6 +5010,7 @@
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
evergreen_pcie_gart_fini(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_fini(rdev);
r600_vram_scratch_fini(rdev);
radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index eb8ac31..c7cac07 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -967,7 +967,10 @@
if (track->cb_dirty) {
tmp = track->cb_target_mask;
for (i = 0; i < 8; i++) {
- if ((tmp >> (i * 4)) & 0xF) {
+ u32 format = G_028C70_FORMAT(track->cb_color_info[i]);
+
+ if (format != V_028C70_COLOR_INVALID &&
+ (tmp >> (i * 4)) & 0xF) {
/* at least one component is enabled */
if (track->cb_color_bo[i] == NULL) {
dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index ed7c8a7..067cc1f 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -128,14 +128,7 @@
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
uint32_t offset = dig->afmt->offset;
uint8_t *frame = buffer + 3;
-
- /* Our header values (type, version, length) should be alright, Intel
- * is using the same. Checksum function also seems to be OK, it works
- * fine for audio infoframe. However calculated value is always lower
- * by 2 in comparison to fglrx. It breaks displaying anything in case
- * of TVs that strictly check the checksum. Hack it manually here to
- * workaround this issue. */
- frame[0x0] += 2;
+ uint8_t *header = buffer;
WREG32(AFMT_AVI_INFO0 + offset,
frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24));
@@ -144,7 +137,7 @@
WREG32(AFMT_AVI_INFO2 + offset,
frame[0x8] | (frame[0x9] << 8) | (frame[0xA] << 16) | (frame[0xB] << 24));
WREG32(AFMT_AVI_INFO3 + offset,
- frame[0xC] | (frame[0xD] << 8));
+ frame[0xC] | (frame[0xD] << 8) | (header[1] << 24));
}
static void evergreen_audio_set_dto(struct drm_encoder *encoder, u32 clock)
@@ -164,9 +157,9 @@
* number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE
* is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
*/
+ WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id));
WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
- WREG32(DCCG_AUDIO_DTO_SOURCE, DCCG_AUDIO_DTO0_SOURCE_SEL(radeon_crtc->crtc_id));
}
@@ -184,6 +177,9 @@
uint32_t offset;
ssize_t err;
+ if (!dig || !dig->afmt)
+ return;
+
/* Silent, r600_hdmi_enable will raise WARN for us */
if (!dig->afmt->enabled)
return;
@@ -223,8 +219,7 @@
/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
WREG32(HDMI_ACR_PACKET_CONTROL + offset,
- HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
- HDMI_ACR_SOURCE); /* select SW CTS value */
+ HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
evergreen_hdmi_update_ACR(encoder, mode->clock);
@@ -287,6 +282,9 @@
struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+ if (!dig || !dig->afmt)
+ return;
+
/* Silent, r600_hdmi_enable will raise WARN for us */
if (enable && dig->afmt->enabled)
return;
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 75c0563..150e318 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -810,6 +810,10 @@
# define LATENCY_LOW_WATERMARK(x) ((x) << 0)
# define LATENCY_HIGH_WATERMARK(x) ((x) << 16)
+#define PIPE0_DMIF_BUFFER_CONTROL 0x0ca0
+# define DMIF_BUFFERS_ALLOCATED(x) ((x) << 0)
+# define DMIF_BUFFERS_ALLOCATED_COMPLETED (1 << 4)
+
#define IH_RB_CNTL 0x3e00
# define IH_RB_ENABLE (1 << 0)
# define IH_IB_SIZE(x) ((x) << 1) /* log2 */
@@ -1100,7 +1104,7 @@
* 6. COMMAND [29:22] | BYTE_COUNT [20:0]
*/
# define PACKET3_CP_DMA_DST_SEL(x) ((x) << 20)
- /* 0 - SRC_ADDR
+ /* 0 - DST_ADDR
* 1 - GDS
*/
# define PACKET3_CP_DMA_ENGINE(x) ((x) << 27)
@@ -1115,7 +1119,7 @@
# define PACKET3_CP_DMA_CP_SYNC (1 << 31)
/* COMMAND */
# define PACKET3_CP_DMA_DIS_WC (1 << 21)
-# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
/* 0 - none
* 1 - 8 in 16
* 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8458330..c254e46 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -753,6 +753,10 @@
(rdev->pdev->device == 0x999C)) {
rdev->config.cayman.max_simds_per_se = 6;
rdev->config.cayman.max_backends_per_se = 2;
+ rdev->config.cayman.max_hw_contexts = 8;
+ rdev->config.cayman.sx_max_export_size = 256;
+ rdev->config.cayman.sx_max_export_pos_size = 64;
+ rdev->config.cayman.sx_max_export_smx_size = 192;
} else if ((rdev->pdev->device == 0x9903) ||
(rdev->pdev->device == 0x9904) ||
(rdev->pdev->device == 0x990A) ||
@@ -763,6 +767,10 @@
(rdev->pdev->device == 0x999D)) {
rdev->config.cayman.max_simds_per_se = 4;
rdev->config.cayman.max_backends_per_se = 2;
+ rdev->config.cayman.max_hw_contexts = 8;
+ rdev->config.cayman.sx_max_export_size = 256;
+ rdev->config.cayman.sx_max_export_pos_size = 64;
+ rdev->config.cayman.sx_max_export_smx_size = 192;
} else if ((rdev->pdev->device == 0x9919) ||
(rdev->pdev->device == 0x9990) ||
(rdev->pdev->device == 0x9991) ||
@@ -773,9 +781,17 @@
(rdev->pdev->device == 0x99A0)) {
rdev->config.cayman.max_simds_per_se = 3;
rdev->config.cayman.max_backends_per_se = 1;
+ rdev->config.cayman.max_hw_contexts = 4;
+ rdev->config.cayman.sx_max_export_size = 128;
+ rdev->config.cayman.sx_max_export_pos_size = 32;
+ rdev->config.cayman.sx_max_export_smx_size = 96;
} else {
rdev->config.cayman.max_simds_per_se = 2;
rdev->config.cayman.max_backends_per_se = 1;
+ rdev->config.cayman.max_hw_contexts = 4;
+ rdev->config.cayman.sx_max_export_size = 128;
+ rdev->config.cayman.sx_max_export_pos_size = 32;
+ rdev->config.cayman.sx_max_export_smx_size = 96;
}
rdev->config.cayman.max_texture_channel_caches = 2;
rdev->config.cayman.max_gprs = 256;
@@ -783,10 +799,6 @@
rdev->config.cayman.max_gs_threads = 32;
rdev->config.cayman.max_stack_entries = 512;
rdev->config.cayman.sx_num_of_sets = 8;
- rdev->config.cayman.sx_max_export_size = 256;
- rdev->config.cayman.sx_max_export_pos_size = 64;
- rdev->config.cayman.sx_max_export_smx_size = 192;
- rdev->config.cayman.max_hw_contexts = 8;
rdev->config.cayman.sq_num_cf_insts = 2;
rdev->config.cayman.sc_prim_fifo_size = 0x40;
@@ -918,12 +930,12 @@
if ((rdev->config.cayman.max_backends_per_se == 1) &&
(rdev->flags & RADEON_IS_IGP)) {
- if ((disabled_rb_mask & 3) == 1) {
- /* RB0 disabled, RB1 enabled */
- tmp = 0x11111111;
- } else {
+ if ((disabled_rb_mask & 3) == 2) {
/* RB1 disabled, RB0 enabled */
tmp = 0x00000000;
+ } else {
+ /* RB0 disabled, RB1 enabled */
+ tmp = 0x11111111;
}
} else {
tmp = gb_addr_config & NUM_PIPES_MASK;
@@ -1166,13 +1178,12 @@
{
struct radeon_ring *ring = &rdev->ring[fence->ring];
u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
+ u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+ PACKET3_SH_ACTION_ENA;
/* flush read cache over gart for this vmid */
- radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
- radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
- radeon_ring_write(ring, 0);
radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
- radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+ radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
radeon_ring_write(ring, 0xFFFFFFFF);
radeon_ring_write(ring, 0);
radeon_ring_write(ring, 10); /* poll interval */
@@ -1188,6 +1199,8 @@
void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
{
struct radeon_ring *ring = &rdev->ring[ib->ring];
+ u32 cp_coher_cntl = PACKET3_FULL_CACHE_ENA | PACKET3_TC_ACTION_ENA |
+ PACKET3_SH_ACTION_ENA;
/* set to DX10/11 mode */
radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
@@ -1212,14 +1225,11 @@
(ib->vm ? (ib->vm->id << 24) : 0));
/* flush read cache over gart for this vmid */
- radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
- radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2);
- radeon_ring_write(ring, ib->vm ? ib->vm->id : 0);
radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
- radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
+ radeon_ring_write(ring, PACKET3_ENGINE_ME | cp_coher_cntl);
radeon_ring_write(ring, 0xFFFFFFFF);
radeon_ring_write(ring, 0);
- radeon_ring_write(ring, 10); /* poll interval */
+ radeon_ring_write(ring, ((ib->vm ? ib->vm->id : 0) << 24) | 10); /* poll interval */
}
void cayman_uvd_semaphore_emit(struct radeon_device *rdev,
@@ -1929,6 +1939,8 @@
/* enable pcie gen2 link */
evergreen_pcie_gen2_enable(rdev);
+ evergreen_mc_program(rdev);
+
if (rdev->flags & RADEON_IS_IGP) {
if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
r = ni_init_microcode(rdev);
@@ -1957,7 +1969,6 @@
if (r)
return r;
- evergreen_mc_program(rdev);
r = cayman_pcie_gart_enable(rdev);
if (r)
return r;
@@ -2133,7 +2144,7 @@
radeon_vm_manager_fini(rdev);
cayman_cp_enable(rdev, false);
cayman_dma_stop(rdev);
- r600_uvd_rbc_stop(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_suspend(rdev);
evergreen_irq_suspend(rdev);
radeon_wb_disable(rdev);
@@ -2265,6 +2276,7 @@
radeon_vm_manager_fini(rdev);
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_fini(rdev);
cayman_pcie_gart_fini(rdev);
r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index e226faf..e49f7b4 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -573,6 +573,7 @@
# define PACKET3_DB_ACTION_ENA (1 << 26)
# define PACKET3_SH_ACTION_ENA (1 << 27)
# define PACKET3_SX_ACTION_ENA (1 << 28)
+# define PACKET3_ENGINE_ME (1 << 31)
#define PACKET3_ME_INITIALIZE 0x44
#define PACKET3_ME_INITIALIZE_DEVICE_ID(x) ((x) << 16)
#define PACKET3_COND_WRITE 0x45
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index d0314ec..f9f0e36 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -743,6 +743,10 @@
tmp |= RADEON_FP2_DETECT_MASK;
}
WREG32(RADEON_GEN_INT_CNTL, tmp);
+
+ /* read back to post the write */
+ RREG32(RADEON_GEN_INT_CNTL);
+
return 0;
}
@@ -2935,9 +2939,11 @@
seq_printf(m, "CP_RB_RPTR 0x%08x\n", rdp);
seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
seq_printf(m, "%u dwords in ring\n", count);
- for (j = 0; j <= count; j++) {
- i = (rdp + j) & ring->ptr_mask;
- seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+ if (ring->ready) {
+ for (j = 0; j <= count; j++) {
+ i = (rdp + j) & ring->ptr_mask;
+ seq_printf(m, "r[%04d]=0x%08x\n", i, ring->ring[i]);
+ }
}
return 0;
}
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 6948eb8..90b0075 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2675,12 +2675,29 @@
return 0;
}
-void r600_uvd_rbc_stop(struct radeon_device *rdev)
+void r600_uvd_stop(struct radeon_device *rdev)
{
struct radeon_ring *ring = &rdev->ring[R600_RING_TYPE_UVD_INDEX];
/* force RBC into idle state */
WREG32(UVD_RBC_RB_CNTL, 0x11010101);
+
+ /* Stall UMC and register bus before resetting VCPU */
+ WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+ WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+ mdelay(1);
+
+ /* put VCPU into reset */
+ WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
+ mdelay(5);
+
+ /* disable VCPU clock */
+ WREG32(UVD_VCPU_CNTL, 0x0);
+
+ /* Unstall UMC and register bus */
+ WREG32_P(UVD_LMI_CTRL2, 0, ~(1 << 8));
+ WREG32_P(UVD_RB_ARB_CTRL, 0, ~(1 << 3));
+
ring->ready = false;
}
@@ -2700,6 +2717,11 @@
/* disable interupt */
WREG32_P(UVD_MASTINT_EN, 0, ~(1 << 1));
+ /* Stall UMC and register bus before resetting VCPU */
+ WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
+ WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
+ mdelay(1);
+
/* put LMI, VCPU, RBC etc... into reset */
WREG32(UVD_SOFT_RESET, LMI_SOFT_RESET | VCPU_SOFT_RESET |
LBSI_SOFT_RESET | RBC_SOFT_RESET | CSM_SOFT_RESET |
@@ -2729,10 +2751,6 @@
WREG32(UVD_MPC_SET_ALU, 0);
WREG32(UVD_MPC_SET_MUX, 0x88);
- /* Stall UMC */
- WREG32_P(UVD_LMI_CTRL2, 1 << 8, ~(1 << 8));
- WREG32_P(UVD_RB_ARB_CTRL, 1 << 3, ~(1 << 3));
-
/* take all subblocks out of reset, except VCPU */
WREG32(UVD_SOFT_RESET, VCPU_SOFT_RESET);
mdelay(5);
@@ -2939,14 +2957,17 @@
struct radeon_fence *fence)
{
struct radeon_ring *ring = &rdev->ring[fence->ring];
+ u32 cp_coher_cntl = PACKET3_TC_ACTION_ENA | PACKET3_VC_ACTION_ENA |
+ PACKET3_SH_ACTION_ENA;
+
+ if (rdev->family >= CHIP_RV770)
+ cp_coher_cntl |= PACKET3_FULL_CACHE_ENA;
if (rdev->wb.use_event) {
u64 addr = rdev->fence_drv[fence->ring].gpu_addr;
/* flush read cache over gart */
radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
- radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
- PACKET3_VC_ACTION_ENA |
- PACKET3_SH_ACTION_ENA);
+ radeon_ring_write(ring, cp_coher_cntl);
radeon_ring_write(ring, 0xFFFFFFFF);
radeon_ring_write(ring, 0);
radeon_ring_write(ring, 10); /* poll interval */
@@ -2960,9 +2981,7 @@
} else {
/* flush read cache over gart */
radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3));
- radeon_ring_write(ring, PACKET3_TC_ACTION_ENA |
- PACKET3_VC_ACTION_ENA |
- PACKET3_SH_ACTION_ENA);
+ radeon_ring_write(ring, cp_coher_cntl);
radeon_ring_write(ring, 0xFFFFFFFF);
radeon_ring_write(ring, 0);
radeon_ring_write(ring, 10); /* poll interval */
@@ -2986,7 +3005,7 @@
struct radeon_fence *fence)
{
struct radeon_ring *ring = &rdev->ring[fence->ring];
- uint32_t addr = rdev->fence_drv[fence->ring].gpu_addr;
+ uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
radeon_ring_write(ring, fence->seq);
@@ -3206,6 +3225,8 @@
/* enable pcie gen2 link */
r600_pcie_gen2_enable(rdev);
+ r600_mc_program(rdev);
+
if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
r = r600_init_microcode(rdev);
if (r) {
@@ -3218,7 +3239,6 @@
if (r)
return r;
- r600_mc_program(rdev);
if (rdev->flags & RADEON_IS_AGP) {
r600_agp_enable(rdev);
} else {
@@ -3439,6 +3459,9 @@
rdev->accel_working = false;
}
+ /* posting read */
+ RREG32(R_000E50_SRBM_STATUS);
+
return 0;
}
@@ -4489,6 +4512,10 @@
break;
}
break;
+ case 124: /* UVD */
+ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+ radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+ break;
case 176: /* CP_INT in ring buffer */
case 177: /* CP_INT in IB1 */
case 178: /* CP_INT in IB2 */
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 01a3ec8..745e66e 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -749,7 +749,10 @@
}
for (i = 0; i < 8; i++) {
- if ((tmp >> (i * 4)) & 0xF) {
+ u32 format = G_0280A0_FORMAT(track->cb_color_info[i]);
+
+ if (format != V_0280A0_COLOR_INVALID &&
+ (tmp >> (i * 4)) & 0xF) {
/* at least one component is enabled */
if (track->cb_color_bo[i] == NULL) {
dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 456750a..5df7116 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -24,6 +24,7 @@
* Authors: Christian König
*/
#include <linux/hdmi.h>
+#include <linux/gcd.h>
#include <drm/drmP.h>
#include <drm/radeon_drm.h>
#include "radeon.h"
@@ -57,28 +58,57 @@
static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
/* 32kHz 44.1kHz 48kHz */
/* Clock N CTS N CTS N CTS */
- { 25174, 4576, 28125, 7007, 31250, 6864, 28125 }, /* 25,20/1.001 MHz */
+ { 25175, 4096, 25175, 28224, 125875, 6144, 25175 }, /* 25,20/1.001 MHz */
{ 25200, 4096, 25200, 6272, 28000, 6144, 25200 }, /* 25.20 MHz */
{ 27000, 4096, 27000, 6272, 30000, 6144, 27000 }, /* 27.00 MHz */
{ 27027, 4096, 27027, 6272, 30030, 6144, 27027 }, /* 27.00*1.001 MHz */
{ 54000, 4096, 54000, 6272, 60000, 6144, 54000 }, /* 54.00 MHz */
{ 54054, 4096, 54054, 6272, 60060, 6144, 54054 }, /* 54.00*1.001 MHz */
- { 74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /* 74.25/1.001 MHz */
+ { 74176, 4096, 74176, 5733, 75335, 6144, 74176 }, /* 74.25/1.001 MHz */
{ 74250, 4096, 74250, 6272, 82500, 6144, 74250 }, /* 74.25 MHz */
- { 148351, 11648, 421875, 8918, 234375, 5824, 140625 }, /* 148.50/1.001 MHz */
+ { 148352, 4096, 148352, 5733, 150670, 6144, 148352 }, /* 148.50/1.001 MHz */
{ 148500, 4096, 148500, 6272, 165000, 6144, 148500 }, /* 148.50 MHz */
- { 0, 4096, 0, 6272, 0, 6144, 0 } /* Other */
};
+
/*
- * calculate CTS value if it's not found in the table
+ * calculate CTS and N values if they are not found in the table
*/
-static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
+static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int *N, int freq)
{
- if (*CTS == 0)
- *CTS = clock * N / (128 * freq) * 1000;
- DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n",
- N, *CTS, freq);
+ int n, cts;
+ unsigned long div, mul;
+
+ /* Safe, but overly large values */
+ n = 128 * freq;
+ cts = clock * 1000;
+
+ /* Smallest valid fraction */
+ div = gcd(n, cts);
+
+ n /= div;
+ cts /= div;
+
+ /*
+ * The optimal N is 128*freq/1000. Calculate the closest larger
+ * value that doesn't truncate any bits.
+ */
+ mul = ((128*freq/1000) + (n-1))/n;
+
+ n *= mul;
+ cts *= mul;
+
+ /* Check that we are in spec (not always possible) */
+ if (n < (128*freq/1500))
+ printk(KERN_WARNING "Calculated ACR N value is too small. You may experience audio problems.\n");
+ if (n > (128*freq/300))
+ printk(KERN_WARNING "Calculated ACR N value is too large. You may experience audio problems.\n");
+
+ *N = n;
+ *CTS = cts;
+
+ DRM_DEBUG("Calculated ACR timing N=%d CTS=%d for frequency %d\n",
+ *N, *CTS, freq);
}
struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
@@ -86,15 +116,16 @@
struct radeon_hdmi_acr res;
u8 i;
- for (i = 0; r600_hdmi_predefined_acr[i].clock != clock &&
- r600_hdmi_predefined_acr[i].clock != 0; i++)
- ;
- res = r600_hdmi_predefined_acr[i];
+ /* Precalculated values for common clocks */
+ for (i = 0; i < ARRAY_SIZE(r600_hdmi_predefined_acr); i++) {
+ if (r600_hdmi_predefined_acr[i].clock == clock)
+ return r600_hdmi_predefined_acr[i];
+ }
- /* In case some CTS are missing */
- r600_hdmi_calc_cts(clock, &res.cts_32khz, res.n_32khz, 32000);
- r600_hdmi_calc_cts(clock, &res.cts_44_1khz, res.n_44_1khz, 44100);
- r600_hdmi_calc_cts(clock, &res.cts_48khz, res.n_48khz, 48000);
+ /* And odd clocks get manually calculated */
+ r600_hdmi_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000);
+ r600_hdmi_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100);
+ r600_hdmi_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000);
return res;
}
@@ -133,14 +164,7 @@
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
uint32_t offset = dig->afmt->offset;
uint8_t *frame = buffer + 3;
-
- /* Our header values (type, version, length) should be alright, Intel
- * is using the same. Checksum function also seems to be OK, it works
- * fine for audio infoframe. However calculated value is always lower
- * by 2 in comparison to fglrx. It breaks displaying anything in case
- * of TVs that strictly check the checksum. Hack it manually here to
- * workaround this issue. */
- frame[0x0] += 2;
+ uint8_t *header = buffer;
WREG32(HDMI0_AVI_INFO0 + offset,
frame[0x0] | (frame[0x1] << 8) | (frame[0x2] << 16) | (frame[0x3] << 24));
@@ -149,7 +173,7 @@
WREG32(HDMI0_AVI_INFO2 + offset,
frame[0x8] | (frame[0x9] << 8) | (frame[0xA] << 16) | (frame[0xB] << 24));
WREG32(HDMI0_AVI_INFO3 + offset,
- frame[0xC] | (frame[0xD] << 8));
+ frame[0xC] | (frame[0xD] << 8) | (header[1] << 24));
}
/*
@@ -245,17 +269,29 @@
* number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE
* is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator
*/
- if (ASIC_IS_DCE3(rdev)) {
- /* according to the reg specs, this should DCE3.2 only, but in
- * practice it seems to cover DCE3.0 as well.
- */
- WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
- WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
- WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+ if (ASIC_IS_DCE32(rdev)) {
+ if (dig->dig_encoder == 0) {
+ WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+ WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+ WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+ } else {
+ WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+ WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+ WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+ }
} else {
- /* according to the reg specs, this should be DCE2.0 and DCE3.0 */
- WREG32(AUDIO_DTO, AUDIO_DTO_PHASE(base_rate / 10) |
- AUDIO_DTO_MODULE(clock / 10));
+ /* according to the reg specs, this should DCE3.2 only, but in
+ * practice it seems to cover DCE2.0/3.0/3.1 as well.
+ */
+ if (dig->dig_encoder == 0) {
+ WREG32(DCCG_AUDIO_DTO0_PHASE, base_rate * 100);
+ WREG32(DCCG_AUDIO_DTO0_MODULE, clock * 100);
+ WREG32(DCCG_AUDIO_DTO_SELECT, 0); /* select DTO0 */
+ } else {
+ WREG32(DCCG_AUDIO_DTO1_PHASE, base_rate * 100);
+ WREG32(DCCG_AUDIO_DTO1_MODULE, clock * 100);
+ WREG32(DCCG_AUDIO_DTO_SELECT, 1); /* select DTO1 */
+ }
}
}
@@ -273,6 +309,9 @@
uint32_t offset;
ssize_t err;
+ if (!dig || !dig->afmt)
+ return;
+
/* Silent, r600_hdmi_enable will raise WARN for us */
if (!dig->afmt->enabled)
return;
@@ -301,8 +340,8 @@
}
WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
- HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
- HDMI0_ACR_SOURCE); /* select SW CTS value */
+ HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+ HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
HDMI0_NULL_SEND | /* send null packets when required */
@@ -455,6 +494,9 @@
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
u32 hdmi = HDMI0_ERROR_ACK;
+ if (!dig || !dig->afmt)
+ return;
+
/* Silent, r600_hdmi_enable will raise WARN for us */
if (enable && dig->afmt->enabled)
return;
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 79df558..eb28716 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1259,7 +1259,7 @@
*/
# define PACKET3_CP_DMA_CP_SYNC (1 << 31)
/* COMMAND */
-# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
/* 0 - none
* 1 - 8 in 16
* 2 - 8 in 32
@@ -1283,6 +1283,7 @@
# define PACKET3_CP_DMA_CMD_DAIC (1 << 29)
#define PACKET3_SURFACE_SYNC 0x43
# define PACKET3_CB0_DEST_BASE_ENA (1 << 6)
+# define PACKET3_FULL_CACHE_ENA (1 << 20) /* r7xx+ only */
# define PACKET3_TC_ACTION_ENA (1 << 23)
# define PACKET3_VC_ACTION_ENA (1 << 24)
# define PACKET3_CB_ACTION_ENA (1 << 25)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 142ce6c..d4ff48c 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -408,6 +408,7 @@
uint64_t gpu_addr;
void *cpu_ptr;
uint32_t domain;
+ uint32_t align;
};
struct radeon_sa_bo;
@@ -1144,6 +1145,7 @@
struct radeon_bo *vcpu_bo;
void *cpu_addr;
uint64_t gpu_addr;
+ void *saved_bo;
atomic_t handles[RADEON_MAX_UVD_HANDLES];
struct drm_file *filp[RADEON_MAX_UVD_HANDLES];
struct delayed_work idle_work;
@@ -1762,7 +1764,7 @@
WREG32(reg, tmp_); \
} while (0)
#define WREG32_AND(reg, and) WREG32_P(reg, 0, and)
-#define WREG32_OR(reg, or) WREG32_P(reg, or, ~or)
+#define WREG32_OR(reg, or) WREG32_P(reg, or, ~(or))
#define WREG32_PLL_P(reg, val, mask) \
do { \
uint32_t tmp_ = RREG32_PLL(reg); \
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index a2802b47..de36c47 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -986,8 +986,8 @@
.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
.dma = &r600_copy_dma,
.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
- .copy = &r600_copy_dma,
- .copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+ .copy = &r600_copy_blit,
+ .copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
},
.surface = {
.set_reg = r600_set_surface_reg,
@@ -1074,8 +1074,8 @@
.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
.dma = &r600_copy_dma,
.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
- .copy = &r600_copy_dma,
- .copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+ .copy = &r600_copy_blit,
+ .copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
},
.surface = {
.set_reg = r600_set_surface_reg,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index a72759e..34223fc 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -399,7 +399,7 @@
/* uvd */
int r600_uvd_init(struct radeon_device *rdev);
int r600_uvd_rbc_start(struct radeon_device *rdev);
-void r600_uvd_rbc_stop(struct radeon_device *rdev);
+void r600_uvd_stop(struct radeon_device *rdev);
int r600_uvd_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
void r600_uvd_fence_emit(struct radeon_device *rdev,
struct radeon_fence *fence);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index dea6f63c..ba2ab9a 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -463,6 +463,13 @@
}
}
+ /* Fujitsu D3003-S2 board lists DVI-I as DVI-I and VGA */
+ if ((dev->pdev->device == 0x9805) &&
+ (dev->pdev->subsystem_vendor == 0x1734) &&
+ (dev->pdev->subsystem_device == 0x11bd)) {
+ if (*connector_type == DRM_MODE_CONNECTOR_VGA)
+ return false;
+ }
return true;
}
@@ -715,13 +722,16 @@
(ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT *)
(ctx->bios + data_offset +
le16_to_cpu(router_obj->asObjects[k].usSrcDstTableOffset));
+ u8 *num_dst_objs = (u8 *)
+ ((u8 *)router_src_dst_table + 1 +
+ (router_src_dst_table->ucNumberOfSrc * 2));
+ u16 *dst_objs = (u16 *)(num_dst_objs + 1);
int enum_id;
router.router_id = router_obj_id;
- for (enum_id = 0; enum_id < router_src_dst_table->ucNumberOfDst;
- enum_id++) {
+ for (enum_id = 0; enum_id < (*num_dst_objs); enum_id++) {
if (le16_to_cpu(path->usConnObjectId) ==
- le16_to_cpu(router_src_dst_table->usDstObjectID[enum_id]))
+ le16_to_cpu(dst_objs[enum_id]))
break;
}
@@ -1651,7 +1661,9 @@
kfree(edid);
}
}
- record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
+ record += fake_edid_record->ucFakeEDIDLength ?
+ fake_edid_record->ucFakeEDIDLength + 2 :
+ sizeof(ATOM_FAKE_EDID_PATCH_RECORD);
break;
case LCD_PANEL_RESOLUTION_RECORD_TYPE:
panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
@@ -1903,7 +1915,7 @@
"adm1032",
"adm1030",
"max6649",
- "lm64",
+ "lm63", /* lm64 */
"f75375",
"asc7xxx",
};
@@ -1914,7 +1926,7 @@
"adm1032",
"adm1030",
"max6649",
- "lm64",
+ "lm63", /* lm64 */
"f75375",
"RV6xx",
"RV770",
@@ -2921,6 +2933,10 @@
/* tell the bios not to handle mode switching */
bios_6_scratch |= ATOM_S6_ACC_BLOCK_DISPLAY_SWITCH;
+ /* clear the vbios dpms state */
+ if (ASIC_IS_DCE4(rdev))
+ bios_2_scratch &= ~ATOM_S2_DEVICE_DPMS_STATE;
+
if (rdev->family >= CHIP_R600) {
WREG32(R600_BIOS_2_SCRATCH, bios_2_scratch);
WREG32(R600_BIOS_6_SCRATCH, bios_6_scratch);
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index d96070b..8c44ef5 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -215,7 +215,8 @@
memcpy(&output, info->buffer.pointer, size);
/* TODO: check version? */
- printk("ATPX version %u\n", output.version);
+ printk("ATPX version %u, functions 0x%08x\n",
+ output.version, output.function_bits);
radeon_atpx_parse_functions(&atpx->functions, output.function_bits);
@@ -522,6 +523,13 @@
has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
}
+ /* some newer PX laptops mark the dGPU as a non-VGA display device */
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+ vga_count++;
+
+ has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true);
+ }
+
if (has_atpx && vga_count == 2) {
acpi_get_name(radeon_atpx_priv.atpx.handle, ACPI_FULL_PATHNAME, &buffer);
printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 061b227..72b0248 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -76,7 +76,7 @@
static bool radeon_read_bios(struct radeon_device *rdev)
{
- uint8_t __iomem *bios;
+ uint8_t __iomem *bios, val1, val2;
size_t size;
rdev->bios = NULL;
@@ -86,15 +86,19 @@
return false;
}
- if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) {
+ val1 = readb(&bios[0]);
+ val2 = readb(&bios[1]);
+
+ if (size == 0 || val1 != 0x55 || val2 != 0xaa) {
pci_unmap_rom(rdev->pdev, bios);
return false;
}
- rdev->bios = kmemdup(bios, size, GFP_KERNEL);
+ rdev->bios = kzalloc(size, GFP_KERNEL);
if (rdev->bios == NULL) {
pci_unmap_rom(rdev->pdev, bios);
return false;
}
+ memcpy_fromio(rdev->bios, bios, size);
pci_unmap_rom(rdev->pdev, bios);
return true;
}
@@ -196,6 +200,20 @@
}
}
+ if (!found) {
+ while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+ dhandle = ACPI_HANDLE(&pdev->dev);
+ if (!dhandle)
+ continue;
+
+ status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+ if (!ACPI_FAILURE(status)) {
+ found = true;
+ break;
+ }
+ }
+ }
+
if (!found)
return false;
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 78edadc..68ce360 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -147,7 +147,7 @@
enum radeon_combios_table_offset table)
{
struct radeon_device *rdev = dev->dev_private;
- int rev;
+ int rev, size;
uint16_t offset = 0, check_offset;
if (!rdev->bios)
@@ -156,174 +156,106 @@
switch (table) {
/* absolute offset tables */
case COMBIOS_ASIC_INIT_1_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0xc);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0xc;
break;
case COMBIOS_BIOS_SUPPORT_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x14);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x14;
break;
case COMBIOS_DAC_PROGRAMMING_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x2a);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x2a;
break;
case COMBIOS_MAX_COLOR_DEPTH_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x2c);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x2c;
break;
case COMBIOS_CRTC_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x2e);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x2e;
break;
case COMBIOS_PLL_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x30);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x30;
break;
case COMBIOS_TV_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x32);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x32;
break;
case COMBIOS_DFP_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x34);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x34;
break;
case COMBIOS_HW_CONFIG_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x36);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x36;
break;
case COMBIOS_MULTIMEDIA_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x38);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x38;
break;
case COMBIOS_TV_STD_PATCH_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x3e);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x3e;
break;
case COMBIOS_LCD_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x40);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x40;
break;
case COMBIOS_MOBILE_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x42);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x42;
break;
case COMBIOS_PLL_INIT_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x46);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x46;
break;
case COMBIOS_MEM_CONFIG_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x48);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x48;
break;
case COMBIOS_SAVE_MASK_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x4a);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x4a;
break;
case COMBIOS_HARDCODED_EDID_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x4c);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x4c;
break;
case COMBIOS_ASIC_INIT_2_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x4e);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x4e;
break;
case COMBIOS_CONNECTOR_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x50);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x50;
break;
case COMBIOS_DYN_CLK_1_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x52);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x52;
break;
case COMBIOS_RESERVED_MEM_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x54);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x54;
break;
case COMBIOS_EXT_TMDS_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x58);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x58;
break;
case COMBIOS_MEM_CLK_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x5a);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x5a;
break;
case COMBIOS_EXT_DAC_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x5c);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x5c;
break;
case COMBIOS_MISC_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x5e);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x5e;
break;
case COMBIOS_CRT_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x60);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x60;
break;
case COMBIOS_INTEGRATED_SYSTEM_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x62);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x62;
break;
case COMBIOS_COMPONENT_VIDEO_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x64);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x64;
break;
case COMBIOS_FAN_SPEED_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x66);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x66;
break;
case COMBIOS_OVERDRIVE_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x68);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x68;
break;
case COMBIOS_OEM_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x6a);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x6a;
break;
case COMBIOS_DYN_CLK_2_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x6c);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x6c;
break;
case COMBIOS_POWER_CONNECTOR_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x6e);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x6e;
break;
case COMBIOS_I2C_INFO_TABLE:
- check_offset = RBIOS16(rdev->bios_header_start + 0x70);
- if (check_offset)
- offset = check_offset;
+ check_offset = 0x70;
break;
/* relative offset tables */
case COMBIOS_ASIC_INIT_3_TABLE: /* offset from misc info */
@@ -439,11 +371,16 @@
}
break;
default:
+ check_offset = 0;
break;
}
- return offset;
+ size = RBIOS8(rdev->bios_header_start + 0x6);
+ /* check absolute offset tables */
+ if (table < COMBIOS_ASIC_INIT_3_TABLE && check_offset && check_offset < size)
+ offset = RBIOS16(rdev->bios_header_start + check_offset);
+ return offset;
}
bool radeon_combios_check_hardcoded_edid(struct radeon_device *rdev)
@@ -965,16 +902,22 @@
dac = RBIOS8(dac_info + 0x3) & 0xf;
p_dac->ps2_pdac_adj = (bg << 8) | (dac);
}
- /* if the values are all zeros, use the table */
- if (p_dac->ps2_pdac_adj)
+ /* if the values are zeros, use the table */
+ if ((dac == 0) || (bg == 0))
+ found = 0;
+ else
found = 1;
}
/* quirks */
- /* Radeon 9100 (R200) */
- if ((dev->pdev->device == 0x514D) &&
+ /* Radeon 7000 (RV100) */
+ if (((dev->pdev->device == 0x5159) &&
(dev->pdev->subsystem_vendor == 0x174B) &&
- (dev->pdev->subsystem_device == 0x7149)) {
+ (dev->pdev->subsystem_device == 0x7c28)) ||
+ /* Radeon 9100 (R200) */
+ ((dev->pdev->device == 0x514D) &&
+ (dev->pdev->subsystem_vendor == 0x174B) &&
+ (dev->pdev->subsystem_device == 0x7149))) {
/* vbios value is bad, use the default */
found = 0;
}
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2399f25..fc604fc 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1345,7 +1345,7 @@
struct radeon_device *rdev = dev->dev_private;
if (ASIC_IS_DCE5(rdev) &&
- (rdev->clock.dp_extclk >= 53900) &&
+ (rdev->clock.default_dispclk >= 53900) &&
radeon_connector_encoder_is_hbr2(connector)) {
return true;
}
@@ -1489,6 +1489,24 @@
.force = radeon_dvi_force,
};
+static const struct drm_connector_funcs radeon_edp_connector_funcs = {
+ .dpms = drm_helper_connector_dpms,
+ .detect = radeon_dp_detect,
+ .fill_modes = drm_helper_probe_single_connector_modes,
+ .set_property = radeon_lvds_set_property,
+ .destroy = radeon_dp_connector_destroy,
+ .force = radeon_dvi_force,
+};
+
+static const struct drm_connector_funcs radeon_lvds_bridge_connector_funcs = {
+ .dpms = drm_helper_connector_dpms,
+ .detect = radeon_dp_detect,
+ .fill_modes = drm_helper_probe_single_connector_modes,
+ .set_property = radeon_lvds_set_property,
+ .destroy = radeon_dp_connector_destroy,
+ .force = radeon_dvi_force,
+};
+
void
radeon_add_atom_connector(struct drm_device *dev,
uint32_t connector_id,
@@ -1580,8 +1598,6 @@
goto failed;
radeon_dig_connector->igp_lane_info = igp_lane_info;
radeon_connector->con_priv = radeon_dig_connector;
- drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
- drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
if (i2c_bus->valid) {
/* add DP i2c bus */
if (connector_type == DRM_MODE_CONNECTOR_eDP)
@@ -1598,6 +1614,10 @@
case DRM_MODE_CONNECTOR_VGA:
case DRM_MODE_CONNECTOR_DVIA:
default:
+ drm_connector_init(dev, &radeon_connector->base,
+ &radeon_dp_connector_funcs, connector_type);
+ drm_connector_helper_add(&radeon_connector->base,
+ &radeon_dp_connector_helper_funcs);
connector->interlace_allowed = true;
connector->doublescan_allowed = true;
radeon_connector->dac_load_detect = true;
@@ -1610,6 +1630,10 @@
case DRM_MODE_CONNECTOR_HDMIA:
case DRM_MODE_CONNECTOR_HDMIB:
case DRM_MODE_CONNECTOR_DisplayPort:
+ drm_connector_init(dev, &radeon_connector->base,
+ &radeon_dp_connector_funcs, connector_type);
+ drm_connector_helper_add(&radeon_connector->base,
+ &radeon_dp_connector_helper_funcs);
drm_object_attach_property(&radeon_connector->base.base,
rdev->mode_info.underscan_property,
UNDERSCAN_OFF);
@@ -1634,6 +1658,10 @@
break;
case DRM_MODE_CONNECTOR_LVDS:
case DRM_MODE_CONNECTOR_eDP:
+ drm_connector_init(dev, &radeon_connector->base,
+ &radeon_lvds_bridge_connector_funcs, connector_type);
+ drm_connector_helper_add(&radeon_connector->base,
+ &radeon_dp_connector_helper_funcs);
drm_object_attach_property(&radeon_connector->base.base,
dev->mode_config.scaling_mode_property,
DRM_MODE_SCALE_FULLSCREEN);
@@ -1797,7 +1825,7 @@
goto failed;
radeon_dig_connector->igp_lane_info = igp_lane_info;
radeon_connector->con_priv = radeon_dig_connector;
- drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
+ drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type);
drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
if (i2c_bus->valid) {
/* add DP i2c bus */
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7e265a5..6627585 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -80,9 +80,11 @@
p->relocs[i].lobj.bo = p->relocs[i].robj;
p->relocs[i].lobj.written = !!r->write_domain;
- /* the first reloc of an UVD job is the
- msg and that must be in VRAM */
- if (p->ring == R600_RING_TYPE_UVD_INDEX && i == 0) {
+ /* the first reloc of an UVD job is the msg and that must be in
+ VRAM, also but everything into VRAM on AGP cards to avoid
+ image corruptions */
+ if (p->ring == R600_RING_TYPE_UVD_INDEX &&
+ (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
/* TODO: is this still needed for NI+ ? */
p->relocs[i].lobj.domain =
RADEON_GEM_DOMAIN_VRAM;
@@ -94,6 +96,12 @@
uint32_t domain = r->write_domain ?
r->write_domain : r->read_domains;
+ if (domain & RADEON_GEM_DOMAIN_CPU) {
+ DRM_ERROR("RADEON_GEM_DOMAIN_CPU is not valid "
+ "for command submission\n");
+ return -EINVAL;
+ }
+
p->relocs[i].lobj.domain = domain;
if (domain == RADEON_GEM_DOMAIN_VRAM)
domain |= RADEON_GEM_DOMAIN_GTT;
@@ -169,11 +177,13 @@
u32 ring = RADEON_CS_RING_GFX;
s32 priority = 0;
+ INIT_LIST_HEAD(&p->validated);
+
if (!cs->num_chunks) {
return 0;
}
+
/* get chunks */
- INIT_LIST_HEAD(&p->validated);
p->idx = 0;
p->ib.sa_bo = NULL;
p->ib.semaphore = NULL;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index b0dc0b6..8df1525 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1196,13 +1196,22 @@
return r;
}
if ((radeon_testing & 1)) {
- radeon_test_moves(rdev);
+ if (rdev->accel_working)
+ radeon_test_moves(rdev);
+ else
+ DRM_INFO("radeon: acceleration disabled, skipping move tests\n");
}
if ((radeon_testing & 2)) {
- radeon_test_syncing(rdev);
+ if (rdev->accel_working)
+ radeon_test_syncing(rdev);
+ else
+ DRM_INFO("radeon: acceleration disabled, skipping sync tests\n");
}
if (radeon_benchmarking) {
- radeon_benchmark(rdev, radeon_benchmarking);
+ if (rdev->accel_working)
+ radeon_benchmark(rdev, radeon_benchmarking);
+ else
+ DRM_INFO("radeon: acceleration disabled, skipping benchmarks\n");
}
return 0;
}
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index eb18bb7..a84de32 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -688,6 +688,10 @@
struct radeon_device *rdev = dev->dev_private;
int ret = 0;
+ /* don't leak the edid if we already fetched it in detect() */
+ if (radeon_connector->edid)
+ goto got_edid;
+
/* on hw with routers, select right port */
if (radeon_connector->router.ddc_valid)
radeon_router_select_ddc_port(radeon_connector);
@@ -727,8 +731,10 @@
radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev);
}
if (radeon_connector->edid) {
+got_edid:
drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
+ drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
return ret;
}
drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 43ec4a4..2915a1c 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -467,6 +467,7 @@
size *= 2;
r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
RADEON_GPU_PAGE_ALIGN(size),
+ RADEON_GPU_PAGE_SIZE,
RADEON_GEM_DOMAIN_VRAM);
if (r) {
dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
@@ -1156,6 +1157,8 @@
return -ENOMEM;
r = radeon_ib_get(rdev, ridx, &ib, NULL, ndw * 4);
+ if (r)
+ return r;
ib.length_dw = 0;
r = radeon_vm_update_pdes(rdev, vm, &ib, bo_va->soffset, bo_va->eoffset);
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index fc60b74..e24ca6a 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -1020,6 +1020,9 @@
/* Add the default buses */
void radeon_i2c_init(struct radeon_device *rdev)
{
+ if (radeon_hw_i2c)
+ DRM_INFO("hw_i2c forced on, you may experience display detection problems!\n");
+
if (rdev->is_atom_bios)
radeon_atombios_i2c_init(rdev);
else
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 5a99d43..1fe12ab 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -241,9 +241,6 @@
{
int r = 0;
- INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
- INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
-
spin_lock_init(&rdev->irq.lock);
r = drm_vblank_init(rdev->ddev, rdev->num_crtc);
if (r) {
@@ -265,6 +262,10 @@
rdev->irq.installed = false;
return r;
}
+
+ INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+ INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
+
DRM_INFO("radeon: irq initialized.\n");
return 0;
}
@@ -284,8 +285,8 @@
rdev->irq.installed = false;
if (rdev->msi_enabled)
pci_disable_msi(rdev->pdev);
+ flush_work(&rdev->hotplug_work);
}
- flush_work(&rdev->hotplug_work);
}
/**
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 4f2d4f4..2c3c4c5 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -414,6 +414,9 @@
value = rdev->config.si.tile_mode_array;
value_size = sizeof(uint32_t)*32;
break;
+ case RADEON_INFO_SI_CP_DMA_COMPUTE:
+ *value = 1;
+ break;
default:
DRM_DEBUG_KMS("Invalid request %d\n", info->request);
return -EINVAL;
@@ -482,6 +485,10 @@
radeon_vm_init(rdev, &fpriv->vm);
+ r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+ if (r)
+ return r;
+
/* map the ib pool buffer read only into
* virtual address space */
bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
@@ -489,6 +496,8 @@
r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
RADEON_VM_PAGE_READABLE |
RADEON_VM_PAGE_SNOOPED);
+
+ radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
if (r) {
radeon_vm_fini(rdev, &fpriv->vm);
kfree(fpriv);
@@ -657,6 +666,8 @@
/* Get associated drm_crtc: */
drmcrtc = &rdev->mode_info.crtcs[crtc]->base;
+ if (!drmcrtc)
+ return -EINVAL;
/* Helper routine in DRM core does all the work: */
return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error,
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index 7cb178a..bc73021 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -422,6 +422,7 @@
/* Pin framebuffer & get tilling informations */
obj = radeon_fb->obj;
rbo = gem_to_radeon_bo(obj);
+retry:
r = radeon_bo_reserve(rbo, false);
if (unlikely(r != 0))
return r;
@@ -430,6 +431,33 @@
&base);
if (unlikely(r != 0)) {
radeon_bo_unreserve(rbo);
+
+ /* On old GPU like RN50 with little vram pining can fails because
+ * current fb is taking all space needed. So instead of unpining
+ * the old buffer after pining the new one, first unpin old one
+ * and then retry pining new one.
+ *
+ * As only master can set mode only master can pin and it is
+ * unlikely the master client will race with itself especialy
+ * on those old gpu with single crtc.
+ *
+ * We don't shutdown the display controller because new buffer
+ * will end up in same spot.
+ */
+ if (!atomic && fb && fb != crtc->fb) {
+ struct radeon_bo *old_rbo;
+ unsigned long nsize, osize;
+
+ old_rbo = gem_to_radeon_bo(to_radeon_framebuffer(fb)->obj);
+ osize = radeon_bo_size(old_rbo);
+ nsize = radeon_bo_size(rbo);
+ if (nsize <= osize && !radeon_bo_reserve(old_rbo, false)) {
+ radeon_bo_unpin(old_rbo);
+ radeon_bo_unreserve(old_rbo);
+ fb = NULL;
+ goto retry;
+ }
+ }
return -EINVAL;
}
radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 1424ccd..f837279 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -582,22 +582,30 @@
rbo = container_of(bo, struct radeon_bo, tbo);
radeon_bo_check_tiling(rbo, 0, 0);
rdev = rbo->rdev;
- if (bo->mem.mem_type == TTM_PL_VRAM) {
- size = bo->mem.num_pages << PAGE_SHIFT;
- offset = bo->mem.start << PAGE_SHIFT;
- if ((offset + size) > rdev->mc.visible_vram_size) {
- /* hurrah the memory is not visible ! */
- radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
- rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
- r = ttm_bo_validate(bo, &rbo->placement, false, false);
- if (unlikely(r != 0))
- return r;
- offset = bo->mem.start << PAGE_SHIFT;
- /* this should not happen */
- if ((offset + size) > rdev->mc.visible_vram_size)
- return -EINVAL;
- }
+ if (bo->mem.mem_type != TTM_PL_VRAM)
+ return 0;
+
+ size = bo->mem.num_pages << PAGE_SHIFT;
+ offset = bo->mem.start << PAGE_SHIFT;
+ if ((offset + size) <= rdev->mc.visible_vram_size)
+ return 0;
+
+ /* hurrah the memory is not visible ! */
+ radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
+ rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+ r = ttm_bo_validate(bo, &rbo->placement, false, false);
+ if (unlikely(r == -ENOMEM)) {
+ radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
+ return ttm_bo_validate(bo, &rbo->placement, false, false);
+ } else if (unlikely(r != 0)) {
+ return r;
}
+
+ offset = bo->mem.start << PAGE_SHIFT;
+ /* this should never happen */
+ if ((offset + size) > rdev->mc.visible_vram_size)
+ return -EINVAL;
+
return 0;
}
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index e2cb80a..2943823 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -158,7 +158,7 @@
extern int radeon_sa_bo_manager_init(struct radeon_device *rdev,
struct radeon_sa_manager *sa_manager,
- unsigned size, u32 domain);
+ unsigned size, u32 align, u32 domain);
extern void radeon_sa_bo_manager_fini(struct radeon_device *rdev,
struct radeon_sa_manager *sa_manager);
extern int radeon_sa_bo_manager_start(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 788c64c..469ba71 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -561,8 +561,10 @@
rdev->pm.current_clock_mode_index = 0;
rdev->pm.current_sclk = rdev->pm.default_sclk;
rdev->pm.current_mclk = rdev->pm.default_mclk;
- rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
- rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+ if (rdev->pm.power_state) {
+ rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage;
+ rdev->pm.current_vddci = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.vddci;
+ }
if (rdev->pm.pm_method == PM_METHOD_DYNPM
&& rdev->pm.dynpm_state == DYNPM_STATE_SUSPENDED) {
rdev->pm.dynpm_state = DYNPM_STATE_ACTIVE;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 82434018..6e0f480 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -224,6 +224,7 @@
}
r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo,
RADEON_IB_POOL_SIZE*64*1024,
+ RADEON_GPU_PAGE_SIZE,
RADEON_GEM_DOMAIN_GTT);
if (r) {
return r;
@@ -822,9 +823,11 @@
* packet that is the root issue
*/
i = (ring->rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask;
- for (j = 0; j <= (count + 32); j++) {
- seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
- i = (i + 1) & ring->ptr_mask;
+ if (ring->ready) {
+ for (j = 0; j <= (count + 32); j++) {
+ seq_printf(m, "r[%5d]=0x%08x\n", i, ring->ring[i]);
+ i = (i + 1) & ring->ptr_mask;
+ }
}
return 0;
}
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 0abe5a9..f0bac68 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -49,7 +49,7 @@
int radeon_sa_bo_manager_init(struct radeon_device *rdev,
struct radeon_sa_manager *sa_manager,
- unsigned size, u32 domain)
+ unsigned size, u32 align, u32 domain)
{
int i, r;
@@ -57,13 +57,14 @@
sa_manager->bo = NULL;
sa_manager->size = size;
sa_manager->domain = domain;
+ sa_manager->align = align;
sa_manager->hole = &sa_manager->olist;
INIT_LIST_HEAD(&sa_manager->olist);
for (i = 0; i < RADEON_NUM_RINGS; ++i) {
INIT_LIST_HEAD(&sa_manager->flist[i]);
}
- r = radeon_bo_create(rdev, size, RADEON_GPU_PAGE_SIZE, true,
+ r = radeon_bo_create(rdev, size, align, true,
domain, NULL, &sa_manager->bo);
if (r) {
dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r);
@@ -317,7 +318,7 @@
unsigned tries[RADEON_NUM_RINGS];
int i, r;
- BUG_ON(align > RADEON_GPU_PAGE_SIZE);
+ BUG_ON(align > sa_manager->align);
BUG_ON(size > sa_manager->size);
*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index bbed4af..f9ebf2b 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -37,8 +37,8 @@
struct radeon_bo **gtt_obj = NULL;
struct radeon_fence *fence = NULL;
uint64_t gtt_addr, vram_addr;
- unsigned i, n, size;
- int r, ring;
+ unsigned n, size;
+ int i, r, ring;
switch (flag) {
case RADEON_TEST_COPY_DMA:
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 6c0ce89..4a14e11 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -189,7 +189,7 @@
rbo = container_of(bo, struct radeon_bo, tbo);
switch (bo->mem.mem_type) {
case TTM_PL_VRAM:
- if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false)
+ if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false)
radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU);
else
radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index cad735d..5715429 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -123,64 +123,6 @@
return r;
}
- r = radeon_uvd_resume(rdev);
- if (r)
- return r;
-
- memset(rdev->uvd.cpu_addr, 0, bo_size);
- memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
-
- r = radeon_uvd_suspend(rdev);
- if (r)
- return r;
-
- for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
- atomic_set(&rdev->uvd.handles[i], 0);
- rdev->uvd.filp[i] = NULL;
- }
-
- return 0;
-}
-
-void radeon_uvd_fini(struct radeon_device *rdev)
-{
- radeon_uvd_suspend(rdev);
- radeon_bo_unref(&rdev->uvd.vcpu_bo);
-}
-
-int radeon_uvd_suspend(struct radeon_device *rdev)
-{
- int r;
-
- if (rdev->uvd.vcpu_bo == NULL)
- return 0;
-
- r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
- if (!r) {
- radeon_bo_kunmap(rdev->uvd.vcpu_bo);
- radeon_bo_unpin(rdev->uvd.vcpu_bo);
- rdev->uvd.cpu_addr = NULL;
- if (!radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_CPU, NULL)) {
- radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr);
- }
- radeon_bo_unreserve(rdev->uvd.vcpu_bo);
-
- if (rdev->uvd.cpu_addr) {
- radeon_fence_driver_start_ring(rdev, R600_RING_TYPE_UVD_INDEX);
- } else {
- rdev->fence_drv[R600_RING_TYPE_UVD_INDEX].cpu_addr = NULL;
- }
- }
- return r;
-}
-
-int radeon_uvd_resume(struct radeon_device *rdev)
-{
- int r;
-
- if (rdev->uvd.vcpu_bo == NULL)
- return -EINVAL;
-
r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
if (r) {
radeon_bo_unref(&rdev->uvd.vcpu_bo);
@@ -188,10 +130,6 @@
return r;
}
- /* Have been pin in cpu unmap unpin */
- radeon_bo_kunmap(rdev->uvd.vcpu_bo);
- radeon_bo_unpin(rdev->uvd.vcpu_bo);
-
r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
&rdev->uvd.gpu_addr);
if (r) {
@@ -209,6 +147,84 @@
radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
+ atomic_set(&rdev->uvd.handles[i], 0);
+ rdev->uvd.filp[i] = NULL;
+ }
+
+ return 0;
+}
+
+void radeon_uvd_fini(struct radeon_device *rdev)
+{
+ int r;
+
+ if (rdev->uvd.vcpu_bo == NULL)
+ return;
+
+ r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
+ if (!r) {
+ radeon_bo_kunmap(rdev->uvd.vcpu_bo);
+ radeon_bo_unpin(rdev->uvd.vcpu_bo);
+ radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+ }
+
+ radeon_bo_unref(&rdev->uvd.vcpu_bo);
+
+ release_firmware(rdev->uvd_fw);
+}
+
+int radeon_uvd_suspend(struct radeon_device *rdev)
+{
+ unsigned size;
+ void *ptr;
+ int i;
+
+ if (rdev->uvd.vcpu_bo == NULL)
+ return 0;
+
+ for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i)
+ if (atomic_read(&rdev->uvd.handles[i]))
+ break;
+
+ if (i == RADEON_MAX_UVD_HANDLES)
+ return 0;
+
+ size = radeon_bo_size(rdev->uvd.vcpu_bo);
+ size -= rdev->uvd_fw->size;
+
+ ptr = rdev->uvd.cpu_addr;
+ ptr += rdev->uvd_fw->size;
+
+ rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
+ memcpy(rdev->uvd.saved_bo, ptr, size);
+
+ return 0;
+}
+
+int radeon_uvd_resume(struct radeon_device *rdev)
+{
+ unsigned size;
+ void *ptr;
+
+ if (rdev->uvd.vcpu_bo == NULL)
+ return -EINVAL;
+
+ memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
+
+ size = radeon_bo_size(rdev->uvd.vcpu_bo);
+ size -= rdev->uvd_fw->size;
+
+ ptr = rdev->uvd.cpu_addr;
+ ptr += rdev->uvd_fw->size;
+
+ if (rdev->uvd.saved_bo != NULL) {
+ memcpy(ptr, rdev->uvd.saved_bo, size);
+ kfree(rdev->uvd.saved_bo);
+ rdev->uvd.saved_bo = NULL;
+ } else
+ memset(ptr, 0, size);
+
return 0;
}
@@ -222,10 +238,12 @@
{
int i, r;
for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
- if (rdev->uvd.filp[i] == filp) {
- uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+ uint32_t handle = atomic_read(&rdev->uvd.handles[i]);
+ if (handle != 0 && rdev->uvd.filp[i] == filp) {
struct radeon_fence *fence;
+ radeon_uvd_note_usage(rdev);
+
r = radeon_uvd_get_destroy_msg(rdev,
R600_RING_TYPE_UVD_INDEX, handle, &fence);
if (r) {
@@ -343,6 +361,14 @@
return -EINVAL;
}
+ if (bo->tbo.sync_obj) {
+ r = radeon_fence_wait(bo->tbo.sync_obj, false);
+ if (r) {
+ DRM_ERROR("Failed waiting for UVD message (%d)!\n", r);
+ return r;
+ }
+ }
+
r = radeon_bo_kmap(bo, &ptr);
if (r)
return r;
@@ -423,6 +449,10 @@
cmd = radeon_get_ib_value(p, p->idx) >> 1;
if (cmd < 0x4) {
+ if (end <= start) {
+ DRM_ERROR("invalid reloc offset %X!\n", offset);
+ return -EINVAL;
+ }
if ((end - start) < buf_sizes[cmd]) {
DRM_ERROR("buffer to small (%d / %d)!\n",
(unsigned)(end - start), buf_sizes[cmd]);
@@ -434,7 +464,7 @@
return -EINVAL;
}
- if ((start >> 28) != (end >> 28)) {
+ if ((start >> 28) != ((end - 1) >> 28)) {
DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n",
start, end);
return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 233a9b9..b8074a8 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -174,10 +174,13 @@
/* FIXME: according to doc we should set HIDE_MMCFG_BAR=0,
* AGPMODE30=0 & AGP30ENHANCED=0 in NB_CNTL */
if ((rdev->family == CHIP_RS690) || (rdev->family == CHIP_RS740)) {
- WREG32_MC(RS480_MC_MISC_CNTL,
- (RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN));
+ tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+ tmp |= RS480_GART_INDEX_REG_EN | RS690_BLOCK_GFX_D3_EN;
+ WREG32_MC(RS480_MC_MISC_CNTL, tmp);
} else {
- WREG32_MC(RS480_MC_MISC_CNTL, RS480_GART_INDEX_REG_EN);
+ tmp = RREG32_MC(RS480_MC_MISC_CNTL);
+ tmp |= RS480_GART_INDEX_REG_EN;
+ WREG32_MC(RS480_MC_MISC_CNTL, tmp);
}
/* Enable gart */
WREG32_MC(RS480_AGP_ADDRESS_SPACE_SIZE, (RS480_GART_EN | size_reg));
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 670b555..971d55f 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -582,8 +582,10 @@
return -EINVAL;
}
addr = addr & 0xFFFFFFFFFFFFF000ULL;
- addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
- addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
+ if (addr != rdev->dummy_page.addr)
+ addr |= R600_PTE_VALID | R600_PTE_READABLE |
+ R600_PTE_WRITEABLE;
+ addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
writeq(addr, ptr + (i * 8));
return 0;
}
@@ -634,6 +636,10 @@
WREG32(R_007D18_DC_HOT_PLUG_DETECT2_INT_CONTROL, hpd2);
if (ASIC_IS_DCE2(rdev))
WREG32(R_007408_HDMI0_AUDIO_PACKET_CONTROL, hdmi0);
+
+ /* posting read */
+ RREG32(R_000040_GEN_INT_CNTL);
+
return 0;
}
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 55880d5..ea28ecb 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -162,6 +162,16 @@
base = RREG32_MC(R_000100_MCCFG_FB_LOCATION);
base = G_000100_MC_FB_START(base) << 16;
rdev->mc.igp_sideport_enabled = radeon_atombios_sideport_present(rdev);
+ /* Some boards seem to be configured for 128MB of sideport memory,
+ * but really only have 64MB. Just skip the sideport and use
+ * UMA memory.
+ */
+ if (rdev->mc.igp_sideport_enabled &&
+ (rdev->mc.real_vram_size == (384 * 1024 * 1024))) {
+ base += 128 * 1024 * 1024;
+ rdev->mc.real_vram_size -= 128 * 1024 * 1024;
+ rdev->mc.mc_vram_size = rdev->mc.real_vram_size;
+ }
/* Use K8 direct mapping for fast fb access. */
rdev->fastfb_working = false;
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 4a62ad2..f5e92cf 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -744,10 +744,10 @@
(const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers));
radeon_program_register_sequence(rdev,
rv730_golden_registers,
- (const u32)ARRAY_SIZE(rv770_golden_registers));
+ (const u32)ARRAY_SIZE(rv730_golden_registers));
radeon_program_register_sequence(rdev,
rv730_mgcg_init,
- (const u32)ARRAY_SIZE(rv770_mgcg_init));
+ (const u32)ARRAY_SIZE(rv730_mgcg_init));
break;
case CHIP_RV710:
radeon_program_register_sequence(rdev,
@@ -758,18 +758,18 @@
(const u32)ARRAY_SIZE(r7xx_golden_dyn_gpr_registers));
radeon_program_register_sequence(rdev,
rv710_golden_registers,
- (const u32)ARRAY_SIZE(rv770_golden_registers));
+ (const u32)ARRAY_SIZE(rv710_golden_registers));
radeon_program_register_sequence(rdev,
rv710_mgcg_init,
- (const u32)ARRAY_SIZE(rv770_mgcg_init));
+ (const u32)ARRAY_SIZE(rv710_mgcg_init));
break;
case CHIP_RV740:
radeon_program_register_sequence(rdev,
rv740_golden_registers,
- (const u32)ARRAY_SIZE(rv770_golden_registers));
+ (const u32)ARRAY_SIZE(rv740_golden_registers));
radeon_program_register_sequence(rdev,
rv740_mgcg_init,
- (const u32)ARRAY_SIZE(rv770_mgcg_init));
+ (const u32)ARRAY_SIZE(rv740_mgcg_init));
break;
default:
break;
@@ -1829,6 +1829,8 @@
/* enable pcie gen2 link */
rv770_pcie_gen2_enable(rdev);
+ rv770_mc_program(rdev);
+
if (!rdev->me_fw || !rdev->pfp_fw || !rdev->rlc_fw) {
r = r600_init_microcode(rdev);
if (r) {
@@ -1841,7 +1843,6 @@
if (r)
return r;
- rv770_mc_program(rdev);
if (rdev->flags & RADEON_IS_AGP) {
rv770_agp_enable(rdev);
} else {
@@ -1983,6 +1984,7 @@
int rv770_suspend(struct radeon_device *rdev)
{
r600_audio_fini(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_suspend(rdev);
r700_cp_stop(rdev);
r600_dma_stop(rdev);
@@ -2098,6 +2100,7 @@
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
rv770_pcie_gart_fini(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_fini(rdev);
r600_vram_scratch_fini(rdev);
radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a1b0da6..2410c38 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1467,7 +1467,8 @@
struct drm_display_mode *mode,
struct drm_display_mode *other_mode)
{
- u32 tmp;
+ u32 tmp, buffer_alloc, i;
+ u32 pipe_offset = radeon_crtc->crtc_id * 0x20;
/*
* Line Buffer Setup
* There are 3 line buffers, each one shared by 2 display controllers.
@@ -1482,16 +1483,30 @@
* non-linked crtcs for maximum line buffer allocation.
*/
if (radeon_crtc->base.enabled && mode) {
- if (other_mode)
+ if (other_mode) {
tmp = 0; /* 1/2 */
- else
+ buffer_alloc = 1;
+ } else {
tmp = 2; /* whole */
- } else
+ buffer_alloc = 2;
+ }
+ } else {
tmp = 0;
+ buffer_alloc = 0;
+ }
WREG32(DC_LB_MEMORY_SPLIT + radeon_crtc->crtc_offset,
DC_LB_MEMORY_CONFIG(tmp));
+ WREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset,
+ DMIF_BUFFERS_ALLOCATED(buffer_alloc));
+ for (i = 0; i < rdev->usec_timeout; i++) {
+ if (RREG32(PIPE0_DMIF_BUFFER_CONTROL + pipe_offset) &
+ DMIF_BUFFERS_ALLOCATED_COMPLETED)
+ break;
+ udelay(1);
+ }
+
if (radeon_crtc->base.enabled && mode) {
switch (tmp) {
case 0:
@@ -3600,8 +3615,15 @@
rdev->mc.aper_base = pci_resource_start(rdev->pdev, 0);
rdev->mc.aper_size = pci_resource_len(rdev->pdev, 0);
/* size in MB on si */
- rdev->mc.mc_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
- rdev->mc.real_vram_size = RREG32(CONFIG_MEMSIZE) * 1024ULL * 1024ULL;
+ tmp = RREG32(CONFIG_MEMSIZE);
+ /* some boards may have garbage in the upper 16 bits */
+ if (tmp & 0xffff0000) {
+ DRM_INFO("Probable bad vram size: 0x%08x\n", tmp);
+ if (tmp & 0xffff)
+ tmp &= 0xffff;
+ }
+ rdev->mc.mc_vram_size = tmp * 1024ULL * 1024ULL;
+ rdev->mc.real_vram_size = rdev->mc.mc_vram_size;
rdev->mc.visible_vram_size = rdev->mc.aper_size;
si_vram_gtt_location(rdev, &rdev->mc);
radeon_update_bandwidth_info(rdev);
@@ -3796,13 +3818,64 @@
return 0;
}
+static int si_vm_packet3_cp_dma_check(u32 *ib, u32 idx)
+{
+ u32 start_reg, reg, i;
+ u32 command = ib[idx + 4];
+ u32 info = ib[idx + 1];
+ u32 idx_value = ib[idx];
+ if (command & PACKET3_CP_DMA_CMD_SAS) {
+ /* src address space is register */
+ if (((info & 0x60000000) >> 29) == 0) {
+ start_reg = idx_value << 2;
+ if (command & PACKET3_CP_DMA_CMD_SAIC) {
+ reg = start_reg;
+ if (!si_vm_reg_valid(reg)) {
+ DRM_ERROR("CP DMA Bad SRC register\n");
+ return -EINVAL;
+ }
+ } else {
+ for (i = 0; i < (command & 0x1fffff); i++) {
+ reg = start_reg + (4 * i);
+ if (!si_vm_reg_valid(reg)) {
+ DRM_ERROR("CP DMA Bad SRC register\n");
+ return -EINVAL;
+ }
+ }
+ }
+ }
+ }
+ if (command & PACKET3_CP_DMA_CMD_DAS) {
+ /* dst address space is register */
+ if (((info & 0x00300000) >> 20) == 0) {
+ start_reg = ib[idx + 2];
+ if (command & PACKET3_CP_DMA_CMD_DAIC) {
+ reg = start_reg;
+ if (!si_vm_reg_valid(reg)) {
+ DRM_ERROR("CP DMA Bad DST register\n");
+ return -EINVAL;
+ }
+ } else {
+ for (i = 0; i < (command & 0x1fffff); i++) {
+ reg = start_reg + (4 * i);
+ if (!si_vm_reg_valid(reg)) {
+ DRM_ERROR("CP DMA Bad DST register\n");
+ return -EINVAL;
+ }
+ }
+ }
+ }
+ }
+ return 0;
+}
+
static int si_vm_packet3_gfx_check(struct radeon_device *rdev,
u32 *ib, struct radeon_cs_packet *pkt)
{
+ int r;
u32 idx = pkt->idx + 1;
u32 idx_value = ib[idx];
u32 start_reg, end_reg, reg, i;
- u32 command, info;
switch (pkt->opcode) {
case PACKET3_NOP:
@@ -3903,50 +3976,9 @@
}
break;
case PACKET3_CP_DMA:
- command = ib[idx + 4];
- info = ib[idx + 1];
- if (command & PACKET3_CP_DMA_CMD_SAS) {
- /* src address space is register */
- if (((info & 0x60000000) >> 29) == 0) {
- start_reg = idx_value << 2;
- if (command & PACKET3_CP_DMA_CMD_SAIC) {
- reg = start_reg;
- if (!si_vm_reg_valid(reg)) {
- DRM_ERROR("CP DMA Bad SRC register\n");
- return -EINVAL;
- }
- } else {
- for (i = 0; i < (command & 0x1fffff); i++) {
- reg = start_reg + (4 * i);
- if (!si_vm_reg_valid(reg)) {
- DRM_ERROR("CP DMA Bad SRC register\n");
- return -EINVAL;
- }
- }
- }
- }
- }
- if (command & PACKET3_CP_DMA_CMD_DAS) {
- /* dst address space is register */
- if (((info & 0x00300000) >> 20) == 0) {
- start_reg = ib[idx + 2];
- if (command & PACKET3_CP_DMA_CMD_DAIC) {
- reg = start_reg;
- if (!si_vm_reg_valid(reg)) {
- DRM_ERROR("CP DMA Bad DST register\n");
- return -EINVAL;
- }
- } else {
- for (i = 0; i < (command & 0x1fffff); i++) {
- reg = start_reg + (4 * i);
- if (!si_vm_reg_valid(reg)) {
- DRM_ERROR("CP DMA Bad DST register\n");
- return -EINVAL;
- }
- }
- }
- }
- }
+ r = si_vm_packet3_cp_dma_check(ib, idx);
+ if (r)
+ return r;
break;
default:
DRM_ERROR("Invalid GFX packet3: 0x%x\n", pkt->opcode);
@@ -3958,6 +3990,7 @@
static int si_vm_packet3_compute_check(struct radeon_device *rdev,
u32 *ib, struct radeon_cs_packet *pkt)
{
+ int r;
u32 idx = pkt->idx + 1;
u32 idx_value = ib[idx];
u32 start_reg, reg, i;
@@ -4030,6 +4063,11 @@
return -EINVAL;
}
break;
+ case PACKET3_CP_DMA:
+ r = si_vm_packet3_cp_dma_check(ib, idx);
+ if (r)
+ return r;
+ break;
default:
DRM_ERROR("Invalid Compute packet3: 0x%x\n", pkt->opcode);
return -EINVAL;
@@ -4481,7 +4519,7 @@
}
if (!ASIC_IS_NODCE(rdev)) {
- WREG32(DACA_AUTODETECT_INT_CONTROL, 0);
+ WREG32(DAC_AUTODETECT_INT_CONTROL, 0);
tmp = RREG32(DC_HPD1_INT_CONTROL) & DC_HPDx_INT_POLARITY;
WREG32(DC_HPD1_INT_CONTROL, tmp);
@@ -5121,6 +5159,10 @@
break;
}
break;
+ case 124: /* UVD */
+ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data);
+ radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX);
+ break;
case 146:
case 147:
dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
@@ -5270,6 +5312,8 @@
struct radeon_ring *ring;
int r;
+ si_mc_program(rdev);
+
if (!rdev->me_fw || !rdev->pfp_fw || !rdev->ce_fw ||
!rdev->rlc_fw || !rdev->mc_fw) {
r = si_init_microcode(rdev);
@@ -5289,7 +5333,6 @@
if (r)
return r;
- si_mc_program(rdev);
r = si_pcie_gart_enable(rdev);
if (r)
return r;
@@ -5473,7 +5516,7 @@
si_cp_enable(rdev, false);
cayman_dma_stop(rdev);
if (rdev->has_uvd) {
- r600_uvd_rbc_stop(rdev);
+ r600_uvd_stop(rdev);
radeon_uvd_suspend(rdev);
}
si_irq_suspend(rdev);
@@ -5613,8 +5656,10 @@
radeon_vm_manager_fini(rdev);
radeon_ib_pool_fini(rdev);
radeon_irq_kms_fini(rdev);
- if (rdev->has_uvd)
+ if (rdev->has_uvd) {
+ r600_uvd_stop(rdev);
radeon_uvd_fini(rdev);
+ }
si_pcie_gart_fini(rdev);
r600_vram_scratch_fini(rdev);
radeon_gem_fini(rdev);
@@ -5659,8 +5704,7 @@
WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_BYPASS_EN_MASK, ~UPLL_BYPASS_EN_MASK);
if (!vclk || !dclk) {
- /* keep the Bypass mode, put PLL to sleep */
- WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+ /* keep the Bypass mode */
return 0;
}
@@ -5676,8 +5720,7 @@
/* set VCO_MODE to 1 */
WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_VCO_MODE_MASK, ~UPLL_VCO_MODE_MASK);
- /* toggle UPLL_SLEEP to 1 then back to 0 */
- WREG32_P(CG_UPLL_FUNC_CNTL, UPLL_SLEEP_MASK, ~UPLL_SLEEP_MASK);
+ /* disable sleep mode */
WREG32_P(CG_UPLL_FUNC_CNTL, 0, ~UPLL_SLEEP_MASK);
/* deassert UPLL_RESET */
@@ -5733,5 +5776,8 @@
mdelay(100);
+ /* posting read */
+ RREG32(SRBM_STATUS);
+
return 0;
}
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 8f2d7d4..9652ed9 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -97,6 +97,10 @@
#define DMIF_ADDR_CALC 0xC00
+#define PIPE0_DMIF_BUFFER_CONTROL 0x0ca0
+# define DMIF_BUFFERS_ALLOCATED(x) ((x) << 0)
+# define DMIF_BUFFERS_ALLOCATED_COMPLETED (1 << 4)
+
#define SRBM_STATUS 0xE50
#define GRBM_RQ_PENDING (1 << 5)
#define VMC_BUSY (1 << 8)
@@ -243,7 +247,7 @@
#define NOOFGROUPS_SHIFT 12
#define NOOFGROUPS_MASK 0x00001000
-#define MC_SEQ_TRAIN_WAKEUP_CNTL 0x2808
+#define MC_SEQ_TRAIN_WAKEUP_CNTL 0x28e8
#define TRAIN_DONE_D0 (1 << 30)
#define TRAIN_DONE_D1 (1 << 31)
@@ -390,7 +394,7 @@
# define GRPH_PFLIP_INT_MASK (1 << 0)
# define GRPH_PFLIP_INT_TYPE (1 << 8)
-#define DACA_AUTODETECT_INT_CONTROL 0x66c8
+#define DAC_AUTODETECT_INT_CONTROL 0x67c8
#define DC_HPD1_INT_STATUS 0x601c
#define DC_HPD2_INT_STATUS 0x6028
@@ -924,7 +928,7 @@
* 6. COMMAND [30:21] | BYTE_COUNT [20:0]
*/
# define PACKET3_CP_DMA_DST_SEL(x) ((x) << 20)
- /* 0 - SRC_ADDR
+ /* 0 - DST_ADDR
* 1 - GDS
*/
# define PACKET3_CP_DMA_ENGINE(x) ((x) << 27)
@@ -939,7 +943,7 @@
# define PACKET3_CP_DMA_CP_SYNC (1 << 31)
/* COMMAND */
# define PACKET3_CP_DMA_DIS_WC (1 << 21)
-# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+# define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
/* 0 - none
* 1 - 8 in 16
* 2 - 8 in 32
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 2b5461b..f5ddd35 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -78,6 +78,7 @@
if ((priv->num_encoders == 0) || (priv->num_connectors == 0)) {
/* oh nos! */
dev_err(dev->dev, "no encoders/connectors found\n");
+ drm_mode_config_cleanup(dev);
return -ENXIO;
}
@@ -116,6 +117,7 @@
struct tilcdc_drm_private *priv = dev->dev_private;
struct tilcdc_module *mod, *cur;
+ drm_fbdev_cma_fini(priv->fbdev);
drm_kms_helper_poll_fini(dev);
drm_mode_config_cleanup(dev);
drm_vblank_cleanup(dev);
@@ -169,33 +171,37 @@
dev->dev_private = priv;
priv->wq = alloc_ordered_workqueue("tilcdc", 0);
+ if (!priv->wq) {
+ ret = -ENOMEM;
+ goto fail_free_priv;
+ }
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res) {
dev_err(dev->dev, "failed to get memory resource\n");
ret = -EINVAL;
- goto fail;
+ goto fail_free_wq;
}
priv->mmio = ioremap_nocache(res->start, resource_size(res));
if (!priv->mmio) {
dev_err(dev->dev, "failed to ioremap\n");
ret = -ENOMEM;
- goto fail;
+ goto fail_free_wq;
}
priv->clk = clk_get(dev->dev, "fck");
if (IS_ERR(priv->clk)) {
dev_err(dev->dev, "failed to get functional clock\n");
ret = -ENODEV;
- goto fail;
+ goto fail_iounmap;
}
priv->disp_clk = clk_get(dev->dev, "dpll_disp_ck");
if (IS_ERR(priv->clk)) {
dev_err(dev->dev, "failed to get display clock\n");
ret = -ENODEV;
- goto fail;
+ goto fail_put_clk;
}
#ifdef CONFIG_CPU_FREQ
@@ -205,7 +211,7 @@
CPUFREQ_TRANSITION_NOTIFIER);
if (ret) {
dev_err(dev->dev, "failed to register cpufreq notifier\n");
- goto fail;
+ goto fail_put_disp_clk;
}
#endif
@@ -237,13 +243,13 @@
ret = modeset_init(dev);
if (ret < 0) {
dev_err(dev->dev, "failed to initialize mode setting\n");
- goto fail;
+ goto fail_cpufreq_unregister;
}
ret = drm_vblank_init(dev, 1);
if (ret < 0) {
dev_err(dev->dev, "failed to initialize vblank\n");
- goto fail;
+ goto fail_mode_config_cleanup;
}
pm_runtime_get_sync(dev->dev);
@@ -251,7 +257,7 @@
pm_runtime_put_sync(dev->dev);
if (ret < 0) {
dev_err(dev->dev, "failed to install IRQ handler\n");
- goto fail;
+ goto fail_vblank_cleanup;
}
platform_set_drvdata(pdev, dev);
@@ -259,13 +265,48 @@
priv->fbdev = drm_fbdev_cma_init(dev, 16,
dev->mode_config.num_crtc,
dev->mode_config.num_connector);
+ if (IS_ERR(priv->fbdev)) {
+ ret = PTR_ERR(priv->fbdev);
+ goto fail_irq_uninstall;
+ }
drm_kms_helper_poll_init(dev);
return 0;
-fail:
- tilcdc_unload(dev);
+fail_irq_uninstall:
+ pm_runtime_get_sync(dev->dev);
+ drm_irq_uninstall(dev);
+ pm_runtime_put_sync(dev->dev);
+
+fail_vblank_cleanup:
+ drm_vblank_cleanup(dev);
+
+fail_mode_config_cleanup:
+ drm_mode_config_cleanup(dev);
+
+fail_cpufreq_unregister:
+ pm_runtime_disable(dev->dev);
+#ifdef CONFIG_CPU_FREQ
+ cpufreq_unregister_notifier(&priv->freq_transition,
+ CPUFREQ_TRANSITION_NOTIFIER);
+fail_put_disp_clk:
+ clk_put(priv->disp_clk);
+#endif
+
+fail_put_clk:
+ clk_put(priv->clk);
+
+fail_iounmap:
+ iounmap(priv->mmio);
+
+fail_free_wq:
+ flush_workqueue(priv->wq);
+ destroy_workqueue(priv->wq);
+
+fail_free_priv:
+ dev->dev_private = NULL;
+ kfree(priv);
return ret;
}
@@ -596,10 +637,10 @@
static void __exit tilcdc_drm_fini(void)
{
DBG("fini");
- tilcdc_tfp410_fini();
- tilcdc_slave_fini();
- tilcdc_panel_fini();
platform_driver_unregister(&tilcdc_platform_driver);
+ tilcdc_panel_fini();
+ tilcdc_slave_fini();
+ tilcdc_tfp410_fini();
}
late_initcall(tilcdc_drm_init);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index 0917665..779d508 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -151,6 +151,7 @@
static void panel_connector_destroy(struct drm_connector *connector)
{
struct panel_connector *panel_connector = to_panel_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(panel_connector);
}
@@ -285,10 +286,8 @@
{
struct panel_module *panel_mod = to_panel_module(mod);
- if (panel_mod->timings) {
+ if (panel_mod->timings)
display_timings_release(panel_mod->timings);
- kfree(panel_mod->timings);
- }
tilcdc_module_cleanup(mod);
kfree(panel_mod->info);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_slave.c b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
index db1d2fc..5d6c597 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_slave.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_slave.c
@@ -142,6 +142,7 @@
static void slave_connector_destroy(struct drm_connector *connector)
{
struct slave_connector *slave_connector = to_slave_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(slave_connector);
}
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index a36788f..986131d 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -168,6 +168,7 @@
static void tfp410_connector_destroy(struct drm_connector *connector)
{
struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
+ drm_sysfs_connector_remove(connector);
drm_connector_cleanup(connector);
kfree(tfp410_connector);
}
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 9b07b7d..0ac0a88 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -498,9 +498,11 @@
moved:
if (bo->evicted) {
- ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
- if (ret)
- pr_err("Can not flush read caches\n");
+ if (bdev->driver->invalidate_caches) {
+ ret = bdev->driver->invalidate_caches(bdev, bo->mem.placement);
+ if (ret)
+ pr_err("Can not flush read caches\n");
+ }
bo->evicted = false;
}
@@ -1153,24 +1155,32 @@
return ret;
}
-static int ttm_bo_mem_compat(struct ttm_placement *placement,
- struct ttm_mem_reg *mem)
+static bool ttm_bo_mem_compat(struct ttm_placement *placement,
+ struct ttm_mem_reg *mem,
+ uint32_t *new_flags)
{
int i;
if (mem->mm_node && placement->lpfn != 0 &&
(mem->start < placement->fpfn ||
mem->start + mem->num_pages > placement->lpfn))
- return -1;
+ return false;
for (i = 0; i < placement->num_placement; i++) {
- if ((placement->placement[i] & mem->placement &
- TTM_PL_MASK_CACHING) &&
- (placement->placement[i] & mem->placement &
- TTM_PL_MASK_MEM))
- return i;
+ *new_flags = placement->placement[i];
+ if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
+ (*new_flags & mem->placement & TTM_PL_MASK_MEM))
+ return true;
}
- return -1;
+
+ for (i = 0; i < placement->num_busy_placement; i++) {
+ *new_flags = placement->busy_placement[i];
+ if ((*new_flags & mem->placement & TTM_PL_MASK_CACHING) &&
+ (*new_flags & mem->placement & TTM_PL_MASK_MEM))
+ return true;
+ }
+
+ return false;
}
int ttm_bo_validate(struct ttm_buffer_object *bo,
@@ -1179,6 +1189,7 @@
bool no_wait_gpu)
{
int ret;
+ uint32_t new_flags;
BUG_ON(!ttm_bo_is_reserved(bo));
/* Check that range is valid */
@@ -1189,8 +1200,7 @@
/*
* Check whether we need to move buffer.
*/
- ret = ttm_bo_mem_compat(placement, &bo->mem);
- if (ret < 0) {
+ if (!ttm_bo_mem_compat(placement, &bo->mem, &new_flags)) {
ret = ttm_bo_move_buffer(bo, placement, interruptible,
no_wait_gpu);
if (ret)
@@ -1200,7 +1210,7 @@
* Use the access and other non-mapping-related flag bits from
* the compatible memory placement flags to the active flags
*/
- ttm_flag_masked(&bo->mem.placement, placement->placement[ret],
+ ttm_flag_masked(&bo->mem.placement, new_flags,
~TTM_PL_MASK_MEMTYPE);
}
/*
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index af89458..b7f7571 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -342,19 +342,25 @@
if (ret)
goto out;
+ /*
+ * Single TTM move. NOP.
+ */
if (old_iomap == NULL && new_iomap == NULL)
goto out2;
+
+ /*
+ * Move nonexistent data. NOP.
+ */
if (old_iomap == NULL && ttm == NULL)
goto out2;
- if (ttm->state == tt_unpopulated) {
+ /*
+ * TTM might be null for moves within the same region.
+ */
+ if (ttm && ttm->state == tt_unpopulated) {
ret = ttm->bdev->driver->ttm_tt_populate(ttm);
- if (ret) {
- /* if we fail here don't nuke the mm node
- * as the bo still owns it */
- old_copy.mm_node = NULL;
+ if (ret)
goto out1;
- }
}
add = 0;
@@ -380,11 +386,8 @@
prot);
} else
ret = ttm_copy_io_page(new_iomap, old_iomap, page);
- if (ret) {
- /* failing here, means keep old copy as-is */
- old_copy.mm_node = NULL;
+ if (ret)
goto out1;
- }
}
mb();
out2:
@@ -402,7 +405,12 @@
ttm_mem_reg_iounmap(bdev, old_mem, new_iomap);
out:
ttm_mem_reg_iounmap(bdev, &old_copy, old_iomap);
- ttm_bo_mem_put(bo, &old_copy);
+
+ /*
+ * On error, keep the mm node!
+ */
+ if (!ret)
+ ttm_bo_mem_put(bo, &old_copy);
return ret;
}
EXPORT_SYMBOL(ttm_bo_move_memcpy);
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index b8b3943..de1a753 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -1006,9 +1006,9 @@
static int ttm_dma_pool_mm_shrink(struct shrinker *shrink,
struct shrink_control *sc)
{
- static atomic_t start_pool = ATOMIC_INIT(0);
+ static unsigned start_pool;
unsigned idx = 0;
- unsigned pool_offset = atomic_add_return(1, &start_pool);
+ unsigned pool_offset;
unsigned shrink_pages = sc->nr_to_scan;
struct device_pools *p;
@@ -1016,7 +1016,9 @@
return 0;
mutex_lock(&_manager->lock);
- pool_offset = pool_offset % _manager->npools;
+ if (!_manager->npools)
+ goto out;
+ pool_offset = ++start_pool % _manager->npools;
list_for_each_entry(p, &_manager->pools, pools) {
unsigned nr_free;
@@ -1033,6 +1035,7 @@
p->pool->dev_name, p->pool->name, current->pid,
nr_free, shrink_pages);
}
+out:
mutex_unlock(&_manager->lock);
/* return estimated number of unused pages in pool */
return ttm_dma_pool_get_num_unused_pages();
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 5e93a52..210d503 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -170,7 +170,7 @@
ttm_tt_unbind(ttm);
}
- if (likely(ttm->pages != NULL)) {
+ if (ttm->state == tt_unbound) {
ttm->bdev->driver->ttm_tt_unpopulate(ttm);
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 07dfd82..6c44c69 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -740,9 +740,17 @@
struct vmw_fpriv *vmw_fp;
vmw_fp = vmw_fpriv(file_priv);
- ttm_object_file_release(&vmw_fp->tfile);
- if (vmw_fp->locked_master)
+
+ if (vmw_fp->locked_master) {
+ struct vmw_master *vmaster =
+ vmw_master(vmw_fp->locked_master);
+
+ ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+ ttm_vt_unlock(&vmaster->lock);
drm_master_put(&vmw_fp->locked_master);
+ }
+
+ ttm_object_file_release(&vmw_fp->tfile);
kfree(vmw_fp);
}
@@ -942,14 +950,13 @@
vmw_fp->locked_master = drm_master_get(file_priv->master);
ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile);
- vmw_execbuf_release_pinned_bo(dev_priv);
-
if (unlikely((ret != 0))) {
DRM_ERROR("Unable to lock TTM at VT switch.\n");
drm_master_put(&vmw_fp->locked_master);
}
- ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
+ ttm_lock_set_kill(&vmaster->lock, false, SIGTERM);
+ vmw_execbuf_release_pinned_bo(dev_priv);
if (!dev_priv->enable_fb) {
ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 394e647..da068bd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -834,14 +834,36 @@
SVGA3dCmdSurfaceDMA dma;
} *cmd;
int ret;
+ SVGA3dCmdSurfaceDMASuffix *suffix;
+ uint32_t bo_size;
cmd = container_of(header, struct vmw_dma_cmd, header);
+ suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma +
+ header->size - sizeof(*suffix));
+
+ /* Make sure device and verifier stays in sync. */
+ if (unlikely(suffix->suffixSize != sizeof(*suffix))) {
+ DRM_ERROR("Invalid DMA suffix size.\n");
+ return -EINVAL;
+ }
+
ret = vmw_translate_guest_ptr(dev_priv, sw_context,
&cmd->dma.guest.ptr,
&vmw_bo);
if (unlikely(ret != 0))
return ret;
+ /* Make sure DMA doesn't cross BO boundaries. */
+ bo_size = vmw_bo->base.num_pages * PAGE_SIZE;
+ if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) {
+ DRM_ERROR("Invalid DMA offset.\n");
+ return -EINVAL;
+ }
+
+ bo_size -= cmd->dma.guest.ptr.offset;
+ if (unlikely(suffix->maximumOffset > bo_size))
+ suffix->maximumOffset = bo_size;
+
ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
user_surface_converter, &cmd->dma.host.sid,
NULL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index ed5ce2a..1b0f34b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -147,7 +147,7 @@
}
if (!vmw_kms_validate_mode_vram(vmw_priv,
- info->fix.line_length,
+ var->xres * var->bits_per_pixel/8,
var->yoffset + var->yres)) {
DRM_ERROR("Requested geom can not fit in framebuffer\n");
return -EINVAL;
@@ -162,6 +162,8 @@
struct vmw_private *vmw_priv = par->vmw_priv;
int ret;
+ info->fix.line_length = info->var.xres * info->var.bits_per_pixel/8;
+
ret = vmw_kms_write_svga(vmw_priv, info->var.xres, info->var.yres,
info->fix.line_length,
par->bpp, par->depth);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index c62d20e..ee742f1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -1049,6 +1049,8 @@
if (ret != 0)
goto out_no_queue;
+ return 0;
+
out_no_queue:
event->base.destroy(&event->base);
out_no_event:
@@ -1123,17 +1125,10 @@
BUG_ON(fence == NULL);
- if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME)
- ret = vmw_event_fence_action_create(file_priv, fence,
- arg->flags,
- arg->user_data,
- true);
- else
- ret = vmw_event_fence_action_create(file_priv, fence,
- arg->flags,
- arg->user_data,
- true);
-
+ ret = vmw_event_fence_action_create(file_priv, fence,
+ arg->flags,
+ arg->user_data,
+ true);
if (unlikely(ret != 0)) {
if (ret != -ERESTARTSYS)
DRM_ERROR("Failed to attach event to fence.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index 3eb1486..8966493 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -163,8 +163,9 @@
mutex_lock(&dev_priv->hw_mutex);
+ vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
while (vmw_read(dev_priv, SVGA_REG_BUSY) != 0)
- vmw_write(dev_priv, SVGA_REG_SYNC, SVGA_SYNC_GENERIC);
+ ;
dev_priv->last_read_seqno = ioread32(fifo_mem + SVGA_FIFO_FENCE);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
index 3751730..1a0bf07 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
@@ -29,7 +29,9 @@
#include <drm/drmP.h>
#include <drm/ttm/ttm_bo_driver.h>
-#define VMW_PPN_SIZE sizeof(unsigned long)
+#define VMW_PPN_SIZE (sizeof(unsigned long))
+/* A future safe maximum remap size. */
+#define VMW_PPN_PER_REMAP ((31 * 1024) / VMW_PPN_SIZE)
static int vmw_gmr2_bind(struct vmw_private *dev_priv,
struct page *pages[],
@@ -38,43 +40,61 @@
{
SVGAFifoCmdDefineGMR2 define_cmd;
SVGAFifoCmdRemapGMR2 remap_cmd;
- uint32_t define_size = sizeof(define_cmd) + 4;
- uint32_t remap_size = VMW_PPN_SIZE * num_pages + sizeof(remap_cmd) + 4;
uint32_t *cmd;
uint32_t *cmd_orig;
+ uint32_t define_size = sizeof(define_cmd) + sizeof(*cmd);
+ uint32_t remap_num = num_pages / VMW_PPN_PER_REMAP + ((num_pages % VMW_PPN_PER_REMAP) > 0);
+ uint32_t remap_size = VMW_PPN_SIZE * num_pages + (sizeof(remap_cmd) + sizeof(*cmd)) * remap_num;
+ uint32_t remap_pos = 0;
+ uint32_t cmd_size = define_size + remap_size;
uint32_t i;
- cmd_orig = cmd = vmw_fifo_reserve(dev_priv, define_size + remap_size);
+ cmd_orig = cmd = vmw_fifo_reserve(dev_priv, cmd_size);
if (unlikely(cmd == NULL))
return -ENOMEM;
define_cmd.gmrId = gmr_id;
define_cmd.numPages = num_pages;
+ *cmd++ = SVGA_CMD_DEFINE_GMR2;
+ memcpy(cmd, &define_cmd, sizeof(define_cmd));
+ cmd += sizeof(define_cmd) / sizeof(*cmd);
+
+ /*
+ * Need to split the command if there are too many
+ * pages that goes into the gmr.
+ */
+
remap_cmd.gmrId = gmr_id;
remap_cmd.flags = (VMW_PPN_SIZE > sizeof(*cmd)) ?
SVGA_REMAP_GMR2_PPN64 : SVGA_REMAP_GMR2_PPN32;
- remap_cmd.offsetPages = 0;
- remap_cmd.numPages = num_pages;
- *cmd++ = SVGA_CMD_DEFINE_GMR2;
- memcpy(cmd, &define_cmd, sizeof(define_cmd));
- cmd += sizeof(define_cmd) / sizeof(uint32);
+ while (num_pages > 0) {
+ unsigned long nr = min(num_pages, (unsigned long)VMW_PPN_PER_REMAP);
- *cmd++ = SVGA_CMD_REMAP_GMR2;
- memcpy(cmd, &remap_cmd, sizeof(remap_cmd));
- cmd += sizeof(remap_cmd) / sizeof(uint32);
+ remap_cmd.offsetPages = remap_pos;
+ remap_cmd.numPages = nr;
- for (i = 0; i < num_pages; ++i) {
- if (VMW_PPN_SIZE <= 4)
- *cmd = page_to_pfn(*pages++);
- else
- *((uint64_t *)cmd) = page_to_pfn(*pages++);
+ *cmd++ = SVGA_CMD_REMAP_GMR2;
+ memcpy(cmd, &remap_cmd, sizeof(remap_cmd));
+ cmd += sizeof(remap_cmd) / sizeof(*cmd);
- cmd += VMW_PPN_SIZE / sizeof(*cmd);
+ for (i = 0; i < nr; ++i) {
+ if (VMW_PPN_SIZE <= 4)
+ *cmd = page_to_pfn(*pages++);
+ else
+ *((uint64_t *)cmd) = page_to_pfn(*pages++);
+
+ cmd += VMW_PPN_SIZE / sizeof(*cmd);
+ }
+
+ num_pages -= nr;
+ remap_pos += nr;
}
- vmw_fifo_commit(dev_priv, define_size + remap_size);
+ BUG_ON(cmd != cmd_orig + cmd_size / sizeof(*cmd));
+
+ vmw_fifo_commit(dev_priv, cmd_size);
return 0;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index bc78425..407d7f9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -970,7 +970,7 @@
if (new_backup)
res->backup_offset = new_backup_offset;
- if (!res->func->may_evict)
+ if (!res->func->may_evict || res->id == -1)
return;
write_lock(&dev_priv->resource_lock);
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index b592eef..b083509 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -48,7 +48,7 @@
unsigned long reg;
int i, id;
- for (i = 0; i <= BIT_WORD(host->info->nb_pts); i++) {
+ for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
reg = host1x_sync_readl(host,
HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
for_each_set_bit(id, ®, BITS_PER_LONG) {
@@ -65,7 +65,7 @@
{
u32 i;
- for (i = 0; i <= BIT_WORD(host->info->nb_pts); ++i) {
+ for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); ++i) {
host1x_sync_writel(host, 0xffffffffu,
HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
host1x_sync_writel(host, 0xffffffffu,
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index fb52f3f..bee88ee 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -352,12 +352,14 @@
force feedback.
config LOGIRUMBLEPAD2_FF
- bool "Logitech RumblePad/Rumblepad 2 force feedback support"
+ bool "Logitech force feedback support (variant 2)"
depends on HID_LOGITECH
select INPUT_FF_MEMLESS
help
- Say Y here if you want to enable force feedback support for Logitech
- RumblePad and Rumblepad 2 devices.
+ Say Y here if you want to enable force feedback support for:
+ - Logitech RumblePad
+ - Logitech Rumblepad 2
+ - Logitech Formula Vibration Feedback Wheel
config LOGIG940_FF
bool "Logitech Flight System G940 force feedback support"
@@ -436,9 +438,11 @@
- Pixcir dual touch panels
- Quanta panels
- eGalax dual-touch panels, including the Joojoo and Wetab tablets
+ - SiS multitouch panels
- Stantum multitouch panels
- Touch International Panels
- Unitec Panels
+ - Wistron optical touch panels
- XAT optical touch panels
- Xiroku optical touch panels
- Zytronic touch panels
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index feae88b..d54e1d0 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -46,6 +46,12 @@
MODULE_PARM_DESC(iso_layout, "Enable/Disable hardcoded ISO-layout of the keyboard. "
"(0 = disabled, [1] = enabled)");
+static unsigned int swap_opt_cmd = 0;
+module_param(swap_opt_cmd, uint, 0644);
+MODULE_PARM_DESC(swap_opt_cmd, "Swap the Option (\"Alt\") and Command (\"Flag\") keys. "
+ "(For people who want to keep Windows PC keyboard muscle memory. "
+ "[0] = as-is, Mac layout. 1 = swapped, Windows layout.)");
+
struct apple_sc {
unsigned long quirks;
unsigned int fn_on;
@@ -150,6 +156,14 @@
{ }
};
+static const struct apple_key_translation swapped_option_cmd_keys[] = {
+ { KEY_LEFTALT, KEY_LEFTMETA },
+ { KEY_LEFTMETA, KEY_LEFTALT },
+ { KEY_RIGHTALT, KEY_RIGHTMETA },
+ { KEY_RIGHTMETA,KEY_RIGHTALT },
+ { }
+};
+
static const struct apple_key_translation *apple_find_translation(
const struct apple_key_translation *table, u16 from)
{
@@ -242,6 +256,14 @@
}
}
+ if (swap_opt_cmd) {
+ trans = apple_find_translation(swapped_option_cmd_keys, usage->code);
+ if (trans) {
+ input_event(input, usage->type, trans->to, value);
+ return 1;
+ }
+ }
+
return 0;
}
@@ -524,6 +546,12 @@
.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS),
.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI),
+ .driver_data = APPLE_HAS_FN },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO),
+ .driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
+ .driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-axff.c b/drivers/hid/hid-axff.c
index 64ab94a..a594e47 100644
--- a/drivers/hid/hid-axff.c
+++ b/drivers/hid/hid-axff.c
@@ -95,7 +95,7 @@
}
}
- if (field_count < 4) {
+ if (field_count < 4 && hid->product != 0xf705) {
hid_err(hid, "not enough fields in the report: %d\n",
field_count);
return -ENODEV;
@@ -180,6 +180,7 @@
static const struct hid_device_id ax_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0x0802), },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0xf705), },
{ }
};
MODULE_DEVICE_TABLE(hid, ax_devices);
diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index 1bdcccc..f745d2c 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -28,7 +28,7 @@
static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
+ if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n");
rdesc[11] = rdesc[16] = 0xff;
rdesc[12] = rdesc[17] = 0x03;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 264f550..2bd798a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -63,6 +63,8 @@
struct hid_report_enum *report_enum = device->report_enum + type;
struct hid_report *report;
+ if (id >= HID_MAX_IDS)
+ return NULL;
if (report_enum->report_id_hash[id])
return report_enum->report_id_hash[id];
@@ -92,7 +94,6 @@
static struct hid_field *hid_register_field(struct hid_report *report, unsigned usages, unsigned values)
{
struct hid_field *field;
- int i;
if (report->maxfield == HID_MAX_FIELDS) {
hid_err(report->device, "too many fields in report\n");
@@ -111,9 +112,6 @@
field->value = (s32 *)(field->usage + usages);
field->report = report;
- for (i = 0; i < usages; i++)
- field->usage[i].usage_index = i;
-
return field;
}
@@ -224,9 +222,9 @@
{
struct hid_report *report;
struct hid_field *field;
- int usages;
+ unsigned usages;
unsigned offset;
- int i;
+ unsigned i;
report = hid_register_report(parser->device, report_type, parser->global.report_id);
if (!report) {
@@ -253,7 +251,8 @@
if (!parser->local.usage_index) /* Ignore padding fields */
return 0;
- usages = max_t(int, parser->local.usage_index, parser->global.report_count);
+ usages = max_t(unsigned, parser->local.usage_index,
+ parser->global.report_count);
field = hid_register_field(report, usages, parser->global.report_count);
if (!field)
@@ -264,13 +263,14 @@
field->application = hid_lookup_collection(parser, HID_COLLECTION_APPLICATION);
for (i = 0; i < usages; i++) {
- int j = i;
+ unsigned j = i;
/* Duplicate the last usage we parsed if we have excess values */
if (i >= parser->local.usage_index)
j = parser->local.usage_index - 1;
field->usage[i].hid = parser->local.usage[j];
field->usage[i].collection_index =
parser->local.collection_index[j];
+ field->usage[i].usage_index = i;
}
field->maxusage = usages;
@@ -404,8 +404,10 @@
case HID_GLOBAL_ITEM_TAG_REPORT_ID:
parser->global.report_id = item_udata(item);
- if (parser->global.report_id == 0) {
- hid_err(parser->device, "report_id 0 is invalid\n");
+ if (parser->global.report_id == 0 ||
+ parser->global.report_id >= HID_MAX_IDS) {
+ hid_err(parser->device, "report_id %u is invalid\n",
+ parser->global.report_id);
return -1;
}
return 0;
@@ -575,7 +577,7 @@
for (i = 0; i < HID_REPORT_TYPES; i++) {
struct hid_report_enum *report_enum = device->report_enum + i;
- for (j = 0; j < 256; j++) {
+ for (j = 0; j < HID_MAX_IDS; j++) {
struct hid_report *report = report_enum->report_id_hash[j];
if (report)
hid_free_report(report);
@@ -755,6 +757,74 @@
}
EXPORT_SYMBOL_GPL(hid_parse_report);
+static const char * const hid_report_names[] = {
+ "HID_INPUT_REPORT",
+ "HID_OUTPUT_REPORT",
+ "HID_FEATURE_REPORT",
+};
+/**
+ * hid_validate_values - validate existing device report's value indexes
+ *
+ * @device: hid device
+ * @type: which report type to examine
+ * @id: which report ID to examine (0 for first)
+ * @field_index: which report field to examine
+ * @report_counts: expected number of values
+ *
+ * Validate the number of values in a given field of a given report, after
+ * parsing.
+ */
+struct hid_report *hid_validate_values(struct hid_device *hid,
+ unsigned int type, unsigned int id,
+ unsigned int field_index,
+ unsigned int report_counts)
+{
+ struct hid_report *report;
+
+ if (type > HID_FEATURE_REPORT) {
+ hid_err(hid, "invalid HID report type %u\n", type);
+ return NULL;
+ }
+
+ if (id >= HID_MAX_IDS) {
+ hid_err(hid, "invalid HID report id %u\n", id);
+ return NULL;
+ }
+
+ /*
+ * Explicitly not using hid_get_report() here since it depends on
+ * ->numbered being checked, which may not always be the case when
+ * drivers go to access report values.
+ */
+ if (id == 0) {
+ /*
+ * Validating on id 0 means we should examine the first
+ * report in the list.
+ */
+ report = list_entry(
+ hid->report_enum[type].report_list.next,
+ struct hid_report, list);
+ } else {
+ report = hid->report_enum[type].report_id_hash[id];
+ }
+ if (!report) {
+ hid_err(hid, "missing %s %u\n", hid_report_names[type], id);
+ return NULL;
+ }
+ if (report->maxfield <= field_index) {
+ hid_err(hid, "not enough fields in %s %u\n",
+ hid_report_names[type], id);
+ return NULL;
+ }
+ if (report->field[field_index]->report_count < report_counts) {
+ hid_err(hid, "not enough values in %s %u field %u\n",
+ hid_report_names[type], id, field_index);
+ return NULL;
+ }
+ return report;
+}
+EXPORT_SYMBOL_GPL(hid_validate_values);
+
/**
* hid_open_report - open a driver-specific device report
*
@@ -1128,7 +1198,8 @@
}
/*
- * Create a report.
+ * Create a report. 'data' has to be allocated using
+ * hid_alloc_report_buf() so that it has proper size.
*/
void hid_output_report(struct hid_report *report, __u8 *data)
@@ -1145,6 +1216,22 @@
EXPORT_SYMBOL_GPL(hid_output_report);
/*
+ * Allocator for buffer that is going to be passed to hid_output_report()
+ */
+u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
+{
+ /*
+ * 7 extra bytes are necessary to achieve proper functionality
+ * of implement() working on 8 byte chunks
+ */
+
+ int len = ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+
+ return kmalloc(len, flags);
+}
+EXPORT_SYMBOL_GPL(hid_alloc_report_buf);
+
+/*
* Set a field value. The report this field belongs to has to be
* created and transferred to the device, to set this value in the
* device.
@@ -1152,7 +1239,12 @@
int hid_set_field(struct hid_field *field, unsigned offset, __s32 value)
{
- unsigned size = field->report_size;
+ unsigned size;
+
+ if (!field)
+ return -1;
+
+ size = field->report_size;
hid_dump_input(field->report->device, field->usage + offset, value);
@@ -1228,7 +1320,7 @@
goto out;
}
- if (hid->claimed != HID_CLAIMED_HIDRAW) {
+ if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) {
for (a = 0; a < report->maxfield; a++)
hid_input_field(hid, report->field[a], cdata, interrupt);
hdrv = hid->driver;
@@ -1480,6 +1572,7 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_X5_005D) },
{ HID_USB_DEVICE(USB_VENDOR_ID_A4TECH, USB_DEVICE_ID_A4TECH_RP_649) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0x0802) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ACRUX, 0xf705) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MIGHTYMOUSE) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICMOUSE) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGICTRACKPAD) },
@@ -1547,6 +1640,9 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
@@ -1591,6 +1687,7 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_I405X) },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LCPOWER, USB_DEVICE_ID_LCPOWER_LC1000 ) },
@@ -1618,6 +1715,7 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_FLIGHT_SYSTEM_G940) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFP_WHEEL) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFGT_WHEEL) },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G25_WHEEL) },
@@ -1665,11 +1763,14 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_KEYBOARD) },
#if IS_ENABLED(CONFIG_HID_ROCCAT)
- { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ARVO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKUFX) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPLUS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEXTD) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KOVAPLUS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_LUA) },
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_PYRA_WIRED) },
@@ -1679,6 +1780,8 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_PS1000) },
{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_WIRELESS_KBD_MOUSE) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS9200_TOUCH) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS817_TOUCH) },
{ HID_USB_DEVICE(USB_VENDOR_ID_SKYCABLE, USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER) },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_BDREMOTE) },
{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
@@ -2179,6 +2282,9 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ANSI) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_ISO) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
{ }
@@ -2228,15 +2334,6 @@
hdev->type == HID_TYPE_USBNONE)
return true;
break;
- case USB_VENDOR_ID_DWAV:
- /* These are handled by usbtouchscreen. hdev->type is probably
- * HID_TYPE_USBNONE, but we say !HID_TYPE_USBMOUSE to match
- * usbtouchscreen. */
- if ((hdev->product == USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER ||
- hdev->product == USB_DEVICE_ID_DWAV_TOUCHCONTROLLER) &&
- hdev->type != HID_TYPE_USBMOUSE)
- return true;
- break;
case USB_VENDOR_ID_VELLEMAN:
/* These are not HID devices. They are handled by comedi. */
if ((hdev->product >= USB_DEVICE_ID_VELLEMAN_K8055_FIRST &&
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 38535c9..45c593d 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -135,6 +135,9 @@
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI 0x0255
#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292
#define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY 0x030a
#define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY 0x030b
#define USB_DEVICE_ID_APPLE_IRCONTROL 0x8240
@@ -327,6 +330,11 @@
#define USB_VENDOR_ID_GENERAL_TOUCH 0x0dfc
#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0003
#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PWT_TENFINGERS 0x0100
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0101 0x0101
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0102 0x0102
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0106 0x0106
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
#define USB_VENDOR_ID_GLAB 0x06c2
#define USB_DEVICE_ID_4_PHIDGETSERVO_30 0x0038
@@ -470,6 +478,7 @@
#define USB_DEVICE_ID_KYE_GPEN_560 0x5003
#define USB_DEVICE_ID_KYE_EASYPEN_I405X 0x5010
#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X 0x5011
+#define USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2 0x501a
#define USB_DEVICE_ID_KYE_EASYPEN_M610X 0x5013
#define USB_VENDOR_ID_LABTEC 0x1020
@@ -554,6 +563,7 @@
#define USB_DEVICE_ID_DINOVO_EDGE 0xc714
#define USB_DEVICE_ID_DINOVO_MINI 0xc71f
#define USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2 0xca03
+#define USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL 0xca04
#define USB_VENDOR_ID_LUMIO 0x202e
#define USB_DEVICE_ID_CRYSTALTOUCH 0x0006
@@ -643,6 +653,7 @@
#define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_16 0x0012
#define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_17 0x0013
#define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_18 0x0014
+#define USB_DEVICE_ID_NTRIG_DUOSENSE 0x1500
#define USB_VENDOR_ID_ONTRAK 0x0a07
#define USB_DEVICE_ID_ONTRAK_ADU100 0x0064
@@ -701,6 +712,7 @@
#define USB_DEVICE_ID_ROCCAT_KONE 0x2ced
#define USB_DEVICE_ID_ROCCAT_KONEPLUS 0x2d51
#define USB_DEVICE_ID_ROCCAT_KONEPURE 0x2dbe
+#define USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL 0x2db4
#define USB_DEVICE_ID_ROCCAT_KONEXTD 0x2e22
#define USB_DEVICE_ID_ROCCAT_KOVAPLUS 0x2d50
#define USB_DEVICE_ID_ROCCAT_LUA 0x2c2e
@@ -725,6 +737,10 @@
#define USB_VENDOR_ID_SIGMATEL 0x066F
#define USB_DEVICE_ID_SIGMATEL_STMP3780 0x3780
+#define USB_VENDOR_ID_SIS2_TOUCH 0x0457
+#define USB_DEVICE_ID_SIS9200_TOUCH 0x9200
+#define USB_DEVICE_ID_SIS817_TOUCH 0x0817
+
#define USB_VENDOR_ID_SKYCABLE 0x1223
#define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07
@@ -771,6 +787,8 @@
#define USB_DEVICE_ID_SYNAPTICS_COMP_TP 0x0009
#define USB_DEVICE_ID_SYNAPTICS_WTP 0x0010
#define USB_DEVICE_ID_SYNAPTICS_DPAD 0x0013
+#define USB_DEVICE_ID_SYNAPTICS_LTS1 0x0af8
+#define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10
#define USB_VENDOR_ID_THINGM 0x27b8
#define USB_DEVICE_ID_BLINK1 0x01ed
@@ -864,6 +882,9 @@
#define USB_DEVICE_ID_SUPER_DUAL_BOX_PRO 0x8802
#define USB_DEVICE_ID_SUPER_JOY_BOX_5_PRO 0x8804
+#define USB_VENDOR_ID_WISTRON 0x0fb8
+#define USB_DEVICE_ID_WISTRON_OPTICAL_TOUCH 0x1109
+
#define USB_VENDOR_ID_X_TENSIONS 0x1ae7
#define USB_DEVICE_ID_SPEEDLINK_VAD_CEZANNE 0x9001
@@ -895,4 +916,7 @@
#define USB_VENDOR_ID_PRIMAX 0x0461
#define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05
+#define USB_VENDOR_ID_SIS 0x0457
+#define USB_DEVICE_ID_SIS_TS 0x1013
+
#endif
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 945b815..a3915d1 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -317,6 +317,9 @@
USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI),
HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
+ USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO),
+ HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE,
USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI),
HID_BATTERY_QUIRK_PERCENT | HID_BATTERY_QUIRK_FEATURE },
{}
@@ -340,7 +343,7 @@
{
struct hid_device *dev = container_of(psy, struct hid_device, battery);
int ret = 0;
- __u8 buf[2] = {};
+ __u8 *buf;
switch (prop) {
case POWER_SUPPLY_PROP_PRESENT:
@@ -349,13 +352,20 @@
break;
case POWER_SUPPLY_PROP_CAPACITY:
+
+ buf = kmalloc(2 * sizeof(__u8), GFP_KERNEL);
+ if (!buf) {
+ ret = -ENOMEM;
+ break;
+ }
ret = dev->hid_get_raw_report(dev, dev->battery_report_id,
- buf, sizeof(buf),
+ buf, 2,
dev->battery_report_type);
if (ret != 2) {
if (ret >= 0)
ret = -EINVAL;
+ kfree(buf);
break;
}
@@ -364,6 +374,7 @@
buf[1] <= dev->battery_max)
val->intval = (100 * (buf[1] - dev->battery_min)) /
(dev->battery_max - dev->battery_min);
+ kfree(buf);
break;
case POWER_SUPPLY_PROP_MODEL_NAME:
@@ -477,6 +488,10 @@
if (field->flags & HID_MAIN_ITEM_CONSTANT)
goto ignore;
+ /* Ignore if report count is out of bounds. */
+ if (field->report_count < 1)
+ goto ignore;
+
/* only LED usages are supported in output fields */
if (field->report_type == HID_OUTPUT_REPORT &&
(usage->hid & HID_USAGE_PAGE) != HID_UP_LED) {
@@ -1051,6 +1066,23 @@
return;
}
+ /*
+ * Ignore reports for absolute data if the data didn't change. This is
+ * not only an optimization but also fixes 'dead' key reports. Some
+ * RollOver implementations for localized keys (like BACKSLASH/PIPE; HID
+ * 0x31 and 0x32) report multiple keys, even though a localized keyboard
+ * can only have one of them physically available. The 'dead' keys
+ * report constant 0. As all map to the same keycode, they'd confuse
+ * the input layer. If we filter the 'dead' keys on the HID level, we
+ * skip the keycode translation and only forward real events.
+ */
+ if (!(field->flags & (HID_MAIN_ITEM_RELATIVE |
+ HID_MAIN_ITEM_BUFFERED_BYTE)) &&
+ (field->flags & HID_MAIN_ITEM_VARIABLE) &&
+ usage->usage_index < field->maxusage &&
+ value == field->value[usage->usage_index])
+ return;
+
/* report the usage code as scancode if the key status has changed */
if (usage->type == EV_KEY && !!test_bit(usage->code, input->key) != value)
input_event(input, EV_MSC, MSC_SCAN, usage->hid);
@@ -1155,7 +1187,11 @@
rep_enum = &hid->report_enum[HID_FEATURE_REPORT];
list_for_each_entry(rep, &rep_enum->report_list, list)
- for (i = 0; i < rep->maxfield; i++)
+ for (i = 0; i < rep->maxfield; i++) {
+ /* Ignore if report count is out of bounds. */
+ if (rep->field[i]->report_count < 1)
+ continue;
+
for (j = 0; j < rep->field[i]->maxusage; j++) {
/* Verify if Battery Strength feature is available */
hidinput_setup_battery(hid, HID_FEATURE_REPORT, rep->field[i]);
@@ -1164,6 +1200,7 @@
drv->feature_mapping(hid, rep->field[i],
rep->field[i]->usage + j);
}
+ }
}
static struct hid_input *hidinput_allocate(struct hid_device *hid)
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index 6af90db..973eed7 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -280,7 +280,7 @@
* - change the button usage range to 4-7 for the extra
* buttons
*/
- if (*rsize >= 74 &&
+ if (*rsize >= 75 &&
rdesc[61] == 0x05 && rdesc[62] == 0x08 &&
rdesc[63] == 0x19 && rdesc[64] == 0x08 &&
rdesc[65] == 0x29 && rdesc[66] == 0x0f &&
@@ -303,6 +303,7 @@
}
break;
case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+ case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
if (*rsize == MOUSEPEN_I608X_RDESC_ORIG_SIZE) {
rdesc = mousepen_i608x_rdesc_fixed;
*rsize = sizeof(mousepen_i608x_rdesc_fixed);
@@ -383,6 +384,7 @@
switch (id->product) {
case USB_DEVICE_ID_KYE_EASYPEN_I405X:
case USB_DEVICE_ID_KYE_MOUSEPEN_I608X:
+ case USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2:
case USB_DEVICE_ID_KYE_EASYPEN_M610X:
ret = kye_tablet_enable(hdev);
if (ret) {
@@ -406,6 +408,8 @@
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
USB_DEVICE_ID_KYE_MOUSEPEN_I608X) },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE,
+ USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_KYE,
USB_DEVICE_ID_KYE_EASYPEN_M610X) },
{ }
};
diff --git a/drivers/hid/hid-lenovo-tpkbd.c b/drivers/hid/hid-lenovo-tpkbd.c
index 07837f5..31cf29a 100644
--- a/drivers/hid/hid-lenovo-tpkbd.c
+++ b/drivers/hid/hid-lenovo-tpkbd.c
@@ -339,7 +339,15 @@
struct tpkbd_data_pointer *data_pointer;
size_t name_sz = strlen(dev_name(dev)) + 16;
char *name_mute, *name_micmute;
- int ret;
+ int i, ret;
+
+ /* Validate required reports. */
+ for (i = 0; i < 4; i++) {
+ if (!hid_validate_values(hdev, HID_FEATURE_REPORT, 4, i, 1))
+ return -ENODEV;
+ }
+ if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 3, 0, 2))
+ return -ENODEV;
if (sysfs_create_group(&hdev->dev.kobj,
&tpkbd_attr_group_pointer)) {
@@ -406,22 +414,27 @@
ret = hid_parse(hdev);
if (ret) {
hid_err(hdev, "hid_parse failed\n");
- goto err_free;
+ goto err;
}
ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
if (ret) {
hid_err(hdev, "hid_hw_start failed\n");
- goto err_free;
+ goto err;
}
uhdev = (struct usbhid_device *) hdev->driver_data;
- if (uhdev->ifnum == 1)
- return tpkbd_probe_tp(hdev);
+ if (uhdev->ifnum == 1) {
+ ret = tpkbd_probe_tp(hdev);
+ if (ret)
+ goto err_hid;
+ }
return 0;
-err_free:
+err_hid:
+ hid_hw_stop(hdev);
+err:
return ret;
}
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 6f12ecd..12fc48c 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -45,7 +45,9 @@
/* Size of the original descriptors of the Driving Force (and Pro) wheels */
#define DF_RDESC_ORIG_SIZE 130
#define DFP_RDESC_ORIG_SIZE 97
+#define FV_RDESC_ORIG_SIZE 130
#define MOMO_RDESC_ORIG_SIZE 87
+#define MOMO2_RDESC_ORIG_SIZE 87
/* Fixed report descriptors for Logitech Driving Force (and Pro)
* wheel controllers
@@ -170,6 +172,73 @@
0xC0 /* End Collection */
};
+static __u8 fv_rdesc_fixed[] = {
+0x05, 0x01, /* Usage Page (Desktop), */
+0x09, 0x04, /* Usage (Joystik), */
+0xA1, 0x01, /* Collection (Application), */
+0xA1, 0x02, /* Collection (Logical), */
+0x95, 0x01, /* Report Count (1), */
+0x75, 0x0A, /* Report Size (10), */
+0x15, 0x00, /* Logical Minimum (0), */
+0x26, 0xFF, 0x03, /* Logical Maximum (1023), */
+0x35, 0x00, /* Physical Minimum (0), */
+0x46, 0xFF, 0x03, /* Physical Maximum (1023), */
+0x09, 0x30, /* Usage (X), */
+0x81, 0x02, /* Input (Variable), */
+0x95, 0x0C, /* Report Count (12), */
+0x75, 0x01, /* Report Size (1), */
+0x25, 0x01, /* Logical Maximum (1), */
+0x45, 0x01, /* Physical Maximum (1), */
+0x05, 0x09, /* Usage Page (Button), */
+0x19, 0x01, /* Usage Minimum (01h), */
+0x29, 0x0C, /* Usage Maximum (0Ch), */
+0x81, 0x02, /* Input (Variable), */
+0x95, 0x02, /* Report Count (2), */
+0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
+0x09, 0x01, /* Usage (01h), */
+0x81, 0x02, /* Input (Variable), */
+0x09, 0x02, /* Usage (02h), */
+0x26, 0xFF, 0x00, /* Logical Maximum (255), */
+0x46, 0xFF, 0x00, /* Physical Maximum (255), */
+0x95, 0x01, /* Report Count (1), */
+0x75, 0x08, /* Report Size (8), */
+0x81, 0x02, /* Input (Variable), */
+0x05, 0x01, /* Usage Page (Desktop), */
+0x25, 0x07, /* Logical Maximum (7), */
+0x46, 0x3B, 0x01, /* Physical Maximum (315), */
+0x75, 0x04, /* Report Size (4), */
+0x65, 0x14, /* Unit (Degrees), */
+0x09, 0x39, /* Usage (Hat Switch), */
+0x81, 0x42, /* Input (Variable, Null State), */
+0x75, 0x01, /* Report Size (1), */
+0x95, 0x04, /* Report Count (4), */
+0x65, 0x00, /* Unit, */
+0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
+0x09, 0x01, /* Usage (01h), */
+0x25, 0x01, /* Logical Maximum (1), */
+0x45, 0x01, /* Physical Maximum (1), */
+0x81, 0x02, /* Input (Variable), */
+0x05, 0x01, /* Usage Page (Desktop), */
+0x95, 0x01, /* Report Count (1), */
+0x75, 0x08, /* Report Size (8), */
+0x26, 0xFF, 0x00, /* Logical Maximum (255), */
+0x46, 0xFF, 0x00, /* Physical Maximum (255), */
+0x09, 0x31, /* Usage (Y), */
+0x81, 0x02, /* Input (Variable), */
+0x09, 0x32, /* Usage (Z), */
+0x81, 0x02, /* Input (Variable), */
+0xC0, /* End Collection, */
+0xA1, 0x02, /* Collection (Logical), */
+0x26, 0xFF, 0x00, /* Logical Maximum (255), */
+0x46, 0xFF, 0x00, /* Physical Maximum (255), */
+0x95, 0x07, /* Report Count (7), */
+0x75, 0x08, /* Report Size (8), */
+0x09, 0x03, /* Usage (03h), */
+0x91, 0x02, /* Output (Variable), */
+0xC0, /* End Collection, */
+0xC0 /* End Collection */
+};
+
static __u8 momo_rdesc_fixed[] = {
0x05, 0x01, /* Usage Page (Desktop), */
0x09, 0x04, /* Usage (Joystik), */
@@ -216,6 +285,54 @@
0xC0 /* End Collection */
};
+static __u8 momo2_rdesc_fixed[] = {
+0x05, 0x01, /* Usage Page (Desktop), */
+0x09, 0x04, /* Usage (Joystik), */
+0xA1, 0x01, /* Collection (Application), */
+0xA1, 0x02, /* Collection (Logical), */
+0x95, 0x01, /* Report Count (1), */
+0x75, 0x0A, /* Report Size (10), */
+0x15, 0x00, /* Logical Minimum (0), */
+0x26, 0xFF, 0x03, /* Logical Maximum (1023), */
+0x35, 0x00, /* Physical Minimum (0), */
+0x46, 0xFF, 0x03, /* Physical Maximum (1023), */
+0x09, 0x30, /* Usage (X), */
+0x81, 0x02, /* Input (Variable), */
+0x95, 0x0A, /* Report Count (10), */
+0x75, 0x01, /* Report Size (1), */
+0x25, 0x01, /* Logical Maximum (1), */
+0x45, 0x01, /* Physical Maximum (1), */
+0x05, 0x09, /* Usage Page (Button), */
+0x19, 0x01, /* Usage Minimum (01h), */
+0x29, 0x0A, /* Usage Maximum (0Ah), */
+0x81, 0x02, /* Input (Variable), */
+0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
+0x09, 0x00, /* Usage (00h), */
+0x95, 0x04, /* Report Count (4), */
+0x81, 0x02, /* Input (Variable), */
+0x95, 0x01, /* Report Count (1), */
+0x75, 0x08, /* Report Size (8), */
+0x26, 0xFF, 0x00, /* Logical Maximum (255), */
+0x46, 0xFF, 0x00, /* Physical Maximum (255), */
+0x09, 0x01, /* Usage (01h), */
+0x81, 0x02, /* Input (Variable), */
+0x05, 0x01, /* Usage Page (Desktop), */
+0x09, 0x31, /* Usage (Y), */
+0x81, 0x02, /* Input (Variable), */
+0x09, 0x32, /* Usage (Z), */
+0x81, 0x02, /* Input (Variable), */
+0x06, 0x00, 0xFF, /* Usage Page (FF00h), */
+0x09, 0x00, /* Usage (00h), */
+0x81, 0x02, /* Input (Variable), */
+0xC0, /* End Collection, */
+0xA1, 0x02, /* Collection (Logical), */
+0x09, 0x02, /* Usage (02h), */
+0x95, 0x07, /* Report Count (7), */
+0x91, 0x02, /* Output (Variable), */
+0xC0, /* End Collection, */
+0xC0 /* End Collection */
+};
+
/*
* Certain Logitech keyboards send in report #3 keys which are far
* above the logical maximum described in descriptor. This extends
@@ -228,14 +345,14 @@
struct usb_device_descriptor *udesc;
__u16 bcdDevice, rev_maj, rev_min;
- if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 &&
+ if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 &&
rdesc[84] == 0x8c && rdesc[85] == 0x02) {
hid_info(hdev,
"fixing up Logitech keyboard report descriptor\n");
rdesc[84] = rdesc[89] = 0x4d;
rdesc[85] = rdesc[90] = 0x10;
}
- if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 &&
+ if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 &&
rdesc[32] == 0x81 && rdesc[33] == 0x06 &&
rdesc[49] == 0x81 && rdesc[50] == 0x06) {
hid_info(hdev,
@@ -275,6 +392,24 @@
}
break;
+ case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
+ if (*rsize == MOMO2_RDESC_ORIG_SIZE) {
+ hid_info(hdev,
+ "fixing up Logitech Momo Racing Force (Black) report descriptor\n");
+ rdesc = momo2_rdesc_fixed;
+ *rsize = sizeof(momo2_rdesc_fixed);
+ }
+ break;
+
+ case USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL:
+ if (*rsize == FV_RDESC_ORIG_SIZE) {
+ hid_info(hdev,
+ "fixing up Logitech Formula Vibration report descriptor\n");
+ rdesc = fv_rdesc_fixed;
+ *rsize = sizeof(fv_rdesc_fixed);
+ }
+ break;
+
case USB_DEVICE_ID_LOGITECH_DFP_WHEEL:
if (*rsize == DFP_RDESC_ORIG_SIZE) {
hid_info(hdev,
@@ -492,6 +627,7 @@
case USB_DEVICE_ID_LOGITECH_G27_WHEEL:
case USB_DEVICE_ID_LOGITECH_WII_WHEEL:
case USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2:
+ case USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL:
field->application = HID_GD_MULTIAXIS;
break;
default:
@@ -639,6 +775,8 @@
.driver_data = LG_NOGET | LG_FF4 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOMO_WHEEL2),
.driver_data = LG_FF4 },
+ { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_VIBRATION_WHEEL),
+ .driver_data = LG_FF2 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G25_WHEEL),
.driver_data = LG_FF4 },
{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DFGT_WHEEL),
diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c
index b3cd150..0e3fb1a 100644
--- a/drivers/hid/hid-lg2ff.c
+++ b/drivers/hid/hid-lg2ff.c
@@ -64,26 +64,13 @@
struct hid_report *report;
struct hid_input *hidinput = list_entry(hid->inputs.next,
struct hid_input, list);
- struct list_head *report_list =
- &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev = hidinput->input;
int error;
- if (list_empty(report_list)) {
- hid_err(hid, "no output report found\n");
+ /* Check that the report looks ok */
+ report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7);
+ if (!report)
return -ENODEV;
- }
-
- report = list_entry(report_list->next, struct hid_report, list);
-
- if (report->maxfield < 1) {
- hid_err(hid, "output report is empty\n");
- return -ENODEV;
- }
- if (report->field[0]->report_count < 7) {
- hid_err(hid, "not enough values in the field\n");
- return -ENODEV;
- }
lg2ff = kmalloc(sizeof(struct lg2ff_device), GFP_KERNEL);
if (!lg2ff)
@@ -108,7 +95,7 @@
hid_hw_request(hid, report, HID_REQ_SET_REPORT);
- hid_info(hid, "Force feedback for Logitech RumblePad/Rumblepad 2 by Anssi Hannula <anssi.hannula@gmail.com>\n");
+ hid_info(hid, "Force feedback for Logitech variant 2 rumble devices by Anssi Hannula <anssi.hannula@gmail.com>\n");
return 0;
}
diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c
index e52f181..8c2da18 100644
--- a/drivers/hid/hid-lg3ff.c
+++ b/drivers/hid/hid-lg3ff.c
@@ -66,10 +66,11 @@
int x, y;
/*
- * Maxusage should always be 63 (maximum fields)
- * likely a better way to ensure this data is clean
+ * Available values in the field should always be 63, but we only use up to
+ * 35. Instead, clear the entire area, however big it is.
*/
- memset(report->field[0]->value, 0, sizeof(__s32)*report->field[0]->maxusage);
+ memset(report->field[0]->value, 0,
+ sizeof(__s32) * report->field[0]->report_count);
switch (effect->type) {
case FF_CONSTANT:
@@ -129,32 +130,14 @@
int lg3ff_init(struct hid_device *hid)
{
struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
- struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev = hidinput->input;
- struct hid_report *report;
- struct hid_field *field;
const signed short *ff_bits = ff3_joystick_ac;
int error;
int i;
- /* Find the report to use */
- if (list_empty(report_list)) {
- hid_err(hid, "No output report found\n");
- return -1;
- }
-
/* Check that the report looks ok */
- report = list_entry(report_list->next, struct hid_report, list);
- if (!report) {
- hid_err(hid, "NULL output report\n");
- return -1;
- }
-
- field = report->field[0];
- if (!field) {
- hid_err(hid, "NULL field\n");
- return -1;
- }
+ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35))
+ return -ENODEV;
/* Assume single fixed device G940 */
for (i = 0; ff_bits[i] >= 0; i++)
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 0ddae2a..3518053 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -218,12 +218,46 @@
struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
__s32 *value = report->field[0]->value;
+ __u32 expand_a, expand_b;
+
+ /* De-activate Auto-Center */
+ if (magnitude == 0) {
+ value[0] = 0xf5;
+ value[1] = 0x00;
+ value[2] = 0x00;
+ value[3] = 0x00;
+ value[4] = 0x00;
+ value[5] = 0x00;
+ value[6] = 0x00;
+
+ hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+ return;
+ }
+
+ if (magnitude <= 0xaaaa) {
+ expand_a = 0x0c * magnitude;
+ expand_b = 0x80 * magnitude;
+ } else {
+ expand_a = (0x0c * 0xaaaa) + 0x06 * (magnitude - 0xaaaa);
+ expand_b = (0x80 * 0xaaaa) + 0xff * (magnitude - 0xaaaa);
+ }
value[0] = 0xfe;
value[1] = 0x0d;
- value[2] = magnitude >> 13;
- value[3] = magnitude >> 13;
- value[4] = magnitude >> 8;
+ value[2] = expand_a / 0xaaaa;
+ value[3] = expand_a / 0xaaaa;
+ value[4] = expand_b / 0xaaaa;
+ value[5] = 0x00;
+ value[6] = 0x00;
+
+ hid_hw_request(hid, report, HID_REQ_SET_REPORT);
+
+ /* Activate Auto-Center */
+ value[0] = 0x14;
+ value[1] = 0x00;
+ value[2] = 0x00;
+ value[3] = 0x00;
+ value[4] = 0x00;
value[5] = 0x00;
value[6] = 0x00;
@@ -484,34 +518,16 @@
int lg4ff_init(struct hid_device *hid)
{
struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
- struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev = hidinput->input;
- struct hid_report *report;
- struct hid_field *field;
struct lg4ff_device_entry *entry;
struct lg_drv_data *drv_data;
struct usb_device_descriptor *udesc;
int error, i, j;
__u16 bcdDevice, rev_maj, rev_min;
- /* Find the report to use */
- if (list_empty(report_list)) {
- hid_err(hid, "No output report found\n");
- return -1;
- }
-
/* Check that the report looks ok */
- report = list_entry(report_list->next, struct hid_report, list);
- if (!report) {
- hid_err(hid, "NULL output report\n");
+ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
return -1;
- }
-
- field = report->field[0];
- if (!field) {
- hid_err(hid, "NULL field\n");
- return -1;
- }
/* Check what wheel has been connected */
for (i = 0; i < ARRAY_SIZE(lg4ff_devices); i++) {
@@ -558,17 +574,6 @@
if (error)
return error;
- /* Check if autocentering is available and
- * set the centering force to zero by default */
- if (test_bit(FF_AUTOCENTER, dev->ffbit)) {
- if (rev_maj == FFEX_REV_MAJ && rev_min == FFEX_REV_MIN) /* Formula Force EX expects different autocentering command */
- dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
- else
- dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
-
- dev->ff->set_autocenter(dev, 0);
- }
-
/* Get private driver data */
drv_data = hid_get_drvdata(hid);
if (!drv_data) {
@@ -589,6 +594,17 @@
entry->max_range = lg4ff_devices[i].max_range;
entry->set_range = lg4ff_devices[i].set_range;
+ /* Check if autocentering is available and
+ * set the centering force to zero by default */
+ if (test_bit(FF_AUTOCENTER, dev->ffbit)) {
+ if (rev_maj == FFEX_REV_MAJ && rev_min == FFEX_REV_MIN) /* Formula Force EX expects different autocentering command */
+ dev->ff->set_autocenter = hid_lg4ff_set_autocenter_ffex;
+ else
+ dev->ff->set_autocenter = hid_lg4ff_set_autocenter_default;
+
+ dev->ff->set_autocenter(dev, 0);
+ }
+
/* Create sysfs interface */
error = device_create_file(&hid->dev, &dev_attr_range);
if (error)
diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c
index d7ea8c8..e1394af 100644
--- a/drivers/hid/hid-lgff.c
+++ b/drivers/hid/hid-lgff.c
@@ -128,27 +128,14 @@
int lgff_init(struct hid_device* hid)
{
struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
- struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev = hidinput->input;
- struct hid_report *report;
- struct hid_field *field;
const signed short *ff_bits = ff_joystick;
int error;
int i;
- /* Find the report to use */
- if (list_empty(report_list)) {
- hid_err(hid, "No output report found\n");
- return -1;
- }
-
/* Check that the report looks ok */
- report = list_entry(report_list->next, struct hid_report, list);
- field = report->field[0];
- if (!field) {
- hid_err(hid, "NULL field\n");
- return -1;
- }
+ if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
+ return -ENODEV;
for (i = 0; i < ARRAY_SIZE(devices); i++) {
if (dev->id.vendor == devices[i].idVendor &&
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 5207591a..d4c6d9f 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -192,6 +192,7 @@
static int logi_dj_output_hidraw_report(struct hid_device *hid, u8 * buf,
size_t count,
unsigned char report_type);
+static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev);
static void logi_dj_recv_destroy_djhid_device(struct dj_receiver_dev *djrcv_dev,
struct dj_report *dj_report)
@@ -232,13 +233,13 @@
if (dj_report->report_params[DEVICE_PAIRED_PARAM_SPFUNCTION] &
SPFUNCTION_DEVICE_LIST_EMPTY) {
dbg_hid("%s: device list is empty\n", __func__);
+ djrcv_dev->querying_devices = false;
return;
}
- if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
- (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
- dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n",
- __func__, dj_report->device_index);
+ if (djrcv_dev->paired_dj_devices[dj_report->device_index]) {
+ /* The device is already known. No need to reallocate it. */
+ dbg_hid("%s: device is already known\n", __func__);
return;
}
@@ -305,6 +306,7 @@
struct dj_report dj_report;
unsigned long flags;
int count;
+ int retval;
dbg_hid("%s\n", __func__);
@@ -337,6 +339,25 @@
logi_dj_recv_destroy_djhid_device(djrcv_dev, &dj_report);
break;
default:
+ /* A normal report (i. e. not belonging to a pair/unpair notification)
+ * arriving here, means that the report arrived but we did not have a
+ * paired dj_device associated to the report's device_index, this
+ * means that the original "device paired" notification corresponding
+ * to this dj_device never arrived to this driver. The reason is that
+ * hid-core discards all packets coming from a device while probe() is
+ * executing. */
+ if (!djrcv_dev->paired_dj_devices[dj_report.device_index]) {
+ /* ok, we don't know the device, just re-ask the
+ * receiver for the list of connected devices. */
+ retval = logi_dj_recv_query_paired_devices(djrcv_dev);
+ if (!retval) {
+ /* everything went fine, so just leave */
+ break;
+ }
+ dev_err(&djrcv_dev->hdev->dev,
+ "%s:logi_dj_recv_query_paired_devices "
+ "error:%d\n", __func__, retval);
+ }
dbg_hid("%s: unexpected report type\n", __func__);
}
}
@@ -367,6 +388,12 @@
if (!djdev) {
dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
" is NULL, index %d\n", dj_report->device_index);
+ kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+ if (schedule_work(&djrcv_dev->work) == 0) {
+ dbg_hid("%s: did not schedule the work item, was already "
+ "queued\n", __func__);
+ }
return;
}
@@ -397,6 +424,12 @@
if (dj_device == NULL) {
dbg_hid("djrcv_dev->paired_dj_devices[dj_report->device_index]"
" is NULL, index %d\n", dj_report->device_index);
+ kfifo_in(&djrcv_dev->notif_fifo, dj_report, sizeof(struct dj_report));
+
+ if (schedule_work(&djrcv_dev->work) == 0) {
+ dbg_hid("%s: did not schedule the work item, was already "
+ "queued\n", __func__);
+ }
return;
}
@@ -421,7 +454,7 @@
struct hid_report *report;
struct hid_report_enum *output_report_enum;
u8 *data = (u8 *)(&dj_report->device_index);
- int i;
+ unsigned int i;
output_report_enum = &hdev->report_enum[HID_OUTPUT_REPORT];
report = output_report_enum->report_id_hash[REPORT_ID_DJ_SHORT];
@@ -431,7 +464,7 @@
return -ENODEV;
}
- for (i = 0; i < report->field[0]->report_count; i++)
+ for (i = 0; i < DJREPORT_SHORT_LENGTH - 1; i++)
report->field[0]->value[i] = data[i];
hid_hw_request(hdev, report, HID_REQ_SET_REPORT);
@@ -444,6 +477,10 @@
struct dj_report *dj_report;
int retval;
+ /* no need to protect djrcv_dev->querying_devices */
+ if (djrcv_dev->querying_devices)
+ return 0;
+
dj_report = kzalloc(sizeof(struct dj_report), GFP_KERNEL);
if (!dj_report)
return -ENOMEM;
@@ -455,6 +492,7 @@
return retval;
}
+
static int logi_dj_recv_switch_to_dj_mode(struct dj_receiver_dev *djrcv_dev,
unsigned timeout)
{
@@ -574,7 +612,7 @@
struct hid_field *field;
struct hid_report *report;
- unsigned char data[8];
+ unsigned char *data;
int offset;
dbg_hid("%s: %s, type:%d | code:%d | value:%d\n",
@@ -590,6 +628,13 @@
return -1;
}
hid_set_field(field, offset, value);
+
+ data = hid_alloc_report_buf(field->report, GFP_KERNEL);
+ if (!data) {
+ dev_warn(&dev->dev, "failed to allocate report buf memory\n");
+ return -1;
+ }
+
hid_output_report(field->report, &data[0]);
output_report_enum = &dj_rcv_hiddev->report_enum[HID_OUTPUT_REPORT];
@@ -600,8 +645,9 @@
hid_hw_request(dj_rcv_hiddev, report, HID_REQ_SET_REPORT);
- return 0;
+ kfree(data);
+ return 0;
}
static int logi_dj_ll_start(struct hid_device *hid)
@@ -633,7 +679,6 @@
struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev);
struct dj_report *dj_report = (struct dj_report *) data;
unsigned long flags;
- bool report_processed = false;
dbg_hid("%s, size:%d\n", __func__, size);
@@ -661,27 +706,41 @@
* anything else with it.
*/
+ /* case 1) */
+ if (data[0] != REPORT_ID_DJ_SHORT)
+ return false;
+
+ if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
+ (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
+ /*
+ * Device index is wrong, bail out.
+ * This driver can ignore safely the receiver notifications,
+ * so ignore those reports too.
+ */
+ if (dj_report->device_index != DJ_RECEIVER_INDEX)
+ dev_err(&hdev->dev, "%s: invalid device index:%d\n",
+ __func__, dj_report->device_index);
+ return false;
+ }
+
spin_lock_irqsave(&djrcv_dev->lock, flags);
- if (dj_report->report_id == REPORT_ID_DJ_SHORT) {
- switch (dj_report->report_type) {
- case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
- case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
- logi_dj_recv_queue_notification(djrcv_dev, dj_report);
- break;
- case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
- if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
- STATUS_LINKLOSS) {
- logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
- }
- break;
- default:
- logi_dj_recv_forward_report(djrcv_dev, dj_report);
+ switch (dj_report->report_type) {
+ case REPORT_TYPE_NOTIF_DEVICE_PAIRED:
+ case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED:
+ logi_dj_recv_queue_notification(djrcv_dev, dj_report);
+ break;
+ case REPORT_TYPE_NOTIF_CONNECTION_STATUS:
+ if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] ==
+ STATUS_LINKLOSS) {
+ logi_dj_recv_forward_null_report(djrcv_dev, dj_report);
}
- report_processed = true;
+ break;
+ default:
+ logi_dj_recv_forward_report(djrcv_dev, dj_report);
}
spin_unlock_irqrestore(&djrcv_dev->lock, flags);
- return report_processed;
+ return true;
}
static int logi_dj_probe(struct hid_device *hdev,
@@ -738,6 +797,12 @@
goto hid_parse_fail;
}
+ if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, REPORT_ID_DJ_SHORT,
+ 0, DJREPORT_SHORT_LENGTH - 1)) {
+ retval = -ENODEV;
+ goto hid_parse_fail;
+ }
+
/* Starts the usb device and connects to upper interfaces hiddev and
* hidraw */
retval = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h
index fd28a5e..daeb0aa 100644
--- a/drivers/hid/hid-logitech-dj.h
+++ b/drivers/hid/hid-logitech-dj.h
@@ -27,6 +27,7 @@
#define DJ_MAX_PAIRED_DEVICES 6
#define DJ_MAX_NUMBER_NOTIFICATIONS 8
+#define DJ_RECEIVER_INDEX 0
#define DJ_DEVICE_INDEX_MIN 1
#define DJ_DEVICE_INDEX_MAX 6
@@ -101,6 +102,7 @@
struct work_struct work;
struct kfifo notif_fifo;
spinlock_t lock;
+ bool querying_devices;
};
struct dj_device {
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 5bc3734..c24f3df 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -290,6 +290,11 @@
if (size < 4 || ((size - 4) % 9) != 0)
return 0;
npoints = (size - 4) / 9;
+ if (npoints > 15) {
+ hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n",
+ size);
+ return 0;
+ }
msc->ntouches = 0;
for (ii = 0; ii < npoints; ii++)
magicmouse_emit_touch(msc, ii, data + ii * 9 + 4);
@@ -307,6 +312,11 @@
if (size < 6 || ((size - 6) % 8) != 0)
return 0;
npoints = (size - 6) / 8;
+ if (npoints > 15) {
+ hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n",
+ size);
+ return 0;
+ }
msc->ntouches = 0;
for (ii = 0; ii < npoints; ii++)
magicmouse_emit_touch(msc, ii, data + ii * 8 + 6);
diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c
index 9e14c00..25daf28 100644
--- a/drivers/hid/hid-monterey.c
+++ b/drivers/hid/hid-monterey.c
@@ -24,7 +24,7 @@
static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
+ if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
hid_info(hdev, "fixing up button/consumer in HID report descriptor\n");
rdesc[30] = 0x0c;
}
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index d39a5ce..3d8e58a 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -101,9 +101,9 @@
unsigned last_slot_field; /* the last field of a slot */
unsigned mt_report_id; /* the report ID of the multitouch device */
unsigned pen_report_id; /* the report ID of the pen device */
- __s8 inputmode; /* InputMode HID feature, -1 if non-existent */
- __s8 inputmode_index; /* InputMode HID feature index in the report */
- __s8 maxcontact_report_id; /* Maximum Contact Number HID feature,
+ __s16 inputmode; /* InputMode HID feature, -1 if non-existent */
+ __s16 inputmode_index; /* InputMode HID feature index in the report */
+ __s16 maxcontact_report_id; /* Maximum Contact Number HID feature,
-1 if non-existent */
__u8 num_received; /* how many contacts we received */
__u8 num_expected; /* expected last contact index */
@@ -244,12 +244,12 @@
{ .name = MT_CLS_GENERALTOUCH_TWOFINGERS,
.quirks = MT_QUIRK_NOT_SEEN_MEANS_UP |
MT_QUIRK_VALID_IS_INRANGE |
- MT_QUIRK_SLOT_IS_CONTACTNUMBER,
+ MT_QUIRK_SLOT_IS_CONTACTID,
.maxcontacts = 2
},
{ .name = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
.quirks = MT_QUIRK_NOT_SEEN_MEANS_UP |
- MT_QUIRK_SLOT_IS_CONTACTNUMBER
+ MT_QUIRK_SLOT_IS_CONTACTID
},
{ .name = MT_CLS_FLATFROG,
@@ -317,20 +317,18 @@
struct hid_field *field, struct hid_usage *usage)
{
struct mt_device *td = hid_get_drvdata(hdev);
- int i;
switch (usage->hid) {
case HID_DG_INPUTMODE:
- td->inputmode = field->report->id;
- td->inputmode_index = 0; /* has to be updated below */
-
- for (i=0; i < field->maxusage; i++) {
- if (field->usage[i].hid == usage->hid) {
- td->inputmode_index = i;
- break;
- }
+ /* Ignore if value index is out of bounds. */
+ if (usage->usage_index >= field->report_count) {
+ dev_err(&hdev->dev, "HID_DG_INPUTMODE out of range\n");
+ break;
}
+ td->inputmode = field->report->id;
+ td->inputmode_index = usage->usage_index;
+
break;
case HID_DG_CONTACTMAX:
td->maxcontact_report_id = field->report->id;
@@ -536,6 +534,10 @@
mt_store_field(usage, td, hi);
return 1;
case HID_DG_CONTACTCOUNT:
+ /* Ignore if indexes are out of bounds. */
+ if (field->index >= field->report->maxfield ||
+ usage->usage_index >= field->report_count)
+ return 1;
td->cc_index = field->index;
td->cc_value_index = usage->usage_index;
return 1;
@@ -1189,6 +1191,21 @@
{ .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PWT_TENFINGERS) },
+ { .driver_data = MT_CLS_GENERALTOUCH_TWOFINGERS,
+ MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+ USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0101) },
+ { .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+ MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+ USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0102) },
+ { .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+ MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+ USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_0106) },
+ { .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+ MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+ USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A) },
+ { .driver_data = MT_CLS_GENERALTOUCH_PWT_TENFINGERS,
+ MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH,
+ USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100) },
/* Gametel game controller */
{ .driver_data = MT_CLS_NSMU,
@@ -1300,6 +1317,14 @@
MT_USB_DEVICE(USB_VENDOR_ID_QUANTA,
USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008) },
+ /* SiS panels */
+ { .driver_data = MT_CLS_DEFAULT,
+ HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH,
+ USB_DEVICE_ID_SIS9200_TOUCH) },
+ { .driver_data = MT_CLS_DEFAULT,
+ HID_USB_DEVICE(USB_VENDOR_ID_SIS2_TOUCH,
+ USB_DEVICE_ID_SIS817_TOUCH) },
+
/* Stantum panels */
{ .driver_data = MT_CLS_CONFIDENCE,
MT_USB_DEVICE(USB_VENDOR_ID_STANTUM,
@@ -1328,6 +1353,12 @@
{ .driver_data = MT_CLS_NSMU,
MT_USB_DEVICE(USB_VENDOR_ID_UNITEC,
USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) },
+
+ /* Wistron panels */
+ { .driver_data = MT_CLS_NSMU,
+ MT_USB_DEVICE(USB_VENDOR_ID_WISTRON,
+ USB_DEVICE_ID_WISTRON_OPTICAL_TOUCH) },
+
/* XAT */
{ .driver_data = MT_CLS_NSMU,
MT_USB_DEVICE(USB_VENDOR_ID_XAT,
diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index ef95102..5482156 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -115,7 +115,8 @@
struct hid_report *report = hdev->report_enum[HID_FEATURE_REPORT].
report_id_hash[0x0d];
- if (!report)
+ if (!report || report->maxfield < 1 ||
+ report->field[0]->report_count < 1)
return -EINVAL;
hid_hw_request(hdev, report, HID_REQ_GET_REPORT);
diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c
index 736b250..6aca4f2 100644
--- a/drivers/hid/hid-petalynx.c
+++ b/drivers/hid/hid-petalynx.c
@@ -25,7 +25,7 @@
static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
+ if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
rdesc[41] == 0x00 && rdesc[59] == 0x26 &&
rdesc[60] == 0xf9 && rdesc[61] == 0x00) {
hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n");
diff --git a/drivers/hid/hid-picolcd_cir.c b/drivers/hid/hid-picolcd_cir.c
index e346038..59d5eb1 100644
--- a/drivers/hid/hid-picolcd_cir.c
+++ b/drivers/hid/hid-picolcd_cir.c
@@ -145,6 +145,7 @@
struct rc_dev *rdev = data->rc_dev;
data->rc_dev = NULL;
- rc_unregister_device(rdev);
+ if (rdev)
+ rc_unregister_device(rdev);
}
diff --git a/drivers/hid/hid-picolcd_core.c b/drivers/hid/hid-picolcd_core.c
index b48092d..020df3c 100644
--- a/drivers/hid/hid-picolcd_core.c
+++ b/drivers/hid/hid-picolcd_core.c
@@ -290,7 +290,7 @@
buf += 10;
cnt -= 10;
}
- if (!report)
+ if (!report || report->maxfield != 1)
return -EINVAL;
while (cnt > 0 && (buf[cnt-1] == '\n' || buf[cnt-1] == '\r'))
@@ -350,6 +350,12 @@
if (!data)
return 1;
+ if (size > 64) {
+ hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n",
+ size);
+ return 0;
+ }
+
if (report->id == REPORT_KEY_STATE) {
if (data->input_keys)
ret = picolcd_raw_keypad(data, report, raw_data+1, size-1);
diff --git a/drivers/hid/hid-picolcd_debugfs.c b/drivers/hid/hid-picolcd_debugfs.c
index 59ab8e1..024cdf3 100644
--- a/drivers/hid/hid-picolcd_debugfs.c
+++ b/drivers/hid/hid-picolcd_debugfs.c
@@ -394,7 +394,7 @@
void picolcd_debug_out_report(struct picolcd_data *data,
struct hid_device *hdev, struct hid_report *report)
{
- u8 raw_data[70];
+ u8 *raw_data;
int raw_size = (report->size >> 3) + 1;
char *buff;
#define BUFF_SZ 256
@@ -407,19 +407,19 @@
if (!buff)
return;
+ raw_data = hid_alloc_report_buf(report, GFP_ATOMIC);
+ if (!raw_data) {
+ kfree(buff);
+ return;
+ }
+
snprintf(buff, BUFF_SZ, "\nout report %d (size %d) = ",
report->id, raw_size);
hid_debug_event(hdev, buff);
- if (raw_size + 5 > sizeof(raw_data)) {
- kfree(buff);
- hid_debug_event(hdev, " TOO BIG\n");
- return;
- } else {
- raw_data[0] = report->id;
- hid_output_report(report, raw_data);
- dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
- hid_debug_event(hdev, buff);
- }
+ raw_data[0] = report->id;
+ hid_output_report(report, raw_data);
+ dump_buff_as_hex(buff, BUFF_SZ, raw_data, raw_size);
+ hid_debug_event(hdev, buff);
switch (report->id) {
case REPORT_LED_STATE:
@@ -644,6 +644,7 @@
break;
}
wake_up_interruptible(&hdev->debug_wait);
+ kfree(raw_data);
kfree(buff);
}
diff --git a/drivers/hid/hid-picolcd_fb.c b/drivers/hid/hid-picolcd_fb.c
index 591f6b2..c930ab8 100644
--- a/drivers/hid/hid-picolcd_fb.c
+++ b/drivers/hid/hid-picolcd_fb.c
@@ -593,10 +593,14 @@
void picolcd_exit_framebuffer(struct picolcd_data *data)
{
struct fb_info *info = data->fb_info;
- struct picolcd_fb_data *fbdata = info->par;
+ struct picolcd_fb_data *fbdata;
unsigned long flags;
+ if (!info)
+ return;
+
device_remove_file(&data->hdev->dev, &dev_attr_fb_update_rate);
+ fbdata = info->par;
/* disconnect framebuffer from HID dev */
spin_lock_irqsave(&fbdata->lock, flags);
diff --git a/drivers/hid/hid-pl.c b/drivers/hid/hid-pl.c
index d29112f..2dcd7d9 100644
--- a/drivers/hid/hid-pl.c
+++ b/drivers/hid/hid-pl.c
@@ -132,8 +132,14 @@
strong = &report->field[0]->value[2];
weak = &report->field[0]->value[3];
debug("detected single-field device");
- } else if (report->maxfield >= 4 && report->field[0]->maxusage == 1 &&
- report->field[0]->usage[0].hid == (HID_UP_LED | 0x43)) {
+ } else if (report->field[0]->maxusage == 1 &&
+ report->field[0]->usage[0].hid ==
+ (HID_UP_LED | 0x43) &&
+ report->maxfield >= 4 &&
+ report->field[0]->report_count >= 1 &&
+ report->field[1]->report_count >= 1 &&
+ report->field[2]->report_count >= 1 &&
+ report->field[3]->report_count >= 1) {
report->field[0]->value[0] = 0x00;
report->field[1]->value[0] = 0x00;
strong = &report->field[2]->value[0];
diff --git a/drivers/hid/hid-roccat-common.c b/drivers/hid/hid-roccat-common.c
index 74f7040..e840899 100644
--- a/drivers/hid/hid-roccat-common.c
+++ b/drivers/hid/hid-roccat-common.c
@@ -65,10 +65,11 @@
EXPORT_SYMBOL_GPL(roccat_common2_send);
enum roccat_common2_control_states {
- ROCCAT_COMMON_CONTROL_STATUS_OVERLOAD = 0,
+ ROCCAT_COMMON_CONTROL_STATUS_CRITICAL = 0,
ROCCAT_COMMON_CONTROL_STATUS_OK = 1,
ROCCAT_COMMON_CONTROL_STATUS_INVALID = 2,
- ROCCAT_COMMON_CONTROL_STATUS_WAIT = 3,
+ ROCCAT_COMMON_CONTROL_STATUS_BUSY = 3,
+ ROCCAT_COMMON_CONTROL_STATUS_CRITICAL_NEW = 4,
};
static int roccat_common2_receive_control_status(struct usb_device *usb_dev)
@@ -88,13 +89,12 @@
switch (control.value) {
case ROCCAT_COMMON_CONTROL_STATUS_OK:
return 0;
- case ROCCAT_COMMON_CONTROL_STATUS_WAIT:
+ case ROCCAT_COMMON_CONTROL_STATUS_BUSY:
msleep(500);
continue;
case ROCCAT_COMMON_CONTROL_STATUS_INVALID:
-
- case ROCCAT_COMMON_CONTROL_STATUS_OVERLOAD:
- /* seems to be critical - replug necessary */
+ case ROCCAT_COMMON_CONTROL_STATUS_CRITICAL:
+ case ROCCAT_COMMON_CONTROL_STATUS_CRITICAL_NEW:
return -EINVAL;
default:
dev_err(&usb_dev->dev,
diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c
index c79d0b0..5850959 100644
--- a/drivers/hid/hid-roccat-konepure.c
+++ b/drivers/hid/hid-roccat-konepure.c
@@ -262,6 +262,7 @@
static const struct hid_device_id konepure_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONEPURE_OPTICAL) },
{ }
};
@@ -300,5 +301,5 @@
module_exit(konepure_exit);
MODULE_AUTHOR("Stefan Achatz");
-MODULE_DESCRIPTION("USB Roccat KonePure driver");
+MODULE_DESCRIPTION("USB Roccat KonePure/Optical driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c
index b8b3778..2c571da 100644
--- a/drivers/hid/hid-roccat-kovaplus.c
+++ b/drivers/hid/hid-roccat-kovaplus.c
@@ -577,9 +577,13 @@
break;
case KOVAPLUS_MOUSE_REPORT_BUTTON_TYPE_CPI:
kovaplus->actual_cpi = kovaplus_convert_event_cpi(button_report->data1);
+ break;
case KOVAPLUS_MOUSE_REPORT_BUTTON_TYPE_SENSITIVITY:
kovaplus->actual_x_sensitivity = button_report->data1;
kovaplus->actual_y_sensitivity = button_report->data2;
+ break;
+ default:
+ break;
}
}
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index d4f1e3b..264ddc4 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -35,6 +35,8 @@
static void profile_activated(struct pyra_device *pyra,
unsigned int new_profile)
{
+ if (new_profile >= ARRAY_SIZE(pyra->profile_settings))
+ return;
pyra->actual_profile = new_profile;
pyra->actual_cpi = pyra->profile_settings[pyra->actual_profile].y_cpi;
}
@@ -236,9 +238,11 @@
if (off != 0 || count != PYRA_SIZE_SETTINGS)
return -EINVAL;
- mutex_lock(&pyra->pyra_lock);
-
settings = (struct pyra_settings const *)buf;
+ if (settings->startup_profile >= ARRAY_SIZE(pyra->profile_settings))
+ return -EINVAL;
+
+ mutex_lock(&pyra->pyra_lock);
retval = pyra_set_settings(usb_dev, settings);
if (retval) {
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index ca749810..b189feb 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -221,7 +221,8 @@
mutex_lock(&data->mutex);
report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
- if (!report || (field_index >= report->maxfield)) {
+ if (!report || (field_index >= report->maxfield) ||
+ report->field[field_index]->report_count < 1) {
ret = -EINVAL;
goto done_proc;
}
@@ -326,7 +327,8 @@
field->logical == attr_usage_id) {
sensor_hub_fill_attr_info(info, i, report->id,
field->unit, field->unit_exponent,
- field->report_size);
+ field->report_size *
+ field->report_count);
ret = 0;
} else {
for (j = 0; j < field->maxusage; ++j) {
@@ -338,7 +340,8 @@
i, report->id,
field->unit,
field->unit_exponent,
- field->report_size);
+ field->report_size *
+ field->report_count);
ret = 0;
break;
}
@@ -425,9 +428,10 @@
hid_dbg(hdev, "%d collection_index:%x hid:%x sz:%x\n",
i, report->field[i]->usage->collection_index,
report->field[i]->usage->hid,
- report->field[i]->report_size/8);
-
- sz = report->field[i]->report_size/8;
+ (report->field[i]->report_size *
+ report->field[i]->report_count)/8);
+ sz = (report->field[i]->report_size *
+ report->field[i]->report_count)/8;
if (pdata->pending.status && pdata->pending.attr_usage_id ==
report->field[i]->usage->hid) {
hid_dbg(hdev, "data was pending ...\n");
diff --git a/drivers/hid/hid-speedlink.c b/drivers/hid/hid-speedlink.c
index a2f587d..7112f3e 100644
--- a/drivers/hid/hid-speedlink.c
+++ b/drivers/hid/hid-speedlink.c
@@ -3,7 +3,7 @@
* Fixes "jumpy" cursor and removes nonexistent keyboard LEDS from
* the HID descriptor.
*
- * Copyright (c) 2011 Stefan Kriwanek <mail@stefankriwanek.de>
+ * Copyright (c) 2011, 2013 Stefan Kriwanek <dev@stefankriwanek.de>
*/
/*
@@ -46,8 +46,13 @@
struct hid_usage *usage, __s32 value)
{
/* No other conditions due to usage_table. */
- /* Fix "jumpy" cursor (invalid events sent by device). */
- if (value == 256)
+
+ /* This fixes the "jumpy" cursor occuring due to invalid events sent
+ * by the device. Some devices only send them with value==+256, others
+ * don't. However, catching abs(value)>=256 is restrictive enough not
+ * to interfere with devices that were bug-free (has been tested).
+ */
+ if (abs(value) >= 256)
return 1;
/* Drop useless distance 0 events (on button clicks etc.) as well */
if (value == 0)
diff --git a/drivers/hid/hid-steelseries.c b/drivers/hid/hid-steelseries.c
index d164911..29f328f 100644
--- a/drivers/hid/hid-steelseries.c
+++ b/drivers/hid/hid-steelseries.c
@@ -249,6 +249,11 @@
goto err_free;
}
+ if (!hid_validate_values(hdev, HID_OUTPUT_REPORT, 0, 0, 16)) {
+ ret = -ENODEV;
+ goto err_free;
+ }
+
ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
if (ret) {
hid_err(hdev, "hw start failed\n");
diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c
index 87fc91e..91072fa 100644
--- a/drivers/hid/hid-sunplus.c
+++ b/drivers/hid/hid-sunplus.c
@@ -24,7 +24,7 @@
static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
unsigned int *rsize)
{
- if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
+ if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
rdesc[106] == 0x03) {
hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n");
rdesc[105] = rdesc[110] = 0x03;
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index 6ec28a3..a29756c 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -68,21 +68,13 @@
struct hid_report *report;
struct hid_input *hidinput = list_entry(hid->inputs.next,
struct hid_input, list);
- struct list_head *report_list =
- &hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev = hidinput->input;
- int error;
+ int i, error;
- if (list_empty(report_list)) {
- hid_err(hid, "no output report found\n");
- return -ENODEV;
- }
-
- report = list_entry(report_list->next, struct hid_report, list);
-
- if (report->maxfield < 4) {
- hid_err(hid, "not enough fields in report\n");
- return -ENODEV;
+ for (i = 0; i < 4; i++) {
+ report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1);
+ if (!report)
+ return -ENODEV;
}
zpff = kzalloc(sizeof(struct zpff_device), GFP_KERNEL);
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index a745163..612a655 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -113,7 +113,7 @@
__u8 *buf;
int ret = 0;
- if (!hidraw_table[minor]) {
+ if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
ret = -ENODEV;
goto out;
}
@@ -261,7 +261,7 @@
}
mutex_lock(&minors_lock);
- if (!hidraw_table[minor]) {
+ if (!hidraw_table[minor] || !hidraw_table[minor]->exist) {
err = -ENODEV;
goto out_unlock;
}
@@ -302,39 +302,38 @@
return fasync_helper(fd, file, on, &list->fasync);
}
+static void drop_ref(struct hidraw *hidraw, int exists_bit)
+{
+ if (exists_bit) {
+ hid_hw_close(hidraw->hid);
+ hidraw->exist = 0;
+ if (hidraw->open)
+ wake_up_interruptible(&hidraw->wait);
+ } else {
+ --hidraw->open;
+ }
+
+ if (!hidraw->open && !hidraw->exist) {
+ device_destroy(hidraw_class, MKDEV(hidraw_major, hidraw->minor));
+ hidraw_table[hidraw->minor] = NULL;
+ kfree(hidraw);
+ }
+}
+
static int hidraw_release(struct inode * inode, struct file * file)
{
unsigned int minor = iminor(inode);
- struct hidraw *dev;
struct hidraw_list *list = file->private_data;
- int ret;
- int i;
mutex_lock(&minors_lock);
- if (!hidraw_table[minor]) {
- ret = -ENODEV;
- goto unlock;
- }
list_del(&list->node);
- dev = hidraw_table[minor];
- if (!--dev->open) {
- if (list->hidraw->exist) {
- hid_hw_power(dev->hid, PM_HINT_NORMAL);
- hid_hw_close(dev->hid);
- } else {
- kfree(list->hidraw);
- }
- }
-
- for (i = 0; i < HIDRAW_BUFFER_SIZE; ++i)
- kfree(list->buffer[i].value);
kfree(list);
- ret = 0;
-unlock:
- mutex_unlock(&minors_lock);
- return ret;
+ drop_ref(hidraw_table[minor], 0);
+
+ mutex_unlock(&minors_lock);
+ return 0;
}
static long hidraw_ioctl(struct file *file, unsigned int cmd,
@@ -539,18 +538,9 @@
struct hidraw *hidraw = hid->hidraw;
mutex_lock(&minors_lock);
- hidraw->exist = 0;
- device_destroy(hidraw_class, MKDEV(hidraw_major, hidraw->minor));
+ drop_ref(hidraw, 1);
- hidraw_table[hidraw->minor] = NULL;
-
- if (hidraw->open) {
- hid_hw_close(hid);
- wake_up_interruptible(&hidraw->wait);
- } else {
- kfree(hidraw);
- }
mutex_unlock(&minors_lock);
}
EXPORT_SYMBOL_GPL(hidraw_disconnect);
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 2b1799a3..ccc2f36b 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -134,6 +134,7 @@
* descriptor. */
unsigned int bufsize; /* i2c buffer size */
char *inbuf; /* Input buffer */
+ char *rawbuf; /* Raw Input buffer */
char *cmdbuf; /* Command buffer */
char *argsbuf; /* Command arguments buffer */
@@ -342,6 +343,9 @@
int ret, ret_size;
int size = le16_to_cpu(ihid->hdesc.wMaxInputLength);
+ if (size > ihid->bufsize)
+ size = ihid->bufsize;
+
ret = i2c_master_recv(ihid->client, ihid->inbuf, size);
if (ret != size) {
if (ret < 0)
@@ -471,9 +475,11 @@
static void i2c_hid_free_buffers(struct i2c_hid *ihid)
{
kfree(ihid->inbuf);
+ kfree(ihid->rawbuf);
kfree(ihid->argsbuf);
kfree(ihid->cmdbuf);
ihid->inbuf = NULL;
+ ihid->rawbuf = NULL;
ihid->cmdbuf = NULL;
ihid->argsbuf = NULL;
ihid->bufsize = 0;
@@ -489,10 +495,11 @@
report_size; /* report */
ihid->inbuf = kzalloc(report_size, GFP_KERNEL);
+ ihid->rawbuf = kzalloc(report_size, GFP_KERNEL);
ihid->argsbuf = kzalloc(args_len, GFP_KERNEL);
ihid->cmdbuf = kzalloc(sizeof(union command) + args_len, GFP_KERNEL);
- if (!ihid->inbuf || !ihid->argsbuf || !ihid->cmdbuf) {
+ if (!ihid->inbuf || !ihid->rawbuf || !ihid->argsbuf || !ihid->cmdbuf) {
i2c_hid_free_buffers(ihid);
return -ENOMEM;
}
@@ -519,12 +526,12 @@
ret = i2c_hid_get_report(client,
report_type == HID_FEATURE_REPORT ? 0x03 : 0x01,
- report_number, ihid->inbuf, ask_count);
+ report_number, ihid->rawbuf, ask_count);
if (ret < 0)
return ret;
- ret_count = ihid->inbuf[0] | (ihid->inbuf[1] << 8);
+ ret_count = ihid->rawbuf[0] | (ihid->rawbuf[1] << 8);
if (ret_count <= 2)
return 0;
@@ -533,7 +540,7 @@
/* The query buffer contains the size, dropping it in the reply */
count = min(count, ret_count - 2);
- memcpy(buf, ihid->inbuf + 2, count);
+ memcpy(buf, ihid->rawbuf + 2, count);
return count;
}
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index fc307e04..0bb3bb8 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -312,7 +312,7 @@
*/
struct uhid_create_req_compat *compat;
- compat = kmalloc(sizeof(*compat), GFP_KERNEL);
+ compat = kzalloc(sizeof(*compat), GFP_KERNEL);
if (!compat)
return -ENOMEM;
@@ -640,7 +640,7 @@
static struct miscdevice uhid_misc = {
.fops = &uhid_fops,
- .minor = MISC_DYNAMIC_MINOR,
+ .minor = UHID_MINOR,
.name = UHID_NAME,
};
@@ -659,3 +659,5 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("David Herrmann <dh.herrmann@gmail.com>");
MODULE_DESCRIPTION("User-space I/O driver support for HID subsystem");
+MODULE_ALIAS_MISCDEV(UHID_MINOR);
+MODULE_ALIAS("devname:" UHID_NAME);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 9941828..ada164e 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -535,7 +535,6 @@
{
int head;
struct usbhid_device *usbhid = hid->driver_data;
- int len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
if ((hid->quirks & HID_QUIRK_NOGET) && dir == USB_DIR_IN)
return;
@@ -546,7 +545,7 @@
return;
}
- usbhid->out[usbhid->outhead].raw_report = kmalloc(len, GFP_ATOMIC);
+ usbhid->out[usbhid->outhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
if (!usbhid->out[usbhid->outhead].raw_report) {
hid_warn(hid, "output queueing failed\n");
return;
@@ -595,7 +594,7 @@
}
if (dir == USB_DIR_OUT) {
- usbhid->ctrl[usbhid->ctrlhead].raw_report = kmalloc(len, GFP_ATOMIC);
+ usbhid->ctrl[usbhid->ctrlhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC);
if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) {
hid_warn(hid, "control queueing failed\n");
return;
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 19b8360..5b46a79 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -84,6 +84,8 @@
{ USB_VENDOR_ID_REALTEK, USB_DEVICE_ID_REALTEK_READER, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_SIGMATEL, USB_DEVICE_ID_SIGMATEL_STMP3780, HID_QUIRK_NOGET },
+ { USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS9200_TOUCH, HID_QUIRK_NOGET },
+ { USB_VENDOR_ID_SIS2_TOUCH, USB_DEVICE_ID_SIS817_TOUCH, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_SUN, USB_DEVICE_ID_RARITAN_KVM_DONGLE, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_1, HID_QUIRK_NOGET },
{ USB_VENDOR_ID_SYMBOL, USB_DEVICE_ID_SYMBOL_SCANNER_2, HID_QUIRK_NOGET },
@@ -108,7 +110,13 @@
{ USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS, HID_QUIRK_MULTI_INPUT },
{ USB_VENDOR_ID_SIGMA_MICRO, USB_DEVICE_ID_SIGMA_MICRO_KEYBOARD, HID_QUIRK_NO_INIT_REPORTS },
{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X, HID_QUIRK_MULTI_INPUT },
+ { USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_2, HID_QUIRK_MULTI_INPUT },
{ USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X, HID_QUIRK_MULTI_INPUT },
+ { USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_DUOSENSE, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS1, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS },
+ { USB_VENDOR_ID_SIS, USB_DEVICE_ID_SIS_TS, HID_QUIRK_NO_INIT_REPORTS },
+
{ 0, 0 }
};
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 0b122f8..05e6a7d 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -169,7 +169,7 @@
GFP_KERNEL);
if (!open_info) {
err = -ENOMEM;
- goto error0;
+ goto error_gpadl;
}
init_completion(&open_info->waitevent);
@@ -185,7 +185,7 @@
if (userdatalen > MAX_USER_DEFINED_BYTES) {
err = -EINVAL;
- goto error0;
+ goto error_gpadl;
}
if (userdatalen)
@@ -199,8 +199,10 @@
ret = vmbus_post_msg(open_msg,
sizeof(struct vmbus_channel_open_channel));
- if (ret != 0)
+ if (ret != 0) {
+ err = ret;
goto error1;
+ }
t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
if (t == 0) {
@@ -224,6 +226,9 @@
list_del(&open_info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+error_gpadl:
+ vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
+
error0:
free_pages((unsigned long)out,
get_order(send_ringbuffer_size + recv_ringbuffer_size));
@@ -392,7 +397,6 @@
u32 next_gpadl_handle;
unsigned long flags;
int ret = 0;
- int t;
next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle);
atomic_inc(&vmbus_connection.next_gpadl_handle);
@@ -439,9 +443,7 @@
}
}
- t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
- BUG_ON(t == 0);
-
+ wait_for_completion(&msginfo->waitevent);
/* At this point, we received the gpadl created msg */
*gpadl_handle = gpadlmsg->gpadl;
@@ -464,7 +466,7 @@
struct vmbus_channel_gpadl_teardown *msg;
struct vmbus_channel_msginfo *info;
unsigned long flags;
- int ret, t;
+ int ret;
info = kmalloc(sizeof(*info) +
sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
@@ -486,11 +488,12 @@
ret = vmbus_post_msg(msg,
sizeof(struct vmbus_channel_gpadl_teardown));
- BUG_ON(ret != 0);
- t = wait_for_completion_timeout(&info->waitevent, 5*HZ);
- BUG_ON(t == 0);
+ if (ret)
+ goto post_msg_err;
- /* Received a torndown response */
+ wait_for_completion(&info->waitevent);
+
+post_msg_err:
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&info->msglistentry);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 253a74b..a3b5558 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -55,6 +55,9 @@
case (VERSION_WIN8):
return VERSION_WIN7;
+ case (VERSION_WIN8_1):
+ return VERSION_WIN8;
+
case (VERSION_WS2008):
default:
return VERSION_INVAL;
@@ -67,7 +70,6 @@
int ret = 0;
struct vmbus_channel_initiate_contact *msg;
unsigned long flags;
- int t;
init_completion(&msginfo->waitevent);
@@ -81,6 +83,9 @@
(void *)((unsigned long)vmbus_connection.monitor_pages +
PAGE_SIZE));
+ if (version == VERSION_WIN8_1)
+ msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
+
/*
* Add to list before we send the request since we may
* receive the response before returning from this routine
@@ -102,15 +107,7 @@
}
/* Wait for the connection response */
- t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ);
- if (t == 0) {
- spin_lock_irqsave(&vmbus_connection.channelmsg_lock,
- flags);
- list_del(&msginfo->msglistentry);
- spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock,
- flags);
- return -ETIMEDOUT;
- }
+ wait_for_completion(&msginfo->waitevent);
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
@@ -307,9 +304,13 @@
*/
do {
- hv_begin_read(&channel->inbound);
+ if (read_state)
+ hv_begin_read(&channel->inbound);
channel->onchannel_callback(arg);
- bytes_to_read = hv_end_read(&channel->inbound);
+ if (read_state)
+ bytes_to_read = hv_end_read(&channel->inbound);
+ else
+ bytes_to_read = 0;
} while (read_state && (bytes_to_read != 0));
} else {
pr_err("no channel callback for relid - %u\n", relid);
@@ -392,10 +393,21 @@
* insufficient resources. Retry the operation a couple of
* times before giving up.
*/
- while (retries < 3) {
- ret = hv_post_message(conn_id, 1, buffer, buflen);
- if (ret != HV_STATUS_INSUFFICIENT_BUFFERS)
+ while (retries < 10) {
+ ret = hv_post_message(conn_id, 1, buffer, buflen);
+
+ switch (ret) {
+ case HV_STATUS_INSUFFICIENT_BUFFERS:
+ ret = -ENOMEM;
+ case -ENOMEM:
+ break;
+ case HV_STATUS_SUCCESS:
return ret;
+ default:
+ pr_err("hv_post_msg() failed; error code:%d\n", ret);
+ return -EINVAL;
+ }
+
retries++;
msleep(100);
}
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 4c605c7..694173f 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -19,6 +19,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
+#include <linux/jiffies.h>
#include <linux/mman.h>
#include <linux/delay.h>
#include <linux/init.h>
@@ -459,6 +460,11 @@
*/
static uint pressure_report_delay = 45;
+/*
+ * The last time we posted a pressure report to host.
+ */
+static unsigned long last_post_time;
+
module_param(hot_add, bool, (S_IRUGO | S_IWUSR));
MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add");
@@ -542,6 +548,7 @@
static struct hv_dynmem_device dm_device;
+static void post_status(struct hv_dynmem_device *dm);
#ifdef CONFIG_MEMORY_HOTPLUG
static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
@@ -562,7 +569,7 @@
struct hv_hotadd_state *has)
{
int ret = 0;
- int i, nid, t;
+ int i, nid;
unsigned long start_pfn;
unsigned long processed_pfn;
unsigned long total_pfn = pfn_count;
@@ -607,15 +614,12 @@
/*
* Wait for the memory block to be onlined.
+ * Since the hot add has succeeded, it is ok to
+ * proceed even if the pages in the hot added region
+ * have not been "onlined" within the allowed time.
*/
- t = wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
- if (t == 0) {
- pr_info("hot_add memory timedout\n");
- has->ha_end_pfn -= HA_CHUNK;
- has->covered_end_pfn -= processed_pfn;
- break;
- }
-
+ wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
+ post_status(&dm_device);
}
return;
@@ -954,11 +958,17 @@
{
struct dm_status status;
struct sysinfo val;
+ unsigned long now = jiffies;
+ unsigned long last_post = last_post_time;
if (pressure_report_delay > 0) {
--pressure_report_delay;
return;
}
+
+ if (!time_after(now, (last_post_time + HZ)))
+ return;
+
si_meminfo(&val);
memset(&status, 0, sizeof(struct dm_status));
status.hdr.type = DM_STATUS_REPORT;
@@ -978,6 +988,22 @@
dm->num_pages_ballooned +
compute_balloon_floor();
+ /*
+ * If our transaction ID is no longer current, just don't
+ * send the status. This can happen if we were interrupted
+ * after we picked our transaction ID.
+ */
+ if (status.hdr.trans_id != atomic_read(&trans_id))
+ return;
+
+ /*
+ * If the last post time that we sampled has changed,
+ * we have raced, don't post the status.
+ */
+ if (last_post != last_post_time)
+ return;
+
+ last_post_time = jiffies;
vmbus_sendpacket(dm->dev->channel, &status,
sizeof(struct dm_status),
(unsigned long)NULL,
@@ -1112,7 +1138,7 @@
if (ret == -EAGAIN)
msleep(20);
-
+ post_status(&dm_device);
} while (ret == -EAGAIN);
if (ret) {
@@ -1139,8 +1165,10 @@
struct dm_unballoon_response resp;
int i;
- for (i = 0; i < range_count; i++)
+ for (i = 0; i < range_count; i++) {
free_balloon_pages(dm, &range_array[i]);
+ post_status(&dm_device);
+ }
if (req->more_pages == 1)
return;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ed50e9e..0e8c1ea 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -111,6 +111,15 @@
kvp_respond_to_host(NULL, HV_E_FAIL);
}
+static void poll_channel(struct vmbus_channel *channel)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&channel->inbound_lock, flags);
+ hv_kvp_onchannelcallback(channel);
+ spin_unlock_irqrestore(&channel->inbound_lock, flags);
+}
+
static int kvp_handle_handshake(struct hv_kvp_msg *msg)
{
int ret = 1;
@@ -139,7 +148,7 @@
kvp_register(dm_reg_value);
kvp_transaction.active = false;
if (kvp_transaction.kvp_context)
- hv_kvp_onchannelcallback(kvp_transaction.kvp_context);
+ poll_channel(kvp_transaction.kvp_context);
}
return ret;
}
@@ -552,6 +561,7 @@
vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
VM_PKT_DATA_INBAND, 0);
+ poll_channel(channel);
}
@@ -585,7 +595,7 @@
return;
}
- vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
+ vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
&requestid);
if (recvlen > 0) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 2f561c5..64c778f 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -279,7 +279,7 @@
(struct hv_util_service *)dev_id->driver_data;
int ret;
- srv->recv_buffer = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
+ srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
if (!srv->recv_buffer)
return -ENOMEM;
if (srv->util_init) {
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index d6fbb577..791f45d 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -32,7 +32,7 @@
void hv_begin_read(struct hv_ring_buffer_info *rbi)
{
rbi->ring_buffer->interrupt_mask = 1;
- smp_mb();
+ mb();
}
u32 hv_end_read(struct hv_ring_buffer_info *rbi)
@@ -41,7 +41,7 @@
u32 write;
rbi->ring_buffer->interrupt_mask = 0;
- smp_mb();
+ mb();
/*
* Now check to see if the ring buffer is still empty.
@@ -71,7 +71,7 @@
static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi)
{
- smp_mb();
+ mb();
if (rbi->ring_buffer->interrupt_mask)
return false;
@@ -442,7 +442,7 @@
sizeof(u64));
/* Issue a full memory barrier before updating the write index */
- smp_mb();
+ mb();
/* Now, update the write location */
hv_set_next_write_location(outring_info, next_write_location);
@@ -549,7 +549,7 @@
/* Make sure all reads are done before we update the read index since */
/* the writer may start writing to the read area once the read index */
/*is updated */
- smp_mb();
+ mb();
/* Update the read index */
hv_set_next_read_location(inring_info, next_read_location);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index bf421e0..f445b08 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -434,7 +434,7 @@
* will not deliver any more messages since there is
* no empty slot
*/
- smp_mb();
+ mb();
if (msg->header.message_flags.msg_pending) {
/*
@@ -686,7 +686,7 @@
if (ret)
pr_err("Unable to register child device\n");
else
- pr_info("child device %s registered\n",
+ pr_debug("child device %s registered\n",
dev_name(&child_device_obj->device));
return ret;
@@ -698,14 +698,14 @@
*/
void vmbus_device_unregister(struct hv_device *device_obj)
{
+ pr_debug("child device %s unregistered\n",
+ dev_name(&device_obj->device));
+
/*
* Kick off the process of unregistering the device.
* This will call vmbus_remove() and eventually vmbus_device_release()
*/
device_unregister(&device_obj->device);
-
- pr_info("child device %s unregistered\n",
- dev_name(&device_obj->device));
}
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 0428e8a..f25f298 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -296,8 +296,8 @@
If you say yes here you get support for the temperature
sensor(s) inside your CPU. Supported are later revisions of
the AMD Family 10h and all revisions of the AMD Family 11h,
- 12h (Llano), 14h (Brazos) and 15h (Bulldozer/Trinity)
- microarchitectures.
+ 12h (Llano), 14h (Brazos), 15h (Bulldozer/Trinity) and
+ 16h (Kabini) microarchitectures.
This driver can also be built as a module. If so, the module
will be called k10temp.
@@ -944,7 +944,7 @@
config SENSORS_NTC_THERMISTOR
tristate "NTC thermistor support"
- depends on (!OF && !IIO) || (OF && IIO)
+ depends on !OF || IIO=n || IIO
help
This driver supports NTC thermistors sensor reading and its
interpretation. The driver can also monitor the temperature and
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index f920619..27ad7fb 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -185,7 +185,7 @@
struct i2c_client *client = to_i2c_client(dev);
struct adm1021_data *data = i2c_get_clientdata(client);
long temp;
- int err;
+ int reg_val, err;
err = kstrtol(buf, 10, &temp);
if (err)
@@ -193,10 +193,11 @@
temp /= 1000;
mutex_lock(&data->update_lock);
- data->temp_max[index] = clamp_val(temp, -128, 127);
+ reg_val = clamp_val(temp, -128, 127);
+ data->temp_max[index] = reg_val * 1000;
if (!read_only)
i2c_smbus_write_byte_data(client, ADM1021_REG_TOS_W(index),
- data->temp_max[index]);
+ reg_val);
mutex_unlock(&data->update_lock);
return count;
@@ -210,7 +211,7 @@
struct i2c_client *client = to_i2c_client(dev);
struct adm1021_data *data = i2c_get_clientdata(client);
long temp;
- int err;
+ int reg_val, err;
err = kstrtol(buf, 10, &temp);
if (err)
@@ -218,10 +219,11 @@
temp /= 1000;
mutex_lock(&data->update_lock);
- data->temp_min[index] = clamp_val(temp, -128, 127);
+ reg_val = clamp_val(temp, -128, 127);
+ data->temp_min[index] = reg_val * 1000;
if (!read_only)
i2c_smbus_write_byte_data(client, ADM1021_REG_THYST_W(index),
- data->temp_min[index]);
+ reg_val);
mutex_unlock(&data->update_lock);
return count;
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index 9ee5e06..39441e5 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -232,6 +232,9 @@
/* Update the value */
reg = (reg & 0x3F) | (val << 6);
+ /* Update the cache */
+ data->fan_div[attr->index] = reg;
+
/* Write value */
i2c_smbus_write_byte_data(client,
ADM1029_REG_FAN_DIV[attr->index], reg);
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index 253ea39..bdceca0 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -365,6 +365,7 @@
if (ret)
return ret;
+ val = clamp_val(val, 0, 127000);
mutex_lock(&data->update_lock);
data->auto_temp[nr] = AUTO_TEMP_MIN_TO_REG(val, data->auto_temp[nr]);
adm1031_write_value(client, ADM1031_REG_AUTO_TEMP(nr),
@@ -394,6 +395,7 @@
if (ret)
return ret;
+ val = clamp_val(val, 0, 127000);
mutex_lock(&data->update_lock);
data->temp_max[nr] = AUTO_TEMP_MAX_TO_REG(val, data->auto_temp[nr],
data->pwm[nr]);
@@ -696,7 +698,7 @@
if (ret)
return ret;
- val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+ val = clamp_val(val, -55000, 127000);
mutex_lock(&data->update_lock);
data->temp_min[nr] = TEMP_TO_REG(val);
adm1031_write_value(client, ADM1031_REG_TEMP_MIN(nr),
@@ -717,7 +719,7 @@
if (ret)
return ret;
- val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+ val = clamp_val(val, -55000, 127000);
mutex_lock(&data->update_lock);
data->temp_max[nr] = TEMP_TO_REG(val);
adm1031_write_value(client, ADM1031_REG_TEMP_MAX(nr),
@@ -738,7 +740,7 @@
if (ret)
return ret;
- val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+ val = clamp_val(val, -55000, 127000);
mutex_lock(&data->update_lock);
data->temp_crit[nr] = TEMP_TO_REG(val);
adm1031_write_value(client, ADM1031_REG_TEMP_CRIT(nr),
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 2798246..3930a7e 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -184,7 +184,7 @@
}
channel = be32_to_cpup(property);
- if (channel > ADS1015_CHANNELS) {
+ if (channel >= ADS1015_CHANNELS) {
dev_err(&client->dev,
"invalid channel index %d on %s\n",
channel, node->full_name);
@@ -198,6 +198,7 @@
dev_err(&client->dev,
"invalid gain on %s\n",
node->full_name);
+ return -EINVAL;
}
}
@@ -208,6 +209,7 @@
dev_err(&client->dev,
"invalid data_rate on %s\n",
node->full_name);
+ return -EINVAL;
}
}
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index b83bf4b..79610bd 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -215,7 +215,7 @@
u16 value)
{
return i2c_smbus_write_byte_data(client, reg, value & 0xFF)
- && i2c_smbus_write_byte_data(client, reg + 1, value >> 8);
+ || i2c_smbus_write_byte_data(client, reg + 1, value >> 8);
}
static void adt7470_init_client(struct i2c_client *client)
@@ -515,7 +515,7 @@
return -EINVAL;
temp = DIV_ROUND_CLOSEST(temp, 1000);
- temp = clamp_val(temp, 0, 255);
+ temp = clamp_val(temp, -128, 127);
mutex_lock(&data->lock);
data->temp_min[attr->index] = temp;
@@ -549,7 +549,7 @@
return -EINVAL;
temp = DIV_ROUND_CLOSEST(temp, 1000);
- temp = clamp_val(temp, 0, 255);
+ temp = clamp_val(temp, -128, 127);
mutex_lock(&data->lock);
data->temp_max[attr->index] = temp;
@@ -826,7 +826,7 @@
return -EINVAL;
temp = DIV_ROUND_CLOSEST(temp, 1000);
- temp = clamp_val(temp, 0, 255);
+ temp = clamp_val(temp, -128, 127);
mutex_lock(&data->lock);
data->pwm_tmin[attr->index] = temp;
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 4fe49d2..09d2d78 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -707,7 +707,7 @@
get_temp_alarm, NULL, IDX_TEMP1_MAX);
static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
get_temp_alarm, NULL, IDX_TEMP1_CRIT);
-static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO,
get_temp, NULL, IDX_TEMP2_INPUT);
static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp,
set_temp, IDX_TEMP2_MIN);
diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c
index 62c2e32..3288f13 100644
--- a/drivers/hwmon/applesmc.c
+++ b/drivers/hwmon/applesmc.c
@@ -230,6 +230,7 @@
static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len)
{
+ u8 status, data = 0;
int i;
if (send_command(cmd) || send_argument(key)) {
@@ -237,6 +238,7 @@
return -EIO;
}
+ /* This has no effect on newer (2012) SMCs */
if (send_byte(len, APPLESMC_DATA_PORT)) {
pr_warn("%.4s: read len fail\n", key);
return -EIO;
@@ -250,6 +252,17 @@
buffer[i] = inb(APPLESMC_DATA_PORT);
}
+ /* Read the data port until bit0 is cleared */
+ for (i = 0; i < 16; i++) {
+ udelay(APPLESMC_MIN_WAIT);
+ status = inb(APPLESMC_CMD_PORT);
+ if (!(status & 0x01))
+ break;
+ data = inb(APPLESMC_DATA_PORT);
+ }
+ if (i)
+ pr_warn("flushed %d bytes, last value is: %d\n", i, data);
+
return 0;
}
@@ -525,16 +538,25 @@
{
struct applesmc_registers *s = &smcreg;
bool left_light_sensor, right_light_sensor;
+ unsigned int count;
u8 tmp[1];
int ret;
if (s->init_complete)
return 0;
- ret = read_register_count(&s->key_count);
+ ret = read_register_count(&count);
if (ret)
return ret;
+ if (s->cache && s->key_count != count) {
+ pr_warn("key count changed from %d to %d\n",
+ s->key_count, count);
+ kfree(s->cache);
+ s->cache = NULL;
+ }
+ s->key_count = count;
+
if (!s->cache)
s->cache = kcalloc(s->key_count, sizeof(*s->cache), GFP_KERNEL);
if (!s->cache)
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 658ce3a..0cf2510 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -52,7 +52,7 @@
#define BASE_SYSFS_ATTR_NO 2 /* Sysfs Base attr no for coretemp */
#define NUM_REAL_CORES 32 /* Number of Real cores per cpu */
-#define CORETEMP_NAME_LENGTH 17 /* String Length of attrs */
+#define CORETEMP_NAME_LENGTH 19 /* String Length of attrs */
#define MAX_CORE_ATTRS 4 /* Maximum no of basic attrs */
#define TOTAL_ATTRS (MAX_CORE_ATTRS + 1)
#define MAX_CORE_DATA (NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 960fac3..48044b0 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -194,7 +194,7 @@
struct device_attribute *devattr,
char *buf)
{
- return sprintf(buf, "da9052-hwmon\n");
+ return sprintf(buf, "da9052\n");
}
static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 029ecab..1b275a2 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -204,7 +204,7 @@
struct device_attribute *devattr,
char *buf)
{
- return sprintf(buf, "da9055-hwmon\n");
+ return sprintf(buf, "da9055\n");
}
static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 4ae3fff1..bea0a34 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -247,8 +247,8 @@
u8 pwm_acz[3];
u8 pwm_freq[6];
u8 pwm_rr[2];
- u8 zone_low[3];
- u8 zone_abs[3];
+ s8 zone_low[3];
+ s8 zone_abs[3];
u8 zone_hyst[2];
u32 alarms;
};
@@ -277,7 +277,7 @@
return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2));
}
-static inline int IN_TO_REG(int val, int nominal)
+static inline int IN_TO_REG(long val, int nominal)
{
return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
}
@@ -293,7 +293,7 @@
return (reg * 1000) >> (res - 8);
}
-static inline int TEMP_TO_REG(int val)
+static inline int TEMP_TO_REG(long val)
{
return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
}
@@ -308,7 +308,7 @@
return TEMP_RANGE[(reg >> 4) & 0x0f];
}
-static int TEMP_RANGE_TO_REG(int val, int reg)
+static int TEMP_RANGE_TO_REG(long val, int reg)
{
int i;
@@ -331,7 +331,7 @@
return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
}
-static inline int TEMP_HYST_TO_REG(int val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
{
int hyst = clamp_val((val + 500) / 1000, 0, 15);
@@ -347,7 +347,7 @@
return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg;
}
-static inline int FAN_TO_REG(int val, int tpc)
+static inline int FAN_TO_REG(long val, int tpc)
{
if (tpc) {
return clamp_val(val / tpc, 0, 0xffff);
@@ -379,7 +379,7 @@
return (edge > 0) ? 1 << (edge - 1) : 0;
}
-static inline int FAN_TYPE_TO_REG(int val, int reg)
+static inline int FAN_TYPE_TO_REG(long val, int reg)
{
int edge = (val == 4) ? 3 : val;
@@ -402,7 +402,7 @@
return 1000 + i * 500;
}
-static int FAN_MAX_TO_REG(int val)
+static int FAN_MAX_TO_REG(long val)
{
int i;
@@ -460,7 +460,7 @@
return acz[(reg >> 5) & 0x07];
}
-static inline int PWM_ACZ_TO_REG(int val, int reg)
+static inline int PWM_ACZ_TO_REG(long val, int reg)
{
int acz = (val == 4) ? 2 : val - 1;
@@ -476,7 +476,7 @@
return PWM_FREQ[reg & 0x0f];
}
-static int PWM_FREQ_TO_REG(int val, int reg)
+static int PWM_FREQ_TO_REG(long val, int reg)
{
int i;
@@ -510,7 +510,7 @@
return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0;
}
-static int PWM_RR_TO_REG(int val, int ix, int reg)
+static int PWM_RR_TO_REG(long val, int ix, int reg)
{
int i;
@@ -528,7 +528,7 @@
return PWM_RR_FROM_REG(reg, ix) ? 1 : 0;
}
-static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg)
+static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg)
{
int en = (ix == 1) ? 0x80 : 0x08;
@@ -1481,13 +1481,16 @@
const char *buf, size_t count)
{
struct dme1737_data *data = dev_get_drvdata(dev);
- long val;
+ unsigned long val;
int err;
- err = kstrtol(buf, 10, &val);
+ err = kstrtoul(buf, 10, &val);
if (err)
return err;
+ if (val > 255)
+ return -EINVAL;
+
data->vrm = val;
return count;
}
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 142e1cb..361f50b 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -162,7 +162,7 @@
if (retval < 0)
goto fail;
- hyst = val - retval * 1000;
+ hyst = retval * 1000 - val;
hyst = DIV_ROUND_CLOSEST(hyst, 1000);
if (hyst < 0 || hyst > 255) {
retval = -ERANGE;
@@ -295,7 +295,7 @@
}
id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
- if (id != 0x01)
+ if (id < 0x01 || id > 0x04)
return -ENODEV;
return 0;
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 3104149..ce1d827 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -172,7 +172,7 @@
return -EINVAL;
}
-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm)
+static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
{
struct gpio_fan_speed *speed = fan_data->speed;
int i;
diff --git a/drivers/hwmon/hih6130.c b/drivers/hwmon/hih6130.c
index 2dc37c7..7d68a08 100644
--- a/drivers/hwmon/hih6130.c
+++ b/drivers/hwmon/hih6130.c
@@ -43,6 +43,7 @@
* @last_update: time of last update (jiffies)
* @temperature: cached temperature measurement value
* @humidity: cached humidity measurement value
+ * @write_length: length for I2C measurement request
*/
struct hih6130 {
struct device *hwmon_dev;
@@ -51,6 +52,7 @@
unsigned long last_update;
int temperature;
int humidity;
+ size_t write_length;
};
/**
@@ -121,8 +123,15 @@
*/
if (time_after(jiffies, hih6130->last_update + HZ) || !hih6130->valid) {
- /* write to slave address, no data, to request a measurement */
- ret = i2c_master_send(client, tmp, 0);
+ /*
+ * Write to slave address to request a measurement.
+ * According with the datasheet it should be with no data, but
+ * for systems with I2C bus drivers that do not allow zero
+ * length packets we write one dummy byte to allow sensor
+ * measurements on them.
+ */
+ tmp[0] = 0;
+ ret = i2c_master_send(client, tmp, hih6130->write_length);
if (ret < 0)
goto out;
@@ -252,6 +261,9 @@
goto fail_remove_sysfs;
}
+ if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_QUICK))
+ hih6130->write_length = 1;
+
return 0;
fail_remove_sysfs:
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 4958b2f..371c1ee 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -147,7 +147,8 @@
switch (reg) {
case INA2XX_SHUNT_VOLTAGE:
- val = DIV_ROUND_CLOSEST(data->regs[reg],
+ /* signed register */
+ val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
data->config->shunt_div);
break;
case INA2XX_BUS_VOLTAGE:
@@ -159,8 +160,8 @@
val = data->regs[reg] * data->config->power_lsb;
break;
case INA2XX_CURRENT:
- /* LSB=1mA (selected). Is in mA */
- val = data->regs[reg];
+ /* signed register, LSB=1mA (selected), in mA */
+ val = (s16)data->regs[reg];
break;
default:
/* programmer goofed */
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index e3b037c..9bcf175 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -1,5 +1,5 @@
/*
- * k10temp.c - AMD Family 10h/11h/12h/14h/15h processor hardware monitoring
+ * k10temp.c - AMD Family 10h/11h/12h/14h/15h/16h processor hardware monitoring
*
* Copyright (c) 2009 Clemens Ladisch <clemens@ladisch.de>
*
@@ -211,6 +211,8 @@
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
+ { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{}
};
MODULE_DEVICE_TABLE(pci, k10temp_id_table);
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index c03b490..1d3600a 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -27,6 +27,8 @@
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/thermal.h>
#include "lm75.h"
@@ -70,6 +72,7 @@
/* Each client has this additional data */
struct lm75_data {
struct device *hwmon_dev;
+ struct thermal_zone_device *tz;
struct mutex update_lock;
u8 orig_conf;
u8 resolution; /* In bits, between 9 and 12 */
@@ -90,22 +93,36 @@
/*-----------------------------------------------------------------------*/
+static inline long lm75_reg_to_mc(s16 temp, u8 resolution)
+{
+ return ((temp >> (16 - resolution)) * 1000) >> (resolution - 8);
+}
+
/* sysfs attributes for hwmon */
+static int lm75_read_temp(void *dev, long *temp)
+{
+ struct lm75_data *data = lm75_update_device(dev);
+
+ if (IS_ERR(data))
+ return PTR_ERR(data);
+
+ *temp = lm75_reg_to_mc(data->temp[0], data->resolution);
+
+ return 0;
+}
+
static ssize_t show_temp(struct device *dev, struct device_attribute *da,
char *buf)
{
struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
struct lm75_data *data = lm75_update_device(dev);
- long temp;
if (IS_ERR(data))
return PTR_ERR(data);
- temp = ((data->temp[attr->index] >> (16 - data->resolution)) * 1000)
- >> (data->resolution - 8);
-
- return sprintf(buf, "%ld\n", temp);
+ return sprintf(buf, "%ld\n", lm75_reg_to_mc(data->temp[attr->index],
+ data->resolution));
}
static ssize_t set_temp(struct device *dev, struct device_attribute *da,
@@ -271,6 +288,13 @@
goto exit_remove;
}
+ data->tz = thermal_zone_of_sensor_register(&client->dev,
+ 0,
+ &client->dev,
+ lm75_read_temp, NULL);
+ if (IS_ERR(data->tz))
+ data->tz = NULL;
+
dev_info(&client->dev, "%s: sensor '%s'\n",
dev_name(data->hwmon_dev), client->name);
@@ -285,6 +309,7 @@
{
struct lm75_data *data = i2c_get_clientdata(client);
+ thermal_zone_of_sensor_unregister(&client->dev, data->tz);
hwmon_device_unregister(data->hwmon_dev);
sysfs_remove_group(&client->dev.kobj, &lm75_group);
lm75_write_value(client, LM75_REG_CONF, data->orig_conf);
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 6cf6bff..b879427 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -94,6 +94,8 @@
{
if (rpm <= 0)
return 255;
+ if (rpm > 1350000)
+ return 1;
return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254);
}
@@ -106,7 +108,7 @@
* TEMP: mC (-128C to +127C)
* REG: 1C/bit, two's complement
*/
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
{
int nval = clamp_val(val, -128000, 127000) ;
return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000;
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 3894c40..b9d6e7d 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -158,7 +158,7 @@
/* Temperature is reported in .001 degC increments */
#define TEMP_TO_REG(val) \
- clamp_val(SCALE(val, 1000, 1), -127, 127)
+ DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000)
#define TEMPEXT_FROM_REG(val, ext) \
SCALE(((val) << 4) + (ext), 16, 1000)
#define TEMP_FROM_REG(val) ((val) * 1000)
@@ -192,7 +192,7 @@
13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000
};
-static int RANGE_TO_REG(int range)
+static int RANGE_TO_REG(long range)
{
int i;
@@ -214,7 +214,7 @@
11, 15, 22, 29, 35, 44, 59, 88
};
-static int FREQ_TO_REG(const int *map, int freq)
+static int FREQ_TO_REG(const int *map, unsigned long freq)
{
int i;
@@ -463,6 +463,9 @@
if (err)
return err;
+ if (val > 255)
+ return -EINVAL;
+
data->vrm = val;
return count;
}
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 8eeb141..7481313 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -278,7 +278,7 @@
[max6696] = {
.flags = LM90_HAVE_EMERGENCY
| LM90_HAVE_EMERGENCY_ALARM | LM90_HAVE_TEMP3,
- .alert_alarms = 0x187c,
+ .alert_alarms = 0x1c7c,
.max_convrate = 6,
.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
},
@@ -1500,19 +1500,22 @@
if ((alarms & 0x7f) == 0 && (alarms2 & 0xfe) == 0) {
dev_info(&client->dev, "Everything OK\n");
} else {
- if (alarms & 0x61)
+ if ((alarms & 0x61) || (alarms2 & 0x80))
dev_warn(&client->dev,
"temp%d out of range, please check!\n", 1);
- if (alarms & 0x1a)
+ if ((alarms & 0x1a) || (alarms2 & 0x20))
dev_warn(&client->dev,
"temp%d out of range, please check!\n", 2);
if (alarms & 0x04)
dev_warn(&client->dev,
"temp%d diode open, please check!\n", 2);
- if (alarms2 & 0x18)
+ if (alarms2 & 0x5a)
dev_warn(&client->dev,
"temp%d out of range, please check!\n", 3);
+ if (alarms2 & 0x04)
+ dev_warn(&client->dev,
+ "temp%d diode open, please check!\n", 3);
/*
* Disable ALERT# output, because these chips don't implement
diff --git a/drivers/hwmon/max1668.c b/drivers/hwmon/max1668.c
index a762635..029b65e 100644
--- a/drivers/hwmon/max1668.c
+++ b/drivers/hwmon/max1668.c
@@ -243,7 +243,7 @@
data->temp_min[index] = clamp_val(temp/1000, -128, 127);
if (i2c_smbus_write_byte_data(client,
MAX1668_REG_LIML_WR(index),
- data->temp_max[index]))
+ data->temp_min[index]))
count = -EIO;
mutex_unlock(&data->update_lock);
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index 328fb03..a41b5f3 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -605,12 +605,12 @@
if (ret < 0)
return ret;
ret = i2c_smbus_write_byte_data(client, MAX6581_REG_IDEALITY,
- pdata->ideality_mask >> 1);
+ pdata->ideality_value);
if (ret < 0)
return ret;
ret = i2c_smbus_write_byte_data(client,
MAX6581_REG_IDEALITY_SELECT,
- pdata->ideality_value);
+ pdata->ideality_mask >> 1);
if (ret < 0)
return ret;
}
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 04638ae..99cec18 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -199,7 +199,7 @@
0, 1, 2, 3, 8, 21, 20, 16, /* in0.. in7 */
17, -1, -1, -1, -1, -1, -1, /* in8..in14 */
-1, /* unused */
- 6, 7, 11, 10, 23, /* fan1..fan5 */
+ 6, 7, 11, -1, -1, /* fan1..fan5 */
-1, -1, -1, /* unused */
4, 5, 13, -1, -1, -1, /* temp1..temp6 */
12, -1 }; /* intrusion0, intrusion1 */
@@ -625,6 +625,7 @@
u8 has_fan_min; /* some fans don't have min register */
bool has_fan_div;
+ u8 num_temp_alarms; /* 2 or 3 */
u8 temp_fixed_num; /* 3 or 6 */
u8 temp_type[NUM_TEMP_FIXED];
s8 temp_offset[NUM_TEMP_FIXED];
@@ -1193,6 +1194,42 @@
(unsigned int)((data->alarms >> nr) & 0x01));
}
+static int find_temp_source(struct nct6775_data *data, int index, int count)
+{
+ int source = data->temp_src[index];
+ int nr;
+
+ for (nr = 0; nr < count; nr++) {
+ int src;
+
+ src = nct6775_read_value(data,
+ data->REG_TEMP_SOURCE[nr]) & 0x1f;
+ if (src == source)
+ return nr;
+ }
+ return -1;
+}
+
+static ssize_t
+show_temp_alarm(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct sensor_device_attribute *sattr = to_sensor_dev_attr(attr);
+ struct nct6775_data *data = nct6775_update_device(dev);
+ unsigned int alarm = 0;
+ int nr;
+
+ /*
+ * For temperatures, there is no fixed mapping from registers to alarm
+ * bits. Alarm bits are determined by the temperature source mapping.
+ */
+ nr = find_temp_source(data, sattr->index, data->num_temp_alarms);
+ if (nr >= 0) {
+ int bit = data->ALARM_BITS[nr + TEMP_ALARM_BASE];
+ alarm = (data->alarms >> bit) & 0x01;
+ }
+ return sprintf(buf, "%u\n", alarm);
+}
+
static SENSOR_DEVICE_ATTR_2(in0_input, S_IRUGO, show_in_reg, NULL, 0, 0);
static SENSOR_DEVICE_ATTR_2(in1_input, S_IRUGO, show_in_reg, NULL, 1, 0);
static SENSOR_DEVICE_ATTR_2(in2_input, S_IRUGO, show_in_reg, NULL, 2, 0);
@@ -1874,22 +1911,18 @@
};
static struct sensor_device_attribute sda_temp_alarm[] = {
- SENSOR_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE),
- SENSOR_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE + 1),
- SENSOR_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE + 2),
- SENSOR_ATTR(temp4_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE + 3),
- SENSOR_ATTR(temp5_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE + 4),
- SENSOR_ATTR(temp6_alarm, S_IRUGO, show_alarm, NULL,
- TEMP_ALARM_BASE + 5),
+ SENSOR_ATTR(temp1_alarm, S_IRUGO, show_temp_alarm, NULL, 0),
+ SENSOR_ATTR(temp2_alarm, S_IRUGO, show_temp_alarm, NULL, 1),
+ SENSOR_ATTR(temp3_alarm, S_IRUGO, show_temp_alarm, NULL, 2),
+ SENSOR_ATTR(temp4_alarm, S_IRUGO, show_temp_alarm, NULL, 3),
+ SENSOR_ATTR(temp5_alarm, S_IRUGO, show_temp_alarm, NULL, 4),
+ SENSOR_ATTR(temp6_alarm, S_IRUGO, show_temp_alarm, NULL, 5),
+ SENSOR_ATTR(temp7_alarm, S_IRUGO, show_temp_alarm, NULL, 6),
+ SENSOR_ATTR(temp8_alarm, S_IRUGO, show_temp_alarm, NULL, 7),
+ SENSOR_ATTR(temp9_alarm, S_IRUGO, show_temp_alarm, NULL, 8),
+ SENSOR_ATTR(temp10_alarm, S_IRUGO, show_temp_alarm, NULL, 9),
};
-#define NUM_TEMP_ALARM ARRAY_SIZE(sda_temp_alarm)
-
static ssize_t
show_pwm_mode(struct device *dev, struct device_attribute *attr, char *buf)
{
@@ -3215,13 +3248,11 @@
device_remove_file(dev, &sda_temp_max[i].dev_attr);
device_remove_file(dev, &sda_temp_max_hyst[i].dev_attr);
device_remove_file(dev, &sda_temp_crit[i].dev_attr);
+ device_remove_file(dev, &sda_temp_alarm[i].dev_attr);
if (!(data->have_temp_fixed & (1 << i)))
continue;
device_remove_file(dev, &sda_temp_type[i].dev_attr);
device_remove_file(dev, &sda_temp_offset[i].dev_attr);
- if (i >= NUM_TEMP_ALARM)
- continue;
- device_remove_file(dev, &sda_temp_alarm[i].dev_attr);
}
device_remove_file(dev, &sda_caseopen[0].dev_attr);
@@ -3419,6 +3450,7 @@
data->auto_pwm_num = 6;
data->has_fan_div = true;
data->temp_fixed_num = 3;
+ data->num_temp_alarms = 3;
data->ALARM_BITS = NCT6775_ALARM_BITS;
@@ -3483,6 +3515,7 @@
data->auto_pwm_num = 4;
data->has_fan_div = false;
data->temp_fixed_num = 3;
+ data->num_temp_alarms = 3;
data->ALARM_BITS = NCT6776_ALARM_BITS;
@@ -3547,6 +3580,7 @@
data->auto_pwm_num = 4;
data->has_fan_div = false;
data->temp_fixed_num = 6;
+ data->num_temp_alarms = 2;
data->ALARM_BITS = NCT6779_ALARM_BITS;
@@ -3843,10 +3877,12 @@
&sda_fan_input[i].dev_attr);
if (err)
goto exit_remove;
- err = device_create_file(dev,
- &sda_fan_alarm[i].dev_attr);
- if (err)
- goto exit_remove;
+ if (data->ALARM_BITS[FAN_ALARM_BASE + i] >= 0) {
+ err = device_create_file(dev,
+ &sda_fan_alarm[i].dev_attr);
+ if (err)
+ goto exit_remove;
+ }
if (data->kind != nct6776 &&
data->kind != nct6779) {
err = device_create_file(dev,
@@ -3897,6 +3933,12 @@
if (err)
goto exit_remove;
}
+ if (find_temp_source(data, i, data->num_temp_alarms) >= 0) {
+ err = device_create_file(dev,
+ &sda_temp_alarm[i].dev_attr);
+ if (err)
+ goto exit_remove;
+ }
if (!(data->have_temp_fixed & (1 << i)))
continue;
err = device_create_file(dev, &sda_temp_type[i].dev_attr);
@@ -3905,12 +3947,6 @@
err = device_create_file(dev, &sda_temp_offset[i].dev_attr);
if (err)
goto exit_remove;
- if (i >= NUM_TEMP_ALARM ||
- data->ALARM_BITS[TEMP_ALARM_BASE + i] < 0)
- continue;
- err = device_create_file(dev, &sda_temp_alarm[i].dev_attr);
- if (err)
- goto exit_remove;
}
for (i = 0; i < ARRAY_SIZE(sda_caseopen); i++) {
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index d6d640a..c64d3d4 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -44,6 +44,7 @@
unsigned int ohm;
};
+/* Order matters, ntc_match references the entries by index */
static const struct platform_device_id ntc_thermistor_id[] = {
{ "ncp15wb473", TYPE_NCPXXWB473 },
{ "ncp18wb473", TYPE_NCPXXWB473 },
@@ -141,11 +142,11 @@
char name[PLATFORM_NAME_SIZE];
};
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
{
struct iio_channel *channel = pdata->chan;
- unsigned int result;
+ s64 result;
int val, ret;
ret = iio_read_channel_raw(channel, &val);
@@ -155,23 +156,23 @@
}
/* unit: mV */
- result = pdata->pullup_uv * val;
+ result = pdata->pullup_uv * (s64) val;
result >>= 12;
- return result;
+ return (int)result;
}
static const struct of_device_id ntc_match[] = {
{ .compatible = "ntc,ncp15wb473",
- .data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+ .data = &ntc_thermistor_id[0] },
{ .compatible = "ntc,ncp18wb473",
- .data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+ .data = &ntc_thermistor_id[1] },
{ .compatible = "ntc,ncp21wb473",
- .data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+ .data = &ntc_thermistor_id[2] },
{ .compatible = "ntc,ncp03wb473",
- .data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+ .data = &ntc_thermistor_id[3] },
{ .compatible = "ntc,ncp15wl333",
- .data = &ntc_thermistor_id[TYPE_NCPXXWL333] },
+ .data = &ntc_thermistor_id[4] },
{ },
};
MODULE_DEVICE_TABLE(of, ntc_match);
@@ -223,6 +224,8 @@
return NULL;
}
+#define ntc_match NULL
+
static void ntc_iio_channel_release(struct ntc_thermistor_platform_data *pdata)
{ }
#endif
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 1404e63..9ec7d2e 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -141,6 +141,8 @@
{
if (rpm <= 0)
return 255;
+ if (rpm > 1350000)
+ return 1;
return clamp_val((1350000 + rpm * div / 2) / (rpm * div), 1, 254);
}
@@ -157,7 +159,7 @@
{
return val * 830 + 52120;
}
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
{
int nval = clamp_val(val, -54120, 157530) ;
return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830;
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index efee4c5..34b9a60 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -86,7 +86,7 @@
*/
static inline s8 TEMP_TO_REG(int val)
{
- return clamp_val(SCALE(val, 1, 1000), -128000, 127000);
+ return SCALE(clamp_val(val, -128000, 127000), 1, 1000);
}
static inline int TEMP_FROM_REG(s8 val)
@@ -384,6 +384,8 @@
err = kstrtoul(buf, 10, &val);
if (err)
return err;
+ if (val > 255)
+ return -EINVAL;
data->vrm = val;
return count;
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index d7b47ab..6748b45 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -27,6 +27,8 @@
#include <linux/mutex.h>
#include <linux/device.h>
#include <linux/jiffies.h>
+#include <linux/thermal.h>
+#include <linux/of.h>
#define DRIVER_NAME "tmp102"
@@ -50,6 +52,7 @@
struct tmp102 {
struct device *hwmon_dev;
+ struct thermal_zone_device *tz;
struct mutex lock;
u16 config_orig;
unsigned long last_update;
@@ -93,6 +96,15 @@
return tmp102;
}
+static int tmp102_read_temp(void *dev, long *temp)
+{
+ struct tmp102 *tmp102 = tmp102_update_device(to_i2c_client(dev));
+
+ *temp = tmp102->temp[0];
+
+ return 0;
+}
+
static ssize_t tmp102_show_temp(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -204,6 +216,12 @@
goto fail_remove_sysfs;
}
+ tmp102->tz = thermal_zone_of_sensor_register(&client->dev, 0,
+ &client->dev,
+ tmp102_read_temp, NULL);
+ if (IS_ERR(tmp102->tz))
+ tmp102->tz = NULL;
+
dev_info(&client->dev, "initialized\n");
return 0;
@@ -220,6 +238,7 @@
{
struct tmp102 *tmp102 = i2c_get_clientdata(client);
+ thermal_zone_of_sensor_unregister(&client->dev, tmp102->tz);
hwmon_device_unregister(tmp102->hwmon_dev);
sysfs_remove_group(&client->dev.kobj, &tmp102_attr_group);
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index 0e70178..aee14e2 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -145,7 +145,7 @@
*/
static inline u8 FAN_TO_REG(long rpm, int div)
{
- if (rpm == 0)
+ if (rpm <= 0 || rpm > 1310720)
return 0;
return clamp_val(1310720 / (rpm * div), 1, 255);
}
diff --git a/drivers/hwmon/w83l786ng.c b/drivers/hwmon/w83l786ng.c
index edb06cd..6ed76ce 100644
--- a/drivers/hwmon/w83l786ng.c
+++ b/drivers/hwmon/w83l786ng.c
@@ -481,9 +481,11 @@
if (err)
return err;
val = clamp_val(val, 0, 255);
+ val = DIV_ROUND_CLOSEST(val, 0x11);
mutex_lock(&data->update_lock);
- data->pwm[nr] = val;
+ data->pwm[nr] = val * 0x11;
+ val |= w83l786ng_read_value(client, W83L786NG_REG_PWM[nr]) & 0xf0;
w83l786ng_write_value(client, W83L786NG_REG_PWM[nr], val);
mutex_unlock(&data->update_lock);
return count;
@@ -510,7 +512,7 @@
mutex_lock(&data->update_lock);
reg = w83l786ng_read_value(client, W83L786NG_REG_FAN_CFG);
data->pwm_enable[nr] = val;
- reg &= ~(0x02 << W83L786NG_PWM_ENABLE_SHIFT[nr]);
+ reg &= ~(0x03 << W83L786NG_PWM_ENABLE_SHIFT[nr]);
reg |= (val - 1) << W83L786NG_PWM_ENABLE_SHIFT[nr];
w83l786ng_write_value(client, W83L786NG_REG_FAN_CFG, reg);
mutex_unlock(&data->update_lock);
@@ -776,9 +778,10 @@
((pwmcfg >> W83L786NG_PWM_MODE_SHIFT[i]) & 1)
? 0 : 1;
data->pwm_enable[i] =
- ((pwmcfg >> W83L786NG_PWM_ENABLE_SHIFT[i]) & 2) + 1;
- data->pwm[i] = w83l786ng_read_value(client,
- W83L786NG_REG_PWM[i]);
+ ((pwmcfg >> W83L786NG_PWM_ENABLE_SHIFT[i]) & 3) + 1;
+ data->pwm[i] =
+ (w83l786ng_read_value(client, W83L786NG_REG_PWM[i])
+ & 0x0f) * 0x11;
}
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 631736e..d4fe13e 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -108,6 +108,9 @@
Lynx Point-LP (PCH)
Avoton (SOC)
Wellsburg (PCH)
+ Coleto Creek (PCH)
+ Wildcat Point-LP (PCH)
+ BayTrail (SOC)
This driver can also be built as a module. If so, the module
will be called i2c-i801.
@@ -150,6 +153,7 @@
ATI SB700/SP5100
ATI SB800
AMD Hudson-2
+ AMD CZ
Serverworks OSB4
Serverworks CSB5
Serverworks CSB6
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 6bb839b..09324d0 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -102,6 +102,7 @@
unsigned twi_cwgr_reg;
struct at91_twi_pdata *pdata;
bool use_dma;
+ bool recv_len_abort;
struct at91_twi_dma dma;
};
@@ -211,7 +212,7 @@
struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
- dev->buf_len, DMA_MEM_TO_DEV);
+ dev->buf_len, DMA_TO_DEVICE);
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
}
@@ -268,12 +269,24 @@
*dev->buf = at91_twi_read(dev, AT91_TWI_RHR) & 0xff;
--dev->buf_len;
+ /* return if aborting, we only needed to read RHR to clear RXRDY*/
+ if (dev->recv_len_abort)
+ return;
+
/* handle I2C_SMBUS_BLOCK_DATA */
if (unlikely(dev->msg->flags & I2C_M_RECV_LEN)) {
- dev->msg->flags &= ~I2C_M_RECV_LEN;
- dev->buf_len += *dev->buf;
- dev->msg->len = dev->buf_len + 1;
- dev_dbg(dev->dev, "received block length %d\n", dev->buf_len);
+ /* ensure length byte is a valid value */
+ if (*dev->buf <= I2C_SMBUS_BLOCK_MAX && *dev->buf > 0) {
+ dev->msg->flags &= ~I2C_M_RECV_LEN;
+ dev->buf_len += *dev->buf;
+ dev->msg->len = dev->buf_len + 1;
+ dev_dbg(dev->dev, "received block length %d\n",
+ dev->buf_len);
+ } else {
+ /* abort and send the stop by reading one more byte */
+ dev->recv_len_abort = true;
+ dev->buf_len = 1;
+ }
}
/* send stop if second but last byte has been read */
@@ -290,7 +303,7 @@
struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
- dev->buf_len, DMA_DEV_TO_MEM);
+ dev->buf_len, DMA_FROM_DEVICE);
/* The last two bytes have to be read without using dma */
dev->buf += dev->buf_len - 2;
@@ -422,8 +435,8 @@
}
}
- ret = wait_for_completion_interruptible_timeout(&dev->cmd_complete,
- dev->adapter.timeout);
+ ret = wait_for_completion_timeout(&dev->cmd_complete,
+ dev->adapter.timeout);
if (ret == 0) {
dev_err(dev->dev, "controller timed out\n");
at91_init_twi_bus(dev);
@@ -445,6 +458,12 @@
ret = -EIO;
goto error;
}
+ if (dev->recv_len_abort) {
+ dev_err(dev->dev, "invalid smbus block length recvd\n");
+ ret = -EPROTO;
+ goto error;
+ }
+
dev_dbg(dev->dev, "transfer complete\n");
return 0;
@@ -501,6 +520,7 @@
dev->buf_len = m_start->len;
dev->buf = m_start->buf;
dev->msg = m_start;
+ dev->recv_len_abort = false;
ret = at91_do_twi_transfer(dev);
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index cf20e06..09f29e9 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -414,11 +414,9 @@
if (dev->cmd_err & DAVINCI_I2C_STR_NACK) {
if (msg->flags & I2C_M_IGNORE_NAK)
return msg->len;
- if (stop) {
- w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
- w |= DAVINCI_I2C_MDR_STP;
- davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
- }
+ w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG);
+ w |= DAVINCI_I2C_MDR_STP;
+ davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w);
return -EREMOTEIO;
}
return -EIO;
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index c41ca63..f24a738 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -380,6 +380,9 @@
ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
dw_writel(dev, ic_con, DW_IC_CON);
+ /* enforce disabled interrupts (due to HW issues) */
+ i2c_dw_disable_int(dev);
+
/* Enable the adapter */
__i2c_dw_enable(dev, true);
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 3a6903f..783fa75 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -58,6 +58,9 @@
Wellsburg (PCH) MS 0x8d7d 32 hard yes yes yes
Wellsburg (PCH) MS 0x8d7e 32 hard yes yes yes
Wellsburg (PCH) MS 0x8d7f 32 hard yes yes yes
+ Coleto Creek (PCH) 0x23b0 32 hard yes yes yes
+ Wildcat Point-LP (PCH) 0x9ca2 32 hard yes yes yes
+ BayTrail (SOC) 0x0f12 32 hard yes yes yes
Features supported by this driver:
Software PEC no
@@ -160,6 +163,7 @@
STATUS_ERROR_FLAGS)
/* Older devices have their ID defined in <linux/pci_ids.h> */
+#define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS 0x0f12
#define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS 0x1c22
#define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22
/* Patsburg also has three 'Integrated Device Function' SMBus controllers */
@@ -169,6 +173,7 @@
#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_SMBUS 0x1e22
#define PCI_DEVICE_ID_INTEL_AVOTON_SMBUS 0x1f3c
#define PCI_DEVICE_ID_INTEL_DH89XXCC_SMBUS 0x2330
+#define PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS 0x23b0
#define PCI_DEVICE_ID_INTEL_5_3400_SERIES_SMBUS 0x3b30
#define PCI_DEVICE_ID_INTEL_LYNXPOINT_SMBUS 0x8c22
#define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS 0x8d22
@@ -176,6 +181,7 @@
#define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS1 0x8d7e
#define PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2 0x8d7f
#define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_SMBUS 0x9c22
+#define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS 0x9ca2
struct i801_mux_config {
char *gpio_chip;
@@ -817,6 +823,9 @@
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS0) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS1) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WELLSBURG_SMBUS_MS2) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COLETOCREEK_SMBUS) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_SMBUS) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS) },
{ 0, }
};
diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c
index cd82eb4..7c9f053 100644
--- a/drivers/i2c/busses/i2c-ismt.c
+++ b/drivers/i2c/busses/i2c-ismt.c
@@ -393,6 +393,9 @@
desc = &priv->hw[priv->head];
+ /* Initialize the DMA buffer */
+ memset(priv->dma_buffer, 0, sizeof(priv->dma_buffer));
+
/* Initialize the descriptor */
memset(desc, 0, sizeof(struct ismt_desc));
desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, read_write);
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index 2039f23..6d8094d 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -494,7 +494,7 @@
* based on this empirical measurement and a lot of previous frobbing.
*/
i2c->cmd_err = 0;
- if (msg->len < 8) {
+ if (0) { /* disable PIO mode until a proper fix is made */
ret = mxs_i2c_pio_setup_xfer(adap, msg, flags);
if (ret)
mxs_i2c_reset(i2c);
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index e02f9e3..7645924 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -928,19 +928,20 @@
if (stat & OMAP_I2C_STAT_NACK) {
err |= OMAP_I2C_STAT_NACK;
omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK);
- break;
}
if (stat & OMAP_I2C_STAT_AL) {
dev_err(dev->dev, "Arbitration lost\n");
err |= OMAP_I2C_STAT_AL;
omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL);
- break;
}
/*
* ProDB0017052: Clear ARDY bit twice
*/
+ if (stat & OMAP_I2C_STAT_ARDY)
+ omap_i2c_ack_stat(dev, OMAP_I2C_STAT_ARDY);
+
if (stat & (OMAP_I2C_STAT_ARDY | OMAP_I2C_STAT_NACK |
OMAP_I2C_STAT_AL)) {
omap_i2c_ack_stat(dev, (OMAP_I2C_STAT_RRDY |
@@ -957,11 +958,13 @@
if (dev->fifo_size)
num_bytes = dev->buf_len;
- omap_i2c_receive_data(dev, num_bytes, true);
-
- if (dev->errata & I2C_OMAP_ERRATA_I207)
+ if (dev->errata & I2C_OMAP_ERRATA_I207) {
i2c_omap_errata_i207(dev, stat);
+ num_bytes = (omap_i2c_read_reg(dev,
+ OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F;
+ }
+ omap_i2c_receive_data(dev, num_bytes, true);
omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR);
continue;
}
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 39ab78c..d05ad59 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -22,7 +22,7 @@
Intel PIIX4, 440MX
Serverworks OSB4, CSB5, CSB6, HT-1000, HT-1100
ATI IXP200, IXP300, IXP400, SB600, SB700/SP5100, SB800
- AMD Hudson-2
+ AMD Hudson-2, CZ
SMSC Victory66
Note: we assume there can only be one device, with one or more
@@ -522,6 +522,7 @@
{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS) },
{ PCI_DEVICE(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SMBUS) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x790b) },
{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
PCI_DEVICE_ID_SERVERWORKS_OSB4) },
{ PCI_DEVICE(PCI_VENDOR_ID_SERVERWORKS,
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 4ba4a95..8a806f5c 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -541,6 +541,12 @@
ret = -EINVAL;
for (i = 0; i < num; i++) {
+ /* This HW can't send STOP after address phase */
+ if (msgs[i].len == 0) {
+ ret = -EOPNOTSUPP;
+ break;
+ }
+
/*-------------- spin lock -----------------*/
spin_lock_irqsave(&priv->lock, flags);
@@ -605,7 +611,8 @@
static u32 rcar_i2c_func(struct i2c_adapter *adap)
{
- return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+ /* This HW can't do SMBUS_QUICK and NOSTART */
+ return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
}
static const struct i2c_algorithm rcar_i2c_algo = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index cab1c91..a72aad9 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1204,10 +1204,10 @@
struct platform_device *pdev = to_platform_device(dev);
struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
- i2c->suspended = 0;
clk_prepare_enable(i2c->clk);
s3c24xx_i2c_init(i2c);
clk_disable_unprepare(i2c->clk);
+ i2c->suspended = 0;
return 0;
}
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 48e31ed..c12299f 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -23,7 +23,11 @@
SMBus 2.0 support by Mark Studebaker <mdsxyz123@yahoo.com> and
Jean Delvare <khali@linux-fr.org>
Mux support by Rodolfo Giometti <giometti@enneenne.com> and
- Michael Lawnick <michael.lawnick.ext@nsn.com> */
+ Michael Lawnick <michael.lawnick.ext@nsn.com>
+ OF support is copyright (c) 2008 Jochen Friedrich <jochen@scram.de>
+ (based on a previous patch from Jon Smirl <jonsmirl@gmail.com>) and
+ (c) 2013 Wolfram Sang <wsa@the-dreams.de>
+ */
#include <linux/module.h>
#include <linux/kernel.h>
@@ -35,7 +39,9 @@
#include <linux/init.h>
#include <linux/idr.h>
#include <linux/mutex.h>
+#include <linux/of.h>
#include <linux/of_device.h>
+#include <linux/of_irq.h>
#include <linux/completion.h>
#include <linux/hardirq.h>
#include <linux/irqflags.h>
@@ -43,6 +49,7 @@
#include <linux/pm_runtime.h>
#include <linux/acpi.h>
#include <asm/uaccess.h>
+#include <linux/err.h>
#include "i2c-core.h"
@@ -206,6 +213,7 @@
adap->bus_recovery_info->set_scl(adap, 1);
return i2c_generic_recovery(adap);
}
+EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery);
int i2c_generic_gpio_recovery(struct i2c_adapter *adap)
{
@@ -220,6 +228,7 @@
return ret;
}
+EXPORT_SYMBOL_GPL(i2c_generic_gpio_recovery);
int i2c_recover_bus(struct i2c_adapter *adap)
{
@@ -229,6 +238,7 @@
dev_dbg(&adap->dev, "Trying i2c bus recovery\n");
return adap->bus_recovery_info->recover_bus(adap);
}
+EXPORT_SYMBOL_GPL(i2c_recover_bus);
static int i2c_device_probe(struct device *dev)
{
@@ -697,6 +707,10 @@
*/
void i2c_unregister_device(struct i2c_client *client)
{
+#if IS_ENABLED(CONFIG_OF_DYNAMIC)
+ if (client->dev.of_node)
+ of_node_clear_flag(client->dev.of_node, OF_POPULATED);
+#endif
device_unregister(&client->dev);
}
EXPORT_SYMBOL_GPL(i2c_unregister_device);
@@ -954,6 +968,113 @@
up_read(&__i2c_board_lock);
}
+/* OF support code */
+
+#if IS_ENABLED(CONFIG_OF)
+static struct i2c_client *of_i2c_register_device(struct i2c_adapter *adap,
+ struct device_node *node)
+{
+ struct i2c_client *result;
+ struct i2c_board_info info = {};
+ struct dev_archdata dev_ad = {};
+ const __be32 *addr;
+ int len;
+
+ dev_dbg(&adap->dev, "of_i2c: register %s\n", node->full_name);
+
+ if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) {
+ dev_err(&adap->dev, "of_i2c: modalias failure on %s\n",
+ node->full_name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ addr = of_get_property(node, "reg", &len);
+ if (!addr || (len < sizeof(int))) {
+ dev_err(&adap->dev, "of_i2c: invalid reg on %s\n",
+ node->full_name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ info.addr = be32_to_cpup(addr);
+ if (info.addr > (1 << 10) - 1) {
+ dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n",
+ info.addr, node->full_name);
+ return ERR_PTR(-EINVAL);
+ }
+
+ info.irq = irq_of_parse_and_map(node, 0);
+ info.of_node = of_node_get(node);
+ info.archdata = &dev_ad;
+
+ if (of_get_property(node, "wakeup-source", NULL))
+ info.flags |= I2C_CLIENT_WAKE;
+
+ request_module("%s%s", I2C_MODULE_PREFIX, info.type);
+
+ result = i2c_new_device(adap, &info);
+ if (result == NULL) {
+ dev_err(&adap->dev, "of_i2c: Failure registering %s\n",
+ node->full_name);
+ of_node_put(node);
+ irq_dispose_mapping(info.irq);
+ return ERR_PTR(-EINVAL);
+ }
+ return result;
+}
+
+static void internal_of_i2c_register_devices(struct i2c_adapter *adap)
+{
+ struct device_node *node;
+
+ /* Only register child devices if the adapter has a node pointer set */
+ if (!adap->dev.of_node)
+ return;
+
+ dev_dbg(&adap->dev, "of_i2c: walking child nodes\n");
+
+ for_each_available_child_of_node(adap->dev.of_node, node) {
+ if (of_node_test_and_set_flag(node, OF_POPULATED))
+ continue;
+ of_i2c_register_device(adap, node);
+ }
+}
+
+static int of_dev_node_match(struct device *dev, void *data)
+{
+ return dev->of_node == data;
+}
+
+/* must call put_device() when done with returned i2c_client device */
+struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
+{
+ struct device *dev;
+
+ dev = bus_find_device(&i2c_bus_type, NULL, node,
+ of_dev_node_match);
+ if (!dev)
+ return NULL;
+
+ return i2c_verify_client(dev);
+}
+EXPORT_SYMBOL(of_find_i2c_device_by_node);
+
+/* must call put_device() when done with returned i2c_adapter device */
+struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node)
+{
+ struct device *dev;
+
+ dev = bus_find_device(&i2c_bus_type, NULL, node,
+ of_dev_node_match);
+ if (!dev)
+ return NULL;
+
+ return i2c_verify_adapter(dev);
+}
+EXPORT_SYMBOL(of_find_i2c_adapter_by_node);
+#else
+static void internal_of_i2c_register_devices(struct i2c_adapter *adap) { }
+#endif /* CONFIG_OF */
+
static int i2c_do_add_adapter(struct i2c_driver *driver,
struct i2c_adapter *adap)
{
@@ -1058,6 +1179,8 @@
exit_recovery:
/* create pre-declared device nodes */
+ internal_of_i2c_register_devices(adap);
+
if (adap->nr < __i2c_first_dynamic_bus_num)
i2c_scan_static_board_info(adap);
@@ -1282,7 +1405,6 @@
}
EXPORT_SYMBOL(i2c_del_adapter);
-
/* ------------------------------------------------------------------------- */
int i2c_for_each_dev(void *data, int (*fn)(struct device *, void *))
@@ -1426,6 +1548,61 @@
}
EXPORT_SYMBOL(i2c_clients_command);
+#if IS_ENABLED(CONFIG_OF_DYNAMIC)
+static int of_i2c_notify(struct notifier_block *nb, unsigned long action,
+ void *arg)
+{
+ struct of_reconfig_data *rd = arg;
+ struct i2c_adapter *adap;
+ struct i2c_client *client;
+
+ switch (of_reconfig_get_state_change(action, rd)) {
+ case OF_RECONFIG_CHANGE_ADD:
+ adap = of_find_i2c_adapter_by_node(rd->dn->parent);
+ if (adap == NULL)
+ return NOTIFY_OK; /* not for us */
+
+ if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) {
+ put_device(&adap->dev);
+ return NOTIFY_OK;
+ }
+
+ client = of_i2c_register_device(adap, rd->dn);
+ put_device(&adap->dev);
+
+ if (IS_ERR(client)) {
+ pr_err("%s: failed to create for '%s'\n",
+ __func__, rd->dn->full_name);
+ return notifier_from_errno(PTR_ERR(client));
+ }
+ break;
+ case OF_RECONFIG_CHANGE_REMOVE:
+ /* already depopulated? */
+ if (!of_node_check_flag(rd->dn, OF_POPULATED))
+ return NOTIFY_OK;
+
+ /* find our device by node */
+ client = of_find_i2c_device_by_node(rd->dn);
+ if (client == NULL)
+ return NOTIFY_OK; /* no? not meant for us */
+
+ /* unregister takes one ref away */
+ i2c_unregister_device(client);
+
+ /* and put the reference of the find */
+ put_device(&client->dev);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+static struct notifier_block i2c_of_notifier = {
+ .notifier_call = of_i2c_notify,
+};
+#else
+extern struct notifier_block i2c_of_notifier;
+#endif /* CONFIG_OF_DYNAMIC */
+
static int __init i2c_init(void)
{
int retval;
@@ -1443,6 +1620,10 @@
retval = i2c_add_driver(&dummy_driver);
if (retval)
goto class_err;
+
+ if (IS_ENABLED(CONFIG_OF_DYNAMIC))
+ WARN_ON(of_reconfig_notifier_register(&i2c_of_notifier));
+
return 0;
class_err:
@@ -1456,6 +1637,8 @@
static void __exit i2c_exit(void)
{
+ if (IS_ENABLED(CONFIG_OF_DYNAMIC))
+ WARN_ON(of_reconfig_notifier_unregister(&i2c_of_notifier));
i2c_del_driver(&dummy_driver);
#ifdef CONFIG_I2C_COMPAT
class_compat_unregister(i2c_adapter_compat_class);
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index 7409ebb..797e311 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -25,7 +25,6 @@
#include <linux/i2c.h>
#include <linux/i2c-mux.h>
#include <linux/of.h>
-#include <linux/of_i2c.h>
/* multiplexer per channel data */
struct i2c_mux_priv {
@@ -185,8 +184,6 @@
dev_info(&parent->dev, "Added multiplexed i2c bus %d\n",
i2c_adapter_id(&priv->adap));
- of_i2c_register_devices(&priv->adap);
-
return &priv->adap;
}
EXPORT_SYMBOL_GPL(i2c_add_mux_adapter);
diff --git a/drivers/i2c/muxes/i2c-mux-gpio.c b/drivers/i2c/muxes/i2c-mux-gpio.c
index 5a0ce00..bb4f69f 100644
--- a/drivers/i2c/muxes/i2c-mux-gpio.c
+++ b/drivers/i2c/muxes/i2c-mux-gpio.c
@@ -31,15 +31,15 @@
int i;
for (i = 0; i < mux->data.n_gpios; i++)
- gpio_set_value(mux->gpio_base + mux->data.gpios[i],
- val & (1 << i));
+ gpio_set_value_cansleep(mux->gpio_base + mux->data.gpios[i],
+ val & (1 << i));
}
static int i2c_mux_gpio_select(struct i2c_adapter *adap, void *data, u32 chan)
{
struct gpiomux *mux = data;
- i2c_mux_gpio_set(mux, mux->data.values[chan]);
+ i2c_mux_gpio_set(mux, chan);
return 0;
}
@@ -223,7 +223,7 @@
unsigned int class = mux->data.classes ? mux->data.classes[i] : 0;
mux->adap[i] = i2c_add_mux_adapter(parent, &pdev->dev, mux, nr,
- i, class,
+ mux->data.values[i], class,
i2c_mux_gpio_select, deselect);
if (!mux->adap[i]) {
ret = -ENODEV;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index fa6964d..d47bb0f 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -359,7 +359,10 @@
if (!(lapic_timer_reliable_states & (1 << (cstate))))
clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
- if (!need_resched()) {
+ if (!current_set_polling_and_test()) {
+
+ if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+ clflush((void *)¤t_thread_info()->flags);
__monitor((void *)¤t_thread_info()->flags, 0, 0);
smp_mb();
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 7229645..7c9a1d9 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -112,9 +112,10 @@
mutex_lock(&st->buf_lock);
st->tx[0] = KXSD9_READ(address);
ret = spi_sync_transfer(st->us, xfers, ARRAY_SIZE(xfers));
- if (ret)
- return ret;
- return (((u16)(st->rx[0])) << 8) | (st->rx[1] & 0xF0);
+ if (!ret)
+ ret = (((u16)(st->rx[0])) << 8) | (st->rx[1] & 0xF0);
+ mutex_unlock(&st->buf_lock);
+ return ret;
}
static IIO_CONST_ATTR(accel_scale_available,
diff --git a/drivers/iio/adc/ad7887.c b/drivers/iio/adc/ad7887.c
index dd15a5b..3394ebd 100644
--- a/drivers/iio/adc/ad7887.c
+++ b/drivers/iio/adc/ad7887.c
@@ -211,7 +211,13 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = 1,
.scan_index = 1,
- .scan_type = IIO_ST('u', 12, 16, 0),
+ .scan_type = {
+ .sign = 'u',
+ .realbits = 12,
+ .storagebits = 16,
+ .shift = 0,
+ .endianness = IIO_BE,
+ },
},
.channel[1] = {
.type = IIO_VOLTAGE,
@@ -221,7 +227,13 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = 0,
.scan_index = 0,
- .scan_type = IIO_ST('u', 12, 16, 0),
+ .scan_type = {
+ .sign = 'u',
+ .realbits = 12,
+ .storagebits = 16,
+ .shift = 0,
+ .endianness = IIO_BE,
+ },
},
.channel[2] = IIO_CHAN_SOFT_TIMESTAMP(2),
.int_vref_mv = 2500,
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index f0d6335..05d2733 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -477,7 +477,7 @@
goto error_free_irq;
/* select default trigger */
- indio_dev->trig = sigma_delta->trig;
+ indio_dev->trig = iio_trigger_get(sigma_delta->trig);
return 0;
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index e5b88d5..14fdaf0 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -161,12 +161,11 @@
return idev->num_channels;
}
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
struct at91_adc_trigger *triggers,
const char *trigger_name)
{
struct at91_adc_state *st = iio_priv(idev);
- u8 value = 0;
int i;
for (i = 0; i < st->trigger_number; i++) {
@@ -179,15 +178,16 @@
return -ENOMEM;
if (strcmp(trigger_name, name) == 0) {
- value = triggers[i].value;
kfree(name);
- break;
+ if (triggers[i].value == 0)
+ return -EINVAL;
+ return triggers[i].value;
}
kfree(name);
}
- return value;
+ return -EINVAL;
}
static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -197,14 +197,14 @@
struct iio_buffer *buffer = idev->buffer;
struct at91_adc_reg_desc *reg = st->registers;
u32 status = at91_adc_readl(st, reg->trigger_register);
- u8 value;
+ int value;
u8 bit;
value = at91_adc_get_trigger_value_by_name(idev,
st->trigger_list,
idev->trig->name);
- if (value == 0)
- return -EINVAL;
+ if (value < 0)
+ return value;
if (state) {
st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c
index 9e6da72..b2b5dcb 100644
--- a/drivers/iio/adc/max1363.c
+++ b/drivers/iio/adc/max1363.c
@@ -1214,8 +1214,8 @@
.num_modes = ARRAY_SIZE(max1238_mode_list),
.default_mode = s0to11,
.info = &max1238_info,
- .channels = max1238_channels,
- .num_channels = ARRAY_SIZE(max1238_channels),
+ .channels = max1038_channels,
+ .num_channels = ARRAY_SIZE(max1038_channels),
},
[max11605] = {
.bits = 8,
@@ -1224,8 +1224,8 @@
.num_modes = ARRAY_SIZE(max1238_mode_list),
.default_mode = s0to11,
.info = &max1238_info,
- .channels = max1238_channels,
- .num_channels = ARRAY_SIZE(max1238_channels),
+ .channels = max1038_channels,
+ .num_channels = ARRAY_SIZE(max1038_channels),
},
[max11606] = {
.bits = 10,
@@ -1274,8 +1274,8 @@
.num_modes = ARRAY_SIZE(max1238_mode_list),
.default_mode = s0to11,
.info = &max1238_info,
- .channels = max1238_channels,
- .num_channels = ARRAY_SIZE(max1238_channels),
+ .channels = max1138_channels,
+ .num_channels = ARRAY_SIZE(max1138_channels),
},
[max11611] = {
.bits = 10,
@@ -1284,8 +1284,8 @@
.num_modes = ARRAY_SIZE(max1238_mode_list),
.default_mode = s0to11,
.info = &max1238_info,
- .channels = max1238_channels,
- .num_channels = ARRAY_SIZE(max1238_channels),
+ .channels = max1138_channels,
+ .num_channels = ARRAY_SIZE(max1138_channels),
},
[max11612] = {
.bits = 12,
diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c
index 8fc3a97..8d8ca6f 100644
--- a/drivers/iio/common/st_sensors/st_sensors_trigger.c
+++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c
@@ -49,7 +49,7 @@
dev_err(&indio_dev->dev, "failed to register iio trigger.\n");
goto iio_trigger_register_error;
}
- indio_dev->trig = sdata->trig;
+ indio_dev->trig = iio_trigger_get(sdata->trig);
return 0;
diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig
index 6be4628..107cafc 100644
--- a/drivers/iio/gyro/Kconfig
+++ b/drivers/iio/gyro/Kconfig
@@ -50,7 +50,7 @@
select IIO_ST_GYRO_BUFFER if (IIO_TRIGGERED_BUFFER)
help
Say yes here to build support for STMicroelectronics gyroscopes:
- L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330.
+ L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330.
This driver can also be built as a module. If so, will be created
these modules:
diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c
index 6c43af9..14917fa 100644
--- a/drivers/iio/gyro/itg3200_buffer.c
+++ b/drivers/iio/gyro/itg3200_buffer.c
@@ -135,7 +135,7 @@
goto error_free_irq;
/* select default trigger */
- indio_dev->trig = st->trig;
+ indio_dev->trig = iio_trigger_get(st->trig);
return 0;
diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h
index 3ad9907..25ee236 100644
--- a/drivers/iio/gyro/st_gyro.h
+++ b/drivers/iio/gyro/st_gyro.h
@@ -19,7 +19,6 @@
#define LSM330DL_GYRO_DEV_NAME "lsm330dl_gyro"
#define LSM330DLC_GYRO_DEV_NAME "lsm330dlc_gyro"
#define L3GD20_GYRO_DEV_NAME "l3gd20"
-#define L3GD20H_GYRO_DEV_NAME "l3gd20h"
#define L3G4IS_GYRO_DEV_NAME "l3g4is_ui"
#define LSM330_GYRO_DEV_NAME "lsm330_gyro"
diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c
index fa9b242..1fabc3f 100644
--- a/drivers/iio/gyro/st_gyro_core.c
+++ b/drivers/iio/gyro/st_gyro_core.c
@@ -162,11 +162,10 @@
.wai = ST_GYRO_2_WAI_EXP,
.sensors_supported = {
[0] = L3GD20_GYRO_DEV_NAME,
- [1] = L3GD20H_GYRO_DEV_NAME,
- [2] = LSM330D_GYRO_DEV_NAME,
- [3] = LSM330DLC_GYRO_DEV_NAME,
- [4] = L3G4IS_GYRO_DEV_NAME,
- [5] = LSM330_GYRO_DEV_NAME,
+ [1] = LSM330D_GYRO_DEV_NAME,
+ [2] = LSM330DLC_GYRO_DEV_NAME,
+ [3] = L3G4IS_GYRO_DEV_NAME,
+ [4] = LSM330_GYRO_DEV_NAME,
},
.ch = (struct iio_chan_spec *)st_gyro_16bit_channels,
.odr = {
diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c
index 8a31050..c1755ce 100644
--- a/drivers/iio/gyro/st_gyro_i2c.c
+++ b/drivers/iio/gyro/st_gyro_i2c.c
@@ -61,7 +61,6 @@
{ LSM330DL_GYRO_DEV_NAME },
{ LSM330DLC_GYRO_DEV_NAME },
{ L3GD20_GYRO_DEV_NAME },
- { L3GD20H_GYRO_DEV_NAME },
{ L3G4IS_GYRO_DEV_NAME },
{ LSM330_GYRO_DEV_NAME },
{},
diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c
index f354039..b37fc9e 100644
--- a/drivers/iio/gyro/st_gyro_spi.c
+++ b/drivers/iio/gyro/st_gyro_spi.c
@@ -60,7 +60,6 @@
{ LSM330DL_GYRO_DEV_NAME },
{ LSM330DLC_GYRO_DEV_NAME },
{ L3GD20_GYRO_DEV_NAME },
- { L3GD20H_GYRO_DEV_NAME },
{ L3G4IS_GYRO_DEV_NAME },
{ LSM330_GYRO_DEV_NAME },
{},
diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h
index 2f8f9d6..0916bf6 100644
--- a/drivers/iio/imu/adis16400.h
+++ b/drivers/iio/imu/adis16400.h
@@ -189,6 +189,7 @@
ADIS16300_SCAN_INCLI_X,
ADIS16300_SCAN_INCLI_Y,
ADIS16400_SCAN_ADC,
+ ADIS16400_SCAN_TIMESTAMP,
};
#ifdef CONFIG_IIO_BUFFER
diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c
index f60591f..7d60c85 100644
--- a/drivers/iio/imu/adis16400_core.c
+++ b/drivers/iio/imu/adis16400_core.c
@@ -26,6 +26,7 @@
#include <linux/list.h>
#include <linux/module.h>
#include <linux/debugfs.h>
+#include <linux/bitops.h>
#include <linux/iio/iio.h>
#include <linux/iio/sysfs.h>
@@ -447,7 +448,7 @@
mutex_unlock(&indio_dev->mlock);
if (ret)
return ret;
- val16 = ((val16 & 0xFFF) << 4) >> 4;
+ val16 = sign_extend32(val16, 11);
*val = val16;
return IIO_VAL_INT;
case IIO_CHAN_INFO_OFFSET:
@@ -632,7 +633,7 @@
ADIS16400_MAGN_CHAN(Z, ADIS16400_ZMAGN_OUT, 14),
ADIS16400_TEMP_CHAN(ADIS16400_TEMP_OUT, 12),
ADIS16400_AUX_ADC_CHAN(ADIS16400_AUX_ADC, 12),
- IIO_CHAN_SOFT_TIMESTAMP(12)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16448_channels[] = {
@@ -651,10 +652,15 @@
.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = ADIS16448_BARO_OUT,
.scan_index = ADIS16400_SCAN_BARO,
- .scan_type = IIO_ST('s', 16, 16, 0),
+ .scan_type = {
+ .sign = 's',
+ .realbits = 16,
+ .storagebits = 16,
+ .endianness = IIO_BE,
+ },
},
ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(11)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16350_channels[] = {
@@ -672,7 +678,7 @@
ADIS16400_MOD_TEMP_CHAN(X, ADIS16350_XTEMP_OUT, 12),
ADIS16400_MOD_TEMP_CHAN(Y, ADIS16350_YTEMP_OUT, 12),
ADIS16400_MOD_TEMP_CHAN(Z, ADIS16350_ZTEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(11)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16300_channels[] = {
@@ -685,7 +691,7 @@
ADIS16400_AUX_ADC_CHAN(ADIS16300_AUX_ADC, 12),
ADIS16400_INCLI_CHAN(X, ADIS16300_PITCH_OUT, 13),
ADIS16400_INCLI_CHAN(Y, ADIS16300_ROLL_OUT, 13),
- IIO_CHAN_SOFT_TIMESTAMP(14)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static const struct iio_chan_spec adis16334_channels[] = {
@@ -696,7 +702,7 @@
ADIS16400_ACCEL_CHAN(Y, ADIS16400_YACCL_OUT, 14),
ADIS16400_ACCEL_CHAN(Z, ADIS16400_ZACCL_OUT, 14),
ADIS16400_TEMP_CHAN(ADIS16350_XTEMP_OUT, 12),
- IIO_CHAN_SOFT_TIMESTAMP(8)
+ IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP),
};
static struct attribute *adis16400_attributes[] = {
diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c
index e0017c2..f53e9a8 100644
--- a/drivers/iio/imu/adis_trigger.c
+++ b/drivers/iio/imu/adis_trigger.c
@@ -60,7 +60,7 @@
iio_trigger_set_drvdata(adis->trig, adis);
ret = iio_trigger_register(adis->trig);
- indio_dev->trig = adis->trig;
+ indio_dev->trig = iio_trigger_get(adis->trig);
if (ret)
goto error_free_irq;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index fe4c61e..111ac38 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -660,6 +660,7 @@
{
struct inv_mpu6050_state *st;
struct iio_dev *indio_dev;
+ struct inv_mpu6050_platform_data *pdata;
int result;
if (!i2c_check_functionality(client->adapter,
@@ -675,8 +676,10 @@
}
st = iio_priv(indio_dev);
st->client = client;
- st->plat_data = *(struct inv_mpu6050_platform_data
- *)dev_get_platdata(&client->dev);
+ pdata = (struct inv_mpu6050_platform_data
+ *)dev_get_platdata(&client->dev);
+ if (pdata)
+ st->plat_data = *pdata;
/* power is turned on inside check chip type*/
result = inv_check_and_setup_chip(st, id);
if (result)
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 7da0832..01d661e 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -25,6 +25,16 @@
#include <linux/poll.h>
#include "inv_mpu_iio.h"
+static void inv_clear_kfifo(struct inv_mpu6050_state *st)
+{
+ unsigned long flags;
+
+ /* take the spin lock sem to avoid interrupt kick in */
+ spin_lock_irqsave(&st->time_stamp_lock, flags);
+ kfifo_reset(&st->timestamps);
+ spin_unlock_irqrestore(&st->time_stamp_lock, flags);
+}
+
int inv_reset_fifo(struct iio_dev *indio_dev)
{
int result;
@@ -51,6 +61,10 @@
INV_MPU6050_BIT_FIFO_RST);
if (result)
goto reset_fifo_fail;
+
+ /* clear timestamps fifo */
+ inv_clear_kfifo(st);
+
/* enable interrupt */
if (st->chip_config.accl_fifo_enable ||
st->chip_config.gyro_fifo_enable) {
@@ -84,16 +98,6 @@
return result;
}
-static void inv_clear_kfifo(struct inv_mpu6050_state *st)
-{
- unsigned long flags;
-
- /* take the spin lock sem to avoid interrupt kick in */
- spin_lock_irqsave(&st->time_stamp_lock, flags);
- kfifo_reset(&st->timestamps);
- spin_unlock_irqrestore(&st->time_stamp_lock, flags);
-}
-
/**
* inv_mpu6050_irq_handler() - Cache a timestamp at each data ready interrupt.
*/
@@ -187,7 +191,6 @@
flush_fifo:
/* Flush HW and SW FIFOs. */
inv_reset_fifo(indio_dev);
- inv_clear_kfifo(st);
mutex_unlock(&indio_dev->mlock);
iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
index 03b9372..926fcce 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
@@ -135,7 +135,7 @@
ret = iio_trigger_register(st->trig);
if (ret)
goto error_free_irq;
- indio_dev->trig = st->trig;
+ indio_dev->trig = iio_trigger_get(st->trig);
return 0;
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index aaadd32..e13c5f4b 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -119,7 +119,8 @@
int ret;
struct iio_dev *indio_dev = dev_to_iio_dev(dev);
- ret = test_bit(to_iio_dev_attr(attr)->address,
+ /* Ensure ret is 0 or 1. */
+ ret = !!test_bit(to_iio_dev_attr(attr)->address,
indio_dev->buffer->scan_mask);
return sprintf(buf, "%d\n", ret);
@@ -762,7 +763,8 @@
if (!buffer->scan_mask)
return 0;
- return test_bit(bit, buffer->scan_mask);
+ /* Ensure return value is 0 or 1. */
+ return !!test_bit(bit, buffer->scan_mask);
};
EXPORT_SYMBOL_GPL(iio_scan_mask_query);
@@ -847,7 +849,7 @@
/* Now we have the two masks, work from least sig and build up sizes */
for_each_set_bit(out_ind,
- indio_dev->active_scan_mask,
+ buffer->scan_mask,
indio_dev->masklength) {
in_ind = find_next_bit(indio_dev->active_scan_mask,
indio_dev->masklength,
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index 98ddc32..4fc88e6 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -178,12 +178,12 @@
index = of_property_match_string(np, "io-channel-names",
name);
chan = of_iio_channel_get(np, index);
- if (!IS_ERR(chan))
+ if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
break;
else if (name && index >= 0) {
pr_err("ERROR: could not get IIO channel %s:%s(%i)\n",
np->full_name, name ? name : "", index);
- return chan;
+ return NULL;
}
/*
@@ -193,8 +193,9 @@
*/
np = np->parent;
if (np && !of_get_property(np, "io-channel-ranges", NULL))
- break;
+ return NULL;
}
+
return chan;
}
@@ -317,6 +318,7 @@
if (channel != NULL)
return channel;
}
+
return iio_channel_get_sys(name, channel_name);
}
EXPORT_SYMBOL_GPL(iio_channel_get);
@@ -451,7 +453,7 @@
int ret;
ret = iio_channel_read(chan, &offset, NULL, IIO_CHAN_INFO_OFFSET);
- if (ret == 0)
+ if (ret >= 0)
raw64 += offset;
scale_type = iio_channel_read(chan, &scale_val, &scale_val2,
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index af6c320..53f8290 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -276,8 +276,6 @@
{
struct ak8975_data *data = iio_priv(indio_dev);
struct i2c_client *client = data->client;
- u16 meas_reg;
- s16 raw;
int ret;
mutex_lock(&data->lock);
@@ -322,16 +320,11 @@
dev_err(&client->dev, "Read axis data fails\n");
goto exit;
}
- meas_reg = ret;
mutex_unlock(&data->lock);
- /* Endian conversion of the measured values. */
- raw = (s16) (le16_to_cpu(meas_reg));
-
/* Clamp to valid range. */
- raw = clamp_t(s16, raw, -4096, 4095);
- *val = raw;
+ *val = clamp_t(s16, ret, -4096, 4095);
return IIO_VAL_INT;
exit:
diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c
index 16f0d6d..3ce3769 100644
--- a/drivers/iio/magnetometer/st_magn_core.c
+++ b/drivers/iio/magnetometer/st_magn_core.c
@@ -40,7 +40,8 @@
#define ST_MAGN_FS_AVL_5600MG 5600
#define ST_MAGN_FS_AVL_8000MG 8000
#define ST_MAGN_FS_AVL_8100MG 8100
-#define ST_MAGN_FS_AVL_10000MG 10000
+#define ST_MAGN_FS_AVL_12000MG 12000
+#define ST_MAGN_FS_AVL_16000MG 16000
/* CUSTOM VALUES FOR SENSOR 1 */
#define ST_MAGN_1_WAI_EXP 0x3c
@@ -67,20 +68,20 @@
#define ST_MAGN_1_FS_AVL_4700_VAL 0x05
#define ST_MAGN_1_FS_AVL_5600_VAL 0x06
#define ST_MAGN_1_FS_AVL_8100_VAL 0x07
-#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 1100
-#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 855
-#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 670
-#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 450
-#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 400
-#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 330
-#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 230
-#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 980
-#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 760
-#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 600
-#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 400
-#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 355
-#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 295
-#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 205
+#define ST_MAGN_1_FS_AVL_1300_GAIN_XY 909
+#define ST_MAGN_1_FS_AVL_1900_GAIN_XY 1169
+#define ST_MAGN_1_FS_AVL_2500_GAIN_XY 1492
+#define ST_MAGN_1_FS_AVL_4000_GAIN_XY 2222
+#define ST_MAGN_1_FS_AVL_4700_GAIN_XY 2500
+#define ST_MAGN_1_FS_AVL_5600_GAIN_XY 3030
+#define ST_MAGN_1_FS_AVL_8100_GAIN_XY 4347
+#define ST_MAGN_1_FS_AVL_1300_GAIN_Z 1020
+#define ST_MAGN_1_FS_AVL_1900_GAIN_Z 1315
+#define ST_MAGN_1_FS_AVL_2500_GAIN_Z 1666
+#define ST_MAGN_1_FS_AVL_4000_GAIN_Z 2500
+#define ST_MAGN_1_FS_AVL_4700_GAIN_Z 2816
+#define ST_MAGN_1_FS_AVL_5600_GAIN_Z 3389
+#define ST_MAGN_1_FS_AVL_8100_GAIN_Z 4878
#define ST_MAGN_1_MULTIREAD_BIT false
/* CUSTOM VALUES FOR SENSOR 2 */
@@ -103,10 +104,12 @@
#define ST_MAGN_2_FS_MASK 0x60
#define ST_MAGN_2_FS_AVL_4000_VAL 0x00
#define ST_MAGN_2_FS_AVL_8000_VAL 0x01
-#define ST_MAGN_2_FS_AVL_10000_VAL 0x02
-#define ST_MAGN_2_FS_AVL_4000_GAIN 430
-#define ST_MAGN_2_FS_AVL_8000_GAIN 230
-#define ST_MAGN_2_FS_AVL_10000_GAIN 230
+#define ST_MAGN_2_FS_AVL_12000_VAL 0x02
+#define ST_MAGN_2_FS_AVL_16000_VAL 0x03
+#define ST_MAGN_2_FS_AVL_4000_GAIN 146
+#define ST_MAGN_2_FS_AVL_8000_GAIN 292
+#define ST_MAGN_2_FS_AVL_12000_GAIN 438
+#define ST_MAGN_2_FS_AVL_16000_GAIN 584
#define ST_MAGN_2_MULTIREAD_BIT false
#define ST_MAGN_2_OUT_X_L_ADDR 0x28
#define ST_MAGN_2_OUT_Y_L_ADDR 0x2a
@@ -252,9 +255,14 @@
.gain = ST_MAGN_2_FS_AVL_8000_GAIN,
},
[2] = {
- .num = ST_MAGN_FS_AVL_10000MG,
- .value = ST_MAGN_2_FS_AVL_10000_VAL,
- .gain = ST_MAGN_2_FS_AVL_10000_GAIN,
+ .num = ST_MAGN_FS_AVL_12000MG,
+ .value = ST_MAGN_2_FS_AVL_12000_VAL,
+ .gain = ST_MAGN_2_FS_AVL_12000_GAIN,
+ },
+ [3] = {
+ .num = ST_MAGN_FS_AVL_16000MG,
+ .value = ST_MAGN_2_FS_AVL_16000_VAL,
+ .gain = ST_MAGN_2_FS_AVL_16000_GAIN,
},
},
},
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index c47c203..4293e89 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -46,6 +46,7 @@
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/sysctl.h>
#include <rdma/iw_cm.h>
#include <rdma/ib_addr.h>
@@ -65,6 +66,20 @@
struct list_head free_list;
};
+static unsigned int default_backlog = 256;
+
+static struct ctl_table_header *iwcm_ctl_table_hdr;
+static struct ctl_table iwcm_ctl_table[] = {
+ {
+ .procname = "default_backlog",
+ .data = &default_backlog,
+ .maxlen = sizeof(default_backlog),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ { }
+};
+
/*
* The following services provide a mechanism for pre-allocating iwcm_work
* elements. The design pre-allocates them based on the cm_id type:
@@ -419,6 +434,9 @@
cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
+ if (!backlog)
+ backlog = default_backlog;
+
ret = alloc_work_entries(cm_id_priv, backlog);
if (ret)
return ret;
@@ -1024,11 +1042,20 @@
if (!iwcm_wq)
return -ENOMEM;
+ iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm",
+ iwcm_ctl_table);
+ if (!iwcm_ctl_table_hdr) {
+ pr_err("iw_cm: couldn't register sysctl paths\n");
+ destroy_workqueue(iwcm_wq);
+ return -ENOMEM;
+ }
+
return 0;
}
static void __exit iw_cm_cleanup(void)
{
+ unregister_net_sysctl_table(iwcm_ctl_table_hdr);
destroy_workqueue(iwcm_wq);
}
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index a841123..c1fef27 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -94,6 +94,17 @@
if (dmasync)
dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
+ if (!size)
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * If the combination of the addr and size requested for this memory
+ * region causes an integer overflow, return error.
+ */
+ if (((addr + size) < addr) ||
+ PAGE_ALIGN(addr + size) < (addr + size))
+ return ERR_PTR(-EINVAL);
+
if (!can_do_mlock())
return ERR_PTR(-EPERM);
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index f0d588f..1acb991 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -98,7 +98,7 @@
struct ib_umad_device {
int start_port, end_port;
- struct kref ref;
+ struct kobject kobj;
struct ib_umad_port port[0];
};
@@ -134,14 +134,18 @@
static void ib_umad_add_one(struct ib_device *device);
static void ib_umad_remove_one(struct ib_device *device);
-static void ib_umad_release_dev(struct kref *ref)
+static void ib_umad_release_dev(struct kobject *kobj)
{
struct ib_umad_device *dev =
- container_of(ref, struct ib_umad_device, ref);
+ container_of(kobj, struct ib_umad_device, kobj);
kfree(dev);
}
+static struct kobj_type ib_umad_dev_ktype = {
+ .release = ib_umad_release_dev,
+};
+
static int hdr_size(struct ib_umad_file *file)
{
return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
@@ -780,27 +784,19 @@
{
struct ib_umad_port *port;
struct ib_umad_file *file;
- int ret;
+ int ret = -ENXIO;
port = container_of(inode->i_cdev, struct ib_umad_port, cdev);
- if (port)
- kref_get(&port->umad_dev->ref);
- else
- return -ENXIO;
mutex_lock(&port->file_mutex);
- if (!port->ib_dev) {
- ret = -ENXIO;
+ if (!port->ib_dev)
goto out;
- }
+ ret = -ENOMEM;
file = kzalloc(sizeof *file, GFP_KERNEL);
- if (!file) {
- kref_put(&port->umad_dev->ref, ib_umad_release_dev);
- ret = -ENOMEM;
+ if (!file)
goto out;
- }
mutex_init(&file->mutex);
spin_lock_init(&file->send_lock);
@@ -814,6 +810,13 @@
list_add_tail(&file->port_list, &port->file_list);
ret = nonseekable_open(inode, filp);
+ if (ret) {
+ list_del(&file->port_list);
+ kfree(file);
+ goto out;
+ }
+
+ kobject_get(&port->umad_dev->kobj);
out:
mutex_unlock(&port->file_mutex);
@@ -852,7 +855,7 @@
mutex_unlock(&file->port->file_mutex);
kfree(file);
- kref_put(&dev->ref, ib_umad_release_dev);
+ kobject_put(&dev->kobj);
return 0;
}
@@ -880,10 +883,6 @@
int ret;
port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
- if (port)
- kref_get(&port->umad_dev->ref);
- else
- return -ENXIO;
if (filp->f_flags & O_NONBLOCK) {
if (down_trylock(&port->sm_sem)) {
@@ -898,17 +897,27 @@
}
ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
- if (ret) {
- up(&port->sm_sem);
- goto fail;
- }
+ if (ret)
+ goto err_up_sem;
filp->private_data = port;
- return nonseekable_open(inode, filp);
+ ret = nonseekable_open(inode, filp);
+ if (ret)
+ goto err_clr_sm_cap;
+
+ kobject_get(&port->umad_dev->kobj);
+
+ return 0;
+
+err_clr_sm_cap:
+ swap(props.set_port_cap_mask, props.clr_port_cap_mask);
+ ib_modify_port(port->ib_dev, port->port_num, 0, &props);
+
+err_up_sem:
+ up(&port->sm_sem);
fail:
- kref_put(&port->umad_dev->ref, ib_umad_release_dev);
return ret;
}
@@ -927,7 +936,7 @@
up(&port->sm_sem);
- kref_put(&port->umad_dev->ref, ib_umad_release_dev);
+ kobject_put(&port->umad_dev->kobj);
return ret;
}
@@ -995,6 +1004,7 @@
}
static int ib_umad_init_port(struct ib_device *device, int port_num,
+ struct ib_umad_device *umad_dev,
struct ib_umad_port *port)
{
int devnum;
@@ -1027,6 +1037,7 @@
cdev_init(&port->cdev, &umad_fops);
port->cdev.owner = THIS_MODULE;
+ port->cdev.kobj.parent = &umad_dev->kobj;
kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num);
if (cdev_add(&port->cdev, base, 1))
goto err_cdev;
@@ -1045,6 +1056,7 @@
base += IB_UMAD_MAX_PORTS;
cdev_init(&port->sm_cdev, &umad_sm_fops);
port->sm_cdev.owner = THIS_MODULE;
+ port->sm_cdev.kobj.parent = &umad_dev->kobj;
kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num);
if (cdev_add(&port->sm_cdev, base, 1))
goto err_sm_cdev;
@@ -1138,7 +1150,7 @@
if (!umad_dev)
return;
- kref_init(&umad_dev->ref);
+ kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
umad_dev->start_port = s;
umad_dev->end_port = e;
@@ -1146,7 +1158,8 @@
for (i = s; i <= e; ++i) {
umad_dev->port[i - s].umad_dev = umad_dev;
- if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
+ if (ib_umad_init_port(device, i, umad_dev,
+ &umad_dev->port[i - s]))
goto err;
}
@@ -1158,7 +1171,7 @@
while (--i >= s)
ib_umad_kill_port(&umad_dev->port[i - s]);
- kref_put(&umad_dev->ref, ib_umad_release_dev);
+ kobject_put(&umad_dev->kobj);
}
static void ib_umad_remove_one(struct ib_device *device)
@@ -1172,7 +1185,7 @@
for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
ib_umad_kill_port(&umad_dev->port[i]);
- kref_put(&umad_dev->ref, ib_umad_release_dev);
+ kobject_put(&umad_dev->kobj);
}
static char *umad_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 2c6f0f2..949b386 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -460,6 +460,7 @@
entry->desc.async.element = element;
entry->desc.async.event_type = event;
+ entry->desc.async.reserved = 0;
entry->counter = counter;
list_add_tail(&entry->list, &file->async_file->event_list);
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c
index 212150c..8cc8375 100644
--- a/drivers/infiniband/hw/ehca/ehca_cq.c
+++ b/drivers/infiniband/hw/ehca/ehca_cq.c
@@ -283,6 +283,7 @@
(my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1));
if (ib_copy_to_udata(udata, &resp, sizeof(resp))) {
ehca_err(device, "Copy to udata failed.");
+ cq = ERR_PTR(-EFAULT);
goto create_cq_exit4;
}
}
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index 714293b..45802e9 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -326,7 +326,7 @@
size_t count, loff_t *off)
{
u32 __iomem *piobuf;
- u32 plen, clen, pbufn;
+ u32 plen, pbufn, maxlen_reserve;
struct ipath_diag_pkt odp;
struct ipath_diag_xpkt dp;
u32 *tmpbuf = NULL;
@@ -335,42 +335,24 @@
u64 val;
u32 l_state, lt_state; /* LinkState, LinkTrainingState */
- if (count < sizeof(odp)) {
- ret = -EINVAL;
- goto bail;
- }
if (count == sizeof(dp)) {
if (copy_from_user(&dp, data, sizeof(dp))) {
ret = -EFAULT;
goto bail;
}
- } else if (copy_from_user(&odp, data, sizeof(odp))) {
- ret = -EFAULT;
- goto bail;
- }
-
- /*
- * Due to padding/alignment issues (lessened with new struct)
- * the old and new structs are the same length. We need to
- * disambiguate them, which we can do because odp.len has never
- * been less than the total of LRH+BTH+DETH so far, while
- * dp.unit (same offset) unit is unlikely to get that high.
- * Similarly, dp.data, the pointer to user at the same offset
- * as odp.unit, is almost certainly at least one (512byte)page
- * "above" NULL. The if-block below can be omitted if compatibility
- * between a new driver and older diagnostic code is unimportant.
- * compatibility the other direction (new diags, old driver) is
- * handled in the diagnostic code, with a warning.
- */
- if (dp.unit >= 20 && dp.data < 512) {
- /* very probable version mismatch. Fix it up */
- memcpy(&odp, &dp, sizeof(odp));
- /* We got a legacy dp, copy elements to dp */
+ } else if (count == sizeof(odp)) {
+ if (copy_from_user(&odp, data, sizeof(odp))) {
+ ret = -EFAULT;
+ goto bail;
+ }
+ dp.len = odp.len;
dp.unit = odp.unit;
dp.data = odp.data;
- dp.len = odp.len;
- dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */
+ dp.pbc_wd = 0;
+ } else {
+ ret = -EINVAL;
+ goto bail;
}
/* send count must be an exact number of dwords */
@@ -379,7 +361,7 @@
goto bail;
}
- clen = dp.len >> 2;
+ plen = dp.len >> 2;
dd = ipath_lookup(dp.unit);
if (!dd || !(dd->ipath_flags & IPATH_PRESENT) ||
@@ -422,16 +404,22 @@
goto bail;
}
- /* need total length before first word written */
- /* +1 word is for the qword padding */
+ /*
+ * need total length before first word written, plus 2 Dwords. One Dword
+ * is for padding so we get the full user data when not aligned on
+ * a word boundary. The other Dword is to make sure we have room for the
+ * ICRC which gets tacked on later.
+ */
+ maxlen_reserve = 2 * sizeof(u32);
+ if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) {
+ ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n",
+ dp.len, dd->ipath_ibmaxlen);
+ ret = -EINVAL;
+ goto bail;
+ }
+
plen = sizeof(u32) + dp.len;
- if ((plen + 4) > dd->ipath_ibmaxlen) {
- ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n",
- plen - 4, dd->ipath_ibmaxlen);
- ret = -EINVAL;
- goto bail; /* before writing pbc */
- }
tmpbuf = vmalloc(plen);
if (!tmpbuf) {
dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, "
@@ -473,11 +461,11 @@
*/
if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) {
ipath_flush_wc();
- __iowrite32_copy(piobuf + 2, tmpbuf, clen - 1);
+ __iowrite32_copy(piobuf + 2, tmpbuf, plen - 1);
ipath_flush_wc();
- __raw_writel(tmpbuf[clen - 1], piobuf + clen + 1);
+ __raw_writel(tmpbuf[plen - 1], piobuf + plen + 1);
} else
- __iowrite32_copy(piobuf + 2, tmpbuf, clen);
+ __iowrite32_copy(piobuf + 2, tmpbuf, plen);
ipath_flush_wc();
diff --git a/drivers/infiniband/hw/ipath/ipath_user_sdma.c b/drivers/infiniband/hw/ipath/ipath_user_sdma.c
index f5cb13b..cc04b7b 100644
--- a/drivers/infiniband/hw/ipath/ipath_user_sdma.c
+++ b/drivers/infiniband/hw/ipath/ipath_user_sdma.c
@@ -280,9 +280,7 @@
int j;
int ret;
- ret = get_user_pages(current, current->mm, addr,
- npages, 0, 1, pages, NULL);
-
+ ret = get_user_pages_fast(addr, npages, 0, pages);
if (ret != npages) {
int i;
@@ -811,10 +809,7 @@
while (dim) {
const int mxp = 8;
- down_write(¤t->mm->mmap_sem);
ret = ipath_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
- up_write(¤t->mm->mmap_sem);
-
if (ret <= 0)
goto done_unlock;
else {
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 4d599ce..6ee5348 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -64,6 +64,14 @@
#define GUID_TBL_BLK_NUM_ENTRIES 8
#define GUID_TBL_BLK_SIZE (GUID_TBL_ENTRY_SIZE * GUID_TBL_BLK_NUM_ENTRIES)
+/* Counters should be saturate once they reach their maximum value */
+#define ASSIGN_32BIT_COUNTER(counter, value) do {\
+ if ((value) > U32_MAX) \
+ counter = cpu_to_be32(U32_MAX); \
+ else \
+ counter = cpu_to_be32(value); \
+} while (0)
+
struct mlx4_mad_rcv_buf {
struct ib_grh grh;
u8 payload[256];
@@ -730,10 +738,14 @@
static void edit_counter(struct mlx4_counter *cnt,
struct ib_pma_portcounters *pma_cnt)
{
- pma_cnt->port_xmit_data = cpu_to_be32((be64_to_cpu(cnt->tx_bytes)>>2));
- pma_cnt->port_rcv_data = cpu_to_be32((be64_to_cpu(cnt->rx_bytes)>>2));
- pma_cnt->port_xmit_packets = cpu_to_be32(be64_to_cpu(cnt->tx_frames));
- pma_cnt->port_rcv_packets = cpu_to_be32(be64_to_cpu(cnt->rx_frames));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+ (be64_to_cpu(cnt->tx_bytes) >> 2));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+ (be64_to_cpu(cnt->rx_bytes) >> 2));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+ be64_to_cpu(cnt->tx_frames));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+ be64_to_cpu(cnt->rx_frames));
}
static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 4f10af2..262a184 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -2174,8 +2174,7 @@
memcpy(wqe->header, wr->wr.ud.header, wr->wr.ud.hlen);
- *lso_hdr_sz = cpu_to_be32((wr->wr.ud.mss - wr->wr.ud.hlen) << 16 |
- wr->wr.ud.hlen);
+ *lso_hdr_sz = cpu_to_be32(wr->wr.ud.mss << 16 | wr->wr.ud.hlen);
*lso_seg_len = halign;
return 0;
}
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index 5b71d43..42dde06 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -695,6 +695,7 @@
if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) {
mthca_free_cq(to_mdev(ibdev), cq);
+ err = -EFAULT;
goto err_free;
}
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 8f67fe2e..7510a3c 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1186,7 +1186,7 @@
nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num);
kfree(nesqp->allocated_buffer);
nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n");
- return NULL;
+ return ERR_PTR(-EFAULT);
}
if (req.user_wqe_buffers) {
virt_wqs = 1;
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index 4d11575..d1b30c6 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -1055,12 +1055,6 @@
/* control high-level access to EEPROM */
struct mutex eep_lock;
uint64_t traffic_wds;
- /* active time is kept in seconds, but logged in hours */
- atomic_t active_time;
- /* Below are nominal shadow of EEPROM, new since last EEPROM update */
- uint8_t eep_st_errs[QIB_EEP_LOG_CNT];
- uint8_t eep_st_new_errs[QIB_EEP_LOG_CNT];
- uint16_t eep_hrs;
/*
* masks for which bits of errs, hwerrs that cause
* each of the counters to increment.
@@ -1278,8 +1272,7 @@
int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr,
const void *buffer, int len);
void qib_get_eeprom_info(struct qib_devdata *);
-int qib_update_eeprom_log(struct qib_devdata *dd);
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr);
+#define qib_inc_eeprom_err(dd, eidx, incr)
void qib_dump_lookup_output_queue(struct qib_devdata *);
void qib_force_pio_avail_update(struct qib_devdata *);
void qib_clear_symerror_on_linkup(unsigned long opaque);
diff --git a/drivers/infiniband/hw/qib/qib_eeprom.c b/drivers/infiniband/hw/qib/qib_eeprom.c
index 4d5d71a..e2280b0 100644
--- a/drivers/infiniband/hw/qib/qib_eeprom.c
+++ b/drivers/infiniband/hw/qib/qib_eeprom.c
@@ -267,190 +267,9 @@
"Board SN %s did not pass functional test: %s\n",
dd->serial, ifp->if_comment);
- memcpy(&dd->eep_st_errs, &ifp->if_errcntp, QIB_EEP_LOG_CNT);
- /*
- * Power-on (actually "active") hours are kept as little-endian value
- * in EEPROM, but as seconds in a (possibly as small as 24-bit)
- * atomic_t while running.
- */
- atomic_set(&dd->active_time, 0);
- dd->eep_hrs = ifp->if_powerhour[0] | (ifp->if_powerhour[1] << 8);
-
done:
vfree(buf);
bail:;
}
-/**
- * qib_update_eeprom_log - copy active-time and error counters to eeprom
- * @dd: the qlogic_ib device
- *
- * Although the time is kept as seconds in the qib_devdata struct, it is
- * rounded to hours for re-write, as we have only 16 bits in EEPROM.
- * First-cut code reads whole (expected) struct qib_flash, modifies,
- * re-writes. Future direction: read/write only what we need, assuming
- * that the EEPROM had to have been "good enough" for driver init, and
- * if not, we aren't making it worse.
- *
- */
-int qib_update_eeprom_log(struct qib_devdata *dd)
-{
- void *buf;
- struct qib_flash *ifp;
- int len, hi_water;
- uint32_t new_time, new_hrs;
- u8 csum;
- int ret, idx;
- unsigned long flags;
-
- /* first, check if we actually need to do anything. */
- ret = 0;
- for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
- if (dd->eep_st_new_errs[idx]) {
- ret = 1;
- break;
- }
- }
- new_time = atomic_read(&dd->active_time);
-
- if (ret == 0 && new_time < 3600)
- goto bail;
-
- /*
- * The quick-check above determined that there is something worthy
- * of logging, so get current contents and do a more detailed idea.
- * read full flash, not just currently used part, since it may have
- * been written with a newer definition
- */
- len = sizeof(struct qib_flash);
- buf = vmalloc(len);
- ret = 1;
- if (!buf) {
- qib_dev_err(dd,
- "Couldn't allocate memory to read %u bytes from eeprom for logging\n",
- len);
- goto bail;
- }
-
- /* Grab semaphore and read current EEPROM. If we get an
- * error, let go, but if not, keep it until we finish write.
- */
- ret = mutex_lock_interruptible(&dd->eep_lock);
- if (ret) {
- qib_dev_err(dd, "Unable to acquire EEPROM for logging\n");
- goto free_bail;
- }
- ret = qib_twsi_blk_rd(dd, dd->twsi_eeprom_dev, 0, buf, len);
- if (ret) {
- mutex_unlock(&dd->eep_lock);
- qib_dev_err(dd, "Unable read EEPROM for logging\n");
- goto free_bail;
- }
- ifp = (struct qib_flash *)buf;
-
- csum = flash_csum(ifp, 0);
- if (csum != ifp->if_csum) {
- mutex_unlock(&dd->eep_lock);
- qib_dev_err(dd, "EEPROM cks err (0x%02X, S/B 0x%02X)\n",
- csum, ifp->if_csum);
- ret = 1;
- goto free_bail;
- }
- hi_water = 0;
- spin_lock_irqsave(&dd->eep_st_lock, flags);
- for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
- int new_val = dd->eep_st_new_errs[idx];
- if (new_val) {
- /*
- * If we have seen any errors, add to EEPROM values
- * We need to saturate at 0xFF (255) and we also
- * would need to adjust the checksum if we were
- * trying to minimize EEPROM traffic
- * Note that we add to actual current count in EEPROM,
- * in case it was altered while we were running.
- */
- new_val += ifp->if_errcntp[idx];
- if (new_val > 0xFF)
- new_val = 0xFF;
- if (ifp->if_errcntp[idx] != new_val) {
- ifp->if_errcntp[idx] = new_val;
- hi_water = offsetof(struct qib_flash,
- if_errcntp) + idx;
- }
- /*
- * update our shadow (used to minimize EEPROM
- * traffic), to match what we are about to write.
- */
- dd->eep_st_errs[idx] = new_val;
- dd->eep_st_new_errs[idx] = 0;
- }
- }
- /*
- * Now update active-time. We would like to round to the nearest hour
- * but unless atomic_t are sure to be proper signed ints we cannot,
- * because we need to account for what we "transfer" to EEPROM and
- * if we log an hour at 31 minutes, then we would need to set
- * active_time to -29 to accurately count the _next_ hour.
- */
- if (new_time >= 3600) {
- new_hrs = new_time / 3600;
- atomic_sub((new_hrs * 3600), &dd->active_time);
- new_hrs += dd->eep_hrs;
- if (new_hrs > 0xFFFF)
- new_hrs = 0xFFFF;
- dd->eep_hrs = new_hrs;
- if ((new_hrs & 0xFF) != ifp->if_powerhour[0]) {
- ifp->if_powerhour[0] = new_hrs & 0xFF;
- hi_water = offsetof(struct qib_flash, if_powerhour);
- }
- if ((new_hrs >> 8) != ifp->if_powerhour[1]) {
- ifp->if_powerhour[1] = new_hrs >> 8;
- hi_water = offsetof(struct qib_flash, if_powerhour) + 1;
- }
- }
- /*
- * There is a tiny possibility that we could somehow fail to write
- * the EEPROM after updating our shadows, but problems from holding
- * the spinlock too long are a much bigger issue.
- */
- spin_unlock_irqrestore(&dd->eep_st_lock, flags);
- if (hi_water) {
- /* we made some change to the data, uopdate cksum and write */
- csum = flash_csum(ifp, 1);
- ret = eeprom_write_with_enable(dd, 0, buf, hi_water + 1);
- }
- mutex_unlock(&dd->eep_lock);
- if (ret)
- qib_dev_err(dd, "Failed updating EEPROM\n");
-
-free_bail:
- vfree(buf);
-bail:
- return ret;
-}
-
-/**
- * qib_inc_eeprom_err - increment one of the four error counters
- * that are logged to EEPROM.
- * @dd: the qlogic_ib device
- * @eidx: 0..3, the counter to increment
- * @incr: how much to add
- *
- * Each counter is 8-bits, and saturates at 255 (0xFF). They
- * are copied to the EEPROM (aka flash) whenever qib_update_eeprom_log()
- * is called, but it can only be called in a context that allows sleep.
- * This function can be called even at interrupt level.
- */
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr)
-{
- uint new_val;
- unsigned long flags;
-
- spin_lock_irqsave(&dd->eep_st_lock, flags);
- new_val = dd->eep_st_new_errs[eidx] + incr;
- if (new_val > 255)
- new_val = 255;
- dd->eep_st_new_errs[eidx] = new_val;
- spin_unlock_irqrestore(&dd->eep_st_lock, flags);
-}
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index 0232ae5..4e26133 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -2682,8 +2682,6 @@
spin_lock_irqsave(&dd->eep_st_lock, flags);
traffic_wds -= dd->traffic_wds;
dd->traffic_wds += traffic_wds;
- if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
- atomic_add(5, &dd->active_time); /* S/B #define */
spin_unlock_irqrestore(&dd->eep_st_lock, flags);
qib_chk_6120_errormask(dd);
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 64d0ecb..3dbabf3 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -3299,8 +3299,6 @@
spin_lock_irqsave(&dd->eep_st_lock, flags);
traffic_wds -= dd->traffic_wds;
dd->traffic_wds += traffic_wds;
- if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
- atomic_add(5, &dd->active_time); /* S/B #define */
spin_unlock_irqrestore(&dd->eep_st_lock, flags);
done:
mod_timer(&dd->stats_timer, jiffies + HZ * ACTIVITY_TIMER);
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 3f6b21e..5f5f20f 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2287,6 +2287,11 @@
qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a);
qib_write_kreg(dd, kr_scratch, 0ULL);
+ /* ensure previous Tx parameters are not still forced */
+ qib_write_kreg_port(ppd, krp_tx_deemph_override,
+ SYM_MASK(IBSD_TX_DEEMPHASIS_OVERRIDE_0,
+ reset_tx_deemphasis_override));
+
if (qib_compat_ddr_negotiate) {
ppd->cpspec->ibdeltainprog = 1;
ppd->cpspec->ibsymsnap = read_7322_creg32_port(ppd,
@@ -4849,8 +4854,6 @@
spin_lock_irqsave(&ppd->dd->eep_st_lock, flags);
traffic_wds -= ppd->dd->traffic_wds;
ppd->dd->traffic_wds += traffic_wds;
- if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
- atomic_add(ACTIVITY_TIMER, &ppd->dd->active_time);
spin_unlock_irqrestore(&ppd->dd->eep_st_lock, flags);
if (ppd->cpspec->qdr_dfe_on && (ppd->link_speed_active &
QIB_IB_QDR) &&
@@ -5853,21 +5856,20 @@
{
struct qib_devdata *dd;
unsigned long val;
- int ret;
-
+ char *n;
if (strlen(str) >= MAX_ATTEN_LEN) {
pr_info("txselect_values string too long\n");
return -ENOSPC;
}
- ret = kstrtoul(str, 0, &val);
- if (ret || val >= (TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ +
+ val = simple_strtoul(str, &n, 0);
+ if (n == str || val >= (TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ +
TXDDS_MFG_SZ)) {
pr_info("txselect_values must start with a number < %d\n",
TXDDS_TABLE_SZ + TXDDS_EXTRA_SZ + TXDDS_MFG_SZ);
- return ret ? ret : -EINVAL;
+ return -EINVAL;
}
-
strcpy(txselect_list, str);
+
list_for_each_entry(dd, &qib_dev_list, list)
if (dd->deviceid == PCI_DEVICE_ID_QLOGIC_IB_7322)
set_no_qsfp_atten(dd, 1);
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 173f805..8f936e3 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -892,7 +892,6 @@
}
}
- qib_update_eeprom_log(dd);
}
/**
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index ccb1191..1dd9fcb 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1028,7 +1028,7 @@
event.event = IB_EVENT_PKEY_CHANGE;
event.device = &dd->verbs_dev.ibdev;
- event.element.port_num = 1;
+ event.element.port_num = port;
ib_dispatch_event(&event);
}
return 0;
diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c
index 3c8e4e3..b9ccbda 100644
--- a/drivers/infiniband/hw/qib/qib_sysfs.c
+++ b/drivers/infiniband/hw/qib/qib_sysfs.c
@@ -611,28 +611,6 @@
return ret < 0 ? ret : count;
}
-static ssize_t show_logged_errs(struct device *device,
- struct device_attribute *attr, char *buf)
-{
- struct qib_ibdev *dev =
- container_of(device, struct qib_ibdev, ibdev.dev);
- struct qib_devdata *dd = dd_from_dev(dev);
- int idx, count;
-
- /* force consistency with actual EEPROM */
- if (qib_update_eeprom_log(dd) != 0)
- return -ENXIO;
-
- count = 0;
- for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
- count += scnprintf(buf + count, PAGE_SIZE - count, "%d%c",
- dd->eep_st_errs[idx],
- idx == (QIB_EEP_LOG_CNT - 1) ? '\n' : ' ');
- }
-
- return count;
-}
-
/*
* Dump tempsense regs. in decimal, to ease shell-scripts.
*/
@@ -679,7 +657,6 @@
static DEVICE_ATTR(nfreectxts, S_IRUGO, show_nfreectxts, NULL);
static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL);
static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL);
-static DEVICE_ATTR(logged_errors, S_IRUGO, show_logged_errs, NULL);
static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL);
static DEVICE_ATTR(localbus_info, S_IRUGO, show_localbus_info, NULL);
static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset);
@@ -693,7 +670,6 @@
&dev_attr_nfreectxts,
&dev_attr_serial,
&dev_attr_boardversion,
- &dev_attr_logged_errors,
&dev_attr_tempsense,
&dev_attr_localbus_info,
&dev_attr_chip_reset,
diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c
index d6c7fe7..3ad651c 100644
--- a/drivers/infiniband/hw/qib/qib_ud.c
+++ b/drivers/infiniband/hw/qib/qib_ud.c
@@ -57,13 +57,20 @@
struct qib_sge *sge;
struct ib_wc wc;
u32 length;
+ enum ib_qp_type sqptype, dqptype;
qp = qib_lookup_qpn(ibp, swqe->wr.wr.ud.remote_qpn);
if (!qp) {
ibp->n_pkt_drops++;
return;
}
- if (qp->ibqp.qp_type != sqp->ibqp.qp_type ||
+
+ sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
+ IB_QPT_UD : sqp->ibqp.qp_type;
+ dqptype = qp->ibqp.qp_type == IB_QPT_GSI ?
+ IB_QPT_UD : qp->ibqp.qp_type;
+
+ if (dqptype != sqptype ||
!(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) {
ibp->n_pkt_drops++;
goto drop;
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 8244208..573b460 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -284,8 +284,7 @@
int j;
int ret;
- ret = get_user_pages(current, current->mm, addr,
- npages, 0, 1, pages, NULL);
+ ret = get_user_pages_fast(addr, npages, 0, pages);
if (ret != npages) {
int i;
@@ -830,10 +829,7 @@
while (dim) {
const int mxp = 8;
- down_write(¤t->mm->mmap_sem);
ret = qib_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
- up_write(¤t->mm->mmap_sem);
-
if (ret <= 0)
goto done_unlock;
else {
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 41712f0..8019e64 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -27,6 +27,7 @@
#include <target/target_core_base.h>
#include <target/target_core_fabric.h>
#include <target/iscsi/iscsi_transport.h>
+#include <linux/semaphore.h>
#include "isert_proto.h"
#include "ib_isert.h"
@@ -39,8 +40,15 @@
static LIST_HEAD(device_list);
static struct workqueue_struct *isert_rx_wq;
static struct workqueue_struct *isert_comp_wq;
+static struct workqueue_struct *isert_release_wq;
static struct kmem_cache *isert_cmd_cache;
+static int
+isert_rdma_post_recvl(struct isert_conn *isert_conn);
+static int
+isert_rdma_accept(struct isert_conn *isert_conn);
+struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np);
+
static void
isert_qp_event_callback(struct ib_event *e, void *context)
{
@@ -106,9 +114,12 @@
attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS;
/*
* FIXME: Use devattr.max_sge - 2 for max_send_sge as
- * work-around for RDMA_READ..
+ * work-around for RDMA_READs with ConnectX-2.
+ *
+ * Also, still make sure to have at least two SGEs for
+ * outgoing control PDU responses.
*/
- attr.cap.max_send_sge = devattr.max_sge - 2;
+ attr.cap.max_send_sge = max(2, devattr.max_sge - 2);
isert_conn->max_sge = attr.cap.max_send_sge;
attr.cap.max_recv_sge = 1;
@@ -123,12 +134,18 @@
ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr);
if (ret) {
pr_err("rdma_create_qp failed for cma_id %d\n", ret);
- return ret;
+ goto err;
}
isert_conn->conn_qp = cma_id->qp;
pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n");
return 0;
+err:
+ mutex_lock(&device_list_mutex);
+ device->cq_active_qps[min_index]--;
+ mutex_unlock(&device_list_mutex);
+
+ return ret;
}
static void
@@ -211,6 +228,13 @@
struct ib_device *ib_dev = device->ib_device;
struct isert_cq_desc *cq_desc;
int ret = 0, i, j;
+ int max_rx_cqe, max_tx_cqe;
+ struct ib_device_attr dev_attr;
+
+ memset(&dev_attr, 0, sizeof(struct ib_device_attr));
+ ret = isert_query_device(device->ib_device, &dev_attr);
+ if (ret)
+ return ret;
device->cqs_used = min_t(int, num_online_cpus(),
device->ib_device->num_comp_vectors);
@@ -233,6 +257,9 @@
goto out_cq_desc;
}
+ max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr.max_cqe);
+ max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr.max_cqe);
+
for (i = 0; i < device->cqs_used; i++) {
cq_desc[i].device = device;
cq_desc[i].cq_index = i;
@@ -241,22 +268,30 @@
isert_cq_rx_callback,
isert_cq_event_callback,
(void *)&cq_desc[i],
- ISER_MAX_RX_CQ_LEN, i);
- if (IS_ERR(device->dev_rx_cq[i]))
+ max_rx_cqe, i);
+ if (IS_ERR(device->dev_rx_cq[i])) {
+ ret = PTR_ERR(device->dev_rx_cq[i]);
+ device->dev_rx_cq[i] = NULL;
goto out_cq;
+ }
device->dev_tx_cq[i] = ib_create_cq(device->ib_device,
isert_cq_tx_callback,
isert_cq_event_callback,
(void *)&cq_desc[i],
- ISER_MAX_TX_CQ_LEN, i);
- if (IS_ERR(device->dev_tx_cq[i]))
+ max_tx_cqe, i);
+ if (IS_ERR(device->dev_tx_cq[i])) {
+ ret = PTR_ERR(device->dev_tx_cq[i]);
+ device->dev_tx_cq[i] = NULL;
+ goto out_cq;
+ }
+
+ ret = ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP);
+ if (ret)
goto out_cq;
- if (ib_req_notify_cq(device->dev_rx_cq[i], IB_CQ_NEXT_COMP))
- goto out_cq;
-
- if (ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP))
+ ret = ib_req_notify_cq(device->dev_tx_cq[i], IB_CQ_NEXT_COMP);
+ if (ret)
goto out_cq;
}
@@ -366,13 +401,21 @@
static int
isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
{
- struct iscsi_np *np = cma_id->context;
- struct isert_np *isert_np = np->np_context;
+ struct isert_np *isert_np = cma_id->context;
+ struct iscsi_np *np = isert_np->np;
struct isert_conn *isert_conn;
struct isert_device *device;
struct ib_device *ib_dev = cma_id->device;
int ret = 0;
+ spin_lock_bh(&np->np_thread_lock);
+ if (!np->enabled) {
+ spin_unlock_bh(&np->np_thread_lock);
+ pr_debug("iscsi_np is not enabled, reject connect request\n");
+ return rdma_reject(cma_id, NULL, 0);
+ }
+ spin_unlock_bh(&np->np_thread_lock);
+
pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n",
cma_id, cma_id->context);
@@ -384,12 +427,12 @@
isert_conn->state = ISER_CONN_INIT;
INIT_LIST_HEAD(&isert_conn->conn_accept_node);
init_completion(&isert_conn->conn_login_comp);
- init_waitqueue_head(&isert_conn->conn_wait);
- init_waitqueue_head(&isert_conn->conn_wait_comp_err);
+ init_completion(&isert_conn->login_req_comp);
+ init_completion(&isert_conn->conn_wait);
+ init_completion(&isert_conn->conn_wait_comp_err);
kref_init(&isert_conn->conn_kref);
- kref_get(&isert_conn->conn_kref);
+ mutex_init(&isert_conn->conn_mutex);
- cma_id->context = isert_conn;
isert_conn->conn_cm_id = cma_id;
isert_conn->responder_resources = event->param.conn.responder_resources;
isert_conn->initiator_depth = event->param.conn.initiator_depth;
@@ -449,12 +492,20 @@
if (ret)
goto out_conn_dev;
+ ret = isert_rdma_post_recvl(isert_conn);
+ if (ret)
+ goto out_conn_dev;
+
+ ret = isert_rdma_accept(isert_conn);
+ if (ret)
+ goto out_conn_dev;
+
mutex_lock(&isert_np->np_accept_mutex);
- list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node);
+ list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list);
mutex_unlock(&isert_np->np_accept_mutex);
- pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np);
- wake_up(&isert_np->np_accept_wq);
+ pr_debug("isert_connect_request() up np_sem np: %p\n", np);
+ up(&isert_np->np_sem);
return 0;
out_conn_dev:
@@ -469,6 +520,7 @@
kfree(isert_conn->login_buf);
out:
kfree(isert_conn);
+ rdma_reject(cma_id, NULL, 0);
return ret;
}
@@ -481,18 +533,20 @@
pr_debug("Entering isert_connect_release(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
+ isert_free_rx_descriptors(isert_conn);
+ rdma_destroy_id(isert_conn->conn_cm_id);
+
if (isert_conn->conn_qp) {
cq_index = ((struct isert_cq_desc *)
isert_conn->conn_qp->recv_cq->cq_context)->cq_index;
pr_debug("isert_connect_release: cq_index: %d\n", cq_index);
+ mutex_lock(&device_list_mutex);
isert_conn->conn_device->cq_active_qps[cq_index]--;
+ mutex_unlock(&device_list_mutex);
- rdma_destroy_qp(isert_conn->conn_cm_id);
+ ib_destroy_qp(isert_conn->conn_qp);
}
- isert_free_rx_descriptors(isert_conn);
- rdma_destroy_id(isert_conn->conn_cm_id);
-
if (isert_conn->login_buf) {
ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma,
ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE);
@@ -512,7 +566,19 @@
static void
isert_connected_handler(struct rdma_cm_id *cma_id)
{
- return;
+ struct isert_conn *isert_conn = cma_id->qp->qp_context;
+
+ pr_info("conn %p\n", isert_conn);
+
+ if (!kref_get_unless_zero(&isert_conn->conn_kref)) {
+ pr_warn("conn %p connect_release is running\n", isert_conn);
+ return;
+ }
+
+ mutex_lock(&isert_conn->conn_mutex);
+ if (isert_conn->state != ISER_CONN_FULL_FEATURE)
+ isert_conn->state = ISER_CONN_UP;
+ mutex_unlock(&isert_conn->conn_mutex);
}
static void
@@ -533,32 +599,102 @@
kref_put(&isert_conn->conn_kref, isert_release_conn_kref);
}
+/**
+ * isert_conn_terminate() - Initiate connection termination
+ * @isert_conn: isert connection struct
+ *
+ * Notes:
+ * In case the connection state is FULL_FEATURE, move state
+ * to TEMINATING and start teardown sequence (rdma_disconnect).
+ * In case the connection state is UP, complete flush as well.
+ *
+ * This routine must be called with conn_mutex held. Thus it is
+ * safe to call multiple times.
+ */
static void
-isert_disconnect_work(struct work_struct *work)
+isert_conn_terminate(struct isert_conn *isert_conn)
{
- struct isert_conn *isert_conn = container_of(work,
- struct isert_conn, conn_logout_work);
+ int err;
- pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
+ switch (isert_conn->state) {
+ case ISER_CONN_TERMINATING:
+ break;
+ case ISER_CONN_UP:
+ /*
+ * No flush completions will occur as we didn't
+ * get to ISER_CONN_FULL_FEATURE yet, complete
+ * to allow teardown progress.
+ */
+ complete(&isert_conn->conn_wait_comp_err);
+ case ISER_CONN_FULL_FEATURE: /* FALLTHRU */
+ pr_info("Terminating conn %p state %d\n",
+ isert_conn, isert_conn->state);
+ isert_conn->state = ISER_CONN_TERMINATING;
+ err = rdma_disconnect(isert_conn->conn_cm_id);
+ if (err)
+ pr_warn("Failed rdma_disconnect isert_conn %p\n",
+ isert_conn);
+ break;
+ default:
+ pr_warn("conn %p teminating in state %d\n",
+ isert_conn, isert_conn->state);
+ }
+}
- isert_conn->state = ISER_CONN_DOWN;
+static int
+isert_np_cma_handler(struct isert_np *isert_np,
+ enum rdma_cm_event_type event)
+{
+ pr_debug("isert np %p, handling event %d\n", isert_np, event);
- if (isert_conn->post_recv_buf_count == 0 &&
- atomic_read(&isert_conn->post_send_buf_count) == 0) {
- pr_debug("Calling wake_up(&isert_conn->conn_wait);\n");
- wake_up(&isert_conn->conn_wait);
+ switch (event) {
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ isert_np->np_cm_id = NULL;
+ break;
+ case RDMA_CM_EVENT_ADDR_CHANGE:
+ isert_np->np_cm_id = isert_setup_id(isert_np);
+ if (IS_ERR(isert_np->np_cm_id)) {
+ pr_err("isert np %p setup id failed: %ld\n",
+ isert_np, PTR_ERR(isert_np->np_cm_id));
+ isert_np->np_cm_id = NULL;
+ }
+ break;
+ default:
+ pr_err("isert np %p Unexpected event %d\n",
+ isert_np, event);
}
- isert_put_conn(isert_conn);
+ return -1;
+}
+
+static int
+isert_disconnected_handler(struct rdma_cm_id *cma_id,
+ enum rdma_cm_event_type event)
+{
+ struct isert_np *isert_np = cma_id->context;
+ struct isert_conn *isert_conn;
+
+ if (isert_np->np_cm_id == cma_id)
+ return isert_np_cma_handler(cma_id->context, event);
+
+ isert_conn = cma_id->qp->qp_context;
+
+ mutex_lock(&isert_conn->conn_mutex);
+ isert_conn_terminate(isert_conn);
+ mutex_unlock(&isert_conn->conn_mutex);
+
+ pr_info("conn %p completing conn_wait\n", isert_conn);
+ complete(&isert_conn->conn_wait);
+
+ return 0;
}
static void
-isert_disconnected_handler(struct rdma_cm_id *cma_id)
+isert_connect_error(struct rdma_cm_id *cma_id)
{
- struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context;
+ struct isert_conn *isert_conn = cma_id->qp->qp_context;
- INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
- schedule_work(&isert_conn->conn_logout_work);
+ isert_put_conn(isert_conn);
}
static int
@@ -571,30 +707,28 @@
switch (event->event) {
case RDMA_CM_EVENT_CONNECT_REQUEST:
- pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n");
ret = isert_connect_request(cma_id, event);
+ if (ret)
+ pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
+ event->event, ret);
break;
case RDMA_CM_EVENT_ESTABLISHED:
- pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n");
isert_connected_handler(cma_id);
break;
- case RDMA_CM_EVENT_DISCONNECTED:
- pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n");
- isert_disconnected_handler(cma_id);
+ case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */
+ case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */
+ case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
+ case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */
+ ret = isert_disconnected_handler(cma_id, event->event);
break;
- case RDMA_CM_EVENT_DEVICE_REMOVAL:
- case RDMA_CM_EVENT_ADDR_CHANGE:
- break;
+ case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */
+ case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */
case RDMA_CM_EVENT_CONNECT_ERROR:
- default:
- pr_err("Unknown RDMA CMA event: %d\n", event->event);
+ isert_connect_error(cma_id);
break;
- }
-
- if (ret != 0) {
- pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n",
- event->event, ret);
- dump_stack();
+ default:
+ pr_err("Unhandled RDMA CMA event: %d\n", event->event);
+ break;
}
return ret;
@@ -793,7 +927,10 @@
if (ret)
return ret;
- isert_conn->state = ISER_CONN_UP;
+ /* Now we are in FULL_FEATURE phase */
+ mutex_lock(&isert_conn->conn_mutex);
+ isert_conn->state = ISER_CONN_FULL_FEATURE;
+ mutex_unlock(&isert_conn->conn_mutex);
goto post_send;
}
@@ -810,18 +947,17 @@
}
static void
-isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen,
- struct isert_conn *isert_conn)
+isert_rx_login_req(struct isert_conn *isert_conn)
{
+ struct iser_rx_desc *rx_desc = (void *)isert_conn->login_req_buf;
+ int rx_buflen = isert_conn->login_req_len;
struct iscsi_conn *conn = isert_conn->conn;
struct iscsi_login *login = conn->conn_login;
int size;
- if (!login) {
- pr_err("conn->conn_login is NULL\n");
- dump_stack();
- return;
- }
+ pr_info("conn %p\n", isert_conn);
+
+ WARN_ON_ONCE(!login);
if (login->first_request) {
struct iscsi_login_req *login_req =
@@ -851,7 +987,8 @@
size, rx_buflen, MAX_KEY_VALUE_PAIRS);
memcpy(login->req_buf, &rx_desc->data[0], size);
- complete(&isert_conn->conn_login_comp);
+ if (login->first_request)
+ complete(&isert_conn->conn_login_comp);
}
static void
@@ -934,15 +1071,12 @@
}
sequence_cmd:
- rc = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
+ rc = iscsit_sequence_cmd(conn, cmd, buf, hdr->cmdsn);
if (!rc && dump_payload == false && unsol_data)
iscsit_set_unsoliticed_dataout(cmd);
-
- if (rc == CMDSN_ERROR_CANNOT_RECOVER)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, (unsigned char *)hdr, cmd);
+ else if (dump_payload && imm_data)
+ target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
return 0;
}
@@ -1131,11 +1265,20 @@
hdr->opcode, hdr->itt, hdr->flags,
(int)(xfer_len - ISER_HEADERS_LEN));
- if ((char *)desc == isert_conn->login_req_buf)
- isert_rx_login_req(desc, xfer_len - ISER_HEADERS_LEN,
- isert_conn);
- else
+ if ((char *)desc == isert_conn->login_req_buf) {
+ isert_conn->login_req_len = xfer_len - ISER_HEADERS_LEN;
+ if (isert_conn->conn) {
+ struct iscsi_login *login = isert_conn->conn->conn_login;
+
+ if (login && !login->first_request)
+ isert_rx_login_req(isert_conn);
+ }
+ mutex_lock(&isert_conn->conn_mutex);
+ complete(&isert_conn->login_req_comp);
+ mutex_unlock(&isert_conn->conn_mutex);
+ } else {
isert_rx_do_work(desc, isert_conn);
+ }
ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen,
DMA_FROM_DEVICE);
@@ -1180,40 +1323,53 @@
}
static void
-isert_put_cmd(struct isert_cmd *isert_cmd)
+isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err)
{
struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
struct isert_conn *isert_conn = isert_cmd->conn;
- struct iscsi_conn *conn;
+ struct iscsi_conn *conn = isert_conn->conn;
pr_debug("Entering isert_put_cmd: %p\n", isert_cmd);
switch (cmd->iscsi_opcode) {
case ISCSI_OP_SCSI_CMD:
- conn = isert_conn->conn;
-
spin_lock_bh(&conn->cmd_lock);
if (!list_empty(&cmd->i_conn_node))
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
- if (cmd->data_direction == DMA_TO_DEVICE)
+ if (cmd->data_direction == DMA_TO_DEVICE) {
iscsit_stop_dataout_timer(cmd);
+ /*
+ * Check for special case during comp_err where
+ * WRITE_PENDING has been handed off from core,
+ * but requires an extra target_put_sess_cmd()
+ * before transport_generic_free_cmd() below.
+ */
+ if (comp_err &&
+ cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) {
+ struct se_cmd *se_cmd = &cmd->se_cmd;
+
+ target_put_sess_cmd(se_cmd->se_sess, se_cmd);
+ }
+ }
isert_unmap_cmd(isert_cmd, isert_conn);
- /*
- * Fall-through
- */
+ transport_generic_free_cmd(&cmd->se_cmd, 0);
+ break;
case ISCSI_OP_SCSI_TMFUNC:
+ spin_lock_bh(&conn->cmd_lock);
+ if (!list_empty(&cmd->i_conn_node))
+ list_del_init(&cmd->i_conn_node);
+ spin_unlock_bh(&conn->cmd_lock);
+
transport_generic_free_cmd(&cmd->se_cmd, 0);
break;
case ISCSI_OP_REJECT:
case ISCSI_OP_NOOP_OUT:
- conn = isert_conn->conn;
-
spin_lock_bh(&conn->cmd_lock);
if (!list_empty(&cmd->i_conn_node))
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
/*
@@ -1222,6 +1378,9 @@
* associated cmd->se_cmd needs to be released.
*/
if (cmd->se_cmd.se_tfo != NULL) {
+ pr_debug("Calling transport_generic_free_cmd from"
+ " isert_put_cmd for 0x%02x\n",
+ cmd->iscsi_opcode);
transport_generic_free_cmd(&cmd->se_cmd, 0);
break;
}
@@ -1247,7 +1406,7 @@
static void
isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd,
- struct ib_device *ib_dev)
+ struct ib_device *ib_dev, bool comp_err)
{
if (isert_cmd->sense_buf_dma != 0) {
pr_debug("Calling ib_dma_unmap_single for isert_cmd->sense_buf_dma\n");
@@ -1257,7 +1416,7 @@
}
isert_unmap_tx_desc(tx_desc, ib_dev);
- isert_put_cmd(isert_cmd);
+ isert_put_cmd(isert_cmd, comp_err);
}
static void
@@ -1284,6 +1443,7 @@
}
cmd->write_data_done = se_cmd->data_length;
+ wr->send_wr_num = 0;
pr_debug("isert_do_rdma_read_comp, calling target_execute_cmd\n");
spin_lock_bh(&cmd->istate_lock);
@@ -1311,22 +1471,19 @@
iscsit_tmr_post_handler(cmd, cmd->conn);
cmd->i_state = ISTATE_SENT_STATUS;
- isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+ isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
break;
case ISTATE_SEND_REJECT:
pr_debug("Got isert_do_control_comp ISTATE_SEND_REJECT: >>>\n");
atomic_dec(&isert_conn->post_send_buf_count);
cmd->i_state = ISTATE_SENT_STATUS;
- complete(&cmd->reject_comp);
- isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev);
+ isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false);
+ break;
case ISTATE_SEND_LOGOUTRSP:
pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
- /*
- * Call atomic_dec(&isert_conn->post_send_buf_count)
- * from isert_free_conn()
- */
- isert_conn->logout_posted = true;
+
+ atomic_dec(&isert_conn->post_send_buf_count);
iscsit_logout_post_handler(cmd, cmd->conn);
break;
default:
@@ -1343,19 +1500,21 @@
struct ib_device *ib_dev)
{
struct iscsi_cmd *cmd = &isert_cmd->iscsi_cmd;
+ struct isert_rdma_wr *wr = &isert_cmd->rdma_wr;
if (cmd->i_state == ISTATE_SEND_TASKMGTRSP ||
- cmd->i_state == ISTATE_SEND_LOGOUTRSP) {
+ cmd->i_state == ISTATE_SEND_LOGOUTRSP ||
+ cmd->i_state == ISTATE_SEND_REJECT) {
isert_unmap_tx_desc(tx_desc, ib_dev);
INIT_WORK(&isert_cmd->comp_work, isert_do_control_comp);
queue_work(isert_comp_wq, &isert_cmd->comp_work);
return;
}
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
cmd->i_state = ISTATE_SENT_STATUS;
- isert_completion_put(tx_desc, isert_cmd, ib_dev);
+ isert_completion_put(tx_desc, isert_cmd, ib_dev, false);
}
static void
@@ -1390,7 +1549,7 @@
case ISER_IB_RDMA_READ:
pr_debug("isert_send_completion: Got ISER_IB_RDMA_READ:\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
isert_completion_rdma_read(tx_desc, isert_cmd);
break;
default:
@@ -1401,27 +1560,40 @@
}
static void
-isert_cq_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
+isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn)
{
struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
- if (tx_desc) {
- struct isert_cmd *isert_cmd = tx_desc->isert_cmd;
+ if (!isert_cmd)
+ isert_unmap_tx_desc(tx_desc, ib_dev);
+ else
+ isert_completion_put(tx_desc, isert_cmd, ib_dev, true);
+}
- if (!isert_cmd)
- isert_unmap_tx_desc(tx_desc, ib_dev);
- else
- isert_completion_put(tx_desc, isert_cmd, ib_dev);
+static void
+isert_cq_rx_comp_err(struct isert_conn *isert_conn)
+{
+ struct iscsi_conn *conn = isert_conn->conn;
+
+ if (isert_conn->post_recv_buf_count)
+ return;
+
+ if (conn->sess) {
+ target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+ target_wait_for_sess_cmds(conn->sess->se_sess);
}
- if (isert_conn->post_recv_buf_count == 0 &&
- atomic_read(&isert_conn->post_send_buf_count) == 0) {
- pr_debug("isert_cq_comp_err >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n");
- pr_debug("Calling wake_up from isert_cq_comp_err\n");
+ while (atomic_read(&isert_conn->post_send_buf_count))
+ msleep(3000);
- isert_conn->state = ISER_CONN_TERMINATING;
- wake_up(&isert_conn->conn_wait_comp_err);
- }
+ mutex_lock(&isert_conn->conn_mutex);
+ isert_conn_terminate(isert_conn);
+ mutex_unlock(&isert_conn->conn_mutex);
+
+ iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+
+ complete(&isert_conn->conn_wait_comp_err);
}
static void
@@ -1446,7 +1618,7 @@
pr_debug("TX wc.status != IB_WC_SUCCESS >>>>>>>>>>>>>>\n");
pr_debug("TX wc.status: 0x%08x\n", wc.status);
atomic_dec(&isert_conn->post_send_buf_count);
- isert_cq_comp_err(tx_desc, isert_conn);
+ isert_cq_tx_comp_err(tx_desc, isert_conn);
}
}
@@ -1488,7 +1660,7 @@
pr_debug("RX wc.status: 0x%08x\n", wc.status);
isert_conn->post_recv_buf_count--;
- isert_cq_comp_err(NULL, isert_conn);
+ isert_cq_rx_comp_err(isert_conn);
}
}
@@ -1637,11 +1809,25 @@
struct isert_cmd, iscsi_cmd);
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
struct ib_send_wr *send_wr = &isert_cmd->tx_desc.send_wr;
+ struct ib_device *ib_dev = isert_conn->conn_cm_id->device;
+ struct ib_sge *tx_dsg = &isert_cmd->tx_desc.tx_sg[1];
+ struct iscsi_reject *hdr =
+ (struct iscsi_reject *)&isert_cmd->tx_desc.iscsi_header;
isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc);
- iscsit_build_reject(cmd, conn, (struct iscsi_reject *)
- &isert_cmd->tx_desc.iscsi_header);
+ iscsit_build_reject(cmd, conn, hdr);
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
+
+ hton24(hdr->dlength, ISCSI_HDR_LEN);
+ isert_cmd->sense_buf_dma = ib_dma_map_single(ib_dev,
+ (void *)cmd->buf_ptr, ISCSI_HDR_LEN,
+ DMA_TO_DEVICE);
+ isert_cmd->sense_buf_len = ISCSI_HDR_LEN;
+ tx_dsg->addr = isert_cmd->sense_buf_dma;
+ tx_dsg->length = ISCSI_HDR_LEN;
+ tx_dsg->lkey = isert_conn->conn_mr->lkey;
+ isert_cmd->tx_desc.num_sge = 2;
+
isert_init_send_wr(isert_cmd, send_wr);
pr_debug("Posting Reject IB_WR_SEND >>>>>>>>>>>>>>>>>>>>>>\n");
@@ -1784,12 +1970,12 @@
isert_init_tx_hdrs(isert_conn, &isert_cmd->tx_desc);
isert_init_send_wr(isert_cmd, &isert_cmd->tx_desc.send_wr);
- atomic_inc(&isert_conn->post_send_buf_count);
+ atomic_add(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
if (rc) {
pr_warn("ib_post_send() failed for IB_WR_RDMA_WRITE\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count);
}
pr_debug("Posted RDMA_WRITE + Response for iSER Data READ\n");
return 1;
@@ -1892,12 +2078,12 @@
data_left -= data_len;
}
- atomic_inc(&isert_conn->post_send_buf_count);
+ atomic_add(wr->send_wr_num, &isert_conn->post_send_buf_count);
rc = ib_post_send(isert_conn->conn_qp, wr->send_wr, &wr_failed);
if (rc) {
pr_warn("ib_post_send() failed for IB_WR_RDMA_READ\n");
- atomic_dec(&isert_conn->post_send_buf_count);
+ atomic_sub(wr->send_wr_num, &isert_conn->post_send_buf_count);
}
pr_debug("Posted RDMA_READ memory for ISER Data WRITE\n");
return 0;
@@ -1963,13 +2149,51 @@
return ret;
}
+struct rdma_cm_id *
+isert_setup_id(struct isert_np *isert_np)
+{
+ struct iscsi_np *np = isert_np->np;
+ struct rdma_cm_id *id;
+ struct sockaddr *sa;
+ int ret;
+
+ sa = (struct sockaddr *)&np->np_sockaddr;
+ pr_debug("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa);
+
+ id = rdma_create_id(isert_cma_handler, isert_np,
+ RDMA_PS_TCP, IB_QPT_RC);
+ if (IS_ERR(id)) {
+ pr_err("rdma_create_id() failed: %ld\n", PTR_ERR(id));
+ ret = PTR_ERR(id);
+ goto out;
+ }
+ pr_debug("id %p context %p\n", id, id->context);
+
+ ret = rdma_bind_addr(id, sa);
+ if (ret) {
+ pr_err("rdma_bind_addr() failed: %d\n", ret);
+ goto out_id;
+ }
+
+ ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG);
+ if (ret) {
+ pr_err("rdma_listen() failed: %d\n", ret);
+ goto out_id;
+ }
+
+ return id;
+out_id:
+ rdma_destroy_id(id);
+out:
+ return ERR_PTR(ret);
+}
+
static int
isert_setup_np(struct iscsi_np *np,
struct __kernel_sockaddr_storage *ksockaddr)
{
struct isert_np *isert_np;
struct rdma_cm_id *isert_lid;
- struct sockaddr *sa;
int ret;
isert_np = kzalloc(sizeof(struct isert_np), GFP_KERNEL);
@@ -1977,13 +2201,12 @@
pr_err("Unable to allocate struct isert_np\n");
return -ENOMEM;
}
- init_waitqueue_head(&isert_np->np_accept_wq);
+ sema_init(&isert_np->np_sem, 0);
mutex_init(&isert_np->np_accept_mutex);
INIT_LIST_HEAD(&isert_np->np_accept_list);
init_completion(&isert_np->np_login_comp);
+ isert_np->np = np;
- sa = (struct sockaddr *)ksockaddr;
- pr_debug("ksockaddr: %p, sa: %p\n", ksockaddr, sa);
/*
* Setup the np->np_sockaddr from the passed sockaddr setup
* in iscsi_target_configfs.c code..
@@ -1991,53 +2214,24 @@
memcpy(&np->np_sockaddr, ksockaddr,
sizeof(struct __kernel_sockaddr_storage));
- isert_lid = rdma_create_id(isert_cma_handler, np, RDMA_PS_TCP,
- IB_QPT_RC);
+ isert_lid = isert_setup_id(isert_np);
if (IS_ERR(isert_lid)) {
- pr_err("rdma_create_id() for isert_listen_handler failed: %ld\n",
- PTR_ERR(isert_lid));
ret = PTR_ERR(isert_lid);
goto out;
}
- ret = rdma_bind_addr(isert_lid, sa);
- if (ret) {
- pr_err("rdma_bind_addr() for isert_lid failed: %d\n", ret);
- goto out_lid;
- }
-
- ret = rdma_listen(isert_lid, ISERT_RDMA_LISTEN_BACKLOG);
- if (ret) {
- pr_err("rdma_listen() for isert_lid failed: %d\n", ret);
- goto out_lid;
- }
-
isert_np->np_cm_id = isert_lid;
np->np_context = isert_np;
- pr_debug("Setup isert_lid->context: %p\n", isert_lid->context);
return 0;
-out_lid:
- rdma_destroy_id(isert_lid);
out:
kfree(isert_np);
+
return ret;
}
static int
-isert_check_accept_queue(struct isert_np *isert_np)
-{
- int empty;
-
- mutex_lock(&isert_np->np_accept_mutex);
- empty = list_empty(&isert_np->np_accept_list);
- mutex_unlock(&isert_np->np_accept_mutex);
-
- return empty;
-}
-
-static int
isert_rdma_accept(struct isert_conn *isert_conn)
{
struct rdma_cm_id *cm_id = isert_conn->conn_cm_id;
@@ -2069,13 +2263,27 @@
struct isert_conn *isert_conn = (struct isert_conn *)conn->context;
int ret;
- pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn);
+ pr_info("before login_req comp conn: %p\n", isert_conn);
+ ret = wait_for_completion_interruptible(&isert_conn->login_req_comp);
+ if (ret) {
+ pr_err("isert_conn %p interrupted before got login req\n",
+ isert_conn);
+ return ret;
+ }
+ isert_conn->login_req_comp.done = 0;
+
+ if (!login->first_request)
+ return 0;
+
+ isert_rx_login_req(isert_conn);
+
+ pr_info("before conn_login_comp conn: %p\n", conn);
ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp);
if (ret)
return ret;
- pr_debug("isert_get_login_rx processing login->req: %p\n", login->req);
+ pr_info("processing login->req: %p\n", login->req);
return 0;
}
@@ -2121,16 +2329,19 @@
int max_accept = 0, ret;
accept_wait:
- ret = wait_event_interruptible(isert_np->np_accept_wq,
- !isert_check_accept_queue(isert_np) ||
- np->np_thread_state == ISCSI_NP_THREAD_RESET);
+ ret = down_interruptible(&isert_np->np_sem);
if (max_accept > 5)
return -ENODEV;
spin_lock_bh(&np->np_thread_lock);
- if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+ if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
spin_unlock_bh(&np->np_thread_lock);
- pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+ pr_debug("np_thread_state %d for isert_accept_np\n",
+ np->np_thread_state);
+ /**
+ * No point in stalling here when np_thread
+ * is in state RESET/SHUTDOWN/EXIT - bail
+ **/
return -ENODEV;
}
spin_unlock_bh(&np->np_thread_lock);
@@ -2150,17 +2361,10 @@
isert_conn->conn = conn;
max_accept = 0;
- ret = isert_rdma_post_recvl(isert_conn);
- if (ret)
- return ret;
-
- ret = isert_rdma_accept(isert_conn);
- if (ret)
- return ret;
-
isert_set_conn_info(np, conn, isert_conn);
- pr_debug("Processing isert_accept_np: isert_conn: %p\n", isert_conn);
+ pr_debug("Processing isert_conn: %p\n", isert_conn);
+
return 0;
}
@@ -2169,41 +2373,58 @@
{
struct isert_np *isert_np = (struct isert_np *)np->np_context;
- rdma_destroy_id(isert_np->np_cm_id);
+ if (isert_np->np_cm_id)
+ rdma_destroy_id(isert_np->np_cm_id);
np->np_context = NULL;
kfree(isert_np);
}
-static void isert_free_conn(struct iscsi_conn *conn)
+static void isert_release_work(struct work_struct *work)
+{
+ struct isert_conn *isert_conn = container_of(work,
+ struct isert_conn,
+ release_work);
+
+ pr_info("Starting release conn %p\n", isert_conn);
+
+ wait_for_completion(&isert_conn->conn_wait);
+
+ mutex_lock(&isert_conn->conn_mutex);
+ isert_conn->state = ISER_CONN_DOWN;
+ mutex_unlock(&isert_conn->conn_mutex);
+
+ pr_info("Destroying conn %p\n", isert_conn);
+ isert_put_conn(isert_conn);
+}
+
+static void isert_wait_conn(struct iscsi_conn *conn)
{
struct isert_conn *isert_conn = conn->context;
- pr_debug("isert_free_conn: Starting \n");
- /*
- * Decrement post_send_buf_count for special case when called
- * from isert_do_control_comp() -> iscsit_logout_post_handler()
- */
- if (isert_conn->logout_posted)
- atomic_dec(&isert_conn->post_send_buf_count);
+ pr_debug("isert_wait_conn: Starting \n");
- if (isert_conn->conn_cm_id)
- rdma_disconnect(isert_conn->conn_cm_id);
+ mutex_lock(&isert_conn->conn_mutex);
/*
* Only wait for conn_wait_comp_err if the isert_conn made it
* into full feature phase..
*/
- if (isert_conn->state > ISER_CONN_INIT) {
- pr_debug("isert_free_conn: Before wait_event comp_err %d\n",
- isert_conn->state);
- wait_event(isert_conn->conn_wait_comp_err,
- isert_conn->state == ISER_CONN_TERMINATING);
- pr_debug("isert_free_conn: After wait_event #1 >>>>>>>>>>>>\n");
+ if (isert_conn->state == ISER_CONN_INIT) {
+ mutex_unlock(&isert_conn->conn_mutex);
+ return;
}
+ isert_conn_terminate(isert_conn);
+ mutex_unlock(&isert_conn->conn_mutex);
- pr_debug("isert_free_conn: wait_event conn_wait %d\n", isert_conn->state);
- wait_event(isert_conn->conn_wait, isert_conn->state == ISER_CONN_DOWN);
- pr_debug("isert_free_conn: After wait_event #2 >>>>>>>>>>>>>>>>>>>>\n");
+ wait_for_completion(&isert_conn->conn_wait_comp_err);
+
+ INIT_WORK(&isert_conn->release_work, isert_release_work);
+ queue_work(isert_release_wq, &isert_conn->release_work);
+}
+
+static void isert_free_conn(struct iscsi_conn *conn)
+{
+ struct isert_conn *isert_conn = conn->context;
isert_put_conn(isert_conn);
}
@@ -2215,6 +2436,7 @@
.iscsit_setup_np = isert_setup_np,
.iscsit_accept_np = isert_accept_np,
.iscsit_free_np = isert_free_np,
+ .iscsit_wait_conn = isert_wait_conn,
.iscsit_free_conn = isert_free_conn,
.iscsit_alloc_cmd = isert_alloc_cmd,
.iscsit_get_login_rx = isert_get_login_rx,
@@ -2243,20 +2465,30 @@
goto destroy_rx_wq;
}
+ isert_release_wq = alloc_workqueue("isert_release_wq", WQ_UNBOUND,
+ WQ_UNBOUND_MAX_ACTIVE);
+ if (!isert_release_wq) {
+ pr_err("Unable to allocate isert_release_wq\n");
+ ret = -ENOMEM;
+ goto destroy_comp_wq;
+ }
+
isert_cmd_cache = kmem_cache_create("isert_cmd_cache",
sizeof(struct isert_cmd), __alignof__(struct isert_cmd),
0, NULL);
if (!isert_cmd_cache) {
pr_err("Unable to create isert_cmd_cache\n");
ret = -ENOMEM;
- goto destroy_tx_cq;
+ goto destroy_release_wq;
}
iscsit_register_transport(&iser_target_transport);
- pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n");
+ pr_info("iSER_TARGET[0] - Loaded iser_target_transport\n");
return 0;
-destroy_tx_cq:
+destroy_release_wq:
+ destroy_workqueue(isert_release_wq);
+destroy_comp_wq:
destroy_workqueue(isert_comp_wq);
destroy_rx_wq:
destroy_workqueue(isert_rx_wq);
@@ -2265,7 +2497,9 @@
static void __exit isert_exit(void)
{
+ flush_scheduled_work();
kmem_cache_destroy(isert_cmd_cache);
+ destroy_workqueue(isert_release_wq);
destroy_workqueue(isert_comp_wq);
destroy_workqueue(isert_rx_wq);
iscsit_unregister_transport(&iser_target_transport);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index b104f4c..b233ee5 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -21,6 +21,7 @@
enum iser_conn_state {
ISER_CONN_INIT,
ISER_CONN_UP,
+ ISER_CONN_FULL_FEATURE,
ISER_CONN_TERMINATING,
ISER_CONN_DOWN,
};
@@ -78,7 +79,6 @@
struct isert_conn {
enum iser_conn_state state;
- bool logout_posted;
int post_recv_buf_count;
atomic_t post_send_buf_count;
u32 responder_resources;
@@ -88,6 +88,7 @@
char *login_req_buf;
char *login_rsp_buf;
u64 login_req_dma;
+ int login_req_len;
u64 login_rsp_dma;
unsigned int conn_rx_desc_head;
struct iser_rx_desc *conn_rx_descs;
@@ -95,16 +96,18 @@
struct iscsi_conn *conn;
struct list_head conn_accept_node;
struct completion conn_login_comp;
+ struct completion login_req_comp;
struct iser_tx_desc conn_login_tx_desc;
struct rdma_cm_id *conn_cm_id;
struct ib_pd *conn_pd;
struct ib_mr *conn_mr;
struct ib_qp *conn_qp;
struct isert_device *conn_device;
- struct work_struct conn_logout_work;
- wait_queue_head_t conn_wait;
- wait_queue_head_t conn_wait_comp_err;
+ struct mutex conn_mutex;
+ struct completion conn_wait;
+ struct completion conn_wait_comp_err;
struct kref conn_kref;
+ struct work_struct release_work;
};
#define ISERT_MAX_CQ 64
@@ -130,7 +133,8 @@
};
struct isert_np {
- wait_queue_head_t np_accept_wq;
+ struct iscsi_np *np;
+ struct semaphore np_sem;
struct rdma_cm_id *np_cm_id;
struct mutex np_accept_mutex;
struct list_head np_accept_list;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 7ccf328..35dd5ff 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -93,6 +93,7 @@
static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event);
static struct scsi_transport_template *ib_srp_transport_template;
+static struct workqueue_struct *srp_remove_wq;
static struct ib_client srp_client = {
.name = "srp",
@@ -456,7 +457,7 @@
spin_unlock_irq(&target->lock);
if (changed)
- queue_work(system_long_wq, &target->remove_work);
+ queue_work(srp_remove_wq, &target->remove_work);
return changed;
}
@@ -1300,14 +1301,13 @@
PFX "Recv failed with error code %d\n", res);
}
-static void srp_handle_qp_err(enum ib_wc_status wc_status,
- enum ib_wc_opcode wc_opcode,
+static void srp_handle_qp_err(enum ib_wc_status wc_status, bool send_err,
struct srp_target_port *target)
{
if (target->connected && !target->qp_in_error) {
shost_printk(KERN_ERR, target->scsi_host,
PFX "failed %s status %d\n",
- wc_opcode & IB_WC_RECV ? "receive" : "send",
+ send_err ? "send" : "receive",
wc_status);
}
target->qp_in_error = true;
@@ -1323,7 +1323,7 @@
if (likely(wc.status == IB_WC_SUCCESS)) {
srp_handle_recv(target, &wc);
} else {
- srp_handle_qp_err(wc.status, wc.opcode, target);
+ srp_handle_qp_err(wc.status, false, target);
}
}
}
@@ -1339,7 +1339,7 @@
iu = (struct srp_iu *) (uintptr_t) wc.wr_id;
list_add(&iu->list, &target->free_tx);
} else {
- srp_handle_qp_err(wc.status, wc.opcode, target);
+ srp_handle_qp_err(wc.status, true, target);
}
}
}
@@ -1410,6 +1410,12 @@
err_iu:
srp_put_tx_iu(target, iu, SRP_IU_CMD);
+ /*
+ * Avoid that the loops that iterate over the request ring can
+ * encounter a dangling SCSI command pointer.
+ */
+ req->scmnd = NULL;
+
spin_lock_irqsave(&target->lock, flags);
list_add(&req->list, &target->free_reqs);
@@ -2525,9 +2531,10 @@
spin_unlock(&host->target_lock);
/*
- * Wait for target port removal tasks.
+ * Wait for tl_err and target port removal tasks.
*/
flush_workqueue(system_long_wq);
+ flush_workqueue(srp_remove_wq);
kfree(host);
}
@@ -2572,16 +2579,22 @@
indirect_sg_entries = cmd_sg_entries;
}
+ srp_remove_wq = create_workqueue("srp_remove");
+ if (IS_ERR(srp_remove_wq)) {
+ ret = PTR_ERR(srp_remove_wq);
+ goto out;
+ }
+
+ ret = -ENOMEM;
ib_srp_transport_template =
srp_attach_transport(&ib_srp_transport_functions);
if (!ib_srp_transport_template)
- return -ENOMEM;
+ goto destroy_wq;
ret = class_register(&srp_class);
if (ret) {
pr_err("couldn't register class infiniband_srp\n");
- srp_release_transport(ib_srp_transport_template);
- return ret;
+ goto release_tr;
}
ib_sa_register_client(&srp_sa_client);
@@ -2589,13 +2602,22 @@
ret = ib_register_client(&srp_client);
if (ret) {
pr_err("couldn't register IB client\n");
- srp_release_transport(ib_srp_transport_template);
- ib_sa_unregister_client(&srp_sa_client);
- class_unregister(&srp_class);
- return ret;
+ goto unreg_sa;
}
- return 0;
+out:
+ return ret;
+
+unreg_sa:
+ ib_sa_unregister_client(&srp_sa_client);
+ class_unregister(&srp_class);
+
+release_tr:
+ srp_release_transport(ib_srp_transport_template);
+
+destroy_wq:
+ destroy_workqueue(srp_remove_wq);
+ goto out;
}
static void __exit srp_cleanup_module(void)
@@ -2604,6 +2626,7 @@
ib_sa_unregister_client(&srp_sa_client);
class_unregister(&srp_class);
srp_release_transport(ib_srp_transport_template);
+ destroy_workqueue(srp_remove_wq);
}
module_init(srp_init_module);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 3f3f041..fcf9f87 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -1078,6 +1078,7 @@
static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
struct srpt_send_ioctx *ioctx)
{
+ struct ib_device *dev = ch->sport->sdev->device;
struct se_cmd *cmd;
struct scatterlist *sg, *sg_orig;
int sg_cnt;
@@ -1124,7 +1125,7 @@
db = ioctx->rbufs;
tsize = cmd->data_length;
- dma_len = sg_dma_len(&sg[0]);
+ dma_len = ib_sg_dma_len(dev, &sg[0]);
riu = ioctx->rdma_ius;
/*
@@ -1155,7 +1156,8 @@
++j;
if (j < count) {
sg = sg_next(sg);
- dma_len = sg_dma_len(sg);
+ dma_len = ib_sg_dma_len(
+ dev, sg);
}
}
} else {
@@ -1192,8 +1194,8 @@
tsize = cmd->data_length;
riu = ioctx->rdma_ius;
sg = sg_orig;
- dma_len = sg_dma_len(&sg[0]);
- dma_addr = sg_dma_address(&sg[0]);
+ dma_len = ib_sg_dma_len(dev, &sg[0]);
+ dma_addr = ib_sg_dma_address(dev, &sg[0]);
/* this second loop is really mapped sg_addres to rdma_iu->ib_sge */
for (i = 0, j = 0;
@@ -1216,8 +1218,10 @@
++j;
if (j < count) {
sg = sg_next(sg);
- dma_len = sg_dma_len(sg);
- dma_addr = sg_dma_address(sg);
+ dma_len = ib_sg_dma_len(
+ dev, sg);
+ dma_addr = ib_sg_dma_address(
+ dev, sg);
}
}
} else {
@@ -1588,7 +1592,7 @@
int resp_data_len;
int resp_len;
- resp_data_len = (rsp_code == SRP_TSK_MGMT_SUCCESS) ? 0 : 4;
+ resp_data_len = 4;
resp_len = sizeof(*srp_rsp) + resp_data_len;
srp_rsp = ioctx->ioctx.buf;
@@ -1600,11 +1604,9 @@
+ atomic_xchg(&ch->req_lim_delta, 0));
srp_rsp->tag = tag;
- if (rsp_code != SRP_TSK_MGMT_SUCCESS) {
- srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID;
- srp_rsp->resp_data_len = cpu_to_be32(resp_data_len);
- srp_rsp->data[3] = rsp_code;
- }
+ srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID;
+ srp_rsp->resp_data_len = cpu_to_be32(resp_data_len);
+ srp_rsp->data[3] = rsp_code;
return resp_len;
}
@@ -2099,6 +2101,7 @@
if (!qp_init)
goto out;
+retry:
ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
ch->rq_size + srp_sq_size, 0);
if (IS_ERR(ch->cq)) {
@@ -2122,6 +2125,13 @@
ch->qp = ib_create_qp(sdev->pd, qp_init);
if (IS_ERR(ch->qp)) {
ret = PTR_ERR(ch->qp);
+ if (ret == -ENOMEM) {
+ srp_sq_size /= 2;
+ if (srp_sq_size >= MIN_SRPT_SQ_SIZE) {
+ ib_destroy_cq(ch->cq);
+ goto retry;
+ }
+ }
printk(KERN_ERR "failed to create_qp ret= %d\n", ret);
goto err_destroy_cq;
}
@@ -2358,6 +2368,8 @@
transport_deregister_session(se_sess);
ch->sess = NULL;
+ ib_destroy_cm_id(ch->cm_id);
+
srpt_destroy_ch_ib(ch);
srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring,
@@ -2368,8 +2380,6 @@
list_del(&ch->list);
spin_unlock_irq(&sdev->spinlock);
- ib_destroy_cm_id(ch->cm_id);
-
if (ch->release_done)
complete(ch->release_done);
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 38b523a..a11ff74 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -80,7 +80,7 @@
comment "Userland interfaces"
config INPUT_MOUSEDEV
- tristate "Mouse interface" if EXPERT
+ tristate "Mouse interface"
default y
help
Say Y here if you want your mouse to be accessible as char devices
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index f0f8928..c122dd2 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -18,6 +18,8 @@
#include <linux/poll.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/input/mt.h>
@@ -289,7 +291,11 @@
mutex_unlock(&evdev->mutex);
evdev_detach_client(evdev, client);
- kfree(client);
+
+ if (is_vmalloc_addr(client))
+ vfree(client);
+ else
+ kfree(client);
evdev_close_device(evdev);
@@ -309,12 +315,14 @@
{
struct evdev *evdev = container_of(inode->i_cdev, struct evdev, cdev);
unsigned int bufsize = evdev_compute_buffer_size(evdev->handle.dev);
+ unsigned int size = sizeof(struct evdev_client) +
+ bufsize * sizeof(struct input_event);
struct evdev_client *client;
int error;
- client = kzalloc(sizeof(struct evdev_client) +
- bufsize * sizeof(struct input_event),
- GFP_KERNEL);
+ client = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+ if (!client)
+ client = vzalloc(size);
if (!client)
return -ENOMEM;
diff --git a/drivers/input/input.c b/drivers/input/input.c
index c044699..a161021 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -257,9 +257,10 @@
}
static int input_get_disposition(struct input_dev *dev,
- unsigned int type, unsigned int code, int value)
+ unsigned int type, unsigned int code, int *pval)
{
int disposition = INPUT_IGNORE_EVENT;
+ int value = *pval;
switch (type) {
@@ -357,6 +358,7 @@
break;
}
+ *pval = value;
return disposition;
}
@@ -365,7 +367,7 @@
{
int disposition;
- disposition = input_get_disposition(dev, type, code, value);
+ disposition = input_get_disposition(dev, type, code, &value);
if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event)
dev->event(dev, type, code, value);
@@ -1866,6 +1868,10 @@
break;
case EV_ABS:
+ input_alloc_absinfo(dev);
+ if (!dev->absinfo)
+ return;
+
__set_bit(code, dev->absbit);
break;
diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index fa061d4..856c1b0 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -167,6 +167,7 @@
{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
{ 0x1689, 0xfd00, "Razer Onza Tournament Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
+ { 0x1689, 0xfd01, "Razer Onza Classic Edition", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
{ 0x1bad, 0xf016, "Mad Catz Xbox 360 Controller", 0, XTYPE_XBOX360 },
@@ -1001,9 +1002,19 @@
}
ep_irq_in = &intf->cur_altsetting->endpoint[1].desc;
- usb_fill_bulk_urb(xpad->bulk_out, udev,
- usb_sndbulkpipe(udev, ep_irq_in->bEndpointAddress),
- xpad->bdata, XPAD_PKT_LEN, xpad_bulk_out, xpad);
+ if (usb_endpoint_is_bulk_out(ep_irq_in)) {
+ usb_fill_bulk_urb(xpad->bulk_out, udev,
+ usb_sndbulkpipe(udev,
+ ep_irq_in->bEndpointAddress),
+ xpad->bdata, XPAD_PKT_LEN,
+ xpad_bulk_out, xpad);
+ } else {
+ usb_fill_int_urb(xpad->bulk_out, udev,
+ usb_sndintpipe(udev,
+ ep_irq_in->bEndpointAddress),
+ xpad->bdata, XPAD_PKT_LEN,
+ xpad_bulk_out, xpad, 0);
+ }
/*
* Submit the int URB immediately rather than waiting for open
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 7ac9c98..292f324 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -2,7 +2,7 @@
# Input core configuration
#
menuconfig INPUT_KEYBOARD
- bool "Keyboards" if EXPERT || !X86
+ bool "Keyboards"
default y
help
Say Y here, and a list of supported keyboards will be displayed.
@@ -67,7 +67,7 @@
module will be called atakbd.
config KEYBOARD_ATKBD
- tristate "AT keyboard" if EXPERT || !X86
+ tristate "AT keyboard"
default y
select SERIO
select SERIO_LIBPS2
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 2626773..6f5d795 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -243,6 +243,12 @@
static void *atkbd_platform_fixup_data;
static unsigned int (*atkbd_platform_scancode_fixup)(struct atkbd *, unsigned int);
+/*
+ * Certain keyboards to not like ATKBD_CMD_RESET_DIS and stop responding
+ * to many commands until full reset (ATKBD_CMD_RESET_BAT) is performed.
+ */
+static bool atkbd_skip_deactivate;
+
static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf,
ssize_t (*handler)(struct atkbd *, char *));
static ssize_t atkbd_attr_set_helper(struct device *dev, const char *buf, size_t count,
@@ -768,7 +774,8 @@
* Make sure nothing is coming from the keyboard and disturbs our
* internal state.
*/
- atkbd_deactivate(atkbd);
+ if (!atkbd_skip_deactivate)
+ atkbd_deactivate(atkbd);
return 0;
}
@@ -1638,6 +1645,12 @@
return 1;
}
+static int __init atkbd_deactivate_fixup(const struct dmi_system_id *id)
+{
+ atkbd_skip_deactivate = true;
+ return 1;
+}
+
static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
{
.matches = {
@@ -1775,6 +1788,12 @@
.callback = atkbd_setup_scancode_fixup,
.driver_data = atkbd_oqo_01plus_scancode_fixup,
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+ },
+ .callback = atkbd_deactivate_fixup,
+ },
{ }
};
diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c
index 7a04f54..e7e12a5 100644
--- a/drivers/input/misc/arizona-haptics.c
+++ b/drivers/input/misc/arizona-haptics.c
@@ -77,16 +77,14 @@
return;
}
+ mutex_unlock(dapm_mutex);
+
ret = snd_soc_dapm_sync(arizona->dapm);
if (ret != 0) {
dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
-
- mutex_unlock(dapm_mutex);
-
} else {
/* This disable sequence will be a noop if already enabled */
mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
@@ -99,16 +97,15 @@
return;
}
+ mutex_unlock(dapm_mutex);
+
ret = snd_soc_dapm_sync(arizona->dapm);
if (ret != 0) {
dev_err(arizona->dev, "Failed to sync DAPM: %d\n",
ret);
- mutex_unlock(dapm_mutex);
return;
}
- mutex_unlock(dapm_mutex);
-
ret = regmap_update_bits(arizona->regmap,
ARIZONA_HAPTICS_CONTROL_1,
ARIZONA_HAP_CTRL_MASK,
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 7c5d72a..19e070f 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -873,7 +873,13 @@
{
struct alps_data *priv = psmouse->private;
- if ((psmouse->packet[0] & 0xc8) == 0x08) { /* PS/2 packet */
+ /*
+ * Check if we are dealing with a bare PS/2 packet, presumably from
+ * a device connected to the external PS/2 port. Because bare PS/2
+ * protocol does not have enough constant bits to self-synchronize
+ * properly we only do this if the device is fully synchronized.
+ */
+ if (!psmouse->out_of_sync_cnt && (psmouse->packet[0] & 0xc8) == 0x08) {
if (psmouse->pktcnt == 3) {
alps_report_bare_ps2_packet(psmouse, psmouse->packet,
true);
@@ -1816,6 +1822,9 @@
/* We are having trouble resyncing ALPS touchpads so disable it for now */
psmouse->resync_time = 0;
+ /* Allow 2 invalid packets without resetting device */
+ psmouse->resetafter = psmouse->pktsize * 2;
+
return 0;
init_fail:
diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index 2baff1b..a73f961 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -88,6 +88,10 @@
#define USB_DEVICE_ID_APPLE_WELLSPRING7A_ANSI 0x0259
#define USB_DEVICE_ID_APPLE_WELLSPRING7A_ISO 0x025a
#define USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS 0x025b
+/* MacbookAir6,2 (unibody, June 2013) */
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291
+#define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292
#define BCM5974_DEVICE(prod) { \
.match_flags = (USB_DEVICE_ID_MATCH_DEVICE | \
@@ -145,6 +149,10 @@
BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7A_ANSI),
BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7A_ISO),
BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS),
+ /* MacbookAir6,2 */
+ BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI),
+ BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ISO),
+ BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
/* Terminating entry */
{}
};
@@ -172,15 +180,18 @@
/* trackpad header types */
enum tp_type {
TYPE1, /* plain trackpad */
- TYPE2 /* button integrated in trackpad */
+ TYPE2, /* button integrated in trackpad */
+ TYPE3 /* additional header fields since June 2013 */
};
/* trackpad finger data offsets, le16-aligned */
#define FINGER_TYPE1 (13 * sizeof(__le16))
#define FINGER_TYPE2 (15 * sizeof(__le16))
+#define FINGER_TYPE3 (19 * sizeof(__le16))
/* trackpad button data offsets */
#define BUTTON_TYPE2 15
+#define BUTTON_TYPE3 23
/* list of device capability bits */
#define HAS_INTEGRATED_BUTTON 1
@@ -400,6 +411,19 @@
{ SN_COORD, -150, 6730 },
{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
},
+ {
+ USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI,
+ USB_DEVICE_ID_APPLE_WELLSPRING8_ISO,
+ USB_DEVICE_ID_APPLE_WELLSPRING8_JIS,
+ HAS_INTEGRATED_BUTTON,
+ 0, sizeof(struct bt_data),
+ 0x83, TYPE3, FINGER_TYPE3, FINGER_TYPE3 + SIZEOF_ALL_FINGERS,
+ { SN_PRESSURE, 0, 300 },
+ { SN_WIDTH, 0, 2048 },
+ { SN_COORD, -4620, 5140 },
+ { SN_COORD, -150, 6600 },
+ { SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
+ },
{}
};
@@ -557,6 +581,9 @@
input_report_key(input, BTN_LEFT, ibt);
}
+ if (c->tp_type == TYPE3)
+ input_report_key(input, BTN_LEFT, dev->tp_data[BUTTON_TYPE3]);
+
input_sync(input);
return 0;
@@ -572,9 +599,14 @@
static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
{
- char *data = kmalloc(8, GFP_KERNEL);
int retval = 0, size;
+ char *data;
+ /* Type 3 does not require a mode switch */
+ if (dev->cfg.tp_type == TYPE3)
+ return 0;
+
+ data = kmalloc(8, GFP_KERNEL);
if (!data) {
dev_err(&dev->intf->dev, "out of memory\n");
retval = -ENOMEM;
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index f51765f..0aaea7a 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -410,7 +410,6 @@
__clear_bit(REL_X, input->relbit);
__clear_bit(REL_Y, input->relbit);
- __set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
__set_bit(EV_KEY, input->evbit);
__set_bit(BTN_LEFT, input->keybit);
__set_bit(BTN_RIGHT, input->keybit);
@@ -439,7 +438,7 @@
case 2: return 5;
default:
/* Invalid contact (e.g. palm). Ignore it. */
- return -1;
+ return 0;
}
}
@@ -452,17 +451,10 @@
{
unsigned char *packet = psmouse->packet;
unsigned char header_byte = packet[0];
- int contact_cnt;
memset(report_data, 0, sizeof(struct cytp_report_data));
- contact_cnt = cypress_get_finger_count(header_byte);
-
- if (contact_cnt < 0) /* e.g. palm detect */
- return -EINVAL;
-
- report_data->contact_cnt = contact_cnt;
-
+ report_data->contact_cnt = cypress_get_finger_count(header_byte);
report_data->tap = (header_byte & ABS_MULTIFINGER_TAP) ? 1 : 0;
if (report_data->contact_cnt == 1) {
@@ -535,11 +527,9 @@
int slots[CYTP_MAX_MT_SLOTS];
int n;
- if (cypress_parse_packet(psmouse, cytp, &report_data))
- return;
+ cypress_parse_packet(psmouse, cytp, &report_data);
n = report_data.contact_cnt;
-
if (n > CYTP_MAX_MT_SLOTS)
n = CYTP_MAX_MT_SLOTS;
@@ -605,10 +595,6 @@
return PSMOUSE_BAD_DATA;
contact_cnt = cypress_get_finger_count(packet[0]);
-
- if (contact_cnt < 0)
- return PSMOUSE_BAD_DATA;
-
if (cytp->mode & CYTP_BIT_ABS_NO_PRESSURE)
cypress_set_packet_size(psmouse, contact_cnt == 2 ? 7 : 4);
else
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 1e8e42f..1af7df2 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -11,6 +11,7 @@
*/
#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/input.h>
@@ -472,8 +473,15 @@
input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2);
input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
- input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
- input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+
+ /* For clickpads map both buttons to BTN_LEFT */
+ if (etd->fw_version & 0x001000) {
+ input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+ } else {
+ input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+ input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+ }
+
input_report_abs(dev, ABS_PRESSURE, pres);
input_report_abs(dev, ABS_TOOL_WIDTH, width);
@@ -483,9 +491,17 @@
static void elantech_input_sync_v4(struct psmouse *psmouse)
{
struct input_dev *dev = psmouse->dev;
+ struct elantech_data *etd = psmouse->private;
unsigned char *packet = psmouse->packet;
- input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+ /* For clickpads map both buttons to BTN_LEFT */
+ if (etd->fw_version & 0x001000) {
+ input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+ } else {
+ input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+ input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+ }
+
input_mt_report_pointer_emulation(dev, true);
input_sync(dev);
}
@@ -768,6 +784,21 @@
}
/*
+ * This writes the reg_07 value again to the hardware at the end of every
+ * set_rate call because the register loses its value. reg_07 allows setting
+ * absolute mode on v4 hardware
+ */
+static void elantech_set_rate_restore_reg_07(struct psmouse *psmouse,
+ unsigned int rate)
+{
+ struct elantech_data *etd = psmouse->private;
+
+ etd->original_set_rate(psmouse, rate);
+ if (elantech_write_reg(psmouse, 0x07, etd->reg_07))
+ psmouse_err(psmouse, "restoring reg_07 failed\n");
+}
+
+/*
* Put the touchpad into absolute mode
*/
static int elantech_set_absolute_mode(struct psmouse *psmouse)
@@ -800,7 +831,11 @@
break;
case 3:
- etd->reg_10 = 0x0b;
+ if (etd->set_hw_resolution)
+ etd->reg_10 = 0x0b;
+ else
+ etd->reg_10 = 0x01;
+
if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
rc = -1;
@@ -954,6 +989,46 @@
}
/*
+ * Advertise INPUT_PROP_BUTTONPAD for clickpads. The testing of bit 12 in
+ * fw_version for this is based on the following fw_version & caps table:
+ *
+ * Laptop-model: fw_version: caps: buttons:
+ * Acer S3 0x461f00 10, 13, 0e clickpad
+ * Acer S7-392 0x581f01 50, 17, 0d clickpad
+ * Acer V5-131 0x461f02 01, 16, 0c clickpad
+ * Acer V5-551 0x461f00 ? clickpad
+ * Asus K53SV 0x450f01 78, 15, 0c 2 hw buttons
+ * Asus G46VW 0x460f02 00, 18, 0c 2 hw buttons
+ * Asus G750JX 0x360f00 00, 16, 0c 2 hw buttons
+ * Asus TP500LN 0x381f17 10, 14, 0e clickpad
+ * Asus X750JN 0x381f17 10, 14, 0e clickpad
+ * Asus UX31 0x361f00 20, 15, 0e clickpad
+ * Asus UX32VD 0x361f02 00, 15, 0e clickpad
+ * Avatar AVIU-145A2 0x361f00 ? clickpad
+ * Gigabyte U2442 0x450f01 58, 17, 0c 2 hw buttons
+ * Lenovo L430 0x350f02 b9, 15, 0c 2 hw buttons (*)
+ * Samsung NF210 0x150b00 78, 14, 0a 2 hw buttons
+ * Samsung NP770Z5E 0x575f01 10, 15, 0f clickpad
+ * Samsung NP700Z5B 0x361f06 21, 15, 0f clickpad
+ * Samsung NP900X3E-A02 0x575f03 ? clickpad
+ * Samsung NP-QX410 0x851b00 19, 14, 0c clickpad
+ * Samsung RC512 0x450f00 08, 15, 0c 2 hw buttons
+ * Samsung RF710 0x450f00 ? 2 hw buttons
+ * System76 Pangolin 0x250f01 ? 2 hw buttons
+ * (*) + 3 trackpoint buttons
+ */
+static void elantech_set_buttonpad_prop(struct psmouse *psmouse)
+{
+ struct input_dev *dev = psmouse->dev;
+ struct elantech_data *etd = psmouse->private;
+
+ if (etd->fw_version & 0x001000) {
+ __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
+ __clear_bit(BTN_RIGHT, dev->keybit);
+ }
+}
+
+/*
* Set the appropriate event bits for the input subsystem
*/
static int elantech_set_input_params(struct psmouse *psmouse)
@@ -996,6 +1071,8 @@
__set_bit(INPUT_PROP_SEMI_MT, dev->propbit);
/* fall through */
case 3:
+ if (etd->hw_version == 3)
+ elantech_set_buttonpad_prop(psmouse);
input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
input_set_abs_params(dev, ABS_Y, y_min, y_max, 0, 0);
if (etd->reports_pressure) {
@@ -1017,9 +1094,7 @@
*/
psmouse_warn(psmouse, "couldn't query resolution data.\n");
}
- /* v4 is clickpad, with only one button. */
- __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
- __clear_bit(BTN_RIGHT, dev->keybit);
+ elantech_set_buttonpad_prop(psmouse);
__set_bit(BTN_TOOL_QUADTAP, dev->keybit);
/* For X to recognize me as touchpad. */
input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
@@ -1165,6 +1240,13 @@
if (param[1] == 0)
return true;
+ /*
+ * Some models have a revision higher then 20. Meaning param[2] may
+ * be 10 or 20, skip the rates check for these.
+ */
+ if (param[0] == 0x46 && (param[1] & 0xef) == 0x0f && param[2] < 40)
+ return true;
+
for (i = 0; i < ARRAY_SIZE(rates); i++)
if (param[2] == rates[i])
return false;
@@ -1262,6 +1344,23 @@
}
/*
+ * Some hw_version 3 models go into error state when we try to set
+ * bit 3 and/or bit 1 of r10.
+ */
+static const struct dmi_system_id no_hw_res_dmi_table[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+ {
+ /* Gigabyte U2442 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "U2442"),
+ },
+ },
+#endif
+ { }
+};
+
+/*
* determine hardware version and set some properties according to it.
*/
static int elantech_set_properties(struct elantech_data *etd)
@@ -1312,6 +1411,9 @@
etd->reports_pressure = true;
}
+ /* Enable real hardware resolution on hw_version 3 ? */
+ etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
+
return 0;
}
@@ -1367,6 +1469,11 @@
goto init_fail;
}
+ if (etd->fw_version == 0x381f17) {
+ etd->original_set_rate = psmouse->set_rate;
+ psmouse->set_rate = elantech_set_rate_restore_reg_07;
+ }
+
if (elantech_set_input_params(psmouse)) {
psmouse_err(psmouse, "failed to query touchpad range.\n");
goto init_fail;
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index 46db3be..13a12cc 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -129,6 +129,7 @@
bool paritycheck;
bool jumpy_cursor;
bool reports_pressure;
+ bool set_hw_resolution;
unsigned char hw_version;
unsigned int fw_version;
unsigned int single_finger_reports;
@@ -137,6 +138,7 @@
struct finger_pos mt[ETP_MAX_FINGERS];
unsigned char parity[256];
int (*send_cmd)(struct psmouse *psmouse, unsigned char c, unsigned char *param);
+ void (*original_set_rate)(struct psmouse *psmouse, unsigned int rate);
};
#ifdef CONFIG_MOUSE_PS2_ELANTECH
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index b2420ae..d1c47d1 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -265,11 +265,22 @@
* Read touchpad resolution and maximum reported coordinates
* Resolution is left zero if touchpad does not support the query
*/
+
+static const int *quirk_min_max;
+
static int synaptics_resolution(struct psmouse *psmouse)
{
struct synaptics_data *priv = psmouse->private;
unsigned char resp[3];
+ if (quirk_min_max) {
+ priv->x_min = quirk_min_max[0];
+ priv->x_max = quirk_min_max[1];
+ priv->y_min = quirk_min_max[2];
+ priv->y_max = quirk_min_max[3];
+ return 0;
+ }
+
if (SYN_ID_MAJOR(priv->identity) < 4)
return 0;
@@ -538,10 +549,61 @@
((buf[0] & 0x04) >> 1) |
((buf[3] & 0x04) >> 2));
+ if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
+ SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
+ hw->w == 2) {
+ synaptics_parse_agm(buf, priv, hw);
+ return 1;
+ }
+
+ hw->x = (((buf[3] & 0x10) << 8) |
+ ((buf[1] & 0x0f) << 8) |
+ buf[4]);
+ hw->y = (((buf[3] & 0x20) << 7) |
+ ((buf[1] & 0xf0) << 4) |
+ buf[5]);
+ hw->z = buf[2];
+
hw->left = (buf[0] & 0x01) ? 1 : 0;
hw->right = (buf[0] & 0x02) ? 1 : 0;
- if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
+ if (SYN_CAP_FORCEPAD(priv->ext_cap_0c)) {
+ /*
+ * ForcePads, like Clickpads, use middle button
+ * bits to report primary button clicks.
+ * Unfortunately they report primary button not
+ * only when user presses on the pad above certain
+ * threshold, but also when there are more than one
+ * finger on the touchpad, which interferes with
+ * out multi-finger gestures.
+ */
+ if (hw->z == 0) {
+ /* No contacts */
+ priv->press = priv->report_press = false;
+ } else if (hw->w >= 4 && ((buf[0] ^ buf[3]) & 0x01)) {
+ /*
+ * Single-finger touch with pressure above
+ * the threshold. If pressure stays long
+ * enough, we'll start reporting primary
+ * button. We rely on the device continuing
+ * sending data even if finger does not
+ * move.
+ */
+ if (!priv->press) {
+ priv->press_start = jiffies;
+ priv->press = true;
+ } else if (time_after(jiffies,
+ priv->press_start +
+ msecs_to_jiffies(50))) {
+ priv->report_press = true;
+ }
+ } else {
+ priv->press = false;
+ }
+
+ hw->left = priv->report_press;
+
+ } else if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
/*
* Clickpad's button is transmitted as middle button,
* however, since it is primary button, we will report
@@ -560,21 +622,6 @@
hw->down = ((buf[0] ^ buf[3]) & 0x02) ? 1 : 0;
}
- if ((SYN_CAP_ADV_GESTURE(priv->ext_cap_0c) ||
- SYN_CAP_IMAGE_SENSOR(priv->ext_cap_0c)) &&
- hw->w == 2) {
- synaptics_parse_agm(buf, priv, hw);
- return 1;
- }
-
- hw->x = (((buf[3] & 0x10) << 8) |
- ((buf[1] & 0x0f) << 8) |
- buf[4]);
- hw->y = (((buf[3] & 0x20) << 7) |
- ((buf[1] & 0xf0) << 4) |
- buf[5]);
- hw->z = buf[2];
-
if (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) &&
((buf[0] ^ buf[3]) & 0x02)) {
switch (SYN_CAP_MULTI_BUTTON_NO(priv->ext_cap) & ~0x01) {
@@ -1485,10 +1532,112 @@
{ }
};
+static const struct dmi_system_id min_max_dmi_table[] __initconst = {
+#if defined(CONFIG_DMI)
+ {
+ /* Lenovo ThinkPad Helix */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
+ },
+ .driver_data = (int []){1024, 5052, 2258, 4832},
+ },
+ {
+ /* Lenovo ThinkPad X240 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
+ },
+ .driver_data = (int []){1232, 5710, 1156, 4696},
+ },
+ {
+ /* Lenovo ThinkPad Edge E431 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Edge E431"),
+ },
+ .driver_data = (int []){1024, 5022, 2508, 4832},
+ },
+ {
+ /* Lenovo ThinkPad T431s */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T431"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad T440s */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad L440 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L440"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad T540p */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad L540 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L540"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo ThinkPad W540 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W540"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+ {
+ /* Lenovo Yoga S1 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+ "ThinkPad S1 Yoga"),
+ },
+ .driver_data = (int []){1232, 5710, 1156, 4696},
+ },
+ {
+ /* Lenovo ThinkPad X1 Carbon Haswell (3rd generation) */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION,
+ "ThinkPad X1 Carbon 2nd"),
+ },
+ .driver_data = (int []){1024, 5112, 2024, 4832},
+ },
+#endif
+ { }
+};
+
void __init synaptics_module_init(void)
{
+ const struct dmi_system_id *min_max_dmi;
+
impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
broken_olpc_ec = dmi_check_system(olpc_dmi_table);
+
+ min_max_dmi = dmi_first_match(min_max_dmi_table);
+ if (min_max_dmi)
+ quirk_min_max = min_max_dmi->driver_data;
}
static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h
index e594af0..fb2e076 100644
--- a/drivers/input/mouse/synaptics.h
+++ b/drivers/input/mouse/synaptics.h
@@ -78,6 +78,11 @@
* 2 0x08 image sensor image sensor tracks 5 fingers, but only
* reports 2.
* 2 0x20 report min query 0x0f gives min coord reported
+ * 2 0x80 forcepad forcepad is a variant of clickpad that
+ * does not have physical buttons but rather
+ * uses pressure above certain threshold to
+ * report primary clicks. Forcepads also have
+ * clickpad bit set.
*/
#define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */
#define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */
@@ -86,6 +91,7 @@
#define SYN_CAP_ADV_GESTURE(ex0c) ((ex0c) & 0x080000)
#define SYN_CAP_REDUCED_FILTERING(ex0c) ((ex0c) & 0x000400)
#define SYN_CAP_IMAGE_SENSOR(ex0c) ((ex0c) & 0x000800)
+#define SYN_CAP_FORCEPAD(ex0c) ((ex0c) & 0x008000)
/* synaptics modes query bits */
#define SYN_MODE_ABSOLUTE(m) ((m) & (1 << 7))
@@ -177,6 +183,11 @@
*/
struct synaptics_hw_state agm;
bool agm_pending; /* new AGM packet received */
+
+ /* ForcePad handling */
+ unsigned long press_start;
+ bool press;
+ bool report_press;
};
void synaptics_module_init(void);
diff --git a/drivers/input/mousedev.c b/drivers/input/mousedev.c
index 4c842c3..b604564 100644
--- a/drivers/input/mousedev.c
+++ b/drivers/input/mousedev.c
@@ -67,7 +67,6 @@
struct device dev;
struct cdev cdev;
bool exist;
- bool is_mixdev;
struct list_head mixdev_node;
bool opened_by_mixdev;
@@ -77,6 +76,9 @@
int old_x[4], old_y[4];
int frac_dx, frac_dy;
unsigned long touch;
+
+ int (*open_device)(struct mousedev *mousedev);
+ void (*close_device)(struct mousedev *mousedev);
};
enum mousedev_emul {
@@ -116,9 +118,6 @@
static struct mousedev *mousedev_mix;
static LIST_HEAD(mousedev_mix_list);
-static void mixdev_open_devices(void);
-static void mixdev_close_devices(void);
-
#define fx(i) (mousedev->old_x[(mousedev->pkt_count - (i)) & 03])
#define fy(i) (mousedev->old_y[(mousedev->pkt_count - (i)) & 03])
@@ -428,9 +427,7 @@
if (retval)
return retval;
- if (mousedev->is_mixdev)
- mixdev_open_devices();
- else if (!mousedev->exist)
+ if (!mousedev->exist)
retval = -ENODEV;
else if (!mousedev->open++) {
retval = input_open_device(&mousedev->handle);
@@ -446,9 +443,7 @@
{
mutex_lock(&mousedev->mutex);
- if (mousedev->is_mixdev)
- mixdev_close_devices();
- else if (mousedev->exist && !--mousedev->open)
+ if (mousedev->exist && !--mousedev->open)
input_close_device(&mousedev->handle);
mutex_unlock(&mousedev->mutex);
@@ -459,21 +454,29 @@
* stream. Note that this function is called with mousedev_mix->mutex
* held.
*/
-static void mixdev_open_devices(void)
+static int mixdev_open_devices(struct mousedev *mixdev)
{
- struct mousedev *mousedev;
+ int error;
- if (mousedev_mix->open++)
- return;
+ error = mutex_lock_interruptible(&mixdev->mutex);
+ if (error)
+ return error;
- list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
- if (!mousedev->opened_by_mixdev) {
- if (mousedev_open_device(mousedev))
- continue;
+ if (!mixdev->open++) {
+ struct mousedev *mousedev;
- mousedev->opened_by_mixdev = true;
+ list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+ if (!mousedev->opened_by_mixdev) {
+ if (mousedev_open_device(mousedev))
+ continue;
+
+ mousedev->opened_by_mixdev = true;
+ }
}
}
+
+ mutex_unlock(&mixdev->mutex);
+ return 0;
}
/*
@@ -481,19 +484,22 @@
* device. Note that this function is called with mousedev_mix->mutex
* held.
*/
-static void mixdev_close_devices(void)
+static void mixdev_close_devices(struct mousedev *mixdev)
{
- struct mousedev *mousedev;
+ mutex_lock(&mixdev->mutex);
- if (--mousedev_mix->open)
- return;
+ if (!--mixdev->open) {
+ struct mousedev *mousedev;
- list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
- if (mousedev->opened_by_mixdev) {
- mousedev->opened_by_mixdev = false;
- mousedev_close_device(mousedev);
+ list_for_each_entry(mousedev, &mousedev_mix_list, mixdev_node) {
+ if (mousedev->opened_by_mixdev) {
+ mousedev->opened_by_mixdev = false;
+ mousedev_close_device(mousedev);
+ }
}
}
+
+ mutex_unlock(&mixdev->mutex);
}
@@ -522,7 +528,7 @@
mousedev_detach_client(mousedev, client);
kfree(client);
- mousedev_close_device(mousedev);
+ mousedev->close_device(mousedev);
return 0;
}
@@ -550,7 +556,7 @@
client->mousedev = mousedev;
mousedev_attach_client(mousedev, client);
- error = mousedev_open_device(mousedev);
+ error = mousedev->open_device(mousedev);
if (error)
goto err_free_client;
@@ -861,16 +867,21 @@
if (mixdev) {
dev_set_name(&mousedev->dev, "mice");
+
+ mousedev->open_device = mixdev_open_devices;
+ mousedev->close_device = mixdev_close_devices;
} else {
int dev_no = minor;
/* Normalize device number if it falls into legacy range */
if (dev_no < MOUSEDEV_MINOR_BASE + MOUSEDEV_MINORS)
dev_no -= MOUSEDEV_MINOR_BASE;
dev_set_name(&mousedev->dev, "mouse%d", dev_no);
+
+ mousedev->open_device = mousedev_open_device;
+ mousedev->close_device = mousedev_close_device;
}
mousedev->exist = true;
- mousedev->is_mixdev = mixdev;
mousedev->handle.dev = input_get_device(dev);
mousedev->handle.name = dev_name(&mousedev->dev);
mousedev->handle.handler = handler;
@@ -919,7 +930,7 @@
device_del(&mousedev->dev);
mousedev_cleanup(mousedev);
input_free_minor(MINOR(mousedev->dev.devt));
- if (!mousedev->is_mixdev)
+ if (mousedev != mousedev_mix)
input_unregister_handle(&mousedev->handle);
put_device(&mousedev->dev);
}
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 1bda828..0455a27 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -2,7 +2,7 @@
# Input core configuration
#
config SERIO
- tristate "Serial I/O support" if EXPERT || !X86
+ tristate "Serial I/O support"
default y
help
Say Yes here if you have any input device that uses serial I/O to
@@ -19,7 +19,7 @@
if SERIO
config SERIO_I8042
- tristate "i8042 PC Keyboard controller" if EXPERT || !X86
+ tristate "i8042 PC Keyboard controller"
default y
depends on !PARISC && (!ARM || ARCH_SHARK || FOOTBRIDGE_HOST) && \
(!SUPERH || SH_CAYMAN) && !M68K && !BLACKFIN && !S390
@@ -169,7 +169,7 @@
module will be called maceps2.
config SERIO_LIBPS2
- tristate "PS/2 driver library" if EXPERT
+ tristate "PS/2 driver library"
depends on SERIO_I8042 || SERIO_I8042=n
help
Say Y here if you are using a driver for device connected
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 5f306f7..4de2571 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -101,6 +101,12 @@
},
{
.matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X750LN"),
+ },
+ },
+ {
+ .matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
DMI_MATCH(DMI_PRODUCT_NAME , "ProLiant"),
DMI_MATCH(DMI_PRODUCT_VERSION, "8500"),
@@ -146,6 +152,14 @@
},
},
{
+ /* Medion Akoya E7225 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Medion"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Akoya E7225"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
+ },
+ },
+ {
/* Blue FB5601 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "blue"),
@@ -402,6 +416,13 @@
},
},
{
+ /* Acer Aspire 7738 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7738"),
+ },
+ },
+ {
/* Gericom Bellagio */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Gericom"),
@@ -458,6 +479,13 @@
DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
},
},
+ {
+ /* Avatar AVIU-145A6 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Intel"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "IC4I"),
+ },
+ },
{ }
};
@@ -601,6 +629,30 @@
DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
},
},
+ {
+ /* Fujitsu A544 laptop */
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1111138 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK A544"),
+ },
+ },
+ {
+ /* Fujitsu AH544 laptop */
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK AH544"),
+ },
+ },
+ {
+ /* Fujitsu U574 laptop */
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=69731 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK U574"),
+ },
+ },
{ }
};
@@ -684,6 +736,35 @@
{ }
};
+/*
+ * Some laptops need keyboard reset before probing for the trackpad to get
+ * it detected, initialised & finally work.
+ */
+static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
+ {
+ /* Gigabyte P35 v2 - Elantech touchpad */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "P35V2"),
+ },
+ },
+ {
+ /* Aorus branded Gigabyte X3 Plus - Elantech touchpad */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X3"),
+ },
+ },
+ {
+ /* Gigabyte P34 - Elantech touchpad */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "P34"),
+ },
+ },
+ { }
+};
+
#endif /* CONFIG_X86 */
#ifdef CONFIG_PNP
@@ -765,6 +846,7 @@
{ .id = "CPQA0D7", .driver_data = 0 },
{ .id = "", },
};
+MODULE_DEVICE_TABLE(pnp, pnp_kbd_devids);
static struct pnp_driver i8042_pnp_kbd_driver = {
.name = "i8042 kbd",
@@ -786,6 +868,7 @@
{ .id = "SYN0801", .driver_data = 0 },
{ .id = "", },
};
+MODULE_DEVICE_TABLE(pnp, pnp_aux_devids);
static struct pnp_driver i8042_pnp_aux_driver = {
.name = "i8042 aux",
@@ -962,6 +1045,9 @@
if (dmi_check_system(i8042_dmi_dritek_table))
i8042_dritek = true;
+ if (dmi_check_system(i8042_dmi_kbdreset_table))
+ i8042_kbdreset = true;
+
/*
* A20 was already enabled during early kernel init. But some buggy
* BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 78e4de4..9870c54 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -67,6 +67,10 @@
module_param_named(notimeout, i8042_notimeout, bool, 0);
MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042");
+static bool i8042_kbdreset;
+module_param_named(kbdreset, i8042_kbdreset, bool, 0);
+MODULE_PARM_DESC(kbdreset, "Reset device connected to KBD port");
+
#ifdef CONFIG_X86
static bool i8042_dritek;
module_param_named(dritek, i8042_dritek, bool, 0);
@@ -783,6 +787,16 @@
return -1;
/*
+ * Reset keyboard (needed on some laptops to successfully detect
+ * touchpad, e.g., some Gigabyte laptop models with Elantech
+ * touchpads).
+ */
+ if (i8042_kbdreset) {
+ pr_warn("Attempting to reset device connected to KBD port\n");
+ i8042_kbd_write(NULL, (unsigned char) 0xff);
+ }
+
+/*
* Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and
* used it for a PCI card or somethig else.
*/
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index 8755f5f..e4ecf3b 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -21,6 +21,7 @@
#include <linux/init.h>
#include <linux/serio.h>
#include <linux/tty.h>
+#include <linux/compat.h>
MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
MODULE_DESCRIPTION("Input device TTY line discipline");
@@ -196,29 +197,56 @@
return 0;
}
+static void serport_set_type(struct tty_struct *tty, unsigned long type)
+{
+ struct serport *serport = tty->disc_data;
+
+ serport->id.proto = type & 0x000000ff;
+ serport->id.id = (type & 0x0000ff00) >> 8;
+ serport->id.extra = (type & 0x00ff0000) >> 16;
+}
+
/*
* serport_ldisc_ioctl() allows to set the port protocol, and device ID
*/
-static int serport_ldisc_ioctl(struct tty_struct * tty, struct file * file, unsigned int cmd, unsigned long arg)
+static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file,
+ unsigned int cmd, unsigned long arg)
{
- struct serport *serport = (struct serport*) tty->disc_data;
- unsigned long type;
-
if (cmd == SPIOCSTYPE) {
+ unsigned long type;
+
if (get_user(type, (unsigned long __user *) arg))
return -EFAULT;
- serport->id.proto = type & 0x000000ff;
- serport->id.id = (type & 0x0000ff00) >> 8;
- serport->id.extra = (type & 0x00ff0000) >> 16;
-
+ serport_set_type(tty, type);
return 0;
}
return -EINVAL;
}
+#ifdef CONFIG_COMPAT
+#define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t)
+static long serport_ldisc_compat_ioctl(struct tty_struct *tty,
+ struct file *file,
+ unsigned int cmd, unsigned long arg)
+{
+ if (cmd == COMPAT_SPIOCSTYPE) {
+ void __user *uarg = compat_ptr(arg);
+ compat_ulong_t compat_type;
+
+ if (get_user(compat_type, (compat_ulong_t __user *)uarg))
+ return -EFAULT;
+
+ serport_set_type(tty, compat_type);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+#endif
+
static void serport_ldisc_write_wakeup(struct tty_struct * tty)
{
struct serport *serport = (struct serport *) tty->disc_data;
@@ -241,6 +269,9 @@
.close = serport_ldisc_close,
.read = serport_ldisc_read,
.ioctl = serport_ldisc_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = serport_ldisc_compat_ioctl,
+#endif
.receive_buf = serport_ldisc_receive,
.write_wakeup = serport_ldisc_write_wakeup
};
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index aaf23ae..3d838c0 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -339,7 +339,7 @@
struct usb_device *dev = interface_to_usbdev(intf);
char limit = 0;
/* result has to be defined as int for some devices */
- int result = 0;
+ int result = 0, touch_max = 0;
int i = 0, usage = WCM_UNDEFINED, finger = 0, pen = 0;
unsigned char *report;
@@ -386,7 +386,8 @@
if (usage == WCM_DESKTOP) {
if (finger) {
features->device_type = BTN_TOOL_FINGER;
-
+ /* touch device at least supports one touch point */
+ touch_max = 1;
switch (features->type) {
case TABLETPC2FG:
features->pktlen = WACOM_PKGLEN_TPC2FG;
@@ -539,6 +540,8 @@
}
out:
+ if (!features->touch_max && touch_max)
+ features->touch_max = touch_max;
result = 0;
kfree(report);
return result;
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 721fdb3..5f87bed 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -106,6 +106,7 @@
struct usbtouch_usb {
unsigned char *data;
dma_addr_t data_dma;
+ int data_size;
unsigned char *buffer;
int buf_len;
struct urb *irq;
@@ -146,12 +147,10 @@
#define USB_DEVICE_HID_CLASS(vend, prod) \
.match_flags = USB_DEVICE_ID_MATCH_INT_CLASS \
- | USB_DEVICE_ID_MATCH_INT_PROTOCOL \
| USB_DEVICE_ID_MATCH_DEVICE, \
.idVendor = (vend), \
.idProduct = (prod), \
- .bInterfaceClass = USB_INTERFACE_CLASS_HID, \
- .bInterfaceProtocol = USB_INTERFACE_PROTOCOL_MOUSE
+ .bInterfaceClass = USB_INTERFACE_CLASS_HID
static const struct usb_device_id usbtouch_devices[] = {
#ifdef CONFIG_TOUCHSCREEN_USB_EGALAX
@@ -1523,7 +1522,7 @@
static void usbtouch_free_buffers(struct usb_device *udev,
struct usbtouch_usb *usbtouch)
{
- usb_free_coherent(udev, usbtouch->type->rept_size,
+ usb_free_coherent(udev, usbtouch->data_size,
usbtouch->data, usbtouch->data_dma);
kfree(usbtouch->buffer);
}
@@ -1568,7 +1567,20 @@
if (!type->process_pkt)
type->process_pkt = usbtouch_process_pkt;
- usbtouch->data = usb_alloc_coherent(udev, type->rept_size,
+ usbtouch->data_size = type->rept_size;
+ if (type->get_pkt_len) {
+ /*
+ * When dealing with variable-length packets we should
+ * not request more than wMaxPacketSize bytes at once
+ * as we do not know if there is more data coming or
+ * we filled exactly wMaxPacketSize bytes and there is
+ * nothing else.
+ */
+ usbtouch->data_size = min(usbtouch->data_size,
+ usb_endpoint_maxp(endpoint));
+ }
+
+ usbtouch->data = usb_alloc_coherent(udev, usbtouch->data_size,
GFP_KERNEL, &usbtouch->data_dma);
if (!usbtouch->data)
goto out_free;
@@ -1628,12 +1640,12 @@
if (usb_endpoint_type(endpoint) == USB_ENDPOINT_XFER_INT)
usb_fill_int_urb(usbtouch->irq, udev,
usb_rcvintpipe(udev, endpoint->bEndpointAddress),
- usbtouch->data, type->rept_size,
+ usbtouch->data, usbtouch->data_size,
usbtouch_irq, usbtouch, endpoint->bInterval);
else
usb_fill_bulk_urb(usbtouch->irq, udev,
usb_rcvbulkpipe(udev, endpoint->bEndpointAddress),
- usbtouch->data, type->rept_size,
+ usbtouch->data, usbtouch->data_size,
usbtouch_irq, usbtouch);
usbtouch->irq->dev = udev;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 21d02b0..dfb401c 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1484,6 +1484,10 @@
/* Large PTE found which maps this address */
unmap_size = PTE_PAGE_SIZE(*pte);
+
+ /* Only unmap from the first pte in the page */
+ if ((unmap_size - 1) & bus_addr)
+ break;
count = PAGE_SIZE_PTE_COUNT(unmap_size);
for (i = 0; i < count; i++)
pte[i] = 0ULL;
@@ -1493,7 +1497,7 @@
unmapped += unmap_size;
}
- BUG_ON(!is_power_of_2(unmapped));
+ BUG_ON(unmapped && !is_power_of_2(unmapped));
return unmapped;
}
@@ -3183,14 +3187,16 @@
static void cleanup_domain(struct protection_domain *domain)
{
- struct iommu_dev_data *dev_data, *next;
+ struct iommu_dev_data *entry;
unsigned long flags;
write_lock_irqsave(&amd_iommu_devtable_lock, flags);
- list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
- __detach_device(dev_data);
- atomic_set(&dev_data->bind, 0);
+ while (!list_empty(&domain->dev_list)) {
+ entry = list_first_entry(&domain->dev_list,
+ struct iommu_dev_data, list);
+ __detach_device(entry);
+ atomic_set(&entry->bind, 0);
}
write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
@@ -3955,7 +3961,7 @@
iommu_flush_dte(iommu, devid);
if (devid != alias) {
irq_lookup_table[alias] = table;
- set_dte_irq_entry(devid, table);
+ set_dte_irq_entry(alias, table);
iommu_flush_dte(iommu, alias);
}
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index b4f0e28..db4e10d 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -782,7 +782,11 @@
int offset;
BUG_ON(!domain->pgd);
- BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
+
+ if (addr_width < BITS_PER_LONG && pfn >> addr_width)
+ /* Address beyond IOMMU's addressing capabilities. */
+ return NULL;
+
parent = domain->pgd;
while (level > 0) {
@@ -890,56 +894,54 @@
return order;
}
+static void dma_pte_free_level(struct dmar_domain *domain, int level,
+ struct dma_pte *pte, unsigned long pfn,
+ unsigned long start_pfn, unsigned long last_pfn)
+{
+ pfn = max(start_pfn, pfn);
+ pte = &pte[pfn_level_offset(pfn, level)];
+
+ do {
+ unsigned long level_pfn;
+ struct dma_pte *level_pte;
+
+ if (!dma_pte_present(pte) || dma_pte_superpage(pte))
+ goto next;
+
+ level_pfn = pfn & level_mask(level - 1);
+ level_pte = phys_to_virt(dma_pte_addr(pte));
+
+ if (level > 2)
+ dma_pte_free_level(domain, level - 1, level_pte,
+ level_pfn, start_pfn, last_pfn);
+
+ /* If range covers entire pagetable, free it */
+ if (!(start_pfn > level_pfn ||
+ last_pfn < level_pfn + level_size(level) - 1)) {
+ dma_clear_pte(pte);
+ domain_flush_cache(domain, pte, sizeof(*pte));
+ free_pgtable_page(level_pte);
+ }
+next:
+ pfn += level_size(level);
+ } while (!first_pte_in_page(++pte) && pfn <= last_pfn);
+}
+
/* free page table pages. last level pte should already be cleared */
static void dma_pte_free_pagetable(struct dmar_domain *domain,
unsigned long start_pfn,
unsigned long last_pfn)
{
int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
- struct dma_pte *first_pte, *pte;
- int total = agaw_to_level(domain->agaw);
- int level;
- unsigned long tmp;
- int large_page = 2;
BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
BUG_ON(start_pfn > last_pfn);
/* We don't need lock here; nobody else touches the iova range */
- level = 2;
- while (level <= total) {
- tmp = align_to_level(start_pfn, level);
+ dma_pte_free_level(domain, agaw_to_level(domain->agaw),
+ domain->pgd, 0, start_pfn, last_pfn);
- /* If we can't even clear one PTE at this level, we're done */
- if (tmp + level_size(level) - 1 > last_pfn)
- return;
-
- do {
- large_page = level;
- first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
- if (large_page > level)
- level = large_page + 1;
- if (!pte) {
- tmp = align_to_level(tmp + 1, level + 1);
- continue;
- }
- do {
- if (dma_pte_present(pte)) {
- free_pgtable_page(phys_to_virt(dma_pte_addr(pte)));
- dma_clear_pte(pte);
- }
- pte++;
- tmp += level_size(level);
- } while (!first_pte_in_page(pte) &&
- tmp + level_size(level) - 1 <= last_pfn);
-
- domain_flush_cache(domain, first_pte,
- (void *)pte - (void *)first_pte);
-
- } while (tmp && tmp + level_size(level) - 1 <= last_pfn);
- level++;
- }
/* free pgd */
if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) {
free_pgtable_page(domain->pgd);
@@ -1794,7 +1796,7 @@
struct dma_pte *first_pte = NULL, *pte = NULL;
phys_addr_t uninitialized_var(pteval);
int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
- unsigned long sg_res;
+ unsigned long sg_res = 0;
unsigned int largepage_lvl = 0;
unsigned long lvl_pages = 0;
@@ -1805,10 +1807,8 @@
prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
- if (sg)
- sg_res = 0;
- else {
- sg_res = nr_pages + 1;
+ if (!sg) {
+ sg_res = nr_pages;
pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
}
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 5b19b2d..45011f6 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -525,12 +525,13 @@
if (disable_irq_remap)
return 0;
if (irq_remap_broken) {
- WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
- "This system BIOS has enabled interrupt remapping\n"
- "on a chipset that contains an erratum making that\n"
- "feature unstable. To maintain system stability\n"
- "interrupt remapping is being disabled. Please\n"
- "contact your BIOS vendor for an update\n");
+ printk(KERN_WARNING
+ "This system BIOS has enabled interrupt remapping\n"
+ "on a chipset that contains an erratum making that\n"
+ "feature unstable. To maintain system stability\n"
+ "interrupt remapping is being disabled. Please\n"
+ "contact your BIOS vendor for an update\n");
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
disable_irq_remap = 1;
return 0;
}
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 4a33351..7709b1d 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -10,6 +10,11 @@
config GIC_NON_BANKED
bool
+config ARM_GIC_V3
+ bool
+ select IRQ_DOMAIN
+ select MULTI_IRQ_HANDLER
+
config ARM_VIC
bool
select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index cda4cb5..bf4667b 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -9,7 +9,8 @@
obj-$(CONFIG_METAG_PERFCOUNTER_IRQS) += irq-metag.o
obj-$(CONFIG_ARCH_SUNXI) += irq-sun4i.o
obj-$(CONFIG_ARCH_SPEAR3XX) += spear-shirq.o
-obj-$(CONFIG_ARM_GIC) += irq-gic.o
+obj-$(CONFIG_ARM_GIC) += irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3) += irq-gic-v3.o irq-gic-common.o
obj-$(CONFIG_ARM_VIC) += irq-vic.o
obj-$(CONFIG_SIRF_IRQ) += irq-sirfsoc.o
obj-$(CONFIG_RENESAS_INTC_IRQPIN) += irq-renesas-intc-irqpin.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index bb328a3..a51ee00 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -229,7 +229,7 @@
ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
& IPI_DOORBELL_MASK;
- writel(~IPI_DOORBELL_MASK, per_cpu_int_base +
+ writel(~ipimask, per_cpu_int_base +
ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
/* Handle all pending doorbells */
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
new file mode 100644
index 0000000..60ac704
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include "irq-gic-common.h"
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+ void __iomem *base, void (*sync_access)(void))
+{
+ u32 enablemask = 1 << (irq % 32);
+ u32 enableoff = (irq / 32) * 4;
+ u32 confmask = 0x2 << ((irq % 16) * 2);
+ u32 confoff = (irq / 16) * 4;
+ bool enabled = false;
+ u32 val;
+
+ /*
+ * Read current configuration register, and insert the config
+ * for "irq", depending on "type".
+ */
+ val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
+ if (type == IRQ_TYPE_LEVEL_HIGH)
+ val &= ~confmask;
+ else if (type == IRQ_TYPE_EDGE_RISING)
+ val |= confmask;
+
+ /*
+ * As recommended by the spec, disable the interrupt before changing
+ * the configuration
+ */
+ if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+ writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+ if (sync_access)
+ sync_access();
+ enabled = true;
+ }
+
+ /*
+ * Write back the new configuration, and possibly re-enable
+ * the interrupt.
+ */
+ writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
+
+ if (enabled)
+ writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+
+ if (sync_access)
+ sync_access();
+}
+
+void __init gic_dist_config(void __iomem *base, int gic_irqs,
+ void (*sync_access)(void))
+{
+ unsigned int i;
+
+ /*
+ * Set all global interrupts to be level triggered, active low.
+ */
+ for (i = 32; i < gic_irqs; i += 16)
+ writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+
+ /*
+ * Set priority on all global interrupts.
+ */
+ for (i = 32; i < gic_irqs; i += 4)
+ writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+
+ /*
+ * Disable all interrupts. Leave the PPI and SGIs alone
+ * as they are enabled by redistributor registers.
+ */
+ for (i = 32; i < gic_irqs; i += 32)
+ writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+
+ if (sync_access)
+ sync_access();
+}
+
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
+{
+ int i;
+
+ /*
+ * Deal with the banked PPI and SGI interrupts - disable all
+ * PPI interrupts, ensure all SGI interrupts are enabled.
+ */
+ writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
+ writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+
+ /*
+ * Set priority on PPI and SGI interrupts
+ */
+ for (i = 0; i < 32; i += 4)
+ writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+
+ if (sync_access)
+ sync_access();
+}
diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h
new file mode 100644
index 0000000..b41f024
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _IRQ_GIC_COMMON_H
+#define _IRQ_GIC_COMMON_H
+
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+ void __iomem *base, void (*sync_access)(void));
+void gic_dist_config(void __iomem *base, int gic_irqs,
+ void (*sync_access)(void));
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
+
+#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
new file mode 100644
index 0000000..57eaa5a
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -0,0 +1,692 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+struct gic_chip_data {
+ void __iomem *dist_base;
+ void __iomem **redist_base;
+ void __percpu __iomem **rdist;
+ struct irq_domain *domain;
+ u64 redist_stride;
+ u32 redist_regions;
+ unsigned int irq_nr;
+};
+
+static struct gic_chip_data gic_data __read_mostly;
+
+#define gic_data_rdist() (this_cpu_ptr(gic_data.rdist))
+#define gic_data_rdist_rd_base() (*gic_data_rdist())
+#define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K)
+
+/* Our default, arbitrary priority value. Linux only uses one anyway. */
+#define DEFAULT_PMR_VALUE 0xf0
+
+static inline unsigned int gic_irq(struct irq_data *d)
+{
+ return d->hwirq;
+}
+
+static inline int gic_irq_in_rdist(struct irq_data *d)
+{
+ return gic_irq(d) < 32;
+}
+
+static inline void __iomem *gic_dist_base(struct irq_data *d)
+{
+ if (gic_irq_in_rdist(d)) /* SGI+PPI -> SGI_base for this CPU */
+ return gic_data_rdist_sgi_base();
+
+ if (d->hwirq <= 1023) /* SPI -> dist_base */
+ return gic_data.dist_base;
+
+ if (d->hwirq >= 8192)
+ BUG(); /* LPI Detected!!! */
+
+ return NULL;
+}
+
+static void gic_do_wait_for_rwp(void __iomem *base)
+{
+ u32 count = 1000000; /* 1s! */
+
+ while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+ count--;
+ if (!count) {
+ pr_err_ratelimited("RWP timeout, gone fishing\n");
+ return;
+ }
+ cpu_relax();
+ udelay(1);
+ };
+}
+
+/* Wait for completion of a distributor change */
+static void gic_dist_wait_for_rwp(void)
+{
+ gic_do_wait_for_rwp(gic_data.dist_base);
+}
+
+/* Wait for completion of a redistributor change */
+static void gic_redist_wait_for_rwp(void)
+{
+ gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+}
+
+/* Low level accessors */
+static u64 gic_read_iar(void)
+{
+ u64 irqstat;
+
+ asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+ return irqstat;
+}
+
+static void gic_write_pmr(u64 val)
+{
+ asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_write_ctlr(u64 val)
+{
+ asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
+ isb();
+}
+
+static void gic_write_grpen1(u64 val)
+{
+ asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
+ isb();
+}
+
+static void gic_write_sgi1r(u64 val)
+{
+ asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_enable_sre(void)
+{
+ u64 val;
+
+ asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+ val |= ICC_SRE_EL1_SRE;
+ asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
+ isb();
+
+ /*
+ * Need to check that the SRE bit has actually been set. If
+ * not, it means that SRE is disabled at EL2. We're going to
+ * die painfully, and there is nothing we can do about it.
+ *
+ * Kindly inform the luser.
+ */
+ asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+ if (!(val & ICC_SRE_EL1_SRE))
+ pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_enable_redist(void)
+{
+ void __iomem *rbase;
+ u32 count = 1000000; /* 1s! */
+ u32 val;
+
+ rbase = gic_data_rdist_rd_base();
+
+ /* Wake up this CPU redistributor */
+ val = readl_relaxed(rbase + GICR_WAKER);
+ val &= ~GICR_WAKER_ProcessorSleep;
+ writel_relaxed(val, rbase + GICR_WAKER);
+
+ while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+ count--;
+ if (!count) {
+ pr_err_ratelimited("redist didn't wake up...\n");
+ return;
+ }
+ cpu_relax();
+ udelay(1);
+ };
+}
+
+/*
+ * Routines to disable, enable, EOI and route interrupts
+ */
+static void gic_poke_irq(struct irq_data *d, u32 offset)
+{
+ u32 mask = 1 << (gic_irq(d) % 32);
+ void (*rwp_wait)(void);
+ void __iomem *base;
+
+ if (gic_irq_in_rdist(d)) {
+ base = gic_data_rdist_sgi_base();
+ rwp_wait = gic_redist_wait_for_rwp;
+ } else {
+ base = gic_data.dist_base;
+ rwp_wait = gic_dist_wait_for_rwp;
+ }
+
+ writel_relaxed(mask, base + offset + (gic_irq(d) / 32) * 4);
+ rwp_wait();
+}
+
+static int gic_peek_irq(struct irq_data *d, u32 offset)
+{
+ u32 mask = 1 << (gic_irq(d) % 32);
+ void __iomem *base;
+
+ if (gic_irq_in_rdist(d))
+ base = gic_data_rdist_sgi_base();
+ else
+ base = gic_data.dist_base;
+
+ return !!(readl_relaxed(base + offset + (gic_irq(d) / 32) * 4) & mask);
+}
+
+static void gic_mask_irq(struct irq_data *d)
+{
+ gic_poke_irq(d, GICD_ICENABLER);
+}
+
+static void gic_unmask_irq(struct irq_data *d)
+{
+ gic_poke_irq(d, GICD_ISENABLER);
+}
+
+static void gic_eoi_irq(struct irq_data *d)
+{
+ gic_write_eoir(gic_irq(d));
+}
+
+static int gic_set_type(struct irq_data *d, unsigned int type)
+{
+ unsigned int irq = gic_irq(d);
+ void (*rwp_wait)(void);
+ void __iomem *base;
+
+ /* Interrupt configuration for SGIs can't be changed */
+ if (irq < 16)
+ return -EINVAL;
+
+ if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+ return -EINVAL;
+
+ if (gic_irq_in_rdist(d)) {
+ base = gic_data_rdist_sgi_base();
+ rwp_wait = gic_redist_wait_for_rwp;
+ } else {
+ base = gic_data.dist_base;
+ rwp_wait = gic_dist_wait_for_rwp;
+ }
+
+ gic_configure_irq(irq, type, base, rwp_wait);
+
+ return 0;
+}
+
+static u64 gic_mpidr_to_affinity(u64 mpidr)
+{
+ u64 aff;
+
+ aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+ return aff;
+}
+
+static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+ u64 irqnr;
+
+ do {
+ irqnr = gic_read_iar();
+
+ if (likely(irqnr > 15 && irqnr < 1020)) {
+ u64 irq = irq_find_mapping(gic_data.domain, irqnr);
+ if (likely(irq)) {
+ handle_IRQ(irq, regs);
+ continue;
+ }
+
+ WARN_ONCE(true, "Unexpected SPI received!\n");
+ gic_write_eoir(irqnr);
+ }
+ if (irqnr < 16) {
+ gic_write_eoir(irqnr);
+#ifdef CONFIG_SMP
+ handle_IPI(irqnr, regs);
+#else
+ WARN_ONCE(true, "Unexpected SGI received!\n");
+#endif
+ continue;
+ }
+ } while (irqnr != ICC_IAR1_EL1_SPURIOUS);
+}
+
+static void __init gic_dist_init(void)
+{
+ unsigned int i;
+ u64 affinity;
+ void __iomem *base = gic_data.dist_base;
+
+ /* Disable the distributor */
+ writel_relaxed(0, base + GICD_CTLR);
+ gic_dist_wait_for_rwp();
+
+ gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
+
+ /* Enable distributor with ARE, Group1 */
+ writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
+ base + GICD_CTLR);
+
+ /*
+ * Set all global interrupts to the boot CPU only. ARE must be
+ * enabled.
+ */
+ affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
+ for (i = 32; i < gic_data.irq_nr; i++)
+ writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+}
+
+static int gic_populate_rdist(void)
+{
+ u64 mpidr = cpu_logical_map(smp_processor_id());
+ u64 typer;
+ u32 aff;
+ int i;
+
+ /*
+ * Convert affinity to a 32bit value that can be matched to
+ * GICR_TYPER bits [63:32].
+ */
+ aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+ MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+ for (i = 0; i < gic_data.redist_regions; i++) {
+ void __iomem *ptr = gic_data.redist_base[i];
+ u32 reg;
+
+ reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
+ if (reg != GIC_PIDR2_ARCH_GICv3 &&
+ reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
+ pr_warn("No redistributor present @%p\n", ptr);
+ break;
+ }
+
+ do {
+ typer = readq_relaxed(ptr + GICR_TYPER);
+ if ((typer >> 32) == aff) {
+ gic_data_rdist_rd_base() = ptr;
+ pr_info("CPU%d: found redistributor %llx @%p\n",
+ smp_processor_id(),
+ (unsigned long long)mpidr, ptr);
+ return 0;
+ }
+
+ if (gic_data.redist_stride) {
+ ptr += gic_data.redist_stride;
+ } else {
+ ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
+ if (typer & GICR_TYPER_VLPIS)
+ ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
+ }
+ } while (!(typer & GICR_TYPER_LAST));
+ }
+
+ /* We couldn't even deal with ourselves... */
+ WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
+ smp_processor_id(), (unsigned long long)mpidr);
+ return -ENODEV;
+}
+
+static void gic_cpu_init(void)
+{
+ void __iomem *rbase;
+
+ /* Register ourselves with the rest of the world */
+ if (gic_populate_rdist())
+ return;
+
+ gic_enable_redist();
+
+ rbase = gic_data_rdist_sgi_base();
+
+ gic_cpu_config(rbase, gic_redist_wait_for_rwp);
+
+ /* Enable system registers */
+ gic_enable_sre();
+
+ /* Set priority mask register */
+ gic_write_pmr(DEFAULT_PMR_VALUE);
+
+ /* EOI deactivates interrupt too (mode 0) */
+ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+ /* ... and let's hit the road... */
+ gic_write_grpen1(1);
+}
+
+#ifdef CONFIG_SMP
+static int gic_secondary_init(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+ gic_cpu_init();
+ return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the GIC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block gic_cpu_notifier = {
+ .notifier_call = gic_secondary_init,
+ .priority = 100,
+};
+
+static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
+ u64 cluster_id)
+{
+ int cpu = *base_cpu;
+ u64 mpidr = cpu_logical_map(cpu);
+ u16 tlist = 0;
+
+ while (cpu < nr_cpu_ids) {
+ /*
+ * If we ever get a cluster of more than 16 CPUs, just
+ * scream and skip that CPU.
+ */
+ if (WARN_ON((mpidr & 0xff) >= 16))
+ goto out;
+
+ tlist |= 1 << (mpidr & 0xf);
+
+ cpu = cpumask_next(cpu, mask);
+ if (cpu == nr_cpu_ids)
+ goto out;
+
+ mpidr = cpu_logical_map(cpu);
+
+ if (cluster_id != (mpidr & ~0xffUL)) {
+ cpu--;
+ goto out;
+ }
+ }
+out:
+ *base_cpu = cpu;
+ return tlist;
+}
+
+static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
+{
+ u64 val;
+
+ val = (MPIDR_AFFINITY_LEVEL(cluster_id, 3) << 48 |
+ MPIDR_AFFINITY_LEVEL(cluster_id, 2) << 32 |
+ irq << 24 |
+ MPIDR_AFFINITY_LEVEL(cluster_id, 1) << 16 |
+ tlist);
+
+ pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+ gic_write_sgi1r(val);
+}
+
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+ int cpu;
+
+ if (WARN_ON(irq >= 16))
+ return;
+
+ /*
+ * Ensure that stores to Normal memory are visible to the
+ * other CPUs before issuing the IPI.
+ */
+ smp_wmb();
+
+ for_each_cpu_mask(cpu, *mask) {
+ u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+ u16 tlist;
+
+ tlist = gic_compute_target_list(&cpu, mask, cluster_id);
+ gic_send_sgi(cluster_id, tlist, irq);
+ }
+
+ /* Force the above writes to ICC_SGI1R_EL1 to be executed */
+ isb();
+}
+
+static void gic_smp_init(void)
+{
+ set_smp_cross_call(gic_raise_softirq);
+ register_cpu_notifier(&gic_cpu_notifier);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+ bool force)
+{
+ unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+ void __iomem *reg;
+ int enabled;
+ u64 val;
+
+ if (gic_irq_in_rdist(d))
+ return -EINVAL;
+
+ /* If interrupt was enabled, disable it first */
+ enabled = gic_peek_irq(d, GICD_ISENABLER);
+ if (enabled)
+ gic_mask_irq(d);
+
+ reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
+ val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
+
+ writeq_relaxed(val, reg);
+
+ /*
+ * If the interrupt was enabled, enabled it again. Otherwise,
+ * just wait for the distributor to have digested our changes.
+ */
+ if (enabled)
+ gic_unmask_irq(d);
+ else
+ gic_dist_wait_for_rwp();
+
+ return IRQ_SET_MASK_OK;
+}
+#else
+#define gic_set_affinity NULL
+#define gic_smp_init() do { } while(0)
+#endif
+
+static struct irq_chip gic_chip = {
+ .name = "GICv3",
+ .irq_mask = gic_mask_irq,
+ .irq_unmask = gic_unmask_irq,
+ .irq_eoi = gic_eoi_irq,
+ .irq_set_type = gic_set_type,
+ .irq_set_affinity = gic_set_affinity,
+};
+
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hw)
+{
+ /* SGIs are private to the core kernel */
+ if (hw < 16)
+ return -EPERM;
+ /* PPIs */
+ if (hw < 32) {
+ irq_set_percpu_devid(irq);
+ irq_set_chip_and_handler(irq, &gic_chip,
+ handle_percpu_devid_irq);
+ set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+ }
+ /* SPIs */
+ if (hw >= 32 && hw < gic_data.irq_nr) {
+ irq_set_chip_and_handler(irq, &gic_chip,
+ handle_fasteoi_irq);
+ set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+ }
+ irq_set_chip_data(irq, d->host_data);
+ return 0;
+}
+
+static int gic_irq_domain_xlate(struct irq_domain *d,
+ struct device_node *controller,
+ const u32 *intspec, unsigned int intsize,
+ unsigned long *out_hwirq, unsigned int *out_type)
+{
+ if (d->of_node != controller)
+ return -EINVAL;
+ if (intsize < 3)
+ return -EINVAL;
+
+ switch(intspec[0]) {
+ case 0: /* SPI */
+ *out_hwirq = intspec[1] + 32;
+ break;
+ case 1: /* PPI */
+ *out_hwirq = intspec[1] + 16;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ *out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+ return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+ .map = gic_irq_domain_map,
+ .xlate = gic_irq_domain_xlate,
+};
+
+static int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+ void __iomem *dist_base;
+ void __iomem **redist_base;
+ u64 redist_stride;
+ u32 redist_regions;
+ u32 reg;
+ int gic_irqs;
+ int err;
+ int i;
+
+ dist_base = of_iomap(node, 0);
+ if (!dist_base) {
+ pr_err("%s: unable to map gic dist registers\n",
+ node->full_name);
+ return -ENXIO;
+ }
+
+ reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+ if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+ pr_err("%s: no distributor detected, giving up\n",
+ node->full_name);
+ err = -ENODEV;
+ goto out_unmap_dist;
+ }
+
+ if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
+ redist_regions = 1;
+
+ redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
+ if (!redist_base) {
+ err = -ENOMEM;
+ goto out_unmap_dist;
+ }
+
+ for (i = 0; i < redist_regions; i++) {
+ redist_base[i] = of_iomap(node, 1 + i);
+ if (!redist_base[i]) {
+ pr_err("%s: couldn't map region %d\n",
+ node->full_name, i);
+ err = -ENODEV;
+ goto out_unmap_rdist;
+ }
+ }
+
+ if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
+ redist_stride = 0;
+
+ gic_data.dist_base = dist_base;
+ gic_data.redist_base = redist_base;
+ gic_data.redist_regions = redist_regions;
+ gic_data.redist_stride = redist_stride;
+
+ /*
+ * Find out how many interrupts are supported.
+ * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+ */
+ gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
+ gic_irqs = (gic_irqs + 1) * 32;
+ if (gic_irqs > 1020)
+ gic_irqs = 1020;
+ gic_data.irq_nr = gic_irqs;
+
+ gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
+ &gic_data);
+ gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+
+ if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ set_handle_irq(gic_handle_irq);
+
+ gic_smp_init();
+ gic_dist_init();
+ gic_cpu_init();
+
+ return 0;
+
+out_free:
+ if (gic_data.domain)
+ irq_domain_remove(gic_data.domain);
+ free_percpu(gic_data.rdist);
+out_unmap_rdist:
+ for (i = 0; i < redist_regions; i++)
+ if (redist_base[i])
+ iounmap(redist_base[i]);
+ kfree(redist_base);
+out_unmap_dist:
+ iounmap(dist_base);
+ return err;
+}
+
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 19ceaa6..4cb670e 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1,6 +1,4 @@
/*
- * linux/arch/arm/common/gic.c
- *
* Copyright (C) 2002 ARM Limited, All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify
@@ -41,16 +39,19 @@
#include <linux/slab.h>
#include <linux/irqchip/chained_irq.h>
#include <linux/irqchip/arm-gic.h>
+#include <trace/events/arm-ipi.h>
+#include <asm/cputype.h>
#include <asm/irq.h>
#include <asm/exception.h>
#include <asm/smp_plat.h>
+#include "irq-gic-common.h"
#include "irqchip.h"
union gic_base {
void __iomem *common_base;
- void __percpu __iomem **percpu_base;
+ void __percpu * __iomem *percpu_base;
};
struct gic_chip_data {
@@ -188,12 +189,6 @@
{
void __iomem *base = gic_dist_base(d);
unsigned int gicirq = gic_irq(d);
- u32 enablemask = 1 << (gicirq % 32);
- u32 enableoff = (gicirq / 32) * 4;
- u32 confmask = 0x2 << ((gicirq % 16) * 2);
- u32 confoff = (gicirq / 16) * 4;
- bool enabled = false;
- u32 val;
/* Interrupt configuration for SGIs can't be changed */
if (gicirq < 16)
@@ -207,25 +202,7 @@
if (gic_arch_extn.irq_set_type)
gic_arch_extn.irq_set_type(d, type);
- val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
- if (type == IRQ_TYPE_LEVEL_HIGH)
- val &= ~confmask;
- else if (type == IRQ_TYPE_EDGE_RISING)
- val |= confmask;
-
- /*
- * As recommended by the spec, disable the interrupt before changing
- * the configuration
- */
- if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
- writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
- enabled = true;
- }
-
- writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
-
- if (enabled)
- writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+ gic_configure_irq(gicirq, type, base, NULL);
raw_spin_unlock(&irq_controller_lock);
@@ -253,10 +230,9 @@
if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
return -EINVAL;
+ raw_spin_lock(&irq_controller_lock);
mask = 0xff << shift;
bit = gic_cpu_map[cpu] << shift;
-
- raw_spin_lock(&irq_controller_lock);
val = readl_relaxed(reg) & ~mask;
writel_relaxed(val | bit, reg);
raw_spin_unlock(&irq_controller_lock);
@@ -280,7 +256,7 @@
#define gic_set_wake NULL
#endif
-static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
u32 irqstat, irqnr;
struct gic_chip_data *gic = &gic_data[0];
@@ -288,7 +264,7 @@
do {
irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
- irqnr = irqstat & ~0x1c00;
+ irqnr = irqstat & GICC_IAR_INT_ID_MASK;
if (likely(irqnr > 15 && irqnr < 1021)) {
irqnr = irq_find_mapping(gic->domain, irqnr);
@@ -384,12 +360,6 @@
writel_relaxed(0, base + GIC_DIST_CTRL);
/*
- * Set all global interrupts to be level triggered, active low.
- */
- for (i = 32; i < gic_irqs; i += 16)
- writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
-
- /*
* Set all global interrupts to this CPU only.
*/
cpumask = gic_get_cpumask(gic);
@@ -398,18 +368,7 @@
for (i = 32; i < gic_irqs; i += 4)
writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
- /*
- * Set priority on all global interrupts.
- */
- for (i = 32; i < gic_irqs; i += 4)
- writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
-
- /*
- * Disable all interrupts. Leave the PPI and SGIs alone
- * as these enables are banked registers.
- */
- for (i = 32; i < gic_irqs; i += 32)
- writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+ gic_dist_config(base, gic_irqs, NULL);
writel_relaxed(1, base + GIC_DIST_CTRL);
}
@@ -436,23 +395,18 @@
if (i != cpu)
gic_cpu_map[i] &= ~cpu_mask;
- /*
- * Deal with the banked PPI and SGI interrupts - disable all
- * PPI interrupts, ensure all SGI interrupts are enabled.
- */
- writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
- writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
-
- /*
- * Set priority on PPI and SGI interrupts
- */
- for (i = 0; i < 32; i += 4)
- writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+ gic_cpu_config(dist_base, NULL);
writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
writel_relaxed(1, base + GIC_CPU_CTRL);
}
+void gic_cpu_if_down(void)
+{
+ void __iomem *cpu_base = gic_data_cpu_base(&gic_data[0]);
+ writel_relaxed(0, cpu_base + GIC_CPU_CTRL);
+}
+
#ifdef CONFIG_CPU_PM
/*
* Saves the GIC distributor registers during suspend or idle. Must be called
@@ -643,26 +597,172 @@
#endif
#ifdef CONFIG_SMP
-void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
{
int cpu;
- unsigned long map = 0;
+ unsigned long flags, map = 0;
+
+ raw_spin_lock_irqsave(&irq_controller_lock, flags);
/* Convert our logical CPU mask into a physical one. */
- for_each_cpu(cpu, mask)
+ for_each_cpu(cpu, mask) {
+ trace_arm_ipi_send(irq, cpu);
map |= gic_cpu_map[cpu];
+ }
/*
* Ensure that stores to Normal memory are visible to the
- * other CPUs before issuing the IPI.
+ * other CPUs before they observe us issuing the IPI.
*/
- dsb();
+ dmb(ishst);
/* this always happens on GIC0 */
writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+
+ raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
}
#endif
+#ifdef CONFIG_BL_SWITCHER
+/*
+ * gic_send_sgi - send a SGI directly to given CPU interface number
+ *
+ * cpu_id: the ID for the destination CPU interface
+ * irq: the IPI number to send a SGI for
+ */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq)
+{
+ BUG_ON(cpu_id >= NR_GIC_CPU_IF);
+ cpu_id = 1 << cpu_id;
+ /* this always happens on GIC0 */
+ writel_relaxed((cpu_id << 16) | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+}
+
+/*
+ * gic_get_cpu_id - get the CPU interface ID for the specified CPU
+ *
+ * @cpu: the logical CPU number to get the GIC ID for.
+ *
+ * Return the CPU interface ID for the given logical CPU number,
+ * or -1 if the CPU number is too large or the interface ID is
+ * unknown (more than one bit set).
+ */
+int gic_get_cpu_id(unsigned int cpu)
+{
+ unsigned int cpu_bit;
+
+ if (cpu >= NR_GIC_CPU_IF)
+ return -1;
+ cpu_bit = gic_cpu_map[cpu];
+ if (cpu_bit & (cpu_bit - 1))
+ return -1;
+ return __ffs(cpu_bit);
+}
+
+/*
+ * gic_migrate_target - migrate IRQs to another CPU interface
+ *
+ * @new_cpu_id: the CPU target ID to migrate IRQs to
+ *
+ * Migrate all peripheral interrupts with a target matching the current CPU
+ * to the interface corresponding to @new_cpu_id. The CPU interface mapping
+ * is also updated. Targets to other CPU interfaces are unchanged.
+ * This must be called with IRQs locally disabled.
+ */
+void gic_migrate_target(unsigned int new_cpu_id)
+{
+ unsigned int cur_cpu_id, gic_irqs, gic_nr = 0;
+ void __iomem *dist_base;
+ int i, ror_val, cpu = smp_processor_id();
+ u32 val, cur_target_mask, active_mask;
+
+ if (gic_nr >= MAX_GIC_NR)
+ BUG();
+
+ dist_base = gic_data_dist_base(&gic_data[gic_nr]);
+ if (!dist_base)
+ return;
+ gic_irqs = gic_data[gic_nr].gic_irqs;
+
+ cur_cpu_id = __ffs(gic_cpu_map[cpu]);
+ cur_target_mask = 0x01010101 << cur_cpu_id;
+ ror_val = (cur_cpu_id - new_cpu_id) & 31;
+
+ raw_spin_lock(&irq_controller_lock);
+
+ /* Update the target interface for this logical CPU */
+ gic_cpu_map[cpu] = 1 << new_cpu_id;
+
+ /*
+ * Find all the peripheral interrupts targetting the current
+ * CPU interface and migrate them to the new CPU interface.
+ * We skip DIST_TARGET 0 to 7 as they are read-only.
+ */
+ for (i = 8; i < DIV_ROUND_UP(gic_irqs, 4); i++) {
+ val = readl_relaxed(dist_base + GIC_DIST_TARGET + i * 4);
+ active_mask = val & cur_target_mask;
+ if (active_mask) {
+ val &= ~active_mask;
+ val |= ror32(active_mask, ror_val);
+ writel_relaxed(val, dist_base + GIC_DIST_TARGET + i*4);
+ }
+ }
+
+ raw_spin_unlock(&irq_controller_lock);
+
+ /*
+ * Now let's migrate and clear any potential SGIs that might be
+ * pending for us (cur_cpu_id). Since GIC_DIST_SGI_PENDING_SET
+ * is a banked register, we can only forward the SGI using
+ * GIC_DIST_SOFTINT. The original SGI source is lost but Linux
+ * doesn't use that information anyway.
+ *
+ * For the same reason we do not adjust SGI source information
+ * for previously sent SGIs by us to other CPUs either.
+ */
+ for (i = 0; i < 16; i += 4) {
+ int j;
+ val = readl_relaxed(dist_base + GIC_DIST_SGI_PENDING_SET + i);
+ if (!val)
+ continue;
+ writel_relaxed(val, dist_base + GIC_DIST_SGI_PENDING_CLEAR + i);
+ for (j = i; j < i + 4; j++) {
+ if (val & 0xff)
+ writel_relaxed((1 << (new_cpu_id + 16)) | j,
+ dist_base + GIC_DIST_SOFTINT);
+ val >>= 8;
+ }
+ }
+}
+
+/*
+ * gic_get_sgir_physaddr - get the physical address for the SGI register
+ *
+ * REturn the physical address of the SGI register to be used
+ * by some early assembly code when the kernel is not yet available.
+ */
+static unsigned long gic_dist_physaddr;
+
+unsigned long gic_get_sgir_physaddr(void)
+{
+ if (!gic_dist_physaddr)
+ return 0;
+ return gic_dist_physaddr + GIC_DIST_SOFTINT;
+}
+
+void __init gic_init_physaddr(struct device_node *node)
+{
+ struct resource res;
+ if (of_address_to_resource(node, 0, &res) == 0) {
+ gic_dist_physaddr = res.start;
+ pr_info("GIC physical location is %#lx\n", gic_dist_physaddr);
+ }
+}
+
+#else
+#define gic_init_physaddr(node) do { } while (0)
+#endif
+
static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
@@ -675,16 +775,25 @@
irq_set_chip_and_handler(irq, &gic_chip,
handle_fasteoi_irq);
set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+
+ gic_routable_irq_domain_ops->map(d, irq, hw);
}
irq_set_chip_data(irq, d->host_data);
return 0;
}
+static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+ gic_routable_irq_domain_ops->unmap(d, irq);
+}
+
static int gic_irq_domain_xlate(struct irq_domain *d,
struct device_node *controller,
const u32 *intspec, unsigned int intsize,
unsigned long *out_hwirq, unsigned int *out_type)
{
+ unsigned long ret = 0;
+
if (d->of_node != controller)
return -EINVAL;
if (intsize < 3)
@@ -694,11 +803,20 @@
*out_hwirq = intspec[1] + 16;
/* For SPIs, we need to add 16 more to get the GIC irq ID number */
- if (!intspec[0])
- *out_hwirq += 16;
+ if (!intspec[0]) {
+ ret = gic_routable_irq_domain_ops->xlate(d, controller,
+ intspec,
+ intsize,
+ out_hwirq,
+ out_type);
+
+ if (IS_ERR_VALUE(ret))
+ return ret;
+ }
*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
- return 0;
+
+ return ret;
}
#ifdef CONFIG_SMP
@@ -720,11 +838,43 @@
};
#endif
-const struct irq_domain_ops gic_irq_domain_ops = {
+static const struct irq_domain_ops gic_irq_domain_ops = {
.map = gic_irq_domain_map,
+ .unmap = gic_irq_domain_unmap,
.xlate = gic_irq_domain_xlate,
};
+/* Default functions for routable irq domain */
+static int gic_routable_irq_domain_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hw)
+{
+ return 0;
+}
+
+static void gic_routable_irq_domain_unmap(struct irq_domain *d,
+ unsigned int irq)
+{
+}
+
+static int gic_routable_irq_domain_xlate(struct irq_domain *d,
+ struct device_node *controller,
+ const u32 *intspec, unsigned int intsize,
+ unsigned long *out_hwirq,
+ unsigned int *out_type)
+{
+ *out_hwirq += 16;
+ return 0;
+}
+
+const struct irq_domain_ops gic_default_routable_irq_domain_ops = {
+ .map = gic_routable_irq_domain_map,
+ .unmap = gic_routable_irq_domain_unmap,
+ .xlate = gic_routable_irq_domain_xlate,
+};
+
+const struct irq_domain_ops *gic_routable_irq_domain_ops =
+ &gic_default_routable_irq_domain_ops;
+
void __init gic_init_bases(unsigned int gic_nr, int irq_start,
void __iomem *dist_base, void __iomem *cpu_base,
u32 percpu_offset, struct device_node *node)
@@ -732,6 +882,7 @@
irq_hw_number_t hwirq_base;
struct gic_chip_data *gic;
int gic_irqs, irq_base, i;
+ int nr_routable_irqs;
BUG_ON(gic_nr >= MAX_GIC_NR);
@@ -750,7 +901,9 @@
}
for_each_possible_cpu(cpu) {
- unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+ u32 mpidr = cpu_logical_map(cpu);
+ u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+ unsigned long offset = percpu_offset * core_id;
*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
}
@@ -797,23 +950,35 @@
gic->gic_irqs = gic_irqs;
gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
- irq_base = irq_alloc_descs(irq_start, 16, gic_irqs, numa_node_id());
- if (IS_ERR_VALUE(irq_base)) {
- WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
- irq_start);
- irq_base = irq_start;
+
+ if (of_property_read_u32(node, "arm,routable-irqs",
+ &nr_routable_irqs)) {
+ irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+ numa_node_id());
+ if (IS_ERR_VALUE(irq_base)) {
+ WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+ irq_start);
+ irq_base = irq_start;
+ }
+
+ gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
+ hwirq_base, &gic_irq_domain_ops, gic);
+ } else {
+ gic->domain = irq_domain_add_linear(node, nr_routable_irqs,
+ &gic_irq_domain_ops,
+ gic);
}
- gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
- hwirq_base, &gic_irq_domain_ops, gic);
+
if (WARN_ON(!gic->domain))
return;
+ if (gic_nr == 0) {
#ifdef CONFIG_SMP
- set_smp_cross_call(gic_raise_softirq);
- register_cpu_notifier(&gic_cpu_notifier);
+ set_smp_cross_call(gic_raise_softirq);
+ register_cpu_notifier(&gic_cpu_notifier);
#endif
-
- set_handle_irq(gic_handle_irq);
+ set_handle_irq(gic_handle_irq);
+ }
gic_chip.flags |= gic_arch_extn.flags;
gic_dist_init(gic);
@@ -824,7 +989,8 @@
#ifdef CONFIG_OF
static int gic_cnt __initdata;
-int __init gic_of_init(struct device_node *node, struct device_node *parent)
+static int __init
+gic_of_init(struct device_node *node, struct device_node *parent)
{
void __iomem *cpu_base;
void __iomem *dist_base;
@@ -844,6 +1010,8 @@
percpu_offset = 0;
gic_init_bases(gic_cnt, -1, dist_base, cpu_base, percpu_offset, node);
+ if (!gic_cnt)
+ gic_init_physaddr(node);
if (parent) {
irq = irq_of_parse_and_map(node, 0);
@@ -852,8 +1020,10 @@
gic_cnt++;
return 0;
}
+IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
+IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 92c41ab..2cb474a 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -515,7 +515,7 @@
* one cpu (the interrupt code doesn't support it), so we just
* pick the first cpu we find in 'cpumask'.
*/
- cpu = cpumask_any(cpumask);
+ cpu = cpumask_any_and(cpumask, cpu_online_mask);
thread = cpu_2_hwthread_id[cpu];
metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr);
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 8e94d7a..c16c186 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -201,7 +201,7 @@
* one cpu (the interrupt code doesn't support it), so we just
* pick the first cpu we find in 'cpumask'.
*/
- cpu = cpumask_any(cpumask);
+ cpu = cpumask_any_and(cpumask, cpu_online_mask);
thread = cpu_2_hwthread_id[cpu];
metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)),
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index 927bff3..2f404ba 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -248,8 +248,8 @@
return 0;
err3:
- for (; k >= 0; k--)
- free_irq(p->irq[k - 1].requested_irq, &p->irq[k - 1]);
+ while (--k >= 0)
+ free_irq(p->irq[k].requested_irq, &p->irq[k]);
irq_domain_remove(p->irq_domain);
err2:
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 8527743..391b9ce 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -125,7 +125,7 @@
};
static struct spear_shirq spear320_shirq_ras3 = {
- .irq_nr = 3,
+ .irq_nr = 7,
.irq_bit_off = 0,
.invalid_irq = 1,
.regs = {
diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
index baf2686..5a4da94 100644
--- a/drivers/isdn/isdnloop/isdnloop.c
+++ b/drivers/isdn/isdnloop/isdnloop.c
@@ -518,9 +518,9 @@
static void
isdnloop_fake_err(isdnloop_card *card)
{
- char buf[60];
+ char buf[64];
- sprintf(buf, "E%s", card->omsg);
+ snprintf(buf, sizeof(buf), "E%s", card->omsg);
isdnloop_fake(card, buf, -1);
isdnloop_fake(card, "NAK", -1);
}
@@ -903,6 +903,8 @@
case 7:
/* 0x;EAZ */
p += 3;
+ if (strlen(p) >= sizeof(card->eazlist[0]))
+ break;
strcpy(card->eazlist[ch - 1], p);
break;
case 8:
@@ -1070,6 +1072,12 @@
return -EBUSY;
if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
return -EFAULT;
+
+ for (i = 0; i < 3; i++) {
+ if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
+ return -EINVAL;
+ }
+
spin_lock_irqsave(&card->isdnloop_lock, flags);
switch (sdef.ptype) {
case ISDN_PTYPE_EURO:
@@ -1083,8 +1091,10 @@
spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
- for (i = 0; i < 3; i++)
- strcpy(card->s0num[i], sdef.num[i]);
+ for (i = 0; i < 3; i++) {
+ strlcpy(card->s0num[i], sdef.num[i],
+ sizeof(card->s0num[0]));
+ }
break;
case ISDN_PTYPE_1TR6:
if (isdnloop_fake(card, "DRV1.04TC-1TR6-CAPI-CNS-BASIS-29.11.95",
@@ -1097,7 +1107,7 @@
spin_unlock_irqrestore(&card->isdnloop_lock, flags);
return -ENOMEM;
}
- strcpy(card->s0num[0], sdef.num[0]);
+ strlcpy(card->s0num[0], sdef.num[0], sizeof(card->s0num[0]));
card->s0num[1][0] = '\0';
card->s0num[2][0] = '\0';
break;
@@ -1125,7 +1135,7 @@
{
ulong a;
int i;
- char cbuf[60];
+ char cbuf[80];
isdn_ctrl cmd;
isdnloop_cdef cdef;
@@ -1190,7 +1200,6 @@
break;
if ((c->arg & 255) < ISDNLOOP_BCH) {
char *p;
- char dial[50];
char dcode[4];
a = c->arg;
@@ -1202,10 +1211,10 @@
} else
/* Normal Dial */
strcpy(dcode, "CAL");
- strcpy(dial, p);
- sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
- dcode, dial, c->parm.setup.si1,
- c->parm.setup.si2, c->parm.setup.eazmsn);
+ snprintf(cbuf, sizeof(cbuf),
+ "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
+ dcode, p, c->parm.setup.si1,
+ c->parm.setup.si2, c->parm.setup.eazmsn);
i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
}
break;
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index e47dcb9..5cefb47 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -117,7 +117,6 @@
{
struct sk_buff *skb;
struct sock *sk = sock->sk;
- struct sockaddr_mISDN *maddr;
int copied, err;
@@ -135,9 +134,9 @@
if (!skb)
return err;
- if (msg->msg_namelen >= sizeof(struct sockaddr_mISDN)) {
- msg->msg_namelen = sizeof(struct sockaddr_mISDN);
- maddr = (struct sockaddr_mISDN *)msg->msg_name;
+ if (msg->msg_name) {
+ struct sockaddr_mISDN *maddr = msg->msg_name;
+
maddr->family = AF_ISDN;
maddr->dev = _pms(sk)->dev->id;
if ((sk->sk_protocol == ISDN_P_LAPD_TE) ||
@@ -150,11 +149,7 @@
maddr->sapi = _pms(sk)->ch.addr & 0xFF;
maddr->tei = (_pms(sk)->ch.addr >> 8) & 0xFF;
}
- } else {
- if (msg->msg_namelen)
- printk(KERN_WARNING "%s: too small namelen %d\n",
- __func__, msg->msg_namelen);
- msg->msg_namelen = 0;
+ msg->msg_namelen = sizeof(*maddr);
}
copied = skb->len + MISDN_HEADER_LEN;
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index faf52c0..5d64b24 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -82,6 +82,15 @@
(sizeof(struct led_pwm_data) * num_leds);
}
+static void led_pwm_cleanup(struct led_pwm_priv *priv)
+{
+ while (priv->num_leds--) {
+ led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+ if (priv->leds[priv->num_leds].can_sleep)
+ cancel_work_sync(&priv->leds[priv->num_leds].work);
+ }
+}
+
static struct led_pwm_priv *led_pwm_create_of(struct platform_device *pdev)
{
struct device_node *node = pdev->dev.of_node;
@@ -139,8 +148,7 @@
return priv;
err:
- while (priv->num_leds--)
- led_classdev_unregister(&priv->leds[priv->num_leds].cdev);
+ led_pwm_cleanup(priv);
return NULL;
}
@@ -200,8 +208,8 @@
return 0;
err:
- while (i--)
- led_classdev_unregister(&priv->leds[i].cdev);
+ priv->num_leds = i;
+ led_pwm_cleanup(priv);
return ret;
}
@@ -209,13 +217,8 @@
static int led_pwm_remove(struct platform_device *pdev)
{
struct led_pwm_priv *priv = platform_get_drvdata(pdev);
- int i;
- for (i = 0; i < priv->num_leds; i++) {
- led_classdev_unregister(&priv->leds[i].cdev);
- if (priv->leds[i].can_sleep)
- cancel_work_sync(&priv->leds[i].work);
- }
+ led_pwm_cleanup(priv);
return 0;
}
diff --git a/drivers/leds/leds-wm831x-status.c b/drivers/leds/leds-wm831x-status.c
index 6bd5c67..b7d83d6 100644
--- a/drivers/leds/leds-wm831x-status.c
+++ b/drivers/leds/leds-wm831x-status.c
@@ -230,9 +230,9 @@
int id = pdev->id % ARRAY_SIZE(chip_pdata->status);
int ret;
- res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+ res = platform_get_resource(pdev, IORESOURCE_REG, 0);
if (res == NULL) {
- dev_err(&pdev->dev, "No I/O resource\n");
+ dev_err(&pdev->dev, "No register resource\n");
ret = -EINVAL;
goto err;
}
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index f0a3347..5169239 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -700,7 +700,7 @@
* interrupts are enabled. We always leave interrupts enabled while
* running the Guest.
*/
- regs->eflags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+ regs->eflags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
/*
* The "Extended Instruction Pointer" register says where the Guest is
diff --git a/drivers/macintosh/windfarm_rm31.c b/drivers/macintosh/windfarm_rm31.c
index 0b9a79b..82fc86a 100644
--- a/drivers/macintosh/windfarm_rm31.c
+++ b/drivers/macintosh/windfarm_rm31.c
@@ -439,15 +439,15 @@
/* Slots fan */
static const struct wf_pid_param slots_param = {
- .interval = 5,
- .history_len = 2,
- .gd = 30 << 20,
- .gp = 5 << 20,
- .gr = 0,
- .itarget = 40 << 16,
- .additive = 1,
- .min = 300,
- .max = 4000,
+ .interval = 1,
+ .history_len = 20,
+ .gd = 0,
+ .gp = 0,
+ .gr = 0x00100000,
+ .itarget = 3200000,
+ .additive = 0,
+ .min = 20,
+ .max = 100,
};
static void slots_fan_tick(void)
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 543ad6a..fefef7e 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -1 +1,5 @@
+# Generic MAILBOX API
+
+obj-$(CONFIG_MAILBOX) += mailbox.o
+
obj-$(CONFIG_PL320_MBOX) += pl320-ipc.o
diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
new file mode 100644
index 0000000..afcb430
--- /dev/null
+++ b/drivers/mailbox/mailbox.c
@@ -0,0 +1,465 @@
+/*
+ * Mailbox: Common code for Mailbox controllers and users
+ *
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/bitops.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox_controller.h>
+
+#define TXDONE_BY_IRQ BIT(0) /* controller has remote RTR irq */
+#define TXDONE_BY_POLL BIT(1) /* controller can read status of last TX */
+#define TXDONE_BY_ACK BIT(2) /* S/W ACK recevied by Client ticks the TX */
+
+static LIST_HEAD(mbox_cons);
+static DEFINE_MUTEX(con_mutex);
+
+static int add_to_rbuf(struct mbox_chan *chan, void *mssg)
+{
+ int idx;
+ unsigned long flags;
+
+ spin_lock_irqsave(&chan->lock, flags);
+
+ /* See if there is any space left */
+ if (chan->msg_count == MBOX_TX_QUEUE_LEN) {
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return -ENOBUFS;
+ }
+
+ idx = chan->msg_free;
+ chan->msg_data[idx] = mssg;
+ chan->msg_count++;
+
+ if (idx == MBOX_TX_QUEUE_LEN - 1)
+ chan->msg_free = 0;
+ else
+ chan->msg_free++;
+
+ spin_unlock_irqrestore(&chan->lock, flags);
+
+ return idx;
+}
+
+static void msg_submit(struct mbox_chan *chan)
+{
+ unsigned count, idx;
+ unsigned long flags;
+ void *data;
+ int err;
+
+ spin_lock_irqsave(&chan->lock, flags);
+
+ if (!chan->msg_count || chan->active_req)
+ goto exit;
+
+ count = chan->msg_count;
+ idx = chan->msg_free;
+ if (idx >= count)
+ idx -= count;
+ else
+ idx += MBOX_TX_QUEUE_LEN - count;
+
+ data = chan->msg_data[idx];
+
+ /* Try to submit a message to the MBOX controller */
+ err = chan->mbox->ops->send_data(chan, data);
+ if (!err) {
+ chan->active_req = data;
+ chan->msg_count--;
+ }
+exit:
+ spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+static void tx_tick(struct mbox_chan *chan, int r)
+{
+ unsigned long flags;
+ void *mssg;
+
+ spin_lock_irqsave(&chan->lock, flags);
+ mssg = chan->active_req;
+ chan->active_req = NULL;
+ spin_unlock_irqrestore(&chan->lock, flags);
+
+ /* Submit next message */
+ msg_submit(chan);
+
+ /* Notify the client */
+ if (mssg && chan->cl->tx_done)
+ chan->cl->tx_done(chan->cl, mssg, r);
+
+ if (chan->cl->tx_block)
+ complete(&chan->tx_complete);
+}
+
+static void poll_txdone(unsigned long data)
+{
+ struct mbox_controller *mbox = (struct mbox_controller *)data;
+ bool txdone, resched = false;
+ int i;
+
+ for (i = 0; i < mbox->num_chans; i++) {
+ struct mbox_chan *chan = &mbox->chans[i];
+
+ if (chan->active_req && chan->cl) {
+ resched = true;
+ txdone = chan->mbox->ops->last_tx_done(chan);
+ if (txdone)
+ tx_tick(chan, 0);
+ }
+ }
+
+ if (resched)
+ mod_timer(&mbox->poll, jiffies +
+ msecs_to_jiffies(mbox->txpoll_period));
+}
+
+/**
+ * mbox_chan_received_data - A way for controller driver to push data
+ * received from remote to the upper layer.
+ * @chan: Pointer to the mailbox channel on which RX happened.
+ * @mssg: Client specific message typecasted as void *
+ *
+ * After startup and before shutdown any data received on the chan
+ * is passed on to the API via atomic mbox_chan_received_data().
+ * The controller should ACK the RX only after this call returns.
+ */
+void mbox_chan_received_data(struct mbox_chan *chan, void *mssg)
+{
+ /* No buffering the received data */
+ if (chan->cl->rx_callback)
+ chan->cl->rx_callback(chan->cl, mssg);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_received_data);
+
+/**
+ * mbox_chan_txdone - A way for controller driver to notify the
+ * framework that the last TX has completed.
+ * @chan: Pointer to the mailbox chan on which TX happened.
+ * @r: Status of last TX - OK or ERROR
+ *
+ * The controller that has IRQ for TX ACK calls this atomic API
+ * to tick the TX state machine. It works only if txdone_irq
+ * is set by the controller.
+ */
+void mbox_chan_txdone(struct mbox_chan *chan, int r)
+{
+ if (unlikely(!(chan->txdone_method & TXDONE_BY_IRQ))) {
+ dev_err(chan->mbox->dev,
+ "Controller can't run the TX ticker\n");
+ return;
+ }
+
+ tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_chan_txdone);
+
+/**
+ * mbox_client_txdone - The way for a client to run the TX state machine.
+ * @chan: Mailbox channel assigned to this client.
+ * @r: Success status of last transmission.
+ *
+ * The client/protocol had received some 'ACK' packet and it notifies
+ * the API that the last packet was sent successfully. This only works
+ * if the controller can't sense TX-Done.
+ */
+void mbox_client_txdone(struct mbox_chan *chan, int r)
+{
+ if (unlikely(!(chan->txdone_method & TXDONE_BY_ACK))) {
+ dev_err(chan->mbox->dev, "Client can't run the TX ticker\n");
+ return;
+ }
+
+ tx_tick(chan, r);
+}
+EXPORT_SYMBOL_GPL(mbox_client_txdone);
+
+/**
+ * mbox_client_peek_data - A way for client driver to pull data
+ * received from remote by the controller.
+ * @chan: Mailbox channel assigned to this client.
+ *
+ * A poke to controller driver for any received data.
+ * The data is actually passed onto client via the
+ * mbox_chan_received_data()
+ * The call can be made from atomic context, so the controller's
+ * implementation of peek_data() must not sleep.
+ *
+ * Return: True, if controller has, and is going to push after this,
+ * some data.
+ * False, if controller doesn't have any data to be read.
+ */
+bool mbox_client_peek_data(struct mbox_chan *chan)
+{
+ if (chan->mbox->ops->peek_data)
+ return chan->mbox->ops->peek_data(chan);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(mbox_client_peek_data);
+
+/**
+ * mbox_send_message - For client to submit a message to be
+ * sent to the remote.
+ * @chan: Mailbox channel assigned to this client.
+ * @mssg: Client specific message typecasted.
+ *
+ * For client to submit data to the controller destined for a remote
+ * processor. If the client had set 'tx_block', the call will return
+ * either when the remote receives the data or when 'tx_tout' millisecs
+ * run out.
+ * In non-blocking mode, the requests are buffered by the API and a
+ * non-negative token is returned for each queued request. If the request
+ * is not queued, a negative token is returned. Upon failure or successful
+ * TX, the API calls 'tx_done' from atomic context, from which the client
+ * could submit yet another request.
+ * The pointer to message should be preserved until it is sent
+ * over the chan, i.e, tx_done() is made.
+ * This function could be called from atomic context as it simply
+ * queues the data and returns a token against the request.
+ *
+ * Return: Non-negative integer for successful submission (non-blocking mode)
+ * or transmission over chan (blocking mode).
+ * Negative value denotes failure.
+ */
+int mbox_send_message(struct mbox_chan *chan, void *mssg)
+{
+ int t;
+
+ if (!chan || !chan->cl)
+ return -EINVAL;
+
+ t = add_to_rbuf(chan, mssg);
+ if (t < 0) {
+ dev_err(chan->mbox->dev, "Try increasing MBOX_TX_QUEUE_LEN\n");
+ return t;
+ }
+
+ msg_submit(chan);
+
+ if (chan->txdone_method == TXDONE_BY_POLL)
+ poll_txdone((unsigned long)chan->mbox);
+
+ if (chan->cl->tx_block && chan->active_req) {
+ unsigned long wait;
+ int ret;
+
+ if (!chan->cl->tx_tout) /* wait forever */
+ wait = msecs_to_jiffies(3600000);
+ else
+ wait = msecs_to_jiffies(chan->cl->tx_tout);
+
+ ret = wait_for_completion_timeout(&chan->tx_complete, wait);
+ if (ret == 0) {
+ t = -EIO;
+ tx_tick(chan, -EIO);
+ }
+ }
+
+ return t;
+}
+EXPORT_SYMBOL_GPL(mbox_send_message);
+
+/**
+ * mbox_request_channel - Request a mailbox channel.
+ * @cl: Identity of the client requesting the channel.
+ * @index: Index of mailbox specifier in 'mboxes' property.
+ *
+ * The Client specifies its requirements and capabilities while asking for
+ * a mailbox channel. It can't be called from atomic context.
+ * The channel is exclusively allocated and can't be used by another
+ * client before the owner calls mbox_free_channel.
+ * After assignment, any packet received on this channel will be
+ * handed over to the client via the 'rx_callback'.
+ * The framework holds reference to the client, so the mbox_client
+ * structure shouldn't be modified until the mbox_free_channel returns.
+ *
+ * Return: Pointer to the channel assigned to the client if successful.
+ * ERR_PTR for request failure.
+ */
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index)
+{
+ struct device *dev = cl->dev;
+ struct mbox_controller *mbox;
+ struct of_phandle_args spec;
+ struct mbox_chan *chan;
+ unsigned long flags;
+ int ret;
+
+ if (!dev || !dev->of_node) {
+ pr_debug("%s: No owner device node\n", __func__);
+ return ERR_PTR(-ENODEV);
+ }
+
+ mutex_lock(&con_mutex);
+
+ if (of_parse_phandle_with_args(dev->of_node, "mboxes",
+ "#mbox-cells", index, &spec)) {
+ dev_dbg(dev, "%s: can't parse \"mboxes\" property\n", __func__);
+ mutex_unlock(&con_mutex);
+ return ERR_PTR(-ENODEV);
+ }
+
+ chan = NULL;
+ list_for_each_entry(mbox, &mbox_cons, node)
+ if (mbox->dev->of_node == spec.np) {
+ chan = mbox->of_xlate(mbox, &spec);
+ break;
+ }
+
+ of_node_put(spec.np);
+
+ if (!chan || chan->cl || !try_module_get(mbox->dev->driver->owner)) {
+ dev_dbg(dev, "%s: mailbox not free\n", __func__);
+ mutex_unlock(&con_mutex);
+ return ERR_PTR(-EBUSY);
+ }
+
+ spin_lock_irqsave(&chan->lock, flags);
+ chan->msg_free = 0;
+ chan->msg_count = 0;
+ chan->active_req = NULL;
+ chan->cl = cl;
+ init_completion(&chan->tx_complete);
+
+ if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone)
+ chan->txdone_method |= TXDONE_BY_ACK;
+
+ spin_unlock_irqrestore(&chan->lock, flags);
+
+ ret = chan->mbox->ops->startup(chan);
+ if (ret) {
+ dev_err(dev, "Unable to startup the chan (%d)\n", ret);
+ mbox_free_channel(chan);
+ chan = ERR_PTR(ret);
+ }
+
+ mutex_unlock(&con_mutex);
+ return chan;
+}
+EXPORT_SYMBOL_GPL(mbox_request_channel);
+
+/**
+ * mbox_free_channel - The client relinquishes control of a mailbox
+ * channel by this call.
+ * @chan: The mailbox channel to be freed.
+ */
+void mbox_free_channel(struct mbox_chan *chan)
+{
+ unsigned long flags;
+
+ if (!chan || !chan->cl)
+ return;
+
+ chan->mbox->ops->shutdown(chan);
+
+ /* The queued TX requests are simply aborted, no callbacks are made */
+ spin_lock_irqsave(&chan->lock, flags);
+ chan->cl = NULL;
+ chan->active_req = NULL;
+ if (chan->txdone_method == (TXDONE_BY_POLL | TXDONE_BY_ACK))
+ chan->txdone_method = TXDONE_BY_POLL;
+
+ module_put(chan->mbox->dev->driver->owner);
+ spin_unlock_irqrestore(&chan->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mbox_free_channel);
+
+static struct mbox_chan *
+of_mbox_index_xlate(struct mbox_controller *mbox,
+ const struct of_phandle_args *sp)
+{
+ int ind = sp->args[0];
+
+ if (ind >= mbox->num_chans)
+ return NULL;
+
+ return &mbox->chans[ind];
+}
+
+/**
+ * mbox_controller_register - Register the mailbox controller
+ * @mbox: Pointer to the mailbox controller.
+ *
+ * The controller driver registers its communication channels
+ */
+int mbox_controller_register(struct mbox_controller *mbox)
+{
+ int i, txdone;
+
+ /* Sanity check */
+ if (!mbox || !mbox->dev || !mbox->ops || !mbox->num_chans)
+ return -EINVAL;
+
+ if (mbox->txdone_irq)
+ txdone = TXDONE_BY_IRQ;
+ else if (mbox->txdone_poll)
+ txdone = TXDONE_BY_POLL;
+ else /* It has to be ACK then */
+ txdone = TXDONE_BY_ACK;
+
+ if (txdone == TXDONE_BY_POLL) {
+ mbox->poll.function = &poll_txdone;
+ mbox->poll.data = (unsigned long)mbox;
+ init_timer(&mbox->poll);
+ }
+
+ for (i = 0; i < mbox->num_chans; i++) {
+ struct mbox_chan *chan = &mbox->chans[i];
+
+ chan->cl = NULL;
+ chan->mbox = mbox;
+ chan->txdone_method = txdone;
+ spin_lock_init(&chan->lock);
+ }
+
+ if (!mbox->of_xlate)
+ mbox->of_xlate = of_mbox_index_xlate;
+
+ mutex_lock(&con_mutex);
+ list_add_tail(&mbox->node, &mbox_cons);
+ mutex_unlock(&con_mutex);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mbox_controller_register);
+
+/**
+ * mbox_controller_unregister - Unregister the mailbox controller
+ * @mbox: Pointer to the mailbox controller.
+ */
+void mbox_controller_unregister(struct mbox_controller *mbox)
+{
+ int i;
+
+ if (!mbox)
+ return;
+
+ mutex_lock(&con_mutex);
+
+ list_del(&mbox->node);
+
+ for (i = 0; i < mbox->num_chans; i++)
+ mbox_free_channel(&mbox->chans[i]);
+
+ if (mbox->txdone_poll)
+ del_timer_sync(&mbox->poll);
+
+ mutex_unlock(&con_mutex);
+}
+EXPORT_SYMBOL_GPL(mbox_controller_unregister);
diff --git a/drivers/mailbox/pl320-ipc.c b/drivers/mailbox/pl320-ipc.c
index d873cba..f3755e0 100644
--- a/drivers/mailbox/pl320-ipc.c
+++ b/drivers/mailbox/pl320-ipc.c
@@ -26,7 +26,7 @@
#include <linux/device.h>
#include <linux/amba/bus.h>
-#include <linux/mailbox.h>
+#include <linux/pl320-ipc.h>
#define IPCMxSOURCE(m) ((m) * 0x40)
#define IPCMxDSET(m) (((m) * 0x40) + 0x004)
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 3bfc8f1..29cff90 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -176,8 +176,12 @@
source "drivers/md/bcache/Kconfig"
+config BLK_DEV_DM_BUILTIN
+ boolean
+
config BLK_DEV_DM
tristate "Device mapper support"
+ select BLK_DEV_DM_BUILTIN
---help---
Device-mapper is a low level volume manager. It works by allowing
people to specify mappings for ranges of logical sectors. Various
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 1439fd4..3591a72 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -32,6 +32,7 @@
obj-$(CONFIG_BCACHE) += bcache/
obj-$(CONFIG_BLK_DEV_MD) += md-mod.o
obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o
+obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
obj-$(CONFIG_DM_BUFIO) += dm-bufio.o
obj-$(CONFIG_DM_BIO_PRISON) += dm-bio-prison.o
obj-$(CONFIG_DM_CRYPT) += dm-crypt.o
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d3e15b4..6bc016e 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -437,6 +437,7 @@
/* If nonzero, we're detaching/unregistering from cache set */
atomic_t detaching;
+ int flush_done;
atomic_long_t sectors_dirty;
unsigned long sectors_dirty_gc;
@@ -498,7 +499,7 @@
*/
atomic_t has_dirty;
- struct ratelimit writeback_rate;
+ struct bch_ratelimit writeback_rate;
struct delayed_work writeback_rate_update;
/*
@@ -507,10 +508,9 @@
*/
sector_t last_read;
- /* Number of writeback bios in flight */
- atomic_t in_flight;
+ /* Limit number of writeback bios in flight */
+ struct semaphore in_flight;
struct closure_with_timer writeback;
- struct closure_waitlist writeback_wait;
struct keybuf writeback_keys;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index cb4578a..1b27cbd 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -918,29 +918,59 @@
/* Mergesort */
-static void btree_sort_fixup(struct btree_iter *iter)
+static void sort_key_next(struct btree_iter *iter,
+ struct btree_iter_set *i)
+{
+ i->k = bkey_next(i->k);
+
+ if (i->k == i->end)
+ *i = iter->data[--iter->used];
+}
+
+static struct bkey *btree_sort_fixup(struct btree_iter *iter, struct bkey *tmp)
{
while (iter->used > 1) {
struct btree_iter_set *top = iter->data, *i = top + 1;
- struct bkey *k;
if (iter->used > 2 &&
btree_iter_cmp(i[0], i[1]))
i++;
- for (k = i->k;
- k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
- k = bkey_next(k))
- if (top->k > i->k)
- __bch_cut_front(top->k, k);
- else if (KEY_SIZE(k))
- bch_cut_back(&START_KEY(k), top->k);
-
- if (top->k < i->k || k == i->k)
+ if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
break;
- heap_sift(iter, i - top, btree_iter_cmp);
+ if (!KEY_SIZE(i->k)) {
+ sort_key_next(iter, i);
+ heap_sift(iter, i - top, btree_iter_cmp);
+ continue;
+ }
+
+ if (top->k > i->k) {
+ if (bkey_cmp(top->k, i->k) >= 0)
+ sort_key_next(iter, i);
+ else
+ bch_cut_front(top->k, i->k);
+
+ heap_sift(iter, i - top, btree_iter_cmp);
+ } else {
+ /* can't happen because of comparison func */
+ BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
+
+ if (bkey_cmp(i->k, top->k) < 0) {
+ bkey_copy(tmp, top->k);
+
+ bch_cut_back(&START_KEY(i->k), tmp);
+ bch_cut_front(i->k, top->k);
+ heap_sift(iter, 0, btree_iter_cmp);
+
+ return tmp;
+ } else {
+ bch_cut_back(&START_KEY(i->k), top->k);
+ }
+ }
}
+
+ return NULL;
}
static void btree_mergesort(struct btree *b, struct bset *out,
@@ -948,15 +978,20 @@
bool fixup, bool remove_stale)
{
struct bkey *k, *last = NULL;
+ BKEY_PADDED(k) tmp;
bool (*bad)(struct btree *, const struct bkey *) = remove_stale
? bch_ptr_bad
: bch_ptr_invalid;
while (!btree_iter_end(iter)) {
if (fixup && !b->level)
- btree_sort_fixup(iter);
+ k = btree_sort_fixup(iter, &tmp.k);
+ else
+ k = NULL;
- k = bch_btree_iter_next(iter);
+ if (!k)
+ k = bch_btree_iter_next(iter);
+
if (bad(b, k))
continue;
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 7a5658f..7d3deab 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -326,10 +326,25 @@
i->csum = btree_csum_set(b, i);
btree_bio_init(b);
- b->bio->bi_rw = REQ_META|WRITE_SYNC;
+ b->bio->bi_rw = REQ_META|WRITE_SYNC|REQ_FUA;
b->bio->bi_size = set_blocks(i, b->c) * block_bytes(b->c);
bch_bio_map(b->bio, i);
+ /*
+ * If we're appending to a leaf node, we don't technically need FUA -
+ * this write just needs to be persisted before the next journal write,
+ * which will be marked FLUSH|FUA.
+ *
+ * Similarly if we're writing a new btree root - the pointer is going to
+ * be in the next journal entry.
+ *
+ * But if we're writing a new btree node (that isn't a root) or
+ * appending to a non leaf btree node, we need either FUA or a flush
+ * when we write the parent with the new pointer. FUA is cheaper than a
+ * flush, and writes appending to leaf nodes aren't blocking anything so
+ * just make all btree node writes FUA to keep things sane.
+ */
+
bkey_copy(&k.key, &b->key);
SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) + bset_offset(b, i));
@@ -618,7 +633,7 @@
return mca_can_free(c) * c->btree_pages;
/* Return -1 if we can't do anything right now */
- if (sc->gfp_mask & __GFP_WAIT)
+ if (sc->gfp_mask & __GFP_IO)
mutex_lock(&c->bucket_lock);
else if (!mutex_trylock(&c->bucket_lock))
return -1;
@@ -1419,8 +1434,10 @@
for_each_cache(ca, c, i)
for_each_bucket(b, ca) {
b->gc_gen = b->gen;
- if (!atomic_read(&b->pin))
+ if (!atomic_read(&b->pin)) {
SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
+ SET_GC_SECTORS_USED(b, 0);
+ }
}
for (d = c->devices;
@@ -2140,6 +2157,9 @@
void bch_btree_set_root(struct btree *b)
{
unsigned i;
+ struct closure cl;
+
+ closure_init_stack(&cl);
BUG_ON(!b->written);
@@ -2153,8 +2173,9 @@
b->c->root = b;
__bkey_put(b->c, &b->key);
- bch_journal_meta(b->c, NULL);
+ bch_journal_meta(b->c, &cl);
pr_debug("%s for %pf", pbtree(b), __builtin_return_address(0));
+ closure_sync(&cl);
}
/* Cache lookup */
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index bd05a9a..9aba201 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -66,16 +66,18 @@
} else {
struct closure *parent = cl->parent;
struct closure_waitlist *wait = closure_waitlist(cl);
+ closure_fn *destructor = cl->fn;
closure_debug_destroy(cl);
+ smp_mb();
atomic_set(&cl->remaining, -1);
if (wait)
closure_wake_up(wait);
- if (cl->fn)
- cl->fn(cl);
+ if (destructor)
+ destructor(cl);
if (parent)
closure_put(parent);
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 48efd4d..d285cd4 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -97,6 +97,8 @@
if (bio->bi_rw & REQ_DISCARD) {
ret = bio_alloc_bioset(gfp, 1, bs);
+ if (!ret)
+ return NULL;
idx = 0;
goto out;
}
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 8c8dfdc..151a4ab 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -151,7 +151,8 @@
bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
pr_debug("%u journal buckets", ca->sb.njournal_buckets);
- /* Read journal buckets ordered by golden ratio hash to quickly
+ /*
+ * Read journal buckets ordered by golden ratio hash to quickly
* find a sequence of buckets with valid journal entries
*/
for (i = 0; i < ca->sb.njournal_buckets; i++) {
@@ -164,36 +165,45 @@
goto bsearch;
}
- /* If that fails, check all the buckets we haven't checked
+ /*
+ * If that fails, check all the buckets we haven't checked
* already
*/
pr_debug("falling back to linear search");
- for (l = 0; l < ca->sb.njournal_buckets; l++) {
- if (test_bit(l, bitmap))
- continue;
-
+ for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
+ l < ca->sb.njournal_buckets;
+ l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
if (read_bucket(l))
goto bsearch;
- }
+
+ if (list_empty(list))
+ continue;
bsearch:
/* Binary search */
m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
pr_debug("starting binary search, l %u r %u", l, r);
while (l + 1 < r) {
- m = (l + r) >> 1;
+ seq = list_entry(list->prev, struct journal_replay,
+ list)->j.seq;
- if (read_bucket(m))
+ m = (l + r) >> 1;
+ read_bucket(m);
+
+ if (seq != list_entry(list->prev, struct journal_replay,
+ list)->j.seq)
l = m;
else
r = m;
}
- /* Read buckets in reverse order until we stop finding more
+ /*
+ * Read buckets in reverse order until we stop finding more
* journal entries
*/
- pr_debug("finishing up");
+ pr_debug("finishing up: m %u njournal_buckets %u",
+ m, ca->sb.njournal_buckets);
l = m;
while (1) {
@@ -221,9 +231,10 @@
}
}
- c->journal.seq = list_entry(list->prev,
- struct journal_replay,
- list)->j.seq;
+ if (!list_empty(list))
+ c->journal.seq = list_entry(list->prev,
+ struct journal_replay,
+ list)->j.seq;
return 0;
#undef read_bucket
@@ -420,7 +431,7 @@
return;
}
- switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) {
+ switch (atomic_read(&ja->discard_in_flight)) {
case DISCARD_IN_FLIGHT:
return;
@@ -617,7 +628,7 @@
bio_reset(bio);
bio->bi_sector = PTR_OFFSET(k, i);
bio->bi_bdev = ca->bdev;
- bio->bi_rw = REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH;
+ bio->bi_rw = REQ_WRITE|REQ_SYNC|REQ_META|REQ_FLUSH|REQ_FUA;
bio->bi_size = sectors << 9;
bio->bi_end_io = journal_write_endio;
@@ -681,6 +692,7 @@
if (cl)
BUG_ON(!closure_wait(&w->wait, cl));
+ closure_flush(&c->journal.io);
__journal_try_write(c, true);
}
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index e5ff12e5..a30a0f8 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -489,6 +489,12 @@
bch_queue_gc(op->c);
}
+ /*
+ * Journal writes are marked REQ_FLUSH; if the original write was a
+ * flush, it'll wait on the journal write.
+ */
+ bio->bi_rw &= ~(REQ_FLUSH|REQ_FUA);
+
do {
unsigned i;
struct bkey *k;
@@ -716,7 +722,7 @@
s->task = current;
s->orig_bio = bio;
s->write = (bio->bi_rw & REQ_WRITE) != 0;
- s->op.flush_journal = (bio->bi_rw & REQ_FLUSH) != 0;
+ s->op.flush_journal = (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;
s->op.skip = (bio->bi_rw & REQ_DISCARD) != 0;
s->recoverable = 1;
s->start_time = jiffies;
@@ -1047,9 +1053,22 @@
trace_bcache_writethrough(s->orig_bio);
closure_bio_submit(bio, cl, s->d);
} else {
- s->op.cache_bio = bio;
trace_bcache_writeback(s->orig_bio);
bch_writeback_add(dc, bio_sectors(bio));
+ s->op.cache_bio = bio;
+
+ if (bio->bi_rw & REQ_FLUSH) {
+ /* Also need to send a flush to the backing device */
+ struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0,
+ dc->disk.bio_split);
+
+ flush->bi_rw = WRITE_FLUSH;
+ flush->bi_bdev = bio->bi_bdev;
+ flush->bi_end_io = request_endio;
+ flush->bi_private = cl;
+
+ closure_bio_submit(flush, cl, s->d);
+ }
}
out:
closure_call(&s->op.cl, bch_insert_data, NULL, cl);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index f88e2b6..b4713ce 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -704,7 +704,8 @@
atomic_set(&d->detaching, 0);
}
- bcache_device_unlink(d);
+ if (!d->flush_done)
+ bcache_device_unlink(d);
d->c->devices[d->id] = NULL;
closure_put(&d->c->caching);
@@ -781,6 +782,8 @@
set_bit(QUEUE_FLAG_NONROT, &d->disk->queue->queue_flags);
set_bit(QUEUE_FLAG_DISCARD, &d->disk->queue->queue_flags);
+ blk_queue_flush(q, REQ_FLUSH|REQ_FUA);
+
return 0;
}
@@ -1014,6 +1017,14 @@
struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
struct bcache_device *d = &dc->disk;
+ mutex_lock(&bch_register_lock);
+ d->flush_done = 1;
+
+ if (d->c)
+ bcache_device_unlink(d);
+
+ mutex_unlock(&bch_register_lock);
+
bch_cache_accounting_destroy(&dc->accounting);
kobject_del(&d->kobj);
@@ -1303,18 +1314,22 @@
static void __cache_set_unregister(struct closure *cl)
{
struct cache_set *c = container_of(cl, struct cache_set, caching);
- struct cached_dev *dc, *t;
+ struct cached_dev *dc;
size_t i;
mutex_lock(&bch_register_lock);
- if (test_bit(CACHE_SET_UNREGISTERING, &c->flags))
- list_for_each_entry_safe(dc, t, &c->cached_devs, list)
- bch_cached_dev_detach(dc);
-
for (i = 0; i < c->nr_uuids; i++)
- if (c->devices[i] && UUID_FLASH_ONLY(&c->uuids[i]))
- bcache_device_stop(c->devices[i]);
+ if (c->devices[i]) {
+ if (!UUID_FLASH_ONLY(&c->uuids[i]) &&
+ test_bit(CACHE_SET_UNREGISTERING, &c->flags)) {
+ dc = container_of(c->devices[i],
+ struct cached_dev, disk);
+ bch_cached_dev_detach(dc);
+ } else {
+ bcache_device_stop(c->devices[i]);
+ }
+ }
mutex_unlock(&bch_register_lock);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4d9cca4..e9bd6c0 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -214,7 +214,13 @@
}
if (attr == &sysfs_label) {
- memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+ if (size > SB_LABEL_SIZE)
+ return -EINVAL;
+ memcpy(dc->sb.label, buf, size);
+ if (size < SB_LABEL_SIZE)
+ dc->sb.label[size] = '\0';
+ if (size && dc->sb.label[size - 1] == '\n')
+ dc->sb.label[size - 1] = '\0';
bch_write_bdev_super(dc, NULL);
if (dc->disk.c) {
memcpy(dc->disk.c->uuids[dc->disk.id].label,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index da3a99e..38a43f8 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -190,7 +190,16 @@
stats->last = now ?: 1;
}
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
+/**
+ * bch_next_delay() - increment @d by the amount of work done, and return how
+ * long to delay until the next time to do some work.
+ *
+ * @d - the struct bch_ratelimit to update
+ * @done - the amount of work done, in arbitrary units
+ *
+ * Returns the amount of time to delay by, in jiffies
+ */
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
{
uint64_t now = local_clock();
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 577393e..43fd78a 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -452,17 +452,23 @@
(ewma) >> factor; \
})
-struct ratelimit {
+struct bch_ratelimit {
+ /* Next time we want to do some work, in nanoseconds */
uint64_t next;
+
+ /*
+ * Rate at which we want to do work, in units per nanosecond
+ * The units here correspond to the units passed to bch_next_delay()
+ */
unsigned rate;
};
-static inline void ratelimit_reset(struct ratelimit *d)
+static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
{
d->next = local_clock();
}
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done);
#define __DIV_SAFE(n, d, zero) \
({ \
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 2714ed3..841f049 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -91,11 +91,15 @@
static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
{
+ uint64_t ret;
+
if (atomic_read(&dc->disk.detaching) ||
!dc->writeback_percent)
return 0;
- return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+ ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+
+ return min_t(uint64_t, ret, HZ);
}
/* Background writeback */
@@ -165,7 +169,7 @@
up_write(&dc->writeback_lock);
- ratelimit_reset(&dc->writeback_rate);
+ bch_ratelimit_reset(&dc->writeback_rate);
/* Punt to workqueue only so we don't recurse and blow the stack */
continue_at(cl, read_dirty, dirty_wq);
@@ -246,9 +250,7 @@
}
bch_keybuf_del(&dc->writeback_keys, w);
- atomic_dec_bug(&dc->in_flight);
-
- closure_wake_up(&dc->writeback_wait);
+ up(&dc->in_flight);
closure_return_with_destructor(cl, dirty_io_destructor);
}
@@ -278,7 +280,7 @@
trace_bcache_write_dirty(&io->bio);
closure_bio_submit(&io->bio, cl, &io->dc->disk);
- continue_at(cl, write_dirty_finish, dirty_wq);
+ continue_at(cl, write_dirty_finish, system_wq);
}
static void read_dirty_endio(struct bio *bio, int error)
@@ -299,7 +301,7 @@
trace_bcache_read_dirty(&io->bio);
closure_bio_submit(&io->bio, cl, &io->dc->disk);
- continue_at(cl, write_dirty, dirty_wq);
+ continue_at(cl, write_dirty, system_wq);
}
static void read_dirty(struct closure *cl)
@@ -324,12 +326,8 @@
if (delay > 0 &&
(KEY_START(&w->key) != dc->last_read ||
- jiffies_to_msecs(delay) > 50)) {
- w->private = NULL;
-
- closure_delay(&dc->writeback, delay);
- continue_at(cl, read_dirty, dirty_wq);
- }
+ jiffies_to_msecs(delay) > 50))
+ delay = schedule_timeout_uninterruptible(delay);
dc->last_read = KEY_OFFSET(&w->key);
@@ -354,15 +352,10 @@
pr_debug("%s", pkey(&w->key));
- closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
+ down(&dc->in_flight);
+ closure_call(&io->cl, read_dirty_submit, NULL, cl);
delay = writeback_delay(dc, KEY_SIZE(&w->key));
-
- atomic_inc(&dc->in_flight);
-
- if (!closure_wait_event(&dc->writeback_wait, cl,
- atomic_read(&dc->in_flight) < 64))
- continue_at(cl, read_dirty, dirty_wq);
}
if (0) {
@@ -372,11 +365,16 @@
bch_keybuf_del(&dc->writeback_keys, w);
}
- refill_dirty(cl);
+ /*
+ * Wait for outstanding writeback IOs to finish (and keybuf slots to be
+ * freed) before refilling again
+ */
+ continue_at(cl, refill_dirty, dirty_wq);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)
{
+ sema_init(&dc->in_flight, 64);
closure_init_unlocked(&dc->writeback);
init_rwsem(&dc->writeback_lock);
@@ -406,7 +404,7 @@
int __init bch_writeback_init(void)
{
- dirty_wq = create_singlethread_workqueue("bcache_writeback");
+ dirty_wq = create_workqueue("bcache_writeback");
if (!dirty_wq)
return -ENOMEM;
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 5a2c754..a79cbd6 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -883,7 +883,6 @@
{
unsigned long i;
int dirty, need_write;
- int wait = 0;
if (!bitmap || !bitmap->storage.filemap ||
test_bit(BITMAP_STALE, &bitmap->flags))
@@ -901,16 +900,13 @@
clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
write_page(bitmap, bitmap->storage.filemap[i], 0);
}
- if (dirty)
- wait = 1;
}
- if (wait) { /* if any writes were performed, we need to wait on them */
- if (bitmap->storage.file)
- wait_event(bitmap->write_wait,
- atomic_read(&bitmap->pending_writes)==0);
- else
- md_super_wait(bitmap->mddev);
- }
+ if (bitmap->storage.file)
+ wait_event(bitmap->write_wait,
+ atomic_read(&bitmap->pending_writes)==0);
+ else
+ md_super_wait(bitmap->mddev);
+
if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
bitmap_file_kick(bitmap);
}
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 0387e05..e855a19 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -462,6 +462,7 @@
c->n_buffers[dirty]++;
b->list_mode = dirty;
list_move(&b->lru_list, &c->lru[dirty]);
+ b->last_accessed = jiffies;
}
/*----------------------------------------------------------------
@@ -528,6 +529,19 @@
end_io(&b->bio, r);
}
+static void inline_endio(struct bio *bio, int error)
+{
+ bio_end_io_t *end_fn = bio->bi_private;
+
+ /*
+ * Reset the bio to free any attached resources
+ * (e.g. bio integrity profiles).
+ */
+ bio_reset(bio);
+
+ end_fn(bio, error);
+}
+
static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
bio_end_io_t *end_io)
{
@@ -539,7 +553,12 @@
b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
b->bio.bi_sector = block << b->c->sectors_per_block_bits;
b->bio.bi_bdev = b->c->bdev;
- b->bio.bi_end_io = end_io;
+ b->bio.bi_end_io = inline_endio;
+ /*
+ * Use of .bi_private isn't a problem here because
+ * the dm_buffer's inline bio is local to bufio.
+ */
+ b->bio.bi_private = end_io;
/*
* We assume that if len >= PAGE_SIZE ptr is page-aligned.
@@ -1660,6 +1679,11 @@
{
__u64 mem;
+ dm_bufio_allocated_kmem_cache = 0;
+ dm_bufio_allocated_get_free_pages = 0;
+ dm_bufio_allocated_vmalloc = 0;
+ dm_bufio_current_allocated = 0;
+
memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches);
memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names);
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
new file mode 100644
index 0000000..6c9049c
--- /dev/null
+++ b/drivers/md/dm-builtin.c
@@ -0,0 +1,48 @@
+#include "dm.h"
+
+/*
+ * The kobject release method must not be placed in the module itself,
+ * otherwise we are subject to module unload races.
+ *
+ * The release method is called when the last reference to the kobject is
+ * dropped. It may be called by any other kernel code that drops the last
+ * reference.
+ *
+ * The release method suffers from module unload race. We may prevent the
+ * module from being unloaded at the start of the release method (using
+ * increased module reference count or synchronizing against the release
+ * method), however there is no way to prevent the module from being
+ * unloaded at the end of the release method.
+ *
+ * If this code were placed in the dm module, the following race may
+ * happen:
+ * 1. Some other process takes a reference to dm kobject
+ * 2. The user issues ioctl function to unload the dm device
+ * 3. dm_sysfs_exit calls kobject_put, however the object is not released
+ * because of the other reference taken at step 1
+ * 4. dm_sysfs_exit waits on the completion
+ * 5. The other process that took the reference in step 1 drops it,
+ * dm_kobject_release is called from this process
+ * 6. dm_kobject_release calls complete()
+ * 7. a reschedule happens before dm_kobject_release returns
+ * 8. dm_sysfs_exit continues, the dm device is unloaded, module reference
+ * count is decremented
+ * 9. The user unloads the dm module
+ * 10. The other process that was rescheduled in step 7 continues to run,
+ * it is now executing code in unloaded module, so it crashes
+ *
+ * Note that if the process that takes the foreign reference to dm kobject
+ * has a low priority and the system is sufficiently loaded with
+ * higher-priority processes that prevent the low-priority process from
+ * being scheduled long enough, this bug may really happen.
+ *
+ * In order to fix this module unload race, we place the release method
+ * into a helper code that is compiled directly into the kernel.
+ */
+
+void dm_kobject_release(struct kobject *kobj)
+{
+ complete(dm_get_completion_from_kobject(kobj));
+}
+
+EXPORT_SYMBOL(dm_kobject_release);
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 1af7255..4a10c15 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -88,6 +88,9 @@
} __packed;
struct dm_cache_metadata {
+ atomic_t ref_count;
+ struct list_head list;
+
struct block_device *bdev;
struct dm_block_manager *bm;
struct dm_space_map *metadata_sm;
@@ -384,6 +387,15 @@
disk_super = dm_block_data(sblock);
+ /* Verify the data block size hasn't changed */
+ if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) {
+ DMERR("changing the data block size (from %u to %llu) is not supported",
+ le32_to_cpu(disk_super->data_block_size),
+ (unsigned long long)cmd->data_block_size);
+ r = -EINVAL;
+ goto bad;
+ }
+
r = __check_incompat_features(disk_super, cmd);
if (r < 0)
goto bad;
@@ -511,8 +523,9 @@
disk_super = dm_block_data(sblock);
update_flags(disk_super, mutator);
read_superblock_fields(cmd, disk_super);
+ dm_bm_unlock(sblock);
- return dm_bm_flush_and_unlock(cmd->bm, sblock);
+ return dm_bm_flush(cmd->bm);
}
static int __begin_transaction(struct dm_cache_metadata *cmd)
@@ -624,10 +637,10 @@
/*----------------------------------------------------------------*/
-struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
- sector_t data_block_size,
- bool may_format_device,
- size_t policy_hint_size)
+static struct dm_cache_metadata *metadata_open(struct block_device *bdev,
+ sector_t data_block_size,
+ bool may_format_device,
+ size_t policy_hint_size)
{
int r;
struct dm_cache_metadata *cmd;
@@ -635,9 +648,10 @@
cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
if (!cmd) {
DMERR("could not allocate metadata struct");
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
+ atomic_set(&cmd->ref_count, 1);
init_rwsem(&cmd->root_lock);
cmd->bdev = bdev;
cmd->data_block_size = data_block_size;
@@ -660,10 +674,96 @@
return cmd;
}
+/*
+ * We keep a little list of ref counted metadata objects to prevent two
+ * different target instances creating separate bufio instances. This is
+ * an issue if a table is reloaded before the suspend.
+ */
+static DEFINE_MUTEX(table_lock);
+static LIST_HEAD(table);
+
+static struct dm_cache_metadata *lookup(struct block_device *bdev)
+{
+ struct dm_cache_metadata *cmd;
+
+ list_for_each_entry(cmd, &table, list)
+ if (cmd->bdev == bdev) {
+ atomic_inc(&cmd->ref_count);
+ return cmd;
+ }
+
+ return NULL;
+}
+
+static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev,
+ sector_t data_block_size,
+ bool may_format_device,
+ size_t policy_hint_size)
+{
+ struct dm_cache_metadata *cmd, *cmd2;
+
+ mutex_lock(&table_lock);
+ cmd = lookup(bdev);
+ mutex_unlock(&table_lock);
+
+ if (cmd)
+ return cmd;
+
+ cmd = metadata_open(bdev, data_block_size, may_format_device, policy_hint_size);
+ if (!IS_ERR(cmd)) {
+ mutex_lock(&table_lock);
+ cmd2 = lookup(bdev);
+ if (cmd2) {
+ mutex_unlock(&table_lock);
+ __destroy_persistent_data_objects(cmd);
+ kfree(cmd);
+ return cmd2;
+ }
+ list_add(&cmd->list, &table);
+ mutex_unlock(&table_lock);
+ }
+
+ return cmd;
+}
+
+static bool same_params(struct dm_cache_metadata *cmd, sector_t data_block_size)
+{
+ if (cmd->data_block_size != data_block_size) {
+ DMERR("data_block_size (%llu) different from that in metadata (%llu)\n",
+ (unsigned long long) data_block_size,
+ (unsigned long long) cmd->data_block_size);
+ return false;
+ }
+
+ return true;
+}
+
+struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
+ sector_t data_block_size,
+ bool may_format_device,
+ size_t policy_hint_size)
+{
+ struct dm_cache_metadata *cmd = lookup_or_open(bdev, data_block_size,
+ may_format_device, policy_hint_size);
+
+ if (!IS_ERR(cmd) && !same_params(cmd, data_block_size)) {
+ dm_cache_metadata_close(cmd);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return cmd;
+}
+
void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
{
- __destroy_persistent_data_objects(cmd);
- kfree(cmd);
+ if (atomic_dec_and_test(&cmd->ref_count)) {
+ mutex_lock(&table_lock);
+ list_del(&cmd->list);
+ mutex_unlock(&table_lock);
+
+ __destroy_persistent_data_objects(cmd);
+ kfree(cmd);
+ }
}
int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size)
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index df44b60..6779736 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -151,6 +151,9 @@
atomic_t nr_migrations;
wait_queue_head_t migration_wait;
+ wait_queue_head_t quiescing_wait;
+ atomic_t quiescing_ack;
+
/*
* cache_size entries, dirty if set
*/
@@ -742,8 +745,9 @@
static void cleanup_migration(struct dm_cache_migration *mg)
{
- dec_nr_migrations(mg->cache);
+ struct cache *cache = mg->cache;
free_migration(mg);
+ dec_nr_migrations(cache);
}
static void migration_failure(struct dm_cache_migration *mg)
@@ -857,12 +861,13 @@
int r;
struct dm_io_region o_region, c_region;
struct cache *cache = mg->cache;
+ sector_t cblock = from_cblock(mg->cblock);
o_region.bdev = cache->origin_dev->bdev;
o_region.count = cache->sectors_per_block;
c_region.bdev = cache->cache_dev->bdev;
- c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block;
+ c_region.sector = cblock * cache->sectors_per_block;
c_region.count = cache->sectors_per_block;
if (mg->writeback || mg->demote) {
@@ -1340,24 +1345,6 @@
/*----------------------------------------------------------------
* Main worker loop
*--------------------------------------------------------------*/
-static void start_quiescing(struct cache *cache)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&cache->lock, flags);
- cache->quiescing = 1;
- spin_unlock_irqrestore(&cache->lock, flags);
-}
-
-static void stop_quiescing(struct cache *cache)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&cache->lock, flags);
- cache->quiescing = 0;
- spin_unlock_irqrestore(&cache->lock, flags);
-}
-
static bool is_quiescing(struct cache *cache)
{
int r;
@@ -1370,6 +1357,41 @@
return r;
}
+static void ack_quiescing(struct cache *cache)
+{
+ if (is_quiescing(cache)) {
+ atomic_inc(&cache->quiescing_ack);
+ wake_up(&cache->quiescing_wait);
+ }
+}
+
+static void wait_for_quiescing_ack(struct cache *cache)
+{
+ wait_event(cache->quiescing_wait, atomic_read(&cache->quiescing_ack));
+}
+
+static void start_quiescing(struct cache *cache)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&cache->lock, flags);
+ cache->quiescing = true;
+ spin_unlock_irqrestore(&cache->lock, flags);
+
+ wait_for_quiescing_ack(cache);
+}
+
+static void stop_quiescing(struct cache *cache)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&cache->lock, flags);
+ cache->quiescing = false;
+ spin_unlock_irqrestore(&cache->lock, flags);
+
+ atomic_set(&cache->quiescing_ack, 0);
+}
+
static void wait_for_migrations(struct cache *cache)
{
wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations));
@@ -1414,16 +1436,15 @@
struct cache *cache = container_of(ws, struct cache, worker);
do {
- if (!is_quiescing(cache))
+ if (!is_quiescing(cache)) {
+ writeback_some_dirty_blocks(cache);
+ process_deferred_writethrough_bios(cache);
process_deferred_bios(cache);
+ }
process_migrations(cache, &cache->quiesced_migrations, issue_copy);
process_migrations(cache, &cache->completed_migrations, complete_migration);
- writeback_some_dirty_blocks(cache);
-
- process_deferred_writethrough_bios(cache);
-
if (commit_if_needed(cache)) {
process_deferred_flush_bios(cache, false);
@@ -1436,6 +1457,9 @@
process_migrations(cache, &cache->need_commit_migrations,
migration_success_post_commit);
}
+
+ ack_quiescing(cache);
+
} while (more_work(cache));
}
@@ -1930,6 +1954,8 @@
ti->num_discard_bios = 1;
ti->discards_supported = true;
ti->discard_zeroes_data_unsupported = true;
+ /* Discard bios must be split on a block boundary */
+ ti->split_discard_bios = true;
cache->features = ca->features;
ti->per_bio_data_size = get_per_bio_data_size(cache);
@@ -1998,6 +2024,9 @@
atomic_set(&cache->nr_migrations, 0);
init_waitqueue_head(&cache->migration_wait);
+ init_waitqueue_head(&cache->quiescing_wait);
+ atomic_set(&cache->quiescing_ack, 0);
+
r = -ENOMEM;
cache->nr_dirty = 0;
cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
@@ -2148,20 +2177,18 @@
bool discarded_block;
struct dm_bio_prison_cell *cell;
struct policy_result lookup_result;
- struct per_bio_data *pb;
+ struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
- if (from_oblock(block) > from_oblock(cache->origin_blocks)) {
+ if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
/*
* This can only occur if the io goes to a partial block at
* the end of the origin device. We don't cache these.
* Just remap to the origin and carry on.
*/
- remap_to_origin_clear_discard(cache, bio, block);
+ remap_to_origin(cache, bio);
return DM_MAPIO_REMAPPED;
}
- pb = init_per_bio_data(bio, pb_data_size);
-
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) {
defer_bio(cache, bio);
return DM_MAPIO_SUBMITTED;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6d2d41a..7409d79 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -18,7 +18,6 @@
#include <linux/crypto.h>
#include <linux/workqueue.h>
#include <linux/backing-dev.h>
-#include <linux/percpu.h>
#include <linux/atomic.h>
#include <linux/scatterlist.h>
#include <asm/page.h>
@@ -44,6 +43,7 @@
unsigned int idx_out;
sector_t cc_sector;
atomic_t cc_pending;
+ struct ablkcipher_request *req;
};
/*
@@ -105,15 +105,7 @@
enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
/*
- * Duplicated per-CPU state for cipher.
- */
-struct crypt_cpu {
- struct ablkcipher_request *req;
-};
-
-/*
- * The fields in here must be read only after initialization,
- * changing state should be in crypt_cpu.
+ * The fields in here must be read only after initialization.
*/
struct crypt_config {
struct dm_dev *dev;
@@ -143,12 +135,6 @@
sector_t iv_offset;
unsigned int iv_size;
- /*
- * Duplicated per cpu state. Access through
- * per_cpu_ptr() only.
- */
- struct crypt_cpu __percpu *cpu;
-
/* ESSIV: struct crypto_cipher *essiv_tfm */
void *iv_private;
struct crypto_ablkcipher **tfms;
@@ -184,11 +170,6 @@
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
-static struct crypt_cpu *this_crypt_config(struct crypt_config *cc)
-{
- return this_cpu_ptr(cc->cpu);
-}
-
/*
* Use this to access cipher attributes that are the same for each CPU.
*/
@@ -738,16 +719,15 @@
static void crypt_alloc_req(struct crypt_config *cc,
struct convert_context *ctx)
{
- struct crypt_cpu *this_cc = this_crypt_config(cc);
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
- if (!this_cc->req)
- this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO);
+ if (!ctx->req)
+ ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
- ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]);
- ablkcipher_request_set_callback(this_cc->req,
+ ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+ ablkcipher_request_set_callback(ctx->req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
- kcryptd_async_done, dmreq_of_req(cc, this_cc->req));
+ kcryptd_async_done, dmreq_of_req(cc, ctx->req));
}
/*
@@ -756,7 +736,6 @@
static int crypt_convert(struct crypt_config *cc,
struct convert_context *ctx)
{
- struct crypt_cpu *this_cc = this_crypt_config(cc);
int r;
atomic_set(&ctx->cc_pending, 1);
@@ -768,7 +747,7 @@
atomic_inc(&ctx->cc_pending);
- r = crypt_convert_block(cc, ctx, this_cc->req);
+ r = crypt_convert_block(cc, ctx, ctx->req);
switch (r) {
/* async */
@@ -777,7 +756,7 @@
INIT_COMPLETION(ctx->restart);
/* fall through*/
case -EINPROGRESS:
- this_cc->req = NULL;
+ ctx->req = NULL;
ctx->cc_sector++;
continue;
@@ -876,6 +855,7 @@
io->sector = sector;
io->error = 0;
io->base_io = NULL;
+ io->ctx.req = NULL;
atomic_set(&io->io_pending, 0);
return io;
@@ -901,6 +881,8 @@
if (!atomic_dec_and_test(&io->io_pending))
return;
+ if (io->ctx.req)
+ mempool_free(io->ctx.req, cc->req_pool);
mempool_free(io, cc->io_pool);
if (likely(!base_io))
@@ -1326,8 +1308,6 @@
static void crypt_dtr(struct dm_target *ti)
{
struct crypt_config *cc = ti->private;
- struct crypt_cpu *cpu_cc;
- int cpu;
ti->private = NULL;
@@ -1339,13 +1319,6 @@
if (cc->crypt_queue)
destroy_workqueue(cc->crypt_queue);
- if (cc->cpu)
- for_each_possible_cpu(cpu) {
- cpu_cc = per_cpu_ptr(cc->cpu, cpu);
- if (cpu_cc->req)
- mempool_free(cpu_cc->req, cc->req_pool);
- }
-
crypt_free_tfms(cc);
if (cc->bs)
@@ -1364,9 +1337,6 @@
if (cc->dev)
dm_put_device(ti, cc->dev);
- if (cc->cpu)
- free_percpu(cc->cpu);
-
kzfree(cc->cipher);
kzfree(cc->cipher_string);
@@ -1421,13 +1391,6 @@
if (tmp)
DMWARN("Ignoring unexpected additional cipher options");
- cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)),
- __alignof__(struct crypt_cpu));
- if (!cc->cpu) {
- ti->error = "Cannot allocate per cpu state";
- goto bad_mem;
- }
-
/*
* For compatibility with the original dm-crypt mapping format, if
* only the cipher name is supplied, use cbc-plain.
@@ -1543,6 +1506,7 @@
unsigned int key_size, opt_params;
unsigned long long tmpll;
int ret;
+ size_t iv_size_padding;
struct dm_arg_set as;
const char *opt_string;
char dummy;
@@ -1579,12 +1543,23 @@
cc->dmreq_start = sizeof(struct ablkcipher_request);
cc->dmreq_start += crypto_ablkcipher_reqsize(any_tfm(cc));
- cc->dmreq_start = ALIGN(cc->dmreq_start, crypto_tfm_ctx_alignment());
- cc->dmreq_start += crypto_ablkcipher_alignmask(any_tfm(cc)) &
- ~(crypto_tfm_ctx_alignment() - 1);
+ cc->dmreq_start = ALIGN(cc->dmreq_start, __alignof__(struct dm_crypt_request));
+
+ if (crypto_ablkcipher_alignmask(any_tfm(cc)) < CRYPTO_MINALIGN) {
+ /* Allocate the padding exactly */
+ iv_size_padding = -(cc->dmreq_start + sizeof(struct dm_crypt_request))
+ & crypto_ablkcipher_alignmask(any_tfm(cc));
+ } else {
+ /*
+ * If the cipher requires greater alignment than kmalloc
+ * alignment, we don't know the exact position of the
+ * initialization vector. We must assume worst case.
+ */
+ iv_size_padding = crypto_ablkcipher_alignmask(any_tfm(cc));
+ }
cc->req_pool = mempool_create_kmalloc_pool(MIN_IOS, cc->dmreq_start +
- sizeof(struct dm_crypt_request) + cc->iv_size);
+ sizeof(struct dm_crypt_request) + iv_size_padding + cc->iv_size);
if (!cc->req_pool) {
ti->error = "Cannot allocate crypt request mempool";
goto bad;
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 496d5f3..2f91d6d 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -20,6 +20,7 @@
struct delay_c {
struct timer_list delay_timer;
struct mutex timer_lock;
+ struct workqueue_struct *kdelayd_wq;
struct work_struct flush_expired_bios;
struct list_head delayed_bios;
atomic_t may_delay;
@@ -45,14 +46,13 @@
static DEFINE_MUTEX(delayed_bios_lock);
-static struct workqueue_struct *kdelayd_wq;
static struct kmem_cache *delayed_cache;
static void handle_delayed_timer(unsigned long data)
{
struct delay_c *dc = (struct delay_c *)data;
- queue_work(kdelayd_wq, &dc->flush_expired_bios);
+ queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
}
static void queue_timeout(struct delay_c *dc, unsigned long expires)
@@ -191,6 +191,12 @@
goto bad_dev_write;
}
+ dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+ if (!dc->kdelayd_wq) {
+ DMERR("Couldn't start kdelayd");
+ goto bad_queue;
+ }
+
setup_timer(&dc->delay_timer, handle_delayed_timer, (unsigned long)dc);
INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
@@ -203,6 +209,8 @@
ti->private = dc;
return 0;
+bad_queue:
+ mempool_destroy(dc->delayed_pool);
bad_dev_write:
if (dc->dev_write)
dm_put_device(ti, dc->dev_write);
@@ -217,7 +225,7 @@
{
struct delay_c *dc = ti->private;
- flush_workqueue(kdelayd_wq);
+ destroy_workqueue(dc->kdelayd_wq);
dm_put_device(ti, dc->dev_read);
@@ -350,12 +358,6 @@
{
int r = -ENOMEM;
- kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
- if (!kdelayd_wq) {
- DMERR("Couldn't start kdelayd");
- goto bad_queue;
- }
-
delayed_cache = KMEM_CACHE(dm_delay_info, 0);
if (!delayed_cache) {
DMERR("Couldn't create delayed bio cache.");
@@ -373,8 +375,6 @@
bad_register:
kmem_cache_destroy(delayed_cache);
bad_memcache:
- destroy_workqueue(kdelayd_wq);
-bad_queue:
return r;
}
@@ -382,7 +382,6 @@
{
dm_unregister_target(&delay_target);
kmem_cache_destroy(delayed_cache);
- destroy_workqueue(kdelayd_wq);
}
/* Module hooks */
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index ea49834..17cb217 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -10,6 +10,7 @@
#include <linux/device-mapper.h>
#include <linux/bio.h>
+#include <linux/completion.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/sched.h>
@@ -34,7 +35,7 @@
struct io {
unsigned long error_bits;
atomic_t count;
- struct task_struct *sleeper;
+ struct completion *wait;
struct dm_io_client *client;
io_notify_fn callback;
void *context;
@@ -122,8 +123,8 @@
invalidate_kernel_vmap_range(io->vma_invalidate_address,
io->vma_invalidate_size);
- if (io->sleeper)
- wake_up_process(io->sleeper);
+ if (io->wait)
+ complete(io->wait);
else {
unsigned long r = io->error_bits;
@@ -290,6 +291,12 @@
unsigned short logical_block_size = queue_logical_block_size(q);
sector_t num_sectors;
+ /* Reject unsupported discard requests */
+ if ((rw & REQ_DISCARD) && !blk_queue_discard(q)) {
+ dec_count(io, region, -EOPNOTSUPP);
+ return;
+ }
+
/*
* where->count may be zero if rw holds a flush and we need to
* send a zero-sized flush.
@@ -386,6 +393,7 @@
*/
volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1];
struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io));
+ DECLARE_COMPLETION_ONSTACK(wait);
if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
WARN_ON(1);
@@ -394,7 +402,7 @@
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
- io->sleeper = current;
+ io->wait = &wait;
io->client = client;
io->vma_invalidate_address = dp->vma_invalidate_address;
@@ -402,15 +410,7 @@
dispatch_io(rw, num_regions, where, dp, io, 1);
- while (1) {
- set_current_state(TASK_UNINTERRUPTIBLE);
-
- if (!atomic_read(&io->count))
- break;
-
- io_schedule();
- }
- set_current_state(TASK_RUNNING);
+ wait_for_completion_io(&wait);
if (error_bits)
*error_bits = io->error_bits;
@@ -433,7 +433,7 @@
io = mempool_alloc(client->pool, GFP_NOIO);
io->error_bits = 0;
atomic_set(&io->count, 1); /* see dispatch_io() */
- io->sleeper = NULL;
+ io->wait = NULL;
io->client = client;
io->callback = fn;
io->context = context;
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index aa04f02..81a79b7 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1644,7 +1644,10 @@
}
if (!dmi) {
+ unsigned noio_flag;
+ noio_flag = memalloc_noio_save();
dmi = __vmalloc(param_kernel->data_size, GFP_NOIO | __GFP_REPEAT | __GFP_HIGH, PAGE_KERNEL);
+ memalloc_noio_restore(noio_flag);
if (dmi)
*param_flags |= DM_PARAMS_VMALLOC;
}
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 08d9a20..c69d0b7 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -272,7 +272,7 @@
r = cn_add_callback(&ulog_cn_id, "dmlogusr", cn_ulog_callback);
if (r) {
- cn_del_callback(&ulog_cn_id);
+ kfree(prealloced_cn_msg);
return r;
}
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index bdf26f5..0ba21b0 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -86,6 +86,7 @@
unsigned queue_if_no_path:1; /* Queue I/O if last path fails? */
unsigned saved_queue_if_no_path:1; /* Saved state during suspension */
unsigned retain_attached_hw_handler:1; /* If there's already a hw_handler present, don't change it. */
+ unsigned pg_init_disabled:1; /* pg_init is not currently allowed */
unsigned pg_init_retries; /* Number of times to retry pg_init */
unsigned pg_init_count; /* Number of times pg_init called */
@@ -497,7 +498,8 @@
(!pgpath && !m->queue_if_no_path))
must_queue = 0;
- if (m->pg_init_required && !m->pg_init_in_progress && pgpath)
+ if (m->pg_init_required && !m->pg_init_in_progress && pgpath &&
+ !m->pg_init_disabled)
__pg_init_all_paths(m);
spin_unlock_irqrestore(&m->lock, flags);
@@ -942,10 +944,20 @@
static void flush_multipath_work(struct multipath *m)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&m->lock, flags);
+ m->pg_init_disabled = 1;
+ spin_unlock_irqrestore(&m->lock, flags);
+
flush_workqueue(kmpath_handlerd);
multipath_wait_for_pg_init_completion(m);
flush_workqueue(kmultipathd);
flush_work(&m->trigger_event);
+
+ spin_lock_irqsave(&m->lock, flags);
+ m->pg_init_disabled = 0;
+ spin_unlock_irqrestore(&m->lock, flags);
}
static void multipath_dtr(struct dm_target *ti)
@@ -1164,7 +1176,7 @@
spin_lock_irqsave(&m->lock, flags);
- if (m->pg_init_count <= m->pg_init_retries)
+ if (m->pg_init_count <= m->pg_init_retries && !m->pg_init_disabled)
m->pg_init_required = 1;
else
limit_reached = 1;
@@ -1284,8 +1296,17 @@
if (!error && !clone->errors)
return 0; /* I/O complete */
- if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ)
+ if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ) {
+ if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+ !clone->q->limits.max_write_same_sectors) {
+ struct queue_limits *limits;
+
+ /* device doesn't really support WRITE SAME, disable it */
+ limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+ limits->max_write_same_sectors = 0;
+ }
return error;
+ }
if (mpio->pgpath)
fail_path(mpio->pgpath);
@@ -1561,7 +1582,6 @@
unsigned long flags;
int r;
-again:
bdev = NULL;
mode = 0;
r = 0;
@@ -1579,7 +1599,7 @@
}
if ((pgpath && m->queue_io) || (!pgpath && m->queue_if_no_path))
- r = -EAGAIN;
+ r = -ENOTCONN;
else if (!bdev)
r = -EIO;
@@ -1588,15 +1608,15 @@
/*
* Only pass ioctls through if the device sizes match exactly.
*/
- if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT)
- r = scsi_verify_blk_ioctl(NULL, cmd);
-
- if (r == -EAGAIN && !fatal_signal_pending(current)) {
- queue_work(kmultipathd, &m->process_queued_ios);
- msleep(10);
- goto again;
+ if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) {
+ int err = scsi_verify_blk_ioctl(NULL, cmd);
+ if (err)
+ r = err;
}
+ if (r == -ENOTCONN && !fatal_signal_pending(current))
+ queue_work(kmultipathd, &m->process_queued_ios);
+
return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
}
@@ -1694,7 +1714,7 @@
*---------------------------------------------------------------*/
static struct target_type multipath_target = {
.name = "multipath",
- .version = {1, 5, 1},
+ .version = {1, 6, 0},
.module = THIS_MODULE,
.ctr = multipath_ctr,
.dtr = multipath_dtr,
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1d3fe1a..84cddcc 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -380,7 +380,7 @@
static int validate_raid_redundancy(struct raid_set *rs)
{
unsigned i, rebuild_cnt = 0;
- unsigned rebuilds_per_group, copies, d;
+ unsigned rebuilds_per_group = 0, copies, d;
unsigned group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
@@ -785,8 +785,7 @@
__le32 layout;
__le32 stripe_sectors;
- __u8 pad[452]; /* Round struct to 512 bytes. */
- /* Always set to 0 when writing. */
+ /* Remainder of a logical block is zero-filled when writing (see super_sync()). */
} __packed;
static int read_disk_sb(struct md_rdev *rdev, int size)
@@ -823,7 +822,7 @@
test_bit(Faulty, &(rs->dev[i].rdev.flags)))
failed_devices |= (1ULL << i);
- memset(sb, 0, sizeof(*sb));
+ memset(sb + 1, 0, rdev->sb_size - sizeof(*sb));
sb->magic = cpu_to_le32(DM_RAID_MAGIC);
sb->features = cpu_to_le32(0); /* No features yet */
@@ -858,7 +857,11 @@
uint64_t events_sb, events_refsb;
rdev->sb_start = 0;
- rdev->sb_size = sizeof(*sb);
+ rdev->sb_size = bdev_logical_block_size(rdev->meta_bdev);
+ if (rdev->sb_size < sizeof(*sb) || rdev->sb_size > PAGE_SIZE) {
+ DMERR("superblock size of a logical block is no longer valid");
+ return -EINVAL;
+ }
ret = read_disk_sb(rdev, rdev->sb_size);
if (ret)
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 699b5be..678556b 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -604,6 +604,15 @@
return;
}
+ /*
+ * If the bio is discard, return an error, but do not
+ * degrade the array.
+ */
+ if (bio->bi_rw & REQ_DISCARD) {
+ bio_endio(bio, -EOPNOTSUPP);
+ return;
+ }
+
for (i = 0; i < ms->nr_mirrors; i++)
if (test_bit(i, &error))
fail_mirror(ms->mirror + i, DM_RAID1_WRITE_ERROR);
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3ac4156..2d2b1b7 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -256,7 +256,7 @@
*/
INIT_WORK_ONSTACK(&req.work, do_metadata);
queue_work(ps->metadata_wq, &req.work);
- flush_work(&req.work);
+ flush_workqueue(ps->metadata_wq);
return req.result;
}
@@ -269,6 +269,14 @@
return NUM_SNAPSHOT_HDR_CHUNKS + ((ps->exceptions_per_area + 1) * area);
}
+static void skip_metadata(struct pstore *ps)
+{
+ uint32_t stride = ps->exceptions_per_area + 1;
+ chunk_t next_free = ps->next_free;
+ if (sector_div(next_free, stride) == NUM_SNAPSHOT_HDR_CHUNKS)
+ ps->next_free++;
+}
+
/*
* Read or write a metadata area. Remembering to skip the first
* chunk which holds the header.
@@ -502,6 +510,8 @@
ps->current_area--;
+ skip_metadata(ps);
+
return 0;
}
@@ -616,8 +626,6 @@
struct dm_exception *e)
{
struct pstore *ps = get_info(store);
- uint32_t stride;
- chunk_t next_free;
sector_t size = get_dev_size(dm_snap_cow(store->snap)->bdev);
/* Is there enough room ? */
@@ -630,10 +638,8 @@
* Move onto the next free pending, making sure to take
* into account the location of the metadata chunks.
*/
- stride = (ps->exceptions_per_area + 1);
- next_free = ++ps->next_free;
- if (sector_div(next_free, stride) == 1)
- ps->next_free++;
+ ps->next_free++;
+ skip_metadata(ps);
atomic_inc(&ps->pending_count);
return 0;
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c434e5a..d892a05 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -66,6 +66,18 @@
atomic_t pending_exceptions_count;
+ /* Protected by "lock" */
+ sector_t exception_start_sequence;
+
+ /* Protected by kcopyd single-threaded callback */
+ sector_t exception_complete_sequence;
+
+ /*
+ * A list of pending exceptions that completed out of order.
+ * Protected by kcopyd single-threaded callback.
+ */
+ struct list_head out_of_order_list;
+
mempool_t *pending_pool;
struct dm_exception_table pending;
@@ -173,6 +185,14 @@
*/
int started;
+ /* There was copying error. */
+ int copy_error;
+
+ /* A sequence number, it is used for in-order completion. */
+ sector_t exception_sequence;
+
+ struct list_head out_of_order_entry;
+
/*
* For writing a complete chunk, bypassing the copy.
*/
@@ -725,17 +745,16 @@
*/
static int init_hash_tables(struct dm_snapshot *s)
{
- sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets;
+ sector_t hash_size, cow_dev_size, max_buckets;
/*
* Calculate based on the size of the original volume or
* the COW volume...
*/
cow_dev_size = get_dev_size(s->cow->bdev);
- origin_dev_size = get_dev_size(s->origin->bdev);
max_buckets = calc_max_buckets();
- hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
+ hash_size = cow_dev_size >> s->store->chunk_shift;
hash_size = min(hash_size, max_buckets);
if (hash_size < 64)
@@ -1095,6 +1114,9 @@
s->valid = 1;
s->active = 0;
atomic_set(&s->pending_exceptions_count, 0);
+ s->exception_start_sequence = 0;
+ s->exception_complete_sequence = 0;
+ INIT_LIST_HEAD(&s->out_of_order_list);
init_rwsem(&s->lock);
INIT_LIST_HEAD(&s->list);
spin_lock_init(&s->pe_lock);
@@ -1417,8 +1439,6 @@
full_bio->bi_end_io = pe->full_bio_end_io;
full_bio->bi_private = pe->full_bio_private;
}
- free_pending_exception(pe);
-
increment_pending_exceptions_done_count();
up_write(&s->lock);
@@ -1435,6 +1455,8 @@
}
retry_origin_bios(s, origin_bios);
+
+ free_pending_exception(pe);
}
static void commit_callback(void *context, int success)
@@ -1444,6 +1466,19 @@
pending_complete(pe, success);
}
+static void complete_exception(struct dm_snap_pending_exception *pe)
+{
+ struct dm_snapshot *s = pe->snap;
+
+ if (unlikely(pe->copy_error))
+ pending_complete(pe, 0);
+
+ else
+ /* Update the metadata if we are persistent */
+ s->store->type->commit_exception(s->store, &pe->e,
+ commit_callback, pe);
+}
+
/*
* Called when the copy I/O has finished. kcopyd actually runs
* this code so don't block.
@@ -1453,13 +1488,32 @@
struct dm_snap_pending_exception *pe = context;
struct dm_snapshot *s = pe->snap;
- if (read_err || write_err)
- pending_complete(pe, 0);
+ pe->copy_error = read_err || write_err;
- else
- /* Update the metadata if we are persistent */
- s->store->type->commit_exception(s->store, &pe->e,
- commit_callback, pe);
+ if (pe->exception_sequence == s->exception_complete_sequence) {
+ s->exception_complete_sequence++;
+ complete_exception(pe);
+
+ while (!list_empty(&s->out_of_order_list)) {
+ pe = list_entry(s->out_of_order_list.next,
+ struct dm_snap_pending_exception, out_of_order_entry);
+ if (pe->exception_sequence != s->exception_complete_sequence)
+ break;
+ s->exception_complete_sequence++;
+ list_del(&pe->out_of_order_entry);
+ complete_exception(pe);
+ }
+ } else {
+ struct list_head *lh;
+ struct dm_snap_pending_exception *pe2;
+
+ list_for_each_prev(lh, &s->out_of_order_list) {
+ pe2 = list_entry(lh, struct dm_snap_pending_exception, out_of_order_entry);
+ if (pe2->exception_sequence < pe->exception_sequence)
+ break;
+ }
+ list_add(&pe->out_of_order_entry, lh);
+ }
}
/*
@@ -1554,6 +1608,8 @@
return NULL;
}
+ pe->exception_sequence = s->exception_start_sequence++;
+
dm_insert_exception(&s->pending, &pe->e);
return pe;
@@ -2193,7 +2249,7 @@
static struct target_type snapshot_target = {
.name = "snapshot",
- .version = {1, 11, 1},
+ .version = {1, 12, 0},
.module = THIS_MODULE,
.ctr = snapshot_ctr,
.dtr = snapshot_dtr,
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 84d2b91..c62c5ab 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -86,6 +86,7 @@
static struct kobj_type dm_ktype = {
.sysfs_ops = &dm_sysfs_ops,
.default_attrs = dm_attrs,
+ .release = dm_kobject_release,
};
/*
@@ -104,5 +105,7 @@
*/
void dm_sysfs_exit(struct mapped_device *md)
{
- kobject_put(dm_kobject(md));
+ struct kobject *kobj = dm_kobject(md);
+ kobject_put(kobj);
+ wait_for_completion(dm_get_completion_from_kobject(kobj));
}
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 1ff252a..bd88d3da 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -215,6 +215,11 @@
num_targets = dm_round_up(num_targets, KEYS_PER_NODE);
+ if (!num_targets) {
+ kfree(t);
+ return -ENOMEM;
+ }
+
if (alloc_targets(t, num_targets)) {
kfree(t);
return -ENOMEM;
@@ -580,14 +585,28 @@
/*
* Used to dynamically allocate the arg array.
+ *
+ * We do first allocation with GFP_NOIO because dm-mpath and dm-thin must
+ * process messages even if some device is suspended. These messages have a
+ * small fixed number of arguments.
+ *
+ * On the other hand, dm-switch needs to process bulk data using messages and
+ * excessive use of GFP_NOIO could cause trouble.
*/
static char **realloc_argv(unsigned *array_size, char **old_argv)
{
char **argv;
unsigned new_size;
+ gfp_t gfp;
- new_size = *array_size ? *array_size * 2 : 64;
- argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL);
+ if (*array_size) {
+ new_size = *array_size * 2;
+ gfp = GFP_KERNEL;
+ } else {
+ new_size = 8;
+ gfp = GFP_NOIO;
+ }
+ argv = kmalloc(new_size * sizeof(*argv), gfp);
if (argv) {
memcpy(argv, old_argv, *array_size * sizeof(*argv));
*array_size = new_size;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 60bce43..3b1503d 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -591,6 +591,15 @@
disk_super = dm_block_data(sblock);
+ /* Verify the data block size hasn't changed */
+ if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) {
+ DMERR("changing the data block size (from %u to %llu) is not supported",
+ le32_to_cpu(disk_super->data_block_size),
+ (unsigned long long)pmd->data_block_size);
+ r = -EINVAL;
+ goto bad_unlock_sblock;
+ }
+
r = __check_incompat_features(disk_super, pmd);
if (r < 0)
goto bad_unlock_sblock;
@@ -1349,6 +1358,12 @@
return td->id;
}
+/*
+ * Check whether @time (of block creation) is older than @td's last snapshot.
+ * If so then the associated block is shared with the last snapshot device.
+ * Any block on a device created *after* the device last got snapshotted is
+ * necessarily not shared.
+ */
static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
{
return td->snapshotted_time > time;
@@ -1458,6 +1473,20 @@
return r;
}
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
+{
+ int r;
+ uint32_t ref_count;
+
+ down_read(&pmd->root_lock);
+ r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+ if (!r)
+ *result = (ref_count != 0);
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
{
int r;
@@ -1469,6 +1498,23 @@
return r;
}
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd)
+{
+ bool r = false;
+ struct dm_thin_device *td, *tmp;
+
+ down_read(&pmd->root_lock);
+ list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) {
+ if (td->changed) {
+ r = td->changed;
+ break;
+ }
+ }
+ up_read(&pmd->root_lock);
+
+ return r;
+}
+
bool dm_thin_aborted_changes(struct dm_thin_device *td)
{
bool r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 845ebbe..8f4d62b 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -161,6 +161,8 @@
*/
bool dm_thin_changed_this_transaction(struct dm_thin_device *td);
+bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd);
+
bool dm_thin_aborted_changes(struct dm_thin_device *td);
int dm_thin_get_highest_mapped_block(struct dm_thin_device *td,
@@ -181,6 +183,8 @@
int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+
/*
* Returns -ENOSPC if the new size is too small and already allocated
* blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 88f2f80..39996ca 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@
unsigned quiesced:1;
unsigned prepared:1;
unsigned pass_discard:1;
+ unsigned definitely_not_shared:1;
struct thin_c *tc;
dm_block_t virt_block;
@@ -640,7 +641,9 @@
*/
r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block);
if (r) {
- DMERR_LIMIT("dm_thin_insert_block() failed");
+ DMERR_LIMIT("%s: dm_thin_insert_block() failed: error = %d",
+ dm_device_name(pool->pool_md), r);
+ set_pool_mode(pool, PM_READ_ONLY);
cell_error(pool, m->cell);
goto out;
}
@@ -681,7 +684,15 @@
cell_defer_no_holder(tc, m->cell2);
if (m->pass_discard)
- remap_and_issue(tc, m->bio, m->data_block);
+ if (m->definitely_not_shared)
+ remap_and_issue(tc, m->bio, m->data_block);
+ else {
+ bool used = false;
+ if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
+ bio_endio(m->bio, 0);
+ else
+ remap_and_issue(tc, m->bio, m->data_block);
+ }
else
bio_endio(m->bio, 0);
@@ -749,13 +760,17 @@
static struct dm_thin_new_mapping *get_next_mapping(struct pool *pool)
{
- struct dm_thin_new_mapping *r = pool->next_mapping;
+ struct dm_thin_new_mapping *m = pool->next_mapping;
BUG_ON(!pool->next_mapping);
+ memset(m, 0, sizeof(struct dm_thin_new_mapping));
+ INIT_LIST_HEAD(&m->list);
+ m->bio = NULL;
+
pool->next_mapping = NULL;
- return r;
+ return m;
}
static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
@@ -767,15 +782,10 @@
struct pool *pool = tc->pool;
struct dm_thin_new_mapping *m = get_next_mapping(pool);
- INIT_LIST_HEAD(&m->list);
- m->quiesced = 0;
- m->prepared = 0;
m->tc = tc;
m->virt_block = virt_block;
m->data_block = data_dest;
m->cell = cell;
- m->err = 0;
- m->bio = NULL;
if (!dm_deferred_set_add_work(pool->shared_read_ds, &m->list))
m->quiesced = 1;
@@ -838,15 +848,12 @@
struct pool *pool = tc->pool;
struct dm_thin_new_mapping *m = get_next_mapping(pool);
- INIT_LIST_HEAD(&m->list);
m->quiesced = 1;
m->prepared = 0;
m->tc = tc;
m->virt_block = virt_block;
m->data_block = data_block;
m->cell = cell;
- m->err = 0;
- m->bio = NULL;
/*
* If the whole block of data is being overwritten or we are not
@@ -1030,12 +1037,12 @@
*/
m = get_next_mapping(pool);
m->tc = tc;
- m->pass_discard = (!lookup_result.shared) && pool->pf.discard_passdown;
+ m->pass_discard = pool->pf.discard_passdown;
+ m->definitely_not_shared = !lookup_result.shared;
m->virt_block = block;
m->data_block = lookup_result.block;
m->cell = cell;
m->cell2 = cell2;
- m->err = 0;
m->bio = bio;
if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list)) {
@@ -1315,9 +1322,9 @@
*/
if (ensure_next_mapping(pool)) {
spin_lock_irqsave(&pool->lock, flags);
+ bio_list_add(&pool->deferred_bios, bio);
bio_list_merge(&pool->deferred_bios, &bios);
spin_unlock_irqrestore(&pool->lock, flags);
-
break;
}
@@ -1337,7 +1344,8 @@
bio_list_init(&pool->deferred_flush_bios);
spin_unlock_irqrestore(&pool->lock, flags);
- if (bio_list_empty(&bios) && !need_commit_due_to_time(pool))
+ if (bio_list_empty(&bios) &&
+ !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool)))
return;
if (commit_or_fallback(pool)) {
@@ -2449,6 +2457,12 @@
struct pool_c *pt = ti->private;
struct pool *pool = pt->pool;
+ if (get_pool_mode(pool) >= PM_READ_ONLY) {
+ DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
+ dm_device_name(pool->pool_md));
+ return -EINVAL;
+ }
+
if (!strcasecmp(argv[0], "create_thin"))
r = process_create_thin_mesg(argc, argv, pool);
@@ -2639,7 +2653,8 @@
*/
if (pt->adjusted_pf.discard_passdown) {
data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
- limits->discard_granularity = data_limits->discard_granularity;
+ limits->discard_granularity = max(data_limits->discard_granularity,
+ pool->sectors_per_block << SECTOR_SHIFT);
} else
limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
}
@@ -2776,6 +2791,7 @@
if (get_pool_mode(tc->pool) == PM_FAIL) {
ti->error = "Couldn't open thin device, Pool is in fail mode";
+ r = -EINVAL;
goto bad_thin_open;
}
@@ -2787,7 +2803,7 @@
r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block);
if (r)
- goto bad_thin_open;
+ goto bad_target_max_io_len;
ti->num_flush_bios = 1;
ti->flush_supported = true;
@@ -2808,6 +2824,8 @@
return 0;
+bad_target_max_io_len:
+ dm_pool_close_thin_device(tc->td);
bad_thin_open:
__pool_dec(tc->pool);
bad_pool_lookup:
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index b948fd8..0d2e812 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -831,9 +831,8 @@
for (i = v->levels - 1; i >= 0; i--) {
sector_t s;
v->hash_level_block[i] = hash_position;
- s = verity_position_at_level(v, v->data_blocks, i);
- s = (s >> v->hash_per_block_bits) +
- !!(s & ((1 << v->hash_per_block_bits) - 1));
+ s = (v->data_blocks + ((sector_t)1 << ((i + 1) * v->hash_per_block_bits)) - 1)
+ >> ((i + 1) * v->hash_per_block_bits);
if (hash_position + s < hash_position) {
ti->error = "Hash device offset overflow";
r = -E2BIG;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index d5370a9..f69fed8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -184,8 +184,8 @@
/* forced geometry settings */
struct hd_geometry geometry;
- /* sysfs handle */
- struct kobject kobj;
+ /* kobject and completion */
+ struct dm_kobject_holder kobj_holder;
/* zero-length flush that will be cloned and submitted to targets */
struct bio flush_bio;
@@ -386,10 +386,12 @@
unsigned int cmd, unsigned long arg)
{
struct mapped_device *md = bdev->bd_disk->private_data;
- struct dm_table *map = dm_get_live_table(md);
+ struct dm_table *map;
struct dm_target *tgt;
int r = -ENOTTY;
+retry:
+ map = dm_get_live_table(md);
if (!map || !dm_table_get_size(map))
goto out;
@@ -410,6 +412,11 @@
out:
dm_table_put(map);
+ if (r == -ENOTCONN) {
+ msleep(10);
+ goto retry;
+ }
+
return r;
}
@@ -1897,6 +1904,7 @@
init_waitqueue_head(&md->wait);
INIT_WORK(&md->work, dm_wq_work);
init_waitqueue_head(&md->eventq);
+ init_completion(&md->kobj_holder.completion);
md->disk->major = _major;
md->disk->first_minor = minor;
@@ -2212,6 +2220,17 @@
}
/*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+ BUG_ON(!atomic_read(&md->holders));
+ return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
* Fully initialize a request-based queue (->elevator, ->request_fn, etc).
*/
static int dm_init_request_based_queue(struct mapped_device *md)
@@ -2251,7 +2270,7 @@
return 0;
}
-static struct mapped_device *dm_find_md(dev_t dev)
+struct mapped_device *dm_get_md(dev_t dev)
{
struct mapped_device *md;
unsigned minor = MINOR(dev);
@@ -2262,12 +2281,15 @@
spin_lock(&_minor_lock);
md = idr_find(&_minor_idr, minor);
- if (md && (md == MINOR_ALLOCED ||
- (MINOR(disk_devt(dm_disk(md))) != minor) ||
- dm_deleting_md(md) ||
- test_bit(DMF_FREEING, &md->flags))) {
- md = NULL;
- goto out;
+ if (md) {
+ if ((md == MINOR_ALLOCED ||
+ (MINOR(disk_devt(dm_disk(md))) != minor) ||
+ dm_deleting_md(md) ||
+ test_bit(DMF_FREEING, &md->flags))) {
+ md = NULL;
+ goto out;
+ }
+ dm_get(md);
}
out:
@@ -2275,16 +2297,6 @@
return md;
}
-
-struct mapped_device *dm_get_md(dev_t dev)
-{
- struct mapped_device *md = dm_find_md(dev);
-
- if (md)
- dm_get(md);
-
- return md;
-}
EXPORT_SYMBOL_GPL(dm_get_md);
void *dm_get_mdptr(struct mapped_device *md)
@@ -2321,10 +2333,16 @@
set_bit(DMF_FREEING, &md->flags);
spin_unlock(&_minor_lock);
+ /*
+ * Take suspend_lock so that presuspend and postsuspend methods
+ * do not race with internal suspend.
+ */
+ mutex_lock(&md->suspend_lock);
if (!dm_suspended_md(md)) {
dm_table_presuspend_targets(map);
dm_table_postsuspend_targets(map);
}
+ mutex_unlock(&md->suspend_lock);
/*
* Rare, but there may be I/O requests still going to complete,
@@ -2717,20 +2735,14 @@
struct kobject *dm_kobject(struct mapped_device *md)
{
- return &md->kobj;
+ return &md->kobj_holder.kobj;
}
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
{
struct mapped_device *md;
- md = container_of(kobj, struct mapped_device, kobj);
- if (&md->kobj != kobj)
- return NULL;
+ md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
if (test_bit(DMF_FREEING, &md->flags) ||
dm_deleting_md(md))
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 45b97da..9b3222f 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -15,6 +15,8 @@
#include <linux/list.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
/*
* Suspend feature flags
@@ -125,12 +127,27 @@
/*
* sysfs interface
*/
+struct dm_kobject_holder {
+ struct kobject kobj;
+ struct completion completion;
+};
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+ return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
int dm_sysfs_init(struct mapped_device *md);
void dm_sysfs_exit(struct mapped_device *md);
struct kobject *dm_kobject(struct mapped_device *md);
struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
/*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
+
+/*
* Targets for linear and striped mappings
*/
int dm_linear_init(void);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9b82377..aaf77b0 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1118,6 +1118,7 @@
rdev->raid_disk = -1;
clear_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
+ clear_bit(Bitmap_sync, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
if (mddev->raid_disks == 0) {
@@ -1196,6 +1197,8 @@
*/
if (ev1 < mddev->bitmap->events_cleared)
return 0;
+ if (ev1 < mddev->events)
+ set_bit(Bitmap_sync, &rdev->flags);
} else {
if (ev1 < mddev->events)
/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -1604,6 +1607,7 @@
rdev->raid_disk = -1;
clear_bit(Faulty, &rdev->flags);
clear_bit(In_sync, &rdev->flags);
+ clear_bit(Bitmap_sync, &rdev->flags);
clear_bit(WriteMostly, &rdev->flags);
if (mddev->raid_disks == 0) {
@@ -1686,6 +1690,8 @@
*/
if (ev1 < mddev->bitmap->events_cleared)
return 0;
+ if (ev1 < mddev->events)
+ set_bit(Bitmap_sync, &rdev->flags);
} else {
if (ev1 < mddev->events)
/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -2829,6 +2835,7 @@
else
rdev->saved_raid_disk = -1;
clear_bit(In_sync, &rdev->flags);
+ clear_bit(Bitmap_sync, &rdev->flags);
err = rdev->mddev->pers->
hot_add_disk(rdev->mddev, rdev);
if (err) {
@@ -3619,6 +3626,7 @@
mddev->in_sync = 1;
del_timer_sync(&mddev->safemode_timer);
}
+ blk_set_stacking_limits(&mddev->queue->limits);
pers->run(mddev);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev_resume(mddev);
@@ -5760,6 +5768,7 @@
info->raid_disk < mddev->raid_disks) {
rdev->raid_disk = info->raid_disk;
set_bit(In_sync, &rdev->flags);
+ clear_bit(Bitmap_sync, &rdev->flags);
} else
rdev->raid_disk = -1;
} else
@@ -7329,8 +7338,10 @@
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
return;
- if (mddev->ro) /* never try to sync a read-only array */
+ if (mddev->ro) {/* never try to sync a read-only array */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
return;
+ }
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
@@ -7436,6 +7447,19 @@
rdev->recovery_offset < j)
j = rdev->recovery_offset;
rcu_read_unlock();
+
+ /* If there is a bitmap, we need to make sure all
+ * writes that started before we added a spare
+ * complete before we start doing a recovery.
+ * Otherwise the write might complete and (via
+ * bitmap_endwrite) set a bit in the bitmap after the
+ * recovery has checked that bit and skipped that
+ * region.
+ */
+ if (mddev->bitmap) {
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ }
}
printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -7693,24 +7717,11 @@
if (test_bit(Faulty, &rdev->flags))
continue;
if (mddev->ro &&
- rdev->saved_raid_disk < 0)
+ ! (rdev->saved_raid_disk >= 0 &&
+ !test_bit(Bitmap_sync, &rdev->flags)))
continue;
rdev->recovery_offset = 0;
- if (rdev->saved_raid_disk >= 0 && mddev->in_sync) {
- spin_lock_irq(&mddev->write_lock);
- if (mddev->in_sync)
- /* OK, this device, which is in_sync,
- * will definitely be noticed before
- * the next write, so recovery isn't
- * needed.
- */
- rdev->recovery_offset = mddev->recovery_cp;
- spin_unlock_irq(&mddev->write_lock);
- }
- if (mddev->ro && rdev->recovery_offset != MaxSector)
- /* not safe to add this disk now */
- continue;
if (mddev->pers->
hot_add_disk(mddev, rdev) == 0) {
if (sysfs_link_rdev(mddev, rdev))
@@ -7788,9 +7799,13 @@
* As we only add devices that are already in-sync,
* we can activate the spares immediately.
*/
- clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
remove_and_add_spares(mddev, NULL);
- mddev->pers->spare_active(mddev);
+ /* There is no thread, but we need to call
+ * ->spare_active and clear saved_raid_disk
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ md_reap_sync_thread(mddev);
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
goto unlock;
}
@@ -8086,6 +8101,7 @@
u64 *p;
int lo, hi;
int rv = 1;
+ unsigned long flags;
if (bb->shift < 0)
/* badblocks are disabled */
@@ -8100,7 +8116,7 @@
sectors = next - s;
}
- write_seqlock_irq(&bb->lock);
+ write_seqlock_irqsave(&bb->lock, flags);
p = bb->page;
lo = 0;
@@ -8216,7 +8232,7 @@
bb->changed = 1;
if (!acknowledged)
bb->unacked_exist = 1;
- write_sequnlock_irq(&bb->lock);
+ write_sequnlock_irqrestore(&bb->lock, flags);
return rv;
}
@@ -8481,7 +8497,8 @@
if (mddev_trylock(mddev)) {
if (mddev->pers)
__md_stop_writes(mddev);
- mddev->safemode = 2;
+ if (mddev->persistent)
+ mddev->safemode = 2;
mddev_unlock(mddev);
}
need_delay = 1;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 653f992b6..ebe748e 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -129,6 +129,9 @@
enum flag_bits {
Faulty, /* device is known to have a fault */
In_sync, /* device is in_sync with rest of array */
+ Bitmap_sync, /* ..actually, not quite In_sync. Need a
+ * bitmap-based recovery to get fully in sync
+ */
Unmerged, /* device is being added to array and should
* be considerred for bvec_merge_fn but not
* yet for actual IO
diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c
index 172147e..1d75b1d 100644
--- a/drivers/md/persistent-data/dm-array.c
+++ b/drivers/md/persistent-data/dm-array.c
@@ -317,8 +317,16 @@
* The shadow op will often be a noop. Only insert if it really
* copied data.
*/
- if (dm_block_location(*block) != b)
+ if (dm_block_location(*block) != b) {
+ /*
+ * dm_tm_shadow_block will have already decremented the old
+ * block, but it is still referenced by the btree. We
+ * increment to stop the insert decrementing it below zero
+ * when overwriting the old value.
+ */
+ dm_tm_inc(info->btree_info.tm, b);
r = insert_ablock(info, index, *block, root);
+ }
return r;
}
@@ -509,15 +517,18 @@
static int grow_needs_more_blocks(struct resize *resize)
{
int r;
+ unsigned old_nr_blocks = resize->old_nr_full_blocks;
if (resize->old_nr_entries_in_last_block > 0) {
+ old_nr_blocks++;
+
r = grow_extend_tail_block(resize, resize->max_entries);
if (r)
return r;
}
r = insert_full_ablocks(resize->info, resize->size_of_block,
- resize->old_nr_full_blocks,
+ old_nr_blocks,
resize->new_nr_full_blocks,
resize->max_entries, resize->value,
&resize->root);
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 81b5138..6372d0b 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@
}
EXPORT_SYMBOL_GPL(dm_bm_unlock);
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
- struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
{
- int r;
-
if (bm->read_only)
return -EPERM;
- r = dm_bufio_write_dirty_buffers(bm->bufio);
- if (unlikely(r)) {
- dm_bm_unlock(superblock);
- return r;
- }
-
- dm_bm_unlock(superblock);
-
return dm_bufio_write_dirty_buffers(bm->bufio);
}
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
void dm_bm_set_read_only(struct dm_block_manager *bm)
{
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index be5bff6..f74c046 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@
*
* This method always blocks.
*/
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
- struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
/*
* Switches the bm to a read only mode. Once read-only mode
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index 37d367b..bf2b80d 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -42,6 +42,12 @@
} __packed;
+/*
+ * Locks a block using the btree node validator.
+ */
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+ struct dm_block **result);
+
void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
struct dm_btree_value_type *vt);
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index cf9fd67..1b5e13e 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -92,7 +92,7 @@
/*----------------------------------------------------------------*/
-static int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
+int bn_read_lock(struct dm_btree_info *info, dm_block_t b,
struct dm_block **result)
{
return dm_tm_read_lock(info->tm, b, &btree_node_validator, result);
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 3586542..0a7592e 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -812,22 +812,26 @@
* FIXME: We shouldn't use a recursive algorithm when we have limited stack
* space. Also this only works for single level trees.
*/
-static int walk_node(struct ro_spine *s, dm_block_t block,
+static int walk_node(struct dm_btree_info *info, dm_block_t block,
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
int r;
unsigned i, nr;
+ struct dm_block *node;
struct btree_node *n;
uint64_t keys;
- r = ro_step(s, block);
- n = ro_node(s);
+ r = bn_read_lock(info, block, &node);
+ if (r)
+ return r;
+
+ n = dm_block_data(node);
nr = le32_to_cpu(n->header.nr_entries);
for (i = 0; i < nr; i++) {
if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) {
- r = walk_node(s, value64(n, i), fn, context);
+ r = walk_node(info, value64(n, i), fn, context);
if (r)
goto out;
} else {
@@ -839,7 +843,7 @@
}
out:
- ro_pop(s);
+ dm_tm_unlock(info->tm, node);
return r;
}
@@ -847,15 +851,7 @@
int (*fn)(void *context, uint64_t *keys, void *leaf),
void *context)
{
- int r;
- struct ro_spine spine;
-
BUG_ON(info->levels > 1);
-
- init_ro_spine(&spine, info);
- r = walk_node(&spine, root, fn, context);
- exit_ro_spine(&spine);
-
- return r;
+ return walk_node(info, root, fn, context);
}
EXPORT_SYMBOL_GPL(dm_btree_walk);
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index 3e7a88d..0d24037 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -245,6 +245,10 @@
return -EINVAL;
}
+ /*
+ * We need to set this before the dm_tm_new_block() call below.
+ */
+ ll->nr_blocks = nr_blocks;
for (i = old_blocks; i < blocks; i++) {
struct dm_block *b;
struct disk_index_entry idx;
@@ -252,6 +256,7 @@
r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b);
if (r < 0)
return r;
+
idx.blocknr = cpu_to_le64(dm_block_location(b));
r = dm_tm_unlock(ll->tm, b);
@@ -266,7 +271,6 @@
return r;
}
- ll->nr_blocks = nr_blocks;
return 0;
}
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 1c95968..056d09c 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -384,12 +384,16 @@
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
int r = sm_metadata_new_block_(sm, b);
- if (r)
+ if (r) {
DMERR("unable to allocate new metadata block");
+ return r;
+ }
r = sm_metadata_get_nr_free(sm, &count);
- if (r)
+ if (r) {
DMERR("couldn't get free block count");
+ return r;
+ }
check_threshold(&smm->threshold, count);
@@ -489,7 +493,9 @@
{
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
- return smm->ll.nr_blocks;
+ *count = smm->ll.nr_blocks;
+
+ return 0;
}
static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
@@ -604,20 +610,38 @@
* Flick into a mode where all blocks get allocated in the new area.
*/
smm->begin = old_len;
- memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
+ memcpy(sm, &bootstrap_ops, sizeof(*sm));
/*
* Extend.
*/
r = sm_ll_extend(&smm->ll, extra_blocks);
+ if (r)
+ goto out;
/*
+ * We repeatedly increment then commit until the commit doesn't
+ * allocate any new blocks.
+ */
+ do {
+ for (i = old_len; !r && i < smm->begin; i++) {
+ r = sm_ll_inc(&smm->ll, i, &ev);
+ if (r)
+ goto out;
+ }
+ old_len = smm->begin;
+
+ r = sm_ll_commit(&smm->ll);
+ if (r)
+ goto out;
+
+ } while (old_len != smm->begin);
+
+out:
+ /*
* Switch back to normal behaviour.
*/
- memcpy(&smm->sm, &ops, sizeof(smm->sm));
- for (i = old_len; !r && i < smm->begin; i++)
- r = sm_ll_inc(&smm->ll, i, &ev);
-
+ memcpy(sm, &ops, sizeof(*sm));
return r;
}
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26..3bc30a0 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@
if (r < 0)
return r;
- return 0;
+ return dm_bm_flush(tm->bm);
}
EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
@@ -164,8 +164,9 @@
return -EWOULDBLOCK;
wipe_shadow_table(tm);
+ dm_bm_unlock(root);
- return dm_bm_flush_and_unlock(tm->bm, root);
+ return dm_bm_flush(tm->bm);
}
EXPORT_SYMBOL_GPL(dm_tm_commit);
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b1390..2772ed2 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@
/*
* We use a 2-phase commit here.
*
- * i) In the first phase the block manager is told to start flushing, and
- * the changes to the space map are written to disk. You should interrogate
- * your particular space map to get detail of its root node etc. to be
- * included in your superblock.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
*
- * ii) @root will be committed last. You shouldn't use more than the
- * first 512 bytes of @root if you wish the transaction to survive a power
- * failure. You *must* have a write lock held on @root for both stage (i)
- * and (ii). The commit will drop the write lock.
+ * ii) Lock your superblock. Update. Then call dm_tm_commit() which will
+ * unlock the superblock and flush it. No other blocks should be updated
+ * during this period. Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
*/
int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
/*
* These methods are the only way to get hold of a writeable block.
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6e17f81..86ac4a4 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -94,6 +94,7 @@
struct pool_info *pi = data;
struct r1bio *r1_bio;
struct bio *bio;
+ int need_pages;
int i, j;
r1_bio = r1bio_pool_alloc(gfp_flags, pi);
@@ -116,15 +117,15 @@
* RESYNC_PAGES for each bio.
*/
if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
- j = pi->raid_disks;
+ need_pages = pi->raid_disks;
else
- j = 1;
- while(j--) {
+ need_pages = 1;
+ for (j = 0; j < need_pages; j++) {
bio = r1_bio->bios[j];
bio->bi_vcnt = RESYNC_PAGES;
if (bio_alloc_pages(bio, gfp_flags))
- goto out_free_bio;
+ goto out_free_pages;
}
/* If not user-requests, copy the page pointers to all bios */
if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
@@ -138,6 +139,14 @@
return r1_bio;
+out_free_pages:
+ while (--j >= 0) {
+ struct bio_vec *bv;
+
+ bio_for_each_segment_all(bv, r1_bio->bios[j], i)
+ __free_page(bv->bv_page);
+ }
+
out_free_bio:
while (++j < pi->raid_disks)
bio_put(r1_bio->bios[j]);
@@ -548,7 +557,7 @@
if (test_bit(WriteMostly, &rdev->flags)) {
/* Don't balance among write-mostly, just
* use the first as a last resort */
- if (best_disk < 0) {
+ if (best_dist_disk < 0) {
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (first_bad < this_sector)
@@ -557,7 +566,8 @@
best_good_sectors = first_bad - this_sector;
} else
best_good_sectors = sectors;
- best_disk = disk;
+ best_dist_disk = disk;
+ best_pending_disk = disk;
}
continue;
}
@@ -1397,12 +1407,12 @@
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
} else
set_bit(Faulty, &rdev->flags);
+ /*
+ * if recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
"md/raid1:%s: Disk failure on %s, disabling device.\n"
@@ -1479,6 +1489,7 @@
}
}
if (rdev
+ && rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
@@ -1848,6 +1859,40 @@
int i;
int vcnt;
+ /* Fix variable parts of all bios */
+ vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
+ for (i = 0; i < conf->raid_disks * 2; i++) {
+ int j;
+ int size;
+ int uptodate;
+ struct bio *b = r1_bio->bios[i];
+ if (b->bi_end_io != end_sync_read)
+ continue;
+ /* fixup the bio for reuse, but preserve BIO_UPTODATE */
+ uptodate = test_bit(BIO_UPTODATE, &b->bi_flags);
+ bio_reset(b);
+ if (!uptodate)
+ clear_bit(BIO_UPTODATE, &b->bi_flags);
+ b->bi_vcnt = vcnt;
+ b->bi_size = r1_bio->sectors << 9;
+ b->bi_sector = r1_bio->sector +
+ conf->mirrors[i].rdev->data_offset;
+ b->bi_bdev = conf->mirrors[i].rdev->bdev;
+ b->bi_end_io = end_sync_read;
+ b->bi_private = r1_bio;
+
+ size = b->bi_size;
+ for (j = 0; j < vcnt ; j++) {
+ struct bio_vec *bi;
+ bi = &b->bi_io_vec[j];
+ bi->bv_offset = 0;
+ if (size > PAGE_SIZE)
+ bi->bv_len = PAGE_SIZE;
+ else
+ bi->bv_len = size;
+ size -= PAGE_SIZE;
+ }
+ }
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
@@ -1856,17 +1901,18 @@
break;
}
r1_bio->read_disk = primary;
- vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
- int size;
+ int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags);
if (sbio->bi_end_io != end_sync_read)
continue;
+ /* Now we can 'fixup' the BIO_UPTODATE flag */
+ set_bit(BIO_UPTODATE, &sbio->bi_flags);
- if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
+ if (uptodate) {
for (j = vcnt; j-- ; ) {
struct page *p, *s;
p = pbio->bi_io_vec[j].bv_page;
@@ -1881,33 +1927,12 @@
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
- && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
+ && uptodate)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
continue;
}
- /* fixup the bio for reuse */
- bio_reset(sbio);
- sbio->bi_vcnt = vcnt;
- sbio->bi_size = r1_bio->sectors << 9;
- sbio->bi_sector = r1_bio->sector +
- conf->mirrors[i].rdev->data_offset;
- sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
- sbio->bi_end_io = end_sync_read;
- sbio->bi_private = r1_bio;
-
- size = sbio->bi_size;
- for (j = 0; j < vcnt ; j++) {
- struct bio_vec *bi;
- bi = &sbio->bi_io_vec[j];
- bi->bv_offset = 0;
- if (size > PAGE_SIZE)
- bi->bv_len = PAGE_SIZE;
- else
- bi->bv_len = size;
- size -= PAGE_SIZE;
- }
bio_copy_data(sbio, pbio);
}
@@ -2027,7 +2052,7 @@
d--;
rdev = conf->mirrors[d].rdev;
if (rdev &&
- test_bit(In_sync, &rdev->flags))
+ !test_bit(Faulty, &rdev->flags))
r1_sync_page_io(rdev, sect, s,
conf->tmppage, WRITE);
}
@@ -2039,7 +2064,7 @@
d--;
rdev = conf->mirrors[d].rdev;
if (rdev &&
- test_bit(In_sync, &rdev->flags)) {
+ !test_bit(Faulty, &rdev->flags)) {
if (r1_sync_page_io(rdev, sect, s,
conf->tmppage, READ)) {
atomic_add(s, &rdev->corrected_errors);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6ddae25..a1ea2a7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1321,7 +1321,7 @@
/* Could not read all from this device, so we will
* need another r10_bio.
*/
- sectors_handled = (r10_bio->sectors + max_sectors
+ sectors_handled = (r10_bio->sector + max_sectors
- bio->bi_sector);
r10_bio->sectors = max_sectors;
spin_lock_irq(&conf->device_lock);
@@ -1329,7 +1329,7 @@
bio->bi_phys_segments = 2;
else
bio->bi_phys_segments++;
- spin_unlock(&conf->device_lock);
+ spin_unlock_irq(&conf->device_lock);
/* Cannot call generic_make_request directly
* as that will be queued in __generic_make_request
* and subsequent mempool_alloc might block
@@ -1681,11 +1681,11 @@
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
+ /*
+ * If recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -1762,6 +1762,7 @@
}
sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
} else if (tmp->rdev
+ && tmp->rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &tmp->rdev->flags)
&& !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
count++;
@@ -2075,11 +2076,17 @@
* both 'first' and 'i', so we just compare them.
* All vec entries are PAGE_SIZE;
*/
- for (j = 0; j < vcnt; j++)
+ int sectors = r10_bio->sectors;
+ for (j = 0; j < vcnt; j++) {
+ int len = PAGE_SIZE;
+ if (sectors < (len / 512))
+ len = sectors * 512;
if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
page_address(tbio->bi_io_vec[j].bv_page),
- fbio->bi_io_vec[j].bv_len))
+ len))
break;
+ sectors -= len/512;
+ }
if (j == vcnt)
continue;
atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
@@ -2262,12 +2269,18 @@
d = r10_bio->devs[1].devnum;
wbio = r10_bio->devs[1].bio;
wbio2 = r10_bio->devs[1].repl_bio;
+ /* Need to test wbio2->bi_end_io before we call
+ * generic_make_request as if the former is NULL,
+ * the latter is free to free wbio2.
+ */
+ if (wbio2 && !wbio2->bi_end_io)
+ wbio2 = NULL;
if (wbio->bi_end_io) {
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
generic_make_request(wbio);
}
- if (wbio2 && wbio2->bi_end_io) {
+ if (wbio2) {
atomic_inc(&conf->mirrors[d].replacement->nr_pending);
md_sync_acct(conf->mirrors[d].replacement->bdev,
bio_sectors(wbio2));
@@ -2909,14 +2922,13 @@
*/
if (mddev->bitmap == NULL &&
mddev->recovery_cp == MaxSector &&
+ mddev->reshape_position == MaxSector &&
+ !test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+ !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
conf->fullsync == 0) {
*skipped = 1;
- max_sector = mddev->dev_sectors;
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
- test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
- max_sector = mddev->resync_max_sectors;
- return max_sector - sector_nr;
+ return mddev->dev_sectors - sector_nr;
}
skipped:
@@ -2936,6 +2948,7 @@
*/
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
end_reshape(conf);
+ close_sync(conf);
return 0;
}
@@ -3186,10 +3199,6 @@
if (j == conf->copies) {
/* Cannot recover, so abort the recovery or
* record a bad block */
- put_buf(r10_bio);
- if (rb2)
- atomic_dec(&rb2->remaining);
- r10_bio = rb2;
if (any_working) {
/* problem is that there are bad blocks
* on other device(s)
@@ -3221,6 +3230,10 @@
mirror->recovery_disabled
= mddev->recovery_disabled;
}
+ put_buf(r10_bio);
+ if (rb2)
+ atomic_dec(&rb2->remaining);
+ r10_bio = rb2;
break;
}
}
@@ -3386,6 +3399,7 @@
if (bio->bi_end_io == end_sync_read) {
md_sync_acct(bio->bi_bdev, nr_sectors);
+ set_bit(BIO_UPTODATE, &bio->bi_flags);
generic_make_request(bio);
}
}
@@ -3532,7 +3546,7 @@
/* FIXME calc properly */
conf->mirrors = kzalloc(sizeof(struct raid10_info)*(mddev->raid_disks +
- max(0,mddev->delta_disks)),
+ max(0,-mddev->delta_disks)),
GFP_KERNEL);
if (!conf->mirrors)
goto out;
@@ -3691,7 +3705,7 @@
conf->geo.far_offset == 0)
goto out_free_conf;
if (conf->prev.far_copies != 1 &&
- conf->geo.far_offset == 0)
+ conf->prev.far_offset == 0)
goto out_free_conf;
}
@@ -4385,7 +4399,7 @@
read_bio->bi_private = r10_bio;
read_bio->bi_end_io = end_sync_read;
read_bio->bi_rw = READ;
- read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+ read_bio->bi_flags &= (~0UL << BIO_RESET_BITS);
read_bio->bi_flags |= 1 << BIO_UPTODATE;
read_bio->bi_vcnt = 0;
read_bio->bi_size = 0;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 05e4a10..1b6986c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -60,6 +60,10 @@
#include "raid0.h"
#include "bitmap.h"
+static bool devices_handle_discard_safely = false;
+module_param(devices_handle_discard_safely, bool, 0644);
+MODULE_PARM_DESC(devices_handle_discard_safely,
+ "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
/*
* Stripe cache
*/
@@ -668,6 +672,12 @@
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
+ /*
+ * If this is discard request, set bi_vcnt 0. We don't
+ * want to confuse SCSI because SCSI will replace payload
+ */
+ if (rw & REQ_DISCARD)
+ bi->bi_vcnt = 0;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
@@ -706,6 +716,12 @@
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
+ /*
+ * If this is discard request, set bi_vcnt 0. We don't
+ * want to confuse SCSI because SCSI will replace payload
+ */
+ if (rw & REQ_DISCARD)
+ rbi->bi_vcnt = 0;
if (conf->mddev->gendisk)
trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
rbi, disk_devt(conf->mddev->gendisk),
@@ -1881,6 +1897,7 @@
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
if (!uptodate) {
+ set_bit(STRIPE_DEGRADED, &sh->state);
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
@@ -2661,7 +2678,8 @@
(s->failed >= 2 && fdev[1]->toread) ||
(sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
!test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
- (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
+ ((sh->raid_conf->level == 6 || sh->sector >= sh->raid_conf->mddev->recovery_cp)
+ && s->failed && s->to_write))) {
/* we would like to get this block, possibly by computing it,
* otherwise read it if the backing disk is insync
*/
@@ -2800,6 +2818,14 @@
}
/* now that discard is done we can proceed with any sync */
clear_bit(STRIPE_DISCARD, &sh->state);
+ /*
+ * SCSI discard will change some bio fields and the stripe has
+ * no updated data, so remove it from hash list and the stripe
+ * will be reinitialized
+ */
+ spin_lock_irq(&conf->device_lock);
+ remove_hash(sh);
+ spin_unlock_irq(&conf->device_lock);
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
set_bit(STRIPE_HANDLE, &sh->state);
@@ -2827,7 +2853,8 @@
* generate correct data from the parity.
*/
if (conf->max_degraded == 2 ||
- (recovery_cp < MaxSector && sh->sector >= recovery_cp)) {
+ (recovery_cp < MaxSector && sh->sector >= recovery_cp &&
+ s->failed == 0)) {
/* Calculate the real rcw later - for now make it
* look like rcw is cheaper
*/
@@ -3371,7 +3398,7 @@
*/
set_bit(R5_Insync, &dev->flags);
- if (rdev && test_bit(R5_WriteError, &dev->flags)) {
+ if (test_bit(R5_WriteError, &dev->flags)) {
/* This flag does not apply to '.replacement'
* only to .rdev, so make sure to check that*/
struct md_rdev *rdev2 = rcu_dereference(
@@ -3384,7 +3411,7 @@
} else
clear_bit(R5_WriteError, &dev->flags);
}
- if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
+ if (test_bit(R5_MadeGood, &dev->flags)) {
/* This flag does not apply to '.replacement'
* only to .rdev, so make sure to check that*/
struct md_rdev *rdev2 = rcu_dereference(
@@ -3462,6 +3489,7 @@
test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
+ clear_bit(STRIPE_REPLACED, &sh->state);
}
spin_unlock(&sh->stripe_lock);
}
@@ -3539,6 +3567,8 @@
set_bit(R5_Wantwrite, &dev->flags);
if (prexor)
continue;
+ if (s.failed > 1)
+ continue;
if (!test_bit(R5_Insync, &dev->flags) ||
((i == sh->pd_idx || i == sh->qd_idx) &&
s.failed == 0))
@@ -3607,19 +3637,23 @@
handle_parity_checks5(conf, sh, &s, disks);
}
- if (s.replacing && s.locked == 0
- && !test_bit(STRIPE_INSYNC, &sh->state)) {
+ if ((s.replacing || s.syncing) && s.locked == 0
+ && !test_bit(STRIPE_COMPUTE_RUN, &sh->state)
+ && !test_bit(STRIPE_REPLACED, &sh->state)) {
/* Write out to replacement devices where possible */
for (i = 0; i < conf->raid_disks; i++)
- if (test_bit(R5_UPTODATE, &sh->dev[i].flags) &&
- test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
+ if (test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
+ WARN_ON(!test_bit(R5_UPTODATE, &sh->dev[i].flags));
set_bit(R5_WantReplace, &sh->dev[i].flags);
set_bit(R5_LOCKED, &sh->dev[i].flags);
s.locked++;
}
- set_bit(STRIPE_INSYNC, &sh->state);
+ if (s.replacing)
+ set_bit(STRIPE_INSYNC, &sh->state);
+ set_bit(STRIPE_REPLACED, &sh->state);
}
if ((s.syncing || s.replacing) && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
clear_bit(STRIPE_SYNCING, &sh->state);
@@ -5011,23 +5045,43 @@
return sectors * (raid_disks - conf->max_degraded);
}
+static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ safe_put_page(percpu->spare_page);
+ kfree(percpu->scribble);
+ percpu->spare_page = NULL;
+ percpu->scribble = NULL;
+}
+
+static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu)
+{
+ if (conf->level == 6 && !percpu->spare_page)
+ percpu->spare_page = alloc_page(GFP_KERNEL);
+ if (!percpu->scribble)
+ percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+
+ if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
+ free_scratch_buffer(conf, percpu);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
static void raid5_free_percpu(struct r5conf *conf)
{
- struct raid5_percpu *percpu;
unsigned long cpu;
if (!conf->percpu)
return;
- get_online_cpus();
- for_each_possible_cpu(cpu) {
- percpu = per_cpu_ptr(conf->percpu, cpu);
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- }
#ifdef CONFIG_HOTPLUG_CPU
unregister_cpu_notifier(&conf->cpu_notify);
#endif
+
+ get_online_cpus();
+ for_each_possible_cpu(cpu)
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
put_online_cpus();
free_percpu(conf->percpu);
@@ -5053,15 +5107,7 @@
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- if (conf->level == 6 && !percpu->spare_page)
- percpu->spare_page = alloc_page(GFP_KERNEL);
- if (!percpu->scribble)
- percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
-
- if (!percpu->scribble ||
- (conf->level == 6 && !percpu->spare_page)) {
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
+ if (alloc_scratch_buffer(conf, percpu)) {
pr_err("%s: failed memory allocation for cpu%ld\n",
__func__, cpu);
return notifier_from_errno(-ENOMEM);
@@ -5069,10 +5115,7 @@
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
- safe_put_page(percpu->spare_page);
- kfree(percpu->scribble);
- percpu->spare_page = NULL;
- percpu->scribble = NULL;
+ free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
break;
default:
break;
@@ -5084,40 +5127,29 @@
static int raid5_alloc_percpu(struct r5conf *conf)
{
unsigned long cpu;
- struct page *spare_page;
- struct raid5_percpu __percpu *allcpus;
- void *scribble;
- int err;
+ int err = 0;
- allcpus = alloc_percpu(struct raid5_percpu);
- if (!allcpus)
+ conf->percpu = alloc_percpu(struct raid5_percpu);
+ if (!conf->percpu)
return -ENOMEM;
- conf->percpu = allcpus;
- get_online_cpus();
- err = 0;
- for_each_present_cpu(cpu) {
- if (conf->level == 6) {
- spare_page = alloc_page(GFP_KERNEL);
- if (!spare_page) {
- err = -ENOMEM;
- break;
- }
- per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
- }
- scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
- if (!scribble) {
- err = -ENOMEM;
- break;
- }
- per_cpu_ptr(conf->percpu, cpu)->scribble = scribble;
- }
#ifdef CONFIG_HOTPLUG_CPU
conf->cpu_notify.notifier_call = raid456_cpu_notify;
conf->cpu_notify.priority = 0;
- if (err == 0)
- err = register_cpu_notifier(&conf->cpu_notify);
+ err = register_cpu_notifier(&conf->cpu_notify);
+ if (err)
+ return err;
#endif
+
+ get_online_cpus();
+ for_each_present_cpu(cpu) {
+ err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+ if (err) {
+ pr_err("%s: failed memory allocation for cpu%ld\n",
+ __func__, cpu);
+ break;
+ }
+ }
put_online_cpus();
return err;
@@ -5585,7 +5617,7 @@
mddev->queue->limits.discard_granularity = stripe;
/*
* unaligned part of discard request will be ignored, so can't
- * guarantee discard_zerors_data
+ * guarantee discard_zeroes_data
*/
mddev->queue->limits.discard_zeroes_data = 0;
@@ -5610,6 +5642,18 @@
!bdev_get_queue(rdev->bdev)->
limits.discard_zeroes_data)
discard_supported = false;
+ /* Unfortunately, discard_zeroes_data is not currently
+ * a guarantee - just a hint. So we only allow DISCARD
+ * if the sysadmin has confirmed that only safe devices
+ * are in use by setting a module parameter.
+ */
+ if (!devices_handle_discard_safely) {
+ if (discard_supported) {
+ pr_info("md/raid456: discard support disabled due to uncertainty.\n");
+ pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
+ }
+ discard_supported = false;
+ }
}
if (discard_supported &&
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index b0b663b..70c4932 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -306,6 +306,7 @@
STRIPE_SYNC_REQUESTED,
STRIPE_SYNCING,
STRIPE_INSYNC,
+ STRIPE_REPLACED,
STRIPE_PREREAD_ACTIVE,
STRIPE_DELAYED,
STRIPE_DEGRADED,
diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c
index 297f1b2..8df1aea 100644
--- a/drivers/media/common/siano/smsdvb-main.c
+++ b/drivers/media/common/siano/smsdvb-main.c
@@ -275,7 +275,8 @@
/* Legacy PER/BER */
tmp = p->ets_packets * 65535;
- do_div(tmp, p->ts_packets + p->ets_packets);
+ if (p->ts_packets + p->ets_packets)
+ do_div(tmp, p->ts_packets + p->ets_packets);
client->legacy_per = tmp;
}
diff --git a/drivers/media/dvb-core/dmxdev.c b/drivers/media/dvb-core/dmxdev.c
index a1a3a51..0b4616b 100644
--- a/drivers/media/dvb-core/dmxdev.c
+++ b/drivers/media/dvb-core/dmxdev.c
@@ -377,10 +377,8 @@
ret = dvb_dmxdev_buffer_write(&dmxdevfilter->buffer, buffer2,
buffer2_len);
}
- if (ret < 0) {
- dvb_ringbuffer_flush(&dmxdevfilter->buffer);
+ if (ret < 0)
dmxdevfilter->buffer.error = ret;
- }
if (dmxdevfilter->params.sec.flags & DMX_ONESHOT)
dmxdevfilter->state = DMXDEV_STATE_DONE;
spin_unlock(&dmxdevfilter->dev->lock);
@@ -416,10 +414,8 @@
ret = dvb_dmxdev_buffer_write(buffer, buffer1, buffer1_len);
if (ret == buffer1_len)
ret = dvb_dmxdev_buffer_write(buffer, buffer2, buffer2_len);
- if (ret < 0) {
- dvb_ringbuffer_flush(buffer);
+ if (ret < 0)
buffer->error = ret;
- }
spin_unlock(&dmxdevfilter->dev->lock);
wake_up(&buffer->queue);
return 0;
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index a204f28..fb504f1 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -24,6 +24,9 @@
#include "af9013_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct af9013_state {
struct i2c_adapter *i2c;
struct dvb_frontend fe;
@@ -50,16 +53,23 @@
const u8 *val, int len)
{
int ret;
- u8 buf[3+len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->config.i2c_addr,
.flags = 0,
- .len = sizeof(buf),
+ .len = 3 + len,
.buf = buf,
}
};
+ if (3 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = (reg >> 8) & 0xff;
buf[1] = (reg >> 0) & 0xff;
buf[2] = mbox;
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index a777b4b..65728c2 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -21,6 +21,9 @@
#include "af9033_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct af9033_state {
struct i2c_adapter *i2c;
struct dvb_frontend fe;
@@ -40,16 +43,23 @@
int len)
{
int ret;
- u8 buf[3 + len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = state->cfg.i2c_addr,
.flags = 0,
- .len = sizeof(buf),
+ .len = 3 + len,
.buf = buf,
}
};
+ if (3 + len > sizeof(buf)) {
+ dev_warn(&state->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = (reg >> 16) & 0xff;
buf[1] = (reg >> 8) & 0xff;
buf[2] = (reg >> 0) & 0xff;
@@ -160,11 +170,18 @@
static int af9033_wr_reg_val_tab(struct af9033_state *state,
const struct reg_val *tab, int tab_len)
{
+#define MAX_TAB_LEN 212
int ret, i, j;
- u8 buf[tab_len];
+ u8 buf[1 + MAX_TAB_LEN];
dev_dbg(&state->i2c->dev, "%s: tab_len=%d\n", __func__, tab_len);
+ if (tab_len > sizeof(buf)) {
+ dev_warn(&state->i2c->dev, "%s: tab len %d is too big\n",
+ KBUILD_MODNAME, tab_len);
+ return -EINVAL;
+ }
+
for (i = 0, j = 0; i < tab_len; i++) {
buf[j] = tab[i].val;
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 1b77909..39a29dd 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -44,6 +44,9 @@
#include "bcm3510.h"
#include "bcm3510_priv.h"
+/* Max transfer size done by bcm3510_do_hab_cmd() function */
+#define MAX_XFER_SIZE 128
+
struct bcm3510_state {
struct i2c_adapter* i2c;
@@ -201,9 +204,19 @@
static int bcm3510_do_hab_cmd(struct bcm3510_state *st, u8 cmd, u8 msgid, u8 *obuf, u8 olen, u8 *ibuf, u8 ilen)
{
- u8 ob[olen+2],ib[ilen+2];
+ u8 ob[MAX_XFER_SIZE], ib[MAX_XFER_SIZE];
int ret = 0;
+ if (ilen + 2 > sizeof(ib)) {
+ deb_hab("do_hab_cmd: ilen=%d is too big!\n", ilen);
+ return -EINVAL;
+ }
+
+ if (olen + 2 > sizeof(ob)) {
+ deb_hab("do_hab_cmd: olen=%d is too big!\n", olen);
+ return -EINVAL;
+ }
+
ob[0] = cmd;
ob[1] = msgid;
memcpy(&ob[2],obuf,olen);
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index 7ca5c69..03930d5 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -21,21 +21,31 @@
#include "cxd2820r_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/* write multiple registers */
static int cxd2820r_wr_regs_i2c(struct cxd2820r_priv *priv, u8 i2c, u8 reg,
u8 *val, int len)
{
int ret;
- u8 buf[len+1];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = i2c,
.flags = 0,
- .len = sizeof(buf),
+ .len = len + 1,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
@@ -55,7 +65,7 @@
u8 *val, int len)
{
int ret;
- u8 buf[len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[2] = {
{
.addr = i2c,
@@ -65,11 +75,18 @@
}, {
.addr = i2c,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = len,
.buf = buf,
}
};
+ if (len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, buf, len);
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index a54182d..362de38 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -157,15 +157,10 @@
return ret;
}
-static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+static u16 __dib8000_read_word(struct dib8000_state *state, u16 reg)
{
u16 ret;
- if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
- dprintk("could not acquire lock");
- return 0;
- }
-
state->i2c_write_buffer[0] = reg >> 8;
state->i2c_write_buffer[1] = reg & 0xff;
@@ -183,6 +178,21 @@
dprintk("i2c read error on %d", reg);
ret = (state->i2c_read_buffer[0] << 8) | state->i2c_read_buffer[1];
+
+ return ret;
+}
+
+static u16 dib8000_read_word(struct dib8000_state *state, u16 reg)
+{
+ u16 ret;
+
+ if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+ dprintk("could not acquire lock");
+ return 0;
+ }
+
+ ret = __dib8000_read_word(state, reg);
+
mutex_unlock(&state->i2c_buffer_lock);
return ret;
@@ -192,8 +202,15 @@
{
u16 rw[2];
- rw[0] = dib8000_read_word(state, reg + 0);
- rw[1] = dib8000_read_word(state, reg + 1);
+ if (mutex_lock_interruptible(&state->i2c_buffer_lock) < 0) {
+ dprintk("could not acquire lock");
+ return 0;
+ }
+
+ rw[0] = __dib8000_read_word(state, reg + 0);
+ rw[1] = __dib8000_read_word(state, reg + 1);
+
+ mutex_unlock(&state->i2c_buffer_lock);
return ((rw[0] << 16) | (rw[1]));
}
@@ -2445,7 +2462,8 @@
if (state->revision == 0x8090)
internal = dib8000_read32(state, 23) / 1000;
- if (state->autosearch_state == AS_SEARCHING_FFT) {
+ if ((state->revision >= 0x8002) &&
+ (state->autosearch_state == AS_SEARCHING_FFT)) {
dib8000_write_word(state, 37, 0x0065); /* P_ctrl_pha_off_max default values */
dib8000_write_word(state, 116, 0x0000); /* P_ana_gain to 0 */
@@ -2481,7 +2499,8 @@
dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (1 << 13)); /* P_restart_ccg = 1 */
dib8000_write_word(state, 770, (dib8000_read_word(state, 770) & 0xdfff) | (0 << 13)); /* P_restart_ccg = 0 */
dib8000_write_word(state, 0, (dib8000_read_word(state, 0) & 0x7ff) | (0 << 15) | (1 << 13)); /* P_restart_search = 0; */
- } else if (state->autosearch_state == AS_SEARCHING_GUARD) {
+ } else if ((state->revision >= 0x8002) &&
+ (state->autosearch_state == AS_SEARCHING_GUARD)) {
c->transmission_mode = TRANSMISSION_MODE_8K;
c->guard_interval = GUARD_INTERVAL_1_8;
c->inversion = 0;
@@ -2583,7 +2602,8 @@
struct dib8000_state *state = fe->demodulator_priv;
u16 irq_pending = dib8000_read_word(state, 1284);
- if (state->autosearch_state == AS_SEARCHING_FFT) {
+ if ((state->revision >= 0x8002) &&
+ (state->autosearch_state == AS_SEARCHING_FFT)) {
if (irq_pending & 0x1) {
dprintk("dib8000_autosearch_irq: max correlation result available");
return 3;
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 1e344b0..22e8c20 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -864,6 +864,13 @@
memcpy(&state->frontend.ops, &ds3000_ops,
sizeof(struct dvb_frontend_ops));
state->frontend.demodulator_priv = state;
+
+ /*
+ * Some devices like T480 starts with voltage on. Be sure
+ * to turn voltage off during init, as this can otherwise
+ * interfere with Unicable SCR systems.
+ */
+ ds3000_set_voltage(&state->frontend, SEC_VOLTAGE_OFF);
return &state->frontend;
error3:
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index c1c3400..cadcae4 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -31,6 +31,9 @@
#include "itd1000.h"
#include "itd1000_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static int debug;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "Turn on/off debugging (default:off).");
@@ -52,10 +55,18 @@
/* don't write more than one byte with flexcop behind */
static int itd1000_write_regs(struct itd1000_state *state, u8 reg, u8 v[], u8 len)
{
- u8 buf[1+len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = state->cfg->i2c_address, .flags = 0, .buf = buf, .len = len+1
};
+
+ if (1 + len > sizeof(buf)) {
+ printk(KERN_WARNING
+ "itd1000: i2c wr reg=%04x: len=%d is too big!\n",
+ reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], v, len);
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 4da5272..c7a1c8e 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -110,28 +110,94 @@
return b1[0];
}
+static u32 m88rs2000_get_mclk(struct dvb_frontend *fe)
+{
+ struct m88rs2000_state *state = fe->demodulator_priv;
+ u32 mclk;
+ u8 reg;
+ /* Must not be 0x00 or 0xff */
+ reg = m88rs2000_readreg(state, 0x86);
+ if (!reg || reg == 0xff)
+ return 0;
+
+ reg /= 2;
+ reg += 1;
+
+ mclk = (u32)(reg * RS2000_FE_CRYSTAL_KHZ + 28 / 2) / 28;
+
+ return mclk;
+}
+
+static int m88rs2000_set_carrieroffset(struct dvb_frontend *fe, s16 offset)
+{
+ struct m88rs2000_state *state = fe->demodulator_priv;
+ u32 mclk;
+ s32 tmp;
+ u8 reg;
+ int ret;
+
+ mclk = m88rs2000_get_mclk(fe);
+ if (!mclk)
+ return -EINVAL;
+
+ tmp = (offset * 4096 + (s32)mclk / 2) / (s32)mclk;
+ if (tmp < 0)
+ tmp += 4096;
+
+ /* Carrier Offset */
+ ret = m88rs2000_writereg(state, 0x9c, (u8)(tmp >> 4));
+
+ reg = m88rs2000_readreg(state, 0x9d);
+ reg &= 0xf;
+ reg |= (u8)(tmp & 0xf) << 4;
+
+ ret |= m88rs2000_writereg(state, 0x9d, reg);
+
+ return ret;
+}
+
static int m88rs2000_set_symbolrate(struct dvb_frontend *fe, u32 srate)
{
struct m88rs2000_state *state = fe->demodulator_priv;
int ret;
- u32 temp;
+ u64 temp;
+ u32 mclk;
u8 b[3];
if ((srate < 1000000) || (srate > 45000000))
return -EINVAL;
+ mclk = m88rs2000_get_mclk(fe);
+ if (!mclk)
+ return -EINVAL;
+
temp = srate / 1000;
- temp *= 11831;
- temp /= 68;
- temp -= 3;
+ temp *= 1 << 24;
+
+ do_div(temp, mclk);
b[0] = (u8) (temp >> 16) & 0xff;
b[1] = (u8) (temp >> 8) & 0xff;
b[2] = (u8) temp & 0xff;
+
ret = m88rs2000_writereg(state, 0x93, b[2]);
ret |= m88rs2000_writereg(state, 0x94, b[1]);
ret |= m88rs2000_writereg(state, 0x95, b[0]);
+ if (srate > 10000000)
+ ret |= m88rs2000_writereg(state, 0xa0, 0x20);
+ else
+ ret |= m88rs2000_writereg(state, 0xa0, 0x60);
+
+ ret |= m88rs2000_writereg(state, 0xa1, 0xe0);
+
+ if (srate > 12000000)
+ ret |= m88rs2000_writereg(state, 0xa3, 0x20);
+ else if (srate > 2800000)
+ ret |= m88rs2000_writereg(state, 0xa3, 0x98);
+ else
+ ret |= m88rs2000_writereg(state, 0xa3, 0x90);
+
deb_info("m88rs2000: m88rs2000_set_symbolrate\n");
return ret;
}
@@ -261,8 +327,6 @@
struct inittab fe_reset[] = {
{DEMOD_WRITE, 0x00, 0x01},
- {DEMOD_WRITE, 0xf1, 0xbf},
- {DEMOD_WRITE, 0x00, 0x01},
{DEMOD_WRITE, 0x20, 0x81},
{DEMOD_WRITE, 0x21, 0x80},
{DEMOD_WRITE, 0x10, 0x33},
@@ -305,9 +369,6 @@
{DEMOD_WRITE, 0x9b, 0x64},
{DEMOD_WRITE, 0x9e, 0x00},
{DEMOD_WRITE, 0x9f, 0xf8},
- {DEMOD_WRITE, 0xa0, 0x20},
- {DEMOD_WRITE, 0xa1, 0xe0},
- {DEMOD_WRITE, 0xa3, 0x38},
{DEMOD_WRITE, 0x98, 0xff},
{DEMOD_WRITE, 0xc0, 0x0f},
{DEMOD_WRITE, 0x89, 0x01},
@@ -540,9 +601,8 @@
struct dtv_frontend_properties *c = &fe->dtv_property_cache;
fe_status_t status;
int i, ret = 0;
- s32 tmp;
u32 tuner_freq;
- u16 offset = 0;
+ s16 offset = 0;
u8 reg;
state->no_lock_count = 0;
@@ -567,29 +627,26 @@
if (ret < 0)
return -ENODEV;
- offset = tuner_freq - c->frequency;
+ offset = (s16)((s32)tuner_freq - c->frequency);
- /* calculate offset assuming 96000kHz*/
- tmp = offset;
- tmp *= 65536;
+ /* default mclk value 96.4285 * 2 * 1000 = 192857 */
+ if (((c->frequency % 192857) >= (192857 - 3000)) ||
+ (c->frequency % 192857) <= 3000)
+ ret = m88rs2000_writereg(state, 0x86, 0xc2);
+ else
+ ret = m88rs2000_writereg(state, 0x86, 0xc6);
- tmp = (2 * tmp + 96000) / (2 * 96000);
- if (tmp < 0)
- tmp += 65536;
+ ret |= m88rs2000_set_carrieroffset(fe, offset);
+ if (ret < 0)
+ return -ENODEV;
- offset = tmp & 0xffff;
+ /* Reset demod by symbol rate */
+ if (c->symbol_rate > 27500000)
+ ret = m88rs2000_writereg(state, 0xf1, 0xa4);
+ else
+ ret = m88rs2000_writereg(state, 0xf1, 0xbf);
- ret = m88rs2000_writereg(state, 0x9a, 0x30);
- /* Unknown usually 0xc6 sometimes 0xc1 */
- reg = m88rs2000_readreg(state, 0x86);
- ret |= m88rs2000_writereg(state, 0x86, reg);
- /* Offset lower nibble always 0 */
- ret |= m88rs2000_writereg(state, 0x9c, (offset >> 8));
- ret |= m88rs2000_writereg(state, 0x9d, offset & 0xf0);
-
-
- /* Reset Demod */
- ret = m88rs2000_tab_set(state, fe_reset);
+ ret |= m88rs2000_tab_set(state, fe_reset);
if (ret < 0)
return -ENODEV;
@@ -655,6 +712,22 @@
return 0;
}
+static int m88rs2000_get_tune_settings(struct dvb_frontend *fe,
+ struct dvb_frontend_tune_settings *tune)
+{
+ struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+ if (c->symbol_rate > 3000000)
+ tune->min_delay_ms = 2000;
+ else
+ tune->min_delay_ms = 3000;
+
+ tune->step_size = c->symbol_rate / 16000;
+ tune->max_drift = c->symbol_rate / 2000;
+
+ return 0;
+}
+
static int m88rs2000_i2c_gate_ctrl(struct dvb_frontend *fe, int enable)
{
struct m88rs2000_state *state = fe->demodulator_priv;
@@ -686,7 +759,7 @@
.symbol_rate_tolerance = 500, /* ppm */
.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
- FE_CAN_QPSK |
+ FE_CAN_QPSK | FE_CAN_INVERSION_AUTO |
FE_CAN_FEC_AUTO
},
@@ -706,6 +779,7 @@
.set_frontend = m88rs2000_set_frontend,
.get_frontend = m88rs2000_get_frontend,
+ .get_tune_settings = m88rs2000_get_tune_settings,
};
struct dvb_frontend *m88rs2000_attach(const struct m88rs2000_config *config,
diff --git a/drivers/media/dvb-frontends/m88rs2000.h b/drivers/media/dvb-frontends/m88rs2000.h
index 14ce31e..0a50ea9 100644
--- a/drivers/media/dvb-frontends/m88rs2000.h
+++ b/drivers/media/dvb-frontends/m88rs2000.h
@@ -53,6 +53,8 @@
}
#endif /* CONFIG_DVB_M88RS2000 */
+#define RS2000_FE_CRYSTAL_KHZ 27000
+
enum {
DEMOD_WRITE = 0x1,
WRITE_DELAY = 0x10,
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index 856374b..2c7217f 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -157,7 +157,6 @@
{ 0x45, 0x04 }, /* CN symbol 4 */
{ 0x48, 0x04 }, /* CN manual mode */
- { 0x50, 0xd5 }, { 0x51, 0x01 }, /* Serial */
{ 0x50, 0xd6 }, { 0x51, 0x1f },
{ 0x50, 0xd2 }, { 0x51, 0x03 },
{ 0x50, 0xd7 }, { 0x51, 0xbf },
@@ -1860,16 +1859,15 @@
dev_dbg(&state->i2c->dev, "%s: IF=%d, IF reg=0x%06llx\n",
__func__, state->if_freq, (long long)pll);
- if (!state->config->is_serial) {
+ if (!state->config->is_serial)
regD5 &= ~1;
- rc = mb86a20s_writereg(state, 0x50, 0xd5);
- if (rc < 0)
- goto err;
- rc = mb86a20s_writereg(state, 0x51, regD5);
- if (rc < 0)
- goto err;
- }
+ rc = mb86a20s_writereg(state, 0x50, 0xd5);
+ if (rc < 0)
+ goto err;
+ rc = mb86a20s_writereg(state, 0x51, regD5);
+ if (rc < 0)
+ goto err;
rc = mb86a20s_writeregdata(state, mb86a20s_init2);
if (rc < 0)
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index ec388c1d..a74ac0d 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -36,6 +36,8 @@
#include "mt312_priv.h"
#include "mt312.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
struct mt312_state {
struct i2c_adapter *i2c;
@@ -96,9 +98,15 @@
const u8 *src, const size_t count)
{
int ret;
- u8 buf[count + 1];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg;
+ if (1 + count > sizeof(buf)) {
+ printk(KERN_WARNING
+ "mt312: write: len=%zd is too big!\n", count);
+ return -EINVAL;
+ }
+
if (debug) {
int i;
dprintk("W(%d):", reg & 0x7f);
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index 8e28894..4bf0575 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -39,6 +39,9 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 256
+
#define NXT2002_DEFAULT_FIRMWARE "dvb-fe-nxt2002.fw"
#define NXT2004_DEFAULT_FIRMWARE "dvb-fe-nxt2004.fw"
#define CRC_CCIT_MASK 0x1021
@@ -95,10 +98,16 @@
static int nxt200x_writebytes (struct nxt200x_state* state, u8 reg,
const u8 *buf, u8 len)
{
- u8 buf2 [len+1];
+ u8 buf2[MAX_XFER_SIZE];
int err;
struct i2c_msg msg = { .addr = state->config->demod_address, .flags = 0, .buf = buf2, .len = len + 1 };
+ if (1 + len > sizeof(buf2)) {
+ pr_warn("%s: i2c wr reg=%04x: len=%d is too big!\n",
+ __func__, reg, len);
+ return -EINVAL;
+ }
+
buf2[0] = reg;
memcpy(&buf2[1], buf, len);
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index 362d26d..7efb796 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -27,20 +27,30 @@
#include "rtl2830_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/* write multiple hardware registers */
static int rtl2830_wr(struct rtl2830_priv *priv, u8 reg, const u8 *val, int len)
{
int ret;
- u8 buf[1+len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg.i2c_addr,
.flags = 0,
- .len = 1+len,
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index facb848..b8dd0a1 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -22,6 +22,9 @@
#include "dvb_math.h"
#include <linux/bitops.h>
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
int rtl2832_debug;
module_param_named(debug, rtl2832_debug, int, 0644);
MODULE_PARM_DESC(debug, "Turn on/off frontend debugging (default:off).");
@@ -162,16 +165,23 @@
static int rtl2832_wr(struct rtl2832_priv *priv, u8 reg, u8 *val, int len)
{
int ret;
- u8 buf[1+len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg.i2c_addr,
.flags = 0,
- .len = 1+len,
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index e2fec9e..93eeaf7 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -836,9 +836,16 @@
static int s5h1420_tuner_i2c_tuner_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg msg[], int num)
{
struct s5h1420_state *state = i2c_get_adapdata(i2c_adap);
- struct i2c_msg m[1 + num];
+ struct i2c_msg m[3];
u8 tx_open[2] = { CON_1, state->CON_1_val | 1 }; /* repeater stops once there was a stop condition */
+ if (1 + num > ARRAY_SIZE(m)) {
+ printk(KERN_WARNING
+ "%s: i2c xfer: num=%d is too big!\n",
+ KBUILD_MODNAME, num);
+ return -EOPNOTSUPP;
+ }
+
memset(m, 0, sizeof(struct i2c_msg) * (1 + num));
m[0].addr = state->config->demod_address;
@@ -847,7 +854,7 @@
memcpy(&m[1], msg, sizeof(struct i2c_msg) * num);
- return i2c_transfer(state->i2c, m, 1+num) == 1 + num ? num : -EIO;
+ return i2c_transfer(state->i2c, m, 1 + num) == 1 + num ? num : -EIO;
}
static struct i2c_algorithm s5h1420_tuner_i2c_algo = {
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index cc278b3..2a979cf 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -32,6 +32,9 @@
#include "stb0899_priv.h"
#include "stb0899_reg.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static unsigned int verbose = 0;//1;
module_param(verbose, int, 0644);
@@ -499,7 +502,7 @@
int stb0899_write_regs(struct stb0899_state *state, unsigned int reg, u8 *data, u32 count)
{
int ret;
- u8 buf[2 + count];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg i2c_msg = {
.addr = state->config->demod_address,
.flags = 0,
@@ -507,6 +510,13 @@
.len = 2 + count
};
+ if (2 + count > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, count);
+ return -EINVAL;
+ }
+
buf[0] = reg >> 8;
buf[1] = reg & 0xff;
memcpy(&buf[2], data, count);
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 45f9523..cea175d 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -31,6 +31,8 @@
static unsigned int verbose;
module_param(verbose, int, 0644);
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
#define FE_ERROR 0
#define FE_NOTICE 1
@@ -183,7 +185,7 @@
static int stb6100_write_reg_range(struct stb6100_state *state, u8 buf[], int start, int len)
{
int rc;
- u8 cmdbuf[len + 1];
+ u8 cmdbuf[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = state->config->tuner_address,
.flags = 0,
@@ -191,6 +193,13 @@
.len = len + 1
};
+ if (1 + len > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr: len=%d is too big!\n",
+ KBUILD_MODNAME, len);
+ return -EINVAL;
+ }
+
if (unlikely(start < 1 || start + len > STB6100_NUMREGS)) {
dprintk(verbose, FE_ERROR, 1, "Invalid register range %d:%d",
start, len);
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 0c8e459..f6c7277 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -33,6 +33,9 @@
#include "stv0367_regs.h"
#include "stv0367_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static int stvdebug;
module_param_named(debug, stvdebug, int, 0644);
@@ -767,7 +770,7 @@
static
int stv0367_writeregs(struct stv0367_state *state, u16 reg, u8 *data, int len)
{
- u8 buf[len + 2];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = state->config->demod_address,
.flags = 0,
@@ -776,6 +779,14 @@
};
int ret;
+ if (2 + len > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
+
buf[0] = MSB(reg);
buf[1] = LSB(reg);
memcpy(buf + 2, data, len);
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index 56d470a..23e872f 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -35,6 +35,9 @@
#include "stv090x.h"
#include "stv090x_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static unsigned int verbose;
module_param(verbose, int, 0644);
@@ -722,9 +725,16 @@
{
const struct stv090x_config *config = state->config;
int ret;
- u8 buf[2 + count];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg i2c_msg = { .addr = config->address, .flags = 0, .buf = buf, .len = 2 + count };
+ if (2 + count > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, count);
+ return -EINVAL;
+ }
+
buf[0] = reg >> 8;
buf[1] = reg & 0xff;
memcpy(&buf[2], data, count);
diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c
index 20b5fa9..b142583 100644
--- a/drivers/media/dvb-frontends/stv6110.c
+++ b/drivers/media/dvb-frontends/stv6110.c
@@ -30,6 +30,9 @@
#include "stv6110.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static int debug;
struct stv6110_priv {
@@ -68,7 +71,7 @@
{
struct stv6110_priv *priv = fe->tuner_priv;
int rc;
- u8 cmdbuf[len + 1];
+ u8 cmdbuf[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = priv->i2c_address,
.flags = 0,
@@ -78,6 +81,13 @@
dprintk("%s\n", __func__);
+ if (1 + len > sizeof(cmdbuf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr: len=%d is too big!\n",
+ KBUILD_MODNAME, len);
+ return -EINVAL;
+ }
+
if (start + len > 8)
return -EINVAL;
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index f36cab1..e66154e 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -32,6 +32,9 @@
#include "stv6110x.h"
#include "stv6110x_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static unsigned int verbose;
module_param(verbose, int, 0644);
MODULE_PARM_DESC(verbose, "Set Verbosity level");
@@ -61,7 +64,8 @@
{
int ret;
const struct stv6110x_config *config = stv6110x->config;
- u8 buf[len + 1];
+ u8 buf[MAX_XFER_SIZE];
+
struct i2c_msg msg = {
.addr = config->addr,
.flags = 0,
@@ -69,6 +73,13 @@
.len = len + 1
};
+ if (1 + len > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr: len=%d is too big!\n",
+ KBUILD_MODNAME, len);
+ return -EINVAL;
+ }
+
if (start + len > 8)
return -EINVAL;
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 2521f7e..def7812 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -20,6 +20,9 @@
#include "tda10071_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static struct dvb_frontend_ops tda10071_ops;
/* write multiple registers */
@@ -27,16 +30,23 @@
int len)
{
int ret;
- u8 buf[len+1];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg.demod_i2c_addr,
.flags = 0,
- .len = sizeof(buf),
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
@@ -56,7 +66,7 @@
int len)
{
int ret;
- u8 buf[len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[2] = {
{
.addr = priv->cfg.demod_i2c_addr,
@@ -66,11 +76,18 @@
}, {
.addr = priv->cfg.demod_i2c_addr,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = len,
.buf = buf,
}
};
+ if (len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, buf, len);
@@ -650,6 +667,7 @@
struct dtv_frontend_properties *c = &fe->dtv_property_cache;
int ret, i;
u8 mode, rolloff, pilot, inversion, div;
+ fe_modulation_t modulation;
dev_dbg(&priv->i2c->dev, "%s: delivery_system=%d modulation=%d " \
"frequency=%d symbol_rate=%d inversion=%d pilot=%d " \
@@ -684,10 +702,13 @@
switch (c->delivery_system) {
case SYS_DVBS:
+ modulation = QPSK;
rolloff = 0;
pilot = 2;
break;
case SYS_DVBS2:
+ modulation = c->modulation;
+
switch (c->rolloff) {
case ROLLOFF_20:
rolloff = 2;
@@ -732,7 +753,7 @@
for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) {
if (c->delivery_system == TDA10071_MODCOD[i].delivery_system &&
- c->modulation == TDA10071_MODCOD[i].modulation &&
+ modulation == TDA10071_MODCOD[i].modulation &&
c->fec_inner == TDA10071_MODCOD[i].fec) {
mode = TDA10071_MODCOD[i].val;
dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n",
diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c
index d281f77..2c54586 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.c
+++ b/drivers/media/dvb-frontends/tda18271c2dd.c
@@ -34,6 +34,9 @@
#include "dvb_frontend.h"
#include "tda18271c2dd.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct SStandardParam {
s32 m_IFFrequency;
u32 m_BandWidth;
@@ -139,11 +142,18 @@
static int WriteRegs(struct tda_state *state,
u8 SubAddr, u8 *Regs, u16 nRegs)
{
- u8 data[nRegs+1];
+ u8 data[MAX_XFER_SIZE];
+
+ if (1 + nRegs > sizeof(data)) {
+ printk(KERN_WARNING
+ "%s: i2c wr: len=%d is too big!\n",
+ KBUILD_MODNAME, nRegs);
+ return -EINVAL;
+ }
data[0] = SubAddr;
memcpy(data + 1, Regs, nRegs);
- return i2c_write(state->i2c, state->adr, data, nRegs+1);
+ return i2c_write(state->i2c, state->adr, data, nRegs + 1);
}
static int WriteReg(struct tda_state *state, u8 SubAddr, u8 Reg)
diff --git a/drivers/media/dvb-frontends/zl10039.c b/drivers/media/dvb-frontends/zl10039.c
index eff9c5f..91b6b2e 100644
--- a/drivers/media/dvb-frontends/zl10039.c
+++ b/drivers/media/dvb-frontends/zl10039.c
@@ -30,6 +30,9 @@
static int debug;
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
#define dprintk(args...) \
do { \
if (debug) \
@@ -98,7 +101,7 @@
const enum zl10039_reg_addr reg, const u8 *src,
const size_t count)
{
- u8 buf[count + 1];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = state->i2c_addr,
.flags = 0,
@@ -106,6 +109,13 @@
.len = count + 1,
};
+ if (1 + count > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: i2c wr reg=%04x: len=%zd is too big!\n",
+ KBUILD_MODNAME, reg, count);
+ return -EINVAL;
+ }
+
dprintk("%s\n", __func__);
/* Write register address and data in one go */
buf[0] = reg;
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 617ad3f..3ead3a8 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1110,7 +1110,7 @@
* windows that fall outside that.
*/
for (i = 0; i < n_win_sizes; i++) {
- struct ov7670_win_size *win = &info->devtype->win_sizes[index];
+ struct ov7670_win_size *win = &info->devtype->win_sizes[i];
if (info->min_width && win->width < info->min_width)
continue;
if (info->min_height && win->height < info->min_height)
diff --git a/drivers/media/i2c/smiapp-pll.c b/drivers/media/i2c/smiapp-pll.c
index d8d5da7..9423051 100644
--- a/drivers/media/i2c/smiapp-pll.c
+++ b/drivers/media/i2c/smiapp-pll.c
@@ -67,7 +67,7 @@
{
dev_dbg(dev, "pre_pll_clk_div\t%d\n", pll->pre_pll_clk_div);
dev_dbg(dev, "pll_multiplier \t%d\n", pll->pll_multiplier);
- if (pll->flags != SMIAPP_PLL_FLAG_NO_OP_CLOCKS) {
+ if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) {
dev_dbg(dev, "op_sys_clk_div \t%d\n", pll->op_sys_clk_div);
dev_dbg(dev, "op_pix_clk_div \t%d\n", pll->op_pix_clk_div);
}
@@ -77,7 +77,7 @@
dev_dbg(dev, "ext_clk_freq_hz \t%d\n", pll->ext_clk_freq_hz);
dev_dbg(dev, "pll_ip_clk_freq_hz \t%d\n", pll->pll_ip_clk_freq_hz);
dev_dbg(dev, "pll_op_clk_freq_hz \t%d\n", pll->pll_op_clk_freq_hz);
- if (pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS) {
+ if (!(pll->flags & SMIAPP_PLL_FLAG_NO_OP_CLOCKS)) {
dev_dbg(dev, "op_sys_clk_freq_hz \t%d\n",
pll->op_sys_clk_freq_hz);
dev_dbg(dev, "op_pix_clk_freq_hz \t%d\n",
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index cae4f46..de8bc35 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2139,7 +2139,7 @@
ret = smiapp_set_compose(subdev, fh, sel);
break;
default:
- BUG();
+ ret = -EINVAL;
}
mutex_unlock(&sensor->mutex);
@@ -2629,7 +2629,9 @@
pll->flags |= SMIAPP_PLL_FLAG_OP_PIX_CLOCK_PER_LANE;
pll->scale_n = sensor->limits[SMIAPP_LIMIT_SCALER_N_MIN];
+ mutex_lock(&sensor->mutex);
rval = smiapp_update_mode(sensor);
+ mutex_unlock(&sensor->mutex);
if (rval) {
dev_err(&client->dev, "update mode failed\n");
goto out_nvm_release;
diff --git a/drivers/media/i2c/tda7432.c b/drivers/media/i2c/tda7432.c
index 28b5121..09f4387 100644
--- a/drivers/media/i2c/tda7432.c
+++ b/drivers/media/i2c/tda7432.c
@@ -293,7 +293,7 @@
if (t->mute->val) {
lf |= TDA7432_MUTE;
lr |= TDA7432_MUTE;
- lf |= TDA7432_MUTE;
+ rf |= TDA7432_MUTE;
rr |= TDA7432_MUTE;
}
/* Mute & update balance*/
diff --git a/drivers/media/i2c/wm8775.c b/drivers/media/i2c/wm8775.c
index 27c27b4..e5f3a78 100644
--- a/drivers/media/i2c/wm8775.c
+++ b/drivers/media/i2c/wm8775.c
@@ -131,12 +131,10 @@
return -EINVAL;
}
state->input = input;
- if (!v4l2_ctrl_g_ctrl(state->mute))
+ if (v4l2_ctrl_g_ctrl(state->mute))
return 0;
if (!v4l2_ctrl_g_ctrl(state->vol))
return 0;
- if (!v4l2_ctrl_g_ctrl(state->bal))
- return 0;
wm8775_set_audio(sd, 1);
return 0;
}
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 1957c0d..fdb5840 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -93,6 +93,7 @@
struct media_entity *ent;
struct media_entity_desc u_ent;
+ memset(&u_ent, 0, sizeof(u_ent));
if (copy_from_user(&u_ent.id, &uent->id, sizeof(u_ent.id)))
return -EFAULT;
@@ -105,8 +106,6 @@
if (ent->name) {
strncpy(u_ent.name, ent->name, sizeof(u_ent.name));
u_ent.name[sizeof(u_ent.name) - 1] = '\0';
- } else {
- memset(u_ent.name, 0, sizeof(u_ent.name));
}
u_ent.type = ent->type;
u_ent.revision = ent->revision;
diff --git a/drivers/media/pci/Kconfig b/drivers/media/pci/Kconfig
index d4e2ed3..53196f1 100644
--- a/drivers/media/pci/Kconfig
+++ b/drivers/media/pci/Kconfig
@@ -1,6 +1,7 @@
+if PCI && MEDIA_SUPPORT
+
menuconfig MEDIA_PCI_SUPPORT
bool "Media PCI Adapters"
- depends on PCI && MEDIA_SUPPORT
help
Enable media drivers for PCI/PCIe bus.
If you have such devices, say Y.
@@ -45,3 +46,4 @@
endif
endif #MEDIA_PCI_SUPPORT
+endif #PCI
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index e7d0884..e2633d9 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -4226,7 +4226,8 @@
}
btv->std = V4L2_STD_PAL;
init_irqreg(btv);
- v4l2_ctrl_handler_setup(hdl);
+ if (!bttv_tvcards[btv->c.type].no_video)
+ v4l2_ctrl_handler_setup(hdl);
if (hdl->error) {
result = hdl->error;
goto fail2;
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 67b61cf..018cb90 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -324,23 +324,27 @@
/* Hauppauge card? get values from tveeprom */
void cx18_read_eeprom(struct cx18 *cx, struct tveeprom *tv)
{
- struct i2c_client c;
+ struct i2c_client *c;
u8 eedata[256];
- memset(&c, 0, sizeof(c));
- strlcpy(c.name, "cx18 tveeprom tmp", sizeof(c.name));
- c.adapter = &cx->i2c_adap[0];
- c.addr = 0xA0 >> 1;
-
memset(tv, 0, sizeof(*tv));
- if (tveeprom_read(&c, eedata, sizeof(eedata)))
+
+ c = kzalloc(sizeof(*c), GFP_KERNEL);
+ if (!c)
return;
+ strlcpy(c->name, "cx18 tveeprom tmp", sizeof(c->name));
+ c->adapter = &cx->i2c_adap[0];
+ c->addr = 0xa0 >> 1;
+
+ if (tveeprom_read(c, eedata, sizeof(eedata)))
+ goto ret;
+
switch (cx->card->type) {
case CX18_CARD_HVR_1600_ESMT:
case CX18_CARD_HVR_1600_SAMSUNG:
case CX18_CARD_HVR_1600_S5H1411:
- tveeprom_hauppauge_analog(&c, tv, eedata);
+ tveeprom_hauppauge_analog(c, tv, eedata);
break;
case CX18_CARD_YUAN_MPC718:
case CX18_CARD_GOTVIEW_PCI_DVD3:
@@ -354,6 +358,9 @@
cx18_eeprom_dump(cx, eedata, sizeof(eedata));
break;
}
+
+ret:
+ kfree(c);
}
static void cx18_process_eeprom(struct cx18 *cx)
@@ -1085,6 +1092,7 @@
setup.addr = ADDR_UNSET;
setup.type = cx->options.tuner;
setup.mode_mask = T_ANALOG_TV; /* matches TV tuners */
+ setup.config = NULL;
if (cx->options.radio > 0)
setup.mode_mask |= T_RADIO;
setup.tuner_callback = (setup.type == TUNER_XC2028) ?
diff --git a/drivers/media/pci/cx23885/cimax2.c b/drivers/media/pci/cx23885/cimax2.c
index 7344849..16fa7ea 100644
--- a/drivers/media/pci/cx23885/cimax2.c
+++ b/drivers/media/pci/cx23885/cimax2.c
@@ -26,6 +26,10 @@
#include "cx23885.h"
#include "cimax2.h"
#include "dvb_ca_en50221.h"
+
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/**** Bit definitions for MC417_RWD and MC417_OEN registers ***
bits 31-16
+-----------+
@@ -125,7 +129,7 @@
u8 *buf, int len)
{
int ret;
- u8 buffer[len + 1];
+ u8 buffer[MAX_XFER_SIZE];
struct i2c_msg msg = {
.addr = addr,
@@ -134,6 +138,13 @@
.len = len + 1
};
+ if (1 + len > sizeof(buffer)) {
+ printk(KERN_WARNING
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buffer[0] = reg;
memcpy(&buffer[1], buf, len);
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 9c5ed10..bb291c6 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1249,6 +1249,10 @@
fe0->dvb.frontend = dvb_attach(ds3000_attach,
&tevii_ds3000_config,
&i2c_bus->i2c_adap);
+ if (fe0->dvb.frontend != NULL) {
+ dvb_attach(ts2020_attach, fe0->dvb.frontend,
+ &tevii_ts2020_config, &i2c_bus->i2c_adap);
+ }
break;
case CX23885_BOARD_PROF_8000:
i2c_bus = &dev->i2c_bus[0];
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index e1863db..7a9b98b 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -159,6 +159,12 @@
/* Instruct the CX2341[56] to start sending packets */
snd_ivtv_lock(itvsc);
+
+ if (ivtv_init_on_first_open(itv)) {
+ snd_ivtv_unlock(itvsc);
+ return -ENXIO;
+ }
+
s = &itv->streams[IVTV_ENC_STREAM_TYPE_PCM];
v4l2_fh_init(&item.fh, s->vdev);
diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c
index 10460fd..dbcdfbf8 100644
--- a/drivers/media/pci/saa7134/saa7134-alsa.c
+++ b/drivers/media/pci/saa7134/saa7134-alsa.c
@@ -172,7 +172,9 @@
dprintk("irq: overrun [full=%d/%d] - Blocks in %d\n",dev->dmasound.read_count,
dev->dmasound.bufsize, dev->dmasound.blocks);
spin_unlock(&dev->slock);
+ snd_pcm_stream_lock(dev->dmasound.substream);
snd_pcm_stop(dev->dmasound.substream,SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(dev->dmasound.substream);
return;
}
diff --git a/drivers/media/pci/saa7134/saa7134-cards.c b/drivers/media/pci/saa7134/saa7134-cards.c
index d45e7f6..e87a734 100644
--- a/drivers/media/pci/saa7134/saa7134-cards.c
+++ b/drivers/media/pci/saa7134/saa7134-cards.c
@@ -8045,8 +8045,8 @@
break;
} /* switch() */
- /* initialize tuner */
- if (TUNER_ABSENT != dev->tuner_type) {
+ /* initialize tuner (don't do this when resuming) */
+ if (!dev->insuspend && TUNER_ABSENT != dev->tuner_type) {
int has_demod = (dev->tda9887_conf & TDA9887_PRESENT);
/* Note: radio tuner address is always filled in,
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index 7618fdae..62141b8 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1348,9 +1348,11 @@
if (fw_debug) {
dev->kthread = kthread_run(saa7164_thread_function, dev,
"saa7164 debug");
- if (!dev->kthread)
+ if (IS_ERR(dev->kthread)) {
+ dev->kthread = NULL;
printk(KERN_ERR "%s() Failed to create "
"debug kernel thread\n", __func__);
+ }
}
} /* != BOARD_UNKNOWN */
diff --git a/drivers/media/pci/ttpci/av7110_hw.c b/drivers/media/pci/ttpci/av7110_hw.c
index f1cbfe5..6299d5d 100644
--- a/drivers/media/pci/ttpci/av7110_hw.c
+++ b/drivers/media/pci/ttpci/av7110_hw.c
@@ -22,7 +22,7 @@
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
* Or, point your browser to http://www.gnu.org/copyleft/gpl.html
*
- * the project's page is at http://www.linuxtv.org/
+ * the project's page is at http://www.linuxtv.org/
*/
/* for debugging ARM communication: */
@@ -40,6 +40,14 @@
#define _NOHANDSHAKE
+/*
+ * Max transfer size done by av7110_fw_cmd()
+ *
+ * The maximum size passed to this function is 6 bytes. The buffer also
+ * uses two additional ones for type and size. So, 8 bytes is enough.
+ */
+#define MAX_XFER_SIZE 8
+
/****************************************************************************
* DEBI functions
****************************************************************************/
@@ -488,11 +496,18 @@
int av7110_fw_cmd(struct av7110 *av7110, int type, int com, int num, ...)
{
va_list args;
- u16 buf[num + 2];
+ u16 buf[MAX_XFER_SIZE];
int i, ret;
// dprintk(4, "%p\n", av7110);
+ if (2 + num > sizeof(buf)) {
+ printk(KERN_WARNING
+ "%s: %s len=%d is too big!\n",
+ KBUILD_MODNAME, __func__, num);
+ return -EINVAL;
+ }
+
buf[0] = ((type << 8) | com);
buf[1] = num;
diff --git a/drivers/media/platform/coda.c b/drivers/media/platform/coda.c
index 9d1481a..c504f70 100644
--- a/drivers/media/platform/coda.c
+++ b/drivers/media/platform/coda.c
@@ -1933,7 +1933,7 @@
#ifdef CONFIG_OF
static const struct of_device_id coda_dt_ids[] = {
- { .compatible = "fsl,imx27-vpu", .data = &coda_platform_ids[CODA_IMX27] },
+ { .compatible = "fsl,imx27-vpu", .data = &coda_devdata[CODA_IMX27] },
{ .compatible = "fsl,imx53-vpu", .data = &coda_devdata[CODA_IMX53] },
{ /* sentinel */ }
};
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.c b/drivers/media/platform/exynos-gsc/gsc-core.c
index 33b5ffc..f45b940 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.c
+++ b/drivers/media/platform/exynos-gsc/gsc-core.c
@@ -1122,10 +1122,14 @@
goto err_clk;
}
- ret = gsc_register_m2m_device(gsc);
+ ret = v4l2_device_register(dev, &gsc->v4l2_dev);
if (ret)
goto err_clk;
+ ret = gsc_register_m2m_device(gsc);
+ if (ret)
+ goto err_v4l2;
+
platform_set_drvdata(pdev, gsc);
pm_runtime_enable(dev);
ret = pm_runtime_get_sync(&pdev->dev);
@@ -1147,6 +1151,8 @@
pm_runtime_put(dev);
err_m2m:
gsc_unregister_m2m_device(gsc);
+err_v4l2:
+ v4l2_device_unregister(&gsc->v4l2_dev);
err_clk:
gsc_clk_put(gsc);
return ret;
@@ -1157,6 +1163,7 @@
struct gsc_dev *gsc = platform_get_drvdata(pdev);
gsc_unregister_m2m_device(gsc);
+ v4l2_device_unregister(&gsc->v4l2_dev);
vb2_dma_contig_cleanup_ctx(gsc->alloc_ctx);
pm_runtime_disable(&pdev->dev);
diff --git a/drivers/media/platform/exynos-gsc/gsc-core.h b/drivers/media/platform/exynos-gsc/gsc-core.h
index cc19bba..76435d3 100644
--- a/drivers/media/platform/exynos-gsc/gsc-core.h
+++ b/drivers/media/platform/exynos-gsc/gsc-core.h
@@ -343,6 +343,7 @@
unsigned long state;
struct vb2_alloc_ctx *alloc_ctx;
struct video_device vdev;
+ struct v4l2_device v4l2_dev;
};
/**
diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index 40a73f7..e576ff2 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -751,6 +751,7 @@
gsc->vdev.release = video_device_release_empty;
gsc->vdev.lock = &gsc->lock;
gsc->vdev.vfl_dir = VFL_DIR_M2M;
+ gsc->vdev.v4l2_dev = &gsc->v4l2_dev;
snprintf(gsc->vdev.name, sizeof(gsc->vdev.name), "%s.%d:m2m",
GSC_MODULE_NAME, gsc->id);
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 15ef8f2..b5b480b 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1441,9 +1441,9 @@
err_unlock:
mutex_unlock(&fmd->media_dev.graph_mutex);
err_clk:
- media_device_unregister(&fmd->media_dev);
fimc_md_put_clocks(fmd);
fimc_md_unregister_entities(fmd);
+ media_device_unregister(&fmd->media_dev);
err_md:
v4l2_device_unregister(&fmd->v4l2_dev);
return ret;
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 1d7dbd5..3e8ef11 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -2249,6 +2249,7 @@
ret = iommu_attach_device(isp->domain, &pdev->dev);
if (ret) {
dev_err(&pdev->dev, "can't attach iommu device: %d\n", ret);
+ ret = -EPROBE_DEFER;
goto free_domain;
}
@@ -2287,6 +2288,7 @@
iommu_detach_device(isp->domain, &pdev->dev);
free_domain:
iommu_domain_free(isp->domain);
+ isp->domain = NULL;
error_isp:
isp_xclk_cleanup(isp);
omap3isp_put(isp);
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index cd8831a..e2e4610 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1079,6 +1079,7 @@
*/
static void preview_config_input_size(struct isp_prev_device *prev, u32 active)
{
+ const struct v4l2_mbus_framefmt *format = &prev->formats[PREV_PAD_SINK];
struct isp_device *isp = to_isp_device(prev);
unsigned int sph = prev->crop.left;
unsigned int eph = prev->crop.left + prev->crop.width - 1;
@@ -1086,6 +1087,14 @@
unsigned int elv = prev->crop.top + prev->crop.height - 1;
u32 features;
+ if (format->code != V4L2_MBUS_FMT_Y8_1X8 &&
+ format->code != V4L2_MBUS_FMT_Y10_1X10) {
+ sph -= 2;
+ eph += 2;
+ slv -= 2;
+ elv += 2;
+ }
+
features = (prev->params.params[0].features & active)
| (prev->params.params[1].features & ~active);
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 553d87e..fd6289d 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -784,6 +784,7 @@
}
*vfd = g2d_videodev;
vfd->lock = &dev->mutex;
+ vfd->v4l2_dev = &dev->v4l2_dev;
ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
if (ret) {
v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index d12faa6..961d7ff 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -177,21 +177,6 @@
mutex_unlock(&dev->mfc_mutex);
}
-static enum s5p_mfc_node_type s5p_mfc_get_node_type(struct file *file)
-{
- struct video_device *vdev = video_devdata(file);
-
- if (!vdev) {
- mfc_err("failed to get video_device");
- return MFCNODE_INVALID;
- }
- if (vdev->index == 0)
- return MFCNODE_DECODER;
- else if (vdev->index == 1)
- return MFCNODE_ENCODER;
- return MFCNODE_INVALID;
-}
-
static void s5p_mfc_clear_int_flags(struct s5p_mfc_dev *dev)
{
mfc_write(dev, 0, S5P_FIMV_RISC_HOST_INT);
@@ -701,6 +686,7 @@
/* Open an MFC node */
static int s5p_mfc_open(struct file *file)
{
+ struct video_device *vdev = video_devdata(file);
struct s5p_mfc_dev *dev = video_drvdata(file);
struct s5p_mfc_ctx *ctx = NULL;
struct vb2_queue *q;
@@ -738,7 +724,7 @@
/* Mark context as idle */
clear_work_bit_irqsave(ctx);
dev->ctx[ctx->num] = ctx;
- if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+ if (vdev == dev->vfd_dec) {
ctx->type = MFCINST_DECODER;
ctx->c_ops = get_dec_codec_ops();
s5p_mfc_dec_init(ctx);
@@ -748,7 +734,7 @@
mfc_err("Failed to setup mfc controls\n");
goto err_ctrls_setup;
}
- } else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+ } else if (vdev == dev->vfd_enc) {
ctx->type = MFCINST_ENCODER;
ctx->c_ops = get_enc_codec_ops();
/* only for encoder */
@@ -793,10 +779,10 @@
q = &ctx->vq_dst;
q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
q->drv_priv = &ctx->fh;
- if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+ if (vdev == dev->vfd_dec) {
q->io_modes = VB2_MMAP;
q->ops = get_dec_queue_ops();
- } else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+ } else if (vdev == dev->vfd_enc) {
q->io_modes = VB2_MMAP | VB2_USERPTR;
q->ops = get_enc_queue_ops();
} else {
@@ -815,10 +801,10 @@
q->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
q->io_modes = VB2_MMAP;
q->drv_priv = &ctx->fh;
- if (s5p_mfc_get_node_type(file) == MFCNODE_DECODER) {
+ if (vdev == dev->vfd_dec) {
q->io_modes = VB2_MMAP;
q->ops = get_dec_queue_ops();
- } else if (s5p_mfc_get_node_type(file) == MFCNODE_ENCODER) {
+ } else if (vdev == dev->vfd_enc) {
q->io_modes = VB2_MMAP | VB2_USERPTR;
q->ops = get_enc_queue_ops();
} else {
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
index ef4074c..d3b54f7 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_common.h
@@ -29,7 +29,7 @@
/* Offset base used to differentiate between CAPTURE and OUTPUT
* while mmaping */
-#define DST_QUEUE_OFF_BASE (TASK_SIZE / 2)
+#define DST_QUEUE_OFF_BASE (1 << 30)
#define MFC_BANK1_ALLOC_CTX 0
#define MFC_BANK2_ALLOC_CTX 1
@@ -113,15 +113,6 @@
};
/**
- * enum s5p_mfc_node_type - The type of an MFC device node.
- */
-enum s5p_mfc_node_type {
- MFCNODE_INVALID = -1,
- MFCNODE_DECODER = 0,
- MFCNODE_ENCODER = 1,
-};
-
-/**
* enum s5p_mfc_inst_type - The type of an MFC instance.
*/
enum s5p_mfc_inst_type {
diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 7d02350..5d538e7 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -776,7 +776,7 @@
v4l_bound_align_image(&pix->width, 0, VOU_MAX_IMAGE_WIDTH, 1,
&pix->height, 0, VOU_MAX_IMAGE_HEIGHT, 1, 0);
- for (i = 0; ARRAY_SIZE(vou_fmt); i++)
+ for (i = 0; i < ARRAY_SIZE(vou_fmt); i++)
if (vou_fmt[i].pfmt == pix->pixelformat)
return 0;
diff --git a/drivers/media/rc/ir-lirc-codec.c b/drivers/media/rc/ir-lirc-codec.c
index e456126..a895ed0 100644
--- a/drivers/media/rc/ir-lirc-codec.c
+++ b/drivers/media/rc/ir-lirc-codec.c
@@ -42,11 +42,17 @@
return -EINVAL;
/* Packet start */
- if (ev.reset)
- return 0;
+ if (ev.reset) {
+ /* Userspace expects a long space event before the start of
+ * the signal to use as a sync. This may be done with repeat
+ * packets and normal samples. But if a reset has been sent
+ * then we assume that a long time has passed, so we send a
+ * space with the maximum time value. */
+ sample = LIRC_SPACE(LIRC_VALUE_MASK);
+ IR_dprintk(2, "delivering reset sync space to lirc_dev\n");
/* Carrier reports */
- if (ev.carrier_report) {
+ } else if (ev.carrier_report) {
sample = LIRC_FREQUENCY(ev.carrier);
IR_dprintk(2, "carrier report (freq: %d)\n", sample);
diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c
index 1b33ed3..c4ce450 100644
--- a/drivers/media/tuners/e4000.c
+++ b/drivers/media/tuners/e4000.c
@@ -20,20 +20,30 @@
#include "e4000_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/* write multiple registers */
static int e4000_wr_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
{
int ret;
- u8 buf[1 + len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg->i2c_addr,
.flags = 0,
- .len = sizeof(buf),
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
@@ -52,7 +62,7 @@
static int e4000_rd_regs(struct e4000_priv *priv, u8 reg, u8 *val, int len)
{
int ret;
- u8 buf[len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[2] = {
{
.addr = priv->cfg->i2c_addr,
@@ -62,11 +72,18 @@
}, {
.addr = priv->cfg->i2c_addr,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = len,
.buf = buf,
}
};
+ if (len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c rd reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, buf, len);
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 81f38aa..f0c9c42 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -20,6 +20,9 @@
#include "fc2580_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/*
* TODO:
* I2C write and read works only for one single register. Multiple registers
@@ -41,16 +44,23 @@
static int fc2580_wr_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
{
int ret;
- u8 buf[1 + len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg->i2c_addr,
.flags = 0,
- .len = sizeof(buf),
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
@@ -69,7 +79,7 @@
static int fc2580_rd_regs(struct fc2580_priv *priv, u8 reg, u8 *val, int len)
{
int ret;
- u8 buf[len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[2] = {
{
.addr = priv->cfg->i2c_addr,
@@ -79,11 +89,18 @@
}, {
.addr = priv->cfg->i2c_addr,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = len,
.buf = buf,
}
};
+ if (len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c rd reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, buf, len);
@@ -178,7 +195,7 @@
f_ref = 2UL * priv->cfg->clock / r_val;
n_val = div_u64_rem(f_vco, f_ref, &k_val);
- k_val_reg = 1UL * k_val * (1 << 20) / f_ref;
+ k_val_reg = div_u64(1ULL * k_val * (1 << 20), f_ref);
ret = fc2580_wr_reg(priv, 0x18, r18_val | ((k_val_reg >> 16) & 0xff));
if (ret < 0)
@@ -331,8 +348,8 @@
if (ret < 0)
goto err;
- ret = fc2580_wr_reg(priv, 0x37, 1UL * priv->cfg->clock * \
- fc2580_if_filter_lut[i].mul / 1000000000);
+ ret = fc2580_wr_reg(priv, 0x37, div_u64(1ULL * priv->cfg->clock *
+ fc2580_if_filter_lut[i].mul, 1000000000));
if (ret < 0)
goto err;
diff --git a/drivers/media/tuners/fc2580_priv.h b/drivers/media/tuners/fc2580_priv.h
index be38a9e..646c994 100644
--- a/drivers/media/tuners/fc2580_priv.h
+++ b/drivers/media/tuners/fc2580_priv.h
@@ -22,6 +22,7 @@
#define FC2580_PRIV_H
#include "fc2580.h"
+#include <linux/math64.h>
struct fc2580_reg_val {
u8 reg;
diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c
index e4a84ee..abe256e 100644
--- a/drivers/media/tuners/tda18212.c
+++ b/drivers/media/tuners/tda18212.c
@@ -20,6 +20,9 @@
#include "tda18212.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct tda18212_priv {
struct tda18212_config *cfg;
struct i2c_adapter *i2c;
@@ -32,16 +35,23 @@
int len)
{
int ret;
- u8 buf[len+1];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg->i2c_address,
.flags = 0,
- .len = sizeof(buf),
+ .len = 1 + len,
.buf = buf,
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
buf[0] = reg;
memcpy(&buf[1], val, len);
@@ -61,7 +71,7 @@
int len)
{
int ret;
- u8 buf[len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[2] = {
{
.addr = priv->cfg->i2c_address,
@@ -71,11 +81,18 @@
}, {
.addr = priv->cfg->i2c_address,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = len,
.buf = buf,
}
};
+ if (len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c rd reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, buf, len);
diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c
index 2d31aeb..9300e93 100644
--- a/drivers/media/tuners/tda18218.c
+++ b/drivers/media/tuners/tda18218.c
@@ -20,11 +20,14 @@
#include "tda18218_priv.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/* write multiple registers */
static int tda18218_wr_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
{
int ret = 0, len2, remaining;
- u8 buf[1 + len];
+ u8 buf[MAX_XFER_SIZE];
struct i2c_msg msg[1] = {
{
.addr = priv->cfg->i2c_address,
@@ -33,6 +36,13 @@
}
};
+ if (1 + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
for (remaining = len; remaining > 0;
remaining -= (priv->cfg->i2c_wr_max - 1)) {
len2 = remaining;
@@ -63,7 +73,7 @@
static int tda18218_rd_regs(struct tda18218_priv *priv, u8 reg, u8 *val, u8 len)
{
int ret;
- u8 buf[reg+len]; /* we must start read always from reg 0x00 */
+ u8 buf[MAX_XFER_SIZE]; /* we must start read always from reg 0x00 */
struct i2c_msg msg[2] = {
{
.addr = priv->cfg->i2c_address,
@@ -73,11 +83,18 @@
}, {
.addr = priv->cfg->i2c_address,
.flags = I2C_M_RD,
- .len = sizeof(buf),
+ .len = reg + len,
.buf = buf,
}
};
+ if (reg + len > sizeof(buf)) {
+ dev_warn(&priv->i2c->dev,
+ "%s: i2c wr reg=%04x: len=%d is too big!\n",
+ KBUILD_MODNAME, reg, len);
+ return -EINVAL;
+ }
+
ret = i2c_transfer(priv->i2c, msg, 2);
if (ret == 2) {
memcpy(val, &buf[reg], len);
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 878d2c4..9771cd8 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -24,6 +24,9 @@
#include <linux/dvb/frontend.h>
#include "dvb_frontend.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 80
+
/* Registers (Write-only) */
#define XREG_INIT 0x00
#define XREG_RF_FREQ 0x02
@@ -547,7 +550,10 @@
{
struct xc2028_data *priv = fe->tuner_priv;
int pos, rc;
- unsigned char *p, *endp, buf[priv->ctrl.max_len];
+ unsigned char *p, *endp, buf[MAX_XFER_SIZE];
+
+ if (priv->ctrl.max_len > sizeof(buf))
+ priv->ctrl.max_len = sizeof(buf);
tuner_dbg("%s called\n", __func__);
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 2018bef..e71decb 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -93,7 +93,7 @@
struct firmware_description *firm;
int firm_size;
u32 if_khz;
- u32 freq_hz;
+ u32 freq_hz, freq_offset;
u32 bandwidth;
u8 video_standard;
u8 rf_mode;
@@ -1157,14 +1157,14 @@
case SYS_ATSC:
dprintk(1, "%s() VSB modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_AIR;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = XC4000_DTV6;
type = DTV6;
break;
case SYS_DVBC_ANNEX_B:
dprintk(1, "%s() QAM modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_CABLE;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = XC4000_DTV6;
type = DTV6;
break;
@@ -1173,23 +1173,23 @@
dprintk(1, "%s() OFDM\n", __func__);
if (bw == 0) {
if (c->frequency < 400000000) {
- priv->freq_hz = c->frequency - 2250000;
+ priv->freq_offset = 2250000;
} else {
- priv->freq_hz = c->frequency - 2750000;
+ priv->freq_offset = 2750000;
}
priv->video_standard = XC4000_DTV7_8;
type = DTV78;
} else if (bw <= 6000000) {
priv->video_standard = XC4000_DTV6;
- priv->freq_hz = c->frequency - 1750000;
+ priv->freq_offset = 1750000;
type = DTV6;
} else if (bw <= 7000000) {
priv->video_standard = XC4000_DTV7;
- priv->freq_hz = c->frequency - 2250000;
+ priv->freq_offset = 2250000;
type = DTV7;
} else {
priv->video_standard = XC4000_DTV8;
- priv->freq_hz = c->frequency - 2750000;
+ priv->freq_offset = 2750000;
type = DTV8;
}
priv->rf_mode = XC_RF_MODE_AIR;
@@ -1200,6 +1200,8 @@
goto fail;
}
+ priv->freq_hz = c->frequency - priv->freq_offset;
+
dprintk(1, "%s() frequency=%d (compensated)\n",
__func__, priv->freq_hz);
@@ -1520,7 +1522,7 @@
{
struct xc4000_priv *priv = fe->tuner_priv;
- *freq = priv->freq_hz;
+ *freq = priv->freq_hz + priv->freq_offset;
if (debug) {
mutex_lock(&priv->lock);
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index 5cd09a6..b2d9e9c 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -55,7 +55,7 @@
u32 if_khz;
u16 xtal_khz;
- u32 freq_hz;
+ u32 freq_hz, freq_offset;
u32 bandwidth;
u8 video_standard;
u8 rf_mode;
@@ -755,13 +755,13 @@
case SYS_ATSC:
dprintk(1, "%s() VSB modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_AIR;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = DTV6;
break;
case SYS_DVBC_ANNEX_B:
dprintk(1, "%s() QAM modulation\n", __func__);
priv->rf_mode = XC_RF_MODE_CABLE;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
priv->video_standard = DTV6;
break;
case SYS_ISDBT:
@@ -776,15 +776,15 @@
switch (bw) {
case 6000000:
priv->video_standard = DTV6;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
break;
case 7000000:
priv->video_standard = DTV7;
- priv->freq_hz = freq - 2250000;
+ priv->freq_offset = 2250000;
break;
case 8000000:
priv->video_standard = DTV8;
- priv->freq_hz = freq - 2750000;
+ priv->freq_offset = 2750000;
break;
default:
printk(KERN_ERR "xc5000 bandwidth not set!\n");
@@ -798,15 +798,15 @@
priv->rf_mode = XC_RF_MODE_CABLE;
if (bw <= 6000000) {
priv->video_standard = DTV6;
- priv->freq_hz = freq - 1750000;
+ priv->freq_offset = 1750000;
b = 6;
} else if (bw <= 7000000) {
priv->video_standard = DTV7;
- priv->freq_hz = freq - 2250000;
+ priv->freq_offset = 2250000;
b = 7;
} else {
priv->video_standard = DTV7_8;
- priv->freq_hz = freq - 2750000;
+ priv->freq_offset = 2750000;
b = 8;
}
dprintk(1, "%s() Bandwidth %dMHz (%d)\n", __func__,
@@ -817,6 +817,8 @@
return -EINVAL;
}
+ priv->freq_hz = freq - priv->freq_offset;
+
dprintk(1, "%s() frequency=%d (compensated to %d)\n",
__func__, freq, priv->freq_hz);
@@ -1067,7 +1069,7 @@
{
struct xc5000_priv *priv = fe->tuner_priv;
dprintk(1, "%s()\n", __func__);
- *freq = priv->freq_hz;
+ *freq = priv->freq_hz + priv->freq_offset;
return 0;
}
diff --git a/drivers/media/usb/Kconfig b/drivers/media/usb/Kconfig
index 0a7d520..7cac453 100644
--- a/drivers/media/usb/Kconfig
+++ b/drivers/media/usb/Kconfig
@@ -1,6 +1,7 @@
+if USB && MEDIA_SUPPORT
+
menuconfig MEDIA_USB_SUPPORT
bool "Media USB Adapters"
- depends on USB && MEDIA_SUPPORT
help
Enable media drivers for USB bus.
If you have such devices, say Y.
@@ -52,3 +53,4 @@
endif
endif #MEDIA_USB_SUPPORT
+endif #USB
diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 75ac994..98e1b93 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -788,11 +788,27 @@
/*
* Auvitek au0828 analog stream enable
- * Please set interface0 to AS5 before enable the stream
*/
static int au0828_analog_stream_enable(struct au0828_dev *d)
{
+ struct usb_interface *iface;
+ int ret;
+
dprintk(1, "au0828_analog_stream_enable called\n");
+
+ iface = usb_ifnum_to_if(d->usbdev, 0);
+ if (iface && iface->cur_altsetting->desc.bAlternateSetting != 5) {
+ dprintk(1, "Changing intf#0 to alt 5\n");
+ /* set au0828 interface0 to AS5 here again */
+ ret = usb_set_interface(d->usbdev, 0, 5);
+ if (ret < 0) {
+ printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
+ return -EBUSY;
+ }
+ }
+
+ /* FIXME: size should be calculated using d->width, d->height */
+
au0828_writereg(d, AU0828_SENSORCTRL_VBI_103, 0x00);
au0828_writereg(d, 0x106, 0x00);
/* set x position */
@@ -1003,15 +1019,6 @@
return -ERESTARTSYS;
}
if (dev->users == 0) {
- /* set au0828 interface0 to AS5 here again */
- ret = usb_set_interface(dev->usbdev, 0, 5);
- if (ret < 0) {
- mutex_unlock(&dev->lock);
- printk(KERN_INFO "Au0828 can't set alternate to 5!\n");
- kfree(fh);
- return -EBUSY;
- }
-
au0828_analog_stream_enable(dev);
au0828_analog_stream_reset(dev);
@@ -1253,13 +1260,6 @@
}
}
- /* set au0828 interface0 to AS5 here again */
- ret = usb_set_interface(dev->usbdev, 0, 5);
- if (ret < 0) {
- printk(KERN_INFO "Au0828 can't set alt setting to 5!\n");
- return -EBUSY;
- }
-
au0828_analog_stream_enable(dev);
return 0;
diff --git a/drivers/media/usb/dvb-usb-v2/af9015.c b/drivers/media/usb/dvb-usb-v2/af9015.c
index d556042..da47d23 100644
--- a/drivers/media/usb/dvb-usb-v2/af9015.c
+++ b/drivers/media/usb/dvb-usb-v2/af9015.c
@@ -397,12 +397,13 @@
return ret;
}
+#define AF9015_EEPROM_SIZE 256
+
/* hash (and dump) eeprom */
static int af9015_eeprom_hash(struct dvb_usb_device *d)
{
struct af9015_state *state = d_to_priv(d);
int ret, i;
- static const unsigned int AF9015_EEPROM_SIZE = 256;
u8 buf[AF9015_EEPROM_SIZE];
struct req_t req = {READ_I2C, AF9015_I2C_EEPROM, 0, 0, 1, 1, NULL};
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index b638fc1..2e93ba5 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -21,6 +21,9 @@
#include "af9035.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
static u16 af9035_checksum(const u8 *buf, size_t len)
@@ -125,9 +128,15 @@
/* write multiple registers */
static int af9035_wr_regs(struct dvb_usb_device *d, u32 reg, u8 *val, int len)
{
- u8 wbuf[6 + len];
+ u8 wbuf[MAX_XFER_SIZE];
u8 mbox = (reg >> 16) & 0xff;
- struct usb_req req = { CMD_MEM_WR, mbox, sizeof(wbuf), wbuf, 0, NULL };
+ struct usb_req req = { CMD_MEM_WR, mbox, 6 + len, wbuf, 0, NULL };
+
+ if (6 + len > sizeof(wbuf)) {
+ dev_warn(&d->udev->dev, "%s: i2c wr: len=%d is too big!\n",
+ KBUILD_MODNAME, len);
+ return -EOPNOTSUPP;
+ }
wbuf[0] = len;
wbuf[1] = 2;
@@ -227,9 +236,17 @@
msg[1].len);
} else {
/* I2C */
- u8 buf[5 + msg[0].len];
- struct usb_req req = { CMD_I2C_RD, 0, sizeof(buf),
+ u8 buf[MAX_XFER_SIZE];
+ struct usb_req req = { CMD_I2C_RD, 0, 5 + msg[0].len,
buf, msg[1].len, msg[1].buf };
+
+ if (5 + msg[0].len > sizeof(buf)) {
+ dev_warn(&d->udev->dev,
+ "%s: i2c xfer: len=%d is too big!\n",
+ KBUILD_MODNAME, msg[0].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
req.mbox |= ((msg[0].addr & 0x80) >> 3);
buf[0] = msg[1].len;
buf[1] = msg[0].addr << 1;
@@ -256,9 +273,17 @@
msg[0].len - 3);
} else {
/* I2C */
- u8 buf[5 + msg[0].len];
- struct usb_req req = { CMD_I2C_WR, 0, sizeof(buf), buf,
- 0, NULL };
+ u8 buf[MAX_XFER_SIZE];
+ struct usb_req req = { CMD_I2C_WR, 0, 5 + msg[0].len,
+ buf, 0, NULL };
+
+ if (5 + msg[0].len > sizeof(buf)) {
+ dev_warn(&d->udev->dev,
+ "%s: i2c xfer: len=%d is too big!\n",
+ KBUILD_MODNAME, msg[0].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
req.mbox |= ((msg[0].addr & 0x80) >> 3);
buf[0] = msg[0].len;
buf[1] = msg[0].addr << 1;
@@ -277,6 +302,7 @@
ret = -EOPNOTSUPP;
}
+unlock:
mutex_unlock(&d->i2c_mutex);
if (ret < 0)
@@ -1489,6 +1515,10 @@
/* XXX: that same ID [0ccd:0099] is used by af9015 driver too */
{ DVB_USB_DEVICE(USB_VID_TERRATEC, 0x0099,
&af9035_props, "TerraTec Cinergy T Stick Dual RC (rev. 2)", NULL) },
+ { DVB_USB_DEVICE(USB_VID_LEADTEK, 0x6a05,
+ &af9035_props, "Leadtek WinFast DTV Dongle Dual", NULL) },
+ { DVB_USB_DEVICE(USB_VID_HAUPPAUGE, 0xf900,
+ &af9035_props, "Hauppauge WinTV-MiniStick 2", NULL) },
{ }
};
MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index 90cfa35..eeab79b 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -442,6 +442,7 @@
* IOD[0] ZL10353 1=enabled
* IOE[0] tuner 0=enabled
* tuner is behind ZL10353 I2C-gate
+ * tuner is behind TDA10023 I2C-gate
*
* E7 TC VID=1c73 PID=861f HW=18 FW=0.7 AMTCI=0.5 "anysee-E7TC(LP)"
* PCB: 508TC (rev0.6)
@@ -956,7 +957,7 @@
if (fe && adap->fe[1]) {
/* attach tuner for 2nd FE */
- fe = dvb_attach(dvb_pll_attach, adap->fe[0],
+ fe = dvb_attach(dvb_pll_attach, adap->fe[1],
(0xc0 >> 1), &d->i2c_adap,
DVB_PLL_SAMSUNG_DTOS403IH102A);
}
diff --git a/drivers/media/usb/dvb-usb-v2/lmedm04.c b/drivers/media/usb/dvb-usb-v2/lmedm04.c
index b3fd0ff..fc28d51 100644
--- a/drivers/media/usb/dvb-usb-v2/lmedm04.c
+++ b/drivers/media/usb/dvb-usb-v2/lmedm04.c
@@ -350,6 +350,7 @@
{
struct dvb_usb_device *d = adap_to_d(adap);
struct lme2510_state *lme_int = adap_to_priv(adap);
+ struct usb_host_endpoint *ep;
lme_int->lme_urb = usb_alloc_urb(0, GFP_ATOMIC);
@@ -371,6 +372,12 @@
adap,
8);
+ /* Quirk of pipe reporting PIPE_BULK but behaves as interrupt */
+ ep = usb_pipe_endpoint(d->udev, lme_int->lme_urb->pipe);
+
+ if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK)
+ lme_int->lme_urb->pipe = usb_rcvbulkpipe(d->udev, 0xa),
+
lme_int->lme_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
usb_submit_urb(lme_int->lme_urb, GFP_ATOMIC);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
index 90f583e..a8f65d8 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
@@ -68,7 +68,7 @@
#else
static inline
struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
- struct mxl111sf_state *mxl_state
+ struct mxl111sf_state *mxl_state,
struct mxl111sf_tuner_config *cfg)
{
printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index efdcb15..419a7c7 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -23,6 +23,9 @@
#include "lgdt3305.h"
#include "lg2160.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
int dvb_usb_mxl111sf_debug;
module_param_named(debug, dvb_usb_mxl111sf_debug, int, 0644);
MODULE_PARM_DESC(debug, "set debugging level "
@@ -63,7 +66,12 @@
{
int wo = (rbuf == NULL || rlen == 0); /* write-only */
int ret;
- u8 sndbuf[1+wlen];
+ u8 sndbuf[MAX_XFER_SIZE];
+
+ if (1 + wlen > sizeof(sndbuf)) {
+ pr_warn("%s: len=%d is too big!\n", __func__, wlen);
+ return -EOPNOTSUPP;
+ }
deb_adv("%s(wlen = %d, rlen = %d)\n", __func__, wlen, rlen);
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index af176b6..e6d3561 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -1081,9 +1081,12 @@
err("usb_register failed. (%d)", result);
return result;
}
+#if IS_MODULE(CONFIG_DVB_USB_AF9005) || defined(CONFIG_DVB_USB_AF9005_REMOTE)
+ /* FIXME: convert to todays kernel IR infrastructure */
rc_decode = symbol_request(af9005_rc_decode);
rc_keys = symbol_request(rc_map_af9005_table);
rc_keys_size = symbol_request(rc_map_af9005_table_size);
+#endif
if (rc_decode == NULL || rc_keys == NULL || rc_keys_size == NULL) {
err("af9005_rc_decode function not found, disabling remote");
af9005_properties.rc.legacy.rc_query = NULL;
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index 3940bb0..a1c641e 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -43,6 +43,9 @@
#include "lgs8gxx.h"
#include "atbm8830.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
/* debug */
static int dvb_usb_cxusb_debug;
module_param_named(debug, dvb_usb_cxusb_debug, int, 0644);
@@ -57,7 +60,14 @@
u8 cmd, u8 *wbuf, int wlen, u8 *rbuf, int rlen)
{
int wo = (rbuf == NULL || rlen == 0); /* write-only */
- u8 sndbuf[1+wlen];
+ u8 sndbuf[MAX_XFER_SIZE];
+
+ if (1 + wlen > sizeof(sndbuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ wlen);
+ return -EOPNOTSUPP;
+ }
+
memset(sndbuf, 0, 1+wlen);
sndbuf[0] = cmd;
@@ -139,6 +149,7 @@
int num)
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
+ int ret;
int i;
if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
@@ -158,7 +169,14 @@
if (msg[i].flags & I2C_M_RD) {
/* read only */
- u8 obuf[3], ibuf[1+msg[i].len];
+ u8 obuf[3], ibuf[MAX_XFER_SIZE];
+
+ if (1 + msg[i].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[i].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = 0;
obuf[1] = msg[i].len;
obuf[2] = msg[i].addr;
@@ -172,7 +190,20 @@
} else if (i+1 < num && (msg[i+1].flags & I2C_M_RD) &&
msg[i].addr == msg[i+1].addr) {
/* write to then read from same address */
- u8 obuf[3+msg[i].len], ibuf[1+msg[i+1].len];
+ u8 obuf[MAX_XFER_SIZE], ibuf[MAX_XFER_SIZE];
+
+ if (3 + msg[i].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[i].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+ if (1 + msg[i + 1].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[i + 1].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = msg[i].len;
obuf[1] = msg[i+1].len;
obuf[2] = msg[i].addr;
@@ -191,7 +222,14 @@
i++;
} else {
/* write only */
- u8 obuf[2+msg[i].len], ibuf;
+ u8 obuf[MAX_XFER_SIZE], ibuf;
+
+ if (2 + msg[i].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[i].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = msg[i].addr;
obuf[1] = msg[i].len;
memcpy(&obuf[2], msg[i].buf, msg[i].len);
@@ -204,8 +242,14 @@
}
}
+ if (i == num)
+ ret = num;
+ else
+ ret = -EREMOTEIO;
+
+unlock:
mutex_unlock(&d->i2c_mutex);
- return i == num ? num : -EREMOTEIO;
+ return ret;
}
static u32 cxusb_i2c_func(struct i2c_adapter *adapter)
diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c
index c2dded9..6d68af0 100644
--- a/drivers/media/usb/dvb-usb/dibusb-common.c
+++ b/drivers/media/usb/dvb-usb/dibusb-common.c
@@ -12,6 +12,9 @@
#include <linux/kconfig.h>
#include "dibusb.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
static int debug;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "set debugging level (1=info (|-able))." DVB_USB_DEBUG_STATUS);
@@ -105,11 +108,16 @@
static int dibusb_i2c_msg(struct dvb_usb_device *d, u8 addr,
u8 *wbuf, u16 wlen, u8 *rbuf, u16 rlen)
{
- u8 sndbuf[wlen+4]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
+ u8 sndbuf[MAX_XFER_SIZE]; /* lead(1) devaddr,direction(1) addr(2) data(wlen) (len(2) (when reading)) */
/* write only ? */
int wo = (rbuf == NULL || rlen == 0),
len = 2 + wlen + (wo ? 0 : 2);
+ if (4 + wlen > sizeof(sndbuf)) {
+ warn("i2c wr: len=%d is too big!\n", wlen);
+ return -EOPNOTSUPP;
+ }
+
sndbuf[0] = wo ? DIBUSB_REQ_I2C_WRITE : DIBUSB_REQ_I2C_READ;
sndbuf[1] = (addr << 1) | (wo ? 0 : 1);
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 6e237b6..4170a45 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -30,6 +30,9 @@
#include "stb6100_proc.h"
#include "m88rs2000.h"
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
#ifndef USB_PID_DW2102
#define USB_PID_DW2102 0x2102
#endif
@@ -298,6 +301,7 @@
static int dw2102_earda_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], int num)
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
+ int ret;
if (!d)
return -ENODEV;
@@ -308,7 +312,15 @@
case 2: {
/* read */
/* first write first register number */
- u8 ibuf[msg[1].len + 2], obuf[3];
+ u8 ibuf[MAX_XFER_SIZE], obuf[3];
+
+ if (2 + msg[1].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[1].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
obuf[0] = msg[0].addr << 1;
obuf[1] = msg[0].len;
obuf[2] = msg[0].buf[0];
@@ -325,7 +337,15 @@
switch (msg[0].addr) {
case 0x68: {
/* write to register */
- u8 obuf[msg[0].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[0].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[1].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
obuf[0] = msg[0].addr << 1;
obuf[1] = msg[0].len;
memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -335,7 +355,15 @@
}
case 0x61: {
/* write to tuner */
- u8 obuf[msg[0].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[0].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[1].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
obuf[0] = msg[0].addr << 1;
obuf[1] = msg[0].len;
memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -362,15 +390,17 @@
break;
}
+ ret = num;
+unlock:
mutex_unlock(&d->i2c_mutex);
- return num;
+ return ret;
}
static int dw2104_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[], int num)
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
- int len, i, j;
+ int len, i, j, ret;
if (!d)
return -ENODEV;
@@ -401,7 +431,15 @@
default: {
if (msg[j].flags == I2C_M_RD) {
/* read registers */
- u8 ibuf[msg[j].len + 2];
+ u8 ibuf[MAX_XFER_SIZE];
+
+ if (2 + msg[j].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[j].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
dw210x_op_rw(d->udev, 0xc3,
(msg[j].addr << 1) + 1, 0,
ibuf, msg[j].len + 2,
@@ -430,7 +468,15 @@
} while (len > 0);
} else {
/* write registers */
- u8 obuf[msg[j].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[j].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[j].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
obuf[0] = msg[j].addr << 1;
obuf[1] = msg[j].len;
memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -443,15 +489,18 @@
}
}
+ ret = num;
+unlock:
mutex_unlock(&d->i2c_mutex);
- return num;
+ return ret;
}
static int dw3101_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
int num)
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
+ int ret;
int i;
if (!d)
@@ -463,7 +512,14 @@
case 2: {
/* read */
/* first write first register number */
- u8 ibuf[msg[1].len + 2], obuf[3];
+ u8 ibuf[MAX_XFER_SIZE], obuf[3];
+
+ if (2 + msg[1].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[1].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = msg[0].addr << 1;
obuf[1] = msg[0].len;
obuf[2] = msg[0].buf[0];
@@ -481,7 +537,14 @@
case 0x60:
case 0x0c: {
/* write to register */
- u8 obuf[msg[0].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[0].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[0].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = msg[0].addr << 1;
obuf[1] = msg[0].len;
memcpy(obuf + 2, msg[0].buf, msg[0].len);
@@ -506,9 +569,11 @@
msg[i].flags == 0 ? ">>>" : "<<<");
debug_dump(msg[i].buf, msg[i].len, deb_xfer);
}
+ ret = num;
+unlock:
mutex_unlock(&d->i2c_mutex);
- return num;
+ return ret;
}
static int s6x0_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
@@ -516,7 +581,7 @@
{
struct dvb_usb_device *d = i2c_get_adapdata(adap);
struct usb_device *udev;
- int len, i, j;
+ int len, i, j, ret;
if (!d)
return -ENODEV;
@@ -563,7 +628,15 @@
default: {
if (msg[j].flags == I2C_M_RD) {
/* read registers */
- u8 ibuf[msg[j].len];
+ u8 ibuf[MAX_XFER_SIZE];
+
+ if (msg[j].len > sizeof(ibuf)) {
+ warn("i2c rd: len=%d is too big!\n",
+ msg[j].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
dw210x_op_rw(d->udev, 0x91, 0, 0,
ibuf, msg[j].len,
DW210X_READ_MSG);
@@ -590,7 +663,15 @@
} while (len > 0);
} else if (j < (num - 1)) {
/* write register addr before read */
- u8 obuf[msg[j].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[j].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[j].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
+
obuf[0] = msg[j + 1].len;
obuf[1] = (msg[j].addr << 1);
memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -602,7 +683,14 @@
break;
} else {
/* write registers */
- u8 obuf[msg[j].len + 2];
+ u8 obuf[MAX_XFER_SIZE];
+
+ if (2 + msg[j].len > sizeof(obuf)) {
+ warn("i2c wr: len=%d is too big!\n",
+ msg[j].len);
+ ret = -EOPNOTSUPP;
+ goto unlock;
+ }
obuf[0] = msg[j].len + 1;
obuf[1] = (msg[j].addr << 1);
memcpy(obuf + 2, msg[j].buf, msg[j].len);
@@ -615,9 +703,11 @@
}
}
}
+ ret = num;
+unlock:
mutex_unlock(&d->i2c_mutex);
- return num;
+ return ret;
}
static int su3000_i2c_transfer(struct i2c_adapter *adap, struct i2c_msg msg[],
diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index b22f8fe..c4d6696 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -673,7 +673,8 @@
static int em28xx_pctv_290e_set_lna(struct dvb_frontend *fe)
{
struct dtv_frontend_properties *c = &fe->dtv_property_cache;
- struct em28xx *dev = fe->dvb->priv;
+ struct em28xx_i2c_bus *i2c_bus = fe->dvb->priv;
+ struct em28xx *dev = i2c_bus->dev;
#ifdef CONFIG_GPIOLIB
struct em28xx_dvb *dvb = dev->dvb;
int ret;
diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 4851cc2..c4ff973 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -726,7 +726,7 @@
*eedata = data;
*eedata_len = len;
- dev_config = (void *)eedata;
+ dev_config = (void *)*eedata;
switch (le16_to_cpu(dev_config->chip_conf) >> 4 & 0x3) {
case 0:
diff --git a/drivers/media/usb/em28xx/em28xx-video.c b/drivers/media/usb/em28xx/em28xx-video.c
index 32d60e5..a2737b4 100644
--- a/drivers/media/usb/em28xx/em28xx-video.c
+++ b/drivers/media/usb/em28xx/em28xx-video.c
@@ -696,13 +696,16 @@
}
spin_lock_irqsave(&dev->slock, flags);
+ if (dev->usb_ctl.vid_buf != NULL) {
+ vb2_buffer_done(&dev->usb_ctl.vid_buf->vb, VB2_BUF_STATE_ERROR);
+ dev->usb_ctl.vid_buf = NULL;
+ }
while (!list_empty(&vidq->active)) {
struct em28xx_buffer *buf;
buf = list_entry(vidq->active.next, struct em28xx_buffer, list);
list_del(&buf->list);
vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
}
- dev->usb_ctl.vid_buf = NULL;
spin_unlock_irqrestore(&dev->slock, flags);
return 0;
@@ -724,13 +727,16 @@
}
spin_lock_irqsave(&dev->slock, flags);
+ if (dev->usb_ctl.vbi_buf != NULL) {
+ vb2_buffer_done(&dev->usb_ctl.vbi_buf->vb, VB2_BUF_STATE_ERROR);
+ dev->usb_ctl.vbi_buf = NULL;
+ }
while (!list_empty(&vbiq->active)) {
struct em28xx_buffer *buf;
buf = list_entry(vbiq->active.next, struct em28xx_buffer, list);
list_del(&buf->list);
vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
}
- dev->usb_ctl.vbi_buf = NULL;
spin_unlock_irqrestore(&dev->slock, flags);
return 0;
diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c
index 6008c8d..20d9c15 100644
--- a/drivers/media/usb/gspca/pac7302.c
+++ b/drivers/media/usb/gspca/pac7302.c
@@ -945,6 +945,7 @@
{USB_DEVICE(0x093a, 0x2620)},
{USB_DEVICE(0x093a, 0x2621)},
{USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP},
+ {USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP},
{USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP},
{USB_DEVICE(0x093a, 0x2625)},
{USB_DEVICE(0x093a, 0x2626)},
diff --git a/drivers/media/usb/gspca/sn9c20x.c b/drivers/media/usb/gspca/sn9c20x.c
index ead9a1f..8b59e5d 100644
--- a/drivers/media/usb/gspca/sn9c20x.c
+++ b/drivers/media/usb/gspca/sn9c20x.c
@@ -2394,6 +2394,7 @@
{USB_DEVICE(0x045e, 0x00f4), SN9C20X(OV9650, 0x30, 0)},
{USB_DEVICE(0x145f, 0x013d), SN9C20X(OV7660, 0x21, 0)},
{USB_DEVICE(0x0458, 0x7029), SN9C20X(HV7131R, 0x11, 0)},
+ {USB_DEVICE(0x0458, 0x7045), SN9C20X(MT9M112, 0x5d, LED_REVERSE)},
{USB_DEVICE(0x0458, 0x704a), SN9C20X(MT9M112, 0x5d, 0)},
{USB_DEVICE(0x0458, 0x704c), SN9C20X(MT9M112, 0x5d, 0)},
{USB_DEVICE(0xa168, 0x0610), SN9C20X(HV7131R, 0x11, 0)},
diff --git a/drivers/media/usb/hdpvr/hdpvr-core.c b/drivers/media/usb/hdpvr/hdpvr-core.c
index 8247c19..77d7b7f 100644
--- a/drivers/media/usb/hdpvr/hdpvr-core.c
+++ b/drivers/media/usb/hdpvr/hdpvr-core.c
@@ -311,6 +311,11 @@
dev->workqueue = 0;
+ /* init video transfer queues first of all */
+ /* to prevent oops in hdpvr_delete() on error paths */
+ INIT_LIST_HEAD(&dev->free_buff_list);
+ INIT_LIST_HEAD(&dev->rec_buff_list);
+
/* register v4l2_device early so it can be used for printks */
if (v4l2_device_register(&interface->dev, &dev->v4l2_dev)) {
dev_err(&interface->dev, "v4l2_device_register failed\n");
@@ -333,10 +338,6 @@
if (!dev->workqueue)
goto error;
- /* init video transfer queues */
- INIT_LIST_HEAD(&dev->free_buff_list);
- INIT_LIST_HEAD(&dev->rec_buff_list);
-
dev->options = hdpvr_default_options;
if (default_video_input < HDPVR_VIDEO_INPUTS)
@@ -413,7 +414,7 @@
video_nr[atomic_inc_return(&dev_nr)]);
if (retval < 0) {
v4l2_err(&dev->v4l2_dev, "registering videodev failed\n");
- goto error;
+ goto reg_fail;
}
/* let the user know what node this device is now attached to */
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 774ba0e..eed70a4 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -81,7 +81,7 @@
}
/*=========================================================================*/
-/* bufffer bits */
+/* buffer bits */
/* function expects dev->io_mutex to be hold by caller */
int hdpvr_cancel_queue(struct hdpvr_device *dev)
@@ -921,7 +921,7 @@
case V4L2_CID_MPEG_AUDIO_ENCODING:
if (dev->flags & HDPVR_FLAG_AC3_CAP) {
opt->audio_codec = ctrl->val;
- return hdpvr_set_audio(dev, opt->audio_input,
+ return hdpvr_set_audio(dev, opt->audio_input + 1,
opt->audio_codec);
}
return 0;
@@ -1191,7 +1191,7 @@
v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
V4L2_CID_MPEG_AUDIO_ENCODING,
ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC,
- 0x7, V4L2_MPEG_AUDIO_ENCODING_AAC);
+ 0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC);
v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
V4L2_CID_MPEG_VIDEO_ENCODING,
V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3,
diff --git a/drivers/media/usb/stk1160/stk1160-core.c b/drivers/media/usb/stk1160/stk1160-core.c
index 34a26e0..03504dc 100644
--- a/drivers/media/usb/stk1160/stk1160-core.c
+++ b/drivers/media/usb/stk1160/stk1160-core.c
@@ -67,17 +67,25 @@
{
int ret;
int pipe = usb_rcvctrlpipe(dev->udev, 0);
+ u8 *buf;
*value = 0;
+
+ buf = kmalloc(sizeof(u8), GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
ret = usb_control_msg(dev->udev, pipe, 0x00,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x00, reg, value, sizeof(u8), HZ);
+ 0x00, reg, buf, sizeof(u8), HZ);
if (ret < 0) {
stk1160_err("read failed on reg 0x%x (%d)\n",
reg, ret);
+ kfree(buf);
return ret;
}
+ *value = *buf;
+ kfree(buf);
return 0;
}
diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index a59153d2..518a529 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -245,6 +245,11 @@
if (mutex_lock_interruptible(&dev->v4l_lock))
return -ERESTARTSYS;
+ /*
+ * Once URBs are cancelled, the URB complete handler
+ * won't be running. This is required to safely release the
+ * current buffer (dev->isoc_ctl.buf).
+ */
stk1160_cancel_isoc(dev);
/*
@@ -665,8 +670,16 @@
stk1160_info("buffer [%p/%d] aborted\n",
buf, buf->vb.v4l2_buf.index);
}
- /* It's important to clear current buffer */
- dev->isoc_ctl.buf = NULL;
+
+ /* It's important to release the current buffer */
+ if (dev->isoc_ctl.buf) {
+ buf = dev->isoc_ctl.buf;
+ dev->isoc_ctl.buf = NULL;
+
+ vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
+ stk1160_info("buffer [%p/%d] aborted\n",
+ buf, buf->vb.v4l2_buf.index);
+ }
spin_unlock_irqrestore(&dev->buf_lock, flags);
}
diff --git a/drivers/media/usb/stk1160/stk1160.h b/drivers/media/usb/stk1160/stk1160.h
index 05b05b1..abdea48 100644
--- a/drivers/media/usb/stk1160/stk1160.h
+++ b/drivers/media/usb/stk1160/stk1160.h
@@ -143,7 +143,6 @@
int num_alt;
struct stk1160_isoc_ctl isoc_ctl;
- char urb_buf[255]; /* urb control msg buffer */
/* frame properties */
int width; /* current frame width */
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 5c45c9d..9c29552 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -156,6 +156,9 @@
0x00, 0x00, 0x00, 0x00,
0x00, 0x00 };
+ if (cmd->msg_len > sizeof(b) - 4)
+ return -EINVAL;
+
memcpy(&b[4], cmd->msg, cmd->msg_len);
state->config->send_command(fe, 0x72,
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 5dbefa6..363cdbf 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -1603,12 +1603,12 @@
{
struct list_head *p, *n;
- usb_put_intf(dev->intf);
- usb_put_dev(dev->udev);
-
uvc_status_cleanup(dev);
uvc_ctrl_cleanup_device(dev);
+ usb_put_intf(dev->intf);
+ usb_put_dev(dev->udev);
+
if (dev->vdev.dev)
v4l2_device_unregister(&dev->vdev);
#ifdef CONFIG_MEDIA_CONTROLLER
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 3394c34..c081812 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -361,6 +361,14 @@
* Clocks and timestamps
*/
+static inline void uvc_video_get_ts(struct timespec *ts)
+{
+ if (uvc_clock_param == CLOCK_MONOTONIC)
+ ktime_get_ts(ts);
+ else
+ ktime_get_real_ts(ts);
+}
+
static void
uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
const __u8 *data, int len)
@@ -420,7 +428,7 @@
stream->clock.last_sof = dev_sof;
host_sof = usb_get_current_frame_number(stream->dev->udev);
- ktime_get_ts(&ts);
+ uvc_video_get_ts(&ts);
/* The UVC specification allows device implementations that can't obtain
* the USB frame number to keep their own frame counters as long as they
@@ -1010,10 +1018,7 @@
return -ENODATA;
}
- if (uvc_clock_param == CLOCK_MONOTONIC)
- ktime_get_ts(&ts);
- else
- ktime_get_real_ts(&ts);
+ uvc_video_get_ts(&ts);
buf->buf.v4l2_buf.sequence = stream->sequence;
buf->buf.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
@@ -1846,7 +1851,25 @@
if (!enable) {
uvc_uninit_video(stream, 1);
- usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+ if (stream->intf->num_altsetting > 1) {
+ usb_set_interface(stream->dev->udev,
+ stream->intfnum, 0);
+ } else {
+ /* UVC doesn't specify how to inform a bulk-based device
+ * when the video stream is stopped. Windows sends a
+ * CLEAR_FEATURE(HALT) request to the video streaming
+ * bulk endpoint, mimic the same behaviour.
+ */
+ unsigned int epnum = stream->header.bEndpointAddress
+ & USB_ENDPOINT_NUMBER_MASK;
+ unsigned int dir = stream->header.bEndpointAddress
+ & USB_ENDPOINT_DIR_MASK;
+ unsigned int pipe;
+
+ pipe = usb_sndbulkpipe(stream->dev->udev, epnum) | dir;
+ usb_clear_halt(stream->dev->udev, pipe);
+ }
+
uvc_queue_enable(&stream->queue, 0);
uvc_video_clock_cleanup(stream);
return 0;
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 3fed63f..ec9a4fa 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -485,16 +485,13 @@
/* Bits that must be zero to be aligned */
unsigned int mask = ~((1 << align) - 1);
+ /* Clamp to aligned min and max */
+ x = clamp(x, (min + ~mask) & mask, max & mask);
+
/* Round to nearest aligned value */
if (align)
x = (x + (1 << (align - 1))) & mask;
- /* Clamp to aligned value of min and max */
- if (x < min)
- x = (min + ~mask) & mask;
- else if (x > max)
- x = max & mask;
-
return x;
}
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index f129551..e2b0a09 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -178,6 +178,9 @@
static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
{
+ if (get_user(kp->type, &up->type))
+ return -EFAULT;
+
switch (kp->type) {
case V4L2_BUF_TYPE_VIDEO_CAPTURE:
case V4L2_BUF_TYPE_VIDEO_OUTPUT:
@@ -204,17 +207,16 @@
static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
{
- if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)) ||
- get_user(kp->type, &up->type))
- return -EFAULT;
+ if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)))
+ return -EFAULT;
return __get_v4l2_format32(kp, up);
}
static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
{
if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) ||
- copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format.fmt)))
- return -EFAULT;
+ copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format)))
+ return -EFAULT;
return __get_v4l2_format32(&kp->format, &up->format);
}
@@ -787,8 +789,8 @@
#define VIDIOC_DQBUF32 _IOWR('V', 17, struct v4l2_buffer32)
#define VIDIOC_ENUMSTD32 _IOWR('V', 25, struct v4l2_standard32)
#define VIDIOC_ENUMINPUT32 _IOWR('V', 26, struct v4l2_input32)
-#define VIDIOC_SUBDEV_G_EDID32 _IOWR('V', 63, struct v4l2_subdev_edid32)
-#define VIDIOC_SUBDEV_S_EDID32 _IOWR('V', 64, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_G_EDID32 _IOWR('V', 40, struct v4l2_subdev_edid32)
+#define VIDIOC_SUBDEV_S_EDID32 _IOWR('V', 41, struct v4l2_subdev_edid32)
#define VIDIOC_TRY_FMT32 _IOWR('V', 64, struct v4l2_format32)
#define VIDIOC_G_EXT_CTRLS32 _IOWR('V', 71, struct v4l2_ext_controls32)
#define VIDIOC_S_EXT_CTRLS32 _IOWR('V', 72, struct v4l2_ext_controls32)
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index e3bdc3b..5e47ba4 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -666,6 +666,7 @@
* to the userspace.
*/
req->count = allocated_buffers;
+ q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
return 0;
}
@@ -714,6 +715,7 @@
memset(q->plane_sizes, 0, sizeof(q->plane_sizes));
memset(q->alloc_ctx, 0, sizeof(q->alloc_ctx));
q->memory = create->memory;
+ q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
}
num_buffers = min(create->count, VIDEO_MAX_FRAME - q->num_buffers);
@@ -1355,6 +1357,7 @@
* dequeued in dqbuf.
*/
list_add_tail(&vb->queued_entry, &q->queued_list);
+ q->waiting_for_buffers = false;
vb->state = VB2_BUF_STATE_QUEUED;
/*
@@ -1724,6 +1727,7 @@
* and videobuf, effectively returning control over them to userspace.
*/
__vb2_queue_cancel(q);
+ q->waiting_for_buffers = !V4L2_TYPE_IS_OUTPUT(q->type);
dprintk(3, "Streamoff successful\n");
return 0;
@@ -2009,9 +2013,16 @@
}
/*
- * There is nothing to wait for if no buffers have already been queued.
+ * There is nothing to wait for if the queue isn't streaming.
*/
- if (list_empty(&q->queued_list))
+ if (!vb2_is_streaming(q))
+ return res | POLLERR;
+ /*
+ * For compatibility with vb1: if QBUF hasn't been called yet, then
+ * return POLLERR as well. This only affects capture queues, output
+ * queues will always initialize waiting_for_buffers to false.
+ */
+ if (q->waiting_for_buffers)
return res | POLLERR;
if (list_empty(&q->done_list))
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index f4176ca..cdd61ab 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -758,7 +758,7 @@
if (error || (card->current_mrq.tpc == MSPRO_CMD_STOP)) {
if (msb->data_dir == READ) {
- for (cnt = 0; cnt < msb->current_seg; cnt++)
+ for (cnt = 0; cnt < msb->current_seg; cnt++) {
t_len += msb->req_sg[cnt].length
/ msb->page_size;
@@ -766,6 +766,7 @@
t_len += msb->current_page - 1;
t_len *= msb->page_size;
+ }
}
} else
t_len = blk_rq_bytes(msb->block_req);
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 5653e50..424f51d 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -1422,6 +1422,11 @@
goto out_mptspi_probe;
}
+ /* VMWare emulation doesn't properly implement WRITE_SAME
+ */
+ if (pdev->subsystem_vendor == 0x15AD)
+ sh->no_write_same = 1;
+
spin_lock_irqsave(&ioc->FreeQlock, flags);
/* Attach the SCSI Host to the IOC structure
diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index 31ca555..30cf7ee 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -1179,12 +1179,18 @@
chip->companion_addr = pdata->companion_addr;
chip->companion = i2c_new_dummy(chip->client->adapter,
chip->companion_addr);
+ if (!chip->companion) {
+ dev_err(&client->dev,
+ "Failed to allocate I2C companion device\n");
+ return -ENODEV;
+ }
chip->regmap_companion = regmap_init_i2c(chip->companion,
&pm860x_regmap_config);
if (IS_ERR(chip->regmap_companion)) {
ret = PTR_ERR(chip->regmap_companion);
dev_err(&chip->companion->dev,
"Failed to allocate register map: %d\n", ret);
+ i2c_unregister_device(chip->companion);
return ret;
}
i2c_set_clientdata(chip->companion, chip);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d54e985..a5e54f0 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1144,7 +1144,15 @@
endmenu
config VEXPRESS_CONFIG
- bool
+ bool "ARM Versatile Express platform infrastructure"
+ depends on ARM || ARM64
help
Platform configuration infrastructure for the ARM Ltd.
Versatile Express.
+
+config VEXPRESS_SPC
+ bool "Versatile Express SPC driver support"
+ depends on ARM
+ depends on VEXPRESS_CONFIG
+ help
+ Serial Power Controller driver for ARM Ltd. test chips.
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 718e94a..3a01203 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -153,5 +153,6 @@
obj-$(CONFIG_MFD_SYSCON) += syscon.o
obj-$(CONFIG_MFD_LM3533) += lm3533-core.o lm3533-ctrlbank.o
obj-$(CONFIG_VEXPRESS_CONFIG) += vexpress-config.o vexpress-sysreg.o
+obj-$(CONFIG_VEXPRESS_SPC) += vexpress-spc.o
obj-$(CONFIG_MFD_RETU) += retu-mfd.o
obj-$(CONFIG_MFD_AS3711) += as3711.o
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 9f12f91..4be5be3 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -51,6 +51,8 @@
* document number TBD : Lynx Point
* document number TBD : Lynx Point-LP
* document number TBD : Wellsburg
+ * document number TBD : Avoton SoC
+ * document number TBD : Coleto Creek
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -207,6 +209,8 @@
LPC_LPT, /* Lynx Point */
LPC_LPT_LP, /* Lynx Point-LP */
LPC_WBG, /* Wellsburg */
+ LPC_AVN, /* Avoton SoC */
+ LPC_COLETO, /* Coleto Creek */
};
struct lpc_ich_info lpc_chipset_info[] = {
@@ -491,6 +495,14 @@
.name = "Wellsburg",
.iTCO_version = 2,
},
+ [LPC_AVN] = {
+ .name = "Avoton SoC",
+ .iTCO_version = 1,
+ },
+ [LPC_COLETO] = {
+ .name = "Coleto Creek",
+ .iTCO_version = 2,
+ },
};
/*
@@ -704,6 +716,11 @@
{ PCI_VDEVICE(INTEL, 0x8d5d), LPC_WBG},
{ PCI_VDEVICE(INTEL, 0x8d5e), LPC_WBG},
{ PCI_VDEVICE(INTEL, 0x8d5f), LPC_WBG},
+ { PCI_VDEVICE(INTEL, 0x1f38), LPC_AVN},
+ { PCI_VDEVICE(INTEL, 0x1f39), LPC_AVN},
+ { PCI_VDEVICE(INTEL, 0x1f3a), LPC_AVN},
+ { PCI_VDEVICE(INTEL, 0x1f3b), LPC_AVN},
+ { PCI_VDEVICE(INTEL, 0x2390), LPC_COLETO},
{ 0, }, /* End of list */
};
MODULE_DEVICE_TABLE(pci, lpc_ich_ids);
diff --git a/drivers/mfd/max77686.c b/drivers/mfd/max77686.c
index 1cbb176..1b6f45a 100644
--- a/drivers/mfd/max77686.c
+++ b/drivers/mfd/max77686.c
@@ -102,7 +102,7 @@
max77686->irq_gpio = pdata->irq_gpio;
max77686->irq = i2c->irq;
- max77686->regmap = regmap_init_i2c(i2c, &max77686_regmap_config);
+ max77686->regmap = devm_regmap_init_i2c(i2c, &max77686_regmap_config);
if (IS_ERR(max77686->regmap)) {
ret = PTR_ERR(max77686->regmap);
dev_err(max77686->dev, "Failed to allocate register map: %d\n",
@@ -121,6 +121,10 @@
dev_info(max77686->dev, "device found\n");
max77686->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+ if (!max77686->rtc) {
+ dev_err(max77686->dev, "Failed to allocate I2C device for RTC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(max77686->rtc, max77686);
max77686_irq_init(max77686);
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
index 9e60fed..299970f 100644
--- a/drivers/mfd/max77693.c
+++ b/drivers/mfd/max77693.c
@@ -149,9 +149,18 @@
dev_info(max77693->dev, "device ID: 0x%x\n", reg_data);
max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+ if (!max77693->muic) {
+ dev_err(max77693->dev, "Failed to allocate I2C device for MUIC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(max77693->muic, max77693);
max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+ if (!max77693->haptic) {
+ dev_err(max77693->dev, "Failed to allocate I2C device for Haptic\n");
+ ret = -ENODEV;
+ goto err_i2c_haptic;
+ }
i2c_set_clientdata(max77693->haptic, max77693);
/*
@@ -187,8 +196,9 @@
max77693_irq_exit(max77693);
err_irq:
err_regmap_muic:
- i2c_unregister_device(max77693->muic);
i2c_unregister_device(max77693->haptic);
+err_i2c_haptic:
+ i2c_unregister_device(max77693->muic);
return ret;
}
diff --git a/drivers/mfd/max8925-i2c.c b/drivers/mfd/max8925-i2c.c
index 92bbebd..c94d333 100644
--- a/drivers/mfd/max8925-i2c.c
+++ b/drivers/mfd/max8925-i2c.c
@@ -180,9 +180,18 @@
mutex_init(&chip->io_lock);
chip->rtc = i2c_new_dummy(chip->i2c->adapter, RTC_I2C_ADDR);
+ if (!chip->rtc) {
+ dev_err(chip->dev, "Failed to allocate I2C device for RTC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(chip->rtc, chip);
chip->adc = i2c_new_dummy(chip->i2c->adapter, ADC_I2C_ADDR);
+ if (!chip->adc) {
+ dev_err(chip->dev, "Failed to allocate I2C device for ADC\n");
+ i2c_unregister_device(chip->rtc);
+ return -ENODEV;
+ }
i2c_set_clientdata(chip->adc, chip);
device_init_wakeup(&client->dev, 1);
diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c
index 1471405..ea1defbc 100644
--- a/drivers/mfd/max8997.c
+++ b/drivers/mfd/max8997.c
@@ -218,10 +218,26 @@
mutex_init(&max8997->iolock);
max8997->rtc = i2c_new_dummy(i2c->adapter, I2C_ADDR_RTC);
+ if (!max8997->rtc) {
+ dev_err(max8997->dev, "Failed to allocate I2C device for RTC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(max8997->rtc, max8997);
+
max8997->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+ if (!max8997->haptic) {
+ dev_err(max8997->dev, "Failed to allocate I2C device for Haptic\n");
+ ret = -ENODEV;
+ goto err_i2c_haptic;
+ }
i2c_set_clientdata(max8997->haptic, max8997);
+
max8997->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+ if (!max8997->muic) {
+ dev_err(max8997->dev, "Failed to allocate I2C device for MUIC\n");
+ ret = -ENODEV;
+ goto err_i2c_muic;
+ }
i2c_set_clientdata(max8997->muic, max8997);
pm_runtime_set_active(max8997->dev);
@@ -248,7 +264,9 @@
err_mfd:
mfd_remove_devices(max8997->dev);
i2c_unregister_device(max8997->muic);
+err_i2c_muic:
i2c_unregister_device(max8997->haptic);
+err_i2c_haptic:
i2c_unregister_device(max8997->rtc);
err:
kfree(max8997);
diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c
index d7218cc..8381a76 100644
--- a/drivers/mfd/max8998.c
+++ b/drivers/mfd/max8998.c
@@ -152,6 +152,10 @@
mutex_init(&max8998->iolock);
max8998->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+ if (!max8998->rtc) {
+ dev_err(&i2c->dev, "Failed to allocate I2C device for RTC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(max8998->rtc, max8998);
max8998_irq_init(max8998);
diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c
index 759fae3..a36f3f2 100644
--- a/drivers/mfd/omap-usb-host.c
+++ b/drivers/mfd/omap-usb-host.c
@@ -445,7 +445,7 @@
for (i = 0; i < omap->nports; i++) {
if (is_ehci_phy_mode(pdata->port_mode[i])) {
- reg &= OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
+ reg &= ~OMAP_UHH_HOSTCONFIG_ULPI_BYPASS;
break;
}
}
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index e968c01..7e28bd0d 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1137,7 +1137,7 @@
pcr->msi_en = msi_en;
if (pcr->msi_en) {
ret = pci_enable_msi(pcidev);
- if (ret < 0)
+ if (ret)
pcr->msi_en = false;
}
@@ -1195,8 +1195,14 @@
pcr->remove_pci = true;
- cancel_delayed_work(&pcr->carddet_work);
- cancel_delayed_work(&pcr->idle_work);
+ /* Disable interrupts at the pcr level */
+ spin_lock_irq(&pcr->lock);
+ rtsx_pci_writel(pcr, RTSX_BIER, 0);
+ pcr->bier = 0;
+ spin_unlock_irq(&pcr->lock);
+
+ cancel_delayed_work_sync(&pcr->carddet_work);
+ cancel_delayed_work_sync(&pcr->idle_work);
mfd_remove_devices(&pcidev->dev);
diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 77ee26ef..81cfe88 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -199,6 +199,10 @@
}
sec_pmic->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
+ if (!sec_pmic->rtc) {
+ dev_err(&i2c->dev, "Failed to allocate I2C for RTC\n");
+ return -ENODEV;
+ }
i2c_set_clientdata(sec_pmic->rtc, sec_pmic);
if (pdata && pdata->cfg_pmic_irq)
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 15e1463..17fe83e 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -263,6 +263,17 @@
return 0;
}
+static int tc6393xb_ohci_suspend(struct platform_device *dev)
+{
+ struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
+
+ /* We can't properly store/restore OHCI state, so fail here */
+ if (tcpd->resume_restore)
+ return -EBUSY;
+
+ return tc6393xb_ohci_disable(dev);
+}
+
static int tc6393xb_fb_enable(struct platform_device *dev)
{
struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -403,7 +414,7 @@
.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
.resources = tc6393xb_ohci_resources,
.enable = tc6393xb_ohci_enable,
- .suspend = tc6393xb_ohci_disable,
+ .suspend = tc6393xb_ohci_suspend,
.resume = tc6393xb_ohci_enable,
.disable = tc6393xb_ohci_disable,
},
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index d792772..de87eaf 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -254,8 +254,10 @@
ret = regmap_add_irq_chip(tps65910->regmap, tps65910->chip_irq,
IRQF_ONESHOT, pdata->irq_base,
tps6591x_irqs_chip, &tps65910->irq_data);
- if (ret < 0)
+ if (ret < 0) {
dev_warn(tps65910->dev, "Failed to add irq_chip %d\n", ret);
+ tps65910->chip_irq = 0;
+ }
return ret;
}
diff --git a/drivers/mfd/vexpress-config.c b/drivers/mfd/vexpress-config.c
index 84ce6b9..1af2b0e 100644
--- a/drivers/mfd/vexpress-config.c
+++ b/drivers/mfd/vexpress-config.c
@@ -86,29 +86,13 @@
}
EXPORT_SYMBOL(vexpress_config_bridge_unregister);
-
-struct vexpress_config_func {
- struct vexpress_config_bridge *bridge;
- void *func;
-};
-
-struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
- struct device_node *node)
+static struct vexpress_config_bridge *
+ vexpress_config_bridge_find(struct device_node *node)
{
- struct device_node *bridge_node;
- struct vexpress_config_func *func;
int i;
+ struct vexpress_config_bridge *res = NULL;
+ struct device_node *bridge_node = of_node_get(node);
- if (WARN_ON(dev && node && dev->of_node != node))
- return NULL;
- if (dev && !node)
- node = dev->of_node;
-
- func = kzalloc(sizeof(*func), GFP_KERNEL);
- if (!func)
- return NULL;
-
- bridge_node = of_node_get(node);
while (bridge_node) {
const __be32 *prop = of_get_property(bridge_node,
"arm,vexpress,config-bridge", NULL);
@@ -129,13 +113,46 @@
if (test_bit(i, vexpress_config_bridges_map) &&
bridge->node == bridge_node) {
- func->bridge = bridge;
- func->func = bridge->info->func_get(dev, node);
+ res = bridge;
break;
}
}
mutex_unlock(&vexpress_config_bridges_mutex);
+ return res;
+}
+
+
+struct vexpress_config_func {
+ struct vexpress_config_bridge *bridge;
+ void *func;
+};
+
+struct vexpress_config_func *__vexpress_config_func_get(
+ struct vexpress_config_bridge *bridge,
+ struct device *dev,
+ struct device_node *node,
+ const char *id)
+{
+ struct vexpress_config_func *func;
+
+ if (WARN_ON(dev && node && dev->of_node != node))
+ return NULL;
+ if (dev && !node)
+ node = dev->of_node;
+
+ if (!bridge)
+ bridge = vexpress_config_bridge_find(node);
+ if (!bridge)
+ return NULL;
+
+ func = kzalloc(sizeof(*func), GFP_KERNEL);
+ if (!func)
+ return NULL;
+
+ func->bridge = bridge;
+ func->func = bridge->info->func_get(dev, node, id);
+
if (!func->func) {
of_node_put(node);
kfree(func);
diff --git a/drivers/mfd/vexpress-spc.c b/drivers/mfd/vexpress-spc.c
new file mode 100644
index 0000000..0c6718a
--- /dev/null
+++ b/drivers/mfd/vexpress-spc.c
@@ -0,0 +1,633 @@
+/*
+ * Versatile Express Serial Power Controller (SPC) support
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * Authors: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+ * Achin Gupta <achin.gupta@arm.com>
+ * Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/vexpress.h>
+
+#include <asm/cacheflush.h>
+
+#define SCC_CFGREG19 0x120
+#define SCC_CFGREG20 0x124
+#define A15_CONF 0x400
+#define A7_CONF 0x500
+#define SYS_INFO 0x700
+#define PERF_LVL_A15 0xB00
+#define PERF_REQ_A15 0xB04
+#define PERF_LVL_A7 0xB08
+#define PERF_REQ_A7 0xB0c
+#define SYS_CFGCTRL 0xB10
+#define SYS_CFGCTRL_REQ 0xB14
+#define PWC_STATUS 0xB18
+#define PWC_FLAG 0xB1c
+#define WAKE_INT_MASK 0xB24
+#define WAKE_INT_RAW 0xB28
+#define WAKE_INT_STAT 0xB2c
+#define A15_PWRDN_EN 0xB30
+#define A7_PWRDN_EN 0xB34
+#define A7_PWRDNACK 0xB54
+#define A15_BX_ADDR0 0xB68
+#define SYS_CFG_WDATA 0xB70
+#define SYS_CFG_RDATA 0xB74
+#define A7_BX_ADDR0 0xB78
+
+#define GBL_WAKEUP_INT_MSK (0x3 << 10)
+
+#define CLKF_SHIFT 16
+#define CLKF_MASK 0x1FFF
+#define CLKR_SHIFT 0
+#define CLKR_MASK 0x3F
+#define CLKOD_SHIFT 8
+#define CLKOD_MASK 0xF
+
+#define OPP_FUNCTION 6
+#define OPP_BASE_DEVICE 0x300
+#define OPP_A15_OFFSET 0x4
+#define OPP_A7_OFFSET 0xc
+
+#define SYS_CFGCTRL_START (1 << 31)
+#define SYS_CFGCTRL_WRITE (1 << 30)
+#define SYS_CFGCTRL_FUNC(n) (((n) & 0x3f) << 20)
+#define SYS_CFGCTRL_DEVICE(n) (((n) & 0xfff) << 0)
+
+#define MAX_OPPS 8
+#define MAX_CLUSTERS 2
+
+enum {
+ A15_OPP_TYPE = 0,
+ A7_OPP_TYPE = 1,
+ SYS_CFGCTRL_TYPE = 2,
+ INVALID_TYPE
+};
+
+#define STAT_COMPLETE(type) ((1 << 0) << (type << 2))
+#define STAT_ERR(type) ((1 << 1) << (type << 2))
+#define RESPONSE_MASK(type) (STAT_COMPLETE(type) | STAT_ERR(type))
+
+struct vexpress_spc_drvdata {
+ void __iomem *baseaddr;
+ u32 a15_clusid;
+ int irq;
+ u32 cur_req_type;
+ u32 freqs[MAX_CLUSTERS][MAX_OPPS];
+ int freqs_cnt[MAX_CLUSTERS];
+};
+
+enum spc_func_type {
+ CONFIG_FUNC = 0,
+ PERF_FUNC = 1,
+};
+
+struct vexpress_spc_func {
+ enum spc_func_type type;
+ u32 function;
+ u32 device;
+};
+
+static struct vexpress_spc_drvdata *info;
+static u32 *vexpress_spc_config_data;
+static struct vexpress_config_bridge *vexpress_spc_config_bridge;
+static struct vexpress_config_func *opp_func, *perf_func;
+
+static int vexpress_spc_load_result = -EAGAIN;
+
+static bool vexpress_spc_initialized(void)
+{
+ return vexpress_spc_load_result == 0;
+}
+
+/**
+ * vexpress_spc_write_resume_reg() - set the jump address used for warm boot
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @addr: physical resume address
+ */
+void vexpress_spc_write_resume_reg(u32 cluster, u32 cpu, u32 addr)
+{
+ void __iomem *baseaddr;
+
+ if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+ return;
+
+ if (cluster != info->a15_clusid)
+ baseaddr = info->baseaddr + A7_BX_ADDR0 + (cpu << 2);
+ else
+ baseaddr = info->baseaddr + A15_BX_ADDR0 + (cpu << 2);
+
+ writel_relaxed(addr, baseaddr);
+}
+
+/**
+ * vexpress_spc_get_nb_cpus() - get number of cpus in a cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ *
+ * Return: number of cpus in the cluster
+ * -EINVAL if cluster number invalid
+ */
+int vexpress_spc_get_nb_cpus(u32 cluster)
+{
+ u32 val;
+
+ if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+ return -EINVAL;
+
+ val = readl_relaxed(info->baseaddr + SYS_INFO);
+ val = (cluster != info->a15_clusid) ? (val >> 20) : (val >> 16);
+ return val & 0xf;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_nb_cpus);
+
+/**
+ * vexpress_spc_get_performance - get current performance level of cluster
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: pointer to the performance level to be assigned
+ *
+ * Return: 0 on success
+ * < 0 on read error
+ */
+int vexpress_spc_get_performance(u32 cluster, u32 *freq)
+{
+ u32 perf_cfg_reg;
+ int perf, ret;
+
+ if (!vexpress_spc_initialized() || (cluster >= MAX_CLUSTERS))
+ return -EINVAL;
+
+ perf_cfg_reg = cluster != info->a15_clusid ? PERF_LVL_A7 : PERF_LVL_A15;
+ ret = vexpress_config_read(perf_func, perf_cfg_reg, &perf);
+
+ if (!ret)
+ *freq = info->freqs[cluster][perf];
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_performance);
+
+/**
+ * vexpress_spc_get_perf_index - get performance level corresponding to
+ * a frequency
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: frequency to be looked-up
+ *
+ * Return: perf level index on success
+ * -EINVAL on error
+ */
+static int vexpress_spc_find_perf_index(u32 cluster, u32 freq)
+{
+ int idx;
+
+ for (idx = 0; idx < info->freqs_cnt[cluster]; idx++)
+ if (info->freqs[cluster][idx] == freq)
+ break;
+ return (idx == info->freqs_cnt[cluster]) ? -EINVAL : idx;
+}
+
+/**
+ * vexpress_spc_set_performance - set current performance level of cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @freq: performance level to be programmed
+ *
+ * Returns: 0 on success
+ * < 0 on write error
+ */
+int vexpress_spc_set_performance(u32 cluster, u32 freq)
+{
+ int ret, perf, offset;
+
+ if (!vexpress_spc_initialized() || (cluster >= MAX_CLUSTERS))
+ return -EINVAL;
+
+ offset = (cluster != info->a15_clusid) ? PERF_LVL_A7 : PERF_LVL_A15;
+
+ perf = vexpress_spc_find_perf_index(cluster, freq);
+
+ if (perf < 0 || perf >= MAX_OPPS)
+ return -EINVAL;
+
+ ret = vexpress_config_write(perf_func, offset, perf);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_set_performance);
+
+static void vexpress_spc_set_wake_intr(u32 mask)
+{
+ writel_relaxed(mask & VEXPRESS_SPC_WAKE_INTR_MASK,
+ info->baseaddr + WAKE_INT_MASK);
+}
+
+static inline void reg_bitmask(u32 *reg, u32 mask, bool set)
+{
+ if (set)
+ *reg |= mask;
+ else
+ *reg &= ~mask;
+}
+
+/**
+ * vexpress_spc_set_global_wakeup_intr()
+ *
+ * Function to set/clear global wakeup IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @set: if true, global wake-up IRQs are set, if false they are cleared
+ */
+void vexpress_spc_set_global_wakeup_intr(bool set)
+{
+ u32 wake_int_mask_reg = 0;
+
+ wake_int_mask_reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+ reg_bitmask(&wake_int_mask_reg, GBL_WAKEUP_INT_MSK, set);
+ vexpress_spc_set_wake_intr(wake_int_mask_reg);
+}
+
+/**
+ * vexpress_spc_set_cpu_wakeup_irq()
+ *
+ * Function to set/clear per-CPU wake-up IRQs. Not protected by locking since
+ * it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cpu: mpidr[7:0] bitfield describing cpu affinity level
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @set: if true, wake-up IRQs are set, if false they are cleared
+ */
+void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster, bool set)
+{
+ u32 mask = 0;
+ u32 wake_int_mask_reg = 0;
+
+ mask = 1 << cpu;
+ if (info->a15_clusid != cluster)
+ mask <<= 4;
+
+ wake_int_mask_reg = readl_relaxed(info->baseaddr + WAKE_INT_MASK);
+ reg_bitmask(&wake_int_mask_reg, mask, set);
+ vexpress_spc_set_wake_intr(wake_int_mask_reg);
+}
+
+/**
+ * vexpress_spc_powerdown_enable()
+ *
+ * Function to enable/disable cluster powerdown. Not protected by locking
+ * since it might be used in code paths where normal cacheable locks are not
+ * working. Locking must be provided by the caller to ensure atomicity.
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @enable: if true enables powerdown, if false disables it
+ */
+void vexpress_spc_powerdown_enable(u32 cluster, bool enable)
+{
+ u32 pwdrn_reg = 0;
+
+ if (cluster >= MAX_CLUSTERS)
+ return;
+ pwdrn_reg = cluster != info->a15_clusid ? A7_PWRDN_EN : A15_PWRDN_EN;
+ writel_relaxed(enable, info->baseaddr + pwdrn_reg);
+}
+
+irqreturn_t vexpress_spc_irq_handler(int irq, void *data)
+{
+ int ret;
+ u32 status = readl_relaxed(info->baseaddr + PWC_STATUS);
+
+ if (!(status & RESPONSE_MASK(info->cur_req_type)))
+ return IRQ_NONE;
+
+ if ((status == STAT_COMPLETE(SYS_CFGCTRL_TYPE))
+ && vexpress_spc_config_data) {
+ *vexpress_spc_config_data =
+ readl_relaxed(info->baseaddr + SYS_CFG_RDATA);
+ vexpress_spc_config_data = NULL;
+ }
+
+ ret = STAT_COMPLETE(info->cur_req_type) ? 0 : -EIO;
+ info->cur_req_type = INVALID_TYPE;
+ vexpress_config_complete(vexpress_spc_config_bridge, ret);
+ return IRQ_HANDLED;
+}
+
+/**
+ * Based on the firmware documentation, this is always fixed to 20
+ * All the 4 OSC: A15 PLL0/1, A7 PLL0/1 must be programmed same
+ * values for both control and value registers.
+ * This function uses A15 PLL 0 registers to compute multiple factor
+ * F out = F in * (CLKF + 1) / ((CLKOD + 1) * (CLKR + 1))
+ */
+static inline int __get_mult_factor(void)
+{
+ int i_div, o_div, f_div;
+ u32 tmp;
+
+ tmp = readl(info->baseaddr + SCC_CFGREG19);
+ f_div = (tmp >> CLKF_SHIFT) & CLKF_MASK;
+
+ tmp = readl(info->baseaddr + SCC_CFGREG20);
+ o_div = (tmp >> CLKOD_SHIFT) & CLKOD_MASK;
+ i_div = (tmp >> CLKR_SHIFT) & CLKR_MASK;
+
+ return (f_div + 1) / ((o_div + 1) * (i_div + 1));
+}
+
+/**
+ * vexpress_spc_populate_opps() - initialize opp tables from microcontroller
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ *
+ * Return: 0 on success
+ * < 0 on error
+ */
+static int vexpress_spc_populate_opps(u32 cluster)
+{
+ u32 data = 0, ret, i, offset;
+ int mult_fact = __get_mult_factor();
+
+ if (WARN_ON_ONCE(cluster >= MAX_CLUSTERS))
+ return -EINVAL;
+
+ offset = cluster != info->a15_clusid ? OPP_A7_OFFSET : OPP_A15_OFFSET;
+ for (i = 0; i < MAX_OPPS; i++) {
+ ret = vexpress_config_read(opp_func, i + offset, &data);
+ if (!ret)
+ info->freqs[cluster][i] = (data & 0xFFFFF) * mult_fact;
+ else
+ break;
+ }
+
+ info->freqs_cnt[cluster] = i;
+ return ret;
+}
+
+/**
+ * vexpress_spc_get_freq_table() - Retrieve a pointer to the frequency
+ * table for a given cluster
+ *
+ * @cluster: mpidr[15:8] bitfield describing cluster affinity level
+ * @fptr: pointer to be initialized
+ * Return: operating points count on success
+ * -EINVAL on pointer error
+ */
+int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr)
+{
+ if (WARN_ON_ONCE(!fptr || cluster >= MAX_CLUSTERS))
+ return -EINVAL;
+ *fptr = info->freqs[cluster];
+ return info->freqs_cnt[cluster];
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_get_freq_table);
+
+static void *vexpress_spc_func_get(struct device *dev,
+ struct device_node *node, const char *id)
+{
+ struct vexpress_spc_func *spc_func;
+ u32 func_device[2];
+ int err = 0;
+
+ spc_func = kzalloc(sizeof(*spc_func), GFP_KERNEL);
+ if (!spc_func)
+ return NULL;
+
+ if (strcmp(id, "opp") == 0) {
+ spc_func->type = CONFIG_FUNC;
+ spc_func->function = OPP_FUNCTION;
+ spc_func->device = OPP_BASE_DEVICE;
+ } else if (strcmp(id, "perf") == 0) {
+ spc_func->type = PERF_FUNC;
+ } else if (node) {
+ of_node_get(node);
+ err = of_property_read_u32_array(node,
+ "arm,vexpress-sysreg,func", func_device,
+ ARRAY_SIZE(func_device));
+ of_node_put(node);
+ spc_func->type = CONFIG_FUNC;
+ spc_func->function = func_device[0];
+ spc_func->device = func_device[1];
+ }
+
+ if (WARN_ON(err)) {
+ kfree(spc_func);
+ return NULL;
+ }
+
+ pr_debug("func 0x%p = 0x%x, %d %d\n", spc_func,
+ spc_func->function,
+ spc_func->device,
+ spc_func->type);
+
+ return spc_func;
+}
+
+static void vexpress_spc_func_put(void *func)
+{
+ kfree(func);
+}
+
+static int vexpress_spc_func_exec(void *func, int offset, bool write,
+ u32 *data)
+{
+ struct vexpress_spc_func *spc_func = func;
+ u32 command;
+
+ if (!data)
+ return -EINVAL;
+ /*
+ * Setting and retrieval of operating points is not part of
+ * DCC config interface. It was made to go through the same
+ * code path so that requests to the M3 can be serialized
+ * properly with config reads/writes through the common
+ * vexpress config interface
+ */
+ switch (spc_func->type) {
+ case PERF_FUNC:
+ if (write) {
+ info->cur_req_type = (offset == PERF_LVL_A15) ?
+ A15_OPP_TYPE : A7_OPP_TYPE;
+ writel_relaxed(*data, info->baseaddr + offset);
+ return VEXPRESS_CONFIG_STATUS_WAIT;
+ } else {
+ *data = readl_relaxed(info->baseaddr + offset);
+ return VEXPRESS_CONFIG_STATUS_DONE;
+ }
+ case CONFIG_FUNC:
+ info->cur_req_type = SYS_CFGCTRL_TYPE;
+
+ command = SYS_CFGCTRL_START;
+ command |= write ? SYS_CFGCTRL_WRITE : 0;
+ command |= SYS_CFGCTRL_FUNC(spc_func->function);
+ command |= SYS_CFGCTRL_DEVICE(spc_func->device + offset);
+
+ pr_debug("command %x\n", command);
+
+ if (!write)
+ vexpress_spc_config_data = data;
+ else
+ writel_relaxed(*data, info->baseaddr + SYS_CFG_WDATA);
+ writel_relaxed(command, info->baseaddr + SYS_CFGCTRL);
+
+ return VEXPRESS_CONFIG_STATUS_WAIT;
+ default:
+ return -EINVAL;
+ }
+}
+
+struct vexpress_config_bridge_info vexpress_spc_config_bridge_info = {
+ .name = "vexpress-spc",
+ .func_get = vexpress_spc_func_get,
+ .func_put = vexpress_spc_func_put,
+ .func_exec = vexpress_spc_func_exec,
+};
+
+static const struct of_device_id vexpress_spc_ids[] __initconst = {
+ { .compatible = "arm,vexpress-spc,v2p-ca15_a7" },
+ { .compatible = "arm,vexpress-spc" },
+ {},
+};
+
+static int __init vexpress_spc_init(void)
+{
+ int ret;
+ struct device_node *node = of_find_matching_node(NULL,
+ vexpress_spc_ids);
+
+ if (!node)
+ return -ENODEV;
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
+ pr_err("%s: unable to allocate mem\n", __func__);
+ return -ENOMEM;
+ }
+ info->cur_req_type = INVALID_TYPE;
+
+ info->baseaddr = of_iomap(node, 0);
+ if (WARN_ON(!info->baseaddr)) {
+ ret = -ENXIO;
+ goto mem_free;
+ }
+
+ info->irq = irq_of_parse_and_map(node, 0);
+
+ if (WARN_ON(!info->irq)) {
+ ret = -ENXIO;
+ goto unmap;
+ }
+
+ readl_relaxed(info->baseaddr + PWC_STATUS);
+
+ ret = request_irq(info->irq, vexpress_spc_irq_handler,
+ IRQF_DISABLED | IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+ "arm-spc", info);
+
+ if (ret) {
+ pr_err("IRQ %d request failed\n", info->irq);
+ ret = -ENODEV;
+ goto unmap;
+ }
+
+ info->a15_clusid = readl_relaxed(info->baseaddr + A15_CONF) & 0xf;
+
+ vexpress_spc_config_bridge = vexpress_config_bridge_register(
+ node, &vexpress_spc_config_bridge_info);
+
+ if (WARN_ON(!vexpress_spc_config_bridge)) {
+ ret = -ENODEV;
+ goto unmap;
+ }
+
+ opp_func = vexpress_config_func_get(vexpress_spc_config_bridge, "opp");
+ perf_func =
+ vexpress_config_func_get(vexpress_spc_config_bridge, "perf");
+
+ if (!opp_func || !perf_func) {
+ ret = -ENODEV;
+ goto unmap;
+ }
+
+ if (vexpress_spc_populate_opps(0) || vexpress_spc_populate_opps(1)) {
+ if (info->irq)
+ free_irq(info->irq, info);
+ pr_err("failed to build OPP table\n");
+ ret = -ENODEV;
+ goto unmap;
+ }
+ /*
+ * Multi-cluster systems may need this data when non-coherent, during
+ * cluster power-up/power-down. Make sure it reaches main memory:
+ */
+ sync_cache_w(info);
+ sync_cache_w(&info);
+ pr_info("vexpress-spc loaded at %p\n", info->baseaddr);
+ return 0;
+
+unmap:
+ iounmap(info->baseaddr);
+
+mem_free:
+ kfree(info);
+ return ret;
+}
+
+static bool __init __vexpress_spc_check_loaded(void);
+/*
+ * Pointer spc_check_loaded is swapped after init hence it is safe
+ * to initialize it to a function in the __init section
+ */
+static bool (*spc_check_loaded)(void) __refdata = &__vexpress_spc_check_loaded;
+
+static bool __init __vexpress_spc_check_loaded(void)
+{
+ if (vexpress_spc_load_result == -EAGAIN)
+ vexpress_spc_load_result = vexpress_spc_init();
+ spc_check_loaded = &vexpress_spc_initialized;
+ return vexpress_spc_initialized();
+}
+
+/*
+ * Function exported to manage early_initcall ordering.
+ * SPC code is needed very early in the boot process
+ * to bring CPUs out of reset and initialize power
+ * management back-end. After boot swap pointers to
+ * make the functionality check available to loadable
+ * modules, when early boot init functions have been
+ * already freed from kernel address space.
+ */
+bool vexpress_spc_check_loaded(void)
+{
+ return spc_check_loaded();
+}
+EXPORT_SYMBOL_GPL(vexpress_spc_check_loaded);
+
+static int __init vexpress_spc_early_init(void)
+{
+ __vexpress_spc_check_loaded();
+ return vexpress_spc_load_result;
+}
+early_initcall(vexpress_spc_early_init);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Serial Power Controller (SPC) support");
diff --git a/drivers/mfd/vexpress-sysreg.c b/drivers/mfd/vexpress-sysreg.c
index 96a020b..7f429af 100644
--- a/drivers/mfd/vexpress-sysreg.c
+++ b/drivers/mfd/vexpress-sysreg.c
@@ -165,7 +165,7 @@
static int vexpress_sysreg_config_tries;
static void *vexpress_sysreg_config_func_get(struct device *dev,
- struct device_node *node)
+ struct device_node *node, const char *id)
{
struct vexpress_sysreg_config_func *config_func;
u32 site;
@@ -351,6 +351,8 @@
}
+#ifdef CONFIG_GPIOLIB
+
#define VEXPRESS_SYSREG_GPIO(_name, _reg, _value) \
[VEXPRESS_GPIO_##_name] = { \
.reg = _reg, \
@@ -445,6 +447,8 @@
.leds = vexpress_sysreg_leds,
};
+#endif
+
static ssize_t vexpress_sysreg_sys_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -480,6 +484,9 @@
setup_timer(&vexpress_sysreg_config_timer,
vexpress_sysreg_config_complete, 0);
+ vexpress_sysreg_dev = &pdev->dev;
+
+#ifdef CONFIG_GPIOLIB
vexpress_sysreg_gpio_chip.dev = &pdev->dev;
err = gpiochip_add(&vexpress_sysreg_gpio_chip);
if (err) {
@@ -490,11 +497,10 @@
return err;
}
- vexpress_sysreg_dev = &pdev->dev;
-
platform_device_register_data(vexpress_sysreg_dev, "leds-gpio",
PLATFORM_DEVID_AUTO, &vexpress_sysreg_leds_pdata,
sizeof(vexpress_sysreg_leds_pdata));
+#endif
device_create_file(vexpress_sysreg_dev, &dev_attr_sys_id);
diff --git a/drivers/misc/atmel_pwm.c b/drivers/misc/atmel_pwm.c
index 494d050..a6dc56e 100644
--- a/drivers/misc/atmel_pwm.c
+++ b/drivers/misc/atmel_pwm.c
@@ -90,8 +90,10 @@
unsigned long flags;
int status = 0;
- /* insist on PWM init, with this signal pinned out */
- if (!pwm || !(pwm->mask & 1 << index))
+ if (!pwm)
+ return -EPROBE_DEFER;
+
+ if (!(pwm->mask & 1 << index))
return -ENODEV;
if (index < 0 || index >= PWM_NCHAN || !ch)
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 00e5fcac8..cbee842 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -198,6 +198,13 @@
{
char name[ENCLOSURE_NAME_SIZE];
+ /*
+ * In odd circumstances, like multipath devices, something else may
+ * already have removed the links, so check for this condition first.
+ */
+ if (!cdev->dev->kobj.sd)
+ return;
+
enclosure_link_name(cdev, name);
sysfs_remove_link(&cdev->dev->kobj, name);
sysfs_remove_link(&cdev->cdev.kobj, "device");
diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c
index 621c7a3..b83e3ca 100644
--- a/drivers/misc/hpilo.c
+++ b/drivers/misc/hpilo.c
@@ -759,7 +759,7 @@
/* Ignore subsystem_device = 0x1979 (set by BIOS) */
if (pdev->subsystem_device == 0x1979)
- goto out;
+ return 0;
if (max_ccb > MAX_CCB)
max_ccb = MAX_CCB;
@@ -899,7 +899,7 @@
class_destroy(ilo_class);
}
-MODULE_VERSION("1.4");
+MODULE_VERSION("1.4.1");
MODULE_ALIAS(ILO_NAME);
MODULE_DESCRIPTION(ILO_NAME);
MODULE_AUTHOR("David Altobelli <david.altobelli@hp.com>");
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index b3e5098..3db9291 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -57,6 +57,7 @@
dev->iamthif_ioctl = false;
dev->iamthif_state = MEI_IAMTHIF_IDLE;
dev->iamthif_timer = 0;
+ dev->iamthif_stall_timer = 0;
}
/**
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 9ecd49a..0513ea0 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -71,7 +71,7 @@
dev_dbg(dev, "Device probe\n");
- strncpy(id.name, dev_name(dev), MEI_CL_NAME_SIZE);
+ strlcpy(id.name, dev_name(dev), sizeof(id.name));
return driver->probe(device, &id);
}
@@ -295,10 +295,13 @@
if (cl->reading_state != MEI_READ_COMPLETE &&
!waitqueue_active(&cl->rx_wait)) {
+
mutex_unlock(&dev->device_lock);
if (wait_event_interruptible(cl->rx_wait,
- (MEI_READ_COMPLETE == cl->reading_state))) {
+ cl->reading_state == MEI_READ_COMPLETE ||
+ mei_cl_is_transitioning(cl))) {
+
if (signal_pending(current))
return -EINTR;
return -ERESTARTSYS;
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index e310ca6..07ed4b5 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -405,6 +405,7 @@
dev_err(&dev->pdev->dev, "failed to disconnect.\n");
goto free;
}
+ cl->timer_count = MEI_CONNECT_TIMEOUT;
mdelay(10); /* Wait for hardware disconnection ready */
list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
} else {
@@ -511,6 +512,7 @@
cl->timer_count = MEI_CONNECT_TIMEOUT;
list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
} else {
+ cl->state = MEI_FILE_INITIALIZING;
list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
}
@@ -664,7 +666,6 @@
goto err;
cb->fop_type = MEI_FOP_READ;
- cl->read_cb = cb;
if (dev->hbuf_is_ready) {
dev->hbuf_is_ready = false;
if (mei_hbm_cl_flow_control_req(dev, cl)) {
@@ -675,6 +676,9 @@
} else {
list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
}
+
+ cl->read_cb = cb;
+
return rets;
err:
mei_io_cb_free(cb);
@@ -799,7 +803,6 @@
list_for_each_entry_safe(cl, next, &dev->file_list, link) {
cl->state = MEI_FILE_DISCONNECTED;
cl->mei_flow_ctrl_creds = 0;
- cl->read_cb = NULL;
cl->timer_count = 0;
}
}
@@ -829,8 +832,16 @@
void mei_cl_all_write_clear(struct mei_device *dev)
{
struct mei_cl_cb *cb, *next;
+ struct list_head *list;
- list_for_each_entry_safe(cb, next, &dev->write_list.list, list) {
+ list = &dev->write_list.list;
+ list_for_each_entry_safe(cb, next, list, list) {
+ list_del(&cb->list);
+ mei_io_cb_free(cb);
+ }
+
+ list = &dev->write_waiting_list.list;
+ list_for_each_entry_safe(cb, next, list, list) {
list_del(&cb->list);
mei_io_cb_free(cb);
}
diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h
index cfdb144..467d9dd 100644
--- a/drivers/misc/mei/client.h
+++ b/drivers/misc/mei/client.h
@@ -76,6 +76,12 @@
(cl1->host_client_id == cl2->host_client_id) &&
(cl1->me_client_id == cl2->me_client_id);
}
+static inline bool mei_cl_is_transitioning(struct mei_cl *cl)
+{
+ return (MEI_FILE_INITIALIZING == cl->state ||
+ MEI_FILE_DISCONNECTED == cl->state ||
+ MEI_FILE_DISCONNECTING == cl->state);
+}
int mei_cl_flow_ctrl_creds(struct mei_cl *cl);
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index 6916045..23b5b7b 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -35,11 +35,15 @@
struct mei_me_client *clients;
int b;
+ dev->me_clients_num = 0;
+ dev->me_client_presentation_num = 0;
+ dev->me_client_index = 0;
+
/* count how many ME clients we have */
for_each_set_bit(b, dev->me_clients_map, MEI_CLIENTS_MAX)
dev->me_clients_num++;
- if (dev->me_clients_num <= 0)
+ if (dev->me_clients_num == 0)
return;
kfree(dev->me_clients);
@@ -221,7 +225,7 @@
struct hbm_props_request *prop_req;
const size_t len = sizeof(struct hbm_props_request);
unsigned long next_client_index;
- u8 client_num;
+ unsigned long client_num;
client_num = dev->me_client_presentation_num;
@@ -650,8 +654,6 @@
if (dev->dev_state == MEI_DEV_INIT_CLIENTS &&
dev->hbm_state == MEI_HBM_ENUM_CLIENTS) {
dev->init_clients_timer = 0;
- dev->me_client_presentation_num = 0;
- dev->me_client_index = 0;
mei_hbm_me_cl_allocate(dev);
dev->hbm_state = MEI_HBM_CLIENT_PROPERTIES;
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 6a203b6..cabc043 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -109,8 +109,17 @@
#define MEI_DEV_ID_PPT_2 0x1CBA /* Panther Point */
#define MEI_DEV_ID_PPT_3 0x1DBA /* Panther Point */
-#define MEI_DEV_ID_LPT 0x8C3A /* Lynx Point */
+#define MEI_DEV_ID_LPT_H 0x8C3A /* Lynx Point H */
+#define MEI_DEV_ID_LPT_W 0x8D3A /* Lynx Point - Wellsburg */
#define MEI_DEV_ID_LPT_LP 0x9C3A /* Lynx Point LP */
+#define MEI_DEV_ID_LPT_HR 0x8CBA /* Lynx Point H Refresh */
+
+#define MEI_DEV_ID_WPT_LP 0x9CBA /* Wildcat Point LP */
+
+/* Host Firmware Status Registers in PCI Config Space */
+#define PCI_CFG_HFS_1 0x40
+#define PCI_CFG_HFS_2 0x48
+
/*
* MEI HW Section
*/
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 822170f..297cc10 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -164,6 +164,9 @@
hcsr |= H_IG;
hcsr &= ~H_RST;
mei_hcsr_set(hw, hcsr);
+
+ /* complete this write before we set host ready on another CPU */
+ mmiowb();
}
/**
* mei_me_hw_reset - resets fw via mei csr register.
@@ -176,18 +179,29 @@
struct mei_me_hw *hw = to_me_hw(dev);
u32 hcsr = mei_hcsr_read(hw);
- dev_dbg(&dev->pdev->dev, "before reset HCSR = 0x%08x.\n", hcsr);
-
- hcsr |= (H_RST | H_IG);
+ hcsr |= H_RST | H_IG | H_IS;
if (intr_enable)
hcsr |= H_IE;
else
- hcsr |= ~H_IE;
+ hcsr &= ~H_IE;
- mei_hcsr_set(hw, hcsr);
+ dev->recvd_hw_ready = false;
+ mei_me_reg_write(hw, H_CSR, hcsr);
- if (dev->dev_state == MEI_DEV_POWER_DOWN)
+ /*
+ * Host reads the H_CSR once to ensure that the
+ * posted write to H_CSR completes.
+ */
+ hcsr = mei_hcsr_read(hw);
+
+ if ((hcsr & H_RST) == 0)
+ dev_warn(&dev->pdev->dev, "H_RST is not set = 0x%08X", hcsr);
+
+ if ((hcsr & H_RDY) == H_RDY)
+ dev_warn(&dev->pdev->dev, "H_RDY is not cleared 0x%08X", hcsr);
+
+ if (intr_enable == false)
mei_me_hw_reset_release(dev);
dev_dbg(&dev->pdev->dev, "current HCSR = 0x%08x.\n", mei_hcsr_read(hw));
@@ -203,6 +217,7 @@
static void mei_me_host_set_ready(struct mei_device *dev)
{
struct mei_me_hw *hw = to_me_hw(dev);
+ hw->host_hw_state = mei_hcsr_read(hw);
hw->host_hw_state |= H_IE | H_IG | H_RDY;
mei_hcsr_set(hw, hw->host_hw_state);
}
@@ -235,17 +250,18 @@
static int mei_me_hw_ready_wait(struct mei_device *dev)
{
int err;
- if (mei_me_hw_is_ready(dev))
- return 0;
mutex_unlock(&dev->device_lock);
err = wait_event_interruptible_timeout(dev->wait_hw_ready,
- dev->recvd_hw_ready, MEI_INTEROP_TIMEOUT);
+ dev->recvd_hw_ready,
+ mei_secs_to_jiffies(MEI_INTEROP_TIMEOUT));
mutex_lock(&dev->device_lock);
if (!err && !dev->recvd_hw_ready) {
+ if (!err)
+ err = -ETIMEDOUT;
dev_err(&dev->pdev->dev,
- "wait hw ready failed. status = 0x%x\n", err);
- return -ETIMEDOUT;
+ "wait hw ready failed. status = %d\n", err);
+ return err;
}
dev->recvd_hw_ready = false;
@@ -482,7 +498,9 @@
/* check if ME wants a reset */
if (!mei_hw_is_ready(dev) &&
dev->dev_state != MEI_DEV_RESETTING &&
- dev->dev_state != MEI_DEV_INITIALIZING) {
+ dev->dev_state != MEI_DEV_INITIALIZING &&
+ dev->dev_state != MEI_DEV_POWER_DOWN &&
+ dev->dev_state != MEI_DEV_POWER_UP) {
dev_dbg(&dev->pdev->dev, "FW not ready.\n");
mei_reset(dev, 1);
mutex_unlock(&dev->device_lock);
@@ -492,19 +510,15 @@
/* check if we need to start the dev */
if (!mei_host_is_ready(dev)) {
if (mei_hw_is_ready(dev)) {
+ mei_me_hw_reset_release(dev);
dev_dbg(&dev->pdev->dev, "we need to start the dev.\n");
dev->recvd_hw_ready = true;
wake_up_interruptible(&dev->wait_hw_ready);
-
- mutex_unlock(&dev->device_lock);
- return IRQ_HANDLED;
} else {
- dev_dbg(&dev->pdev->dev, "Reset Completed.\n");
- mei_me_hw_reset_release(dev);
- mutex_unlock(&dev->device_lock);
- return IRQ_HANDLED;
+ dev_dbg(&dev->pdev->dev, "Spurious Interrupt\n");
}
+ goto end;
}
/* check slots available for reading */
slots = mei_count_full_read_slots(dev);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index f580d30..878bc1c 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -143,7 +143,8 @@
dev->hbm_state = MEI_HBM_IDLE;
- if (dev->dev_state != MEI_DEV_INITIALIZING) {
+ if (dev->dev_state != MEI_DEV_INITIALIZING &&
+ dev->dev_state != MEI_DEV_POWER_UP) {
if (dev->dev_state != MEI_DEV_DISABLED &&
dev->dev_state != MEI_DEV_POWER_DOWN)
dev->dev_state = MEI_DEV_RESETTING;
@@ -163,6 +164,9 @@
memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg));
}
+ /* we're already in reset, cancel the init timer */
+ dev->init_clients_timer = 0;
+
dev->me_clients_num = 0;
dev->rd_msg_hdr = 0;
dev->wd_pending = false;
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 053139f..701698d 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -262,19 +262,16 @@
mutex_unlock(&dev->device_lock);
if (wait_event_interruptible(cl->rx_wait,
- (MEI_READ_COMPLETE == cl->reading_state ||
- MEI_FILE_INITIALIZING == cl->state ||
- MEI_FILE_DISCONNECTED == cl->state ||
- MEI_FILE_DISCONNECTING == cl->state))) {
+ MEI_READ_COMPLETE == cl->reading_state ||
+ mei_cl_is_transitioning(cl))) {
+
if (signal_pending(current))
return -EINTR;
return -ERESTARTSYS;
}
mutex_lock(&dev->device_lock);
- if (MEI_FILE_INITIALIZING == cl->state ||
- MEI_FILE_DISCONNECTED == cl->state ||
- MEI_FILE_DISCONNECTING == cl->state) {
+ if (mei_cl_is_transitioning(cl)) {
rets = -EBUSY;
goto out;
}
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index 4de5140..73c7700 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -402,9 +402,9 @@
struct mei_me_client *me_clients; /* Note: memory has to be allocated */
DECLARE_BITMAP(me_clients_map, MEI_CLIENTS_MAX);
DECLARE_BITMAP(host_clients_map, MEI_CLIENTS_MAX);
- u8 me_clients_num;
- u8 me_client_presentation_num;
- u8 me_client_index;
+ unsigned long me_clients_num;
+ unsigned long me_client_presentation_num;
+ unsigned long me_client_index;
struct mei_cl wd_cl;
enum mei_wd_states wd_state;
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index d0c6907..4b7ea3f 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -342,9 +342,10 @@
ndev = (struct mei_nfc_dev *) cldev->priv_data;
dev = ndev->cl->dev;
+ err = -ENOMEM;
mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL);
if (!mei_buf)
- return -ENOMEM;
+ goto out;
hdr = (struct mei_nfc_hci_hdr *) mei_buf;
hdr->cmd = MEI_NFC_CMD_HCI_SEND;
@@ -354,12 +355,9 @@
hdr->data_size = length;
memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length);
-
err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE);
if (err < 0)
- return err;
-
- kfree(mei_buf);
+ goto out;
if (!wait_event_interruptible_timeout(ndev->send_wq,
ndev->recv_req_id == ndev->req_id, HZ)) {
@@ -368,7 +366,8 @@
} else {
ndev->req_id++;
}
-
+out:
+ kfree(mei_buf);
return err;
}
@@ -485,8 +484,11 @@
if (ndev->cl_info)
return 0;
- cl_info = mei_cl_allocate(dev);
- cl = mei_cl_allocate(dev);
+ ndev->cl_info = mei_cl_allocate(dev);
+ ndev->cl = mei_cl_allocate(dev);
+
+ cl = ndev->cl;
+ cl_info = ndev->cl_info;
if (!cl || !cl_info) {
ret = -ENOMEM;
@@ -527,10 +529,9 @@
cl->device_uuid = mei_nfc_guid;
+
list_add_tail(&cl->device_link, &dev->device_list);
- ndev->cl_info = cl_info;
- ndev->cl = cl;
ndev->req_id = 1;
INIT_WORK(&ndev->init_work, mei_nfc_init);
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 0f26832..3c9e257 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -79,8 +79,11 @@
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_1)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_2)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_PPT_3)},
- {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_H)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_W)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_LP)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_LPT_HR)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, MEI_DEV_ID_WPT_LP)},
/* required last entry */
{0, }
@@ -102,15 +105,31 @@
const struct pci_device_id *ent)
{
u32 reg;
- if (ent->device == MEI_DEV_ID_PBG_1) {
- pci_read_config_dword(pdev, 0x48, ®);
- /* make sure that bit 9 is up and bit 10 is down */
- if ((reg & 0x600) == 0x200) {
- dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
- return false;
- }
+ /* Cougar Point || Patsburg */
+ if (ent->device == MEI_DEV_ID_CPT_1 ||
+ ent->device == MEI_DEV_ID_PBG_1) {
+ pci_read_config_dword(pdev, PCI_CFG_HFS_2, ®);
+ /* make sure that bit 9 (NM) is up and bit 10 (DM) is down */
+ if ((reg & 0x600) == 0x200)
+ goto no_mei;
}
+
+ /* Lynx Point */
+ if (ent->device == MEI_DEV_ID_LPT_H ||
+ ent->device == MEI_DEV_ID_LPT_W ||
+ ent->device == MEI_DEV_ID_LPT_HR) {
+ /* Read ME FW Status check for SPS Firmware */
+ pci_read_config_dword(pdev, PCI_CFG_HFS_1, ®);
+ /* if bits [19:16] = 15, running SPS Firmware */
+ if ((reg & 0xf0000) == 0xf0000)
+ goto no_mei;
+ }
+
return true;
+
+no_mei:
+ dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
+ return false;
}
/**
* mei_probe - Device Initialization Routine
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index dd27b07..7ad6682 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -257,7 +257,7 @@
int ret;
struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
- ret = snprintf(buf, PAGE_SIZE, "%d",
+ ret = snprintf(buf, PAGE_SIZE, "%d\n",
get_disk_ro(dev_to_disk(dev)) ^
md->read_only);
mmc_blk_put(md);
@@ -769,7 +769,7 @@
* Otherwise we don't understand what happened, so abort.
*/
static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req,
- struct mmc_blk_request *brq, int *ecc_err)
+ struct mmc_blk_request *brq, int *ecc_err, int *gen_err)
{
bool prev_cmd_status_valid = true;
u32 status, stop_status = 0;
@@ -807,6 +807,16 @@
(brq->cmd.resp[0] & R1_CARD_ECC_FAILED))
*ecc_err = 1;
+ /* Flag General errors */
+ if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ)
+ if ((status & R1_ERROR) ||
+ (brq->stop.resp[0] & R1_ERROR)) {
+ pr_err("%s: %s: general error sending stop or status command, stop cmd response %#x, card status %#x\n",
+ req->rq_disk->disk_name, __func__,
+ brq->stop.resp[0], status);
+ *gen_err = 1;
+ }
+
/*
* Check the current card state. If it is in some data transfer
* mode, tell it to stop (and hopefully transition back to TRAN.)
@@ -826,6 +836,13 @@
return ERR_ABORT;
if (stop_status & R1_CARD_ECC_FAILED)
*ecc_err = 1;
+ if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ)
+ if (stop_status & R1_ERROR) {
+ pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n",
+ req->rq_disk->disk_name, __func__,
+ stop_status);
+ *gen_err = 1;
+ }
}
/* Check for set block count errors */
@@ -1069,7 +1086,7 @@
mmc_active);
struct mmc_blk_request *brq = &mq_mrq->brq;
struct request *req = mq_mrq->req;
- int ecc_err = 0;
+ int ecc_err = 0, gen_err = 0;
/*
* sbc.error indicates a problem with the set block count
@@ -1083,7 +1100,7 @@
*/
if (brq->sbc.error || brq->cmd.error || brq->stop.error ||
brq->data.error) {
- switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err)) {
+ switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err, &gen_err)) {
case ERR_RETRY:
return MMC_BLK_RETRY;
case ERR_ABORT:
@@ -1115,6 +1132,14 @@
u32 status;
unsigned long timeout;
+ /* Check stop command response */
+ if (brq->stop.resp[0] & R1_ERROR) {
+ pr_err("%s: %s: general error sending stop command, stop cmd response %#x\n",
+ req->rq_disk->disk_name, __func__,
+ brq->stop.resp[0]);
+ gen_err = 1;
+ }
+
timeout = jiffies + msecs_to_jiffies(MMC_BLK_TIMEOUT_MS);
do {
int err = get_card_status(card, &status, 5);
@@ -1124,6 +1149,13 @@
return MMC_BLK_CMD_ERR;
}
+ if (status & R1_ERROR) {
+ pr_err("%s: %s: general error sending status command, card status %#x\n",
+ req->rq_disk->disk_name, __func__,
+ status);
+ gen_err = 1;
+ }
+
/* Timeout if the device never becomes ready for data
* and never leaves the program state.
*/
@@ -1143,6 +1175,13 @@
(R1_CURRENT_STATE(status) == R1_STATE_PRG));
}
+ /* if general error occurs, retry the write operation. */
+ if (gen_err) {
+ pr_warn("%s: retrying write for general error\n",
+ req->rq_disk->disk_name);
+ return MMC_BLK_RETRY;
+ }
+
if (brq->data.error) {
pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n",
req->rq_disk->disk_name, brq->data.error,
@@ -1892,6 +1931,7 @@
struct mmc_card *card = md->queue.card;
struct mmc_host *host = card->host;
unsigned long flags;
+ unsigned int cmd_flags = req ? req->cmd_flags : 0;
if (req && !mq->mqrq_prev->req)
/* claim host only for the first request */
@@ -1907,7 +1947,7 @@
}
mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
- if (req && req->cmd_flags & REQ_DISCARD) {
+ if (cmd_flags & REQ_DISCARD) {
/* complete ongoing async transfer before issuing discard */
if (card->host->areq)
mmc_blk_issue_rw_rq(mq, NULL);
@@ -1916,7 +1956,7 @@
ret = mmc_blk_issue_secdiscard_rq(mq, req);
else
ret = mmc_blk_issue_discard_rq(mq, req);
- } else if (req && req->cmd_flags & REQ_FLUSH) {
+ } else if (cmd_flags & REQ_FLUSH) {
/* complete ongoing async transfer before issuing flush */
if (card->host->areq)
mmc_blk_issue_rw_rq(mq, NULL);
@@ -1932,7 +1972,7 @@
out:
if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
- (req && (req->cmd_flags & MMC_REQ_SPECIAL_MASK)))
+ (cmd_flags & MMC_REQ_SPECIAL_MASK))
/*
* Release host when there are no more requests
* and after special request(discard, flush) is done.
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index aca59d9..84b054b 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -584,6 +584,13 @@
if (host->mrq->cmd->data) {
host->mrq->cmd->data->error = -ETIMEDOUT;
host->data = NULL;
+ /*
+ * With some SDIO modules, sometimes DMA transfer hangs. If
+ * stop_transfer() is not called then the DMA request is not
+ * removed, following ones are queued and never computed.
+ */
+ if (host->state == STATE_DATA_XFER)
+ host->stop_transfer(host);
} else {
host->mrq->cmd->error = -ETIMEDOUT;
host->cmd = NULL;
@@ -1181,11 +1188,22 @@
iflags |= ATMCI_CMDRDY;
cmd = mrq->cmd;
cmdflags = atmci_prepare_command(slot->mmc, cmd);
- atmci_send_command(host, cmd, cmdflags);
+
+ /*
+ * DMA transfer should be started before sending the command to avoid
+ * unexpected errors especially for read operations in SDIO mode.
+ * Unfortunately, in PDC mode, command has to be sent before starting
+ * the transfer.
+ */
+ if (host->submit_data != &atmci_submit_data_dma)
+ atmci_send_command(host, cmd, cmdflags);
if (data)
host->submit_data(host, data);
+ if (host->submit_data == &atmci_submit_data_dma)
+ atmci_send_command(host, cmd, cmdflags);
+
if (mrq->stop) {
host->stop_cmdr = atmci_prepare_command(slot->mmc, mrq->stop);
host->stop_cmdr |= ATMCI_CMDR_STOP_XFER;
@@ -1787,12 +1805,14 @@
if (unlikely(status)) {
host->stop_transfer(host);
host->data = NULL;
- if (status & ATMCI_DTOE) {
- data->error = -ETIMEDOUT;
- } else if (status & ATMCI_DCRCE) {
- data->error = -EILSEQ;
- } else {
- data->error = -EIO;
+ if (data) {
+ if (status & ATMCI_DTOE) {
+ data->error = -ETIMEDOUT;
+ } else if (status & ATMCI_DCRCE) {
+ data->error = -EILSEQ;
+ } else {
+ data->error = -EIO;
+ }
}
}
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index ad13f42..4c65a5a 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -247,6 +247,9 @@
case MMC_RSP_R1:
rsp_type = SD_RSP_TYPE_R1;
break;
+ case MMC_RSP_R1 & ~MMC_RSP_CRC:
+ rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
+ break;
case MMC_RSP_R1B:
rsp_type = SD_RSP_TYPE_R1b;
break;
@@ -338,6 +341,13 @@
}
if (rsp_type == SD_RSP_TYPE_R2) {
+ /*
+ * The controller offloads the last byte {CRC-7, end bit 1'b1}
+ * of response type R2. Assign dummy CRC, 0, and end bit to the
+ * byte(ptr[16], goes into the LSB of resp[3] later).
+ */
+ ptr[16] = 1;
+
for (i = 0; i < 4; i++) {
cmd->resp[i] = get_unaligned_be32(ptr + 1 + i * 4);
dev_dbg(sdmmc_dev(host), "cmd->resp[%d] = 0x%08x\n",
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 1ae358e..4edb24b 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -201,8 +201,8 @@
if (!pdata)
return NULL;
- of_property_read_u32(np, "mrvl,clk-delay-cycles", &clk_delay_cycles);
- if (clk_delay_cycles > 0)
+ if (!of_property_read_u32(np, "mrvl,clk-delay-cycles",
+ &clk_delay_cycles))
pdata->clk_delay_cycles = clk_delay_cycles;
return pdata;
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 2ea429c..836e2ac 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1316,6 +1316,8 @@
sdhci_runtime_pm_get(host);
+ present = mmc_gpio_get_cd(host->mmc);
+
spin_lock_irqsave(&host->lock, flags);
WARN_ON(host->mrq != NULL);
@@ -1344,7 +1346,6 @@
* zero: cd-gpio is used, and card is removed
* one: cd-gpio is used, and card is present
*/
- present = mmc_gpio_get_cd(host->mmc);
if (present < 0) {
/* If polling, assume that the card is always present. */
if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index fff9286..491e9ec 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -104,6 +104,7 @@
pio:
if (!desc) {
/* DMA failed, fall back to PIO */
+ tmio_mmc_enable_dma(host, false);
if (ret >= 0)
ret = -EIO;
host->chan_rx = NULL;
@@ -116,7 +117,6 @@
}
dev_warn(&host->pdev->dev,
"DMA failed: %d, falling back to PIO\n", ret);
- tmio_mmc_enable_dma(host, false);
}
dev_dbg(&host->pdev->dev, "%s(): desc %p, cookie %d, sg[%d]\n", __func__,
@@ -185,6 +185,7 @@
pio:
if (!desc) {
/* DMA failed, fall back to PIO */
+ tmio_mmc_enable_dma(host, false);
if (ret >= 0)
ret = -EIO;
host->chan_tx = NULL;
@@ -197,7 +198,6 @@
}
dev_warn(&host->pdev->dev,
"DMA failed: %d, falling back to PIO\n", ret);
- tmio_mmc_enable_dma(host, false);
}
dev_dbg(&host->pdev->dev, "%s(): desc %p, cookie %d\n", __func__,
diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c
index 19d6372..71e4f6c 100644
--- a/drivers/mtd/ftl.c
+++ b/drivers/mtd/ftl.c
@@ -1075,7 +1075,6 @@
return;
}
- ftl_freepart(partition);
kfree(partition);
}
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index a60f6c1..50543f1 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -95,7 +95,7 @@
config MTD_NAND_OMAP_BCH
depends on MTD_NAND && MTD_NAND_OMAP2 && ARCH_OMAP3
- bool "Enable support for hardware BCH error correction"
+ tristate "Enable support for hardware BCH error correction"
default n
select BCH
select BCH_CONST_PARAMS
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 2d23d29..cc69e41 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -1096,6 +1096,7 @@
goto err_pmecc_data_alloc;
}
+ nand_chip->options |= NAND_NO_SUBPAGE_WRITE;
nand_chip->ecc.read_page = atmel_nand_pmecc_read_page;
nand_chip->ecc.write_page = atmel_nand_pmecc_write_page;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 2065720..c31d183 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -725,6 +725,19 @@
return 0;
}
+/* ECC will be calculated automatically, and errors will be detected in
+ * waitfunc.
+ */
+static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+ uint32_t offset, uint32_t data_len,
+ const uint8_t *buf, int oob_required)
+{
+ fsl_elbc_write_buf(mtd, buf, mtd->writesize);
+ fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+ return 0;
+}
+
static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
{
struct fsl_lbc_ctrl *ctrl = priv->ctrl;
@@ -763,6 +776,7 @@
chip->ecc.read_page = fsl_elbc_read_page;
chip->ecc.write_page = fsl_elbc_write_page;
+ chip->ecc.write_subpage = fsl_elbc_write_subpage;
/* If CS Base Register selects full hardware ECC then use it */
if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 25ecfa1..ab6581f 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -264,8 +264,6 @@
struct gpmi_nand_data *this = param;
struct completion *dma_c = &this->dma_done;
- complete(dma_c);
-
switch (this->dma_type) {
case DMA_FOR_COMMAND:
dma_unmap_sg(this->dev, &this->cmd_sgl, 1, DMA_TO_DEVICE);
@@ -290,6 +288,8 @@
default:
pr_err("in wrong DMA operation.\n");
}
+
+ complete(dma_c);
}
int start_dma_without_bch_irq(struct gpmi_nand_data *this,
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 07e5784..9896b63 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -676,7 +676,6 @@
ecc_stat >>= 4;
} while (--no_subpages);
- mtd->ecc_stats.corrected += ret;
pr_debug("%d Symbol Correctable RS-ECC Error\n", ret);
return ret;
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index dfcd0a5..633db88 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2793,7 +2793,9 @@
if (!chip->select_chip)
chip->select_chip = nand_select_chip;
- if (!chip->read_byte)
+
+ /* If called twice, pointers that depend on busw may need to be reset */
+ if (!chip->read_byte || chip->read_byte == nand_read_byte)
chip->read_byte = busw ? nand_read_byte16 : nand_read_byte;
if (!chip->read_word)
chip->read_word = nand_read_word;
@@ -2801,9 +2803,9 @@
chip->block_bad = nand_block_bad;
if (!chip->block_markbad)
chip->block_markbad = nand_default_block_markbad;
- if (!chip->write_buf)
+ if (!chip->write_buf || chip->write_buf == nand_write_buf)
chip->write_buf = busw ? nand_write_buf16 : nand_write_buf;
- if (!chip->read_buf)
+ if (!chip->read_buf || chip->read_buf == nand_read_buf)
chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
if (!chip->scan_bbt)
chip->scan_bbt = nand_default_bbt;
@@ -2902,10 +2904,21 @@
sanitize_string(p->model, sizeof(p->model));
if (!mtd->name)
mtd->name = p->model;
+
mtd->writesize = le32_to_cpu(p->byte_per_page);
- mtd->erasesize = le32_to_cpu(p->pages_per_block) * mtd->writesize;
+
+ /*
+ * pages_per_block and blocks_per_lun may not be a power-of-2 size
+ * (don't ask me who thought of this...). MTD assumes that these
+ * dimensions will be power-of-2, so just truncate the remaining area.
+ */
+ mtd->erasesize = 1 << (fls(le32_to_cpu(p->pages_per_block)) - 1);
+ mtd->erasesize *= mtd->writesize;
+
mtd->oobsize = le16_to_cpu(p->spare_bytes_per_page);
- chip->chipsize = le32_to_cpu(p->blocks_per_lun);
+
+ /* See erasesize comment */
+ chip->chipsize = 1 << (fls(le32_to_cpu(p->blocks_per_lun)) - 1);
chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
*busw = 0;
if (le16_to_cpu(p->features) & 1)
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index cd6be2e..14203f3 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -225,7 +225,7 @@
val = __raw_readl(nand->reg + REG_FMICSR);
if (!(val & NAND_EN))
- __raw_writel(val | NAND_EN, REG_FMICSR);
+ __raw_writel(val | NAND_EN, nand->reg + REG_FMICSR);
val = __raw_readl(nand->reg + REG_SMCSR);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 81b80af..e9b1797 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -948,7 +948,7 @@
u32 val;
val = readl(info->reg.gpmc_ecc_config);
- if (((val >> ECC_CONFIG_CS_SHIFT) & ~CS_MASK) != info->gpmc_cs)
+ if (((val >> ECC_CONFIG_CS_SHIFT) & CS_MASK) != info->gpmc_cs)
return -EINVAL;
/* read ecc result */
@@ -1463,7 +1463,7 @@
/* Check if any error reported */
if (!is_error_reported)
- return 0;
+ return stat;
/* Decode BCH error using ELM module */
elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec);
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index f9d5615..4b55cd4 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -59,15 +59,12 @@
struct attribute_group *attr_group;
struct attribute **attributes;
struct sm_sysfs_attribute *vendor_attribute;
+ char *vendor;
- int vendor_len = strnlen(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
- SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET);
-
- char *vendor = kmalloc(vendor_len, GFP_KERNEL);
+ vendor = kstrndup(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
+ SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET, GFP_KERNEL);
if (!vendor)
goto error1;
- memcpy(vendor, ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, vendor_len);
- vendor[vendor_len] = 0;
/* Initialize sysfs attributes */
vendor_attribute =
@@ -78,7 +75,7 @@
sysfs_attr_init(&vendor_attribute->dev_attr.attr);
vendor_attribute->data = vendor;
- vendor_attribute->len = vendor_len;
+ vendor_attribute->len = strlen(vendor);
vendor_attribute->dev_attr.attr.name = "vendor";
vendor_attribute->dev_attr.attr.mode = S_IRUGO;
vendor_attribute->dev_attr.show = sm_attr_show;
diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c
index c071d41..79d69bd 100644
--- a/drivers/mtd/ubi/attach.c
+++ b/drivers/mtd/ubi/attach.c
@@ -408,7 +408,7 @@
second_is_newer = !second_is_newer;
} else {
dbg_bld("PEB %d CRC is OK", pnum);
- bitflips = !!err;
+ bitflips |= !!err;
}
mutex_unlock(&ubi->buf_mutex);
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index 4f02848..fc764e7 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -475,7 +475,7 @@
/* Validate the request */
err = -EINVAL;
if (req.lnum < 0 || req.lnum >= vol->reserved_pebs ||
- req.bytes < 0 || req.lnum >= vol->usable_leb_size)
+ req.bytes < 0 || req.bytes > vol->usable_leb_size)
break;
err = get_exclusive(desc);
diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
index 0e11671d..930cf2c 100644
--- a/drivers/mtd/ubi/eba.c
+++ b/drivers/mtd/ubi/eba.c
@@ -1362,7 +1362,8 @@
* during re-size.
*/
ubi_move_aeb_to_list(av, aeb, &ai->erase);
- vol->eba_tbl[aeb->lnum] = aeb->pnum;
+ else
+ vol->eba_tbl[aeb->lnum] = aeb->pnum;
}
}
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 0648c69..bf8108d 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -330,6 +330,7 @@
av = tmp_av;
else {
ubi_err("orphaned volume in fastmap pool!");
+ kmem_cache_free(ai->aeb_slab_cache, new_aeb);
return UBI_BAD_FASTMAP;
}
diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c
index ec2c2dc..2a1b6e0 100644
--- a/drivers/mtd/ubi/upd.c
+++ b/drivers/mtd/ubi/upd.c
@@ -133,6 +133,10 @@
ubi_assert(!vol->updating && !vol->changing_leb);
vol->updating = 1;
+ vol->upd_buf = vmalloc(ubi->leb_size);
+ if (!vol->upd_buf)
+ return -ENOMEM;
+
err = set_update_marker(ubi, vol);
if (err)
return err;
@@ -152,14 +156,12 @@
err = clear_update_marker(ubi, vol, 0);
if (err)
return err;
+
+ vfree(vol->upd_buf);
vol->updating = 0;
return 0;
}
- vol->upd_buf = vmalloc(ubi->leb_size);
- if (!vol->upd_buf)
- return -ENOMEM;
-
vol->upd_ebs = div_u64(bytes + vol->usable_leb_size - 1,
vol->usable_leb_size);
vol->upd_bytes = bytes;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 5df49d3..c082540 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -999,7 +999,7 @@
int cancel)
{
int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
- int vol_id = -1, uninitialized_var(lnum);
+ int vol_id = -1, lnum = -1;
#ifdef CONFIG_MTD_UBI_FASTMAP
int anchor = wrk->anchor;
#endif
@@ -1069,6 +1069,9 @@
if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) {
dbg_wl("no WL needed: min used EC %d, max free EC %d",
e1->ec, e2->ec);
+
+ /* Give the unused PEB back */
+ wl_tree_add(e2, &ubi->free);
goto out_cancel;
}
self_check_in_wl_tree(ubi, e1, &ubi->used);
@@ -1206,7 +1209,6 @@
err = do_sync_erase(ubi, e1, vol_id, lnum, 0);
if (err) {
- kmem_cache_free(ubi_wl_entry_slab, e1);
if (e2)
kmem_cache_free(ubi_wl_entry_slab, e2);
goto out_ro;
@@ -1220,10 +1222,8 @@
dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase",
e2->pnum, vol_id, lnum);
err = do_sync_erase(ubi, e2, vol_id, lnum, 0);
- if (err) {
- kmem_cache_free(ubi_wl_entry_slab, e2);
+ if (err)
goto out_ro;
- }
}
dbg_wl("done");
@@ -1259,10 +1259,9 @@
ubi_free_vid_hdr(ubi, vid_hdr);
err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
- if (err) {
- kmem_cache_free(ubi_wl_entry_slab, e2);
+ if (err)
goto out_ro;
- }
+
mutex_unlock(&ubi->move_mutex);
return 0;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 3835321..3bc3ebc 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -139,6 +139,7 @@
config MACVTAP
tristate "MAC-VLAN based tap driver"
depends on MACVLAN
+ depends on INET
help
This adds a specialized tap character device driver that is based
on the MAC-VLAN network interface, called macvtap. A macvtap device
@@ -209,6 +210,7 @@
config TUN
tristate "Universal TUN/TAP device driver support"
+ depends on INET
select CRC32
---help---
TUN/TAP provides packet reception and transmission for user space
diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c
index a746ba2..a956053 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -1007,7 +1007,7 @@
soft = &pkt.soft.rfc1201;
- lp->hw.copy_from_card(dev, bufnum, 0, &pkt, sizeof(ARC_HDR_SIZE));
+ lp->hw.copy_from_card(dev, bufnum, 0, &pkt, ARC_HDR_SIZE);
if (pkt.hard.offset[0]) {
ofs = pkt.hard.offset[0];
length = 256 - ofs;
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 390061d..00c6c08 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1854,8 +1854,6 @@
BOND_AD_INFO(bond).agg_select_timer = timeout;
}
-static u16 aggregator_identifier;
-
/**
* bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures
* @bond: bonding struct to work on
@@ -1869,7 +1867,7 @@
if (MAC_ADDRESS_COMPARE(&(BOND_AD_INFO(bond).system.sys_mac_addr),
bond->dev->dev_addr)) {
- aggregator_identifier = 0;
+ BOND_AD_INFO(bond).aggregator_identifier = 0;
BOND_AD_INFO(bond).system.sys_priority = 0xFFFF;
BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr);
@@ -1940,7 +1938,7 @@
ad_initialize_agg(aggregator);
aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr);
- aggregator->aggregator_identifier = (++aggregator_identifier);
+ aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier;
aggregator->slave = slave;
aggregator->is_active = 0;
aggregator->num_of_ports = 0;
diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h
index 5d91ad0..1f081c8 100644
--- a/drivers/net/bonding/bond_3ad.h
+++ b/drivers/net/bonding/bond_3ad.h
@@ -253,6 +253,7 @@
struct ad_bond_info {
struct ad_system system; /* 802.3ad system structure */
u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes
+ u16 aggregator_identifier;
};
struct ad_slave_info {
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f975696..b143ce9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1991,6 +1991,7 @@
struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave, *oldcurrent;
struct sockaddr addr;
+ int old_flags = bond_dev->flags;
netdev_features_t old_features = bond_dev->features;
/* slave is not a slave or master is not master of this slave */
@@ -2123,12 +2124,18 @@
* already taken care of above when we detached the slave
*/
if (!USES_PRIMARY(bond->params.mode)) {
- /* unset promiscuity level from slave */
- if (bond_dev->flags & IFF_PROMISC)
+ /* unset promiscuity level from slave
+ * NOTE: The NETDEV_CHANGEADDR call above may change the value
+ * of the IFF_PROMISC flag in the bond_dev, but we need the
+ * value of that flag before that change, as that was the value
+ * when this slave was attached, so we cache at the start of the
+ * function and use it here. Same goes for ALLMULTI below
+ */
+ if (old_flags & IFF_PROMISC)
dev_set_promiscuity(slave_dev, -1);
/* unset allmulti level from slave */
- if (bond_dev->flags & IFF_ALLMULTI)
+ if (old_flags & IFF_ALLMULTI)
dev_set_allmulti(slave_dev, -1);
/* flush master's mc_list from slave */
@@ -3770,11 +3777,17 @@
* The bonding ndo_neigh_setup is called at init time beofre any
* slave exists. So we must declare proxy setup function which will
* be used at run time to resolve the actual slave neigh param setup.
+ *
+ * It's also called by master devices (such as vlans) to setup their
+ * underlying devices. In that case - do nothing, we're already set up from
+ * our init.
*/
static int bond_neigh_setup(struct net_device *dev,
struct neigh_parms *parms)
{
- parms->neigh_setup = bond_neigh_init;
+ /* modify only our neigh_parms */
+ if (parms->dev == dev)
+ parms->neigh_setup = bond_neigh_init;
return 0;
}
@@ -4982,6 +4995,7 @@
out:
return res;
err:
+ bond_destroy_debugfs();
rtnl_link_unregister(&bond_link_ops);
err_link:
unregister_pernet_subsys(&bond_net_ops);
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index d7434e0..a88d04b 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -537,8 +537,9 @@
goto out;
}
if (bond->params.mode == BOND_MODE_ALB ||
- bond->params.mode == BOND_MODE_TLB) {
- pr_info("%s: ARP monitoring cannot be used with ALB/TLB. Only MII monitoring is supported on %s.\n",
+ bond->params.mode == BOND_MODE_TLB ||
+ bond->params.mode == BOND_MODE_8023AD) {
+ pr_info("%s: ARP monitoring cannot be used with ALB/TLB/802.3ad. Only MII monitoring is supported on %s.\n",
bond->dev->name, bond->dev->name);
ret = -EINVAL;
goto out;
@@ -696,6 +697,8 @@
int new_value, ret = count;
struct bonding *bond = to_bond(d);
+ if (!rtnl_trylock())
+ return restart_syscall();
if (!(bond->params.miimon)) {
pr_err("%s: Unable to set down delay as MII monitoring is disabled\n",
bond->dev->name);
@@ -729,6 +732,7 @@
}
out:
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,
@@ -751,6 +755,8 @@
int new_value, ret = count;
struct bonding *bond = to_bond(d);
+ if (!rtnl_trylock())
+ return restart_syscall();
if (!(bond->params.miimon)) {
pr_err("%s: Unable to set up delay as MII monitoring is disabled\n",
bond->dev->name);
@@ -784,6 +790,7 @@
}
out:
+ rtnl_unlock();
return ret;
}
static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index db52f441..535d5dd 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -1409,10 +1409,10 @@
static const struct platform_device_id at91_can_id_table[] = {
{
- .name = "at91_can",
+ .name = "at91sam9x5_can",
.driver_data = (kernel_ulong_t)&at91_at91sam9x5_data,
}, {
- .name = "at91sam9x5_can",
+ .name = "at91_can",
.driver_data = (kernel_ulong_t)&at91_at91sam9263_data,
}, {
/* sentinel */
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index a668cd4..e59c42b 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -712,22 +712,31 @@
return 0;
}
-static int c_can_get_berr_counter(const struct net_device *dev,
- struct can_berr_counter *bec)
+static int __c_can_get_berr_counter(const struct net_device *dev,
+ struct can_berr_counter *bec)
{
unsigned int reg_err_counter;
struct c_can_priv *priv = netdev_priv(dev);
- c_can_pm_runtime_get_sync(priv);
-
reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
bec->rxerr = (reg_err_counter & ERR_CNT_REC_MASK) >>
ERR_CNT_REC_SHIFT;
bec->txerr = reg_err_counter & ERR_CNT_TEC_MASK;
+ return 0;
+}
+
+static int c_can_get_berr_counter(const struct net_device *dev,
+ struct can_berr_counter *bec)
+{
+ struct c_can_priv *priv = netdev_priv(dev);
+ int err;
+
+ c_can_pm_runtime_get_sync(priv);
+ err = __c_can_get_berr_counter(dev, bec);
c_can_pm_runtime_put_sync(priv);
- return 0;
+ return err;
}
/*
@@ -814,9 +823,6 @@
msg_ctrl_save = priv->read_reg(priv,
C_CAN_IFACE(MSGCTRL_REG, 0));
- if (msg_ctrl_save & IF_MCONT_EOB)
- return num_rx_pkts;
-
if (msg_ctrl_save & IF_MCONT_MSGLST) {
c_can_handle_lost_msg_obj(dev, 0, msg_obj);
num_rx_pkts++;
@@ -824,6 +830,9 @@
continue;
}
+ if (msg_ctrl_save & IF_MCONT_EOB)
+ return num_rx_pkts;
+
if (!(msg_ctrl_save & IF_MCONT_NEWDAT))
continue;
@@ -872,7 +881,7 @@
if (unlikely(!skb))
return 0;
- c_can_get_berr_counter(dev, &bec);
+ __c_can_get_berr_counter(dev, &bec);
reg_err_counter = priv->read_reg(priv, C_CAN_ERR_CNT_REG);
rx_err_passive = (reg_err_counter & ERR_CNT_RP_MASK) >>
ERR_CNT_RP_SHIFT;
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index f9cba41..f66aeb7 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -324,19 +324,10 @@
}
if (!priv->echo_skb[idx]) {
- struct sock *srcsk = skb->sk;
- if (atomic_read(&skb->users) != 1) {
- struct sk_buff *old_skb = skb;
-
- skb = skb_clone(old_skb, GFP_ATOMIC);
- kfree_skb(old_skb);
- if (!skb)
- return;
- } else
- skb_orphan(skb);
-
- skb->sk = srcsk;
+ skb = can_create_echo_skb(skb);
+ if (!skb)
+ return;
/* make settings for echo to reduce code in irq context */
skb->protocol = htons(ETH_P_CAN);
@@ -394,7 +385,7 @@
BUG_ON(idx >= priv->echo_skb_max);
if (priv->echo_skb[idx]) {
- kfree_skb(priv->echo_skb[idx]);
+ dev_kfree_skb_any(priv->echo_skb[idx]);
priv->echo_skb[idx] = NULL;
}
}
@@ -512,6 +503,14 @@
skb->pkt_type = PACKET_BROADCAST;
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb_reset_mac_header(skb);
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+
+ skb_reset_mac_header(skb);
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+
can_skb_reserve(skb);
can_skb_prv(skb)->ifindex = dev->ifindex;
@@ -652,10 +651,14 @@
if (dev->flags & IFF_UP)
return -EBUSY;
cm = nla_data(data[IFLA_CAN_CTRLMODE]);
- if (cm->flags & ~priv->ctrlmode_supported)
+
+ /* check whether changed bits are allowed to be modified */
+ if (cm->mask & ~priv->ctrlmode_supported)
return -EOPNOTSUPP;
+
+ /* clear bits to be modified and copy the flag values */
priv->ctrlmode &= ~cm->mask;
- priv->ctrlmode |= cm->flags;
+ priv->ctrlmode |= (cm->flags & cm->mask);
}
if (data[IFLA_CAN_BITTIMING]) {
@@ -705,14 +708,14 @@
size_t size;
size = nla_total_size(sizeof(u32)); /* IFLA_CAN_STATE */
- size += sizeof(struct can_ctrlmode); /* IFLA_CAN_CTRLMODE */
+ size += nla_total_size(sizeof(struct can_ctrlmode)); /* IFLA_CAN_CTRLMODE */
size += nla_total_size(sizeof(u32)); /* IFLA_CAN_RESTART_MS */
- size += sizeof(struct can_bittiming); /* IFLA_CAN_BITTIMING */
- size += sizeof(struct can_clock); /* IFLA_CAN_CLOCK */
+ size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */
+ size += nla_total_size(sizeof(struct can_clock)); /* IFLA_CAN_CLOCK */
if (priv->do_get_berr_counter) /* IFLA_CAN_BERR_COUNTER */
- size += sizeof(struct can_berr_counter);
+ size += nla_total_size(sizeof(struct can_berr_counter));
if (priv->bittiming_const) /* IFLA_CAN_BITTIMING_CONST */
- size += sizeof(struct can_bittiming_const);
+ size += nla_total_size(sizeof(struct can_bittiming_const));
return size;
}
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 769d29e..6d388cf 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -63,7 +63,7 @@
#define FLEXCAN_MCR_BCC BIT(16)
#define FLEXCAN_MCR_LPRIO_EN BIT(13)
#define FLEXCAN_MCR_AEN BIT(12)
-#define FLEXCAN_MCR_MAXMB(x) ((x) & 0xf)
+#define FLEXCAN_MCR_MAXMB(x) ((x) & 0x1f)
#define FLEXCAN_MCR_IDAM_A (0 << 8)
#define FLEXCAN_MCR_IDAM_B (1 << 8)
#define FLEXCAN_MCR_IDAM_C (2 << 8)
@@ -711,7 +711,6 @@
{
struct flexcan_priv *priv = netdev_priv(dev);
struct flexcan_regs __iomem *regs = priv->base;
- unsigned int i;
int err;
u32 reg_mcr, reg_ctrl;
@@ -745,9 +744,11 @@
*
*/
reg_mcr = flexcan_read(®s->mcr);
+ reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_FEN | FLEXCAN_MCR_HALT |
FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN |
- FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS;
+ FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS |
+ FLEXCAN_MCR_MAXMB(FLEXCAN_TX_BUF_ID);
netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr);
flexcan_write(reg_mcr, ®s->mcr);
@@ -781,16 +782,9 @@
netdev_dbg(dev, "%s: writing ctrl=0x%08x", __func__, reg_ctrl);
flexcan_write(reg_ctrl, ®s->ctrl);
- for (i = 0; i < ARRAY_SIZE(regs->cantxfg); i++) {
- flexcan_write(0, ®s->cantxfg[i].can_ctrl);
- flexcan_write(0, ®s->cantxfg[i].can_id);
- flexcan_write(0, ®s->cantxfg[i].data[0]);
- flexcan_write(0, ®s->cantxfg[i].data[1]);
-
- /* put MB into rx queue */
- flexcan_write(FLEXCAN_MB_CNT_CODE(0x4),
- ®s->cantxfg[i].can_ctrl);
- }
+ /* Abort any pending TX, mark Mailbox as INACTIVE */
+ flexcan_write(FLEXCAN_MB_CNT_CODE(0x4),
+ ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl);
/* acceptance mask/acceptance code (accept everything) */
flexcan_write(0x0, ®s->rxgmask);
@@ -868,7 +862,7 @@
/* start chip and queuing */
err = flexcan_chip_start(dev);
if (err)
- goto out_close;
+ goto out_free_irq;
can_led_event(dev, CAN_LED_EVENT_OPEN);
@@ -877,6 +871,8 @@
return 0;
+ out_free_irq:
+ free_irq(dev->irq, dev);
out_close:
close_candev(dev);
out:
@@ -983,9 +979,9 @@
}
static const struct of_device_id flexcan_of_match[] = {
- { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
- { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
+ { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
+ { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, flexcan_of_match);
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index c4bc1d2..b08383f 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -19,6 +19,7 @@
#include <linux/netdevice.h>
#include <linux/can.h>
#include <linux/can/dev.h>
+#include <linux/can/skb.h>
#include <linux/can/error.h>
#include <linux/mfd/janz.h>
@@ -1134,20 +1135,9 @@
*/
static void ican3_put_echo_skb(struct ican3_dev *mod, struct sk_buff *skb)
{
- struct sock *srcsk = skb->sk;
-
- if (atomic_read(&skb->users) != 1) {
- struct sk_buff *old_skb = skb;
-
- skb = skb_clone(old_skb, GFP_ATOMIC);
- kfree_skb(old_skb);
- if (!skb)
- return;
- } else {
- skb_orphan(skb);
- }
-
- skb->sk = srcsk;
+ skb = can_create_echo_skb(skb);
+ if (!skb)
+ return;
/* save this skb for tx interrupt echo handling */
skb_queue_tail(&mod->echoq, skb);
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 6b6f0ad..7042f5f 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -551,7 +551,7 @@
{
struct sja1000_priv *priv;
struct peak_pci_chan *chan;
- struct net_device *dev;
+ struct net_device *dev, *prev_dev;
void __iomem *cfg_base, *reg_base;
u16 sub_sys_id, icr;
int i, err, channels;
@@ -687,11 +687,13 @@
writew(0x0, cfg_base + PITA_ICR + 2);
chan = NULL;
- for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) {
- unregister_sja1000dev(dev);
- free_sja1000dev(dev);
+ for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) {
priv = netdev_priv(dev);
chan = priv->priv;
+ prev_dev = chan->prev_dev;
+
+ unregister_sja1000dev(dev);
+ free_sja1000dev(dev);
}
/* free any PCIeC resources too */
@@ -725,10 +727,12 @@
/* Loop over all registered devices */
while (1) {
+ struct net_device *prev_dev = chan->prev_dev;
+
dev_info(&pdev->dev, "removing device %s\n", dev->name);
unregister_sja1000dev(dev);
free_sja1000dev(dev);
- dev = chan->prev_dev;
+ dev = prev_dev;
if (!dev) {
/* do that only for first channel */
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 7164a99..f17c301 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -494,20 +494,20 @@
uint8_t isrc, status;
int n = 0;
- /* Shared interrupts and IRQ off? */
- if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
- return IRQ_NONE;
-
if (priv->pre_irq)
priv->pre_irq(priv);
+ /* Shared interrupts and IRQ off? */
+ if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF)
+ goto out;
+
while ((isrc = priv->read_reg(priv, SJA1000_IR)) &&
(n < SJA1000_MAX_IRQ)) {
- n++;
+
status = priv->read_reg(priv, SJA1000_SR);
/* check for absent controller due to hw unplug */
if (status == 0xFF && sja1000_is_absent(priv))
- return IRQ_NONE;
+ goto out;
if (isrc & IRQ_WUI)
netdev_warn(dev, "wakeup interrupt\n");
@@ -535,7 +535,7 @@
status = priv->read_reg(priv, SJA1000_SR);
/* check for absent controller */
if (status == 0xFF && sja1000_is_absent(priv))
- return IRQ_NONE;
+ goto out;
}
}
if (isrc & (IRQ_DOI | IRQ_EI | IRQ_BEI | IRQ_EPI | IRQ_ALI)) {
@@ -543,8 +543,9 @@
if (sja1000_err(dev, isrc, status))
break;
}
+ n++;
}
-
+out:
if (priv->post_irq)
priv->post_irq(priv);
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 6aa7b32..d5455c7 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -1132,6 +1132,7 @@
}
}
unlink_all_urbs(dev);
+ kfree(dev);
}
}
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 3b95465..a3fb8b5 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -474,6 +474,8 @@
return err;
dev->nchannels = msg.u.cardinfo.nchannels;
+ if (dev->nchannels > MAX_NET_DEVICES)
+ return -EINVAL;
return 0;
}
@@ -577,7 +579,7 @@
usb_sndbulkpipe(dev->udev,
dev->bulk_out->bEndpointAddress),
buf, msg->len,
- kvaser_usb_simple_msg_callback, priv);
+ kvaser_usb_simple_msg_callback, netdev);
usb_anchor_urb(urb, &priv->tx_submitted);
err = usb_submit_urb(urb, GFP_ATOMIC);
@@ -652,11 +654,6 @@
priv = dev->nets[channel];
stats = &priv->netdev->stats;
- if (status & M16C_STATE_BUS_RESET) {
- kvaser_usb_unlink_tx_urbs(priv);
- return;
- }
-
skb = alloc_can_err_skb(priv->netdev, &cf);
if (!skb) {
stats->rx_dropped++;
@@ -667,7 +664,7 @@
netdev_dbg(priv->netdev, "Error status: 0x%02x\n", status);
- if (status & M16C_STATE_BUS_OFF) {
+ if (status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
cf->can_id |= CAN_ERR_BUSOFF;
priv->can.can_stats.bus_off++;
@@ -693,9 +690,7 @@
}
new_state = CAN_STATE_ERROR_PASSIVE;
- }
-
- if (status == M16C_STATE_BUS_ERROR) {
+ } else if (status & M16C_STATE_BUS_ERROR) {
if ((priv->can.state < CAN_STATE_ERROR_WARNING) &&
((txerr >= 96) || (rxerr >= 96))) {
cf->can_id |= CAN_ERR_CRTL;
@@ -705,7 +700,8 @@
priv->can.can_stats.error_warning++;
new_state = CAN_STATE_ERROR_WARNING;
- } else if (priv->can.state > CAN_STATE_ERROR_ACTIVE) {
+ } else if ((priv->can.state > CAN_STATE_ERROR_ACTIVE) &&
+ ((txerr < 96) && (rxerr < 96))) {
cf->can_id |= CAN_ERR_PROT;
cf->data[2] = CAN_ERR_PROT_ACTIVE;
@@ -1236,6 +1232,9 @@
if (err)
netdev_warn(netdev, "Cannot stop device, error %d\n", err);
+ /* reset tx contexts */
+ kvaser_usb_unlink_tx_urbs(priv);
+
priv->can.state = CAN_STATE_STOPPED;
close_candev(priv->netdev);
@@ -1284,12 +1283,14 @@
if (!urb) {
netdev_err(netdev, "No memory left for URBs\n");
stats->tx_dropped++;
- goto nourbmem;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
}
buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
if (!buf) {
stats->tx_dropped++;
+ dev_kfree_skb(skb);
goto nobufmem;
}
@@ -1324,6 +1325,7 @@
}
}
+ /* This should never happen; it implies a flow control bug */
if (!context) {
netdev_warn(netdev, "cannot find free context\n");
ret = NETDEV_TX_BUSY;
@@ -1354,9 +1356,6 @@
if (unlikely(err)) {
can_free_echo_skb(netdev, context->echo_index);
- skb = NULL; /* set to NULL to avoid double free in
- * dev_kfree_skb(skb) */
-
atomic_dec(&priv->active_tx_urbs);
usb_unanchor_urb(urb);
@@ -1378,8 +1377,6 @@
kfree(buf);
nobufmem:
usb_free_urb(urb);
-nourbmem:
- dev_kfree_skb(skb);
return ret;
}
@@ -1491,6 +1488,10 @@
struct kvaser_usb_net_priv *priv;
int i, err;
+ err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel);
+ if (err)
+ return err;
+
netdev = alloc_candev(sizeof(*priv), MAX_TX_URBS);
if (!netdev) {
dev_err(&intf->dev, "Cannot alloc candev\n");
@@ -1544,9 +1545,9 @@
return 0;
}
-static void kvaser_usb_get_endpoints(const struct usb_interface *intf,
- struct usb_endpoint_descriptor **in,
- struct usb_endpoint_descriptor **out)
+static int kvaser_usb_get_endpoints(const struct usb_interface *intf,
+ struct usb_endpoint_descriptor **in,
+ struct usb_endpoint_descriptor **out)
{
const struct usb_host_interface *iface_desc;
struct usb_endpoint_descriptor *endpoint;
@@ -1557,12 +1558,18 @@
for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
endpoint = &iface_desc->endpoint[i].desc;
- if (usb_endpoint_is_bulk_in(endpoint))
+ if (!*in && usb_endpoint_is_bulk_in(endpoint))
*in = endpoint;
- if (usb_endpoint_is_bulk_out(endpoint))
+ if (!*out && usb_endpoint_is_bulk_out(endpoint))
*out = endpoint;
+
+ /* use first bulk endpoint for in and out */
+ if (*in && *out)
+ return 0;
}
+
+ return -ENODEV;
}
static int kvaser_usb_probe(struct usb_interface *intf,
@@ -1570,14 +1577,14 @@
{
struct kvaser_usb *dev;
int err = -ENOMEM;
- int i;
+ int i, retry = 3;
dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
if (!dev)
return -ENOMEM;
- kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
- if (!dev->bulk_in || !dev->bulk_out) {
+ err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
+ if (err) {
dev_err(&intf->dev, "Cannot get usb endpoint(s)");
return err;
}
@@ -1588,10 +1595,15 @@
usb_set_intfdata(intf, dev);
- for (i = 0; i < MAX_NET_DEVICES; i++)
- kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, i);
+ /* On some x86 laptops, plugging a Kvaser device again after
+ * an unplug makes the firmware always ignore the very first
+ * command. For such a case, provide some room for retries
+ * instead of completely exiting the driver.
+ */
+ do {
+ err = kvaser_usb_get_software_info(dev);
+ } while (--retry && err == -ETIMEDOUT);
- err = kvaser_usb_get_software_info(dev);
if (err) {
dev_err(&intf->dev,
"Cannot get software infos, error %d\n", err);
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 25723d8..925ab8e 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -649,7 +649,7 @@
if ((mc->ptr + rec_len) > mc->end)
goto decode_failed;
- memcpy(cf->data, mc->ptr, rec_len);
+ memcpy(cf->data, mc->ptr, cf->can_dlc);
mc->ptr += rec_len;
}
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index a0f647f..3a220d2 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -727,7 +727,7 @@
dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
if (!dev->cmd_buf) {
err = -ENOMEM;
- goto lbl_set_intf_data;
+ goto lbl_free_candev;
}
dev->udev = usb_dev;
@@ -766,7 +766,7 @@
err = register_candev(netdev);
if (err) {
dev_err(&intf->dev, "couldn't register CAN device: %d\n", err);
- goto lbl_free_cmd_buf;
+ goto lbl_restore_intf_data;
}
if (dev->prev_siblings)
@@ -779,14 +779,14 @@
if (dev->adapter->dev_init) {
err = dev->adapter->dev_init(dev);
if (err)
- goto lbl_free_cmd_buf;
+ goto lbl_unregister_candev;
}
/* set bus off */
if (dev->adapter->dev_set_bus) {
err = dev->adapter->dev_set_bus(dev, 0);
if (err)
- goto lbl_free_cmd_buf;
+ goto lbl_unregister_candev;
}
/* get device number early */
@@ -798,11 +798,14 @@
return 0;
-lbl_free_cmd_buf:
+lbl_unregister_candev:
+ unregister_candev(netdev);
+
+lbl_restore_intf_data:
+ usb_set_intfdata(intf, dev->prev_siblings);
kfree(dev->cmd_buf);
-lbl_set_intf_data:
- usb_set_intfdata(intf, dev->prev_siblings);
+lbl_free_candev:
free_candev(netdev);
return err;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 8ee9d15..f7f796a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -333,8 +333,6 @@
if (!(dev->state & PCAN_USB_STATE_CONNECTED))
return 0;
- memset(req_addr, '\0', req_size);
-
req_type = USB_TYPE_VENDOR | USB_RECIP_OTHER;
switch (req_id) {
@@ -345,6 +343,7 @@
default:
p = usb_rcvctrlpipe(dev->udev, 0);
req_type |= USB_DIR_IN;
+ memset(req_addr, '\0', req_size);
break;
}
@@ -927,6 +926,9 @@
/* set LED in default state (end of init phase) */
pcan_usb_pro_set_led(dev, 0, 1);
+ kfree(bi);
+ kfree(fi);
+
return 0;
err_out:
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 0a2a5ee..4e94057 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -46,6 +46,7 @@
#include <linux/if_ether.h>
#include <linux/can.h>
#include <linux/can/dev.h>
+#include <linux/can/skb.h>
#include <linux/slab.h>
#include <net/rtnetlink.h>
@@ -109,25 +110,23 @@
stats->rx_packets++;
stats->rx_bytes += cfd->len;
}
- kfree_skb(skb);
+ consume_skb(skb);
return NETDEV_TX_OK;
}
/* perform standard echo handling for CAN network interfaces */
if (loop) {
- struct sock *srcsk = skb->sk;
- skb = skb_share_check(skb, GFP_ATOMIC);
+ skb = can_create_echo_skb(skb);
if (!skb)
return NETDEV_TX_OK;
/* receive with packet counting */
- skb->sk = srcsk;
vcan_rx(skb, dev);
} else {
/* no looped packets => no counting */
- kfree_skb(skb);
+ consume_skb(skb);
}
return NETDEV_TX_OK;
}
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 42aa54a..b710c6b 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -185,6 +185,8 @@
rtnl_lock();
err = __rtnl_link_register(&dummy_link_ops);
+ if (err < 0)
+ goto out;
for (i = 0; i < numdummies && !err; i++) {
err = dummy_init_one();
@@ -192,6 +194,8 @@
}
if (err < 0)
__rtnl_link_unregister(&dummy_link_ops);
+
+out:
rtnl_unlock();
return err;
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index ed21307..f6415fd 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -1516,7 +1516,7 @@
{
struct pcnet32_private *lp;
int i, media;
- int fdx, mii, fset, dxsuflo;
+ int fdx, mii, fset, dxsuflo, sram;
int chip_version;
char *chipname;
struct net_device *dev;
@@ -1553,7 +1553,7 @@
}
/* initialize variables */
- fdx = mii = fset = dxsuflo = 0;
+ fdx = mii = fset = dxsuflo = sram = 0;
chip_version = (chip_version >> 12) & 0xffff;
switch (chip_version) {
@@ -1586,6 +1586,7 @@
chipname = "PCnet/FAST III 79C973"; /* PCI */
fdx = 1;
mii = 1;
+ sram = 1;
break;
case 0x2626:
chipname = "PCnet/Home 79C978"; /* PCI */
@@ -1609,6 +1610,7 @@
chipname = "PCnet/FAST III 79C975"; /* PCI */
fdx = 1;
mii = 1;
+ sram = 1;
break;
case 0x2628:
chipname = "PCnet/PRO 79C976";
@@ -1637,6 +1639,31 @@
dxsuflo = 1;
}
+ /*
+ * The Am79C973/Am79C975 controllers come with 12K of SRAM
+ * which we can use for the Tx/Rx buffers but most importantly,
+ * the use of SRAM allow us to use the BCR18:NOUFLO bit to avoid
+ * Tx fifo underflows.
+ */
+ if (sram) {
+ /*
+ * The SRAM is being configured in two steps. First we
+ * set the SRAM size in the BCR25:SRAM_SIZE bits. According
+ * to the datasheet, each bit corresponds to a 512-byte
+ * page so we can have at most 24 pages. The SRAM_SIZE
+ * holds the value of the upper 8 bits of the 16-bit SRAM size.
+ * The low 8-bits start at 0x00 and end at 0xff. So the
+ * address range is from 0x0000 up to 0x17ff. Therefore,
+ * the SRAM_SIZE is set to 0x17. The next step is to set
+ * the BCR26:SRAM_BND midway through so the Tx and Rx
+ * buffers can share the SRAM equally.
+ */
+ a->write_bcr(ioaddr, 25, 0x17);
+ a->write_bcr(ioaddr, 26, 0xc);
+ /* And finally enable the NOUFLO bit */
+ a->write_bcr(ioaddr, 18, a->read_bcr(ioaddr, 18) | (1 << 11));
+ }
+
dev = alloc_etherdev(sizeof(*lp));
if (!dev) {
ret = -ENOMEM;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 418de8b..a85a9c2 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -184,15 +184,16 @@
schedule_work(&alx->reset_wk);
}
-static bool alx_clean_rx_irq(struct alx_priv *alx, int budget)
+static int alx_clean_rx_irq(struct alx_priv *alx, int budget)
{
struct alx_rx_queue *rxq = &alx->rxq;
struct alx_rrd *rrd;
struct alx_buffer *rxb;
struct sk_buff *skb;
u16 length, rfd_cleaned = 0;
+ int work = 0;
- while (budget > 0) {
+ while (work < budget) {
rrd = &rxq->rrd[rxq->rrd_read_idx];
if (!(rrd->word3 & cpu_to_le32(1 << RRD_UPDATED_SHIFT)))
break;
@@ -203,7 +204,7 @@
ALX_GET_FIELD(le32_to_cpu(rrd->word0),
RRD_NOR) != 1) {
alx_schedule_reset(alx);
- return 0;
+ return work;
}
rxb = &rxq->bufs[rxq->read_idx];
@@ -243,7 +244,7 @@
}
napi_gro_receive(&alx->napi, skb);
- budget--;
+ work++;
next_pkt:
if (++rxq->read_idx == alx->rx_ringsz)
@@ -258,21 +259,22 @@
if (rfd_cleaned)
alx_refill_rx_ring(alx, GFP_ATOMIC);
- return budget > 0;
+ return work;
}
static int alx_poll(struct napi_struct *napi, int budget)
{
struct alx_priv *alx = container_of(napi, struct alx_priv, napi);
struct alx_hw *hw = &alx->hw;
- bool complete = true;
unsigned long flags;
+ bool tx_complete;
+ int work;
- complete = alx_clean_tx_irq(alx) &&
- alx_clean_rx_irq(alx, budget);
+ tx_complete = alx_clean_tx_irq(alx);
+ work = alx_clean_rx_irq(alx, budget);
- if (!complete)
- return 1;
+ if (!tx_complete || work == budget)
+ return budget;
napi_complete(&alx->napi);
@@ -284,7 +286,7 @@
alx_post_write(hw);
- return 0;
+ return work;
}
static irqreturn_t alx_intr_handle(struct alx_priv *alx, u32 intr)
@@ -1303,6 +1305,8 @@
SET_NETDEV_DEV(netdev, &pdev->dev);
alx = netdev_priv(netdev);
+ spin_lock_init(&alx->hw.mdio_lock);
+ spin_lock_init(&alx->irq_lock);
alx->dev = netdev;
alx->hw.pdev = pdev;
alx->msg_enable = NETIF_MSG_LINK | NETIF_MSG_HW | NETIF_MSG_IFUP |
@@ -1385,9 +1389,6 @@
INIT_WORK(&alx->link_check_wk, alx_link_check);
INIT_WORK(&alx->reset_wk, alx_reset);
- spin_lock_init(&alx->hw.mdio_lock);
- spin_lock_init(&alx->irq_lock);
-
netif_carrier_off(netdev);
err = register_netdev(netdev);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h
index b2bf324..0f05565 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c.h
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h
@@ -520,6 +520,9 @@
struct net_device *netdev;
struct pci_dev *pdev;
struct napi_struct napi;
+ struct page *rx_page;
+ unsigned int rx_page_offset;
+ unsigned int rx_frag_size;
struct atl1c_hw hw;
struct atl1c_hw_stats hw_stats;
struct mii_if_info mii; /* MII interface info */
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 0ba9007..11cdf1d 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -481,10 +481,15 @@
static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter,
struct net_device *dev)
{
+ unsigned int head_size;
int mtu = dev->mtu;
adapter->rx_buffer_len = mtu > AT_RX_BUF_SIZE ?
roundup(mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN, 8) : AT_RX_BUF_SIZE;
+
+ head_size = SKB_DATA_ALIGN(adapter->rx_buffer_len + NET_SKB_PAD) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ adapter->rx_frag_size = roundup_pow_of_two(head_size);
}
static netdev_features_t atl1c_fix_features(struct net_device *netdev,
@@ -952,6 +957,10 @@
kfree(adapter->tpd_ring[0].buffer_info);
adapter->tpd_ring[0].buffer_info = NULL;
}
+ if (adapter->rx_page) {
+ put_page(adapter->rx_page);
+ adapter->rx_page = NULL;
+ }
}
/**
@@ -1639,6 +1648,35 @@
skb_checksum_none_assert(skb);
}
+static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter)
+{
+ struct sk_buff *skb;
+ struct page *page;
+
+ if (adapter->rx_frag_size > PAGE_SIZE)
+ return netdev_alloc_skb(adapter->netdev,
+ adapter->rx_buffer_len);
+
+ page = adapter->rx_page;
+ if (!page) {
+ adapter->rx_page = page = alloc_page(GFP_ATOMIC);
+ if (unlikely(!page))
+ return NULL;
+ adapter->rx_page_offset = 0;
+ }
+
+ skb = build_skb(page_address(page) + adapter->rx_page_offset,
+ adapter->rx_frag_size);
+ if (likely(skb)) {
+ adapter->rx_page_offset += adapter->rx_frag_size;
+ if (adapter->rx_page_offset >= PAGE_SIZE)
+ adapter->rx_page = NULL;
+ else
+ get_page(page);
+ }
+ return skb;
+}
+
static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
{
struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring;
@@ -1660,7 +1698,7 @@
while (next_info->flags & ATL1C_BUFFER_FREE) {
rfd_desc = ATL1C_RFD_DESC(rfd_ring, rfd_next_to_use);
- skb = netdev_alloc_skb(adapter->netdev, adapter->rx_buffer_len);
+ skb = atl1c_alloc_skb(adapter);
if (unlikely(!skb)) {
if (netif_msg_rx_err(adapter))
dev_warn(&pdev->dev, "alloc rx buffer failed\n");
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 0688bb8..c23bb02 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1665,8 +1665,8 @@
return 0;
}
-static void atl1e_tx_map(struct atl1e_adapter *adapter,
- struct sk_buff *skb, struct atl1e_tpd_desc *tpd)
+static int atl1e_tx_map(struct atl1e_adapter *adapter,
+ struct sk_buff *skb, struct atl1e_tpd_desc *tpd)
{
struct atl1e_tpd_desc *use_tpd = NULL;
struct atl1e_tx_buffer *tx_buffer = NULL;
@@ -1677,6 +1677,8 @@
u16 nr_frags;
u16 f;
int segment;
+ int ring_start = adapter->tx_ring.next_to_use;
+ int ring_end;
nr_frags = skb_shinfo(skb)->nr_frags;
segment = (tpd->word3 >> TPD_SEGMENT_EN_SHIFT) & TPD_SEGMENT_EN_MASK;
@@ -1689,6 +1691,9 @@
tx_buffer->length = map_len;
tx_buffer->dma = pci_map_single(adapter->pdev,
skb->data, hdr_len, PCI_DMA_TODEVICE);
+ if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma))
+ return -ENOSPC;
+
ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_SINGLE);
mapped_len += map_len;
use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma);
@@ -1715,6 +1720,22 @@
tx_buffer->dma =
pci_map_single(adapter->pdev, skb->data + mapped_len,
map_len, PCI_DMA_TODEVICE);
+
+ if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) {
+ /* We need to unwind the mappings we've done */
+ ring_end = adapter->tx_ring.next_to_use;
+ adapter->tx_ring.next_to_use = ring_start;
+ while (adapter->tx_ring.next_to_use != ring_end) {
+ tpd = atl1e_get_tpd(adapter);
+ tx_buffer = atl1e_get_tx_buffer(adapter, tpd);
+ pci_unmap_single(adapter->pdev, tx_buffer->dma,
+ tx_buffer->length, PCI_DMA_TODEVICE);
+ }
+ /* Reset the tx rings next pointer */
+ adapter->tx_ring.next_to_use = ring_start;
+ return -ENOSPC;
+ }
+
ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_SINGLE);
mapped_len += map_len;
use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma);
@@ -1750,6 +1771,23 @@
(i * MAX_TX_BUF_LEN),
tx_buffer->length,
DMA_TO_DEVICE);
+
+ if (dma_mapping_error(&adapter->pdev->dev, tx_buffer->dma)) {
+ /* We need to unwind the mappings we've done */
+ ring_end = adapter->tx_ring.next_to_use;
+ adapter->tx_ring.next_to_use = ring_start;
+ while (adapter->tx_ring.next_to_use != ring_end) {
+ tpd = atl1e_get_tpd(adapter);
+ tx_buffer = atl1e_get_tx_buffer(adapter, tpd);
+ dma_unmap_page(&adapter->pdev->dev, tx_buffer->dma,
+ tx_buffer->length, DMA_TO_DEVICE);
+ }
+
+ /* Reset the ring next to use pointer */
+ adapter->tx_ring.next_to_use = ring_start;
+ return -ENOSPC;
+ }
+
ATL1E_SET_PCIMAP_TYPE(tx_buffer, ATL1E_TX_PCIMAP_PAGE);
use_tpd->buffer_addr = cpu_to_le64(tx_buffer->dma);
use_tpd->word2 = (use_tpd->word2 & (~TPD_BUFLEN_MASK)) |
@@ -1767,6 +1805,7 @@
/* The last buffer info contain the skb address,
so it will be free after unmap */
tx_buffer->skb = skb;
+ return 0;
}
static void atl1e_tx_queue(struct atl1e_adapter *adapter, u16 count,
@@ -1834,10 +1873,15 @@
return NETDEV_TX_OK;
}
- atl1e_tx_map(adapter, skb, tpd);
+ if (atl1e_tx_map(adapter, skb, tpd)) {
+ dev_kfree_skb_any(skb);
+ goto out;
+ }
+
atl1e_tx_queue(adapter, tpd_req, tpd);
netdev->trans_start = jiffies; /* NETIF_F_LLTX driver :( */
+out:
spin_unlock_irqrestore(&adapter->tx_lock, flags);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index eec0af4..1c6bc96 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -908,7 +908,7 @@
struct bcma_drv_cc *cc = &bgmac->core->bus->drv_cc;
u8 et_swtype = 0;
u8 sw_type = BGMAC_CHIPCTL_1_SW_TYPE_EPHY |
- BGMAC_CHIPCTL_1_IF_TYPE_RMII;
+ BGMAC_CHIPCTL_1_IF_TYPE_MII;
char buf[2];
if (bcm47xx_nvram_getenv("et_swtype", buf, 1) > 0) {
diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h
index 98d4b5f..12a35cf 100644
--- a/drivers/net/ethernet/broadcom/bgmac.h
+++ b/drivers/net/ethernet/broadcom/bgmac.h
@@ -333,7 +333,7 @@
#define BGMAC_CHIPCTL_1_IF_TYPE_MASK 0x00000030
#define BGMAC_CHIPCTL_1_IF_TYPE_RMII 0x00000000
-#define BGMAC_CHIPCTL_1_IF_TYPE_MI 0x00000010
+#define BGMAC_CHIPCTL_1_IF_TYPE_MII 0x00000010
#define BGMAC_CHIPCTL_1_IF_TYPE_RGMII 0x00000020
#define BGMAC_CHIPCTL_1_SW_TYPE_MASK 0x000000C0
#define BGMAC_CHIPCTL_1_SW_TYPE_EPHY 0x00000000
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 5d20449..161dcba 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -2869,7 +2869,7 @@
sw_cons = BNX2_NEXT_TX_BD(sw_cons);
tx_bytes += skb->len;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
tx_pkt++;
if (tx_pkt == budget)
break;
@@ -6610,7 +6610,7 @@
mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
if (dma_mapping_error(&bp->pdev->dev, mapping)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -6703,7 +6703,7 @@
PCI_DMA_TODEVICE);
}
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 3dba2a7..ec86177 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -312,6 +312,7 @@
u8 flags;
/* Set on the first BD descriptor when there is a split BD */
#define BNX2X_TSO_SPLIT_BD (1<<0)
+#define BNX2X_HAS_SECOND_PBD (1<<1)
};
struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 638e554..372a755 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -153,6 +153,7 @@
struct sk_buff *skb = tx_buf->skb;
u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons;
int nbd;
+ u16 split_bd_len = 0;
/* prefetch skb end pointer to speedup dev_kfree_skb() */
prefetch(&skb->end);
@@ -160,10 +161,7 @@
DP(NETIF_MSG_TX_DONE, "fp[%d]: pkt_idx %d buff @(%p)->skb %p\n",
txdata->txq_index, idx, tx_buf, skb);
- /* unmap first bd */
tx_start_bd = &txdata->tx_desc_ring[bd_idx].start_bd;
- dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
- BD_UNMAP_LEN(tx_start_bd), DMA_TO_DEVICE);
nbd = le16_to_cpu(tx_start_bd->nbd) - 1;
@@ -182,12 +180,25 @@
--nbd;
bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
- /* ...and the TSO split header bd since they have no mapping */
- if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
+ if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+ /* Skip second parse bd... */
--nbd;
bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
}
+ /* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
+ if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
+ tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
+ split_bd_len = BD_UNMAP_LEN(tx_data_bd);
+ --nbd;
+ bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+ }
+
+ /* unmap first bd */
+ dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
+ BD_UNMAP_LEN(tx_start_bd) + split_bd_len,
+ DMA_TO_DEVICE);
+
/* now free frags */
while (nbd > 0) {
@@ -670,6 +681,7 @@
}
}
#endif
+ skb_record_rx_queue(skb, fp->rx_queue);
napi_gro_receive(&fp->napi, skb);
}
@@ -739,7 +751,8 @@
return;
}
- bnx2x_frag_free(fp, new_data);
+ if (new_data)
+ bnx2x_frag_free(fp, new_data);
drop:
/* drop the packet and keep the buffer in the bin */
DP(NETIF_MSG_RX_STATUS,
@@ -3748,6 +3761,9 @@
/* set encapsulation flag in start BD */
SET_FLAG(tx_start_bd->general_data,
ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+ tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
nbd++;
} else if (xmit_type & XMIT_CSUM) {
/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 32a9609..fd50781 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -1038,9 +1038,6 @@
ETH_VLAN_FILTER_CLASSIFY, config);
}
-#define list_next_entry(pos, member) \
- list_entry((pos)->member.next, typeof(*(pos)), member)
-
/**
* bnx2x_vlan_mac_restore - reconfigure next MAC/VLAN/VLAN-MAC element
*
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index a13463e..680d26d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -3003,6 +3003,19 @@
return false;
}
+static bool tg3_phy_led_bug(struct tg3 *tp)
+{
+ switch (tg3_asic_rev(tp)) {
+ case ASIC_REV_5719:
+ if ((tp->phy_flags & TG3_PHYFLG_MII_SERDES) &&
+ !tp->pci_fn)
+ return true;
+ return false;
+ }
+
+ return false;
+}
+
static void tg3_power_down_phy(struct tg3 *tp, bool do_low_power)
{
u32 val;
@@ -3050,8 +3063,9 @@
}
return;
} else if (do_low_power) {
- tg3_writephy(tp, MII_TG3_EXT_CTRL,
- MII_TG3_EXT_CTRL_FORCE_LED_OFF);
+ if (!tg3_phy_led_bug(tp))
+ tg3_writephy(tp, MII_TG3_EXT_CTRL,
+ MII_TG3_EXT_CTRL_FORCE_LED_OFF);
val = MII_TG3_AUXCTL_PCTL_100TX_LPWR |
MII_TG3_AUXCTL_PCTL_SPR_ISOLATE |
@@ -6423,7 +6437,7 @@
pkts_compl++;
bytes_compl += skb->len;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
if (unlikely(tx_bug)) {
tg3_tx_recover(tp);
@@ -6673,8 +6687,7 @@
work_mask |= opaque_key;
- if ((desc->err_vlan & RXD_ERR_MASK) != 0 &&
- (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) {
+ if (desc->err_vlan & RXD_ERR_MASK) {
drop_it:
tg3_recycle_rx(tnapi, tpr, opaque_key,
desc_idx, *post_ptr);
@@ -6708,12 +6721,6 @@
pci_unmap_single(tp->pdev, dma_addr, skb_size,
PCI_DMA_FROMDEVICE);
- skb = build_skb(data, frag_size);
- if (!skb) {
- tg3_frag_free(frag_size != 0, data);
- goto drop_it_no_recycle;
- }
- skb_reserve(skb, TG3_RX_OFFSET(tp));
/* Ensure that the update to the data happens
* after the usage of the old DMA mapping.
*/
@@ -6721,6 +6728,12 @@
ri->data = NULL;
+ skb = build_skb(data, frag_size);
+ if (!skb) {
+ tg3_frag_free(frag_size != 0, data);
+ goto drop_it_no_recycle;
+ }
+ skb_reserve(skb, TG3_RX_OFFSET(tp));
} else {
tg3_recycle_rx(tnapi, tpr, opaque_key,
desc_idx, *post_ptr);
@@ -6754,8 +6767,9 @@
skb->protocol = eth_type_trans(skb, tp->dev);
if (len > (tp->dev->mtu + ETH_HLEN) &&
- skb->protocol != htons(ETH_P_8021Q)) {
- dev_kfree_skb(skb);
+ skb->protocol != htons(ETH_P_8021Q) &&
+ skb->protocol != htons(ETH_P_8021AD)) {
+ dev_kfree_skb_any(skb);
goto drop_it_no_recycle;
}
@@ -7468,7 +7482,7 @@
{
u32 base = (u32) mapping & 0xffffffff;
- return (base > 0xffffdcc0) && (base + len + 8 < base);
+ return base + len + 8 < base;
}
/* Test for TSO DMA buffers that cross into regions which are within MSS bytes
@@ -7638,7 +7652,7 @@
PCI_DMA_TODEVICE);
/* Make sure the mapping succeeded */
if (pci_dma_mapping_error(tp->pdev, new_addr)) {
- dev_kfree_skb(new_skb);
+ dev_kfree_skb_any(new_skb);
ret = -1;
} else {
u32 save_entry = *entry;
@@ -7653,13 +7667,13 @@
new_skb->len, base_flags,
mss, vlan)) {
tg3_tx_skb_unmap(tnapi, save_entry, -1);
- dev_kfree_skb(new_skb);
+ dev_kfree_skb_any(new_skb);
ret = -1;
}
}
}
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
*pskb = new_skb;
return ret;
}
@@ -7702,7 +7716,7 @@
} while (segs);
tg3_tso_bug_end:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -7746,8 +7760,6 @@
entry = tnapi->tx_prod;
base_flags = 0;
- if (skb->ip_summed == CHECKSUM_PARTIAL)
- base_flags |= TXD_FLAG_TCPUDP_CSUM;
mss = skb_shinfo(skb)->gso_size;
if (mss) {
@@ -7763,6 +7775,13 @@
hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN;
+ /* HW/FW can not correctly segment packets that have been
+ * vlan encapsulated.
+ */
+ if (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD))
+ return tg3_tso_bug(tp, skb);
+
if (!skb_is_gso_v6(skb)) {
iph->check = 0;
iph->tot_len = htons(mss + hdr_len);
@@ -7809,6 +7828,17 @@
base_flags |= tsflags << 12;
}
}
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ /* HW/FW can not correctly checksum packets that have been
+ * vlan encapsulated.
+ */
+ if (skb->protocol == htons(ETH_P_8021Q) ||
+ skb->protocol == htons(ETH_P_8021AD)) {
+ if (skb_checksum_help(skb))
+ goto drop;
+ } else {
+ base_flags |= TXD_FLAG_TCPUDP_CSUM;
+ }
}
if (tg3_flag(tp, USE_JUMBO_BDFLAG) &&
@@ -7924,7 +7954,7 @@
tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, --i);
tnapi->tx_buffers[tnapi->tx_prod].skb = NULL;
drop:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
drop_nofree:
tp->tx_dropped++;
return NETDEV_TX_OK;
@@ -8362,7 +8392,8 @@
if (tnapi->rx_rcb)
memset(tnapi->rx_rcb, 0, TG3_RX_RCB_RING_BYTES(tp));
- if (tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
+ if (tnapi->prodring.rx_std &&
+ tg3_rx_prodring_alloc(tp, &tnapi->prodring)) {
tg3_free_rings(tp);
return -ENOMEM;
}
@@ -12060,7 +12091,9 @@
if (tg3_flag(tp, MAX_RXPEND_64) &&
tp->rx_pending > 63)
tp->rx_pending = 63;
- tp->rx_jumbo_pending = ering->rx_jumbo_pending;
+
+ if (tg3_flag(tp, JUMBO_RING_ENABLE))
+ tp->rx_jumbo_pending = ering->rx_jumbo_pending;
for (i = 0; i < tp->irq_max; i++)
tp->napi[i].tx_pending = ering->tx_pending;
@@ -13763,12 +13796,12 @@
tg3_netif_stop(tp);
+ tg3_set_mtu(dev, tp, new_mtu);
+
tg3_full_lock(tp, 1);
tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
- tg3_set_mtu(dev, tp, new_mtu);
-
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
@@ -16283,6 +16316,9 @@
/* Clear this out for sanity. */
tw32(TG3PCI_MEM_WIN_BASE_ADDR, 0);
+ /* Clear TG3PCI_REG_BASE_ADDR to prevent hangs. */
+ tw32(TG3PCI_REG_BASE_ADDR, 0);
+
pci_read_config_dword(tp->pdev, TG3PCI_PCISTATE,
&pci_state_reg);
if ((pci_state_reg & PCISTATE_CONV_PCI_MODE) == 0 &&
@@ -17292,8 +17328,6 @@
tg3_init_bufmgr_config(tp);
- features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
-
/* 5700 B0 chips do not support checksumming correctly due
* to hardware bugs.
*/
@@ -17325,7 +17359,8 @@
features |= NETIF_F_TSO_ECN;
}
- dev->features |= features;
+ dev->features |= features | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_CTAG_RX;
dev->vlan_features |= features;
/*
@@ -17354,23 +17389,6 @@
goto err_out_apeunmap;
}
- /*
- * Reset chip in case UNDI or EFI driver did not shutdown
- * DMA self test will enable WDMAC and we'll see (spurious)
- * pending DMA on the PCI bus at that point.
- */
- if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) ||
- (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
- tw32(MEMARB_MODE, MEMARB_MODE_ENABLE);
- tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
- }
-
- err = tg3_test_dma(tp);
- if (err) {
- dev_err(&pdev->dev, "DMA engine test failed, aborting\n");
- goto err_out_apeunmap;
- }
-
intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW;
rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW;
sndmbx = MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW;
@@ -17415,6 +17433,23 @@
sndmbx += 0xc;
}
+ /*
+ * Reset chip in case UNDI or EFI driver did not shutdown
+ * DMA self test will enable WDMAC and we'll see (spurious)
+ * pending DMA on the PCI bus at that point.
+ */
+ if ((tr32(HOSTCC_MODE) & HOSTCC_MODE_ENABLE) ||
+ (tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
+ tw32(MEMARB_MODE, MEMARB_MODE_ENABLE);
+ tg3_halt(tp, RESET_KIND_SHUTDOWN, 1);
+ }
+
+ err = tg3_test_dma(tp);
+ if (err) {
+ dev_err(&pdev->dev, "DMA engine test failed, aborting\n");
+ goto err_out_apeunmap;
+ }
+
tg3_init_coal(tp);
pci_set_drvdata(pdev, dev);
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index ff6e30e..046059c 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2587,7 +2587,11 @@
#define RXD_ERR_TOO_SMALL 0x00400000
#define RXD_ERR_NO_RESOURCES 0x00800000
#define RXD_ERR_HUGE_FRAME 0x01000000
-#define RXD_ERR_MASK 0xffff0000
+
+#define RXD_ERR_MASK (RXD_ERR_BAD_CRC | RXD_ERR_COLLISION | \
+ RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE | \
+ RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL | \
+ RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME)
u32 reserved;
u32 opaque;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index c89aa41..b4e0dc8 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -1070,7 +1070,7 @@
static void macb_configure_caps(struct macb *bp)
{
if (macb_is_gem(bp)) {
- if (GEM_BF(IRQCOR, gem_readl(bp, DCFG1)) == 0)
+ if (GEM_BFEXT(IRQCOR, gem_readl(bp, DCFG1)) == 0)
bp->caps |= MACB_CAPS_ISR_CLEAR_ON_WRITE;
}
}
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index f12e6b8..f057a18 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -1600,7 +1600,8 @@
flits = skb_transport_offset(skb) / 8;
sgp = ndesc == 1 ? (struct sg_ent *)&d->flit[flits] : sgl;
sgl_flits = make_sgl(skb, sgp, skb_transport_header(skb),
- skb->tail - skb->transport_header,
+ skb_tail_pointer(skb) -
+ skb_transport_header(skb),
adap->pdev);
if (need_skb_unmap()) {
setup_deferred_unmapping(skb, adap->pdev, sgp, sgl_flits);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 635f559..8cc0eaa 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1294,10 +1294,14 @@
skb_put(skb, bytes_written);
skb->protocol = eth_type_trans(skb, netdev);
- if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc) {
- skb->csum = htons(checksum);
- skb->ip_summed = CHECKSUM_COMPLETE;
- }
+ /* Hardware does not provide whole packet checksum. It only
+ * provides pseudo checksum. Since hw validates the packet
+ * checksum but not provide us the checksum value. use
+ * CHECSUM_UNNECESSARY.
+ */
+ if ((netdev->features & NETIF_F_RXCSUM) && tcp_udp_csum_ok &&
+ ipv4_csum_ok)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
if (vlan_stripped)
__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 1db2df6..696674e 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1150,7 +1150,6 @@
if (lancer_chip(adapter)) {
req->hdr.version = 1;
- req->if_id = cpu_to_le16(adapter->if_handle);
} else if (BEx_chip(adapter)) {
if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC)
req->hdr.version = 2;
@@ -1158,6 +1157,8 @@
req->hdr.version = 2;
}
+ if (req->hdr.version > 0)
+ req->if_id = cpu_to_le16(adapter->if_handle);
req->num_pages = PAGES_4K_SPANNED(q_mem->va, q_mem->size);
req->ulp_num = BE_ULP1_NUM;
req->type = BE_ETH_TX_RING_TYPE_STANDARD;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a0b4be5..88e85cb 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -782,16 +782,22 @@
if (vlan_tx_tag_present(skb))
vlan_tag = be_get_tx_vlan_tag(adapter, skb);
- else if (qnq_async_evt_rcvd(adapter) && adapter->pvid)
- vlan_tag = adapter->pvid;
+
+ if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
+ if (!vlan_tag)
+ vlan_tag = adapter->pvid;
+ /* f/w workaround to set skip_hw_vlan = 1, informs the F/W to
+ * skip VLAN insertion
+ */
+ if (skip_hw_vlan)
+ *skip_hw_vlan = true;
+ }
if (vlan_tag) {
skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag);
if (unlikely(!skb))
return skb;
skb->vlan_tci = 0;
- if (skip_hw_vlan)
- *skip_hw_vlan = true;
}
/* Insert the outer VLAN, if any */
@@ -1761,7 +1767,7 @@
queue_tail_inc(txq);
} while (cur_index != last_index);
- kfree_skb(sent_skb);
+ dev_kfree_skb_any(sent_skb);
return num_wrbs;
}
@@ -2555,8 +2561,8 @@
/* Wait for all pending tx completions to arrive so that
* all tx skbs are freed.
*/
- be_tx_compl_clean(adapter);
netif_tx_disable(netdev);
+ be_tx_compl_clean(adapter);
be_rx_qs_destroy(adapter);
@@ -2657,7 +2663,7 @@
for_all_evt_queues(adapter, eqo, i) {
napi_enable(&eqo->napi);
- be_eq_notify(adapter, eqo->q.id, true, false, 0);
+ be_eq_notify(adapter, eqo->q.id, true, true, 0);
}
adapter->flags |= BE_FLAGS_NAPI_ENABLED;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d48099f..fbd0d7d 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -371,6 +371,8 @@
else
bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ skb_tx_timestamp(skb);
+
fep->cur_tx = bdp;
if (fep->cur_tx == fep->dirty_tx)
@@ -379,8 +381,6 @@
/* Trigger transmission start */
writel(0, fep->hwp + FEC_X_DES_ACTIVE);
- skb_tx_timestamp(skb);
-
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 90ea0b1..716dae7 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3023,7 +3023,7 @@
dev->hw_features = NETIF_F_SG | NETIF_F_TSO |
NETIF_F_IP_CSUM | NETIF_F_HW_VLAN_CTAG_TX;
- dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_TSO |
+ dev->features = NETIF_F_SG | NETIF_F_TSO |
NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 70fd559..040ecf2 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -293,6 +293,18 @@
atomic_add(buffers_added, &(pool->available));
}
+/*
+ * The final 8 bytes of the buffer list is a counter of frames dropped
+ * because there was not a buffer in the buffer list capable of holding
+ * the frame.
+ */
+static void ibmveth_update_rx_no_buffer(struct ibmveth_adapter *adapter)
+{
+ __be64 *p = adapter->buffer_list_addr + 4096 - 8;
+
+ adapter->rx_no_buffer = be64_to_cpup(p);
+}
+
/* replenish routine */
static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
{
@@ -308,8 +320,7 @@
ibmveth_replenish_buffer_pool(adapter, pool);
}
- adapter->rx_no_buffer = *(u64 *)(((char*)adapter->buffer_list_addr) +
- 4096 - 8);
+ ibmveth_update_rx_no_buffer(adapter);
}
/* empty and free ana buffer pool - also used to do cleanup in error paths */
@@ -689,8 +700,7 @@
free_irq(netdev->irq, netdev);
- adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) +
- 4096 - 8);
+ ibmveth_update_rx_no_buffer(adapter);
ibmveth_cleanup(adapter);
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index d2bea3f..69d3f59 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3039,7 +3039,7 @@
*enable_wake = false;
}
- pci_disable_device(pdev);
+ pci_clear_master(pdev);
}
static int __e100_power_off(struct pci_dev *pdev, bool wake)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 59ad007..a978fc82 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -144,6 +144,11 @@
static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int *work_done, int work_to_do);
+static void e1000_alloc_dummy_rx_buffers(struct e1000_adapter *adapter,
+ struct e1000_rx_ring *rx_ring,
+ int cleaned_count)
+{
+}
static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter,
struct e1000_rx_ring *rx_ring,
int cleaned_count);
@@ -3555,8 +3560,11 @@
msleep(1);
/* e1000_down has a dependency on max_frame_size */
hw->max_frame_size = max_frame;
- if (netif_running(netdev))
+ if (netif_running(netdev)) {
+ /* prevent buffers from being reallocated */
+ adapter->alloc_rx_buf = e1000_alloc_dummy_rx_buffers;
e1000_down(adapter);
+ }
/* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN
* means we reserve 2 more, this pushes us to allocate from the next
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 59c76a6..be4d7c1 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1757,19 +1757,23 @@
* it across the board.
*/
ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
- if (ret_val)
+ if (ret_val) {
/* If the first read fails, another entity may have
* ownership of the resources, wait and try again to
* see if they have relinquished the resources yet.
*/
- udelay(usec_interval);
+ if (usec_interval >= 1000)
+ msleep(usec_interval / 1000);
+ else
+ udelay(usec_interval);
+ }
ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
if (ret_val)
break;
if (phy_status & BMSR_LSTATUS)
break;
if (usec_interval >= 1000)
- mdelay(usec_interval / 1000);
+ msleep(usec_interval / 1000);
else
udelay(usec_interval);
}
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 115b0da..5dec66a 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1595,7 +1595,10 @@
* ownership of the resources, wait and try again to
* see if they have relinquished the resources yet.
*/
- udelay(usec_interval);
+ if (usec_interval >= 1000)
+ mdelay(usec_interval/1000);
+ else
+ udelay(usec_interval);
}
ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
if (ret_val)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 64cbe0d..3f342fb 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1584,6 +1584,8 @@
igb_power_up_phy_copper(&adapter->hw);
else
igb_power_up_serdes_link_82575(&adapter->hw);
+
+ igb_setup_link(&adapter->hw);
}
/**
@@ -7229,6 +7231,8 @@
if (netif_running(netdev))
igb_close(netdev);
+ else
+ igb_reset(adapter);
igb_clear_interrupt_scheme(adapter);
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index fce3e92..c5a9dcc 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1527,12 +1527,12 @@
int tso;
if (test_bit(__IXGB_DOWN, &adapter->flags)) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
if (skb->len <= 0) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
@@ -1549,7 +1549,7 @@
tso = ixgb_tso(adapter, skb);
if (tso < 0) {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
index ac78077..7a77f37 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
@@ -108,9 +108,8 @@
/* Enable arbiter */
reg &= ~IXGBE_DPMCS_ARBDIS;
- /* Enable DFP and Recycle mode */
- reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM);
reg |= IXGBE_DPMCS_TSOEF;
+
/* Configure Max TSO packet size 34KB including payload and headers */
reg |= (0x4 << IXGBE_DPMCS_MTSOS_SHIFT);
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index d1cbfb1..4be11ff 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1125,15 +1125,13 @@
p->rx_discard += rdlp(mp, RX_DISCARD_FRAME_CNT);
p->rx_overrun += rdlp(mp, RX_OVERRUN_FRAME_CNT);
spin_unlock_bh(&mp->mib_counters_lock);
-
- mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
}
static void mib_counters_timer_wrapper(unsigned long _mp)
{
struct mv643xx_eth_private *mp = (void *)_mp;
-
mib_counters_update(mp);
+ mod_timer(&mp->mib_counters_timer, jiffies + 30 * HZ);
}
@@ -2231,6 +2229,7 @@
mp->int_mask |= INT_TX_END_0 << i;
}
+ add_timer(&mp->mib_counters_timer);
port_start(mp);
wrlp(mp, INT_MASK_EXT, INT_EXT_LINK_PHY | INT_EXT_TX);
@@ -2739,7 +2738,6 @@
mp->mib_counters_timer.data = (unsigned long)mp;
mp->mib_counters_timer.function = mib_counters_timer_wrapper;
mp->mib_counters_timer.expires = jiffies + 30 * HZ;
- add_timer(&mp->mib_counters_timer);
spin_lock_init(&mp->mib_counters_lock);
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index c966785..8b6c923 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -99,16 +99,56 @@
#define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff
#define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00
#define MVNETA_RXQ_TIME_COAL_REG(q) (0x2580 + ((q) << 2))
+
+/* Exception Interrupt Port/Queue Cause register */
+
#define MVNETA_INTR_NEW_CAUSE 0x25a0
-#define MVNETA_RX_INTR_MASK(nr_rxqs) (((1 << nr_rxqs) - 1) << 8)
#define MVNETA_INTR_NEW_MASK 0x25a4
+
+/* bits 0..7 = TXQ SENT, one bit per queue.
+ * bits 8..15 = RXQ OCCUP, one bit per queue.
+ * bits 16..23 = RXQ FREE, one bit per queue.
+ * bit 29 = OLD_REG_SUM, see old reg ?
+ * bit 30 = TX_ERR_SUM, one bit for 4 ports
+ * bit 31 = MISC_SUM, one bit for 4 ports
+ */
+#define MVNETA_TX_INTR_MASK(nr_txqs) (((1 << nr_txqs) - 1) << 0)
+#define MVNETA_TX_INTR_MASK_ALL (0xff << 0)
+#define MVNETA_RX_INTR_MASK(nr_rxqs) (((1 << nr_rxqs) - 1) << 8)
+#define MVNETA_RX_INTR_MASK_ALL (0xff << 8)
+
#define MVNETA_INTR_OLD_CAUSE 0x25a8
#define MVNETA_INTR_OLD_MASK 0x25ac
+
+/* Data Path Port/Queue Cause Register */
#define MVNETA_INTR_MISC_CAUSE 0x25b0
#define MVNETA_INTR_MISC_MASK 0x25b4
+
+#define MVNETA_CAUSE_PHY_STATUS_CHANGE BIT(0)
+#define MVNETA_CAUSE_LINK_CHANGE BIT(1)
+#define MVNETA_CAUSE_PTP BIT(4)
+
+#define MVNETA_CAUSE_INTERNAL_ADDR_ERR BIT(7)
+#define MVNETA_CAUSE_RX_OVERRUN BIT(8)
+#define MVNETA_CAUSE_RX_CRC_ERROR BIT(9)
+#define MVNETA_CAUSE_RX_LARGE_PKT BIT(10)
+#define MVNETA_CAUSE_TX_UNDERUN BIT(11)
+#define MVNETA_CAUSE_PRBS_ERR BIT(12)
+#define MVNETA_CAUSE_PSC_SYNC_CHANGE BIT(13)
+#define MVNETA_CAUSE_SERDES_SYNC_ERR BIT(14)
+
+#define MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT 16
+#define MVNETA_CAUSE_BMU_ALLOC_ERR_ALL_MASK (0xF << MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT)
+#define MVNETA_CAUSE_BMU_ALLOC_ERR_MASK(pool) (1 << (MVNETA_CAUSE_BMU_ALLOC_ERR_SHIFT + (pool)))
+
+#define MVNETA_CAUSE_TXQ_ERROR_SHIFT 24
+#define MVNETA_CAUSE_TXQ_ERROR_ALL_MASK (0xFF << MVNETA_CAUSE_TXQ_ERROR_SHIFT)
+#define MVNETA_CAUSE_TXQ_ERROR_MASK(q) (1 << (MVNETA_CAUSE_TXQ_ERROR_SHIFT + (q)))
+
#define MVNETA_INTR_ENABLE 0x25b8
#define MVNETA_TXQ_INTR_ENABLE_ALL_MASK 0x0000ff00
-#define MVNETA_RXQ_INTR_ENABLE_ALL_MASK 0xff000000
+#define MVNETA_RXQ_INTR_ENABLE_ALL_MASK 0xff000000 // note: neta says it's 0x000000FF
+
#define MVNETA_RXQ_CMD 0x2680
#define MVNETA_RXQ_DISABLE_SHIFT 8
#define MVNETA_RXQ_ENABLE_MASK 0x000000ff
@@ -119,7 +159,7 @@
#define MVNETA_GMAC_MAX_RX_SIZE_MASK 0x7ffc
#define MVNETA_GMAC0_PORT_ENABLE BIT(0)
#define MVNETA_GMAC_CTRL_2 0x2c08
-#define MVNETA_GMAC2_PSC_ENABLE BIT(3)
+#define MVNETA_GMAC2_PCS_ENABLE BIT(3)
#define MVNETA_GMAC2_PORT_RGMII BIT(4)
#define MVNETA_GMAC2_PORT_RESET BIT(6)
#define MVNETA_GMAC_STATUS 0x2c10
@@ -136,7 +176,9 @@
#define MVNETA_GMAC_FORCE_LINK_PASS BIT(1)
#define MVNETA_GMAC_CONFIG_MII_SPEED BIT(5)
#define MVNETA_GMAC_CONFIG_GMII_SPEED BIT(6)
+#define MVNETA_GMAC_AN_SPEED_EN BIT(7)
#define MVNETA_GMAC_CONFIG_FULL_DUPLEX BIT(12)
+#define MVNETA_GMAC_AN_DUPLEX_EN BIT(13)
#define MVNETA_MIB_COUNTERS_BASE 0x3080
#define MVNETA_MIB_LATE_COLLISION 0x7c
#define MVNETA_DA_FILT_SPEC_MCAST 0x3400
@@ -168,13 +210,10 @@
/* Various constants */
/* Coalescing */
-#define MVNETA_TXDONE_COAL_PKTS 16
+#define MVNETA_TXDONE_COAL_PKTS 1
#define MVNETA_RX_COAL_PKTS 32
#define MVNETA_RX_COAL_USEC 100
-/* Timer */
-#define MVNETA_TX_DONE_TIMER_PERIOD 10
-
/* Napi polling weight */
#define MVNETA_RX_POLL_WEIGHT 64
@@ -217,10 +256,12 @@
#define MVNETA_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD)
-struct mvneta_stats {
+struct mvneta_pcpu_stats {
struct u64_stats_sync syncp;
- u64 packets;
- u64 bytes;
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
};
struct mvneta_port {
@@ -228,16 +269,11 @@
void __iomem *base;
struct mvneta_rx_queue *rxqs;
struct mvneta_tx_queue *txqs;
- struct timer_list tx_done_timer;
struct net_device *dev;
u32 cause_rx_tx;
struct napi_struct napi;
- /* Flags */
- unsigned long flags;
-#define MVNETA_F_TX_DONE_TIMER_BIT 0
-
/* Napi weight */
int weight;
@@ -246,8 +282,7 @@
u8 mcast_count[256];
u16 tx_ring_size;
u16 rx_ring_size;
- struct mvneta_stats tx_stats;
- struct mvneta_stats rx_stats;
+ struct mvneta_pcpu_stats *stats;
struct mii_bus *mii_bus;
struct phy_device *phy_dev;
@@ -426,21 +461,29 @@
{
struct mvneta_port *pp = netdev_priv(dev);
unsigned int start;
+ int cpu;
- memset(stats, 0, sizeof(struct rtnl_link_stats64));
+ for_each_possible_cpu(cpu) {
+ struct mvneta_pcpu_stats *cpu_stats;
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
- do {
- start = u64_stats_fetch_begin_bh(&pp->rx_stats.syncp);
- stats->rx_packets = pp->rx_stats.packets;
- stats->rx_bytes = pp->rx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&pp->rx_stats.syncp, start));
+ cpu_stats = per_cpu_ptr(pp->stats, cpu);
+ do {
+ start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+ rx_packets = cpu_stats->rx_packets;
+ rx_bytes = cpu_stats->rx_bytes;
+ tx_packets = cpu_stats->tx_packets;
+ tx_bytes = cpu_stats->tx_bytes;
+ } while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
-
- do {
- start = u64_stats_fetch_begin_bh(&pp->tx_stats.syncp);
- stats->tx_packets = pp->tx_stats.packets;
- stats->tx_bytes = pp->tx_stats.bytes;
- } while (u64_stats_fetch_retry_bh(&pp->tx_stats.syncp, start));
+ stats->rx_packets += rx_packets;
+ stats->rx_bytes += rx_bytes;
+ stats->tx_packets += tx_packets;
+ stats->tx_bytes += tx_bytes;
+ }
stats->rx_errors = dev->stats.rx_errors;
stats->rx_dropped = dev->stats.rx_dropped;
@@ -653,7 +696,7 @@
u32 val;
val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
- val |= MVNETA_GMAC2_PSC_ENABLE;
+ val |= MVNETA_GMAC2_PCS_ENABLE;
mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
}
@@ -911,6 +954,13 @@
/* Assign port SDMA configuration */
mvreg_write(pp, MVNETA_SDMA_CONFIG, val);
+ /* Disable PHY polling in hardware, since we're using the
+ * kernel phylib to do this.
+ */
+ val = mvreg_read(pp, MVNETA_UNIT_CONTROL);
+ val &= ~MVNETA_PHY_POLLING_ENABLE;
+ mvreg_write(pp, MVNETA_UNIT_CONTROL, val);
+
mvneta_set_ucast_table(pp, -1);
mvneta_set_special_mcast_table(pp, -1);
mvneta_set_other_mcast_table(pp, -1);
@@ -1054,17 +1104,6 @@
txq->done_pkts_coal = value;
}
-/* Trigger tx done timer in MVNETA_TX_DONE_TIMER_PERIOD msecs */
-static void mvneta_add_tx_done_timer(struct mvneta_port *pp)
-{
- if (test_and_set_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags) == 0) {
- pp->tx_done_timer.expires = jiffies +
- msecs_to_jiffies(MVNETA_TX_DONE_TIMER_PERIOD);
- add_timer(&pp->tx_done_timer);
- }
-}
-
-
/* Handle rx descriptor fill by setting buf_cookie and buf_phys_addr */
static void mvneta_rx_desc_fill(struct mvneta_rx_desc *rx_desc,
u32 phys_addr, u32 cookie)
@@ -1136,7 +1175,7 @@
command = l3_offs << MVNETA_TX_L3_OFF_SHIFT;
command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
- if (l3_proto == swab16(ETH_P_IP))
+ if (l3_proto == htons(ETH_P_IP))
command |= MVNETA_TXD_IP_CSUM;
else
command |= MVNETA_TX_L3_IP6;
@@ -1345,6 +1384,8 @@
{
struct net_device *dev = pp->dev;
int rx_done, rx_filled;
+ u32 rcvd_pkts = 0;
+ u32 rcvd_bytes = 0;
/* Get number of received packets */
rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
@@ -1382,10 +1423,8 @@
rx_bytes = rx_desc->data_size -
(ETH_FCS_LEN + MVNETA_MH_SIZE);
- u64_stats_update_begin(&pp->rx_stats.syncp);
- pp->rx_stats.packets++;
- pp->rx_stats.bytes += rx_bytes;
- u64_stats_update_end(&pp->rx_stats.syncp);
+ rcvd_pkts++;
+ rcvd_bytes += rx_bytes;
/* Linux processing */
skb_reserve(skb, MVNETA_MH_SIZE);
@@ -1406,6 +1445,15 @@
}
}
+ if (rcvd_pkts) {
+ struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets += rcvd_pkts;
+ stats->rx_bytes += rcvd_bytes;
+ u64_stats_update_end(&stats->syncp);
+ }
+
/* Update rxq management counters */
mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
@@ -1536,25 +1584,17 @@
out:
if (frags > 0) {
- u64_stats_update_begin(&pp->tx_stats.syncp);
- pp->tx_stats.packets++;
- pp->tx_stats.bytes += skb->len;
- u64_stats_update_end(&pp->tx_stats.syncp);
+ struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->tx_packets++;
+ stats->tx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
} else {
dev->stats.tx_dropped++;
dev_kfree_skb_any(skb);
}
- if (txq->count >= MVNETA_TXDONE_COAL_PKTS)
- mvneta_txq_done(pp, txq);
-
- /* If after calling mvneta_txq_done, count equals
- * frags, we need to set the timer
- */
- if (txq->count == frags && frags > 0)
- mvneta_add_tx_done_timer(pp);
-
return NETDEV_TX_OK;
}
@@ -1830,14 +1870,22 @@
/* Read cause register */
cause_rx_tx = mvreg_read(pp, MVNETA_INTR_NEW_CAUSE) &
- MVNETA_RX_INTR_MASK(rxq_number);
+ (MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
+
+ /* Release Tx descriptors */
+ if (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL) {
+ int tx_todo = 0;
+
+ mvneta_tx_done_gbe(pp, (cause_rx_tx & MVNETA_TX_INTR_MASK_ALL), &tx_todo);
+ cause_rx_tx &= ~MVNETA_TX_INTR_MASK_ALL;
+ }
/* For the case where the last mvneta_poll did not process all
* RX packets
*/
cause_rx_tx |= pp->cause_rx_tx;
if (rxq_number > 1) {
- while ((cause_rx_tx != 0) && (budget > 0)) {
+ while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) {
int count;
struct mvneta_rx_queue *rxq;
/* get rx queue number from cause_rx_tx */
@@ -1869,7 +1917,7 @@
napi_complete(napi);
local_irq_save(flags);
mvreg_write(pp, MVNETA_INTR_NEW_MASK,
- MVNETA_RX_INTR_MASK(rxq_number));
+ MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
local_irq_restore(flags);
}
@@ -1877,26 +1925,6 @@
return rx_done;
}
-/* tx done timer callback */
-static void mvneta_tx_done_timer_callback(unsigned long data)
-{
- struct net_device *dev = (struct net_device *)data;
- struct mvneta_port *pp = netdev_priv(dev);
- int tx_done = 0, tx_todo = 0;
-
- if (!netif_running(dev))
- return ;
-
- clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
- tx_done = mvneta_tx_done_gbe(pp,
- (((1 << txq_number) - 1) &
- MVNETA_CAUSE_TXQ_SENT_DESC_ALL_MASK),
- &tx_todo);
- if (tx_todo > 0)
- mvneta_add_tx_done_timer(pp);
-}
-
/* Handle rxq fill: allocates rxq skbs; called when initializing a port */
static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
int num)
@@ -2146,7 +2174,7 @@
/* Unmask interrupts */
mvreg_write(pp, MVNETA_INTR_NEW_MASK,
- MVNETA_RX_INTR_MASK(rxq_number));
+ MVNETA_RX_INTR_MASK(rxq_number) | MVNETA_TX_INTR_MASK(txq_number));
phy_start(pp->phy_dev);
netif_tx_start_all_queues(pp->dev);
@@ -2179,16 +2207,6 @@
mvneta_rx_reset(pp);
}
-/* tx timeout callback - display a message and stop/start the network device */
-static void mvneta_tx_timeout(struct net_device *dev)
-{
- struct mvneta_port *pp = netdev_priv(dev);
-
- netdev_info(dev, "tx timeout\n");
- mvneta_stop_dev(pp);
- mvneta_start_dev(pp);
-}
-
/* Return positive if MTU is valid */
static int mvneta_check_mtu_valid(struct net_device *dev, int mtu)
{
@@ -2288,14 +2306,16 @@
val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
val &= ~(MVNETA_GMAC_CONFIG_MII_SPEED |
MVNETA_GMAC_CONFIG_GMII_SPEED |
- MVNETA_GMAC_CONFIG_FULL_DUPLEX);
+ MVNETA_GMAC_CONFIG_FULL_DUPLEX |
+ MVNETA_GMAC_AN_SPEED_EN |
+ MVNETA_GMAC_AN_DUPLEX_EN);
if (phydev->duplex)
val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX;
if (phydev->speed == SPEED_1000)
val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
- else
+ else if (phydev->speed == SPEED_100)
val |= MVNETA_GMAC_CONFIG_MII_SPEED;
mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
@@ -2415,8 +2435,6 @@
free_irq(dev->irq, pp);
mvneta_cleanup_rxqs(pp);
mvneta_cleanup_txqs(pp);
- del_timer(&pp->tx_done_timer);
- clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
return 0;
}
@@ -2537,7 +2555,6 @@
.ndo_set_rx_mode = mvneta_set_rx_mode,
.ndo_set_mac_address = mvneta_set_mac_addr,
.ndo_change_mtu = mvneta_change_mtu,
- .ndo_tx_timeout = mvneta_tx_timeout,
.ndo_get_stats64 = mvneta_get_stats64,
};
@@ -2718,10 +2735,6 @@
pp = netdev_priv(dev);
- pp->tx_done_timer.function = mvneta_tx_done_timer_callback;
- init_timer(&pp->tx_done_timer);
- clear_bit(MVNETA_F_TX_DONE_TIMER_BIT, &pp->flags);
-
pp->weight = MVNETA_RX_POLL_WEIGHT;
pp->phy_node = phy_node;
pp->phy_interface = phy_mode;
@@ -2740,7 +2753,12 @@
clk_prepare_enable(pp->clk);
- pp->tx_done_timer.data = (unsigned long)dev;
+ /* Alloc per-cpu stats */
+ pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
+ if (!pp->stats) {
+ err = -ENOMEM;
+ goto err_clk;
+ }
pp->tx_ring_size = MVNETA_MAX_TXD;
pp->rx_ring_size = MVNETA_MAX_RXD;
@@ -2751,7 +2769,7 @@
err = mvneta_init(pp, phy_addr);
if (err < 0) {
dev_err(&pdev->dev, "can't init eth hal\n");
- goto err_clk;
+ goto err_free_stats;
}
mvneta_port_power_up(pp, phy_mode);
@@ -2780,6 +2798,8 @@
err_deinit:
mvneta_deinit(pp);
+err_free_stats:
+ free_percpu(pp->stats);
err_clk:
clk_disable_unprepare(pp->clk);
err_unmap:
@@ -2800,6 +2820,7 @@
unregister_netdev(dev);
mvneta_deinit(pp);
clk_disable_unprepare(pp->clk);
+ free_percpu(pp->stats);
iounmap(pp->base);
irq_dispose_mapping(dev->irq);
free_netdev(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0e572a5..28d706b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1544,7 +1544,7 @@
vp_oper->vlan_idx = NO_INDX;
}
if (NO_INDX != vp_oper->mac_idx) {
- __mlx4_unregister_mac(&priv->dev, port, vp_oper->mac_idx);
+ __mlx4_unregister_mac(&priv->dev, port, vp_oper->state.mac);
vp_oper->mac_idx = NO_INDX;
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1e6c594..58c18d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -55,7 +55,6 @@
cq->ring = ring;
cq->is_tx = mode;
- spin_lock_init(&cq->lock);
err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
cq->buf_size, 2 * PAGE_SIZE);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index a5c9df07..c72e214 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -264,6 +264,10 @@
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
mdev->port_cnt++;
+ /* Initialize time stamp mechanism */
+ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
+ mlx4_en_init_timestamp(mdev);
+
mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
if (!dev->caps.comp_pool) {
mdev->profile.prof[i].rx_ring_num =
@@ -301,10 +305,6 @@
mdev->pndev[i] = NULL;
}
- /* Initialize time stamp mechanism */
- if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
- mlx4_en_init_timestamp(mdev);
-
return mdev;
err_mr:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 89c47ea..063f3f4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1190,15 +1190,11 @@
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_cq *cq;
- unsigned long flags;
int i;
for (i = 0; i < priv->rx_ring_num; i++) {
cq = &priv->rx_cq[i];
- spin_lock_irqsave(&cq->lock, flags);
- napi_synchronize(&cq->napi);
- mlx4_en_process_rx_cq(dev, cq, 0);
- spin_unlock_irqrestore(&cq->lock, flags);
+ napi_schedule(&cq->napi);
}
}
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 4e6877a..bd8800c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -191,6 +191,39 @@
MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp);
}
+static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv,
+ struct mlx4_en_tx_ring *ring, int index,
+ u8 owner)
+{
+ __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
+ struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE;
+ struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
+ void *end = ring->buf + ring->buf_size;
+ __be32 *ptr = (__be32 *)tx_desc;
+ int i;
+
+ /* Optimize the common case when there are no wraparounds */
+ if (likely((void *)tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) {
+ /* Stamp the freed descriptor */
+ for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+ i += STAMP_STRIDE) {
+ *ptr = stamp;
+ ptr += STAMP_DWORDS;
+ }
+ } else {
+ /* Stamp the freed descriptor */
+ for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE;
+ i += STAMP_STRIDE) {
+ *ptr = stamp;
+ ptr += STAMP_DWORDS;
+ if ((void *)ptr >= end) {
+ ptr = ring->buf;
+ stamp ^= cpu_to_be32(0x80000000);
+ }
+ }
+ }
+}
+
static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring,
@@ -205,8 +238,6 @@
void *end = ring->buf + ring->buf_size;
int frags = skb_shinfo(skb)->nr_frags;
int i;
- __be32 *ptr = (__be32 *)tx_desc;
- __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT));
struct skb_shared_hwtstamps hwts;
if (timestamp) {
@@ -232,12 +263,6 @@
skb_frag_size(frag), PCI_DMA_TODEVICE);
}
}
- /* Stamp the freed descriptor */
- for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
- *ptr = stamp;
- ptr += STAMP_DWORDS;
- }
-
} else {
if (!tx_info->inl) {
if ((void *) data >= end) {
@@ -263,16 +288,6 @@
++data;
}
}
- /* Stamp the freed descriptor */
- for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) {
- *ptr = stamp;
- ptr += STAMP_DWORDS;
- if ((void *) ptr >= end) {
- ptr = ring->buf;
- stamp ^= cpu_to_be32(0x80000000);
- }
- }
-
}
dev_kfree_skb_any(skb);
return tx_info->nr_txbb;
@@ -318,8 +333,9 @@
struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
struct mlx4_cqe *cqe;
u16 index;
- u16 new_index, ring_index;
+ u16 new_index, ring_index, stamp_index;
u32 txbbs_skipped = 0;
+ u32 txbbs_stamp = 0;
u32 cons_index = mcq->cons_index;
int size = cq->size;
u32 size_mask = ring->size_mask;
@@ -335,6 +351,7 @@
index = cons_index & size_mask;
cqe = &buf[(index << factor) + factor];
ring_index = ring->cons & size_mask;
+ stamp_index = ring_index;
/* Process all completed CQEs */
while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
@@ -359,6 +376,12 @@
priv, ring, ring_index,
!!((ring->cons + txbbs_skipped) &
ring->size), timestamp);
+
+ mlx4_en_stamp_wqe(priv, ring, stamp_index,
+ !!((ring->cons + txbbs_stamp) &
+ ring->size));
+ stamp_index = ring_index;
+ txbbs_stamp = txbbs_skipped;
packets++;
bytes += ring->tx_info[ring_index].nr_bytes;
} while (ring_index != new_index);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 2c97901..593177d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -840,16 +840,7 @@
MLX4_CMD_NATIVE);
if (!err && dev->caps.function != slave) {
- /* if config MAC in DB use it */
- if (priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac)
- def_mac = priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac;
- else {
- /* set slave default_mac address */
- MLX4_GET(def_mac, outbox->buf, QUERY_PORT_MAC_OFFSET);
- def_mac += slave << 8;
- priv->mfunc.master.vf_admin[slave].vport[vhcr->in_modifier].mac = def_mac;
- }
-
+ def_mac = priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac;
MLX4_PUT(outbox->buf, def_mac, QUERY_PORT_MAC_OFFSET);
/* get port type - currently only eth is enabled */
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 8a43499..3fb2643 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -371,7 +371,7 @@
dev->caps.sqp_demux = (mlx4_is_master(dev)) ? MLX4_MAX_NUM_SLAVES : 0;
- if (!enable_64b_cqe_eqe) {
+ if (!enable_64b_cqe_eqe && !mlx4_is_slave(dev)) {
if (dev_cap->flags &
(MLX4_DEV_CAP_FLAG_64B_CQE | MLX4_DEV_CAP_FLAG_64B_EQE)) {
mlx4_warn(dev, "64B EQEs/CQEs supported by the device but not enabled\n");
@@ -2129,13 +2129,8 @@
/* Allow large DMA segments, up to the firmware limit of 1 GB */
dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
- priv = kzalloc(sizeof(*priv), GFP_KERNEL);
- if (!priv) {
- err = -ENOMEM;
- goto err_release_regions;
- }
-
- dev = &priv->dev;
+ dev = pci_get_drvdata(pdev);
+ priv = mlx4_priv(dev);
dev->pdev = pdev;
INIT_LIST_HEAD(&priv->ctx_list);
spin_lock_init(&priv->ctx_lock);
@@ -2300,8 +2295,7 @@
mlx4_sense_init(dev);
mlx4_start_sense(dev);
- priv->pci_dev_data = pci_dev_data;
- pci_set_drvdata(pdev, dev);
+ priv->removed = 0;
return 0;
@@ -2367,84 +2361,110 @@
static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
+ struct mlx4_priv *priv;
+ struct mlx4_dev *dev;
+
printk_once(KERN_INFO "%s", mlx4_version);
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ dev = &priv->dev;
+ pci_set_drvdata(pdev, dev);
+ priv->pci_dev_data = id->driver_data;
+
return __mlx4_init_one(pdev, id->driver_data);
}
+static void __mlx4_remove_one(struct pci_dev *pdev)
+{
+ struct mlx4_dev *dev = pci_get_drvdata(pdev);
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int pci_dev_data;
+ int p;
+
+ if (priv->removed)
+ return;
+
+ pci_dev_data = priv->pci_dev_data;
+
+ /* in SRIOV it is not allowed to unload the pf's
+ * driver while there are alive vf's */
+ if (mlx4_is_master(dev)) {
+ if (mlx4_how_many_lives_vf(dev))
+ printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+ }
+ mlx4_stop_sense(dev);
+ mlx4_unregister_device(dev);
+
+ for (p = 1; p <= dev->caps.num_ports; p++) {
+ mlx4_cleanup_port_info(&priv->port[p]);
+ mlx4_CLOSE_PORT(dev, p);
+ }
+
+ if (mlx4_is_master(dev))
+ mlx4_free_resource_tracker(dev,
+ RES_TR_FREE_SLAVES_ONLY);
+
+ mlx4_cleanup_counters_table(dev);
+ mlx4_cleanup_qp_table(dev);
+ mlx4_cleanup_srq_table(dev);
+ mlx4_cleanup_cq_table(dev);
+ mlx4_cmd_use_polling(dev);
+ mlx4_cleanup_eq_table(dev);
+ mlx4_cleanup_mcg_table(dev);
+ mlx4_cleanup_mr_table(dev);
+ mlx4_cleanup_xrcd_table(dev);
+ mlx4_cleanup_pd_table(dev);
+
+ if (mlx4_is_master(dev))
+ mlx4_free_resource_tracker(dev,
+ RES_TR_FREE_STRUCTS_ONLY);
+
+ iounmap(priv->kar);
+ mlx4_uar_free(dev, &priv->driver_uar);
+ mlx4_cleanup_uar_table(dev);
+ if (!mlx4_is_slave(dev))
+ mlx4_clear_steering(dev);
+ mlx4_free_eq_table(dev);
+ if (mlx4_is_master(dev))
+ mlx4_multi_func_cleanup(dev);
+ mlx4_close_hca(dev);
+ if (mlx4_is_slave(dev))
+ mlx4_multi_func_cleanup(dev);
+ mlx4_cmd_cleanup(dev);
+
+ if (dev->flags & MLX4_FLAG_MSI_X)
+ pci_disable_msix(pdev);
+ if (dev->flags & MLX4_FLAG_SRIOV) {
+ mlx4_warn(dev, "Disabling SR-IOV\n");
+ pci_disable_sriov(pdev);
+ }
+
+ if (!mlx4_is_slave(dev))
+ mlx4_free_ownership(dev);
+
+ kfree(dev->caps.qp0_tunnel);
+ kfree(dev->caps.qp0_proxy);
+ kfree(dev->caps.qp1_tunnel);
+ kfree(dev->caps.qp1_proxy);
+
+ pci_release_regions(pdev);
+ pci_disable_device(pdev);
+ memset(priv, 0, sizeof(*priv));
+ priv->pci_dev_data = pci_dev_data;
+ priv->removed = 1;
+}
+
static void mlx4_remove_one(struct pci_dev *pdev)
{
struct mlx4_dev *dev = pci_get_drvdata(pdev);
struct mlx4_priv *priv = mlx4_priv(dev);
- int p;
- if (dev) {
- /* in SRIOV it is not allowed to unload the pf's
- * driver while there are alive vf's */
- if (mlx4_is_master(dev)) {
- if (mlx4_how_many_lives_vf(dev))
- printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
- }
- mlx4_stop_sense(dev);
- mlx4_unregister_device(dev);
-
- for (p = 1; p <= dev->caps.num_ports; p++) {
- mlx4_cleanup_port_info(&priv->port[p]);
- mlx4_CLOSE_PORT(dev, p);
- }
-
- if (mlx4_is_master(dev))
- mlx4_free_resource_tracker(dev,
- RES_TR_FREE_SLAVES_ONLY);
-
- mlx4_cleanup_counters_table(dev);
- mlx4_cleanup_mcg_table(dev);
- mlx4_cleanup_qp_table(dev);
- mlx4_cleanup_srq_table(dev);
- mlx4_cleanup_cq_table(dev);
- mlx4_cmd_use_polling(dev);
- mlx4_cleanup_eq_table(dev);
- mlx4_cleanup_mr_table(dev);
- mlx4_cleanup_xrcd_table(dev);
- mlx4_cleanup_pd_table(dev);
-
- if (mlx4_is_master(dev))
- mlx4_free_resource_tracker(dev,
- RES_TR_FREE_STRUCTS_ONLY);
-
- iounmap(priv->kar);
- mlx4_uar_free(dev, &priv->driver_uar);
- mlx4_cleanup_uar_table(dev);
- if (!mlx4_is_slave(dev))
- mlx4_clear_steering(dev);
- mlx4_free_eq_table(dev);
- if (mlx4_is_master(dev))
- mlx4_multi_func_cleanup(dev);
- mlx4_close_hca(dev);
- if (mlx4_is_slave(dev))
- mlx4_multi_func_cleanup(dev);
- mlx4_cmd_cleanup(dev);
-
- if (dev->flags & MLX4_FLAG_MSI_X)
- pci_disable_msix(pdev);
- if (dev->flags & MLX4_FLAG_SRIOV) {
- mlx4_warn(dev, "Disabling SR-IOV\n");
- pci_disable_sriov(pdev);
- }
-
- if (!mlx4_is_slave(dev))
- mlx4_free_ownership(dev);
-
- kfree(dev->caps.qp0_tunnel);
- kfree(dev->caps.qp0_proxy);
- kfree(dev->caps.qp1_tunnel);
- kfree(dev->caps.qp1_proxy);
-
- kfree(priv);
- pci_release_regions(pdev);
- pci_disable_device(pdev);
- pci_set_drvdata(pdev, NULL);
- }
+ __mlx4_remove_one(pdev);
+ kfree(priv);
+ pci_set_drvdata(pdev, NULL);
}
int mlx4_restart_one(struct pci_dev *pdev)
@@ -2454,7 +2474,7 @@
int pci_dev_data;
pci_dev_data = priv->pci_dev_data;
- mlx4_remove_one(pdev);
+ __mlx4_remove_one(pdev);
return __mlx4_init_one(pdev, pci_dev_data);
}
@@ -2509,7 +2529,7 @@
static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
pci_channel_state_t state)
{
- mlx4_remove_one(pdev);
+ __mlx4_remove_one(pdev);
return state == pci_channel_io_perm_failure ?
PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -2517,7 +2537,11 @@
static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
{
- int ret = __mlx4_init_one(pdev, 0);
+ struct mlx4_dev *dev = pci_get_drvdata(pdev);
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ int ret;
+
+ ret = __mlx4_init_one(pdev, priv->pci_dev_data);
return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index df15bb6..da4f000 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -743,6 +743,7 @@
spinlock_t ctx_lock;
int pci_dev_data;
+ int removed;
struct list_head pgdir_list;
struct mutex pgdir_mutex;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b1d7657..628e1f9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -299,7 +299,6 @@
struct mlx4_cq mcq;
struct mlx4_hwq_resources wqres;
int ring;
- spinlock_t lock;
struct net_device *dev;
struct napi_struct napi;
int size;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 1157f02..6cc8088 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -1207,7 +1207,7 @@
switch (op) {
case RES_OP_RESERVE:
- count = get_param_l(&in_param);
+ count = get_param_l(&in_param) & 0xffffff;
align = get_param_h(&in_param);
err = __mlx4_qp_reserve_range(dev, count, align, &base);
if (err)
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 7be9788..4fb93c5 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -856,6 +856,10 @@
return -ENOMEM;
dmatest_bus = pci_map_page(mgp->pdev, dmatest_page, 0, PAGE_SIZE,
DMA_BIDIRECTIONAL);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, dmatest_bus))) {
+ __free_page(dmatest_page);
+ return -ENOMEM;
+ }
/* Run a small DMA test.
* The magic multipliers to the length tell the firmware
@@ -1191,6 +1195,7 @@
int bytes, int watchdog)
{
struct page *page;
+ dma_addr_t bus;
int idx;
#if MYRI10GE_ALLOC_SIZE > 4096
int end_offset;
@@ -1215,11 +1220,21 @@
rx->watchdog_needed = 1;
return;
}
+
+ bus = pci_map_page(mgp->pdev, page, 0,
+ MYRI10GE_ALLOC_SIZE,
+ PCI_DMA_FROMDEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+ __free_pages(page, MYRI10GE_ALLOC_ORDER);
+ if (rx->fill_cnt - rx->cnt < 16)
+ rx->watchdog_needed = 1;
+ return;
+ }
+
rx->page = page;
rx->page_offset = 0;
- rx->bus = pci_map_page(mgp->pdev, page, 0,
- MYRI10GE_ALLOC_SIZE,
- PCI_DMA_FROMDEVICE);
+ rx->bus = bus;
+
}
rx->info[idx].page = rx->page;
rx->info[idx].page_offset = rx->page_offset;
@@ -2576,6 +2591,35 @@
mb();
}
+static void myri10ge_unmap_tx_dma(struct myri10ge_priv *mgp,
+ struct myri10ge_tx_buf *tx, int idx)
+{
+ unsigned int len;
+ int last_idx;
+
+ /* Free any DMA resources we've alloced and clear out the skb slot */
+ last_idx = (idx + 1) & tx->mask;
+ idx = tx->req & tx->mask;
+ do {
+ len = dma_unmap_len(&tx->info[idx], len);
+ if (len) {
+ if (tx->info[idx].skb != NULL)
+ pci_unmap_single(mgp->pdev,
+ dma_unmap_addr(&tx->info[idx],
+ bus), len,
+ PCI_DMA_TODEVICE);
+ else
+ pci_unmap_page(mgp->pdev,
+ dma_unmap_addr(&tx->info[idx],
+ bus), len,
+ PCI_DMA_TODEVICE);
+ dma_unmap_len_set(&tx->info[idx], len, 0);
+ tx->info[idx].skb = NULL;
+ }
+ idx = (idx + 1) & tx->mask;
+ } while (idx != last_idx);
+}
+
/*
* Transmit a packet. We need to split the packet so that a single
* segment does not cross myri10ge->tx_boundary, so this makes segment
@@ -2599,7 +2643,7 @@
u32 low;
__be32 high_swapped;
unsigned int len;
- int idx, last_idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
+ int idx, avail, frag_cnt, frag_idx, count, mss, max_segments;
u16 pseudo_hdr_offset, cksum_offset, queue;
int cum_len, seglen, boundary, rdma_count;
u8 flags, odd_flag;
@@ -2696,9 +2740,12 @@
/* map the skb for DMA */
len = skb_headlen(skb);
+ bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus)))
+ goto drop;
+
idx = tx->req & tx->mask;
tx->info[idx].skb = skb;
- bus = pci_map_single(mgp->pdev, skb->data, len, PCI_DMA_TODEVICE);
dma_unmap_addr_set(&tx->info[idx], bus, bus);
dma_unmap_len_set(&tx->info[idx], len, len);
@@ -2797,12 +2844,16 @@
break;
/* map next fragment for DMA */
- idx = (count + tx->req) & tx->mask;
frag = &skb_shinfo(skb)->frags[frag_idx];
frag_idx++;
len = skb_frag_size(frag);
bus = skb_frag_dma_map(&mgp->pdev->dev, frag, 0, len,
DMA_TO_DEVICE);
+ if (unlikely(pci_dma_mapping_error(mgp->pdev, bus))) {
+ myri10ge_unmap_tx_dma(mgp, tx, idx);
+ goto drop;
+ }
+ idx = (count + tx->req) & tx->mask;
dma_unmap_addr_set(&tx->info[idx], bus, bus);
dma_unmap_len_set(&tx->info[idx], len, len);
}
@@ -2833,31 +2884,8 @@
return NETDEV_TX_OK;
abort_linearize:
- /* Free any DMA resources we've alloced and clear out the skb
- * slot so as to not trip up assertions, and to avoid a
- * double-free if linearizing fails */
+ myri10ge_unmap_tx_dma(mgp, tx, idx);
- last_idx = (idx + 1) & tx->mask;
- idx = tx->req & tx->mask;
- tx->info[idx].skb = NULL;
- do {
- len = dma_unmap_len(&tx->info[idx], len);
- if (len) {
- if (tx->info[idx].skb != NULL)
- pci_unmap_single(mgp->pdev,
- dma_unmap_addr(&tx->info[idx],
- bus), len,
- PCI_DMA_TODEVICE);
- else
- pci_unmap_page(mgp->pdev,
- dma_unmap_addr(&tx->info[idx],
- bus), len,
- PCI_DMA_TODEVICE);
- dma_unmap_len_set(&tx->info[idx], len, 0);
- tx->info[idx].skb = NULL;
- }
- idx = (idx + 1) & tx->mask;
- } while (idx != last_idx);
if (skb_is_gso(skb)) {
netdev_err(mgp->dev, "TSO but wanted to linearize?!?!?\n");
goto drop;
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index af951f3..50104a7 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2315,7 +2315,10 @@
work_done = netxen_process_rcv_ring(sds_ring, budget);
- if ((work_done < budget) && tx_complete) {
+ if (!tx_complete)
+ work_done = budget;
+
+ if (work_done < budget) {
napi_complete(&sds_ring->napi);
if (test_bit(__NX_DEV_UP, &adapter->state))
netxen_nic_enable_int(sds_ring);
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 0352345..437d4cf 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -478,7 +478,7 @@
while (1) {
u32 status, len;
- dma_addr_t mapping;
+ dma_addr_t mapping, new_mapping;
struct sk_buff *skb, *new_skb;
struct cp_desc *desc;
const unsigned buflen = cp->rx_buf_sz;
@@ -520,6 +520,14 @@
goto rx_next;
}
+ new_mapping = dma_map_single(&cp->pdev->dev, new_skb->data, buflen,
+ PCI_DMA_FROMDEVICE);
+ if (dma_mapping_error(&cp->pdev->dev, new_mapping)) {
+ dev->stats.rx_dropped++;
+ kfree_skb(new_skb);
+ goto rx_next;
+ }
+
dma_unmap_single(&cp->pdev->dev, mapping,
buflen, PCI_DMA_FROMDEVICE);
@@ -531,12 +539,11 @@
skb_put(skb, len);
- mapping = dma_map_single(&cp->pdev->dev, new_skb->data, buflen,
- PCI_DMA_FROMDEVICE);
cp->rx_skb[rx_tail] = new_skb;
cp_rx_skb(cp, skb, desc);
rx++;
+ mapping = new_mapping;
rx_next:
cp->rx_ring[rx_tail].opts2 = 0;
@@ -671,9 +678,6 @@
le32_to_cpu(txd->opts1) & 0xffff,
PCI_DMA_TODEVICE);
- bytes_compl += skb->len;
- pkts_compl++;
-
if (status & LastFrag) {
if (status & (TxError | TxFIFOUnder)) {
netif_dbg(cp, tx_err, cp->dev,
@@ -695,6 +699,8 @@
netif_dbg(cp, tx_done, cp->dev,
"tx done, slot %d\n", tx_tail);
}
+ bytes_compl += skb->len;
+ pkts_compl++;
dev_kfree_skb_irq(skb);
}
@@ -716,6 +722,22 @@
TxVlanTag | swab16(vlan_tx_tag_get(skb)) : 0x00;
}
+static void unwind_tx_frag_mapping(struct cp_private *cp, struct sk_buff *skb,
+ int first, int entry_last)
+{
+ int frag, index;
+ struct cp_desc *txd;
+ skb_frag_t *this_frag;
+ for (frag = 0; frag+first < entry_last; frag++) {
+ index = first+frag;
+ cp->tx_skb[index] = NULL;
+ txd = &cp->tx_ring[index];
+ this_frag = &skb_shinfo(skb)->frags[frag];
+ dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr),
+ skb_frag_size(this_frag), PCI_DMA_TODEVICE);
+ }
+}
+
static netdev_tx_t cp_start_xmit (struct sk_buff *skb,
struct net_device *dev)
{
@@ -749,6 +771,9 @@
len = skb->len;
mapping = dma_map_single(&cp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE);
+ if (dma_mapping_error(&cp->pdev->dev, mapping))
+ goto out_dma_error;
+
txd->opts2 = opts2;
txd->addr = cpu_to_le64(mapping);
wmb();
@@ -786,6 +811,9 @@
first_len = skb_headlen(skb);
first_mapping = dma_map_single(&cp->pdev->dev, skb->data,
first_len, PCI_DMA_TODEVICE);
+ if (dma_mapping_error(&cp->pdev->dev, first_mapping))
+ goto out_dma_error;
+
cp->tx_skb[entry] = skb;
entry = NEXT_TX(entry);
@@ -799,6 +827,11 @@
mapping = dma_map_single(&cp->pdev->dev,
skb_frag_address(this_frag),
len, PCI_DMA_TODEVICE);
+ if (dma_mapping_error(&cp->pdev->dev, mapping)) {
+ unwind_tx_frag_mapping(cp, skb, first_entry, entry);
+ goto out_dma_error;
+ }
+
eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0;
ctrl = eor | len | DescOwn;
@@ -859,11 +892,16 @@
if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1))
netif_stop_queue(dev);
+out_unlock:
spin_unlock_irqrestore(&cp->lock, intr_flags);
cpw8(TxPoll, NormalTxPoll);
return NETDEV_TX_OK;
+out_dma_error:
+ dev_kfree_skb_any(skb);
+ cp->dev->stats.tx_dropped++;
+ goto out_unlock;
}
/* Set or clear the multicast filter for this adaptor.
@@ -1054,6 +1092,10 @@
mapping = dma_map_single(&cp->pdev->dev, skb->data,
cp->rx_buf_sz, PCI_DMA_FROMDEVICE);
+ if (dma_mapping_error(&cp->pdev->dev, mapping)) {
+ kfree_skb(skb);
+ goto err_out;
+ }
cp->rx_skb[i] = skb;
cp->rx_ring[i].opts2 = 0;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 3ccedeb..942673f 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -1715,9 +1715,9 @@
if (len < ETH_ZLEN)
memset(tp->tx_buf[entry], 0, ETH_ZLEN);
skb_copy_and_csum_dev(skb, tp->tx_buf[entry]);
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
} else {
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 393f961..2183c618 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -3456,6 +3456,11 @@
rtl_writephy(tp, 0x14, 0x9065);
rtl_writephy(tp, 0x14, 0x1065);
+ /* Check ALDPS bit, disable it if enabled */
+ rtl_writephy(tp, 0x1f, 0x0a43);
+ if (rtl_readphy(tp, 0x10) & 0x0004)
+ rtl_w1w0_phy(tp, 0x10, 0x0000, 0x0004);
+
rtl_writephy(tp, 0x1f, 0x0000);
}
@@ -4218,6 +4223,7 @@
case RTL_GIGA_MAC_VER_23:
case RTL_GIGA_MAC_VER_24:
case RTL_GIGA_MAC_VER_34:
+ case RTL_GIGA_MAC_VER_35:
RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
break;
case RTL_GIGA_MAC_VER_40:
@@ -5762,7 +5768,7 @@
tp->TxDescArray + entry);
if (skb) {
tp->dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
tx_skb->skb = NULL;
}
}
@@ -5987,7 +5993,7 @@
err_dma_1:
rtl8169_unmap_tx_skb(d, tp->tx_skb + entry, txd);
err_dma_0:
- dev_kfree_skb(skb);
+ dev_kfree_skb_any(skb);
err_update_stats:
dev->stats.tx_dropped++;
return NETDEV_TX_OK;
@@ -6070,7 +6076,7 @@
tp->tx_stats.packets++;
tp->tx_stats.bytes += tx_skb->skb->len;
u64_stats_update_end(&tp->tx_stats.syncp);
- dev_kfree_skb(tx_skb->skb);
+ dev_kfree_skb_any(tx_skb->skb);
tx_skb->skb = NULL;
}
dirty_tx++;
diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
index 2397f0e..a520465 100644
--- a/drivers/net/ethernet/sfc/filter.c
+++ b/drivers/net/ethernet/sfc/filter.c
@@ -675,7 +675,7 @@
BUILD_BUG_ON(EFX_FILTER_INDEX_UC_DEF != 0);
BUILD_BUG_ON(EFX_FILTER_INDEX_MC_DEF !=
EFX_FILTER_MC_DEF - EFX_FILTER_UC_DEF);
- rep_index = spec->type - EFX_FILTER_INDEX_UC_DEF;
+ rep_index = spec->type - EFX_FILTER_UC_DEF;
ins_index = rep_index;
spin_lock_bh(&state->lock);
@@ -1196,7 +1196,9 @@
EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
- efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT, 0, rxq_index);
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT,
+ efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
+ rxq_index);
rc = efx_filter_set_ipv4_full(&spec, ip->protocol,
ip->daddr, ports[1], ip->saddr, ports[0]);
if (rc)
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 9a95abf..540ad16 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1319,6 +1319,13 @@
struct efx_ptp_data *ptp = efx->ptp_data;
int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
+ if (!ptp) {
+ if (net_ratelimit())
+ netif_warn(efx, drv, efx->net_dev,
+ "Received PTP event but PTP not set up\n");
+ return;
+ }
+
if (!ptp->enabled)
return;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index a7dfe36..5173eaa 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -282,9 +282,9 @@
}
/* Recycle the pages that are used by buffers that have just been received. */
-static void efx_recycle_rx_buffers(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf,
- unsigned int n_frags)
+static void efx_recycle_rx_pages(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
{
struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
@@ -294,6 +294,20 @@
} while (--n_frags);
}
+static void efx_discard_rx_packet(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
+{
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
+
+ efx_recycle_rx_pages(channel, rx_buf, n_frags);
+
+ do {
+ efx_free_rx_buffer(rx_buf);
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--n_frags);
+}
+
/**
* efx_fast_push_rx_descriptors - push new RX descriptors quickly
* @rx_queue: RX descriptor queue
@@ -533,8 +547,7 @@
*/
if (unlikely(rx_buf->flags & EFX_RX_PKT_DISCARD)) {
efx_rx_flush_packet(channel);
- put_page(rx_buf->page);
- efx_recycle_rx_buffers(channel, rx_buf, n_frags);
+ efx_discard_rx_packet(channel, rx_buf, n_frags);
return;
}
@@ -570,9 +583,9 @@
efx_sync_rx_buffer(efx, rx_buf, rx_buf->len);
}
- /* All fragments have been DMA-synced, so recycle buffers and pages. */
+ /* All fragments have been DMA-synced, so recycle pages. */
rx_buf = efx_rx_buffer(rx_queue, index);
- efx_recycle_rx_buffers(channel, rx_buf, n_frags);
+ efx_recycle_rx_pages(channel, rx_buf, n_frags);
/* Pipeline receives so that we give time for packet headers to be
* prefetched into cache.
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index bb4c167..ff9e994 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -97,7 +97,7 @@
config SMSC911X
tristate "SMSC LAN911x/LAN921x families embedded ethernet support"
- depends on (ARM || SUPERH || BLACKFIN || MIPS || MN10300)
+ depends on HAS_IOMEM
select CRC32
select NET_CORE
select MII
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index dfbf978..bdd703c 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1896,7 +1896,7 @@
SMC_SELECT_BANK(lp, 1);
val = SMC_GET_BASE(lp);
val = ((val & 0x1F00) >> 3) << SMC_IO_SHIFT;
- if (((unsigned int)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) {
+ if (((unsigned long)ioaddr & (0x3e0 << SMC_IO_SHIFT)) != val) {
printk("%s: IOADDR %p doesn't match configuration (%x).\n",
CARDNAME, ioaddr, val);
}
diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h
index 370e13d..5128587 100644
--- a/drivers/net/ethernet/smsc/smc91x.h
+++ b/drivers/net/ethernet/smsc/smc91x.h
@@ -46,7 +46,8 @@
defined(CONFIG_MACH_LITTLETON) ||\
defined(CONFIG_MACH_ZYLONITE2) ||\
defined(CONFIG_ARCH_VIPER) ||\
- defined(CONFIG_MACH_STARGATE2)
+ defined(CONFIG_MACH_STARGATE2) ||\
+ defined(CONFIG_ARCH_VERSATILE)
#include <asm/mach-types.h>
@@ -154,6 +155,8 @@
#define SMC_outl(v, a, r) writel(v, (a) + (r))
#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l)
#define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l)
+#define SMC_insw(a, r, p, l) readsw((a) + (r), p, l)
+#define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l)
#define SMC_IRQ_FLAGS (-1) /* from resource */
/* We actually can't write halfwords properly if not word aligned */
@@ -206,23 +209,6 @@
#define RPC_LSA_DEFAULT RPC_LED_TX_RX
#define RPC_LSB_DEFAULT RPC_LED_100_10
-#elif defined(CONFIG_ARCH_VERSATILE)
-
-#define SMC_CAN_USE_8BIT 1
-#define SMC_CAN_USE_16BIT 1
-#define SMC_CAN_USE_32BIT 1
-#define SMC_NOWAIT 1
-
-#define SMC_inb(a, r) readb((a) + (r))
-#define SMC_inw(a, r) readw((a) + (r))
-#define SMC_inl(a, r) readl((a) + (r))
-#define SMC_outb(v, a, r) writeb(v, (a) + (r))
-#define SMC_outw(v, a, r) writew(v, (a) + (r))
-#define SMC_outl(v, a, r) writel(v, (a) + (r))
-#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l)
-#define SMC_outsl(a, r, p, l) writesl((a) + (r), p, l)
-#define SMC_IRQ_FLAGS (-1) /* from resource */
-
#elif defined(CONFIG_MN10300)
/*
@@ -1124,8 +1110,7 @@
void __iomem *__ioaddr = ioaddr; \
if (__len >= 2 && (unsigned long)__ptr & 2) { \
__len -= 2; \
- SMC_outw(*(u16 *)__ptr, ioaddr, \
- DATA_REG(lp)); \
+ SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \
__ptr += 2; \
} \
if (SMC_CAN_USE_DATACS && lp->datacs) \
@@ -1133,8 +1118,7 @@
SMC_outsl(__ioaddr, DATA_REG(lp), __ptr, __len>>2); \
if (__len & 2) { \
__ptr += (__len & ~3); \
- SMC_outw(*((u16 *)__ptr), ioaddr, \
- DATA_REG(lp)); \
+ SMC_outsw(ioaddr, DATA_REG(lp), __ptr, 1); \
} \
} else if (SMC_16BIT(lp)) \
SMC_outsw(ioaddr, DATA_REG(lp), p, (l) >> 1); \
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 1df0ff3..ade8bdf 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -656,7 +656,7 @@
spin_lock_irqsave(&port->vio.lock, flags);
dr = &port->vio.drings[VIO_DRIVER_TX_RING];
- if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+ if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
if (!netif_queue_stopped(dev)) {
netif_stop_queue(dev);
@@ -704,7 +704,7 @@
dev->stats.tx_bytes += skb->len;
dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
- if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+ if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
netif_stop_queue(dev);
if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
netif_wake_queue(dev);
@@ -1083,6 +1083,24 @@
return vp;
}
+static void vnet_cleanup(void)
+{
+ struct vnet *vp;
+ struct net_device *dev;
+
+ mutex_lock(&vnet_list_mutex);
+ while (!list_empty(&vnet_list)) {
+ vp = list_first_entry(&vnet_list, struct vnet, list);
+ list_del(&vp->list);
+ dev = vp->dev;
+ /* vio_unregister_driver() should have cleaned up port_list */
+ BUG_ON(!list_empty(&vp->port_list));
+ unregister_netdev(dev);
+ free_netdev(dev);
+ }
+ mutex_unlock(&vnet_list_mutex);
+}
+
static const char *local_mac_prop = "local-mac-address";
static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
@@ -1239,6 +1257,7 @@
dev_set_drvdata(&vdev->dev, NULL);
kfree(port);
+
}
return 0;
}
@@ -1266,6 +1285,7 @@
static void __exit vnet_exit(void)
{
vio_unregister_driver(&vnet_port_driver);
+ vnet_cleanup();
}
module_init(vnet_init);
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 571452e..61a1540 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2019,7 +2019,6 @@
ndev->features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO
| NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM
- /*| NETIF_F_FRAGLIST */
;
ndev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
NETIF_F_TSO | NETIF_F_HW_VLAN_CTAG_TX;
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index d1a769f..e18240d 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1293,6 +1293,19 @@
if (vid == priv->data.default_vlan)
return 0;
+ if (priv->data.dual_emac) {
+ /* In dual EMAC, reserved VLAN id should not be used for
+ * creating VLAN interfaces as this can break the dual
+ * EMAC port separation
+ */
+ int i;
+
+ for (i = 0; i < priv->data.slaves; i++) {
+ if (vid == priv->slaves[i].port_vlan)
+ return -EINVAL;
+ }
+ }
+
dev_info(priv->dev, "Adding vlanid %d to vlan filter\n", vid);
return cpsw_add_vlan_ale_entry(priv, vid);
}
@@ -1306,6 +1319,15 @@
if (vid == priv->data.default_vlan)
return 0;
+ if (priv->data.dual_emac) {
+ int i;
+
+ for (i = 0; i < priv->data.slaves; i++) {
+ if (vid == priv->slaves[i].port_vlan)
+ return -EINVAL;
+ }
+ }
+
dev_info(priv->dev, "removing vlanid %d from vlan filter\n", vid);
ret = cpsw_ale_del_vlan(priv->ale, vid, 0);
if (ret != 0)
@@ -1547,6 +1569,10 @@
mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
phyid = be32_to_cpup(parp+1);
mdio = of_find_device_by_node(mdio_node);
+ if (!mdio) {
+ pr_err("Missing mdio platform device\n");
+ return -EINVAL;
+ }
snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
PHY_ID_FMT, mdio->name, phyid);
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 860e15d..7233610 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -876,8 +876,7 @@
netdev_mc_count(ndev) > EMAC_DEF_MAX_MULTICAST_ADDRESSES) {
mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST);
emac_add_mcast(priv, EMAC_ALL_MULTI_SET, NULL);
- }
- if (!netdev_mc_empty(ndev)) {
+ } else if (!netdev_mc_empty(ndev)) {
struct netdev_hw_addr *ha;
mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST);
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ca98acabf..c879969 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -32,7 +32,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#define DRV_NAME "via-rhine"
-#define DRV_VERSION "1.5.0"
+#define DRV_VERSION "1.5.1"
#define DRV_RELDATE "2010-10-09"
#include <linux/types.h>
@@ -1611,6 +1611,7 @@
goto out_unlock;
napi_disable(&rp->napi);
+ netif_tx_disable(dev);
spin_lock_bh(&rp->lock);
/* clear all descriptors */
@@ -1694,7 +1695,12 @@
cpu_to_le32(TXDESC | (skb->len >= ETH_ZLEN ? skb->len : ETH_ZLEN));
if (unlikely(vlan_tx_tag_present(skb))) {
- rp->tx_ring[entry].tx_status = cpu_to_le32((vlan_tx_tag_get(skb)) << 16);
+ u16 vid_pcp = vlan_tx_tag_get(skb);
+
+ /* drop CFI/DEI bit, register needs VID and PCP */
+ vid_pcp = (vid_pcp & VLAN_VID_MASK) |
+ ((vid_pcp & VLAN_PRIO_MASK) >> 1);
+ rp->tx_ring[entry].tx_status = cpu_to_le32((vid_pcp) << 16);
/* request tagging */
rp->tx_ring[entry].desc_length |= cpu_to_le32(0x020000);
}
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 57c2e5e..52de70b 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -297,6 +297,12 @@
lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1)));
lp->dma_out(lp, TX_CURDESC_PTR, lp->tx_bd_p);
+ /* Init descriptor indexes */
+ lp->tx_bd_ci = 0;
+ lp->tx_bd_next = 0;
+ lp->tx_bd_tail = 0;
+ lp->rx_bd_ci = 0;
+
return 0;
out:
@@ -1010,7 +1016,7 @@
dev_set_drvdata(&op->dev, ndev);
SET_NETDEV_DEV(ndev, &op->dev);
ndev->flags &= ~IFF_MULTICAST; /* clear multicast */
- ndev->features = NETIF_F_SG | NETIF_F_FRAGLIST;
+ ndev->features = NETIF_F_SG;
ndev->netdev_ops = &temac_netdev_ops;
ndev->ethtool_ops = &temac_ethtool_ops;
#if 0
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 24748e8..2e2eeba 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1488,7 +1488,7 @@
SET_NETDEV_DEV(ndev, &op->dev);
ndev->flags &= ~IFF_MULTICAST; /* clear multicast */
- ndev->features = NETIF_F_SG | NETIF_F_FRAGLIST;
+ ndev->features = NETIF_F_SG;
ndev->netdev_ops = &axienet_netdev_ops;
ndev->ethtool_ops = &axienet_ethtool_ops;
diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 3169252..5d78c1d 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -571,6 +571,8 @@
case HDLCDRVCTL_CALIBRATE:
if(!capable(CAP_SYS_RAWIO))
return -EPERM;
+ if (bi.data.calibrate > INT_MAX / s->par.bitrate)
+ return -EINVAL;
s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;
return 0;
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 0721e72..82529a2 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1058,6 +1058,7 @@
break;
case SIOCYAMGCFG:
+ memset(&yi, 0, sizeof(yi));
yi.cfg.mask = 0xffffffff;
yi.cfg.iobase = yp->iobase;
yi.cfg.irq = yp->irq;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 4dccead..59e9c56 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -138,6 +138,7 @@
struct hv_netvsc_packet *packet;
int ret;
unsigned int i, num_pages, npg_data;
+ u32 skb_length = skb->len;
/* Add multipages for skb->data and additional 2 for RNDIS */
npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1)
@@ -208,7 +209,7 @@
ret = rndis_filter_send(net_device_ctx->device_ctx,
packet);
if (ret == 0) {
- net->stats.tx_bytes += skb->len;
+ net->stats.tx_bytes += skb_length;
net->stats.tx_packets++;
} else {
kfree(packet);
@@ -328,7 +329,6 @@
return -EINVAL;
nvdev->start_remove = true;
- cancel_delayed_work_sync(&ndevctx->dwork);
cancel_work_sync(&ndevctx->work);
netif_tx_disable(ndev);
rndis_filter_device_remove(hdev);
@@ -431,8 +431,8 @@
net->netdev_ops = &device_ops;
/* TODO: Add GSO and Checksum offload */
- net->hw_features = NETIF_F_SG;
- net->features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_TX;
+ net->hw_features = 0;
+ net->features = NETIF_F_HW_VLAN_CTAG_TX;
SET_ETHTOOL_OPS(net, ðtool_ops);
SET_NETDEV_DEV(net, &dev->device);
diff --git a/drivers/net/ieee802154/fakehard.c b/drivers/net/ieee802154/fakehard.c
index bf0d55e..6adbef8 100644
--- a/drivers/net/ieee802154/fakehard.c
+++ b/drivers/net/ieee802154/fakehard.c
@@ -376,17 +376,20 @@
err = wpan_phy_register(phy);
if (err)
- goto out;
+ goto err_phy_reg;
err = register_netdev(dev);
- if (err < 0)
- goto out;
+ if (err)
+ goto err_netdev_reg;
dev_info(&pdev->dev, "Added ieee802154 HardMAC hardware\n");
return 0;
-out:
- unregister_netdev(dev);
+err_netdev_reg:
+ wpan_phy_unregister(phy);
+err_phy_reg:
+ free_netdev(dev);
+ wpan_phy_free(phy);
return err;
}
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index dc9f6a4..a3bed28 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -291,11 +291,17 @@
rtnl_lock();
err = __rtnl_link_register(&ifb_link_ops);
+ if (err < 0)
+ goto out;
- for (i = 0; i < numifbs && !err; i++)
+ for (i = 0; i < numifbs && !err; i++) {
err = ifb_init_one(i);
+ cond_resched();
+ }
if (err)
__rtnl_link_unregister(&ifb_link_ops);
+
+out:
rtnl_unlock();
return err;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 6e91931..9be91cb 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -261,11 +261,9 @@
const struct macvlan_dev *vlan = netdev_priv(dev);
const struct macvlan_port *port = vlan->port;
const struct macvlan_dev *dest;
- __u8 ip_summed = skb->ip_summed;
if (vlan->mode == MACVLAN_MODE_BRIDGE) {
const struct ethhdr *eth = (void *)skb->data;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
/* send to other bridge ports directly */
if (is_multicast_ether_addr(eth->h_dest)) {
@@ -283,7 +281,6 @@
}
xmit_world:
- skb->ip_summed = ip_summed;
skb->dev = vlan->lowerdev;
return dev_queue_xmit(skb);
}
@@ -423,8 +420,10 @@
struct macvlan_dev *vlan = netdev_priv(dev);
struct net_device *lowerdev = vlan->lowerdev;
- if (change & IFF_ALLMULTI)
- dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+ if (dev->flags & IFF_UP) {
+ if (change & IFF_ALLMULTI)
+ dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+ }
}
static void macvlan_set_mac_lists(struct net_device *dev)
@@ -501,6 +500,7 @@
(lowerdev->state & MACVLAN_STATE_MASK);
dev->features = lowerdev->features & MACVLAN_FEATURES;
dev->features |= NETIF_F_LLTX;
+ dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
dev->gso_max_size = lowerdev->gso_max_size;
dev->iflink = lowerdev->ifindex;
dev->hard_header_len = lowerdev->hard_header_len;
@@ -727,6 +727,10 @@
return -EADDRNOTAVAIL;
}
+ if (data && data[IFLA_MACVLAN_FLAGS] &&
+ nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~MACVLAN_FLAG_NOPROMISC)
+ return -EINVAL;
+
if (data && data[IFLA_MACVLAN_MODE]) {
switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) {
case MACVLAN_MODE_PRIVATE:
@@ -958,7 +962,6 @@
list_for_each_entry_safe(vlan, next, &port->vlans, list)
vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
unregister_netdevice_many(&list_kill);
- list_del(&list_kill);
break;
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid underlaying device to change its type. */
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index b6dd6a7..8fc46fc 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -625,6 +625,8 @@
if (skb->ip_summed == CHECKSUM_PARTIAL) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
vnet_hdr->csum_start = skb_checksum_start_offset(skb);
+ if (vlan_tx_tag_present(skb))
+ vnet_hdr->csum_start += VLAN_HLEN;
vnet_hdr->csum_offset = skb->csum_offset;
} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
@@ -633,12 +635,38 @@
return 0;
}
+static unsigned long iov_pages(const struct iovec *iv, int offset,
+ unsigned long nr_segs)
+{
+ unsigned long seg, base;
+ int pages = 0, len, size;
+
+ while (nr_segs && (offset >= iv->iov_len)) {
+ offset -= iv->iov_len;
+ ++iv;
+ --nr_segs;
+ }
+
+ for (seg = 0; seg < nr_segs; seg++) {
+ base = (unsigned long)iv[seg].iov_base + offset;
+ len = iv[seg].iov_len - offset;
+ size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+ pages += size;
+ offset = 0;
+ }
+
+ return pages;
+}
+
+/* Neighbour code has some assumptions on HH_DATA_MOD alignment */
+#define MACVTAP_RESERVE HH_DATA_OFF(ETH_HLEN)
/* Get packet from user space buffer */
static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
const struct iovec *iv, unsigned long total_len,
size_t count, int noblock)
{
+ int good_linear = SKB_MAX_HEAD(MACVTAP_RESERVE);
struct sk_buff *skb;
struct macvlan_dev *vlan;
unsigned long len = total_len;
@@ -647,6 +675,7 @@
int vnet_hdr_len = 0;
int copylen = 0;
bool zerocopy = false;
+ size_t linear;
if (q->flags & IFF_VNET_HDR) {
vnet_hdr_len = q->vnet_hdr_sz;
@@ -678,42 +707,40 @@
if (unlikely(count > UIO_MAXIOV))
goto err;
- if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY))
- zerocopy = true;
+ if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
+ copylen = vnet_hdr.hdr_len ? vnet_hdr.hdr_len : GOODCOPY_LEN;
+ if (copylen > good_linear)
+ copylen = good_linear;
+ linear = copylen;
+ if (iov_pages(iv, vnet_hdr_len + copylen, count)
+ <= MAX_SKB_FRAGS)
+ zerocopy = true;
+ }
- if (zerocopy) {
- /* Userspace may produce vectors with count greater than
- * MAX_SKB_FRAGS, so we need to linearize parts of the skb
- * to let the rest of data to be fit in the frags.
- */
- if (count > MAX_SKB_FRAGS) {
- copylen = iov_length(iv, count - MAX_SKB_FRAGS);
- if (copylen < vnet_hdr_len)
- copylen = 0;
- else
- copylen -= vnet_hdr_len;
- }
- /* There are 256 bytes to be copied in skb, so there is enough
- * room for skb expand head in case it is used.
- * The rest buffer is mapped from userspace.
- */
- if (copylen < vnet_hdr.hdr_len)
- copylen = vnet_hdr.hdr_len;
- if (!copylen)
- copylen = GOODCOPY_LEN;
- } else
+ if (!zerocopy) {
copylen = len;
+ if (vnet_hdr.hdr_len > good_linear)
+ linear = good_linear;
+ else
+ linear = vnet_hdr.hdr_len;
+ }
- skb = macvtap_alloc_skb(&q->sk, NET_IP_ALIGN, copylen,
- vnet_hdr.hdr_len, noblock, &err);
+ skb = macvtap_alloc_skb(&q->sk, MACVTAP_RESERVE, copylen,
+ linear, noblock, &err);
if (!skb)
goto err;
if (zerocopy)
err = zerocopy_sg_from_iovec(skb, iv, vnet_hdr_len, count);
- else
+ else {
err = skb_copy_datagram_from_iovec(skb, 0, iv, vnet_hdr_len,
len);
+ if (!err && m && m->msg_control) {
+ struct ubuf_info *uarg = m->msg_control;
+ uarg->callback(uarg, false);
+ }
+ }
+
if (err)
goto err_kfree;
@@ -775,11 +802,10 @@
const struct sk_buff *skb,
const struct iovec *iv, int len)
{
- struct macvlan_dev *vlan;
int ret;
int vnet_hdr_len = 0;
int vlan_offset = 0;
- int copied;
+ int copied, total;
if (q->flags & IFF_VNET_HDR) {
struct virtio_net_hdr vnet_hdr;
@@ -794,7 +820,8 @@
if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
return -EFAULT;
}
- copied = vnet_hdr_len;
+ total = copied = vnet_hdr_len;
+ total += skb->len;
if (!vlan_tx_tag_present(skb))
len = min_t(int, skb->len, len);
@@ -809,6 +836,7 @@
vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
len = min_t(int, skb->len + VLAN_HLEN, len);
+ total += VLAN_HLEN;
copy = min_t(int, vlan_offset, len);
ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
@@ -826,16 +854,9 @@
}
ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
- copied += len;
done:
- rcu_read_lock_bh();
- vlan = rcu_dereference_bh(q->vlan);
- if (vlan)
- macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
- rcu_read_unlock_bh();
-
- return ret ? ret : copied;
+ return ret ? ret : total;
}
static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
@@ -887,7 +908,9 @@
}
ret = macvtap_do_read(q, iocb, iv, len, file->f_flags & O_NONBLOCK);
- ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */
+ ret = min_t(ssize_t, ret, len);
+ if (ret > 0)
+ iocb->ki_pos = ret;
out:
return ret;
}
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 38f0b31..dcaeb81 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -203,6 +203,25 @@
}
/**
+ * phy_check_valid - check if there is a valid PHY setting which matches
+ * speed, duplex, and feature mask
+ * @speed: speed to match
+ * @duplex: duplex to match
+ * @features: A mask of the valid settings
+ *
+ * Description: Returns true if there is a valid setting, false otherwise.
+ */
+static inline bool phy_check_valid(int speed, int duplex, u32 features)
+{
+ unsigned int idx;
+
+ idx = phy_find_valid(phy_find_setting(speed, duplex), features);
+
+ return settings[idx].speed == speed && settings[idx].duplex == duplex &&
+ (settings[idx].setting & features);
+}
+
+/**
* phy_sanitize_settings - make sure the PHY is set to supported speed and duplex
* @phydev: the target phy_device struct
*
@@ -439,7 +458,7 @@
{
phydev->adjust_state = handler;
- schedule_delayed_work(&phydev->state_queue, HZ);
+ queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, HZ);
}
/**
@@ -500,7 +519,7 @@
disable_irq_nosync(irq);
atomic_inc(&phydev->irq_disable);
- schedule_work(&phydev->phy_queue);
+ queue_work(system_power_efficient_wq, &phydev->phy_queue);
return IRQ_HANDLED;
}
@@ -655,7 +674,7 @@
/* reschedule state queue work to run as soon as possible */
cancel_delayed_work_sync(&phydev->state_queue);
- schedule_delayed_work(&phydev->state_queue, 0);
+ queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
return;
@@ -918,7 +937,8 @@
if (err < 0)
phy_error(phydev);
- schedule_delayed_work(&phydev->state_queue, PHY_STATE_TIME * HZ);
+ queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
+ PHY_STATE_TIME * HZ);
}
static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
@@ -1011,7 +1031,7 @@
(phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
int eee_lp, eee_cap, eee_adv;
u32 lp, cap, adv;
- int idx, status;
+ int status;
/* Read phy status to properly get the right settings */
status = phy_read_status(phydev);
@@ -1043,8 +1063,7 @@
adv = mmd_eee_adv_to_ethtool_adv_t(eee_adv);
lp = mmd_eee_adv_to_ethtool_adv_t(eee_lp);
- idx = phy_find_setting(phydev->speed, phydev->duplex);
- if (!(lp & adv & settings[idx].setting))
+ if (!phy_check_valid(phydev->speed, phydev->duplex, lp & adv))
goto eee_exit;
if (clk_stop_enable) {
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index 602c625..b5edc7f 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -246,7 +246,7 @@
/*
* See if we managed to reduce the size of the packet.
*/
- if (olen < isize) {
+ if (olen < isize && olen <= osize) {
state->stats.comp_bytes += olen;
state->stats.comp_packets++;
} else {
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 72ff14b..5a1897d 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -601,7 +601,7 @@
if (file == ppp->owner)
ppp_shutdown_interface(ppp);
}
- if (atomic_long_read(&file->f_count) <= 2) {
+ if (atomic_long_read(&file->f_count) < 2) {
ppp_release(NULL, file);
err = 0;
} else
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index bb07ba9..becfa3e 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -675,7 +675,7 @@
po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
dev->hard_header_len);
- po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr);
+ po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
po->chan.private = sk;
po->chan.ops = &pppoe_chan_ops;
@@ -979,8 +979,6 @@
if (error < 0)
goto end;
- m->msg_namelen = 0;
-
if (skb) {
total_len = min_t(size_t, total_len, skb->len);
error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 162464f..0d5a5fa 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@
nf_reset(skb);
skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
ip_send_check(iph);
ip_local_out(skb);
@@ -506,7 +506,9 @@
int len = sizeof(struct sockaddr_pppox);
struct sockaddr_pppox sp;
- sp.sa_family = AF_PPPOX;
+ memset(&sp.sa_addr, 0, sizeof(sp.sa_addr));
+
+ sp.sa_family = AF_PPPOX;
sp.sa_protocol = PX_PROTO_PPTP;
sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b305105..14179a6 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -42,9 +42,7 @@
static struct team_port *team_port_get_rcu(const struct net_device *dev)
{
- struct team_port *port = rcu_dereference(dev->rx_handler_data);
-
- return team_port_exists(dev) ? port : NULL;
+ return rcu_dereference(dev->rx_handler_data);
}
static struct team_port *team_port_get_rtnl(const struct net_device *dev)
@@ -1217,6 +1215,8 @@
return 0;
}
+static void __team_carrier_check(struct team *team);
+
static int team_user_linkup_option_set(struct team *team,
struct team_gsetter_ctx *ctx)
{
@@ -1224,6 +1224,7 @@
port->user.linkup = ctx->data.bool_val;
team_refresh_port_linkup(port);
+ __team_carrier_check(port->team);
return 0;
}
@@ -1243,6 +1244,7 @@
port->user.linkup_enabled = ctx->data.bool_val;
team_refresh_port_linkup(port);
+ __team_carrier_check(port->team);
return 0;
}
@@ -1519,11 +1521,11 @@
if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
- rcu_read_lock();
- list_for_each_entry_rcu(port, &team->port_list, list)
+ mutex_lock(&team->lock);
+ list_for_each_entry(port, &team->port_list, list)
if (team->ops.port_change_dev_addr)
team->ops.port_change_dev_addr(team, port);
- rcu_read_unlock();
+ mutex_unlock(&team->lock);
return 0;
}
@@ -1538,6 +1540,7 @@
* to traverse list in reverse under rcu_read_lock
*/
mutex_lock(&team->lock);
+ team->port_mtu_change_allowed = true;
list_for_each_entry(port, &team->port_list, list) {
err = dev_set_mtu(port->dev, new_mtu);
if (err) {
@@ -1546,6 +1549,7 @@
goto unwind;
}
}
+ team->port_mtu_change_allowed = false;
mutex_unlock(&team->lock);
dev->mtu = new_mtu;
@@ -1555,6 +1559,7 @@
unwind:
list_for_each_entry_continue_reverse(port, &team->port_list, list)
dev_set_mtu(port->dev, dev->mtu);
+ team->port_mtu_change_allowed = false;
mutex_unlock(&team->lock);
return err;
@@ -2674,7 +2679,9 @@
break;
case NETDEV_CHANGEMTU:
/* Forbid to change mtu of underlaying device */
- return NOTIFY_BAD;
+ if (!port->team->port_mtu_change_allowed)
+ return NOTIFY_BAD;
+ break;
case NETDEV_PRE_TYPE_CHANGE:
/* Forbid to change type of underlaying device */
return NOTIFY_BAD;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9c61f87..5824971 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1037,6 +1037,29 @@
return 0;
}
+static unsigned long iov_pages(const struct iovec *iv, int offset,
+ unsigned long nr_segs)
+{
+ unsigned long seg, base;
+ int pages = 0, len, size;
+
+ while (nr_segs && (offset >= iv->iov_len)) {
+ offset -= iv->iov_len;
+ ++iv;
+ --nr_segs;
+ }
+
+ for (seg = 0; seg < nr_segs; seg++) {
+ base = (unsigned long)iv[seg].iov_base + offset;
+ len = iv[seg].iov_len - offset;
+ size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+ pages += size;
+ offset = 0;
+ }
+
+ return pages;
+}
+
/* Get packet from user space buffer */
static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
void *msg_control, const struct iovec *iv,
@@ -1044,8 +1067,9 @@
{
struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
struct sk_buff *skb;
- size_t len = total_len, align = NET_SKB_PAD;
+ size_t len = total_len, align = NET_SKB_PAD, linear;
struct virtio_net_hdr gso = { 0 };
+ int good_linear;
int offset = 0;
int copylen;
bool zerocopy = false;
@@ -1053,8 +1077,9 @@
u32 rxhash;
if (!(tun->flags & TUN_NO_PI)) {
- if ((len -= sizeof(pi)) > total_len)
+ if (len < sizeof(pi))
return -EINVAL;
+ len -= sizeof(pi);
if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
return -EFAULT;
@@ -1062,8 +1087,9 @@
}
if (tun->flags & TUN_VNET_HDR) {
- if ((len -= tun->vnet_hdr_sz) > total_len)
+ if (len < tun->vnet_hdr_sz)
return -EINVAL;
+ len -= tun->vnet_hdr_sz;
if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
return -EFAULT;
@@ -1084,34 +1110,30 @@
return -EINVAL;
}
- if (msg_control)
- zerocopy = true;
+ good_linear = SKB_MAX_HEAD(align);
- if (zerocopy) {
- /* Userspace may produce vectors with count greater than
- * MAX_SKB_FRAGS, so we need to linearize parts of the skb
- * to let the rest of data to be fit in the frags.
- */
- if (count > MAX_SKB_FRAGS) {
- copylen = iov_length(iv, count - MAX_SKB_FRAGS);
- if (copylen < offset)
- copylen = 0;
- else
- copylen -= offset;
- } else
- copylen = 0;
- /* There are 256 bytes to be copied in skb, so there is enough
- * room for skb expand head in case it is used.
+ if (msg_control) {
+ /* There are 256 bytes to be copied in skb, so there is
+ * enough room for skb expand head in case it is used.
* The rest of the buffer is mapped from userspace.
*/
- if (copylen < gso.hdr_len)
- copylen = gso.hdr_len;
- if (!copylen)
- copylen = GOODCOPY_LEN;
- } else
- copylen = len;
+ copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN;
+ if (copylen > good_linear)
+ copylen = good_linear;
+ linear = copylen;
+ if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS)
+ zerocopy = true;
+ }
- skb = tun_alloc_skb(tfile, align, copylen, gso.hdr_len, noblock);
+ if (!zerocopy) {
+ copylen = len;
+ if (gso.hdr_len > good_linear)
+ linear = good_linear;
+ else
+ linear = gso.hdr_len;
+ }
+
+ skb = tun_alloc_skb(tfile, align, copylen, linear, noblock);
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
tun->dev->stats.rx_dropped++;
@@ -1120,8 +1142,13 @@
if (zerocopy)
err = zerocopy_sg_from_iovec(skb, iv, offset, count);
- else
+ else {
err = skb_copy_datagram_from_iovec(skb, 0, iv, offset, len);
+ if (!err && msg_control) {
+ struct ubuf_info *uarg = msg_control;
+ uarg->callback(uarg, false);
+ }
+ }
if (err) {
tun->dev->stats.rx_dropped++;
@@ -1385,6 +1412,8 @@
ret = tun_do_read(tun, tfile, iocb, iv, len,
file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
+ if (ret > 0)
+ iocb->ki_pos = ret;
out:
tun_put(tun);
return ret;
@@ -1674,11 +1703,11 @@
INIT_LIST_HEAD(&tun->disabled);
err = tun_attach(tun, file);
if (err < 0)
- goto err_free_dev;
+ goto err_free_flow;
err = register_netdevice(tun->dev);
if (err < 0)
- goto err_free_dev;
+ goto err_detach;
if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
device_create_file(&tun->dev->dev, &dev_attr_owner) ||
@@ -1722,7 +1751,12 @@
strcpy(ifr->ifr_name, tun->dev->name);
return 0;
- err_free_dev:
+err_detach:
+ tun_detach_all(dev);
+err_free_flow:
+ tun_flow_uninit(tun);
+ security_tun_dev_free_security(tun->security);
+err_free_dev:
free_netdev(dev);
return err;
}
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index ad5d1e4..97b5de7 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -915,7 +915,8 @@
.status = asix_status,
.link_reset = ax88178_link_reset,
.reset = ax88178_reset,
- .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR,
+ .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+ FLAG_MULTI_PACKET,
.rx_fixup = asix_rx_fixup_common,
.tx_fixup = asix_tx_fixup,
};
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index bd8758f..3b449c4 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -695,6 +695,7 @@
{
struct usbnet *dev = netdev_priv(net);
struct sockaddr *addr = p;
+ int ret;
if (netif_running(net))
return -EBUSY;
@@ -704,8 +705,12 @@
memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);
/* Set the MAC address */
- return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
+ ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN,
ETH_ALEN, net->dev_addr);
+ if (ret < 0)
+ return ret;
+
+ return 0;
}
static const struct net_device_ops ax88179_netdev_ops = {
@@ -1029,10 +1034,10 @@
dev->mii.supports_gmii = 1;
dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+ NETIF_F_RXCSUM;
dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+ NETIF_F_RXCSUM;
/* Enable checksum offload */
*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
@@ -1109,6 +1114,10 @@
u16 hdr_off;
u32 *pkt_hdr;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
skb_trim(skb, skb->len - 4);
memcpy(&rx_hdr, skb_tail_pointer(skb), 4);
le32_to_cpus(&rx_hdr);
@@ -1173,7 +1182,6 @@
if (((skb->len + 8) % frame_size) == 0)
tx_hdr2 |= 0x80008000; /* Enable padding */
- skb_linearize(skb);
headroom = skb_headroom(skb);
tailroom = skb_tailroom(skb);
@@ -1317,10 +1325,10 @@
1, 1, tmp);
dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+ NETIF_F_RXCSUM;
dev->net->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO;
+ NETIF_F_RXCSUM;
/* Enable checksum offload */
*tmp = AX_RXCOE_IP | AX_RXCOE_TCP | AX_RXCOE_UDP |
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 04ee044..b1897c7 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -709,6 +709,11 @@
.bInterfaceProtocol = USB_CDC_PROTO_NONE,
.driver_info = (unsigned long)&wwan_info,
}, {
+ /* Telit modules */
+ USB_VENDOR_AND_INTERFACE_INFO(0x1bc7, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = (kernel_ulong_t) &wwan_info,
+}, {
USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET,
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long) &cdc_info,
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 8728198..7cabe45 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -120,6 +120,16 @@
cdc_ncm_unbind(dev, intf);
}
+/* verify that the ethernet protocol is IPv4 or IPv6 */
+static bool is_ip_proto(__be16 proto)
+{
+ switch (proto) {
+ case htons(ETH_P_IP):
+ case htons(ETH_P_IPV6):
+ return true;
+ }
+ return false;
+}
static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
{
@@ -128,6 +138,7 @@
struct cdc_ncm_ctx *ctx = info->ctx;
__le32 sign = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN);
u16 tci = 0;
+ bool is_ip;
u8 *c;
if (!ctx)
@@ -137,25 +148,32 @@
if (skb->len <= ETH_HLEN)
goto error;
+ /* Some applications using e.g. packet sockets will
+ * bypass the VLAN acceleration and create tagged
+ * ethernet frames directly. We primarily look for
+ * the accelerated out-of-band tag, but fall back if
+ * required
+ */
+ skb_reset_mac_header(skb);
+ if (vlan_get_tag(skb, &tci) < 0 && skb->len > VLAN_ETH_HLEN &&
+ __vlan_get_tag(skb, &tci) == 0) {
+ is_ip = is_ip_proto(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto);
+ skb_pull(skb, VLAN_ETH_HLEN);
+ } else {
+ is_ip = is_ip_proto(eth_hdr(skb)->h_proto);
+ skb_pull(skb, ETH_HLEN);
+ }
+
/* mapping VLANs to MBIM sessions:
* no tag => IPS session <0>
* 1 - 255 => IPS session <vlanid>
* 256 - 511 => DSS session <vlanid - 256>
* 512 - 4095 => unsupported, drop
*/
- vlan_get_tag(skb, &tci);
-
switch (tci & 0x0f00) {
case 0x0000: /* VLAN ID 0 - 255 */
- /* verify that datagram is IPv4 or IPv6 */
- skb_reset_mac_header(skb);
- switch (eth_hdr(skb)->h_proto) {
- case htons(ETH_P_IP):
- case htons(ETH_P_IPV6):
- break;
- default:
+ if (!is_ip)
goto error;
- }
c = (u8 *)&sign;
c[3] = tci;
break;
@@ -169,7 +187,6 @@
"unsupported tci=0x%04x\n", tci);
goto error;
}
- skb_pull(skb, ETH_HLEN);
}
spin_lock_bh(&ctx->mtx);
@@ -400,6 +417,10 @@
{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68a2, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&cdc_mbim_info_zlp,
},
+ /* HP hs2434 Mobile Broadband Module needs ZLPs */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x3f0, 0x4b1d, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&cdc_mbim_info_zlp,
+ },
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&cdc_mbim_info,
},
diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c
index 1e207f0..49ab45e 100644
--- a/drivers/net/usb/cx82310_eth.c
+++ b/drivers/net/usb/cx82310_eth.c
@@ -302,9 +302,18 @@
.tx_fixup = cx82310_tx_fixup,
};
+#define USB_DEVICE_CLASS(vend, prod, cl, sc, pr) \
+ .match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
+ USB_DEVICE_ID_MATCH_DEV_INFO, \
+ .idVendor = (vend), \
+ .idProduct = (prod), \
+ .bDeviceClass = (cl), \
+ .bDeviceSubClass = (sc), \
+ .bDeviceProtocol = (pr)
+
static const struct usb_device_id products[] = {
{
- USB_DEVICE_AND_INTERFACE_INFO(0x0572, 0xcb01, 0xff, 0, 0),
+ USB_DEVICE_CLASS(0x0572, 0xcb01, 0xff, 0, 0),
.driver_info = (unsigned long) &cx82310_info
},
{ },
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 2dbb946..c0bfc81 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -303,7 +303,7 @@
rx_ctl |= 0x02;
} else if (net->flags & IFF_ALLMULTI ||
netdev_mc_count(net) > DM_MAX_MCAST) {
- rx_ctl |= 0x04;
+ rx_ctl |= 0x08;
} else if (!netdev_mc_empty(net)) {
struct netdev_hw_addr *ha;
@@ -364,7 +364,12 @@
dev->net->ethtool_ops = &dm9601_ethtool_ops;
dev->net->hard_header_len += DM_TX_OVERHEAD;
dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
- dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD;
+
+ /* dm9620/21a require room for 4 byte padding, even in dm9601
+ * mode, so we need +1 to be able to receive full size
+ * ethernet frames.
+ */
+ dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD + 1;
dev->mii.dev = dev->net;
dev->mii.mdio_read = dm9601_mdio_read;
@@ -468,7 +473,7 @@
static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
gfp_t flags)
{
- int len;
+ int len, pad;
/* format:
b1: packet length low
@@ -476,12 +481,23 @@
b3..n: packet data
*/
- len = skb->len;
+ len = skb->len + DM_TX_OVERHEAD;
- if (skb_headroom(skb) < DM_TX_OVERHEAD) {
+ /* workaround for dm962x errata with tx fifo getting out of
+ * sync if a USB bulk transfer retry happens right after a
+ * packet with odd / maxpacket length by adding up to 3 bytes
+ * padding.
+ */
+ while ((len & 1) || !(len % dev->maxpacket))
+ len++;
+
+ len -= DM_TX_OVERHEAD; /* hw header doesn't count as part of length */
+ pad = len - skb->len;
+
+ if (skb_headroom(skb) < DM_TX_OVERHEAD || skb_tailroom(skb) < pad) {
struct sk_buff *skb2;
- skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, 0, flags);
+ skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, pad, flags);
dev_kfree_skb_any(skb);
skb = skb2;
if (!skb)
@@ -490,10 +506,10 @@
__skb_push(skb, DM_TX_OVERHEAD);
- /* usbnet adds padding if length is a multiple of packet size
- if so, adjust length value in header */
- if ((skb->len % dev->maxpacket) == 0)
- len++;
+ if (pad) {
+ memset(skb->data + skb->len, 0, pad);
+ __skb_put(skb, pad);
+ }
skb->data[0] = len;
skb->data[1] = len >> 8;
diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index a7e3f4e..82ab61d 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -86,6 +86,10 @@
u32 size;
u32 count;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
header = (struct gl_header *) skb->data;
// get the packet count of the received skb
diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 03832d3..9237c45 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -529,8 +529,9 @@
{
u8 status;
- if (skb->len == 0) {
- dev_err(&dev->udev->dev, "unexpected empty rx frame\n");
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len) {
+ dev_err(&dev->udev->dev, "unexpected tiny rx frame\n");
return 0;
}
diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c
index 93e0716..7f4a3a4 100644
--- a/drivers/net/usb/net1080.c
+++ b/drivers/net/usb/net1080.c
@@ -366,6 +366,10 @@
struct nc_trailer *trailer;
u16 hdr_len, packet_len;
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
if (!(skb->len & 0x01)) {
netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n",
skb->len, dev->net->hard_header_len, dev->hard_mtu,
diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c
index 0fcc8e6..74323e9 100644
--- a/drivers/net/usb/plusb.c
+++ b/drivers/net/usb/plusb.c
@@ -136,6 +136,11 @@
}, {
USB_DEVICE(0x050d, 0x258a), /* Belkin F5U258/F5U279 (PL-25A1) */
.driver_info = (unsigned long) &prolific_info,
+}, {
+ USB_DEVICE(0x3923, 0x7825), /* National Instruments USB
+ * Host-to-Host Cable
+ */
+ .driver_info = (unsigned long) &prolific_info,
},
{ }, // END
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 5645921..43204f4 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -80,10 +80,10 @@
{
__be16 proto;
- /* usbnet rx_complete guarantees that skb->len is at least
- * hard_header_len, so we can inspect the dest address without
- * checking skb->len
- */
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
switch (skb->data[0] & 0xf0) {
case 0x40:
proto = htons(ETH_P_IP);
@@ -518,11 +518,158 @@
/* 3. Combined interface devices matching on interface number */
{QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */
+ {QMI_FIXED_INTF(0x05c6, 0x7000, 0)},
+ {QMI_FIXED_INTF(0x05c6, 0x7001, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7002, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x7101, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x7102, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x8000, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x8001, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9000, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9003, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9005, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x900a, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900b, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x900c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x900d, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x900f, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9010, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9010, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9011, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9011, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9021, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x9022, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9025, 4)}, /* Alcatel-sbell ASB TL131 TDD LTE (China Mobile) */
+ {QMI_FIXED_INTF(0x05c6, 0x9026, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x902e, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9031, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9032, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9033, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9034, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9035, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9036, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9037, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9038, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x903b, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x903c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x903d, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x903e, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9043, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9046, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9047, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9048, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x904c, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9050, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9052, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9053, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9053, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9054, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9054, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9055, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9056, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9062, 9)},
+ {QMI_FIXED_INTF(0x05c6, 0x9064, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9065, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9065, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9066, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9066, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9067, 1)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 2)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9068, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9069, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9070, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9070, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9075, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9076, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9077, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9078, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9079, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 5)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 6)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 7)},
+ {QMI_FIXED_INTF(0x05c6, 0x9080, 8)},
+ {QMI_FIXED_INTF(0x05c6, 0x9083, 3)},
+ {QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
+ {QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
+ {QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
+ {QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
{QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */
{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */
+ {QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */
+ {QMI_FIXED_INTF(0x16d8, 0x6007, 0)}, /* CMOTech CHE-628S */
+ {QMI_FIXED_INTF(0x16d8, 0x6008, 0)}, /* CMOTech CMU-301 */
+ {QMI_FIXED_INTF(0x16d8, 0x6280, 0)}, /* CMOTech CHU-628 */
+ {QMI_FIXED_INTF(0x16d8, 0x7001, 0)}, /* CMOTech CHU-720S */
+ {QMI_FIXED_INTF(0x16d8, 0x7002, 0)}, /* CMOTech 7002 */
+ {QMI_FIXED_INTF(0x16d8, 0x7003, 4)}, /* CMOTech CHU-629K */
+ {QMI_FIXED_INTF(0x16d8, 0x7004, 3)}, /* CMOTech 7004 */
+ {QMI_FIXED_INTF(0x16d8, 0x7006, 5)}, /* CMOTech CGU-629 */
+ {QMI_FIXED_INTF(0x16d8, 0x700a, 4)}, /* CMOTech CHU-629S */
+ {QMI_FIXED_INTF(0x16d8, 0x7211, 0)}, /* CMOTech CHU-720I */
+ {QMI_FIXED_INTF(0x16d8, 0x7212, 0)}, /* CMOTech 7212 */
+ {QMI_FIXED_INTF(0x16d8, 0x7213, 0)}, /* CMOTech 7213 */
+ {QMI_FIXED_INTF(0x16d8, 0x7251, 1)}, /* CMOTech 7251 */
+ {QMI_FIXED_INTF(0x16d8, 0x7252, 1)}, /* CMOTech 7252 */
+ {QMI_FIXED_INTF(0x16d8, 0x7253, 1)}, /* CMOTech 7253 */
{QMI_FIXED_INTF(0x19d2, 0x0002, 1)},
{QMI_FIXED_INTF(0x19d2, 0x0012, 1)},
{QMI_FIXED_INTF(0x19d2, 0x0017, 3)},
+ {QMI_FIXED_INTF(0x19d2, 0x0019, 3)}, /* ONDA MT689DC */
{QMI_FIXED_INTF(0x19d2, 0x0021, 4)},
{QMI_FIXED_INTF(0x19d2, 0x0025, 1)},
{QMI_FIXED_INTF(0x19d2, 0x0031, 4)},
@@ -569,21 +716,47 @@
{QMI_FIXED_INTF(0x19d2, 0x1255, 3)},
{QMI_FIXED_INTF(0x19d2, 0x1255, 4)},
{QMI_FIXED_INTF(0x19d2, 0x1256, 4)},
+ {QMI_FIXED_INTF(0x19d2, 0x1270, 5)}, /* ZTE MF667 */
{QMI_FIXED_INTF(0x19d2, 0x1401, 2)},
{QMI_FIXED_INTF(0x19d2, 0x1402, 2)}, /* ZTE MF60 */
{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
{QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */
+ {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */
{QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */
{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */
{QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */
{QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */
{QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */
+ {QMI_FIXED_INTF(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC73xx */
+ {QMI_FIXED_INTF(0x1199, 0x68c0, 10)}, /* Sierra Wireless MC73xx */
+ {QMI_FIXED_INTF(0x1199, 0x68c0, 11)}, /* Sierra Wireless MC73xx */
{QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */
+ {QMI_FIXED_INTF(0x1199, 0x901f, 8)}, /* Sierra Wireless EM7355 */
+ {QMI_FIXED_INTF(0x1199, 0x9041, 8)}, /* Sierra Wireless MC7305/MC7355 */
+ {QMI_FIXED_INTF(0x1199, 0x9051, 8)}, /* Netgear AirCard 340U */
+ {QMI_FIXED_INTF(0x1199, 0x9057, 8)},
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
+ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
+ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
- {QMI_FIXED_INTF(0x1e2d, 0x12d1, 4)}, /* Cinterion PLxx */
+ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc002, 4)}, /* Olivetti Olicard 140 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc004, 6)}, /* Olivetti Olicard 155 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)}, /* Olivetti Olicard 160 */
+ {QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)}, /* Olivetti Olicard 500 */
+ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */
+ {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */
+ {QMI_FIXED_INTF(0x413c, 0x81a2, 8)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
+ {QMI_FIXED_INTF(0x413c, 0x81a3, 8)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
+ {QMI_FIXED_INTF(0x413c, 0x81a4, 8)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
+ {QMI_FIXED_INTF(0x413c, 0x81a8, 8)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
+ {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
+ {QMI_FIXED_INTF(0x03f0, 0x581d, 4)}, /* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
/* 4. Gobi 1000 devices */
{QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
@@ -610,7 +783,6 @@
{QMI_GOBI_DEVICE(0x413c, 0x8186)}, /* Dell Gobi 2000 Modem device (N0218, VU936) */
{QMI_GOBI_DEVICE(0x413c, 0x8194)}, /* Dell Gobi 3000 Composite */
{QMI_GOBI_DEVICE(0x05c6, 0x920b)}, /* Generic Gobi 2000 Modem device */
- {QMI_GOBI_DEVICE(0x05c6, 0x920d)}, /* Gobi 3000 Composite */
{QMI_GOBI_DEVICE(0x05c6, 0x9225)}, /* Sony Gobi 2000 Modem device (N0279, VU730) */
{QMI_GOBI_DEVICE(0x05c6, 0x9245)}, /* Samsung Gobi 2000 Modem device (VL176) */
{QMI_GOBI_DEVICE(0x03f0, 0x251d)}, /* HP Gobi 2000 Modem device (VP412) */
@@ -618,6 +790,7 @@
{QMI_GOBI_DEVICE(0x05c6, 0x9265)}, /* Asus Gobi 2000 Modem device (VR305) */
{QMI_GOBI_DEVICE(0x05c6, 0x9235)}, /* Top Global Gobi 2000 Modem device (VR306) */
{QMI_GOBI_DEVICE(0x05c6, 0x9275)}, /* iRex Technologies Gobi 2000 Modem device (VR307) */
+ {QMI_GOBI_DEVICE(0x0af0, 0x8120)}, /* Option GTM681W */
{QMI_GOBI_DEVICE(0x1199, 0x68a5)}, /* Sierra Wireless Modem */
{QMI_GOBI_DEVICE(0x1199, 0x68a9)}, /* Sierra Wireless Modem */
{QMI_GOBI_DEVICE(0x1199, 0x9001)}, /* Sierra Wireless Gobi 2000 Modem device (VT773) */
@@ -631,7 +804,6 @@
{QMI_GOBI_DEVICE(0x1199, 0x9009)}, /* Sierra Wireless Gobi 2000 Modem device (VT773) */
{QMI_GOBI_DEVICE(0x1199, 0x900a)}, /* Sierra Wireless Gobi 2000 Modem device (VT773) */
{QMI_GOBI_DEVICE(0x1199, 0x9011)}, /* Sierra Wireless Gobi 2000 Modem device (MC8305) */
- {QMI_FIXED_INTF(0x1199, 0x9011, 5)}, /* alternate interface number!? */
{QMI_GOBI_DEVICE(0x16d8, 0x8002)}, /* CMDTech Gobi 2000 Modem device (VU922) */
{QMI_GOBI_DEVICE(0x05c6, 0x9205)}, /* Gobi 2000 Modem device */
{QMI_GOBI_DEVICE(0x1199, 0x9013)}, /* Sierra Wireless Gobi 3000 Modem device (MC8355) */
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index cc49aac..691fca4 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -494,6 +494,10 @@
*/
int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
/* peripheral may have batched packets to us... */
while (likely(skb->len)) {
struct rndis_data_hdr *hdr = (void *)skb->data;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 75409748c..12afae0 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -45,7 +45,6 @@
#define EEPROM_MAC_OFFSET (0x01)
#define DEFAULT_TX_CSUM_ENABLE (true)
#define DEFAULT_RX_CSUM_ENABLE (true)
-#define DEFAULT_TSO_ENABLE (true)
#define SMSC75XX_INTERNAL_PHY_ID (1)
#define SMSC75XX_TX_OVERHEAD (8)
#define MAX_RX_FIFO_SIZE (20 * 1024)
@@ -1410,17 +1409,14 @@
INIT_WORK(&pdata->set_multicast, smsc75xx_deferred_multicast_write);
- if (DEFAULT_TX_CSUM_ENABLE) {
+ if (DEFAULT_TX_CSUM_ENABLE)
dev->net->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- if (DEFAULT_TSO_ENABLE)
- dev->net->features |= NETIF_F_SG |
- NETIF_F_TSO | NETIF_F_TSO6;
- }
+
if (DEFAULT_RX_CSUM_ENABLE)
dev->net->features |= NETIF_F_RXCSUM;
dev->net->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
- NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_RXCSUM;
+ NETIF_F_RXCSUM;
ret = smsc75xx_wait_ready(dev, 0);
if (ret < 0) {
@@ -2112,6 +2108,10 @@
static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
while (skb->len > 0) {
u32 rx_cmd_a, rx_cmd_b, align_count, size;
struct sk_buff *ax_skb;
@@ -2200,8 +2200,6 @@
{
u32 tx_cmd_a, tx_cmd_b;
- skb_linearize(skb);
-
if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) {
struct sk_buff *skb2 =
skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags);
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 3f38ba8..9375b8c 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1725,6 +1725,10 @@
static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
{
+ /* This check is no longer done by usbnet */
+ if (skb->len < dev->net->hard_header_len)
+ return 0;
+
while (skb->len > 0) {
u32 header, align_count;
struct sk_buff *ax_skb;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 06ee82f..3d50e7d 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -206,9 +206,6 @@
break;
}
- if (!netif_running (dev->net))
- return;
-
status = usb_submit_urb (urb, GFP_ATOMIC);
if (status != 0)
netif_err(dev, timer, dev->net,
@@ -520,17 +517,19 @@
}
// else network stack removes extra byte if we forced a short packet
- if (skb->len) {
- /* all data was already cloned from skb inside the driver */
- if (dev->driver_info->flags & FLAG_MULTI_PACKET)
- dev_kfree_skb_any(skb);
- else
- usbnet_skb_return(dev, skb);
+ /* all data was already cloned from skb inside the driver */
+ if (dev->driver_info->flags & FLAG_MULTI_PACKET)
+ goto done;
+
+ if (skb->len < ETH_HLEN) {
+ dev->net->stats.rx_errors++;
+ dev->net->stats.rx_length_errors++;
+ netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len);
+ } else {
+ usbnet_skb_return(dev, skb);
return;
}
- netif_dbg(dev, rx_err, dev->net, "drop\n");
- dev->net->stats.rx_errors++;
done:
skb_queue_tail(&dev->done, skb);
}
@@ -552,13 +551,6 @@
switch (urb_status) {
/* success */
case 0:
- if (skb->len < dev->net->hard_header_len) {
- state = rx_cleanup;
- dev->net->stats.rx_errors++;
- dev->net->stats.rx_length_errors++;
- netif_dbg(dev, rx_err, dev->net,
- "rx length %d\n", skb->len);
- }
break;
/* stalls need manual reset. this is rare ... except that
@@ -735,14 +727,12 @@
// precondition: never called in_interrupt
static void usbnet_terminate_urbs(struct usbnet *dev)
{
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(unlink_wakeup);
DECLARE_WAITQUEUE(wait, current);
int temp;
/* ensure there are no more active urbs */
- add_wait_queue(&unlink_wakeup, &wait);
+ add_wait_queue(&dev->wait, &wait);
set_current_state(TASK_UNINTERRUPTIBLE);
- dev->wait = &unlink_wakeup;
temp = unlink_urbs(dev, &dev->txq) +
unlink_urbs(dev, &dev->rxq);
@@ -756,15 +746,14 @@
"waited for %d urb completions\n", temp);
}
set_current_state(TASK_RUNNING);
- dev->wait = NULL;
- remove_wait_queue(&unlink_wakeup, &wait);
+ remove_wait_queue(&dev->wait, &wait);
}
int usbnet_stop (struct net_device *net)
{
struct usbnet *dev = netdev_priv(net);
struct driver_info *info = dev->driver_info;
- int retval;
+ int retval, pm;
clear_bit(EVENT_DEV_OPEN, &dev->flags);
netif_stop_queue (net);
@@ -774,6 +763,8 @@
net->stats.rx_packets, net->stats.tx_packets,
net->stats.rx_errors, net->stats.tx_errors);
+ /* to not race resume */
+ pm = usb_autopm_get_interface(dev->intf);
/* allow minidriver to stop correctly (wireless devices to turn off
* radio etc) */
if (info->stop) {
@@ -800,6 +791,9 @@
dev->flags = 0;
del_timer_sync (&dev->delay);
tasklet_kill (&dev->bh);
+ if (!pm)
+ usb_autopm_put_interface(dev->intf);
+
if (info->manage_power &&
!test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags))
info->manage_power(dev, 0);
@@ -1368,11 +1362,12 @@
/* restart RX again after disabling due to high error rate */
clear_bit(EVENT_RX_KILL, &dev->flags);
- // waiting for all pending urbs to complete?
- if (dev->wait) {
- if ((dev->txq.qlen + dev->rxq.qlen + dev->done.qlen) == 0) {
- wake_up (dev->wait);
- }
+ /* waiting for all pending urbs to complete?
+ * only then can we forgo submitting anew
+ */
+ if (waitqueue_active(&dev->wait)) {
+ if (dev->txq.qlen + dev->rxq.qlen + dev->done.qlen == 0)
+ wake_up_all(&dev->wait);
// or are we maybe short a few urbs?
} else if (netif_running (dev->net) &&
@@ -1510,6 +1505,7 @@
dev->driver_name = name;
dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV
| NETIF_MSG_PROBE | NETIF_MSG_LINK);
+ init_waitqueue_head(&dev->wait);
skb_queue_head_init (&dev->rxq);
skb_queue_head_init (&dev->txq);
skb_queue_head_init (&dev->done);
@@ -1702,9 +1698,10 @@
spin_unlock_irq(&dev->txq.lock);
if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
- /* handle remote wakeup ASAP */
- if (!dev->wait &&
- netif_device_present(dev->net) &&
+ /* handle remote wakeup ASAP
+ * we cannot race against stop
+ */
+ if (netif_device_present(dev->net) &&
!timer_pending(&dev->delay) &&
!test_bit(EVENT_RX_HALT, &dev->flags))
rx_alloc_submit(dev, GFP_NOIO);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c9e0038..2835bfe 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -294,26 +294,61 @@
return skb;
}
-static int receive_mergeable(struct receive_queue *rq, struct sk_buff *skb)
+static struct sk_buff *receive_small(void *buf, unsigned int len)
{
- struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb);
- struct page *page;
- int num_buf, i, len;
+ struct sk_buff * skb = buf;
- num_buf = hdr->mhdr.num_buffers;
+ len -= sizeof(struct virtio_net_hdr);
+ skb_trim(skb, len);
+
+ return skb;
+}
+
+static struct sk_buff *receive_big(struct net_device *dev,
+ struct receive_queue *rq,
+ void *buf)
+{
+ struct page *page = buf;
+ struct sk_buff *skb = page_to_skb(rq, page, 0);
+
+ if (unlikely(!skb))
+ goto err;
+
+ return skb;
+
+err:
+ dev->stats.rx_dropped++;
+ give_pages(rq, page);
+ return NULL;
+}
+
+static struct sk_buff *receive_mergeable(struct net_device *dev,
+ struct receive_queue *rq,
+ void *buf,
+ unsigned int len)
+{
+ struct skb_vnet_hdr *hdr = page_address(buf);
+ int num_buf = hdr->mhdr.num_buffers;
+ struct page *page = buf;
+ struct sk_buff *skb = page_to_skb(rq, page, len);
+ int i;
+
+ if (unlikely(!skb))
+ goto err_skb;
+
while (--num_buf) {
i = skb_shinfo(skb)->nr_frags;
if (i >= MAX_SKB_FRAGS) {
pr_debug("%s: packet too long\n", skb->dev->name);
skb->dev->stats.rx_length_errors++;
- return -EINVAL;
+ goto err_frags;
}
page = virtqueue_get_buf(rq->vq, &len);
if (!page) {
- pr_debug("%s: rx error: %d buffers missing\n",
- skb->dev->name, hdr->mhdr.num_buffers);
- skb->dev->stats.rx_length_errors++;
- return -EINVAL;
+ pr_debug("%s: rx error: %d buffers %d missing\n",
+ dev->name, hdr->mhdr.num_buffers, num_buf);
+ dev->stats.rx_length_errors++;
+ goto err_buf;
}
if (len > PAGE_SIZE)
@@ -323,7 +358,26 @@
--rq->num;
}
- return 0;
+ return skb;
+err_skb:
+ give_pages(rq, page);
+ while (--num_buf) {
+err_frags:
+ buf = virtqueue_get_buf(rq->vq, &len);
+ if (unlikely(!buf)) {
+ pr_debug("%s: rx error: %d buffers missing\n",
+ dev->name, num_buf);
+ dev->stats.rx_length_errors++;
+ break;
+ }
+ page = buf;
+ give_pages(rq, page);
+ --rq->num;
+ }
+err_buf:
+ dev->stats.rx_dropped++;
+ dev_kfree_skb(skb);
+ return NULL;
}
static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len)
@@ -332,7 +386,6 @@
struct net_device *dev = vi->dev;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
struct sk_buff *skb;
- struct page *page;
struct skb_vnet_hdr *hdr;
if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) {
@@ -344,25 +397,15 @@
dev_kfree_skb(buf);
return;
}
+ if (vi->mergeable_rx_bufs)
+ skb = receive_mergeable(dev, rq, buf, len);
+ else if (vi->big_packets)
+ skb = receive_big(dev, rq, buf);
+ else
+ skb = receive_small(buf, len);
- if (!vi->mergeable_rx_bufs && !vi->big_packets) {
- skb = buf;
- len -= sizeof(struct virtio_net_hdr);
- skb_trim(skb, len);
- } else {
- page = buf;
- skb = page_to_skb(rq, page, len);
- if (unlikely(!skb)) {
- dev->stats.rx_dropped++;
- give_pages(rq, page);
- return;
- }
- if (vi->mergeable_rx_bufs)
- if (receive_mergeable(rq, skb)) {
- dev_kfree_skb(skb);
- return;
- }
- }
+ if (unlikely(!skb))
+ return;
hdr = skb_vnet_hdr(skb);
@@ -602,7 +645,7 @@
container_of(napi, struct receive_queue, napi);
struct virtnet_info *vi = rq->vq->vdev->priv;
void *buf;
- unsigned int len, received = 0;
+ unsigned int r, len, received = 0;
again:
while (received < budget &&
@@ -619,8 +662,9 @@
/* Out of packets? */
if (received < budget) {
+ r = virtqueue_enable_cb_prepare(rq->vq);
napi_complete(napi);
- if (unlikely(!virtqueue_enable_cb(rq->vq)) &&
+ if (unlikely(virtqueue_poll(rq->vq, r)) &&
napi_schedule_prep(napi)) {
virtqueue_disable_cb(rq->vq);
__napi_schedule(napi);
@@ -901,7 +945,6 @@
struct scatterlist sg;
struct virtio_net_ctrl_mq s;
struct net_device *dev = vi->dev;
- int i;
if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ))
return 0;
@@ -915,10 +958,10 @@
queue_pairs);
return -EINVAL;
} else {
- for (i = vi->curr_queue_pairs; i < queue_pairs; i++)
- if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
vi->curr_queue_pairs = queue_pairs;
+ /* virtnet_open() will refill when device is going to up. */
+ if (dev->flags & IFF_UP)
+ schedule_delayed_work(&vi->refill, 0);
}
return 0;
@@ -1108,6 +1151,7 @@
default:
break;
}
+
return NOTIFY_OK;
}
@@ -1284,6 +1328,11 @@
static void virtnet_free_queues(struct virtnet_info *vi)
{
+ int i;
+
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ netif_napi_del(&vi->rq[i].napi);
+
kfree(vi->rq);
kfree(vi->sq);
}
@@ -1548,7 +1597,8 @@
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
- virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+ virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
vi->big_packets = true;
if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
@@ -1664,6 +1714,8 @@
struct virtnet_info *vi = vdev->priv;
int i;
+ unregister_hotcpu_notifier(&vi->nb);
+
/* Prevent config work handler from accessing the device */
mutex_lock(&vi->config_lock);
vi->config_enable = false;
@@ -1694,21 +1746,28 @@
if (err)
return err;
- if (netif_running(vi->dev))
+ if (netif_running(vi->dev)) {
+ for (i = 0; i < vi->curr_queue_pairs; i++)
+ if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+ schedule_delayed_work(&vi->refill, 0);
+
for (i = 0; i < vi->max_queue_pairs; i++)
virtnet_napi_enable(&vi->rq[i]);
+ }
netif_device_attach(vi->dev);
- for (i = 0; i < vi->curr_queue_pairs; i++)
- if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
mutex_lock(&vi->config_lock);
vi->config_enable = true;
mutex_unlock(&vi->config_lock);
+ rtnl_lock();
virtnet_set_queues(vi, vi->curr_queue_pairs);
+ rtnl_unlock();
+
+ err = register_hotcpu_notifier(&vi->nb);
+ if (err)
+ return err;
return 0;
}
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 55a62ca..d081585 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1741,11 +1741,20 @@
{
struct vmxnet3_adapter *adapter = netdev_priv(netdev);
- if (adapter->intr.mask_mode == VMXNET3_IMM_ACTIVE)
- vmxnet3_disable_all_intrs(adapter);
-
- vmxnet3_do_poll(adapter, adapter->rx_queue[0].rx_ring[0].size);
- vmxnet3_enable_all_intrs(adapter);
+ switch (adapter->intr.type) {
+#ifdef CONFIG_PCI_MSI
+ case VMXNET3_IT_MSIX: {
+ int i;
+ for (i = 0; i < adapter->num_rx_queues; i++)
+ vmxnet3_msix_rx(0, &adapter->rx_queue[i]);
+ break;
+ }
+#endif
+ case VMXNET3_IT_MSI:
+ default:
+ vmxnet3_intr(0, adapter->netdev);
+ break;
+ }
}
#endif /* CONFIG_NET_POLL_CONTROLLER */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 57325f3..a1dc186 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -845,6 +845,9 @@
neigh_release(n);
+ if (reply == NULL)
+ goto out;
+
skb_reset_mac_header(reply);
__skb_pull(reply, skb_network_offset(reply));
reply->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1090,7 +1093,7 @@
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- tunnel_ip_select_ident(skb, old_iph, &rt->dst);
+ __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
nf_reset(skb);
@@ -1311,7 +1314,7 @@
eth_hw_addr_random(dev);
ether_setup(dev);
- dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+ dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = vxlan_free;
@@ -1451,7 +1454,7 @@
dev->mtu = lowerdev->mtu - VXLAN_HEADROOM;
/* update header length based on lower device */
- dev->hard_header_len = lowerdev->hard_header_len +
+ dev->needed_headroom = lowerdev->hard_header_len +
VXLAN_HEADROOM;
}
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 3f0c4f2..bcfff0d 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -1972,6 +1972,7 @@
}
i = port->index;
+ memset(&sync, 0, sizeof(sync));
sync.clock_rate = FST_RDL(card, portConfig[i].lineSpeed);
/* Lucky card and linux use same encoding here */
sync.clock_type = FST_RDB(card, portConfig[i].internalClock) ==
diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c
index 6a24a5a..4c0a697 100644
--- a/drivers/net/wan/wanxl.c
+++ b/drivers/net/wan/wanxl.c
@@ -355,6 +355,7 @@
ifr->ifr_settings.size = size; /* data size wanted */
return -ENOBUFS;
}
+ memset(&line, 0, sizeof(line));
line.clock_type = get_status(port)->clocking;
line.clock_rate = 0;
line.loopback = 0;
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 17d7fec..57fc06e 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1764,7 +1764,7 @@
AR5523_DEVICE_UX(0x2001, 0x3a04), /* Dlink / DWLAG122 */
AR5523_DEVICE_UG(0x1690, 0x0712), /* Gigaset / AR5523 */
AR5523_DEVICE_UG(0x1690, 0x0710), /* Gigaset / SMCWUSBTG */
- AR5523_DEVICE_UG(0x129b, 0x160c), /* Gigaset / USB stick 108
+ AR5523_DEVICE_UG(0x129b, 0x160b), /* Gigaset / USB stick 108
(CyberTAN Technology) */
AR5523_DEVICE_UG(0x16ab, 0x7801), /* Globalsun / AR5523_1 */
AR5523_DEVICE_UX(0x16ab, 0x7811), /* Globalsun / AR5523_2 */
diff --git a/drivers/net/wireless/ath/ath5k/qcu.c b/drivers/net/wireless/ath/ath5k/qcu.c
index 65fe929..3bfd0b8 100644
--- a/drivers/net/wireless/ath/ath5k/qcu.c
+++ b/drivers/net/wireless/ath/ath5k/qcu.c
@@ -225,13 +225,7 @@
} else {
switch (queue_type) {
case AR5K_TX_QUEUE_DATA:
- for (queue = AR5K_TX_QUEUE_ID_DATA_MIN;
- ah->ah_txq[queue].tqi_type !=
- AR5K_TX_QUEUE_INACTIVE; queue++) {
-
- if (queue > AR5K_TX_QUEUE_ID_DATA_MAX)
- return -EINVAL;
- }
+ queue = queue_info->tqi_subtype;
break;
case AR5K_TX_QUEUE_UAPSD:
queue = AR5K_TX_QUEUE_ID_UAPSD;
diff --git a/drivers/net/wireless/ath/ath5k/reset.c b/drivers/net/wireless/ath/ath5k/reset.c
index a3399c4..b9b651e 100644
--- a/drivers/net/wireless/ath/ath5k/reset.c
+++ b/drivers/net/wireless/ath/ath5k/reset.c
@@ -478,7 +478,7 @@
regval = ioread32(reg);
iowrite32(regval | val, reg);
regval = ioread32(reg);
- usleep_range(100, 150);
+ udelay(100); /* NB: should be atomic */
/* Bring BB/MAC out of reset */
iowrite32(regval & ~val, reg);
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_mac.c b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
index 8d78253..a366d6b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
@@ -76,9 +76,16 @@
mask2 |= ATH9K_INT_CST;
if (isr2 & AR_ISR_S2_TSFOOR)
mask2 |= ATH9K_INT_TSFOOR;
+
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR_S2, isr2);
+ isr &= ~AR_ISR_BCNMISC;
+ }
}
- isr = REG_READ(ah, AR_ISR_RAC);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)
+ isr = REG_READ(ah, AR_ISR_RAC);
+
if (isr == 0xffffffff) {
*masked = 0;
return false;
@@ -97,11 +104,23 @@
*masked |= ATH9K_INT_TX;
- s0_s = REG_READ(ah, AR_ISR_S0_S);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+ s0_s = REG_READ(ah, AR_ISR_S0_S);
+ s1_s = REG_READ(ah, AR_ISR_S1_S);
+ } else {
+ s0_s = REG_READ(ah, AR_ISR_S0);
+ REG_WRITE(ah, AR_ISR_S0, s0_s);
+ s1_s = REG_READ(ah, AR_ISR_S1);
+ REG_WRITE(ah, AR_ISR_S1, s1_s);
+
+ isr &= ~(AR_ISR_TXOK |
+ AR_ISR_TXDESC |
+ AR_ISR_TXERR |
+ AR_ISR_TXEOL);
+ }
+
ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXOK);
ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXDESC);
-
- s1_s = REG_READ(ah, AR_ISR_S1_S);
ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXERR);
ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXEOL);
}
@@ -114,13 +133,15 @@
*masked |= mask2;
}
- if (AR_SREV_9100(ah))
- return true;
-
- if (isr & AR_ISR_GENTMR) {
+ if (!AR_SREV_9100(ah) && (isr & AR_ISR_GENTMR)) {
u32 s5_s;
- s5_s = REG_READ(ah, AR_ISR_S5_S);
+ if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+ s5_s = REG_READ(ah, AR_ISR_S5_S);
+ } else {
+ s5_s = REG_READ(ah, AR_ISR_S5);
+ }
+
ah->intr_gen_timer_trigger =
MS(s5_s, AR_ISR_S5_GENTIMER_TRIG);
@@ -133,8 +154,21 @@
if ((s5_s & AR_ISR_S5_TIM_TIMER) &&
!(pCap->hw_caps & ATH9K_HW_CAP_AUTOSLEEP))
*masked |= ATH9K_INT_TIM_TIMER;
+
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR_S5, s5_s);
+ isr &= ~AR_ISR_GENTMR;
+ }
}
+ if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+ REG_WRITE(ah, AR_ISR, isr);
+ REG_READ(ah, AR_ISR);
+ }
+
+ if (AR_SREV_9100(ah))
+ return true;
+
if (sync_cause) {
ath9k_debug_sync_cause(common, sync_cause);
fatal_int =
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index e6b92ff..f71a9ed 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -3563,14 +3563,18 @@
{
struct ath9k_hw_capabilities *pCap = &ah->caps;
int chain;
- u32 regval;
+ u32 regval, value;
static const u32 switch_chain_reg[AR9300_MAX_CHAINS] = {
AR_PHY_SWITCH_CHAIN_0,
AR_PHY_SWITCH_CHAIN_1,
AR_PHY_SWITCH_CHAIN_2,
};
- u32 value = ar9003_hw_ant_ctrl_common_get(ah, is2ghz);
+ if (AR_SREV_9485(ah) && (ar9003_hw_get_rx_gain_idx(ah) == 0))
+ ath9k_hw_cfg_output(ah, AR9300_EXT_LNA_CTL_GPIO_AR9485,
+ AR_GPIO_OUTPUT_MUX_AS_PCIE_ATTENTION_LED);
+
+ value = ar9003_hw_ant_ctrl_common_get(ah, is2ghz);
if (AR_SREV_9462(ah) || AR_SREV_9565(ah)) {
REG_RMW_FIELD(ah, AR_PHY_SWITCH_COM,
@@ -3933,18 +3937,20 @@
int quick_drop;
s32 t[3], f[3] = {5180, 5500, 5785};
- if (!(pBase->miscConfiguration & BIT(1)))
+ if (!(pBase->miscConfiguration & BIT(4)))
return;
- if (freq < 4000)
- quick_drop = eep->modalHeader2G.quick_drop;
- else {
- t[0] = eep->base_ext1.quick_drop_low;
- t[1] = eep->modalHeader5G.quick_drop;
- t[2] = eep->base_ext1.quick_drop_high;
- quick_drop = ar9003_hw_power_interpolate(freq, f, t, 3);
+ if (AR_SREV_9300(ah) || AR_SREV_9580(ah) || AR_SREV_9340(ah)) {
+ if (freq < 4000) {
+ quick_drop = eep->modalHeader2G.quick_drop;
+ } else {
+ t[0] = eep->base_ext1.quick_drop_low;
+ t[1] = eep->modalHeader5G.quick_drop;
+ t[2] = eep->base_ext1.quick_drop_high;
+ quick_drop = ar9003_hw_power_interpolate(freq, f, t, 3);
+ }
+ REG_RMW_FIELD(ah, AR_PHY_AGC, AR_PHY_AGC_QUICK_DROP, quick_drop);
}
- REG_RMW_FIELD(ah, AR_PHY_AGC, AR_PHY_AGC_QUICK_DROP, quick_drop);
}
static void ar9003_hw_txend_to_xpa_off_apply(struct ath_hw *ah, bool is2ghz)
@@ -3984,7 +3990,7 @@
struct ar9300_eeprom *eep = &ah->eeprom.ar9300_eep;
u8 bias;
- if (!(eep->baseEepHeader.featureEnable & 0x40))
+ if (!(eep->baseEepHeader.miscConfiguration & 0x40))
return;
if (!AR_SREV_9300(ah))
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index e1714d7..3457ca5 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1076,6 +1076,10 @@
* is_on == 0 means MRC CCK is OFF (more noise imm)
*/
bool is_on = param ? 1 : 0;
+
+ if (ah->caps.rx_chainmask == 1)
+ break;
+
REG_RMW_FIELD(ah, AR_PHY_MRC_CCK_CTRL,
AR_PHY_MRC_CCK_ENABLE, is_on);
REG_RMW_FIELD(ah, AR_PHY_MRC_CCK_CTRL,
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
index e717741..5013c73 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h
@@ -351,6 +351,8 @@
#define AR_PHY_CCA_NOM_VAL_9330_2GHZ -118
+#define AR9300_EXT_LNA_CTL_GPIO_AR9485 9
+
/*
* AGC Field Definitions
*/
diff --git a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
index 999ab08..4ae3cf7 100644
--- a/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9462_2p0_initvals.h
@@ -56,7 +56,7 @@
{0x00009e14, 0x37b95d5e, 0x37b9605e, 0x3236605e, 0x32365a5e},
{0x00009e18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
{0x00009e1c, 0x0001cf9c, 0x0001cf9c, 0x00021f9c, 0x00021f9c},
- {0x00009e20, 0x000003b5, 0x000003b5, 0x000003ce, 0x000003ce},
+ {0x00009e20, 0x000003a5, 0x000003a5, 0x000003a5, 0x000003a5},
{0x00009e2c, 0x0000001c, 0x0000001c, 0x00000021, 0x00000021},
{0x00009e3c, 0xcf946220, 0xcf946220, 0xcfd5c782, 0xcfd5c282},
{0x00009e44, 0x62321e27, 0x62321e27, 0xfe291e27, 0xfe291e27},
@@ -95,7 +95,7 @@
{0x0000ae04, 0x001c0000, 0x001c0000, 0x001c0000, 0x00100000},
{0x0000ae18, 0x00000000, 0x00000000, 0x00000000, 0x00000000},
{0x0000ae1c, 0x0000019c, 0x0000019c, 0x0000019c, 0x0000019c},
- {0x0000ae20, 0x000001b5, 0x000001b5, 0x000001ce, 0x000001ce},
+ {0x0000ae20, 0x000001a6, 0x000001a6, 0x000001aa, 0x000001aa},
{0x0000b284, 0x00000000, 0x00000000, 0x00000550, 0x00000550},
};
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 42b03dc..4ebd9fd 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -79,10 +79,6 @@
sizeof(struct ath_buf_state)); \
} while (0)
-#define ATH_RXBUF_RESET(_bf) do { \
- (_bf)->bf_stale = false; \
- } while (0)
-
/**
* enum buffer_type - Buffer type flags
*
@@ -316,6 +312,7 @@
struct ath_descdma rxdma;
struct ath_rx_edma rx_edma[ATH9K_RX_QUEUE_MAX];
+ struct ath_buf *buf_hold;
struct sk_buff *frag;
u32 ampdu_ref;
diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c
index 7304e75..5e8219a 100644
--- a/drivers/net/wireless/ath/ath9k/calib.c
+++ b/drivers/net/wireless/ath/ath9k/calib.c
@@ -387,7 +387,6 @@
if (!caldata) {
chan->noisefloor = nf;
- ah->noise = ath9k_hw_getchan_noise(ah, chan);
return false;
}
diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index f5dda84..75a6376 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -1289,7 +1289,9 @@
usb_set_intfdata(interface, NULL);
- if (!unplugged && (hif_dev->flags & HIF_USB_START))
+ /* If firmware was loaded we should drop it
+ * go back to first stage bootloader. */
+ if (!unplugged && (hif_dev->flags & HIF_USB_READY))
ath9k_hif_usb_reboot(udev);
kfree(hif_dev);
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
index a47f5e0..3b202ff 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c
@@ -846,6 +846,7 @@
if (error != 0)
goto err_rx;
+ ath9k_hw_disable(priv->ah);
#ifdef CONFIG_MAC80211_LEDS
/* must be initialized before ieee80211_register_hw */
priv->led_cdev.default_trigger = ieee80211_create_tpt_led_trigger(priv->hw,
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 62f1b76..04b3822 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -145,21 +145,26 @@
struct ath9k_vif_iter_data *iter_data = data;
int i;
- for (i = 0; i < ETH_ALEN; i++)
- iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+ if (iter_data->hw_macaddr != NULL) {
+ for (i = 0; i < ETH_ALEN; i++)
+ iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+ } else {
+ iter_data->hw_macaddr = mac;
+ }
}
-static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
+static void ath9k_htc_set_mac_bssid_mask(struct ath9k_htc_priv *priv,
struct ieee80211_vif *vif)
{
struct ath_common *common = ath9k_hw_common(priv->ah);
struct ath9k_vif_iter_data iter_data;
/*
- * Use the hardware MAC address as reference, the hardware uses it
- * together with the BSSID mask when matching addresses.
+ * Pick the MAC address of the first interface as the new hardware
+ * MAC address. The hardware will use it together with the BSSID mask
+ * when matching addresses.
*/
- iter_data.hw_macaddr = common->macaddr;
+ iter_data.hw_macaddr = NULL;
memset(&iter_data.mask, 0xff, ETH_ALEN);
if (vif)
@@ -171,6 +176,10 @@
ath9k_htc_bssid_iter, &iter_data);
memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
+
+ if (iter_data.hw_macaddr)
+ memcpy(common->macaddr, iter_data.hw_macaddr, ETH_ALEN);
+
ath_hw_setbssidmask(common);
}
@@ -1076,7 +1085,7 @@
goto out;
}
- ath9k_htc_set_bssid_mask(priv, vif);
+ ath9k_htc_set_mac_bssid_mask(priv, vif);
priv->vif_slot |= (1 << avp->index);
priv->nvifs++;
@@ -1139,7 +1148,7 @@
ath9k_htc_set_opmode(priv);
- ath9k_htc_set_bssid_mask(priv, vif);
+ ath9k_htc_set_mac_bssid_mask(priv, vif);
/*
* Stop ANI only if there are no associated station interfaces.
@@ -1322,21 +1331,22 @@
struct ath_common *common = ath9k_hw_common(priv->ah);
struct ath9k_htc_target_rate trate;
+ if (!(changed & IEEE80211_RC_SUPP_RATES_CHANGED))
+ return;
+
mutex_lock(&priv->mutex);
ath9k_htc_ps_wakeup(priv);
- if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
- memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
- ath9k_htc_setup_rate(priv, sta, &trate);
- if (!ath9k_htc_send_rate_cmd(priv, &trate))
- ath_dbg(common, CONFIG,
- "Supported rates for sta: %pM updated, rate caps: 0x%X\n",
- sta->addr, be32_to_cpu(trate.capflags));
- else
- ath_dbg(common, CONFIG,
- "Unable to update supported rates for sta: %pM\n",
- sta->addr);
- }
+ memset(&trate, 0, sizeof(struct ath9k_htc_target_rate));
+ ath9k_htc_setup_rate(priv, sta, &trate);
+ if (!ath9k_htc_send_rate_cmd(priv, &trate))
+ ath_dbg(common, CONFIG,
+ "Supported rates for sta: %pM updated, rate caps: 0x%X\n",
+ sta->addr, be32_to_cpu(trate.capflags));
+ else
+ ath_dbg(common, CONFIG,
+ "Unable to update supported rates for sta: %pM\n",
+ sta->addr);
ath9k_htc_ps_restore(priv);
mutex_unlock(&priv->mutex);
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 6bd0e92..417a089 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -448,6 +448,7 @@
struct ieee80211_conf *cur_conf = &priv->hw->conf;
bool txok;
int slot;
+ int hdrlen, padsize;
slot = strip_drv_header(priv, skb);
if (slot < 0) {
@@ -504,6 +505,15 @@
ath9k_htc_tx_clear_slot(priv, slot);
+ /* Remove padding before handing frame back to mac80211 */
+ hdrlen = ieee80211_get_hdrlen_from_skb(skb);
+
+ padsize = hdrlen & 3;
+ if (padsize && skb->len > hdrlen + padsize) {
+ memmove(skb->data + padsize, skb->data, hdrlen);
+ skb_pull(skb, padsize);
+ }
+
/* Send status to mac80211 */
ieee80211_tx_status(priv->hw, skb);
}
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 15dfefc..b1d5037 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1872,7 +1872,8 @@
ah->caldata = caldata;
if (caldata && (chan->channel != caldata->channel ||
- chan->channelFlags != caldata->channelFlags)) {
+ chan->channelFlags != caldata->channelFlags ||
+ chan->chanmode != caldata->chanmode)) {
/* Operating channel changed, reset channel calibration data */
memset(caldata, 0, sizeof(*caldata));
ath9k_init_nfcal_hist_buffer(ah, chan);
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index ae30343..d7d9e31 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -215,8 +215,8 @@
#define AH_WOW_BEACON_MISS BIT(3)
enum ath_hw_txq_subtype {
- ATH_TXQ_AC_BE = 0,
- ATH_TXQ_AC_BK = 1,
+ ATH_TXQ_AC_BK = 0,
+ ATH_TXQ_AC_BE = 1,
ATH_TXQ_AC_VI = 2,
ATH_TXQ_AC_VO = 3,
};
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 2ba4945..bd126c2 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -767,7 +767,8 @@
IEEE80211_HW_PS_NULLFUNC_STACK |
IEEE80211_HW_SPECTRUM_MGMT |
IEEE80211_HW_REPORTS_TX_ACK_STATUS |
- IEEE80211_HW_SUPPORTS_RC_TABLE;
+ IEEE80211_HW_SUPPORTS_RC_TABLE |
+ IEEE80211_HW_SUPPORTS_HT_CCK_RATES;
if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_HT)
hw->flags |= IEEE80211_HW_AMPDU_AGGREGATION;
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 566109a..941b08b 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -311,14 +311,7 @@
q = ATH9K_NUM_TX_QUEUES - 3;
break;
case ATH9K_TX_QUEUE_DATA:
- for (q = 0; q < ATH9K_NUM_TX_QUEUES; q++)
- if (ah->txq[q].tqi_type ==
- ATH9K_TX_QUEUE_INACTIVE)
- break;
- if (q == ATH9K_NUM_TX_QUEUES) {
- ath_err(common, "No available TX queue\n");
- return -1;
- }
+ q = qinfo->tqi_subtype;
break;
default:
ath_err(common, "Invalid TX queue type: %u\n", type);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 5092eca..82a1b5b 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -173,8 +173,7 @@
{
ieee80211_queue_delayed_work(sc->hw, &sc->tx_complete_work, 0);
- if (AR_SREV_9340(sc->sc_ah) || AR_SREV_9485(sc->sc_ah) ||
- AR_SREV_9550(sc->sc_ah))
+ if (AR_SREV_9340(sc->sc_ah) || AR_SREV_9330(sc->sc_ah))
ieee80211_queue_delayed_work(sc->hw, &sc->hw_pll_work,
msecs_to_jiffies(ATH_PLL_WORK_INTERVAL));
@@ -210,6 +209,7 @@
struct ath_hw *ah = sc->sc_ah;
struct ath_common *common = ath9k_hw_common(ah);
unsigned long flags;
+ int i;
if (ath_startrecv(sc) != 0) {
ath_err(common, "Unable to restart recv logic\n");
@@ -237,6 +237,15 @@
}
work:
ath_restart_work(sc);
+
+ for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
+ if (!ATH_TXQ_SETUP(sc, i))
+ continue;
+
+ spin_lock_bh(&sc->tx.txq[i].axq_lock);
+ ath_txq_schedule(sc, &sc->tx.txq[i]);
+ spin_unlock_bh(&sc->tx.txq[i].axq_lock);
+ }
}
if ((ah->caps.hw_caps & ATH9K_HW_CAP_ANT_DIV_COMB) && sc->ant_rx != 3)
@@ -544,21 +553,10 @@
static int ath_reset(struct ath_softc *sc)
{
- int i, r;
+ int r;
ath9k_ps_wakeup(sc);
-
r = ath_reset_internal(sc, NULL);
-
- for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
- if (!ATH_TXQ_SETUP(sc, i))
- continue;
-
- spin_lock_bh(&sc->tx.txq[i].axq_lock);
- ath_txq_schedule(sc, &sc->tx.txq[i]);
- spin_unlock_bh(&sc->tx.txq[i].axq_lock);
- }
-
ath9k_ps_restore(sc);
return r;
@@ -891,8 +889,9 @@
struct ath_common *common = ath9k_hw_common(ah);
/*
- * Use the hardware MAC address as reference, the hardware uses it
- * together with the BSSID mask when matching addresses.
+ * Pick the MAC address of the first interface as the new hardware
+ * MAC address. The hardware will use it together with the BSSID mask
+ * when matching addresses.
*/
memset(iter_data, 0, sizeof(*iter_data));
memset(&iter_data->mask, 0xff, ETH_ALEN);
@@ -1211,13 +1210,6 @@
ath_update_survey_stats(sc);
spin_unlock_irqrestore(&common->cc_lock, flags);
- /*
- * Preserve the current channel values, before updating
- * the same channel
- */
- if (ah->curchan && (old_pos == pos))
- ath9k_hw_getnf(ah, ah->curchan);
-
ath9k_cmn_update_ichannel(&sc->sc_ah->channels[pos],
curchan, channel_type);
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index 8be2b5d..f53dbd1 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -42,8 +42,6 @@
struct ath_desc *ds;
struct sk_buff *skb;
- ATH_RXBUF_RESET(bf);
-
ds = bf->bf_desc;
ds->ds_link = 0; /* link to null */
ds->ds_data = bf->bf_buf_addr;
@@ -70,6 +68,14 @@
sc->rx.rxlink = &ds->ds_link;
}
+static void ath_rx_buf_relink(struct ath_softc *sc, struct ath_buf *bf)
+{
+ if (sc->rx.buf_hold)
+ ath_rx_buf_link(sc, sc->rx.buf_hold);
+
+ sc->rx.buf_hold = bf;
+}
+
static void ath_setdefantenna(struct ath_softc *sc, u32 antenna)
{
/* XXX block beacon interrupts */
@@ -117,7 +123,6 @@
skb = bf->bf_mpdu;
- ATH_RXBUF_RESET(bf);
memset(skb->data, 0, ah->caps.rx_status_len);
dma_sync_single_for_device(sc->dev, bf->bf_buf_addr,
ah->caps.rx_status_len, DMA_TO_DEVICE);
@@ -432,6 +437,7 @@
if (list_empty(&sc->rx.rxbuf))
goto start_recv;
+ sc->rx.buf_hold = NULL;
sc->rx.rxlink = NULL;
list_for_each_entry_safe(bf, tbf, &sc->rx.rxbuf, list) {
ath_rx_buf_link(sc, bf);
@@ -677,6 +683,9 @@
}
bf = list_first_entry(&sc->rx.rxbuf, struct ath_buf, list);
+ if (bf == sc->rx.buf_hold)
+ return NULL;
+
ds = bf->bf_desc;
/*
@@ -1378,7 +1387,7 @@
if (edma) {
ath_rx_edma_buf_link(sc, qtype);
} else {
- ath_rx_buf_link(sc, bf);
+ ath_rx_buf_relink(sc, bf);
ath9k_hw_rxena(ah);
}
} while (1);
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 83ab6be..0c9b2f1 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1255,14 +1255,16 @@
for (tidno = 0, tid = &an->tid[tidno];
tidno < IEEE80211_NUM_TIDS; tidno++, tid++) {
- if (!tid->sched)
- continue;
-
ac = tid->ac;
txq = ac->txq;
ath_txq_lock(sc, txq);
+ if (!tid->sched) {
+ ath_txq_unlock(sc, txq);
+ continue;
+ }
+
buffered = !skb_queue_empty(&tid->buf_q);
tid->sched = false;
@@ -2387,6 +2389,7 @@
for (acno = 0, ac = &an->ac[acno];
acno < IEEE80211_NUM_ACS; acno++, ac++) {
ac->sched = false;
+ ac->clear_ps_filter = true;
ac->txq = sc->tx.txq_map[acno];
INIT_LIST_HEAD(&ac->tid_q);
}
diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h
index 9dce106..95a334f 100644
--- a/drivers/net/wireless/ath/carl9170/carl9170.h
+++ b/drivers/net/wireless/ath/carl9170/carl9170.h
@@ -253,6 +253,7 @@
atomic_t rx_work_urbs;
atomic_t rx_pool_urbs;
kernel_ulong_t features;
+ bool usb_ep_cmd_is_bulk;
/* firmware settings */
struct completion fw_load_wait;
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index e9010a4..0686375 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1857,7 +1857,8 @@
IEEE80211_HW_SUPPORTS_PS |
IEEE80211_HW_PS_NULLFUNC_STACK |
IEEE80211_HW_NEED_DTIM_BEFORE_ASSOC |
- IEEE80211_HW_SIGNAL_DBM;
+ IEEE80211_HW_SIGNAL_DBM |
+ IEEE80211_HW_SUPPORTS_HT_CCK_RATES;
if (!modparam_noht) {
/*
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index 307bc0d..83d20c8 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -621,9 +621,16 @@
goto err_free;
}
- usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev,
- AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4,
- carl9170_usb_cmd_complete, ar, 1);
+ if (ar->usb_ep_cmd_is_bulk)
+ usb_fill_bulk_urb(urb, ar->udev,
+ usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar);
+ else
+ usb_fill_int_urb(urb, ar->udev,
+ usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD),
+ cmd, cmd->hdr.len + 4,
+ carl9170_usb_cmd_complete, ar, 1);
if (free_buf)
urb->transfer_flags |= URB_FREE_BUFFER;
@@ -1032,9 +1039,10 @@
static int carl9170_usb_probe(struct usb_interface *intf,
const struct usb_device_id *id)
{
+ struct usb_endpoint_descriptor *ep;
struct ar9170 *ar;
struct usb_device *udev;
- int err;
+ int i, err;
err = usb_reset_device(interface_to_usbdev(intf));
if (err)
@@ -1050,6 +1058,21 @@
ar->intf = intf;
ar->features = id->driver_info;
+ /* We need to remember the type of endpoint 4 because it differs
+ * between high- and full-speed configuration. The high-speed
+ * configuration specifies it as interrupt and the full-speed
+ * configuration as bulk endpoint. This information is required
+ * later when sending urbs to that endpoint.
+ */
+ for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) {
+ ep = &intf->cur_altsetting->endpoint[i].desc;
+
+ if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD &&
+ usb_endpoint_dir_out(ep) &&
+ usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK)
+ ar->usb_ep_cmd_is_bulk = true;
+ }
+
usb_set_intfdata(intf, ar);
SET_IEEE80211_DEV(ar->hw, &intf->dev);
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 727b1f5..d57e5be 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -145,7 +145,7 @@
le16_to_cpu(hdr.type), hdr.flags);
if (len <= MAX_MBOXITEM_SIZE) {
int n = 0;
- unsigned char printbuf[16 * 3 + 2];
+ char printbuf[16 * 3 + 2];
unsigned char databuf[MAX_MBOXITEM_SIZE];
void __iomem *src = wmi_buffer(wil, d.addr) +
sizeof(struct wil6210_mbox_hdr);
@@ -416,7 +416,7 @@
seq_printf(s, " SKB = %p\n", skb);
if (skb) {
- unsigned char printbuf[16 * 3 + 2];
+ char printbuf[16 * 3 + 2];
int i = 0;
int len = skb_headlen(skb);
void *p = skb->data;
diff --git a/drivers/net/wireless/b43/Kconfig b/drivers/net/wireless/b43/Kconfig
index 078e6f3..13f91ac 100644
--- a/drivers/net/wireless/b43/Kconfig
+++ b/drivers/net/wireless/b43/Kconfig
@@ -28,7 +28,7 @@
config B43_BCMA
bool "Support for BCMA bus"
- depends on B43 && BCMA
+ depends on B43 && (BCMA = y || BCMA = B43)
default y
config B43_BCMA_EXTRA
@@ -39,7 +39,7 @@
config B43_SSB
bool
- depends on B43 && SSB
+ depends on B43 && (SSB = y || SSB = B43)
default y
# Auto-select SSB PCI-HOST support, if possible
diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h
index 7f3d461..54376fd 100644
--- a/drivers/net/wireless/b43/b43.h
+++ b/drivers/net/wireless/b43/b43.h
@@ -731,8 +731,6 @@
struct b43_request_fw_context {
/* The device we are requesting the fw for. */
struct b43_wldev *dev;
- /* a completion event structure needed if this call is asynchronous */
- struct completion fw_load_complete;
/* a pointer to the firmware object */
const struct firmware *blob;
/* The type of firmware to request. */
@@ -809,6 +807,8 @@
struct b43_wldev {
struct b43_bus_dev *dev;
struct b43_wl *wl;
+ /* a completion event structure needed if this call is asynchronous */
+ struct completion fw_load_complete;
/* The device initialization status.
* Use b43_status() to query. */
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index a95b77a..0b7edd3 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -2068,6 +2068,7 @@
static void b43_release_firmware(struct b43_wldev *dev)
{
+ complete(&dev->fw_load_complete);
b43_do_release_fw(&dev->fw.ucode);
b43_do_release_fw(&dev->fw.pcm);
b43_do_release_fw(&dev->fw.initvals);
@@ -2093,7 +2094,7 @@
struct b43_request_fw_context *ctx = context;
ctx->blob = firmware;
- complete(&ctx->fw_load_complete);
+ complete(&ctx->dev->fw_load_complete);
}
int b43_do_request_fw(struct b43_request_fw_context *ctx,
@@ -2140,7 +2141,7 @@
}
if (async) {
/* do this part asynchronously */
- init_completion(&ctx->fw_load_complete);
+ init_completion(&ctx->dev->fw_load_complete);
err = request_firmware_nowait(THIS_MODULE, 1, ctx->fwname,
ctx->dev->dev->dev, GFP_KERNEL,
ctx, b43_fw_cb);
@@ -2148,12 +2149,11 @@
pr_err("Unable to load firmware\n");
return err;
}
- /* stall here until fw ready */
- wait_for_completion(&ctx->fw_load_complete);
+ wait_for_completion(&ctx->dev->fw_load_complete);
if (ctx->blob)
goto fw_ready;
/* On some ARM systems, the async request will fail, but the next sync
- * request works. For this reason, we dall through here
+ * request works. For this reason, we fall through here
*/
}
err = request_firmware(&ctx->blob, ctx->fwname,
@@ -2422,6 +2422,7 @@
static int b43_one_core_attach(struct b43_bus_dev *dev, struct b43_wl *wl);
static void b43_one_core_detach(struct b43_bus_dev *dev);
+static int b43_rng_init(struct b43_wl *wl);
static void b43_request_firmware(struct work_struct *work)
{
@@ -2473,6 +2474,10 @@
goto err_one_core_detach;
wl->hw_registred = true;
b43_leds_register(wl->current_dev);
+
+ /* Register HW RNG driver */
+ b43_rng_init(wl);
+
goto out;
err_one_core_detach:
@@ -4634,9 +4639,6 @@
if (!dev || b43_status(dev) != B43_STAT_INITIALIZED)
return;
- /* Unregister HW RNG driver */
- b43_rng_exit(dev->wl);
-
b43_set_status(dev, B43_STAT_UNINIT);
/* Stop the microcode PSM. */
@@ -4779,9 +4781,6 @@
b43_set_status(dev, B43_STAT_INITIALIZED);
- /* Register HW RNG driver */
- b43_rng_init(dev->wl);
-
out:
return err;
@@ -5442,6 +5441,9 @@
b43_one_core_detach(wldev->dev);
+ /* Unregister HW RNG driver */
+ b43_rng_exit(wl);
+
b43_leds_unregister(wl);
ieee80211_free_hw(wl->hw);
@@ -5519,6 +5521,9 @@
b43_one_core_detach(dev);
+ /* Unregister HW RNG driver */
+ b43_rng_exit(wl);
+
if (list_empty(&wl->devlist)) {
b43_leds_unregister(wl);
/* Last core on the chip unregistered.
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 7c970d3..80ecca3 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -5175,22 +5175,22 @@
int ch = new_channel->hw_value;
u16 old_band_5ghz;
- u32 tmp32;
+ u16 tmp16;
old_band_5ghz =
b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
- tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
- b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+ tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+ b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
- b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+ b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
- tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
- b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+ tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+ b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
- b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+ b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
}
b43_chantab_phy_upload(dev, e);
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 8cb206a..ebcce00 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -810,9 +810,13 @@
break;
case B43_PHYTYPE_G:
status.band = IEEE80211_BAND_2GHZ;
- /* chanid is the radio channel cookie value as used
- * to tune the radio. */
- status.freq = chanid + 2400;
+ /* Somewhere between 478.104 and 508.1084 firmware for G-PHY
+ * has been modified to be compatible with N-PHY and others.
+ */
+ if (dev->fw.rev >= 508)
+ status.freq = ieee80211_channel_to_frequency(chanid, status.band);
+ else
+ status.freq = chanid + 2400;
break;
case B43_PHYTYPE_N:
case B43_PHYTYPE_LP:
@@ -821,10 +825,10 @@
* channel number in b43. */
if (chanstat & B43_RX_CHAN_5GHZ) {
status.band = IEEE80211_BAND_5GHZ;
- status.freq = b43_freq_to_channel_5ghz(chanid);
+ status.freq = b43_channel_to_freq_5ghz(chanid);
} else {
status.band = IEEE80211_BAND_2GHZ;
- status.freq = b43_freq_to_channel_2ghz(chanid);
+ status.freq = b43_channel_to_freq_2ghz(chanid);
}
break;
default:
diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c
index 5726688..349c776 100644
--- a/drivers/net/wireless/b43legacy/main.c
+++ b/drivers/net/wireless/b43legacy/main.c
@@ -3919,6 +3919,7 @@
* as the ieee80211 unreg will destroy the workqueue. */
cancel_work_sync(&wldev->restart_work);
cancel_work_sync(&wl->firmware_load);
+ complete(&wldev->fw_load_complete);
B43legacy_WARN_ON(!wl);
if (!wldev->fw.ucode)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
index 44fa0cd..0f6eb2b 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh_sdmmc.c
@@ -575,8 +575,6 @@
static int brcmf_sdio_pd_probe(struct platform_device *pdev)
{
- int ret;
-
brcmf_dbg(SDIO, "Enter\n");
brcmfmac_sdio_pdata = pdev->dev.platform_data;
@@ -584,11 +582,7 @@
if (brcmfmac_sdio_pdata->power_on)
brcmfmac_sdio_pdata->power_on();
- ret = sdio_register_driver(&brcmf_sdmmc_driver);
- if (ret)
- brcmf_err("sdio_register_driver failed: %d\n", ret);
-
- return ret;
+ return 0;
}
static int brcmf_sdio_pd_remove(struct platform_device *pdev)
@@ -610,6 +604,15 @@
}
};
+void brcmf_sdio_register(void)
+{
+ int ret;
+
+ ret = sdio_register_driver(&brcmf_sdmmc_driver);
+ if (ret)
+ brcmf_err("sdio_register_driver failed: %d\n", ret);
+}
+
void brcmf_sdio_exit(void)
{
brcmf_dbg(SDIO, "Enter\n");
@@ -620,18 +623,13 @@
sdio_unregister_driver(&brcmf_sdmmc_driver);
}
-void brcmf_sdio_init(void)
+void __init brcmf_sdio_init(void)
{
int ret;
brcmf_dbg(SDIO, "Enter\n");
ret = platform_driver_probe(&brcmf_sdio_pd, brcmf_sdio_pd_probe);
- if (ret == -ENODEV) {
- brcmf_dbg(SDIO, "No platform data available, registering without.\n");
- ret = sdio_register_driver(&brcmf_sdmmc_driver);
- }
-
- if (ret)
- brcmf_err("driver registration failed: %d\n", ret);
+ if (ret == -ENODEV)
+ brcmf_dbg(SDIO, "No platform data available.\n");
}
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
index 080395f..e715d33 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
@@ -154,10 +154,11 @@
#ifdef CONFIG_BRCMFMAC_SDIO
extern void brcmf_sdio_exit(void);
extern void brcmf_sdio_init(void);
+extern void brcmf_sdio_register(void);
#endif
#ifdef CONFIG_BRCMFMAC_USB
extern void brcmf_usb_exit(void);
-extern void brcmf_usb_init(void);
+extern void brcmf_usb_register(void);
#endif
#endif /* _BRCMF_BUS_H_ */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
index 2c59357..95d7099 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
@@ -1034,21 +1034,23 @@
return bus->chip << 4 | bus->chiprev;
}
-static void brcmf_driver_init(struct work_struct *work)
+static void brcmf_driver_register(struct work_struct *work)
{
- brcmf_debugfs_init();
-
#ifdef CONFIG_BRCMFMAC_SDIO
- brcmf_sdio_init();
+ brcmf_sdio_register();
#endif
#ifdef CONFIG_BRCMFMAC_USB
- brcmf_usb_init();
+ brcmf_usb_register();
#endif
}
-static DECLARE_WORK(brcmf_driver_work, brcmf_driver_init);
+static DECLARE_WORK(brcmf_driver_work, brcmf_driver_register);
static int __init brcmfmac_module_init(void)
{
+ brcmf_debugfs_init();
+#ifdef CONFIG_BRCMFMAC_SDIO
+ brcmf_sdio_init();
+#endif
if (!schedule_work(&brcmf_driver_work))
return -EBUSY;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
index 01aed7a..b0ab98b 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
@@ -1532,7 +1532,7 @@
brcmf_release_fw(&fw_image_list);
}
-void brcmf_usb_init(void)
+void brcmf_usb_register(void)
{
brcmf_dbg(USB, "Enter\n");
INIT_LIST_HEAD(&fw_image_list);
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/dma.c b/drivers/net/wireless/brcm80211/brcmsmac/dma.c
index 1860c57..4fb9635 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/dma.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/dma.c
@@ -1015,9 +1015,10 @@
/*
* post receive buffers
- * return false is refill failed completely and ring is empty this will stall
- * the rx dma and user might want to call rxfill again asap. This unlikely
- * happens on memory-rich NIC, but often on memory-constrained dongle
+ * Return false if refill failed completely or dma mapping failed. The ring
+ * is empty, which will stall the rx dma and user might want to call rxfill
+ * again asap. This is unlikely to happen on a memory-rich NIC, but often on
+ * memory-constrained dongle.
*/
bool dma_rxfill(struct dma_pub *pub)
{
@@ -1078,6 +1079,8 @@
pa = dma_map_single(di->dmadev, p->data, di->rxbufsize,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(di->dmadev, pa))
+ return false;
/* save the free packet pointer */
di->rxp[rxout] = p;
@@ -1284,7 +1287,11 @@
/* get physical address of buffer start */
pa = dma_map_single(di->dmadev, data, len, DMA_TO_DEVICE);
-
+ /* if mapping failed, free skb */
+ if (dma_mapping_error(di->dmadev, pa)) {
+ brcmu_pkt_buf_free_skb(p);
+ return;
+ }
/* With a DMA segment list, Descriptor table is filled
* using the segment list instead of looping over
* buffers in multi-chain DMA. Therefore, EOF for SGLIST
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 3a65447..8e8543c 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -426,6 +426,12 @@
bool blocked;
int err;
+ if (!wl->ucode.bcm43xx_bomminor) {
+ err = brcms_request_fw(wl, wl->wlc->hw->d11core);
+ if (err)
+ return -ENOENT;
+ }
+
ieee80211_wake_queues(hw);
spin_lock_bh(&wl->lock);
blocked = brcms_rfkill_set_hw_state(wl);
@@ -433,14 +439,6 @@
if (!blocked)
wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy);
- if (!wl->ucode.bcm43xx_bomminor) {
- err = brcms_request_fw(wl, wl->wlc->hw->d11core);
- if (err) {
- brcms_remove(wl->wlc->hw->d11core);
- return -ENOENT;
- }
- }
-
spin_lock_bh(&wl->lock);
/* avoid acknowledging frames before a non-monitor device is added */
wl->mute_tx = true;
diff --git a/drivers/net/wireless/hostap/hostap_ioctl.c b/drivers/net/wireless/hostap/hostap_ioctl.c
index ac07473..e509030 100644
--- a/drivers/net/wireless/hostap/hostap_ioctl.c
+++ b/drivers/net/wireless/hostap/hostap_ioctl.c
@@ -523,9 +523,9 @@
data->length = prism2_ap_get_sta_qual(local, addr, qual, IW_MAX_AP, 1);
- memcpy(extra, &addr, sizeof(struct sockaddr) * data->length);
+ memcpy(extra, addr, sizeof(struct sockaddr) * data->length);
data->flags = 1; /* has quality information */
- memcpy(extra + sizeof(struct sockaddr) * data->length, &qual,
+ memcpy(extra + sizeof(struct sockaddr) * data->length, qual,
sizeof(struct iw_quality) * data->length);
kfree(addr);
diff --git a/drivers/net/wireless/iwlegacy/3945.c b/drivers/net/wireless/iwlegacy/3945.c
index dc1e6da..9a5f36e 100644
--- a/drivers/net/wireless/iwlegacy/3945.c
+++ b/drivers/net/wireless/iwlegacy/3945.c
@@ -462,6 +462,8 @@
}
}
+#define SMALL_PACKET_SIZE 256
+
static void
il3945_pass_packet_to_mac80211(struct il_priv *il, struct il_rx_buf *rxb,
struct ieee80211_rx_status *stats)
@@ -470,14 +472,13 @@
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)IL_RX_DATA(pkt);
struct il3945_rx_frame_hdr *rx_hdr = IL_RX_HDR(pkt);
struct il3945_rx_frame_end *rx_end = IL_RX_END(pkt);
- u16 len = le16_to_cpu(rx_hdr->len);
+ u32 len = le16_to_cpu(rx_hdr->len);
struct sk_buff *skb;
__le16 fc = hdr->frame_control;
+ u32 fraglen = PAGE_SIZE << il->hw_params.rx_page_order;
/* We received data from the HW, so stop the watchdog */
- if (unlikely
- (len + IL39_RX_FRAME_SIZE >
- PAGE_SIZE << il->hw_params.rx_page_order)) {
+ if (unlikely(len + IL39_RX_FRAME_SIZE > fraglen)) {
D_DROP("Corruption detected!\n");
return;
}
@@ -488,26 +489,32 @@
return;
}
- skb = dev_alloc_skb(128);
+ skb = dev_alloc_skb(SMALL_PACKET_SIZE);
if (!skb) {
IL_ERR("dev_alloc_skb failed\n");
return;
}
if (!il3945_mod_params.sw_crypto)
- il_set_decrypted_flag(il, (struct ieee80211_hdr *)rxb_addr(rxb),
+ il_set_decrypted_flag(il, (struct ieee80211_hdr *)pkt,
le32_to_cpu(rx_end->status), stats);
- skb_add_rx_frag(skb, 0, rxb->page,
- (void *)rx_hdr->payload - (void *)pkt, len,
- len);
-
+ /* If frame is small enough to fit into skb->head, copy it
+ * and do not consume a full page
+ */
+ if (len <= SMALL_PACKET_SIZE) {
+ memcpy(skb_put(skb, len), rx_hdr->payload, len);
+ } else {
+ skb_add_rx_frag(skb, 0, rxb->page,
+ (void *)rx_hdr->payload - (void *)pkt, len,
+ fraglen);
+ il->alloc_rxb_page--;
+ rxb->page = NULL;
+ }
il_update_stats(il, false, fc, len);
memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
ieee80211_rx(il->hw, skb);
- il->alloc_rxb_page--;
- rxb->page = NULL;
}
#define IL_DELAY_NEXT_SCAN_AFTER_ASSOC (HZ*6)
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 9a95045..d2586f0 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -574,9 +574,11 @@
return decrypt_out;
}
+#define SMALL_PACKET_SIZE 256
+
static void
il4965_pass_packet_to_mac80211(struct il_priv *il, struct ieee80211_hdr *hdr,
- u16 len, u32 ampdu_status, struct il_rx_buf *rxb,
+ u32 len, u32 ampdu_status, struct il_rx_buf *rxb,
struct ieee80211_rx_status *stats)
{
struct sk_buff *skb;
@@ -593,21 +595,25 @@
il_set_decrypted_flag(il, hdr, ampdu_status, stats))
return;
- skb = dev_alloc_skb(128);
+ skb = dev_alloc_skb(SMALL_PACKET_SIZE);
if (!skb) {
IL_ERR("dev_alloc_skb failed\n");
return;
}
- skb_add_rx_frag(skb, 0, rxb->page, (void *)hdr - rxb_addr(rxb), len,
- len);
+ if (len <= SMALL_PACKET_SIZE) {
+ memcpy(skb_put(skb, len), hdr, len);
+ } else {
+ skb_add_rx_frag(skb, 0, rxb->page, (void *)hdr - rxb_addr(rxb),
+ len, PAGE_SIZE << il->hw_params.rx_page_order);
+ il->alloc_rxb_page--;
+ rxb->page = NULL;
+ }
il_update_stats(il, false, fc, len);
memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
ieee80211_rx(il->hw, skb);
- il->alloc_rxb_page--;
- rxb->page = NULL;
}
/* Called for N_RX (legacy ABG frames), or
@@ -4442,13 +4448,13 @@
* is killed. Hence update the killswitch state here. The
* rfkill handler will care about restarting if needed.
*/
- if (!test_bit(S_ALIVE, &il->status)) {
- if (hw_rf_kill)
- set_bit(S_RFKILL, &il->status);
- else
- clear_bit(S_RFKILL, &il->status);
- wiphy_rfkill_set_hw_state(il->hw->wiphy, hw_rf_kill);
+ if (hw_rf_kill) {
+ set_bit(S_RFKILL, &il->status);
+ } else {
+ clear_bit(S_RFKILL, &il->status);
+ il_force_reset(il, true);
}
+ wiphy_rfkill_set_hw_state(il->hw->wiphy, hw_rf_kill);
handled |= CSR_INT_BIT_RF_KILL;
}
@@ -5316,6 +5322,9 @@
il->active_rate = RATES_MASK;
+ il_power_update_mode(il, true);
+ D_INFO("Updated power mode\n");
+
if (il_is_associated(il)) {
struct il_rxon_cmd *active_rxon =
(struct il_rxon_cmd *)&il->active;
@@ -5346,9 +5355,6 @@
D_INFO("ALIVE processing complete.\n");
wake_up(&il->wait_command_queue);
- il_power_update_mode(il, true);
- D_INFO("Updated power mode\n");
-
return;
restart:
diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c
index e9a3cbc..9c9ebad 100644
--- a/drivers/net/wireless/iwlegacy/common.c
+++ b/drivers/net/wireless/iwlegacy/common.c
@@ -4660,6 +4660,7 @@
return 0;
}
+EXPORT_SYMBOL(il_force_reset);
int
il_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h
index 71ea775..e783ea0 100644
--- a/drivers/net/wireless/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/iwlwifi/dvm/dev.h
@@ -670,7 +670,6 @@
unsigned long reload_jiffies;
int reload_count;
bool ucode_loaded;
- bool init_ucode_run; /* Don't run init uCode again */
u8 plcp_delta_threshold;
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index cab23af..e9d09f1 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -739,6 +739,24 @@
return ret;
}
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+ if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+ return false;
+ return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+ if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+ return false;
+ if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+ return true;
+
+ /* disabled by default */
+ return false;
+}
+
static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
enum ieee80211_ampdu_mlme_action action,
@@ -760,7 +778,7 @@
switch (action) {
case IEEE80211_AMPDU_RX_START:
- if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+ if (!iwl_enable_rx_ampdu(priv->cfg))
break;
IWL_DEBUG_HT(priv, "start Rx\n");
ret = iwl_sta_rx_agg_start(priv, sta, tid, *ssn);
@@ -772,7 +790,7 @@
case IEEE80211_AMPDU_TX_START:
if (!priv->trans->ops->txq_enable)
break;
- if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+ if (!iwl_enable_tx_ampdu(priv->cfg))
break;
IWL_DEBUG_HT(priv, "start Tx\n");
ret = iwlagn_tx_agg_start(priv, vif, sta, tid, ssn);
@@ -1059,7 +1077,10 @@
if (test_bit(STATUS_EXIT_PENDING, &priv->status))
return;
- if (test_and_clear_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
+ if (!test_and_clear_bit(STATUS_CHANNEL_SWITCH_PENDING, &priv->status))
+ return;
+
+ if (ctx->vif)
ieee80211_chswitch_done(ctx->vif, is_success);
}
diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c
index 74d7572..c2b8e49 100644
--- a/drivers/net/wireless/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/iwlwifi/dvm/main.c
@@ -252,13 +252,17 @@
struct iwl_priv *priv =
container_of(work, struct iwl_priv, bt_runtime_config);
+ mutex_lock(&priv->mutex);
if (test_bit(STATUS_EXIT_PENDING, &priv->status))
- return;
+ goto out;
/* dont send host command if rf-kill is on */
if (!iwl_is_ready_rf(priv))
- return;
+ goto out;
+
iwlagn_send_advance_bt_config(priv);
+out:
+ mutex_unlock(&priv->mutex);
}
static void iwl_bg_bt_full_concurrency(struct work_struct *work)
@@ -758,7 +762,7 @@
BT_COEX_PRIO_TBL_EVT_INIT_CALIB2);
if (ret)
return ret;
- } else {
+ } else if (priv->cfg->bt_params) {
/*
* default is 2-wire BT coexexistence support
*/
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index c3c13ce..e800002 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -590,6 +590,7 @@
sizeof(priv->tid_data[sta_id][tid]));
priv->stations[sta_id].used &= ~IWL_STA_DRIVER_ACTIVE;
+ priv->stations[sta_id].used &= ~IWL_STA_UCODE_INPROGRESS;
priv->num_stations--;
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index a900aaf..2b5dbff 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -445,27 +445,19 @@
/* Copy MAC header from skb into command buffer */
memcpy(tx_cmd->hdr, hdr, hdr_len);
+ txq_id = info->hw_queue;
+
if (is_agg)
txq_id = priv->tid_data[sta_id][tid].agg.txq_id;
else if (info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) {
/*
- * Send this frame after DTIM -- there's a special queue
- * reserved for this for contexts that support AP mode.
- */
- txq_id = ctx->mcast_queue;
-
- /*
* The microcode will clear the more data
* bit in the last frame it transmits.
*/
hdr->frame_control |=
cpu_to_le16(IEEE80211_FCTL_MOREDATA);
- } else if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
- txq_id = IWL_AUX_QUEUE;
- else
- txq_id = ctx->ac_to_queue[skb_get_queue_mapping(skb)];
+ }
- WARN_ON_ONCE(!is_agg && txq_id != info->hw_queue);
WARN_ON_ONCE(is_agg &&
priv->queue_to_mac80211[txq_id] != info->hw_queue);
@@ -1330,8 +1322,6 @@
struct iwl_compressed_ba_resp *ba_resp = (void *)pkt->data;
struct iwl_ht_agg *agg;
struct sk_buff_head reclaimed_skbs;
- struct ieee80211_tx_info *info;
- struct ieee80211_hdr *hdr;
struct sk_buff *skb;
int sta_id;
int tid;
@@ -1418,22 +1408,28 @@
freed = 0;
skb_queue_walk(&reclaimed_skbs, skb) {
- hdr = (struct ieee80211_hdr *)skb->data;
+ struct ieee80211_hdr *hdr = (void *)skb->data;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
if (ieee80211_is_data_qos(hdr->frame_control))
freed++;
else
WARN_ON_ONCE(1);
- info = IEEE80211_SKB_CB(skb);
iwl_trans_free_tx_cmd(priv->trans, info->driver_data[1]);
+ memset(&info->status, 0, sizeof(info->status));
+ /* Packet was transmitted successfully, failures come as single
+ * frames because before failing a frame the firmware transmits
+ * it without aggregation at least once.
+ */
+ info->flags |= IEEE80211_TX_STAT_ACK;
+
if (freed == 1) {
/* this is the first skb we deliver in this batch */
/* put the rate scaling data there */
info = IEEE80211_SKB_CB(skb);
memset(&info->status, 0, sizeof(info->status));
- info->flags |= IEEE80211_TX_STAT_ACK;
info->flags |= IEEE80211_TX_STAT_AMPDU;
info->status.ampdu_ack_len = ba_resp->txed_2_done;
info->status.ampdu_len = ba_resp->txed;
diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c
index 0a1cdc5..5ad94a8 100644
--- a/drivers/net/wireless/iwlwifi/dvm/ucode.c
+++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c
@@ -425,9 +425,6 @@
if (!priv->fw->img[IWL_UCODE_INIT].sec[0].len)
return 0;
- if (priv->init_ucode_run)
- return 0;
-
iwl_init_notification_wait(&priv->notif_wait, &calib_wait,
calib_complete, ARRAY_SIZE(calib_complete),
iwlagn_wait_calib, priv);
@@ -447,8 +444,6 @@
*/
ret = iwl_wait_notification(&priv->notif_wait, &calib_wait,
UCODE_CALIB_TIMEOUT);
- if (!ret)
- priv->init_ucode_run = true;
goto out;
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index b5ab8d1..5282088 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -268,6 +268,12 @@
.ht_params = &iwl6000_ht_params,
};
+const struct iwl_cfg iwl6035_2agn_sff_cfg = {
+ .name = "Intel(R) Centrino(R) Ultimate-N 6235 AGN",
+ IWL_DEVICE_6035,
+ .ht_params = &iwl6000_ht_params,
+};
+
const struct iwl_cfg iwl1030_bgn_cfg = {
.name = "Intel(R) Centrino(R) Wireless-N 1030 BGN",
IWL_DEVICE_6030,
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 50263e8..9fd01dc 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -67,16 +67,16 @@
#include "iwl-agn-hw.h"
/* Highest firmware API version supported */
-#define IWL7260_UCODE_API_MAX 6
-#define IWL3160_UCODE_API_MAX 6
+#define IWL7260_UCODE_API_MAX 7
+#define IWL3160_UCODE_API_MAX 7
/* Oldest version we won't warn about */
-#define IWL7260_UCODE_API_OK 6
-#define IWL3160_UCODE_API_OK 6
+#define IWL7260_UCODE_API_OK 7
+#define IWL3160_UCODE_API_OK 7
/* Lowest firmware API version supported */
-#define IWL7260_UCODE_API_MIN 6
-#define IWL3160_UCODE_API_MIN 6
+#define IWL7260_UCODE_API_MIN 7
+#define IWL3160_UCODE_API_MIN 7
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
@@ -125,21 +125,63 @@
const struct iwl_cfg iwl7260_2ac_cfg = {
- .name = "Intel(R) Dual Band Wireless AC7260",
+ .name = "Intel(R) Dual Band Wireless AC 7260",
.fw_name_pre = IWL7260_FW_PRE,
IWL_DEVICE_7000,
.ht_params = &iwl7000_ht_params,
.nvm_ver = IWL7260_NVM_VERSION,
.nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
};
-const struct iwl_cfg iwl3160_ac_cfg = {
- .name = "Intel(R) Dual Band Wireless AC3160",
+const struct iwl_cfg iwl7260_2n_cfg = {
+ .name = "Intel(R) Dual Band Wireless N 7260",
+ .fw_name_pre = IWL7260_FW_PRE,
+ IWL_DEVICE_7000,
+ .ht_params = &iwl7000_ht_params,
+ .nvm_ver = IWL7260_NVM_VERSION,
+ .nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl7260_n_cfg = {
+ .name = "Intel(R) Wireless N 7260",
+ .fw_name_pre = IWL7260_FW_PRE,
+ IWL_DEVICE_7000,
+ .ht_params = &iwl7000_ht_params,
+ .nvm_ver = IWL7260_NVM_VERSION,
+ .nvm_calib_ver = IWL7260_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_2ac_cfg = {
+ .name = "Intel(R) Dual Band Wireless AC 3160",
.fw_name_pre = IWL3160_FW_PRE,
IWL_DEVICE_7000,
.ht_params = &iwl7000_ht_params,
.nvm_ver = IWL3160_NVM_VERSION,
.nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_2n_cfg = {
+ .name = "Intel(R) Dual Band Wireless N 3160",
+ .fw_name_pre = IWL3160_FW_PRE,
+ IWL_DEVICE_7000,
+ .ht_params = &iwl7000_ht_params,
+ .nvm_ver = IWL3160_NVM_VERSION,
+ .nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
+};
+
+const struct iwl_cfg iwl3160_n_cfg = {
+ .name = "Intel(R) Wireless N 3160",
+ .fw_name_pre = IWL3160_FW_PRE,
+ IWL_DEVICE_7000,
+ .ht_params = &iwl7000_ht_params,
+ .nvm_ver = IWL3160_NVM_VERSION,
+ .nvm_calib_ver = IWL3160_TX_POWER_VERSION,
+ .host_interrupt_operation_mode = true,
};
MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h
index c38aa8f..8ca006b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/iwlwifi/iwl-config.h
@@ -241,6 +241,8 @@
* @rx_with_siso_diversity: 1x1 device with rx antenna diversity
* @internal_wimax_coex: internal wifi/wimax combo device
* @temp_offset_v2: support v2 of temperature offset calibration
+ * @host_interrupt_operation_mode: device needs host interrupt operation
+ * mode set
*
* We enable the driver to be backward compatible wrt. hardware features.
* API differences in uCode shouldn't be handled here but through TLVs
@@ -273,6 +275,7 @@
const bool rx_with_siso_diversity;
const bool internal_wimax_coex;
const bool temp_offset_v2;
+ const bool host_interrupt_operation_mode;
};
/*
@@ -316,10 +319,15 @@
extern const struct iwl_cfg iwl2000_2bgn_d_cfg;
extern const struct iwl_cfg iwl2030_2bgn_cfg;
extern const struct iwl_cfg iwl6035_2agn_cfg;
+extern const struct iwl_cfg iwl6035_2agn_sff_cfg;
extern const struct iwl_cfg iwl105_bgn_cfg;
extern const struct iwl_cfg iwl105_bgn_d_cfg;
extern const struct iwl_cfg iwl135_bgn_cfg;
extern const struct iwl_cfg iwl7260_2ac_cfg;
-extern const struct iwl_cfg iwl3160_ac_cfg;
+extern const struct iwl_cfg iwl7260_2n_cfg;
+extern const struct iwl_cfg iwl7260_n_cfg;
+extern const struct iwl_cfg iwl3160_2ac_cfg;
+extern const struct iwl_cfg iwl3160_2n_cfg;
+extern const struct iwl_cfg iwl3160_n_cfg;
#endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-csr.h b/drivers/net/wireless/iwlwifi/iwl-csr.h
index 20e845d..bba1af4 100644
--- a/drivers/net/wireless/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/iwlwifi/iwl-csr.h
@@ -463,13 +463,10 @@
* the CSR_INT_COALESCING is an 8 bit register in 32-usec unit
*
* default interrupt coalescing timer is 64 x 32 = 2048 usecs
- * default interrupt coalescing calibration timer is 16 x 32 = 512 usecs
*/
#define IWL_HOST_INT_TIMEOUT_MAX (0xFF)
#define IWL_HOST_INT_TIMEOUT_DEF (0x40)
#define IWL_HOST_INT_TIMEOUT_MIN (0x0)
-#define IWL_HOST_INT_CALIB_TIMEOUT_MAX (0xFF)
-#define IWL_HOST_INT_CALIB_TIMEOUT_DEF (0x10)
-#define IWL_HOST_INT_CALIB_TIMEOUT_MIN (0x0)
+#define IWL_HOST_INT_OPER_MODE BIT(31)
#endif /* !__iwl_csr_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c
index 40fed1f..96050e6 100644
--- a/drivers/net/wireless/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/iwlwifi/iwl-drv.c
@@ -1211,7 +1211,7 @@
MODULE_PARM_DESC(swcrypto, "using crypto in software (default 0 [hardware])");
module_param_named(11n_disable, iwlwifi_mod_params.disable_11n, uint, S_IRUGO);
MODULE_PARM_DESC(11n_disable,
- "disable 11n functionality, bitmap: 1: full, 2: agg TX, 4: agg RX");
+ "disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX");
module_param_named(amsdu_size_8K, iwlwifi_mod_params.amsdu_size_8K,
int, S_IRUGO);
MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size (default 0)");
diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h
index d6f6c37..e99bc55 100644
--- a/drivers/net/wireless/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h
@@ -79,9 +79,12 @@
IWL_POWER_NUM
};
-#define IWL_DISABLE_HT_ALL BIT(0)
-#define IWL_DISABLE_HT_TXAGG BIT(1)
-#define IWL_DISABLE_HT_RXAGG BIT(2)
+enum iwl_disable_11n {
+ IWL_DISABLE_HT_ALL = BIT(0),
+ IWL_DISABLE_HT_TXAGG = BIT(1),
+ IWL_DISABLE_HT_RXAGG = BIT(2),
+ IWL_ENABLE_HT_TXAGG = BIT(3),
+};
/**
* struct iwl_mod_params
@@ -90,7 +93,7 @@
*
* @sw_crypto: using hardware encryption, default = 0
* @disable_11n: disable 11n capabilities, default = 0,
- * use IWL_DISABLE_HT_* constants
+ * use IWL_[DIS,EN]ABLE_HT_* constants
* @amsdu_size_8K: enable 8K amsdu size, default = 0
* @restart_fw: restart firmware, default = 1
* @plcp_check: enable plcp health check, default = true
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 6199a0a..a7cf535 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -180,6 +180,11 @@
for (ch_idx = 0; ch_idx < IWL_NUM_CHANNELS; ch_idx++) {
ch_flags = __le16_to_cpup(nvm_ch_flags + ch_idx);
+
+ if (ch_idx >= NUM_2GHZ_CHANNELS &&
+ !data->sku_cap_band_52GHz_enable)
+ ch_flags &= ~NVM_CHANNEL_VALID;
+
if (!(ch_flags & NVM_CHANNEL_VALID)) {
IWL_DEBUG_EEPROM(dev,
"Ch. %d Flags %x [%sGHz] - No traffic\n",
diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h
index 386f2a7..c26a6dc 100644
--- a/drivers/net/wireless/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/iwlwifi/iwl-prph.h
@@ -260,4 +260,8 @@
/*********************** END TX SCHEDULER *************************************/
+/* Oscillator clock */
+#define OSC_CLK (0xa04068)
+#define OSC_CLK_FORCE_CONTROL (0x8)
+
#endif /* __iwl_prph_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 7a13790..d8df1d9 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -489,6 +489,7 @@
* Set during transport allocation.
* @hw_id_str: a string with info about HW ID. Set during transport allocation.
* @pm_support: set to true in start_hw if link pm is supported
+ * @ltr_enabled: set to true if the LTR is enabled
* @dev_cmd_pool: pool for Tx cmd allocation - for internal use only.
* The user should use iwl_trans_{alloc,free}_tx_cmd.
* @dev_cmd_headroom: room needed for the transport's private use before the
@@ -513,6 +514,7 @@
u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
bool pm_support;
+ bool ltr_enabled;
/* The following fields are internal only */
struct kmem_cache *dev_cmd_pool;
@@ -605,8 +607,10 @@
{
int ret;
- WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
- "%s bad state = %d", __func__, trans->state);
+ if (trans->state != IWL_TRANS_FW_ALIVE) {
+ IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+ return -EIO;
+ }
if (!(cmd->flags & CMD_ASYNC))
lock_map_acquire_read(&trans->sync_cmd_lockdep_map);
diff --git a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
index 810bfa5..9649f51 100644
--- a/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/bt-coex.c
@@ -523,8 +523,11 @@
mutex_lock(&mvm->mutex);
- /* Rssi update while not associated ?! */
- if (WARN_ON_ONCE(mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT))
+ /*
+ * Rssi update while not associated - can happen since the statistics
+ * are handled asynchronously
+ */
+ if (mvmvif->ap_sta_id == IWL_MVM_STATION_COUNT)
goto out_unlock;
/* No open connection - reports should be disabled */
diff --git a/drivers/net/wireless/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
index 2053dcc..109dc8e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
@@ -119,6 +119,10 @@
if (sscanf(buf, "%d %d", &sta_id, &drain) != 2)
return -EINVAL;
+ if (sta_id < 0 || sta_id >= IWL_MVM_STATION_COUNT)
+ return -EINVAL;
+ if (drain < 0 || drain > 1)
+ return -EINVAL;
mutex_lock(&mvm->mutex);
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
index 51e015d..6f8b2c1 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
@@ -75,13 +75,15 @@
* struct iwl_d3_manager_config - D3 manager configuration command
* @min_sleep_time: minimum sleep time (in usec)
* @wakeup_flags: wakeup flags, see &enum iwl_d3_wakeup_flags
+ * @wakeup_host_timer: force wakeup after this many seconds
*
* The structure is used for the D3_CONFIG_CMD command.
*/
struct iwl_d3_manager_config {
__le32 min_sleep_time;
__le32 wakeup_flags;
-} __packed; /* D3_MANAGER_CONFIG_CMD_S_VER_3 */
+ __le32 wakeup_host_timer;
+} __packed; /* D3_MANAGER_CONFIG_CMD_S_VER_4 */
/* TODO: OFFLOADS_QUERY_API_S_VER_1 */
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-mac.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-mac.h
index d68640e..98b1feb 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-mac.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-mac.h
@@ -71,7 +71,13 @@
#define MAC_INDEX_MIN_DRIVER 0
#define NUM_MAC_INDEX_DRIVER MAC_INDEX_AUX
-#define AC_NUM 4 /* Number of access categories */
+enum iwl_ac {
+ AC_BK,
+ AC_BE,
+ AC_VI,
+ AC_VO,
+ AC_NUM,
+};
/**
* enum iwl_mac_protection_flags - MAC context flags
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
index 81fe45f..ac38ecf 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-power.h
@@ -67,7 +67,40 @@
/* Power Management Commands, Responses, Notifications */
/**
- * enum iwl_scan_flags - masks for power table command flags
+ * enum iwl_ltr_config_flags - masks for LTR config command flags
+ * @LTR_CFG_FLAG_FEATURE_ENABLE: Feature operational status
+ * @LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS: allow LTR change on shadow
+ * memory access
+ * @LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH: allow LTR msg send on ANY LTR
+ * reg change
+ * @LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3: allow LTR msg send on transition from
+ * D0 to D3
+ * @LTR_CFG_FLAG_SW_SET_SHORT: fixed static short LTR register
+ * @LTR_CFG_FLAG_SW_SET_LONG: fixed static short LONG register
+ * @LTR_CFG_FLAG_DENIE_C10_ON_PD: allow going into C10 on PD
+ */
+enum iwl_ltr_config_flags {
+ LTR_CFG_FLAG_FEATURE_ENABLE = BIT(0),
+ LTR_CFG_FLAG_HW_DIS_ON_SHADOW_REG_ACCESS = BIT(1),
+ LTR_CFG_FLAG_HW_EN_SHRT_WR_THROUGH = BIT(2),
+ LTR_CFG_FLAG_HW_DIS_ON_D0_2_D3 = BIT(3),
+ LTR_CFG_FLAG_SW_SET_SHORT = BIT(4),
+ LTR_CFG_FLAG_SW_SET_LONG = BIT(5),
+ LTR_CFG_FLAG_DENIE_C10_ON_PD = BIT(6),
+};
+
+/**
+ * struct iwl_ltr_config_cmd - configures the LTR
+ * @flags: See %enum iwl_ltr_config_flags
+ */
+struct iwl_ltr_config_cmd {
+ __le32 flags;
+ __le32 static_long;
+ __le32 static_short;
+} __packed;
+
+/**
+ * enum iwl_power_flags - masks for power table command flags
* @POWER_FLAGS_POWER_SAVE_ENA_MSK: '1' Allow to save power by turning off
* receiver and transmitter. '0' - does not allow.
* @POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK: '0' Driver disables power management,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index b60d141..365095a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -69,7 +69,6 @@
/* Scan Commands, Responses, Notifications */
/* Masks for iwl_scan_channel.type flags */
-#define SCAN_CHANNEL_TYPE_PASSIVE 0
#define SCAN_CHANNEL_TYPE_ACTIVE BIT(0)
#define SCAN_CHANNEL_NARROW_BAND BIT(22)
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index c638455..4b6730d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -138,6 +138,7 @@
/* Power */
POWER_TABLE_CMD = 0x77,
+ LTR_CONFIG = 0xee,
/* Scanning */
SCAN_REQUEST_CMD = 0x80,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index e18c92d..d250d45 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -443,6 +443,15 @@
if (ret)
goto error;
+ if (mvm->trans->ltr_enabled) {
+ struct iwl_ltr_config_cmd cmd = {
+ .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE),
+ };
+
+ WARN_ON(iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
+ sizeof(cmd), &cmd));
+ }
+
IWL_DEBUG_INFO(mvm, "RT uCode started.\n");
return 0;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
index b2cc3d9..d8e858cc 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
@@ -193,14 +193,11 @@
u32 iwl_mvm_mac_get_queues_mask(struct iwl_mvm *mvm,
struct ieee80211_vif *vif)
{
- u32 qmask, ac;
+ u32 qmask = 0, ac;
if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
return BIT(IWL_MVM_OFFCHANNEL_QUEUE);
- qmask = (vif->cab_queue != IEEE80211_INVAL_HW_QUEUE) ?
- BIT(vif->cab_queue) : 0;
-
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
if (vif->hw_queue[ac] != IEEE80211_INVAL_HW_QUEUE)
qmask |= BIT(vif->hw_queue[ac]);
@@ -362,7 +359,7 @@
break;
case NL80211_IFTYPE_AP:
iwl_trans_ac_txq_enable(mvm->trans, vif->cab_queue,
- IWL_MVM_TX_FIFO_VO);
+ IWL_MVM_TX_FIFO_MCAST);
/* fall through */
default:
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
@@ -550,6 +547,10 @@
cmd->ac[i].fifos_mask = BIT(iwl_mvm_ac_to_tx_fifo[i]);
}
+ /* in AP mode, the MCAST FIFO takes the EDCA params from VO */
+ if (vif->type == NL80211_IFTYPE_AP)
+ cmd->ac[AC_VO].fifos_mask |= BIT(IWL_MVM_TX_FIFO_MCAST);
+
if (vif->bss_conf.qos)
cmd->qos_flags |= cpu_to_le32(MAC_QOS_FLG_UPDATE_EDCA);
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index a5eb8c8..ec0d32a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -243,7 +243,11 @@
if (ret)
return ret;
- return ieee80211_register_hw(mvm->hw);
+ ret = ieee80211_register_hw(mvm->hw);
+ if (ret)
+ iwl_mvm_leds_exit(mvm);
+
+ return ret;
}
static void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
@@ -274,6 +278,24 @@
ieee80211_free_txskb(hw, skb);
}
+static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg)
+{
+ if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG)
+ return false;
+ return true;
+}
+
+static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg)
+{
+ if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG)
+ return false;
+ if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG)
+ return true;
+
+ /* enabled by default */
+ return true;
+}
+
static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
enum ieee80211_ampdu_mlme_action action,
@@ -293,7 +315,7 @@
switch (action) {
case IEEE80211_AMPDU_RX_START:
- if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) {
+ if (!iwl_enable_rx_ampdu(mvm->cfg)) {
ret = -EINVAL;
break;
}
@@ -303,7 +325,7 @@
ret = iwl_mvm_sta_rx_agg(mvm, sta, tid, 0, false);
break;
case IEEE80211_AMPDU_TX_START:
- if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) {
+ if (!iwl_enable_tx_ampdu(mvm->cfg)) {
ret = -EINVAL;
break;
}
@@ -338,9 +360,6 @@
mvmvif->uploaded = false;
mvmvif->ap_sta_id = IWL_MVM_STATION_COUNT;
- /* does this make sense at all? */
- mvmvif->color++;
-
spin_lock_bh(&mvm->time_event_lock);
iwl_mvm_te_clear_data(mvm, &mvmvif->time_event_data);
spin_unlock_bh(&mvm->time_event_lock);
@@ -987,6 +1006,21 @@
mutex_lock(&mvm->mutex);
if (old_state == IEEE80211_STA_NOTEXIST &&
new_state == IEEE80211_STA_NONE) {
+ /*
+ * Firmware bug - it'll crash if the beacon interval is less
+ * than 16. We can't avoid connecting at all, so refuse the
+ * station state change, this will cause mac80211 to abandon
+ * attempts to connect to this AP, and eventually wpa_s will
+ * blacklist the AP...
+ */
+ if (vif->type == NL80211_IFTYPE_STATION &&
+ vif->bss_conf.beacon_int < 16) {
+ IWL_ERR(mvm,
+ "AP %pM beacon interval is %d, refusing due to firmware bug!\n",
+ sta->addr, vif->bss_conf.beacon_int);
+ ret = -EINVAL;
+ goto out_unlock;
+ }
ret = iwl_mvm_add_sta(mvm, vif, sta);
} else if (old_state == IEEE80211_STA_NONE &&
new_state == IEEE80211_STA_AUTH) {
@@ -1015,6 +1049,7 @@
} else {
ret = -EIO;
}
+ out_unlock:
mutex_unlock(&mvm->mutex);
return ret;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index 9f46b23..8086231 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -88,6 +88,7 @@
IWL_MVM_TX_FIFO_BE,
IWL_MVM_TX_FIFO_VI,
IWL_MVM_TX_FIFO_VO,
+ IWL_MVM_TX_FIFO_MCAST = 5,
};
extern struct ieee80211_ops iwl_mvm_hw_ops;
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index b29c31a..649d301 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -293,6 +293,7 @@
CMD(BT_PROFILE_NOTIFICATION),
CMD(BT_CONFIG),
CMD(MCAST_FILTER_CMD),
+ CMD(LTR_CONFIG),
};
#undef CMD
@@ -424,6 +425,7 @@
out_unregister:
ieee80211_unregister_hw(mvm->hw);
+ iwl_mvm_leds_exit(mvm);
out_free:
iwl_phy_db_free(mvm->phy_db);
kfree(mvm->scan_cmd);
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 2476e43..b987dfb 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -137,8 +137,8 @@
{
int fw_idx, req_idx;
- fw_idx = 0;
- for (req_idx = req->n_ssids - 1; req_idx > 0; req_idx--) {
+ for (req_idx = req->n_ssids - 1, fw_idx = 0; req_idx > 0;
+ req_idx--, fw_idx++) {
cmd->direct_scan[fw_idx].id = WLAN_EID_SSID;
cmd->direct_scan[fw_idx].len = req->ssids[req_idx].ssid_len;
memcpy(cmd->direct_scan[fw_idx].ssid,
@@ -176,19 +176,12 @@
struct iwl_scan_channel *chan = (struct iwl_scan_channel *)
(cmd->data + le16_to_cpu(cmd->tx_cmd.len));
int i;
- __le32 chan_type_value;
-
- if (req->n_ssids > 0)
- chan_type_value = cpu_to_le32(BIT(req->n_ssids + 1) - 1);
- else
- chan_type_value = SCAN_CHANNEL_TYPE_PASSIVE;
for (i = 0; i < cmd->channel_count; i++) {
chan->channel = cpu_to_le16(req->channels[i]->hw_value);
+ chan->type = cpu_to_le32(BIT(req->n_ssids) - 1);
if (req->channels[i]->flags & IEEE80211_CHAN_PASSIVE_SCAN)
- chan->type = SCAN_CHANNEL_TYPE_PASSIVE;
- else
- chan->type = chan_type_value;
+ chan->type &= cpu_to_le32(~SCAN_CHANNEL_TYPE_ACTIVE);
chan->active_dwell = cpu_to_le16(active_dwell);
chan->passive_dwell = cpu_to_le16(passive_dwell);
chan->iteration_count = cpu_to_le16(1);
@@ -320,7 +313,8 @@
iwl_mvm_scan_fill_ssids(cmd, req);
- cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL);
+ cmd->tx_cmd.tx_flags = cpu_to_le32(TX_CMD_FLG_SEQ_CTL |
+ TX_CMD_FLG_BT_DIS);
cmd->tx_cmd.sta_id = mvm->aux_sta.sta_id;
cmd->tx_cmd.life_time = cpu_to_le32(TX_CMD_LIFE_TIME_INFINITE);
cmd->tx_cmd.rate_n_flags =
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index 5c664ed..68f0bbe 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -226,9 +226,6 @@
if (vif->hw_queue[i] != IEEE80211_INVAL_HW_QUEUE)
mvm_sta->tfd_queue_msk |= BIT(vif->hw_queue[i]);
- if (vif->cab_queue != IEEE80211_INVAL_HW_QUEUE)
- mvm_sta->tfd_queue_msk |= BIT(vif->cab_queue);
-
/* for HW restart - need to reset the seq_number etc... */
memset(mvm_sta->tid_data, 0, sizeof(mvm_sta->tid_data));
@@ -621,8 +618,12 @@
cmd.mac_id_n_color = cpu_to_le32(mvm_sta->mac_id_n_color);
cmd.sta_id = mvm_sta->sta_id;
cmd.add_modify = STA_MODE_MODIFY;
- cmd.add_immediate_ba_tid = (u8) tid;
- cmd.add_immediate_ba_ssn = cpu_to_le16(ssn);
+ if (start) {
+ cmd.add_immediate_ba_tid = (u8) tid;
+ cmd.add_immediate_ba_ssn = cpu_to_le16(ssn);
+ } else {
+ cmd.remove_immediate_ba_tid = (u8) tid;
+ }
cmd.modify_mask = start ? STA_MODIFY_ADD_BA_TID :
STA_MODIFY_REMOVE_BA_TID;
@@ -894,6 +895,7 @@
struct iwl_mvm_sta *mvmsta = (void *)sta->drv_priv;
struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid];
u16 txq_id;
+ enum iwl_mvm_agg_state old_state;
/*
* First set the agg state to OFF to avoid calling
@@ -903,13 +905,17 @@
txq_id = tid_data->txq_id;
IWL_DEBUG_TX_QUEUES(mvm, "Flush AGG: sta %d tid %d q %d state %d\n",
mvmsta->sta_id, tid, txq_id, tid_data->state);
+ old_state = tid_data->state;
tid_data->state = IWL_AGG_OFF;
spin_unlock_bh(&mvmsta->lock);
- if (iwl_mvm_flush_tx_path(mvm, BIT(txq_id), true))
- IWL_ERR(mvm, "Couldn't flush the AGG queue\n");
+ if (old_state >= IWL_AGG_ON) {
+ if (iwl_mvm_flush_tx_path(mvm, BIT(txq_id), true))
+ IWL_ERR(mvm, "Couldn't flush the AGG queue\n");
- iwl_trans_txq_disable(mvm->trans, tid_data->txq_id);
+ iwl_trans_txq_disable(mvm->trans, tid_data->txq_id);
+ }
+
mvm->queue_to_mac80211[tid_data->txq_id] =
IWL_INVALID_MAC80211_QUEUE;
@@ -1287,17 +1293,11 @@
struct iwl_mvm_add_sta_cmd cmd = {
.add_modify = STA_MODE_MODIFY,
.sta_id = mvmsta->sta_id,
- .modify_mask = STA_MODIFY_SLEEPING_STA_TX_COUNT,
- .sleep_state_flags = cpu_to_le16(STA_SLEEP_STATE_AWAKE),
+ .station_flags_msk = cpu_to_le32(STA_FLG_PS),
.mac_id_n_color = cpu_to_le32(mvmsta->mac_id_n_color),
};
int ret;
- /*
- * Same modify mask for sleep_tx_count and sleep_state_flags but this
- * should be fine since if we set the STA as "awake", then
- * sleep_tx_count is not relevant.
- */
ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA, CMD_ASYNC, sizeof(cmd), &cmd);
if (ret)
IWL_ERR(mvm, "Failed to send ADD_STA command (%d)\n", ret);
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 48c1891..3dd0e5b 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -175,7 +175,7 @@
* table is controlled by LINK_QUALITY commands
*/
- if (ieee80211_is_data(fc)) {
+ if (ieee80211_is_data(fc) && sta) {
tx_cmd->initial_rate_index = 0;
tx_cmd->tx_flags |= cpu_to_le32(TX_CMD_FLG_STA_RATE);
return;
@@ -610,8 +610,8 @@
!(info->flags & IEEE80211_TX_STAT_ACK))
info->flags |= IEEE80211_TX_STAT_AMPDU_NO_BACK;
- /* W/A FW bug: seq_ctl is wrong when the queue is flushed */
- if (status == TX_STATUS_FAIL_FIFO_FLUSHED) {
+ /* W/A FW bug: seq_ctl is wrong when the status isn't success */
+ if (status != TX_STATUS_SUCCESS) {
struct ieee80211_hdr *hdr = (void *)skb->data;
seq_ctl = le16_to_cpu(hdr->seq_ctrl);
}
@@ -819,16 +819,12 @@
struct iwl_mvm_ba_notif *ba_notif = (void *)pkt->data;
struct sk_buff_head reclaimed_skbs;
struct iwl_mvm_tid_data *tid_data;
- struct ieee80211_tx_info *info;
struct ieee80211_sta *sta;
struct iwl_mvm_sta *mvmsta;
- struct ieee80211_hdr *hdr;
struct sk_buff *skb;
int sta_id, tid, freed;
-
/* "flow" corresponds to Tx queue */
u16 scd_flow = le16_to_cpu(ba_notif->scd_flow);
-
/* "ssn" is start of block-ack Tx window, corresponds to index
* (in Tx queue's circular buffer) of first TFD/frame in window */
u16 ba_resp_scd_ssn = le16_to_cpu(ba_notif->scd_ssn);
@@ -836,6 +832,11 @@
sta_id = ba_notif->sta_id;
tid = ba_notif->tid;
+ if (WARN_ONCE(sta_id >= IWL_MVM_STATION_COUNT ||
+ tid >= IWL_MAX_TID_COUNT,
+ "sta_id %d tid %d", sta_id, tid))
+ return 0;
+
rcu_read_lock();
sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
@@ -885,22 +886,26 @@
freed = 0;
skb_queue_walk(&reclaimed_skbs, skb) {
- hdr = (struct ieee80211_hdr *)skb->data;
+ struct ieee80211_hdr *hdr = (void *)skb->data;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
if (ieee80211_is_data_qos(hdr->frame_control))
freed++;
else
WARN_ON_ONCE(1);
- info = IEEE80211_SKB_CB(skb);
iwl_trans_free_tx_cmd(mvm->trans, info->driver_data[1]);
+ memset(&info->status, 0, sizeof(info->status));
+ /* Packet was transmitted successfully, failures come as single
+ * frames because before failing a frame the firmware transmits
+ * it without aggregation at least once.
+ */
+ info->flags |= IEEE80211_TX_STAT_ACK;
+
if (freed == 1) {
/* this is the first skb we deliver in this batch */
/* put the rate scaling data there */
- info = IEEE80211_SKB_CB(skb);
- memset(&info->status, 0, sizeof(info->status));
- info->flags |= IEEE80211_TX_STAT_ACK;
info->flags |= IEEE80211_TX_STAT_AMPDU;
info->status.ampdu_ack_len = ba_notif->txed_2_done;
info->status.ampdu_len = ba_notif->txed;
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index 687b34e..0d9e081 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -401,6 +401,8 @@
mvm->status, table.valid);
}
+ IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
+
trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
table.data1, table.data2, table.data3,
table.blink1, table.blink2, table.ilink1,
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 8cb53ec..bb020ad 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -129,6 +129,7 @@
{IWL_PCI_DEVICE(0x423C, 0x1306, iwl5150_abg_cfg)}, /* Half Mini Card */
{IWL_PCI_DEVICE(0x423C, 0x1221, iwl5150_agn_cfg)}, /* Mini Card */
{IWL_PCI_DEVICE(0x423C, 0x1321, iwl5150_agn_cfg)}, /* Half Mini Card */
+ {IWL_PCI_DEVICE(0x423C, 0x1326, iwl5150_abg_cfg)}, /* Half Mini Card */
{IWL_PCI_DEVICE(0x423D, 0x1211, iwl5150_agn_cfg)}, /* Mini Card */
{IWL_PCI_DEVICE(0x423D, 0x1311, iwl5150_agn_cfg)}, /* Half Mini Card */
@@ -137,13 +138,16 @@
/* 6x00 Series */
{IWL_PCI_DEVICE(0x422B, 0x1101, iwl6000_3agn_cfg)},
+ {IWL_PCI_DEVICE(0x422B, 0x1108, iwl6000_3agn_cfg)},
{IWL_PCI_DEVICE(0x422B, 0x1121, iwl6000_3agn_cfg)},
+ {IWL_PCI_DEVICE(0x422B, 0x1128, iwl6000_3agn_cfg)},
{IWL_PCI_DEVICE(0x422C, 0x1301, iwl6000i_2agn_cfg)},
{IWL_PCI_DEVICE(0x422C, 0x1306, iwl6000i_2abg_cfg)},
{IWL_PCI_DEVICE(0x422C, 0x1307, iwl6000i_2bg_cfg)},
{IWL_PCI_DEVICE(0x422C, 0x1321, iwl6000i_2agn_cfg)},
{IWL_PCI_DEVICE(0x422C, 0x1326, iwl6000i_2abg_cfg)},
{IWL_PCI_DEVICE(0x4238, 0x1111, iwl6000_3agn_cfg)},
+ {IWL_PCI_DEVICE(0x4238, 0x1118, iwl6000_3agn_cfg)},
{IWL_PCI_DEVICE(0x4239, 0x1311, iwl6000i_2agn_cfg)},
{IWL_PCI_DEVICE(0x4239, 0x1316, iwl6000i_2abg_cfg)},
@@ -151,12 +155,16 @@
{IWL_PCI_DEVICE(0x0082, 0x1301, iwl6005_2agn_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x1306, iwl6005_2abg_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x1307, iwl6005_2bg_cfg)},
+ {IWL_PCI_DEVICE(0x0082, 0x1308, iwl6005_2agn_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x1321, iwl6005_2agn_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x1326, iwl6005_2abg_cfg)},
+ {IWL_PCI_DEVICE(0x0082, 0x1328, iwl6005_2agn_cfg)},
{IWL_PCI_DEVICE(0x0085, 0x1311, iwl6005_2agn_cfg)},
+ {IWL_PCI_DEVICE(0x0085, 0x1318, iwl6005_2agn_cfg)},
{IWL_PCI_DEVICE(0x0085, 0x1316, iwl6005_2abg_cfg)},
{IWL_PCI_DEVICE(0x0082, 0xC020, iwl6005_2agn_sff_cfg)},
{IWL_PCI_DEVICE(0x0085, 0xC220, iwl6005_2agn_sff_cfg)},
+ {IWL_PCI_DEVICE(0x0085, 0xC228, iwl6005_2agn_sff_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x4820, iwl6005_2agn_d_cfg)},
{IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_2agn_mow1_cfg)},/* low 5GHz active */
{IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_2agn_mow2_cfg)},/* high 5GHz active */
@@ -238,8 +246,11 @@
/* 6x35 Series */
{IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)},
+ {IWL_PCI_DEVICE(0x088E, 0x406A, iwl6035_2agn_sff_cfg)},
{IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)},
+ {IWL_PCI_DEVICE(0x088F, 0x426A, iwl6035_2agn_sff_cfg)},
{IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)},
+ {IWL_PCI_DEVICE(0x088E, 0x446A, iwl6035_2agn_sff_cfg)},
{IWL_PCI_DEVICE(0x088E, 0x4860, iwl6035_2agn_cfg)},
{IWL_PCI_DEVICE(0x088F, 0x5260, iwl6035_2agn_cfg)},
@@ -256,10 +267,87 @@
/* 7000 Series */
{IWL_PCI_DEVICE(0x08B1, 0x4070, iwl7260_2ac_cfg)},
- {IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4072, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4170, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4C60, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4C70, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4060, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x406A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4160, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4062, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4162, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4270, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4272, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4260, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x426A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4262, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4470, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4472, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4460, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x446A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4462, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4870, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x486E, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4570, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4560, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4370, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4360, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x5070, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4020, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x402A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0x4220, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0x4420, iwl7260_2n_cfg)},
{IWL_PCI_DEVICE(0x08B1, 0xC070, iwl7260_2ac_cfg)},
- {IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_ac_cfg)},
- {IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC072, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC170, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC060, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC06A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC160, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC062, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC162, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC770, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC760, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC270, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xCC70, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xCC60, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC272, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC260, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC26A, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC262, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC470, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC472, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC460, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC462, iwl7260_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC570, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC560, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC370, iwl7260_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC360, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC020, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC02A, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B2, 0xC220, iwl7260_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B1, 0xC420, iwl7260_2n_cfg)},
+
+/* 3160 Series */
+ {IWL_PCI_DEVICE(0x08B3, 0x0070, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0072, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0170, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0172, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0060, iwl3160_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0062, iwl3160_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B4, 0x0270, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B4, 0x0272, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0470, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x0472, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B4, 0x0370, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8070, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8072, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8170, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8172, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8060, iwl3160_2n_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8062, iwl3160_n_cfg)},
+ {IWL_PCI_DEVICE(0x08B4, 0x8270, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8470, iwl3160_2ac_cfg)},
+ {IWL_PCI_DEVICE(0x08B3, 0x8570, iwl3160_2ac_cfg)},
{0}
};
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index 567e67a..296026b 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -489,6 +489,10 @@
/* Set interrupt coalescing timer to default (2048 usecs) */
iwl_write8(trans, CSR_INT_COALESCING, IWL_HOST_INT_TIMEOUT_DEF);
+
+ /* W/A for interrupt coalescing bug in 7260 and 3160 */
+ if (trans->cfg->host_interrupt_operation_mode)
+ iwl_set_bit(trans, CSR_INT_COALESCING, IWL_HOST_INT_OPER_MODE);
}
int iwl_pcie_rx_init(struct iwl_trans *trans)
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 50ba0a4..6a5eb2b 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -116,11 +116,13 @@
/* PCI registers */
#define PCI_CFG_RETRY_TIMEOUT 0x041
+#define PCI_EXP_DEVCTL2_LTR_EN 0x0400
static void iwl_pcie_apm_config(struct iwl_trans *trans)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
u16 lctl;
+ u16 cap;
/*
* HW bug W/A for instability in PCIe bus L0S->L1 transition.
@@ -131,16 +133,17 @@
* power savings, even without L1.
*/
pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_LNKCTL, &lctl);
- if (lctl & PCI_EXP_LNKCTL_ASPM_L1) {
- /* L1-ASPM enabled; disable(!) L0S */
+ if (lctl & PCI_EXP_LNKCTL_ASPM_L1)
iwl_set_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
- dev_info(trans->dev, "L1 Enabled; Disabling L0S\n");
- } else {
- /* L1-ASPM disabled; enable(!) L0S */
+ else
iwl_clear_bit(trans, CSR_GIO_REG, CSR_GIO_REG_VAL_L0S_ENABLED);
- dev_info(trans->dev, "L1 Disabled; Enabling L0S\n");
- }
trans->pm_support = !(lctl & PCI_EXP_LNKCTL_ASPM_L0S);
+
+ pcie_capability_read_word(trans_pcie->pci_dev, PCI_EXP_DEVCTL2, &cap);
+ trans->ltr_enabled = cap & PCI_EXP_DEVCTL2_LTR_EN;
+ dev_info(trans->dev, "L1 %sabled - LTR %sabled\n",
+ (lctl & PCI_EXP_LNKCTL_ASPM_L1) ? "En" : "Dis",
+ trans->ltr_enabled ? "En" : "Dis");
}
/*
@@ -207,6 +210,22 @@
}
/*
+ * Enable the oscillator to count wake up time for L1 exit. This
+ * consumes slightly more power (100uA) - but allows to be sure
+ * that we wake up from L1 on time.
+ *
+ * This looks weird: read twice the same register, discard the
+ * value, set a bit, and yet again, read that same register
+ * just to discard the value. But that's the way the hardware
+ * seems to like it.
+ */
+ iwl_read_prph(trans, OSC_CLK);
+ iwl_read_prph(trans, OSC_CLK);
+ iwl_set_bits_prph(trans, OSC_CLK, OSC_CLK_FORCE_CONTROL);
+ iwl_read_prph(trans, OSC_CLK);
+ iwl_read_prph(trans, OSC_CLK);
+
+ /*
* Enable DMA clock and wait for it to stabilize.
*
* Write to "CLK_EN_REG"; "1" bits enable clocks, while "0" bits
@@ -276,9 +295,6 @@
spin_lock_irqsave(&trans_pcie->irq_lock, flags);
iwl_pcie_apm_init(trans);
- /* Set interrupt coalescing calibration timer to default (512 usecs) */
- iwl_write8(trans, CSR_INT_COALESCING, IWL_HOST_INT_CALIB_TIMEOUT_DEF);
-
spin_unlock_irqrestore(&trans_pcie->irq_lock, flags);
iwl_pcie_set_pwr(trans, false);
@@ -326,6 +342,7 @@
{
int ret;
int t = 0;
+ int iter;
IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n");
@@ -334,18 +351,23 @@
if (ret >= 0)
return 0;
- /* If HW is not ready, prepare the conditions to check again */
- iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
- CSR_HW_IF_CONFIG_REG_PREPARE);
+ for (iter = 0; iter < 10; iter++) {
+ /* If HW is not ready, prepare the conditions to check again */
+ iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+ CSR_HW_IF_CONFIG_REG_PREPARE);
- do {
- ret = iwl_pcie_set_hw_ready(trans);
- if (ret >= 0)
- return 0;
+ do {
+ ret = iwl_pcie_set_hw_ready(trans);
+ if (ret >= 0)
+ return 0;
- usleep_range(200, 1000);
- t += 200;
- } while (t < 150000);
+ usleep_range(200, 1000);
+ t += 200;
+ } while (t < 150000);
+ msleep(25);
+ }
+
+ IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter);
return ret;
}
@@ -1481,16 +1503,16 @@
spin_lock_init(&trans_pcie->reg_lock);
init_waitqueue_head(&trans_pcie->ucode_write_waitq);
- /* W/A - seems to solve weird behavior. We need to remove this if we
- * don't want to stay in L1 all the time. This wastes a lot of power */
- pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
- PCIE_LINK_STATE_CLKPM);
-
if (pci_enable_device(pdev)) {
err = -ENODEV;
goto out_no_pci;
}
+ /* W/A - seems to solve weird behavior. We need to remove this if we
+ * don't want to stay in L1 all the time. This wastes a lot of power */
+ pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+ PCIE_LINK_STATE_CLKPM);
+
pci_set_master(pdev);
err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index c5e3029..f05962c 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -576,10 +576,16 @@
spin_lock_bh(&txq->lock);
while (q->write_ptr != q->read_ptr) {
+ IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
+ txq_id, q->read_ptr);
iwl_pcie_txq_free_tfd(trans, txq);
q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd);
}
+ txq->active = false;
spin_unlock_bh(&txq->lock);
+
+ /* just in case - this queue may have been stopped */
+ iwl_wake_queue(trans, txq);
}
/*
@@ -714,7 +720,12 @@
iwl_write_direct32(trans, FH_KW_MEM_ADDR_REG,
trans_pcie->kw.dma >> 4);
- iwl_pcie_tx_start(trans, trans_pcie->scd_base_addr);
+ /*
+ * Send 0 as the scd_base_addr since the device may have be reset
+ * while we were in WoWLAN in which case SCD_SRAM_BASE_ADDR will
+ * contain garbage.
+ */
+ iwl_pcie_tx_start(trans, 0);
}
/*
@@ -927,6 +938,12 @@
spin_lock_bh(&txq->lock);
+ if (!txq->active) {
+ IWL_DEBUG_TX_QUEUES(trans, "Q %d inactive - ignoring idx %d\n",
+ txq_id, ssn);
+ goto out;
+ }
+
if (txq->q.read_ptr == tfd_num)
goto out;
@@ -1103,6 +1120,7 @@
(fifo << SCD_QUEUE_STTS_REG_POS_TXF) |
(1 << SCD_QUEUE_STTS_REG_POS_WSL) |
SCD_QUEUE_STTS_REG_MSK);
+ trans_pcie->txq[txq_id].active = true;
IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d on FIFO %d WrPtr: %d\n",
txq_id, fifo, ssn & 0xff);
}
diff --git a/drivers/net/wireless/libertas/debugfs.c b/drivers/net/wireless/libertas/debugfs.c
index 668dd27..cc6a0a5 100644
--- a/drivers/net/wireless/libertas/debugfs.c
+++ b/drivers/net/wireless/libertas/debugfs.c
@@ -913,7 +913,10 @@
char *p2;
struct debug_data *d = f->private_data;
- pdata = kmalloc(cnt, GFP_KERNEL);
+ if (cnt == 0)
+ return 0;
+
+ pdata = kmalloc(cnt + 1, GFP_KERNEL);
if (pdata == NULL)
return 0;
@@ -922,6 +925,7 @@
kfree(pdata);
return 0;
}
+ pdata[cnt] = '\0';
p0 = pdata;
for (i = 0; i < num_of_items; i++) {
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index 5e0eec4..5d9a808 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -189,8 +189,7 @@
vht_cap->header.len =
cpu_to_le16(sizeof(struct ieee80211_vht_cap));
memcpy((u8 *)vht_cap + sizeof(struct mwifiex_ie_types_header),
- (u8 *)bss_desc->bcn_vht_cap +
- sizeof(struct ieee_types_header),
+ (u8 *)bss_desc->bcn_vht_cap,
le16_to_cpu(vht_cap->header.len));
mwifiex_fill_vht_cap_tlv(priv, vht_cap, bss_desc->bss_band);
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index 41e9d25..2658c8c 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -307,8 +307,7 @@
ht_cap->header.len =
cpu_to_le16(sizeof(struct ieee80211_ht_cap));
memcpy((u8 *) ht_cap + sizeof(struct mwifiex_ie_types_header),
- (u8 *) bss_desc->bcn_ht_cap +
- sizeof(struct ieee_types_header),
+ (u8 *)bss_desc->bcn_ht_cap,
le16_to_cpu(ht_cap->header.len));
mwifiex_fill_cap_info(priv, radio_type, ht_cap);
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.c b/drivers/net/wireless/mwifiex/11n_aggr.c
index a78e065..d69d024 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/mwifiex/11n_aggr.c
@@ -149,7 +149,7 @@
*/
int
mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
- struct mwifiex_ra_list_tbl *pra_list, int headroom,
+ struct mwifiex_ra_list_tbl *pra_list,
int ptrindex, unsigned long ra_list_flags)
__releases(&priv->wmm.ra_list_spinlock)
{
@@ -159,6 +159,7 @@
int pad = 0, ret;
struct mwifiex_tx_param tx_param;
struct txpd *ptx_pd = NULL;
+ int headroom = adapter->iface_type == MWIFIEX_USB ? 0 : INTF_HEADER_LEN;
skb_src = skb_peek(&pra_list->skb_head);
if (!skb_src) {
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.h b/drivers/net/wireless/mwifiex/11n_aggr.h
index 900e1c6..892098d 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.h
+++ b/drivers/net/wireless/mwifiex/11n_aggr.h
@@ -26,7 +26,7 @@
int mwifiex_11n_deaggregate_pkt(struct mwifiex_private *priv,
struct sk_buff *skb);
int mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
- struct mwifiex_ra_list_tbl *ptr, int headroom,
+ struct mwifiex_ra_list_tbl *ptr,
int ptr_index, unsigned long flags)
__releases(&priv->wmm.ra_list_spinlock);
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index e42b266..e7f7cdf 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1668,9 +1668,9 @@
struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
int ret;
- if (priv->bss_mode != NL80211_IFTYPE_STATION) {
+ if (GET_BSS_ROLE(priv) != MWIFIEX_BSS_ROLE_STA) {
wiphy_err(wiphy,
- "%s: reject infra assoc request in non-STA mode\n",
+ "%s: reject infra assoc request in non-STA role\n",
dev->name);
return -EINVAL;
}
diff --git a/drivers/net/wireless/mwifiex/cfp.c b/drivers/net/wireless/mwifiex/cfp.c
index 988552d..5178c46 100644
--- a/drivers/net/wireless/mwifiex/cfp.c
+++ b/drivers/net/wireless/mwifiex/cfp.c
@@ -415,7 +415,8 @@
u32 k = 0;
struct mwifiex_adapter *adapter = priv->adapter;
- if (priv->bss_mode == NL80211_IFTYPE_STATION) {
+ if (priv->bss_mode == NL80211_IFTYPE_STATION ||
+ priv->bss_mode == NL80211_IFTYPE_P2P_CLIENT) {
switch (adapter->config_bands) {
case BAND_B:
dev_dbg(adapter->dev, "info: infra band=%d "
diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c
index 26755d9..7a97f6c 100644
--- a/drivers/net/wireless/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/mwifiex/cmdevt.c
@@ -1154,7 +1154,7 @@
uint32_t conditions = le32_to_cpu(phs_cfg->params.hs_config.conditions);
if (phs_cfg->action == cpu_to_le16(HS_ACTIVATE) &&
- adapter->iface_type == MWIFIEX_SDIO) {
+ adapter->iface_type != MWIFIEX_USB) {
mwifiex_hs_activated_event(priv, true);
return 0;
} else {
@@ -1166,8 +1166,7 @@
}
if (conditions != HS_CFG_CANCEL) {
adapter->is_hs_configured = true;
- if (adapter->iface_type == MWIFIEX_USB ||
- adapter->iface_type == MWIFIEX_PCIE)
+ if (adapter->iface_type == MWIFIEX_USB)
mwifiex_hs_activated_event(priv, true);
} else {
adapter->is_hs_configured = false;
diff --git a/drivers/net/wireless/mwifiex/fw.h b/drivers/net/wireless/mwifiex/fw.h
index 1f7578d..5400a1e 100644
--- a/drivers/net/wireless/mwifiex/fw.h
+++ b/drivers/net/wireless/mwifiex/fw.h
@@ -228,7 +228,7 @@
/* HW_SPEC fw_cap_info */
-#define ISSUPP_11ACENABLED(fw_cap_info) (fw_cap_info & (BIT(13)|BIT(14)))
+#define ISSUPP_11ACENABLED(fw_cap_info) (fw_cap_info & (BIT(12)|BIT(13)))
#define GET_VHTCAP_CHWDSET(vht_cap_info) ((vht_cap_info >> 2) & 0x3)
#define GET_VHTNSSMCS(mcs_mapset, nss) ((mcs_mapset >> (2 * (nss - 1))) & 0x3)
diff --git a/drivers/net/wireless/mwifiex/join.c b/drivers/net/wireless/mwifiex/join.c
index 6bcb66e..96bda6c 100644
--- a/drivers/net/wireless/mwifiex/join.c
+++ b/drivers/net/wireless/mwifiex/join.c
@@ -1290,8 +1290,10 @@
{
u8 current_bssid[ETH_ALEN];
- /* Return error if the adapter or table entry is not marked as infra */
- if ((priv->bss_mode != NL80211_IFTYPE_STATION) ||
+ /* Return error if the adapter is not STA role or table entry
+ * is not marked as infra.
+ */
+ if ((GET_BSS_ROLE(priv) != MWIFIEX_BSS_ROLE_STA) ||
(bss_desc->bss_mode != NL80211_IFTYPE_STATION))
return -1;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 2eb88ea..83c6196 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -270,10 +270,12 @@
}
} while (true);
- if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter))
- goto process_start;
-
spin_lock_irqsave(&adapter->main_proc_lock, flags);
+ if ((adapter->int_status) || IS_CARD_RX_RCVD(adapter)) {
+ spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
+ goto process_start;
+ }
+
adapter->mwifiex_processing = false;
spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
@@ -363,20 +365,6 @@
dev_err(adapter->dev, "cannot create default STA interface\n");
goto err_add_intf;
}
-
- /* Create AP interface by default */
- if (!mwifiex_add_virtual_intf(adapter->wiphy, "uap%d",
- NL80211_IFTYPE_AP, NULL, NULL)) {
- dev_err(adapter->dev, "cannot create default AP interface\n");
- goto err_add_intf;
- }
-
- /* Create P2P interface by default */
- if (!mwifiex_add_virtual_intf(adapter->wiphy, "p2p%d",
- NL80211_IFTYPE_P2P_CLIENT, NULL, NULL)) {
- dev_err(adapter->dev, "cannot create default P2P interface\n");
- goto err_add_intf;
- }
rtnl_unlock();
mwifiex_drv_get_driver_version(adapter, fmt, sizeof(fmt) - 1);
@@ -513,6 +501,7 @@
}
tx_info = MWIFIEX_SKB_TXCB(skb);
+ memset(tx_info, 0, sizeof(*tx_info));
tx_info->bss_num = priv->bss_num;
tx_info->bss_type = priv->bss_type;
@@ -573,9 +562,8 @@
mcast_list.mode = MWIFIEX_ALL_MULTI_MODE;
} else {
mcast_list.mode = MWIFIEX_MULTICAST_MODE;
- if (netdev_mc_count(dev))
- mcast_list.num_multicast_addr =
- mwifiex_copy_mcast_addr(&mcast_list, dev);
+ mcast_list.num_multicast_addr =
+ mwifiex_copy_mcast_addr(&mcast_list, dev);
}
mwifiex_request_set_multicast_list(priv, &mcast_list);
}
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index 20c9c4c..801c709 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -1195,6 +1195,12 @@
rd_index = card->rxbd_rdptr & reg->rx_mask;
skb_data = card->rx_buf_list[rd_index];
+ /* If skb allocation was failed earlier for Rx packet,
+ * rx_buf_list[rd_index] would have been left with a NULL.
+ */
+ if (!skb_data)
+ return -ENOMEM;
+
MWIFIEX_SKB_PACB(skb_data, &buf_pa);
pci_unmap_single(card->dev, buf_pa, MWIFIEX_RX_DATA_BUF_SIZE,
PCI_DMA_FROMDEVICE);
@@ -1509,6 +1515,14 @@
if (adapter->ps_state == PS_STATE_SLEEP_CFM) {
mwifiex_process_sleep_confirm_resp(adapter, skb->data,
skb->len);
+ mwifiex_pcie_enable_host_int(adapter);
+ if (mwifiex_write_reg(adapter,
+ PCIE_CPU_INT_EVENT,
+ CPU_INTR_SLEEP_CFM_DONE)) {
+ dev_warn(adapter->dev,
+ "Write register failed\n");
+ return -1;
+ }
while (reg->sleep_cookie && (count++ < 10) &&
mwifiex_pcie_ok_to_access_hw(adapter))
usleep_range(50, 60);
@@ -1979,23 +1993,9 @@
adapter->int_status |= pcie_ireg;
spin_unlock_irqrestore(&adapter->int_lock, flags);
- if (pcie_ireg & HOST_INTR_CMD_DONE) {
- if ((adapter->ps_state == PS_STATE_SLEEP_CFM) ||
- (adapter->ps_state == PS_STATE_SLEEP)) {
- mwifiex_pcie_enable_host_int(adapter);
- if (mwifiex_write_reg(adapter,
- PCIE_CPU_INT_EVENT,
- CPU_INTR_SLEEP_CFM_DONE)
- ) {
- dev_warn(adapter->dev,
- "Write register failed\n");
- return;
-
- }
- }
- } else if (!adapter->pps_uapsd_mode &&
- adapter->ps_state == PS_STATE_SLEEP &&
- mwifiex_pcie_ok_to_access_hw(adapter)) {
+ if (!adapter->pps_uapsd_mode &&
+ adapter->ps_state == PS_STATE_SLEEP &&
+ mwifiex_pcie_ok_to_access_hw(adapter)) {
/* Potentially for PCIe we could get other
* interrupts like shared. Don't change power
* state until cookie is set */
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 9cf5d8f..470347a 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -1622,7 +1622,7 @@
const u8 *ie_buf;
size_t ie_len;
u16 channel = 0;
- u64 fw_tsf = 0;
+ __le64 fw_tsf = 0;
u16 beacon_size = 0;
u32 curr_bcn_bytes;
u32 freq;
@@ -1749,7 +1749,7 @@
ie_buf, ie_len, rssi, GFP_KERNEL);
bss_priv = (struct mwifiex_bss_priv *)bss->priv;
bss_priv->band = band;
- bss_priv->fw_tsf = fw_tsf;
+ bss_priv->fw_tsf = le64_to_cpu(fw_tsf);
if (priv->media_connected &&
!memcmp(bssid,
priv->curr_bss_params.bss_descriptor
@@ -2040,12 +2040,12 @@
curr_bss->ht_info_offset);
if (curr_bss->bcn_vht_cap)
- curr_bss->bcn_ht_cap = (void *)(curr_bss->beacon_buf +
- curr_bss->vht_cap_offset);
+ curr_bss->bcn_vht_cap = (void *)(curr_bss->beacon_buf +
+ curr_bss->vht_cap_offset);
if (curr_bss->bcn_vht_oper)
- curr_bss->bcn_ht_oper = (void *)(curr_bss->beacon_buf +
- curr_bss->vht_info_offset);
+ curr_bss->bcn_vht_oper = (void *)(curr_bss->beacon_buf +
+ curr_bss->vht_info_offset);
if (curr_bss->bcn_bss_co_2040)
curr_bss->bcn_bss_co_2040 =
diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c
index 363ba31..047a6f3 100644
--- a/drivers/net/wireless/mwifiex/sdio.c
+++ b/drivers/net/wireless/mwifiex/sdio.c
@@ -930,7 +930,10 @@
struct sk_buff *skb, u32 upld_typ)
{
u8 *cmd_buf;
+ __le16 *curr_ptr = (__le16 *)skb->data;
+ u16 pkt_len = le16_to_cpu(*curr_ptr);
+ skb_trim(skb, pkt_len);
skb_pull(skb, INTF_HEADER_LEN);
switch (upld_typ) {
@@ -1441,8 +1444,8 @@
/* Allocate buffer and copy payload */
blk_size = MWIFIEX_SDIO_BLOCK_SIZE;
buf_block_len = (pkt_len + blk_size - 1) / blk_size;
- *(u16 *) &payload[0] = (u16) pkt_len;
- *(u16 *) &payload[2] = type;
+ *(__le16 *)&payload[0] = cpu_to_le16((u16)pkt_len);
+ *(__le16 *)&payload[2] = cpu_to_le16(type);
/*
* This is SDIO specific header
diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c
index 1a8a19d..0a9f59c 100644
--- a/drivers/net/wireless/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/mwifiex/sta_ioctl.c
@@ -104,16 +104,14 @@
} else {
priv->curr_pkt_filter &=
~HostCmd_ACT_MAC_ALL_MULTICAST_ENABLE;
- if (mcast_list->num_multicast_addr) {
- dev_dbg(priv->adapter->dev,
- "info: Set multicast list=%d\n",
- mcast_list->num_multicast_addr);
- /* Send multicast addresses to firmware */
- ret = mwifiex_send_cmd_async(priv,
- HostCmd_CMD_MAC_MULTICAST_ADR,
- HostCmd_ACT_GEN_SET, 0,
- mcast_list);
- }
+ dev_dbg(priv->adapter->dev,
+ "info: Set multicast list=%d\n",
+ mcast_list->num_multicast_addr);
+ /* Send multicast addresses to firmware */
+ ret = mwifiex_send_cmd_async(priv,
+ HostCmd_CMD_MAC_MULTICAST_ADR,
+ HostCmd_ACT_GEN_SET, 0,
+ mcast_list);
}
}
dev_dbg(priv->adapter->dev,
@@ -311,8 +309,8 @@
if (bss_desc && bss_desc->ssid.ssid_len &&
(!mwifiex_ssid_cmp(&priv->curr_bss_params.bss_descriptor.
ssid, &bss_desc->ssid))) {
- kfree(bss_desc);
- return 0;
+ ret = 0;
+ goto done;
}
/* Exit Adhoc mode first */
diff --git a/drivers/net/wireless/mwifiex/uap_txrx.c b/drivers/net/wireless/mwifiex/uap_txrx.c
index a018e42..48e6724 100644
--- a/drivers/net/wireless/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/mwifiex/uap_txrx.c
@@ -34,6 +34,7 @@
struct mwifiex_txinfo *tx_info;
int hdr_chop;
struct timeval tv;
+ struct ethhdr *p_ethhdr;
u8 rfc1042_eth_hdr[ETH_ALEN] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 };
uap_rx_pd = (struct uap_rxpd *)(skb->data);
@@ -48,14 +49,36 @@
}
if (!memcmp(&rx_pkt_hdr->rfc1042_hdr,
- rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr)))
+ rfc1042_eth_hdr, sizeof(rfc1042_eth_hdr))) {
+ /* Replace the 803 header and rfc1042 header (llc/snap) with
+ * an Ethernet II header, keep the src/dst and snap_type
+ * (ethertype).
+ *
+ * The firmware only passes up SNAP frames converting all RX
+ * data from 802.11 to 802.2/LLC/SNAP frames.
+ *
+ * To create the Ethernet II, just move the src, dst address
+ * right before the snap_type.
+ */
+ p_ethhdr = (struct ethhdr *)
+ ((u8 *)(&rx_pkt_hdr->eth803_hdr)
+ + sizeof(rx_pkt_hdr->eth803_hdr)
+ + sizeof(rx_pkt_hdr->rfc1042_hdr)
+ - sizeof(rx_pkt_hdr->eth803_hdr.h_dest)
+ - sizeof(rx_pkt_hdr->eth803_hdr.h_source)
+ - sizeof(rx_pkt_hdr->rfc1042_hdr.snap_type));
+ memcpy(p_ethhdr->h_source, rx_pkt_hdr->eth803_hdr.h_source,
+ sizeof(p_ethhdr->h_source));
+ memcpy(p_ethhdr->h_dest, rx_pkt_hdr->eth803_hdr.h_dest,
+ sizeof(p_ethhdr->h_dest));
/* Chop off the rxpd + the excess memory from
* 802.2/llc/snap header that was removed.
*/
- hdr_chop = (u8 *)eth_hdr - (u8 *)uap_rx_pd;
- else
+ hdr_chop = (u8 *)p_ethhdr - (u8 *)uap_rx_pd;
+ } else {
/* Chop off the rxpd */
hdr_chop = (u8 *)&rx_pkt_hdr->eth803_hdr - (u8 *)uap_rx_pd;
+ }
/* Chop off the leading header bytes so the it points
* to the start of either the reconstructed EthII frame
diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c
index f90fe21..923e348 100644
--- a/drivers/net/wireless/mwifiex/usb.c
+++ b/drivers/net/wireless/mwifiex/usb.c
@@ -446,9 +446,6 @@
*/
adapter->is_suspended = true;
- for (i = 0; i < adapter->priv_num; i++)
- netif_carrier_off(adapter->priv[i]->netdev);
-
if (atomic_read(&card->rx_cmd_urb_pending) && card->rx_cmd.urb)
usb_kill_urb(card->rx_cmd.urb);
@@ -508,23 +505,12 @@
MWIFIEX_RX_CMD_BUF_SIZE);
}
- for (i = 0; i < adapter->priv_num; i++)
- if (adapter->priv[i]->media_connected)
- netif_carrier_on(adapter->priv[i]->netdev);
-
/* Disable Host Sleep */
if (adapter->hs_activated)
mwifiex_cancel_hs(mwifiex_get_priv(adapter,
MWIFIEX_BSS_ROLE_ANY),
MWIFIEX_ASYNC_CMD);
-#ifdef CONFIG_PM
- /* Resume handler may be called due to remote wakeup,
- * force to exit suspend anyway
- */
- usb_disable_autosuspend(card->udev);
-#endif /* CONFIG_PM */
-
return 0;
}
@@ -583,7 +569,6 @@
.id_table = mwifiex_usb_table,
.suspend = mwifiex_usb_suspend,
.resume = mwifiex_usb_resume,
- .supports_autosuspend = 1,
};
static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter)
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 4be3d33..80f72f6 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -556,7 +556,8 @@
mwifiex_wmm_delete_all_ralist(priv);
memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
- if (priv->adapter->if_ops.clean_pcie_ring)
+ if (priv->adapter->if_ops.clean_pcie_ring &&
+ !priv->adapter->surprise_removed)
priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
}
@@ -1236,8 +1237,7 @@
if (mwifiex_is_amsdu_allowed(priv, tid) &&
mwifiex_is_11n_aggragation_possible(priv, ptr,
adapter->tx_buf_size))
- mwifiex_11n_aggregate_pkt(priv, ptr, INTF_HEADER_LEN,
- ptr_index, flags);
+ mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index, flags);
/* ra_list_spinlock has been freed in
mwifiex_11n_aggregate_pkt() */
else
diff --git a/drivers/net/wireless/p54/p54usb.c b/drivers/net/wireless/p54/p54usb.c
index b9deef6..f42dc3c 100644
--- a/drivers/net/wireless/p54/p54usb.c
+++ b/drivers/net/wireless/p54/p54usb.c
@@ -83,6 +83,7 @@
{USB_DEVICE(0x06a9, 0x000e)}, /* Westell 802.11g USB (A90-211WG-01) */
{USB_DEVICE(0x06b9, 0x0121)}, /* Thomson SpeedTouch 121g */
{USB_DEVICE(0x0707, 0xee13)}, /* SMC 2862W-G version 2 */
+ {USB_DEVICE(0x07aa, 0x0020)}, /* Corega WLUSB2GTST USB */
{USB_DEVICE(0x0803, 0x4310)}, /* Zoom 4410a */
{USB_DEVICE(0x083a, 0x4521)}, /* Siemens Gigaset USB Adapter 54 version 2 */
{USB_DEVICE(0x083a, 0x4531)}, /* T-Com Sinus 154 data II */
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index f95de0d..1de59b0 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -587,7 +587,7 @@
chan = priv->curchan;
if (chan) {
struct survey_info *survey = &priv->survey[chan->hw_value];
- survey->noise = clamp_t(s8, priv->noise, -128, 127);
+ survey->noise = clamp(priv->noise, -128, 127);
survey->channel_time = priv->survey_raw.active;
survey->channel_time_tx = priv->survey_raw.tx;
survey->channel_time_busy = priv->survey_raw.tx +
diff --git a/drivers/net/wireless/prism54/islpci_dev.c b/drivers/net/wireless/prism54/islpci_dev.c
index 5970ff6..d498b02 100644
--- a/drivers/net/wireless/prism54/islpci_dev.c
+++ b/drivers/net/wireless/prism54/islpci_dev.c
@@ -811,6 +811,10 @@
.ndo_validate_addr = eth_validate_addr,
};
+static struct device_type wlan_type = {
+ .name = "wlan",
+};
+
struct net_device *
islpci_setup(struct pci_dev *pdev)
{
@@ -821,9 +825,8 @@
return ndev;
pci_set_drvdata(pdev, ndev);
-#if defined(SET_NETDEV_DEV)
SET_NETDEV_DEV(ndev, &pdev->dev);
-#endif
+ SET_NETDEV_DEVTYPE(ndev, &wlan_type);
/* setup the structure members */
ndev->base_addr = pci_resource_start(pdev, 0);
diff --git a/drivers/net/wireless/rt2x00/rt2400pci.c b/drivers/net/wireless/rt2x00/rt2400pci.c
index f714373..a3a2dcd 100644
--- a/drivers/net/wireless/rt2x00/rt2400pci.c
+++ b/drivers/net/wireless/rt2x00/rt2400pci.c
@@ -1261,7 +1261,7 @@
*/
rxdesc->timestamp = ((u64)rx_high << 32) | rx_low;
rxdesc->signal = rt2x00_get_field32(word2, RXD_W2_SIGNAL) & ~0x08;
- rxdesc->rssi = rt2x00_get_field32(word2, RXD_W3_RSSI) -
+ rxdesc->rssi = rt2x00_get_field32(word3, RXD_W3_RSSI) -
entry->queue->rt2x00dev->rssi_offset;
rxdesc->size = rt2x00_get_field32(word0, RXD_W0_DATABYTE_COUNT);
diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index 77e45b2..d582feb 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1684,8 +1684,13 @@
/*
* Detect if this device has an hardware controlled radio.
*/
- if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO))
+ if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) {
__set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags);
+ /*
+ * On this device RFKILL initialized during probe does not work.
+ */
+ __set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags);
+ }
/*
* Check if the BBP tuning should be enabled.
diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h
index a7630d5..a629313 100644
--- a/drivers/net/wireless/rt2x00/rt2800.h
+++ b/drivers/net/wireless/rt2x00/rt2800.h
@@ -1920,7 +1920,7 @@
* 2 - drop tx power by 12dBm,
* 3 - increase tx power by 6dBm
*/
-#define BBP1_TX_POWER_CTRL FIELD8(0x07)
+#define BBP1_TX_POWER_CTRL FIELD8(0x03)
#define BBP1_TX_ANTENNA FIELD8(0x18)
/*
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 72f32e5..12652d2 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -2392,7 +2392,7 @@
rt2800_rfcsr_write(rt2x00dev, 49, rfcsr);
rt2800_rfcsr_read(rt2x00dev, 50, &rfcsr);
- if (info->default_power1 > power_bound)
+ if (info->default_power2 > power_bound)
rt2x00_set_field8(&rfcsr, RFCSR50_TX, power_bound);
else
rt2x00_set_field8(&rfcsr, RFCSR50_TX, info->default_power2);
@@ -2767,6 +2767,13 @@
int i;
/*
+ * First check if temperature compensation is supported.
+ */
+ rt2x00_eeprom_read(rt2x00dev, EEPROM_NIC_CONF1, &eeprom);
+ if (!rt2x00_get_field16(eeprom, EEPROM_NIC_CONF1_EXTERNAL_TX_ALC))
+ return 0;
+
+ /*
* Read TSSI boundaries for temperature compensation from
* the EEPROM.
*
@@ -3393,10 +3400,13 @@
vgc = rt2800_get_default_vgc(rt2x00dev);
- if (rt2x00_rt(rt2x00dev, RT5592) && qual->rssi > -65)
- vgc += 0x20;
- else if (qual->rssi > -80)
- vgc += 0x10;
+ if (rt2x00_rt(rt2x00dev, RT5592)) {
+ if (qual->rssi > -65)
+ vgc += 0x20;
+ } else {
+ if (qual->rssi > -80)
+ vgc += 0x10;
+ }
rt2800_set_vgc(rt2x00dev, qual, vgc);
}
@@ -4041,10 +4051,6 @@
u8 reg_id;
u8 value;
- if (unlikely(rt2800_wait_bbp_rf_ready(rt2x00dev) ||
- rt2800_wait_bbp_ready(rt2x00dev)))
- return -EACCES;
-
if (rt2x00_rt(rt2x00dev, RT5592)) {
rt2800_init_bbp_5592(rt2x00dev);
return 0;
@@ -5185,20 +5191,23 @@
rt2800_init_registers(rt2x00dev)))
return -EIO;
+ if (unlikely(rt2800_wait_bbp_rf_ready(rt2x00dev)))
+ return -EIO;
+
/*
* Send signal to firmware during boot time.
*/
rt2800_register_write(rt2x00dev, H2M_BBP_AGENT, 0);
rt2800_register_write(rt2x00dev, H2M_MAILBOX_CSR, 0);
- if (rt2x00_is_usb(rt2x00dev)) {
+ if (rt2x00_is_usb(rt2x00dev))
rt2800_register_write(rt2x00dev, H2M_INT_SRC, 0);
- rt2800_mcu_request(rt2x00dev, MCU_BOOT_SIGNAL, 0, 0, 0);
- }
+ rt2800_mcu_request(rt2x00dev, MCU_BOOT_SIGNAL, 0, 0, 0);
msleep(1);
- if (unlikely(rt2800_init_bbp(rt2x00dev)))
+ if (unlikely(rt2800_wait_bbp_ready(rt2x00dev)))
return -EIO;
+ rt2800_init_bbp(rt2x00dev);
rt2800_init_rfcsr(rt2x00dev);
if (rt2x00_is_usb(rt2x00dev) &&
@@ -5912,7 +5921,8 @@
IEEE80211_HW_SUPPORTS_PS |
IEEE80211_HW_PS_NULLFUNC_STACK |
IEEE80211_HW_AMPDU_AGGREGATION |
- IEEE80211_HW_REPORTS_TX_ACK_STATUS;
+ IEEE80211_HW_REPORTS_TX_ACK_STATUS |
+ IEEE80211_HW_SUPPORTS_HT_CCK_RATES;
/*
* Don't set IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING for USB devices
@@ -6056,8 +6066,8 @@
default_power2 = rt2x00_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_A2);
for (i = 14; i < spec->num_channels; i++) {
- info[i].default_power1 = default_power1[i];
- info[i].default_power2 = default_power2[i];
+ info[i].default_power1 = default_power1[i - 14];
+ info[i].default_power2 = default_power2[i - 14];
}
}
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index ac854d7..400b867 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -148,6 +148,8 @@
return false;
}
+#define TXSTATUS_READ_INTERVAL 1000000
+
static bool rt2800usb_tx_sta_fifo_read_completed(struct rt2x00_dev *rt2x00dev,
int urb_status, u32 tx_status)
{
@@ -176,8 +178,9 @@
queue_work(rt2x00dev->workqueue, &rt2x00dev->txdone_work);
if (rt2800usb_txstatus_pending(rt2x00dev)) {
- /* Read register after 250 us */
- hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 250000),
+ /* Read register after 1 ms */
+ hrtimer_start(&rt2x00dev->txstatus_timer,
+ ktime_set(0, TXSTATUS_READ_INTERVAL),
HRTIMER_MODE_REL);
return false;
}
@@ -202,8 +205,9 @@
if (test_and_set_bit(TX_STATUS_READING, &rt2x00dev->flags))
return;
- /* Read TX_STA_FIFO register after 500 us */
- hrtimer_start(&rt2x00dev->txstatus_timer, ktime_set(0, 500000),
+ /* Read TX_STA_FIFO register after 2 ms */
+ hrtimer_start(&rt2x00dev->txstatus_timer,
+ ktime_set(0, 2*TXSTATUS_READ_INTERVAL),
HRTIMER_MODE_REL);
}
@@ -1087,6 +1091,7 @@
/* Ovislink */
{ USB_DEVICE(0x1b75, 0x3071) },
{ USB_DEVICE(0x1b75, 0x3072) },
+ { USB_DEVICE(0x1b75, 0xa200) },
/* Para */
{ USB_DEVICE(0x20b8, 0x8888) },
/* Pegatron */
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index 7510723..1e716ff 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -708,6 +708,7 @@
REQUIRE_SW_SEQNO,
REQUIRE_HT_TX_DESC,
REQUIRE_PS_AUTOWAKE,
+ REQUIRE_DELAYED_RFKILL,
/*
* Capabilities
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 90dc143..e22942b 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -181,6 +181,7 @@
static void rt2x00lib_bc_buffer_iter(void *data, u8 *mac,
struct ieee80211_vif *vif)
{
+ struct ieee80211_tx_control control = {};
struct rt2x00_dev *rt2x00dev = data;
struct sk_buff *skb;
@@ -195,7 +196,7 @@
*/
skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
while (skb) {
- rt2x00mac_tx(rt2x00dev->hw, NULL, skb);
+ rt2x00mac_tx(rt2x00dev->hw, &control, skb);
skb = ieee80211_get_buffered_bc(rt2x00dev->hw, vif);
}
}
@@ -1127,9 +1128,10 @@
return;
/*
- * Unregister extra components.
+ * Stop rfkill polling.
*/
- rt2x00rfkill_unregister(rt2x00dev);
+ if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+ rt2x00rfkill_unregister(rt2x00dev);
/*
* Allow the HW to uninitialize.
@@ -1167,6 +1169,12 @@
set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags);
+ /*
+ * Start rfkill polling.
+ */
+ if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+ rt2x00rfkill_register(rt2x00dev);
+
return 0;
}
@@ -1362,7 +1370,12 @@
rt2x00link_register(rt2x00dev);
rt2x00leds_register(rt2x00dev);
rt2x00debug_register(rt2x00dev);
- rt2x00rfkill_register(rt2x00dev);
+
+ /*
+ * Start rfkill polling.
+ */
+ if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+ rt2x00rfkill_register(rt2x00dev);
return 0;
@@ -1378,6 +1391,12 @@
clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
/*
+ * Stop rfkill polling.
+ */
+ if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+ rt2x00rfkill_unregister(rt2x00dev);
+
+ /*
* Disable radio.
*/
rt2x00lib_disable_radio(rt2x00dev);
diff --git a/drivers/net/wireless/rt2x00/rt2x00lib.h b/drivers/net/wireless/rt2x00/rt2x00lib.h
index a093598..7f40ab8 100644
--- a/drivers/net/wireless/rt2x00/rt2x00lib.h
+++ b/drivers/net/wireless/rt2x00/rt2x00lib.h
@@ -146,7 +146,7 @@
* @local: frame is not from mac80211
*/
int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
- bool local);
+ struct ieee80211_sta *sta, bool local);
/**
* rt2x00queue_update_beacon - Send new beacon from mac80211
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index f883802..c03748d 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -90,7 +90,7 @@
frag_skb->data, data_length, tx_info,
(struct ieee80211_rts *)(skb->data));
- retval = rt2x00queue_write_tx_frame(queue, skb, true);
+ retval = rt2x00queue_write_tx_frame(queue, skb, NULL, true);
if (retval) {
dev_kfree_skb_any(skb);
rt2x00_warn(rt2x00dev, "Failed to send RTS/CTS frame\n");
@@ -151,7 +151,7 @@
goto exit_fail;
}
- if (unlikely(rt2x00queue_write_tx_frame(queue, skb, false)))
+ if (unlikely(rt2x00queue_write_tx_frame(queue, skb, control->sta, false)))
goto exit_fail;
/*
@@ -489,6 +489,8 @@
crypto.cipher = rt2x00crypto_key_to_cipher(key);
if (crypto.cipher == CIPHER_NONE)
return -EOPNOTSUPP;
+ if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev))
+ return -EOPNOTSUPP;
crypto.cmd = cmd;
@@ -623,20 +625,18 @@
bss_conf->bssid);
/*
- * Update the beacon. This is only required on USB devices. PCI
- * devices fetch beacons periodically.
- */
- if (changes & BSS_CHANGED_BEACON && rt2x00_is_usb(rt2x00dev))
- rt2x00queue_update_beacon(rt2x00dev, vif);
-
- /*
* Start/stop beaconing.
*/
if (changes & BSS_CHANGED_BEACON_ENABLED) {
if (!bss_conf->enable_beacon && intf->enable_beacon) {
- rt2x00queue_clear_beacon(rt2x00dev, vif);
rt2x00dev->intf_beaconing--;
intf->enable_beacon = false;
+ /*
+ * Clear beacon in the H/W for this vif. This is needed
+ * to disable beaconing on this particular interface
+ * and keep it running on other interfaces.
+ */
+ rt2x00queue_clear_beacon(rt2x00dev, vif);
if (rt2x00dev->intf_beaconing == 0) {
/*
@@ -647,11 +647,15 @@
rt2x00queue_stop_queue(rt2x00dev->bcn);
mutex_unlock(&intf->beacon_skb_mutex);
}
-
-
} else if (bss_conf->enable_beacon && !intf->enable_beacon) {
rt2x00dev->intf_beaconing++;
intf->enable_beacon = true;
+ /*
+ * Upload beacon to the H/W. This is only required on
+ * USB devices. PCI devices fetch beacons periodically.
+ */
+ if (rt2x00_is_usb(rt2x00dev))
+ rt2x00queue_update_beacon(rt2x00dev, vif);
if (rt2x00dev->intf_beaconing == 1) {
/*
@@ -754,6 +758,9 @@
struct rt2x00_dev *rt2x00dev = hw->priv;
struct data_queue *queue;
+ if (!test_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags))
+ return;
+
tx_queue_for_each(rt2x00dev, queue)
rt2x00queue_flush_queue(queue, drop);
}
diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c
index 2c12311..5be4eee 100644
--- a/drivers/net/wireless/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/rt2x00/rt2x00queue.c
@@ -160,55 +160,29 @@
skb_trim(skb, frame_length);
}
-void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int header_length)
+/*
+ * H/W needs L2 padding between the header and the paylod if header size
+ * is not 4 bytes aligned.
+ */
+void rt2x00queue_insert_l2pad(struct sk_buff *skb, unsigned int hdr_len)
{
- unsigned int payload_length = skb->len - header_length;
- unsigned int header_align = ALIGN_SIZE(skb, 0);
- unsigned int payload_align = ALIGN_SIZE(skb, header_length);
- unsigned int l2pad = payload_length ? L2PAD_SIZE(header_length) : 0;
-
- /*
- * Adjust the header alignment if the payload needs to be moved more
- * than the header.
- */
- if (payload_align > header_align)
- header_align += 4;
-
- /* There is nothing to do if no alignment is needed */
- if (!header_align)
- return;
-
- /* Reserve the amount of space needed in front of the frame */
- skb_push(skb, header_align);
-
- /*
- * Move the header.
- */
- memmove(skb->data, skb->data + header_align, header_length);
-
- /* Move the payload, if present and if required */
- if (payload_length && payload_align)
- memmove(skb->data + header_length + l2pad,
- skb->data + header_length + l2pad + payload_align,
- payload_length);
-
- /* Trim the skb to the correct size */
- skb_trim(skb, header_length + l2pad + payload_length);
-}
-
-void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int header_length)
-{
- /*
- * L2 padding is only present if the skb contains more than just the
- * IEEE 802.11 header.
- */
- unsigned int l2pad = (skb->len > header_length) ?
- L2PAD_SIZE(header_length) : 0;
+ unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
if (!l2pad)
return;
- memmove(skb->data + l2pad, skb->data, header_length);
+ skb_push(skb, l2pad);
+ memmove(skb->data, skb->data + l2pad, hdr_len);
+}
+
+void rt2x00queue_remove_l2pad(struct sk_buff *skb, unsigned int hdr_len)
+{
+ unsigned int l2pad = (skb->len > hdr_len) ? L2PAD_SIZE(hdr_len) : 0;
+
+ if (!l2pad)
+ return;
+
+ memmove(skb->data + l2pad, skb->data, hdr_len);
skb_pull(skb, l2pad);
}
@@ -635,7 +609,7 @@
}
int rt2x00queue_write_tx_frame(struct data_queue *queue, struct sk_buff *skb,
- bool local)
+ struct ieee80211_sta *sta, bool local)
{
struct ieee80211_tx_info *tx_info;
struct queue_entry *entry;
@@ -649,7 +623,7 @@
* after that we are free to use the skb->cb array
* for our information.
*/
- rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, NULL);
+ rt2x00queue_create_tx_descriptor(queue->rt2x00dev, skb, &txdesc, sta);
/*
* All information is retrieved from the skb->cb array,
@@ -936,13 +910,8 @@
spin_unlock_irqrestore(&queue->index_lock, irqflags);
}
-void rt2x00queue_pause_queue(struct data_queue *queue)
+void rt2x00queue_pause_queue_nocheck(struct data_queue *queue)
{
- if (!test_bit(DEVICE_STATE_PRESENT, &queue->rt2x00dev->flags) ||
- !test_bit(QUEUE_STARTED, &queue->flags) ||
- test_and_set_bit(QUEUE_PAUSED, &queue->flags))
- return;
-
switch (queue->qid) {
case QID_AC_VO:
case QID_AC_VI:
@@ -958,6 +927,15 @@
break;
}
}
+void rt2x00queue_pause_queue(struct data_queue *queue)
+{
+ if (!test_bit(DEVICE_STATE_PRESENT, &queue->rt2x00dev->flags) ||
+ !test_bit(QUEUE_STARTED, &queue->flags) ||
+ test_and_set_bit(QUEUE_PAUSED, &queue->flags))
+ return;
+
+ rt2x00queue_pause_queue_nocheck(queue);
+}
EXPORT_SYMBOL_GPL(rt2x00queue_pause_queue);
void rt2x00queue_unpause_queue(struct data_queue *queue)
@@ -1019,7 +997,7 @@
return;
}
- rt2x00queue_pause_queue(queue);
+ rt2x00queue_pause_queue_nocheck(queue);
queue->rt2x00dev->ops->lib->stop_queue(queue);
diff --git a/drivers/net/wireless/rt2x00/rt61pci.c b/drivers/net/wireless/rt2x00/rt61pci.c
index 0dc8180..883a54c 100644
--- a/drivers/net/wireless/rt2x00/rt61pci.c
+++ b/drivers/net/wireless/rt2x00/rt61pci.c
@@ -2825,7 +2825,8 @@
tx_power = rt2x00_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_A_START);
for (i = 14; i < spec->num_channels; i++) {
info[i].max_power = MAX_TXPOWER;
- info[i].default_power1 = TXPOWER_FROM_DEV(tx_power[i]);
+ info[i].default_power1 =
+ TXPOWER_FROM_DEV(tx_power[i - 14]);
}
}
diff --git a/drivers/net/wireless/rt2x00/rt73usb.c b/drivers/net/wireless/rt2x00/rt73usb.c
index 377e09b..2bbca18 100644
--- a/drivers/net/wireless/rt2x00/rt73usb.c
+++ b/drivers/net/wireless/rt2x00/rt73usb.c
@@ -2167,7 +2167,8 @@
tx_power = rt2x00_eeprom_addr(rt2x00dev, EEPROM_TXPOWER_A_START);
for (i = 14; i < spec->num_channels; i++) {
info[i].max_power = MAX_TXPOWER;
- info[i].default_power1 = TXPOWER_FROM_DEV(tx_power[i]);
+ info[i].default_power1 =
+ TXPOWER_FROM_DEV(tx_power[i - 14]);
}
}
diff --git a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
index e19a20a..ecd1ac4 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
+++ b/drivers/net/wireless/rtl818x/rtl8187/rtl8187.h
@@ -15,6 +15,8 @@
#ifndef RTL8187_H
#define RTL8187_H
+#include <linux/cache.h>
+
#include "rtl818x.h"
#include "leds.h"
@@ -139,7 +141,10 @@
u8 aifsn[4];
u8 rfkill_mask;
struct {
- __le64 buf;
+ union {
+ __le64 buf;
+ u8 dummy1[L1_CACHE_BYTES];
+ } ____cacheline_aligned;
struct sk_buff_head queue;
} b_tx_status; /* This queue is used by both -b and non-b devices */
struct mutex io_mutex;
@@ -147,7 +152,8 @@
u8 bits8;
__le16 bits16;
__le32 bits32;
- } *io_dmabuf;
+ u8 dummy2[L1_CACHE_BYTES];
+ } *io_dmabuf ____cacheline_aligned;
bool rfkill_off;
u16 seqno;
};
diff --git a/drivers/net/wireless/rtlwifi/base.c b/drivers/net/wireless/rtlwifi/base.c
index af59dd5..6fc0853 100644
--- a/drivers/net/wireless/rtlwifi/base.c
+++ b/drivers/net/wireless/rtlwifi/base.c
@@ -37,6 +37,7 @@
#include <linux/ip.h>
#include <linux/module.h>
+#include <linux/udp.h>
/*
*NOTICE!!!: This file will be very big, we should
@@ -1066,64 +1067,52 @@
if (!ieee80211_is_data(fc))
return false;
+ ip = (const struct iphdr *)(skb->data + mac_hdr_len +
+ SNAP_SIZE + PROTOC_TYPE_SIZE);
+ ether_type = be16_to_cpup((__be16 *)
+ (skb->data + mac_hdr_len + SNAP_SIZE));
- ip = (struct iphdr *)((u8 *) skb->data + mac_hdr_len +
- SNAP_SIZE + PROTOC_TYPE_SIZE);
- ether_type = *(u16 *) ((u8 *) skb->data + mac_hdr_len + SNAP_SIZE);
- /* ether_type = ntohs(ether_type); */
+ switch (ether_type) {
+ case ETH_P_IP: {
+ struct udphdr *udp;
+ u16 src;
+ u16 dst;
- if (ETH_P_IP == ether_type) {
- if (IPPROTO_UDP == ip->protocol) {
- struct udphdr *udp = (struct udphdr *)((u8 *) ip +
- (ip->ihl << 2));
- if (((((u8 *) udp)[1] == 68) &&
- (((u8 *) udp)[3] == 67)) ||
- ((((u8 *) udp)[1] == 67) &&
- (((u8 *) udp)[3] == 68))) {
- /*
- * 68 : UDP BOOTP client
- * 67 : UDP BOOTP server
- */
- RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV),
- DBG_DMESG, "dhcp %s !!\n",
- is_tx ? "Tx" : "Rx");
+ if (ip->protocol != IPPROTO_UDP)
+ return false;
+ udp = (struct udphdr *)((u8 *)ip + (ip->ihl << 2));
+ src = be16_to_cpu(udp->source);
+ dst = be16_to_cpu(udp->dest);
- if (is_tx) {
- rtlpriv->enter_ps = false;
- schedule_work(&rtlpriv->
- works.lps_change_work);
- ppsc->last_delaylps_stamp_jiffies =
- jiffies;
- }
+ /* If this case involves port 68 (UDP BOOTP client) connecting
+ * with port 67 (UDP BOOTP server), then return true so that
+ * the lowest speed is used.
+ */
+ if (!((src == 68 && dst == 67) || (src == 67 && dst == 68)))
+ return false;
- return true;
- }
- }
- } else if (ETH_P_ARP == ether_type) {
- if (is_tx) {
- rtlpriv->enter_ps = false;
- schedule_work(&rtlpriv->works.lps_change_work);
- ppsc->last_delaylps_stamp_jiffies = jiffies;
- }
-
- return true;
- } else if (ETH_P_PAE == ether_type) {
+ RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
+ "dhcp %s !!\n", is_tx ? "Tx" : "Rx");
+ break;
+ }
+ case ETH_P_ARP:
+ break;
+ case ETH_P_PAE:
RT_TRACE(rtlpriv, (COMP_SEND | COMP_RECV), DBG_DMESG,
"802.1X %s EAPOL pkt!!\n", is_tx ? "Tx" : "Rx");
-
- if (is_tx) {
- rtlpriv->enter_ps = false;
- schedule_work(&rtlpriv->works.lps_change_work);
- ppsc->last_delaylps_stamp_jiffies = jiffies;
- }
-
- return true;
- } else if (ETH_P_IPV6 == ether_type) {
- /* IPv6 */
- return true;
+ break;
+ case ETH_P_IPV6:
+ /* TODO: Is this right? */
+ return false;
+ default:
+ return false;
}
-
- return false;
+ if (is_tx) {
+ rtlpriv->enter_ps = false;
+ schedule_work(&rtlpriv->works.lps_change_work);
+ ppsc->last_delaylps_stamp_jiffies = jiffies;
+ }
+ return true;
}
/*********************************************************
@@ -1438,7 +1427,8 @@
/* if we can't recv beacon for 6s, we should
* reconnect this AP
*/
- if (rtlpriv->link_info.roam_times >= 3) {
+ if ((rtlpriv->link_info.roam_times >= 3) &&
+ !is_zero_ether_addr(rtlpriv->mac80211.bssid)) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
"AP off, try to reconnect now\n");
rtlpriv->link_info.roam_times = 0;
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index ee84844..e230197 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -46,10 +46,20 @@
"Firmware callback routine entered!\n");
complete(&rtlpriv->firmware_loading_complete);
if (!firmware) {
+ if (rtlpriv->cfg->alt_fw_name) {
+ err = request_firmware(&firmware,
+ rtlpriv->cfg->alt_fw_name,
+ rtlpriv->io.dev);
+ pr_info("Loading alternative firmware %s\n",
+ rtlpriv->cfg->alt_fw_name);
+ if (!err)
+ goto found_alt;
+ }
pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name);
rtlpriv->max_fw_size = 0;
return;
}
+found_alt:
if (firmware->size > rtlpriv->max_fw_size) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG,
"Firmware is too big!\n");
@@ -184,6 +194,7 @@
rtlpriv->cfg->maps
[RTL_IBSS_INT_MASKS]);
}
+ mac->link_state = MAC80211_LINKED;
break;
case NL80211_IFTYPE_ADHOC:
RT_TRACE(rtlpriv, COMP_MAC80211, DBG_LOUD,
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index c97e9d3..ee6a626 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -734,6 +734,8 @@
};
int index = rtlpci->rx_ring[rx_queue_idx].idx;
+ if (rtlpci->driver_is_goingto_unload)
+ return;
/*RX NORMAL PKT */
while (count--) {
/*rx descriptor */
@@ -1008,19 +1010,6 @@
return;
}
-static void rtl_lps_change_work_callback(struct work_struct *work)
-{
- struct rtl_works *rtlworks =
- container_of(work, struct rtl_works, lps_change_work);
- struct ieee80211_hw *hw = rtlworks->hw;
- struct rtl_priv *rtlpriv = rtl_priv(hw);
-
- if (rtlpriv->enter_ps)
- rtl_lps_enter(hw);
- else
- rtl_lps_leave(hw);
-}
-
static void _rtl_pci_init_trx_var(struct ieee80211_hw *hw)
{
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
@@ -1643,6 +1632,7 @@
*/
set_hal_stop(rtlhal);
+ rtlpci->driver_is_goingto_unload = true;
rtlpriv->cfg->ops->disable_interrupt(hw);
cancel_work_sync(&rtlpriv->works.lps_change_work);
@@ -1660,7 +1650,6 @@
ppsc->rfchange_inprogress = true;
spin_unlock_irqrestore(&rtlpriv->locks.rf_ps_lock, flags);
- rtlpci->driver_is_goingto_unload = true;
rtlpriv->cfg->ops->hw_disable(hw);
/* some things are not needed if firmware not available */
if (!rtlpriv->max_fw_size)
diff --git a/drivers/net/wireless/rtlwifi/ps.c b/drivers/net/wireless/rtlwifi/ps.c
index 884bcea..ace1a08 100644
--- a/drivers/net/wireless/rtlwifi/ps.c
+++ b/drivers/net/wireless/rtlwifi/ps.c
@@ -48,7 +48,7 @@
/*<2> Enable Adapter */
if (rtlpriv->cfg->ops->hw_init(hw))
- return 1;
+ return false;
RT_CLEAR_PS_LEVEL(ppsc, RT_RF_OFF_LEVL_HALT_NIC);
/*<3> Enable Interrupt */
@@ -611,6 +611,18 @@
MSECS(sleep_intv * mac->vif->bss_conf.beacon_int - 40));
}
+void rtl_lps_change_work_callback(struct work_struct *work)
+{
+ struct rtl_works *rtlworks =
+ container_of(work, struct rtl_works, lps_change_work);
+ struct ieee80211_hw *hw = rtlworks->hw;
+ struct rtl_priv *rtlpriv = rtl_priv(hw);
+
+ if (rtlpriv->enter_ps)
+ rtl_lps_enter(hw);
+ else
+ rtl_lps_leave(hw);
+}
void rtl_swlps_wq_callback(void *data)
{
diff --git a/drivers/net/wireless/rtlwifi/ps.h b/drivers/net/wireless/rtlwifi/ps.h
index 4d682b7..88bd76e 100644
--- a/drivers/net/wireless/rtlwifi/ps.h
+++ b/drivers/net/wireless/rtlwifi/ps.h
@@ -49,5 +49,6 @@
void rtl_swlps_rf_sleep(struct ieee80211_hw *hw);
void rtl_p2p_ps_cmd(struct ieee80211_hw *hw, u8 p2p_ps_state);
void rtl_p2p_info(struct ieee80211_hw *hw, void *data, unsigned int len);
+void rtl_lps_change_work_callback(struct work_struct *work);
#endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c b/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
index 21a5cf0..a6184b6 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/dm.c
@@ -1078,7 +1078,7 @@
rtldm->swing_flag_ofdm = true;
}
- if (rtldm->swing_idx_cck != rtldm->swing_idx_cck) {
+ if (rtldm->swing_idx_cck_cur != rtldm->swing_idx_cck) {
rtldm->swing_idx_cck_cur = rtldm->swing_idx_cck;
rtldm->swing_flag_cck = true;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index b68cae3..f923d8c 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -143,6 +143,7 @@
} else {
rtlhal->fw_clk_change_in_progress = false;
spin_unlock_bh(&rtlpriv->locks.fw_ps_lock);
+ break;
}
}
@@ -1024,9 +1025,20 @@
bool rtstatus = true;
int err = 0;
u8 tmp_u1b, u1byte;
+ unsigned long flags;
RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Rtl8188EE hw init\n");
rtlpriv->rtlhal.being_init_adapter = true;
+ /* As this function can take a very long time (up to 350 ms)
+ * and can be called with irqs disabled, reenable the irqs
+ * to let the other devices continue being serviced.
+ *
+ * It is safe doing so since our own interrupts will only be enabled
+ * in a subsequent step.
+ */
+ local_save_flags(flags);
+ local_irq_enable();
+
rtlpriv->intf_ops->disable_aspm(hw);
tmp_u1b = rtl_read_byte(rtlpriv, REG_SYS_CLKR+1);
@@ -1042,7 +1054,7 @@
if (rtstatus != true) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
err = 1;
- return err;
+ goto exit;
}
err = rtl88e_download_fw(hw, false);
@@ -1050,8 +1062,7 @@
RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
"Failed to download FW. Init HW without FW now..\n");
err = 1;
- rtlhal->fw_ready = false;
- return err;
+ goto exit;
} else {
rtlhal->fw_ready = true;
}
@@ -1134,10 +1145,12 @@
}
rtl_write_byte(rtlpriv, REG_NAV_CTRL+2, ((30000+127)/128));
rtl88e_dm_init(hw);
+exit:
+ local_irq_restore(flags);
rtlpriv->rtlhal.being_init_adapter = false;
RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "end of Rtl8188EE hw init %x\n",
err);
- return 0;
+ return err;
}
static enum version_8188e _rtl88ee_read_chip_version(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
index a8871d6..ea4d014 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
@@ -293,7 +293,7 @@
u8 *psaddr;
__le16 fc;
u16 type, ufc;
- bool match_bssid, packet_toself, packet_beacon, addr;
+ bool match_bssid, packet_toself, packet_beacon = false, addr;
tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
index d2d57a2..06cb94c 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.c
@@ -158,6 +158,42 @@
{0x09, 0x08, 0x07, 0x04, 0x00, 0x00, 0x00, 0x00}
};
+static u32 power_index_reg[6] = {0xc90, 0xc91, 0xc92, 0xc98, 0xc99, 0xc9a};
+
+void dm_restorepowerindex(struct ieee80211_hw *hw)
+{
+ struct rtl_priv *rtlpriv = rtl_priv(hw);
+ u8 index;
+
+ for (index = 0; index < 6; index++)
+ rtl_write_byte(rtlpriv, power_index_reg[index],
+ rtlpriv->dm.powerindex_backup[index]);
+}
+EXPORT_SYMBOL_GPL(dm_restorepowerindex);
+
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value)
+{
+ struct rtl_priv *rtlpriv = rtl_priv(hw);
+ u8 index;
+
+ for (index = 0; index < 6; index++)
+ rtl_write_byte(rtlpriv, power_index_reg[index], value);
+}
+EXPORT_SYMBOL_GPL(dm_writepowerindex);
+
+void dm_savepowerindex(struct ieee80211_hw *hw)
+{
+ struct rtl_priv *rtlpriv = rtl_priv(hw);
+ u8 index;
+ u8 tmp;
+
+ for (index = 0; index < 6; index++) {
+ tmp = rtl_read_byte(rtlpriv, power_index_reg[index]);
+ rtlpriv->dm.powerindex_backup[index] = tmp;
+ }
+}
+EXPORT_SYMBOL_GPL(dm_savepowerindex);
+
static void rtl92c_dm_diginit(struct ieee80211_hw *hw)
{
struct rtl_priv *rtlpriv = rtl_priv(hw);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
index 518e208..4f232a0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192c/dm_common.h
@@ -91,6 +91,17 @@
#define TX_POWER_NEAR_FIELD_THRESH_LVL2 74
#define TX_POWER_NEAR_FIELD_THRESH_LVL1 67
+#define DYNAMIC_FUNC_DISABLE 0x0
+#define DYNAMIC_FUNC_DIG BIT(0)
+#define DYNAMIC_FUNC_HP BIT(1)
+#define DYNAMIC_FUNC_SS BIT(2) /*Tx Power Tracking*/
+#define DYNAMIC_FUNC_BT BIT(3)
+#define DYNAMIC_FUNC_ANT_DIV BIT(4)
+
+#define RSSI_CCK 0
+#define RSSI_OFDM 1
+#define RSSI_DEFAULT 2
+
struct swat_t {
u8 failure_cnt;
u8 try_flag;
@@ -167,5 +178,8 @@
void rtl92c_phy_iq_calibrate(struct ieee80211_hw *hw, bool recovery);
void rtl92c_dm_dynamic_txpower(struct ieee80211_hw *hw);
void rtl92c_dm_bt_coexist(struct ieee80211_hw *hw);
+void dm_savepowerindex(struct ieee80211_hw *hw);
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value);
+void dm_restorepowerindex(struct ieee80211_hw *hw);
#endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
index a82b30a..2eb0b38 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
@@ -937,14 +937,26 @@
bool is92c;
int err;
u8 tmp_u1b;
+ unsigned long flags;
rtlpci->being_init_adapter = true;
+
+ /* Since this function can take a very long time (up to 350 ms)
+ * and can be called with irqs disabled, reenable the irqs
+ * to let the other devices continue being serviced.
+ *
+ * It is safe doing so since our own interrupts will only be enabled
+ * in a subsequent step.
+ */
+ local_save_flags(flags);
+ local_irq_enable();
+
rtlpriv->intf_ops->disable_aspm(hw);
rtstatus = _rtl92ce_init_mac(hw);
if (!rtstatus) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
err = 1;
- return err;
+ goto exit;
}
err = rtl92c_download_fw(hw);
@@ -952,7 +964,7 @@
RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
"Failed to download FW. Init HW without FW now..\n");
err = 1;
- return err;
+ goto exit;
}
rtlhal->last_hmeboxnum = 0;
@@ -1032,6 +1044,8 @@
RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
}
rtl92c_dm_init(hw);
+exit:
+ local_irq_restore(flags);
rtlpci->being_init_adapter = false;
return err;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
index 16a0b9e..c16209a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.c
@@ -101,6 +101,15 @@
"PHY_SetTxPowerLevel8192S() Channel = %d\n",
rtlphy->current_channel);
rtl92c_phy_set_txpower_level(hw, rtlphy->current_channel);
+ if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+ TXHIGHPWRLEVEL_NORMAL)
+ dm_restorepowerindex(hw);
+ else if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+ TXHIGHPWRLEVEL_LEVEL1)
+ dm_writepowerindex(hw, 0x14);
+ else if (rtlpriv->dm.dynamic_txhighpower_lvl ==
+ TXHIGHPWRLEVEL_LEVEL2)
+ dm_writepowerindex(hw, 0x10);
}
rtlpriv->dm.last_dtp_lvl = rtlpriv->dm.dynamic_txhighpower_lvl;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
index d947e7d..fafa6ba 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/dm.h
@@ -30,3 +30,6 @@
#include "../rtl8192ce/dm.h"
void rtl92cu_dm_dynamic_txpower(struct ieee80211_hw *hw);
+void dm_savepowerindex(struct ieee80211_hw *hw);
+void dm_writepowerindex(struct ieee80211_hw *hw, u8 value);
+void dm_restorepowerindex(struct ieee80211_hw *hw);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
index 189ba12..c3f2b55 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
@@ -985,19 +985,30 @@
struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
int err = 0;
static bool iqk_initialized;
+ unsigned long flags;
+
+ /* As this function can take a very long time (up to 350 ms)
+ * and can be called with irqs disabled, reenable the irqs
+ * to let the other devices continue being serviced.
+ *
+ * It is safe doing so since our own interrupts will only be enabled
+ * in a subsequent step.
+ */
+ local_save_flags(flags);
+ local_irq_enable();
rtlhal->hw_type = HARDWARE_TYPE_RTL8192CU;
err = _rtl92cu_init_mac(hw);
if (err) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "init mac failed!\n");
- return err;
+ goto exit;
}
err = rtl92c_download_fw(hw);
if (err) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
"Failed to download FW. Init HW without FW now..\n");
err = 1;
- return err;
+ goto exit;
}
rtlhal->last_hmeboxnum = 0; /* h2c */
_rtl92cu_phy_param_tab_init(hw);
@@ -1034,6 +1045,8 @@
_InitPABias(hw);
_update_mac_setting(hw);
rtl92c_dm_init(hw);
+exit:
+ local_irq_restore(flags);
return err;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c b/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
index da4f587..2c68c13 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/mac.c
@@ -778,7 +778,7 @@
static void _rtl92c_query_rxphystatus(struct ieee80211_hw *hw,
struct rtl_stats *pstats,
- struct rx_desc_92c *pdesc,
+ struct rx_desc_92c *p_desc,
struct rx_fwinfo_92c *p_drvinfo,
bool packet_match_bssid,
bool packet_toself,
@@ -793,11 +793,11 @@
u32 rssi, total_rssi = 0;
bool in_powersavemode = false;
bool is_cck_rate;
+ u8 *pdesc = (u8 *)p_desc;
- is_cck_rate = RX_HAL_IS_CCK_RATE(pdesc);
+ is_cck_rate = RX_HAL_IS_CCK_RATE(p_desc);
pstats->packet_matchbssid = packet_match_bssid;
pstats->packet_toself = packet_toself;
- pstats->is_cck = is_cck_rate;
pstats->packet_beacon = packet_beacon;
pstats->is_cck = is_cck_rate;
pstats->RX_SIGQ[0] = -1;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c b/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
index 953f1a0..b878d56 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/rf.c
@@ -85,17 +85,15 @@
if (mac->act_scanning) {
tx_agc[RF90_PATH_A] = 0x3f3f3f3f;
tx_agc[RF90_PATH_B] = 0x3f3f3f3f;
- if (turbo_scanoff) {
- for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
- tx_agc[idx1] = ppowerlevel[idx1] |
- (ppowerlevel[idx1] << 8) |
- (ppowerlevel[idx1] << 16) |
- (ppowerlevel[idx1] << 24);
- if (rtlhal->interface == INTF_USB) {
- if (tx_agc[idx1] > 0x20 &&
- rtlefuse->external_pa)
- tx_agc[idx1] = 0x20;
- }
+ for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
+ tx_agc[idx1] = ppowerlevel[idx1] |
+ (ppowerlevel[idx1] << 8) |
+ (ppowerlevel[idx1] << 16) |
+ (ppowerlevel[idx1] << 24);
+ if (rtlhal->interface == INTF_USB) {
+ if (tx_agc[idx1] > 0x20 &&
+ rtlefuse->external_pa)
+ tx_agc[idx1] = 0x20;
}
}
} else {
@@ -104,10 +102,10 @@
tx_agc[RF90_PATH_A] = 0x10101010;
tx_agc[RF90_PATH_B] = 0x10101010;
} else if (rtlpriv->dm.dynamic_txhighpower_lvl ==
- TXHIGHPWRLEVEL_LEVEL1) {
+ TXHIGHPWRLEVEL_LEVEL2) {
tx_agc[RF90_PATH_A] = 0x00000000;
tx_agc[RF90_PATH_B] = 0x00000000;
- } else{
+ } else {
for (idx1 = RF90_PATH_A; idx1 <= RF90_PATH_B; idx1++) {
tx_agc[idx1] = ppowerlevel[idx1] |
(ppowerlevel[idx1] << 8) |
@@ -373,7 +371,12 @@
regoffset == RTXAGC_B_MCS07_MCS04)
regoffset = 0xc98;
for (i = 0; i < 3; i++) {
- writeVal = (writeVal > 6) ? (writeVal - 6) : 0;
+ if (i != 2)
+ writeVal = (writeVal > 8) ?
+ (writeVal - 8) : 0;
+ else
+ writeVal = (writeVal > 6) ?
+ (writeVal - 6) : 0;
rtl_write_byte(rtlpriv, (u32)(regoffset + i),
(u8)writeVal);
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
index 826f085..7555095 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
@@ -49,6 +49,9 @@
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Realtek 8192C/8188C 802.11n USB wireless");
MODULE_FIRMWARE("rtlwifi/rtl8192cufw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_A.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_B.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8192cufw_TMSC.bin");
static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw)
{
@@ -68,14 +71,21 @@
"Can't alloc buffer for fw\n");
return 1;
}
-
+ if (IS_VENDOR_UMC_A_CUT(rtlpriv->rtlhal.version) &&
+ !IS_92C_SERIAL(rtlpriv->rtlhal.version)) {
+ rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_A.bin";
+ } else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlpriv->rtlhal.version)) {
+ rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_B.bin";
+ } else {
+ rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_TMSC.bin";
+ }
+ /* provide name of alternative file */
+ rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin";
pr_info("Loading firmware %s\n", rtlpriv->cfg->fw_name);
rtlpriv->max_fw_size = 0x4000;
err = request_firmware_nowait(THIS_MODULE, 1,
rtlpriv->cfg->fw_name, rtlpriv->io.dev,
GFP_KERNEL, hw, rtl_fw_cb);
-
-
return err;
}
@@ -303,9 +313,12 @@
{RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/
{RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/
{RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/
+ {RTL_USB_DEVICE(0x0b05, 0x17ba, rtl92cu_hal_cfg)}, /*ASUS-Edimax*/
{RTL_USB_DEVICE(0x0bda, 0x5088, rtl92cu_hal_cfg)}, /*Thinkware-CC&C*/
{RTL_USB_DEVICE(0x0df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
{RTL_USB_DEVICE(0x0df6, 0x005c, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/
+ {RTL_USB_DEVICE(0x0df6, 0x0070, rtl92cu_hal_cfg)}, /*Sitecom - 150N */
+ {RTL_USB_DEVICE(0x0df6, 0x0077, rtl92cu_hal_cfg)}, /*Sitecom-WLA2100V2*/
{RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/
{RTL_USB_DEVICE(0x4856, 0x0091, rtl92cu_hal_cfg)}, /*NetweeN - Feixun*/
/* HP - Lite-On ,8188CUS Slim Combo */
@@ -357,8 +370,10 @@
{RTL_USB_DEVICE(0x2001, 0x3307, rtl92cu_hal_cfg)}, /*D-Link-Cameo*/
{RTL_USB_DEVICE(0x2001, 0x3309, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/
{RTL_USB_DEVICE(0x2001, 0x330a, rtl92cu_hal_cfg)}, /*D-Link-Alpha*/
+ {RTL_USB_DEVICE(0x2001, 0x330d, rtl92cu_hal_cfg)}, /*D-Link DWA-131 */
{RTL_USB_DEVICE(0x2019, 0xab2b, rtl92cu_hal_cfg)}, /*Planex -Abocom*/
{RTL_USB_DEVICE(0x20f4, 0x624d, rtl92cu_hal_cfg)}, /*TRENDNet*/
+ {RTL_USB_DEVICE(0x2357, 0x0100, rtl92cu_hal_cfg)}, /*TP-Link WN8200ND*/
{RTL_USB_DEVICE(0x7392, 0x7822, rtl92cu_hal_cfg)}, /*Edimax -Edimax*/
{}
};
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
index 763cf1d..5c52a8a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/trx.c
@@ -303,10 +303,10 @@
bool rtl92cu_rx_query_desc(struct ieee80211_hw *hw,
struct rtl_stats *stats,
struct ieee80211_rx_status *rx_status,
- u8 *p_desc, struct sk_buff *skb)
+ u8 *pdesc, struct sk_buff *skb)
{
struct rx_fwinfo_92c *p_drvinfo;
- struct rx_desc_92c *pdesc = (struct rx_desc_92c *)p_desc;
+ struct rx_desc_92c *p_desc = (struct rx_desc_92c *)pdesc;
u32 phystatus = GET_RX_DESC_PHY_STATUS(pdesc);
stats->length = (u16) GET_RX_DESC_PKT_LEN(pdesc);
@@ -343,12 +343,13 @@
(bool)GET_RX_DESC_PAGGR(pdesc));
rx_status->mactime = GET_RX_DESC_TSFL(pdesc);
if (phystatus) {
- p_drvinfo = (struct rx_fwinfo_92c *)(pdesc + RTL_RX_DESC_SIZE);
- rtl92c_translate_rx_signal_stuff(hw, skb, stats, pdesc,
+ p_drvinfo = (struct rx_fwinfo_92c *)(skb->data +
+ stats->rx_bufshift);
+ rtl92c_translate_rx_signal_stuff(hw, skb, stats, p_desc,
p_drvinfo);
}
/*rx_status->qual = stats->signal; */
- rx_status->signal = stats->rssi + 10;
+ rx_status->signal = stats->recvsignalpower + 10;
/*rx_status->noise = -stats->noise; */
return true;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
index b8ec718..542394c 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192de/trx.c
@@ -525,7 +525,7 @@
p_drvinfo);
}
/*rx_status->qual = stats->signal; */
- rx_status->signal = stats->rssi + 10;
+ rx_status->signal = stats->recvsignalpower + 10;
/*rx_status->noise = -stats->noise; */
return true;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
index 4f46178..c471400 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
@@ -955,7 +955,7 @@
struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
u8 tmp_byte = 0;
-
+ unsigned long flags;
bool rtstatus = true;
u8 tmp_u1b;
int err = false;
@@ -967,6 +967,16 @@
rtlpci->being_init_adapter = true;
+ /* As this function can take a very long time (up to 350 ms)
+ * and can be called with irqs disabled, reenable the irqs
+ * to let the other devices continue being serviced.
+ *
+ * It is safe doing so since our own interrupts will only be enabled
+ * in a subsequent step.
+ */
+ local_save_flags(flags);
+ local_irq_enable();
+
rtlpriv->intf_ops->disable_aspm(hw);
/* 1. MAC Initialize */
@@ -984,7 +994,8 @@
RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
"Failed to download FW. Init HW without FW now... "
"Please copy FW into /lib/firmware/rtlwifi\n");
- return 1;
+ err = 1;
+ goto exit;
}
/* After FW download, we have to reset MAC register */
@@ -997,7 +1008,8 @@
/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
if (!rtl92s_phy_mac_config(hw)) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "MAC Config failed\n");
- return rtstatus;
+ err = rtstatus;
+ goto exit;
}
/* because last function modify RCR, so we update
@@ -1016,7 +1028,8 @@
/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
if (!rtl92s_phy_bb_config(hw)) {
RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, "BB Config failed\n");
- return rtstatus;
+ err = rtstatus;
+ goto exit;
}
/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */
@@ -1033,7 +1046,8 @@
if (!rtl92s_phy_rf_config(hw)) {
RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "RF Config failed\n");
- return rtstatus;
+ err = rtstatus;
+ goto exit;
}
/* After read predefined TXT, we must set BB/MAC/RF
@@ -1122,8 +1136,9 @@
rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
rtl92s_dm_init(hw);
+exit:
+ local_irq_restore(flags);
rtlpci->being_init_adapter = false;
-
return err;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
index 5061f1d..92d38ab 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/rf.c
@@ -265,7 +265,7 @@
rtlefuse->pwrgroup_ht40
[RF90_PATH_A][chnl - 1]) {
pwrdiff_limit[i] =
- rtlefuse->pwrgroup_ht20
+ rtlefuse->pwrgroup_ht40
[RF90_PATH_A][chnl - 1];
}
} else {
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index c709511..c240b75 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -49,6 +49,12 @@
if (ieee80211_is_nullfunc(fc))
return QSLT_HIGH;
+ /* Kernel commit 1bf4bbb4024dcdab changed EAPOL packets to use
+ * queue V0 at priority 7; however, the RTL8192SE appears to have
+ * that queue at priority 6
+ */
+ if (skb->priority == 7)
+ return QSLT_VO;
return skb->priority;
}
@@ -329,7 +335,7 @@
}
/*rx_status->qual = stats->signal; */
- rx_status->signal = stats->rssi + 10;
+ rx_status->signal = stats->recvsignalpower + 10;
/*rx_status->noise = -stats->noise; */
return true;
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index c333dfd..99f6bc5 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -880,14 +880,25 @@
bool rtstatus = true;
int err;
u8 tmp_u1b;
+ unsigned long flags;
rtlpriv->rtlhal.being_init_adapter = true;
+ /* As this function can take a very long time (up to 350 ms)
+ * and can be called with irqs disabled, reenable the irqs
+ * to let the other devices continue being serviced.
+ *
+ * It is safe doing so since our own interrupts will only be enabled
+ * in a subsequent step.
+ */
+ local_save_flags(flags);
+ local_irq_enable();
+
rtlpriv->intf_ops->disable_aspm(hw);
rtstatus = _rtl8712e_init_mac(hw);
if (rtstatus != true) {
RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
err = 1;
- return err;
+ goto exit;
}
err = rtl8723ae_download_fw(hw);
@@ -895,8 +906,7 @@
RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
"Failed to download FW. Init HW without FW now..\n");
err = 1;
- rtlhal->fw_ready = false;
- return err;
+ goto exit;
} else {
rtlhal->fw_ready = true;
}
@@ -971,6 +981,8 @@
RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
}
rtl8723ae_dm_init(hw);
+exit:
+ local_irq_restore(flags);
rtlpriv->rtlhal.being_init_adapter = false;
return err;
}
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
index e4c4cdc..d9ee2ef 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
@@ -251,7 +251,7 @@
.bar_id = 2,
.write_readback = true,
.name = "rtl8723ae_pci",
- .fw_name = "rtlwifi/rtl8723aefw.bin",
+ .fw_name = "rtlwifi/rtl8723fw.bin",
.ops = &rtl8723ae_hal_ops,
.mod_params = &rtl8723ae_mod_params,
.maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL,
@@ -353,8 +353,8 @@
MODULE_AUTHOR("Larry Finger <Larry.Finger@lwfinger.net>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Realtek 8723E 802.11n PCI wireless");
-MODULE_FIRMWARE("rtlwifi/rtl8723aefw.bin");
-MODULE_FIRMWARE("rtlwifi/rtl8723aefw_B.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723fw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723fw_B.bin");
module_param_named(swenc, rtl8723ae_mod_params.sw_crypto, bool, 0444);
module_param_named(debug, rtl8723ae_mod_params.debug, int, 0444);
diff --git a/drivers/net/wireless/rtlwifi/stats.c b/drivers/net/wireless/rtlwifi/stats.c
index 8ed3174..4f083fc 100644
--- a/drivers/net/wireless/rtlwifi/stats.c
+++ b/drivers/net/wireless/rtlwifi/stats.c
@@ -176,6 +176,7 @@
struct rtl_sta_info *drv_priv = NULL;
struct ieee80211_sta *sta = NULL;
long undec_sm_pwdb;
+ long undec_sm_cck;
rcu_read_lock();
if (rtlpriv->mac80211.opmode != NL80211_IFTYPE_STATION)
@@ -185,12 +186,16 @@
if (sta) {
drv_priv = (struct rtl_sta_info *) sta->drv_priv;
undec_sm_pwdb = drv_priv->rssi_stat.undec_sm_pwdb;
+ undec_sm_cck = drv_priv->rssi_stat.undec_sm_cck;
} else {
undec_sm_pwdb = rtlpriv->dm.undec_sm_pwdb;
+ undec_sm_cck = rtlpriv->dm.undec_sm_cck;
}
if (undec_sm_pwdb < 0)
undec_sm_pwdb = pstatus->rx_pwdb_all;
+ if (undec_sm_cck < 0)
+ undec_sm_cck = pstatus->rx_pwdb_all;
if (pstatus->rx_pwdb_all > (u32) undec_sm_pwdb) {
undec_sm_pwdb = (((undec_sm_pwdb) *
(RX_SMOOTH_FACTOR - 1)) +
@@ -200,6 +205,15 @@
undec_sm_pwdb = (((undec_sm_pwdb) * (RX_SMOOTH_FACTOR - 1)) +
(pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
}
+ if (pstatus->rx_pwdb_all > (u32) undec_sm_cck) {
+ undec_sm_cck = (((undec_sm_pwdb) *
+ (RX_SMOOTH_FACTOR - 1)) +
+ (pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
+ undec_sm_cck = undec_sm_cck + 1;
+ } else {
+ undec_sm_pwdb = (((undec_sm_cck) * (RX_SMOOTH_FACTOR - 1)) +
+ (pstatus->rx_pwdb_all)) / (RX_SMOOTH_FACTOR);
+ }
if (sta) {
drv_priv->rssi_stat.undec_sm_pwdb = undec_sm_pwdb;
diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c
index a3532e0..57b12a5 100644
--- a/drivers/net/wireless/rtlwifi/usb.c
+++ b/drivers/net/wireless/rtlwifi/usb.c
@@ -477,6 +477,8 @@
if (unicast)
rtlpriv->link_info.num_rx_inperiod++;
}
+ /* static bcn for roaming */
+ rtl_beacon_statistic(hw, skb);
}
}
@@ -548,7 +550,7 @@
}
}
-#define __RX_SKB_MAX_QUEUED 32
+#define __RX_SKB_MAX_QUEUED 64
static void _rtl_rx_work(unsigned long param)
{
@@ -1070,6 +1072,8 @@
spin_lock_init(&rtlpriv->locks.usb_lock);
INIT_WORK(&rtlpriv->works.fill_h2c_cmd,
rtl_fill_h2c_cmd_work_callback);
+ INIT_WORK(&rtlpriv->works.lps_change_work,
+ rtl_lps_change_work_callback);
rtlpriv->usb_data_index = 0;
init_completion(&rtlpriv->firmware_loading_complete);
diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h
index cc03e7c..e576a927 100644
--- a/drivers/net/wireless/rtlwifi/wifi.h
+++ b/drivers/net/wireless/rtlwifi/wifi.h
@@ -77,11 +77,7 @@
#define RTL_SLOT_TIME_9 9
#define RTL_SLOT_TIME_20 20
-/*related with tcp/ip. */
-/*if_ehther.h*/
-#define ETH_P_PAE 0x888E /*Port Access Entity (IEEE 802.1X) */
-#define ETH_P_IP 0x0800 /*Internet Protocol packet */
-#define ETH_P_ARP 0x0806 /*Address Resolution packet */
+/*related to tcp/ip. */
#define SNAP_SIZE 6
#define PROTOC_TYPE_SIZE 2
@@ -1039,6 +1035,7 @@
struct rssi_sta {
long undec_sm_pwdb;
+ long undec_sm_cck;
};
struct rtl_tid_data {
@@ -1329,8 +1326,10 @@
struct rtl_dm {
/*PHY status for Dynamic Management */
long entry_min_undec_sm_pwdb;
+ long undec_sm_cck;
long undec_sm_pwdb; /*out dm */
long entry_max_undec_sm_pwdb;
+ s32 ofdm_pkt_cnt;
bool dm_initialgain_enable;
bool dynamic_txpower_enable;
bool current_turbo_edca;
@@ -1345,6 +1344,7 @@
bool inform_fw_driverctrldm;
bool current_mrc_switch;
u8 txpowercount;
+ u8 powerindex_backup[6];
u8 thermalvalue_rxgain;
u8 thermalvalue_iqk;
@@ -1356,7 +1356,9 @@
bool done_txpower;
u8 dynamic_txhighpower_lvl; /*Tx high power level */
u8 dm_flag; /*Indicate each dynamic mechanism's status. */
+ u8 dm_flag_tmp;
u8 dm_type;
+ u8 dm_rssi_sel;
u8 txpower_track_control;
bool interrupt_migration;
bool disable_tx_int;
@@ -1810,6 +1812,7 @@
bool write_readback;
char *name;
char *fw_name;
+ char *alt_fw_name;
struct rtl_hal_ops *ops;
struct rtl_mod_params *mod_params;
struct rtl_hal_usbint_cfg *usb_interface_cfg;
@@ -1954,6 +1957,7 @@
u8 pre_ccastate;
u8 cur_ccasate;
u8 large_fa_hit;
+ u8 dig_dynamic_min;
u8 forbidden_igi;
u8 dig_state;
u8 dig_highpwrstate;
@@ -2034,22 +2038,15 @@
struct dig_t dm_digtable;
struct ps_t dm_pstable;
- /* section shared by individual drivers */
- union {
- struct { /* data buffer pointer for USB reads */
- __le32 *usb_data;
- int usb_data_index;
- bool initialized;
- };
- struct { /* section for 8723ae */
- bool reg_init; /* true if regs saved */
- u32 reg_874;
- u32 reg_c70;
- u32 reg_85c;
- u32 reg_a74;
- bool bt_operation_on;
- };
- };
+ u32 reg_874;
+ u32 reg_c70;
+ u32 reg_85c;
+ u32 reg_a74;
+ bool reg_init; /* true if regs saved */
+ bool bt_operation_on;
+ __le32 *usb_data;
+ int usb_data_index;
+ bool initialized;
bool enter_ps; /* true when entering PS */
u8 rate_mask[5];
@@ -2057,7 +2054,7 @@
that it points to the data allocated
beyond this structure like:
rtl_pci_priv or rtl_usb_priv */
- u8 priv[0];
+ u8 priv[0] __aligned(sizeof(void *));
};
#define rtl_priv(hw) (((struct rtl_priv *)(hw)->priv))
diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c
index 7f1669c..779dc2b 100644
--- a/drivers/net/wireless/ti/wl18xx/debugfs.c
+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c
@@ -136,7 +136,7 @@
WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, accum_arp_pend_requests, "%u");
WL18XX_DEBUGFS_FWSTATS_FILE(rx_filter, max_arp_queue_dep, "%u");
-WL18XX_DEBUGFS_FWSTATS_FILE(rx_rate, rx_frames_per_rates, "%u");
+WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(rx_rate, rx_frames_per_rates, 50);
WL18XX_DEBUGFS_FWSTATS_FILE_ARRAY(aggr_size, tx_agg_vs_rate,
AGGR_STATS_TX_AGG*AGGR_STATS_TX_RATE);
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h
index f7381dd..1bce432 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.h
+++ b/drivers/net/wireless/ti/wlcore/debugfs.h
@@ -26,8 +26,8 @@
#include "wlcore.h"
-int wl1271_format_buffer(char __user *userbuf, size_t count,
- loff_t *ppos, char *fmt, ...);
+__printf(4, 5) int wl1271_format_buffer(char __user *userbuf, size_t count,
+ loff_t *ppos, char *fmt, ...);
int wl1271_debugfs_init(struct wl1271 *wl);
void wl1271_debugfs_exit(struct wl1271 *wl);
diff --git a/drivers/net/wireless/zd1201.c b/drivers/net/wireless/zd1201.c
index 4941f20..b8ba1f9 100644
--- a/drivers/net/wireless/zd1201.c
+++ b/drivers/net/wireless/zd1201.c
@@ -98,10 +98,12 @@
goto exit;
err = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), 0x4,
- USB_DIR_IN | 0x40, 0,0, &ret, sizeof(ret), ZD1201_FW_TIMEOUT);
+ USB_DIR_IN | 0x40, 0, 0, buf, sizeof(ret), ZD1201_FW_TIMEOUT);
if (err < 0)
goto exit;
+ memcpy(&ret, buf, sizeof(ret));
+
if (ret & 0x80) {
err = -EIO;
goto exit;
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 9d7f172..f2faa77 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -88,6 +88,7 @@
unsigned long credit_usec;
unsigned long remaining_credit;
struct timer_list credit_timeout;
+ u64 credit_window_start;
/* Statistics */
unsigned long rx_gso_checksum_fixup;
@@ -115,6 +116,7 @@
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
unsigned long rx_ring_ref, unsigned int evtchn);
void xenvif_disconnect(struct xenvif *vif);
+void xenvif_free(struct xenvif *vif);
void xenvif_get(struct xenvif *vif);
void xenvif_put(struct xenvif *vif);
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index d984141..540a796 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -275,8 +275,7 @@
vif->credit_bytes = vif->remaining_credit = ~0UL;
vif->credit_usec = 0UL;
init_timer(&vif->credit_timeout);
- /* Initialize 'expires' now: it's used to track the credit window. */
- vif->credit_timeout.expires = jiffies;
+ vif->credit_window_start = get_jiffies_64();
dev->netdev_ops = &xenvif_netdev_ops;
dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
@@ -304,6 +303,9 @@
}
netdev_dbg(dev, "Successfully created xenvif\n");
+
+ __module_get(THIS_MODULE);
+
return vif;
}
@@ -363,15 +365,22 @@
if (netif_carrier_ok(vif->dev))
xenvif_carrier_off(vif);
+ if (vif->irq) {
+ unbind_from_irqhandler(vif->irq, vif);
+ vif->irq = 0;
+ }
+
+ xen_netbk_unmap_frontend_rings(vif);
+}
+
+void xenvif_free(struct xenvif *vif)
+{
atomic_dec(&vif->refcnt);
wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
- if (vif->irq)
- unbind_from_irqhandler(vif->irq, vif);
-
unregister_netdev(vif->dev);
- xen_netbk_unmap_frontend_rings(vif);
-
free_netdev(vif->dev);
+
+ module_put(THIS_MODULE);
}
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 8c20935..70b830f 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -347,13 +347,56 @@
* into multiple copies tend to give large frags their
* own buffers as before.
*/
- if ((offset + size > MAX_BUFFER_OFFSET) &&
- (size <= MAX_BUFFER_OFFSET) && offset && !head)
+ BUG_ON(size > MAX_BUFFER_OFFSET);
+ if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
return true;
return false;
}
+struct xenvif_count_slot_state {
+ unsigned long copy_off;
+ bool head;
+};
+
+unsigned int xenvif_count_frag_slots(struct xenvif *vif,
+ unsigned long offset, unsigned long size,
+ struct xenvif_count_slot_state *state)
+{
+ unsigned count = 0;
+
+ offset &= ~PAGE_MASK;
+
+ while (size > 0) {
+ unsigned long bytes;
+
+ bytes = PAGE_SIZE - offset;
+
+ if (bytes > size)
+ bytes = size;
+
+ if (start_new_rx_buffer(state->copy_off, bytes, state->head)) {
+ count++;
+ state->copy_off = 0;
+ }
+
+ if (state->copy_off + bytes > MAX_BUFFER_OFFSET)
+ bytes = MAX_BUFFER_OFFSET - state->copy_off;
+
+ state->copy_off += bytes;
+
+ offset += bytes;
+ size -= bytes;
+
+ if (offset == PAGE_SIZE)
+ offset = 0;
+
+ state->head = false;
+ }
+
+ return count;
+}
+
/*
* Figure out how many ring slots we're going to need to send @skb to
* the guest. This function is essentially a dry run of
@@ -361,48 +404,39 @@
*/
unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
{
+ struct xenvif_count_slot_state state;
unsigned int count;
- int i, copy_off;
+ unsigned char *data;
+ unsigned i;
- count = DIV_ROUND_UP(skb_headlen(skb), PAGE_SIZE);
+ state.head = true;
+ state.copy_off = 0;
- copy_off = skb_headlen(skb) % PAGE_SIZE;
+ /* Slot for the first (partial) page of data. */
+ count = 1;
+ /* Need a slot for the GSO prefix for GSO extra data? */
if (skb_shinfo(skb)->gso_size)
count++;
+ data = skb->data;
+ while (data < skb_tail_pointer(skb)) {
+ unsigned long offset = offset_in_page(data);
+ unsigned long size = PAGE_SIZE - offset;
+
+ if (data + size > skb_tail_pointer(skb))
+ size = skb_tail_pointer(skb) - data;
+
+ count += xenvif_count_frag_slots(vif, offset, size, &state);
+
+ data += size;
+ }
+
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
- unsigned long bytes;
- offset &= ~PAGE_MASK;
-
- while (size > 0) {
- BUG_ON(offset >= PAGE_SIZE);
- BUG_ON(copy_off > MAX_BUFFER_OFFSET);
-
- bytes = PAGE_SIZE - offset;
-
- if (bytes > size)
- bytes = size;
-
- if (start_new_rx_buffer(copy_off, bytes, 0)) {
- count++;
- copy_off = 0;
- }
-
- if (copy_off + bytes > MAX_BUFFER_OFFSET)
- bytes = MAX_BUFFER_OFFSET - copy_off;
-
- copy_off += bytes;
-
- offset += bytes;
- size -= bytes;
-
- if (offset == PAGE_SIZE)
- offset = 0;
- }
+ count += xenvif_count_frag_slots(vif, offset, size, &state);
}
return count;
}
@@ -1389,9 +1423,8 @@
static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
{
- unsigned long now = jiffies;
- unsigned long next_credit =
- vif->credit_timeout.expires +
+ u64 now = get_jiffies_64();
+ u64 next_credit = vif->credit_window_start +
msecs_to_jiffies(vif->credit_usec / 1000);
/* Timer could already be pending in rare cases. */
@@ -1399,8 +1432,8 @@
return true;
/* Passed the point where we can replenish credit? */
- if (time_after_eq(now, next_credit)) {
- vif->credit_timeout.expires = now;
+ if (time_after_eq64(now, next_credit)) {
+ vif->credit_window_start = now;
tx_add_credit(vif);
}
@@ -1412,6 +1445,7 @@
tx_credit_callback;
mod_timer(&vif->credit_timeout,
next_credit);
+ vif->credit_window_start = next_credit;
return true;
}
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 410018c..8a9e875 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -24,6 +24,12 @@
struct backend_info {
struct xenbus_device *dev;
struct xenvif *vif;
+
+ /* This is the state that will be reflected in xenstore when any
+ * active hotplug script completes.
+ */
+ enum xenbus_state state;
+
enum xenbus_state frontend_state;
struct xenbus_watch hotplug_status_watch;
u8 have_hotplug_status_watch:1;
@@ -33,16 +39,20 @@
static void connect(struct backend_info *);
static void backend_create_xenvif(struct backend_info *be);
static void unregister_hotplug_status_watch(struct backend_info *be);
+static void set_backend_state(struct backend_info *be,
+ enum xenbus_state state);
static int netback_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
+ set_backend_state(be, XenbusStateClosed);
+
unregister_hotplug_status_watch(be);
if (be->vif) {
kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
- xenvif_disconnect(be->vif);
+ xenvif_free(be->vif);
be->vif = NULL;
}
kfree(be);
@@ -126,6 +136,8 @@
if (err)
goto fail;
+ be->state = XenbusStateInitWait;
+
/* This kicks hotplug scripts, so do it immediately. */
backend_create_xenvif(be);
@@ -198,15 +210,113 @@
kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
}
-
-static void disconnect_backend(struct xenbus_device *dev)
+static void backend_disconnect(struct backend_info *be)
{
- struct backend_info *be = dev_get_drvdata(&dev->dev);
-
- if (be->vif) {
- xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
+ if (be->vif)
xenvif_disconnect(be->vif);
- be->vif = NULL;
+}
+
+static void backend_connect(struct backend_info *be)
+{
+ if (be->vif)
+ connect(be);
+}
+
+static inline void backend_switch_state(struct backend_info *be,
+ enum xenbus_state state)
+{
+ struct xenbus_device *dev = be->dev;
+
+ pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state));
+ be->state = state;
+
+ /* If we are waiting for a hotplug script then defer the
+ * actual xenbus state change.
+ */
+ if (!be->have_hotplug_status_watch)
+ xenbus_switch_state(dev, state);
+}
+
+/* Handle backend state transitions:
+ *
+ * The backend state starts in InitWait and the following transitions are
+ * allowed.
+ *
+ * InitWait -> Connected
+ *
+ * ^ \ |
+ * | \ |
+ * | \ |
+ * | \ |
+ * | \ |
+ * | \ |
+ * | V V
+ *
+ * Closed <-> Closing
+ *
+ * The state argument specifies the eventual state of the backend and the
+ * function transitions to that state via the shortest path.
+ */
+static void set_backend_state(struct backend_info *be,
+ enum xenbus_state state)
+{
+ while (be->state != state) {
+ switch (be->state) {
+ case XenbusStateClosed:
+ switch (state) {
+ case XenbusStateInitWait:
+ case XenbusStateConnected:
+ pr_info("%s: prepare for reconnect\n",
+ be->dev->nodename);
+ backend_switch_state(be, XenbusStateInitWait);
+ break;
+ case XenbusStateClosing:
+ backend_switch_state(be, XenbusStateClosing);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ case XenbusStateInitWait:
+ switch (state) {
+ case XenbusStateConnected:
+ backend_connect(be);
+ backend_switch_state(be, XenbusStateConnected);
+ break;
+ case XenbusStateClosing:
+ case XenbusStateClosed:
+ backend_switch_state(be, XenbusStateClosing);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ case XenbusStateConnected:
+ switch (state) {
+ case XenbusStateInitWait:
+ case XenbusStateClosing:
+ case XenbusStateClosed:
+ backend_disconnect(be);
+ backend_switch_state(be, XenbusStateClosing);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ case XenbusStateClosing:
+ switch (state) {
+ case XenbusStateInitWait:
+ case XenbusStateConnected:
+ case XenbusStateClosed:
+ backend_switch_state(be, XenbusStateClosed);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ default:
+ BUG();
+ }
}
}
@@ -218,43 +328,33 @@
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
- pr_debug("frontend state %s", xenbus_strstate(frontend_state));
+ pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state));
be->frontend_state = frontend_state;
switch (frontend_state) {
case XenbusStateInitialising:
- if (dev->state == XenbusStateClosed) {
- printk(KERN_INFO "%s: %s: prepare for reconnect\n",
- __func__, dev->nodename);
- xenbus_switch_state(dev, XenbusStateInitWait);
- }
+ set_backend_state(be, XenbusStateInitWait);
break;
case XenbusStateInitialised:
break;
case XenbusStateConnected:
- if (dev->state == XenbusStateConnected)
- break;
- backend_create_xenvif(be);
- if (be->vif)
- connect(be);
+ set_backend_state(be, XenbusStateConnected);
break;
case XenbusStateClosing:
- if (be->vif)
- kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
- disconnect_backend(dev);
- xenbus_switch_state(dev, XenbusStateClosing);
+ set_backend_state(be, XenbusStateClosing);
break;
case XenbusStateClosed:
- xenbus_switch_state(dev, XenbusStateClosed);
+ set_backend_state(be, XenbusStateClosed);
if (xenbus_dev_is_online(dev))
break;
/* fall through if not online */
case XenbusStateUnknown:
+ set_backend_state(be, XenbusStateClosed);
device_unregister(&dev->dev);
break;
@@ -347,7 +447,9 @@
if (IS_ERR(str))
return;
if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
- xenbus_switch_state(be->dev, XenbusStateConnected);
+ /* Complete any pending state change */
+ xenbus_switch_state(be->dev, be->state);
+
/* Not interested in this watch anymore. */
unregister_hotplug_status_watch(be);
}
@@ -377,12 +479,8 @@
err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
hotplug_status_changed,
"%s/%s", dev->nodename, "hotplug-status");
- if (err) {
- /* Switch now, since we can't do a watch. */
- xenbus_switch_state(dev, XenbusStateConnected);
- } else {
+ if (!err)
be->have_hotplug_status_watch = 1;
- }
netif_wake_queue(be->vif->dev);
}
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 1db10141..a1db958 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -107,6 +107,7 @@
} tx_skbs[NET_TX_RING_SIZE];
grant_ref_t gref_tx_head;
grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
+ struct page *grant_tx_page[NET_TX_RING_SIZE];
unsigned tx_skb_freelist;
spinlock_t rx_lock ____cacheline_aligned_in_smp;
@@ -276,8 +277,7 @@
break;
}
- __skb_fill_page_desc(skb, 0, page, 0, 0);
- skb_shinfo(skb)->nr_frags = 1;
+ skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
__skb_queue_tail(&np->rx_batch, skb);
}
@@ -387,6 +387,7 @@
gnttab_release_grant_reference(
&np->gref_tx_head, np->grant_tx_ref[id]);
np->grant_tx_ref[id] = GRANT_INVALID_REF;
+ np->grant_tx_page[id] = NULL;
add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id);
dev_kfree_skb_irq(skb);
}
@@ -443,6 +444,7 @@
gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
+ np->grant_tx_page[id] = virt_to_page(data);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
@@ -457,9 +459,6 @@
len = skb_frag_size(frag);
offset = frag->page_offset;
- /* Data must not cross a page boundary. */
- BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
-
/* Skip unused frames from start of page */
page += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
@@ -467,8 +466,6 @@
while (len > 0) {
unsigned long bytes;
- BUG_ON(offset >= PAGE_SIZE);
-
bytes = PAGE_SIZE - offset;
if (bytes > len)
bytes = len;
@@ -488,6 +485,7 @@
np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
+ np->grant_tx_page[id] = page;
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = bytes;
@@ -587,6 +585,7 @@
mfn = virt_to_mfn(data);
gnttab_grant_foreign_access_ref(
ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
+ np->grant_tx_page[id] = virt_to_page(data);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
@@ -822,7 +821,6 @@
struct sk_buff_head *list)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
- int nr_frags = shinfo->nr_frags;
RING_IDX cons = np->rx.rsp_cons;
struct sk_buff *nskb;
@@ -831,19 +829,21 @@
RING_GET_RESPONSE(&np->rx, ++cons);
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
- __skb_fill_page_desc(skb, nr_frags,
- skb_frag_page(nfrag),
- rx->offset, rx->status);
+ if (shinfo->nr_frags == MAX_SKB_FRAGS) {
+ unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
- skb->data_len += rx->status;
+ BUG_ON(pull_to <= skb_headlen(skb));
+ __pskb_pull_tail(skb, pull_to - skb_headlen(skb));
+ }
+ BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
+
+ skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
+ rx->offset, rx->status, PAGE_SIZE);
skb_shinfo(nskb)->nr_frags = 0;
kfree_skb(nskb);
-
- nr_frags++;
}
- shinfo->nr_frags = nr_frags;
return cons;
}
@@ -929,7 +929,8 @@
while ((skb = __skb_dequeue(rxq)) != NULL) {
int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
- __pskb_pull_tail(skb, pull_to - skb_headlen(skb));
+ if (pull_to > skb_headlen(skb))
+ __pskb_pull_tail(skb, pull_to - skb_headlen(skb));
/* Ethernet work: Delayed to here as it peeks the header. */
skb->protocol = eth_type_trans(skb, dev);
@@ -1015,16 +1016,10 @@
skb_shinfo(skb)->frags[0].page_offset = rx->offset;
skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
skb->data_len = rx->status;
+ skb->len += rx->status;
i = xennet_fill_frags(np, skb, &tmpq);
- /*
- * Truesize is the actual allocation size, even if the
- * allocation is only partially used.
- */
- skb->truesize += PAGE_SIZE * skb_shinfo(skb)->nr_frags;
- skb->len += skb->data_len;
-
if (rx->flags & XEN_NETRXF_csum_blank)
skb->ip_summed = CHECKSUM_PARTIAL;
else if (rx->flags & XEN_NETRXF_data_validated)
@@ -1120,10 +1115,11 @@
continue;
skb = np->tx_skbs[i].skb;
- gnttab_end_foreign_access_ref(np->grant_tx_ref[i],
- GNTMAP_readonly);
- gnttab_release_grant_reference(&np->gref_tx_head,
- np->grant_tx_ref[i]);
+ get_page(np->grant_tx_page[i]);
+ gnttab_end_foreign_access(np->grant_tx_ref[i],
+ GNTMAP_readonly,
+ (unsigned long)page_address(np->grant_tx_page[i]));
+ np->grant_tx_page[i] = NULL;
np->grant_tx_ref[i] = GRANT_INVALID_REF;
add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
dev_kfree_skb_irq(skb);
@@ -1132,78 +1128,35 @@
static void xennet_release_rx_bufs(struct netfront_info *np)
{
- struct mmu_update *mmu = np->rx_mmu;
- struct multicall_entry *mcl = np->rx_mcl;
- struct sk_buff_head free_list;
- struct sk_buff *skb;
- unsigned long mfn;
- int xfer = 0, noxfer = 0, unused = 0;
int id, ref;
- dev_warn(&np->netdev->dev, "%s: fix me for copying receiver.\n",
- __func__);
- return;
-
- skb_queue_head_init(&free_list);
-
spin_lock_bh(&np->rx_lock);
for (id = 0; id < NET_RX_RING_SIZE; id++) {
- ref = np->grant_rx_ref[id];
- if (ref == GRANT_INVALID_REF) {
- unused++;
- continue;
- }
+ struct sk_buff *skb;
+ struct page *page;
skb = np->rx_skbs[id];
- mfn = gnttab_end_foreign_transfer_ref(ref);
- gnttab_release_grant_reference(&np->gref_rx_head, ref);
+ if (!skb)
+ continue;
+
+ ref = np->grant_rx_ref[id];
+ if (ref == GRANT_INVALID_REF)
+ continue;
+
+ page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
+
+ /* gnttab_end_foreign_access() needs a page ref until
+ * foreign access is ended (which may be deferred).
+ */
+ get_page(page);
+ gnttab_end_foreign_access(ref, 0,
+ (unsigned long)page_address(page));
np->grant_rx_ref[id] = GRANT_INVALID_REF;
- if (0 == mfn) {
- skb_shinfo(skb)->nr_frags = 0;
- dev_kfree_skb(skb);
- noxfer++;
- continue;
- }
-
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Remap the page. */
- const struct page *page =
- skb_frag_page(&skb_shinfo(skb)->frags[0]);
- unsigned long pfn = page_to_pfn(page);
- void *vaddr = page_address(page);
-
- MULTI_update_va_mapping(mcl, (unsigned long)vaddr,
- mfn_pte(mfn, PAGE_KERNEL),
- 0);
- mcl++;
- mmu->ptr = ((u64)mfn << PAGE_SHIFT)
- | MMU_MACHPHYS_UPDATE;
- mmu->val = pfn;
- mmu++;
-
- set_phys_to_machine(pfn, mfn);
- }
- __skb_queue_tail(&free_list, skb);
- xfer++;
+ kfree_skb(skb);
}
- dev_info(&np->netdev->dev, "%s: %d xfer, %d noxfer, %d unused\n",
- __func__, xfer, noxfer, unused);
-
- if (xfer) {
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Do all the remapping work and M2P updates. */
- MULTI_mmu_update(mcl, np->rx_mmu, mmu - np->rx_mmu,
- NULL, DOMID_SELF);
- mcl++;
- HYPERVISOR_multicall(np->rx_mcl, mcl - np->rx_mcl);
- }
- }
-
- __skb_queue_purge(&free_list);
-
spin_unlock_bh(&np->rx_lock);
}
@@ -1338,6 +1291,7 @@
for (i = 0; i < NET_RX_RING_SIZE; i++) {
np->rx_skbs[i] = NULL;
np->grant_rx_ref[i] = GRANT_INVALID_REF;
+ np->grant_tx_page[i] = NULL;
}
/* A grant for every tx ring slot */
diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c
index 3420d83..384ab8c 100644
--- a/drivers/nfc/microread/microread.c
+++ b/drivers/nfc/microread/microread.c
@@ -501,9 +501,13 @@
targets->sens_res =
be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A_ATQA]);
targets->sel_res = skb->data[MICROREAD_EMCF_A_SAK];
- memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
- skb->data[MICROREAD_EMCF_A_LEN]);
targets->nfcid1_len = skb->data[MICROREAD_EMCF_A_LEN];
+ if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+ r = -EINVAL;
+ goto exit_free;
+ }
+ memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A_UID],
+ targets->nfcid1_len);
break;
case MICROREAD_GATE_ID_MREAD_ISO_A_3:
targets->supported_protocols =
@@ -511,9 +515,13 @@
targets->sens_res =
be16_to_cpu(*(u16 *)&skb->data[MICROREAD_EMCF_A3_ATQA]);
targets->sel_res = skb->data[MICROREAD_EMCF_A3_SAK];
- memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
- skb->data[MICROREAD_EMCF_A3_LEN]);
targets->nfcid1_len = skb->data[MICROREAD_EMCF_A3_LEN];
+ if (targets->nfcid1_len > sizeof(targets->nfcid1)) {
+ r = -EINVAL;
+ goto exit_free;
+ }
+ memcpy(targets->nfcid1, &skb->data[MICROREAD_EMCF_A3_UID],
+ targets->nfcid1_len);
break;
case MICROREAD_GATE_ID_MREAD_ISO_B:
targets->supported_protocols = NFC_PROTO_ISO14443_B_MASK;
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c
index 2dacd19..b9bf8b5 100644
--- a/drivers/ntb/ntb_hw.c
+++ b/drivers/ntb/ntb_hw.c
@@ -78,6 +78,8 @@
BWD_HW,
};
+static struct dentry *debugfs_dir;
+
/* Translate memory window 0,1 to BAR 2,4 */
#define MW_TO_BAR(mw) (mw * 2 + 2)
@@ -531,9 +533,9 @@
}
if (val & SNB_PPD_DEV_TYPE)
- ndev->dev_type = NTB_DEV_DSD;
- else
ndev->dev_type = NTB_DEV_USD;
+ else
+ ndev->dev_type = NTB_DEV_DSD;
ndev->reg_ofs.pdb = ndev->reg_base + SNB_PDOORBELL_OFFSET;
ndev->reg_ofs.pdb_mask = ndev->reg_base + SNB_PDBMSK_OFFSET;
@@ -547,7 +549,7 @@
if (ndev->conn_type == NTB_CONN_B2B) {
ndev->reg_ofs.sdb = ndev->reg_base + SNB_B2B_DOORBELL_OFFSET;
ndev->reg_ofs.spad_write = ndev->reg_base + SNB_B2B_SPAD_OFFSET;
- ndev->limits.max_spads = SNB_MAX_SPADS;
+ ndev->limits.max_spads = SNB_MAX_B2B_SPADS;
} else {
ndev->reg_ofs.sdb = ndev->reg_base + SNB_SDOORBELL_OFFSET;
ndev->reg_ofs.spad_write = ndev->reg_base + SNB_SPAD_OFFSET;
@@ -644,10 +646,16 @@
rc = -ENODEV;
}
+ if (rc)
+ return rc;
+
+ dev_info(&ndev->pdev->dev, "Device Type = %s\n",
+ ndev->dev_type == NTB_DEV_USD ? "USD/DSP" : "DSD/USP");
+
/* Enable Bus Master and Memory Space on the secondary side */
writew(PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER, ndev->reg_ofs.spci_cmd);
- return rc;
+ return 0;
}
static void ntb_device_free(struct ntb_device *ndev)
@@ -992,6 +1000,28 @@
kfree(ndev->db_cb);
}
+static void ntb_setup_debugfs(struct ntb_device *ndev)
+{
+ if (!debugfs_initialized())
+ return;
+
+ if (!debugfs_dir)
+ debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
+
+ ndev->debugfs_dir = debugfs_create_dir(pci_name(ndev->pdev),
+ debugfs_dir);
+}
+
+static void ntb_free_debugfs(struct ntb_device *ndev)
+{
+ debugfs_remove_recursive(ndev->debugfs_dir);
+
+ if (debugfs_dir && simple_empty(debugfs_dir)) {
+ debugfs_remove_recursive(debugfs_dir);
+ debugfs_dir = NULL;
+ }
+}
+
static int ntb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct ntb_device *ndev;
@@ -1004,6 +1034,7 @@
ndev->pdev = pdev;
ndev->link_status = NTB_LINK_DOWN;
pci_set_drvdata(pdev, ndev);
+ ntb_setup_debugfs(ndev);
rc = pci_enable_device(pdev);
if (rc)
@@ -1100,6 +1131,7 @@
err1:
pci_disable_device(pdev);
err:
+ ntb_free_debugfs(ndev);
kfree(ndev);
dev_err(&pdev->dev, "Error loading %s module\n", KBUILD_MODNAME);
@@ -1129,6 +1161,7 @@
iounmap(ndev->reg_base);
pci_release_selected_regions(pdev, NTB_BAR_MASK);
pci_disable_device(pdev);
+ ntb_free_debugfs(ndev);
kfree(ndev);
}
diff --git a/drivers/ntb/ntb_hw.h b/drivers/ntb/ntb_hw.h
index 3a3038c..6a4f56f 100644
--- a/drivers/ntb/ntb_hw.h
+++ b/drivers/ntb/ntb_hw.h
@@ -127,6 +127,8 @@
unsigned char link_status;
struct delayed_work hb_timer;
unsigned long last_ts;
+
+ struct dentry *debugfs_dir;
};
/**
@@ -155,6 +157,20 @@
return ndev->pdev;
}
+/**
+ * ntb_query_debugfs() - return the debugfs pointer
+ * @ndev: pointer to ntb_device instance
+ *
+ * Given the ntb pointer, return the debugfs directory pointer for the NTB
+ * hardware device
+ *
+ * RETURNS: a pointer to the debugfs directory
+ */
+static inline struct dentry *ntb_query_debugfs(struct ntb_device *ndev)
+{
+ return ndev->debugfs_dir;
+}
+
struct ntb_device *ntb_register_transport(struct pci_dev *pdev,
void *transport);
void ntb_unregister_transport(struct ntb_device *ndev);
diff --git a/drivers/ntb/ntb_regs.h b/drivers/ntb/ntb_regs.h
index 5bfa8c0..96209b4 100644
--- a/drivers/ntb/ntb_regs.h
+++ b/drivers/ntb/ntb_regs.h
@@ -53,8 +53,8 @@
#define NTB_LINK_WIDTH_MASK 0x03f0
#define SNB_MSIX_CNT 4
-#define SNB_MAX_SPADS 16
-#define SNB_MAX_COMPAT_SPADS 8
+#define SNB_MAX_B2B_SPADS 16
+#define SNB_MAX_COMPAT_SPADS 16
/* Reserve the uppermost bit for link interrupt */
#define SNB_MAX_DB_BITS 15
#define SNB_DB_BITS_PER_VEC 5
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f8d7081..c308915 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -157,7 +157,6 @@
bool transport_link;
struct delayed_work link_work;
struct work_struct link_cleanup;
- struct dentry *debugfs_dir;
};
enum {
@@ -824,12 +823,12 @@
qp->tx_max_frame = min(transport_mtu, tx_size / 2);
qp->tx_max_entry = tx_size / qp->tx_max_frame;
- if (nt->debugfs_dir) {
+ if (ntb_query_debugfs(nt->ndev)) {
char debugfs_name[4];
snprintf(debugfs_name, 4, "qp%d", qp_num);
qp->debugfs_dir = debugfs_create_dir(debugfs_name,
- nt->debugfs_dir);
+ ntb_query_debugfs(nt->ndev));
qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
qp->debugfs_dir, qp,
@@ -857,11 +856,6 @@
if (!nt)
return -ENOMEM;
- if (debugfs_initialized())
- nt->debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL);
- else
- nt->debugfs_dir = NULL;
-
nt->ndev = ntb_register_transport(pdev, nt);
if (!nt->ndev) {
rc = -EIO;
@@ -907,7 +901,6 @@
err1:
ntb_unregister_transport(nt->ndev);
err:
- debugfs_remove_recursive(nt->debugfs_dir);
kfree(nt);
return rc;
}
@@ -921,16 +914,16 @@
nt->transport_link = NTB_LINK_DOWN;
/* verify that all the qp's are freed */
- for (i = 0; i < nt->max_qps; i++)
+ for (i = 0; i < nt->max_qps; i++) {
if (!test_bit(i, &nt->qp_bitmap))
ntb_transport_free_queue(&nt->qps[i]);
+ debugfs_remove_recursive(nt->qps[i].debugfs_dir);
+ }
ntb_bus_remove(nt);
cancel_delayed_work_sync(&nt->link_work);
- debugfs_remove_recursive(nt->debugfs_dir);
-
ntb_unregister_event_callback(nt->ndev);
pdev = ntb_query_pdev(nt->ndev);
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index d37bfcf..6adfa3e 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -7,14 +7,6 @@
menu "Device Tree and Open Firmware support"
depends on OF
-config PROC_DEVICETREE
- bool "Support for device tree in /proc"
- depends on PROC_FS && !SPARC
- help
- This option adds a device-tree directory under /proc which contains
- an image of the device tree that the kernel copies from Open
- Firmware or other boot firmware. If unsure, say Y here.
-
config OF_SELFTEST
bool "Device Tree Runtime self tests"
help
@@ -27,6 +19,7 @@
config OF_FLATTREE
bool
select DTC
+ select LIBFDT
config OF_EARLY_FLATTREE
bool
@@ -51,12 +44,6 @@
config OF_DEVICE
def_bool y
-config OF_I2C
- def_tristate I2C
- depends on I2C
- help
- OpenFirmware I2C accessors
-
config OF_NET
depends on NETDEVICES
def_bool y
@@ -83,4 +70,20 @@
depends on MTD
def_bool y
+config OF_RESERVED_MEM
+ depends on OF_EARLY_FLATTREE
+ bool
+ help
+ Helpers to allow for reservation of memory regions
+
+config OF_RESOLVE
+ bool
+
+config OF_OVERLAY
+ bool
+ depends on OF
+ select OF_DYNAMIC
+ select OF_DEVICE
+ select OF_RESOLVE
+
endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index e027f44..4d91616 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -1,13 +1,18 @@
obj-y = base.o
+obj-$(CONFIG_OF_DYNAMIC) += dynamic.o
obj-$(CONFIG_OF_FLATTREE) += fdt.o
obj-$(CONFIG_OF_PROMTREE) += pdt.o
obj-$(CONFIG_OF_ADDRESS) += address.o
obj-$(CONFIG_OF_IRQ) += irq.o
obj-$(CONFIG_OF_DEVICE) += device.o platform.o
-obj-$(CONFIG_OF_I2C) += of_i2c.o
obj-$(CONFIG_OF_NET) += of_net.o
obj-$(CONFIG_OF_SELFTEST) += selftest.o
obj-$(CONFIG_OF_MDIO) += of_mdio.o
obj-$(CONFIG_OF_PCI) += of_pci.o
obj-$(CONFIG_OF_PCI_IRQ) += of_pci_irq.o
obj-$(CONFIG_OF_MTD) += of_mtd.o
+obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
+obj-$(CONFIG_OF_RESOLVE) += resolver.o
+obj-$(CONFIG_OF_OVERLAY) += overlay.o
+
+CFLAGS_fdt.o = -I$(src)/../../scripts/dtc/libfdt
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 04da786..2704df1 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -69,14 +69,6 @@
(unsigned long long)cp, (unsigned long long)s,
(unsigned long long)da);
- /*
- * If the number of address cells is larger than 2 we assume the
- * mapping doesn't specify a physical address. Rather, the address
- * specifies an identifier that must match exactly.
- */
- if (na > 2 && memcmp(range, addr, na * 4) != 0)
- return OF_BAD_ADDR;
-
if (da < cp || da >= (cp + s))
return OF_BAD_ADDR;
return da - cp;
@@ -106,8 +98,13 @@
static int of_bus_pci_match(struct device_node *np)
{
- /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */
- return !strcmp(np->type, "pci") || !strcmp(np->type, "vci");
+ /*
+ * "pciex" is PCI Express
+ * "vci" is for the /chaos bridge on 1st-gen PCI powermacs
+ * "ht" is hypertransport
+ */
+ return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex") ||
+ !strcmp(np->type, "vci") || !strcmp(np->type, "ht");
}
static void of_bus_pci_count_cells(struct device_node *np,
@@ -337,6 +334,21 @@
return NULL;
}
+static int of_empty_ranges_quirk(void)
+{
+ if (IS_ENABLED(CONFIG_PPC)) {
+ /* To save cycles, we cache the result */
+ static int quirk_state = -1;
+
+ if (quirk_state < 0)
+ quirk_state =
+ of_machine_is_compatible("Power Macintosh") ||
+ of_machine_is_compatible("MacRISC");
+ return quirk_state;
+ }
+ return false;
+}
+
static int of_translate_one(struct device_node *parent, struct of_bus *bus,
struct of_bus *pbus, __be32 *addr,
int na, int ns, int pna, const char *rprop)
@@ -362,12 +374,10 @@
* This code is only enabled on powerpc. --gcl
*/
ranges = of_get_property(parent, rprop, &rlen);
-#if !defined(CONFIG_PPC)
- if (ranges == NULL) {
+ if (ranges == NULL && !of_empty_ranges_quirk()) {
pr_err("OF: no ranges; cannot translate\n");
return 1;
}
-#endif /* !defined(CONFIG_PPC) */
if (ranges == NULL || rlen == 0) {
offset = of_read_number(addr, na);
memset(addr, 0, pna * 4);
@@ -418,7 +428,7 @@
int na, ns, pna, pns;
u64 result = OF_BAD_ADDR;
- pr_debug("OF: ** translation for device %s **\n", dev->full_name);
+ pr_debug("OF: ** translation for device %s **\n", of_node_full_name(dev));
/* Increase refcount at current level */
of_node_get(dev);
@@ -433,13 +443,13 @@
bus->count_cells(dev, &na, &ns);
if (!OF_CHECK_COUNTS(na, ns)) {
printk(KERN_ERR "prom_parse: Bad cell count for %s\n",
- dev->full_name);
+ of_node_full_name(dev));
goto bail;
}
memcpy(addr, in_addr, na * 4);
pr_debug("OF: bus is %s (na=%d, ns=%d) on %s\n",
- bus->name, na, ns, parent->full_name);
+ bus->name, na, ns, of_node_full_name(parent));
of_dump_addr("OF: translating address:", addr, na);
/* Translate */
diff --git a/drivers/of/base.c b/drivers/of/base.c
index a6f584a..f066835 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -18,10 +18,13 @@
* 2 of the License, or (at your option) any later version.
*/
#include <linux/ctype.h>
+#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_graph.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
+#include <linux/string.h>
#include <linux/proc_fs.h>
#include "of_private.h"
@@ -32,8 +35,17 @@
EXPORT_SYMBOL(of_allnodes);
struct device_node *of_chosen;
struct device_node *of_aliases;
+static struct device_node *of_stdout;
-DEFINE_MUTEX(of_aliases_mutex);
+struct kset *of_kset;
+
+/*
+ * Used to protect the of_aliases, to hold off addition of nodes to sysfs.
+ * This mutex must be held whenever modifications are being made to the
+ * device tree. The of_{attach,detach}_node() and
+ * of_{add,remove,update}_property() helpers make sure this happens.
+ */
+DEFINE_MUTEX(of_mutex);
/* use when traversing tree through the allnext, child, sibling,
* or parent members of struct device_node.
@@ -72,81 +84,118 @@
}
EXPORT_SYMBOL(of_n_size_cells);
-#if defined(CONFIG_OF_DYNAMIC)
-/**
- * of_node_get - Increment refcount of a node
- * @node: Node to inc refcount, NULL is supported to
- * simplify writing of callers
- *
- * Returns node.
- */
-struct device_node *of_node_get(struct device_node *node)
+#ifndef CONFIG_OF_DYNAMIC
+static void of_node_release(struct kobject *kobj)
{
- if (node)
- kref_get(&node->kref);
- return node;
+ /* Without CONFIG_OF_DYNAMIC, no nodes gets freed */
}
-EXPORT_SYMBOL(of_node_get);
-
-static inline struct device_node *kref_to_device_node(struct kref *kref)
-{
- return container_of(kref, struct device_node, kref);
-}
-
-/**
- * of_node_release - release a dynamically allocated node
- * @kref: kref element of the node to be released
- *
- * In of_node_put() this function is passed to kref_put()
- * as the destructor.
- */
-static void of_node_release(struct kref *kref)
-{
- struct device_node *node = kref_to_device_node(kref);
- struct property *prop = node->properties;
-
- /* We should never be releasing nodes that haven't been detached. */
- if (!of_node_check_flag(node, OF_DETACHED)) {
- pr_err("ERROR: Bad of_node_put() on %s\n", node->full_name);
- dump_stack();
- kref_init(&node->kref);
- return;
- }
-
- if (!of_node_check_flag(node, OF_DYNAMIC))
- return;
-
- while (prop) {
- struct property *next = prop->next;
- kfree(prop->name);
- kfree(prop->value);
- kfree(prop);
- prop = next;
-
- if (!prop) {
- prop = node->deadprops;
- node->deadprops = NULL;
- }
- }
- kfree(node->full_name);
- kfree(node->data);
- kfree(node);
-}
-
-/**
- * of_node_put - Decrement refcount of a node
- * @node: Node to dec refcount, NULL is supported to
- * simplify writing of callers
- *
- */
-void of_node_put(struct device_node *node)
-{
- if (node)
- kref_put(&node->kref, of_node_release);
-}
-EXPORT_SYMBOL(of_node_put);
#endif /* CONFIG_OF_DYNAMIC */
+struct kobj_type of_node_ktype = {
+ .release = of_node_release,
+};
+
+static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf,
+ loff_t offset, size_t count)
+{
+ struct property *pp = container_of(bin_attr, struct property, attr);
+ return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
+}
+
+static const char *safe_name(struct kobject *kobj, const char *orig_name)
+{
+ const char *name = orig_name;
+ struct sysfs_dirent *kn;
+ int i = 0;
+
+ /* don't be a hero. After 16 tries give up */
+ while (i < 16 && (kn = sysfs_get_dirent(kobj->sd, NULL, name))) {
+ sysfs_put(kn);
+ if (name != orig_name)
+ kfree(name);
+ name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
+ }
+
+ if (name != orig_name)
+ pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
+ kobject_name(kobj), name);
+ return name;
+}
+
+int __of_add_property_sysfs(struct device_node *np, struct property *pp)
+{
+ int rc;
+
+ /* Important: Don't leak passwords */
+ bool secure = strncmp(pp->name, "security-", 9) == 0;
+
+ if (!of_kset || !of_node_is_attached(np))
+ return 0;
+
+ sysfs_bin_attr_init(&pp->attr);
+ pp->attr.attr.name = safe_name(&np->kobj, pp->name);
+ pp->attr.attr.mode = secure ? S_IRUSR : S_IRUGO;
+ pp->attr.size = secure ? 0 : pp->length;
+ pp->attr.read = of_node_property_read;
+
+ rc = sysfs_create_bin_file(&np->kobj, &pp->attr);
+ WARN(rc, "error adding attribute %s to node %s\n", pp->name, np->full_name);
+ return rc;
+}
+
+int __of_attach_node_sysfs(struct device_node *np)
+{
+ const char *name;
+ struct property *pp;
+ int rc;
+
+ if (!of_kset)
+ return 0;
+
+ np->kobj.kset = of_kset;
+ if (!np->parent) {
+ /* Nodes without parents are new top level trees */
+ rc = kobject_add(&np->kobj, NULL, safe_name(&of_kset->kobj, "base"));
+ } else {
+ name = safe_name(&np->parent->kobj, kbasename(np->full_name));
+ if (!name || !name[0])
+ return -EINVAL;
+
+ rc = kobject_add(&np->kobj, &np->parent->kobj, "%s", name);
+ }
+ if (rc)
+ return rc;
+
+ for_each_property_of_node(np, pp)
+ __of_add_property_sysfs(np, pp);
+
+ return 0;
+}
+
+static int __init of_init(void)
+{
+ struct device_node *np;
+
+ /* Create the kset, and register existing nodes */
+ mutex_lock(&of_mutex);
+ of_kset = kset_create_and_add("devicetree", NULL, firmware_kobj);
+ if (!of_kset) {
+ mutex_unlock(&of_mutex);
+ return -ENOMEM;
+ }
+ for_each_of_allnodes(np)
+ __of_attach_node_sysfs(np);
+ mutex_unlock(&of_mutex);
+
+ /* Symlink in /proc as required by userspace ABI */
+ if (of_allnodes)
+ proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base");
+
+ return 0;
+}
+core_initcall(of_init);
+
static struct property *__of_find_property(const struct device_node *np,
const char *name, int *lenp)
{
@@ -209,8 +258,8 @@
* Find a property with a given name for a given node
* and return the value.
*/
-static const void *__of_get_property(const struct device_node *np,
- const char *name, int *lenp)
+const void *__of_get_property(const struct device_node *np,
+ const char *name, int *lenp)
{
struct property *pp = __of_find_property(np, name, lenp);
@@ -230,6 +279,100 @@
}
EXPORT_SYMBOL(of_get_property);
+/*
+ * arch_match_cpu_phys_id - Match the given logical CPU and physical id
+ *
+ * @cpu: logical cpu index of a core/thread
+ * @phys_id: physical identifier of a core/thread
+ *
+ * CPU logical to physical index mapping is architecture specific.
+ * However this __weak function provides a default match of physical
+ * id to logical cpu index. phys_id provided here is usually values read
+ * from the device tree which must match the hardware internal registers.
+ *
+ * Returns true if the physical identifier and the logical cpu index
+ * correspond to the same core/thread, false otherwise.
+ */
+bool __weak arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+ return (u32)phys_id == cpu;
+}
+
+/**
+ * Checks if the given "prop_name" property holds the physical id of the
+ * core/thread corresponding to the logical cpu 'cpu'. If 'thread' is not
+ * NULL, local thread number within the core is returned in it.
+ */
+static bool __of_find_n_match_cpu_property(struct device_node *cpun,
+ const char *prop_name, int cpu, unsigned int *thread)
+{
+ const __be32 *cell;
+ int ac, prop_len, tid;
+ u64 hwid;
+
+ ac = of_n_addr_cells(cpun);
+ cell = of_get_property(cpun, prop_name, &prop_len);
+ if (!cell)
+ return false;
+ prop_len /= sizeof(*cell);
+ for (tid = 0; tid < prop_len; tid++) {
+ hwid = of_read_number(cell, ac);
+ if (arch_match_cpu_phys_id(cpu, hwid)) {
+ if (thread)
+ *thread = tid;
+ return true;
+ }
+ cell += ac;
+ }
+ return false;
+}
+
+/**
+ * of_get_cpu_node - Get device node associated with the given logical CPU
+ *
+ * @cpu: CPU number(logical index) for which device node is required
+ * @thread: if not NULL, local thread number within the physical core is
+ * returned
+ *
+ * The main purpose of this function is to retrieve the device node for the
+ * given logical CPU index. It should be used to initialize the of_node in
+ * cpu device. Once of_node in cpu device is populated, all the further
+ * references can use that instead.
+ *
+ * CPU logical to physical index mapping is architecture specific and is built
+ * before booting secondary cores. This function uses arch_match_cpu_phys_id
+ * which can be overridden by architecture specific implementation.
+ *
+ * Returns a node pointer for the logical cpu if found, else NULL.
+ */
+struct device_node *of_get_cpu_node(int cpu, unsigned int *thread)
+{
+ struct device_node *cpun, *cpus;
+
+ cpus = of_find_node_by_path("/cpus");
+ if (!cpus) {
+ pr_warn("Missing cpus node, bailing out\n");
+ return NULL;
+ }
+
+ for_each_child_of_node(cpus, cpun) {
+ if (of_node_cmp(cpun->type, "cpu"))
+ continue;
+ /* Check for non-standard "ibm,ppc-interrupt-server#s" property
+ * for thread ids on PowerPC. If it doesn't exist fallback to
+ * standard "reg" property.
+ */
+ if (IS_ENABLED(CONFIG_PPC) &&
+ __of_find_n_match_cpu_property(cpun,
+ "ibm,ppc-interrupt-server#s", cpu, thread))
+ return cpun;
+ if (__of_find_n_match_cpu_property(cpun, "reg", cpu, thread))
+ return cpun;
+ }
+ return NULL;
+}
+EXPORT_SYMBOL(of_get_cpu_node);
+
/** Checks if the given "compat" string matches one of the strings in
* the device's "compatible" property
*/
@@ -750,6 +893,38 @@
EXPORT_SYMBOL(of_find_node_by_phandle);
/**
+ * of_property_count_elems_of_size - Count the number of elements in a property
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @elem_size: size of the individual element
+ *
+ * Search for a property in a device node and count the number of elements of
+ * size elem_size in it. Returns number of elements on sucess, -EINVAL if the
+ * property does not exist or its length does not match a multiple of elem_size
+ * and -ENODATA if the property does not have a value.
+ */
+int of_property_count_elems_of_size(const struct device_node *np,
+ const char *propname, int elem_size)
+{
+ struct property *prop = of_find_property(np, propname, NULL);
+
+ if (!prop)
+ return -EINVAL;
+ if (!prop->value)
+ return -ENODATA;
+
+ if (prop->length % elem_size != 0) {
+ pr_err("size of %s in node %s is not a multiple of %d\n",
+ propname, np->full_name, elem_size);
+ return -EINVAL;
+ }
+
+ return prop->length / elem_size;
+}
+EXPORT_SYMBOL_GPL(of_property_count_elems_of_size);
+
+/**
* of_find_property_value_of_size
*
* @np: device node from which the property value is to be read.
@@ -963,52 +1138,6 @@
EXPORT_SYMBOL_GPL(of_property_read_string);
/**
- * of_property_read_string_index - Find and read a string from a multiple
- * strings property.
- * @np: device node from which the property value is to be read.
- * @propname: name of the property to be searched.
- * @index: index of the string in the list of strings
- * @out_string: pointer to null terminated return string, modified only if
- * return value is 0.
- *
- * Search for a property in a device tree node and retrieve a null
- * terminated string value (pointer to data, not a copy) in the list of strings
- * contained in that property.
- * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
- * property does not have a value, and -EILSEQ if the string is not
- * null-terminated within the length of the property data.
- *
- * The out_string pointer is modified only if a valid string can be decoded.
- */
-int of_property_read_string_index(struct device_node *np, const char *propname,
- int index, const char **output)
-{
- struct property *prop = of_find_property(np, propname, NULL);
- int i = 0;
- size_t l = 0, total = 0;
- const char *p;
-
- if (!prop)
- return -EINVAL;
- if (!prop->value)
- return -ENODATA;
- if (strnlen(prop->value, prop->length) >= prop->length)
- return -EILSEQ;
-
- p = prop->value;
-
- for (i = 0; total < prop->length; total += l, p += l) {
- l = strlen(p) + 1;
- if (i++ == index) {
- *output = p;
- return 0;
- }
- }
- return -ENODATA;
-}
-EXPORT_SYMBOL_GPL(of_property_read_string_index);
-
-/**
* of_property_match_string() - Find string in a list and return index
* @np: pointer to node containing string list property
* @propname: string list property name
@@ -1034,7 +1163,7 @@
end = p + prop->length;
for (i = 0; p < end; i++, p += l) {
- l = strlen(p) + 1;
+ l = strnlen(p, end - p) + 1;
if (p + l > end)
return -EILSEQ;
pr_debug("comparing %s with %s\n", string, p);
@@ -1046,99 +1175,46 @@
EXPORT_SYMBOL_GPL(of_property_match_string);
/**
- * of_property_count_strings - Find and return the number of strings from a
- * multiple strings property.
+ * of_property_read_string_util() - Utility helper for parsing string properties
* @np: device node from which the property value is to be read.
* @propname: name of the property to be searched.
+ * @out_strs: output array of string pointers.
+ * @sz: number of array elements to read.
+ * @skip: Number of strings to skip over at beginning of list.
*
- * Search for a property in a device tree node and retrieve the number of null
- * terminated string contain in it. Returns the number of strings on
- * success, -EINVAL if the property does not exist, -ENODATA if property
- * does not have a value, and -EILSEQ if the string is not null-terminated
- * within the length of the property data.
+ * Don't call this function directly. It is a utility helper for the
+ * of_property_read_string*() family of functions.
*/
-int of_property_count_strings(struct device_node *np, const char *propname)
+int of_property_read_string_helper(struct device_node *np, const char *propname,
+ const char **out_strs, size_t sz, int skip)
{
struct property *prop = of_find_property(np, propname, NULL);
- int i = 0;
- size_t l = 0, total = 0;
- const char *p;
+ int l = 0, i = 0;
+ const char *p, *end;
if (!prop)
return -EINVAL;
if (!prop->value)
return -ENODATA;
- if (strnlen(prop->value, prop->length) >= prop->length)
- return -EILSEQ;
-
p = prop->value;
+ end = p + prop->length;
- for (i = 0; total < prop->length; total += l, p += l, i++)
- l = strlen(p) + 1;
-
- return i;
+ for (i = 0; p < end && (!out_strs || i < skip + sz); i++, p += l) {
+ l = strnlen(p, end - p) + 1;
+ if (p + l > end)
+ return -EILSEQ;
+ if (out_strs && i >= skip)
+ *out_strs++ = p;
+ }
+ i -= skip;
+ return i <= 0 ? -ENODATA : i;
}
-EXPORT_SYMBOL_GPL(of_property_count_strings);
+EXPORT_SYMBOL_GPL(of_property_read_string_helper);
-/**
- * of_parse_phandle - Resolve a phandle property to a device_node pointer
- * @np: Pointer to device node holding phandle property
- * @phandle_name: Name of property holding a phandle value
- * @index: For properties holding a table of phandles, this is the index into
- * the table
- *
- * Returns the device_node pointer with refcount incremented. Use
- * of_node_put() on it when done.
- */
-struct device_node *of_parse_phandle(const struct device_node *np,
- const char *phandle_name, int index)
-{
- const __be32 *phandle;
- int size;
-
- phandle = of_get_property(np, phandle_name, &size);
- if ((!phandle) || (size < sizeof(*phandle) * (index + 1)))
- return NULL;
-
- return of_find_node_by_phandle(be32_to_cpup(phandle + index));
-}
-EXPORT_SYMBOL(of_parse_phandle);
-
-/**
- * of_parse_phandle_with_args() - Find a node pointed by phandle in a list
- * @np: pointer to a device tree node containing a list
- * @list_name: property name that contains a list
- * @cells_name: property name that specifies phandles' arguments count
- * @index: index of a phandle to parse out
- * @out_args: optional pointer to output arguments structure (will be filled)
- *
- * This function is useful to parse lists of phandles and their arguments.
- * Returns 0 on success and fills out_args, on error returns appropriate
- * errno value.
- *
- * Caller is responsible to call of_node_put() on the returned out_args->node
- * pointer.
- *
- * Example:
- *
- * phandle1: node1 {
- * #list-cells = <2>;
- * }
- *
- * phandle2: node2 {
- * #list-cells = <1>;
- * }
- *
- * node3 {
- * list = <&phandle1 1 2 &phandle2 3>;
- * }
- *
- * To get a device_node of the `node2' node you may call this:
- * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args);
- */
static int __of_parse_phandle_with_args(const struct device_node *np,
const char *list_name,
- const char *cells_name, int index,
+ const char *cells_name,
+ int cell_count, int index,
struct of_phandle_args *out_args)
{
const __be32 *list, *list_end;
@@ -1166,19 +1242,32 @@
if (phandle) {
/*
* Find the provider node and parse the #*-cells
- * property to determine the argument length
+ * property to determine the argument length.
+ *
+ * This is not needed if the cell count is hard-coded
+ * (i.e. cells_name not set, but cell_count is set),
+ * except when we're going to return the found node
+ * below.
*/
- node = of_find_node_by_phandle(phandle);
- if (!node) {
- pr_err("%s: could not find phandle\n",
- np->full_name);
- goto err;
+ if (cells_name || cur_index == index) {
+ node = of_find_node_by_phandle(phandle);
+ if (!node) {
+ pr_err("%s: could not find phandle\n",
+ np->full_name);
+ goto err;
+ }
}
- if (of_property_read_u32(node, cells_name, &count)) {
- pr_err("%s: could not get %s for %s\n",
- np->full_name, cells_name,
- node->full_name);
- goto err;
+
+ if (cells_name) {
+ if (of_property_read_u32(node, cells_name,
+ &count)) {
+ pr_err("%s: could not get %s for %s\n",
+ np->full_name, cells_name,
+ node->full_name);
+ goto err;
+ }
+ } else {
+ count = cell_count;
}
/*
@@ -1238,17 +1327,117 @@
return rc;
}
+/**
+ * of_parse_phandle - Resolve a phandle property to a device_node pointer
+ * @np: Pointer to device node holding phandle property
+ * @phandle_name: Name of property holding a phandle value
+ * @index: For properties holding a table of phandles, this is the index into
+ * the table
+ *
+ * Returns the device_node pointer with refcount incremented. Use
+ * of_node_put() on it when done.
+ */
+struct device_node *of_parse_phandle(const struct device_node *np,
+ const char *phandle_name, int index)
+{
+ struct of_phandle_args args;
+
+ if (index < 0)
+ return NULL;
+
+ if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0,
+ index, &args))
+ return NULL;
+
+ return args.np;
+}
+EXPORT_SYMBOL(of_parse_phandle);
+
+/**
+ * of_parse_phandle_with_args() - Find a node pointed by phandle in a list
+ * @np: pointer to a device tree node containing a list
+ * @list_name: property name that contains a list
+ * @cells_name: property name that specifies phandles' arguments count
+ * @index: index of a phandle to parse out
+ * @out_args: optional pointer to output arguments structure (will be filled)
+ *
+ * This function is useful to parse lists of phandles and their arguments.
+ * Returns 0 on success and fills out_args, on error returns appropriate
+ * errno value.
+ *
+ * Caller is responsible to call of_node_put() on the returned out_args->node
+ * pointer.
+ *
+ * Example:
+ *
+ * phandle1: node1 {
+ * #list-cells = <2>;
+ * }
+ *
+ * phandle2: node2 {
+ * #list-cells = <1>;
+ * }
+ *
+ * node3 {
+ * list = <&phandle1 1 2 &phandle2 3>;
+ * }
+ *
+ * To get a device_node of the `node2' node you may call this:
+ * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args);
+ */
int of_parse_phandle_with_args(const struct device_node *np, const char *list_name,
const char *cells_name, int index,
struct of_phandle_args *out_args)
{
if (index < 0)
return -EINVAL;
- return __of_parse_phandle_with_args(np, list_name, cells_name, index, out_args);
+ return __of_parse_phandle_with_args(np, list_name, cells_name, 0,
+ index, out_args);
}
EXPORT_SYMBOL(of_parse_phandle_with_args);
/**
+ * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list
+ * @np: pointer to a device tree node containing a list
+ * @list_name: property name that contains a list
+ * @cell_count: number of argument cells following the phandle
+ * @index: index of a phandle to parse out
+ * @out_args: optional pointer to output arguments structure (will be filled)
+ *
+ * This function is useful to parse lists of phandles and their arguments.
+ * Returns 0 on success and fills out_args, on error returns appropriate
+ * errno value.
+ *
+ * Caller is responsible to call of_node_put() on the returned out_args->node
+ * pointer.
+ *
+ * Example:
+ *
+ * phandle1: node1 {
+ * }
+ *
+ * phandle2: node2 {
+ * }
+ *
+ * node3 {
+ * list = <&phandle1 0 2 &phandle2 2 3>;
+ * }
+ *
+ * To get a device_node of the `node2' node you may call this:
+ * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args);
+ */
+int of_parse_phandle_with_fixed_args(const struct device_node *np,
+ const char *list_name, int cell_count,
+ int index, struct of_phandle_args *out_args)
+{
+ if (index < 0)
+ return -EINVAL;
+ return __of_parse_phandle_with_args(np, list_name, NULL, cell_count,
+ index, out_args);
+}
+EXPORT_SYMBOL(of_parse_phandle_with_fixed_args);
+
+/**
* of_count_phandle_with_args() - Find the number of phandles references in a property
* @np: pointer to a device tree node containing a list
* @list_name: property name that contains a list
@@ -1266,64 +1455,83 @@
int of_count_phandle_with_args(const struct device_node *np, const char *list_name,
const char *cells_name)
{
- return __of_parse_phandle_with_args(np, list_name, cells_name, -1, NULL);
+ return __of_parse_phandle_with_args(np, list_name, cells_name, 0, -1,
+ NULL);
}
EXPORT_SYMBOL(of_count_phandle_with_args);
-#if defined(CONFIG_OF_DYNAMIC)
-static int of_property_notify(int action, struct device_node *np,
- struct property *prop)
+/**
+ * __of_add_property - Add a property to a node without lock operations
+ */
+int __of_add_property(struct device_node *np, struct property *prop)
{
- struct of_prop_reconfig pr;
+ struct property **next;
- pr.dn = np;
- pr.prop = prop;
- return of_reconfig_notify(action, &pr);
-}
-#else
-static int of_property_notify(int action, struct device_node *np,
- struct property *prop)
-{
+ prop->next = NULL;
+ next = &np->properties;
+ while (*next) {
+ if (strcmp(prop->name, (*next)->name) == 0)
+ /* duplicate ! don't insert it */
+ return -EEXIST;
+
+ next = &(*next)->next;
+ }
+ *next = prop;
+
return 0;
}
-#endif
/**
* of_add_property - Add a property to a node
*/
int of_add_property(struct device_node *np, struct property *prop)
{
- struct property **next;
unsigned long flags;
int rc;
- rc = of_property_notify(OF_RECONFIG_ADD_PROPERTY, np, prop);
- if (rc)
- return rc;
+ mutex_lock(&of_mutex);
- prop->next = NULL;
raw_spin_lock_irqsave(&devtree_lock, flags);
- next = &np->properties;
- while (*next) {
- if (strcmp(prop->name, (*next)->name) == 0) {
- /* duplicate ! don't insert it */
- raw_spin_unlock_irqrestore(&devtree_lock, flags);
- return -1;
- }
- next = &(*next)->next;
- }
- *next = prop;
+ rc = __of_add_property(np, prop);
raw_spin_unlock_irqrestore(&devtree_lock, flags);
-#ifdef CONFIG_PROC_DEVICETREE
- /* try to add to proc as well if it was initialized */
- if (np->pde)
- proc_device_tree_add_prop(np->pde, prop);
-#endif /* CONFIG_PROC_DEVICETREE */
+ if (!rc)
+ __of_add_property_sysfs(np, prop);
+
+ mutex_unlock(&of_mutex);
+
+ if (!rc)
+ of_property_notify(OF_RECONFIG_ADD_PROPERTY, np, prop, NULL);
+
+ return rc;
+}
+
+int __of_remove_property(struct device_node *np, struct property *prop)
+{
+ struct property **next;
+
+ for (next = &np->properties; *next; next = &(*next)->next) {
+ if (*next == prop)
+ break;
+ }
+ if (*next == NULL)
+ return -ENODEV;
+
+ /* found the node */
+ *next = prop->next;
+ prop->next = np->deadprops;
+ np->deadprops = prop;
return 0;
}
+void __of_remove_property_sysfs(struct device_node *np, struct property *prop)
+{
+ /* at early boot, bail here and defer setup to of_init() */
+ if (of_kset && of_node_is_attached(np))
+ sysfs_remove_bin_file(&np->kobj, &prop->attr);
+}
+
/**
* of_remove_property - Remove a property from a node.
*
@@ -1334,42 +1542,64 @@
*/
int of_remove_property(struct device_node *np, struct property *prop)
{
- struct property **next;
unsigned long flags;
- int found = 0;
int rc;
- rc = of_property_notify(OF_RECONFIG_REMOVE_PROPERTY, np, prop);
- if (rc)
- return rc;
+ mutex_lock(&of_mutex);
raw_spin_lock_irqsave(&devtree_lock, flags);
- next = &np->properties;
- while (*next) {
- if (*next == prop) {
- /* found the node */
- *next = prop->next;
- prop->next = np->deadprops;
- np->deadprops = prop;
- found = 1;
- break;
- }
- next = &(*next)->next;
- }
+ rc = __of_remove_property(np, prop);
raw_spin_unlock_irqrestore(&devtree_lock, flags);
- if (!found)
- return -ENODEV;
+ if (!rc)
+ __of_remove_property_sysfs(np, prop);
-#ifdef CONFIG_PROC_DEVICETREE
- /* try to remove the proc node as well */
- if (np->pde)
- proc_device_tree_remove_prop(np->pde, prop);
-#endif /* CONFIG_PROC_DEVICETREE */
+ mutex_unlock(&of_mutex);
+
+ if (!rc)
+ of_property_notify(OF_RECONFIG_REMOVE_PROPERTY, np, prop, NULL);
+
+ return rc;
+}
+
+int __of_update_property(struct device_node *np, struct property *newprop,
+ struct property **oldpropp)
+{
+ struct property **next, *oldprop;
+
+ for (next = &np->properties; *next; next = &(*next)->next) {
+ if (of_prop_cmp((*next)->name, newprop->name) == 0)
+ break;
+ }
+ *oldpropp = oldprop = *next;
+
+ if (oldprop) {
+ /* replace the node */
+ newprop->next = oldprop->next;
+ *next = newprop;
+ oldprop->next = np->deadprops;
+ np->deadprops = oldprop;
+ } else {
+ /* new node */
+ newprop->next = NULL;
+ *next = newprop;
+ }
return 0;
}
+void __of_update_property_sysfs(struct device_node *np, struct property *newprop,
+ struct property *oldprop)
+{
+ /* At early boot, bail out and defer setup to of_init() */
+ if (!of_kset)
+ return;
+
+ if (oldprop)
+ sysfs_remove_bin_file(&np->kobj, &oldprop->attr);
+ __of_add_property_sysfs(np, newprop);
+}
+
/*
* of_update_property - Update a property in a node, if the property does
* not exist, add it.
@@ -1381,190 +1611,29 @@
*/
int of_update_property(struct device_node *np, struct property *newprop)
{
- struct property **next, *oldprop;
+ struct property *oldprop;
unsigned long flags;
- int rc, found = 0;
-
- rc = of_property_notify(OF_RECONFIG_UPDATE_PROPERTY, np, newprop);
- if (rc)
- return rc;
+ int rc;
if (!newprop->name)
return -EINVAL;
- oldprop = of_find_property(np, newprop->name, NULL);
- if (!oldprop)
- return of_add_property(np, newprop);
+ mutex_lock(&of_mutex);
raw_spin_lock_irqsave(&devtree_lock, flags);
- next = &np->properties;
- while (*next) {
- if (*next == oldprop) {
- /* found the node */
- newprop->next = oldprop->next;
- *next = newprop;
- oldprop->next = np->deadprops;
- np->deadprops = oldprop;
- found = 1;
- break;
- }
- next = &(*next)->next;
- }
+ rc = __of_update_property(np, newprop, &oldprop);
raw_spin_unlock_irqrestore(&devtree_lock, flags);
- if (!found)
- return -ENODEV;
+ if (!rc)
+ __of_update_property_sysfs(np, newprop, oldprop);
-#ifdef CONFIG_PROC_DEVICETREE
- /* try to add to proc as well if it was initialized */
- if (np->pde)
- proc_device_tree_update_prop(np->pde, newprop, oldprop);
-#endif /* CONFIG_PROC_DEVICETREE */
+ mutex_unlock(&of_mutex);
- return 0;
-}
+ if (!rc)
+ of_property_notify(OF_RECONFIG_UPDATE_PROPERTY, np, newprop, oldprop);
-#if defined(CONFIG_OF_DYNAMIC)
-/*
- * Support for dynamic device trees.
- *
- * On some platforms, the device tree can be manipulated at runtime.
- * The routines in this section support adding, removing and changing
- * device tree nodes.
- */
-
-static BLOCKING_NOTIFIER_HEAD(of_reconfig_chain);
-
-int of_reconfig_notifier_register(struct notifier_block *nb)
-{
- return blocking_notifier_chain_register(&of_reconfig_chain, nb);
-}
-EXPORT_SYMBOL_GPL(of_reconfig_notifier_register);
-
-int of_reconfig_notifier_unregister(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&of_reconfig_chain, nb);
-}
-EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister);
-
-int of_reconfig_notify(unsigned long action, void *p)
-{
- int rc;
-
- rc = blocking_notifier_call_chain(&of_reconfig_chain, action, p);
- return notifier_to_errno(rc);
-}
-
-#ifdef CONFIG_PROC_DEVICETREE
-static void of_add_proc_dt_entry(struct device_node *dn)
-{
- struct proc_dir_entry *ent;
-
- ent = proc_mkdir(strrchr(dn->full_name, '/') + 1, dn->parent->pde);
- if (ent)
- proc_device_tree_add_node(dn, ent);
-}
-#else
-static void of_add_proc_dt_entry(struct device_node *dn)
-{
- return;
-}
-#endif
-
-/**
- * of_attach_node - Plug a device node into the tree and global list.
- */
-int of_attach_node(struct device_node *np)
-{
- unsigned long flags;
- int rc;
-
- rc = of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, np);
- if (rc)
- return rc;
-
- raw_spin_lock_irqsave(&devtree_lock, flags);
- np->sibling = np->parent->child;
- np->allnext = of_allnodes;
- np->parent->child = np;
- of_allnodes = np;
- raw_spin_unlock_irqrestore(&devtree_lock, flags);
-
- of_add_proc_dt_entry(np);
- return 0;
-}
-
-#ifdef CONFIG_PROC_DEVICETREE
-static void of_remove_proc_dt_entry(struct device_node *dn)
-{
- proc_remove(dn->pde);
-}
-#else
-static void of_remove_proc_dt_entry(struct device_node *dn)
-{
- return;
-}
-#endif
-
-/**
- * of_detach_node - "Unplug" a node from the device tree.
- *
- * The caller must hold a reference to the node. The memory associated with
- * the node is not freed until its refcount goes to zero.
- */
-int of_detach_node(struct device_node *np)
-{
- struct device_node *parent;
- unsigned long flags;
- int rc = 0;
-
- rc = of_reconfig_notify(OF_RECONFIG_DETACH_NODE, np);
- if (rc)
- return rc;
-
- raw_spin_lock_irqsave(&devtree_lock, flags);
-
- if (of_node_check_flag(np, OF_DETACHED)) {
- /* someone already detached it */
- raw_spin_unlock_irqrestore(&devtree_lock, flags);
- return rc;
- }
-
- parent = np->parent;
- if (!parent) {
- raw_spin_unlock_irqrestore(&devtree_lock, flags);
- return rc;
- }
-
- if (of_allnodes == np)
- of_allnodes = np->allnext;
- else {
- struct device_node *prev;
- for (prev = of_allnodes;
- prev->allnext != np;
- prev = prev->allnext)
- ;
- prev->allnext = np->allnext;
- }
-
- if (parent->child == np)
- parent->child = np->sibling;
- else {
- struct device_node *prevsib;
- for (prevsib = np->parent->child;
- prevsib->sibling != np;
- prevsib = prevsib->sibling)
- ;
- prevsib->sibling = np->sibling;
- }
-
- of_node_set_flag(np, OF_DETACHED);
- raw_spin_unlock_irqrestore(&devtree_lock, flags);
-
- of_remove_proc_dt_entry(np);
return rc;
}
-#endif /* defined(CONFIG_OF_DYNAMIC) */
static void of_alias_add(struct alias_prop *ap, struct device_node *np,
int id, const char *stem, int stem_len)
@@ -1595,6 +1664,15 @@
of_chosen = of_find_node_by_path("/chosen");
if (of_chosen == NULL)
of_chosen = of_find_node_by_path("/chosen@0");
+
+ if (of_chosen) {
+ const char *name;
+
+ name = of_get_property(of_chosen, "linux,stdout-path", NULL);
+ if (name)
+ of_stdout = of_find_node_by_path(name);
+ }
+
of_aliases = of_find_node_by_path("/aliases");
if (!of_aliases)
return;
@@ -1629,6 +1707,7 @@
ap = dt_alloc(sizeof(*ap) + len + 1, 4);
if (!ap)
continue;
+ memset(ap, 0, sizeof(*ap) + len + 1);
ap->alias = start;
of_alias_add(ap, np, id, start, len);
}
@@ -1647,7 +1726,7 @@
struct alias_prop *app;
int id = -ENODEV;
- mutex_lock(&of_aliases_mutex);
+ mutex_lock(&of_mutex);
list_for_each_entry(app, &aliases_lookup, link) {
if (strcmp(app->stem, stem) != 0)
continue;
@@ -1657,7 +1736,7 @@
break;
}
}
- mutex_unlock(&of_aliases_mutex);
+ mutex_unlock(&of_mutex);
return id;
}
@@ -1703,3 +1782,170 @@
return curv;
}
EXPORT_SYMBOL_GPL(of_prop_next_string);
+
+/**
+ * of_device_is_stdout_path - check if a device node matches the
+ * linux,stdout-path property
+ *
+ * Check if this device node matches the linux,stdout-path property
+ * in the chosen node. return true if yes, false otherwise.
+ */
+int of_device_is_stdout_path(struct device_node *dn)
+{
+ if (!of_stdout)
+ return false;
+
+ return of_stdout == dn;
+}
+EXPORT_SYMBOL_GPL(of_device_is_stdout_path);
+
+/**
+ * of_graph_parse_endpoint() - parse common endpoint node properties
+ * @node: pointer to endpoint device_node
+ * @endpoint: pointer to the OF endpoint data structure
+ *
+ * The caller should hold a reference to @node.
+ */
+int of_graph_parse_endpoint(const struct device_node *node,
+ struct of_endpoint *endpoint)
+{
+ struct device_node *port_node = of_get_parent(node);
+
+ WARN_ONCE(!port_node, "%s(): endpoint %s has no parent node\n",
+ __func__, node->full_name);
+
+ memset(endpoint, 0, sizeof(*endpoint));
+
+ endpoint->local_node = node;
+ /*
+ * It doesn't matter whether the two calls below succeed.
+ * If they don't then the default value 0 is used.
+ */
+ of_property_read_u32(port_node, "reg", &endpoint->port);
+ of_property_read_u32(node, "reg", &endpoint->id);
+
+ of_node_put(port_node);
+
+ return 0;
+}
+EXPORT_SYMBOL(of_graph_parse_endpoint);
+
+/**
+ * of_graph_get_next_endpoint() - get next endpoint node
+ * @parent: pointer to the parent device node
+ * @prev: previous endpoint node, or NULL to get first
+ *
+ * Return: An 'endpoint' node pointer with refcount incremented. Refcount
+ * of the passed @prev node is not decremented, the caller have to use
+ * of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+ struct device_node *prev)
+{
+ struct device_node *endpoint;
+ struct device_node *port;
+
+ if (!parent)
+ return NULL;
+
+ /*
+ * Start by locating the port node. If no previous endpoint is specified
+ * search for the first port node, otherwise get the previous endpoint
+ * parent port node.
+ */
+ if (!prev) {
+ struct device_node *node;
+
+ node = of_get_child_by_name(parent, "ports");
+ if (node)
+ parent = node;
+
+ port = of_get_child_by_name(parent, "port");
+ of_node_put(node);
+
+ if (!port) {
+ pr_err("%s(): no port node found in %s\n",
+ __func__, parent->full_name);
+ return NULL;
+ }
+ } else {
+ port = of_get_parent(prev);
+ if (WARN_ONCE(!port, "%s(): endpoint %s has no parent node\n",
+ __func__, prev->full_name))
+ return NULL;
+
+ /*
+ * Avoid dropping prev node refcount to 0 when getting the next
+ * child below.
+ */
+ of_node_get(prev);
+ }
+
+ while (1) {
+ /*
+ * Now that we have a port node, get the next endpoint by
+ * getting the next child. If the previous endpoint is NULL this
+ * will return the first child.
+ */
+ endpoint = of_get_next_child(port, prev);
+ if (endpoint) {
+ of_node_put(port);
+ return endpoint;
+ }
+
+ /* No more endpoints under this port, try the next one. */
+ prev = NULL;
+
+ do {
+ port = of_get_next_child(parent, port);
+ if (!port)
+ return NULL;
+ } while (of_node_cmp(port->name, "port"));
+ }
+}
+EXPORT_SYMBOL(of_graph_get_next_endpoint);
+
+/**
+ * of_graph_get_remote_port_parent() - get remote port's parent node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote device node associated with remote endpoint node linked
+ * to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port_parent(
+ const struct device_node *node)
+{
+ struct device_node *np;
+ unsigned int depth;
+
+ /* Get remote endpoint node. */
+ np = of_parse_phandle(node, "remote-endpoint", 0);
+
+ /* Walk 3 levels up only if there is 'ports' node. */
+ for (depth = 3; depth && np; depth--) {
+ np = of_get_next_parent(np);
+ if (depth == 2 && of_node_cmp(np->name, "ports"))
+ break;
+ }
+ return np;
+}
+EXPORT_SYMBOL(of_graph_get_remote_port_parent);
+
+/**
+ * of_graph_get_remote_port() - get remote port node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote port node associated with remote endpoint node linked
+ * to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port(const struct device_node *node)
+{
+ struct device_node *np;
+
+ /* Get remote endpoint node. */
+ np = of_parse_phandle(node, "remote-endpoint", 0);
+ if (!np)
+ return NULL;
+ return of_get_next_parent(np);
+}
+EXPORT_SYMBOL(of_graph_get_remote_port);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index f685e55..4f942b5 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -157,7 +157,7 @@
add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen);
seen = 0;
- mutex_lock(&of_aliases_mutex);
+ mutex_lock(&of_mutex);
list_for_each_entry(app, &aliases_lookup, link) {
if (dev->of_node == app->np) {
add_uevent_var(env, "OF_ALIAS_%d=%s", seen,
@@ -165,7 +165,7 @@
seen++;
}
}
- mutex_unlock(&of_aliases_mutex);
+ mutex_unlock(&of_mutex);
}
int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env)
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
new file mode 100644
index 0000000..16524c8
--- /dev/null
+++ b/drivers/of/dynamic.c
@@ -0,0 +1,791 @@
+/*
+ * Support for dynamic device trees.
+ *
+ * On some platforms, the device tree can be manipulated at runtime.
+ * The routines in this section support adding, removing and changing
+ * device tree nodes.
+ */
+
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/proc_fs.h>
+
+#include "of_private.h"
+
+/**
+ * of_node_get() - Increment refcount of a node
+ * @node: Node to inc refcount, NULL is supported to simplify writing of
+ * callers
+ *
+ * Returns node.
+ */
+struct device_node *of_node_get(struct device_node *node)
+{
+ if (node)
+ kobject_get(&node->kobj);
+ return node;
+}
+EXPORT_SYMBOL(of_node_get);
+
+/**
+ * of_node_put() - Decrement refcount of a node
+ * @node: Node to dec refcount, NULL is supported to simplify writing of
+ * callers
+ */
+void of_node_put(struct device_node *node)
+{
+ if (node)
+ kobject_put(&node->kobj);
+}
+EXPORT_SYMBOL(of_node_put);
+
+void __of_detach_node_sysfs(struct device_node *np)
+{
+ struct property *pp;
+
+ BUG_ON(!of_node_is_initialized(np));
+ if (!of_kset)
+ return;
+
+ /* only remove properties if on sysfs */
+ if (of_node_is_attached(np)) {
+ for_each_property_of_node(np, pp)
+ sysfs_remove_bin_file(&np->kobj, &pp->attr);
+ kobject_del(&np->kobj);
+ }
+
+ /* finally remove the kobj_init ref */
+ of_node_put(np);
+}
+
+static BLOCKING_NOTIFIER_HEAD(of_reconfig_chain);
+
+int of_reconfig_notifier_register(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&of_reconfig_chain, nb);
+}
+EXPORT_SYMBOL_GPL(of_reconfig_notifier_register);
+
+int of_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&of_reconfig_chain, nb);
+}
+EXPORT_SYMBOL_GPL(of_reconfig_notifier_unregister);
+
+#ifdef DEBUG
+const char *action_names[] = {
+ [OF_RECONFIG_ATTACH_NODE] = "ATTACH_NODE",
+ [OF_RECONFIG_DETACH_NODE] = "DETACH_NODE",
+ [OF_RECONFIG_ADD_PROPERTY] = "ADD_PROPERTY",
+ [OF_RECONFIG_REMOVE_PROPERTY] = "REMOVE_PROPERTY",
+ [OF_RECONFIG_UPDATE_PROPERTY] = "UPDATE_PROPERTY",
+};
+#endif
+
+int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p)
+{
+ int rc;
+#ifdef DEBUG
+ struct of_reconfig_data *pr = p;
+
+ switch (action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ case OF_RECONFIG_DETACH_NODE:
+ pr_debug("of/notify %-15s %s\n", action_names[action],
+ pr->dn->full_name);
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ pr_debug("of/notify %-15s %s:%s\n", action_names[action],
+ pr->dn->full_name, pr->prop->name);
+ break;
+
+ }
+#endif
+ rc = blocking_notifier_call_chain(&of_reconfig_chain, action, p);
+ return notifier_to_errno(rc);
+}
+
+/*
+ * of_reconfig_get_state_change() - Returns new state of device
+ * @action - action of the of notifier
+ * @arg - argument of the of notifier
+ *
+ * Returns the new state of a device based on the notifier used.
+ * Returns 0 on device going from enabled to disabled, 1 on device
+ * going from disabled to enabled and -1 on no change.
+ */
+int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr)
+{
+ struct property *prop, *old_prop = NULL;
+ int is_status, status_state, old_status_state, prev_state, new_state;
+
+ /* figure out if a device should be created or destroyed */
+ switch (action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ case OF_RECONFIG_DETACH_NODE:
+ prop = of_find_property(pr->dn, "status", NULL);
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ prop = pr->prop;
+ break;
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ prop = pr->prop;
+ old_prop = pr->old_prop;
+ break;
+ default:
+ return OF_RECONFIG_NO_CHANGE;
+ }
+
+ is_status = 0;
+ status_state = -1;
+ old_status_state = -1;
+ prev_state = -1;
+ new_state = -1;
+
+ if (prop && !strcmp(prop->name, "status")) {
+ is_status = 1;
+ status_state = !strcmp(prop->value, "okay") ||
+ !strcmp(prop->value, "ok");
+ if (old_prop)
+ old_status_state = !strcmp(old_prop->value, "okay") ||
+ !strcmp(old_prop->value, "ok");
+ }
+
+ switch (action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ prev_state = 0;
+ /* -1 & 0 status either missing or okay */
+ new_state = status_state != 0;
+ break;
+ case OF_RECONFIG_DETACH_NODE:
+ /* -1 & 0 status either missing or okay */
+ prev_state = status_state != 0;
+ new_state = 0;
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ if (is_status) {
+ /* no status property -> enabled (legacy) */
+ prev_state = 1;
+ new_state = status_state;
+ }
+ break;
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ if (is_status) {
+ prev_state = status_state;
+ /* no status property -> enabled (legacy) */
+ new_state = 1;
+ }
+ break;
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ if (is_status) {
+ prev_state = old_status_state != 0;
+ new_state = status_state != 0;
+ }
+ break;
+ }
+
+ if (prev_state == new_state)
+ return OF_RECONFIG_NO_CHANGE;
+
+ return new_state ? OF_RECONFIG_CHANGE_ADD : OF_RECONFIG_CHANGE_REMOVE;
+}
+EXPORT_SYMBOL_GPL(of_reconfig_get_state_change);
+
+int of_property_notify(int action, struct device_node *np,
+ struct property *prop, struct property *oldprop)
+{
+ struct of_reconfig_data pr;
+
+ /* only call notifiers if the node is attached */
+ if (!of_node_is_attached(np))
+ return 0;
+
+ pr.dn = np;
+ pr.prop = prop;
+ pr.old_prop = oldprop;
+ return of_reconfig_notify(action, &pr);
+}
+
+void __of_attach_node(struct device_node *np)
+{
+ const __be32 *phandle;
+ int sz;
+
+ np->name = __of_get_property(np, "name", NULL) ? : "<NULL>";
+ np->type = __of_get_property(np, "device_type", NULL) ? : "<NULL>";
+
+ phandle = __of_get_property(np, "phandle", &sz);
+ if (!phandle)
+ phandle = __of_get_property(np, "linux,phandle", &sz);
+ if (IS_ENABLED(PPC_PSERIES) && !phandle)
+ phandle = __of_get_property(np, "ibm,phandle", &sz);
+ np->phandle = (phandle && (sz >= 4)) ? be32_to_cpup(phandle) : 0;
+
+ np->child = NULL;
+ np->sibling = np->parent->child;
+ np->allnext = np->parent->allnext;
+ np->parent->allnext = np;
+ np->parent->child = np;
+ of_node_clear_flag(np, OF_DETACHED);
+}
+
+/**
+ * of_attach_node() - Plug a device node into the tree and global list.
+ */
+int of_attach_node(struct device_node *np)
+{
+ struct of_reconfig_data rd;
+ unsigned long flags;
+
+ memset(&rd, 0, sizeof(rd));
+ rd.dn = np;
+
+ mutex_lock(&of_mutex);
+ raw_spin_lock_irqsave(&devtree_lock, flags);
+ __of_attach_node(np);
+ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ __of_attach_node_sysfs(np);
+ mutex_unlock(&of_mutex);
+
+ of_reconfig_notify(OF_RECONFIG_ATTACH_NODE, &rd);
+
+ return 0;
+}
+
+void __of_detach_node(struct device_node *np)
+{
+ struct device_node *parent;
+
+ if (WARN_ON(of_node_check_flag(np, OF_DETACHED)))
+ return;
+
+ parent = np->parent;
+ if (WARN_ON(!parent))
+ return;
+
+ if (of_allnodes == np)
+ of_allnodes = np->allnext;
+ else {
+ struct device_node *prev;
+ for (prev = of_allnodes;
+ prev->allnext != np;
+ prev = prev->allnext)
+ ;
+ prev->allnext = np->allnext;
+ }
+
+ if (parent->child == np)
+ parent->child = np->sibling;
+ else {
+ struct device_node *prevsib;
+ for (prevsib = np->parent->child;
+ prevsib->sibling != np;
+ prevsib = prevsib->sibling)
+ ;
+ prevsib->sibling = np->sibling;
+ }
+
+ of_node_set_flag(np, OF_DETACHED);
+}
+
+/**
+ * of_detach_node() - "Unplug" a node from the device tree.
+ *
+ * The caller must hold a reference to the node. The memory associated with
+ * the node is not freed until its refcount goes to zero.
+ */
+int of_detach_node(struct device_node *np)
+{
+ struct of_reconfig_data rd;
+ unsigned long flags;
+ int rc = 0;
+
+ memset(&rd, 0, sizeof(rd));
+ rd.dn = np;
+
+ mutex_lock(&of_mutex);
+ raw_spin_lock_irqsave(&devtree_lock, flags);
+ __of_detach_node(np);
+ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ __of_detach_node_sysfs(np);
+ mutex_unlock(&of_mutex);
+
+ of_reconfig_notify(OF_RECONFIG_DETACH_NODE, &rd);
+
+ return rc;
+}
+
+/**
+ * of_node_release() - release a dynamically allocated node
+ * @kref: kref element of the node to be released
+ *
+ * In of_node_put() this function is passed to kref_put() as the destructor.
+ */
+void of_node_release(struct kobject *kobj)
+{
+ struct device_node *node = kobj_to_device_node(kobj);
+ struct property *prop = node->properties;
+
+ /* We should never be releasing nodes that haven't been detached. */
+ if (!of_node_check_flag(node, OF_DETACHED)) {
+ pr_err("ERROR: Bad of_node_put() on %s\n", node->full_name);
+ dump_stack();
+ return;
+ }
+
+ if (!of_node_check_flag(node, OF_DYNAMIC))
+ return;
+
+ while (prop) {
+ struct property *next = prop->next;
+ kfree(prop->name);
+ kfree(prop->value);
+ kfree(prop);
+ prop = next;
+
+ if (!prop) {
+ prop = node->deadprops;
+ node->deadprops = NULL;
+ }
+ }
+ kfree(node->full_name);
+ kfree(node->data);
+ kfree(node);
+}
+
+/**
+ * __of_prop_dup - Copy a property dynamically.
+ * @prop: Property to copy
+ * @allocflags: Allocation flags (typically pass GFP_KERNEL)
+ *
+ * Copy a property by dynamically allocating the memory of both the
+ * property stucture and the property name & contents. The property's
+ * flags have the OF_DYNAMIC bit set so that we can differentiate between
+ * dynamically allocated properties and not.
+ * Returns the newly allocated property or NULL on out of memory error.
+ */
+struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags)
+{
+ struct property *new;
+
+ new = kzalloc(sizeof(*new), allocflags);
+ if (!new)
+ return NULL;
+
+ /*
+ * NOTE: There is no check for zero length value.
+ * In case of a boolean property This will allocate a value
+ * of zero bytes. We do this to work around the use
+ * of of_get_property() calls on boolean values.
+ */
+ new->name = kstrdup(prop->name, allocflags);
+ new->value = kmemdup(prop->value, prop->length, allocflags);
+ new->length = prop->length;
+ if (!new->name || !new->value)
+ goto err_free;
+
+ /* mark the property as dynamic */
+ of_property_set_flag(new, OF_DYNAMIC);
+
+ return new;
+
+ err_free:
+ kfree(new->name);
+ kfree(new->value);
+ kfree(new);
+ return NULL;
+}
+
+/**
+ * __of_node_dup() - Duplicate or create an empty device node dynamically.
+ * @fmt: Format string (plus vargs) for new full name of the device node
+ *
+ * Create an device tree node, either by duplicating an empty node or by allocating
+ * an empty one suitable for further modification. The node data are
+ * dynamically allocated and all the node flags have the OF_DYNAMIC &
+ * OF_DETACHED bits set. Returns the newly allocated node or NULL on out of
+ * memory error.
+ */
+struct device_node *__of_node_dup(const struct device_node *np, const char *fmt, ...)
+{
+ va_list vargs;
+ struct device_node *node;
+
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
+ if (!node)
+ return NULL;
+ va_start(vargs, fmt);
+ node->full_name = kvasprintf(GFP_KERNEL, fmt, vargs);
+ va_end(vargs);
+ if (!node->full_name) {
+ kfree(node);
+ return NULL;
+ }
+
+ of_node_set_flag(node, OF_DYNAMIC);
+ of_node_set_flag(node, OF_DETACHED);
+ of_node_init(node);
+
+ /* Iterate over and duplicate all properties */
+ if (np) {
+ struct property *pp, *new_pp;
+ for_each_property_of_node(np, pp) {
+ new_pp = __of_prop_dup(pp, GFP_KERNEL);
+ if (!new_pp)
+ goto err_prop;
+ if (__of_add_property(node, new_pp)) {
+ kfree(new_pp->name);
+ kfree(new_pp->value);
+ kfree(new_pp);
+ goto err_prop;
+ }
+ }
+ }
+ return node;
+
+ err_prop:
+ of_node_put(node); /* Frees the node and properties */
+ return NULL;
+}
+
+static void __of_changeset_entry_destroy(struct of_changeset_entry *ce)
+{
+ of_node_put(ce->np);
+ list_del(&ce->node);
+ kfree(ce);
+}
+
+#ifdef DEBUG
+static void __of_changeset_entry_dump(struct of_changeset_entry *ce)
+{
+ switch (ce->action) {
+ case OF_RECONFIG_ADD_PROPERTY:
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ pr_debug("of/cset<%p> %-15s %s/%s\n", ce, action_names[ce->action],
+ ce->np->full_name, ce->prop->name);
+ break;
+ case OF_RECONFIG_ATTACH_NODE:
+ case OF_RECONFIG_DETACH_NODE:
+ pr_debug("of/cset<%p> %-15s %s\n", ce, action_names[ce->action],
+ ce->np->full_name);
+ break;
+ }
+}
+#else
+static inline void __of_changeset_entry_dump(struct of_changeset_entry *ce)
+{
+ /* empty */
+}
+#endif
+
+static void __of_changeset_entry_invert(struct of_changeset_entry *ce,
+ struct of_changeset_entry *rce)
+{
+ memcpy(rce, ce, sizeof(*rce));
+
+ switch (ce->action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ rce->action = OF_RECONFIG_DETACH_NODE;
+ break;
+ case OF_RECONFIG_DETACH_NODE:
+ rce->action = OF_RECONFIG_ATTACH_NODE;
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ rce->action = OF_RECONFIG_REMOVE_PROPERTY;
+ break;
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ rce->action = OF_RECONFIG_ADD_PROPERTY;
+ break;
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ rce->old_prop = ce->prop;
+ rce->prop = ce->old_prop;
+ break;
+ }
+}
+
+static void __of_changeset_entry_notify(struct of_changeset_entry *ce, bool revert)
+{
+ struct of_reconfig_data rd;
+ struct of_changeset_entry ce_inverted;
+ int ret;
+
+ if (revert) {
+ __of_changeset_entry_invert(ce, &ce_inverted);
+ ce = &ce_inverted;
+ }
+
+ switch (ce->action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ case OF_RECONFIG_DETACH_NODE:
+ memset(&rd, 0, sizeof(rd));
+ rd.dn = ce->np;
+ ret = of_reconfig_notify(ce->action, &rd);
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ ret = of_property_notify(ce->action, ce->np, ce->prop, ce->old_prop);
+ break;
+ default:
+ pr_err("%s: invalid devicetree changeset action: %i\n", __func__,
+ (int)ce->action);
+ return;
+ }
+
+ if (ret)
+ pr_err("%s: notifier error @%s\n", __func__, ce->np->full_name);
+}
+
+static int __of_changeset_entry_apply(struct of_changeset_entry *ce)
+{
+ struct property *old_prop, **propp;
+ unsigned long flags;
+ int ret = 0;
+
+ __of_changeset_entry_dump(ce);
+
+ raw_spin_lock_irqsave(&devtree_lock, flags);
+ switch (ce->action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ __of_attach_node(ce->np);
+ break;
+ case OF_RECONFIG_DETACH_NODE:
+ __of_detach_node(ce->np);
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ /* If the property is in deadprops then it must be removed */
+ for (propp = &ce->np->deadprops; *propp; propp = &(*propp)->next) {
+ if (*propp == ce->prop) {
+ *propp = ce->prop->next;
+ ce->prop->next = NULL;
+ break;
+ }
+ }
+
+ ret = __of_add_property(ce->np, ce->prop);
+ if (ret) {
+ pr_err("%s: add_property failed @%s/%s\n",
+ __func__, ce->np->full_name,
+ ce->prop->name);
+ break;
+ }
+ break;
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ ret = __of_remove_property(ce->np, ce->prop);
+ if (ret) {
+ pr_err("%s: remove_property failed @%s/%s\n",
+ __func__, ce->np->full_name,
+ ce->prop->name);
+ break;
+ }
+ break;
+
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ /* If the property is in deadprops then it must be removed */
+ for (propp = &ce->np->deadprops; *propp; propp = &(*propp)->next) {
+ if (*propp == ce->prop) {
+ *propp = ce->prop->next;
+ ce->prop->next = NULL;
+ break;
+ }
+ }
+
+ ret = __of_update_property(ce->np, ce->prop, &old_prop);
+ if (ret) {
+ pr_err("%s: update_property failed @%s/%s\n",
+ __func__, ce->np->full_name,
+ ce->prop->name);
+ break;
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ }
+ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ if (ret)
+ return ret;
+
+ switch (ce->action) {
+ case OF_RECONFIG_ATTACH_NODE:
+ __of_attach_node_sysfs(ce->np);
+ break;
+ case OF_RECONFIG_DETACH_NODE:
+ __of_detach_node_sysfs(ce->np);
+ break;
+ case OF_RECONFIG_ADD_PROPERTY:
+ /* ignore duplicate names */
+ __of_add_property_sysfs(ce->np, ce->prop);
+ break;
+ case OF_RECONFIG_REMOVE_PROPERTY:
+ __of_remove_property_sysfs(ce->np, ce->prop);
+ break;
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ __of_update_property_sysfs(ce->np, ce->prop, ce->old_prop);
+ break;
+ }
+
+ return 0;
+}
+
+static inline int __of_changeset_entry_revert(struct of_changeset_entry *ce)
+{
+ struct of_changeset_entry ce_inverted;
+
+ __of_changeset_entry_invert(ce, &ce_inverted);
+ return __of_changeset_entry_apply(&ce_inverted);
+}
+
+/**
+ * of_changeset_init - Initialize a changeset for use
+ *
+ * @ocs: changeset pointer
+ *
+ * Initialize a changeset structure
+ */
+void of_changeset_init(struct of_changeset *ocs)
+{
+ memset(ocs, 0, sizeof(*ocs));
+ INIT_LIST_HEAD(&ocs->entries);
+}
+
+/**
+ * of_changeset_destroy - Destroy a changeset
+ *
+ * @ocs: changeset pointer
+ *
+ * Destroys a changeset. Note that if a changeset is applied,
+ * its changes to the tree cannot be reverted.
+ */
+void of_changeset_destroy(struct of_changeset *ocs)
+{
+ struct of_changeset_entry *ce, *cen;
+
+ list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node)
+ __of_changeset_entry_destroy(ce);
+}
+
+/**
+ * of_changeset_apply - Applies a changeset
+ *
+ * @ocs: changeset pointer
+ *
+ * Applies a changeset to the live tree.
+ * Any side-effects of live tree state changes are applied here on
+ * sucess, like creation/destruction of devices and side-effects
+ * like creation of sysfs properties and directories.
+ * Returns 0 on success, a negative error value in case of an error.
+ * On error the partially applied effects are reverted.
+ */
+int of_changeset_apply(struct of_changeset *ocs)
+{
+ struct of_changeset_entry *ce;
+ int ret;
+
+ /* perform the rest of the work */
+ pr_debug("of_changeset: applying...\n");
+ list_for_each_entry(ce, &ocs->entries, node) {
+ ret = __of_changeset_entry_apply(ce);
+ if (ret) {
+ pr_err("%s: Error applying changeset (%d)\n", __func__, ret);
+ list_for_each_entry_continue_reverse(ce, &ocs->entries, node)
+ __of_changeset_entry_revert(ce);
+ return ret;
+ }
+ }
+ pr_debug("of_changeset: applied, emitting notifiers.\n");
+
+ /* drop the global lock while emitting notifiers */
+ mutex_unlock(&of_mutex);
+ list_for_each_entry(ce, &ocs->entries, node)
+ __of_changeset_entry_notify(ce, 0);
+ mutex_lock(&of_mutex);
+ pr_debug("of_changeset: notifiers sent.\n");
+
+ return 0;
+}
+
+/**
+ * of_changeset_revert - Reverts an applied changeset
+ *
+ * @ocs: changeset pointer
+ *
+ * Reverts a changeset returning the state of the tree to what it
+ * was before the application.
+ * Any side-effects like creation/destruction of devices and
+ * removal of sysfs properties and directories are applied.
+ * Returns 0 on success, a negative error value in case of an error.
+ */
+int of_changeset_revert(struct of_changeset *ocs)
+{
+ struct of_changeset_entry *ce;
+ int ret;
+
+ pr_debug("of_changeset: reverting...\n");
+ list_for_each_entry_reverse(ce, &ocs->entries, node) {
+ ret = __of_changeset_entry_revert(ce);
+ if (ret) {
+ pr_err("%s: Error reverting changeset (%d)\n", __func__, ret);
+ list_for_each_entry_continue(ce, &ocs->entries, node)
+ __of_changeset_entry_apply(ce);
+ return ret;
+ }
+ }
+ pr_debug("of_changeset: reverted, emitting notifiers.\n");
+
+ /* drop the global lock while emitting notifiers */
+ mutex_unlock(&of_mutex);
+ list_for_each_entry_reverse(ce, &ocs->entries, node)
+ __of_changeset_entry_notify(ce, 1);
+ mutex_lock(&of_mutex);
+ pr_debug("of_changeset: notifiers sent.\n");
+
+ return 0;
+}
+
+/**
+ * of_changeset_action - Perform a changeset action
+ *
+ * @ocs: changeset pointer
+ * @action: action to perform
+ * @np: Pointer to device node
+ * @prop: Pointer to property
+ *
+ * On action being one of:
+ * + OF_RECONFIG_ATTACH_NODE
+ * + OF_RECONFIG_DETACH_NODE,
+ * + OF_RECONFIG_ADD_PROPERTY
+ * + OF_RECONFIG_REMOVE_PROPERTY,
+ * + OF_RECONFIG_UPDATE_PROPERTY
+ * Returns 0 on success, a negative error value in case of an error.
+ */
+int of_changeset_action(struct of_changeset *ocs, unsigned long action,
+ struct device_node *np, struct property *prop)
+{
+ struct of_changeset_entry *ce;
+
+ ce = kzalloc(sizeof(*ce), GFP_KERNEL);
+ if (!ce) {
+ pr_err("%s: Failed to allocate\n", __func__);
+ return -ENOMEM;
+ }
+ /* get a reference to the node */
+ ce->action = action;
+ ce->np = of_node_get(np);
+ ce->prop = prop;
+
+ if (action == OF_RECONFIG_UPDATE_PROPERTY && prop)
+ ce->old_prop = of_find_property(np, prop->name, NULL);
+
+ /* add it to the list */
+ list_add_tail(&ce->node, &ocs->entries);
+ return 0;
+}
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 808be06..42fcf57 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -14,9 +14,13 @@
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/sizes.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
#include <asm/setup.h> /* for COMMAND_LINE_SIZE */
#ifdef CONFIG_PPC
@@ -25,54 +29,6 @@
#include <asm/page.h>
-char *of_fdt_get_string(struct boot_param_header *blob, u32 offset)
-{
- return ((char *)blob) +
- be32_to_cpu(blob->off_dt_strings) + offset;
-}
-
-/**
- * of_fdt_get_property - Given a node in the given flat blob, return
- * the property ptr
- */
-void *of_fdt_get_property(struct boot_param_header *blob,
- unsigned long node, const char *name,
- unsigned long *size)
-{
- unsigned long p = node;
-
- do {
- u32 tag = be32_to_cpup((__be32 *)p);
- u32 sz, noff;
- const char *nstr;
-
- p += 4;
- if (tag == OF_DT_NOP)
- continue;
- if (tag != OF_DT_PROP)
- return NULL;
-
- sz = be32_to_cpup((__be32 *)p);
- noff = be32_to_cpup((__be32 *)(p + 4));
- p += 8;
- if (be32_to_cpu(blob->version) < 0x10)
- p = ALIGN(p, sz >= 8 ? 8 : 4);
-
- nstr = of_fdt_get_string(blob, noff);
- if (nstr == NULL) {
- pr_warning("Can't find property index name !\n");
- return NULL;
- }
- if (strcmp(name, nstr) == 0) {
- if (size)
- *size = sz;
- return (void *)p;
- }
- p += sz;
- p = ALIGN(p, 4);
- } while (1);
-}
-
/**
* of_fdt_is_compatible - Return true if given node from the given blob has
* compat in its compatible list
@@ -87,9 +43,10 @@
unsigned long node, const char *compat)
{
const char *cp;
- unsigned long cplen, l, score = 0;
+ int cplen;
+ unsigned long l, score = 0;
- cp = of_fdt_get_property(blob, node, "compatible", &cplen);
+ cp = fdt_getprop(blob, node, "compatible", &cplen);
if (cp == NULL)
return 0;
while (cplen > 0) {
@@ -125,12 +82,12 @@
return score;
}
-static void *unflatten_dt_alloc(unsigned long *mem, unsigned long size,
+static void *unflatten_dt_alloc(void **mem, unsigned long size,
unsigned long align)
{
void *res;
- *mem = ALIGN(*mem, align);
+ *mem = PTR_ALIGN(*mem, align);
res = (void *)*mem;
*mem += size;
@@ -146,30 +103,29 @@
* @allnextpp: pointer to ->allnext from last allocated device_node
* @fpsize: Size of the node path up at the current depth.
*/
-static unsigned long unflatten_dt_node(struct boot_param_header *blob,
- unsigned long mem,
- unsigned long *p,
+static void * unflatten_dt_node(struct boot_param_header *blob,
+ void *mem,
+ int *poffset,
struct device_node *dad,
struct device_node ***allnextpp,
unsigned long fpsize)
{
+ const __be32 *p;
struct device_node *np;
struct property *pp, **prev_pp = NULL;
- char *pathp;
- u32 tag;
+ const char *pathp;
unsigned int l, allocl;
+ static int depth = 0;
+ int old_depth;
+ int offset;
int has_name = 0;
int new_format = 0;
- tag = be32_to_cpup((__be32 *)(*p));
- if (tag != OF_DT_BEGIN_NODE) {
- pr_err("Weird tag at start of node: %x\n", tag);
+ pathp = fdt_get_name(blob, *poffset, &l);
+ if (!pathp)
return mem;
- }
- *p += 4;
- pathp = (char *)*p;
- l = allocl = strlen(pathp) + 1;
- *p = ALIGN(*p + l, 4);
+
+ allocl = l++;
/* version 0x10 has a more compact unit name here instead of the full
* path. we accumulate the full path size using "fpsize", we'll rebuild
@@ -187,7 +143,7 @@
fpsize = 1;
allocl = 2;
l = 1;
- *pathp = '\0';
+ pathp = "";
} else {
/* account for '/' and path size minus terminal 0
* already in 'l'
@@ -201,7 +157,7 @@
__alignof__(struct device_node));
if (allnextpp) {
char *fn;
- memset(np, 0, sizeof(*np));
+ of_node_init(np);
np->full_name = fn = ((char *)np) + sizeof(*np);
if (new_format) {
/* rebuild full path for new format */
@@ -232,35 +188,25 @@
dad->next->sibling = np;
dad->next = np;
}
- kref_init(&np->kref);
}
/* process properties */
- while (1) {
- u32 sz, noff;
- char *pname;
+ for (offset = fdt_first_property_offset(blob, *poffset);
+ (offset >= 0);
+ (offset = fdt_next_property_offset(blob, offset))) {
+ const char *pname;
+ u32 sz;
- tag = be32_to_cpup((__be32 *)(*p));
- if (tag == OF_DT_NOP) {
- *p += 4;
- continue;
- }
- if (tag != OF_DT_PROP)
+ if (!(p = fdt_getprop_by_offset(blob, offset, &pname, &sz))) {
+ offset = -FDT_ERR_INTERNAL;
break;
- *p += 4;
- sz = be32_to_cpup((__be32 *)(*p));
- noff = be32_to_cpup((__be32 *)((*p) + 4));
- *p += 8;
- if (be32_to_cpu(blob->version) < 0x10)
- *p = ALIGN(*p, sz >= 8 ? 8 : 4);
+ }
- pname = of_fdt_get_string(blob, noff);
if (pname == NULL) {
pr_info("Can't find property name in list !\n");
break;
}
if (strcmp(pname, "name") == 0)
has_name = 1;
- l = strlen(pname) + 1;
pp = unflatten_dt_alloc(&mem, sizeof(struct property),
__alignof__(struct property));
if (allnextpp) {
@@ -272,26 +218,25 @@
if ((strcmp(pname, "phandle") == 0) ||
(strcmp(pname, "linux,phandle") == 0)) {
if (np->phandle == 0)
- np->phandle = be32_to_cpup((__be32*)*p);
+ np->phandle = be32_to_cpup(p);
}
/* And we process the "ibm,phandle" property
* used in pSeries dynamic device tree
* stuff */
if (strcmp(pname, "ibm,phandle") == 0)
- np->phandle = be32_to_cpup((__be32 *)*p);
- pp->name = pname;
+ np->phandle = be32_to_cpup(p);
+ pp->name = (char *)pname;
pp->length = sz;
- pp->value = (void *)*p;
+ pp->value = (__be32 *)p;
*prev_pp = pp;
prev_pp = &pp->next;
}
- *p = ALIGN((*p) + sz, 4);
}
/* with version 0x10 we may not have the name property, recreate
* it here from the unit name if absent
*/
if (!has_name) {
- char *p1 = pathp, *ps = pathp, *pa = NULL;
+ const char *p1 = pathp, *ps = pathp, *pa = NULL;
int sz;
while (*p1) {
@@ -328,19 +273,18 @@
if (!np->type)
np->type = "<NULL>";
}
- while (tag == OF_DT_BEGIN_NODE || tag == OF_DT_NOP) {
- if (tag == OF_DT_NOP)
- *p += 4;
- else
- mem = unflatten_dt_node(blob, mem, p, np, allnextpp,
- fpsize);
- tag = be32_to_cpup((__be32 *)(*p));
- }
- if (tag != OF_DT_END_NODE) {
- pr_err("Weird tag at end of node: %x\n", tag);
- return mem;
- }
- *p += 4;
+
+ old_depth = depth;
+ *poffset = fdt_next_node(blob, *poffset, &depth);
+ if (depth < 0)
+ depth = 0;
+ while (*poffset > 0 && depth > old_depth)
+ mem = unflatten_dt_node(blob, mem, poffset, np, allnextpp,
+ fpsize);
+
+ if (*poffset < 0 && *poffset != -FDT_ERR_NOTFOUND)
+ pr_err("unflatten: error %d processing FDT\n", *poffset);
+
return mem;
}
@@ -360,7 +304,9 @@
struct device_node **mynodes,
void * (*dt_alloc)(u64 size, u64 align))
{
- unsigned long start, mem, size;
+ unsigned long size;
+ int start;
+ void *mem;
struct device_node **allnextp = mynodes;
pr_debug(" -> unflatten_device_tree()\n");
@@ -381,28 +327,27 @@
}
/* First pass, scan for size */
- start = ((unsigned long)blob) +
- be32_to_cpu(blob->off_dt_struct);
- size = unflatten_dt_node(blob, 0, &start, NULL, NULL, 0);
- size = (size | 3) + 1;
+ start = 0;
+ size = (unsigned long)unflatten_dt_node(blob, 0, &start, NULL, NULL, 0);
+ size = ALIGN(size, 4);
pr_debug(" size is %lx, allocating...\n", size);
/* Allocate memory for the expanded device tree */
- mem = (unsigned long)
- dt_alloc(size + 4, __alignof__(struct device_node));
+ mem = dt_alloc(size + 4, __alignof__(struct device_node));
+
+ memset((void *)mem, 0, size);
+
+ memset((void *)mem, 0, size);
((__be32 *)mem)[size / 4] = cpu_to_be32(0xdeadbeef);
- pr_debug(" unflattening %lx...\n", mem);
+ pr_debug(" unflattening %p...\n", mem);
/* Second pass, do actual unflattening */
- start = ((unsigned long)blob) +
- be32_to_cpu(blob->off_dt_struct);
+ start = 0;
unflatten_dt_node(blob, mem, &start, NULL, &allnextp, 0);
- if (be32_to_cpup((__be32 *)start) != OF_DT_END)
- pr_warning("Weird tag at end of tree: %08x\n", *((u32 *)start));
- if (be32_to_cpu(((__be32 *)mem)[size / 4]) != 0xdeadbeef)
+ if (be32_to_cpup(mem + size) != 0xdeadbeef)
pr_warning("End of tree marker overwritten: %08x\n",
be32_to_cpu(((__be32 *)mem)[size / 4]));
*allnextp = NULL;
@@ -441,6 +386,129 @@
#ifdef CONFIG_OF_EARLY_FLATTREE
/**
+ * res_mem_reserve_reg() - reserve all memory described in 'reg' property
+ */
+static int __init __reserved_mem_reserve_reg(unsigned long node,
+ const char *uname)
+{
+ int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+ phys_addr_t base, size;
+ int len;
+ const __be32 *prop;
+ int nomap, first = 1;
+
+ prop = of_get_flat_dt_prop(node, "reg", &len);
+ if (!prop)
+ return -ENOENT;
+
+ if (len && len % t_len != 0) {
+ pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n",
+ uname);
+ return -EINVAL;
+ }
+
+ nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+ while (len >= t_len) {
+ base = dt_mem_next_cell(dt_root_addr_cells, &prop);
+ size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+ if (base && size &&
+ early_init_dt_reserve_memory_arch(base, size, nomap) == 0)
+ pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %ld MiB\n",
+ uname, &base, (unsigned long)size / SZ_1M);
+ else
+ pr_info("Reserved memory: failed to reserve memory for node '%s': base %pa, size %ld MiB\n",
+ uname, &base, (unsigned long)size / SZ_1M);
+
+ len -= t_len;
+ if (first) {
+ fdt_reserved_mem_save_node(node, uname, base, size);
+ first = 0;
+ }
+ }
+ return 0;
+}
+
+/**
+ * __reserved_mem_check_root() - check if #size-cells, #address-cells provided
+ * in /reserved-memory matches the values supported by the current implementation,
+ * also check if ranges property has been provided
+ */
+static int __init __reserved_mem_check_root(unsigned long node)
+{
+ const __be32 *prop;
+
+ prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
+ if (!prop || be32_to_cpup(prop) != dt_root_size_cells)
+ return -EINVAL;
+
+ prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
+ if (!prop || be32_to_cpup(prop) != dt_root_addr_cells)
+ return -EINVAL;
+
+ prop = of_get_flat_dt_prop(node, "ranges", NULL);
+ if (!prop)
+ return -EINVAL;
+ return 0;
+}
+
+/**
+ * fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
+ */
+static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
+ int depth, void *data)
+{
+ static int found;
+ const char *status;
+ int err;
+
+ if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
+ if (__reserved_mem_check_root(node) != 0) {
+ pr_err("Reserved memory: unsupported node format, ignoring\n");
+ /* break scan */
+ return 1;
+ }
+ found = 1;
+ /* scan next node */
+ return 0;
+ } else if (!found) {
+ /* scan next node */
+ return 0;
+ } else if (found && depth < 2) {
+ /* scanning of /reserved-memory has been finished */
+ return 1;
+ }
+
+ status = of_get_flat_dt_prop(node, "status", NULL);
+ if (status && strcmp(status, "okay") != 0 && strcmp(status, "ok") != 0)
+ return 0;
+
+ err = __reserved_mem_reserve_reg(node, uname);
+ if (err == -ENOENT && of_get_flat_dt_prop(node, "size", NULL))
+ fdt_reserved_mem_save_node(node, uname, 0, 0);
+
+ /* scan next node */
+ return 0;
+}
+
+/**
+ * early_init_fdt_scan_reserved_mem() - create reserved memory regions
+ *
+ * This function grabs memory from early allocator for device exclusive use
+ * defined in device tree structures. It should be called by arch specific code
+ * once the early allocator (i.e. memblock) has been fully activated.
+ */
+void __init early_init_fdt_scan_reserved_mem(void)
+{
+ if (!initial_boot_params)
+ return;
+
+ of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
+ fdt_init_reserved_mem();
+}
+
+/**
* of_scan_flat_dt - scan flattened tree blob and call callback on each.
* @it: callback function
* @data: context data pointer
@@ -454,47 +522,19 @@
void *data),
void *data)
{
- unsigned long p = ((unsigned long)initial_boot_params) +
- be32_to_cpu(initial_boot_params->off_dt_struct);
- int rc = 0;
- int depth = -1;
+ const void *blob = initial_boot_params;
+ const char *pathp;
+ int offset, rc = 0, depth = -1;
- do {
- u32 tag = be32_to_cpup((__be32 *)p);
- const char *pathp;
+ for (offset = fdt_next_node(blob, -1, &depth);
+ offset >= 0 && depth >= 0 && !rc;
+ offset = fdt_next_node(blob, offset, &depth)) {
- p += 4;
- if (tag == OF_DT_END_NODE) {
- depth--;
- continue;
- }
- if (tag == OF_DT_NOP)
- continue;
- if (tag == OF_DT_END)
- break;
- if (tag == OF_DT_PROP) {
- u32 sz = be32_to_cpup((__be32 *)p);
- p += 8;
- if (be32_to_cpu(initial_boot_params->version) < 0x10)
- p = ALIGN(p, sz >= 8 ? 8 : 4);
- p += sz;
- p = ALIGN(p, 4);
- continue;
- }
- if (tag != OF_DT_BEGIN_NODE) {
- pr_err("Invalid tag %x in flat device tree!\n", tag);
- return -EINVAL;
- }
- depth++;
- pathp = (char *)p;
- p = ALIGN(p + strlen(pathp) + 1, 4);
+ pathp = fdt_get_name(blob, offset, NULL);
if (*pathp == '/')
pathp = kbasename(pathp);
- rc = it(p, pathp, depth, data);
- if (rc != 0)
- break;
- } while (1);
-
+ rc = it(offset, pathp, depth, data);
+ }
return rc;
}
@@ -503,14 +543,7 @@
*/
unsigned long __init of_get_flat_dt_root(void)
{
- unsigned long p = ((unsigned long)initial_boot_params) +
- be32_to_cpu(initial_boot_params->off_dt_struct);
-
- while (be32_to_cpup((__be32 *)p) == OF_DT_NOP)
- p += 4;
- BUG_ON(be32_to_cpup((__be32 *)p) != OF_DT_BEGIN_NODE);
- p += 4;
- return ALIGN(p + strlen((char *)p) + 1, 4);
+ return 0;
}
/**
@@ -519,10 +552,10 @@
* This function can be used within scan_flattened_dt callback to get
* access to properties
*/
-void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
- unsigned long *size)
+const void *__init of_get_flat_dt_prop(unsigned long node, const char *name,
+ int *size)
{
- return of_fdt_get_property(initial_boot_params, node, name, size);
+ return fdt_getprop(initial_boot_params, node, name, size);
}
/**
@@ -543,6 +576,15 @@
return of_fdt_match(initial_boot_params, node, compat);
}
+struct fdt_scan_status {
+ const char *name;
+ int namelen;
+ int depth;
+ int found;
+ int (*iterator)(unsigned long node, const char *uname, int depth, void *data);
+ void *data;
+};
+
#ifdef CONFIG_BLK_DEV_INITRD
/**
* early_init_dt_check_for_initrd - Decode initrd location from flat tree
@@ -550,23 +592,25 @@
*/
void __init early_init_dt_check_for_initrd(unsigned long node)
{
- unsigned long start, end, len;
- __be32 *prop;
+ u64 start, end;
+ int len;
+ const __be32 *prop;
pr_debug("Looking for initrd properties... ");
prop = of_get_flat_dt_prop(node, "linux,initrd-start", &len);
if (!prop)
return;
- start = of_read_ulong(prop, len/4);
+ start = of_read_number(prop, len/4);
prop = of_get_flat_dt_prop(node, "linux,initrd-end", &len);
if (!prop)
return;
- end = of_read_ulong(prop, len/4);
+ end = of_read_number(prop, len/4);
early_init_dt_setup_initrd_arch(start, end);
- pr_debug("initrd_start=0x%lx initrd_end=0x%lx\n", start, end);
+ pr_debug("initrd_start=0x%llx initrd_end=0x%llx\n",
+ (unsigned long long)start, (unsigned long long)end);
}
#else
inline void early_init_dt_check_for_initrd(unsigned long node)
@@ -580,7 +624,7 @@
int __init early_init_dt_scan_root(unsigned long node, const char *uname,
int depth, void *data)
{
- __be32 *prop;
+ const __be32 *prop;
if (depth != 0)
return 0;
@@ -602,9 +646,9 @@
return 1;
}
-u64 __init dt_mem_next_cell(int s, __be32 **cellp)
+u64 __init dt_mem_next_cell(int s, const __be32 **cellp)
{
- __be32 *p = *cellp;
+ const __be32 *p = *cellp;
*cellp = p + s;
return of_read_number(p, s);
@@ -616,9 +660,9 @@
int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
int depth, void *data)
{
- char *type = of_get_flat_dt_prop(node, "device_type", NULL);
- __be32 *reg, *endp;
- unsigned long l;
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+ const __be32 *reg, *endp;
+ int l;
/* We are scanning "memory" nodes only */
if (type == NULL) {
@@ -639,7 +683,7 @@
endp = reg + (l / sizeof(__be32));
- pr_debug("memory scan node %s, reg size %ld, data: %x %x %x %x,\n",
+ pr_debug("memory scan node %s, reg size %d, data: %x %x %x %x,\n",
uname, l, reg[0], reg[1], reg[2], reg[3]);
while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
@@ -662,8 +706,8 @@
int __init early_init_dt_scan_chosen(unsigned long node, const char *uname,
int depth, void *data)
{
- unsigned long l;
- char *p;
+ int l;
+ const char *p;
pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
@@ -696,6 +740,80 @@
return 1;
}
+#ifdef CONFIG_HAVE_MEMBLOCK
+void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
+{
+ const u64 phys_offset = __pa(PAGE_OFFSET);
+ base &= PAGE_MASK;
+ size &= PAGE_MASK;
+ if (base + size < phys_offset) {
+ pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
+ base, base + size);
+ return;
+ }
+ if (base < phys_offset) {
+ pr_warning("Ignoring memory range 0x%llx - 0x%llx\n",
+ base, phys_offset);
+ size -= phys_offset - base;
+ base = phys_offset;
+ }
+ memblock_add(base, size);
+}
+
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+ phys_addr_t size, bool nomap)
+{
+ if (memblock_is_region_reserved(base, size))
+ return -EBUSY;
+ if (nomap)
+ return memblock_remove(base, size);
+ return memblock_reserve(base, size);
+}
+
+/*
+ * called from unflatten_device_tree() to bootstrap devicetree itself
+ * Architectures can override this definition if memblock isn't used
+ */
+void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
+{
+ return __va(memblock_alloc(size, align));
+}
+#else
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+ phys_addr_t size, bool nomap)
+{
+ pr_err("Reserved memory not supported, ignoring range 0x%llx - 0x%llx%s\n",
+ base, size, nomap ? " (nomap)" : "");
+ return -ENOSYS;
+}
+#endif
+
+bool __init early_init_dt_scan(void *params)
+{
+ if (!params)
+ return false;
+
+ /* Setup flat device-tree pointer */
+ initial_boot_params = params;
+
+ /* check device tree validity */
+ if (be32_to_cpu(initial_boot_params->magic) != OF_DT_HEADER) {
+ initial_boot_params = NULL;
+ return false;
+ }
+
+ /* Retrieve various information from the /chosen node */
+ of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
+
+ /* Initialize {size,address}-cells info */
+ of_scan_flat_dt(early_init_dt_scan_root, NULL);
+
+ /* Setup memory, calling early_init_dt_add_memory_arch */
+ of_scan_flat_dt(early_init_dt_scan_memory, NULL);
+
+ return true;
+}
+
/**
* unflatten_device_tree - create tree of device_nodes from flat blob
*
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index a3c1c5a..5ecb3d8 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -102,7 +102,7 @@
int imaplen, match, i;
pr_debug("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
- parent->full_name, be32_to_cpup(intspec),
+ of_node_full_name(parent), be32_to_cpup(intspec),
be32_to_cpup(intspec + 1), ointsize);
ipar = of_node_get(parent);
@@ -126,7 +126,7 @@
goto fail;
}
- pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize);
+ pr_debug("of_irq_map_raw: ipar=%s, size=%d\n", of_node_full_name(ipar), intsize);
if (ointsize != intsize)
return -EINVAL;
@@ -287,7 +287,7 @@
u32 intsize, intlen;
int res = -EINVAL;
- pr_debug("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index);
+ pr_debug("of_irq_map_one: dev=%s, index=%d\n", of_node_full_name(device), index);
/* OldWorld mac stuff is "special", handle out of line */
if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)
@@ -345,6 +345,7 @@
if (r && irq) {
const char *name = NULL;
+ memset(r, 0, sizeof(*r));
/*
* Get optional "interrupts-names" property to add a name
* to the resource.
@@ -353,8 +354,8 @@
&name);
r->start = r->end = irq;
- r->flags = IORESOURCE_IRQ;
- r->name = name ? name : dev->full_name;
+ r->flags = IORESOURCE_IRQ | irqd_get_trigger_type(irq_get_irq_data(irq));
+ r->name = name ? name : of_node_full_name(dev);
}
return irq;
@@ -482,8 +483,9 @@
}
/* Get the next pending parent that might have children */
- desc = list_first_entry(&intc_parent_list, typeof(*desc), list);
- if (list_empty(&intc_parent_list) || !desc) {
+ desc = list_first_entry_or_null(&intc_parent_list,
+ typeof(*desc), list);
+ if (!desc) {
pr_err("of_irq_init: children remain, but no parents\n");
break;
}
diff --git a/drivers/of/of_i2c.c b/drivers/of/of_i2c.c
deleted file mode 100644
index b667264..0000000
--- a/drivers/of/of_i2c.c
+++ /dev/null
@@ -1,114 +0,0 @@
-/*
- * OF helpers for the I2C API
- *
- * Copyright (c) 2008 Jochen Friedrich <jochen@scram.de>
- *
- * Based on a previous patch from Jon Smirl <jonsmirl@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/i2c.h>
-#include <linux/irq.h>
-#include <linux/of.h>
-#include <linux/of_i2c.h>
-#include <linux/of_irq.h>
-#include <linux/module.h>
-
-void of_i2c_register_devices(struct i2c_adapter *adap)
-{
- void *result;
- struct device_node *node;
-
- /* Only register child devices if the adapter has a node pointer set */
- if (!adap->dev.of_node)
- return;
-
- dev_dbg(&adap->dev, "of_i2c: walking child nodes\n");
-
- for_each_available_child_of_node(adap->dev.of_node, node) {
- struct i2c_board_info info = {};
- struct dev_archdata dev_ad = {};
- const __be32 *addr;
- int len;
-
- dev_dbg(&adap->dev, "of_i2c: register %s\n", node->full_name);
-
- if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) {
- dev_err(&adap->dev, "of_i2c: modalias failure on %s\n",
- node->full_name);
- continue;
- }
-
- addr = of_get_property(node, "reg", &len);
- if (!addr || (len < sizeof(int))) {
- dev_err(&adap->dev, "of_i2c: invalid reg on %s\n",
- node->full_name);
- continue;
- }
-
- info.addr = be32_to_cpup(addr);
- if (info.addr > (1 << 10) - 1) {
- dev_err(&adap->dev, "of_i2c: invalid addr=%x on %s\n",
- info.addr, node->full_name);
- continue;
- }
-
- info.irq = irq_of_parse_and_map(node, 0);
- info.of_node = of_node_get(node);
- info.archdata = &dev_ad;
-
- if (of_get_property(node, "wakeup-source", NULL))
- info.flags |= I2C_CLIENT_WAKE;
-
- request_module("%s%s", I2C_MODULE_PREFIX, info.type);
-
- result = i2c_new_device(adap, &info);
- if (result == NULL) {
- dev_err(&adap->dev, "of_i2c: Failure registering %s\n",
- node->full_name);
- of_node_put(node);
- irq_dispose_mapping(info.irq);
- continue;
- }
- }
-}
-EXPORT_SYMBOL(of_i2c_register_devices);
-
-static int of_dev_node_match(struct device *dev, void *data)
-{
- return dev->of_node == data;
-}
-
-/* must call put_device() when done with returned i2c_client device */
-struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
-{
- struct device *dev;
-
- dev = bus_find_device(&i2c_bus_type, NULL, node,
- of_dev_node_match);
- if (!dev)
- return NULL;
-
- return i2c_verify_client(dev);
-}
-EXPORT_SYMBOL(of_find_i2c_device_by_node);
-
-/* must call put_device() when done with returned i2c_adapter device */
-struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node)
-{
- struct device *dev;
-
- dev = bus_find_device(&i2c_bus_type, NULL, node,
- of_dev_node_match);
- if (!dev)
- return NULL;
-
- return i2c_verify_adapter(dev);
-}
-EXPORT_SYMBOL(of_find_i2c_adapter_by_node);
-
-MODULE_LICENSE("GPL");
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index ff350c8..8e882e7 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -31,6 +31,63 @@
char stem[0];
};
-extern struct mutex of_aliases_mutex;
+extern struct mutex of_mutex;
extern struct list_head aliases_lookup;
+extern struct kset *of_kset;
+
+
+static inline struct device_node *kobj_to_device_node(struct kobject *kobj)
+{
+ return container_of(kobj, struct device_node, kobj);
+}
+
+#if defined(CONFIG_OF_DYNAMIC)
+extern int of_property_notify(int action, struct device_node *np,
+ struct property *prop, struct property *old_prop);
+extern void of_node_release(struct kobject *kobj);
+#else /* CONFIG_OF_DYNAMIC */
+static inline int of_property_notify(int action, struct device_node *np,
+ struct property *prop, struct property *old_prop)
+{
+ return 0;
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
+/**
+ * General utilities for working with live trees.
+ *
+ * All functions with two leading underscores operate
+ * without taking node references, so you either have to
+ * own the devtree lock or work on detached trees only.
+ */
+struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags);
+__printf(2, 3) struct device_node *__of_node_dup(const struct device_node *np, const char *fmt, ...);
+
+extern const void *__of_get_property(const struct device_node *np,
+ const char *name, int *lenp);
+extern int __of_add_property(struct device_node *np, struct property *prop);
+extern int __of_add_property_sysfs(struct device_node *np,
+ struct property *prop);
+extern int __of_remove_property(struct device_node *np, struct property *prop);
+extern void __of_remove_property_sysfs(struct device_node *np,
+ struct property *prop);
+extern int __of_update_property(struct device_node *np,
+ struct property *newprop, struct property **oldprop);
+extern void __of_update_property_sysfs(struct device_node *np,
+ struct property *newprop, struct property *oldprop);
+
+extern void __of_attach_node(struct device_node *np);
+extern int __of_attach_node_sysfs(struct device_node *np);
+extern void __of_detach_node(struct device_node *np);
+extern void __of_detach_node_sysfs(struct device_node *np);
+
+/* iterators for transactions, used for overlays */
+/* forward iterator */
+#define for_each_transaction_entry(_oft, _te) \
+ list_for_each_entry(_te, &(_oft)->te_list, node)
+
+/* reverse iterator */
+#define for_each_transaction_entry_reverse(_oft, _te) \
+ list_for_each_entry_reverse(_te, &(_oft)->te_list, node)
+
#endif /* _LINUX_OF_PRIVATE_H */
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
new file mode 100644
index 0000000..e420eb5
--- /dev/null
+++ b/drivers/of/of_reserved_mem.c
@@ -0,0 +1,217 @@
+/*
+ * Device tree based initialization code for reserved memory.
+ *
+ * Copyright (c) 2013, The Linux Foundation. All Rights Reserved.
+ * Copyright (c) 2013,2014 Samsung Electronics Co., Ltd.
+ * http://www.samsung.com
+ * Author: Marek Szyprowski <m.szyprowski@samsung.com>
+ * Author: Josh Cartwright <joshc@codeaurora.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+#include <linux/of_reserved_mem.h>
+
+#define MAX_RESERVED_REGIONS 16
+static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
+static int reserved_mem_count;
+
+#if defined(CONFIG_HAVE_MEMBLOCK)
+#include <linux/memblock.h>
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+ phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+ phys_addr_t *res_base)
+{
+ /*
+ * We use __memblock_alloc_base() because memblock_alloc_base()
+ * panic()s on allocation failure.
+ */
+ phys_addr_t base = __memblock_alloc_base(size, align, end);
+ if (!base)
+ return -ENOMEM;
+
+ /*
+ * Check if the allocated region fits in to start..end window
+ */
+ if (base < start) {
+ memblock_free(base, size);
+ return -ENOMEM;
+ }
+
+ *res_base = base;
+ if (nomap)
+ return memblock_remove(base, size);
+ return 0;
+}
+#else
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+ phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+ phys_addr_t *res_base)
+{
+ pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n",
+ size, nomap ? " (nomap)" : "");
+ return -ENOSYS;
+}
+#endif
+
+/**
+ * res_mem_save_node() - save fdt node for second pass initialization
+ */
+void __init fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+ phys_addr_t base, phys_addr_t size)
+{
+ struct reserved_mem *rmem = &reserved_mem[reserved_mem_count];
+
+ if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) {
+ pr_err("Reserved memory: not enough space all defined regions.\n");
+ return;
+ }
+
+ rmem->fdt_node = node;
+ rmem->name = uname;
+ rmem->base = base;
+ rmem->size = size;
+
+ reserved_mem_count++;
+ return;
+}
+
+/**
+ * res_mem_alloc_size() - allocate reserved memory described by 'size', 'align'
+ * and 'alloc-ranges' properties
+ */
+static int __init __reserved_mem_alloc_size(unsigned long node,
+ const char *uname, phys_addr_t *res_base, phys_addr_t *res_size)
+{
+ int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+ phys_addr_t start = 0, end = 0;
+ phys_addr_t base = 0, align = 0, size;
+ int len;
+ const __be32 *prop;
+ int nomap;
+ int ret;
+
+ prop = of_get_flat_dt_prop(node, "size", &len);
+ if (!prop)
+ return -EINVAL;
+
+ if (len != dt_root_size_cells * sizeof(__be32)) {
+ pr_err("Reserved memory: invalid size property in '%s' node.\n",
+ uname);
+ return -EINVAL;
+ }
+ size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+ nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+ prop = of_get_flat_dt_prop(node, "alignment", &len);
+ if (prop) {
+ if (len != dt_root_addr_cells * sizeof(__be32)) {
+ pr_err("Reserved memory: invalid alignment property in '%s' node.\n",
+ uname);
+ return -EINVAL;
+ }
+ align = dt_mem_next_cell(dt_root_addr_cells, &prop);
+ }
+
+ prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
+ if (prop) {
+
+ if (len % t_len != 0) {
+ pr_err("Reserved memory: invalid alloc-ranges property in '%s', skipping node.\n",
+ uname);
+ return -EINVAL;
+ }
+
+ base = 0;
+
+ while (len > 0) {
+ start = dt_mem_next_cell(dt_root_addr_cells, &prop);
+ end = start + dt_mem_next_cell(dt_root_size_cells,
+ &prop);
+
+ ret = early_init_dt_alloc_reserved_memory_arch(size,
+ align, start, end, nomap, &base);
+ if (ret == 0) {
+ pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+ uname, &base,
+ (unsigned long)size / SZ_1M);
+ break;
+ }
+ len -= t_len;
+ }
+
+ } else {
+ ret = early_init_dt_alloc_reserved_memory_arch(size, align,
+ 0, 0, nomap, &base);
+ if (ret == 0)
+ pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+ uname, &base, (unsigned long)size / SZ_1M);
+ }
+
+ if (base == 0) {
+ pr_info("Reserved memory: failed to allocate memory for node '%s'\n",
+ uname);
+ return -ENOMEM;
+ }
+
+ *res_base = base;
+ *res_size = size;
+
+ return 0;
+}
+
+static const struct of_device_id __rmem_of_table_sentinel
+ __used __section(__reservedmem_of_table_end);
+
+/**
+ * res_mem_init_node() - call region specific reserved memory init code
+ */
+static int __init __reserved_mem_init_node(struct reserved_mem *rmem)
+{
+ extern const struct of_device_id __reservedmem_of_table[];
+ const struct of_device_id *i;
+
+ for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) {
+ reservedmem_of_init_fn initfn = i->data;
+ const char *compat = i->compatible;
+
+ if (!of_flat_dt_is_compatible(rmem->fdt_node, compat))
+ continue;
+
+ if (initfn(rmem, rmem->fdt_node, rmem->name) == 0) {
+ pr_info("Reserved memory: initialized node %s, compatible id %s\n",
+ rmem->name, compat);
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+/**
+ * fdt_init_reserved_mem - allocate and init all saved reserved memory regions
+ */
+void __init fdt_init_reserved_mem(void)
+{
+ int i;
+ for (i = 0; i < reserved_mem_count; i++) {
+ struct reserved_mem *rmem = &reserved_mem[i];
+ unsigned long node = rmem->fdt_node;
+ int err = 0;
+
+ if (rmem->size == 0)
+ err = __reserved_mem_alloc_size(node, rmem->name,
+ &rmem->base, &rmem->size);
+ if (err == 0)
+ __reserved_mem_init_node(rmem);
+ }
+}
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
new file mode 100644
index 0000000..4066648
--- /dev/null
+++ b/drivers/of/overlay.c
@@ -0,0 +1,552 @@
+/*
+ * Functions for working with device tree overlays
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+#undef DEBUG
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/idr.h>
+
+#include "of_private.h"
+
+/**
+ * struct of_overlay_info - Holds a single overlay info
+ * @target: target of the overlay operation
+ * @overlay: pointer to the overlay contents node
+ *
+ * Holds a single overlay state, including all the overlay logs &
+ * records.
+ */
+struct of_overlay_info {
+ struct device_node *target;
+ struct device_node *overlay;
+};
+
+/**
+ * struct of_overlay - Holds a complete overlay transaction
+ * @node: List on which we are located
+ * @count: Count of ovinfo structures
+ * @ovinfo_tab: Overlay info table (count sized)
+ * @cset: Changeset to be used
+ *
+ * Holds a complete overlay transaction
+ */
+struct of_overlay {
+ int id;
+ struct list_head node;
+ int count;
+ struct of_overlay_info *ovinfo_tab;
+ struct of_changeset cset;
+};
+
+static int of_overlay_apply_one(struct of_overlay *ov,
+ struct device_node *target, const struct device_node *overlay);
+
+static int of_overlay_apply_single_property(struct of_overlay *ov,
+ struct device_node *target, struct property *prop)
+{
+ struct property *propn, *tprop;
+
+ /* NOTE: Multiple changes of single properties not supported */
+ tprop = of_find_property(target, prop->name, NULL);
+
+ /* special properties are not meant to be updated (silent NOP) */
+ if (of_prop_cmp(prop->name, "name") == 0 ||
+ of_prop_cmp(prop->name, "phandle") == 0 ||
+ of_prop_cmp(prop->name, "linux,phandle") == 0)
+ return 0;
+
+ propn = __of_prop_dup(prop, GFP_KERNEL);
+ if (propn == NULL)
+ return -ENOMEM;
+
+ /* not found? add */
+ if (tprop == NULL)
+ return of_changeset_add_property(&ov->cset, target, propn);
+
+ /* found? update */
+ return of_changeset_update_property(&ov->cset, target, propn);
+}
+
+static int of_overlay_apply_single_device_node(struct of_overlay *ov,
+ struct device_node *target, struct device_node *child)
+{
+ const char *cname;
+ struct device_node *tchild, *grandchild;
+ int ret = 0;
+
+ cname = kbasename(child->full_name);
+ if (cname == NULL)
+ return -ENOMEM;
+
+ /* NOTE: Multiple mods of created nodes not supported */
+ tchild = of_get_child_by_name(target, cname);
+ if (tchild != NULL) {
+ /* apply overlay recursively */
+ ret = of_overlay_apply_one(ov, tchild, child);
+ of_node_put(tchild);
+ } else {
+ /* create empty tree as a target */
+ tchild = __of_node_dup(child, "%s/%s", target->full_name, cname);
+ if (!tchild)
+ return -ENOMEM;
+
+ /* point to parent */
+ tchild->parent = target;
+
+ ret = of_changeset_attach_node(&ov->cset, tchild);
+ if (ret)
+ return ret;
+
+ ret = of_overlay_apply_one(ov, tchild, child);
+ if (ret)
+ return ret;
+ }
+
+ return ret;
+}
+
+/*
+ * Apply a single overlay node recursively.
+ *
+ * Note that the in case of an error the target node is left
+ * in a inconsistent state. Error recovery should be performed
+ * by using the changeset.
+ */
+static int of_overlay_apply_one(struct of_overlay *ov,
+ struct device_node *target, const struct device_node *overlay)
+{
+ struct device_node *child;
+ struct property *prop;
+ int ret;
+
+ for_each_property_of_node(overlay, prop) {
+ ret = of_overlay_apply_single_property(ov, target, prop);
+ if (ret) {
+ pr_err("%s: Failed to apply prop @%s/%s\n",
+ __func__, target->full_name, prop->name);
+ return ret;
+ }
+ }
+
+ for_each_child_of_node(overlay, child) {
+ ret = of_overlay_apply_single_device_node(ov, target, child);
+ if (ret != 0) {
+ pr_err("%s: Failed to apply single node @%s/%s\n",
+ __func__, target->full_name,
+ child->name);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * of_overlay_apply() - Apply @count overlays pointed at by @ovinfo_tab
+ * @ov: Overlay to apply
+ *
+ * Applies the overlays given, while handling all error conditions
+ * appropriately. Either the operation succeeds, or if it fails the
+ * live tree is reverted to the state before the attempt.
+ * Returns 0, or an error if the overlay attempt failed.
+ */
+static int of_overlay_apply(struct of_overlay *ov)
+{
+ int i, err;
+
+ /* first we apply the overlays atomically */
+ for (i = 0; i < ov->count; i++) {
+ struct of_overlay_info *ovinfo = &ov->ovinfo_tab[i];
+
+ err = of_overlay_apply_one(ov, ovinfo->target, ovinfo->overlay);
+ if (err != 0) {
+ pr_err("%s: overlay failed '%s'\n",
+ __func__, ovinfo->target->full_name);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Find the target node using a number of different strategies
+ * in order of preference
+ *
+ * "target" property containing the phandle of the target
+ * "target-path" property containing the path of the target
+ */
+static struct device_node *find_target_node(struct device_node *info_node)
+{
+ const char *path;
+ u32 val;
+ int ret;
+
+ /* first try to go by using the target as a phandle */
+ ret = of_property_read_u32(info_node, "target", &val);
+ if (ret == 0)
+ return of_find_node_by_phandle(val);
+
+ /* now try to locate by path */
+ ret = of_property_read_string(info_node, "target-path", &path);
+ if (ret == 0)
+ return of_find_node_by_path(path);
+
+ pr_err("%s: Failed to find target for node %p (%s)\n", __func__,
+ info_node, info_node->name);
+
+ return NULL;
+}
+
+/**
+ * of_fill_overlay_info() - Fill an overlay info structure
+ * @ov Overlay to fill
+ * @info_node: Device node containing the overlay
+ * @ovinfo: Pointer to the overlay info structure to fill
+ *
+ * Fills an overlay info structure with the overlay information
+ * from a device node. This device node must have a target property
+ * which contains a phandle of the overlay target node, and an
+ * __overlay__ child node which has the overlay contents.
+ * Both ovinfo->target & ovinfo->overlay have their references taken.
+ *
+ * Returns 0 on success, or a negative error value.
+ */
+static int of_fill_overlay_info(struct of_overlay *ov,
+ struct device_node *info_node, struct of_overlay_info *ovinfo)
+{
+ ovinfo->overlay = of_get_child_by_name(info_node, "__overlay__");
+ if (ovinfo->overlay == NULL)
+ goto err_fail;
+
+ ovinfo->target = find_target_node(info_node);
+ if (ovinfo->target == NULL)
+ goto err_fail;
+
+ return 0;
+
+err_fail:
+ of_node_put(ovinfo->target);
+ of_node_put(ovinfo->overlay);
+
+ memset(ovinfo, 0, sizeof(*ovinfo));
+ return -EINVAL;
+}
+
+/**
+ * of_build_overlay_info() - Build an overlay info array
+ * @ov Overlay to build
+ * @tree: Device node containing all the overlays
+ *
+ * Helper function that given a tree containing overlay information,
+ * allocates and builds an overlay info array containing it, ready
+ * for use using of_overlay_apply.
+ *
+ * Returns 0 on success with the @cntp @ovinfop pointers valid,
+ * while on error a negative error value is returned.
+ */
+static int of_build_overlay_info(struct of_overlay *ov,
+ struct device_node *tree)
+{
+ struct device_node *node;
+ struct of_overlay_info *ovinfo;
+ int cnt, err;
+
+ /* worst case; every child is a node */
+ cnt = 0;
+ for_each_child_of_node(tree, node)
+ cnt++;
+
+ ovinfo = kcalloc(cnt, sizeof(*ovinfo), GFP_KERNEL);
+ if (ovinfo == NULL)
+ return -ENOMEM;
+
+ cnt = 0;
+ for_each_child_of_node(tree, node) {
+ memset(&ovinfo[cnt], 0, sizeof(*ovinfo));
+ err = of_fill_overlay_info(ov, node, &ovinfo[cnt]);
+ if (err == 0)
+ cnt++;
+ }
+
+ /* if nothing filled, return error */
+ if (cnt == 0) {
+ kfree(ovinfo);
+ return -ENODEV;
+ }
+
+ ov->count = cnt;
+ ov->ovinfo_tab = ovinfo;
+
+ return 0;
+}
+
+/**
+ * of_free_overlay_info() - Free an overlay info array
+ * @ov Overlay to free the overlay info from
+ * @ovinfo_tab: Array of overlay_info's to free
+ *
+ * Releases the memory of a previously allocated ovinfo array
+ * by of_build_overlay_info.
+ * Returns 0, or an error if the arguments are bogus.
+ */
+static int of_free_overlay_info(struct of_overlay *ov)
+{
+ struct of_overlay_info *ovinfo;
+ int i;
+
+ /* do it in reverse */
+ for (i = ov->count - 1; i >= 0; i--) {
+ ovinfo = &ov->ovinfo_tab[i];
+
+ of_node_put(ovinfo->target);
+ of_node_put(ovinfo->overlay);
+ }
+ kfree(ov->ovinfo_tab);
+
+ return 0;
+}
+
+static LIST_HEAD(ov_list);
+static DEFINE_IDR(ov_idr);
+
+/**
+ * of_overlay_create() - Create and apply an overlay
+ * @tree: Device node containing all the overlays
+ *
+ * Creates and applies an overlay while also keeping track
+ * of the overlay in a list. This list can be used to prevent
+ * illegal overlay removals.
+ *
+ * Returns the id of the created overlay, or an negative error number
+ */
+int of_overlay_create(struct device_node *tree)
+{
+ struct of_overlay *ov;
+ int err, id;
+
+ /* allocate the overlay structure */
+ ov = kzalloc(sizeof(*ov), GFP_KERNEL);
+ if (ov == NULL)
+ return -ENOMEM;
+ ov->id = -1;
+
+ INIT_LIST_HEAD(&ov->node);
+
+ of_changeset_init(&ov->cset);
+
+ mutex_lock(&of_mutex);
+
+ id = idr_alloc(&ov_idr, ov, 0, 0, GFP_KERNEL);
+ if (id < 0) {
+ pr_err("%s: idr_alloc() failed for tree@%s\n",
+ __func__, tree->full_name);
+ err = id;
+ goto err_destroy_trans;
+ }
+ ov->id = id;
+
+ /* build the overlay info structures */
+ err = of_build_overlay_info(ov, tree);
+ if (err) {
+ pr_err("%s: of_build_overlay_info() failed for tree@%s\n",
+ __func__, tree->full_name);
+ goto err_free_idr;
+ }
+
+ /* apply the overlay */
+ err = of_overlay_apply(ov);
+ if (err) {
+ pr_err("%s: of_overlay_apply() failed for tree@%s\n",
+ __func__, tree->full_name);
+ goto err_abort_trans;
+ }
+
+ /* apply the changeset */
+ err = of_changeset_apply(&ov->cset);
+ if (err) {
+ pr_err("%s: of_changeset_apply() failed for tree@%s\n",
+ __func__, tree->full_name);
+ goto err_revert_overlay;
+ }
+
+ /* add to the tail of the overlay list */
+ list_add_tail(&ov->node, &ov_list);
+
+ mutex_unlock(&of_mutex);
+
+ return id;
+
+err_revert_overlay:
+err_abort_trans:
+ of_free_overlay_info(ov);
+err_free_idr:
+ idr_remove(&ov_idr, ov->id);
+err_destroy_trans:
+ of_changeset_destroy(&ov->cset);
+ kfree(ov);
+ mutex_unlock(&of_mutex);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(of_overlay_create);
+
+/* check whether the given node, lies under the given tree */
+static int overlay_subtree_check(struct device_node *tree,
+ struct device_node *dn)
+{
+ struct device_node *child;
+
+ /* match? */
+ if (tree == dn)
+ return 1;
+
+ for_each_child_of_node(tree, child) {
+ if (overlay_subtree_check(child, dn))
+ return 1;
+ }
+
+ return 0;
+}
+
+/* check whether this overlay is the topmost */
+static int overlay_is_topmost(struct of_overlay *ov, struct device_node *dn)
+{
+ struct of_overlay *ovt;
+ struct of_changeset_entry *ce;
+
+ list_for_each_entry_reverse(ovt, &ov_list, node) {
+ /* if we hit ourselves, we're done */
+ if (ovt == ov)
+ break;
+
+ /* check against each subtree affected by this overlay */
+ list_for_each_entry(ce, &ovt->cset.entries, node) {
+ if (overlay_subtree_check(ce->np, dn)) {
+ pr_err("%s: #%d clashes #%d @%s\n",
+ __func__, ov->id, ovt->id,
+ dn->full_name);
+ return 0;
+ }
+ }
+ }
+
+ /* overlay is topmost */
+ return 1;
+}
+
+/*
+ * We can safely remove the overlay only if it's the top-most one.
+ * Newly applied overlays are inserted at the tail of the overlay list,
+ * so a top most overlay is the one that is closest to the tail.
+ *
+ * The topmost check is done by exploiting this property. For each
+ * affected device node in the log list we check if this overlay is
+ * the one closest to the tail. If another overlay has affected this
+ * device node and is closest to the tail, then removal is not permited.
+ */
+static int overlay_removal_is_ok(struct of_overlay *ov)
+{
+ struct of_changeset_entry *ce;
+
+ list_for_each_entry(ce, &ov->cset.entries, node) {
+ if (!overlay_is_topmost(ov, ce->np)) {
+ pr_err("%s: overlay #%d is not topmost\n",
+ __func__, ov->id);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+/**
+ * of_overlay_destroy() - Removes an overlay
+ * @id: Overlay id number returned by a previous call to of_overlay_create
+ *
+ * Removes an overlay if it is permissible.
+ *
+ * Returns 0 on success, or an negative error number
+ */
+int of_overlay_destroy(int id)
+{
+ struct of_overlay *ov;
+ int err;
+
+ mutex_lock(&of_mutex);
+
+ ov = idr_find(&ov_idr, id);
+ if (ov == NULL) {
+ err = -ENODEV;
+ pr_err("%s: Could not find overlay #%d\n",
+ __func__, id);
+ goto out;
+ }
+
+ /* check whether the overlay is safe to remove */
+ if (!overlay_removal_is_ok(ov)) {
+ err = -EBUSY;
+ pr_err("%s: removal check failed for overlay #%d\n",
+ __func__, id);
+ goto out;
+ }
+
+
+ list_del(&ov->node);
+ of_changeset_revert(&ov->cset);
+ of_free_overlay_info(ov);
+ idr_remove(&ov_idr, id);
+ of_changeset_destroy(&ov->cset);
+ kfree(ov);
+
+ err = 0;
+
+out:
+ mutex_unlock(&of_mutex);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(of_overlay_destroy);
+
+/**
+ * of_overlay_destroy_all() - Removes all overlays from the system
+ *
+ * Removes all overlays from the system in the correct order.
+ *
+ * Returns 0 on success, or an negative error number
+ */
+int of_overlay_destroy_all(void)
+{
+ struct of_overlay *ov, *ovn;
+
+ mutex_lock(&of_mutex);
+
+ /* the tail of list is guaranteed to be safe to remove */
+ list_for_each_entry_safe_reverse(ov, ovn, &ov_list, node) {
+ list_del(&ov->node);
+ of_changeset_revert(&ov->cset);
+ of_free_overlay_info(ov);
+ idr_remove(&ov_idr, ov->id);
+ kfree(ov);
+ }
+
+ mutex_unlock(&of_mutex);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(of_overlay_destroy_all);
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index 37b56fd..37961b8 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -177,11 +177,10 @@
return NULL;
dp = prom_early_alloc(sizeof(*dp));
+ of_node_init(dp);
of_pdt_incr_unique_id(dp);
dp->parent = parent;
- kref_init(&dp->kref);
-
dp->name = of_pdt_get_one_property(node, "name");
dp->type = of_pdt_get_one_property(node, "device_type");
dp->phandle = node;
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index e0a6514..41bff21 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -204,12 +204,13 @@
{
struct platform_device *dev;
- if (!of_device_is_available(np))
+ if (!of_device_is_available(np) ||
+ of_node_test_and_set_flag(np, OF_POPULATED))
return NULL;
dev = of_device_alloc(np, bus_id, parent);
if (!dev)
- return NULL;
+ goto err_clear_flag;
#if defined(CONFIG_MICROBLAZE)
dev->archdata.dma_mask = 0xffffffffUL;
@@ -225,10 +226,14 @@
if (of_device_add(dev) != 0) {
platform_device_put(dev);
- return NULL;
+ goto err_clear_flag;
}
return dev;
+
+err_clear_flag:
+ of_node_clear_flag(np, OF_POPULATED);
+ return NULL;
}
/**
@@ -260,12 +265,16 @@
pr_debug("Creating amba device %s\n", node->full_name);
- if (!of_device_is_available(node))
+ if (!of_device_is_available(node) ||
+ of_node_test_and_set_flag(node, OF_POPULATED))
return NULL;
dev = amba_device_alloc(NULL, 0, 0);
- if (!dev)
- return NULL;
+ if (!dev) {
+ pr_err("%s(): amba_device_alloc() failed for %s\n",
+ __func__, node->full_name);
+ goto err_clear_flag;
+ }
/* setup generic device info */
dev->dev.coherent_dma_mask = ~0;
@@ -301,6 +310,8 @@
err_free:
amba_device_put(dev);
+err_clear_flag:
+ of_node_clear_flag(node, OF_POPULATED);
return NULL;
}
#else /* CONFIG_ARM_AMBA */
@@ -390,6 +401,7 @@
break;
}
}
+ of_node_set_flag(bus, OF_POPULATED_BUS);
return rc;
}
@@ -473,4 +485,109 @@
return rc;
}
EXPORT_SYMBOL_GPL(of_platform_populate);
+
+static int of_platform_device_destroy(struct device *dev, void *data)
+{
+ /* Do not touch devices not populated from the device tree */
+ if (!dev->of_node || !of_node_check_flag(dev->of_node, OF_POPULATED))
+ return 0;
+
+ /* Recurse for any nodes that were treated as busses */
+ if (of_node_check_flag(dev->of_node, OF_POPULATED_BUS))
+ device_for_each_child(dev, NULL, of_platform_device_destroy);
+
+ if (dev->bus == &platform_bus_type)
+ platform_device_unregister(to_platform_device(dev));
+#ifdef CONFIG_ARM_AMBA
+ else if (dev->bus == &amba_bustype)
+ amba_device_unregister(to_amba_device(dev));
+#endif
+
+ of_node_clear_flag(dev->of_node, OF_POPULATED);
+ of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
+ return 0;
+}
+
+/**
+ * of_platform_depopulate() - Remove devices populated from device tree
+ * @parent: device which children will be removed
+ *
+ * Complementary to of_platform_populate(), this function removes children
+ * of the given device (and, recurrently, their children) that have been
+ * created from their respective device tree nodes (and only those,
+ * leaving others - eg. manually created - unharmed).
+ *
+ * Returns 0 when all children devices have been removed or
+ * -EBUSY when some children remained.
+ */
+void of_platform_depopulate(struct device *parent)
+{
+ device_for_each_child(parent, NULL, of_platform_device_destroy);
+}
+EXPORT_SYMBOL_GPL(of_platform_depopulate);
+
+#ifdef CONFIG_OF_DYNAMIC
+static int of_platform_notify(struct notifier_block *nb,
+ unsigned long action, void *arg)
+{
+ struct of_reconfig_data *rd = arg;
+ struct platform_device *pdev_parent, *pdev;
+ bool children_left;
+
+ switch (of_reconfig_get_state_change(action, rd)) {
+ case OF_RECONFIG_CHANGE_ADD:
+ /* verify that the parent is a bus */
+ if (!of_node_check_flag(rd->dn->parent, OF_POPULATED_BUS))
+ return NOTIFY_OK; /* not for us */
+
+ /* already populated? (driver using of_populate manually) */
+ if (of_node_check_flag(rd->dn, OF_POPULATED))
+ return NOTIFY_OK;
+
+ /* pdev_parent may be NULL when no bus platform device */
+ pdev_parent = of_find_device_by_node(rd->dn->parent);
+ pdev = of_platform_device_create(rd->dn, NULL,
+ pdev_parent ? &pdev_parent->dev : NULL);
+ of_dev_put(pdev_parent);
+
+ if (pdev == NULL) {
+ pr_err("%s: failed to create for '%s'\n",
+ __func__, rd->dn->full_name);
+ /* of_platform_device_create tosses the error code */
+ return notifier_from_errno(-EINVAL);
+ }
+ break;
+
+ case OF_RECONFIG_CHANGE_REMOVE:
+
+ /* already depopulated? */
+ if (!of_node_check_flag(rd->dn, OF_POPULATED))
+ return NOTIFY_OK;
+
+ /* find our device by node */
+ pdev = of_find_device_by_node(rd->dn);
+ if (pdev == NULL)
+ return NOTIFY_OK; /* no? not meant for us */
+
+ /* unregister takes one ref away */
+ of_platform_device_destroy(&pdev->dev, &children_left);
+
+ /* and put the reference of the find */
+ of_dev_put(pdev);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block platform_of_notifier = {
+ .notifier_call = of_platform_notify,
+};
+
+void of_platform_register_reconfig_notifier(void)
+{
+ WARN_ON(of_reconfig_notifier_register(&platform_of_notifier));
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
#endif /* CONFIG_OF_ADDRESS */
diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
new file mode 100644
index 0000000..640eb4c
--- /dev/null
+++ b/drivers/of/resolver.c
@@ -0,0 +1,412 @@
+/*
+ * Functions for dealing with DT resolution
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+
+/* illegal phandle value (set when unresolved) */
+#define OF_PHANDLE_ILLEGAL 0xdeadbeef
+
+/**
+ * Find a node with the give full name by recursively following any of
+ * the child node links.
+ */
+static struct device_node *__of_find_node_by_full_name(struct device_node *node,
+ const char *full_name)
+{
+ struct device_node *child, *found;
+
+ if (node == NULL)
+ return NULL;
+
+ /* check */
+ if (of_node_cmp(node->full_name, full_name) == 0)
+ return node;
+
+ for_each_child_of_node(node, child) {
+ found = __of_find_node_by_full_name(child, full_name);
+ if (found != NULL)
+ return found;
+ }
+
+ return NULL;
+}
+
+/*
+ * Find live tree's maximum phandle value.
+ */
+static phandle of_get_tree_max_phandle(void)
+{
+ struct device_node *node;
+ phandle phandle;
+ unsigned long flags;
+
+ /* now search recursively */
+ raw_spin_lock_irqsave(&devtree_lock, flags);
+ phandle = 0;
+ for_each_of_allnodes(node) {
+ if (node->phandle != OF_PHANDLE_ILLEGAL &&
+ node->phandle > phandle)
+ phandle = node->phandle;
+ }
+ raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+ return phandle;
+}
+
+/*
+ * Adjust a subtree's phandle values by a given delta.
+ * Makes sure not to just adjust the device node's phandle value,
+ * but modify the phandle properties values as well.
+ */
+static void __of_adjust_tree_phandles(struct device_node *node,
+ int phandle_delta)
+{
+ struct device_node *child;
+ struct property *prop;
+ phandle phandle;
+
+ /* first adjust the node's phandle direct value */
+ if (node->phandle != 0 && node->phandle != OF_PHANDLE_ILLEGAL)
+ node->phandle += phandle_delta;
+
+ /* now adjust phandle & linux,phandle values */
+ for_each_property_of_node(node, prop) {
+
+ /* only look for these two */
+ if (of_prop_cmp(prop->name, "phandle") != 0 &&
+ of_prop_cmp(prop->name, "linux,phandle") != 0)
+ continue;
+
+ /* must be big enough */
+ if (prop->length < 4)
+ continue;
+
+ /* read phandle value */
+ phandle = be32_to_cpup(prop->value);
+ if (phandle == OF_PHANDLE_ILLEGAL) /* unresolved */
+ continue;
+
+ /* adjust */
+ *(uint32_t *)prop->value = cpu_to_be32(node->phandle);
+ }
+
+ /* now do the children recursively */
+ for_each_child_of_node(node, child)
+ __of_adjust_tree_phandles(child, phandle_delta);
+}
+
+static int __of_adjust_phandle_ref(struct device_node *node,
+ struct property *rprop, int value)
+{
+ phandle phandle;
+ struct device_node *refnode;
+ struct property *sprop;
+ char *propval, *propcur, *propend, *nodestr, *propstr, *s;
+ int offset, propcurlen;
+ int err = 0;
+
+ /* make a copy */
+ propval = kmalloc(rprop->length, GFP_KERNEL);
+ if (!propval) {
+ pr_err("%s: Could not copy value of '%s'\n",
+ __func__, rprop->name);
+ return -ENOMEM;
+ }
+ memcpy(propval, rprop->value, rprop->length);
+
+ propend = propval + rprop->length;
+ for (propcur = propval; propcur < propend; propcur += propcurlen + 1) {
+ propcurlen = strlen(propcur);
+
+ nodestr = propcur;
+ s = strchr(propcur, ':');
+ if (!s) {
+ pr_err("%s: Illegal symbol entry '%s' (1)\n",
+ __func__, propcur);
+ err = -EINVAL;
+ goto err_fail;
+ }
+ *s++ = '\0';
+
+ propstr = s;
+ s = strchr(s, ':');
+ if (!s) {
+ pr_err("%s: Illegal symbol entry '%s' (2)\n",
+ __func__, (char *)rprop->value);
+ err = -EINVAL;
+ goto err_fail;
+ }
+
+ *s++ = '\0';
+ err = kstrtoint(s, 10, &offset);
+ if (err != 0) {
+ pr_err("%s: Could get offset '%s'\n",
+ __func__, (char *)rprop->value);
+ goto err_fail;
+ }
+
+ /* look into the resolve node for the full path */
+ refnode = __of_find_node_by_full_name(node, nodestr);
+ if (!refnode) {
+ pr_warn("%s: Could not find refnode '%s'\n",
+ __func__, (char *)rprop->value);
+ continue;
+ }
+
+ /* now find the property */
+ for_each_property_of_node(refnode, sprop) {
+ if (of_prop_cmp(sprop->name, propstr) == 0)
+ break;
+ }
+
+ if (!sprop) {
+ pr_err("%s: Could not find property '%s'\n",
+ __func__, (char *)rprop->value);
+ err = -ENOENT;
+ goto err_fail;
+ }
+
+ phandle = value;
+ *(__be32 *)(sprop->value + offset) = cpu_to_be32(phandle);
+ }
+
+err_fail:
+ kfree(propval);
+ return err;
+}
+
+/* compare nodes taking into account that 'name' strips out the @ part */
+static int __of_node_name_cmp(const struct device_node *dn1,
+ const struct device_node *dn2)
+{
+ const char *n1 = strrchr(dn1->full_name, '/') ? : "/";
+ const char *n2 = strrchr(dn2->full_name, '/') ? : "/";
+
+ return of_node_cmp(n1, n2);
+}
+
+/*
+ * Adjust the local phandle references by the given phandle delta.
+ * Assumes the existances of a __local_fixups__ node at the root.
+ * Assumes that __of_verify_tree_phandle_references has been called.
+ * Does not take any devtree locks so make sure you call this on a tree
+ * which is at the detached state.
+ */
+static int __of_adjust_tree_phandle_references(struct device_node *node,
+ struct device_node *target, int phandle_delta)
+{
+ struct device_node *child, *childtarget;
+ struct property *rprop, *sprop;
+ int err, i, count;
+ unsigned int off;
+ phandle phandle;
+
+ if (node == NULL)
+ return 0;
+
+ for_each_property_of_node(node, rprop) {
+
+ /* skip properties added automatically */
+ if (of_prop_cmp(rprop->name, "name") == 0 ||
+ of_prop_cmp(rprop->name, "phandle") == 0 ||
+ of_prop_cmp(rprop->name, "linux,phandle") == 0)
+ continue;
+
+ if ((rprop->length % 4) != 0 || rprop->length == 0) {
+ pr_err("%s: Illegal property (size) '%s' @%s\n",
+ __func__, rprop->name, node->full_name);
+ return -EINVAL;
+ }
+ count = rprop->length / sizeof(__be32);
+
+ /* now find the target property */
+ for_each_property_of_node(target, sprop) {
+ if (of_prop_cmp(sprop->name, rprop->name) == 0)
+ break;
+ }
+
+ if (sprop == NULL) {
+ pr_err("%s: Could not find target property '%s' @%s\n",
+ __func__, rprop->name, node->full_name);
+ return -EINVAL;
+ }
+
+ for (i = 0; i < count; i++) {
+ off = be32_to_cpu(((__be32 *)rprop->value)[i]);
+ /* make sure the offset doesn't overstep (even wrap) */
+ if (off >= sprop->length ||
+ (off + 4) > sprop->length) {
+ pr_err("%s: Illegal property '%s' @%s\n",
+ __func__, rprop->name,
+ node->full_name);
+ return -EINVAL;
+ }
+
+ if (phandle_delta) {
+ /* adjust */
+ phandle = be32_to_cpu(*(__be32 *)(sprop->value + off));
+ phandle += phandle_delta;
+ *(__be32 *)(sprop->value + off) = cpu_to_be32(phandle);
+ }
+ }
+ }
+
+ for_each_child_of_node(node, child) {
+
+ for_each_child_of_node(target, childtarget)
+ if (__of_node_name_cmp(child, childtarget) == 0)
+ break;
+
+ if (!childtarget) {
+ pr_err("%s: Could not find target child '%s' @%s\n",
+ __func__, child->name, node->full_name);
+ return -EINVAL;
+ }
+
+ err = __of_adjust_tree_phandle_references(child, childtarget,
+ phandle_delta);
+ if (err != 0)
+ return err;
+ }
+
+ return 0;
+}
+
+/**
+ * of_resolve - Resolve the given node against the live tree.
+ *
+ * @resolve: Node to resolve
+ *
+ * Perform dynamic Device Tree resolution against the live tree
+ * to the given node to resolve. This depends on the live tree
+ * having a __symbols__ node, and the resolve node the __fixups__ &
+ * __local_fixups__ nodes (if needed).
+ * The result of the operation is a resolve node that it's contents
+ * are fit to be inserted or operate upon the live tree.
+ * Returns 0 on success or a negative error value on error.
+ */
+int of_resolve_phandles(struct device_node *resolve)
+{
+ struct device_node *child, *childroot, *refnode;
+ struct device_node *root_sym, *resolve_sym, *resolve_fix;
+ struct property *rprop;
+ const char *refpath;
+ phandle phandle, phandle_delta;
+ int err;
+
+ /* the resolve node must exist, and be detached */
+ if (!resolve || !of_node_check_flag(resolve, OF_DETACHED))
+ return -EINVAL;
+
+ /* first we need to adjust the phandles */
+ phandle_delta = of_get_tree_max_phandle() + 1;
+ __of_adjust_tree_phandles(resolve, phandle_delta);
+
+ /* locate the local fixups */
+ childroot = NULL;
+ for_each_child_of_node(resolve, childroot)
+ if (of_node_cmp(childroot->name, "__local_fixups__") == 0)
+ break;
+
+ if (childroot != NULL) {
+ /* resolve root is guaranteed to be the '/' */
+ err = __of_adjust_tree_phandle_references(childroot,
+ resolve, 0);
+ if (err != 0)
+ return err;
+
+ BUG_ON(__of_adjust_tree_phandle_references(childroot,
+ resolve, phandle_delta));
+ }
+
+ root_sym = NULL;
+ resolve_sym = NULL;
+ resolve_fix = NULL;
+
+ /* this may fail (if no fixups are required) */
+ root_sym = of_find_node_by_path("/__symbols__");
+
+ /* locate the symbols & fixups nodes on resolve */
+ for_each_child_of_node(resolve, child) {
+
+ if (!resolve_sym &&
+ of_node_cmp(child->name, "__symbols__") == 0)
+ resolve_sym = child;
+
+ if (!resolve_fix &&
+ of_node_cmp(child->name, "__fixups__") == 0)
+ resolve_fix = child;
+
+ /* both found, don't bother anymore */
+ if (resolve_sym && resolve_fix)
+ break;
+ }
+
+ /* we do allow for the case where no fixups are needed */
+ if (!resolve_fix) {
+ err = 0; /* no error */
+ goto out;
+ }
+
+ /* we need to fixup, but no root symbols... */
+ if (!root_sym) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ for_each_property_of_node(resolve_fix, rprop) {
+
+ /* skip properties added automatically */
+ if (of_prop_cmp(rprop->name, "name") == 0)
+ continue;
+
+ err = of_property_read_string(root_sym,
+ rprop->name, &refpath);
+ if (err != 0) {
+ pr_err("%s: Could not find symbol '%s'\n",
+ __func__, rprop->name);
+ goto out;
+ }
+
+ refnode = of_find_node_by_path(refpath);
+ if (!refnode) {
+ pr_err("%s: Could not find node by path '%s'\n",
+ __func__, refpath);
+ err = -ENOENT;
+ goto out;
+ }
+
+ phandle = refnode->phandle;
+ of_node_put(refnode);
+
+ pr_debug("%s: %s phandle is 0x%08x\n",
+ __func__, rprop->name, phandle);
+
+ err = __of_adjust_phandle_ref(resolve, rprop, phandle);
+ if (err)
+ break;
+ }
+
+out:
+ /* NULL is handled by of_node_put as NOP */
+ of_node_put(root_sym);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(of_resolve_phandles);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index 0eb5c38..37f57ad 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -14,11 +14,17 @@
#include <linux/slab.h>
#include <linux/device.h>
-static bool selftest_passed = true;
+#include "of_private.h"
+
+static struct selftest_results {
+ int passed;
+ int failed;
+} selftest_results;
+
#define selftest(result, fmt, ...) { \
if (!(result)) { \
pr_err("FAIL %s:%i " fmt, __FILE__, __LINE__, ##__VA_ARGS__); \
- selftest_passed = false; \
+ selftest_results.passed = false; \
} else { \
pr_info("pass %s:%i\n", __FILE__, __LINE__); \
} \
@@ -126,8 +132,9 @@
selftest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc);
}
-static void __init of_selftest_property_match_string(void)
+static void __init of_selftest_property_string(void)
{
+ const char *strings[4];
struct device_node *np;
int rc;
@@ -145,13 +152,141 @@
rc = of_property_match_string(np, "phandle-list-names", "third");
selftest(rc == 2, "third expected:0 got:%i\n", rc);
rc = of_property_match_string(np, "phandle-list-names", "fourth");
- selftest(rc == -ENODATA, "unmatched string; rc=%i", rc);
+ selftest(rc == -ENODATA, "unmatched string; rc=%i\n", rc);
rc = of_property_match_string(np, "missing-property", "blah");
- selftest(rc == -EINVAL, "missing property; rc=%i", rc);
+ selftest(rc == -EINVAL, "missing property; rc=%i\n", rc);
rc = of_property_match_string(np, "empty-property", "blah");
- selftest(rc == -ENODATA, "empty property; rc=%i", rc);
+ selftest(rc == -ENODATA, "empty property; rc=%i\n", rc);
rc = of_property_match_string(np, "unterminated-string", "blah");
- selftest(rc == -EILSEQ, "unterminated string; rc=%i", rc);
+ selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+
+ /* of_property_count_strings() tests */
+ rc = of_property_count_strings(np, "string-property");
+ selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+ rc = of_property_count_strings(np, "phandle-list-names");
+ selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+ rc = of_property_count_strings(np, "unterminated-string");
+ selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+ rc = of_property_count_strings(np, "unterminated-string-list");
+ selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+
+ /* of_property_read_string_index() tests */
+ rc = of_property_read_string_index(np, "string-property", 0, strings);
+ selftest(rc == 0 && !strcmp(strings[0], "foobar"), "of_property_read_string_index() failure; rc=%i\n", rc);
+ strings[0] = NULL;
+ rc = of_property_read_string_index(np, "string-property", 1, strings);
+ selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+ rc = of_property_read_string_index(np, "phandle-list-names", 0, strings);
+ selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+ rc = of_property_read_string_index(np, "phandle-list-names", 1, strings);
+ selftest(rc == 0 && !strcmp(strings[0], "second"), "of_property_read_string_index() failure; rc=%i\n", rc);
+ rc = of_property_read_string_index(np, "phandle-list-names", 2, strings);
+ selftest(rc == 0 && !strcmp(strings[0], "third"), "of_property_read_string_index() failure; rc=%i\n", rc);
+ strings[0] = NULL;
+ rc = of_property_read_string_index(np, "phandle-list-names", 3, strings);
+ selftest(rc == -ENODATA && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+ strings[0] = NULL;
+ rc = of_property_read_string_index(np, "unterminated-string", 0, strings);
+ selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+ rc = of_property_read_string_index(np, "unterminated-string-list", 0, strings);
+ selftest(rc == 0 && !strcmp(strings[0], "first"), "of_property_read_string_index() failure; rc=%i\n", rc);
+ strings[0] = NULL;
+ rc = of_property_read_string_index(np, "unterminated-string-list", 2, strings); /* should fail */
+ selftest(rc == -EILSEQ && strings[0] == NULL, "of_property_read_string_index() failure; rc=%i\n", rc);
+ strings[1] = NULL;
+
+ /* of_property_read_string_array() tests */
+ rc = of_property_read_string_array(np, "string-property", strings, 4);
+ selftest(rc == 1, "Incorrect string count; rc=%i\n", rc);
+ rc = of_property_read_string_array(np, "phandle-list-names", strings, 4);
+ selftest(rc == 3, "Incorrect string count; rc=%i\n", rc);
+ rc = of_property_read_string_array(np, "unterminated-string", strings, 4);
+ selftest(rc == -EILSEQ, "unterminated string; rc=%i\n", rc);
+ /* -- An incorrectly formed string should cause a failure */
+ rc = of_property_read_string_array(np, "unterminated-string-list", strings, 4);
+ selftest(rc == -EILSEQ, "unterminated string array; rc=%i\n", rc);
+ /* -- parsing the correctly formed strings should still work: */
+ strings[2] = NULL;
+ rc = of_property_read_string_array(np, "unterminated-string-list", strings, 2);
+ selftest(rc == 2 && strings[2] == NULL, "of_property_read_string_array() failure; rc=%i\n", rc);
+ strings[1] = NULL;
+ rc = of_property_read_string_array(np, "phandle-list-names", strings, 1);
+ selftest(rc == 1 && strings[1] == NULL, "Overwrote end of string array; rc=%i, str='%s'\n", rc, strings[1]);
+}
+
+#define propcmp(p1, p2) (((p1)->length == (p2)->length) && \
+ (p1)->value && (p2)->value && \
+ !memcmp((p1)->value, (p2)->value, (p1)->length) && \
+ !strcmp((p1)->name, (p2)->name))
+static void __init of_selftest_property_copy(void)
+{
+#ifdef CONFIG_OF_DYNAMIC
+ struct property p1 = { .name = "p1", .length = 0, .value = "" };
+ struct property p2 = { .name = "p2", .length = 5, .value = "abcd" };
+ struct property *new;
+
+ new = __of_prop_dup(&p1, GFP_KERNEL);
+ selftest(new && propcmp(&p1, new), "empty property didn't copy correctly\n");
+ kfree(new->value);
+ kfree(new->name);
+ kfree(new);
+
+ new = __of_prop_dup(&p2, GFP_KERNEL);
+ selftest(new && propcmp(&p2, new), "non-empty property didn't copy correctly\n");
+ kfree(new->value);
+ kfree(new->name);
+ kfree(new);
+#endif
+}
+
+static void __init of_selftest_changeset(void)
+{
+#ifdef CONFIG_OF_DYNAMIC
+ struct property *ppadd, padd = { .name = "prop-add", .length = 0, .value = "" };
+ struct property *ppupdate, pupdate = { .name = "prop-update", .length = 5, .value = "abcd" };
+ struct property *ppremove;
+ struct device_node *n1, *n2, *n21, *nremove, *parent;
+ struct of_changeset chgset;
+
+ of_changeset_init(&chgset);
+ n1 = __of_node_dup(NULL, "/testcase-data/changeset/n1");
+ selftest(n1, "testcase setup failure\n");
+ n2 = __of_node_dup(NULL, "/testcase-data/changeset/n2");
+ selftest(n2, "testcase setup failure\n");
+ n21 = __of_node_dup(NULL, "%s/%s", "/testcase-data/changeset/n2", "n21");
+ selftest(n21, "testcase setup failure %p\n", n21);
+ nremove = of_find_node_by_path("/testcase-data/changeset/node-remove");
+ selftest(nremove, "testcase setup failure\n");
+ ppadd = __of_prop_dup(&padd, GFP_KERNEL);
+ selftest(ppadd, "testcase setup failure\n");
+ ppupdate = __of_prop_dup(&pupdate, GFP_KERNEL);
+ selftest(ppupdate, "testcase setup failure\n");
+ parent = nremove->parent;
+ n1->parent = parent;
+ n2->parent = parent;
+ n21->parent = n2;
+ n2->child = n21;
+ ppremove = of_find_property(parent, "prop-remove", NULL);
+ selftest(ppremove, "failed to find removal prop");
+
+ of_changeset_init(&chgset);
+ selftest(!of_changeset_attach_node(&chgset, n1), "fail attach n1\n");
+ selftest(!of_changeset_attach_node(&chgset, n2), "fail attach n2\n");
+ selftest(!of_changeset_detach_node(&chgset, nremove), "fail remove node\n");
+ selftest(!of_changeset_attach_node(&chgset, n21), "fail attach n21\n");
+ selftest(!of_changeset_add_property(&chgset, parent, ppadd), "fail add prop\n");
+ selftest(!of_changeset_update_property(&chgset, parent, ppupdate), "fail update prop\n");
+ selftest(!of_changeset_remove_property(&chgset, parent, ppremove), "fail remove prop\n");
+ mutex_lock(&of_mutex);
+ selftest(!of_changeset_apply(&chgset), "apply failed\n");
+ mutex_unlock(&of_mutex);
+
+ mutex_lock(&of_mutex);
+ selftest(!of_changeset_revert(&chgset), "revert failed\n");
+ mutex_unlock(&of_mutex);
+
+ of_changeset_destroy(&chgset);
+#endif
}
static int __init of_selftest(void)
@@ -168,7 +303,11 @@
pr_info("start of selftest - you will see error messages\n");
of_selftest_parse_phandle_with_args();
of_selftest_property_match_string();
- pr_info("end of selftest - %s\n", selftest_passed ? "PASS" : "FAIL");
+ of_selftest_property_copy();
+ of_selftest_changeset();
+ of_selftest_property_string();
+ pr_info("end of selftest - %i passed, %i failed\n",
+ selftest_results.passed, selftest_results.failed);
return 0;
}
late_initcall(of_selftest);
diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi
new file mode 100644
index 0000000..669bb07
--- /dev/null
+++ b/drivers/of/testcase-data/testcases.dtsi
@@ -0,0 +1,14 @@
+/ {
+ testcase-data {
+ changeset {
+ prop-update = "hello";
+ prop-remove = "world";
+ node-remove {
+ };
+ };
+ };
+};
+#include "tests-phandle.dtsi"
+#include "tests-interrupts.dtsi"
+#include "tests-match.dtsi"
+#include "tests-platform.dtsi"
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index e79e006..9ee04b4 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -811,18 +811,28 @@
return pcidev->irq;
}
-static struct iosapic_info *first_isi = NULL;
+static struct iosapic_info *iosapic_list;
#ifdef CONFIG_64BIT
-int iosapic_serial_irq(int num)
+int iosapic_serial_irq(struct parisc_device *dev)
{
- struct iosapic_info *isi = first_isi;
- struct irt_entry *irte = NULL; /* only used if PAT PDC */
+ struct iosapic_info *isi;
+ struct irt_entry *irte;
struct vector_info *vi;
- int isi_line; /* line used by device */
+ int cnt;
+ int intin;
+
+ intin = (dev->mod_info >> 24) & 15;
/* lookup IRT entry for isi/slot/pin set */
- irte = &irt_cell[num];
+ for (cnt = 0; cnt < irt_num_entry; cnt++) {
+ irte = &irt_cell[cnt];
+ if (COMPARE_IRTE_ADDR(irte, dev->mod0) &&
+ irte->dest_iosapic_intin == intin)
+ break;
+ }
+ if (cnt >= irt_num_entry)
+ return 0; /* no irq found, force polling */
DBG_IRT("iosapic_serial_irq(): irte %p %x %x %x %x %x %x %x %x\n",
irte,
@@ -834,11 +844,17 @@
irte->src_seg_id,
irte->dest_iosapic_intin,
(u32) irte->dest_iosapic_addr);
- isi_line = irte->dest_iosapic_intin;
+
+ /* search for iosapic */
+ for (isi = iosapic_list; isi; isi = isi->isi_next)
+ if (isi->isi_hpa == dev->mod0)
+ break;
+ if (!isi)
+ return 0; /* no iosapic found, force polling */
/* get vector info for this input line */
- vi = isi->isi_vector + isi_line;
- DBG_IRT("iosapic_serial_irq: line %d vi 0x%p\n", isi_line, vi);
+ vi = isi->isi_vector + intin;
+ DBG_IRT("iosapic_serial_irq: line %d vi 0x%p\n", iosapic_intin, vi);
/* If this IRQ line has already been setup, skip it */
if (vi->irte)
@@ -941,8 +957,8 @@
vip->irqline = (unsigned char) cnt;
vip->iosapic = isi;
}
- if (!first_isi)
- first_isi = isi;
+ isi->isi_next = iosapic_list;
+ iosapic_list = isi;
return isi;
}
diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c
index 1f05913..19f6f70 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -613,6 +613,54 @@
return 0; /* truncation successful */
}
+/*
+ * extend_lmmio_len: extend lmmio range to maximum length
+ *
+ * This is needed at least on C8000 systems to get the ATI FireGL card
+ * working. On other systems we will currently not extend the lmmio space.
+ */
+static unsigned long
+extend_lmmio_len(unsigned long start, unsigned long end, unsigned long lba_len)
+{
+ struct resource *tmp;
+
+ pr_debug("LMMIO mismatch: PAT length = 0x%lx, MASK register = 0x%lx\n",
+ end - start, lba_len);
+
+ lba_len = min(lba_len+1, 256UL*1024*1024); /* limit to 256 MB */
+
+ pr_debug("LBA: lmmio_space [0x%lx-0x%lx] - original\n", start, end);
+
+ if (boot_cpu_data.cpu_type < mako) {
+ pr_info("LBA: Not a C8000 system - not extending LMMIO range.\n");
+ return end;
+ }
+
+ end += lba_len;
+ if (end < start) /* fix overflow */
+ end = -1ULL;
+
+ pr_debug("LBA: lmmio_space [0x%lx-0x%lx] - current\n", start, end);
+
+ /* first overlap */
+ for (tmp = iomem_resource.child; tmp; tmp = tmp->sibling) {
+ pr_debug("LBA: testing %pR\n", tmp);
+ if (tmp->start == start)
+ continue; /* ignore ourself */
+ if (tmp->end < start)
+ continue;
+ if (tmp->start > end)
+ continue;
+ if (end >= tmp->start)
+ end = tmp->start - 1;
+ }
+
+ pr_info("LBA: lmmio_space [0x%lx-0x%lx] - new\n", start, end);
+
+ /* return new end */
+ return end;
+}
+
#else
#define truncate_pat_collision(r,n) (0)
#endif
@@ -994,6 +1042,14 @@
case PAT_LMMIO:
/* used to fix up pre-initialized MEM BARs */
if (!lba_dev->hba.lmmio_space.flags) {
+ unsigned long lba_len;
+
+ lba_len = ~READ_REG32(lba_dev->hba.base_addr
+ + LBA_LMMIO_MASK);
+ if ((p->end - p->start) != lba_len)
+ p->end = extend_lmmio_len(p->start,
+ p->end, lba_len);
+
sprintf(lba_dev->hba.lmmio_name,
"PCI%02x LMMIO",
(int)lba_dev->hba.bus_num.start);
diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig
index a505760..46d2de2 100644
--- a/drivers/parport/Kconfig
+++ b/drivers/parport/Kconfig
@@ -36,7 +36,9 @@
config PARPORT_PC
tristate "PC-style hardware"
depends on (!SPARC64 || PCI) && !SPARC32 && !M32R && !FRV && !S390 && \
- (!M68K || ISA) && !MN10300 && !AVR32 && !BLACKFIN && !XTENSA
+ (!M68K || ISA) && !MN10300 && !AVR32 && !BLACKFIN && \
+ !XTENSA && !CRIS && !H8300 && !ARM64
+
---help---
You should say Y here if you have a PC-style parallel port. All
IBM PC compatible computers and some Alphas have PC-style
diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 903e128..b0a0d53 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2596,8 +2596,6 @@
syba_2p_epp,
syba_1p_ecp,
titan_010l,
- titan_1284p1,
- titan_1284p2,
avlab_1p,
avlab_2p,
oxsemi_952,
@@ -2656,8 +2654,6 @@
/* syba_2p_epp AP138B */ { 2, { { 0, 0x078 }, { 0, 0x178 }, } },
/* syba_1p_ecp W83787 */ { 1, { { 0, 0x078 }, } },
/* titan_010l */ { 1, { { 3, -1 }, } },
- /* titan_1284p1 */ { 1, { { 0, 1 }, } },
- /* titan_1284p2 */ { 2, { { 0, 1 }, { 2, 3 }, } },
/* avlab_1p */ { 1, { { 0, 1}, } },
/* avlab_2p */ { 2, { { 0, 1}, { 2, 3 },} },
/* The Oxford Semi cards are unusual: 954 doesn't support ECP,
@@ -2673,8 +2669,8 @@
/* netmos_9705 */ { 1, { { 0, -1 }, } },
/* netmos_9715 */ { 2, { { 0, 1 }, { 2, 3 },} },
/* netmos_9755 */ { 2, { { 0, 1 }, { 2, 3 },} },
- /* netmos_9805 */ { 1, { { 0, -1 }, } },
- /* netmos_9815 */ { 2, { { 0, -1 }, { 2, -1 }, } },
+ /* netmos_9805 */ { 1, { { 0, 1 }, } },
+ /* netmos_9815 */ { 2, { { 0, 1 }, { 2, 3 }, } },
/* netmos_9901 */ { 1, { { 0, -1 }, } },
/* netmos_9865 */ { 1, { { 0, -1 }, } },
/* quatech_sppxp100 */ { 1, { { 0, 1 }, } },
@@ -2718,8 +2714,6 @@
PCI_ANY_ID, PCI_ANY_ID, 0, 0, syba_1p_ecp },
{ PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_010L,
PCI_ANY_ID, PCI_ANY_ID, 0, 0, titan_010l },
- { 0x9710, 0x9805, 0x1000, 0x0010, 0, 0, titan_1284p1 },
- { 0x9710, 0x9815, 0x1000, 0x0020, 0, 0, titan_1284p2 },
/* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
/* AFAVLAB_TK9902 */
{ 0x14db, 0x2120, PCI_ANY_ID, PCI_ANY_ID, 0, 0, avlab_1p},
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 1cc2366..061da8c 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -484,28 +484,29 @@
{
int type = pci_pcie_type(dev);
- return pcie_cap_version(dev) > 1 ||
+ return type == PCI_EXP_TYPE_ENDPOINT ||
+ type == PCI_EXP_TYPE_LEG_END ||
type == PCI_EXP_TYPE_ROOT_PORT ||
- type == PCI_EXP_TYPE_ENDPOINT ||
- type == PCI_EXP_TYPE_LEG_END;
+ type == PCI_EXP_TYPE_UPSTREAM ||
+ type == PCI_EXP_TYPE_DOWNSTREAM ||
+ type == PCI_EXP_TYPE_PCI_BRIDGE ||
+ type == PCI_EXP_TYPE_PCIE_BRIDGE;
}
static inline bool pcie_cap_has_sltctl(const struct pci_dev *dev)
{
int type = pci_pcie_type(dev);
- return pcie_cap_version(dev) > 1 ||
- type == PCI_EXP_TYPE_ROOT_PORT ||
- (type == PCI_EXP_TYPE_DOWNSTREAM &&
- pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT);
+ return (type == PCI_EXP_TYPE_ROOT_PORT ||
+ type == PCI_EXP_TYPE_DOWNSTREAM) &&
+ pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT;
}
static inline bool pcie_cap_has_rtctl(const struct pci_dev *dev)
{
int type = pci_pcie_type(dev);
- return pcie_cap_version(dev) > 1 ||
- type == PCI_EXP_TYPE_ROOT_PORT ||
+ return type == PCI_EXP_TYPE_ROOT_PORT ||
type == PCI_EXP_TYPE_RC_EC;
}
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index aac7a40..0e0d0f7 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -92,7 +92,14 @@
if (ret)
presence = 0;
- list_for_each_entry_safe(dev, temp, &parent->devices, bus_list) {
+ /*
+ * Stopping an SR-IOV PF device removes all the associated VFs,
+ * which will update the bus->devices list and confuse the
+ * iterator. Therefore, iterate in reverse so we remove the VFs
+ * first, then the PF. We do the same in pci_stop_bus_device().
+ */
+ list_for_each_entry_safe_reverse(dev, temp, &parent->devices,
+ bus_list) {
pci_dev_get(dev);
if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE && presence) {
pci_read_config_byte(dev, PCI_BRIDGE_CONTROL, &bctl);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 5849927..6efc2ec 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -282,8 +282,8 @@
return WRONG_BUS_FREQUENCY;
}
- bsp = ctrl->pci_dev->bus->cur_bus_speed;
- msp = ctrl->pci_dev->bus->max_bus_speed;
+ bsp = ctrl->pci_dev->subordinate->cur_bus_speed;
+ msp = ctrl->pci_dev->subordinate->max_bus_speed;
/* Check if there are other slots or devices on the same bus */
if (!list_empty(&ctrl->pci_dev->subordinate->devices))
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index c93071d..a971a6f 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -92,6 +92,8 @@
pci_read_config_word(dev, iov->pos + PCI_SRIOV_VF_DID, &virtfn->device);
pci_setup_device(virtfn);
virtfn->dev.parent = dev->dev.parent;
+ virtfn->physfn = pci_dev_get(dev);
+ virtfn->is_virtfn = 1;
for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
res = dev->resource + PCI_IOV_RESOURCES + i;
@@ -113,9 +115,6 @@
pci_device_add(virtfn, virtfn->bus);
mutex_unlock(&iov->dev->sriov->lock);
- virtfn->physfn = pci_dev_get(dev);
- virtfn->is_virtfn = 1;
-
rc = pci_bus_add_device(virtfn);
sprintf(buf, "virtfn%u", id);
rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 2c10752..402063f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -530,6 +530,20 @@
return ret;
}
+static int msi_verify_entries(struct pci_dev *dev)
+{
+ struct msi_desc *entry;
+
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ if (!dev->no_64bit_msi || !entry->msg.address_hi)
+ continue;
+ dev_err(&dev->dev, "Device has broken 64-bit MSI but arch"
+ " tried to assign one above 4G\n");
+ return -EIO;
+ }
+ return 0;
+}
+
/**
* msi_capability_init - configure device's MSI capability structure
* @dev: pointer to the pci_dev data structure of MSI device function
@@ -583,6 +597,13 @@
return ret;
}
+ ret = msi_verify_entries(dev);
+ if (ret) {
+ msi_mask_irq(entry, mask, ~mask);
+ free_msi_irqs(dev);
+ return ret;
+ }
+
ret = populate_msi_sysfs(dev);
if (ret) {
msi_mask_irq(entry, mask, ~mask);
@@ -698,6 +719,11 @@
if (ret)
goto error;
+ /* Check if all MSI entries honor device restrictions */
+ ret = msi_verify_entries(dev);
+ if (ret)
+ goto error;
+
/*
* Some devices require MSI-X to be enabled before we can touch the
* MSI-X registers. We need to mask all the vectors to prevent
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index e4b1fb2..0eab3a3 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -47,6 +47,9 @@
if (event != ACPI_NOTIFY_DEVICE_WAKE || !pci_dev)
return;
+ if (pci_dev->pme_poll)
+ pci_dev->pme_poll = false;
+
if (pci_dev->current_state == PCI_D3cold) {
pci_wakeup_event(pci_dev);
pm_runtime_resume(&pci_dev->dev);
@@ -57,9 +60,6 @@
if (pci_dev->pme_support)
pci_check_pme_status(pci_dev);
- if (pci_dev->pme_poll)
- pci_dev->pme_poll = false;
-
pci_wakeup_event(pci_dev);
pm_runtime_resume(&pci_dev->dev);
@@ -317,13 +317,20 @@
/* ACPI bus type */
static int acpi_pci_find_device(struct device *dev, acpi_handle *handle)
{
- struct pci_dev * pci_dev;
- u64 addr;
+ struct pci_dev *pci_dev = to_pci_dev(dev);
+ bool is_bridge;
+ u64 addr;
- pci_dev = to_pci_dev(dev);
+ /*
+ * pci_is_bridge() is not suitable here, because pci_dev->subordinate
+ * is set only after acpi_pci_find_device() has been called for the
+ * given device.
+ */
+ is_bridge = pci_dev->hdr_type == PCI_HEADER_TYPE_BRIDGE
+ || pci_dev->hdr_type == PCI_HEADER_TYPE_CARDBUS;
/* Please ref to ACPI spec for the syntax of _ADR */
addr = (PCI_SLOT(pci_dev->devfn) << 16) | PCI_FUNC(pci_dev->devfn);
- *handle = acpi_get_child(DEVICE_ACPI_HANDLE(dev->parent), addr);
+ *handle = acpi_find_child(ACPI_HANDLE(dev->parent), addr, is_bridge);
if (!*handle)
return -ENODEV;
return 0;
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 79277fb..5548a13 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -19,6 +19,7 @@
#include <linux/cpu.h>
#include <linux/pm_runtime.h>
#include <linux/suspend.h>
+#include <linux/kexec.h>
#include "pci.h"
struct pci_dynid {
@@ -388,12 +389,17 @@
pci_msi_shutdown(pci_dev);
pci_msix_shutdown(pci_dev);
+#ifdef CONFIG_KEXEC
/*
- * Turn off Bus Master bit on the device to tell it to not
- * continue to do DMA. Don't touch devices in D3cold or unknown states.
+ * If this is a kexec reboot, turn off Bus Master bit on the
+ * device to tell it to not continue to do DMA. Don't touch
+ * devices in D3cold or unknown states.
+ * If it is not a kexec reboot, firmware will hit the PCI
+ * devices with big hammer and stop their DMA any way.
*/
- if (pci_dev->current_state <= PCI_D3hot)
+ if (kexec_in_progress && (pci_dev->current_state <= PCI_D3hot))
pci_clear_master(pci_dev);
+#endif
}
#ifdef CONFIG_PM
@@ -1261,7 +1267,7 @@
if (add_uevent_var(env, "PCI_SLOT_NAME=%s", pci_name(pdev)))
return -ENOMEM;
- if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x",
+ if (add_uevent_var(env, "MODALIAS=pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X",
pdev->vendor, pdev->device,
pdev->subsystem_vendor, pdev->subsystem_device,
(u8)(pdev->class >> 16), (u8)(pdev->class >> 8),
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5b4a9d9..689f3c8 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -175,7 +175,7 @@
{
struct pci_dev *pci_dev = to_pci_dev(dev);
- return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02x\n",
+ return sprintf(buf, "pci:v%08Xd%08Xsv%08Xsd%08Xbc%02Xsc%02Xi%02X\n",
pci_dev->vendor, pci_dev->device,
pci_dev->subsystem_vendor, pci_dev->subsystem_device,
(u8)(pci_dev->class >> 16), (u8)(pci_dev->class >> 8),
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a899d8b..d6ceb2e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1119,6 +1119,8 @@
static int do_pci_enable_device(struct pci_dev *dev, int bars)
{
int err;
+ u16 cmd;
+ u8 pin;
err = pci_set_power_state(dev, PCI_D0);
if (err < 0 && err != -EIO)
@@ -1128,6 +1130,17 @@
return err;
pci_fixup_device(pci_fixup_enable, dev);
+ if (dev->msi_enabled || dev->msix_enabled)
+ return 0;
+
+ pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (pin) {
+ pci_read_config_word(dev, PCI_COMMAND, &cmd);
+ if (cmd & PCI_COMMAND_INTX_DISABLE)
+ pci_write_config_word(dev, PCI_COMMAND,
+ cmd & ~PCI_COMMAND_INTX_DISABLE);
+ }
+
return 0;
}
@@ -3646,7 +3659,7 @@
u16 cmd;
int rc;
- WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) & (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
+ WARN_ON((flags & PCI_VGA_STATE_CHANGE_DECODES) && (command_bits & ~(PCI_COMMAND_IO|PCI_COMMAND_MEMORY)));
/* ARCH specific VGA enables */
rc = pci_set_vga_state_arch(dev, decode, command_bits, flags);
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 696caed..ce8acc7 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -223,7 +223,6 @@
static void pcie_portdrv_remove(struct pci_dev *dev)
{
pcie_port_device_remove(dev);
- pci_disable_device(dev);
}
static int error_detected_iter(struct device *device, void *data)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 70f10fa..034a4d2 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -210,14 +210,17 @@
res->flags |= IORESOURCE_SIZEALIGN;
if (res->flags & IORESOURCE_IO) {
l &= PCI_BASE_ADDRESS_IO_MASK;
+ sz &= PCI_BASE_ADDRESS_IO_MASK;
mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT;
} else {
l &= PCI_BASE_ADDRESS_MEM_MASK;
+ sz &= PCI_BASE_ADDRESS_MEM_MASK;
mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
}
} else {
res->flags |= (l & IORESOURCE_ROM_ENABLE);
l &= PCI_ROM_ADDRESS_MASK;
+ sz &= PCI_ROM_ADDRESS_MASK;
mask = (u32)PCI_ROM_ADDRESS_MASK;
}
@@ -1703,12 +1706,16 @@
bridge->dev.release = pci_release_bus_bridge_dev;
dev_set_name(&bridge->dev, "pci%04x:%02x", pci_domain_nr(b), bus);
error = pcibios_root_bridge_prepare(bridge);
- if (error)
- goto bridge_dev_reg_err;
+ if (error) {
+ kfree(bridge);
+ goto err_out;
+ }
error = device_register(&bridge->dev);
- if (error)
- goto bridge_dev_reg_err;
+ if (error) {
+ put_device(&bridge->dev);
+ goto err_out;
+ }
b->bridge = get_device(&bridge->dev);
device_enable_async_suspend(b->bridge);
pci_set_bus_of_node(b);
@@ -1764,8 +1771,6 @@
class_dev_reg_err:
put_device(&bridge->dev);
device_unregister(&bridge->dev);
-bridge_dev_reg_err:
- kfree(bridge);
err_out:
kfree(b);
return NULL;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 7d68aee..910339c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -28,6 +28,7 @@
#include <linux/ioport.h>
#include <linux/sched.h>
#include <linux/ktime.h>
+#include <linux/mm.h>
#include <asm/dma.h> /* isa_dma_bridge_buggy */
#include "pci.h"
@@ -291,6 +292,25 @@
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, PCI_DEVICE_ID_IBM_CITRINE, quirk_citrine);
+/* On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
+static void quirk_extend_bar_to_page(struct pci_dev *dev)
+{
+ int i;
+
+ for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+ struct resource *r = &dev->resource[i];
+
+ if (r->flags & IORESOURCE_MEM && resource_size(r) < PAGE_SIZE) {
+ r->end = PAGE_SIZE - 1;
+ r->start = 0;
+ r->flags |= IORESOURCE_UNSET;
+ dev_info(&dev->dev, "expanded BAR %d to page size: %pR\n",
+ i, r);
+ }
+ }
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_IBM, 0x034a, quirk_extend_bar_to_page);
+
/*
* S3 868 and 968 chips report region size equal to 32M, but they decode 64M.
* If it's needed, re-allocate the region.
@@ -1022,6 +1042,8 @@
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP700_SATA, quirk_amd_ide_mode);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE, quirk_amd_ide_mode);
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_HUDSON2_SATA_IDE, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x7900, quirk_amd_ide_mode);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, 0x7900, quirk_amd_ide_mode);
/*
* Serverworks CSB5 IDE does not fully support native mode
@@ -2928,6 +2950,7 @@
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0102, disable_igfx_irq);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x010a, disable_igfx_irq);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x0152, disable_igfx_irq);
/*
* Some devices may pass our check in pci_intx_mask_supported if
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index c5d0a08..d6d4997 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -69,6 +69,7 @@
{
void __iomem *image;
int last_image;
+ unsigned length;
image = rom;
do {
@@ -91,9 +92,9 @@
if (readb(pds + 3) != 'R')
break;
last_image = readb(pds + 21) & 0x80;
- /* this length is reliable */
- image += readw(pds + 16) * 512;
- } while (!last_image);
+ length = readw(pds + 16);
+ image += length * 512;
+ } while (length && !last_image);
/* never return a size larger than the PCI resource window */
/* there are known ROMs that get the size wrong */
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index d254e23..64a7de2 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -300,6 +300,47 @@
}
}
+static unsigned long pci_fail_res_type_mask(struct list_head *fail_head)
+{
+ struct pci_dev_resource *fail_res;
+ unsigned long mask = 0;
+
+ /* check failed type */
+ list_for_each_entry(fail_res, fail_head, list)
+ mask |= fail_res->flags;
+
+ /*
+ * one pref failed resource will set IORESOURCE_MEM,
+ * as we can allocate pref in non-pref range.
+ * Will release all assigned non-pref sibling resources
+ * according to that bit.
+ */
+ return mask & (IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH);
+}
+
+static bool pci_need_to_release(unsigned long mask, struct resource *res)
+{
+ if (res->flags & IORESOURCE_IO)
+ return !!(mask & IORESOURCE_IO);
+
+ /* check pref at first */
+ if (res->flags & IORESOURCE_PREFETCH) {
+ if (mask & IORESOURCE_PREFETCH)
+ return true;
+ /* count pref if its parent is non-pref */
+ else if ((mask & IORESOURCE_MEM) &&
+ !(res->parent->flags & IORESOURCE_PREFETCH))
+ return true;
+ else
+ return false;
+ }
+
+ if (res->flags & IORESOURCE_MEM)
+ return !!(mask & IORESOURCE_MEM);
+
+ return false; /* should not get here */
+}
+
static void __assign_resources_sorted(struct list_head *head,
struct list_head *realloc_head,
struct list_head *fail_head)
@@ -312,11 +353,24 @@
* if could do that, could get out early.
* if could not do that, we still try to assign requested at first,
* then try to reassign add_size for some resources.
+ *
+ * Separate three resource type checking if we need to release
+ * assigned resource after requested + add_size try.
+ * 1. if there is io port assign fail, will release assigned
+ * io port.
+ * 2. if there is pref mmio assign fail, release assigned
+ * pref mmio.
+ * if assigned pref mmio's parent is non-pref mmio and there
+ * is non-pref mmio assign fail, will release that assigned
+ * pref mmio.
+ * 3. if there is non-pref mmio assign fail or pref mmio
+ * assigned fail, will release assigned non-pref mmio.
*/
LIST_HEAD(save_head);
LIST_HEAD(local_fail_head);
struct pci_dev_resource *save_res;
- struct pci_dev_resource *dev_res;
+ struct pci_dev_resource *dev_res, *tmp_res;
+ unsigned long fail_type;
/* Check if optional add_size is there */
if (!realloc_head || list_empty(realloc_head))
@@ -348,6 +402,19 @@
return;
}
+ /* check failed type */
+ fail_type = pci_fail_res_type_mask(&local_fail_head);
+ /* remove not need to be released assigned res from head list etc */
+ list_for_each_entry_safe(dev_res, tmp_res, head, list)
+ if (dev_res->res->parent &&
+ !pci_need_to_release(fail_type, dev_res->res)) {
+ /* remove it from realloc_head list */
+ remove_from_list(realloc_head, dev_res->res);
+ remove_from_list(&save_head, dev_res->res);
+ list_del(&dev_res->list);
+ kfree(dev_res);
+ }
+
free_list(&local_fail_head);
/* Release assigned resource */
list_for_each_entry(dev_res, head, list)
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 966abc6..f7197a7 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -678,10 +678,9 @@
if (!pcifront_dev) {
dev_info(&pdev->xdev->dev, "Installing PCI frontend\n");
pcifront_dev = pdev;
- } else {
- dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
+ } else
err = -EEXIST;
- }
+
spin_unlock(&pcifront_dev_lock);
if (!err && !swiotlb_nr_tbl()) {
@@ -848,7 +847,7 @@
goto out;
err = pcifront_connect_and_init_dma(pdev);
- if (err) {
+ if (err && err != -EEXIST) {
xenbus_dev_fatal(pdev->xdev, err,
"Error setting up PCI Frontend");
goto out;
diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 01463c7..1b2c631 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -100,9 +100,9 @@
int vcc = gpio_is_valid(cf->board->vcc_pin);
*sp = SS_DETECT | SS_3VCARD;
- if (!rdy || gpio_get_value(rdy))
+ if (!rdy || gpio_get_value(cf->board->irq_pin))
*sp |= SS_READY;
- if (!vcc || gpio_get_value(vcc))
+ if (!vcc || gpio_get_value(cf->board->vcc_pin))
*sp |= SS_POWERON;
} else
*sp = 0;
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 9bdaeb8..b32d6c7 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -2,7 +2,7 @@
ccflags-$(CONFIG_DEBUG_PINCTRL) += -DDEBUG
-obj-$(CONFIG_PINCTRL) += core.o
+obj-$(CONFIG_PINCTRL) += core.o pinctrl-utils.o
obj-$(CONFIG_PINMUX) += pinmux.o
obj-$(CONFIG_PINCONF) += pinconf.o
ifeq ($(CONFIG_OF),y)
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 5327f35..9c9fc69 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -807,7 +807,9 @@
kref_init(&p->users);
/* Add the pinctrl handle to the global list */
+ mutex_lock(&pinctrl_list_mutex);
list_add_tail(&p->node, &pinctrl_list);
+ mutex_unlock(&pinctrl_list_mutex);
return p;
}
@@ -1691,14 +1693,15 @@
if (pctldev == NULL)
return;
- mutex_lock(&pinctrldev_list_mutex);
mutex_lock(&pctldev->mutex);
-
pinctrl_remove_device_debugfs(pctldev);
+ mutex_unlock(&pctldev->mutex);
if (!IS_ERR(pctldev->p))
pinctrl_put(pctldev->p);
+ mutex_lock(&pinctrldev_list_mutex);
+ mutex_lock(&pctldev->mutex);
/* TODO: check that no pinmuxes are still active? */
list_del(&pctldev->node);
/* Destroy descriptor tree */
diff --git a/drivers/pinctrl/mvebu/pinctrl-dove.c b/drivers/pinctrl/mvebu/pinctrl-dove.c
index 428ea96..e29e6d8 100644
--- a/drivers/pinctrl/mvebu/pinctrl-dove.c
+++ b/drivers/pinctrl/mvebu/pinctrl-dove.c
@@ -323,7 +323,7 @@
unsigned long gcfg2 = readl(DOVE_GLOBAL_CONFIG_2);
gcfg1 &= ~DOVE_TWSI_ENABLE_OPTION1;
- gcfg2 &= ~(DOVE_TWSI_ENABLE_OPTION2 | DOVE_TWSI_ENABLE_OPTION2);
+ gcfg2 &= ~(DOVE_TWSI_ENABLE_OPTION2 | DOVE_TWSI_ENABLE_OPTION3);
switch (config) {
case 1:
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 2ad5a8d..872e74a 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -21,8 +21,10 @@
#include <linux/pinctrl/pinctrl.h>
#include <linux/pinctrl/pinconf.h>
#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/of.h>
#include "core.h"
#include "pinconf.h"
+#include "pinctrl-utils.h"
#ifdef CONFIG_DEBUG_FS
@@ -37,14 +39,19 @@
static struct pin_config_item conf_items[] = {
PCONFDUMP(PIN_CONFIG_BIAS_DISABLE, "input bias disabled", NULL),
PCONFDUMP(PIN_CONFIG_BIAS_HIGH_IMPEDANCE, "input bias high impedance", NULL),
+ PCONFDUMP(PIN_CONFIG_BIAS_BUS_HOLD, "input bias bus hold", NULL),
PCONFDUMP(PIN_CONFIG_BIAS_PULL_UP, "input bias pull up", NULL),
PCONFDUMP(PIN_CONFIG_BIAS_PULL_DOWN, "input bias pull down", NULL),
+ PCONFDUMP(PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
+ "input bias pull to pin specific state", NULL),
PCONFDUMP(PIN_CONFIG_DRIVE_PUSH_PULL, "output drive push pull", NULL),
PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_DRAIN, "output drive open drain", NULL),
PCONFDUMP(PIN_CONFIG_DRIVE_OPEN_SOURCE, "output drive open source", NULL),
+ PCONFDUMP(PIN_CONFIG_DRIVE_STRENGTH, "output drive strength", "mA"),
+ PCONFDUMP(PIN_CONFIG_INPUT_ENABLE, "input enabled", NULL),
PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT_ENABLE, "input schmitt enabled", NULL),
PCONFDUMP(PIN_CONFIG_INPUT_SCHMITT, "input schmitt trigger", NULL),
- PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "time units"),
+ PCONFDUMP(PIN_CONFIG_INPUT_DEBOUNCE, "input debounce", "usec"),
PCONFDUMP(PIN_CONFIG_POWER_SOURCE, "pin power source", "selector"),
PCONFDUMP(PIN_CONFIG_SLEW_RATE, "slew rate", NULL),
PCONFDUMP(PIN_CONFIG_LOW_POWER_MODE, "pin low power", "mode"),
@@ -135,3 +142,198 @@
}
EXPORT_SYMBOL_GPL(pinconf_generic_dump_config);
#endif
+
+#ifdef CONFIG_OF
+struct pinconf_generic_dt_params {
+ const char * const property;
+ enum pin_config_param param;
+ u32 default_value;
+};
+
+static struct pinconf_generic_dt_params dt_params[] = {
+ { "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 },
+ { "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 },
+ { "bias-bus-hold", PIN_CONFIG_BIAS_BUS_HOLD, 0 },
+ { "bias-pull-up", PIN_CONFIG_BIAS_PULL_UP, 1 },
+ { "bias-pull-down", PIN_CONFIG_BIAS_PULL_DOWN, 1 },
+ { "bias-pull-pin-default", PIN_CONFIG_BIAS_PULL_PIN_DEFAULT, 1 },
+ { "drive-push-pull", PIN_CONFIG_DRIVE_PUSH_PULL, 0 },
+ { "drive-open-drain", PIN_CONFIG_DRIVE_OPEN_DRAIN, 0 },
+ { "drive-open-source", PIN_CONFIG_DRIVE_OPEN_SOURCE, 0 },
+ { "drive-strength", PIN_CONFIG_DRIVE_STRENGTH, 0 },
+ { "input-enable", PIN_CONFIG_INPUT_ENABLE, 1 },
+ { "input-disable", PIN_CONFIG_INPUT_ENABLE, 0 },
+ { "input-schmitt-enable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 1 },
+ { "input-schmitt-disable", PIN_CONFIG_INPUT_SCHMITT_ENABLE, 0 },
+ { "input-debounce", PIN_CONFIG_INPUT_DEBOUNCE, 0 },
+ { "low-power-enable", PIN_CONFIG_LOW_POWER_MODE, 1 },
+ { "low-power-disable", PIN_CONFIG_LOW_POWER_MODE, 0 },
+ { "output-low", PIN_CONFIG_OUTPUT, 0, },
+ { "output-high", PIN_CONFIG_OUTPUT, 1, },
+ { "slew-rate", PIN_CONFIG_SLEW_RATE, 0},
+};
+
+/**
+ * pinconf_generic_parse_dt_config()
+ * parse the config properties into generic pinconfig values.
+ * @np: node containing the pinconfig properties
+ * @configs: array with nconfigs entries containing the generic pinconf values
+ * @nconfigs: umber of configurations
+ */
+int pinconf_generic_parse_dt_config(struct device_node *np,
+ unsigned long **configs,
+ unsigned int *nconfigs)
+{
+ unsigned long *cfg;
+ unsigned int ncfg = 0;
+ int ret;
+ int i;
+ u32 val;
+
+ if (!np)
+ return -EINVAL;
+
+ /* allocate a temporary array big enough to hold one of each option */
+ cfg = kzalloc(sizeof(*cfg) * ARRAY_SIZE(dt_params), GFP_KERNEL);
+ if (!cfg)
+ return -ENOMEM;
+
+ for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
+ struct pinconf_generic_dt_params *par = &dt_params[i];
+ ret = of_property_read_u32(np, par->property, &val);
+
+ /* property not found */
+ if (ret == -EINVAL)
+ continue;
+
+ /* use default value, when no value is specified */
+ if (ret)
+ val = par->default_value;
+
+ pr_debug("found %s with value %u\n", par->property, val);
+ cfg[ncfg] = pinconf_to_config_packed(par->param, val);
+ ncfg++;
+ }
+
+ ret = 0;
+
+ /* no configs found at all */
+ if (ncfg == 0) {
+ *configs = NULL;
+ *nconfigs = 0;
+ goto out;
+ }
+
+ /*
+ * Now limit the number of configs to the real number of
+ * found properties.
+ */
+ *configs = kzalloc(ncfg * sizeof(unsigned long), GFP_KERNEL);
+ if (!*configs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ memcpy(*configs, cfg, ncfg * sizeof(unsigned long));
+ *nconfigs = ncfg;
+
+out:
+ kfree(cfg);
+ return ret;
+}
+
+int pinconf_generic_dt_subnode_to_map_new(struct pinctrl_dev *pctldev,
+ struct device_node *np, struct pinctrl_map **map,
+ unsigned *reserved_maps, unsigned *num_maps,
+ enum pinctrl_map_type type)
+{
+ int ret;
+ const char *function;
+ struct device *dev = pctldev->dev;
+ unsigned long *configs = NULL;
+ unsigned num_configs = 0;
+ unsigned reserve;
+ struct property *prop;
+ const char *group;
+
+ ret = of_property_read_string(np, "function", &function);
+ if (ret < 0) {
+ /* EINVAL=missing, which is fine since it's optional */
+ if (ret != -EINVAL)
+ dev_err(dev, "could not parse property function\n");
+ function = NULL;
+ }
+
+ ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+ if (ret < 0) {
+ dev_err(dev, "could not parse node property\n");
+ return ret;
+ }
+
+ reserve = 0;
+ if (function != NULL)
+ reserve++;
+ if (num_configs)
+ reserve++;
+ ret = of_property_count_strings(np, "pins");
+ if (ret < 0) {
+ dev_err(dev, "could not parse property pins\n");
+ goto exit;
+ }
+ reserve *= ret;
+
+ ret = pinctrl_utils_reserve_map(pctldev, map, reserved_maps,
+ num_maps, reserve);
+ if (ret < 0)
+ goto exit;
+
+ of_property_for_each_string(np, "pins", prop, group) {
+ if (function) {
+ ret = pinctrl_utils_add_map_mux(pctldev, map,
+ reserved_maps, num_maps, group,
+ function);
+ if (ret < 0)
+ goto exit;
+ }
+
+ if (num_configs) {
+ ret = pinctrl_utils_add_map_configs(pctldev, map,
+ reserved_maps, num_maps, group, configs,
+ num_configs, type);
+ if (ret < 0)
+ goto exit;
+ }
+ }
+ ret = 0;
+
+exit:
+ kfree(configs);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pinconf_generic_dt_subnode_to_map_new);
+
+int pinconf_generic_dt_node_to_map_new(struct pinctrl_dev *pctldev,
+ struct device_node *np_config, struct pinctrl_map **map,
+ unsigned *num_maps, enum pinctrl_map_type type)
+{
+ unsigned reserved_maps;
+ struct device_node *np;
+ int ret;
+
+ reserved_maps = 0;
+ *map = NULL;
+ *num_maps = 0;
+
+ for_each_child_of_node(np_config, np) {
+ ret = pinconf_generic_dt_subnode_to_map_new(pctldev, np, map,
+ &reserved_maps, num_maps, type);
+ if (ret < 0) {
+ pinctrl_utils_dt_free_map(pctldev, *map, *num_maps);
+ return ret;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pinconf_generic_dt_node_to_map_new);
+
+#endif
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 694c3ac..596a252 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -35,7 +35,9 @@
return -EINVAL;
}
/* We have to be able to config the pins in SOME way */
- if (!ops->pin_config_set && !ops->pin_config_group_set) {
+ if (!ops->pin_config_set && !ops->pin_config_group_set
+ && !ops->pin_config_set_bulk
+ && !ops->pin_config_group_set_bulk) {
dev_err(pctldev->dev,
"pinconf has to be able to set a pins config\n");
return -EINVAL;
@@ -75,98 +77,6 @@
return ops->pin_config_get(pctldev, pin, config);
}
-/**
- * pin_config_get() - get the configuration of a single pin parameter
- * @dev_name: name of the pin controller device for this pin
- * @name: name of the pin to get the config for
- * @config: the config pointed to by this argument will be filled in with the
- * current pin state, it can be used directly by drivers as a numeral, or
- * it can be dereferenced to any struct.
- */
-int pin_config_get(const char *dev_name, const char *name,
- unsigned long *config)
-{
- struct pinctrl_dev *pctldev;
- int pin;
-
- pctldev = get_pinctrl_dev_from_devname(dev_name);
- if (!pctldev) {
- pin = -EINVAL;
- return pin;
- }
-
- mutex_lock(&pctldev->mutex);
-
- pin = pin_get_from_name(pctldev, name);
- if (pin < 0)
- goto unlock;
-
- pin = pin_config_get_for_pin(pctldev, pin, config);
-
-unlock:
- mutex_unlock(&pctldev->mutex);
- return pin;
-}
-EXPORT_SYMBOL(pin_config_get);
-
-static int pin_config_set_for_pin(struct pinctrl_dev *pctldev, unsigned pin,
- unsigned long config)
-{
- const struct pinconf_ops *ops = pctldev->desc->confops;
- int ret;
-
- if (!ops || !ops->pin_config_set) {
- dev_err(pctldev->dev, "cannot configure pin, missing "
- "config function in driver\n");
- return -EINVAL;
- }
-
- ret = ops->pin_config_set(pctldev, pin, config);
- if (ret) {
- dev_err(pctldev->dev,
- "unable to set pin configuration on pin %d\n", pin);
- return ret;
- }
-
- return 0;
-}
-
-/**
- * pin_config_set() - set the configuration of a single pin parameter
- * @dev_name: name of pin controller device for this pin
- * @name: name of the pin to set the config for
- * @config: the config in this argument will contain the desired pin state, it
- * can be used directly by drivers as a numeral, or it can be dereferenced
- * to any struct.
- */
-int pin_config_set(const char *dev_name, const char *name,
- unsigned long config)
-{
- struct pinctrl_dev *pctldev;
- int pin, ret;
-
- pctldev = get_pinctrl_dev_from_devname(dev_name);
- if (!pctldev) {
- ret = -EINVAL;
- return ret;
- }
-
- mutex_lock(&pctldev->mutex);
-
- pin = pin_get_from_name(pctldev, name);
- if (pin < 0) {
- ret = pin;
- goto unlock;
- }
-
- ret = pin_config_set_for_pin(pctldev, pin, config);
-
-unlock:
- mutex_unlock(&pctldev->mutex);
- return ret;
-}
-EXPORT_SYMBOL(pin_config_set);
-
int pin_config_group_get(const char *dev_name, const char *pin_group,
unsigned long *config)
{
@@ -204,88 +114,6 @@
mutex_unlock(&pctldev->mutex);
return ret;
}
-EXPORT_SYMBOL(pin_config_group_get);
-
-int pin_config_group_set(const char *dev_name, const char *pin_group,
- unsigned long config)
-{
- struct pinctrl_dev *pctldev;
- const struct pinconf_ops *ops;
- const struct pinctrl_ops *pctlops;
- int selector;
- const unsigned *pins;
- unsigned num_pins;
- int ret;
- int i;
-
- pctldev = get_pinctrl_dev_from_devname(dev_name);
- if (!pctldev) {
- ret = -EINVAL;
- return ret;
- }
-
- mutex_lock(&pctldev->mutex);
-
- ops = pctldev->desc->confops;
- pctlops = pctldev->desc->pctlops;
-
- if (!ops || (!ops->pin_config_group_set && !ops->pin_config_set)) {
- dev_err(pctldev->dev, "cannot configure pin group, missing "
- "config function in driver\n");
- ret = -EINVAL;
- goto unlock;
- }
-
- selector = pinctrl_get_group_selector(pctldev, pin_group);
- if (selector < 0) {
- ret = selector;
- goto unlock;
- }
-
- ret = pctlops->get_group_pins(pctldev, selector, &pins, &num_pins);
- if (ret) {
- dev_err(pctldev->dev, "cannot configure pin group, error "
- "getting pins\n");
- goto unlock;
- }
-
- /*
- * If the pin controller supports handling entire groups we use that
- * capability.
- */
- if (ops->pin_config_group_set) {
- ret = ops->pin_config_group_set(pctldev, selector, config);
- /*
- * If the pin controller prefer that a certain group be handled
- * pin-by-pin as well, it returns -EAGAIN.
- */
- if (ret != -EAGAIN)
- goto unlock;
- }
-
- /*
- * If the controller cannot handle entire groups, we configure each pin
- * individually.
- */
- if (!ops->pin_config_set) {
- ret = 0;
- goto unlock;
- }
-
- for (i = 0; i < num_pins; i++) {
- ret = ops->pin_config_set(pctldev, pins[i], config);
- if (ret < 0)
- goto unlock;
- }
-
- ret = 0;
-
-unlock:
- mutex_unlock(&pctldev->mutex);
-
- return ret;
-}
-EXPORT_SYMBOL(pin_config_group_set);
int pinconf_map_to_setting(struct pinctrl_map const *map,
struct pinctrl_setting *setting)
@@ -332,7 +160,7 @@
{
struct pinctrl_dev *pctldev = setting->pctldev;
const struct pinconf_ops *ops = pctldev->desc->confops;
- int i, ret;
+ int ret, i;
if (!ops) {
dev_err(pctldev->dev, "missing confops\n");
@@ -341,39 +169,66 @@
switch (setting->type) {
case PIN_MAP_TYPE_CONFIGS_PIN:
- if (!ops->pin_config_set) {
+ if (!ops->pin_config_set && !ops->pin_config_set_bulk) {
dev_err(pctldev->dev, "missing pin_config_set op\n");
return -EINVAL;
}
- for (i = 0; i < setting->data.configs.num_configs; i++) {
- ret = ops->pin_config_set(pctldev,
+ if (ops->pin_config_set_bulk) {
+ ret = ops->pin_config_set_bulk(pctldev,
setting->data.configs.group_or_pin,
- setting->data.configs.configs[i]);
+ setting->data.configs.configs,
+ setting->data.configs.num_configs);
if (ret < 0) {
dev_err(pctldev->dev,
- "pin_config_set op failed for pin %d config %08lx\n",
- setting->data.configs.group_or_pin,
- setting->data.configs.configs[i]);
+ "pin_config_set_bulk op failed for pin %d\n",
+ setting->data.configs.group_or_pin);
return ret;
}
+ } else if (ops->pin_config_set) {
+ for (i = 0; i < setting->data.configs.num_configs; i++) {
+ ret = ops->pin_config_set(pctldev,
+ setting->data.configs.group_or_pin,
+ setting->data.configs.configs[i]);
+ if (ret < 0) {
+ dev_err(pctldev->dev,
+ "pin_config_set op failed for pin %d config %08lx\n",
+ setting->data.configs.group_or_pin,
+ setting->data.configs.configs[i]);
+ return ret;
+ }
+ }
}
break;
case PIN_MAP_TYPE_CONFIGS_GROUP:
- if (!ops->pin_config_group_set) {
+ if (!ops->pin_config_group_set &&
+ !ops->pin_config_group_set_bulk) {
dev_err(pctldev->dev,
"missing pin_config_group_set op\n");
return -EINVAL;
}
- for (i = 0; i < setting->data.configs.num_configs; i++) {
- ret = ops->pin_config_group_set(pctldev,
+ if (ops->pin_config_group_set_bulk) {
+ ret = ops->pin_config_group_set_bulk(pctldev,
setting->data.configs.group_or_pin,
- setting->data.configs.configs[i]);
+ setting->data.configs.configs,
+ setting->data.configs.num_configs);
if (ret < 0) {
dev_err(pctldev->dev,
- "pin_config_group_set op failed for group %d config %08lx\n",
+ "pin_config_group_set_bulk op failed for group %d\n",
+ setting->data.configs.group_or_pin);
+ return ret;
+ }
+ } else if (ops->pin_config_group_set) {
+ for (i = 0; i < setting->data.configs.num_configs; i++) {
+ ret = ops->pin_config_group_set(pctldev,
setting->data.configs.group_or_pin,
setting->data.configs.configs[i]);
- return ret;
+ if (ret < 0) {
+ dev_err(pctldev->dev,
+ "pin_config_group_set op failed for group %d config %08lx\n",
+ setting->data.configs.group_or_pin,
+ setting->data.configs.configs[i]);
+ return ret;
+ }
}
}
break;
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index 92c7267..a4a5417 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -123,3 +123,9 @@
return;
}
#endif
+
+#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
+int pinconf_generic_parse_dt_config(struct device_node *np,
+ unsigned long **configs,
+ unsigned int *nconfigs);
+#endif
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 5d7529e..314e5e8 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -325,7 +325,7 @@
static unsigned at91_mux_get_pullup(void __iomem *pio, unsigned pin)
{
- return (readl_relaxed(pio + PIO_PUSR) >> pin) & 0x1;
+ return !((readl_relaxed(pio + PIO_PUSR) >> pin) & 0x1);
}
static void at91_mux_set_pullup(void __iomem *pio, unsigned mask, bool on)
@@ -445,7 +445,7 @@
static bool at91_mux_pio3_get_pulldown(void __iomem *pio, unsigned pin)
{
- return (__raw_readl(pio + PIO_PPDSR) >> pin) & 0x1;
+ return !((__raw_readl(pio + PIO_PPDSR) >> pin) & 0x1);
}
static void at91_mux_pio3_set_pulldown(void __iomem *pio, unsigned mask, bool is_on)
diff --git a/drivers/pinctrl/pinctrl-sunxi.c b/drivers/pinctrl/pinctrl-sunxi.c
index b7d8c89..876d7cc 100644
--- a/drivers/pinctrl/pinctrl-sunxi.c
+++ b/drivers/pinctrl/pinctrl-sunxi.c
@@ -1754,12 +1754,6 @@
return val;
}
-static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip,
- unsigned offset, int value)
-{
- return pinctrl_gpio_direction_output(chip->base + offset);
-}
-
static void sunxi_pinctrl_gpio_set(struct gpio_chip *chip,
unsigned offset, int value)
{
@@ -1770,6 +1764,13 @@
writel((value & DATA_PINS_MASK) << index, pctl->membase + reg);
}
+static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip,
+ unsigned offset, int value)
+{
+ sunxi_pinctrl_gpio_set(chip, offset, value);
+ return pinctrl_gpio_direction_output(chip->base + offset);
+}
+
static int sunxi_pinctrl_gpio_of_xlate(struct gpio_chip *gc,
const struct of_phandle_args *gpiospec,
u32 *flags)
diff --git a/drivers/pinctrl/pinctrl-utils.c b/drivers/pinctrl/pinctrl-utils.c
new file mode 100644
index 0000000..48277e0
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-utils.c
@@ -0,0 +1,141 @@
+/*
+ * Utils functions to implement the pincontrol driver.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include "core.h"
+#include "pinctrl-utils.h"
+
+int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, unsigned reserve)
+{
+ unsigned old_num = *reserved_maps;
+ unsigned new_num = *num_maps + reserve;
+ struct pinctrl_map *new_map;
+
+ if (old_num >= new_num)
+ return 0;
+
+ new_map = krealloc(*map, sizeof(*new_map) * new_num, GFP_KERNEL);
+ if (!new_map) {
+ dev_err(pctldev->dev, "krealloc(map) failed\n");
+ return -ENOMEM;
+ }
+
+ memset(new_map + old_num, 0, (new_num - old_num) * sizeof(*new_map));
+
+ *map = new_map;
+ *reserved_maps = new_num;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_reserve_map);
+
+int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, const char *group,
+ const char *function)
+{
+ if (WARN_ON(*num_maps == *reserved_maps))
+ return -ENOSPC;
+
+ (*map)[*num_maps].type = PIN_MAP_TYPE_MUX_GROUP;
+ (*map)[*num_maps].data.mux.group = group;
+ (*map)[*num_maps].data.mux.function = function;
+ (*num_maps)++;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_mux);
+
+int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, const char *group,
+ unsigned long *configs, unsigned num_configs,
+ enum pinctrl_map_type type)
+{
+ unsigned long *dup_configs;
+
+ if (WARN_ON(*num_maps == *reserved_maps))
+ return -ENOSPC;
+
+ dup_configs = kmemdup(configs, num_configs * sizeof(*dup_configs),
+ GFP_KERNEL);
+ if (!dup_configs) {
+ dev_err(pctldev->dev, "kmemdup(configs) failed\n");
+ return -ENOMEM;
+ }
+
+ (*map)[*num_maps].type = type;
+ (*map)[*num_maps].data.configs.group_or_pin = group;
+ (*map)[*num_maps].data.configs.configs = dup_configs;
+ (*map)[*num_maps].data.configs.num_configs = num_configs;
+ (*num_maps)++;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_map_configs);
+
+int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
+ unsigned long **configs, unsigned *num_configs,
+ unsigned long config)
+{
+ unsigned old_num = *num_configs;
+ unsigned new_num = old_num + 1;
+ unsigned long *new_configs;
+
+ new_configs = krealloc(*configs, sizeof(*new_configs) * new_num,
+ GFP_KERNEL);
+ if (!new_configs) {
+ dev_err(pctldev->dev, "krealloc(configs) failed\n");
+ return -ENOMEM;
+ }
+
+ new_configs[old_num] = config;
+
+ *configs = new_configs;
+ *num_configs = new_num;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_add_config);
+
+void pinctrl_utils_dt_free_map(struct pinctrl_dev *pctldev,
+ struct pinctrl_map *map, unsigned num_maps)
+{
+ int i;
+
+ for (i = 0; i < num_maps; i++) {
+ switch (map[i].type) {
+ case PIN_MAP_TYPE_CONFIGS_GROUP:
+ case PIN_MAP_TYPE_CONFIGS_PIN:
+ kfree(map[i].data.configs.configs);
+ break;
+ default:
+ break;
+ }
+ }
+ kfree(map);
+}
+EXPORT_SYMBOL_GPL(pinctrl_utils_dt_free_map);
diff --git a/drivers/pinctrl/pinctrl-utils.h b/drivers/pinctrl/pinctrl-utils.h
new file mode 100644
index 0000000..d0ffe1c
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-utils.h
@@ -0,0 +1,43 @@
+/*
+ * Utils functions to implement the pincontrol driver.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
+ * 02111-1307, USA
+ */
+#ifndef __PINCTRL_UTILS_H__
+#define __PINCTRL_UTILS_H__
+
+int pinctrl_utils_reserve_map(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, unsigned reserve);
+int pinctrl_utils_add_map_mux(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, const char *group,
+ const char *function);
+int pinctrl_utils_add_map_configs(struct pinctrl_dev *pctldev,
+ struct pinctrl_map **map, unsigned *reserved_maps,
+ unsigned *num_maps, const char *group,
+ unsigned long *configs, unsigned num_configs,
+ enum pinctrl_map_type type);
+int pinctrl_utils_add_config(struct pinctrl_dev *pctldev,
+ unsigned long **configs, unsigned *num_configs,
+ unsigned long config);
+void pinctrl_utils_dt_free_map(struct pinctrl_dev *pctldev,
+ struct pinctrl_map *map, unsigned num_maps);
+
+#endif /* __PINCTRL_UTILS_H__ */
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index 70d986e..8b54b5d 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -276,7 +276,20 @@
if (!configs)
return -ENOMEM;
- configs[0] = pull;
+ switch (pull) {
+ case 0:
+ configs[0] = PIN_CONFIG_BIAS_DISABLE;
+ break;
+ case 1:
+ configs[0] = PIN_CONFIG_BIAS_PULL_DOWN;
+ break;
+ case 2:
+ configs[0] = PIN_CONFIG_BIAS_PULL_UP;
+ break;
+ default:
+ configs[0] = PIN_CONFIG_BIAS_DISABLE;
+ dev_err(data->dev, "invalid pull state %d - disabling\n", pull);
+ }
map->type = PIN_MAP_TYPE_CONFIGS_PIN;
map->data.configs.group_or_pin = data->groups[group];
diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c
index 0f9f859..f911952 100644
--- a/drivers/platform/olpc/olpc-ec.c
+++ b/drivers/platform/olpc/olpc-ec.c
@@ -330,7 +330,7 @@
return platform_driver_register(&olpc_ec_plat_driver);
}
-module_init(olpc_ec_init_module);
+arch_initcall(olpc_ec_init_module);
MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>");
MODULE_LICENSE("GPL");
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index c9076bd..59a8d32 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -572,6 +572,17 @@
DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5750"),
},
},
+ {
+ /*
+ * Note no video_set_backlight_video_vendor, we must use the
+ * acer interface, as there is no native backlight interface.
+ */
+ .ident = "Acer KAV80",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "KAV80"),
+ },
+ },
{}
};
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index fa9a217..b264d8f 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -163,18 +163,24 @@
const struct key_entry *key;
int reported_key;
u16 *buffer_entry = (u16 *)obj->buffer.pointer;
+ int buffer_size = obj->buffer.length/2;
- if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
+ if (buffer_size >= 2 && dell_new_hk_type && buffer_entry[1] != 0x10) {
pr_info("Received unknown WMI event (0x%x)\n",
buffer_entry[1]);
kfree(obj);
return;
}
- if (dell_new_hk_type || buffer_entry[1] == 0x0)
+ if (buffer_size >= 3 && (dell_new_hk_type || buffer_entry[1] == 0x0))
reported_key = (int)buffer_entry[2];
- else
+ else if (buffer_size >= 2)
reported_key = (int)buffer_entry[1] & 0xffff;
+ else {
+ pr_info("Received unknown WMI event\n");
+ kfree(obj);
+ return;
+ }
key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
reported_key);
diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
index a8e43cf..3458eb6f 100644
--- a/drivers/platform/x86/hp_accel.c
+++ b/drivers/platform/x86/hp_accel.c
@@ -77,6 +77,7 @@
static struct acpi_device_id lis3lv02d_device_ids[] = {
{"HPQ0004", 0}, /* HP Mobile Data Protection System PNP */
{"HPQ6000", 0}, /* HP Mobile Data Protection System PNP */
+ {"HPQ6007", 0}, /* HP Mobile Data Protection System PNP */
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, lis3lv02d_device_ids);
@@ -236,6 +237,7 @@
AXIS_DMI_MATCH("HPB64xx", "HP ProBook 64", xy_swap),
AXIS_DMI_MATCH("HPB64xx", "HP EliteBook 84", xy_swap),
AXIS_DMI_MATCH("HPB65xx", "HP ProBook 65", x_inverted),
+ AXIS_DMI_MATCH("HPZBook15", "HP ZBook 15", x_inverted),
{ NULL, }
/* Laptop models without axis info (yet):
* "NC6910" "HP Compaq 6910"
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 9847ab1..a8b7466 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -183,9 +183,7 @@
struct resource r;
int i, flags;
- if (acpi_dev_resource_memory(res, &r)
- || acpi_dev_resource_io(res, &r)
- || acpi_dev_resource_address_space(res, &r)
+ if (acpi_dev_resource_address_space(res, &r)
|| acpi_dev_resource_ext_address_space(res, &r)) {
pnp_add_resource(dev, &r);
return AE_OK;
@@ -217,6 +215,17 @@
}
switch (res->type) {
+ case ACPI_RESOURCE_TYPE_MEMORY24:
+ case ACPI_RESOURCE_TYPE_MEMORY32:
+ case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+ if (acpi_dev_resource_memory(res, &r))
+ pnp_add_resource(dev, &r);
+ break;
+ case ACPI_RESOURCE_TYPE_IO:
+ case ACPI_RESOURCE_TYPE_FIXED_IO:
+ if (acpi_dev_resource_io(res, &r))
+ pnp_add_resource(dev, &r);
+ break;
case ACPI_RESOURCE_TYPE_DMA:
dma = &res->data.dma;
if (dma->channel_count > 0 && dma->channels[0] != (u8) -1)
diff --git a/drivers/power/88pm860x_charger.c b/drivers/power/88pm860x_charger.c
index 36fb4b5..1ef35ab 100644
--- a/drivers/power/88pm860x_charger.c
+++ b/drivers/power/88pm860x_charger.c
@@ -711,6 +711,7 @@
return 0;
out_irq:
+ power_supply_unregister(&info->usb);
while (--i >= 0)
free_irq(info->irq[i], info);
out:
diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c
index fefc39f..98de1dd 100644
--- a/drivers/power/charger-manager.c
+++ b/drivers/power/charger-manager.c
@@ -450,7 +450,7 @@
strncpy(env_str, event, UEVENT_BUF_SIZE);
kobject_uevent(&cm->dev->kobj, KOBJ_CHANGE);
- dev_info(cm->dev, event);
+ dev_info(cm->dev, "%s", event);
}
/**
diff --git a/drivers/power/lp8788-charger.c b/drivers/power/lp8788-charger.c
index ed49b50..72da2a6 100644
--- a/drivers/power/lp8788-charger.c
+++ b/drivers/power/lp8788-charger.c
@@ -417,8 +417,10 @@
pchg->battery.num_properties = ARRAY_SIZE(lp8788_battery_prop);
pchg->battery.get_property = lp8788_battery_get_property;
- if (power_supply_register(&pdev->dev, &pchg->battery))
+ if (power_supply_register(&pdev->dev, &pchg->battery)) {
+ power_supply_unregister(&pchg->charger);
return -EPERM;
+ }
return 0;
}
diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c
index c7ff6d6..0fbac86 100644
--- a/drivers/power/max17040_battery.c
+++ b/drivers/power/max17040_battery.c
@@ -148,7 +148,7 @@
{
struct max17040_chip *chip = i2c_get_clientdata(client);
- if (chip->pdata->battery_online)
+ if (chip->pdata && chip->pdata->battery_online)
chip->online = chip->pdata->battery_online();
else
chip->online = 1;
@@ -158,7 +158,8 @@
{
struct max17040_chip *chip = i2c_get_clientdata(client);
- if (!chip->pdata->charger_online || !chip->pdata->charger_enable) {
+ if (!chip->pdata || !chip->pdata->charger_online
+ || !chip->pdata->charger_enable) {
chip->status = POWER_SUPPLY_STATUS_UNKNOWN;
return;
}
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index 349e9ae8..ee039dc 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -32,7 +32,8 @@
user presses a key. u-boot then boots into Linux.
config POWER_RESET_VEXPRESS
- bool
+ bool "ARM Versatile Express power-off and reset driver"
+ depends on ARM || ARM64
depends on POWER_RESET
help
Power off and reset support for the ARM Ltd. Versatile
diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h
index b4b0d83..7061ac0 100644
--- a/drivers/rapidio/devices/tsi721.h
+++ b/drivers/rapidio/devices/tsi721.h
@@ -678,6 +678,7 @@
struct list_head free_list;
dma_cookie_t completed_cookie;
struct tasklet_struct tasklet;
+ bool active;
};
#endif /* CONFIG_RAPIDIO_DMA_ENGINE */
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 502663f..47257b6 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -206,8 +206,8 @@
{
/* Disable BDMA channel interrupts */
iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE);
-
- tasklet_schedule(&bdma_chan->tasklet);
+ if (bdma_chan->active)
+ tasklet_schedule(&bdma_chan->tasklet);
}
#ifdef CONFIG_PCI_MSI
@@ -287,6 +287,12 @@
"desc %p not ACKed\n", tx_desc);
}
+ if (ret == NULL) {
+ dev_dbg(bdma_chan->dchan.device->dev,
+ "%s: unable to obtain tx descriptor\n", __func__);
+ goto err_out;
+ }
+
i = bdma_chan->wr_count_next % bdma_chan->bd_num;
if (i == bdma_chan->bd_num - 1) {
i = 0;
@@ -297,7 +303,7 @@
tx_desc->txd.phys = bdma_chan->bd_phys +
i * sizeof(struct tsi721_dma_desc);
tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i];
-
+err_out:
spin_unlock_bh(&bdma_chan->lock);
return ret;
@@ -562,7 +568,7 @@
}
#endif /* CONFIG_PCI_MSI */
- tasklet_enable(&bdma_chan->tasklet);
+ bdma_chan->active = true;
tsi721_bdma_interrupt_enable(bdma_chan, 1);
return bdma_chan->bd_num - 1;
@@ -576,9 +582,7 @@
static void tsi721_free_chan_resources(struct dma_chan *dchan)
{
struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan);
-#ifdef CONFIG_PCI_MSI
struct tsi721_device *priv = to_tsi721(dchan->device);
-#endif
LIST_HEAD(list);
dev_dbg(dchan->device->dev, "%s: Entry\n", __func__);
@@ -589,14 +593,25 @@
BUG_ON(!list_empty(&bdma_chan->active_list));
BUG_ON(!list_empty(&bdma_chan->queue));
- tasklet_disable(&bdma_chan->tasklet);
+ tsi721_bdma_interrupt_enable(bdma_chan, 0);
+ bdma_chan->active = false;
+
+#ifdef CONFIG_PCI_MSI
+ if (priv->flags & TSI721_USING_MSIX) {
+ synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE +
+ bdma_chan->id].vector);
+ synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT +
+ bdma_chan->id].vector);
+ } else
+#endif
+ synchronize_irq(priv->pdev->irq);
+
+ tasklet_kill(&bdma_chan->tasklet);
spin_lock_bh(&bdma_chan->lock);
list_splice_init(&bdma_chan->free_list, &list);
spin_unlock_bh(&bdma_chan->lock);
- tsi721_bdma_interrupt_enable(bdma_chan, 0);
-
#ifdef CONFIG_PCI_MSI
if (priv->flags & TSI721_USING_MSIX) {
free_irq(priv->msix[TSI721_VECT_DMA0_DONE +
@@ -790,6 +805,7 @@
bdma_chan->dchan.cookie = 1;
bdma_chan->dchan.chan_id = i;
bdma_chan->id = i;
+ bdma_chan->active = false;
spin_lock_init(&bdma_chan->lock);
@@ -799,7 +815,6 @@
tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet,
(unsigned long)bdma_chan);
- tasklet_disable(&bdma_chan->tasklet);
list_add_tail(&bdma_chan->dchan.device_node,
&mport->dma.channels);
}
diff --git a/drivers/rapidio/switches/idt_gen2.c b/drivers/rapidio/switches/idt_gen2.c
index 809b7a3..5d3b0f0 100644
--- a/drivers/rapidio/switches/idt_gen2.c
+++ b/drivers/rapidio/switches/idt_gen2.c
@@ -15,6 +15,8 @@
#include <linux/rio_drv.h>
#include <linux/rio_ids.h>
#include <linux/delay.h>
+
+#include <asm/page.h>
#include "../rio.h"
#define LOCAL_RTE_CONF_DESTID_SEL 0x010070
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 81d8681..b1b35f3 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -141,8 +141,6 @@
.map_voltage = regulator_map_voltage_linear,
.get_voltage_sel = regulator_get_voltage_sel_regmap,
.set_voltage_sel = regulator_set_voltage_sel_regmap,
- .get_bypass = regulator_get_bypass_regmap,
- .set_bypass = regulator_set_bypass_regmap,
};
static const struct regulator_desc arizona_ldo1 = {
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 815d6df..73cc3bb 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -919,6 +919,8 @@
return 0;
}
+static int _regulator_do_enable(struct regulator_dev *rdev);
+
/**
* set_machine_constraints - sets regulator constraints
* @rdev: regulator source
@@ -975,10 +977,9 @@
/* If the constraints say the regulator should be on at this point
* and we have control then make sure it is enabled.
*/
- if ((rdev->constraints->always_on || rdev->constraints->boot_on) &&
- ops->enable) {
- ret = ops->enable(rdev);
- if (ret < 0) {
+ if (rdev->constraints->always_on || rdev->constraints->boot_on) {
+ ret = _regulator_do_enable(rdev);
+ if (ret < 0 && ret != -EINVAL) {
rdev_err(rdev, "failed to enable\n");
goto out;
}
@@ -1409,7 +1410,7 @@
}
EXPORT_SYMBOL_GPL(regulator_get_exclusive);
-/* Locks held by regulator_put() */
+/* regulator_list_mutex lock held by regulator_put() */
static void _regulator_put(struct regulator *regulator)
{
struct regulator_dev *rdev;
@@ -1424,12 +1425,14 @@
/* remove any sysfs entries */
if (regulator->dev)
sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+ mutex_lock(&rdev->mutex);
kfree(regulator->supply_name);
list_del(®ulator->list);
kfree(regulator);
rdev->open_count--;
rdev->exclusive = 0;
+ mutex_unlock(&rdev->mutex);
module_put(rdev->owner);
}
@@ -1593,10 +1596,12 @@
trace_regulator_enable(rdev_get_name(rdev));
if (rdev->ena_pin) {
- ret = regulator_ena_gpio_ctrl(rdev, true);
- if (ret < 0)
- return ret;
- rdev->ena_gpio_state = 1;
+ if (!rdev->ena_gpio_state) {
+ ret = regulator_ena_gpio_ctrl(rdev, true);
+ if (ret < 0)
+ return ret;
+ rdev->ena_gpio_state = 1;
+ }
} else if (rdev->desc->ops->enable) {
ret = rdev->desc->ops->enable(rdev);
if (ret < 0)
@@ -1698,10 +1703,12 @@
trace_regulator_disable(rdev_get_name(rdev));
if (rdev->ena_pin) {
- ret = regulator_ena_gpio_ctrl(rdev, false);
- if (ret < 0)
- return ret;
- rdev->ena_gpio_state = 0;
+ if (rdev->ena_gpio_state) {
+ ret = regulator_ena_gpio_ctrl(rdev, false);
+ if (ret < 0)
+ return ret;
+ rdev->ena_gpio_state = 0;
+ }
} else if (rdev->desc->ops->disable) {
ret = rdev->desc->ops->disable(rdev);
@@ -1711,8 +1718,6 @@
trace_regulator_disable_complete(rdev_get_name(rdev));
- _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
- NULL);
return 0;
}
@@ -1736,6 +1741,8 @@
rdev_err(rdev, "failed to disable\n");
return ret;
}
+ _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE,
+ NULL);
}
rdev->use_count = 0;
@@ -1788,20 +1795,16 @@
{
int ret = 0;
- /* force disable */
- if (rdev->desc->ops->disable) {
- /* ah well, who wants to live forever... */
- ret = rdev->desc->ops->disable(rdev);
- if (ret < 0) {
- rdev_err(rdev, "failed to force disable\n");
- return ret;
- }
- /* notify other consumers that power has been forced off */
- _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
- REGULATOR_EVENT_DISABLE, NULL);
+ ret = _regulator_do_disable(rdev);
+ if (ret < 0) {
+ rdev_err(rdev, "failed to force disable\n");
+ return ret;
}
- return ret;
+ _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE |
+ REGULATOR_EVENT_DISABLE, NULL);
+
+ return 0;
}
/**
@@ -1890,8 +1893,9 @@
rdev->deferred_disables++;
mutex_unlock(&rdev->mutex);
- ret = schedule_delayed_work(&rdev->disable_work,
- msecs_to_jiffies(ms));
+ ret = queue_delayed_work(system_power_efficient_wq,
+ &rdev->disable_work,
+ msecs_to_jiffies(ms));
if (ret < 0)
return ret;
else
@@ -3615,12 +3619,6 @@
config->ena_gpio, ret);
goto wash;
}
-
- if (config->ena_gpio_flags & GPIOF_OUT_INIT_HIGH)
- rdev->ena_gpio_state = 1;
-
- if (config->ena_gpio_invert)
- rdev->ena_gpio_state = !rdev->ena_gpio_state;
}
/* set regulator constraints */
@@ -3787,23 +3785,20 @@
mutex_lock(®ulator_list_mutex);
list_for_each_entry(rdev, ®ulator_list, list) {
- struct regulator_ops *ops = rdev->desc->ops;
-
mutex_lock(&rdev->mutex);
- if ((rdev->use_count > 0 || rdev->constraints->always_on) &&
- ops->enable) {
- error = ops->enable(rdev);
- if (error)
- ret = error;
+ if (rdev->use_count > 0 || rdev->constraints->always_on) {
+ if (!_regulator_is_enabled(rdev)) {
+ error = _regulator_do_enable(rdev);
+ if (error)
+ ret = error;
+ }
} else {
if (!has_full_constraints)
goto unlock;
- if (!ops->disable)
- goto unlock;
if (!_regulator_is_enabled(rdev))
goto unlock;
- error = ops->disable(rdev);
+ error = _regulator_do_disable(rdev);
if (error)
ret = error;
}
@@ -3993,7 +3988,7 @@
ops = rdev->desc->ops;
c = rdev->constraints;
- if (!ops->disable || (c && c->always_on))
+ if (c && c->always_on)
continue;
mutex_lock(&rdev->mutex);
@@ -4014,7 +4009,7 @@
/* We log since this may kill the system if it
* goes wrong. */
rdev_info(rdev, "disabling\n");
- ret = ops->disable(rdev);
+ ret = _regulator_do_disable(rdev);
if (ret != 0) {
rdev_err(rdev, "couldn't disable: %d\n", ret);
}
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index f296f3f..e51cc5f 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -49,6 +49,7 @@
static const struct at91_rtc_config *at91_rtc_config;
static DECLARE_COMPLETION(at91_rtc_updated);
+static DECLARE_COMPLETION(at91_rtc_upd_rdy);
static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
static void __iomem *at91_rtc_regs;
static int irq;
@@ -162,6 +163,8 @@
1900 + tm->tm_year, tm->tm_mon, tm->tm_mday,
tm->tm_hour, tm->tm_min, tm->tm_sec);
+ wait_for_completion(&at91_rtc_upd_rdy);
+
/* Stop Time/Calendar from counting */
cr = at91_rtc_read(AT91_RTC_CR);
at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
@@ -184,7 +187,9 @@
/* Restart Time/Calendar */
cr = at91_rtc_read(AT91_RTC_CR);
+ at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_SECEV);
at91_rtc_write(AT91_RTC_CR, cr & ~(AT91_RTC_UPDCAL | AT91_RTC_UPDTIM));
+ at91_rtc_write_ier(AT91_RTC_SECEV);
return 0;
}
@@ -221,6 +226,8 @@
at91_alarm_year = tm.tm_year;
+ tm.tm_mon = alrm->time.tm_mon;
+ tm.tm_mday = alrm->time.tm_mday;
tm.tm_hour = alrm->time.tm_hour;
tm.tm_min = alrm->time.tm_min;
tm.tm_sec = alrm->time.tm_sec;
@@ -289,8 +296,10 @@
if (rtsr) { /* this interrupt is shared! Is it ours? */
if (rtsr & AT91_RTC_ALARM)
events |= (RTC_AF | RTC_IRQF);
- if (rtsr & AT91_RTC_SECEV)
- events |= (RTC_UF | RTC_IRQF);
+ if (rtsr & AT91_RTC_SECEV) {
+ complete(&at91_rtc_upd_rdy);
+ at91_rtc_write_idr(AT91_RTC_SECEV);
+ }
if (rtsr & AT91_RTC_ACKUPD)
complete(&at91_rtc_updated);
@@ -413,6 +422,11 @@
}
platform_set_drvdata(pdev, rtc);
+ /* enable SECEV interrupt in order to initialize at91_rtc_upd_rdy
+ * completion.
+ */
+ at91_rtc_write_ier(AT91_RTC_SECEV);
+
dev_info(&pdev->dev, "AT91 Real Time Clock driver.\n");
return 0;
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index f1cb706..6ae046b 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -34,11 +34,11 @@
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/platform_device.h>
-#include <linux/mod_devicetable.h>
#include <linux/log2.h>
#include <linux/pm.h>
#include <linux/of.h>
#include <linux/of_platform.h>
+#include <linux/dmi.h>
/* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
#include <asm-generic/rtc.h>
@@ -377,6 +377,51 @@
return 0;
}
+/*
+ * Do not disable RTC alarm on shutdown - workaround for b0rked BIOSes.
+ */
+static bool alarm_disable_quirk;
+
+static int __init set_alarm_disable_quirk(const struct dmi_system_id *id)
+{
+ alarm_disable_quirk = true;
+ pr_info("rtc-cmos: BIOS has alarm-disable quirk. ");
+ pr_info("RTC alarms disabled\n");
+ return 0;
+}
+
+static const struct dmi_system_id rtc_quirks[] __initconst = {
+ /* https://bugzilla.novell.com/show_bug.cgi?id=805740 */
+ {
+ .callback = set_alarm_disable_quirk,
+ .ident = "IBM Truman",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "4852570"),
+ },
+ },
+ /* https://bugzilla.novell.com/show_bug.cgi?id=812592 */
+ {
+ .callback = set_alarm_disable_quirk,
+ .ident = "Gigabyte GA-990XA-UD3",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR,
+ "Gigabyte Technology Co., Ltd."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "GA-990XA-UD3"),
+ },
+ },
+ /* http://permalink.gmane.org/gmane.linux.kernel/1604474 */
+ {
+ .callback = set_alarm_disable_quirk,
+ .ident = "Toshiba Satellite L300",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L300"),
+ },
+ },
+ {}
+};
+
static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
{
struct cmos_rtc *cmos = dev_get_drvdata(dev);
@@ -385,6 +430,9 @@
if (!is_valid_irq(cmos->irq))
return -EINVAL;
+ if (alarm_disable_quirk)
+ return 0;
+
spin_lock_irqsave(&rtc_lock, flags);
if (enabled)
@@ -1163,6 +1211,8 @@
platform_driver_registered = true;
}
+ dmi_check_system(rtc_quirks);
+
if (retval == 0)
return 0;
diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c
index 771812d..3bb9401 100644
--- a/drivers/rtc/rtc-max77686.c
+++ b/drivers/rtc/rtc-max77686.c
@@ -240,9 +240,9 @@
}
alrm->pending = 0;
- ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS1, &val);
+ ret = regmap_read(info->max77686->regmap, MAX77686_REG_STATUS2, &val);
if (ret < 0) {
- dev_err(info->dev, "%s:%d fail to read status1 reg(%d)\n",
+ dev_err(info->dev, "%s:%d fail to read status2 reg(%d)\n",
__func__, __LINE__, ret);
goto out;
}
diff --git a/drivers/rtc/rtc-max8907.c b/drivers/rtc/rtc-max8907.c
index 86afb79..5d0ce59 100644
--- a/drivers/rtc/rtc-max8907.c
+++ b/drivers/rtc/rtc-max8907.c
@@ -51,7 +51,7 @@
{
struct max8907_rtc *rtc = data;
- regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x7f, 0);
+ regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0);
rtc_update_irq(rtc->rtc_dev, 1, RTC_IRQF | RTC_AF);
@@ -64,7 +64,7 @@
bcd2bin(regs[RTC_YEAR1]) - 1900;
tm->tm_mon = bcd2bin(regs[RTC_MONTH] & 0x1f) - 1;
tm->tm_mday = bcd2bin(regs[RTC_DATE] & 0x3f);
- tm->tm_wday = (regs[RTC_WEEKDAY] & 0x07) - 1;
+ tm->tm_wday = (regs[RTC_WEEKDAY] & 0x07);
if (regs[RTC_HOUR] & HOUR_12) {
tm->tm_hour = bcd2bin(regs[RTC_HOUR] & 0x01f);
if (tm->tm_hour == 12)
@@ -88,7 +88,7 @@
regs[RTC_YEAR1] = bin2bcd(low);
regs[RTC_MONTH] = bin2bcd(tm->tm_mon + 1);
regs[RTC_DATE] = bin2bcd(tm->tm_mday);
- regs[RTC_WEEKDAY] = tm->tm_wday + 1;
+ regs[RTC_WEEKDAY] = tm->tm_wday;
regs[RTC_HOUR] = bin2bcd(tm->tm_hour);
regs[RTC_MIN] = bin2bcd(tm->tm_min);
regs[RTC_SEC] = bin2bcd(tm->tm_sec);
@@ -153,7 +153,7 @@
tm_to_regs(&alrm->time, regs);
/* Disable alarm while we update the target time */
- ret = regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x7f, 0);
+ ret = regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0);
if (ret < 0)
return ret;
@@ -163,8 +163,7 @@
return ret;
if (alrm->enabled)
- ret = regmap_update_bits(rtc->regmap, MAX8907_REG_ALARM0_CNTL,
- 0x7f, 0x7f);
+ ret = regmap_write(rtc->regmap, MAX8907_REG_ALARM0_CNTL, 0x77);
return ret;
}
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index 5032c24..9100a34 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -310,7 +310,7 @@
dev_dbg(&client->dev, "alarm IRQ armed\n");
} else {
/* disable AIE irq */
- ret = rv3029c2_rtc_i2c_alarm_set_irq(client, 1);
+ ret = rv3029c2_rtc_i2c_alarm_set_irq(client, 0);
if (ret)
return ret;
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d72a9216e..e91ec8c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2879,12 +2879,12 @@
elevator_exit(block->request_queue->elevator);
block->request_queue->elevator = NULL;
+ mutex_lock(&block->request_queue->sysfs_lock);
rc = elevator_init(block->request_queue, "deadline");
- if (rc) {
+ if (rc)
blk_cleanup_queue(block->request_queue);
- return rc;
- }
- return 0;
+ mutex_unlock(&block->request_queue->sysfs_lock);
+ return rc;
}
/*
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index eb5d227..19915c5 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -288,12 +288,16 @@
unsigned long flags;
spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
- if (raw->flags & RAW3215_TIMER_RUNS) {
- del_timer(&raw->timer);
- raw->flags &= ~RAW3215_TIMER_RUNS;
- if (!(raw->port.flags & ASYNC_SUSPENDED)) {
- raw3215_mk_write_req(raw);
- raw3215_start_io(raw);
+ raw->flags &= ~RAW3215_TIMER_RUNS;
+ if (!(raw->port.flags & ASYNC_SUSPENDED)) {
+ raw3215_mk_write_req(raw);
+ raw3215_start_io(raw);
+ if ((raw->queued_read || raw->queued_write) &&
+ !(raw->flags & RAW3215_WORKING) &&
+ !(raw->flags & RAW3215_TIMER_RUNS)) {
+ raw->timer.expires = RAW3215_TIMEOUT + jiffies;
+ add_timer(&raw->timer);
+ raw->flags |= RAW3215_TIMER_RUNS;
}
}
spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
@@ -317,17 +321,15 @@
(raw->flags & RAW3215_FLUSHING)) {
/* execute write requests bigger than minimum size */
raw3215_start_io(raw);
- if (raw->flags & RAW3215_TIMER_RUNS) {
- del_timer(&raw->timer);
- raw->flags &= ~RAW3215_TIMER_RUNS;
- }
- } else if (!(raw->flags & RAW3215_TIMER_RUNS)) {
- /* delay small writes */
- raw->timer.expires = RAW3215_TIMEOUT + jiffies;
- add_timer(&raw->timer);
- raw->flags |= RAW3215_TIMER_RUNS;
}
}
+ if ((raw->queued_read || raw->queued_write) &&
+ !(raw->flags & RAW3215_WORKING) &&
+ !(raw->flags & RAW3215_TIMER_RUNS)) {
+ raw->timer.expires = RAW3215_TIMEOUT + jiffies;
+ add_timer(&raw->timer);
+ raw->flags |= RAW3215_TIMER_RUNS;
+ }
}
/*
@@ -922,7 +924,7 @@
raw3215_freelist = req;
}
- cdev = ccw_device_probe_console();
+ cdev = ccw_device_probe_console(&raw3215_ccw_driver);
if (IS_ERR(cdev))
return -ENODEV;
@@ -1027,12 +1029,26 @@
const unsigned char *buf, int count)
{
struct raw3215_info *raw;
+ int i, written;
if (!tty)
return 0;
raw = (struct raw3215_info *) tty->driver_data;
- raw3215_write(raw, buf, count);
- return count;
+ written = count;
+ while (count > 0) {
+ for (i = 0; i < count; i++)
+ if (buf[i] == '\t' || buf[i] == '\n')
+ break;
+ raw3215_write(raw, buf, i);
+ count -= i;
+ buf += i;
+ if (count > 0) {
+ raw3215_putchar(raw, *buf);
+ count--;
+ buf++;
+ }
+ }
+ return written;
}
/*
@@ -1180,7 +1196,7 @@
driver->subtype = SYSTEM_TYPE_TTY;
driver->init_termios = tty_std_termios;
driver->init_termios.c_iflag = IGNBRK | IGNPAR;
- driver->init_termios.c_oflag = ONLCR | XTABS;
+ driver->init_termios.c_oflag = ONLCR;
driver->init_termios.c_lflag = ISIG;
driver->flags = TTY_DRIVER_REAL_RAW;
tty_set_operations(driver, &tty3215_ops);
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index 699fd3e..bb6b0df5 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -576,7 +576,6 @@
static int __init
con3270_init(void)
{
- struct ccw_device *cdev;
struct raw3270 *rp;
void *cbuf;
int i;
@@ -591,10 +590,7 @@
cpcmd("TERM AUTOCR OFF", NULL, 0, NULL);
}
- cdev = ccw_device_probe_console();
- if (IS_ERR(cdev))
- return -ENODEV;
- rp = raw3270_setup_console(cdev);
+ rp = raw3270_setup_console();
if (IS_ERR(rp))
return PTR_ERR(rp);
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 24a08e8..651d1f5 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -776,16 +776,24 @@
}
#ifdef CONFIG_TN3270_CONSOLE
+/* Tentative definition - see below for actual definition. */
+static struct ccw_driver raw3270_ccw_driver;
+
/*
* Setup 3270 device configured as console.
*/
-struct raw3270 __init *raw3270_setup_console(struct ccw_device *cdev)
+struct raw3270 __init *raw3270_setup_console(void)
{
+ struct ccw_device *cdev;
unsigned long flags;
struct raw3270 *rp;
char *ascebc;
int rc;
+ cdev = ccw_device_probe_console(&raw3270_ccw_driver);
+ if (IS_ERR(cdev))
+ return ERR_CAST(cdev);
+
rp = kzalloc(sizeof(struct raw3270), GFP_KERNEL | GFP_DMA);
ascebc = kzalloc(256, GFP_KERNEL);
rc = raw3270_setup_device(cdev, rp, ascebc);
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 7b73ff8..359276a 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -190,7 +190,7 @@
wake_up(&raw3270_wait_queue);
}
-struct raw3270 *raw3270_setup_console(struct ccw_device *cdev);
+struct raw3270 *raw3270_setup_console(void);
void raw3270_wait_cons_dev(struct raw3270 *);
/* Notifier for device addition/removal */
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index cee69da..4dd71ca 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -942,7 +942,7 @@
return rc;
}
- tp->screen = tty3270_alloc_screen(tp->view.cols, tp->view.rows);
+ tp->screen = tty3270_alloc_screen(tp->view.rows, tp->view.cols);
if (IS_ERR(tp->screen)) {
rc = PTR_ERR(tp->screen);
raw3270_put_view(&tp->view);
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 8ea7d9b..815e290 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -500,18 +500,27 @@
static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
{
- do {
+ static int ntsm_unsupported;
+
+ while (true) {
memset(sei, 0, sizeof(*sei));
sei->request.length = 0x0010;
sei->request.code = 0x000e;
- sei->ntsm = ntsm;
+ if (!ntsm_unsupported)
+ sei->ntsm = ntsm;
if (chsc(sei))
break;
if (sei->response.code != 0x0001) {
- CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
- sei->response.code);
+ CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n",
+ sei->response.code, sei->ntsm);
+
+ if (sei->response.code == 3 && sei->ntsm) {
+ /* Fallback for old firmware. */
+ ntsm_unsupported = 1;
+ continue;
+ }
break;
}
@@ -527,7 +536,10 @@
CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt);
break;
}
- } while (sei->u.nt0_area.flags & 0x80);
+
+ if (!(sei->u.nt0_area.flags & 0x80))
+ break;
+ }
}
/*
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 1ab5f6c..8d04a9a 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1610,7 +1610,7 @@
return rc;
}
-struct ccw_device *ccw_device_probe_console(void)
+struct ccw_device *ccw_device_probe_console(struct ccw_driver *drv)
{
struct io_subchannel_private *io_priv;
struct ccw_device *cdev;
@@ -1632,6 +1632,7 @@
kfree(io_priv);
return cdev;
}
+ cdev->drv = drv;
set_io_private(sch, io_priv);
ret = ccw_device_console_enable(cdev, sch);
if (ret) {
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 9de41aa..6f512fa 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -44,6 +44,7 @@
#include <linux/hrtimer.h>
#include <linux/ktime.h>
#include <asm/facility.h>
+#include <linux/crypto.h>
#include "ap_bus.h"
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 6cd0fc1..e06cb8f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4448,7 +4448,7 @@
struct qeth_cmd_buffer *iob;
struct qeth_ipa_cmd *cmd;
struct qeth_snmp_ureq *ureq;
- int req_len;
+ unsigned int req_len;
struct qeth_arp_query_info qinfo = {0, };
int rc = 0;
@@ -4464,6 +4464,10 @@
/* skip 4 bytes (data_len struct member) to get req_len */
if (copy_from_user(&req_len, udata + sizeof(int), sizeof(int)))
return -EFAULT;
+ if (req_len > (QETH_BUFSIZE - IPA_PDU_HEADER_SIZE -
+ sizeof(struct qeth_ipacmd_hdr) -
+ sizeof(struct qeth_ipacmd_setadpparms_hdr)))
+ return -EINVAL;
ureq = memdup_user(udata, req_len + sizeof(struct qeth_snmp_ureq_hdr));
if (IS_ERR(ureq)) {
QETH_CARD_TEXT(card, 2, "snmpnome");
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index f6adde4..3743ac9 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -3,7 +3,7 @@
*
* Module interface and handling of zfcp data structures.
*
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2013
*/
/*
@@ -23,6 +23,7 @@
* Christof Schmitt
* Martin Petermann
* Sven Schuetz
+ * Steffen Maier
*/
#define KMSG_COMPONENT "zfcp"
@@ -415,6 +416,8 @@
adapter->dma_parms.max_segment_size = ZFCP_QDIO_SBALE_LEN;
adapter->ccw_device->dev.dma_parms = &adapter->dma_parms;
+ adapter->stat_read_buf_num = FSF_STATUS_READS_RECOM;
+
if (!zfcp_scsi_adapter_register(adapter))
return adapter;
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index 4133ab6..8e8f353 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -102,10 +102,13 @@
if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_INUSE)
zfcp_erp_action_dismiss(&port->erp_action);
- else
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ else {
+ spin_lock(port->adapter->scsi_host->host_lock);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
zfcp_erp_action_dismiss_lun(sdev);
+ spin_unlock(port->adapter->scsi_host->host_lock);
+ }
}
static void zfcp_erp_action_dismiss_adapter(struct zfcp_adapter *adapter)
@@ -592,9 +595,11 @@
{
struct scsi_device *sdev;
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock(port->adapter->scsi_host->host_lock);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
_zfcp_erp_lun_reopen(sdev, clear, id, 0);
+ spin_unlock(port->adapter->scsi_host->host_lock);
}
static void zfcp_erp_strategy_followup_failed(struct zfcp_erp_action *act)
@@ -1435,8 +1440,10 @@
atomic_set_mask(common_mask, &port->status);
read_unlock_irqrestore(&adapter->port_list_lock, flags);
- shost_for_each_device(sdev, adapter->scsi_host)
+ spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, adapter->scsi_host)
atomic_set_mask(common_mask, &sdev_to_zfcp(sdev)->status);
+ spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
}
/**
@@ -1470,11 +1477,13 @@
}
read_unlock_irqrestore(&adapter->port_list_lock, flags);
- shost_for_each_device(sdev, adapter->scsi_host) {
+ spin_lock_irqsave(adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, adapter->scsi_host) {
atomic_clear_mask(common_mask, &sdev_to_zfcp(sdev)->status);
if (clear_counter)
atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
}
+ spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags);
}
/**
@@ -1488,16 +1497,19 @@
{
struct scsi_device *sdev;
u32 common_mask = mask & ZFCP_COMMON_FLAGS;
+ unsigned long flags;
atomic_set_mask(mask, &port->status);
if (!common_mask)
return;
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port)
atomic_set_mask(common_mask,
&sdev_to_zfcp(sdev)->status);
+ spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
}
/**
@@ -1512,6 +1524,7 @@
struct scsi_device *sdev;
u32 common_mask = mask & ZFCP_COMMON_FLAGS;
u32 clear_counter = mask & ZFCP_STATUS_COMMON_ERP_FAILED;
+ unsigned long flags;
atomic_clear_mask(mask, &port->status);
@@ -1521,13 +1534,15 @@
if (clear_counter)
atomic_set(&port->erp_counter, 0);
- shost_for_each_device(sdev, port->adapter->scsi_host)
+ spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags);
+ __shost_for_each_device(sdev, port->adapter->scsi_host)
if (sdev_to_zfcp(sdev)->port == port) {
atomic_clear_mask(common_mask,
&sdev_to_zfcp(sdev)->status);
if (clear_counter)
atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0);
}
+ spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags);
}
/**
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index c7e148f..9152999 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -3,7 +3,7 @@
*
* Implementation of FSF commands.
*
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2013
*/
#define KMSG_COMPONENT "zfcp"
@@ -483,12 +483,8 @@
fc_host_port_name(shost) = nsp->fl_wwpn;
fc_host_node_name(shost) = nsp->fl_wwnn;
- fc_host_port_id(shost) = ntoh24(bottom->s_id);
- fc_host_speed(shost) =
- zfcp_fsf_convert_portspeed(bottom->fc_link_speed);
fc_host_supported_classes(shost) = FC_COS_CLASS2 | FC_COS_CLASS3;
- adapter->hydra_version = bottom->adapter_type;
adapter->timer_ticks = bottom->timer_interval & ZFCP_FSF_TIMER_INT_MASK;
adapter->stat_read_buf_num = max(bottom->status_read_buf_num,
(u16)FSF_STATUS_READS_RECOM);
@@ -496,6 +492,19 @@
if (fc_host_permanent_port_name(shost) == -1)
fc_host_permanent_port_name(shost) = fc_host_port_name(shost);
+ zfcp_scsi_set_prot(adapter);
+
+ /* no error return above here, otherwise must fix call chains */
+ /* do not evaluate invalid fields */
+ if (req->qtcb->header.fsf_status == FSF_EXCHANGE_CONFIG_DATA_INCOMPLETE)
+ return 0;
+
+ fc_host_port_id(shost) = ntoh24(bottom->s_id);
+ fc_host_speed(shost) =
+ zfcp_fsf_convert_portspeed(bottom->fc_link_speed);
+
+ adapter->hydra_version = bottom->adapter_type;
+
switch (bottom->fc_topology) {
case FSF_TOPO_P2P:
adapter->peer_d_id = ntoh24(bottom->peer_d_id);
@@ -517,8 +526,6 @@
return -EIO;
}
- zfcp_scsi_set_prot(adapter);
-
return 0;
}
@@ -563,8 +570,14 @@
fc_host_port_type(shost) = FC_PORTTYPE_UNKNOWN;
adapter->hydra_version = 0;
+ /* avoids adapter shutdown to be able to recognize
+ * events such as LINK UP */
+ atomic_set_mask(ZFCP_STATUS_ADAPTER_XCONFIG_OK,
+ &adapter->status);
zfcp_fsf_link_down_info_eval(req,
&qtcb->header.fsf_status_qual.link_down_info);
+ if (zfcp_fsf_exchange_config_evaluate(req))
+ return;
break;
default:
zfcp_erp_adapter_shutdown(adapter, 0, "fsecdh3");
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 665e3cf..de0598e 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -224,11 +224,9 @@
static int zfcp_qdio_sbal_check(struct zfcp_qdio *qdio)
{
- spin_lock_irq(&qdio->req_q_lock);
if (atomic_read(&qdio->req_q_free) ||
!(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP))
return 1;
- spin_unlock_irq(&qdio->req_q_lock);
return 0;
}
@@ -246,9 +244,8 @@
{
long ret;
- spin_unlock_irq(&qdio->req_q_lock);
- ret = wait_event_interruptible_timeout(qdio->req_q_wq,
- zfcp_qdio_sbal_check(qdio), 5 * HZ);
+ ret = wait_event_interruptible_lock_irq_timeout(qdio->req_q_wq,
+ zfcp_qdio_sbal_check(qdio), qdio->req_q_lock, 5 * HZ);
if (!(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP))
return -EIO;
@@ -262,7 +259,6 @@
zfcp_erp_adapter_reopen(qdio->adapter, 0, "qdsbg_1");
}
- spin_lock_irq(&qdio->req_q_lock);
return -EIO;
}
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 7b31e3f..7b35364 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -3,7 +3,7 @@
*
* Interface to Linux SCSI midlayer.
*
- * Copyright IBM Corp. 2002, 2010
+ * Copyright IBM Corp. 2002, 2013
*/
#define KMSG_COMPONENT "zfcp"
@@ -311,8 +311,12 @@
.proc_name = "zfcp",
.can_queue = 4096,
.this_id = -1,
- .sg_tablesize = 1, /* adjusted later */
- .max_sectors = 8, /* adjusted later */
+ .sg_tablesize = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1)
+ * ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2),
+ /* GCD, adjusted later */
+ .max_sectors = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1)
+ * ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2) * 8,
+ /* GCD, adjusted later */
.dma_boundary = ZFCP_QDIO_SBALE_LEN - 1,
.cmd_per_lun = 1,
.use_clustering = 1,
diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c
index 160e751..0787b97 100644
--- a/drivers/sbus/char/bbc_envctrl.c
+++ b/drivers/sbus/char/bbc_envctrl.c
@@ -452,6 +452,9 @@
if (!tp)
return;
+ INIT_LIST_HEAD(&tp->bp_list);
+ INIT_LIST_HEAD(&tp->glob_list);
+
tp->client = bbc_i2c_attach(bp, op);
if (!tp->client) {
kfree(tp);
@@ -497,6 +500,9 @@
if (!fp)
return;
+ INIT_LIST_HEAD(&fp->bp_list);
+ INIT_LIST_HEAD(&fp->glob_list);
+
fp->client = bbc_i2c_attach(bp, op);
if (!fp->client) {
kfree(fp);
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index c1441ed..e0e6cd6 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -301,13 +301,18 @@
if (!bp)
return NULL;
+ INIT_LIST_HEAD(&bp->temps);
+ INIT_LIST_HEAD(&bp->fans);
+
bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs");
if (!bp->i2c_control_regs)
goto fail;
- bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
- if (!bp->i2c_bussel_reg)
- goto fail;
+ if (op->num_resources == 2) {
+ bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel");
+ if (!bp->i2c_bussel_reg)
+ goto fail;
+ }
bp->waiting = 0;
init_waitqueue_head(&bp->wq);
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 5e1e12c..0a73253 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -2025,7 +2025,8 @@
.cmd_per_lun = TW_MAX_CMDS_PER_LUN,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = twa_host_attrs,
- .emulated = 1
+ .emulated = 1,
+ .no_write_same = 1,
};
/* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index c845bdb..4de3460 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1600,7 +1600,8 @@
.cmd_per_lun = TW_MAX_CMDS_PER_LUN,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = twl_host_attrs,
- .emulated = 1
+ .emulated = 1,
+ .no_write_same = 1,
};
/* This function will probe and initialize a card */
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index 56662ae..430ee37 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -2277,7 +2277,8 @@
.cmd_per_lun = TW_MAX_CMDS_PER_LUN,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = tw_host_attrs,
- .emulated = 1
+ .emulated = 1,
+ .no_write_same = 1,
};
/* This function will probe and initialize a card */
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 86af29f..1348fa4 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1353,7 +1353,6 @@
tristate "Emulex LightPulse Fibre Channel Support"
depends on PCI && SCSI
select SCSI_FC_ATTRS
- select GENERIC_CSUM
select CRC_T10DIF
help
This lpfc driver supports the Emulex LightPulse
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index 1ef041b..ee6cadd 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -510,7 +510,8 @@
goto cleanup;
}
- if (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr))) {
+ if ((fibsize < (sizeof(struct user_aac_srb) - sizeof(struct user_sgentry))) ||
+ (fibsize > (dev->max_fib_size - sizeof(struct aac_fibhdr)))) {
rcode = -EINVAL;
goto cleanup;
}
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 408a42e..4921ed19 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -771,6 +771,8 @@
static int aac_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
{
struct aac_dev *dev = (struct aac_dev *)sdev->host->hostdata;
+ if (!capable(CAP_SYS_RAWIO))
+ return -EPERM;
return aac_compat_do_ioctl(dev, cmd, (unsigned long)arg);
}
@@ -1079,6 +1081,7 @@
#endif
.use_clustering = ENABLE_CLUSTERING,
.emulated = 1,
+ .no_write_same = 1,
};
static void __aac_shutdown(struct aac_dev * aac)
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 0f56d8d..7e17107 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -93,6 +93,9 @@
int send_it = 0;
extern int aac_sync_mode;
+ src_writel(dev, MUnit.ODR_C, bellbits);
+ src_readl(dev, MUnit.ODR_C);
+
if (!aac_sync_mode) {
src_writel(dev, MUnit.ODR_C, bellbits);
src_readl(dev, MUnit.ODR_C);
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 33c52bc..1822cb9 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -137,6 +137,7 @@
.cmd_per_lun = ARCMSR_MAX_CMD_PERLUN,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = arcmsr_host_attrs,
+ .no_write_same = 1,
};
static struct pci_device_id arcmsr_device_id_table[] = {
{PCI_DEVICE(PCI_VENDOR_ID_ARECA, PCI_DEVICE_ID_ARECA_1110)},
@@ -2500,16 +2501,15 @@
static int arcmsr_iop_confirm(struct AdapterControlBlock *acb)
{
uint32_t cdb_phyaddr, cdb_phyaddr_hi32;
- dma_addr_t dma_coherent_handle;
+
/*
********************************************************************
** here we need to tell iop 331 our freeccb.HighPart
** if freeccb.HighPart is not zero
********************************************************************
*/
- dma_coherent_handle = acb->dma_coherent_handle;
- cdb_phyaddr = (uint32_t)(dma_coherent_handle);
- cdb_phyaddr_hi32 = (uint32_t)((cdb_phyaddr >> 16) >> 16);
+ cdb_phyaddr = lower_32_bits(acb->dma_coherent_handle);
+ cdb_phyaddr_hi32 = upper_32_bits(acb->dma_coherent_handle);
acb->cdb_phyaddr_hi32 = cdb_phyaddr_hi32;
/*
***********************************************************************
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index d24a286..bfe812f 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -564,7 +564,6 @@
"beiscsi_hba_alloc - iscsi_host_alloc failed\n");
return NULL;
}
- shost->dma_boundary = pcidev->dma_mask;
shost->max_id = BE2_MAX_SESSIONS;
shost->max_channel = 0;
shost->max_cmd_len = BEISCSI_MAX_CMD_LEN;
@@ -5081,9 +5080,9 @@
hba_free:
if (phba->msix_enabled)
pci_disable_msix(phba->pcidev);
- iscsi_host_remove(phba->shost);
pci_dev_put(phba->pcidev);
iscsi_host_free(phba->shost);
+ pci_set_drvdata(pcidev, NULL);
disable_pci:
pci_disable_device(pcidev);
return ret;
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 245a959..ef0a78b 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -812,17 +812,20 @@
if (ip_action == IP_ACTION_ADD) {
memcpy(req->ip_params.ip_record.ip_addr.addr, ip_param->value,
- ip_param->len);
+ sizeof(req->ip_params.ip_record.ip_addr.addr));
if (subnet_param)
memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
- subnet_param->value, subnet_param->len);
+ subnet_param->value,
+ sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
} else {
memcpy(req->ip_params.ip_record.ip_addr.addr,
- if_info->ip_addr.addr, ip_param->len);
+ if_info->ip_addr.addr,
+ sizeof(req->ip_params.ip_record.ip_addr.addr));
memcpy(req->ip_params.ip_record.ip_addr.subnet_mask,
- if_info->ip_addr.subnet_mask, ip_param->len);
+ if_info->ip_addr.subnet_mask,
+ sizeof(req->ip_params.ip_record.ip_addr.subnet_mask));
}
rc = mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
@@ -850,7 +853,7 @@
req->action = gtway_action;
req->ip_addr.ip_type = BE2_IPV4;
- memcpy(req->ip_addr.addr, gt_addr, param_len);
+ memcpy(req->ip_addr.addr, gt_addr, sizeof(req->ip_addr.addr));
return mgmt_exec_nonemb_cmd(phba, &nonemb_cmd, NULL, 0);
}
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index a449706..6c6c7c3 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -299,6 +299,7 @@
struct bfa_fcs_lport_s *bfa_fcs_lookup_port(struct bfa_fcs_s *fcs,
u16 vf_id, wwn_t lpwwn);
+void bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port, char *symname);
void bfa_fcs_lport_get_info(struct bfa_fcs_lport_s *port,
struct bfa_lport_info_s *port_info);
void bfa_fcs_lport_get_attr(struct bfa_fcs_lport_s *port,
diff --git a/drivers/scsi/bfa/bfa_fcs_lport.c b/drivers/scsi/bfa/bfa_fcs_lport.c
index 1224d04..2826961 100644
--- a/drivers/scsi/bfa/bfa_fcs_lport.c
+++ b/drivers/scsi/bfa/bfa_fcs_lport.c
@@ -1097,6 +1097,17 @@
bfa_sm_send_event(lport, BFA_FCS_PORT_SM_CREATE);
}
+void
+bfa_fcs_lport_set_symname(struct bfa_fcs_lport_s *port,
+ char *symname)
+{
+ strcpy(port->port_cfg.sym_name.symname, symname);
+
+ if (bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
+ bfa_fcs_lport_ns_util_send_rspn_id(
+ BFA_FCS_GET_NS_FROM_PORT(port), NULL);
+}
+
/*
* fcs_lport_api
*/
@@ -4950,9 +4961,6 @@
u8 *psymbl = &symbl[0];
int len;
- if (!bfa_sm_cmp_state(port, bfa_fcs_lport_sm_online))
- return;
-
/* Avoid sending RSPN in the following states. */
if (bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_offline) ||
bfa_sm_cmp_state(ns, bfa_fcs_lport_ns_sm_plogi_sending) ||
diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h
index 23a90e7..a119421 100644
--- a/drivers/scsi/bfa/bfa_ioc.h
+++ b/drivers/scsi/bfa/bfa_ioc.h
@@ -72,7 +72,7 @@
} while (0)
#define bfa_swap_words(_x) ( \
- ((_x) << 32) | ((_x) >> 32))
+ ((u64)(_x) << 32) | ((u64)(_x) >> 32))
#ifdef __BIG_ENDIAN
#define bfa_sge_to_be(_x)
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index a5f7690..ae2564d 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -1824,7 +1824,7 @@
static u32 *
bfad_load_fwimg(struct pci_dev *pdev)
{
- if (pdev->device == BFA_PCI_DEVICE_ID_CT2) {
+ if (bfa_asic_id_ct2(pdev->device)) {
if (bfi_image_ct2_size == 0)
bfad_read_firmware(pdev, &bfi_image_ct2,
&bfi_image_ct2_size, BFAD_FW_FILE_CT2);
@@ -1834,12 +1834,14 @@
bfad_read_firmware(pdev, &bfi_image_ct,
&bfi_image_ct_size, BFAD_FW_FILE_CT);
return bfi_image_ct;
- } else {
+ } else if (bfa_asic_id_cb(pdev->device)) {
if (bfi_image_cb_size == 0)
bfad_read_firmware(pdev, &bfi_image_cb,
&bfi_image_cb_size, BFAD_FW_FILE_CB);
return bfi_image_cb;
}
+
+ return NULL;
}
static void
diff --git a/drivers/scsi/bfa/bfad_attr.c b/drivers/scsi/bfa/bfad_attr.c
index 72f5dc3..58eeca2 100644
--- a/drivers/scsi/bfa/bfad_attr.c
+++ b/drivers/scsi/bfa/bfad_attr.c
@@ -610,11 +610,8 @@
return;
spin_lock_irqsave(&bfad->bfad_lock, flags);
- if (strlen(sym_name) > 0) {
- strcpy(fcs_vport->lport.port_cfg.sym_name.symname, sym_name);
- bfa_fcs_lport_ns_util_send_rspn_id(
- BFA_FCS_GET_NS_FROM_PORT((&fcs_vport->lport)), NULL);
- }
+ if (strlen(sym_name) > 0)
+ bfa_fcs_lport_set_symname(&fcs_vport->lport, sym_name);
spin_unlock_irqrestore(&bfad->bfad_lock, flags);
}
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 69ac554..aad5535 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -411,6 +411,7 @@
struct fc_frame_header *fh;
struct fcoe_rcv_info *fr;
struct fcoe_percpu_s *bg;
+ struct sk_buff *tmp_skb;
unsigned short oxid;
interface = container_of(ptype, struct bnx2fc_interface,
@@ -423,6 +424,12 @@
goto err;
}
+ tmp_skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!tmp_skb)
+ goto err;
+
+ skb = tmp_skb;
+
if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) {
printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n");
goto err;
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 34552bf..55548dc 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -530,7 +530,7 @@
static int esp_alloc_lun_tag(struct esp_cmd_entry *ent,
struct esp_lun_data *lp)
{
- if (!ent->tag[0]) {
+ if (!ent->orig_tag[0]) {
/* Non-tagged, slot already taken? */
if (lp->non_tagged_cmd)
return -EBUSY;
@@ -564,9 +564,9 @@
return -EBUSY;
}
- BUG_ON(lp->tagged_cmds[ent->tag[1]]);
+ BUG_ON(lp->tagged_cmds[ent->orig_tag[1]]);
- lp->tagged_cmds[ent->tag[1]] = ent;
+ lp->tagged_cmds[ent->orig_tag[1]] = ent;
lp->num_tagged++;
return 0;
@@ -575,9 +575,9 @@
static void esp_free_lun_tag(struct esp_cmd_entry *ent,
struct esp_lun_data *lp)
{
- if (ent->tag[0]) {
- BUG_ON(lp->tagged_cmds[ent->tag[1]] != ent);
- lp->tagged_cmds[ent->tag[1]] = NULL;
+ if (ent->orig_tag[0]) {
+ BUG_ON(lp->tagged_cmds[ent->orig_tag[1]] != ent);
+ lp->tagged_cmds[ent->orig_tag[1]] = NULL;
lp->num_tagged--;
} else {
BUG_ON(lp->non_tagged_cmd != ent);
@@ -667,6 +667,8 @@
ent->tag[0] = 0;
ent->tag[1] = 0;
}
+ ent->orig_tag[0] = ent->tag[0];
+ ent->orig_tag[1] = ent->tag[1];
if (esp_alloc_lun_tag(ent, lp) < 0)
continue;
diff --git a/drivers/scsi/esp_scsi.h b/drivers/scsi/esp_scsi.h
index 28e22ac..cd68805 100644
--- a/drivers/scsi/esp_scsi.h
+++ b/drivers/scsi/esp_scsi.h
@@ -271,6 +271,7 @@
#define ESP_CMD_FLAG_AUTOSENSE 0x04 /* Doing automatic REQUEST_SENSE */
u8 tag[2];
+ u8 orig_tag[2];
u8 status;
u8 message;
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 6d55b4e..aec3d4d 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -4686,6 +4686,7 @@
.cmd_per_lun = GDTH_MAXC_P_L,
.unchecked_isa_dma = 1,
.use_clustering = ENABLE_CLUSTERING,
+ .no_write_same = 1,
};
#ifdef CONFIG_ISA
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index df0c3c7..3cafe0d 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -388,6 +388,7 @@
shost->unchecked_isa_dma = sht->unchecked_isa_dma;
shost->use_clustering = sht->use_clustering;
shost->ordered_tag = sht->ordered_tag;
+ shost->no_write_same = sht->no_write_same;
if (sht->supported_mode == MODE_UNKNOWN)
/* means we didn't set it ... default to INITIATOR */
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 7f4f790..62ed744 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -538,6 +538,7 @@
.sdev_attrs = hpsa_sdev_attrs,
.shost_attrs = hpsa_shost_attrs,
.max_sectors = 8192,
+ .no_write_same = 1,
};
@@ -1205,8 +1206,8 @@
scsi_set_resid(cmd, ei->ResidualCnt);
if (ei->CommandStatus == 0) {
- cmd->scsi_done(cmd);
cmd_free(h, cp);
+ cmd->scsi_done(cmd);
return;
}
@@ -1265,7 +1266,7 @@
"has check condition: aborted command: "
"ASC: 0x%x, ASCQ: 0x%x\n",
cp, asc, ascq);
- cmd->result = DID_SOFT_ERROR << 16;
+ cmd->result |= DID_SOFT_ERROR << 16;
break;
}
/* Must be some other type of check condition */
@@ -1379,8 +1380,8 @@
dev_warn(&h->pdev->dev, "cp %p returned unknown status %x\n",
cp, ei->CommandStatus);
}
- cmd->scsi_done(cmd);
cmd_free(h, cp);
+ cmd->scsi_done(cmd);
}
static void hpsa_pci_unmap(struct pci_dev *pdev,
@@ -3117,7 +3118,7 @@
}
if (ioc->Request.Type.Direction == XFER_WRITE) {
if (copy_from_user(buff[sg_used], data_ptr, sz)) {
- status = -ENOMEM;
+ status = -EFAULT;
goto cleanup1;
}
} else
@@ -4904,7 +4905,7 @@
hpsa_hba_inquiry(h);
hpsa_register_scsi(h); /* hook ourselves into SCSI subsystem */
start_controller_lockup_detector(h);
- return 1;
+ return 0;
clean4:
hpsa_free_sg_chain_blocks(h);
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index d0fa4b6..c62b3e5 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -185,6 +185,11 @@
if (crq->valid & 0x80) {
if (++queue->cur == queue->size)
queue->cur = 0;
+
+ /* Ensure the read of the valid bit occurs before reading any
+ * other bits of the CRQ entry
+ */
+ rmb();
} else
crq = NULL;
spin_unlock_irqrestore(&queue->lock, flags);
@@ -203,6 +208,11 @@
{
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
+ /*
+ * Ensure the command buffer is flushed to memory before handing it
+ * over to the VIOS to prevent it from fetching any stale data.
+ */
+ mb();
return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
}
@@ -794,7 +804,8 @@
evt->hostdata->dev);
if (evt->cmnd_done)
evt->cmnd_done(evt->cmnd);
- } else if (evt->done)
+ } else if (evt->done && evt->crq.format != VIOSRP_MAD_FORMAT &&
+ evt->iu.srp.login_req.opcode != SRP_LOGIN_REQ)
evt->done(evt);
free_event_struct(&evt->hostdata->pool, evt);
spin_lock_irqsave(hostdata->host->host_lock, flags);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 6c4cedb..f7732f3 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -645,6 +645,7 @@
ipr_reinit_ipr_cmnd(ipr_cmd);
ipr_cmd->u.scratch = 0;
ipr_cmd->sibling = NULL;
+ ipr_cmd->eh_comp = NULL;
ipr_cmd->fast_done = fast_done;
init_timer(&ipr_cmd->timer);
}
@@ -810,6 +811,8 @@
scsi_dma_unmap(ipr_cmd->scsi_cmd);
scsi_cmd->scsi_done(scsi_cmd);
+ if (ipr_cmd->eh_comp)
+ complete(ipr_cmd->eh_comp);
list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
}
@@ -4767,6 +4770,84 @@
return rc;
}
+/**
+ * ipr_match_lun - Match function for specified LUN
+ * @ipr_cmd: ipr command struct
+ * @device: device to match (sdev)
+ *
+ * Returns:
+ * 1 if command matches sdev / 0 if command does not match sdev
+ **/
+static int ipr_match_lun(struct ipr_cmnd *ipr_cmd, void *device)
+{
+ if (ipr_cmd->scsi_cmd && ipr_cmd->scsi_cmd->device == device)
+ return 1;
+ return 0;
+}
+
+/**
+ * ipr_wait_for_ops - Wait for matching commands to complete
+ * @ipr_cmd: ipr command struct
+ * @device: device to match (sdev)
+ * @match: match function to use
+ *
+ * Returns:
+ * SUCCESS / FAILED
+ **/
+static int ipr_wait_for_ops(struct ipr_ioa_cfg *ioa_cfg, void *device,
+ int (*match)(struct ipr_cmnd *, void *))
+{
+ struct ipr_cmnd *ipr_cmd;
+ int wait;
+ unsigned long flags;
+ struct ipr_hrr_queue *hrrq;
+ signed long timeout = IPR_ABORT_TASK_TIMEOUT;
+ DECLARE_COMPLETION_ONSTACK(comp);
+
+ ENTER;
+ do {
+ wait = 0;
+
+ for_each_hrrq(hrrq, ioa_cfg) {
+ spin_lock_irqsave(hrrq->lock, flags);
+ list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) {
+ if (match(ipr_cmd, device)) {
+ ipr_cmd->eh_comp = ∁
+ wait++;
+ }
+ }
+ spin_unlock_irqrestore(hrrq->lock, flags);
+ }
+
+ if (wait) {
+ timeout = wait_for_completion_timeout(&comp, timeout);
+
+ if (!timeout) {
+ wait = 0;
+
+ for_each_hrrq(hrrq, ioa_cfg) {
+ spin_lock_irqsave(hrrq->lock, flags);
+ list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) {
+ if (match(ipr_cmd, device)) {
+ ipr_cmd->eh_comp = NULL;
+ wait++;
+ }
+ }
+ spin_unlock_irqrestore(hrrq->lock, flags);
+ }
+
+ if (wait)
+ dev_err(&ioa_cfg->pdev->dev, "Timed out waiting for aborted commands\n");
+ LEAVE;
+ return wait ? FAILED : SUCCESS;
+ }
+ }
+ } while (wait);
+
+ LEAVE;
+ return SUCCESS;
+}
+
static int ipr_eh_host_reset(struct scsi_cmnd *cmd)
{
struct ipr_ioa_cfg *ioa_cfg;
@@ -4985,11 +5066,17 @@
static int ipr_eh_dev_reset(struct scsi_cmnd *cmd)
{
int rc;
+ struct ipr_ioa_cfg *ioa_cfg;
+
+ ioa_cfg = (struct ipr_ioa_cfg *) cmd->device->host->hostdata;
spin_lock_irq(cmd->device->host->host_lock);
rc = __ipr_eh_dev_reset(cmd);
spin_unlock_irq(cmd->device->host->host_lock);
+ if (rc == SUCCESS)
+ rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun);
+
return rc;
}
@@ -5167,13 +5254,18 @@
{
unsigned long flags;
int rc;
+ struct ipr_ioa_cfg *ioa_cfg;
ENTER;
+ ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata;
+
spin_lock_irqsave(scsi_cmd->device->host->host_lock, flags);
rc = ipr_cancel_op(scsi_cmd);
spin_unlock_irqrestore(scsi_cmd->device->host->host_lock, flags);
+ if (rc == SUCCESS)
+ rc = ipr_wait_for_ops(ioa_cfg, scsi_cmd->device, ipr_match_lun);
LEAVE;
return rc;
}
@@ -6267,7 +6359,8 @@
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = ipr_ioa_attrs,
.sdev_attrs = ipr_dev_attrs,
- .proc_name = IPR_NAME
+ .proc_name = IPR_NAME,
+ .no_write_same = 1,
};
/**
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 07a85ce..535f573 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1578,6 +1578,7 @@
struct scsi_device *sdev;
} u;
+ struct completion *eh_comp;
struct ipr_hrr_queue *hrrq;
struct ipr_ioa_cfg *ioa_cfg;
};
diff --git a/drivers/scsi/ips.c b/drivers/scsi/ips.c
index 8d5ea8a..52a216f 100644
--- a/drivers/scsi/ips.c
+++ b/drivers/scsi/ips.c
@@ -374,6 +374,7 @@
.sg_tablesize = IPS_MAX_SG,
.cmd_per_lun = 3,
.use_clustering = ENABLE_CLUSTERING,
+ .no_write_same = 1,
};
diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h
index 4911310..22a9bb1 100644
--- a/drivers/scsi/isci/host.h
+++ b/drivers/scsi/isci/host.h
@@ -311,9 +311,8 @@
}
#define for_each_isci_host(id, ihost, pdev) \
- for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \
- id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \
- ihost = to_pci_info(pdev)->hosts[++id])
+ for (id = 0; id < SCI_MAX_CONTROLLERS && \
+ (ihost = to_pci_info(pdev)->hosts[id]); id++)
static inline void wait_for_start(struct isci_host *ihost)
{
diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c
index cd962da..5017bde 100644
--- a/drivers/scsi/isci/port_config.c
+++ b/drivers/scsi/isci/port_config.c
@@ -615,13 +615,6 @@
SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION);
} else {
/* the phy is already the part of the port */
- u32 port_state = iport->sm.current_state_id;
-
- /* if the PORT'S state is resetting then the link up is from
- * port hard reset in this case, we need to tell the port
- * that link up is recieved
- */
- BUG_ON(port_state != SCI_PORT_RESETTING);
port_agent->phy_ready_mask |= 1 << phy_index;
sci_port_link_up(iport, iphy);
}
diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c
index 9bb020a..5d6fda7 100644
--- a/drivers/scsi/isci/task.c
+++ b/drivers/scsi/isci/task.c
@@ -491,6 +491,7 @@
struct isci_tmf tmf;
int ret = TMF_RESP_FUNC_FAILED;
unsigned long flags;
+ int target_done_already = 0;
/* Get the isci_request reference from the task. Note that
* this check does not depend on the pending request list
@@ -505,9 +506,11 @@
/* If task is already done, the request isn't valid */
if (!(task->task_state_flags & SAS_TASK_STATE_DONE) &&
(task->task_state_flags & SAS_TASK_AT_INITIATOR) &&
- old_request)
+ old_request) {
idev = isci_get_device(task->dev->lldd_dev);
-
+ target_done_already = test_bit(IREQ_COMPLETE_IN_TARGET,
+ &old_request->flags);
+ }
spin_unlock(&task->task_state_lock);
spin_unlock_irqrestore(&ihost->scic_lock, flags);
@@ -561,7 +564,7 @@
if (task->task_proto == SAS_PROTOCOL_SMP ||
sas_protocol_ata(task->task_proto) ||
- test_bit(IREQ_COMPLETE_IN_TARGET, &old_request->flags) ||
+ target_done_already ||
test_bit(IDEV_GONE, &idev->flags)) {
spin_unlock_irqrestore(&ihost->scic_lock, flags);
@@ -798,7 +801,7 @@
/* XXX: need to cleanup any ireqs targeting this
* domain_device
*/
- ret = TMF_RESP_FUNC_COMPLETE;
+ ret = -ENODEV;
goto out;
}
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 5de9469..f91d417 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -717,11 +717,21 @@
return NULL;
}
+ if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) {
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN);
+ return NULL;
+ }
+
task = conn->login_task;
} else {
if (session->state != ISCSI_STATE_LOGGED_IN)
return NULL;
+ if (data_size != 0) {
+ iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode);
+ return NULL;
+ }
+
BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE);
BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED);
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 161c98e..d289583 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -211,7 +211,7 @@
qc->tf.nsect = 0;
}
- ata_tf_to_fis(&qc->tf, 1, 0, (u8*)&task->ata_task.fis);
+ ata_tf_to_fis(&qc->tf, qc->dev->link->pmp, 1, (u8 *)&task->ata_task.fis);
task->uldd_task = qc;
if (ata_is_atapi(qc->tf.protocol)) {
memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len);
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 62b58d3..60de662 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -500,6 +500,7 @@
struct sas_discovery_event *ev = to_sas_discovery_event(work);
struct asd_sas_port *port = ev->port;
struct sas_ha_struct *ha = port->ha;
+ struct domain_device *ddev = port->port_dev;
/* prevent revalidation from finding sata links in recovery */
mutex_lock(&ha->disco_mutex);
@@ -514,8 +515,9 @@
SAS_DPRINTK("REVALIDATING DOMAIN on port %d, pid:%d\n", port->id,
task_pid_nr(current));
- if (port->port_dev)
- res = sas_ex_revalidate_domain(port->port_dev);
+ if (ddev && (ddev->dev_type == SAS_FANOUT_EXPANDER_DEVICE ||
+ ddev->dev_type == SAS_EDGE_EXPANDER_DEVICE))
+ res = sas_ex_revalidate_domain(ddev);
SAS_DPRINTK("done REVALIDATING DOMAIN on port %d, pid:%d, res 0x%x\n",
port->id, task_pid_nr(current), res);
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 846f475f..60cf7b1 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -4244,6 +4244,7 @@
.eh_device_reset_handler = megaraid_reset,
.eh_bus_reset_handler = megaraid_reset,
.eh_host_reset_handler = megaraid_reset,
+ .no_write_same = 1,
};
static int
diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c
index e6a1e0b..3316d80 100644
--- a/drivers/scsi/megaraid/megaraid_mbox.c
+++ b/drivers/scsi/megaraid/megaraid_mbox.c
@@ -367,6 +367,7 @@
.eh_host_reset_handler = megaraid_reset_handler,
.change_queue_depth = megaraid_change_queue_depth,
.use_clustering = ENABLE_CLUSTERING,
+ .no_write_same = 1,
.sdev_attrs = megaraid_sdev_attrs,
.shost_attrs = megaraid_shost_attrs,
};
diff --git a/drivers/scsi/megaraid/megaraid_mm.c b/drivers/scsi/megaraid/megaraid_mm.c
index 25506c7..9bec171 100644
--- a/drivers/scsi/megaraid/megaraid_mm.c
+++ b/drivers/scsi/megaraid/megaraid_mm.c
@@ -486,6 +486,8 @@
pthru32->dataxferaddr = kioc->buf_paddr;
if (kioc->data_dir & UIOC_WR) {
+ if (pthru32->dataxferlen > kioc->xferlen)
+ return -EINVAL;
if (copy_from_user(kioc->buf_vaddr, kioc->user_data,
pthru32->dataxferlen)) {
return (-EFAULT);
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 684cc34..b521213 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -1295,7 +1295,6 @@
u32 *reply_queue;
dma_addr_t reply_queue_h;
- unsigned long base_addr;
struct megasas_register_set __iomem *reg_set;
struct megasas_pd_list pd_list[MEGASAS_MAX_PD];
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 3a9ddae..78b4fe8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -933,7 +933,7 @@
abort_fr->abort_mfi_phys_addr_hi = 0;
cmd->sync_cmd = 1;
- cmd->cmd_status = 0xFF;
+ cmd->cmd_status = ENODATA;
instance->instancet->issue_dcmd(instance, cmd);
@@ -2099,6 +2099,7 @@
.bios_param = megasas_bios_param,
.use_clustering = ENABLE_CLUSTERING,
.change_queue_depth = megasas_change_queue_depth,
+ .no_write_same = 1,
};
/**
@@ -3460,6 +3461,7 @@
u32 max_sectors_1;
u32 max_sectors_2;
u32 tmp_sectors, msix_enable;
+ resource_size_t base_addr;
struct megasas_register_set __iomem *reg_set;
struct megasas_ctrl_info *ctrl_info;
unsigned long bar_list;
@@ -3468,14 +3470,14 @@
/* Find first memory bar */
bar_list = pci_select_bars(instance->pdev, IORESOURCE_MEM);
instance->bar = find_first_bit(&bar_list, sizeof(unsigned long));
- instance->base_addr = pci_resource_start(instance->pdev, instance->bar);
if (pci_request_selected_regions(instance->pdev, instance->bar,
"megasas: LSI")) {
printk(KERN_DEBUG "megasas: IO memory region busy!\n");
return -EBUSY;
}
- instance->reg_set = ioremap_nocache(instance->base_addr, 8192);
+ base_addr = pci_resource_start(instance->pdev, instance->bar);
+ instance->reg_set = ioremap_nocache(base_addr, 8192);
if (!instance->reg_set) {
printk(KERN_DEBUG "megasas: Failed to map IO mem\n");
@@ -3508,11 +3510,21 @@
break;
}
- /*
- * We expect the FW state to be READY
- */
- if (megasas_transition_to_ready(instance, 0))
- goto fail_ready_state;
+ if (megasas_transition_to_ready(instance, 0)) {
+ atomic_set(&instance->fw_reset_no_pci_access, 1);
+ instance->instancet->adp_reset
+ (instance, instance->reg_set);
+ atomic_set(&instance->fw_reset_no_pci_access, 0);
+ dev_info(&instance->pdev->dev,
+ "megasas: FW restarted successfully from %s!\n",
+ __func__);
+
+ /*waitting for about 30 second before retry*/
+ ssleep(30);
+
+ if (megasas_transition_to_ready(instance, 0))
+ goto fail_ready_state;
+ }
/* Check if MSI-X is supported while in ready state */
msix_enable = (instance->instancet->read_fw_status_reg(reg_set) &
@@ -4852,10 +4864,12 @@
sense, sense_handle);
}
- for (i = 0; i < ioc->sge_count && kbuff_arr[i]; i++) {
- dma_free_coherent(&instance->pdev->dev,
- kern_sge32[i].length,
- kbuff_arr[i], kern_sge32[i].phys_addr);
+ for (i = 0; i < ioc->sge_count; i++) {
+ if (kbuff_arr[i])
+ dma_free_coherent(&instance->pdev->dev,
+ kern_sge32[i].length,
+ kbuff_arr[i],
+ kern_sge32[i].phys_addr);
}
megasas_return_cmd(instance, cmd);
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c
index bcb23d2..c76b18b 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -80,10 +80,6 @@
module_param(msix_disable, int, 0);
MODULE_PARM_DESC(msix_disable, " disable msix routed interrupts (default=0)");
-static int missing_delay[2] = {-1, -1};
-module_param_array(missing_delay, int, NULL, 0);
-MODULE_PARM_DESC(missing_delay, " device missing delay , io missing delay");
-
static int mpt2sas_fwfault_debug;
MODULE_PARM_DESC(mpt2sas_fwfault_debug, " enable detection of firmware fault "
"and halt firmware - (default=0)");
@@ -2199,7 +2195,7 @@
}
/**
- * _base_update_missing_delay - change the missing delay timers
+ * mpt2sas_base_update_missing_delay - change the missing delay timers
* @ioc: per adapter object
* @device_missing_delay: amount of time till device is reported missing
* @io_missing_delay: interval IO is returned when there is a missing device
@@ -2210,8 +2206,8 @@
* delay, as well as the io missing delay. This should be called at driver
* load time.
*/
-static void
-_base_update_missing_delay(struct MPT2SAS_ADAPTER *ioc,
+void
+mpt2sas_base_update_missing_delay(struct MPT2SAS_ADAPTER *ioc,
u16 device_missing_delay, u8 io_missing_delay)
{
u16 dmd, dmd_new, dmd_orignal;
@@ -4407,9 +4403,6 @@
if (r)
goto out_free_resources;
- if (missing_delay[0] != -1 && missing_delay[1] != -1)
- _base_update_missing_delay(ioc, missing_delay[0],
- missing_delay[1]);
ioc->non_operational_loop = 0;
return 0;
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 4caaac1..1130197 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -1055,6 +1055,9 @@
void mpt2sas_halt_firmware(struct MPT2SAS_ADAPTER *ioc);
+void mpt2sas_base_update_missing_delay(struct MPT2SAS_ADAPTER *ioc,
+ u16 device_missing_delay, u8 io_missing_delay);
+
int mpt2sas_port_enable(struct MPT2SAS_ADAPTER *ioc);
/* scsih shared API */
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index c6bdc92..fe76185 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -101,6 +101,10 @@
module_param(max_sectors, ushort, 0);
MODULE_PARM_DESC(max_sectors, "max sectors, range 64 to 32767 default=32767");
+static int missing_delay[2] = {-1, -1};
+module_param_array(missing_delay, int, NULL, 0);
+MODULE_PARM_DESC(missing_delay, " device missing delay , io missing delay");
+
/* scsi-mid layer global parmeter is max_report_luns, which is 511 */
#define MPT2SAS_MAX_LUN (16895)
static int max_lun = MPT2SAS_MAX_LUN;
@@ -3994,11 +3998,7 @@
else
mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
} else
-/* MPI Revision I (UNIT = 0xA) - removed MPI2_SCSIIO_CONTROL_UNTAGGED */
-/* mpi_control |= MPI2_SCSIIO_CONTROL_UNTAGGED;
- */
- mpi_control |= (0x500);
-
+ mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
} else
mpi_control |= MPI2_SCSIIO_CONTROL_SIMPLEQ;
/* Make sure Device is not raid volume.
@@ -7303,7 +7303,9 @@
case MPT2SAS_PORT_ENABLE_COMPLETE:
ioc->start_scan = 0;
-
+ if (missing_delay[0] != -1 && missing_delay[1] != -1)
+ mpt2sas_base_update_missing_delay(ioc, missing_delay[0],
+ missing_delay[1]);
dewtprintk(ioc, printk(MPT2SAS_INFO_FMT "port enable: complete "
"from worker thread\n", ioc->name));
@@ -8172,7 +8174,6 @@
mpt2sas_base_free_resources(ioc);
pci_save_state(pdev);
- pci_disable_device(pdev);
pci_set_power_state(pdev, device_state);
return 0;
}
diff --git a/drivers/scsi/mpt3sas/Makefile b/drivers/scsi/mpt3sas/Makefile
index 4c1d2e7..efb0c4c 100644
--- a/drivers/scsi/mpt3sas/Makefile
+++ b/drivers/scsi/mpt3sas/Makefile
@@ -1,5 +1,5 @@
# mpt3sas makefile
-obj-m += mpt3sas.o
+obj-$(CONFIG_SCSI_MPT3SAS) += mpt3sas.o
mpt3sas-y += mpt3sas_base.o \
mpt3sas_config.o \
mpt3sas_scsih.o \
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index dcbf7c8..f8c4b85 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1273,6 +1273,7 @@
struct MPT3SAS_DEVICE *sas_device_priv_data;
struct scsi_target *starget;
struct _raid_device *raid_device;
+ struct _sas_device *sas_device;
unsigned long flags;
sas_device_priv_data = kzalloc(sizeof(struct scsi_device), GFP_KERNEL);
@@ -1301,6 +1302,19 @@
spin_unlock_irqrestore(&ioc->raid_device_lock, flags);
}
+ if (!(sas_target_priv_data->flags & MPT_TARGET_FLAGS_VOLUME)) {
+ spin_lock_irqsave(&ioc->sas_device_lock, flags);
+ sas_device = mpt3sas_scsih_sas_device_find_by_sas_address(ioc,
+ sas_target_priv_data->sas_address);
+ if (sas_device && (sas_device->starget == NULL)) {
+ sdev_printk(KERN_INFO, sdev,
+ "%s : sas_device->starget set to starget @ %d\n",
+ __func__, __LINE__);
+ sas_device->starget = starget;
+ }
+ spin_unlock_irqrestore(&ioc->sas_device_lock, flags);
+ }
+
return 0;
}
@@ -6392,7 +6406,7 @@
handle))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
+ if (ioc_status != MPI2_IOCSTATUS_SUCCESS)
break;
handle = le16_to_cpu(sas_device_pg0.DevHandle);
device_info = le32_to_cpu(sas_device_pg0.DeviceInfo);
@@ -6494,7 +6508,7 @@
&volume_pg1, MPI2_RAID_VOLUME_PGAD_FORM_GET_NEXT_HANDLE, handle))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
+ if (ioc_status != MPI2_IOCSTATUS_SUCCESS)
break;
handle = le16_to_cpu(volume_pg1.DevHandle);
@@ -6518,7 +6532,7 @@
phys_disk_num))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
+ if (ioc_status != MPI2_IOCSTATUS_SUCCESS)
break;
phys_disk_num = pd_pg0.PhysDiskNum;
handle = le16_to_cpu(pd_pg0.DevHandle);
@@ -6597,7 +6611,7 @@
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
+ if (ioc_status != MPI2_IOCSTATUS_SUCCESS)
break;
handle = le16_to_cpu(expander_pg0.DevHandle);
@@ -6742,8 +6756,6 @@
MPI2_SAS_EXPAND_PGAD_FORM_GET_NEXT_HNDL, handle))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
- break;
if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
pr_info(MPT3SAS_FMT "\tbreak from expander scan: " \
"ioc_status(0x%04x), loginfo(0x%08x)\n",
@@ -6787,8 +6799,6 @@
phys_disk_num))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
- break;
if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
pr_info(MPT3SAS_FMT "\tbreak from phys disk scan: "\
"ioc_status(0x%04x), loginfo(0x%08x)\n",
@@ -6854,8 +6864,6 @@
&volume_pg1, MPI2_RAID_VOLUME_PGAD_FORM_GET_NEXT_HANDLE, handle))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
- break;
if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
pr_info(MPT3SAS_FMT "\tbreak from volume scan: " \
"ioc_status(0x%04x), loginfo(0x%08x)\n",
@@ -6914,8 +6922,6 @@
handle))) {
ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
MPI2_IOCSTATUS_MASK;
- if (ioc_status == MPI2_IOCSTATUS_CONFIG_INVALID_PAGE)
- break;
if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
pr_info(MPT3SAS_FMT "\tbreak from end device scan:"\
" ioc_status(0x%04x), loginfo(0x%08x)\n",
diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c
index c9e2449..fa50c7d 100644
--- a/drivers/scsi/mvsas/mv_sas.c
+++ b/drivers/scsi/mvsas/mv_sas.c
@@ -441,14 +441,11 @@
static int mvs_task_prep_ata(struct mvs_info *mvi,
struct mvs_task_exec_info *tei)
{
- struct sas_ha_struct *sha = mvi->sas;
struct sas_task *task = tei->task;
struct domain_device *dev = task->dev;
struct mvs_device *mvi_dev = dev->lldd_dev;
struct mvs_cmd_hdr *hdr = tei->hdr;
struct asd_sas_port *sas_port = dev->port;
- struct sas_phy *sphy = dev->phy;
- struct asd_sas_phy *sas_phy = sha->sas_phy[sphy->number];
struct mvs_slot_info *slot;
void *buf_prd;
u32 tag = tei->tag, hdr_tag;
@@ -468,7 +465,7 @@
slot->tx = mvi->tx_prod;
del_q = TXQ_MODE_I | tag |
(TXQ_CMD_STP << TXQ_CMD_SHIFT) |
- (MVS_PHY_ID << TXQ_PHY_SHIFT) |
+ ((sas_port->phy_mask & TXQ_PHY_MASK) << TXQ_PHY_SHIFT) |
(mvi_dev->taskfileset << TXQ_SRS_SHIFT);
mvi->tx[mvi->tx_prod] = cpu_to_le32(del_q);
diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c
index 1e3879d..0665f9c 100644
--- a/drivers/scsi/nsp32.c
+++ b/drivers/scsi/nsp32.c
@@ -2899,7 +2899,7 @@
* reset SCSI bus
*/
nsp32_write1(base, SCSI_BUS_CONTROL, BUSCTL_RST);
- udelay(RESET_HOLD_TIME);
+ mdelay(RESET_HOLD_TIME / 1000);
nsp32_write1(base, SCSI_BUS_CONTROL, 0);
for(i = 0; i < 5; i++) {
intrdat = nsp32_read2(base, IRQ_STATUS); /* dummy read */
diff --git a/drivers/scsi/osd/osd_uld.c b/drivers/scsi/osd/osd_uld.c
index 0fab6b5..9d86947 100644
--- a/drivers/scsi/osd/osd_uld.c
+++ b/drivers/scsi/osd/osd_uld.c
@@ -485,7 +485,7 @@
oud->class_dev.class = &osd_uld_class;
oud->class_dev.parent = dev;
oud->class_dev.release = __remove;
- error = dev_set_name(&oud->class_dev, disk->disk_name);
+ error = dev_set_name(&oud->class_dev, "%s", disk->disk_name);
if (error) {
OSD_ERR("dev_set_name failed => %d\n", error);
goto err_put_cdev;
diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c
index 69dd49c..ce3f129d 100644
--- a/drivers/scsi/pm8001/pm8001_hwi.c
+++ b/drivers/scsi/pm8001/pm8001_hwi.c
@@ -221,7 +221,7 @@
pm8001_ha->main_cfg_tbl.pm8001_tbl.fatal_err_interrupt = 0x01;
for (i = 0; i < PM8001_MAX_INB_NUM; i++) {
pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt =
- PM8001_MPI_QUEUE | (64 << 16) | (0x00<<30);
+ PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30);
pm8001_ha->inbnd_q_tbl[i].upper_base_addr =
pm8001_ha->memoryMap.region[IB + i].phys_addr_hi;
pm8001_ha->inbnd_q_tbl[i].lower_base_addr =
@@ -247,7 +247,7 @@
}
for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) {
pm8001_ha->outbnd_q_tbl[i].element_size_cnt =
- PM8001_MPI_QUEUE | (64 << 16) | (0x01<<30);
+ PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30);
pm8001_ha->outbnd_q_tbl[i].upper_base_addr =
pm8001_ha->memoryMap.region[OB + i].phys_addr_hi;
pm8001_ha->outbnd_q_tbl[i].lower_base_addr =
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index 302514d..e1c4896 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -275,7 +275,7 @@
for (i = 0; i < PM8001_MAX_SPCV_INB_NUM; i++) {
pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt =
- PM8001_MPI_QUEUE | (64 << 16) | (0x00<<30);
+ PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30);
pm8001_ha->inbnd_q_tbl[i].upper_base_addr =
pm8001_ha->memoryMap.region[IB + i].phys_addr_hi;
pm8001_ha->inbnd_q_tbl[i].lower_base_addr =
@@ -301,7 +301,7 @@
}
for (i = 0; i < PM8001_MAX_SPCV_OUTB_NUM; i++) {
pm8001_ha->outbnd_q_tbl[i].element_size_cnt =
- PM8001_MPI_QUEUE | (64 << 16) | (0x01<<30);
+ PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30);
pm8001_ha->outbnd_q_tbl[i].upper_base_addr =
pm8001_ha->memoryMap.region[OB + i].phys_addr_hi;
pm8001_ha->outbnd_q_tbl[i].lower_base_addr =
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 8e1b737..bfb72ec 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4314,6 +4314,7 @@
.this_id = -1,
.sg_tablesize = PMCRAID_MAX_IOADLS,
.max_sectors = PMCRAID_IOA_MAX_SECTORS,
+ .no_write_same = 1,
.cmd_per_lun = PMCRAID_MAX_CMD_PER_LUN,
.use_clustering = ENABLE_CLUSTERING,
.shost_attrs = pmcraid_host_attrs,
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index c32efc7..799c266 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2980,8 +2980,7 @@
IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
IS_QLA82XX(ha) || IS_QLA83XX(ha))
#define IS_MSIX_NACK_CAPABLE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
-#define IS_NOPOLLING_TYPE(ha) ((IS_QLA25XX(ha) || IS_QLA81XX(ha) || \
- IS_QLA83XX(ha)) && (ha)->flags.msix_enabled)
+#define IS_NOPOLLING_TYPE(ha) (IS_QLA81XX(ha) && (ha)->flags.msix_enabled)
#define IS_FAC_REQUIRED(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
#define IS_NOCACHE_VPD_TYPE(ha) (IS_QLA81XX(ha) || IS_QLA83XX(ha))
#define IS_ALOGIO_CAPABLE(ha) (IS_QLA23XX(ha) || IS_FWI2_CAPABLE(ha))
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 15e4080..51cd27a 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -419,6 +419,8 @@
__constant_cpu_to_le16(CF_SIMPLE_TAG);
break;
}
+ } else {
+ cmd_pkt->control_flags = __constant_cpu_to_le16(CF_SIMPLE_TAG);
}
/* Load SCSI command packet. */
@@ -1308,11 +1310,11 @@
fcp_cmnd->task_attribute = TSK_ORDERED;
break;
default:
- fcp_cmnd->task_attribute = 0;
+ fcp_cmnd->task_attribute = TSK_SIMPLE;
break;
}
} else {
- fcp_cmnd->task_attribute = 0;
+ fcp_cmnd->task_attribute = TSK_SIMPLE;
}
cmd_pkt->fcp_rsp_dseg_len = 0; /* Let response come in status iocb */
@@ -1527,7 +1529,12 @@
case ORDERED_QUEUE_TAG:
cmd_pkt->task = TSK_ORDERED;
break;
+ default:
+ cmd_pkt->task = TSK_SIMPLE;
+ break;
}
+ } else {
+ cmd_pkt->task = TSK_SIMPLE;
}
/* Load SCSI command packet. */
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index ad72c1d..66c495d 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2553,7 +2553,7 @@
ha->flags.enable_64bit_addressing ? "enable" :
"disable");
ret = qla2x00_mem_alloc(ha, req_length, rsp_length, &req, &rsp);
- if (!ret) {
+ if (ret) {
ql_log_pci(ql_log_fatal, pdev, 0x0031,
"Failed to allocate memory for adapter, aborting.\n");
@@ -3458,10 +3458,10 @@
else {
qla2x00_set_reserved_loop_ids(ha);
ql_dbg_pci(ql_dbg_init, ha->pdev, 0x0123,
- "loop_id_map=%p. \n", ha->loop_id_map);
+ "loop_id_map=%p.\n", ha->loop_id_map);
}
- return 1;
+ return 0;
fail_async_pd:
dma_pool_free(ha->s_dma_pool, ha->ex_init_cb, ha->ex_init_cb_dma);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index fcdc22306..e688494 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1514,12 +1514,10 @@
static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
uint32_t req_cnt)
{
- struct qla_hw_data *ha = vha->hw;
- device_reg_t __iomem *reg = ha->iobase;
uint32_t cnt;
if (vha->req->cnt < (req_cnt + 2)) {
- cnt = (uint16_t)RD_REG_DWORD(®->isp24.req_q_out);
+ cnt = (uint16_t)RD_REG_DWORD(vha->req->req_q_out);
ql_dbg(ql_dbg_tgt, vha, 0xe00a,
"Request ring circled: cnt=%d, vha->->ring_index=%d, "
@@ -3339,7 +3337,8 @@
ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c,
"SRR cmd %p (se_cmd %p, tag %d, op %x), "
"sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag,
- se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset);
+ se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0,
+ cmd->sg_cnt, cmd->offset);
qlt_handle_srr(vha, sctio, imm);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 66b0b26..c817160 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -762,7 +762,16 @@
pr_debug("fc_rport domain: port_id 0x%06x\n", nacl->nport_id);
node = btree_remove32(&lport->lport_fcport_map, nacl->nport_id);
- WARN_ON(node && (node != se_nacl));
+ if (WARN_ON(node && (node != se_nacl))) {
+ /*
+ * The nacl no longer matches what we think it should be.
+ * Most likely a new dynamic acl has been added while
+ * someone dropped the hardware lock. It clearly is a
+ * bug elsewhere, but this bit can't make things worse.
+ */
+ btree_insert32(&lport->lport_fcport_map, nacl->nport_id,
+ node, GFP_ATOMIC);
+ }
pr_debug("Removed from fcport_map: %p for WWNN: 0x%016LX, port_id: 0x%06x\n",
se_nacl, nacl->nport_wwnn, nacl->nport_id);
@@ -1456,7 +1465,7 @@
/*
* Finally register the new FC Nexus with TCM
*/
- __transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
+ transport_register_session(se_nacl->se_tpg, se_nacl, se_sess, sess);
return 0;
}
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 2c0d0ec..eaa808e 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -1031,6 +1031,9 @@
{
int i, result;
+ if (sdev->skip_vpd_pages)
+ goto fail;
+
/* Ask for all the pages supported by this device */
result = scsi_vpd_inquiry(sdev, buf, 0, buf_len);
if (result)
@@ -1070,8 +1073,8 @@
* @opcode: opcode for command to look up
*
* Uses the REPORT SUPPORTED OPERATION CODES to look up the given
- * opcode. Returns 0 if RSOC fails or if the command opcode is
- * unsupported. Returns 1 if the device claims to support the command.
+ * opcode. Returns -EINVAL if RSOC fails, 0 if the command opcode is
+ * unsupported and 1 if the device claims to support the command.
*/
int scsi_report_opcode(struct scsi_device *sdev, unsigned char *buffer,
unsigned int len, unsigned char opcode)
@@ -1081,7 +1084,7 @@
int result;
if (sdev->no_report_opcodes || sdev->scsi_level < SCSI_SPC_3)
- return 0;
+ return -EINVAL;
memset(cmd, 0, 16);
cmd[0] = MAINTENANCE_IN;
@@ -1097,7 +1100,7 @@
if (result && scsi_sense_valid(&sshdr) &&
sshdr.sense_key == ILLEGAL_REQUEST &&
(sshdr.asc == 0x20 || sshdr.asc == 0x24) && sshdr.ascq == 0x00)
- return 0;
+ return -EINVAL;
if ((buffer[1] & 3) == 3) /* Command supported */
return 1;
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f43de1e..3668b1b 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1689,8 +1689,10 @@
* is no point trying to lock the door of an off-line device.
*/
shost_for_each_device(sdev, shost) {
- if (scsi_device_online(sdev) && sdev->locked)
+ if (scsi_device_online(sdev) && sdev->was_reset && sdev->locked) {
scsi_eh_lock_door(sdev);
+ sdev->was_reset = 0;
+ }
}
/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 86d5220..9f3168e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -815,6 +815,14 @@
scsi_next_command(cmd);
return;
}
+ } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+ /*
+ * Certain non BLOCK_PC requests are commands that don't
+ * actually transfer anything (FLUSH), so cannot use
+ * good_bytes != blk_rq_bytes(req) as the signal for an error.
+ * This sets the error explicitly for the problem case.
+ */
+ error = __scsi_error_from_host_byte(cmd, result);
}
/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
@@ -1234,9 +1242,11 @@
"rejecting I/O to dead device\n");
ret = BLKPREP_KILL;
break;
- case SDEV_QUIESCE:
case SDEV_BLOCK:
case SDEV_CREATED_BLOCK:
+ ret = BLKPREP_DEFER;
+ break;
+ case SDEV_QUIESCE:
/*
* If the devices is blocked we defer normal commands.
*/
diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c
index fe30ea9..109802f 100644
--- a/drivers/scsi/scsi_netlink.c
+++ b/drivers/scsi/scsi_netlink.c
@@ -77,7 +77,7 @@
goto next_msg;
}
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!netlink_capable(skb, CAP_SYS_ADMIN)) {
err = -EPERM;
goto next_msg;
}
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 3e58b22..8592404 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -320,6 +320,7 @@
struct Scsi_Host *shost = dev_to_shost(dev->parent);
unsigned long flags;
+ starget->state = STARGET_DEL;
transport_destroy_device(dev);
spin_lock_irqsave(shost->host_lock, flags);
if (shost->hostt->target_destroy)
@@ -371,6 +372,37 @@
}
/**
+ * scsi_target_reap_ref_release - remove target from visibility
+ * @kref: the reap_ref in the target being released
+ *
+ * Called on last put of reap_ref, which is the indication that no device
+ * under this target is visible anymore, so render the target invisible in
+ * sysfs. Note: we have to be in user context here because the target reaps
+ * should be done in places where the scsi device visibility is being removed.
+ */
+static void scsi_target_reap_ref_release(struct kref *kref)
+{
+ struct scsi_target *starget
+ = container_of(kref, struct scsi_target, reap_ref);
+
+ /*
+ * if we get here and the target is still in the CREATED state that
+ * means it was allocated but never made visible (because a scan
+ * turned up no LUNs), so don't call device_del() on it.
+ */
+ if (starget->state != STARGET_CREATED) {
+ transport_remove_device(&starget->dev);
+ device_del(&starget->dev);
+ }
+ scsi_target_destroy(starget);
+}
+
+static void scsi_target_reap_ref_put(struct scsi_target *starget)
+{
+ kref_put(&starget->reap_ref, scsi_target_reap_ref_release);
+}
+
+/**
* scsi_alloc_target - allocate a new or find an existing target
* @parent: parent of the target (need not be a scsi host)
* @channel: target channel number (zero if no channels)
@@ -392,7 +424,7 @@
+ shost->transportt->target_size;
struct scsi_target *starget;
struct scsi_target *found_target;
- int error;
+ int error, ref_got;
starget = kzalloc(size, GFP_KERNEL);
if (!starget) {
@@ -401,7 +433,7 @@
}
dev = &starget->dev;
device_initialize(dev);
- starget->reap_ref = 1;
+ kref_init(&starget->reap_ref);
dev->parent = get_device(parent);
dev_set_name(dev, "target%d:%d:%d", shost->host_no, channel, id);
dev->bus = &scsi_bus_type;
@@ -441,29 +473,36 @@
return starget;
found:
- found_target->reap_ref++;
+ /*
+ * release routine already fired if kref is zero, so if we can still
+ * take the reference, the target must be alive. If we can't, it must
+ * be dying and we need to wait for a new target
+ */
+ ref_got = kref_get_unless_zero(&found_target->reap_ref);
+
spin_unlock_irqrestore(shost->host_lock, flags);
- if (found_target->state != STARGET_DEL) {
+ if (ref_got) {
put_device(dev);
return found_target;
}
- /* Unfortunately, we found a dying target; need to
- * wait until it's dead before we can get a new one */
+ /*
+ * Unfortunately, we found a dying target; need to wait until it's
+ * dead before we can get a new one. There is an anomaly here. We
+ * *should* call scsi_target_reap() to balance the kref_get() of the
+ * reap_ref above. However, since the target being released, it's
+ * already invisible and the reap_ref is irrelevant. If we call
+ * scsi_target_reap() we might spuriously do another device_del() on
+ * an already invisible target.
+ */
put_device(&found_target->dev);
- flush_scheduled_work();
+ /*
+ * length of time is irrelevant here, we just want to yield the CPU
+ * for a tick to avoid busy waiting for the target to die.
+ */
+ msleep(1);
goto retry;
}
-static void scsi_target_reap_usercontext(struct work_struct *work)
-{
- struct scsi_target *starget =
- container_of(work, struct scsi_target, ew.work);
-
- transport_remove_device(&starget->dev);
- device_del(&starget->dev);
- scsi_target_destroy(starget);
-}
-
/**
* scsi_target_reap - check to see if target is in use and destroy if not
* @starget: target to be checked
@@ -474,28 +513,13 @@
*/
void scsi_target_reap(struct scsi_target *starget)
{
- struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
- unsigned long flags;
- enum scsi_target_state state;
- int empty = 0;
-
- spin_lock_irqsave(shost->host_lock, flags);
- state = starget->state;
- if (--starget->reap_ref == 0 && list_empty(&starget->devices)) {
- empty = 1;
- starget->state = STARGET_DEL;
- }
- spin_unlock_irqrestore(shost->host_lock, flags);
-
- if (!empty)
- return;
-
- BUG_ON(state == STARGET_DEL);
- if (state == STARGET_CREATED)
- scsi_target_destroy(starget);
- else
- execute_in_process_context(scsi_target_reap_usercontext,
- &starget->ew);
+ /*
+ * serious problem if this triggers: STARGET_DEL is only set in the if
+ * the reap_ref drops to zero, so we're trying to do another final put
+ * on an already released kref
+ */
+ BUG_ON(starget->state == STARGET_DEL);
+ scsi_target_reap_ref_put(starget);
}
/**
@@ -1527,6 +1551,10 @@
}
mutex_unlock(&shost->scan_mutex);
scsi_autopm_put_target(starget);
+ /*
+ * paired with scsi_alloc_target(). Target will be destroyed unless
+ * scsi_probe_and_add_lun made an underlying device visible
+ */
scsi_target_reap(starget);
put_device(&starget->dev);
@@ -1607,8 +1635,10 @@
out_reap:
scsi_autopm_put_target(starget);
- /* now determine if the target has any children at all
- * and if not, nuke it */
+ /*
+ * paired with scsi_alloc_target(): determine if the target has
+ * any children at all and if not, nuke it
+ */
scsi_target_reap(starget);
put_device(&starget->dev);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 931a7d9..9e2dd47 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -332,17 +332,14 @@
{
struct scsi_device *sdev;
struct device *parent;
- struct scsi_target *starget;
struct list_head *this, *tmp;
unsigned long flags;
sdev = container_of(work, struct scsi_device, ew.work);
parent = sdev->sdev_gendev.parent;
- starget = to_scsi_target(parent);
spin_lock_irqsave(sdev->host->host_lock, flags);
- starget->reap_ref++;
list_del(&sdev->siblings);
list_del(&sdev->same_target_siblings);
list_del(&sdev->starved_entry);
@@ -362,8 +359,6 @@
/* NULL queue means the device can't be used */
sdev->request_queue = NULL;
- scsi_target_reap(scsi_target(sdev));
-
kfree(sdev->inquiry);
kfree(sdev);
@@ -978,6 +973,13 @@
sdev->host->hostt->slave_destroy(sdev);
transport_destroy_device(dev);
+ /*
+ * Paired with the kref_get() in scsi_sysfs_initialize(). We have
+ * remoed sysfs visibility from the device, so make the target
+ * invisible if this was the last device underneath it.
+ */
+ scsi_target_reap(scsi_target(sdev));
+
put_device(dev);
}
@@ -1040,7 +1042,7 @@
continue;
if (starget->dev.parent == dev || &starget->dev == dev) {
/* assuming new targets arrive at the end */
- starget->reap_ref++;
+ kref_get(&starget->reap_ref);
spin_unlock_irqrestore(shost->host_lock, flags);
if (last)
scsi_target_reap(last);
@@ -1124,6 +1126,12 @@
list_add_tail(&sdev->same_target_siblings, &starget->devices);
list_add_tail(&sdev->siblings, &shost->__devices);
spin_unlock_irqrestore(shost->host_lock, flags);
+ /*
+ * device can now only be removed via __scsi_remove_device() so hold
+ * the target. Target will be held in CREATED state until something
+ * beneath it becomes visible (in which case it moves to RUNNING)
+ */
+ kref_get(&starget->reap_ref);
}
int scsi_is_sdev_device(const struct device *dev)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c1c5552..26b543b 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -142,7 +142,7 @@
char *buffer_data;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
- const char *temp = "temporary ";
+ static const char temp[] = "temporary ";
int len;
if (sdp->type != TYPE_DISK)
@@ -442,8 +442,10 @@
if (max == 0)
sdp->no_write_same = 1;
- else if (max <= SD_MAX_WS16_BLOCKS)
+ else if (max <= SD_MAX_WS16_BLOCKS) {
+ sdp->no_write_same = 0;
sdkp->max_ws_blocks = max;
+ }
sd_config_write_same(sdkp);
@@ -740,7 +742,6 @@
{
struct request_queue *q = sdkp->disk->queue;
unsigned int logical_block_size = sdkp->device->sector_size;
- unsigned int blocks = 0;
if (sdkp->device->no_write_same) {
sdkp->max_ws_blocks = 0;
@@ -752,18 +753,20 @@
* blocks per I/O unless the device explicitly advertises a
* bigger limit.
*/
- if (sdkp->max_ws_blocks == 0)
- sdkp->max_ws_blocks = SD_MAX_WS10_BLOCKS;
-
- if (sdkp->ws16 || sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS)
- blocks = min_not_zero(sdkp->max_ws_blocks,
- (u32)SD_MAX_WS16_BLOCKS);
- else
- blocks = min_not_zero(sdkp->max_ws_blocks,
- (u32)SD_MAX_WS10_BLOCKS);
+ if (sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS)
+ sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
+ (u32)SD_MAX_WS16_BLOCKS);
+ else if (sdkp->ws16 || sdkp->ws10 || sdkp->device->no_report_opcodes)
+ sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks,
+ (u32)SD_MAX_WS10_BLOCKS);
+ else {
+ sdkp->device->no_write_same = 1;
+ sdkp->max_ws_blocks = 0;
+ }
out:
- blk_queue_max_write_same_sectors(q, blocks * (logical_block_size >> 9));
+ blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
+ (logical_block_size >> 9));
}
/**
@@ -825,10 +828,17 @@
static void sd_unprep_fn(struct request_queue *q, struct request *rq)
{
+ struct scsi_cmnd *SCpnt = rq->special;
+
if (rq->cmd_flags & REQ_DISCARD) {
free_page((unsigned long)rq->buffer);
rq->buffer = NULL;
}
+ if (SCpnt->cmnd != rq->cmd) {
+ mempool_free(SCpnt->cmnd, sd_cdb_pool);
+ SCpnt->cmnd = NULL;
+ SCpnt->cmd_len = 0;
+ }
}
/**
@@ -1707,21 +1717,6 @@
if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
sd_dif_complete(SCpnt, good_bytes);
- if (scsi_host_dif_capable(sdkp->device->host, sdkp->protection_type)
- == SD_DIF_TYPE2_PROTECTION && SCpnt->cmnd != SCpnt->request->cmd) {
-
- /* We have to print a failed command here as the
- * extended CDB gets freed before scsi_io_completion()
- * is called.
- */
- if (result)
- scsi_print_command(SCpnt);
-
- mempool_free(SCpnt->cmnd, sd_cdb_pool);
- SCpnt->cmnd = NULL;
- SCpnt->cmd_len = 0;
- }
-
return good_bytes;
}
@@ -2414,14 +2409,9 @@
}
}
- if (modepage == 0x3F) {
- sd_printk(KERN_ERR, sdkp, "No Caching mode page "
- "present\n");
- goto defaults;
- } else if ((buffer[offset] & 0x3f) != modepage) {
- sd_printk(KERN_ERR, sdkp, "Got wrong page\n");
- goto defaults;
- }
+ sd_printk(KERN_ERR, sdkp, "No Caching mode page found\n");
+ goto defaults;
+
Page_found:
if (modepage == 8) {
sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0);
@@ -2635,9 +2625,33 @@
static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer)
{
- if (scsi_report_opcode(sdkp->device, buffer, SD_BUF_SIZE,
- WRITE_SAME_16))
+ struct scsi_device *sdev = sdkp->device;
+
+ if (sdev->host->no_write_same) {
+ sdev->no_write_same = 1;
+
+ return;
+ }
+
+ if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) {
+ /* too large values might cause issues with arcmsr */
+ int vpd_buf_len = 64;
+
+ sdev->no_report_opcodes = 1;
+
+ /* Disable WRITE SAME if REPORT SUPPORTED OPERATION
+ * CODES is unsupported and the device has an ATA
+ * Information VPD page (SAT).
+ */
+ if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len))
+ sdev->no_write_same = 1;
+ }
+
+ if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1)
sdkp->ws16 = 1;
+
+ if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1)
+ sdkp->ws10 = 1;
}
static int sd_try_extended_inquiry(struct scsi_device *sdp)
@@ -2838,6 +2852,7 @@
gd->events |= DISK_EVENT_MEDIA_CHANGE;
}
+ blk_pm_runtime_init(sdp->request_queue, dev);
add_disk(gd);
if (sdkp->capacity)
sd_dif_config_host(sdkp);
@@ -2846,7 +2861,6 @@
sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n",
sdp->removable ? "removable " : "");
- blk_pm_runtime_init(sdp->request_queue, dev);
scsi_autopm_put_device(sdp);
put_device(&sdkp->dev);
}
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 2386aeb..7a049de 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -84,6 +84,7 @@
unsigned lbpws : 1;
unsigned lbpws10 : 1;
unsigned lbpvpd : 1;
+ unsigned ws10 : 1;
unsigned ws16 : 1;
};
#define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev)
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index df5e961..eb81c98 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -522,7 +522,7 @@
sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp)
{
sg_io_hdr_t *hp = &srp->header;
- int err = 0;
+ int err = 0, err2;
int len;
if (count < SZ_SG_IO_HDR) {
@@ -551,8 +551,8 @@
goto err_out;
}
err_out:
- err = sg_finish_rem_req(srp);
- return (0 == err) ? count : err;
+ err2 = sg_finish_rem_req(srp);
+ return err ? : err2 ? : count;
}
static ssize_t
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 16a3a0c..913b91c 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -33,6 +33,7 @@
#include <linux/device.h>
#include <linux/hyperv.h>
#include <linux/mempool.h>
+#include <linux/blkdev.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_host.h>
@@ -630,21 +631,22 @@
if (bounce_sgl[j].length == PAGE_SIZE) {
/* full..move to next entry */
sg_kunmap_atomic(bounce_addr);
+ bounce_addr = 0;
j++;
-
- /* if we need to use another bounce buffer */
- if (srclen || i != orig_sgl_count - 1)
- bounce_addr = sg_kmap_atomic(bounce_sgl,j);
-
- } else if (srclen == 0 && i == orig_sgl_count - 1) {
- /* unmap the last bounce that is < PAGE_SIZE */
- sg_kunmap_atomic(bounce_addr);
}
+
+ /* if we need to use another bounce buffer */
+ if (srclen && bounce_addr == 0)
+ bounce_addr = sg_kmap_atomic(bounce_sgl, j);
+
}
sg_kunmap_atomic(src_addr - orig_sgl[i].offset);
}
+ if (bounce_addr)
+ sg_kunmap_atomic(bounce_addr);
+
local_irq_restore(flags);
return total_copied;
@@ -803,6 +805,13 @@
case ATA_12:
set_host_byte(scmnd, DID_PASSTHROUGH);
break;
+ /*
+ * On Some Windows hosts TEST_UNIT_READY command can return
+ * SRB_STATUS_ERROR, let the upper level code deal with it
+ * based on the sense information.
+ */
+ case TEST_UNIT_READY:
+ break;
default:
set_host_byte(scmnd, DID_TARGET_FAILURE);
}
@@ -1189,6 +1198,9 @@
{
struct stor_mem_pools *memp = sdevice->hostdata;
+ if (!memp)
+ return;
+
mempool_destroy(memp->request_mempool);
kmem_cache_destroy(memp->request_pool);
kfree(memp);
@@ -1282,6 +1294,16 @@
return SUCCESS;
}
+/*
+ * The host guarantees to respond to each command, although I/O latencies might
+ * be unbounded on Azure. Reset the timer unconditionally to give the host a
+ * chance to perform EH.
+ */
+static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd)
+{
+ return BLK_EH_RESET_TIMER;
+}
+
static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd)
{
bool allowed = true;
@@ -1418,13 +1440,12 @@
if (ret == -EAGAIN) {
/* no more space */
- if (cmd_request->bounce_sgl_count) {
+ if (cmd_request->bounce_sgl_count)
destroy_bounce_buffer(cmd_request->bounce_sgl,
cmd_request->bounce_sgl_count);
- ret = SCSI_MLQUEUE_DEVICE_BUSY;
- goto queue_error;
- }
+ ret = SCSI_MLQUEUE_DEVICE_BUSY;
+ goto queue_error;
}
return 0;
@@ -1441,6 +1462,7 @@
.bios_param = storvsc_get_chs,
.queuecommand = storvsc_queuecommand,
.eh_host_reset_handler = storvsc_host_reset_handler,
+ .eh_timed_out = storvsc_eh_timed_out,
.slave_alloc = storvsc_device_alloc,
.slave_destroy = storvsc_device_destroy,
.slave_configure = storvsc_device_configure,
@@ -1454,6 +1476,7 @@
.use_clustering = DISABLE_CLUSTERING,
/* Make sure we dont get a sg segment crosses a page boundary */
.dma_boundary = PAGE_SIZE-1,
+ .no_write_same = 1,
};
enum {
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index d92fe40..6b349e3 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3000,7 +3000,11 @@
if ((target == -1 || cp->target == target) &&
(lun == -1 || cp->lun == lun) &&
(task == -1 || cp->tag == task)) {
+#ifdef SYM_OPT_HANDLE_DEVICE_QUEUEING
sym_set_cam_status(cp->cmd, DID_SOFT_ERROR);
+#else
+ sym_set_cam_status(cp->cmd, DID_REQUEUE);
+#endif
sym_remque(&cp->link_ccbq);
sym_insque_tail(&cp->link_ccbq, &np->comp_ccbq);
}
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 2168258..11f5326 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -270,6 +270,16 @@
virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd);
};
+static void virtscsi_poll_requests(struct virtio_scsi *vscsi)
+{
+ int i, num_vqs;
+
+ num_vqs = vscsi->num_queues;
+ for (i = 0; i < num_vqs; i++)
+ virtscsi_vq_done(vscsi, &vscsi->req_vqs[i],
+ virtscsi_complete_cmd);
+}
+
static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
{
struct virtio_scsi_cmd *cmd = buf;
@@ -288,6 +298,8 @@
virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free);
};
+static void virtscsi_handle_event(struct work_struct *work);
+
static int virtscsi_kick_event(struct virtio_scsi *vscsi,
struct virtio_scsi_event_node *event_node)
{
@@ -295,6 +307,7 @@
struct scatterlist sg;
unsigned long flags;
+ INIT_WORK(&event_node->work, virtscsi_handle_event);
sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));
spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
@@ -412,7 +425,6 @@
{
struct virtio_scsi_event_node *event_node = buf;
- INIT_WORK(&event_node->work, virtscsi_handle_event);
schedule_work(&event_node->work);
}
@@ -602,6 +614,18 @@
cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED)
ret = SUCCESS;
+ /*
+ * The spec guarantees that all requests related to the TMF have
+ * been completed, but the callback might not have run yet if
+ * we're using independent interrupts (e.g. MSI). Poll the
+ * virtqueues once.
+ *
+ * In the abort case, sc->scsi_done will do nothing, because
+ * the block layer must have detected a timeout and as a result
+ * REQ_ATOM_COMPLETE has been set.
+ */
+ virtscsi_poll_requests(vscsi);
+
out:
mempool_free(cmd, virtscsi_cmd_pool);
return ret;
@@ -751,8 +775,12 @@
vscsi->affinity_hint_set = true;
} else {
- for (i = 0; i < vscsi->num_queues - VIRTIO_SCSI_VQ_BASE; i++)
+ for (i = 0; i < vscsi->num_queues; i++) {
+ if (!vscsi->req_vqs[i].vq)
+ continue;
+
virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
+ }
vscsi->affinity_hint_set = false;
}
@@ -957,6 +985,10 @@
#ifdef CONFIG_PM
static int virtscsi_freeze(struct virtio_device *vdev)
{
+ struct Scsi_Host *sh = virtio_scsi_host(vdev);
+ struct virtio_scsi *vscsi = shost_priv(sh);
+
+ unregister_hotcpu_notifier(&vscsi->nb);
virtscsi_remove_vqs(vdev);
return 0;
}
@@ -965,8 +997,17 @@
{
struct Scsi_Host *sh = virtio_scsi_host(vdev);
struct virtio_scsi *vscsi = shost_priv(sh);
+ int err;
- return virtscsi_init(vdev, vscsi);
+ err = virtscsi_init(vdev, vscsi);
+ if (err)
+ return err;
+
+ err = register_hotcpu_notifier(&vscsi->nb);
+ if (err)
+ vdev->config->del_vqs(vdev);
+
+ return err;
}
#endif
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index e504b76..23f1ba6 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -132,9 +132,9 @@
flags = GPIOF_DIR_OUT;
if (spi->mode & SPI_CS_HIGH)
- flags |= GPIOF_INIT_HIGH;
- else
flags |= GPIOF_INIT_LOW;
+ else
+ flags |= GPIOF_INIT_HIGH;
status = gpio_request_one(cdata->gpio, flags,
dev_name(&spi->dev));
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index a4ec5f4..cd716f4 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -180,8 +180,6 @@
transfer_list);
}
- len -= prepend_len;
-
init_completion(&bs->done);
/* Fill in the Message control register */
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 50b13c9..df0aacc 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -610,7 +610,7 @@
else
buf = (void *)t->tx_buf;
t->tx_dma = dma_map_single(&spi->dev, buf,
- t->len, DMA_FROM_DEVICE);
+ t->len, DMA_TO_DEVICE);
if (!t->tx_dma) {
ret = -EFAULT;
goto err_tx_map;
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index b9f0192..1389fef 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,7 +89,13 @@
static void mid_spi_dma_exit(struct dw_spi *dws)
{
+ if (!dws->dma_inited)
+ return;
+
+ dmaengine_terminate_all(dws->txchan);
dma_release_channel(dws->txchan);
+
+ dmaengine_terminate_all(dws->rxchan);
dma_release_channel(dws->rxchan);
}
@@ -136,7 +142,7 @@
txconf.dst_addr = dws->dma_addr;
txconf.dst_maxburst = LNW_DMA_MSIZE_16;
txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+ txconf.dst_addr_width = dws->dma_width;
txconf.device_fc = false;
txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
@@ -159,7 +165,7 @@
rxconf.src_addr = dws->dma_addr;
rxconf.src_maxburst = LNW_DMA_MSIZE_16;
rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+ rxconf.src_addr_width = dws->dma_width;
rxconf.device_fc = false;
rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
@@ -216,7 +222,6 @@
iounmap(clk_reg);
dws->num_cs = 16;
- dws->fifo_len = 40; /* FIFO has 40 words buffer */
#ifdef CONFIG_SPI_DW_MID_DMA
dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL);
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index c1abc06..137a4de 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -394,9 +394,6 @@
chip = dws->cur_chip;
spi = message->spi;
- if (unlikely(!chip->clk_div))
- chip->clk_div = dws->max_freq / chip->speed_hz;
-
if (message->state == ERROR_STATE) {
message->status = -EIO;
goto early_exit;
@@ -438,7 +435,7 @@
if (transfer->speed_hz) {
speed = chip->speed_hz;
- if (transfer->speed_hz != speed) {
+ if ((transfer->speed_hz != speed) || (!chip->clk_div)) {
speed = transfer->speed_hz;
if (speed > dws->max_freq) {
printk(KERN_ERR "MRST SPI0: unsupported"
@@ -677,7 +674,6 @@
dev_err(&spi->dev, "No max speed HZ parameter\n");
return -EINVAL;
}
- chip->speed_hz = spi->max_speed_hz;
chip->tmode = 0; /* Tx & Rx */
/* Default SPI mode is SCPOL = 0, SCPH = 0 */
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 86d2158..798729e 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -136,6 +136,7 @@
void __iomem *base;
unsigned long phys;
int word_len;
+ u16 mode;
struct list_head node;
/* Context save and restore shadow register */
u32 chconf0;
@@ -801,6 +802,8 @@
mcspi_write_chconf0(spi, l);
+ cs->mode = spi->mode;
+
dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n",
OMAP2_MCSPI_MAX_FREQ >> div,
(spi->mode & SPI_CPHA) ? "trailing" : "leading",
@@ -871,6 +874,7 @@
return -ENOMEM;
cs->base = mcspi->base + spi->chip_select * 0x14;
cs->phys = mcspi->phys + spi->chip_select * 0x14;
+ cs->mode = 0;
cs->chconf0 = 0;
spi->controller_state = cs;
/* Link this to context save list */
@@ -1043,6 +1047,16 @@
mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
}
+ /*
+ * The slave driver could have changed spi->mode in which case
+ * it will be different from cs->mode (the current hardware setup).
+ * If so, set par_override (even though its not a parity issue) so
+ * omap2_mcspi_setup_transfer will be called to configure the hardware
+ * with the correct mode on the first iteration of the loop below.
+ */
+ if (spi->mode != cs->mode)
+ par_override = 1;
+
omap2_mcspi_set_enable(spi, 0);
m->status = status;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 66a5f82..183aa80 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -403,8 +403,6 @@
struct resource *r;
unsigned long tclk_hz;
int status = 0;
- const u32 *iprop;
- int size;
master = spi_alloc_master(&pdev->dev, sizeof *spi);
if (master == NULL) {
@@ -415,10 +413,10 @@
if (pdev->id != -1)
master->bus_num = pdev->id;
if (pdev->dev.of_node) {
- iprop = of_get_property(pdev->dev.of_node, "cell-index",
- &size);
- if (iprop && size == sizeof(*iprop))
- master->bus_num = *iprop;
+ u32 cell_index;
+ if (!of_property_read_u32(pdev->dev.of_node, "cell-index",
+ &cell_index))
+ master->bus_num = cell_index;
}
/* we support only mode 0, and no options */
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 371cc66f..a6f0878 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -508,12 +508,12 @@
pl022->cur_msg = NULL;
pl022->cur_transfer = NULL;
pl022->cur_chip = NULL;
- spi_finalize_current_message(pl022->master);
/* disable the SPI/SSP operation */
writew((readw(SSP_CR1(pl022->virtbase)) &
(~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase));
+ spi_finalize_current_message(pl022->master);
}
/**
@@ -1080,7 +1080,7 @@
pl022->sgt_tx.nents, DMA_TO_DEVICE);
err_tx_sgmap:
dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl,
- pl022->sgt_tx.nents, DMA_FROM_DEVICE);
+ pl022->sgt_rx.nents, DMA_FROM_DEVICE);
err_rx_sgmap:
sg_free_table(&pl022->sgt_tx);
err_alloc_tx_sg:
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 48b396f..cc42ee5 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -393,8 +393,8 @@
cs_deassert(drv_data);
}
- spi_finalize_current_message(drv_data->master);
drv_data->cur_chip = NULL;
+ spi_finalize_current_message(drv_data->master);
}
static void reset_sccr1(struct driver_data *drv_data)
@@ -1324,7 +1324,9 @@
if (status != 0)
return status;
write_SSCR0(0, drv_data->ioaddr);
- clk_disable_unprepare(ssp->clk);
+
+ if (!pm_runtime_suspended(dev))
+ clk_disable_unprepare(ssp->clk);
return 0;
}
@@ -1338,7 +1340,8 @@
pxa2xx_spi_dma_resume(drv_data);
/* Enable the SSP clock */
- clk_prepare_enable(ssp->clk);
+ if (!pm_runtime_suspended(dev))
+ clk_prepare_enable(ssp->clk);
/* Start the queue running */
status = spi_master_resume(drv_data->master);
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 911e9e0..a08f923 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -243,7 +243,10 @@
k_tmp->len = u_tmp->len;
total += k_tmp->len;
- if (total > bufsiz) {
+ /* Check total length of transfers. Also check each
+ * transfer length to avoid arithmetic overflow.
+ */
+ if (total > bufsiz || k_tmp->len > bufsiz) {
status = -EMSGSIZE;
goto done;
}
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index aefe820..25c8bff 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -72,10 +72,6 @@
source "drivers/staging/iio/Kconfig"
-source "drivers/staging/zsmalloc/Kconfig"
-
-source "drivers/staging/zram/Kconfig"
-
source "drivers/staging/wlags49_h2/Kconfig"
source "drivers/staging/wlags49_h25/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 415772e..f9d86a4 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -30,8 +30,6 @@
obj-$(CONFIG_VME_BUS) += vme/
obj-$(CONFIG_DX_SEP) += sep/
obj-$(CONFIG_IIO) += iio/
-obj-$(CONFIG_ZRAM) += zram/
-obj-$(CONFIG_ZSMALLOC) += zsmalloc/
obj-$(CONFIG_WLAGS49_H2) += wlags49_h2/
obj-$(CONFIG_WLAGS49_H25) += wlags49_h25/
obj-$(CONFIG_FB_SM7XX) += sm7xxfb/
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index 1567ac2..0fce5fc 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -2902,7 +2902,7 @@
refs++;
if (!ref->death)
- goto out;
+ continue;
death++;
@@ -2915,7 +2915,6 @@
BUG();
}
-out:
binder_debug(BINDER_DEBUG_DEAD_BINDER,
"node %d now dead, refs %d, death %d\n",
node->debug_id, refs, death);
diff --git a/drivers/staging/android/logger.c b/drivers/staging/android/logger.c
index 9bd8747..34519ea 100644
--- a/drivers/staging/android/logger.c
+++ b/drivers/staging/android/logger.c
@@ -469,7 +469,7 @@
unsigned long nr_segs, loff_t ppos)
{
struct logger_log *log = file_get_log(iocb->ki_filp);
- size_t orig = log->w_off;
+ size_t orig;
struct logger_entry header;
struct timespec now;
ssize_t ret = 0;
@@ -490,6 +490,8 @@
mutex_lock(&log->mutex);
+ orig = log->w_off;
+
/*
* Fix up any readers, pulling them forward to the first readable
* entry after (what will be) the new write offset. We do this now
diff --git a/drivers/staging/bcm/Bcmchar.c b/drivers/staging/bcm/Bcmchar.c
index 35641e5..8fa64d9 100644
--- a/drivers/staging/bcm/Bcmchar.c
+++ b/drivers/staging/bcm/Bcmchar.c
@@ -1960,6 +1960,7 @@
BCM_DEBUG_PRINT(Adapter, DBG_TYPE_OTHERS, OSAL_DBG, DBG_LVL_ALL, "Called IOCTL_BCM_GET_DEVICE_DRIVER_INFO\n");
+ memset(&DevInfo, 0, sizeof(DevInfo));
DevInfo.MaxRDMBufferSize = BUFFER_4K;
DevInfo.u32DSDStartOffset = EEPROM_CALPARAM_START;
DevInfo.u32RxAlignmentCorrection = 0;
diff --git a/drivers/staging/comedi/comedi_compat32.c b/drivers/staging/comedi/comedi_compat32.c
index ad208cd..83bcf96 100644
--- a/drivers/staging/comedi/comedi_compat32.c
+++ b/drivers/staging/comedi/comedi_compat32.c
@@ -270,7 +270,7 @@
{
struct comedi_cmd __user *cmd;
struct comedi32_cmd_struct __user *cmd32;
- int rc;
+ int rc, err;
cmd32 = compat_ptr(arg);
cmd = compat_alloc_user_space(sizeof(*cmd));
@@ -279,7 +279,15 @@
if (rc)
return rc;
- return translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd);
+ rc = translated_ioctl(file, COMEDI_CMD, (unsigned long)cmd);
+ if (rc == -EAGAIN) {
+ /* Special case: copy cmd back to user. */
+ err = put_compat_cmd(cmd32, cmd);
+ if (err)
+ rc = err;
+ }
+
+ return rc;
}
/* Handle 32-bit COMEDI_CMDTEST ioctl. */
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 924c54c..0ae406a 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -1401,22 +1401,19 @@
DPRINTK("subdevice busy\n");
return -EBUSY;
}
- s->busy = file;
/* make sure channel/gain list isn't too long */
if (cmd.chanlist_len > s->len_chanlist) {
DPRINTK("channel/gain list too long %u > %d\n",
cmd.chanlist_len, s->len_chanlist);
- ret = -EINVAL;
- goto cleanup;
+ return -EINVAL;
}
/* make sure channel/gain list isn't too short */
if (cmd.chanlist_len < 1) {
DPRINTK("channel/gain list too short %u < 1\n",
cmd.chanlist_len);
- ret = -EINVAL;
- goto cleanup;
+ return -EINVAL;
}
async->cmd = cmd;
@@ -1426,8 +1423,7 @@
kmalloc(async->cmd.chanlist_len * sizeof(int), GFP_KERNEL);
if (!async->cmd.chanlist) {
DPRINTK("allocation failed\n");
- ret = -ENOMEM;
- goto cleanup;
+ return -ENOMEM;
}
if (copy_from_user(async->cmd.chanlist, user_chanlist,
@@ -1479,6 +1475,9 @@
comedi_set_subdevice_runflags(s, ~0, SRF_USER | SRF_RUNNING);
+ /* set s->busy _after_ setting SRF_RUNNING flag to avoid race with
+ * comedi_read() or comedi_write() */
+ s->busy = file;
ret = s->do_cmd(dev, s);
if (ret == 0)
return 0;
@@ -1693,6 +1692,7 @@
void *file)
{
struct comedi_subdevice *s;
+ int ret;
if (arg >= dev->n_subdevices)
return -EINVAL;
@@ -1709,7 +1709,11 @@
if (s->busy != file)
return -EBUSY;
- return do_cancel(dev, s);
+ ret = do_cancel(dev, s);
+ if (comedi_get_subdevice_runflags(s) & SRF_USER)
+ wake_up_interruptible(&s->async->wait_head);
+
+ return ret;
}
/*
@@ -2041,11 +2045,13 @@
if (!comedi_is_subdevice_running(s)) {
if (count == 0) {
+ mutex_lock(&dev->mutex);
if (comedi_is_subdevice_in_error(s))
retval = -EPIPE;
else
retval = 0;
do_become_nonbusy(dev, s);
+ mutex_unlock(&dev->mutex);
}
break;
}
@@ -2144,11 +2150,13 @@
if (n == 0) {
if (!comedi_is_subdevice_running(s)) {
+ mutex_lock(&dev->mutex);
do_become_nonbusy(dev, s);
if (comedi_is_subdevice_in_error(s))
retval = -EPIPE;
else
retval = 0;
+ mutex_unlock(&dev->mutex);
break;
}
if (file->f_flags & O_NONBLOCK) {
@@ -2186,9 +2194,11 @@
buf += n;
break; /* makes device work like a pipe */
}
- if (comedi_is_subdevice_idle(s) &&
- async->buf_read_count - async->buf_write_count == 0) {
- do_become_nonbusy(dev, s);
+ if (comedi_is_subdevice_idle(s)) {
+ mutex_lock(&dev->mutex);
+ if (async->buf_read_count - async->buf_write_count == 0)
+ do_become_nonbusy(dev, s);
+ mutex_unlock(&dev->mutex);
}
set_current_state(TASK_RUNNING);
remove_wait_queue(&async->wait_head, &wait);
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index 06d190f..4a2b042 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -464,7 +464,7 @@
ret = comedi_device_postconfig(dev);
if (ret < 0) {
comedi_device_detach(dev);
- module_put(dev->driver->module);
+ module_put(driv->module);
}
/* On success, the driver module count has been incremented. */
return ret;
diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c
index 76dec96..e54031c 100644
--- a/drivers/staging/comedi/drivers/8255_pci.c
+++ b/drivers/staging/comedi/drivers/8255_pci.c
@@ -59,6 +59,7 @@
#include "../comedidev.h"
#include "8255.h"
+#include "mite.h"
enum pci_8255_boardid {
BOARD_ADLINK_PCI7224,
@@ -66,7 +67,8 @@
BOARD_ADLINK_PCI7296,
BOARD_CB_PCIDIO24,
BOARD_CB_PCIDIO24H,
- BOARD_CB_PCIDIO48H,
+ BOARD_CB_PCIDIO48H_OLD,
+ BOARD_CB_PCIDIO48H_NEW,
BOARD_CB_PCIDIO96H,
BOARD_NI_PCIDIO96,
BOARD_NI_PCIDIO96B,
@@ -81,6 +83,7 @@
const char *name;
int dio_badr;
int n_8255;
+ unsigned int has_mite:1;
};
static const struct pci_8255_boardinfo pci_8255_boards[] = {
@@ -109,11 +112,16 @@
.dio_badr = 2,
.n_8255 = 1,
},
- [BOARD_CB_PCIDIO48H] = {
+ [BOARD_CB_PCIDIO48H_OLD] = {
.name = "cb_pci-dio48h",
.dio_badr = 1,
.n_8255 = 2,
},
+ [BOARD_CB_PCIDIO48H_NEW] = {
+ .name = "cb_pci-dio48h",
+ .dio_badr = 2,
+ .n_8255 = 2,
+ },
[BOARD_CB_PCIDIO96H] = {
.name = "cb_pci-dio96h",
.dio_badr = 2,
@@ -123,36 +131,43 @@
.name = "ni_pci-dio-96",
.dio_badr = 1,
.n_8255 = 4,
+ .has_mite = 1,
},
[BOARD_NI_PCIDIO96B] = {
.name = "ni_pci-dio-96b",
.dio_badr = 1,
.n_8255 = 4,
+ .has_mite = 1,
},
[BOARD_NI_PXI6508] = {
.name = "ni_pxi-6508",
.dio_badr = 1,
.n_8255 = 4,
+ .has_mite = 1,
},
[BOARD_NI_PCI6503] = {
.name = "ni_pci-6503",
.dio_badr = 1,
.n_8255 = 1,
+ .has_mite = 1,
},
[BOARD_NI_PCI6503B] = {
.name = "ni_pci-6503b",
.dio_badr = 1,
.n_8255 = 1,
+ .has_mite = 1,
},
[BOARD_NI_PCI6503X] = {
.name = "ni_pci-6503x",
.dio_badr = 1,
.n_8255 = 1,
+ .has_mite = 1,
},
[BOARD_NI_PXI_6503] = {
.name = "ni_pxi-6503",
.dio_badr = 1,
.n_8255 = 1,
+ .has_mite = 1,
},
};
@@ -160,6 +175,25 @@
void __iomem *mmio_base;
};
+static int pci_8255_mite_init(struct pci_dev *pcidev)
+{
+ void __iomem *mite_base;
+ u32 main_phys_addr;
+
+ /* ioremap the MITE registers (BAR 0) temporarily */
+ mite_base = pci_ioremap_bar(pcidev, 0);
+ if (!mite_base)
+ return -ENOMEM;
+
+ /* set data window to main registers (BAR 1) */
+ main_phys_addr = pci_resource_start(pcidev, 1);
+ writel(main_phys_addr | WENAB, mite_base + MITE_IODWBSR);
+
+ /* finished with MITE registers */
+ iounmap(mite_base);
+ return 0;
+}
+
static int pci_8255_mmio(int dir, int port, int data, unsigned long iobase)
{
void __iomem *mmio_base = (void __iomem *)iobase;
@@ -199,6 +233,12 @@
if (ret)
return ret;
+ if (board->has_mite) {
+ ret = pci_8255_mite_init(pcidev);
+ if (ret)
+ return ret;
+ }
+
is_mmio = (pci_resource_flags(pcidev, board->dio_badr) &
IORESOURCE_MEM) != 0;
if (is_mmio) {
@@ -270,7 +310,10 @@
{ PCI_VDEVICE(ADLINK, 0x7296), BOARD_ADLINK_PCI7296 },
{ PCI_VDEVICE(CB, 0x0028), BOARD_CB_PCIDIO24 },
{ PCI_VDEVICE(CB, 0x0014), BOARD_CB_PCIDIO24H },
- { PCI_VDEVICE(CB, 0x000b), BOARD_CB_PCIDIO48H },
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, 0x0000, 0x0000),
+ .driver_data = BOARD_CB_PCIDIO48H_OLD },
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_CB, 0x000b, PCI_VENDOR_ID_CB, 0x000b),
+ .driver_data = BOARD_CB_PCIDIO48H_NEW },
{ PCI_VDEVICE(CB, 0x0017), BOARD_CB_PCIDIO96H },
{ PCI_VDEVICE(NI, 0x0160), BOARD_NI_PCIDIO96 },
{ PCI_VDEVICE(NI, 0x1630), BOARD_NI_PCIDIO96B },
diff --git a/drivers/staging/comedi/drivers/addi_apci_1032.c b/drivers/staging/comedi/drivers/addi_apci_1032.c
index 3d4878f..d919a98 100644
--- a/drivers/staging/comedi/drivers/addi_apci_1032.c
+++ b/drivers/staging/comedi/drivers/addi_apci_1032.c
@@ -332,8 +332,8 @@
s = &dev->subdevices[1];
if (dev->irq) {
dev->read_subdev = s;
- s->type = COMEDI_SUBD_DI | SDF_CMD_READ;
- s->subdev_flags = SDF_READABLE;
+ s->type = COMEDI_SUBD_DI;
+ s->subdev_flags = SDF_READABLE | SDF_CMD_READ;
s->n_chan = 1;
s->maxdata = 1;
s->range_table = &range_digital;
diff --git a/drivers/staging/comedi/drivers/adl_pci9111.c b/drivers/staging/comedi/drivers/adl_pci9111.c
index 6247fdc..71043a1 100644
--- a/drivers/staging/comedi/drivers/adl_pci9111.c
+++ b/drivers/staging/comedi/drivers/adl_pci9111.c
@@ -873,7 +873,7 @@
pci9111_reset(dev);
if (pcidev->irq > 0) {
- ret = request_irq(dev->irq, pci9111_interrupt,
+ ret = request_irq(pcidev->irq, pci9111_interrupt,
IRQF_SHARED, dev->board_name, dev);
if (ret)
return ret;
diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c
index f847bbc..acb66a9 100644
--- a/drivers/staging/comedi/drivers/adv_pci1710.c
+++ b/drivers/staging/comedi/drivers/adv_pci1710.c
@@ -489,6 +489,7 @@
struct comedi_insn *insn, unsigned int *data)
{
struct pci1710_private *devpriv = dev->private;
+ unsigned int val;
int n, chan, range, ofs;
chan = CR_CHAN(insn->chanspec);
@@ -504,11 +505,14 @@
outw(devpriv->da_ranges, dev->iobase + PCI171x_DAREF);
ofs = PCI171x_DA1;
}
+ val = devpriv->ao_data[chan];
- for (n = 0; n < insn->n; n++)
- outw(data[n], dev->iobase + ofs);
+ for (n = 0; n < insn->n; n++) {
+ val = data[n];
+ outw(val, dev->iobase + ofs);
+ }
- devpriv->ao_data[chan] = data[n];
+ devpriv->ao_data[chan] = val;
return n;
@@ -678,6 +682,7 @@
struct comedi_insn *insn, unsigned int *data)
{
struct pci1710_private *devpriv = dev->private;
+ unsigned int val;
int n, rangereg, chan;
chan = CR_CHAN(insn->chanspec);
@@ -687,13 +692,15 @@
outb(rangereg, dev->iobase + PCI1720_RANGE);
devpriv->da_ranges = rangereg;
}
+ val = devpriv->ao_data[chan];
for (n = 0; n < insn->n; n++) {
- outw(data[n], dev->iobase + PCI1720_DA0 + (chan << 1));
+ val = data[n];
+ outw(val, dev->iobase + PCI1720_DA0 + (chan << 1));
outb(0, dev->iobase + PCI1720_SYNCOUT); /* update outputs */
}
- devpriv->ao_data[chan] = data[n];
+ devpriv->ao_data[chan] = val;
return n;
}
diff --git a/drivers/staging/comedi/drivers/amplc_pc263.c b/drivers/staging/comedi/drivers/amplc_pc263.c
index 94a752d..0d88e62 100644
--- a/drivers/staging/comedi/drivers/amplc_pc263.c
+++ b/drivers/staging/comedi/drivers/amplc_pc263.c
@@ -72,6 +72,9 @@
outb(s->state & 0xFF, dev->iobase);
outb(s->state >> 8, dev->iobase + 1);
}
+
+ data[1] = s->state;
+
return insn->n;
}
diff --git a/drivers/staging/comedi/drivers/amplc_pci263.c b/drivers/staging/comedi/drivers/amplc_pci263.c
index 8b57533..9c53199 100644
--- a/drivers/staging/comedi/drivers/amplc_pci263.c
+++ b/drivers/staging/comedi/drivers/amplc_pci263.c
@@ -59,6 +59,9 @@
outb(s->state & 0xFF, dev->iobase);
outb(s->state >> 8, dev->iobase + 1);
}
+
+ data[1] = s->state;
+
return insn->n;
}
diff --git a/drivers/staging/comedi/drivers/cb_pcidas64.c b/drivers/staging/comedi/drivers/cb_pcidas64.c
index c3e5495..4220a44 100644
--- a/drivers/staging/comedi/drivers/cb_pcidas64.c
+++ b/drivers/staging/comedi/drivers/cb_pcidas64.c
@@ -455,6 +455,29 @@
}
};
+static const uint8_t ai_range_code_64xx[8] = {
+ 0x0, 0x1, 0x2, 0x3, /* bipolar 10, 5, 2,5, 1.25 */
+ 0x8, 0x9, 0xa, 0xb /* unipolar 10, 5, 2.5, 1.25 */
+};
+
+/* analog input ranges for 64-Mx boards */
+static const struct comedi_lrange ai_ranges_64_mx = {
+ 7, {
+ BIP_RANGE(5),
+ BIP_RANGE(2.5),
+ BIP_RANGE(1.25),
+ BIP_RANGE(0.625),
+ UNI_RANGE(5),
+ UNI_RANGE(2.5),
+ UNI_RANGE(1.25)
+ }
+};
+
+static const uint8_t ai_range_code_64_mx[7] = {
+ 0x0, 0x1, 0x2, 0x3, /* bipolar 5, 2.5, 1.25, 0.625 */
+ 0x9, 0xa, 0xb /* unipolar 5, 2.5, 1.25 */
+};
+
/* analog input ranges for 60xx boards */
static const struct comedi_lrange ai_ranges_60xx = {
4,
@@ -466,6 +489,10 @@
}
};
+static const uint8_t ai_range_code_60xx[4] = {
+ 0x0, 0x1, 0x4, 0x7 /* bipolar 10, 5, 0.5, 0.05 */
+};
+
/* analog input ranges for 6030, etc boards */
static const struct comedi_lrange ai_ranges_6030 = {
14,
@@ -487,6 +514,11 @@
}
};
+static const uint8_t ai_range_code_6030[14] = {
+ 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, /* bip 10, 5, 2, 1, 0.5, 0.2, 0.1 */
+ 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* uni 10, 5, 2, 1, 0.5, 0.2, 0.1 */
+};
+
/* analog input ranges for 6052, etc boards */
static const struct comedi_lrange ai_ranges_6052 = {
15,
@@ -509,6 +541,11 @@
}
};
+static const uint8_t ai_range_code_6052[15] = {
+ 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, /* bipolar 10 ... 0.05 */
+ 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf /* unipolar 10 ... 0.1 */
+};
+
/* analog input ranges for 4020 board */
static const struct comedi_lrange ai_ranges_4020 = {
2,
@@ -616,6 +653,7 @@
int ai_bits; /* analog input resolution */
int ai_speed; /* fastest conversion period in ns */
const struct comedi_lrange *ai_range_table;
+ const uint8_t *ai_range_code;
int ao_nchan; /* number of analog out channels */
int ao_bits; /* analog output resolution */
int ao_scan_speed; /* analog output scan speed */
@@ -674,6 +712,7 @@
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
.ai_range_table = &ai_ranges_64xx,
+ .ai_range_code = ai_range_code_64xx,
.ao_range_table = &ao_ranges_64xx,
.ao_range_code = ao_range_code_64xx,
.ai_fifo = &ai_fifo_64xx,
@@ -689,6 +728,7 @@
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
.ai_range_table = &ai_ranges_64xx,
+ .ai_range_code = ai_range_code_64xx,
.ao_range_table = &ao_ranges_64xx,
.ao_range_code = ao_range_code_64xx,
.ai_fifo = &ai_fifo_64xx,
@@ -703,7 +743,8 @@
.ao_bits = 16,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ao_range_table = &ao_ranges_64xx,
.ao_range_code = ao_range_code_64xx,
.ai_fifo = &ai_fifo_64xx,
@@ -718,7 +759,8 @@
.ao_bits = 16,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ao_range_table = &ao_ranges_64xx,
.ao_range_code = ao_range_code_64xx,
.ai_fifo = &ai_fifo_64xx,
@@ -733,7 +775,8 @@
.ao_bits = 16,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ao_range_table = &ao_ranges_64xx,
.ao_range_code = ao_range_code_64xx,
.ai_fifo = &ai_fifo_64xx,
@@ -748,6 +791,7 @@
.ao_bits = 16,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -763,6 +807,7 @@
.ao_scan_speed = 100000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -777,6 +822,7 @@
.ao_scan_speed = 100000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -792,6 +838,7 @@
.ao_scan_speed = 100000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -807,6 +854,7 @@
.ao_scan_speed = 10000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6030,
+ .ai_range_code = ai_range_code_6030,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -822,6 +870,7 @@
.ao_scan_speed = 10000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6030,
+ .ai_range_code = ai_range_code_6030,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -835,6 +884,7 @@
.ao_nchan = 0,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6030,
+ .ai_range_code = ai_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
.has_8255 = 0,
},
@@ -846,6 +896,7 @@
.ao_nchan = 0,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6030,
+ .ai_range_code = ai_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
.has_8255 = 0,
},
@@ -858,6 +909,7 @@
.ao_scan_speed = 0,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
.has_8255 = 0,
},
@@ -871,6 +923,7 @@
.ao_scan_speed = 100000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -886,6 +939,7 @@
.ao_scan_speed = 100000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_60xx,
+ .ai_range_code = ai_range_code_60xx,
.ao_range_table = &range_bipolar10,
.ao_range_code = ao_range_code_60xx,
.ai_fifo = &ai_fifo_60xx,
@@ -901,6 +955,7 @@
.ao_scan_speed = 1000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6052,
+ .ai_range_code = ai_range_code_6052,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -916,6 +971,7 @@
.ao_scan_speed = 3333,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6052,
+ .ai_range_code = ai_range_code_6052,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -931,6 +987,7 @@
.ao_scan_speed = 1000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6052,
+ .ai_range_code = ai_range_code_6052,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -946,6 +1003,7 @@
.ao_scan_speed = 1000,
.layout = LAYOUT_60XX,
.ai_range_table = &ai_ranges_6052,
+ .ai_range_code = ai_range_code_6052,
.ao_range_table = &ao_ranges_6030,
.ao_range_code = ao_range_code_6030,
.ai_fifo = &ai_fifo_60xx,
@@ -980,6 +1038,7 @@
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
.ai_range_table = &ai_ranges_64xx,
+ .ai_range_code = ai_range_code_64xx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -991,7 +1050,8 @@
.ao_nchan = 0,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1003,7 +1063,8 @@
.ao_nchan = 0,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1015,7 +1076,8 @@
.ao_nchan = 0,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1027,7 +1089,8 @@
.ao_nchan = 2,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1039,7 +1102,8 @@
.ao_nchan = 2,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1051,7 +1115,8 @@
.ao_nchan = 2,
.ao_scan_speed = 10000,
.layout = LAYOUT_64XX,
- .ai_range_table = &ai_ranges_64xx,
+ .ai_range_table = &ai_ranges_64_mx,
+ .ai_range_code = ai_range_code_64_mx,
.ai_fifo = ai_fifo_64xx,
.has_8255 = 1,
},
@@ -1148,45 +1213,8 @@
unsigned int range_index)
{
const struct pcidas64_board *thisboard = comedi_board(dev);
- const struct comedi_krange *range =
- &thisboard->ai_range_table->range[range_index];
- unsigned int bits = 0;
- switch (range->max) {
- case 10000000:
- bits = 0x000;
- break;
- case 5000000:
- bits = 0x100;
- break;
- case 2000000:
- case 2500000:
- bits = 0x200;
- break;
- case 1000000:
- case 1250000:
- bits = 0x300;
- break;
- case 500000:
- bits = 0x400;
- break;
- case 200000:
- case 250000:
- bits = 0x500;
- break;
- case 100000:
- bits = 0x600;
- break;
- case 50000:
- bits = 0x700;
- break;
- default:
- comedi_error(dev, "bug! in ai_range_bits_6xxx");
- break;
- }
- if (range->min == 0)
- bits += 0x900;
- return bits;
+ return thisboard->ai_range_code[range_index] << 8;
}
static unsigned int hw_revision(const struct comedi_device *dev,
diff --git a/drivers/staging/comedi/drivers/dt282x.c b/drivers/staging/comedi/drivers/dt282x.c
index 90f2de9..f4c1e99 100644
--- a/drivers/staging/comedi/drivers/dt282x.c
+++ b/drivers/staging/comedi/drivers/dt282x.c
@@ -269,8 +269,9 @@
} \
udelay(5); \
} \
- if (_i) \
+ if (_i) { \
b \
+ } \
} while (0)
static int prep_ai_dma(struct comedi_device *dev, int chan, int size);
diff --git a/drivers/staging/comedi/drivers/ni_65xx.c b/drivers/staging/comedi/drivers/ni_65xx.c
index 3f71f0f..05eb6fe 100644
--- a/drivers/staging/comedi/drivers/ni_65xx.c
+++ b/drivers/staging/comedi/drivers/ni_65xx.c
@@ -383,28 +383,23 @@
{
const struct ni_65xx_board *board = comedi_board(dev);
struct ni_65xx_private *devpriv = dev->private;
- unsigned base_bitfield_channel;
- const unsigned max_ports_per_bitfield = 5;
+ int base_bitfield_channel;
unsigned read_bits = 0;
- unsigned j;
+ int last_port_offset = ni_65xx_port_by_channel(s->n_chan - 1);
+ int port_offset;
base_bitfield_channel = CR_CHAN(insn->chanspec);
- for (j = 0; j < max_ports_per_bitfield; ++j) {
- const unsigned port_offset =
- ni_65xx_port_by_channel(base_bitfield_channel) + j;
- const unsigned port =
- sprivate(s)->base_port + port_offset;
- unsigned base_port_channel;
+ for (port_offset = ni_65xx_port_by_channel(base_bitfield_channel);
+ port_offset <= last_port_offset; port_offset++) {
+ unsigned port = sprivate(s)->base_port + port_offset;
+ int base_port_channel = port_offset * ni_65xx_channels_per_port;
unsigned port_mask, port_data, port_read_bits;
- int bitshift;
- if (port >= ni_65xx_total_num_ports(board))
+ int bitshift = base_port_channel - base_bitfield_channel;
+
+ if (bitshift >= 32)
break;
- base_port_channel = port_offset * ni_65xx_channels_per_port;
port_mask = data[0];
port_data = data[1];
- bitshift = base_port_channel - base_bitfield_channel;
- if (bitshift >= 32 || bitshift <= -32)
- break;
if (bitshift > 0) {
port_mask >>= bitshift;
port_data >>= bitshift;
diff --git a/drivers/staging/comedi/drivers/ni_daq_700.c b/drivers/staging/comedi/drivers/ni_daq_700.c
index d067ef7..5e80d42 100644
--- a/drivers/staging/comedi/drivers/ni_daq_700.c
+++ b/drivers/staging/comedi/drivers/ni_daq_700.c
@@ -127,6 +127,8 @@
/* write channel to multiplexer */
/* set mask scan bit high to disable scanning */
outb(chan | 0x80, dev->iobase + CMD_R1);
+ /* mux needs 2us to really settle [Fred Brooks]. */
+ udelay(2);
/* convert n samples */
for (n = 0; n < insn->n; n++) {
diff --git a/drivers/staging/comedi/drivers/pcmuio.c b/drivers/staging/comedi/drivers/pcmuio.c
index 0c98e26..b5ed093 100644
--- a/drivers/staging/comedi/drivers/pcmuio.c
+++ b/drivers/staging/comedi/drivers/pcmuio.c
@@ -935,12 +935,13 @@
struct pcmuio_private *devpriv = dev->private;
int i;
- for (i = 0; i < MAX_ASICS; ++i) {
- if (devpriv->asics[i].irq)
- free_irq(devpriv->asics[i].irq, dev);
- }
- if (devpriv && devpriv->sprivs)
+ if (devpriv) {
+ for (i = 0; i < MAX_ASICS; ++i) {
+ if (devpriv->asics[i].irq)
+ free_irq(devpriv->asics[i].irq, dev);
+ }
kfree(devpriv->sprivs);
+ }
comedi_legacy_detach(dev);
}
diff --git a/drivers/staging/comedi/drivers/ssv_dnp.c b/drivers/staging/comedi/drivers/ssv_dnp.c
index a76df09..8c84dc0 100644
--- a/drivers/staging/comedi/drivers/ssv_dnp.c
+++ b/drivers/staging/comedi/drivers/ssv_dnp.c
@@ -87,11 +87,11 @@
/* on return, data[1] contains the value of the digital input lines. */
outb(PADR, CSCIR);
- data[0] = inb(CSCDR);
+ data[1] = inb(CSCDR);
outb(PBDR, CSCIR);
- data[0] += inb(CSCDR) << 8;
+ data[1] += inb(CSCDR) << 8;
outb(PCDR, CSCIR);
- data[0] += ((inb(CSCDR) & 0xF0) << 12);
+ data[1] += ((inb(CSCDR) & 0xF0) << 12);
return insn->n;
diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c
index 8dc97b3..b0cb2de 100644
--- a/drivers/staging/iio/adc/ad799x_core.c
+++ b/drivers/staging/iio/adc/ad799x_core.c
@@ -644,7 +644,8 @@
return 0;
error_free_irq:
- free_irq(client->irq, indio_dev);
+ if (client->irq > 0)
+ free_irq(client->irq, indio_dev);
error_cleanup_ring:
ad799x_ring_cleanup(indio_dev);
error_disable_reg:
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index 163c638..972a072 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -234,7 +234,6 @@
{
struct mxs_lradc *lradc = iio_priv(iio_dev);
int ret;
- unsigned long mask;
if (m != IIO_CHAN_INFO_RAW)
return -EINVAL;
@@ -243,12 +242,6 @@
if (chan->channel > LRADC_MAX_TOTAL_CHANS)
return -EINVAL;
- /* Validate the channel if it doesn't intersect with reserved chans. */
- bitmap_set(&mask, chan->channel, 1);
- ret = iio_validate_scan_mask_onehot(iio_dev, &mask);
- if (ret)
- return -EINVAL;
-
/*
* See if there is no buffered operation in progess. If there is, simply
* bail out. This can be improved to support both buffered and raw IO at
@@ -661,12 +654,13 @@
{
int ret;
struct iio_trigger *trig;
+ struct mxs_lradc *lradc = iio_priv(iio);
trig = iio_trigger_alloc("%s-dev%i", iio->name, iio->id);
if (trig == NULL)
return -ENOMEM;
- trig->dev.parent = iio->dev.parent;
+ trig->dev.parent = lradc->dev;
iio_trigger_set_drvdata(trig, iio);
trig->ops = &mxs_lradc_trigger_ops;
@@ -676,15 +670,17 @@
return ret;
}
- iio->trig = trig;
+ lradc->trig = trig;
return 0;
}
static void mxs_lradc_trigger_remove(struct iio_dev *iio)
{
- iio_trigger_unregister(iio->trig);
- iio_trigger_free(iio->trig);
+ struct mxs_lradc *lradc = iio_priv(iio);
+
+ iio_trigger_unregister(lradc->trig);
+ iio_trigger_free(lradc->trig);
}
static int mxs_lradc_buffer_preenable(struct iio_dev *iio)
diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c
index 6330af6..bc23d66 100644
--- a/drivers/staging/iio/impedance-analyzer/ad5933.c
+++ b/drivers/staging/iio/impedance-analyzer/ad5933.c
@@ -115,6 +115,7 @@
.channel = 0,
.info_mask_separate = BIT(IIO_CHAN_INFO_PROCESSED),
.address = AD5933_REG_TEMP_DATA,
+ .scan_index = -1,
.scan_type = {
.sign = 's',
.realbits = 14,
@@ -124,9 +125,7 @@
.type = IIO_VOLTAGE,
.indexed = 1,
.channel = 0,
- .extend_name = "real_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
- BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "real",
.address = AD5933_REG_REAL_DATA,
.scan_index = 0,
.scan_type = {
@@ -138,9 +137,7 @@
.type = IIO_VOLTAGE,
.indexed = 1,
.channel = 0,
- .extend_name = "imag_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) |
- BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "imag",
.address = AD5933_REG_IMAG_DATA,
.scan_index = 1,
.scan_type = {
@@ -746,14 +743,14 @@
indio_dev->name = id->name;
indio_dev->modes = INDIO_DIRECT_MODE;
indio_dev->channels = ad5933_channels;
- indio_dev->num_channels = 1; /* only register temp0_input */
+ indio_dev->num_channels = ARRAY_SIZE(ad5933_channels);
ret = ad5933_register_ring_funcs_and_init(indio_dev);
if (ret)
goto error_disable_reg;
- /* skip temp0_input, register in0_(real|imag)_raw */
- ret = iio_buffer_register(indio_dev, &ad5933_channels[1], 2);
+ ret = iio_buffer_register(indio_dev, ad5933_channels,
+ ARRAY_SIZE(ad5933_channels));
if (ret)
goto error_unreg_ring;
diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index c99f890..64c73ad 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -672,9 +672,13 @@
chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
chip->tsl2x7x_settings.prox_pulse_count;
chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
- chip->tsl2x7x_settings.prox_thres_low;
+ (chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+ chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+ (chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
- chip->tsl2x7x_settings.prox_thres_high;
+ (chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+ chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+ (chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
/* and make sure we're not already on */
if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
diff --git a/drivers/staging/iio/meter/ade7758.h b/drivers/staging/iio/meter/ade7758.h
index 0731820..e8c98cf 100644
--- a/drivers/staging/iio/meter/ade7758.h
+++ b/drivers/staging/iio/meter/ade7758.h
@@ -119,7 +119,6 @@
u8 *tx;
u8 *rx;
struct mutex buf_lock;
- const struct iio_chan_spec *ade7758_ring_channels;
struct spi_transfer ring_xfer[4];
struct spi_message ring_msg;
/*
diff --git a/drivers/staging/iio/meter/ade7758_core.c b/drivers/staging/iio/meter/ade7758_core.c
index 8f5bcfa..75d9fe6 100644
--- a/drivers/staging/iio/meter/ade7758_core.c
+++ b/drivers/staging/iio/meter/ade7758_core.c
@@ -648,9 +648,6 @@
.type = IIO_VOLTAGE,
.indexed = 1,
.channel = 0,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_A, AD7758_VOLTAGE),
.scan_index = 0,
.scan_type = {
@@ -662,9 +659,6 @@
.type = IIO_CURRENT,
.indexed = 1,
.channel = 0,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_A, AD7758_CURRENT),
.scan_index = 1,
.scan_type = {
@@ -676,9 +670,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 0,
- .extend_name = "apparent_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "apparent",
.address = AD7758_WT(AD7758_PHASE_A, AD7758_APP_PWR),
.scan_index = 2,
.scan_type = {
@@ -690,9 +682,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 0,
- .extend_name = "active_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "active",
.address = AD7758_WT(AD7758_PHASE_A, AD7758_ACT_PWR),
.scan_index = 3,
.scan_type = {
@@ -704,9 +694,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 0,
- .extend_name = "reactive_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "reactive",
.address = AD7758_WT(AD7758_PHASE_A, AD7758_REACT_PWR),
.scan_index = 4,
.scan_type = {
@@ -718,9 +706,6 @@
.type = IIO_VOLTAGE,
.indexed = 1,
.channel = 1,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_B, AD7758_VOLTAGE),
.scan_index = 5,
.scan_type = {
@@ -732,9 +717,6 @@
.type = IIO_CURRENT,
.indexed = 1,
.channel = 1,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_B, AD7758_CURRENT),
.scan_index = 6,
.scan_type = {
@@ -746,9 +728,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 1,
- .extend_name = "apparent_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "apparent",
.address = AD7758_WT(AD7758_PHASE_B, AD7758_APP_PWR),
.scan_index = 7,
.scan_type = {
@@ -760,9 +740,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 1,
- .extend_name = "active_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "active",
.address = AD7758_WT(AD7758_PHASE_B, AD7758_ACT_PWR),
.scan_index = 8,
.scan_type = {
@@ -774,9 +752,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 1,
- .extend_name = "reactive_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "reactive",
.address = AD7758_WT(AD7758_PHASE_B, AD7758_REACT_PWR),
.scan_index = 9,
.scan_type = {
@@ -788,9 +764,6 @@
.type = IIO_VOLTAGE,
.indexed = 1,
.channel = 2,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_C, AD7758_VOLTAGE),
.scan_index = 10,
.scan_type = {
@@ -802,9 +775,6 @@
.type = IIO_CURRENT,
.indexed = 1,
.channel = 2,
- .extend_name = "raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
.address = AD7758_WT(AD7758_PHASE_C, AD7758_CURRENT),
.scan_index = 11,
.scan_type = {
@@ -816,9 +786,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 2,
- .extend_name = "apparent_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "apparent",
.address = AD7758_WT(AD7758_PHASE_C, AD7758_APP_PWR),
.scan_index = 12,
.scan_type = {
@@ -830,9 +798,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 2,
- .extend_name = "active_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "active",
.address = AD7758_WT(AD7758_PHASE_C, AD7758_ACT_PWR),
.scan_index = 13,
.scan_type = {
@@ -844,9 +810,7 @@
.type = IIO_POWER,
.indexed = 1,
.channel = 2,
- .extend_name = "reactive_raw",
- .info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
- .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE),
+ .extend_name = "reactive",
.address = AD7758_WT(AD7758_PHASE_C, AD7758_REACT_PWR),
.scan_index = 14,
.scan_type = {
@@ -890,13 +854,14 @@
goto error_free_rx;
}
st->us = spi;
- st->ade7758_ring_channels = &ade7758_channels[0];
mutex_init(&st->buf_lock);
indio_dev->name = spi->dev.driver->name;
indio_dev->dev.parent = &spi->dev;
indio_dev->info = &ade7758_info;
indio_dev->modes = INDIO_DIRECT_MODE;
+ indio_dev->channels = ade7758_channels;
+ indio_dev->num_channels = ARRAY_SIZE(ade7758_channels);
ret = ade7758_configure_ring(indio_dev);
if (ret)
diff --git a/drivers/staging/iio/meter/ade7758_ring.c b/drivers/staging/iio/meter/ade7758_ring.c
index b29e2d5..6a0ef97 100644
--- a/drivers/staging/iio/meter/ade7758_ring.c
+++ b/drivers/staging/iio/meter/ade7758_ring.c
@@ -89,11 +89,10 @@
**/
static int ade7758_ring_preenable(struct iio_dev *indio_dev)
{
- struct ade7758_state *st = iio_priv(indio_dev);
unsigned channel;
int ret;
- if (!bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
+ if (bitmap_empty(indio_dev->active_scan_mask, indio_dev->masklength))
return -EINVAL;
ret = iio_sw_buffer_preenable(indio_dev);
@@ -104,7 +103,7 @@
indio_dev->masklength);
ade7758_write_waveform_type(&indio_dev->dev,
- st->ade7758_ring_channels[channel].address);
+ indio_dev->channels[channel].address);
return 0;
}
diff --git a/drivers/staging/iio/meter/ade7758_trigger.c b/drivers/staging/iio/meter/ade7758_trigger.c
index 7a94ddd..8c4f289 100644
--- a/drivers/staging/iio/meter/ade7758_trigger.c
+++ b/drivers/staging/iio/meter/ade7758_trigger.c
@@ -85,7 +85,7 @@
ret = iio_trigger_register(st->trig);
/* select default trigger */
- indio_dev->trig = st->trig;
+ indio_dev->trig = iio_trigger_get(st->trig);
if (ret)
goto error_free_irq;
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 6455305..a532ca5 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -681,6 +681,7 @@
return i;
}
+EXPORT_SYMBOL_GPL(imx_drm_encoder_get_mux_id);
/*
* imx_drm_remove_encoder - remove an encoder
diff --git a/drivers/staging/line6/pcm.c b/drivers/staging/line6/pcm.c
index 02f77d7..a7856ba 100644
--- a/drivers/staging/line6/pcm.c
+++ b/drivers/staging/line6/pcm.c
@@ -385,8 +385,11 @@
*/
static void pcm_disconnect_substream(struct snd_pcm_substream *substream)
{
- if (substream->runtime && snd_pcm_running(substream))
+ if (substream->runtime && snd_pcm_running(substream)) {
+ snd_pcm_stream_lock_irq(substream);
snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED);
+ snd_pcm_stream_unlock_irq(substream);
+ }
}
/*
diff --git a/drivers/staging/media/lirc/lirc_zilog.c b/drivers/staging/media/lirc/lirc_zilog.c
index 11d5338..0feeaad 100644
--- a/drivers/staging/media/lirc/lirc_zilog.c
+++ b/drivers/staging/media/lirc/lirc_zilog.c
@@ -61,6 +61,9 @@
#include <media/lirc_dev.h>
#include <media/lirc.h>
+/* Max transfer size done by I2C transfer functions */
+#define MAX_XFER_SIZE 64
+
struct IR;
struct IR_rx {
@@ -941,7 +944,14 @@
schedule();
set_current_state(TASK_INTERRUPTIBLE);
} else {
- unsigned char buf[rbuf->chunk_size];
+ unsigned char buf[MAX_XFER_SIZE];
+
+ if (rbuf->chunk_size > sizeof(buf)) {
+ zilog_error("chunk_size is too big (%d)!\n",
+ rbuf->chunk_size);
+ ret = -EINVAL;
+ break;
+ }
m = lirc_buffer_read(rbuf, buf);
if (m == rbuf->chunk_size) {
ret = copy_to_user((void *)outbuf+written, buf,
diff --git a/drivers/staging/ozwpan/ozcdev.c b/drivers/staging/ozwpan/ozcdev.c
index 27d0666..224ccff 100644
--- a/drivers/staging/ozwpan/ozcdev.c
+++ b/drivers/staging/ozwpan/ozcdev.c
@@ -153,6 +153,9 @@
struct oz_app_hdr *app_hdr;
struct oz_serial_ctx *ctx;
+ if (count > sizeof(ei->data) - sizeof(*elt) - sizeof(*app_hdr))
+ return -EINVAL;
+
spin_lock_bh(&g_cdev.lock);
pd = g_cdev.active_pd;
if (pd)
diff --git a/drivers/staging/rtl8712/rtl871x_recv.c b/drivers/staging/rtl8712/rtl871x_recv.c
index 23ec684..274c359 100644
--- a/drivers/staging/rtl8712/rtl871x_recv.c
+++ b/drivers/staging/rtl8712/rtl871x_recv.c
@@ -254,7 +254,7 @@
struct sta_info *psta;
struct sta_priv *pstapriv;
union recv_frame *prtnframe;
- u16 ether_type = 0;
+ u16 ether_type;
pstapriv = &adapter->stapriv;
ptr = get_recvframe_data(precv_frame);
@@ -263,15 +263,14 @@
psta = r8712_get_stainfo(pstapriv, psta_addr);
auth_alg = adapter->securitypriv.AuthAlgrthm;
if (auth_alg == 2) {
+ /* get ether_type */
+ ptr = ptr + pfhdr->attrib.hdrlen + LLC_HEADER_SIZE;
+ memcpy(ðer_type, ptr, 2);
+ ether_type = ntohs((unsigned short)ether_type);
+
if ((psta != NULL) && (psta->ieee8021x_blocked)) {
/* blocked
* only accept EAPOL frame */
- prtnframe = precv_frame;
- /*get ether_type */
- ptr = ptr + pfhdr->attrib.hdrlen +
- pfhdr->attrib.iv_len + LLC_HEADER_SIZE;
- memcpy(ðer_type, ptr, 2);
- ether_type = ntohs((unsigned short)ether_type);
if (ether_type == 0x888e)
prtnframe = precv_frame;
else {
diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c
index c812d6c7..e3a005d 100644
--- a/drivers/staging/rtl8712/usb_intf.c
+++ b/drivers/staging/rtl8712/usb_intf.c
@@ -358,6 +358,10 @@
return (hex_to_bin(hch) << 4) | hex_to_bin(lch);
}
+static const struct device_type wlan_type = {
+ .name = "wlan",
+};
+
/*
* drv_init() - a device potentially for us
*
@@ -393,6 +397,7 @@
padapter->pusb_intf = pusb_intf;
usb_set_intfdata(pusb_intf, pnetdev);
SET_NETDEV_DEV(pnetdev, &pusb_intf->dev);
+ pnetdev->dev.type = &wlan_type;
/* step 2. */
padapter->dvobj_init = &r8712_usb_dvobj_init;
padapter->dvobj_deinit = &r8712_usb_dvobj_deinit;
diff --git a/drivers/staging/sb105x/sb_pci_mp.c b/drivers/staging/sb105x/sb_pci_mp.c
index cd94f6c..b90e96b 100644
--- a/drivers/staging/sb105x/sb_pci_mp.c
+++ b/drivers/staging/sb105x/sb_pci_mp.c
@@ -1063,7 +1063,7 @@
static int mp_get_count(struct sb_uart_state *state, struct serial_icounter_struct *icnt)
{
- struct serial_icounter_struct icount;
+ struct serial_icounter_struct icount = {};
struct sb_uart_icount cnow;
struct sb_uart_port *port = state->port;
diff --git a/drivers/staging/serqt_usb2/serqt_usb2.c b/drivers/staging/serqt_usb2/serqt_usb2.c
index 8a6e5ea..380d9d7 100644
--- a/drivers/staging/serqt_usb2/serqt_usb2.c
+++ b/drivers/staging/serqt_usb2/serqt_usb2.c
@@ -725,7 +725,7 @@
goto startup_error;
}
- switch (serial->dev->descriptor.idProduct) {
+ switch (le16_to_cpu(serial->dev->descriptor.idProduct)) {
case QUATECH_DSU100:
case QUATECH_QSU100:
case QUATECH_ESU100A:
diff --git a/drivers/staging/speakup/main.c b/drivers/staging/speakup/main.c
index 6c7b55c..e70a48e 100644
--- a/drivers/staging/speakup/main.c
+++ b/drivers/staging/speakup/main.c
@@ -2219,6 +2219,7 @@
unregister_keyboard_notifier(&keyboard_notifier_block);
unregister_vt_notifier(&vt_notifier_block);
speakup_unregister_devsynth();
+ speakup_cancel_paste();
del_timer(&cursor_timer);
kthread_stop(speakup_task);
speakup_task = NULL;
diff --git a/drivers/staging/speakup/selection.c b/drivers/staging/speakup/selection.c
index f0fb003..b935975 100644
--- a/drivers/staging/speakup/selection.c
+++ b/drivers/staging/speakup/selection.c
@@ -4,6 +4,9 @@
#include <linux/sched.h>
#include <linux/device.h> /* for dev_warn */
#include <linux/selection.h>
+#include <linux/workqueue.h>
+#include <linux/tty.h>
+#include <asm/cmpxchg.h>
#include "speakup.h"
@@ -121,31 +124,60 @@
return 0;
}
-/* TODO: move to some helper thread, probably. That'd fix having to check for
- * in_atomic(). */
-int speakup_paste_selection(struct tty_struct *tty)
+struct speakup_paste_work {
+ struct work_struct work;
+ struct tty_struct *tty;
+};
+
+static void __speakup_paste_selection(struct work_struct *work)
{
+ struct speakup_paste_work *spw =
+ container_of(work, struct speakup_paste_work, work);
+ struct tty_struct *tty = xchg(&spw->tty, NULL);
struct vc_data *vc = (struct vc_data *) tty->driver_data;
int pasted = 0, count;
+ struct tty_ldisc *ld;
DECLARE_WAITQUEUE(wait, current);
+
+ ld = tty_ldisc_ref_wait(tty);
+
+ /* FIXME: this is completely unsafe */
add_wait_queue(&vc->paste_wait, &wait);
while (sel_buffer && sel_buffer_lth > pasted) {
set_current_state(TASK_INTERRUPTIBLE);
if (test_bit(TTY_THROTTLED, &tty->flags)) {
- if (in_atomic())
- /* if we are in an interrupt handler, abort */
- break;
schedule();
continue;
}
count = sel_buffer_lth - pasted;
count = min_t(int, count, tty->receive_room);
- tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
- NULL, count);
+ ld->ops->receive_buf(tty, sel_buffer + pasted, NULL, count);
pasted += count;
}
remove_wait_queue(&vc->paste_wait, &wait);
current->state = TASK_RUNNING;
+
+ tty_ldisc_deref(ld);
+ tty_kref_put(tty);
+}
+
+static struct speakup_paste_work speakup_paste_work = {
+ .work = __WORK_INITIALIZER(speakup_paste_work.work,
+ __speakup_paste_selection)
+};
+
+int speakup_paste_selection(struct tty_struct *tty)
+{
+ if (cmpxchg(&speakup_paste_work.tty, NULL, tty) != NULL)
+ return -EBUSY;
+
+ tty_kref_get(tty);
+ schedule_work_on(WORK_CPU_UNBOUND, &speakup_paste_work.work);
return 0;
}
+void speakup_cancel_paste(void)
+{
+ cancel_work_sync(&speakup_paste_work.work);
+ tty_kref_put(speakup_paste_work.tty);
+}
diff --git a/drivers/staging/speakup/speakup.h b/drivers/staging/speakup/speakup.h
index 0126f71..74fe724 100644
--- a/drivers/staging/speakup/speakup.h
+++ b/drivers/staging/speakup/speakup.h
@@ -77,6 +77,7 @@
extern void speakup_clear_selection(void);
extern int speakup_set_selection(struct tty_struct *tty);
extern int speakup_paste_selection(struct tty_struct *tty);
+extern void speakup_cancel_paste(void);
extern void speakup_register_devsynth(void);
extern void speakup_unregister_devsynth(void);
extern void synth_write(const char *buf, size_t count);
diff --git a/drivers/staging/tidspbridge/Kconfig b/drivers/staging/tidspbridge/Kconfig
index 60848f1..f7deabc 100644
--- a/drivers/staging/tidspbridge/Kconfig
+++ b/drivers/staging/tidspbridge/Kconfig
@@ -4,7 +4,7 @@
menuconfig TIDSPBRIDGE
tristate "DSP Bridge driver"
- depends on ARCH_OMAP3 && !ARCH_MULTIPLATFORM
+ depends on ARCH_OMAP3 && !ARCH_MULTIPLATFORM && BROKEN
select OMAP_MBOX_FWK
help
DSP/BIOS Bridge is designed for platforms that contain a GPP and
diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c
index 2f084e18..a1aca44 100644
--- a/drivers/staging/tidspbridge/core/dsp-clock.c
+++ b/drivers/staging/tidspbridge/core/dsp-clock.c
@@ -226,7 +226,7 @@
case GPT_CLK:
status = omap_dm_timer_start(timer[clk_id - 1]);
break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
case MCBSP_CLK:
omap_mcbsp_request(MCBSP_ID(clk_id));
omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PAD_SRC);
@@ -302,7 +302,7 @@
case GPT_CLK:
status = omap_dm_timer_stop(timer[clk_id - 1]);
break;
-#ifdef CONFIG_OMAP_MCBSP
+#ifdef CONFIG_SND_OMAP_SOC_MCBSP
case MCBSP_CLK:
omap2_mcbsp_set_clks_src(MCBSP_ID(clk_id), MCBSP_CLKS_PRCM_SRC);
omap_mcbsp_free(MCBSP_ID(clk_id));
diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c
index f983915..3496a77 100644
--- a/drivers/staging/vt6655/bssdb.c
+++ b/drivers/staging/vt6655/bssdb.c
@@ -1026,7 +1026,7 @@
pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1));
}
- {
+ if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) {
pDevice->byReAssocCount++;
if ((pDevice->byReAssocCount > 10) && (pDevice->bLinkPass != true)) { //10 sec timeout
printk("Re-association timeout!!!\n");
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 08b250f..d170b6f 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -2434,6 +2434,7 @@
int handled = 0;
unsigned char byData = 0;
int ii = 0;
+ unsigned long flags;
// unsigned char byRSSI;
MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr);
@@ -2459,7 +2460,8 @@
handled = 1;
MACvIntDisable(pDevice->PortOffset);
- spin_lock_irq(&pDevice->lock);
+
+ spin_lock_irqsave(&pDevice->lock, flags);
//Make sure current page is 0
VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel);
@@ -2700,7 +2702,8 @@
MACvSelectPage1(pDevice->PortOffset);
}
- spin_unlock_irq(&pDevice->lock);
+ spin_unlock_irqrestore(&pDevice->lock, flags);
+
MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE);
return IRQ_RETVAL(handled);
diff --git a/drivers/staging/vt6655/rf.c b/drivers/staging/vt6655/rf.c
index 6948984..c2d6028 100644
--- a/drivers/staging/vt6655/rf.c
+++ b/drivers/staging/vt6655/rf.c
@@ -966,6 +966,7 @@
break;
case RATE_6M:
case RATE_9M:
+ case RATE_12M:
case RATE_18M:
byPwr = pDevice->abyOFDMPwrTbl[uCH];
if (pDevice->byRFType == RF_UW2452) {
diff --git a/drivers/staging/vt6656/baseband.c b/drivers/staging/vt6656/baseband.c
index 33fa767..5518533 100644
--- a/drivers/staging/vt6656/baseband.c
+++ b/drivers/staging/vt6656/baseband.c
@@ -941,6 +941,7 @@
u8 * pbyAgc;
u16 wLengthAgc;
u8 abyArray[256];
+ u8 data;
ntStatus = CONTROLnsRequestIn(pDevice,
MESSAGE_TYPE_READ,
@@ -1106,6 +1107,16 @@
ControlvWriteByte(pDevice,MESSAGE_REQUEST_BBREG,0x0D,0x01);
RFbRFTableDownload(pDevice);
+
+ /* Fix for TX USB resets from vendors driver */
+ CONTROLnsRequestIn(pDevice, MESSAGE_TYPE_READ, USB_REG4,
+ MESSAGE_REQUEST_MEM, sizeof(data), &data);
+
+ data |= 0x2;
+
+ CONTROLnsRequestOut(pDevice, MESSAGE_TYPE_WRITE, USB_REG4,
+ MESSAGE_REQUEST_MEM, sizeof(data), &data);
+
return true;//ntStatus;
}
@@ -1455,7 +1466,6 @@
if( bScanning )
{ // need Max sensitivity //RSSI -69, -70,....
- if(pDevice->byBBPreEDIndex == 0) break;
pDevice->byBBPreEDIndex = 0;
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x30); //CR206(0xCE)
@@ -1598,7 +1608,6 @@
if( bScanning )
{ // need Max sensitivity //RSSI -69, -70, ...
- if(pDevice->byBBPreEDIndex == 0) break;
pDevice->byBBPreEDIndex = 0;
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x24); //CR206(0xCE)
@@ -1750,7 +1759,6 @@
case RF_VT3342A0: //RobertYu:20060627, testing table
if( bScanning )
{ // need Max sensitivity //RSSI -67, -68, ...
- if(pDevice->byBBPreEDIndex == 0) break;
pDevice->byBBPreEDIndex = 0;
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xC9, 0x00); //CR201(0xC9)
ControlvWriteByte(pDevice, MESSAGE_REQUEST_BBREG, 0xCE, 0x38); //CR206(0xCE)
diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c
index 24291ae..0beb246 100644
--- a/drivers/staging/vt6656/card.c
+++ b/drivers/staging/vt6656/card.c
@@ -761,7 +761,7 @@
uBeaconInterval = wBeaconInterval * 1024;
// Next TBTT = ((local_current_TSF / beacon_interval) + 1 ) * beacon_interval
- uLowNextTBTT = ((qwTSF & 0xffffffffU) >> 10) << 10;
+ uLowNextTBTT = ((qwTSF & 0xffffffffULL) >> 10) << 10;
uLowRemain = (uLowNextTBTT) % uBeaconInterval;
uHighRemain = ((0x80000000 % uBeaconInterval) * 2 * (u32)(qwTSF >> 32))
% uBeaconInterval;
diff --git a/drivers/staging/vt6656/iwctl.c b/drivers/staging/vt6656/iwctl.c
index d0cf7d8a..8872e0f 100644
--- a/drivers/staging/vt6656/iwctl.c
+++ b/drivers/staging/vt6656/iwctl.c
@@ -1634,6 +1634,9 @@
if (pMgmt == NULL)
return -EFAULT;
+ if (!(pDevice->flags & DEVICE_FLAGS_OPENED))
+ return -ENODEV;
+
buf = kzalloc(sizeof(struct viawget_wpa_param), GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index 3a3fdc5..06b966c 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -1099,6 +1099,8 @@
memset(pMgmt->abyCurrBSSID, 0, 6);
pMgmt->eCurrState = WMAC_STATE_IDLE;
+ pDevice->flags &= ~DEVICE_FLAGS_OPENED;
+
device_free_tx_bufs(pDevice);
device_free_rx_bufs(pDevice);
device_free_int_bufs(pDevice);
@@ -1110,7 +1112,6 @@
usb_free_urb(pDevice->pInterruptURB);
BSSvClearNodeDBTable(pDevice, 0);
- pDevice->flags &=(~DEVICE_FLAGS_OPENED);
DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "device_close2 \n");
diff --git a/drivers/staging/vt6656/rndis.h b/drivers/staging/vt6656/rndis.h
index 5e07306..5cf5e73 100644
--- a/drivers/staging/vt6656/rndis.h
+++ b/drivers/staging/vt6656/rndis.h
@@ -66,6 +66,8 @@
#define VIAUSB20_PACKET_HEADER 0x04
+#define USB_REG4 0x604
+
typedef struct _CMD_MESSAGE
{
u8 byData[256];
diff --git a/drivers/staging/wlags49_h2/wl_priv.c b/drivers/staging/wlags49_h2/wl_priv.c
index c97e0e1..7e10dcd 100644
--- a/drivers/staging/wlags49_h2/wl_priv.c
+++ b/drivers/staging/wlags49_h2/wl_priv.c
@@ -570,6 +570,7 @@
ltv_t *pLtv;
bool_t ltvAllocated = FALSE;
ENCSTRCT sEncryption;
+ size_t len;
#ifdef USE_WDS
hcf_16 hcfPort = HCF_PORT_0;
@@ -686,7 +687,8 @@
break;
case CFG_CNF_OWN_NAME:
memset(lp->StationName, 0, sizeof(lp->StationName));
- memcpy((void *)lp->StationName, (void *)&pLtv->u.u8[2], (size_t)pLtv->u.u16[0]);
+ len = min_t(size_t, pLtv->u.u16[0], sizeof(lp->StationName));
+ strlcpy(lp->StationName, &pLtv->u.u8[2], len);
pLtv->u.u16[0] = CNV_INT_TO_LITTLE(pLtv->u.u16[0]);
break;
case CFG_CNF_LOAD_BALANCING:
@@ -1783,6 +1785,7 @@
{
struct wl_private *lp = wl_priv(dev);
unsigned long flags;
+ size_t len;
int ret = 0;
/*------------------------------------------------------------------------*/
@@ -1793,8 +1796,8 @@
wl_lock(lp, &flags);
memset(lp->StationName, 0, sizeof(lp->StationName));
-
- memcpy(lp->StationName, extra, wrqu->data.length);
+ len = min_t(size_t, wrqu->data.length, sizeof(lp->StationName));
+ strlcpy(lp->StationName, extra, len);
/* Commit the adapter parameters */
wl_apply(lp);
diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c
index dcceed2..81972fa 100644
--- a/drivers/staging/zcache/zcache-main.c
+++ b/drivers/staging/zcache/zcache-main.c
@@ -1811,10 +1811,12 @@
#else
if (*zcache_comp_name != '\0') {
ret = crypto_has_comp(zcache_comp_name, 0, 0);
- if (!ret)
+ if (!ret) {
pr_info("zcache: %s not supported\n",
zcache_comp_name);
- goto out;
+ ret = 1;
+ goto out;
+ }
}
if (!ret)
strcpy(zcache_comp_name, "lzo");
diff --git a/drivers/staging/zram/Kconfig b/drivers/staging/zram/Kconfig
deleted file mode 100644
index 983314c..0000000
--- a/drivers/staging/zram/Kconfig
+++ /dev/null
@@ -1,25 +0,0 @@
-config ZRAM
- tristate "Compressed RAM block device support"
- depends on BLOCK && SYSFS && ZSMALLOC
- select LZO_COMPRESS
- select LZO_DECOMPRESS
- default n
- help
- Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
- Pages written to these disks are compressed and stored in memory
- itself. These disks allow very fast I/O and compression provides
- good amounts of memory savings.
-
- It has several use cases, for example: /tmp storage, use as swap
- disks and maybe many more.
-
- See zram.txt for more information.
- Project home: <https://compcache.googlecode.com/>
-
-config ZRAM_DEBUG
- bool "Compressed RAM block device debug support"
- depends on ZRAM
- default n
- help
- This option adds additional debugging code to the compressed
- RAM block device driver.
diff --git a/drivers/staging/zram/Makefile b/drivers/staging/zram/Makefile
deleted file mode 100644
index 7f4a301..0000000
--- a/drivers/staging/zram/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zram-y := zram_drv.o zram_sysfs.o
-
-obj-$(CONFIG_ZRAM) += zram.o
diff --git a/drivers/staging/zram/zram.txt b/drivers/staging/zram/zram.txt
deleted file mode 100644
index 765d790..0000000
--- a/drivers/staging/zram/zram.txt
+++ /dev/null
@@ -1,77 +0,0 @@
-zram: Compressed RAM based block devices
-----------------------------------------
-
-Project home: http://compcache.googlecode.com/
-
-* Introduction
-
-The zram module creates RAM based block devices named /dev/zram<id>
-(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
-in memory itself. These disks allow very fast I/O and compression provides
-good amounts of memory savings. Some of the usecases include /tmp storage,
-use as swap disks, various caches under /var and maybe many more :)
-
-Statistics for individual zram devices are exported through sysfs nodes at
-/sys/block/zram<id>/
-
-* Usage
-
-Following shows a typical sequence of steps for using zram.
-
-1) Load Module:
- modprobe zram num_devices=4
- This creates 4 devices: /dev/zram{0,1,2,3}
- (num_devices parameter is optional. Default: 1)
-
-2) Set Disksize
- Set disk size by writing the value to sysfs node 'disksize'.
- The value can be either in bytes or you can use mem suffixes.
- Examples:
- # Initialize /dev/zram0 with 50MB disksize
- echo $((50*1024*1024)) > /sys/block/zram0/disksize
-
- # Using mem suffixes
- echo 256K > /sys/block/zram0/disksize
- echo 512M > /sys/block/zram0/disksize
- echo 1G > /sys/block/zram0/disksize
-
-3) Activate:
- mkswap /dev/zram0
- swapon /dev/zram0
-
- mkfs.ext4 /dev/zram1
- mount /dev/zram1 /tmp
-
-4) Stats:
- Per-device statistics are exported as various nodes under
- /sys/block/zram<id>/
- disksize
- num_reads
- num_writes
- invalid_io
- notify_free
- discard
- zero_pages
- orig_data_size
- compr_data_size
- mem_used_total
-
-5) Deactivate:
- swapoff /dev/zram0
- umount /dev/zram1
-
-6) Reset:
- Write any positive value to 'reset' sysfs node
- echo 1 > /sys/block/zram0/reset
- echo 1 > /sys/block/zram1/reset
-
- This frees all the memory allocated for the given device and
- resets the disksize to zero. You must set the disksize again
- before reusing the device.
-
-Please report any problems at:
- - Mailing list: linux-mm-cc at laptop dot org
- - Issue tracker: http://code.google.com/p/compcache/issues/list
-
-Nitin Gupta
-ngupta@vflare.org
diff --git a/drivers/staging/zram/zram_drv.c b/drivers/staging/zram/zram_drv.c
deleted file mode 100644
index e34e3fe0..0000000
--- a/drivers/staging/zram/zram_drv.c
+++ /dev/null
@@ -1,748 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#define KMSG_COMPONENT "zram"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#ifdef CONFIG_ZRAM_DEBUG
-#define DEBUG
-#endif
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/bio.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/buffer_head.h>
-#include <linux/device.h>
-#include <linux/genhd.h>
-#include <linux/highmem.h>
-#include <linux/slab.h>
-#include <linux/lzo.h>
-#include <linux/string.h>
-#include <linux/vmalloc.h>
-
-#include "zram_drv.h"
-
-/* Globals */
-static int zram_major;
-struct zram *zram_devices;
-
-/* Module params (documentation at end) */
-static unsigned int num_devices = 1;
-
-static void zram_stat64_add(struct zram *zram, u64 *v, u64 inc)
-{
- spin_lock(&zram->stat64_lock);
- *v = *v + inc;
- spin_unlock(&zram->stat64_lock);
-}
-
-static void zram_stat64_sub(struct zram *zram, u64 *v, u64 dec)
-{
- spin_lock(&zram->stat64_lock);
- *v = *v - dec;
- spin_unlock(&zram->stat64_lock);
-}
-
-static void zram_stat64_inc(struct zram *zram, u64 *v)
-{
- zram_stat64_add(zram, v, 1);
-}
-
-static int zram_test_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- return meta->table[index].flags & BIT(flag);
-}
-
-static void zram_set_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags |= BIT(flag);
-}
-
-static void zram_clear_flag(struct zram_meta *meta, u32 index,
- enum zram_pageflags flag)
-{
- meta->table[index].flags &= ~BIT(flag);
-}
-
-static int page_zero_filled(void *ptr)
-{
- unsigned int pos;
- unsigned long *page;
-
- page = (unsigned long *)ptr;
-
- for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
- if (page[pos])
- return 0;
- }
-
- return 1;
-}
-
-static void zram_free_page(struct zram *zram, size_t index)
-{
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
- u16 size = meta->table[index].size;
-
- if (unlikely(!handle)) {
- /*
- * No memory is allocated for zero filled pages.
- * Simply clear zero page flag.
- */
- if (zram_test_flag(meta, index, ZRAM_ZERO)) {
- zram_clear_flag(meta, index, ZRAM_ZERO);
- zram->stats.pages_zero--;
- }
- return;
- }
-
- if (unlikely(size > max_zpage_size))
- zram->stats.bad_compress--;
-
- zs_free(meta->mem_pool, handle);
-
- if (size <= PAGE_SIZE / 2)
- zram->stats.good_compress--;
-
- zram_stat64_sub(zram, &zram->stats.compr_size,
- meta->table[index].size);
- zram->stats.pages_stored--;
-
- meta->table[index].handle = 0;
- meta->table[index].size = 0;
-}
-
-static void handle_zero_page(struct bio_vec *bvec)
-{
- struct page *page = bvec->bv_page;
- void *user_mem;
-
- user_mem = kmap_atomic(page);
- memset(user_mem + bvec->bv_offset, 0, bvec->bv_len);
- kunmap_atomic(user_mem);
-
- flush_dcache_page(page);
-}
-
-static inline int is_partial_io(struct bio_vec *bvec)
-{
- return bvec->bv_len != PAGE_SIZE;
-}
-
-static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
-{
- int ret = LZO_E_OK;
- size_t clen = PAGE_SIZE;
- unsigned char *cmem;
- struct zram_meta *meta = zram->meta;
- unsigned long handle = meta->table[index].handle;
-
- if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
- memset(mem, 0, PAGE_SIZE);
- return 0;
- }
-
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
- if (meta->table[index].size == PAGE_SIZE)
- memcpy(mem, cmem, PAGE_SIZE);
- else
- ret = lzo1x_decompress_safe(cmem, meta->table[index].size,
- mem, &clen);
- zs_unmap_object(meta->mem_pool, handle);
-
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Decompression failed! err=%d, page=%u\n", ret, index);
- zram_stat64_inc(zram, &zram->stats.failed_reads);
- return ret;
- }
-
- return 0;
-}
-
-static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
- u32 index, int offset, struct bio *bio)
-{
- int ret;
- struct page *page;
- unsigned char *user_mem, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
- page = bvec->bv_page;
-
- if (unlikely(!meta->table[index].handle) ||
- zram_test_flag(meta, index, ZRAM_ZERO)) {
- handle_zero_page(bvec);
- return 0;
- }
-
- if (is_partial_io(bvec))
- /* Use a temporary buffer to decompress the page */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
-
- user_mem = kmap_atomic(page);
- if (!is_partial_io(bvec))
- uncmem = user_mem;
-
- if (!uncmem) {
- pr_info("Unable to allocate temp memory\n");
- ret = -ENOMEM;
- goto out_cleanup;
- }
-
- ret = zram_decompress_page(zram, uncmem, index);
- /* Should NEVER happen. Return bio error if it does. */
- if (unlikely(ret != LZO_E_OK))
- goto out_cleanup;
-
- if (is_partial_io(bvec))
- memcpy(user_mem + bvec->bv_offset, uncmem + offset,
- bvec->bv_len);
-
- flush_dcache_page(page);
- ret = 0;
-out_cleanup:
- kunmap_atomic(user_mem);
- if (is_partial_io(bvec))
- kfree(uncmem);
- return ret;
-}
-
-static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset)
-{
- int ret = 0;
- size_t clen;
- unsigned long handle;
- struct page *page;
- unsigned char *user_mem, *cmem, *src, *uncmem = NULL;
- struct zram_meta *meta = zram->meta;
-
- page = bvec->bv_page;
- src = meta->compress_buffer;
-
- if (is_partial_io(bvec)) {
- /*
- * This is a partial IO. We need to read the full page
- * before to write the changes.
- */
- uncmem = kmalloc(PAGE_SIZE, GFP_NOIO);
- if (!uncmem) {
- ret = -ENOMEM;
- goto out;
- }
- ret = zram_decompress_page(zram, uncmem, index);
- if (ret)
- goto out;
- }
-
- /*
- * System overwrites unused sectors. Free memory associated
- * with this sector now.
- */
- if (meta->table[index].handle ||
- zram_test_flag(meta, index, ZRAM_ZERO))
- zram_free_page(zram, index);
-
- user_mem = kmap_atomic(page);
-
- if (is_partial_io(bvec)) {
- memcpy(uncmem + offset, user_mem + bvec->bv_offset,
- bvec->bv_len);
- kunmap_atomic(user_mem);
- user_mem = NULL;
- } else {
- uncmem = user_mem;
- }
-
- if (page_zero_filled(uncmem)) {
- kunmap_atomic(user_mem);
- if (is_partial_io(bvec))
- kfree(uncmem);
- zram->stats.pages_zero++;
- zram_set_flag(meta, index, ZRAM_ZERO);
- ret = 0;
- goto out;
- }
-
- ret = lzo1x_1_compress(uncmem, PAGE_SIZE, src, &clen,
- meta->compress_workmem);
-
- if (!is_partial_io(bvec)) {
- kunmap_atomic(user_mem);
- user_mem = NULL;
- uncmem = NULL;
- }
-
- if (unlikely(ret != LZO_E_OK)) {
- pr_err("Compression failed! err=%d\n", ret);
- goto out;
- }
-
- if (unlikely(clen > max_zpage_size)) {
- zram->stats.bad_compress++;
- clen = PAGE_SIZE;
- src = NULL;
- if (is_partial_io(bvec))
- src = uncmem;
- }
-
- handle = zs_malloc(meta->mem_pool, clen);
- if (!handle) {
- pr_info("Error allocating memory for compressed "
- "page: %u, size=%zu\n", index, clen);
- ret = -ENOMEM;
- goto out;
- }
- cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
-
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec))
- src = kmap_atomic(page);
- memcpy(cmem, src, clen);
- if ((clen == PAGE_SIZE) && !is_partial_io(bvec))
- kunmap_atomic(src);
-
- zs_unmap_object(meta->mem_pool, handle);
-
- meta->table[index].handle = handle;
- meta->table[index].size = clen;
-
- /* Update stats */
- zram_stat64_add(zram, &zram->stats.compr_size, clen);
- zram->stats.pages_stored++;
- if (clen <= PAGE_SIZE / 2)
- zram->stats.good_compress++;
-
-out:
- if (is_partial_io(bvec))
- kfree(uncmem);
-
- if (ret)
- zram_stat64_inc(zram, &zram->stats.failed_writes);
- return ret;
-}
-
-static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
- int offset, struct bio *bio, int rw)
-{
- int ret;
-
- if (rw == READ) {
- down_read(&zram->lock);
- ret = zram_bvec_read(zram, bvec, index, offset, bio);
- up_read(&zram->lock);
- } else {
- down_write(&zram->lock);
- ret = zram_bvec_write(zram, bvec, index, offset);
- up_write(&zram->lock);
- }
-
- return ret;
-}
-
-static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
-{
- if (*offset + bvec->bv_len >= PAGE_SIZE)
- (*index)++;
- *offset = (*offset + bvec->bv_len) % PAGE_SIZE;
-}
-
-static void __zram_make_request(struct zram *zram, struct bio *bio, int rw)
-{
- int i, offset;
- u32 index;
- struct bio_vec *bvec;
-
- switch (rw) {
- case READ:
- zram_stat64_inc(zram, &zram->stats.num_reads);
- break;
- case WRITE:
- zram_stat64_inc(zram, &zram->stats.num_writes);
- break;
- }
-
- index = bio->bi_sector >> SECTORS_PER_PAGE_SHIFT;
- offset = (bio->bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
-
- bio_for_each_segment(bvec, bio, i) {
- int max_transfer_size = PAGE_SIZE - offset;
-
- if (bvec->bv_len > max_transfer_size) {
- /*
- * zram_bvec_rw() can only make operation on a single
- * zram page. Split the bio vector.
- */
- struct bio_vec bv;
-
- bv.bv_page = bvec->bv_page;
- bv.bv_len = max_transfer_size;
- bv.bv_offset = bvec->bv_offset;
-
- if (zram_bvec_rw(zram, &bv, index, offset, bio, rw) < 0)
- goto out;
-
- bv.bv_len = bvec->bv_len - max_transfer_size;
- bv.bv_offset += max_transfer_size;
- if (zram_bvec_rw(zram, &bv, index+1, 0, bio, rw) < 0)
- goto out;
- } else
- if (zram_bvec_rw(zram, bvec, index, offset, bio, rw)
- < 0)
- goto out;
-
- update_position(&index, &offset, bvec);
- }
-
- set_bit(BIO_UPTODATE, &bio->bi_flags);
- bio_endio(bio, 0);
- return;
-
-out:
- bio_io_error(bio);
-}
-
-/*
- * Check if request is within bounds and aligned on zram logical blocks.
- */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
-{
- if (unlikely(
- (bio->bi_sector >= (zram->disksize >> SECTOR_SHIFT)) ||
- (bio->bi_sector & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)) ||
- (bio->bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))) {
-
- return 0;
- }
-
- /* I/O request is valid */
- return 1;
-}
-
-/*
- * Handler function for all zram I/O requests.
- */
-static void zram_make_request(struct request_queue *queue, struct bio *bio)
-{
- struct zram *zram = queue->queuedata;
-
- down_read(&zram->init_lock);
- if (unlikely(!zram->init_done))
- goto error;
-
- if (!valid_io_request(zram, bio)) {
- zram_stat64_inc(zram, &zram->stats.invalid_io);
- goto error;
- }
-
- __zram_make_request(zram, bio, bio_data_dir(bio));
- up_read(&zram->init_lock);
-
- return;
-
-error:
- up_read(&zram->init_lock);
- bio_io_error(bio);
-}
-
-static void __zram_reset_device(struct zram *zram)
-{
- size_t index;
- struct zram_meta *meta;
-
- if (!zram->init_done)
- return;
-
- meta = zram->meta;
- zram->init_done = 0;
-
- /* Free all pages that are still in this zram device */
- for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) {
- unsigned long handle = meta->table[index].handle;
- if (!handle)
- continue;
-
- zs_free(meta->mem_pool, handle);
- }
-
- zram_meta_free(zram->meta);
- zram->meta = NULL;
- /* Reset stats */
- memset(&zram->stats, 0, sizeof(zram->stats));
-
- zram->disksize = 0;
- set_capacity(zram->disk, 0);
-}
-
-void zram_reset_device(struct zram *zram)
-{
- down_write(&zram->init_lock);
- __zram_reset_device(zram);
- up_write(&zram->init_lock);
-}
-
-void zram_meta_free(struct zram_meta *meta)
-{
- zs_destroy_pool(meta->mem_pool);
- kfree(meta->compress_workmem);
- free_pages((unsigned long)meta->compress_buffer, 1);
- vfree(meta->table);
- kfree(meta);
-}
-
-struct zram_meta *zram_meta_alloc(u64 disksize)
-{
- size_t num_pages;
- struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
- if (!meta)
- goto out;
-
- meta->compress_workmem = kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
- if (!meta->compress_workmem)
- goto free_meta;
-
- meta->compress_buffer =
- (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1);
- if (!meta->compress_buffer) {
- pr_err("Error allocating compressor buffer space\n");
- goto free_workmem;
- }
-
- num_pages = disksize >> PAGE_SHIFT;
- meta->table = vzalloc(num_pages * sizeof(*meta->table));
- if (!meta->table) {
- pr_err("Error allocating zram address table\n");
- goto free_buffer;
- }
-
- meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM);
- if (!meta->mem_pool) {
- pr_err("Error creating memory pool\n");
- goto free_table;
- }
-
- return meta;
-
-free_table:
- vfree(meta->table);
-free_buffer:
- free_pages((unsigned long)meta->compress_buffer, 1);
-free_workmem:
- kfree(meta->compress_workmem);
-free_meta:
- kfree(meta);
- meta = NULL;
-out:
- return meta;
-}
-
-void zram_init_device(struct zram *zram, struct zram_meta *meta)
-{
- if (zram->disksize > 2 * (totalram_pages << PAGE_SHIFT)) {
- pr_info(
- "There is little point creating a zram of greater than "
- "twice the size of memory since we expect a 2:1 compression "
- "ratio. Note that zram uses about 0.1%% of the size of "
- "the disk when not in use so a huge zram is "
- "wasteful.\n"
- "\tMemory Size: %lu kB\n"
- "\tSize you selected: %llu kB\n"
- "Continuing anyway ...\n",
- (totalram_pages << PAGE_SHIFT) >> 10, zram->disksize >> 10
- );
- }
-
- /* zram devices sort of resembles non-rotational disks */
- queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue);
-
- zram->meta = meta;
- zram->init_done = 1;
-
- pr_debug("Initialization done!\n");
-}
-
-static void zram_slot_free_notify(struct block_device *bdev,
- unsigned long index)
-{
- struct zram *zram;
-
- zram = bdev->bd_disk->private_data;
- zram_free_page(zram, index);
- zram_stat64_inc(zram, &zram->stats.notify_free);
-}
-
-static const struct block_device_operations zram_devops = {
- .swap_slot_free_notify = zram_slot_free_notify,
- .owner = THIS_MODULE
-};
-
-static int create_device(struct zram *zram, int device_id)
-{
- int ret = 0;
-
- init_rwsem(&zram->lock);
- init_rwsem(&zram->init_lock);
- spin_lock_init(&zram->stat64_lock);
-
- zram->queue = blk_alloc_queue(GFP_KERNEL);
- if (!zram->queue) {
- pr_err("Error allocating disk queue for device %d\n",
- device_id);
- ret = -ENOMEM;
- goto out;
- }
-
- blk_queue_make_request(zram->queue, zram_make_request);
- zram->queue->queuedata = zram;
-
- /* gendisk structure */
- zram->disk = alloc_disk(1);
- if (!zram->disk) {
- blk_cleanup_queue(zram->queue);
- pr_warn("Error allocating disk structure for device %d\n",
- device_id);
- ret = -ENOMEM;
- goto out;
- }
-
- zram->disk->major = zram_major;
- zram->disk->first_minor = device_id;
- zram->disk->fops = &zram_devops;
- zram->disk->queue = zram->queue;
- zram->disk->private_data = zram;
- snprintf(zram->disk->disk_name, 16, "zram%d", device_id);
-
- /* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
- set_capacity(zram->disk, 0);
-
- /*
- * To ensure that we always get PAGE_SIZE aligned
- * and n*PAGE_SIZED sized I/O requests.
- */
- blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
- blk_queue_logical_block_size(zram->disk->queue,
- ZRAM_LOGICAL_BLOCK_SIZE);
- blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
- blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
-
- add_disk(zram->disk);
-
- ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
- if (ret < 0) {
- pr_warn("Error creating sysfs group");
- goto out;
- }
-
- zram->init_done = 0;
-
-out:
- return ret;
-}
-
-static void destroy_device(struct zram *zram)
-{
- sysfs_remove_group(&disk_to_dev(zram->disk)->kobj,
- &zram_disk_attr_group);
-
- if (zram->disk) {
- del_gendisk(zram->disk);
- put_disk(zram->disk);
- }
-
- if (zram->queue)
- blk_cleanup_queue(zram->queue);
-}
-
-unsigned int zram_get_num_devices(void)
-{
- return num_devices;
-}
-
-static int __init zram_init(void)
-{
- int ret, dev_id;
-
- if (num_devices > max_num_devices) {
- pr_warn("Invalid value for num_devices: %u\n",
- num_devices);
- ret = -EINVAL;
- goto out;
- }
-
- zram_major = register_blkdev(0, "zram");
- if (zram_major <= 0) {
- pr_warn("Unable to get major number\n");
- ret = -EBUSY;
- goto out;
- }
-
- /* Allocate the device array and initialize each one */
- zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL);
- if (!zram_devices) {
- ret = -ENOMEM;
- goto unregister;
- }
-
- for (dev_id = 0; dev_id < num_devices; dev_id++) {
- ret = create_device(&zram_devices[dev_id], dev_id);
- if (ret)
- goto free_devices;
- }
-
- pr_info("Created %u device(s) ...\n", num_devices);
-
- return 0;
-
-free_devices:
- while (dev_id)
- destroy_device(&zram_devices[--dev_id]);
- kfree(zram_devices);
-unregister:
- unregister_blkdev(zram_major, "zram");
-out:
- return ret;
-}
-
-static void __exit zram_exit(void)
-{
- int i;
- struct zram *zram;
-
- for (i = 0; i < num_devices; i++) {
- zram = &zram_devices[i];
-
- destroy_device(zram);
- zram_reset_device(zram);
- }
-
- unregister_blkdev(zram_major, "zram");
-
- kfree(zram_devices);
- pr_debug("Cleanup done!\n");
-}
-
-module_param(num_devices, uint, 0);
-MODULE_PARM_DESC(num_devices, "Number of zram devices");
-
-module_init(zram_init);
-module_exit(zram_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
-MODULE_DESCRIPTION("Compressed RAM Block Device");
diff --git a/drivers/staging/zram/zram_drv.h b/drivers/staging/zram/zram_drv.h
deleted file mode 100644
index 2d1a3f1..0000000
--- a/drivers/staging/zram/zram_drv.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com
- */
-
-#ifndef _ZRAM_DRV_H_
-#define _ZRAM_DRV_H_
-
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-
-#include "../zsmalloc/zsmalloc.h"
-
-/*
- * Some arbitrary value. This is just to catch
- * invalid value for num_devices module parameter.
- */
-static const unsigned max_num_devices = 32;
-
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
-#define SECTOR_SHIFT 9
-#define SECTOR_SIZE (1 << SECTOR_SHIFT)
-#define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
-#define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT)
-#define ZRAM_LOGICAL_BLOCK_SHIFT 12
-#define ZRAM_LOGICAL_BLOCK_SIZE (1 << ZRAM_LOGICAL_BLOCK_SHIFT)
-#define ZRAM_SECTOR_PER_LOGICAL_BLOCK \
- (1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
-
-/* Flags for zram pages (table[page_no].flags) */
-enum zram_pageflags {
- /* Page consists entirely of zeros */
- ZRAM_ZERO,
-
- __NR_ZRAM_PAGEFLAGS,
-};
-
-/*-- Data structures */
-
-/* Allocated for each disk page */
-struct table {
- unsigned long handle;
- u16 size; /* object size (excluding header) */
- u8 count; /* object ref count (not yet used) */
- u8 flags;
-} __aligned(4);
-
-struct zram_stats {
- u64 compr_size; /* compressed size of pages stored */
- u64 num_reads; /* failed + successful */
- u64 num_writes; /* --do-- */
- u64 failed_reads; /* should NEVER! happen */
- u64 failed_writes; /* can happen when memory is too low */
- u64 invalid_io; /* non-page-aligned I/O requests */
- u64 notify_free; /* no. of swap slot free notifications */
- u32 pages_zero; /* no. of zero filled pages */
- u32 pages_stored; /* no. of pages currently stored */
- u32 good_compress; /* % of pages with compression ratio<=50% */
- u32 bad_compress; /* % of pages with compression ratio>=75% */
-};
-
-struct zram_meta {
- void *compress_workmem;
- void *compress_buffer;
- struct table *table;
- struct zs_pool *mem_pool;
-};
-
-struct zram {
- struct zram_meta *meta;
- spinlock_t stat64_lock; /* protect 64-bit stats */
- struct rw_semaphore lock; /* protect compression buffers and table
- * against concurrent read and writes */
- struct request_queue *queue;
- struct gendisk *disk;
- int init_done;
- /* Prevent concurrent execution of device init, reset and R/W request */
- struct rw_semaphore init_lock;
- /*
- * This is the limit on amount of *uncompressed* worth of data
- * we can store in a disk.
- */
- u64 disksize; /* bytes */
-
- struct zram_stats stats;
-};
-
-extern struct zram *zram_devices;
-unsigned int zram_get_num_devices(void);
-#ifdef CONFIG_SYSFS
-extern struct attribute_group zram_disk_attr_group;
-#endif
-
-extern void zram_reset_device(struct zram *zram);
-extern struct zram_meta *zram_meta_alloc(u64 disksize);
-extern void zram_meta_free(struct zram_meta *meta);
-extern void zram_init_device(struct zram *zram, struct zram_meta *meta);
-
-#endif
diff --git a/drivers/staging/zram/zram_sysfs.c b/drivers/staging/zram/zram_sysfs.c
deleted file mode 100644
index e6a929d..0000000
--- a/drivers/staging/zram/zram_sysfs.c
+++ /dev/null
@@ -1,227 +0,0 @@
-/*
- * Compressed RAM block device
- *
- * Copyright (C) 2008, 2009, 2010 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the licence that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- *
- * Project home: http://compcache.googlecode.com/
- */
-
-#include <linux/device.h>
-#include <linux/genhd.h>
-#include <linux/mm.h>
-#include <linux/kernel.h>
-
-#include "zram_drv.h"
-
-static u64 zram_stat64_read(struct zram *zram, u64 *v)
-{
- u64 val;
-
- spin_lock(&zram->stat64_lock);
- val = *v;
- spin_unlock(&zram->stat64_lock);
-
- return val;
-}
-
-static struct zram *dev_to_zram(struct device *dev)
-{
- int i;
- struct zram *zram = NULL;
-
- for (i = 0; i < zram_get_num_devices(); i++) {
- zram = &zram_devices[i];
- if (disk_to_dev(zram->disk) == dev)
- break;
- }
-
- return zram;
-}
-
-static ssize_t disksize_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n", zram->disksize);
-}
-
-static ssize_t disksize_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- u64 disksize;
- struct zram_meta *meta;
- struct zram *zram = dev_to_zram(dev);
-
- disksize = memparse(buf, NULL);
- if (!disksize)
- return -EINVAL;
-
- disksize = PAGE_ALIGN(disksize);
- meta = zram_meta_alloc(disksize);
- down_write(&zram->init_lock);
- if (zram->init_done) {
- up_write(&zram->init_lock);
- zram_meta_free(meta);
- pr_info("Cannot change disksize for initialized device\n");
- return -EBUSY;
- }
-
- zram->disksize = disksize;
- set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
- zram_init_device(zram, meta);
- up_write(&zram->init_lock);
-
- return len;
-}
-
-static ssize_t initstate_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->init_done);
-}
-
-static ssize_t reset_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t len)
-{
- int ret;
- unsigned short do_reset;
- struct zram *zram;
- struct block_device *bdev;
-
- zram = dev_to_zram(dev);
- bdev = bdget_disk(zram->disk, 0);
-
- /* Do not reset an active device! */
- if (bdev->bd_holders)
- return -EBUSY;
-
- ret = kstrtou16(buf, 10, &do_reset);
- if (ret)
- return ret;
-
- if (!do_reset)
- return -EINVAL;
-
- /* Make sure all pending I/O is finished */
- if (bdev)
- fsync_bdev(bdev);
-
- zram_reset_device(zram);
- return len;
-}
-
-static ssize_t num_reads_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.num_reads));
-}
-
-static ssize_t num_writes_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.num_writes));
-}
-
-static ssize_t invalid_io_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.invalid_io));
-}
-
-static ssize_t notify_free_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.notify_free));
-}
-
-static ssize_t zero_pages_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%u\n", zram->stats.pages_zero);
-}
-
-static ssize_t orig_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- (u64)(zram->stats.pages_stored) << PAGE_SHIFT);
-}
-
-static ssize_t compr_data_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct zram *zram = dev_to_zram(dev);
-
- return sprintf(buf, "%llu\n",
- zram_stat64_read(zram, &zram->stats.compr_size));
-}
-
-static ssize_t mem_used_total_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- u64 val = 0;
- struct zram *zram = dev_to_zram(dev);
- struct zram_meta *meta = zram->meta;
-
- if (zram->init_done)
- val = zs_get_total_size_bytes(meta->mem_pool);
-
- return sprintf(buf, "%llu\n", val);
-}
-
-static DEVICE_ATTR(disksize, S_IRUGO | S_IWUSR,
- disksize_show, disksize_store);
-static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
-static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
-static DEVICE_ATTR(num_reads, S_IRUGO, num_reads_show, NULL);
-static DEVICE_ATTR(num_writes, S_IRUGO, num_writes_show, NULL);
-static DEVICE_ATTR(invalid_io, S_IRUGO, invalid_io_show, NULL);
-static DEVICE_ATTR(notify_free, S_IRUGO, notify_free_show, NULL);
-static DEVICE_ATTR(zero_pages, S_IRUGO, zero_pages_show, NULL);
-static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
-static DEVICE_ATTR(compr_data_size, S_IRUGO, compr_data_size_show, NULL);
-static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
-
-static struct attribute *zram_disk_attrs[] = {
- &dev_attr_disksize.attr,
- &dev_attr_initstate.attr,
- &dev_attr_reset.attr,
- &dev_attr_num_reads.attr,
- &dev_attr_num_writes.attr,
- &dev_attr_invalid_io.attr,
- &dev_attr_notify_free.attr,
- &dev_attr_zero_pages.attr,
- &dev_attr_orig_data_size.attr,
- &dev_attr_compr_data_size.attr,
- &dev_attr_mem_used_total.attr,
- NULL,
-};
-
-struct attribute_group zram_disk_attr_group = {
- .attrs = zram_disk_attrs,
-};
diff --git a/drivers/staging/zsmalloc/Makefile b/drivers/staging/zsmalloc/Makefile
deleted file mode 100644
index b134848..0000000
--- a/drivers/staging/zsmalloc/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-zsmalloc-y := zsmalloc-main.o
-
-obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
deleted file mode 100644
index f82f7e6..0000000
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ /dev/null
@@ -1,1064 +0,0 @@
-/*
- * zsmalloc memory allocator
- *
- * Copyright (C) 2011 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the license that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- */
-
-
-/*
- * This allocator is designed for use with zcache and zram. Thus, the
- * allocator is supposed to work well under low memory conditions. In
- * particular, it never attempts higher order page allocation which is
- * very likely to fail under memory pressure. On the other hand, if we
- * just use single (0-order) pages, it would suffer from very high
- * fragmentation -- any object of size PAGE_SIZE/2 or larger would occupy
- * an entire page. This was one of the major issues with its predecessor
- * (xvmalloc).
- *
- * To overcome these issues, zsmalloc allocates a bunch of 0-order pages
- * and links them together using various 'struct page' fields. These linked
- * pages act as a single higher-order page i.e. an object can span 0-order
- * page boundaries. The code refers to these linked pages as a single entity
- * called zspage.
- *
- * Following is how we use various fields and flags of underlying
- * struct page(s) to form a zspage.
- *
- * Usage of struct page fields:
- * page->first_page: points to the first component (0-order) page
- * page->index (union with page->freelist): offset of the first object
- * starting in this page. For the first page, this is
- * always 0, so we use this field (aka freelist) to point
- * to the first free object in zspage.
- * page->lru: links together all component pages (except the first page)
- * of a zspage
- *
- * For _first_ page only:
- *
- * page->private (union with page->first_page): refers to the
- * component page after the first page
- * page->freelist: points to the first free object in zspage.
- * Free objects are linked together using in-place
- * metadata.
- * page->objects: maximum number of objects we can store in this
- * zspage (class->zspage_order * PAGE_SIZE / class->size)
- * page->lru: links together first pages of various zspages.
- * Basically forming list of zspages in a fullness group.
- * page->mapping: class index and fullness group of the zspage
- *
- * Usage of struct page flags:
- * PG_private: identifies the first component page
- * PG_private2: identifies the last component page
- *
- */
-
-#ifdef CONFIG_ZSMALLOC_DEBUG
-#define DEBUG
-#endif
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/bitops.h>
-#include <linux/errno.h>
-#include <linux/highmem.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <asm/tlbflush.h>
-#include <asm/pgtable.h>
-#include <linux/cpumask.h>
-#include <linux/cpu.h>
-#include <linux/vmalloc.h>
-#include <linux/hardirq.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#include "zsmalloc.h"
-
-/*
- * This must be power of 2 and greater than of equal to sizeof(link_free).
- * These two conditions ensure that any 'struct link_free' itself doesn't
- * span more than 1 page which avoids complex case of mapping 2 pages simply
- * to restore link_free pointer values.
- */
-#define ZS_ALIGN 8
-
-/*
- * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
- * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
- */
-#define ZS_MAX_ZSPAGE_ORDER 2
-#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
-
-/*
- * Object location (<PFN>, <obj_idx>) is encoded as
- * as single (void *) handle value.
- *
- * Note that object index <obj_idx> is relative to system
- * page <PFN> it is stored in, so for each sub-page belonging
- * to a zspage, obj_idx starts with 0.
- *
- * This is made more complicated by various memory models and PAE.
- */
-
-#ifndef MAX_PHYSMEM_BITS
-#ifdef CONFIG_HIGHMEM64G
-#define MAX_PHYSMEM_BITS 36
-#else /* !CONFIG_HIGHMEM64G */
-/*
- * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
- * be PAGE_SHIFT
- */
-#define MAX_PHYSMEM_BITS BITS_PER_LONG
-#endif
-#endif
-#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
-#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
-#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
-
-#define MAX(a, b) ((a) >= (b) ? (a) : (b))
-/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
-#define ZS_MIN_ALLOC_SIZE \
- MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
-#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
-
-/*
- * On systems with 4K page size, this gives 254 size classes! There is a
- * trader-off here:
- * - Large number of size classes is potentially wasteful as free page are
- * spread across these classes
- * - Small number of size classes causes large internal fragmentation
- * - Probably its better to use specific size classes (empirically
- * determined). NOTE: all those class sizes must be set as multiple of
- * ZS_ALIGN to make sure link_free itself never has to span 2 pages.
- *
- * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
- * (reason above)
- */
-#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
-#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
- ZS_SIZE_CLASS_DELTA + 1)
-
-/*
- * We do not maintain any list for completely empty or full pages
- */
-enum fullness_group {
- ZS_ALMOST_FULL,
- ZS_ALMOST_EMPTY,
- _ZS_NR_FULLNESS_GROUPS,
-
- ZS_EMPTY,
- ZS_FULL
-};
-
-/*
- * We assign a page to ZS_ALMOST_EMPTY fullness group when:
- * n <= N / f, where
- * n = number of allocated objects
- * N = total number of objects zspage can store
- * f = 1/fullness_threshold_frac
- *
- * Similarly, we assign zspage to:
- * ZS_ALMOST_FULL when n > N / f
- * ZS_EMPTY when n == 0
- * ZS_FULL when n == N
- *
- * (see: fix_fullness_group())
- */
-static const int fullness_threshold_frac = 4;
-
-struct size_class {
- /*
- * Size of objects stored in this class. Must be multiple
- * of ZS_ALIGN.
- */
- int size;
- unsigned int index;
-
- /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
- int pages_per_zspage;
-
- spinlock_t lock;
-
- /* stats */
- u64 pages_allocated;
-
- struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
-};
-
-/*
- * Placed within free objects to form a singly linked list.
- * For every zspage, first_page->freelist gives head of this list.
- *
- * This must be power of 2 and less than or equal to ZS_ALIGN
- */
-struct link_free {
- /* Handle of next free chunk (encodes <PFN, obj_idx>) */
- void *next;
-};
-
-struct zs_pool {
- struct size_class size_class[ZS_SIZE_CLASSES];
-
- gfp_t flags; /* allocation flags used when growing pool */
-};
-
-/*
- * A zspage's class index and fullness group
- * are encoded in its (first)page->mapping
- */
-#define CLASS_IDX_BITS 28
-#define FULLNESS_BITS 4
-#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1)
-#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1)
-
-/*
- * By default, zsmalloc uses a copy-based object mapping method to access
- * allocations that span two pages. However, if a particular architecture
- * performs VM mapping faster than copying, then it should be added here
- * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
- * page table mapping rather than copying for object mapping.
-*/
-#if defined(CONFIG_ARM) && !defined(MODULE)
-#define USE_PGTABLE_MAPPING
-#endif
-
-struct mapping_area {
-#ifdef USE_PGTABLE_MAPPING
- struct vm_struct *vm; /* vm area for mapping object that span pages */
-#else
- char *vm_buf; /* copy buffer for objects that span pages */
-#endif
- char *vm_addr; /* address of kmap_atomic()'ed pages */
- enum zs_mapmode vm_mm; /* mapping mode */
-};
-
-
-/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
-static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
-
-static int is_first_page(struct page *page)
-{
- return PagePrivate(page);
-}
-
-static int is_last_page(struct page *page)
-{
- return PagePrivate2(page);
-}
-
-static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
- enum fullness_group *fullness)
-{
- unsigned long m;
- BUG_ON(!is_first_page(page));
-
- m = (unsigned long)page->mapping;
- *fullness = m & FULLNESS_MASK;
- *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
-}
-
-static void set_zspage_mapping(struct page *page, unsigned int class_idx,
- enum fullness_group fullness)
-{
- unsigned long m;
- BUG_ON(!is_first_page(page));
-
- m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
- (fullness & FULLNESS_MASK);
- page->mapping = (struct address_space *)m;
-}
-
-static int get_size_class_index(int size)
-{
- int idx = 0;
-
- if (likely(size > ZS_MIN_ALLOC_SIZE))
- idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
- ZS_SIZE_CLASS_DELTA);
-
- return idx;
-}
-
-static enum fullness_group get_fullness_group(struct page *page)
-{
- int inuse, max_objects;
- enum fullness_group fg;
- BUG_ON(!is_first_page(page));
-
- inuse = page->inuse;
- max_objects = page->objects;
-
- if (inuse == 0)
- fg = ZS_EMPTY;
- else if (inuse == max_objects)
- fg = ZS_FULL;
- else if (inuse <= max_objects / fullness_threshold_frac)
- fg = ZS_ALMOST_EMPTY;
- else
- fg = ZS_ALMOST_FULL;
-
- return fg;
-}
-
-static void insert_zspage(struct page *page, struct size_class *class,
- enum fullness_group fullness)
-{
- struct page **head;
-
- BUG_ON(!is_first_page(page));
-
- if (fullness >= _ZS_NR_FULLNESS_GROUPS)
- return;
-
- head = &class->fullness_list[fullness];
- if (*head)
- list_add_tail(&page->lru, &(*head)->lru);
-
- *head = page;
-}
-
-static void remove_zspage(struct page *page, struct size_class *class,
- enum fullness_group fullness)
-{
- struct page **head;
-
- BUG_ON(!is_first_page(page));
-
- if (fullness >= _ZS_NR_FULLNESS_GROUPS)
- return;
-
- head = &class->fullness_list[fullness];
- BUG_ON(!*head);
- if (list_empty(&(*head)->lru))
- *head = NULL;
- else if (*head == page)
- *head = (struct page *)list_entry((*head)->lru.next,
- struct page, lru);
-
- list_del_init(&page->lru);
-}
-
-static enum fullness_group fix_fullness_group(struct zs_pool *pool,
- struct page *page)
-{
- int class_idx;
- struct size_class *class;
- enum fullness_group currfg, newfg;
-
- BUG_ON(!is_first_page(page));
-
- get_zspage_mapping(page, &class_idx, &currfg);
- newfg = get_fullness_group(page);
- if (newfg == currfg)
- goto out;
-
- class = &pool->size_class[class_idx];
- remove_zspage(page, class, currfg);
- insert_zspage(page, class, newfg);
- set_zspage_mapping(page, class_idx, newfg);
-
-out:
- return newfg;
-}
-
-/*
- * We have to decide on how many pages to link together
- * to form a zspage for each size class. This is important
- * to reduce wastage due to unusable space left at end of
- * each zspage which is given as:
- * wastage = Zp - Zp % size_class
- * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
- *
- * For example, for size class of 3/8 * PAGE_SIZE, we should
- * link together 3 PAGE_SIZE sized pages to form a zspage
- * since then we can perfectly fit in 8 such objects.
- */
-static int get_pages_per_zspage(int class_size)
-{
- int i, max_usedpc = 0;
- /* zspage order which gives maximum used size per KB */
- int max_usedpc_order = 1;
-
- for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
- int zspage_size;
- int waste, usedpc;
-
- zspage_size = i * PAGE_SIZE;
- waste = zspage_size % class_size;
- usedpc = (zspage_size - waste) * 100 / zspage_size;
-
- if (usedpc > max_usedpc) {
- max_usedpc = usedpc;
- max_usedpc_order = i;
- }
- }
-
- return max_usedpc_order;
-}
-
-/*
- * A single 'zspage' is composed of many system pages which are
- * linked together using fields in struct page. This function finds
- * the first/head page, given any component page of a zspage.
- */
-static struct page *get_first_page(struct page *page)
-{
- if (is_first_page(page))
- return page;
- else
- return page->first_page;
-}
-
-static struct page *get_next_page(struct page *page)
-{
- struct page *next;
-
- if (is_last_page(page))
- next = NULL;
- else if (is_first_page(page))
- next = (struct page *)page->private;
- else
- next = list_entry(page->lru.next, struct page, lru);
-
- return next;
-}
-
-/* Encode <page, obj_idx> as a single handle value */
-static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
-{
- unsigned long handle;
-
- if (!page) {
- BUG_ON(obj_idx);
- return NULL;
- }
-
- handle = page_to_pfn(page) << OBJ_INDEX_BITS;
- handle |= (obj_idx & OBJ_INDEX_MASK);
-
- return (void *)handle;
-}
-
-/* Decode <page, obj_idx> pair from the given object handle */
-static void obj_handle_to_location(unsigned long handle, struct page **page,
- unsigned long *obj_idx)
-{
- *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
- *obj_idx = handle & OBJ_INDEX_MASK;
-}
-
-static unsigned long obj_idx_to_offset(struct page *page,
- unsigned long obj_idx, int class_size)
-{
- unsigned long off = 0;
-
- if (!is_first_page(page))
- off = page->index;
-
- return off + obj_idx * class_size;
-}
-
-static void reset_page(struct page *page)
-{
- clear_bit(PG_private, &page->flags);
- clear_bit(PG_private_2, &page->flags);
- set_page_private(page, 0);
- page->mapping = NULL;
- page->freelist = NULL;
- page_mapcount_reset(page);
-}
-
-static void free_zspage(struct page *first_page)
-{
- struct page *nextp, *tmp, *head_extra;
-
- BUG_ON(!is_first_page(first_page));
- BUG_ON(first_page->inuse);
-
- head_extra = (struct page *)page_private(first_page);
-
- reset_page(first_page);
- __free_page(first_page);
-
- /* zspage with only 1 system page */
- if (!head_extra)
- return;
-
- list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
- list_del(&nextp->lru);
- reset_page(nextp);
- __free_page(nextp);
- }
- reset_page(head_extra);
- __free_page(head_extra);
-}
-
-/* Initialize a newly allocated zspage */
-static void init_zspage(struct page *first_page, struct size_class *class)
-{
- unsigned long off = 0;
- struct page *page = first_page;
-
- BUG_ON(!is_first_page(first_page));
- while (page) {
- struct page *next_page;
- struct link_free *link;
- unsigned int i, objs_on_page;
-
- /*
- * page->index stores offset of first object starting
- * in the page. For the first page, this is always 0,
- * so we use first_page->index (aka ->freelist) to store
- * head of corresponding zspage's freelist.
- */
- if (page != first_page)
- page->index = off;
-
- link = (struct link_free *)kmap_atomic(page) +
- off / sizeof(*link);
- objs_on_page = (PAGE_SIZE - off) / class->size;
-
- for (i = 1; i <= objs_on_page; i++) {
- off += class->size;
- if (off < PAGE_SIZE) {
- link->next = obj_location_to_handle(page, i);
- link += class->size / sizeof(*link);
- }
- }
-
- /*
- * We now come to the last (full or partial) object on this
- * page, which must point to the first object on the next
- * page (if present)
- */
- next_page = get_next_page(page);
- link->next = obj_location_to_handle(next_page, 0);
- kunmap_atomic(link);
- page = next_page;
- off = (off + class->size) % PAGE_SIZE;
- }
-}
-
-/*
- * Allocate a zspage for the given size class
- */
-static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
-{
- int i, error;
- struct page *first_page = NULL, *uninitialized_var(prev_page);
-
- /*
- * Allocate individual pages and link them together as:
- * 1. first page->private = first sub-page
- * 2. all sub-pages are linked together using page->lru
- * 3. each sub-page is linked to the first page using page->first_page
- *
- * For each size class, First/Head pages are linked together using
- * page->lru. Also, we set PG_private to identify the first page
- * (i.e. no other sub-page has this flag set) and PG_private_2 to
- * identify the last page.
- */
- error = -ENOMEM;
- for (i = 0; i < class->pages_per_zspage; i++) {
- struct page *page;
-
- page = alloc_page(flags);
- if (!page)
- goto cleanup;
-
- INIT_LIST_HEAD(&page->lru);
- if (i == 0) { /* first page */
- SetPagePrivate(page);
- set_page_private(page, 0);
- first_page = page;
- first_page->inuse = 0;
- }
- if (i == 1)
- first_page->private = (unsigned long)page;
- if (i >= 1)
- page->first_page = first_page;
- if (i >= 2)
- list_add(&page->lru, &prev_page->lru);
- if (i == class->pages_per_zspage - 1) /* last page */
- SetPagePrivate2(page);
- prev_page = page;
- }
-
- init_zspage(first_page, class);
-
- first_page->freelist = obj_location_to_handle(first_page, 0);
- /* Maximum number of objects we can store in this zspage */
- first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
-
- error = 0; /* Success */
-
-cleanup:
- if (unlikely(error) && first_page) {
- free_zspage(first_page);
- first_page = NULL;
- }
-
- return first_page;
-}
-
-static struct page *find_get_zspage(struct size_class *class)
-{
- int i;
- struct page *page;
-
- for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
- page = class->fullness_list[i];
- if (page)
- break;
- }
-
- return page;
-}
-
-#ifdef USE_PGTABLE_MAPPING
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm)
- return 0;
- area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
- if (!area->vm)
- return -ENOMEM;
- return 0;
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm)
- free_vm_area(area->vm);
- area->vm = NULL;
-}
-
-static inline void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
- area->vm_addr = area->vm->addr;
- return area->vm_addr + off;
-}
-
-static inline void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- unsigned long addr = (unsigned long)area->vm_addr;
-
- unmap_kernel_range(addr, PAGE_SIZE * 2);
-}
-
-#else /* USE_PGTABLE_MAPPING */
-
-static inline int __zs_cpu_up(struct mapping_area *area)
-{
- /*
- * Make sure we don't leak memory if a cpu UP notification
- * and zs_init() race and both call zs_cpu_up() on the same cpu
- */
- if (area->vm_buf)
- return 0;
- area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
- if (!area->vm_buf)
- return -ENOMEM;
- return 0;
-}
-
-static inline void __zs_cpu_down(struct mapping_area *area)
-{
- if (area->vm_buf)
- free_page((unsigned long)area->vm_buf);
- area->vm_buf = NULL;
-}
-
-static void *__zs_map_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* disable page faults to match kmap_atomic() return conditions */
- pagefault_disable();
-
- /* no read fastpath */
- if (area->vm_mm == ZS_MM_WO)
- goto out;
-
- sizes[0] = PAGE_SIZE - off;
- sizes[1] = size - sizes[0];
-
- /* copy object to per-cpu buffer */
- addr = kmap_atomic(pages[0]);
- memcpy(buf, addr + off, sizes[0]);
- kunmap_atomic(addr);
- addr = kmap_atomic(pages[1]);
- memcpy(buf + sizes[0], addr, sizes[1]);
- kunmap_atomic(addr);
-out:
- return area->vm_buf;
-}
-
-static void __zs_unmap_object(struct mapping_area *area,
- struct page *pages[2], int off, int size)
-{
- int sizes[2];
- void *addr;
- char *buf = area->vm_buf;
-
- /* no write fastpath */
- if (area->vm_mm == ZS_MM_RO)
- goto out;
-
- sizes[0] = PAGE_SIZE - off;
- sizes[1] = size - sizes[0];
-
- /* copy per-cpu buffer to object */
- addr = kmap_atomic(pages[0]);
- memcpy(addr + off, buf, sizes[0]);
- kunmap_atomic(addr);
- addr = kmap_atomic(pages[1]);
- memcpy(addr, buf + sizes[0], sizes[1]);
- kunmap_atomic(addr);
-
-out:
- /* enable page faults to match kunmap_atomic() return conditions */
- pagefault_enable();
-}
-
-#endif /* USE_PGTABLE_MAPPING */
-
-static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
- void *pcpu)
-{
- int ret, cpu = (long)pcpu;
- struct mapping_area *area;
-
- switch (action) {
- case CPU_UP_PREPARE:
- area = &per_cpu(zs_map_area, cpu);
- ret = __zs_cpu_up(area);
- if (ret)
- return notifier_from_errno(ret);
- break;
- case CPU_DEAD:
- case CPU_UP_CANCELED:
- area = &per_cpu(zs_map_area, cpu);
- __zs_cpu_down(area);
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block zs_cpu_nb = {
- .notifier_call = zs_cpu_notifier
-};
-
-static void zs_exit(void)
-{
- int cpu;
-
- for_each_online_cpu(cpu)
- zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
- unregister_cpu_notifier(&zs_cpu_nb);
-}
-
-static int zs_init(void)
-{
- int cpu, ret;
-
- register_cpu_notifier(&zs_cpu_nb);
- for_each_online_cpu(cpu) {
- ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
- if (notifier_to_errno(ret))
- goto fail;
- }
- return 0;
-fail:
- zs_exit();
- return notifier_to_errno(ret);
-}
-
-/**
- * zs_create_pool - Creates an allocation pool to work from.
- * @flags: allocation flags used to allocate pool metadata
- *
- * This function must be called before anything when using
- * the zsmalloc allocator.
- *
- * On success, a pointer to the newly created pool is returned,
- * otherwise NULL.
- */
-struct zs_pool *zs_create_pool(gfp_t flags)
-{
- int i, ovhd_size;
- struct zs_pool *pool;
-
- ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
- pool = kzalloc(ovhd_size, GFP_KERNEL);
- if (!pool)
- return NULL;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++) {
- int size;
- struct size_class *class;
-
- size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
- if (size > ZS_MAX_ALLOC_SIZE)
- size = ZS_MAX_ALLOC_SIZE;
-
- class = &pool->size_class[i];
- class->size = size;
- class->index = i;
- spin_lock_init(&class->lock);
- class->pages_per_zspage = get_pages_per_zspage(size);
-
- }
-
- pool->flags = flags;
-
- return pool;
-}
-EXPORT_SYMBOL_GPL(zs_create_pool);
-
-void zs_destroy_pool(struct zs_pool *pool)
-{
- int i;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++) {
- int fg;
- struct size_class *class = &pool->size_class[i];
-
- for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
- if (class->fullness_list[fg]) {
- pr_info("Freeing non-empty class with size "
- "%db, fullness group %d\n",
- class->size, fg);
- }
- }
- }
- kfree(pool);
-}
-EXPORT_SYMBOL_GPL(zs_destroy_pool);
-
-/**
- * zs_malloc - Allocate block of given size from pool.
- * @pool: pool to allocate from
- * @size: size of block to allocate
- *
- * On success, handle to the allocated object is returned,
- * otherwise 0.
- * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
- */
-unsigned long zs_malloc(struct zs_pool *pool, size_t size)
-{
- unsigned long obj;
- struct link_free *link;
- int class_idx;
- struct size_class *class;
-
- struct page *first_page, *m_page;
- unsigned long m_objidx, m_offset;
-
- if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
- return 0;
-
- class_idx = get_size_class_index(size);
- class = &pool->size_class[class_idx];
- BUG_ON(class_idx != class->index);
-
- spin_lock(&class->lock);
- first_page = find_get_zspage(class);
-
- if (!first_page) {
- spin_unlock(&class->lock);
- first_page = alloc_zspage(class, pool->flags);
- if (unlikely(!first_page))
- return 0;
-
- set_zspage_mapping(first_page, class->index, ZS_EMPTY);
- spin_lock(&class->lock);
- class->pages_allocated += class->pages_per_zspage;
- }
-
- obj = (unsigned long)first_page->freelist;
- obj_handle_to_location(obj, &m_page, &m_objidx);
- m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
-
- link = (struct link_free *)kmap_atomic(m_page) +
- m_offset / sizeof(*link);
- first_page->freelist = link->next;
- memset(link, POISON_INUSE, sizeof(*link));
- kunmap_atomic(link);
-
- first_page->inuse++;
- /* Now move the zspage to another fullness group, if required */
- fix_fullness_group(pool, first_page);
- spin_unlock(&class->lock);
-
- return obj;
-}
-EXPORT_SYMBOL_GPL(zs_malloc);
-
-void zs_free(struct zs_pool *pool, unsigned long obj)
-{
- struct link_free *link;
- struct page *first_page, *f_page;
- unsigned long f_objidx, f_offset;
-
- int class_idx;
- struct size_class *class;
- enum fullness_group fullness;
-
- if (unlikely(!obj))
- return;
-
- obj_handle_to_location(obj, &f_page, &f_objidx);
- first_page = get_first_page(f_page);
-
- get_zspage_mapping(first_page, &class_idx, &fullness);
- class = &pool->size_class[class_idx];
- f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
-
- spin_lock(&class->lock);
-
- /* Insert this object in containing zspage's freelist */
- link = (struct link_free *)((unsigned char *)kmap_atomic(f_page)
- + f_offset);
- link->next = first_page->freelist;
- kunmap_atomic(link);
- first_page->freelist = (void *)obj;
-
- first_page->inuse--;
- fullness = fix_fullness_group(pool, first_page);
-
- if (fullness == ZS_EMPTY)
- class->pages_allocated -= class->pages_per_zspage;
-
- spin_unlock(&class->lock);
-
- if (fullness == ZS_EMPTY)
- free_zspage(first_page);
-}
-EXPORT_SYMBOL_GPL(zs_free);
-
-/**
- * zs_map_object - get address of allocated object from handle.
- * @pool: pool from which the object was allocated
- * @handle: handle returned from zs_malloc
- *
- * Before using an object allocated from zs_malloc, it must be mapped using
- * this function. When done with the object, it must be unmapped using
- * zs_unmap_object.
- *
- * Only one object can be mapped per cpu at a time. There is no protection
- * against nested mappings.
- *
- * This function returns with preemption and page faults disabled.
-*/
-void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- enum zs_mapmode mm)
-{
- struct page *page;
- unsigned long obj_idx, off;
-
- unsigned int class_idx;
- enum fullness_group fg;
- struct size_class *class;
- struct mapping_area *area;
- struct page *pages[2];
-
- BUG_ON(!handle);
-
- /*
- * Because we use per-cpu mapping areas shared among the
- * pools/users, we can't allow mapping in interrupt context
- * because it can corrupt another users mappings.
- */
- BUG_ON(in_interrupt());
-
- obj_handle_to_location(handle, &page, &obj_idx);
- get_zspage_mapping(get_first_page(page), &class_idx, &fg);
- class = &pool->size_class[class_idx];
- off = obj_idx_to_offset(page, obj_idx, class->size);
-
- area = &get_cpu_var(zs_map_area);
- area->vm_mm = mm;
- if (off + class->size <= PAGE_SIZE) {
- /* this object is contained entirely within a page */
- area->vm_addr = kmap_atomic(page);
- return area->vm_addr + off;
- }
-
- /* this object spans two pages */
- pages[0] = page;
- pages[1] = get_next_page(page);
- BUG_ON(!pages[1]);
-
- return __zs_map_object(area, pages, off, class->size);
-}
-EXPORT_SYMBOL_GPL(zs_map_object);
-
-void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
-{
- struct page *page;
- unsigned long obj_idx, off;
-
- unsigned int class_idx;
- enum fullness_group fg;
- struct size_class *class;
- struct mapping_area *area;
-
- BUG_ON(!handle);
-
- obj_handle_to_location(handle, &page, &obj_idx);
- get_zspage_mapping(get_first_page(page), &class_idx, &fg);
- class = &pool->size_class[class_idx];
- off = obj_idx_to_offset(page, obj_idx, class->size);
-
- area = &__get_cpu_var(zs_map_area);
- if (off + class->size <= PAGE_SIZE)
- kunmap_atomic(area->vm_addr);
- else {
- struct page *pages[2];
-
- pages[0] = page;
- pages[1] = get_next_page(page);
- BUG_ON(!pages[1]);
-
- __zs_unmap_object(area, pages, off, class->size);
- }
- put_cpu_var(zs_map_area);
-}
-EXPORT_SYMBOL_GPL(zs_unmap_object);
-
-u64 zs_get_total_size_bytes(struct zs_pool *pool)
-{
- int i;
- u64 npages = 0;
-
- for (i = 0; i < ZS_SIZE_CLASSES; i++)
- npages += pool->size_class[i].pages_allocated;
-
- return npages << PAGE_SHIFT;
-}
-EXPORT_SYMBOL_GPL(zs_get_total_size_bytes);
-
-module_init(zs_init);
-module_exit(zs_exit);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
diff --git a/drivers/staging/zsmalloc/zsmalloc.h b/drivers/staging/zsmalloc/zsmalloc.h
deleted file mode 100644
index 46dbd05..0000000
--- a/drivers/staging/zsmalloc/zsmalloc.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * zsmalloc memory allocator
- *
- * Copyright (C) 2011 Nitin Gupta
- *
- * This code is released using a dual license strategy: BSD/GPL
- * You can choose the license that better fits your requirements.
- *
- * Released under the terms of 3-clause BSD License
- * Released under the terms of GNU General Public License Version 2.0
- */
-
-#ifndef _ZS_MALLOC_H_
-#define _ZS_MALLOC_H_
-
-#include <linux/types.h>
-
-/*
- * zsmalloc mapping modes
- *
- * NOTE: These only make a difference when a mapped object spans pages
-*/
-enum zs_mapmode {
- ZS_MM_RW, /* normal read-write mapping */
- ZS_MM_RO, /* read-only (no copy-out at unmap time) */
- ZS_MM_WO /* write-only (no copy-in at map time) */
-};
-
-struct zs_pool;
-
-struct zs_pool *zs_create_pool(gfp_t flags);
-void zs_destroy_pool(struct zs_pool *pool);
-
-unsigned long zs_malloc(struct zs_pool *pool, size_t size);
-void zs_free(struct zs_pool *pool, unsigned long obj);
-
-void *zs_map_object(struct zs_pool *pool, unsigned long handle,
- enum zs_mapmode mm);
-void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
-
-u64 zs_get_total_size_bytes(struct zs_pool *pool);
-
-#endif
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d7705e5..5a3ea20 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -54,7 +54,7 @@
static LIST_HEAD(g_tiqn_list);
static LIST_HEAD(g_np_list);
static DEFINE_SPINLOCK(tiqn_lock);
-static DEFINE_SPINLOCK(np_lock);
+static DEFINE_MUTEX(np_lock);
static struct idr tiqn_idr;
struct idr sess_idr;
@@ -303,6 +303,9 @@
return false;
}
+/*
+ * Called with mutex np_lock held
+ */
static struct iscsi_np *iscsit_get_np(
struct __kernel_sockaddr_storage *sockaddr,
int network_transport)
@@ -310,11 +313,10 @@
struct iscsi_np *np;
bool match;
- spin_lock_bh(&np_lock);
list_for_each_entry(np, &g_np_list, np_list) {
- spin_lock(&np->np_thread_lock);
+ spin_lock_bh(&np->np_thread_lock);
if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) {
- spin_unlock(&np->np_thread_lock);
+ spin_unlock_bh(&np->np_thread_lock);
continue;
}
@@ -326,13 +328,11 @@
* while iscsi_tpg_add_network_portal() is called.
*/
np->np_exports++;
- spin_unlock(&np->np_thread_lock);
- spin_unlock_bh(&np_lock);
+ spin_unlock_bh(&np->np_thread_lock);
return np;
}
- spin_unlock(&np->np_thread_lock);
+ spin_unlock_bh(&np->np_thread_lock);
}
- spin_unlock_bh(&np_lock);
return NULL;
}
@@ -346,16 +346,22 @@
struct sockaddr_in6 *sock_in6;
struct iscsi_np *np;
int ret;
+
+ mutex_lock(&np_lock);
+
/*
* Locate the existing struct iscsi_np if already active..
*/
np = iscsit_get_np(sockaddr, network_transport);
- if (np)
+ if (np) {
+ mutex_unlock(&np_lock);
return np;
+ }
np = kzalloc(sizeof(struct iscsi_np), GFP_KERNEL);
if (!np) {
pr_err("Unable to allocate memory for struct iscsi_np\n");
+ mutex_unlock(&np_lock);
return ERR_PTR(-ENOMEM);
}
@@ -378,6 +384,7 @@
ret = iscsi_target_setup_login_socket(np, sockaddr);
if (ret != 0) {
kfree(np);
+ mutex_unlock(&np_lock);
return ERR_PTR(ret);
}
@@ -386,6 +393,7 @@
pr_err("Unable to create kthread: iscsi_np\n");
ret = PTR_ERR(np->np_thread);
kfree(np);
+ mutex_unlock(&np_lock);
return ERR_PTR(ret);
}
/*
@@ -396,10 +404,10 @@
* point because iscsi_np has not been added to g_np_list yet.
*/
np->np_exports = 1;
+ np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
- spin_lock_bh(&np_lock);
list_add_tail(&np->np_list, &g_np_list);
- spin_unlock_bh(&np_lock);
+ mutex_unlock(&np_lock);
pr_debug("CORE[0] - Added Network Portal: %s:%hu on %s\n",
np->np_ip, np->np_port, np->np_transport->name);
@@ -452,6 +460,7 @@
spin_lock_bh(&np->np_thread_lock);
np->np_exports--;
if (np->np_exports) {
+ np->enabled = true;
spin_unlock_bh(&np->np_thread_lock);
return 0;
}
@@ -469,9 +478,9 @@
np->np_transport->iscsit_free_np(np);
- spin_lock_bh(&np_lock);
+ mutex_lock(&np_lock);
list_del(&np->np_list);
- spin_unlock_bh(&np_lock);
+ mutex_unlock(&np_lock);
pr_debug("CORE[0] - Removed Network Portal: %s:%hu on %s\n",
np->np_ip, np->np_port, np->np_transport->name);
@@ -628,25 +637,18 @@
}
static int iscsit_add_reject(
+ struct iscsi_conn *conn,
u8 reason,
- int fail_conn,
- unsigned char *buf,
- struct iscsi_conn *conn)
+ unsigned char *buf)
{
struct iscsi_cmd *cmd;
- struct iscsi_reject *hdr;
- int ret;
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
return -1;
cmd->iscsi_opcode = ISCSI_OP_REJECT;
- if (fail_conn)
- cmd->cmd_flags |= ICF_REJECT_FAIL_CONN;
-
- hdr = (struct iscsi_reject *) cmd->pdu;
- hdr->reason = reason;
+ cmd->reject_reason = reason;
cmd->buf_ptr = kmemdup(buf, ISCSI_HDR_LEN, GFP_KERNEL);
if (!cmd->buf_ptr) {
@@ -662,23 +664,16 @@
cmd->i_state = ISTATE_SEND_REJECT;
iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
- ret = wait_for_completion_interruptible(&cmd->reject_comp);
- if (ret != 0)
- return -1;
-
- return (!fail_conn) ? 0 : -1;
+ return -1;
}
-int iscsit_add_reject_from_cmd(
+static int iscsit_add_reject_from_cmd(
+ struct iscsi_cmd *cmd,
u8 reason,
- int fail_conn,
- int add_to_conn,
- unsigned char *buf,
- struct iscsi_cmd *cmd)
+ bool add_to_conn,
+ unsigned char *buf)
{
struct iscsi_conn *conn;
- struct iscsi_reject *hdr;
- int ret;
if (!cmd->conn) {
pr_err("cmd->conn is NULL for ITT: 0x%08x\n",
@@ -688,11 +683,7 @@
conn = cmd->conn;
cmd->iscsi_opcode = ISCSI_OP_REJECT;
- if (fail_conn)
- cmd->cmd_flags |= ICF_REJECT_FAIL_CONN;
-
- hdr = (struct iscsi_reject *) cmd->pdu;
- hdr->reason = reason;
+ cmd->reject_reason = reason;
cmd->buf_ptr = kmemdup(buf, ISCSI_HDR_LEN, GFP_KERNEL);
if (!cmd->buf_ptr) {
@@ -709,8 +700,6 @@
cmd->i_state = ISTATE_SEND_REJECT;
iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
-
- ret = wait_for_completion_interruptible(&cmd->reject_comp);
/*
* Perform the kref_put now if se_cmd has already been setup by
* scsit_setup_scsi_cmd()
@@ -719,12 +708,19 @@
pr_debug("iscsi reject: calling target_put_sess_cmd >>>>>>\n");
target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
}
- if (ret != 0)
- return -1;
-
- return (!fail_conn) ? 0 : -1;
+ return -1;
}
-EXPORT_SYMBOL(iscsit_add_reject_from_cmd);
+
+static int iscsit_add_reject_cmd(struct iscsi_cmd *cmd, u8 reason,
+ unsigned char *buf)
+{
+ return iscsit_add_reject_from_cmd(cmd, reason, true, buf);
+}
+
+int iscsit_reject_cmd(struct iscsi_cmd *cmd, u8 reason, unsigned char *buf)
+{
+ return iscsit_add_reject_from_cmd(cmd, reason, false, buf);
+}
/*
* Map some portion of the allocated scatterlist to an iovec, suitable for
@@ -844,93 +840,91 @@
!(hdr->flags & ISCSI_FLAG_CMD_FINAL)) {
pr_err("ISCSI_FLAG_CMD_WRITE & ISCSI_FLAG_CMD_FINAL"
" not set. Bad iSCSI Initiator.\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
if (((hdr->flags & ISCSI_FLAG_CMD_READ) ||
(hdr->flags & ISCSI_FLAG_CMD_WRITE)) && !hdr->data_length) {
/*
- * Vmware ESX v3.0 uses a modified Cisco Initiator (v3.4.2)
- * that adds support for RESERVE/RELEASE. There is a bug
- * add with this new functionality that sets R/W bits when
- * neither CDB carries any READ or WRITE datapayloads.
+ * From RFC-3720 Section 10.3.1:
+ *
+ * "Either or both of R and W MAY be 1 when either the
+ * Expected Data Transfer Length and/or Bidirectional Read
+ * Expected Data Transfer Length are 0"
+ *
+ * For this case, go ahead and clear the unnecssary bits
+ * to avoid any confusion with ->data_direction.
*/
- if ((hdr->cdb[0] == 0x16) || (hdr->cdb[0] == 0x17)) {
- hdr->flags &= ~ISCSI_FLAG_CMD_READ;
- hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
- goto done;
- }
+ hdr->flags &= ~ISCSI_FLAG_CMD_READ;
+ hdr->flags &= ~ISCSI_FLAG_CMD_WRITE;
- pr_err("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
+ pr_warn("ISCSI_FLAG_CMD_READ or ISCSI_FLAG_CMD_WRITE"
" set when Expected Data Transfer Length is 0 for"
- " CDB: 0x%02x. Bad iSCSI Initiator.\n", hdr->cdb[0]);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ " CDB: 0x%02x, Fixing up flags\n", hdr->cdb[0]);
}
-done:
if (!(hdr->flags & ISCSI_FLAG_CMD_READ) &&
!(hdr->flags & ISCSI_FLAG_CMD_WRITE) && (hdr->data_length != 0)) {
pr_err("ISCSI_FLAG_CMD_READ and/or ISCSI_FLAG_CMD_WRITE"
" MUST be set if Expected Data Transfer Length is not 0."
" Bad iSCSI Initiator\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
if ((hdr->flags & ISCSI_FLAG_CMD_READ) &&
(hdr->flags & ISCSI_FLAG_CMD_WRITE)) {
pr_err("Bidirectional operations not supported!\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
if (hdr->opcode & ISCSI_OP_IMMEDIATE) {
pr_err("Illegally set Immediate Bit in iSCSI Initiator"
" Scsi Command PDU.\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
if (payload_length && !conn->sess->sess_ops->ImmediateData) {
pr_err("ImmediateData=No but DataSegmentLength=%u,"
" protocol error.\n", payload_length);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
- if ((be32_to_cpu(hdr->data_length )== payload_length) &&
+ if ((be32_to_cpu(hdr->data_length) == payload_length) &&
(!(hdr->flags & ISCSI_FLAG_CMD_FINAL))) {
pr_err("Expected Data Transfer Length and Length of"
" Immediate Data are the same, but ISCSI_FLAG_CMD_FINAL"
" bit is not set protocol error\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
if (payload_length > be32_to_cpu(hdr->data_length)) {
pr_err("DataSegmentLength: %u is greater than"
" EDTL: %u, protocol error.\n", payload_length,
hdr->data_length);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) {
pr_err("DataSegmentLength: %u is greater than"
" MaxXmitDataSegmentLength: %u, protocol error.\n",
payload_length, conn->conn_ops->MaxXmitDataSegmentLength);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
if (payload_length > conn->sess->sess_ops->FirstBurstLength) {
pr_err("DataSegmentLength: %u is greater than"
" FirstBurstLength: %u, protocol error.\n",
payload_length, conn->sess->sess_ops->FirstBurstLength);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
data_direction = (hdr->flags & ISCSI_FLAG_CMD_WRITE) ? DMA_TO_DEVICE :
@@ -985,9 +979,8 @@
dr = iscsit_allocate_datain_req();
if (!dr)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
iscsit_attach_datain_req(cmd, dr);
}
@@ -1015,18 +1008,16 @@
cmd->sense_reason = target_setup_cmd_from_cdb(&cmd->se_cmd, hdr->cdb);
if (cmd->sense_reason) {
if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) {
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
}
goto attach_cmd;
}
if (iscsit_build_pdu_and_seq_lists(cmd, payload_length) < 0) {
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
}
attach_cmd:
@@ -1068,17 +1059,13 @@
* be acknowledged. (See below)
*/
if (!cmd->immediate_data) {
- cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
- if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
- if (!cmd->sense_reason)
- return 0;
-
+ cmdsn_ret = iscsit_sequence_cmd(conn, cmd,
+ (unsigned char *)hdr, hdr->cmdsn);
+ if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
+ return -1;
+ else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
return 0;
- } else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER) {
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, (unsigned char *)hdr, cmd);
}
}
@@ -1103,7 +1090,9 @@
* iscsit_check_received_cmdsn() in iscsit_get_immediate_data() below.
*/
if (cmd->sense_reason) {
- target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+ if (cmd->reject_reason)
+ return 0;
+
return 1;
}
/*
@@ -1111,10 +1100,8 @@
* the backend memory allocation.
*/
cmd->sense_reason = transport_generic_new_cmd(&cmd->se_cmd);
- if (cmd->sense_reason) {
- target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+ if (cmd->sense_reason)
return 1;
- }
return 0;
}
@@ -1124,6 +1111,7 @@
iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
bool dump_payload)
{
+ struct iscsi_conn *conn = cmd->conn;
int cmdsn_ret = 0, immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION;
/*
* Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes.
@@ -1140,20 +1128,21 @@
* DataCRC, check against ExpCmdSN/MaxCmdSN if
* Immediate Bit is not set.
*/
- cmdsn_ret = iscsit_sequence_cmd(cmd->conn, cmd, hdr->cmdsn);
+ cmdsn_ret = iscsit_sequence_cmd(cmd->conn, cmd,
+ (unsigned char *)hdr, hdr->cmdsn);
+ if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
+ return -1;
- if (cmd->sense_reason) {
- if (iscsit_dump_data_payload(cmd->conn,
- cmd->first_burst_len, 1) < 0)
- return -1;
+ if (cmd->sense_reason || cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
+ int rc;
+
+ rc = iscsit_dump_data_payload(cmd->conn,
+ cmd->first_burst_len, 1);
+ target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+ return rc;
} else if (cmd->unsolicited_data)
iscsit_set_unsoliticed_dataout(cmd);
- if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, (unsigned char *)hdr, cmd);
-
} else if (immed_ret == IMMEDIATE_DATA_ERL1_CRC_FAILURE) {
/*
* Immediate Data failed DataCRC and ERL>=1,
@@ -1184,15 +1173,14 @@
rc = iscsit_setup_scsi_cmd(conn, cmd, buf);
if (rc < 0)
- return rc;
+ return 0;
/*
* Allocation iovecs needed for struct socket operations for
* traditional iSCSI block I/O.
*/
if (iscsit_allocate_iovecs(cmd) < 0) {
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
}
immed_data = cmd->immediate_data;
@@ -1283,8 +1271,8 @@
if (!payload_length) {
pr_err("DataOUT payload is ZERO, protocol error.\n");
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buf);
}
/* iSCSI write */
@@ -1301,8 +1289,8 @@
pr_err("DataSegmentLength: %u is greater than"
" MaxXmitDataSegmentLength: %u\n", payload_length,
conn->conn_ops->MaxXmitDataSegmentLength);
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buf);
}
cmd = iscsit_find_cmd_from_itt_or_dump(conn, hdr->itt,
@@ -1325,8 +1313,7 @@
if (cmd->data_direction != DMA_TO_DEVICE) {
pr_err("Command ITT: 0x%08x received DataOUT for a"
" NON-WRITE command.\n", cmd->init_task_tag);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return iscsit_dump_data_payload(conn, payload_length, 1);
}
se_cmd = &cmd->se_cmd;
iscsit_mod_dataout_timer(cmd);
@@ -1335,8 +1322,7 @@
pr_err("DataOut Offset: %u, Length %u greater than"
" iSCSI Command EDTL %u, protocol error.\n",
hdr->offset, payload_length, cmd->se_cmd.data_length);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_INVALID, buf);
}
if (cmd->unsolicited_data) {
@@ -1528,7 +1514,7 @@
rc = iscsit_check_dataout_hdr(conn, buf, &cmd);
if (rc < 0)
- return rc;
+ return 0;
else if (!cmd)
return 0;
@@ -1557,8 +1543,12 @@
if (hdr->itt == RESERVED_ITT && !(hdr->opcode & ISCSI_OP_IMMEDIATE)) {
pr_err("NOPOUT ITT is reserved, but Immediate Bit is"
" not set, protocol error.\n");
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ if (!cmd)
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ (unsigned char *)hdr);
+
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR,
+ (unsigned char *)hdr);
}
if (payload_length > conn->conn_ops->MaxXmitDataSegmentLength) {
@@ -1566,8 +1556,12 @@
" greater than MaxXmitDataSegmentLength: %u, protocol"
" error.\n", payload_length,
conn->conn_ops->MaxXmitDataSegmentLength);
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ if (!cmd)
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ (unsigned char *)hdr);
+
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR,
+ (unsigned char *)hdr);
}
pr_debug("Got NOPOUT Ping %s ITT: 0x%08x, TTT: 0x%08x,"
@@ -1584,9 +1578,9 @@
*/
if (hdr->ttt == cpu_to_be32(0xFFFFFFFF)) {
if (!cmd)
- return iscsit_add_reject(
+ return iscsit_reject_cmd(cmd,
ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ (unsigned char *)hdr);
cmd->iscsi_opcode = ISCSI_OP_NOOP_OUT;
cmd->i_state = ISTATE_SEND_NOPIN;
@@ -1700,15 +1694,14 @@
return 0;
}
- cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
+ cmdsn_ret = iscsit_sequence_cmd(conn, cmd,
+ (unsigned char *)hdr, hdr->cmdsn);
if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
ret = 0;
goto ping_out;
}
if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return -1;
return 0;
}
@@ -1757,8 +1750,8 @@
struct se_tmr_req *se_tmr;
struct iscsi_tmr_req *tmr_req;
struct iscsi_tm *hdr;
- int out_of_order_cmdsn = 0;
- int ret;
+ int out_of_order_cmdsn = 0, ret;
+ bool sess_ref = false;
u8 function;
hdr = (struct iscsi_tm *) buf;
@@ -1782,8 +1775,8 @@
pr_err("Task Management Request TASK_REASSIGN not"
" issued as immediate command, bad iSCSI Initiator"
"implementation\n");
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
if ((function != ISCSI_TM_FUNC_ABORT_TASK) &&
be32_to_cpu(hdr->refcmdsn) != ISCSI_RESERVED_TAG)
@@ -1795,9 +1788,9 @@
if (!cmd->tmr_req) {
pr_err("Unable to allocate memory for"
" Task Management command!\n");
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES,
+ buf);
}
/*
@@ -1814,6 +1807,9 @@
conn->sess->se_sess, 0, DMA_NONE,
MSG_SIMPLE_TAG, cmd->sense_buffer + 2);
+ target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true);
+ sess_ref = true;
+
switch (function) {
case ISCSI_TM_FUNC_ABORT_TASK:
tcm_function = TMR_ABORT_TASK;
@@ -1839,17 +1835,15 @@
default:
pr_err("Unknown iSCSI TMR Function:"
" 0x%02x\n", function);
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
}
ret = core_tmr_alloc_req(&cmd->se_cmd, cmd->tmr_req,
tcm_function, GFP_KERNEL);
if (ret < 0)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 1, buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
cmd->tmr_req->se_tmr_req = cmd->se_cmd.se_tmr_req;
}
@@ -1908,9 +1902,8 @@
break;
if (iscsit_check_task_reassign_expdatasn(tmr_req, conn) < 0)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_INVALID, 1, 1,
- buf, cmd);
+ return iscsit_add_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
break;
default:
pr_err("Unknown TMR function: 0x%02x, protocol"
@@ -1928,15 +1921,13 @@
spin_unlock_bh(&conn->cmd_lock);
if (!(hdr->opcode & ISCSI_OP_IMMEDIATE)) {
- int cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
+ int cmdsn_ret = iscsit_sequence_cmd(conn, cmd, buf, hdr->cmdsn);
if (cmdsn_ret == CMDSN_HIGHER_THAN_EXP)
out_of_order_cmdsn = 1;
else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP)
return 0;
else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return -1;
}
iscsit_ack_from_expstatsn(conn, be32_to_cpu(hdr->exp_statsn));
@@ -1956,6 +1947,11 @@
* For connection recovery, this is also the default action for
* TMR TASK_REASSIGN.
*/
+ if (sess_ref) {
+ pr_debug("Handle TMR, using sess_ref=true check\n");
+ target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd);
+ }
+
iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
return 0;
}
@@ -1981,8 +1977,7 @@
pr_err("Unable to accept text parameter length: %u"
"greater than MaxXmitDataSegmentLength %u.\n",
payload_length, conn->conn_ops->MaxXmitDataSegmentLength);
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR, buf);
}
pr_debug("Got Text Request: ITT: 0x%08x, CmdSN: 0x%08x,"
@@ -2084,8 +2079,8 @@
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
- return iscsit_add_reject(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ return iscsit_add_reject(conn,
+ ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
cmd->iscsi_opcode = ISCSI_OP_TEXT;
cmd->i_state = ISTATE_SEND_TEXTRSP;
@@ -2103,11 +2098,10 @@
iscsit_ack_from_expstatsn(conn, be32_to_cpu(hdr->exp_statsn));
if (!(hdr->opcode & ISCSI_OP_IMMEDIATE)) {
- cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
+ cmdsn_ret = iscsit_sequence_cmd(conn, cmd,
+ (unsigned char *)hdr, hdr->cmdsn);
if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return -1;
return 0;
}
@@ -2292,14 +2286,11 @@
if (ret < 0)
return ret;
} else {
- cmdsn_ret = iscsit_sequence_cmd(conn, cmd, hdr->cmdsn);
- if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) {
+ cmdsn_ret = iscsit_sequence_cmd(conn, cmd, buf, hdr->cmdsn);
+ if (cmdsn_ret == CMDSN_LOWER_THAN_EXP)
logout_remove = 0;
- } else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER) {
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
- }
+ else if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER)
+ return -1;
}
return logout_remove;
@@ -2323,8 +2314,8 @@
if (!conn->sess->sess_ops->ErrorRecoveryLevel) {
pr_err("Initiator sent SNACK request while in"
" ErrorRecoveryLevel=0.\n");
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buf);
}
/*
* SNACK_DATA and SNACK_R2T are both 0, so check which function to
@@ -2348,13 +2339,13 @@
case ISCSI_FLAG_SNACK_TYPE_RDATA:
/* FIXME: Support R-Data SNACK */
pr_err("R-Data SNACK Not Supported.\n");
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buf);
default:
pr_err("Unknown SNACK type 0x%02x, protocol"
" error.\n", hdr->flags & 0x0f);
- return iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buf, conn);
+ return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buf);
}
return 0;
@@ -2426,14 +2417,14 @@
pr_err("Unable to recover from"
" Immediate Data digest failure while"
" in ERL=0.\n");
- iscsit_add_reject_from_cmd(
+ iscsit_reject_cmd(cmd,
ISCSI_REASON_DATA_DIGEST_ERROR,
- 1, 0, (unsigned char *)hdr, cmd);
+ (unsigned char *)hdr);
return IMMEDIATE_DATA_CANNOT_RECOVER;
} else {
- iscsit_add_reject_from_cmd(
+ iscsit_reject_cmd(cmd,
ISCSI_REASON_DATA_DIGEST_ERROR,
- 0, 0, (unsigned char *)hdr, cmd);
+ (unsigned char *)hdr);
return IMMEDIATE_DATA_ERL1_CRC_FAILURE;
}
} else {
@@ -2464,6 +2455,7 @@
{
struct iscsi_cmd *cmd;
struct iscsi_conn *conn_p;
+ bool found = false;
/*
* Only send a Asynchronous Message on connections whos network
@@ -2472,11 +2464,12 @@
list_for_each_entry(conn_p, &conn->sess->sess_conn_list, conn_list) {
if (conn_p->conn_state == TARG_CONN_STATE_LOGGED_IN) {
iscsit_inc_conn_usage_count(conn_p);
+ found = true;
break;
}
}
- if (!conn_p)
+ if (!found)
return;
cmd = iscsit_allocate_cmd(conn_p, GFP_ATOMIC);
@@ -3533,6 +3526,7 @@
struct iscsi_reject *hdr)
{
hdr->opcode = ISCSI_OP_REJECT;
+ hdr->reason = cmd->reject_reason;
hdr->flags |= ISCSI_FLAG_CMD_FINAL;
hton24(hdr->dlength, ISCSI_HDR_LEN);
hdr->ffffffff = cpu_to_be32(0xffffffff);
@@ -3662,7 +3656,7 @@
break;
case ISTATE_REMOVE:
spin_lock_bh(&conn->cmd_lock);
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, false);
@@ -3806,18 +3800,11 @@
case ISTATE_SEND_STATUS_RECOVERY:
case ISTATE_SEND_TEXTRSP:
case ISTATE_SEND_TASKMGTRSP:
+ case ISTATE_SEND_REJECT:
spin_lock_bh(&cmd->istate_lock);
cmd->i_state = ISTATE_SENT_STATUS;
spin_unlock_bh(&cmd->istate_lock);
break;
- case ISTATE_SEND_REJECT:
- if (cmd->cmd_flags & ICF_REJECT_FAIL_CONN) {
- cmd->cmd_flags &= ~ICF_REJECT_FAIL_CONN;
- complete(&cmd->reject_comp);
- goto err;
- }
- complete(&cmd->reject_comp);
- break;
default:
pr_err("Unknown Opcode: 0x%02x ITT:"
" 0x%08x, i_state: %d on CID: %hu\n",
@@ -3922,8 +3909,7 @@
case ISCSI_OP_SCSI_CMD:
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
- return iscsit_add_reject(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ goto reject;
ret = iscsit_handle_scsi_cmd(conn, cmd, buf);
break;
@@ -3935,16 +3921,14 @@
if (hdr->ttt == cpu_to_be32(0xFFFFFFFF)) {
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
- return iscsit_add_reject(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ goto reject;
}
ret = iscsit_handle_nop_out(conn, cmd, buf);
break;
case ISCSI_OP_SCSI_TMFUNC:
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
- return iscsit_add_reject(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ goto reject;
ret = iscsit_handle_task_mgt_cmd(conn, cmd, buf);
break;
@@ -3954,8 +3938,7 @@
case ISCSI_OP_LOGOUT:
cmd = iscsit_allocate_cmd(conn, GFP_KERNEL);
if (!cmd)
- return iscsit_add_reject(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, buf, conn);
+ goto reject;
ret = iscsit_handle_logout_cmd(conn, cmd, buf);
if (ret > 0)
@@ -3987,6 +3970,8 @@
}
return ret;
+reject:
+ return iscsit_add_reject(conn, ISCSI_REASON_BOOKMARK_NO_RESOURCES, buf);
}
int iscsi_target_rx_thread(void *arg)
@@ -4086,8 +4071,8 @@
(!(opcode & ISCSI_OP_LOGOUT)))) {
pr_err("Received illegal iSCSI Opcode: 0x%02x"
" while in Discovery Session, rejecting.\n", opcode);
- iscsit_add_reject(ISCSI_REASON_PROTOCOL_ERROR, 1,
- buffer, conn);
+ iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+ buffer);
goto transport_err;
}
@@ -4117,7 +4102,7 @@
spin_lock_bh(&conn->cmd_lock);
list_for_each_entry_safe(cmd, cmd_tmp, &conn->conn_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_increment_maxcmdsn(cmd, sess);
@@ -4151,18 +4136,26 @@
pr_debug("Closing iSCSI connection CID %hu on SID:"
" %u\n", conn->cid, sess->sid);
/*
- * Always up conn_logout_comp just in case the RX Thread is sleeping
- * and the logout response never got sent because the connection
- * failed.
+ * Always up conn_logout_comp for the traditional TCP case just in case
+ * the RX Thread in iscsi_target_rx_opcode() is sleeping and the logout
+ * response never got sent because the connection failed.
+ *
+ * However for iser-target, isert_wait4logout() is using conn_logout_comp
+ * to signal logout response TX interrupt completion. Go ahead and skip
+ * this for iser since isert_rx_opcode() does not wait on logout failure,
+ * and to avoid iscsi_conn pointer dereference in iser-target code.
*/
- complete(&conn->conn_logout_comp);
+ if (conn->conn_transport->transport_type == ISCSI_TCP)
+ complete(&conn->conn_logout_comp);
iscsi_release_thread_set(conn);
iscsit_stop_timers_for_cmds(conn);
iscsit_stop_nopin_response_timer(conn);
iscsit_stop_nopin_timer(conn);
- iscsit_free_queue_reqs_for_conn(conn);
+
+ if (conn->conn_transport->iscsit_wait_conn)
+ conn->conn_transport->iscsit_wait_conn(conn);
/*
* During Connection recovery drop unacknowledged out of order
@@ -4180,6 +4173,7 @@
iscsit_clear_ooo_cmdsns_for_conn(conn);
iscsit_release_commands_from_conn(conn);
}
+ iscsit_free_queue_reqs_for_conn(conn);
/*
* Handle decrementing session or connection usage count if
@@ -4465,6 +4459,7 @@
{
struct iscsi_conn *l_conn;
struct iscsi_session *sess = conn->sess;
+ bool conn_found = false;
if (!sess)
return;
@@ -4473,12 +4468,13 @@
list_for_each_entry(l_conn, &sess->sess_conn_list, conn_list) {
if (l_conn->cid == cid) {
iscsit_inc_conn_usage_count(l_conn);
+ conn_found = true;
break;
}
}
spin_unlock_bh(&sess->conn_lock);
- if (!l_conn)
+ if (!conn_found)
return;
if (l_conn->sock)
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index a0050b2..2c437cb 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -15,7 +15,7 @@
extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *,
struct iscsi_portal_group *);
extern int iscsit_del_np(struct iscsi_np *);
-extern int iscsit_add_reject_from_cmd(u8, int, int, unsigned char *, struct iscsi_cmd *);
+extern int iscsit_reject_cmd(struct iscsi_cmd *cmd, u8, unsigned char *);
extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *);
extern int iscsit_logout_closesession(struct iscsi_cmd *, struct iscsi_conn *);
extern int iscsit_logout_closeconnection(struct iscsi_cmd *, struct iscsi_conn *);
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index cee1754..3c9a8df 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -148,6 +148,7 @@
unsigned char client_digest[MD5_SIGNATURE_SIZE];
unsigned char server_digest[MD5_SIGNATURE_SIZE];
unsigned char chap_n[MAX_CHAP_N_SIZE], chap_r[MAX_RESPONSE_LENGTH];
+ size_t compare_len;
struct iscsi_chap *chap = conn->auth_protocol;
struct crypto_hash *tfm;
struct hash_desc desc;
@@ -186,7 +187,9 @@
goto out;
}
- if (memcmp(chap_n, auth->userid, strlen(auth->userid)) != 0) {
+ /* Include the terminating NULL in the compare */
+ compare_len = strlen(auth->userid) + 1;
+ if (strncmp(chap_n, auth->userid, compare_len) != 0) {
pr_err("CHAP_N values do not match!\n");
goto out;
}
@@ -313,6 +316,16 @@
goto out;
}
/*
+ * During mutual authentication, the CHAP_C generated by the
+ * initiator must not match the original CHAP_C generated by
+ * the target.
+ */
+ if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+ pr_err("initiator CHAP_C matches target CHAP_C, failing"
+ " login attempt\n");
+ goto out;
+ }
+ /*
* Generate CHAP_N and CHAP_R for mutual authentication.
*/
tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 8d8b3ff..c45b336 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -474,7 +474,7 @@
if (!capable(CAP_SYS_ADMIN)) \
return -EPERM; \
\
- snprintf(auth->name, PAGE_SIZE, "%s", page); \
+ snprintf(auth->name, sizeof(auth->name), "%s", page); \
if (!strncmp("NULL", auth->name, 4)) \
auth->naf_flags &= ~flags; \
else \
@@ -1650,6 +1650,11 @@
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
cmd->i_state = ISTATE_SEND_STATUS;
+
+ if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
+ iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
+ return 0;
+ }
cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
return 0;
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 60ec4b9..e117870 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -132,7 +132,6 @@
ICF_CONTIG_MEMORY = 0x00000020,
ICF_ATTACHED_TO_RQUEUE = 0x00000040,
ICF_OOO_CMDSN = 0x00000080,
- ICF_REJECT_FAIL_CONN = 0x00000100,
};
/* struct iscsi_cmd->i_state */
@@ -366,6 +365,8 @@
u8 maxcmdsn_inc;
/* Immediate Unsolicited Dataout */
u8 unsolicited_data;
+ /* Reject reason code */
+ u8 reject_reason;
/* CID contained in logout PDU when opcode == ISCSI_INIT_LOGOUT_CMND */
u16 logout_cid;
/* Command flags */
@@ -446,7 +447,6 @@
struct list_head datain_list;
/* R2T List */
struct list_head cmd_r2t_list;
- struct completion reject_comp;
/* Timer for DataOUT */
struct timer_list dataout_timer;
/* Iovecs for SCSI data payload RX/TX w/ kernel level sockets */
@@ -760,6 +760,7 @@
int np_ip_proto;
int np_sock_type;
enum np_thread_state_table np_thread_state;
+ bool enabled;
enum iscsi_timer_flags_table np_login_timer_flags;
u32 np_exports;
enum np_flags_table np_flags;
diff --git a/drivers/target/iscsi/iscsi_target_device.c b/drivers/target/iscsi/iscsi_target_device.c
index 1b74033..4edcc47 100644
--- a/drivers/target/iscsi/iscsi_target_device.c
+++ b/drivers/target/iscsi/iscsi_target_device.c
@@ -60,11 +60,7 @@
cmd->maxcmdsn_inc = 1;
- if (!mutex_trylock(&sess->cmdsn_mutex)) {
- sess->max_cmd_sn += 1;
- pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
- return;
- }
+ mutex_lock(&sess->cmdsn_mutex);
sess->max_cmd_sn += 1;
pr_debug("Updated MaxCmdSN to 0x%08x\n", sess->max_cmd_sn);
mutex_unlock(&sess->cmdsn_mutex);
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index dcb199d..08bd878 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -746,13 +746,12 @@
if (!conn->sess->sess_ops->ErrorRecoveryLevel) {
pr_err("Unable to recover from DataOUT CRC"
" failure while ERL=0, closing session.\n");
- iscsit_add_reject_from_cmd(ISCSI_REASON_DATA_DIGEST_ERROR,
- 1, 0, buf, cmd);
+ iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR,
+ buf);
return DATAOUT_CANNOT_RECOVER;
}
- iscsit_add_reject_from_cmd(ISCSI_REASON_DATA_DIGEST_ERROR,
- 0, 0, buf, cmd);
+ iscsit_reject_cmd(cmd, ISCSI_REASON_DATA_DIGEST_ERROR, buf);
return iscsit_dataout_post_crc_failed(cmd, buf);
}
}
@@ -909,6 +908,7 @@
wait_for_completion(&conn->conn_wait_comp);
complete(&conn->conn_post_wait_comp);
}
+EXPORT_SYMBOL(iscsit_cause_connection_reinstatement);
void iscsit_fall_back_to_erl0(struct iscsi_session *sess)
{
diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c
index 40d9dbc..586c268 100644
--- a/drivers/target/iscsi/iscsi_target_erl1.c
+++ b/drivers/target/iscsi/iscsi_target_erl1.c
@@ -162,9 +162,8 @@
" protocol error.\n", cmd->init_task_tag, begrun,
(begrun + runlength), cmd->acked_data_sn);
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd,
+ ISCSI_REASON_PROTOCOL_ERROR, buf);
}
if (runlength) {
@@ -173,8 +172,8 @@
" with BegRun: 0x%08x, RunLength: 0x%08x, exceeds"
" current R2TSN: 0x%08x, protocol error.\n",
cmd->init_task_tag, begrun, runlength, cmd->r2t_sn);
- return iscsit_add_reject_from_cmd(
- ISCSI_REASON_BOOKMARK_INVALID, 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd,
+ ISCSI_REASON_BOOKMARK_INVALID, buf);
}
last_r2tsn = (begrun + runlength);
} else
@@ -433,8 +432,7 @@
" protocol error.\n", cmd->init_task_tag, begrun,
(begrun + runlength), cmd->acked_data_sn);
- return iscsit_add_reject_from_cmd(ISCSI_REASON_PROTOCOL_ERROR,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf);
}
/*
@@ -445,14 +443,14 @@
pr_err("Initiator requesting BegRun: 0x%08x, RunLength"
": 0x%08x greater than maximum DataSN: 0x%08x.\n",
begrun, runlength, (cmd->data_sn - 1));
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_INVALID,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_INVALID,
+ buf);
}
dr = iscsit_allocate_datain_req();
if (!dr)
- return iscsit_add_reject_from_cmd(ISCSI_REASON_BOOKMARK_NO_RESOURCES,
- 1, 0, buf, cmd);
+ return iscsit_reject_cmd(cmd, ISCSI_REASON_BOOKMARK_NO_RESOURCES,
+ buf);
dr->data_sn = dr->begrun = begrun;
dr->runlength = runlength;
@@ -1090,7 +1088,7 @@
ooo_cmdsn = iscsit_allocate_ooo_cmdsn();
if (!ooo_cmdsn)
- return CMDSN_ERROR_CANNOT_RECOVER;
+ return -ENOMEM;
ooo_cmdsn->cmd = cmd;
ooo_cmdsn->batch_count = (batch) ?
@@ -1101,10 +1099,10 @@
if (iscsit_attach_ooo_cmdsn(sess, ooo_cmdsn) < 0) {
kmem_cache_free(lio_ooo_cache, ooo_cmdsn);
- return CMDSN_ERROR_CANNOT_RECOVER;
+ return -ENOMEM;
}
- return CMDSN_HIGHER_THAN_EXP;
+ return 0;
}
static int iscsit_set_dataout_timeout_values(
diff --git a/drivers/target/iscsi/iscsi_target_erl2.c b/drivers/target/iscsi/iscsi_target_erl2.c
index 45a5afd..0d2d013 100644
--- a/drivers/target/iscsi/iscsi_target_erl2.c
+++ b/drivers/target/iscsi/iscsi_target_erl2.c
@@ -140,7 +140,7 @@
list_for_each_entry_safe(cmd, cmd_tmp,
&cr->conn_recovery_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
cmd->conn = NULL;
spin_unlock(&cr->conn_recovery_cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -162,7 +162,7 @@
list_for_each_entry_safe(cmd, cmd_tmp,
&cr->conn_recovery_cmd_list, i_conn_node) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
cmd->conn = NULL;
spin_unlock(&cr->conn_recovery_cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -218,7 +218,7 @@
}
cr = cmd->cr;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
return --cr->cmd_count;
}
@@ -299,7 +299,7 @@
if (!(cmd->cmd_flags & ICF_OOO_CMDSN))
continue;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
@@ -337,7 +337,7 @@
/*
* Only perform connection recovery on ISCSI_OP_SCSI_CMD or
* ISCSI_OP_NOOP_OUT opcodes. For all other opcodes call
- * list_del(&cmd->i_conn_node); to release the command to the
+ * list_del_init(&cmd->i_conn_node); to release the command to the
* session pool and remove it from the connection's list.
*
* Also stop the DataOUT timer, which will be restarted after
@@ -353,7 +353,7 @@
" CID: %hu\n", cmd->iscsi_opcode,
cmd->init_task_tag, cmd->cmd_sn, conn->cid);
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
spin_lock_bh(&conn->cmd_lock);
@@ -373,7 +373,7 @@
*/
if (!(cmd->cmd_flags & ICF_OOO_CMDSN) && !cmd->immediate_cmd &&
iscsi_sna_gte(cmd->cmd_sn, conn->sess->exp_cmd_sn)) {
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_cmd(cmd, true);
spin_lock_bh(&conn->cmd_lock);
@@ -395,7 +395,7 @@
cmd->sess = conn->sess;
- list_del(&cmd->i_conn_node);
+ list_del_init(&cmd->i_conn_node);
spin_unlock_bh(&conn->cmd_lock);
iscsit_free_all_datain_reqs(cmd);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 3402241..0493e8b1 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -250,6 +250,28 @@
mutex_unlock(&auth_id_lock);
}
+static __printf(2, 3) int iscsi_change_param_sprintf(
+ struct iscsi_conn *conn,
+ const char *fmt, ...)
+{
+ va_list args;
+ unsigned char buf[64];
+
+ memset(buf, 0, sizeof buf);
+
+ va_start(args, fmt);
+ vsnprintf(buf, sizeof buf, fmt, args);
+ va_end(args);
+
+ if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
+ iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+ ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ return -1;
+ }
+
+ return 0;
+}
+
/*
* This is the leading connection of a new session,
* or session reinstatement.
@@ -339,7 +361,6 @@
{
struct iscsi_node_attrib *na;
struct iscsi_session *sess = conn->sess;
- unsigned char buf[32];
bool iser = false;
sess->tpg = conn->tpg;
@@ -380,26 +401,16 @@
*
* In our case, we have already located the struct iscsi_tiqn at this point.
*/
- memset(buf, 0, 32);
- sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
- if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
- iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
- ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
return -1;
- }
/*
* Workaround for Initiators that have broken connection recovery logic.
*
* "We would really like to get rid of this." Linux-iSCSI.org team
*/
- memset(buf, 0, 32);
- sprintf(buf, "ErrorRecoveryLevel=%d", na->default_erl);
- if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
- iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
- ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ if (iscsi_change_param_sprintf(conn, "ErrorRecoveryLevel=%d", na->default_erl))
return -1;
- }
if (iscsi_login_disable_FIM_keys(conn->param_list, conn) < 0)
return -1;
@@ -411,12 +422,9 @@
unsigned long mrdsl, off;
int rc;
- sprintf(buf, "RDMAExtensions=Yes");
- if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
- iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
- ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ if (iscsi_change_param_sprintf(conn, "RDMAExtensions=Yes"))
return -1;
- }
+
/*
* Make MaxRecvDataSegmentLength PAGE_SIZE aligned for
* Immediate Data + Unsolicitied Data-OUT if necessary..
@@ -446,12 +454,8 @@
pr_warn("Aligning ISER MaxRecvDataSegmentLength: %lu down"
" to PAGE_SIZE\n", mrdsl);
- sprintf(buf, "MaxRecvDataSegmentLength=%lu\n", mrdsl);
- if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
- iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
- ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ if (iscsi_change_param_sprintf(conn, "MaxRecvDataSegmentLength=%lu\n", mrdsl))
return -1;
- }
}
return 0;
@@ -593,13 +597,8 @@
*
* In our case, we have already located the struct iscsi_tiqn at this point.
*/
- memset(buf, 0, 32);
- sprintf(buf, "TargetPortalGroupTag=%hu", ISCSI_TPG_S(sess)->tpgt);
- if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
- iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
- ISCSI_LOGIN_STATUS_NO_RESOURCES);
+ if (iscsi_change_param_sprintf(conn, "TargetPortalGroupTag=%hu", sess->tpg->tpgt))
return -1;
- }
return iscsi_login_disable_FIM_keys(conn->param_list, conn);
}
@@ -984,6 +983,7 @@
}
np->np_transport = t;
+ np->enabled = true;
return 0;
}
@@ -1163,12 +1163,11 @@
if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
spin_unlock_bh(&np->np_thread_lock);
complete(&np->np_restart_comp);
- if (ret == -ENODEV) {
- iscsit_put_transport(conn->conn_transport);
- kfree(conn);
- conn = NULL;
+ iscsit_put_transport(conn->conn_transport);
+ kfree(conn);
+ conn = NULL;
+ if (ret == -ENODEV)
goto out;
- }
/* Get another socket */
return 1;
}
@@ -1361,6 +1360,9 @@
conn->sock = NULL;
}
+ if (conn->conn_transport->iscsit_wait_conn)
+ conn->conn_transport->iscsit_wait_conn(conn);
+
if (conn->conn_transport->iscsit_free_conn)
conn->conn_transport->iscsit_free_conn(conn);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index cd5018f..72d9dec 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -90,7 +90,7 @@
if (len < 0)
return -1;
- if (len > max_length) {
+ if (len >= max_length) {
pr_err("Length of input: %d exceeds max_length:"
" %d\n", len, max_length);
return -1;
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e382221..30be6c9 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -603,7 +603,7 @@
param_list = kzalloc(sizeof(struct iscsi_param_list), GFP_KERNEL);
if (!param_list) {
pr_err("Unable to allocate memory for struct iscsi_param_list.\n");
- goto err_out;
+ return -1;
}
INIT_LIST_HEAD(¶m_list->param_list);
INIT_LIST_HEAD(¶m_list->extra_response_list);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 439260b..75a4e83 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -138,7 +138,7 @@
list_for_each_entry(tpg, &tiqn->tiqn_tpg_list, tpg_list) {
spin_lock(&tpg->tpg_state_lock);
- if (tpg->tpg_state == TPG_STATE_FREE) {
+ if (tpg->tpg_state != TPG_STATE_ACTIVE) {
spin_unlock(&tpg->tpg_state_lock);
continue;
}
@@ -175,13 +175,16 @@
static void iscsit_clear_tpg_np_login_thread(
struct iscsi_tpg_np *tpg_np,
- struct iscsi_portal_group *tpg)
+ struct iscsi_portal_group *tpg,
+ bool shutdown)
{
if (!tpg_np->tpg_np) {
pr_err("struct iscsi_tpg_np->tpg_np is NULL!\n");
return;
}
+ if (shutdown)
+ tpg_np->tpg_np->enabled = false;
iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg);
}
@@ -197,7 +200,7 @@
continue;
}
spin_unlock(&tpg->tpg_np_lock);
- iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+ iscsit_clear_tpg_np_login_thread(tpg_np, tpg, false);
spin_lock(&tpg->tpg_np_lock);
}
spin_unlock(&tpg->tpg_np_lock);
@@ -520,7 +523,7 @@
struct iscsi_portal_group *tpg,
struct iscsi_np *np)
{
- iscsit_clear_tpg_np_login_thread(tpg_np, tpg);
+ iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true);
pr_debug("CORE[%s] - Removed Network Portal: %s:%hu,%hu on %s\n",
tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt,
diff --git a/drivers/target/iscsi/iscsi_target_tq.c b/drivers/target/iscsi/iscsi_target_tq.c
index 8128952..bd53364 100644
--- a/drivers/target/iscsi/iscsi_target_tq.c
+++ b/drivers/target/iscsi/iscsi_target_tq.c
@@ -26,36 +26,22 @@
#include "iscsi_target_tq.h"
#include "iscsi_target.h"
-static LIST_HEAD(active_ts_list);
static LIST_HEAD(inactive_ts_list);
-static DEFINE_SPINLOCK(active_ts_lock);
static DEFINE_SPINLOCK(inactive_ts_lock);
static DEFINE_SPINLOCK(ts_bitmap_lock);
-static void iscsi_add_ts_to_active_list(struct iscsi_thread_set *ts)
-{
- spin_lock(&active_ts_lock);
- list_add_tail(&ts->ts_list, &active_ts_list);
- iscsit_global->active_ts++;
- spin_unlock(&active_ts_lock);
-}
-
static void iscsi_add_ts_to_inactive_list(struct iscsi_thread_set *ts)
{
+ if (!list_empty(&ts->ts_list)) {
+ WARN_ON(1);
+ return;
+ }
spin_lock(&inactive_ts_lock);
list_add_tail(&ts->ts_list, &inactive_ts_list);
iscsit_global->inactive_ts++;
spin_unlock(&inactive_ts_lock);
}
-static void iscsi_del_ts_from_active_list(struct iscsi_thread_set *ts)
-{
- spin_lock(&active_ts_lock);
- list_del(&ts->ts_list);
- iscsit_global->active_ts--;
- spin_unlock(&active_ts_lock);
-}
-
static struct iscsi_thread_set *iscsi_get_ts_from_inactive_list(void)
{
struct iscsi_thread_set *ts;
@@ -68,7 +54,7 @@
ts = list_first_entry(&inactive_ts_list, struct iscsi_thread_set, ts_list);
- list_del(&ts->ts_list);
+ list_del_init(&ts->ts_list);
iscsit_global->inactive_ts--;
spin_unlock(&inactive_ts_lock);
@@ -219,8 +205,6 @@
void iscsi_activate_thread_set(struct iscsi_conn *conn, struct iscsi_thread_set *ts)
{
- iscsi_add_ts_to_active_list(ts);
-
spin_lock_bh(&ts->ts_state_lock);
conn->thread_set = ts;
ts->conn = conn;
@@ -423,7 +407,6 @@
if (ts->delay_inactive && (--ts->thread_count == 0)) {
spin_unlock_bh(&ts->ts_state_lock);
- iscsi_del_ts_from_active_list(ts);
if (!iscsit_global->in_shutdown)
iscsi_deallocate_extra_thread_sets();
@@ -476,7 +459,6 @@
if (ts->delay_inactive && (--ts->thread_count == 0)) {
spin_unlock_bh(&ts->ts_state_lock);
- iscsi_del_ts_from_active_list(ts);
if (!iscsit_global->in_shutdown)
iscsi_deallocate_extra_thread_sets();
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 08a3bac..016e882 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -178,7 +178,6 @@
INIT_LIST_HEAD(&cmd->i_conn_node);
INIT_LIST_HEAD(&cmd->datain_list);
INIT_LIST_HEAD(&cmd->cmd_r2t_list);
- init_completion(&cmd->reject_comp);
spin_lock_init(&cmd->datain_lock);
spin_lock_init(&cmd->dataout_timeout_lock);
spin_lock_init(&cmd->istate_lock);
@@ -284,13 +283,12 @@
* Commands may be received out of order if MC/S is in use.
* Ensure they are executed in CmdSN order.
*/
-int iscsit_sequence_cmd(
- struct iscsi_conn *conn,
- struct iscsi_cmd *cmd,
- __be32 cmdsn)
+int iscsit_sequence_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ unsigned char *buf, __be32 cmdsn)
{
- int ret;
- int cmdsn_ret;
+ int ret, cmdsn_ret;
+ bool reject = false;
+ u8 reason = ISCSI_REASON_BOOKMARK_NO_RESOURCES;
mutex_lock(&conn->sess->cmdsn_mutex);
@@ -300,9 +298,19 @@
ret = iscsit_execute_cmd(cmd, 0);
if ((ret >= 0) && !list_empty(&conn->sess->sess_ooo_cmdsn_list))
iscsit_execute_ooo_cmdsns(conn->sess);
+ else if (ret < 0) {
+ reject = true;
+ ret = CMDSN_ERROR_CANNOT_RECOVER;
+ }
break;
case CMDSN_HIGHER_THAN_EXP:
ret = iscsit_handle_ooo_cmdsn(conn->sess, cmd, be32_to_cpu(cmdsn));
+ if (ret < 0) {
+ reject = true;
+ ret = CMDSN_ERROR_CANNOT_RECOVER;
+ break;
+ }
+ ret = CMDSN_HIGHER_THAN_EXP;
break;
case CMDSN_LOWER_THAN_EXP:
cmd->i_state = ISTATE_REMOVE;
@@ -310,11 +318,16 @@
ret = cmdsn_ret;
break;
default:
+ reason = ISCSI_REASON_PROTOCOL_ERROR;
+ reject = true;
ret = cmdsn_ret;
break;
}
mutex_unlock(&conn->sess->cmdsn_mutex);
+ if (reject)
+ iscsit_reject_cmd(cmd, reason, buf);
+
return ret;
}
EXPORT_SYMBOL(iscsit_sequence_cmd);
@@ -721,7 +734,7 @@
* Fallthrough
*/
case ISCSI_OP_SCSI_TMFUNC:
- rc = transport_generic_free_cmd(&cmd->se_cmd, 1);
+ rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
__iscsit_free_cmd(cmd, true, shutdown);
target_put_sess_cmd(se_cmd->se_sess, se_cmd);
@@ -737,7 +750,7 @@
se_cmd = &cmd->se_cmd;
__iscsit_free_cmd(cmd, true, shutdown);
- rc = transport_generic_free_cmd(&cmd->se_cmd, 1);
+ rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
if (!rc && shutdown && se_cmd->se_sess) {
__iscsit_free_cmd(cmd, true, shutdown);
target_put_sess_cmd(se_cmd->se_sess, se_cmd);
@@ -1275,6 +1288,8 @@
login->login_failed = 1;
iscsit_collect_login_stats(conn, status_class, status_detail);
+ memset(&login->rsp[0], 0, ISCSI_HDR_LEN);
+
hdr = (struct iscsi_login_rsp *)&login->rsp[0];
hdr->opcode = ISCSI_OP_LOGIN_RSP;
hdr->status_class = status_class;
@@ -1334,15 +1349,15 @@
struct iscsi_conn *conn,
struct iscsi_data_count *count)
{
- int data = count->data_length, total_tx = 0, tx_loop = 0, iov_len;
+ int ret, iov_len;
struct kvec *iov_p;
struct msghdr msg;
if (!conn || !conn->sock || !conn->conn_ops)
return -1;
- if (data <= 0) {
- pr_err("Data length is: %d\n", data);
+ if (count->data_length <= 0) {
+ pr_err("Data length is: %d\n", count->data_length);
return -1;
}
@@ -1351,20 +1366,16 @@
iov_p = count->iov;
iov_len = count->iov_count;
- while (total_tx < data) {
- tx_loop = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len,
- (data - total_tx));
- if (tx_loop <= 0) {
- pr_debug("tx_loop: %d total_tx %d\n",
- tx_loop, total_tx);
- return tx_loop;
- }
- total_tx += tx_loop;
- pr_debug("tx_loop: %d, total_tx: %d, data: %d\n",
- tx_loop, total_tx, data);
+ ret = kernel_sendmsg(conn->sock, &msg, iov_p, iov_len,
+ count->data_length);
+ if (ret != count->data_length) {
+ pr_err("Unexpected ret: %d send data %d\n",
+ ret, count->data_length);
+ return -EPIPE;
}
+ pr_debug("ret: %d, sent data: %d\n", ret, count->data_length);
- return total_tx;
+ return ret;
}
int rx_data(
diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h
index a442265..e4fc34a 100644
--- a/drivers/target/iscsi/iscsi_target_util.h
+++ b/drivers/target/iscsi/iscsi_target_util.h
@@ -13,7 +13,8 @@
extern struct iscsi_seq *iscsit_get_seq_holder_for_datain(struct iscsi_cmd *, u32);
extern struct iscsi_seq *iscsit_get_seq_holder_for_r2t(struct iscsi_cmd *);
extern struct iscsi_r2t *iscsit_get_holder_for_r2tsn(struct iscsi_cmd *, u32);
-int iscsit_sequence_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, __be32 cmdsn);
+extern int iscsit_sequence_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
+ unsigned char * ,__be32 cmdsn);
extern int iscsit_check_unsolicited_dataout(struct iscsi_cmd *, unsigned char *);
extern struct iscsi_cmd *iscsit_find_cmd_from_itt(struct iscsi_conn *, itt_t);
extern struct iscsi_cmd *iscsit_find_cmd_from_itt_or_dump(struct iscsi_conn *,
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 7c90814..9c02eb4 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -179,7 +179,7 @@
goto out_done;
}
- tl_nexus = tl_hba->tl_nexus;
+ tl_nexus = tl_tpg->tl_nexus;
if (!tl_nexus) {
scmd_printk(KERN_ERR, sc, "TCM_Loop I_T Nexus"
" does not exist\n");
@@ -258,20 +258,20 @@
*/
tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
/*
+ * Locate the tl_tpg and se_tpg pointers from TargetID in sc->device->id
+ */
+ tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
+ se_tpg = &tl_tpg->tl_se_tpg;
+ /*
* Locate the tl_nexus and se_sess pointers
*/
- tl_nexus = tl_hba->tl_nexus;
+ tl_nexus = tl_tpg->tl_nexus;
if (!tl_nexus) {
pr_err("Unable to perform device reset without"
" active I_T Nexus\n");
return FAILED;
}
se_sess = tl_nexus->se_sess;
- /*
- * Locate the tl_tpg and se_tpg pointers from TargetID in sc->device->id
- */
- tl_tpg = &tl_hba->tl_hba_tpgs[sc->device->id];
- se_tpg = &tl_tpg->tl_se_tpg;
tl_cmd = kmem_cache_zalloc(tcm_loop_cmd_cache, GFP_KERNEL);
if (!tl_cmd) {
@@ -879,8 +879,8 @@
struct tcm_loop_nexus *tl_nexus;
int ret = -ENOMEM;
- if (tl_tpg->tl_hba->tl_nexus) {
- pr_debug("tl_tpg->tl_hba->tl_nexus already exists\n");
+ if (tl_tpg->tl_nexus) {
+ pr_debug("tl_tpg->tl_nexus already exists\n");
return -EEXIST;
}
se_tpg = &tl_tpg->tl_se_tpg;
@@ -915,7 +915,7 @@
*/
__transport_register_session(se_tpg, tl_nexus->se_sess->se_node_acl,
tl_nexus->se_sess, tl_nexus);
- tl_tpg->tl_hba->tl_nexus = tl_nexus;
+ tl_tpg->tl_nexus = tl_nexus;
pr_debug("TCM_Loop_ConfigFS: Established I_T Nexus to emulated"
" %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba),
name);
@@ -931,9 +931,8 @@
{
struct se_session *se_sess;
struct tcm_loop_nexus *tl_nexus;
- struct tcm_loop_hba *tl_hba = tpg->tl_hba;
- tl_nexus = tpg->tl_hba->tl_nexus;
+ tl_nexus = tpg->tl_nexus;
if (!tl_nexus)
return -ENODEV;
@@ -949,13 +948,13 @@
}
pr_debug("TCM_Loop_ConfigFS: Removing I_T Nexus to emulated"
- " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tl_hba),
+ " %s Initiator Port: %s\n", tcm_loop_dump_proto_id(tpg->tl_hba),
tl_nexus->se_sess->se_node_acl->initiatorname);
/*
* Release the SCSI I_T Nexus to the emulated SAS Target Port
*/
transport_deregister_session(tl_nexus->se_sess);
- tpg->tl_hba->tl_nexus = NULL;
+ tpg->tl_nexus = NULL;
kfree(tl_nexus);
return 0;
}
@@ -971,7 +970,7 @@
struct tcm_loop_nexus *tl_nexus;
ssize_t ret;
- tl_nexus = tl_tpg->tl_hba->tl_nexus;
+ tl_nexus = tl_tpg->tl_nexus;
if (!tl_nexus)
return -ENODEV;
diff --git a/drivers/target/loopback/tcm_loop.h b/drivers/target/loopback/tcm_loop.h
index dd7a84e..4ed8588 100644
--- a/drivers/target/loopback/tcm_loop.h
+++ b/drivers/target/loopback/tcm_loop.h
@@ -25,11 +25,6 @@
};
struct tcm_loop_nexus {
- int it_nexus_active;
- /*
- * Pointer to Linux/SCSI HBA from linux/include/scsi_host.h
- */
- struct scsi_host *sh;
/*
* Pointer to TCM session for I_T Nexus
*/
@@ -45,6 +40,7 @@
atomic_t tl_tpg_port_count;
struct se_portal_group tl_se_tpg;
struct tcm_loop_hba *tl_hba;
+ struct tcm_loop_nexus *tl_nexus;
};
struct tcm_loop_hba {
@@ -53,7 +49,6 @@
struct se_hba_s *se_hba;
struct se_lun *tl_hba_lun;
struct se_port *tl_hba_lun_sep;
- struct tcm_loop_nexus *tl_nexus;
struct device dev;
struct Scsi_Host *sh;
struct tcm_loop_tpg tl_hba_tpgs[TL_TPGS_PER_HBA];
diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c
index cbe48ab..df58a67 100644
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -409,7 +409,16 @@
case REPORT_LUNS:
case RECEIVE_DIAGNOSTIC:
case SEND_DIAGNOSTIC:
+ case READ_CAPACITY:
return 0;
+ case SERVICE_ACTION_IN:
+ switch (cdb[1] & 0x1f) {
+ case SAI_READ_CAPACITY_16:
+ return 0;
+ default:
+ *alua_ascq = ASCQ_04H_ALUA_TG_PT_STANDBY;
+ return 1;
+ }
case MAINTENANCE_IN:
switch (cdb[1] & 0x1f) {
case MI_REPORT_TARGET_PGS:
@@ -730,7 +739,7 @@
if (ret < 0)
pr_err("Error writing ALUA metadata file: %s\n", path);
fput(file);
- return ret ? -EIO : 0;
+ return (ret < 0) ? -EIO : 0;
}
/*
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 4a8bd36..8cda408 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -2034,6 +2034,11 @@
" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
return -EINVAL;
}
+ if (!(dev->dev_flags & DF_CONFIGURED)) {
+ pr_err("Unable to set alua_access_state while device is"
+ " not configured\n");
+ return -ENODEV;
+ }
ret = strict_strtoul(page, 0, &tmp);
if (ret < 0) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 4630481..4deb0c9 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -614,6 +614,7 @@
dev->export_count--;
spin_unlock(&hba->device_lock);
+ lun->lun_sep = NULL;
lun->lun_se_dev = NULL;
}
@@ -796,10 +797,10 @@
pr_err("emulate_write_cache not supported for pSCSI\n");
return -EINVAL;
}
- if (dev->transport->get_write_cache) {
- pr_warn("emulate_write_cache cannot be changed when underlying"
- " HW reports WriteCacheEnabled, ignoring request\n");
- return 0;
+ if (flag &&
+ dev->transport->get_write_cache) {
+ pr_err("emulate_write_cache not supported for this device\n");
+ return -EINVAL;
}
dev->dev_attrib.emulate_write_cache = flag;
@@ -1036,10 +1037,10 @@
" changed for TCM/pSCSI\n", dev);
return -EINVAL;
}
- if (optimal_sectors > dev->dev_attrib.fabric_max_sectors) {
+ if (optimal_sectors > dev->dev_attrib.hw_max_sectors) {
pr_err("dev[%p]: Passed optimal_sectors %u cannot be"
- " greater than fabric_max_sectors: %u\n", dev,
- optimal_sectors, dev->dev_attrib.fabric_max_sectors);
+ " greater than hw_max_sectors: %u\n", dev,
+ optimal_sectors, dev->dev_attrib.hw_max_sectors);
return -EINVAL;
}
@@ -1078,6 +1079,11 @@
dev->dev_attrib.block_size = block_size;
pr_debug("dev[%p]: SE Device block_size changed to %u\n",
dev, block_size);
+
+ if (dev->dev_attrib.max_bytes_per_io)
+ dev->dev_attrib.hw_max_sectors =
+ dev->dev_attrib.max_bytes_per_io / block_size;
+
return 0;
}
@@ -1287,7 +1293,8 @@
* Check to see if there are any existing persistent reservation APTPL
* pre-registrations that need to be enabled for this LUN ACL..
*/
- core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, lacl);
+ core_scsi3_check_aptpl_registration(lun->lun_se_dev, tpg, lun, nacl,
+ lacl->mapped_lun);
return 0;
}
@@ -1435,7 +1442,6 @@
DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT;
dev->dev_attrib.max_write_same_len = DA_MAX_WRITE_SAME_LEN;
dev->dev_attrib.fabric_max_sectors = DA_FABRIC_MAX_SECTORS;
- dev->dev_attrib.optimal_sectors = DA_FABRIC_MAX_SECTORS;
return dev;
}
@@ -1468,6 +1474,7 @@
dev->dev_attrib.hw_max_sectors =
se_dev_align_max_sectors(dev->dev_attrib.hw_max_sectors,
dev->dev_attrib.hw_block_size);
+ dev->dev_attrib.optimal_sectors = dev->dev_attrib.hw_max_sectors;
dev->dev_index = scsi_get_new_index(SCSI_DEVICE_INDEX);
dev->creation_time = get_jiffies_64();
diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index b11890d..8baaa0a 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c
@@ -66,9 +66,8 @@
pr_debug("CORE_HBA[%d] - TCM FILEIO HBA Driver %s on Generic"
" Target Core Stack %s\n", hba->hba_id, FD_VERSION,
TARGET_CORE_MOD_VERSION);
- pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic"
- " MaxSectors: %u\n",
- hba->hba_id, fd_host->fd_host_id, FD_MAX_SECTORS);
+ pr_debug("CORE_HBA[%d] - Attached FILEIO HBA: %u to Generic\n",
+ hba->hba_id, fd_host->fd_host_id);
return 0;
}
@@ -220,7 +219,8 @@
}
dev->dev_attrib.hw_block_size = fd_dev->fd_block_size;
- dev->dev_attrib.hw_max_sectors = FD_MAX_SECTORS;
+ dev->dev_attrib.max_bytes_per_io = FD_MAX_BYTES;
+ dev->dev_attrib.hw_max_sectors = FD_MAX_BYTES / fd_dev->fd_block_size;
dev->dev_attrib.hw_queue_depth = FD_MAX_DEVICE_QUEUE_DEPTH;
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
@@ -554,7 +554,16 @@
enum dma_data_direction data_direction = cmd->data_direction;
struct se_device *dev = cmd->se_dev;
int ret = 0;
-
+ /*
+ * We are currently limited by the number of iovecs (2048) per
+ * single vfs_[writev,readv] call.
+ */
+ if (cmd->data_length > FD_MAX_BYTES) {
+ pr_err("FILEIO: Not able to process I/O of %u bytes due to"
+ "FD_MAX_BYTES: %u iovec count limitiation\n",
+ cmd->data_length, FD_MAX_BYTES);
+ return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ }
/*
* Call vectorized fileio functions to map struct scatterlist
* physical memory addresses to struct iovec virtual memory.
diff --git a/drivers/target/target_core_file.h b/drivers/target/target_core_file.h
index 37ffc5b..d7772c1 100644
--- a/drivers/target/target_core_file.h
+++ b/drivers/target/target_core_file.h
@@ -7,7 +7,10 @@
#define FD_DEVICE_QUEUE_DEPTH 32
#define FD_MAX_DEVICE_QUEUE_DEPTH 128
#define FD_BLOCKSIZE 512
-#define FD_MAX_SECTORS 2048
+/*
+ * Limited by the number of iovecs (2048) per vfs_[writev,readv] call
+ */
+#define FD_MAX_BYTES 8388608
#define RRF_EMULATE_CDB 0x01
#define RRF_GOT_LBA 0x02
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index aa1620a..b358b3d 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -122,7 +122,7 @@
q = bdev_get_queue(bd);
dev->dev_attrib.hw_block_size = bdev_logical_block_size(bd);
- dev->dev_attrib.hw_max_sectors = UINT_MAX;
+ dev->dev_attrib.hw_max_sectors = queue_max_hw_sectors(q);
dev->dev_attrib.hw_queue_depth = q->nr_requests;
/*
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 3240f2c..7f85f4a 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -518,6 +518,18 @@
return 0;
}
+ } else if (we && registered_nexus) {
+ /*
+ * Reads are allowed for Write Exclusive locks
+ * from all registrants.
+ */
+ if (cmd->data_direction == DMA_FROM_DEVICE) {
+ pr_debug("Allowing READ CDB: 0x%02x for %s"
+ " reservation\n", cdb[0],
+ core_scsi3_pr_dump_type(pr_reg_type));
+
+ return 0;
+ }
}
pr_debug("%s Conflict for %sregistered nexus %s CDB: 0x%2x"
" for %s reservation\n", transport_dump_cmd_direction(cmd),
@@ -945,10 +957,10 @@
struct se_device *dev,
struct se_portal_group *tpg,
struct se_lun *lun,
- struct se_lun_acl *lun_acl)
+ struct se_node_acl *nacl,
+ u32 mapped_lun)
{
- struct se_node_acl *nacl = lun_acl->se_lun_nacl;
- struct se_dev_entry *deve = nacl->device_list[lun_acl->mapped_lun];
+ struct se_dev_entry *deve = nacl->device_list[mapped_lun];
if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
return 0;
@@ -1987,7 +1999,7 @@
pr_debug("Error writing APTPL metadata file: %s\n", path);
fput(file);
- return ret ? -EIO : 0;
+ return (ret < 0) ? -EIO : 0;
}
static int
@@ -2397,6 +2409,7 @@
spin_lock(&dev->dev_reservation_lock);
pr_res_holder = dev->dev_pr_res_holder;
if (pr_res_holder) {
+ int pr_res_type = pr_res_holder->pr_res_type;
/*
* From spc4r17 Section 5.7.9: Reserving:
*
@@ -2407,7 +2420,9 @@
* the logical unit, then the command shall be completed with
* RESERVATION CONFLICT status.
*/
- if (pr_res_holder != pr_reg) {
+ if ((pr_res_holder != pr_reg) &&
+ (pr_res_type != PR_TYPE_WRITE_EXCLUSIVE_ALLREG) &&
+ (pr_res_type != PR_TYPE_EXCLUSIVE_ACCESS_ALLREG)) {
struct se_node_acl *pr_res_nacl = pr_res_holder->pr_reg_nacl;
pr_err("SPC-3 PR: Attempted RESERVE from"
" [%s]: %s while reservation already held by"
@@ -4012,7 +4027,8 @@
unsigned char *buf;
u32 add_desc_len = 0, add_len = 0, desc_len, exp_desc_len;
u32 off = 8; /* off into first Full Status descriptor */
- int format_code = 0;
+ int format_code = 0, pr_res_type = 0, pr_res_scope = 0;
+ bool all_reg = false;
if (cmd->data_length < 8) {
pr_err("PRIN SA READ_FULL_STATUS SCSI Data Length: %u"
@@ -4029,6 +4045,19 @@
buf[2] = ((dev->t10_pr.pr_generation >> 8) & 0xff);
buf[3] = (dev->t10_pr.pr_generation & 0xff);
+ spin_lock(&dev->dev_reservation_lock);
+ if (dev->dev_pr_res_holder) {
+ struct t10_pr_registration *pr_holder = dev->dev_pr_res_holder;
+
+ if (pr_holder->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_ALLREG ||
+ pr_holder->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_ALLREG) {
+ all_reg = true;
+ pr_res_type = pr_holder->pr_res_type;
+ pr_res_scope = pr_holder->pr_res_scope;
+ }
+ }
+ spin_unlock(&dev->dev_reservation_lock);
+
spin_lock(&pr_tmpl->registration_lock);
list_for_each_entry_safe(pr_reg, pr_reg_tmp,
&pr_tmpl->registration_list, pr_reg_list) {
@@ -4078,14 +4107,20 @@
* reservation holder for PR_HOLDER bit.
*
* Also, if this registration is the reservation
- * holder, fill in SCOPE and TYPE in the next byte.
+ * holder or there is an All Registrants reservation
+ * active, fill in SCOPE and TYPE in the next byte.
*/
if (pr_reg->pr_res_holder) {
buf[off++] |= 0x01;
buf[off++] = (pr_reg->pr_res_scope & 0xf0) |
(pr_reg->pr_res_type & 0x0f);
- } else
+ } else if (all_reg) {
+ buf[off++] |= 0x01;
+ buf[off++] = (pr_res_scope & 0xf0) |
+ (pr_res_type & 0x0f);
+ } else {
off += 2;
+ }
off += 4; /* Skip over reserved area */
/*
diff --git a/drivers/target/target_core_pr.h b/drivers/target/target_core_pr.h
index b4a0042..ea9220d 100644
--- a/drivers/target/target_core_pr.h
+++ b/drivers/target/target_core_pr.h
@@ -55,7 +55,7 @@
unsigned char *, u16, u32, int, int, u8);
extern int core_scsi3_check_aptpl_registration(struct se_device *,
struct se_portal_group *, struct se_lun *,
- struct se_lun_acl *);
+ struct se_node_acl *, u32);
extern void core_scsi3_free_pr_reg_from_nacl(struct se_device *,
struct se_node_acl *);
extern void core_scsi3_free_all_registrations(struct se_device *);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index e992b27..b1e77ff 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -134,10 +134,10 @@
* pSCSI Host ID and enable for phba mode
*/
sh = scsi_host_lookup(phv->phv_host_id);
- if (IS_ERR(sh)) {
+ if (!sh) {
pr_err("pSCSI: Unable to locate SCSI Host for"
" phv_host_id: %d\n", phv->phv_host_id);
- return PTR_ERR(sh);
+ return -EINVAL;
}
phv->phv_lld_host = sh;
@@ -515,10 +515,10 @@
sh = phv->phv_lld_host;
} else {
sh = scsi_host_lookup(pdv->pdv_host_id);
- if (IS_ERR(sh)) {
+ if (!sh) {
pr_err("pSCSI: Unable to locate"
" pdv_host_id: %d\n", pdv->pdv_host_id);
- return PTR_ERR(sh);
+ return -EINVAL;
}
}
} else {
@@ -1112,7 +1112,7 @@
struct pscsi_dev_virt *pdv = PSCSI_DEV(dev);
struct scsi_device *sd = pdv->pdv_sd;
- return sd->type;
+ return (sd) ? sd->type : TYPE_NO_LUN;
}
static sector_t pscsi_get_blocks(struct se_device *dev)
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 0921a64..5c3b6778 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -174,7 +174,7 @@
- 1;
for (j = 0; j < sg_per_table; j++) {
- pg = alloc_pages(GFP_KERNEL, 0);
+ pg = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
if (!pg) {
pr_err("Unable to allocate scatterlist"
" pages for struct rd_dev_sg_table\n");
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index bbc5b0e..70b0d26 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -63,7 +63,7 @@
transport_kunmap_data_sg(cmd);
}
- target_complete_cmd(cmd, GOOD);
+ target_complete_cmd_with_length(cmd, GOOD, 8);
return 0;
}
@@ -101,7 +101,7 @@
transport_kunmap_data_sg(cmd);
}
- target_complete_cmd(cmd, GOOD);
+ target_complete_cmd_with_length(cmd, GOOD, 32);
return 0;
}
@@ -561,23 +561,9 @@
if (cmd->se_cmd_flags & SCF_SCSI_DATA_CDB) {
unsigned long long end_lba;
- if (sectors > dev->dev_attrib.fabric_max_sectors) {
- printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
- " big sectors %u exceeds fabric_max_sectors:"
- " %u\n", cdb[0], sectors,
- dev->dev_attrib.fabric_max_sectors);
- return TCM_INVALID_CDB_FIELD;
- }
- if (sectors > dev->dev_attrib.hw_max_sectors) {
- printk_ratelimited(KERN_ERR "SCSI OP %02xh with too"
- " big sectors %u exceeds backend hw_max_sectors:"
- " %u\n", cdb[0], sectors,
- dev->dev_attrib.hw_max_sectors);
- return TCM_INVALID_CDB_FIELD;
- }
-
end_lba = dev->transport->get_blocks(dev) + 1;
- if (cmd->t_task_lba + sectors > end_lba) {
+ if (((cmd->t_task_lba + sectors) < cmd->t_task_lba) ||
+ ((cmd->t_task_lba + sectors) > end_lba)) {
pr_err("cmd exceeds last lba %llu "
"(lba %llu, sectors %u)\n",
end_lba, cmd->t_task_lba, sectors);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 4cb667d..9998ae2 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -97,9 +97,12 @@
buf[7] = 0x2; /* CmdQue=1 */
- snprintf(&buf[8], 8, "LIO-ORG");
- snprintf(&buf[16], 16, "%s", dev->t10_wwn.model);
- snprintf(&buf[32], 4, "%s", dev->t10_wwn.revision);
+ memcpy(&buf[8], "LIO-ORG ", 8);
+ memset(&buf[16], 0x20, 16);
+ memcpy(&buf[16], dev->t10_wwn.model,
+ min_t(size_t, strlen(dev->t10_wwn.model), 16));
+ memcpy(&buf[32], dev->t10_wwn.revision,
+ min_t(size_t, strlen(dev->t10_wwn.revision), 4));
buf[4] = 31; /* Set additional length to 31 */
return 0;
@@ -441,7 +444,6 @@
spc_emulate_evpd_b0(struct se_cmd *cmd, unsigned char *buf)
{
struct se_device *dev = cmd->se_dev;
- u32 max_sectors;
int have_tp = 0;
/*
@@ -466,9 +468,7 @@
/*
* Set MAXIMUM TRANSFER LENGTH
*/
- max_sectors = min(dev->dev_attrib.fabric_max_sectors,
- dev->dev_attrib.hw_max_sectors);
- put_unaligned_be32(max_sectors, &buf[8]);
+ put_unaligned_be32(dev->dev_attrib.hw_max_sectors, &buf[8]);
/*
* Set OPTIMAL TRANSFER LENGTH
@@ -625,6 +625,7 @@
unsigned char buf[SE_INQUIRY_BUF];
sense_reason_t ret;
int p;
+ int len = 0;
memset(buf, 0, SE_INQUIRY_BUF);
@@ -642,6 +643,7 @@
}
ret = spc_emulate_inquiry_std(cmd, buf);
+ len = buf[4] + 5;
goto out;
}
@@ -649,6 +651,7 @@
if (cdb[2] == evpd_handlers[p].page) {
buf[1] = cdb[2];
ret = evpd_handlers[p].emulate(cmd, buf);
+ len = get_unaligned_be16(&buf[2]) + 4;
goto out;
}
}
@@ -664,7 +667,7 @@
}
if (!ret)
- target_complete_cmd(cmd, GOOD);
+ target_complete_cmd_with_length(cmd, GOOD, len);
return ret;
}
@@ -982,7 +985,7 @@
transport_kunmap_data_sg(cmd);
}
- target_complete_cmd(cmd, GOOD);
+ target_complete_cmd_with_length(cmd, GOOD, length);
return 0;
}
@@ -1159,7 +1162,7 @@
buf[3] = (lun_count & 0xff);
transport_kunmap_data_sg(cmd);
- target_complete_cmd(cmd, GOOD);
+ target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
return 0;
}
EXPORT_SYMBOL(spc_emulate_report_luns);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index aac9d27..8572207 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -40,6 +40,7 @@
#include <target/target_core_fabric.h>
#include "target_core_internal.h"
+#include "target_core_pr.h"
extern struct se_device *g_lun0_dev;
@@ -165,6 +166,13 @@
core_enable_device_list_for_node(lun, NULL, lun->unpacked_lun,
lun_access, acl, tpg);
+ /*
+ * Check to see if there are any existing persistent reservation
+ * APTPL pre-registrations that need to be enabled for this dynamic
+ * LUN ACL now..
+ */
+ core_scsi3_check_aptpl_registration(dev, tpg, lun, acl,
+ lun->unpacked_lun);
spin_lock(&tpg->tpg_lun_lock);
}
spin_unlock(&tpg->tpg_lun_lock);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 21e3158..daf0f63 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -488,7 +488,7 @@
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
- complete(&cmd->t_transport_stop_comp);
+ complete_all(&cmd->t_transport_stop_comp);
return 1;
}
@@ -617,7 +617,7 @@
if (cmd->transport_state & CMD_T_ABORTED &&
cmd->transport_state & CMD_T_STOP) {
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
- complete(&cmd->t_transport_stop_comp);
+ complete_all(&cmd->t_transport_stop_comp);
return;
} else if (cmd->transport_state & CMD_T_FAILED) {
INIT_WORK(&cmd->work, target_complete_failure_work);
@@ -633,6 +633,23 @@
}
EXPORT_SYMBOL(target_complete_cmd);
+void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
+{
+ if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
+ if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+ cmd->residual_count += cmd->data_length - length;
+ } else {
+ cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
+ cmd->residual_count = cmd->data_length - length;
+ }
+
+ cmd->data_length = length;
+ }
+
+ target_complete_cmd(cmd, scsi_status);
+}
+EXPORT_SYMBOL(target_complete_cmd_with_length);
+
static void target_add_to_state_list(struct se_cmd *cmd)
{
struct se_device *dev = cmd->se_dev;
@@ -1688,7 +1705,7 @@
cmd->se_tfo->get_task_tag(cmd));
spin_unlock_irq(&cmd->t_state_lock);
- complete(&cmd->t_transport_stop_comp);
+ complete_all(&cmd->t_transport_stop_comp);
return;
}
@@ -1771,8 +1788,7 @@
if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
ret = cmd->se_tfo->queue_status(cmd);
- if (ret)
- goto out;
+ goto out;
}
switch (cmd->data_direction) {
@@ -2112,7 +2128,7 @@
* and let it call back once the write buffers are ready.
*/
target_add_to_state_list(cmd);
- if (cmd->data_direction != DMA_TO_DEVICE) {
+ if (cmd->data_direction != DMA_TO_DEVICE || cmd->data_length == 0) {
target_execute_cmd(cmd);
return 0;
}
@@ -2206,6 +2222,10 @@
out:
spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+
+ if (ret && ack_kref)
+ target_put_sess_cmd(se_sess, se_cmd);
+
return ret;
}
EXPORT_SYMBOL(target_get_sess_cmd);
@@ -2877,6 +2897,12 @@
int transport_generic_handle_tmr(
struct se_cmd *cmd)
{
+ unsigned long flags;
+
+ spin_lock_irqsave(&cmd->t_state_lock, flags);
+ cmd->transport_state |= CMD_T_ACTIVE;
+ spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
INIT_WORK(&cmd->work, target_tmr_work);
queue_work(cmd->se_dev->tmr_wq, &cmd->work);
return 0;
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index e415af3..c67d379 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -346,7 +346,7 @@
ep = fc_seq_exch(seq);
if (ep) {
lport = ep->lp;
- if (lport && (ep->xid <= lport->lro_xid))
+ if (lport && (ep->xid <= lport->lro_xid)) {
/*
* "ddp_done" trigger invalidation of HW
* specific DDP context
@@ -361,6 +361,7 @@
* identified using ep->xid)
*/
cmd->was_ddp_setup = 0;
+ }
}
}
}
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index 4859505..639fdb3 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -68,6 +68,7 @@
if (tport) {
tport->tpg = tpg;
+ tpg->tport = tport;
return tport;
}
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 5e3c025..e92e1dc 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -17,8 +17,30 @@
config THERMAL_HWMON
bool
+ prompt "Expose thermal sensors as hwmon device"
depends on HWMON=y || HWMON=THERMAL
default y
+ help
+ In case a sensor is registered with the thermal
+ framework, this option will also register it
+ as a hwmon. The sensor will then have the common
+ hwmon sysfs interface.
+
+ Say 'Y' here if you want all thermal sensors to
+ have hwmon sysfs interface too.
+
+config THERMAL_OF
+ bool
+ prompt "APIs to parse thermal data out of device tree"
+ depends on OF
+ default y
+ help
+ This options provides helpers to add the support to
+ read and parse thermal data definitions out of the
+ device tree blob.
+
+ Say 'Y' here if you need to build thermal infrastructure
+ based on device tree.
choice
prompt "Default Thermal governor"
@@ -69,6 +91,7 @@
config CPU_THERMAL
bool "generic cpu cooling support"
depends on CPU_FREQ
+ depends on THERMAL_OF
select CPU_FREQ_TABLE
help
This implements the generic cpu cooling mechanism through frequency
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index c054d41..71f8eef4 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -5,6 +5,10 @@
obj-$(CONFIG_THERMAL) += thermal_sys.o
thermal_sys-y += thermal_core.o
+# interface to/from other layers providing sensors
+thermal_sys-$(CONFIG_THERMAL_HWMON) += thermal_hwmon.o
+thermal_sys-$(CONFIG_THERMAL_OF) += of-thermal.o
+
# governors
thermal_sys-$(CONFIG_THERMAL_GOV_FAIR_SHARE) += fair_share.o
thermal_sys-$(CONFIG_THERMAL_GOV_STEP_WISE) += step_wise.o
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index c94bf2e..4246262 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -167,13 +167,20 @@
continue;
/* get the frequency order */
- if (freq != CPUFREQ_ENTRY_INVALID && descend != -1)
+ if (freq != CPUFREQ_ENTRY_INVALID && descend == -1)
descend = !!(freq > table[i].frequency);
freq = table[i].frequency;
max_level++;
}
+ /* No valid cpu frequency entry */
+ if (max_level == 0)
+ return -EINVAL;
+
+ /* max_level is an index, not a counter */
+ max_level--;
+
/* get max level */
if (property == GET_MAXL) {
*output = (unsigned int)max_level;
@@ -181,7 +188,7 @@
}
if (property == GET_FREQ)
- level = descend ? input : (max_level - input - 1);
+ level = descend ? input : (max_level - input);
for (i = 0, j = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
/* ignore invalid entry */
@@ -197,7 +204,7 @@
if (property == GET_LEVEL && (unsigned int)input == freq) {
/* get level by frequency */
- *output = descend ? j : (max_level - j - 1);
+ *output = descend ? j : (max_level - j);
return 0;
}
if (property == GET_FREQ && level == j) {
@@ -322,6 +329,8 @@
if (cpumask_test_cpu(policy->cpu, ¬ify_device->allowed_cpus))
max_freq = notify_device->cpufreq_val;
+ else
+ return 0;
/* Never exceed user_policy.max */
if (max_freq > policy->user_policy.max)
@@ -415,18 +424,21 @@
};
/**
- * cpufreq_cooling_register - function to create cpufreq cooling device.
+ * __cpufreq_cooling_register - helper function to create cpufreq cooling device
+ * @np: a valid struct device_node to the cooling device device tree node
* @clip_cpus: cpumask of cpus where the frequency constraints will happen.
*
* This interface function registers the cpufreq cooling device with the name
* "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
- * cooling devices.
+ * cooling devices. It also gives the opportunity to link the cooling device
+ * with a device tree node, in order to bind it via the thermal DT code.
*
* Return: a valid struct thermal_cooling_device pointer on success,
* on failure, it returns a corresponding ERR_PTR().
*/
-struct thermal_cooling_device *
-cpufreq_cooling_register(const struct cpumask *clip_cpus)
+static struct thermal_cooling_device *
+__cpufreq_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus)
{
struct thermal_cooling_device *cool_dev;
struct cpufreq_cooling_device *cpufreq_dev = NULL;
@@ -465,12 +477,12 @@
snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
cpufreq_dev->id);
- cool_dev = thermal_cooling_device_register(dev_name, cpufreq_dev,
- &cpufreq_cooling_ops);
- if (!cool_dev) {
+ cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
+ &cpufreq_cooling_ops);
+ if (IS_ERR(cool_dev)) {
release_idr(&cpufreq_idr, cpufreq_dev->id);
kfree(cpufreq_dev);
- return ERR_PTR(-EINVAL);
+ return cool_dev;
}
cpufreq_dev->cool_dev = cool_dev;
cpufreq_dev->cpufreq_state = 0;
@@ -486,9 +498,50 @@
return cool_dev;
}
+
+/**
+ * cpufreq_cooling_register - function to create cpufreq cooling device.
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ *
+ * This interface function registers the cpufreq cooling device with the name
+ * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
+ * cooling devices.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+cpufreq_cooling_register(const struct cpumask *clip_cpus)
+{
+ return __cpufreq_cooling_register(NULL, clip_cpus);
+}
EXPORT_SYMBOL_GPL(cpufreq_cooling_register);
/**
+ * of_cpufreq_cooling_register - function to create cpufreq cooling device.
+ * @np: a valid struct device_node to the cooling device device tree node
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen.
+ *
+ * This interface function registers the cpufreq cooling device with the name
+ * "thermal-cpufreq-%x". This api can support multiple instances of cpufreq
+ * cooling devices. Using this API, the cpufreq cooling device will be
+ * linked to the device tree node provided.
+ *
+ * Return: a valid struct thermal_cooling_device pointer on success,
+ * on failure, it returns a corresponding ERR_PTR().
+ */
+struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus)
+{
+ if (!np)
+ return ERR_PTR(-EINVAL);
+
+ return __cpufreq_cooling_register(np, clip_cpus);
+}
+EXPORT_SYMBOL_GPL(of_cpufreq_cooling_register);
+
+/**
* cpufreq_cooling_unregister - function to remove cpufreq cooling device.
* @cdev: thermal cooling device pointer.
*
@@ -496,8 +549,12 @@
*/
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{
- struct cpufreq_cooling_device *cpufreq_dev = cdev->devdata;
+ struct cpufreq_cooling_device *cpufreq_dev;
+ if (!cdev)
+ return;
+
+ cpufreq_dev = cdev->devdata;
mutex_lock(&cooling_cpufreq_lock);
cpufreq_dev_count--;
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
new file mode 100644
index 0000000..4b2b999
--- /dev/null
+++ b/drivers/thermal/of-thermal.c
@@ -0,0 +1,850 @@
+/*
+ * of-thermal.c - Generic Thermal Management device tree support.
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/string.h>
+
+#include "thermal_core.h"
+
+/*** Private data structures to represent thermal device tree data ***/
+
+/**
+ * struct __thermal_trip - representation of a point in temperature domain
+ * @np: pointer to struct device_node that this trip point was created from
+ * @temperature: temperature value in miliCelsius
+ * @hysteresis: relative hysteresis in miliCelsius
+ * @type: trip point type
+ */
+
+struct __thermal_trip {
+ struct device_node *np;
+ unsigned long int temperature;
+ unsigned long int hysteresis;
+ enum thermal_trip_type type;
+};
+
+/**
+ * struct __thermal_bind_param - a match between trip and cooling device
+ * @cooling_device: a pointer to identify the referred cooling device
+ * @trip_id: the trip point index
+ * @usage: the percentage (from 0 to 100) of cooling contribution
+ * @min: minimum cooling state used at this trip point
+ * @max: maximum cooling state used at this trip point
+ */
+
+struct __thermal_bind_params {
+ struct device_node *cooling_device;
+ unsigned int trip_id;
+ unsigned int usage;
+ unsigned long min;
+ unsigned long max;
+};
+
+/**
+ * struct __thermal_zone - internal representation of a thermal zone
+ * @mode: current thermal zone device mode (enabled/disabled)
+ * @passive_delay: polling interval while passive cooling is activated
+ * @polling_delay: zone polling interval
+ * @ntrips: number of trip points
+ * @trips: an array of trip points (0..ntrips - 1)
+ * @num_tbps: number of thermal bind params
+ * @tbps: an array of thermal bind params (0..num_tbps - 1)
+ * @sensor_data: sensor private data used while reading temperature and trend
+ * @get_temp: sensor callback to read temperature
+ * @get_trend: sensor callback to read temperature trend
+ */
+
+struct __thermal_zone {
+ enum thermal_device_mode mode;
+ int passive_delay;
+ int polling_delay;
+
+ /* trip data */
+ int ntrips;
+ struct __thermal_trip *trips;
+
+ /* cooling binding data */
+ int num_tbps;
+ struct __thermal_bind_params *tbps;
+
+ /* sensor interface */
+ void *sensor_data;
+ int (*get_temp)(void *, long *);
+ int (*get_trend)(void *, long *);
+};
+
+/*** DT thermal zone device callbacks ***/
+
+static int of_thermal_get_temp(struct thermal_zone_device *tz,
+ unsigned long *temp)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (!data->get_temp)
+ return -EINVAL;
+
+ return data->get_temp(data->sensor_data, temp);
+}
+
+static int of_thermal_get_trend(struct thermal_zone_device *tz, int trip,
+ enum thermal_trend *trend)
+{
+ struct __thermal_zone *data = tz->devdata;
+ long dev_trend;
+ int r;
+
+ if (!data->get_trend)
+ return -EINVAL;
+
+ r = data->get_trend(data->sensor_data, &dev_trend);
+ if (r)
+ return r;
+
+ /* TODO: These intervals might have some thresholds, but in core code */
+ if (dev_trend > 0)
+ *trend = THERMAL_TREND_RAISING;
+ else if (dev_trend < 0)
+ *trend = THERMAL_TREND_DROPPING;
+ else
+ *trend = THERMAL_TREND_STABLE;
+
+ return 0;
+}
+
+static int of_thermal_bind(struct thermal_zone_device *thermal,
+ struct thermal_cooling_device *cdev)
+{
+ struct __thermal_zone *data = thermal->devdata;
+ int i;
+
+ if (!data || IS_ERR(data))
+ return -ENODEV;
+
+ /* find where to bind */
+ for (i = 0; i < data->num_tbps; i++) {
+ struct __thermal_bind_params *tbp = data->tbps + i;
+
+ if (tbp->cooling_device == cdev->np) {
+ int ret;
+
+ ret = thermal_zone_bind_cooling_device(thermal,
+ tbp->trip_id, cdev,
+ tbp->max,
+ tbp->min);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int of_thermal_unbind(struct thermal_zone_device *thermal,
+ struct thermal_cooling_device *cdev)
+{
+ struct __thermal_zone *data = thermal->devdata;
+ int i;
+
+ if (!data || IS_ERR(data))
+ return -ENODEV;
+
+ /* find where to unbind */
+ for (i = 0; i < data->num_tbps; i++) {
+ struct __thermal_bind_params *tbp = data->tbps + i;
+
+ if (tbp->cooling_device == cdev->np) {
+ int ret;
+
+ ret = thermal_zone_unbind_cooling_device(thermal,
+ tbp->trip_id, cdev);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int of_thermal_get_mode(struct thermal_zone_device *tz,
+ enum thermal_device_mode *mode)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ *mode = data->mode;
+
+ return 0;
+}
+
+static int of_thermal_set_mode(struct thermal_zone_device *tz,
+ enum thermal_device_mode mode)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ mutex_lock(&tz->lock);
+
+ if (mode == THERMAL_DEVICE_ENABLED)
+ tz->polling_delay = data->polling_delay;
+ else
+ tz->polling_delay = 0;
+
+ mutex_unlock(&tz->lock);
+
+ data->mode = mode;
+ thermal_zone_device_update(tz);
+
+ return 0;
+}
+
+static int of_thermal_get_trip_type(struct thermal_zone_device *tz, int trip,
+ enum thermal_trip_type *type)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (trip >= data->ntrips || trip < 0)
+ return -EDOM;
+
+ *type = data->trips[trip].type;
+
+ return 0;
+}
+
+static int of_thermal_get_trip_temp(struct thermal_zone_device *tz, int trip,
+ unsigned long *temp)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (trip >= data->ntrips || trip < 0)
+ return -EDOM;
+
+ *temp = data->trips[trip].temperature;
+
+ return 0;
+}
+
+static int of_thermal_set_trip_temp(struct thermal_zone_device *tz, int trip,
+ unsigned long temp)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (trip >= data->ntrips || trip < 0)
+ return -EDOM;
+
+ /* thermal framework should take care of data->mask & (1 << trip) */
+ data->trips[trip].temperature = temp;
+
+ return 0;
+}
+
+static int of_thermal_get_trip_hyst(struct thermal_zone_device *tz, int trip,
+ unsigned long *hyst)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (trip >= data->ntrips || trip < 0)
+ return -EDOM;
+
+ *hyst = data->trips[trip].hysteresis;
+
+ return 0;
+}
+
+static int of_thermal_set_trip_hyst(struct thermal_zone_device *tz, int trip,
+ unsigned long hyst)
+{
+ struct __thermal_zone *data = tz->devdata;
+
+ if (trip >= data->ntrips || trip < 0)
+ return -EDOM;
+
+ /* thermal framework should take care of data->mask & (1 << trip) */
+ data->trips[trip].hysteresis = hyst;
+
+ return 0;
+}
+
+static int of_thermal_get_crit_temp(struct thermal_zone_device *tz,
+ unsigned long *temp)
+{
+ struct __thermal_zone *data = tz->devdata;
+ int i;
+
+ for (i = 0; i < data->ntrips; i++)
+ if (data->trips[i].type == THERMAL_TRIP_CRITICAL) {
+ *temp = data->trips[i].temperature;
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static struct thermal_zone_device_ops of_thermal_ops = {
+ .get_mode = of_thermal_get_mode,
+ .set_mode = of_thermal_set_mode,
+
+ .get_trip_type = of_thermal_get_trip_type,
+ .get_trip_temp = of_thermal_get_trip_temp,
+ .set_trip_temp = of_thermal_set_trip_temp,
+ .get_trip_hyst = of_thermal_get_trip_hyst,
+ .set_trip_hyst = of_thermal_set_trip_hyst,
+ .get_crit_temp = of_thermal_get_crit_temp,
+
+ .bind = of_thermal_bind,
+ .unbind = of_thermal_unbind,
+};
+
+/*** sensor API ***/
+
+static struct thermal_zone_device *
+thermal_zone_of_add_sensor(struct device_node *zone,
+ struct device_node *sensor, void *data,
+ int (*get_temp)(void *, long *),
+ int (*get_trend)(void *, long *))
+{
+ struct thermal_zone_device *tzd;
+ struct __thermal_zone *tz;
+
+ tzd = thermal_zone_get_zone_by_name(zone->name);
+ if (IS_ERR(tzd))
+ return ERR_PTR(-EPROBE_DEFER);
+
+ tz = tzd->devdata;
+
+ mutex_lock(&tzd->lock);
+ tz->get_temp = get_temp;
+ tz->get_trend = get_trend;
+ tz->sensor_data = data;
+
+ tzd->ops->get_temp = of_thermal_get_temp;
+ tzd->ops->get_trend = of_thermal_get_trend;
+ mutex_unlock(&tzd->lock);
+
+ return tzd;
+}
+
+/**
+ * thermal_zone_of_sensor_register - registers a sensor to a DT thermal zone
+ * @dev: a valid struct device pointer of a sensor device. Must contain
+ * a valid .of_node, for the sensor node.
+ * @sensor_id: a sensor identifier, in case the sensor IP has more
+ * than one sensors
+ * @data: a private pointer (owned by the caller) that will be passed
+ * back, when a temperature reading is needed.
+ * @get_temp: a pointer to a function that reads the sensor temperature.
+ * @get_trend: a pointer to a function that reads the sensor temperature trend.
+ *
+ * This function will search the list of thermal zones described in device
+ * tree and look for the zone that refer to the sensor device pointed by
+ * @dev->of_node as temperature providers. For the zone pointing to the
+ * sensor node, the sensor will be added to the DT thermal zone device.
+ *
+ * The thermal zone temperature is provided by the @get_temp function
+ * pointer. When called, it will have the private pointer @data back.
+ *
+ * The thermal zone temperature trend is provided by the @get_trend function
+ * pointer. When called, it will have the private pointer @data back.
+ *
+ * TODO:
+ * 01 - This function must enqueue the new sensor instead of using
+ * it as the only source of temperature values.
+ *
+ * 02 - There must be a way to match the sensor with all thermal zones
+ * that refer to it.
+ *
+ * Return: On success returns a valid struct thermal_zone_device,
+ * otherwise, it returns a corresponding ERR_PTR(). Caller must
+ * check the return value with help of IS_ERR() helper.
+ */
+struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int sensor_id,
+ void *data, int (*get_temp)(void *, long *),
+ int (*get_trend)(void *, long *))
+{
+ struct device_node *np, *child, *sensor_np;
+
+ np = of_find_node_by_name(NULL, "thermal-zones");
+ if (!np)
+ return ERR_PTR(-ENODEV);
+
+ if (!dev || !dev->of_node)
+ return ERR_PTR(-EINVAL);
+
+ sensor_np = dev->of_node;
+
+ for_each_child_of_node(np, child) {
+ struct of_phandle_args sensor_specs;
+ int ret, id;
+
+ /* For now, thermal framework supports only 1 sensor per zone */
+ ret = of_parse_phandle_with_args(child, "thermal-sensors",
+ "#thermal-sensor-cells",
+ 0, &sensor_specs);
+ if (ret)
+ continue;
+
+ if (sensor_specs.args_count >= 1) {
+ id = sensor_specs.args[0];
+ WARN(sensor_specs.args_count > 1,
+ "%s: too many cells in sensor specifier %d\n",
+ sensor_specs.np->name, sensor_specs.args_count);
+ } else {
+ id = 0;
+ }
+
+ if (sensor_specs.np == sensor_np && id == sensor_id) {
+ of_node_put(np);
+ return thermal_zone_of_add_sensor(child, sensor_np,
+ data,
+ get_temp,
+ get_trend);
+ }
+ }
+ of_node_put(np);
+
+ return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_register);
+
+/**
+ * thermal_zone_of_sensor_unregister - unregisters a sensor from a DT thermal zone
+ * @dev: a valid struct device pointer of a sensor device. Must contain
+ * a valid .of_node, for the sensor node.
+ * @tzd: a pointer to struct thermal_zone_device where the sensor is registered.
+ *
+ * This function removes the sensor callbacks and private data from the
+ * thermal zone device registered with thermal_zone_of_sensor_register()
+ * API. It will also silent the zone by remove the .get_temp() and .get_trend()
+ * thermal zone device callbacks.
+ *
+ * TODO: When the support to several sensors per zone is added, this
+ * function must search the sensor list based on @dev parameter.
+ *
+ */
+void thermal_zone_of_sensor_unregister(struct device *dev,
+ struct thermal_zone_device *tzd)
+{
+ struct __thermal_zone *tz;
+
+ if (!dev || !tzd || !tzd->devdata)
+ return;
+
+ tz = tzd->devdata;
+
+ /* no __thermal_zone, nothing to be done */
+ if (!tz)
+ return;
+
+ mutex_lock(&tzd->lock);
+ tzd->ops->get_temp = NULL;
+ tzd->ops->get_trend = NULL;
+
+ tz->get_temp = NULL;
+ tz->get_trend = NULL;
+ tz->sensor_data = NULL;
+ mutex_unlock(&tzd->lock);
+}
+EXPORT_SYMBOL_GPL(thermal_zone_of_sensor_unregister);
+
+/*** functions parsing device tree nodes ***/
+
+/**
+ * thermal_of_populate_bind_params - parse and fill cooling map data
+ * @np: DT node containing a cooling-map node
+ * @__tbp: data structure to be filled with cooling map info
+ * @trips: array of thermal zone trip points
+ * @ntrips: number of trip points inside trips.
+ *
+ * This function parses a cooling-map type of node represented by
+ * @np parameter and fills the read data into @__tbp data structure.
+ * It needs the already parsed array of trip points of the thermal zone
+ * in consideration.
+ *
+ * Return: 0 on success, proper error code otherwise
+ */
+static int thermal_of_populate_bind_params(struct device_node *np,
+ struct __thermal_bind_params *__tbp,
+ struct __thermal_trip *trips,
+ int ntrips)
+{
+ struct of_phandle_args cooling_spec;
+ struct device_node *trip;
+ int ret, i;
+ u32 prop;
+
+ /* Default weight. Usage is optional */
+ __tbp->usage = 0;
+ ret = of_property_read_u32(np, "contribution", &prop);
+ if (ret == 0)
+ __tbp->usage = prop;
+
+ trip = of_parse_phandle(np, "trip", 0);
+ if (!trip) {
+ pr_err("missing trip property\n");
+ return -ENODEV;
+ }
+
+ /* match using device_node */
+ for (i = 0; i < ntrips; i++)
+ if (trip == trips[i].np) {
+ __tbp->trip_id = i;
+ break;
+ }
+
+ if (i == ntrips) {
+ ret = -ENODEV;
+ goto end;
+ }
+
+ ret = of_parse_phandle_with_args(np, "cooling-device", "#cooling-cells",
+ 0, &cooling_spec);
+ if (ret < 0) {
+ pr_err("missing cooling_device property\n");
+ goto end;
+ }
+ __tbp->cooling_device = cooling_spec.np;
+ if (cooling_spec.args_count >= 2) { /* at least min and max */
+ __tbp->min = cooling_spec.args[0];
+ __tbp->max = cooling_spec.args[1];
+ } else {
+ pr_err("wrong reference to cooling device, missing limits\n");
+ }
+
+end:
+ of_node_put(trip);
+
+ return ret;
+}
+
+/**
+ * It maps 'enum thermal_trip_type' found in include/linux/thermal.h
+ * into the device tree binding of 'trip', property type.
+ */
+static const char * const trip_types[] = {
+ [THERMAL_TRIP_ACTIVE] = "active",
+ [THERMAL_TRIP_PASSIVE] = "passive",
+ [THERMAL_TRIP_HOT] = "hot",
+ [THERMAL_TRIP_CRITICAL] = "critical",
+};
+
+/**
+ * thermal_of_get_trip_type - Get phy mode for given device_node
+ * @np: Pointer to the given device_node
+ * @type: Pointer to resulting trip type
+ *
+ * The function gets trip type string from property 'type',
+ * and store its index in trip_types table in @type,
+ *
+ * Return: 0 on success, or errno in error case.
+ */
+static int thermal_of_get_trip_type(struct device_node *np,
+ enum thermal_trip_type *type)
+{
+ const char *t;
+ int err, i;
+
+ err = of_property_read_string(np, "type", &t);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i < ARRAY_SIZE(trip_types); i++)
+ if (!strcasecmp(t, trip_types[i])) {
+ *type = i;
+ return 0;
+ }
+
+ return -ENODEV;
+}
+
+/**
+ * thermal_of_populate_trip - parse and fill one trip point data
+ * @np: DT node containing a trip point node
+ * @trip: trip point data structure to be filled up
+ *
+ * This function parses a trip point type of node represented by
+ * @np parameter and fills the read data into @trip data structure.
+ *
+ * Return: 0 on success, proper error code otherwise
+ */
+static int thermal_of_populate_trip(struct device_node *np,
+ struct __thermal_trip *trip)
+{
+ int prop;
+ int ret;
+
+ ret = of_property_read_u32(np, "temperature", &prop);
+ if (ret < 0) {
+ pr_err("missing temperature property\n");
+ return ret;
+ }
+ trip->temperature = prop;
+
+ ret = of_property_read_u32(np, "hysteresis", &prop);
+ if (ret < 0) {
+ pr_err("missing hysteresis property\n");
+ return ret;
+ }
+ trip->hysteresis = prop;
+
+ ret = thermal_of_get_trip_type(np, &trip->type);
+ if (ret < 0) {
+ pr_err("wrong trip type property\n");
+ return ret;
+ }
+
+ /* Required for cooling map matching */
+ trip->np = np;
+
+ return 0;
+}
+
+/**
+ * thermal_of_build_thermal_zone - parse and fill one thermal zone data
+ * @np: DT node containing a thermal zone node
+ *
+ * This function parses a thermal zone type of node represented by
+ * @np parameter and fills the read data into a __thermal_zone data structure
+ * and return this pointer.
+ *
+ * TODO: Missing properties to parse: thermal-sensor-names and coefficients
+ *
+ * Return: On success returns a valid struct __thermal_zone,
+ * otherwise, it returns a corresponding ERR_PTR(). Caller must
+ * check the return value with help of IS_ERR() helper.
+ */
+static struct __thermal_zone *
+thermal_of_build_thermal_zone(struct device_node *np)
+{
+ struct device_node *child = NULL, *gchild;
+ struct __thermal_zone *tz;
+ int ret, i;
+ u32 prop;
+
+ if (!np) {
+ pr_err("no thermal zone np\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ tz = kzalloc(sizeof(*tz), GFP_KERNEL);
+ if (!tz)
+ return ERR_PTR(-ENOMEM);
+
+ ret = of_property_read_u32(np, "polling-delay-passive", &prop);
+ if (ret < 0) {
+ pr_err("missing polling-delay-passive property\n");
+ goto free_tz;
+ }
+ tz->passive_delay = prop;
+
+ ret = of_property_read_u32(np, "polling-delay", &prop);
+ if (ret < 0) {
+ pr_err("missing polling-delay property\n");
+ goto free_tz;
+ }
+ tz->polling_delay = prop;
+
+ /* trips */
+ child = of_get_child_by_name(np, "trips");
+
+ /* No trips provided */
+ if (!child)
+ goto finish;
+
+ tz->ntrips = of_get_child_count(child);
+ if (tz->ntrips == 0) /* must have at least one child */
+ goto finish;
+
+ tz->trips = kzalloc(tz->ntrips * sizeof(*tz->trips), GFP_KERNEL);
+ if (!tz->trips) {
+ ret = -ENOMEM;
+ goto free_tz;
+ }
+
+ i = 0;
+ for_each_child_of_node(child, gchild) {
+ ret = thermal_of_populate_trip(gchild, &tz->trips[i++]);
+ if (ret)
+ goto free_trips;
+ }
+
+ of_node_put(child);
+
+ /* cooling-maps */
+ child = of_get_child_by_name(np, "cooling-maps");
+
+ /* cooling-maps not provided */
+ if (!child)
+ goto finish;
+
+ tz->num_tbps = of_get_child_count(child);
+ if (tz->num_tbps == 0)
+ goto finish;
+
+ tz->tbps = kzalloc(tz->num_tbps * sizeof(*tz->tbps), GFP_KERNEL);
+ if (!tz->tbps) {
+ ret = -ENOMEM;
+ goto free_trips;
+ }
+
+ i = 0;
+ for_each_child_of_node(child, gchild) {
+ ret = thermal_of_populate_bind_params(gchild, &tz->tbps[i++],
+ tz->trips, tz->ntrips);
+ if (ret)
+ goto free_tbps;
+ }
+
+finish:
+ of_node_put(child);
+ tz->mode = THERMAL_DEVICE_DISABLED;
+
+ return tz;
+
+free_tbps:
+ kfree(tz->tbps);
+free_trips:
+ kfree(tz->trips);
+free_tz:
+ kfree(tz);
+ of_node_put(child);
+
+ return ERR_PTR(ret);
+}
+
+static inline void of_thermal_free_zone(struct __thermal_zone *tz)
+{
+ kfree(tz->tbps);
+ kfree(tz->trips);
+ kfree(tz);
+}
+
+/**
+ * of_parse_thermal_zones - parse device tree thermal data
+ *
+ * Initialization function that can be called by machine initialization
+ * code to parse thermal data and populate the thermal framework
+ * with hardware thermal zones info. This function only parses thermal zones.
+ * Cooling devices and sensor devices nodes are supposed to be parsed
+ * by their respective drivers.
+ *
+ * Return: 0 on success, proper error code otherwise
+ *
+ */
+int __init of_parse_thermal_zones(void)
+{
+ struct device_node *np, *child;
+ struct __thermal_zone *tz;
+ struct thermal_zone_device_ops *ops;
+
+ np = of_find_node_by_name(NULL, "thermal-zones");
+ if (!np) {
+ pr_debug("unable to find thermal zones\n");
+ return 0; /* Run successfully on systems without thermal DT */
+ }
+
+ for_each_child_of_node(np, child) {
+ struct thermal_zone_device *zone;
+ struct thermal_zone_params *tzp;
+
+ tz = thermal_of_build_thermal_zone(child);
+ if (IS_ERR(tz)) {
+ pr_err("failed to build thermal zone %s: %ld\n",
+ child->name,
+ PTR_ERR(tz));
+ continue;
+ }
+
+ ops = kmemdup(&of_thermal_ops, sizeof(*ops), GFP_KERNEL);
+ if (!ops)
+ goto exit_free;
+
+ tzp = kzalloc(sizeof(*tzp), GFP_KERNEL);
+ if (!tzp) {
+ kfree(ops);
+ goto exit_free;
+ }
+
+ /* No hwmon because there might be hwmon drivers registering */
+ tzp->no_hwmon = true;
+
+ zone = thermal_zone_device_register(child->name, tz->ntrips,
+ 0, tz,
+ ops, tzp,
+ tz->passive_delay,
+ tz->polling_delay);
+ if (IS_ERR(zone)) {
+ pr_err("Failed to build %s zone %ld\n", child->name,
+ PTR_ERR(zone));
+ kfree(tzp);
+ kfree(ops);
+ of_thermal_free_zone(tz);
+ /* attempting to build remaining zones still */
+ }
+ }
+
+ return 0;
+
+exit_free:
+ of_thermal_free_zone(tz);
+
+ /* no memory available, so free what we have built */
+ of_thermal_destroy_zones();
+
+ return -ENOMEM;
+}
+
+/**
+ * of_thermal_destroy_zones - remove all zones parsed and allocated resources
+ *
+ * Finds all zones parsed and added to the thermal framework and remove them
+ * from the system, together with their resources.
+ *
+ */
+void of_thermal_destroy_zones(void)
+{
+ struct device_node *np, *child;
+
+ np = of_find_node_by_name(NULL, "thermal-zones");
+ if (!np) {
+ pr_err("unable to find thermal zones\n");
+ return;
+ }
+
+ for_each_child_of_node(np, child) {
+ struct thermal_zone_device *zone;
+
+ zone = thermal_zone_get_zone_by_name(child->name);
+ if (IS_ERR(zone))
+ continue;
+
+ thermal_zone_device_unregister(zone);
+ kfree(zone->tzp);
+ kfree(zone->ops);
+ of_thermal_free_zone(zone->devdata);
+ }
+}
diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c
index 4d4ddae..c83a309 100644
--- a/drivers/thermal/step_wise.c
+++ b/drivers/thermal/step_wise.c
@@ -53,6 +53,7 @@
unsigned long cur_state;
cdev->ops->get_cur_state(cdev, &cur_state);
+ dev_dbg(&cdev->device, "cur_state=%ld\n", cur_state);
switch (trend) {
case THERMAL_TREND_RAISING:
@@ -124,6 +125,9 @@
if (tz->temperature >= trip_temp)
throttle = true;
+ dev_dbg(&tz->device, "Trip%d[type=%d,temp=%ld]:trend=%d,throttle=%d\n",
+ trip, trip_type, trip_temp, trend, throttle);
+
mutex_lock(&tz->lock);
list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
@@ -132,6 +136,8 @@
old_target = instance->target;
instance->target = get_target_state(instance, trend, throttle);
+ dev_dbg(&instance->cdev->device, "old_target=%d, target=%d\n",
+ old_target, (int)instance->target);
/* Activate a passive thermal instance */
if (old_target == THERMAL_NO_TARGET &&
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index d755440..edc0cb8 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -33,10 +33,13 @@
#include <linux/idr.h>
#include <linux/thermal.h>
#include <linux/reboot.h>
+#include <linux/string.h>
+#include <linux/of.h>
#include <net/netlink.h>
#include <net/genetlink.h>
#include "thermal_core.h"
+#include "thermal_hwmon.h"
MODULE_AUTHOR("Zhang Rui");
MODULE_DESCRIPTION("Generic thermal management sysfs support");
@@ -53,10 +56,15 @@
static DEFINE_MUTEX(thermal_list_lock);
static DEFINE_MUTEX(thermal_governor_lock);
+static struct thermal_governor *def_governor;
+
static struct thermal_governor *__find_governor(const char *name)
{
struct thermal_governor *pos;
+ if (!name || !name[0])
+ return def_governor;
+
list_for_each_entry(pos, &thermal_governor_list, governor_list)
if (!strnicmp(name, pos->name, THERMAL_NAME_LENGTH))
return pos;
@@ -79,17 +87,23 @@
if (__find_governor(governor->name) == NULL) {
err = 0;
list_add(&governor->governor_list, &thermal_governor_list);
+ if (!def_governor && !strncmp(governor->name,
+ DEFAULT_THERMAL_GOVERNOR, THERMAL_NAME_LENGTH))
+ def_governor = governor;
}
mutex_lock(&thermal_list_lock);
list_for_each_entry(pos, &thermal_tz_list, node) {
+ /*
+ * only thermal zones with specified tz->tzp->governor_name
+ * may run with tz->govenor unset
+ */
if (pos->governor)
continue;
- if (pos->tzp)
- name = pos->tzp->governor_name;
- else
- name = DEFAULT_THERMAL_GOVERNOR;
+
+ name = pos->tzp->governor_name;
+
if (!strnicmp(name, governor->name, THERMAL_NAME_LENGTH))
pos->governor = governor;
}
@@ -235,10 +249,11 @@
if (!pos->tzp && !pos->ops->bind)
continue;
- if (!pos->tzp && pos->ops->bind) {
+ if (pos->ops->bind) {
ret = pos->ops->bind(pos, cdev);
if (ret)
print_bind_err_msg(pos, cdev, ret);
+ continue;
}
tzp = pos->tzp;
@@ -269,8 +284,8 @@
mutex_lock(&thermal_list_lock);
- /* If there is no platform data, try to use ops->bind */
- if (!tzp && tz->ops->bind) {
+ /* If there is ops->bind, try to use ops->bind */
+ if (tz->ops->bind) {
list_for_each_entry(pos, &thermal_cdev_list, node) {
ret = tz->ops->bind(tz, pos);
if (ret)
@@ -326,8 +341,8 @@
static void handle_non_critical_trips(struct thermal_zone_device *tz,
int trip, enum thermal_trip_type trip_type)
{
- if (tz->governor)
- tz->governor->throttle(tz, trip);
+ tz->governor ? tz->governor->throttle(tz, trip) :
+ def_governor->throttle(tz, trip);
}
static void handle_critical_trips(struct thermal_zone_device *tz,
@@ -388,7 +403,7 @@
enum thermal_trip_type type;
#endif
- if (!tz || IS_ERR(tz))
+ if (!tz || IS_ERR(tz) || !tz->ops->get_temp)
goto exit;
mutex_lock(&tz->lock);
@@ -435,12 +450,18 @@
tz->last_temperature = tz->temperature;
tz->temperature = temp;
mutex_unlock(&tz->lock);
+
+ dev_dbg(&tz->device, "last_temperature=%d, current_temperature=%d\n",
+ tz->last_temperature, tz->temperature);
}
void thermal_zone_device_update(struct thermal_zone_device *tz)
{
int count;
+ if (!tz->ops->get_temp)
+ return;
+
update_temperature(tz);
for (count = 0; count < tz->trips; count++)
@@ -756,6 +777,9 @@
ret = tz->ops->set_emul_temp(tz, temperature);
}
+ if (!ret)
+ thermal_zone_device_update(tz);
+
return ret ? ret : count;
}
static DEVICE_ATTR(emul_temp, S_IWUSR, NULL, emul_temp_store);
@@ -854,260 +878,6 @@
/* Device management */
-#if defined(CONFIG_THERMAL_HWMON)
-
-/* hwmon sys I/F */
-#include <linux/hwmon.h>
-
-/* thermal zone devices with the same type share one hwmon device */
-struct thermal_hwmon_device {
- char type[THERMAL_NAME_LENGTH];
- struct device *device;
- int count;
- struct list_head tz_list;
- struct list_head node;
-};
-
-struct thermal_hwmon_attr {
- struct device_attribute attr;
- char name[16];
-};
-
-/* one temperature input for each thermal zone */
-struct thermal_hwmon_temp {
- struct list_head hwmon_node;
- struct thermal_zone_device *tz;
- struct thermal_hwmon_attr temp_input; /* hwmon sys attr */
- struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */
-};
-
-static LIST_HEAD(thermal_hwmon_list);
-
-static ssize_t
-name_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", hwmon->type);
-}
-static DEVICE_ATTR(name, 0444, name_show, NULL);
-
-static ssize_t
-temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
- long temperature;
- int ret;
- struct thermal_hwmon_attr *hwmon_attr
- = container_of(attr, struct thermal_hwmon_attr, attr);
- struct thermal_hwmon_temp *temp
- = container_of(hwmon_attr, struct thermal_hwmon_temp,
- temp_input);
- struct thermal_zone_device *tz = temp->tz;
-
- ret = thermal_zone_get_temp(tz, &temperature);
-
- if (ret)
- return ret;
-
- return sprintf(buf, "%ld\n", temperature);
-}
-
-static ssize_t
-temp_crit_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct thermal_hwmon_attr *hwmon_attr
- = container_of(attr, struct thermal_hwmon_attr, attr);
- struct thermal_hwmon_temp *temp
- = container_of(hwmon_attr, struct thermal_hwmon_temp,
- temp_crit);
- struct thermal_zone_device *tz = temp->tz;
- long temperature;
- int ret;
-
- ret = tz->ops->get_trip_temp(tz, 0, &temperature);
- if (ret)
- return ret;
-
- return sprintf(buf, "%ld\n", temperature);
-}
-
-
-static struct thermal_hwmon_device *
-thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
-
- mutex_lock(&thermal_list_lock);
- list_for_each_entry(hwmon, &thermal_hwmon_list, node)
- if (!strcmp(hwmon->type, tz->type)) {
- mutex_unlock(&thermal_list_lock);
- return hwmon;
- }
- mutex_unlock(&thermal_list_lock);
-
- return NULL;
-}
-
-/* Find the temperature input matching a given thermal zone */
-static struct thermal_hwmon_temp *
-thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
- const struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_temp *temp;
-
- mutex_lock(&thermal_list_lock);
- list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
- if (temp->tz == tz) {
- mutex_unlock(&thermal_list_lock);
- return temp;
- }
- mutex_unlock(&thermal_list_lock);
-
- return NULL;
-}
-
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
- struct thermal_hwmon_temp *temp;
- int new_hwmon_device = 1;
- int result;
-
- hwmon = thermal_hwmon_lookup_by_type(tz);
- if (hwmon) {
- new_hwmon_device = 0;
- goto register_sys_interface;
- }
-
- hwmon = kzalloc(sizeof(struct thermal_hwmon_device), GFP_KERNEL);
- if (!hwmon)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&hwmon->tz_list);
- strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
- hwmon->device = hwmon_device_register(NULL);
- if (IS_ERR(hwmon->device)) {
- result = PTR_ERR(hwmon->device);
- goto free_mem;
- }
- dev_set_drvdata(hwmon->device, hwmon);
- result = device_create_file(hwmon->device, &dev_attr_name);
- if (result)
- goto free_mem;
-
- register_sys_interface:
- temp = kzalloc(sizeof(struct thermal_hwmon_temp), GFP_KERNEL);
- if (!temp) {
- result = -ENOMEM;
- goto unregister_name;
- }
-
- temp->tz = tz;
- hwmon->count++;
-
- snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
- "temp%d_input", hwmon->count);
- temp->temp_input.attr.attr.name = temp->temp_input.name;
- temp->temp_input.attr.attr.mode = 0444;
- temp->temp_input.attr.show = temp_input_show;
- sysfs_attr_init(&temp->temp_input.attr.attr);
- result = device_create_file(hwmon->device, &temp->temp_input.attr);
- if (result)
- goto free_temp_mem;
-
- if (tz->ops->get_crit_temp) {
- unsigned long temperature;
- if (!tz->ops->get_crit_temp(tz, &temperature)) {
- snprintf(temp->temp_crit.name,
- sizeof(temp->temp_crit.name),
- "temp%d_crit", hwmon->count);
- temp->temp_crit.attr.attr.name = temp->temp_crit.name;
- temp->temp_crit.attr.attr.mode = 0444;
- temp->temp_crit.attr.show = temp_crit_show;
- sysfs_attr_init(&temp->temp_crit.attr.attr);
- result = device_create_file(hwmon->device,
- &temp->temp_crit.attr);
- if (result)
- goto unregister_input;
- }
- }
-
- mutex_lock(&thermal_list_lock);
- if (new_hwmon_device)
- list_add_tail(&hwmon->node, &thermal_hwmon_list);
- list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
- mutex_unlock(&thermal_list_lock);
-
- return 0;
-
- unregister_input:
- device_remove_file(hwmon->device, &temp->temp_input.attr);
- free_temp_mem:
- kfree(temp);
- unregister_name:
- if (new_hwmon_device) {
- device_remove_file(hwmon->device, &dev_attr_name);
- hwmon_device_unregister(hwmon->device);
- }
- free_mem:
- if (new_hwmon_device)
- kfree(hwmon);
-
- return result;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- struct thermal_hwmon_device *hwmon;
- struct thermal_hwmon_temp *temp;
-
- hwmon = thermal_hwmon_lookup_by_type(tz);
- if (unlikely(!hwmon)) {
- /* Should never happen... */
- dev_dbg(&tz->device, "hwmon device lookup failed!\n");
- return;
- }
-
- temp = thermal_hwmon_lookup_temp(hwmon, tz);
- if (unlikely(!temp)) {
- /* Should never happen... */
- dev_dbg(&tz->device, "temperature input lookup failed!\n");
- return;
- }
-
- device_remove_file(hwmon->device, &temp->temp_input.attr);
- if (tz->ops->get_crit_temp)
- device_remove_file(hwmon->device, &temp->temp_crit.attr);
-
- mutex_lock(&thermal_list_lock);
- list_del(&temp->hwmon_node);
- kfree(temp);
- if (!list_empty(&hwmon->tz_list)) {
- mutex_unlock(&thermal_list_lock);
- return;
- }
- list_del(&hwmon->node);
- mutex_unlock(&thermal_list_lock);
-
- device_remove_file(hwmon->device, &dev_attr_name);
- hwmon_device_unregister(hwmon->device);
- kfree(hwmon);
-}
-#else
-static int
-thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
-{
- return 0;
-}
-
-static void
-thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
-{
-}
-#endif
-
/**
* thermal_zone_bind_cooling_device() - bind a cooling device to a thermal zone
* @tz: pointer to struct thermal_zone_device
@@ -1287,7 +1057,8 @@
};
/**
- * thermal_cooling_device_register() - register a new thermal cooling device
+ * __thermal_cooling_device_register() - register a new thermal cooling device
+ * @np: a pointer to a device tree node.
* @type: the thermal cooling device type.
* @devdata: device private data.
* @ops: standard thermal cooling devices callbacks.
@@ -1295,13 +1066,16 @@
* This interface function adds a new thermal cooling device (fan/processor/...)
* to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
* to all the thermal zone devices registered at the same time.
+ * It also gives the opportunity to link the cooling device to a device tree
+ * node, so that it can be bound to a thermal zone created out of device tree.
*
* Return: a pointer to the created struct thermal_cooling_device or an
* ERR_PTR. Caller must check return value with IS_ERR*() helpers.
*/
-struct thermal_cooling_device *
-thermal_cooling_device_register(char *type, void *devdata,
- const struct thermal_cooling_device_ops *ops)
+static struct thermal_cooling_device *
+__thermal_cooling_device_register(struct device_node *np,
+ char *type, void *devdata,
+ const struct thermal_cooling_device_ops *ops)
{
struct thermal_cooling_device *cdev;
int result;
@@ -1326,8 +1100,9 @@
strlcpy(cdev->type, type ? : "", sizeof(cdev->type));
mutex_init(&cdev->lock);
INIT_LIST_HEAD(&cdev->thermal_instances);
+ cdev->np = np;
cdev->ops = ops;
- cdev->updated = true;
+ cdev->updated = false;
cdev->device.class = &thermal_class;
cdev->devdata = devdata;
dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
@@ -1368,9 +1143,53 @@
device_unregister(&cdev->device);
return ERR_PTR(result);
}
+
+/**
+ * thermal_cooling_device_register() - register a new thermal cooling device
+ * @type: the thermal cooling device type.
+ * @devdata: device private data.
+ * @ops: standard thermal cooling devices callbacks.
+ *
+ * This interface function adds a new thermal cooling device (fan/processor/...)
+ * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+ * to all the thermal zone devices registered at the same time.
+ *
+ * Return: a pointer to the created struct thermal_cooling_device or an
+ * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
+ */
+struct thermal_cooling_device *
+thermal_cooling_device_register(char *type, void *devdata,
+ const struct thermal_cooling_device_ops *ops)
+{
+ return __thermal_cooling_device_register(NULL, type, devdata, ops);
+}
EXPORT_SYMBOL_GPL(thermal_cooling_device_register);
/**
+ * thermal_of_cooling_device_register() - register an OF thermal cooling device
+ * @np: a pointer to a device tree node.
+ * @type: the thermal cooling device type.
+ * @devdata: device private data.
+ * @ops: standard thermal cooling devices callbacks.
+ *
+ * This function will register a cooling device with device tree node reference.
+ * This interface function adds a new thermal cooling device (fan/processor/...)
+ * to /sys/class/thermal/ folder as cooling_device[0-*]. It tries to bind itself
+ * to all the thermal zone devices registered at the same time.
+ *
+ * Return: a pointer to the created struct thermal_cooling_device or an
+ * ERR_PTR. Caller must check return value with IS_ERR*() helpers.
+ */
+struct thermal_cooling_device *
+thermal_of_cooling_device_register(struct device_node *np,
+ char *type, void *devdata,
+ const struct thermal_cooling_device_ops *ops)
+{
+ return __thermal_cooling_device_register(np, type, devdata, ops);
+}
+EXPORT_SYMBOL_GPL(thermal_of_cooling_device_register);
+
+/**
* thermal_cooling_device_unregister - removes the registered thermal cooling device
* @cdev: the thermal cooling device to remove.
*
@@ -1442,6 +1261,8 @@
mutex_lock(&cdev->lock);
/* Make sure cdev enters the deepest cooling state */
list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) {
+ dev_dbg(&cdev->device, "zone%d->target=%lu\n",
+ instance->tz->id, instance->target);
if (instance->target == THERMAL_NO_TARGET)
continue;
if (instance->target > target)
@@ -1450,6 +1271,7 @@
mutex_unlock(&cdev->lock);
cdev->ops->set_cur_state(cdev, target);
cdev->updated = true;
+ dev_dbg(&cdev->device, "set to state %lu\n", target);
}
EXPORT_SYMBOL(thermal_cdev_update);
@@ -1605,7 +1427,7 @@
*/
struct thermal_zone_device *thermal_zone_device_register(const char *type,
int trips, int mask, void *devdata,
- const struct thermal_zone_device_ops *ops,
+ struct thermal_zone_device_ops *ops,
const struct thermal_zone_params *tzp,
int passive_delay, int polling_delay)
{
@@ -1621,7 +1443,7 @@
if (trips > THERMAL_MAX_TRIPS || trips < 0 || mask >> trips)
return ERR_PTR(-EINVAL);
- if (!ops || !ops->get_temp)
+ if (!ops)
return ERR_PTR(-EINVAL);
if (trips > 0 && !ops->get_trip_type)
@@ -1706,13 +1528,15 @@
if (tz->tzp)
tz->governor = __find_governor(tz->tzp->governor_name);
else
- tz->governor = __find_governor(DEFAULT_THERMAL_GOVERNOR);
+ tz->governor = def_governor;
mutex_unlock(&thermal_governor_lock);
- result = thermal_add_hwmon_sysfs(tz);
- if (result)
- goto unregister;
+ if (!tz->tzp || !tz->tzp->no_hwmon) {
+ result = thermal_add_hwmon_sysfs(tz);
+ if (result)
+ goto unregister;
+ }
mutex_lock(&thermal_list_lock);
list_add_tail(&tz->node, &thermal_tz_list);
@@ -1723,6 +1547,9 @@
INIT_DELAYED_WORK(&(tz->poll_queue), thermal_zone_device_check);
+ if (!tz->ops->get_temp)
+ thermal_zone_device_set_polling(tz, 0);
+
thermal_zone_device_update(tz);
if (!result)
@@ -1980,8 +1807,14 @@
if (result)
goto unregister_class;
+ result = of_parse_thermal_zones();
+ if (result)
+ goto exit_netlink;
+
return 0;
+exit_netlink:
+ genetlink_exit();
unregister_governors:
thermal_unregister_governors();
unregister_class:
@@ -1997,6 +1830,7 @@
static void __exit thermal_exit(void)
{
+ of_thermal_destroy_zones();
genetlink_exit();
class_unregister(&thermal_class);
thermal_unregister_governors();
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 7cf2f66..3db339f 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -77,4 +77,13 @@
static inline void thermal_gov_user_space_unregister(void) {}
#endif /* CONFIG_THERMAL_GOV_USER_SPACE */
+/* device tree support */
+#ifdef CONFIG_THERMAL_OF
+int of_parse_thermal_zones(void);
+void of_thermal_destroy_zones(void);
+#else
+static inline int of_parse_thermal_zones(void) { return 0; }
+static inline void of_thermal_destroy_zones(void) { }
+#endif
+
#endif /* __THERMAL_CORE_H__ */
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
new file mode 100644
index 0000000..fdb0719
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.c
@@ -0,0 +1,269 @@
+/*
+ * thermal_hwmon.c - Generic Thermal Management hwmon support.
+ *
+ * Code based on Intel thermal_core.c. Copyrights of the original code:
+ * Copyright (C) 2008 Intel Corp
+ * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <linux/hwmon.h>
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include "thermal_hwmon.h"
+
+/* hwmon sys I/F */
+/* thermal zone devices with the same type share one hwmon device */
+struct thermal_hwmon_device {
+ char type[THERMAL_NAME_LENGTH];
+ struct device *device;
+ int count;
+ struct list_head tz_list;
+ struct list_head node;
+};
+
+struct thermal_hwmon_attr {
+ struct device_attribute attr;
+ char name[16];
+};
+
+/* one temperature input for each thermal zone */
+struct thermal_hwmon_temp {
+ struct list_head hwmon_node;
+ struct thermal_zone_device *tz;
+ struct thermal_hwmon_attr temp_input; /* hwmon sys attr */
+ struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */
+};
+
+static LIST_HEAD(thermal_hwmon_list);
+
+static DEFINE_MUTEX(thermal_hwmon_list_lock);
+
+static ssize_t
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
+ return sprintf(buf, "%s\n", hwmon->type);
+}
+static DEVICE_ATTR(name, 0444, name_show, NULL);
+
+static ssize_t
+temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ long temperature;
+ int ret;
+ struct thermal_hwmon_attr *hwmon_attr
+ = container_of(attr, struct thermal_hwmon_attr, attr);
+ struct thermal_hwmon_temp *temp
+ = container_of(hwmon_attr, struct thermal_hwmon_temp,
+ temp_input);
+ struct thermal_zone_device *tz = temp->tz;
+
+ ret = thermal_zone_get_temp(tz, &temperature);
+
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%ld\n", temperature);
+}
+
+static ssize_t
+temp_crit_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct thermal_hwmon_attr *hwmon_attr
+ = container_of(attr, struct thermal_hwmon_attr, attr);
+ struct thermal_hwmon_temp *temp
+ = container_of(hwmon_attr, struct thermal_hwmon_temp,
+ temp_crit);
+ struct thermal_zone_device *tz = temp->tz;
+ long temperature;
+ int ret;
+
+ ret = tz->ops->get_trip_temp(tz, 0, &temperature);
+ if (ret)
+ return ret;
+
+ return sprintf(buf, "%ld\n", temperature);
+}
+
+
+static struct thermal_hwmon_device *
+thermal_hwmon_lookup_by_type(const struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_for_each_entry(hwmon, &thermal_hwmon_list, node)
+ if (!strcmp(hwmon->type, tz->type)) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return hwmon;
+ }
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return NULL;
+}
+
+/* Find the temperature input matching a given thermal zone */
+static struct thermal_hwmon_temp *
+thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
+ const struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_temp *temp;
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_for_each_entry(temp, &hwmon->tz_list, hwmon_node)
+ if (temp->tz == tz) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return temp;
+ }
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return NULL;
+}
+
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+ struct thermal_hwmon_temp *temp;
+ int new_hwmon_device = 1;
+ int result;
+
+ hwmon = thermal_hwmon_lookup_by_type(tz);
+ if (hwmon) {
+ new_hwmon_device = 0;
+ goto register_sys_interface;
+ }
+
+ hwmon = kzalloc(sizeof(*hwmon), GFP_KERNEL);
+ if (!hwmon)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&hwmon->tz_list);
+ strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
+ hwmon->device = hwmon_device_register(NULL);
+ if (IS_ERR(hwmon->device)) {
+ result = PTR_ERR(hwmon->device);
+ goto free_mem;
+ }
+ dev_set_drvdata(hwmon->device, hwmon);
+ result = device_create_file(hwmon->device, &dev_attr_name);
+ if (result)
+ goto free_mem;
+
+ register_sys_interface:
+ temp = kzalloc(sizeof(*temp), GFP_KERNEL);
+ if (!temp) {
+ result = -ENOMEM;
+ goto unregister_name;
+ }
+
+ temp->tz = tz;
+ hwmon->count++;
+
+ snprintf(temp->temp_input.name, sizeof(temp->temp_input.name),
+ "temp%d_input", hwmon->count);
+ temp->temp_input.attr.attr.name = temp->temp_input.name;
+ temp->temp_input.attr.attr.mode = 0444;
+ temp->temp_input.attr.show = temp_input_show;
+ sysfs_attr_init(&temp->temp_input.attr.attr);
+ result = device_create_file(hwmon->device, &temp->temp_input.attr);
+ if (result)
+ goto free_temp_mem;
+
+ if (tz->ops->get_crit_temp) {
+ unsigned long temperature;
+ if (!tz->ops->get_crit_temp(tz, &temperature)) {
+ snprintf(temp->temp_crit.name,
+ sizeof(temp->temp_crit.name),
+ "temp%d_crit", hwmon->count);
+ temp->temp_crit.attr.attr.name = temp->temp_crit.name;
+ temp->temp_crit.attr.attr.mode = 0444;
+ temp->temp_crit.attr.show = temp_crit_show;
+ sysfs_attr_init(&temp->temp_crit.attr.attr);
+ result = device_create_file(hwmon->device,
+ &temp->temp_crit.attr);
+ if (result)
+ goto unregister_input;
+ }
+ }
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ if (new_hwmon_device)
+ list_add_tail(&hwmon->node, &thermal_hwmon_list);
+ list_add_tail(&temp->hwmon_node, &hwmon->tz_list);
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ return 0;
+
+ unregister_input:
+ device_remove_file(hwmon->device, &temp->temp_input.attr);
+ free_temp_mem:
+ kfree(temp);
+ unregister_name:
+ if (new_hwmon_device) {
+ device_remove_file(hwmon->device, &dev_attr_name);
+ hwmon_device_unregister(hwmon->device);
+ }
+ free_mem:
+ if (new_hwmon_device)
+ kfree(hwmon);
+
+ return result;
+}
+
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ struct thermal_hwmon_device *hwmon;
+ struct thermal_hwmon_temp *temp;
+
+ hwmon = thermal_hwmon_lookup_by_type(tz);
+ if (unlikely(!hwmon)) {
+ /* Should never happen... */
+ dev_dbg(&tz->device, "hwmon device lookup failed!\n");
+ return;
+ }
+
+ temp = thermal_hwmon_lookup_temp(hwmon, tz);
+ if (unlikely(!temp)) {
+ /* Should never happen... */
+ dev_dbg(&tz->device, "temperature input lookup failed!\n");
+ return;
+ }
+
+ device_remove_file(hwmon->device, &temp->temp_input.attr);
+ if (tz->ops->get_crit_temp)
+ device_remove_file(hwmon->device, &temp->temp_crit.attr);
+
+ mutex_lock(&thermal_hwmon_list_lock);
+ list_del(&temp->hwmon_node);
+ kfree(temp);
+ if (!list_empty(&hwmon->tz_list)) {
+ mutex_unlock(&thermal_hwmon_list_lock);
+ return;
+ }
+ list_del(&hwmon->node);
+ mutex_unlock(&thermal_hwmon_list_lock);
+
+ device_remove_file(hwmon->device, &dev_attr_name);
+ hwmon_device_unregister(hwmon->device);
+ kfree(hwmon);
+}
diff --git a/drivers/thermal/thermal_hwmon.h b/drivers/thermal/thermal_hwmon.h
new file mode 100644
index 0000000..c798fdb
--- /dev/null
+++ b/drivers/thermal/thermal_hwmon.h
@@ -0,0 +1,49 @@
+/*
+ * thermal_hwmon.h - Generic Thermal Management hwmon support.
+ *
+ * Code based on Intel thermal_core.c. Copyrights of the original code:
+ * Copyright (C) 2008 Intel Corp
+ * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com>
+ * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com>
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Copyright (C) 2013 Eduardo Valentin <eduardo.valentin@ti.com>
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef __THERMAL_HWMON_H__
+#define __THERMAL_HWMON_H__
+
+#include <linux/thermal.h>
+
+#ifdef CONFIG_THERMAL_HWMON
+int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz);
+void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz);
+#else
+static int
+thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+ return 0;
+}
+
+static void
+thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
+{
+}
+#endif
+
+#endif /* __THERMAL_HWMON_H__ */
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index eb255e8..f179033 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -31,6 +31,7 @@
#include <linux/list.h>
#include <linux/module.h>
#include <linux/major.h>
+#include <linux/atomic.h>
#include <linux/sysrq.h>
#include <linux/tty.h>
#include <linux/tty_flip.h>
@@ -70,6 +71,9 @@
/* Picks up late kicks after list walk but before schedule() */
static int hvc_kicked;
+/* hvc_init is triggered from hvc_alloc, i.e. only when actually used */
+static atomic_t hvc_needs_init __read_mostly = ATOMIC_INIT(-1);
+
static int hvc_init(void);
#ifdef CONFIG_MAGIC_SYSRQ
@@ -186,7 +190,7 @@
return hvc_driver;
}
-static int __init hvc_console_setup(struct console *co, char *options)
+static int hvc_console_setup(struct console *co, char *options)
{
if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES)
return -ENODEV;
@@ -842,7 +846,7 @@
int i;
/* We wait until a driver actually comes along */
- if (!hvc_driver) {
+ if (atomic_inc_not_zero(&hvc_needs_init)) {
int err = hvc_init();
if (err)
return ERR_PTR(err);
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 682210d..4fc32c8 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -636,6 +636,7 @@
.name = "xenboot",
.write = xenboot_write_console,
.flags = CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME,
+ .index = -1,
};
#endif /* CONFIG_EARLY_PRINTK */
diff --git a/drivers/tty/hvc/hvsi_lib.c b/drivers/tty/hvc/hvsi_lib.c
index 3396eb9..ac27671 100644
--- a/drivers/tty/hvc/hvsi_lib.c
+++ b/drivers/tty/hvc/hvsi_lib.c
@@ -341,8 +341,8 @@
pr_devel("HVSI@%x: ... waiting handshake\n", pv->termno);
- /* Try for up to 200s */
- for (timeout = 0; timeout < 20; timeout++) {
+ /* Try for up to 400ms */
+ for (timeout = 0; timeout < 40; timeout++) {
if (pv->established)
goto established;
if (!hvsi_get_packet(pv))
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 6422390..3ee7217 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -1089,6 +1089,7 @@
{
unsigned int addr = 0;
unsigned int modem = 0;
+ unsigned int brk = 0;
struct gsm_dlci *dlci;
int len = clen;
u8 *dp = data;
@@ -1115,6 +1116,16 @@
if (len == 0)
return;
}
+ len--;
+ if (len > 0) {
+ while (gsm_read_ea(&brk, *dp++) == 0) {
+ len--;
+ if (len == 0)
+ return;
+ }
+ modem <<= 7;
+ modem |= (brk & 0x7f);
+ }
tty = tty_port_tty_get(&dlci->port);
gsm_process_modem(tty, dlci, modem, clen);
if (tty) {
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 6c7fe90..6cfe401 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2066,8 +2066,12 @@
if (tty->ops->flush_chars)
tty->ops->flush_chars(tty);
} else {
+ struct n_tty_data *ldata = tty->disc_data;
+
while (nr > 0) {
+ mutex_lock(&ldata->output_lock);
c = tty->ops->write(tty, b, nr);
+ mutex_unlock(&ldata->output_lock);
if (c < 0) {
retval = c;
goto break_out;
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index abfd990..7cb3681 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -215,6 +215,9 @@
unsigned long flags;
struct pid *pgrp;
+ if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP)
+ return -EINVAL;
+
if (tty->link) {
spin_lock_irqsave(&tty->link->ctrl_lock, flags);
pgrp = get_pid(tty->link->pgrp);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 86c00b1c..d8c06a3 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -555,7 +555,7 @@
*/
if ((p->port.type == PORT_XR17V35X) ||
(p->port.type == PORT_XR17D15X)) {
- serial_out(p, UART_EXAR_SLEEP, 0xff);
+ serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0);
return;
}
@@ -1520,7 +1520,7 @@
status = serial8250_rx_chars(up, status);
}
serial8250_modem_status(up);
- if (status & UART_LSR_THRE)
+ if (!up->dma && (status & UART_LSR_THRE))
serial8250_tx_chars(up);
spin_unlock_irqrestore(&port->lock, flags);
@@ -2670,6 +2670,10 @@
if (port->type == PORT_16550A && port->iotype == UPIO_AU)
up->bugs |= UART_BUG_NOMSR;
+ /* HW bugs may trigger IRQ while IIR == NO_INT */
+ if (port->type == PORT_TEGRA)
+ up->bugs |= UART_BUG_NOMSR;
+
if (port->type != PORT_UNKNOWN && flags & UART_CONFIG_IRQ)
autoconfig_irq(up);
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index 7046769..148ffe4 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -20,12 +20,15 @@
struct uart_8250_port *p = param;
struct uart_8250_dma *dma = p->dma;
struct circ_buf *xmit = &p->port.state->xmit;
-
- dma->tx_running = 0;
+ unsigned long flags;
dma_sync_single_for_cpu(dma->txchan->device->dev, dma->tx_addr,
UART_XMIT_SIZE, DMA_TO_DEVICE);
+ spin_lock_irqsave(&p->port.lock, flags);
+
+ dma->tx_running = 0;
+
xmit->tail += dma->tx_size;
xmit->tail &= UART_XMIT_SIZE - 1;
p->port.icount.tx += dma->tx_size;
@@ -35,6 +38,8 @@
if (!uart_circ_empty(xmit) && !uart_tx_stopped(&p->port))
serial8250_tx_dma(p);
+
+ spin_unlock_irqrestore(&p->port.lock, flags);
}
static void __dma_rx_complete(void *param)
@@ -187,21 +192,28 @@
dma->rx_buf = dma_alloc_coherent(dma->rxchan->device->dev, dma->rx_size,
&dma->rx_addr, GFP_KERNEL);
- if (!dma->rx_buf) {
- dma_release_channel(dma->rxchan);
- dma_release_channel(dma->txchan);
- return -ENOMEM;
- }
+ if (!dma->rx_buf)
+ goto err;
/* TX buffer */
dma->tx_addr = dma_map_single(dma->txchan->device->dev,
p->port.state->xmit.buf,
UART_XMIT_SIZE,
DMA_TO_DEVICE);
+ if (dma_mapping_error(dma->txchan->device->dev, dma->tx_addr)) {
+ dma_free_coherent(dma->rxchan->device->dev, dma->rx_size,
+ dma->rx_buf, dma->rx_addr);
+ goto err;
+ }
dev_dbg_ratelimited(p->port.dev, "got both dma channels\n");
return 0;
+err:
+ dma_release_channel(dma->rxchan);
+ dma_release_channel(dma->txchan);
+
+ return -ENOMEM;
}
EXPORT_SYMBOL_GPL(serial8250_request_dma);
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index d07b6af..86281fa 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -54,58 +54,106 @@
struct dw8250_data {
- int last_lcr;
+ int last_mcr;
int line;
struct clk *clk;
};
+static inline int dw8250_modify_msr(struct uart_port *p, int offset, int value)
+{
+ struct dw8250_data *d = p->private_data;
+
+ /* If reading MSR, report CTS asserted when auto-CTS/RTS enabled */
+ if (offset == UART_MSR && d->last_mcr & UART_MCR_AFE) {
+ value |= UART_MSR_CTS;
+ value &= ~UART_MSR_DCTS;
+ }
+
+ return value;
+}
+
+static void dw8250_force_idle(struct uart_port *p)
+{
+ serial8250_clear_and_reinit_fifos(container_of
+ (p, struct uart_8250_port, port));
+ (void)p->serial_in(p, UART_RX);
+}
+
static void dw8250_serial_out(struct uart_port *p, int offset, int value)
{
struct dw8250_data *d = p->private_data;
- if (offset == UART_LCR)
- d->last_lcr = value;
+ if (offset == UART_MCR)
+ d->last_mcr = value;
- offset <<= p->regshift;
- writeb(value, p->membase + offset);
+ writeb(value, p->membase + (offset << p->regshift));
+
+ /* Make sure LCR write wasn't ignored */
+ if (offset == UART_LCR) {
+ int tries = 1000;
+ while (tries--) {
+ unsigned int lcr = p->serial_in(p, UART_LCR);
+ if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
+ return;
+ dw8250_force_idle(p);
+ writeb(value, p->membase + (UART_LCR << p->regshift));
+ }
+ /*
+ * FIXME: this deadlocks if port->lock is already held
+ * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+ */
+ }
}
static unsigned int dw8250_serial_in(struct uart_port *p, int offset)
{
- offset <<= p->regshift;
+ unsigned int value = readb(p->membase + (offset << p->regshift));
- return readb(p->membase + offset);
+ return dw8250_modify_msr(p, offset, value);
}
static void dw8250_serial_out32(struct uart_port *p, int offset, int value)
{
struct dw8250_data *d = p->private_data;
- if (offset == UART_LCR)
- d->last_lcr = value;
+ if (offset == UART_MCR)
+ d->last_mcr = value;
- offset <<= p->regshift;
- writel(value, p->membase + offset);
+ writel(value, p->membase + (offset << p->regshift));
+
+ /* Make sure LCR write wasn't ignored */
+ if (offset == UART_LCR) {
+ int tries = 1000;
+ while (tries--) {
+ unsigned int lcr = p->serial_in(p, UART_LCR);
+ if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
+ return;
+ dw8250_force_idle(p);
+ writel(value, p->membase + (UART_LCR << p->regshift));
+ }
+ /*
+ * FIXME: this deadlocks if port->lock is already held
+ * dev_err(p->dev, "Couldn't set LCR to %d\n", value);
+ */
+ }
}
static unsigned int dw8250_serial_in32(struct uart_port *p, int offset)
{
- offset <<= p->regshift;
+ unsigned int value = readl(p->membase + (offset << p->regshift));
- return readl(p->membase + offset);
+ return dw8250_modify_msr(p, offset, value);
}
static int dw8250_handle_irq(struct uart_port *p)
{
- struct dw8250_data *d = p->private_data;
unsigned int iir = p->serial_in(p, UART_IIR);
if (serial8250_handle_irq(p, iir)) {
return 1;
} else if ((iir & UART_IIR_BUSY) == UART_IIR_BUSY) {
- /* Clear the USR and write the LCR again. */
+ /* Clear the USR */
(void)p->serial_in(p, DW_UART_USR);
- p->serial_out(p, UART_LCR, d->last_lcr);
return 1;
}
@@ -369,6 +417,8 @@
static const struct acpi_device_id dw8250_acpi_match[] = {
{ "INT33C4", 0 },
{ "INT33C5", 0 },
+ { "INT3434", 0 },
+ { "INT3435", 0 },
{ "80860F0A", 0 },
{ },
};
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index 721904f..4858b8a 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -35,18 +35,8 @@
#include <linux/serial_8250.h>
#include <asm/io.h>
#include <asm/serial.h>
-#ifdef CONFIG_FIX_EARLYCON_MEM
-#include <asm/pgtable.h>
-#include <asm/fixmap.h>
-#endif
-struct early_serial8250_device {
- struct uart_port port;
- char options[16]; /* e.g., 115200n8 */
- unsigned int baud;
-};
-
-static struct early_serial8250_device early_device;
+static struct earlycon_device *early_device;
unsigned int __weak __init serial8250_early_in(struct uart_port *port, int offset)
{
@@ -100,7 +90,7 @@
static void __init early_serial8250_write(struct console *console,
const char *s, unsigned int count)
{
- struct uart_port *port = &early_device.port;
+ struct uart_port *port = &early_device->port;
unsigned int ier;
/* Save the IER and disable interrupts */
@@ -129,7 +119,7 @@
return (port->uartclk / 16) / quot;
}
-static void __init init_port(struct early_serial8250_device *device)
+static void __init init_port(struct earlycon_device *device)
{
struct uart_port *port = &device->port;
unsigned int divisor;
@@ -148,127 +138,45 @@
serial8250_early_out(port, UART_LCR, c & ~UART_LCR_DLAB);
}
-static int __init parse_options(struct early_serial8250_device *device,
- char *options)
+static int __init early_serial8250_setup(struct earlycon_device *device,
+ const char *options)
{
- struct uart_port *port = &device->port;
- int mmio, mmio32, length;
-
- if (!options)
- return -ENODEV;
-
- port->uartclk = BASE_BAUD * 16;
-
- mmio = !strncmp(options, "mmio,", 5);
- mmio32 = !strncmp(options, "mmio32,", 7);
- if (mmio || mmio32) {
- port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
- port->mapbase = simple_strtoul(options + (mmio ? 5 : 7),
- &options, 0);
- if (mmio32)
- port->regshift = 2;
-#ifdef CONFIG_FIX_EARLYCON_MEM
- set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
- port->mapbase & PAGE_MASK);
- port->membase =
- (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
- port->membase += port->mapbase & ~PAGE_MASK;
-#else
- port->membase = ioremap_nocache(port->mapbase, 64);
- if (!port->membase) {
- printk(KERN_ERR "%s: Couldn't ioremap 0x%llx\n",
- __func__,
- (unsigned long long) port->mapbase);
- return -ENOMEM;
- }
-#endif
- } else if (!strncmp(options, "io,", 3)) {
- port->iotype = UPIO_PORT;
- port->iobase = simple_strtoul(options + 3, &options, 0);
- mmio = 0;
- } else
- return -EINVAL;
-
- options = strchr(options, ',');
- if (options) {
- options++;
- device->baud = simple_strtoul(options, NULL, 0);
- length = min(strcspn(options, " "), sizeof(device->options));
- strlcpy(device->options, options, length);
- } else {
- device->baud = probe_baud(port);
- snprintf(device->options, sizeof(device->options), "%u",
- device->baud);
- }
-
- if (mmio || mmio32)
- printk(KERN_INFO
- "Early serial console at MMIO%s 0x%llx (options '%s')\n",
- mmio32 ? "32" : "",
- (unsigned long long)port->mapbase,
- device->options);
- else
- printk(KERN_INFO
- "Early serial console at I/O port 0x%lx (options '%s')\n",
- port->iobase,
- device->options);
-
- return 0;
-}
-
-static struct console early_serial8250_console __initdata = {
- .name = "uart",
- .write = early_serial8250_write,
- .flags = CON_PRINTBUFFER | CON_BOOT,
- .index = -1,
-};
-
-static int __init early_serial8250_setup(char *options)
-{
- struct early_serial8250_device *device = &early_device;
- int err;
-
- if (device->port.membase || device->port.iobase)
+ if (!(device->port.membase || device->port.iobase))
return 0;
- err = parse_options(device, options);
- if (err < 0)
- return err;
+ if (!device->baud) {
+ device->baud = probe_baud(&device->port);
+ snprintf(device->options, sizeof(device->options), "%u",
+ device->baud);
+ }
init_port(device);
+
+ early_device = device;
+ device->con->write = early_serial8250_write;
return 0;
}
+EARLYCON_DECLARE(uart8250, early_serial8250_setup);
+EARLYCON_DECLARE(uart, early_serial8250_setup);
int __init setup_early_serial8250_console(char *cmdline)
{
- char *options;
- int err;
+ char match[] = "uart8250";
- options = strstr(cmdline, "uart8250,");
- if (!options) {
- options = strstr(cmdline, "uart,");
- if (!options)
- return 0;
- }
+ if (cmdline && cmdline[4] == ',')
+ match[4] = '\0';
- options = strchr(cmdline, ',') + 1;
- err = early_serial8250_setup(options);
- if (err < 0)
- return err;
-
- register_console(&early_serial8250_console);
-
- return 0;
+ return setup_earlycon(cmdline, match, early_serial8250_setup);
}
int serial8250_find_port_for_earlycon(void)
{
- struct early_serial8250_device *device = &early_device;
- struct uart_port *port = &device->port;
+ struct earlycon_device *device = early_device;
+ struct uart_port *port = device ? &device->port : NULL;
int line;
int ret;
- if (!device->port.membase && !device->port.iobase)
+ if (!port || (!port->membase && !port->iobase))
return -ENODEV;
line = serial8250_find_port(port);
@@ -283,5 +191,3 @@
return ret;
}
-
-early_param("earlycon", setup_early_serial8250_console);
diff --git a/drivers/tty/serial/8250/8250_gsc.c b/drivers/tty/serial/8250/8250_gsc.c
index bb91b47..2e3ea1a 100644
--- a/drivers/tty/serial/8250/8250_gsc.c
+++ b/drivers/tty/serial/8250/8250_gsc.c
@@ -31,9 +31,8 @@
int err;
#ifdef CONFIG_64BIT
- extern int iosapic_serial_irq(int cellnum);
if (!dev->irq && (dev->id.sversion == 0xad))
- dev->irq = iosapic_serial_irq(dev->mod_index-1);
+ dev->irq = iosapic_serial_irq(dev);
#endif
if (!dev->irq) {
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 26e3a97..98b8423 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -68,7 +68,7 @@
"Please send the output of lspci -vv, this\n"
"message (0x%04x,0x%04x,0x%04x,0x%04x), the\n"
"manufacturer and name of serial board or\n"
- "modem board to rmk+serial@arm.linux.org.uk.\n",
+ "modem board to <linux-serial@vger.kernel.org>.\n",
pci_name(dev), str, dev->vendor, dev->device,
dev->subsystem_vendor, dev->subsystem_device);
}
@@ -1260,10 +1260,10 @@
unsigned long base = pci_resource_start(dev, 0);
if (base) {
u32 tmp;
- outl(inl(base + 0x38), base + 0x38);
+ outl(inl(base + 0x38) | 0x00002000, base + 0x38);
tmp = inl(base + 0x3c);
outl(tmp | 0x01000000, base + 0x3c);
- outl(tmp, base + 0x3c);
+ outl(tmp &= ~0x01000000, base + 0x3c);
}
}
return 0;
@@ -1545,6 +1545,7 @@
#define PCI_DEVICE_ID_TITAN_800E 0xA014
#define PCI_DEVICE_ID_TITAN_200EI 0xA016
#define PCI_DEVICE_ID_TITAN_200EISI 0xA017
+#define PCI_DEVICE_ID_TITAN_200V3 0xA306
#define PCI_DEVICE_ID_TITAN_400V3 0xA310
#define PCI_DEVICE_ID_TITAN_410V3 0xA312
#define PCI_DEVICE_ID_TITAN_800V3 0xA314
@@ -4139,6 +4140,9 @@
{ PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_200EISI,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_oxsemi_2_4000000 },
+ { PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_200V3,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_b0_bt_2_921600 },
{ PCI_VENDOR_ID_TITAN, PCI_DEVICE_ID_TITAN_400V3,
PCI_ANY_ID, PCI_ANY_ID, 0, 0,
pbn_b0_4_921600 },
@@ -4797,10 +4801,6 @@
PCI_VENDOR_ID_IBM, 0x0299,
0, 0, pbn_b0_bt_2_115200 },
- { PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9835,
- 0x1000, 0x0012,
- 0, 0, pbn_b0_bt_2_115200 },
-
{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9901,
0xA000, 0x1000,
0, 0, pbn_b0_1_115200 },
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index 80fe91e..902c4bf 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -62,6 +62,7 @@
bool "Console on 8250/16550 and compatible serial port"
depends on SERIAL_8250=y
select SERIAL_CORE_CONSOLE
+ select SERIAL_EARLYCON
---help---
If you say Y here, it will be possible to use a serial port as the
system console (the system console is the device which receives all
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 7e7006f..1ad9aad 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -7,6 +7,13 @@
menu "Serial drivers"
depends on HAS_IOMEM && GENERIC_HARDIRQS
+config SERIAL_EARLYCON
+ bool
+ help
+ Support for early consoles with the earlycon parameter. This enables
+ the console before standard serial driver is probed. The console is
+ enabled when early_param is processed.
+
source "drivers/tty/serial/8250/Kconfig"
comment "Non-8250 serial port support"
diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile
index eedfec4..e51c680 100644
--- a/drivers/tty/serial/Makefile
+++ b/drivers/tty/serial/Makefile
@@ -5,6 +5,8 @@
obj-$(CONFIG_SERIAL_CORE) += serial_core.o
obj-$(CONFIG_SERIAL_21285) += 21285.o
+obj-$(CONFIG_SERIAL_EARLYCON) += earlycon.o
+
# These Sparc drivers have to appear before others such as 8250
# which share ttySx minor node space. Otherwise console device
# names change and other unplesantries.
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 13471dd..d983370 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -231,7 +231,9 @@
flag);
}
+ spin_unlock(&port->lock);
tty_flip_buffer_push(&port->state->port);
+ spin_lock(&port->lock);
}
static void altera_uart_tx_chars(struct altera_uart *pp)
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index e2774f9..7a55fe7 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1543,6 +1543,8 @@
/*
* Provoke TX FIFO interrupt into asserting.
*/
+ spin_lock_irq(&uap->port.lock);
+
cr = UART01x_CR_UARTEN | UART011_CR_TXE | UART011_CR_LBE;
writew(cr, uap->port.membase + UART011_CR);
writew(0, uap->port.membase + UART011_FBRD);
@@ -1567,6 +1569,8 @@
cr |= UART01x_CR_UARTEN | UART011_CR_RXE | UART011_CR_TXE;
writew(cr, uap->port.membase + UART011_CR);
+ spin_unlock_irq(&uap->port.lock);
+
/*
* initialise the old status of the modem signals
*/
@@ -1636,11 +1640,13 @@
* it during startup().
*/
uap->autorts = false;
+ spin_lock_irq(&uap->port.lock);
cr = readw(uap->port.membase + UART011_CR);
uap->old_cr = cr;
cr &= UART011_CR_RTS | UART011_CR_DTR;
cr |= UART01x_CR_UARTEN | UART011_CR_TXE;
writew(cr, uap->port.membase + UART011_CR);
+ spin_unlock_irq(&uap->port.lock);
/*
* disable break condition and fifos
diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c
index cbf1d15..22f280a 100644
--- a/drivers/tty/serial/arc_uart.c
+++ b/drivers/tty/serial/arc_uart.c
@@ -773,6 +773,6 @@
module_exit(arc_serial_exit);
MODULE_LICENSE("GPL");
-MODULE_ALIAS("plat-arcfpga/uart");
+MODULE_ALIAS("platform:" DRIVER_NAME);
MODULE_AUTHOR("Vineet Gupta");
MODULE_DESCRIPTION("ARC(Synopsys) On-Chip(fpga) serial driver");
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3467462..82127ac 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1022,12 +1022,24 @@
static void atmel_shutdown(struct uart_port *port)
{
struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
+
/*
- * Ensure everything is stopped.
+ * Clear out any scheduled tasklets before
+ * we destroy the buffers
+ */
+ tasklet_kill(&atmel_port->tasklet);
+
+ /*
+ * Ensure everything is stopped and
+ * disable all interrupts, port and break condition.
*/
atmel_stop_rx(port);
atmel_stop_tx(port);
+ UART_PUT_CR(port, ATMEL_US_RSTSTA);
+ UART_PUT_IDR(port, -1);
+
+
/*
* Shut-down the DMA.
*/
@@ -1054,12 +1066,6 @@
}
/*
- * Disable all interrupts, port and break condition.
- */
- UART_PUT_CR(port, ATMEL_US_RSTSTA);
- UART_PUT_IDR(port, -1);
-
- /*
* Free the interrupt
*/
free_irq(port->irq, port);
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
new file mode 100644
index 0000000..4f27f78
--- /dev/null
+++ b/drivers/tty/serial/earlycon.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Rob Herring <robh@kernel.org>
+ *
+ * Based on 8250 earlycon:
+ * (c) Copyright 2004 Hewlett-Packard Development Company, L.P.
+ * Bjorn Helgaas <bjorn.helgaas@hp.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/serial_core.h>
+
+#ifdef CONFIG_FIX_EARLYCON_MEM
+#include <asm/fixmap.h>
+#endif
+
+#include <asm/serial.h>
+
+static struct console early_con = {
+ .name = "uart", /* 8250 console switch requires this name */
+ .flags = CON_PRINTBUFFER | CON_BOOT,
+ .index = -1,
+};
+
+static struct earlycon_device early_console_dev = {
+ .con = &early_con,
+};
+
+static void __iomem * __init earlycon_map(unsigned long paddr, size_t size)
+{
+ void __iomem *base;
+#ifdef CONFIG_FIX_EARLYCON_MEM
+ set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr & PAGE_MASK);
+ base = (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
+ base += paddr & ~PAGE_MASK;
+#else
+ base = ioremap(paddr, size);
+#endif
+ if (!base)
+ pr_err("%s: Couldn't map 0x%llx\n", __func__,
+ (unsigned long long)paddr);
+
+ return base;
+}
+
+static int __init parse_options(struct earlycon_device *device,
+ char *options)
+{
+ struct uart_port *port = &device->port;
+ int mmio, mmio32, length, ret;
+ unsigned long addr;
+
+ if (!options)
+ return -ENODEV;
+
+ mmio = !strncmp(options, "mmio,", 5);
+ mmio32 = !strncmp(options, "mmio32,", 7);
+ if (mmio || mmio32) {
+ port->iotype = (mmio ? UPIO_MEM : UPIO_MEM32);
+ options += mmio ? 5 : 7;
+ ret = kstrtoul(options, 0, &addr);
+ if (ret)
+ return ret;
+ port->mapbase = addr;
+ if (mmio32)
+ port->regshift = 2;
+ } else if (!strncmp(options, "io,", 3)) {
+ port->iotype = UPIO_PORT;
+ options += 3;
+ ret = kstrtoul(options, 0, &addr);
+ if (ret)
+ return ret;
+ port->iobase = addr;
+ mmio = 0;
+ } else if (!strncmp(options, "0x", 2)) {
+ port->iotype = UPIO_MEM;
+ ret = kstrtoul(options, 0, &addr);
+ if (ret)
+ return ret;
+ port->mapbase = addr;
+ } else {
+ return -EINVAL;
+ }
+
+ port->uartclk = BASE_BAUD * 16;
+
+ options = strchr(options, ',');
+ if (options) {
+ options++;
+ ret = kstrtouint(options, 0, &device->baud);
+ if (ret)
+ return ret;
+ length = min(strcspn(options, " ") + 1,
+ (size_t)(sizeof(device->options)));
+ strlcpy(device->options, options, length);
+ }
+
+ if (mmio || mmio32)
+ pr_info("Early serial console at MMIO%s 0x%llx (options '%s')\n",
+ mmio32 ? "32" : "",
+ (unsigned long long)port->mapbase,
+ device->options);
+ else
+ pr_info("Early serial console at I/O port 0x%lx (options '%s')\n",
+ port->iobase,
+ device->options);
+
+ return 0;
+}
+
+int __init setup_earlycon(char *buf, const char *match,
+ int (*setup)(struct earlycon_device *, const char *))
+{
+ int err;
+ size_t len;
+ struct uart_port *port = &early_console_dev.port;
+
+ if (!buf || !match || !setup)
+ return 0;
+
+ len = strlen(match);
+ if (strncmp(buf, match, len))
+ return 0;
+ if (buf[len] && (buf[len] != ','))
+ return 0;
+
+ buf += len + 1;
+
+ err = parse_options(&early_console_dev, buf);
+ /* On parsing error, pass the options buf to the setup function */
+ if (!err)
+ buf = NULL;
+
+ if (port->mapbase)
+ port->membase = earlycon_map(port->mapbase, 64);
+
+ early_console_dev.con->data = &early_console_dev;
+ err = setup(&early_console_dev, buf);
+ if (err < 0)
+ return err;
+ if (!early_console_dev.con->write)
+ return -ENODEV;
+
+ register_console(early_console_dev.con);
+ return 0;
+}
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 4f5f161..f85b8e6 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -678,11 +678,18 @@
static irqreturn_t mxs_auart_irq_handle(int irq, void *context)
{
- u32 istatus, istat;
+ u32 istat;
struct mxs_auart_port *s = context;
u32 stat = readl(s->port.membase + AUART_STAT);
- istatus = istat = readl(s->port.membase + AUART_INTR);
+ istat = readl(s->port.membase + AUART_INTR);
+
+ /* ack irq */
+ writel(istat & (AUART_INTR_RTIS
+ | AUART_INTR_TXIS
+ | AUART_INTR_RXIS
+ | AUART_INTR_CTSMIS),
+ s->port.membase + AUART_INTR_CLR);
if (istat & AUART_INTR_CTSMIS) {
uart_handle_cts_change(&s->port, stat & AUART_STAT_CTS);
@@ -702,12 +709,6 @@
istat &= ~AUART_INTR_TXIS;
}
- writel(istatus & (AUART_INTR_RTIS
- | AUART_INTR_TXIS
- | AUART_INTR_RXIS
- | AUART_INTR_CTSMIS),
- s->port.membase + AUART_INTR_CLR);
-
return IRQ_HANDLED;
}
@@ -850,7 +851,7 @@
struct mxs_auart_port *s;
struct uart_port *port;
unsigned int old_ctrl0, old_ctrl2;
- unsigned int to = 1000;
+ unsigned int to = 20000;
if (co->index >= MXS_AUART_PORTS || co->index < 0)
return;
@@ -871,18 +872,23 @@
uart_console_write(port, str, count, mxs_auart_console_putchar);
- /*
- * Finally, wait for transmitter to become empty
- * and restore the TCR
- */
+ /* Finally, wait for transmitter to become empty ... */
while (readl(port->membase + AUART_STAT) & AUART_STAT_BUSY) {
+ udelay(1);
if (!to--)
break;
- udelay(1);
}
- writel(old_ctrl0, port->membase + AUART_CTRL0);
- writel(old_ctrl2, port->membase + AUART_CTRL2);
+ /*
+ * ... and restore the TCR if we waited long enough for the transmitter
+ * to be idle. This might keep the transmitter enabled although it is
+ * unused, but that is better than to disable it while it is still
+ * transmitting.
+ */
+ if (!(readl(port->membase + AUART_STAT) & AUART_STAT_BUSY)) {
+ writel(old_ctrl0, port->membase + AUART_CTRL0);
+ writel(old_ctrl2, port->membase + AUART_CTRL2);
+ }
clk_disable(s->clk);
}
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 21a7e17..20e4c94 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -217,6 +217,7 @@
#define FRI2_64_UARTCLK 64000000 /* 64.0000 MHz */
#define FRI2_48_UARTCLK 48000000 /* 48.0000 MHz */
#define NTC1_UARTCLK 64000000 /* 64.0000 MHz */
+#define MINNOW_UARTCLK 50000000 /* 50.0000 MHz */
struct pch_uart_buffer {
unsigned char *buf;
@@ -398,6 +399,10 @@
strstr(cmp, "nanoETXexpress-TT")))
return NTC1_UARTCLK;
+ cmp = dmi_get_system_info(DMI_BOARD_NAME);
+ if (cmp && strstr(cmp, "MinnowBoard"))
+ return MINNOW_UARTCLK;
+
return DEFAULT_UARTCLK;
}
@@ -653,11 +658,12 @@
dev_warn(port->dev, "Rx overrun: dropping %u bytes\n",
size - room);
if (!room)
- return room;
+ goto out;
tty_insert_flip_string(tport, sg_virt(&priv->sg_rx), size);
port->icount.rx += room;
+out:
tty_kref_put(tty);
return room;
@@ -1066,6 +1072,8 @@
if (tty == NULL) {
for (i = 0; error_msg[i] != NULL; i++)
dev_err(&priv->pdev->dev, error_msg[i]);
+ } else {
+ tty_kref_put(tty);
}
}
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index b1785f5..7735bbd 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -2051,6 +2051,9 @@
/* Probe ports */
pmz_probe();
+ if (pmz_ports_count == 0)
+ return -ENODEV;
+
/* TODO: Autoprobe console based on OF */
/* pmz_console.index = i; */
register_console(&pmz_console);
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 0c8a9fa..4522aac 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -249,6 +249,8 @@
ufcon |= S3C2410_UFCON_RESETRX;
wr_regl(port, S3C2410_UFCON, ufcon);
rx_enabled(port) = 1;
+ spin_unlock_irqrestore(&port->lock,
+ flags);
goto out;
}
continue;
@@ -297,10 +299,11 @@
ignore_char:
continue;
}
+
+ spin_unlock_irqrestore(&port->lock, flags);
tty_flip_buffer_push(&port->state->port);
out:
- spin_unlock_irqrestore(&port->lock, flags);
return IRQ_HANDLED;
}
@@ -534,11 +537,15 @@
unsigned int old)
{
struct s3c24xx_uart_port *ourport = to_ourport(port);
+ int timeout = 10000;
ourport->pm_level = level;
switch (level) {
case 3:
+ while (--timeout && !s3c24xx_serial_txempty_nofifo(port))
+ udelay(100);
+
if (!IS_ERR(ourport->baudclk))
clk_disable_unprepare(ourport->baudclk);
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 9799d04..357a837 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -726,7 +726,7 @@
static void tegra_uart_stop_rx(struct uart_port *u)
{
struct tegra_uart_port *tup = to_tegra_uport(u);
- struct tty_struct *tty = tty_port_tty_get(&tup->uport.state->port);
+ struct tty_struct *tty;
struct tty_port *port = &u->state->port;
struct dma_tx_state state;
unsigned long ier;
@@ -738,6 +738,8 @@
if (!tup->rx_in_progress)
return;
+ tty = tty_port_tty_get(&tup->uport.state->port);
+
tegra_uart_wait_sym_time(tup, 1); /* wait a character interval */
ier = tup->ier_shadow;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index f87dbfd..1fabb22 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -241,6 +241,9 @@
/*
* Turn off DTR and RTS early.
*/
+ if (uart_console(uport) && tty)
+ uport->cons->cflag = tty->termios.c_cflag;
+
if (!tty || (tty->termios.c_cflag & HUPCL))
uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
@@ -356,7 +359,7 @@
* The spd_hi, spd_vhi, spd_shi, spd_warp kludge...
* Die! Die! Die!
*/
- if (baud == 38400)
+ if (try == 0 && baud == 38400)
baud = altbaud;
/*
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index a422c8b..aa53fee1 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -157,6 +157,15 @@
(up->port.line == up->port.cons->index))
saw_console_brk = 1;
+ if (count == 0) {
+ if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) {
+ stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR |
+ SAB82532_ISR0_FERR);
+ up->port.icount.brk++;
+ uart_handle_break(&up->port);
+ }
+ }
+
for (i = 0; i < count; i++) {
unsigned char ch = buf[i], flag;
diff --git a/drivers/tty/serial/vt8500_serial.c b/drivers/tty/serial/vt8500_serial.c
index 1a8bc22..f72b43f 100644
--- a/drivers/tty/serial/vt8500_serial.c
+++ b/drivers/tty/serial/vt8500_serial.c
@@ -559,12 +559,13 @@
if (!mmres || !irqres)
return -ENODEV;
- if (np)
+ if (np) {
port = of_alias_get_id(np, "serial");
if (port >= VT8500_MAX_PORTS)
port = -1;
- else
+ } else {
port = -1;
+ }
if (port < 0) {
/* calculate the port id */
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 6464029..2967b6e 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -850,7 +850,8 @@
struct pid *tty_pgrp = tty_get_pgrp(tty);
if (tty_pgrp) {
kill_pgrp(tty_pgrp, SIGHUP, on_exit);
- kill_pgrp(tty_pgrp, SIGCONT, on_exit);
+ if (!on_exit)
+ kill_pgrp(tty_pgrp, SIGCONT, on_exit);
put_pid(tty_pgrp);
}
}
@@ -991,8 +992,8 @@
/* We limit tty time update visibility to every 8 seconds or so. */
static void tty_update_time(struct timespec *time)
{
- unsigned long sec = get_seconds() & ~7;
- if ((long)(sec - time->tv_sec) > 0)
+ unsigned long sec = get_seconds();
+ if (abs(sec - time->tv_sec) & ~7)
time->tv_sec = sec;
}
@@ -1266,12 +1267,13 @@
*
* Locking: None
*/
-static void tty_line_name(struct tty_driver *driver, int index, char *p)
+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
{
if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE)
- strcpy(p, driver->name);
+ return sprintf(p, "%s", driver->name);
else
- sprintf(p, "%s%d", driver->name, index + driver->name_base);
+ return sprintf(p, "%s%d", driver->name,
+ index + driver->name_base);
}
/**
@@ -1618,6 +1620,8 @@
tty_free_termios(tty);
tty_driver_remove_tty(tty->driver, tty);
tty->port->itty = NULL;
+ if (tty->link)
+ tty->link->port->itty = NULL;
cancel_work_sync(&tty->port->buf.work);
if (tty->link)
@@ -1694,6 +1698,7 @@
int pty_master, tty_closing, o_tty_closing, do_sleep;
int idx;
char buf[64];
+ long timeout = 0;
if (tty_paranoia_check(tty, inode, __func__))
return 0;
@@ -1778,7 +1783,11 @@
__func__, tty_name(tty, buf));
tty_unlock_pair(tty, o_tty);
mutex_unlock(&tty_mutex);
- schedule();
+ schedule_timeout_killable(timeout);
+ if (timeout < 120 * HZ)
+ timeout = 2 * timeout + 1;
+ else
+ timeout = MAX_SCHEDULE_TIMEOUT;
}
/*
@@ -3535,9 +3544,19 @@
if (i >= ARRAY_SIZE(cs))
break;
}
- while (i--)
- count += sprintf(buf + count, "%s%d%c",
- cs[i]->name, cs[i]->index, i ? ' ':'\n');
+ while (i--) {
+ int index = cs[i]->index;
+ struct tty_driver *drv = cs[i]->device(cs[i], &index);
+
+ /* don't resolve tty0 as some programs depend on it */
+ if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
+ count += tty_line_name(drv, index, buf + count);
+ else
+ count += sprintf(buf + count, "%s%d",
+ cs[i]->name, cs[i]->index);
+
+ count += sprintf(buf + count, "%c", i ? ' ':'\n');
+ }
console_unlock();
return count;
diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c
index 3500d41..b46aca5 100644
--- a/drivers/tty/tty_ioctl.c
+++ b/drivers/tty/tty_ioctl.c
@@ -217,11 +217,17 @@
#endif
if (!timeout)
timeout = MAX_SCHEDULE_TIMEOUT;
+
if (wait_event_interruptible_timeout(tty->write_wait,
- !tty_chars_in_buffer(tty), timeout) >= 0) {
- if (tty->ops->wait_until_sent)
- tty->ops->wait_until_sent(tty, timeout);
+ !tty_chars_in_buffer(tty), timeout) < 0) {
+ return;
}
+
+ if (timeout == MAX_SCHEDULE_TIMEOUT)
+ timeout = 0;
+
+ if (tty->ops->wait_until_sent)
+ tty->ops->wait_until_sent(tty, timeout);
}
EXPORT_SYMBOL(tty_wait_until_sent);
@@ -1201,6 +1207,9 @@
}
return 0;
case TCFLSH:
+ retval = tty_check_change(tty);
+ if (retval)
+ return retval;
return __tty_perform_flush(tty, arg);
default:
/* Try the mode commands */
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 121aeb9..f597e88 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -256,10 +256,9 @@
{
struct tty_struct *tty = tty_port_tty_get(port);
- if (tty && (!check_clocal || !C_CLOCAL(tty))) {
+ if (tty && (!check_clocal || !C_CLOCAL(tty)))
tty_hangup(tty);
- tty_kref_put(tty);
- }
+ tty_kref_put(tty);
}
EXPORT_SYMBOL_GPL(tty_port_tty_hangup);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 740202d..db9d69f 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -498,6 +498,7 @@
#endif
if (DO_UPDATE(vc))
do_update_region(vc, (unsigned long) p, count);
+ notify_update(vc);
}
/* used by selection: complement pointer position */
@@ -514,6 +515,7 @@
scr_writew(old, screenpos(vc, old_offset, 1));
if (DO_UPDATE(vc))
vc->vc_sw->con_putc(vc, old, oldy, oldx);
+ notify_update(vc);
}
old_offset = offset;
@@ -531,8 +533,8 @@
oldy = (offset >> 1) / vc->vc_cols;
vc->vc_sw->con_putc(vc, new, oldy, oldx);
}
+ notify_update(vc);
}
-
}
static void insert_char(struct vc_data *vc, unsigned int nr)
@@ -1164,6 +1166,8 @@
scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char,
vc->vc_screenbuf_size >> 1);
set_origin(vc);
+ if (CON_IS_VISIBLE(vc))
+ update_screen(vc);
/* fall through */
case 2: /* erase whole display */
count = vc->vc_cols * vc->vc_rows;
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index b645c47..2d57a00 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -630,36 +630,57 @@
return 0;
}
-static const struct vm_operations_struct uio_vm_ops = {
+static const struct vm_operations_struct uio_logical_vm_ops = {
.open = uio_vma_open,
.close = uio_vma_close,
.fault = uio_vma_fault,
};
+static int uio_mmap_logical(struct vm_area_struct *vma)
+{
+ vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_ops = &uio_logical_vm_ops;
+ uio_vma_open(vma);
+ return 0;
+}
+
+static const struct vm_operations_struct uio_physical_vm_ops = {
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+ .access = generic_access_phys,
+#endif
+};
+
static int uio_mmap_physical(struct vm_area_struct *vma)
{
struct uio_device *idev = vma->vm_private_data;
int mi = uio_find_mem_index(vma);
+ struct uio_mem *mem;
if (mi < 0)
return -EINVAL;
+ mem = idev->info->mem + mi;
+ if (vma->vm_end - vma->vm_start > mem->size)
+ return -EINVAL;
+
+ vma->vm_ops = &uio_physical_vm_ops;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ /*
+ * We cannot use the vm_iomap_memory() helper here,
+ * because vma->vm_pgoff is the map index we looked
+ * up above in uio_find_mem_index(), rather than an
+ * actual page offset into the mmap.
+ *
+ * So we just do the physical mmap without a page
+ * offset.
+ */
return remap_pfn_range(vma,
vma->vm_start,
- idev->info->mem[mi].addr >> PAGE_SHIFT,
+ mem->addr >> PAGE_SHIFT,
vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
-static int uio_mmap_logical(struct vm_area_struct *vma)
-{
- vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
- vma->vm_ops = &uio_vm_ops;
- uio_vma_open(vma);
- return 0;
-}
-
static int uio_mmap(struct file *filep, struct vm_area_struct *vma)
{
struct uio_listener *listener = filep->private_data;
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 92e1dc9..73f62ca 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -2,59 +2,15 @@
# USB device configuration
#
-# many non-PCI SOC chips embed OHCI
+# These are unused now, remove them once they are no longer selected
config USB_ARCH_HAS_OHCI
- boolean
- # ARM:
- default y if SA1111
- default y if ARCH_OMAP
- default y if ARCH_S3C24XX
- default y if PXA27x
- default y if PXA3xx
- default y if ARCH_EP93XX
- default y if ARCH_AT91
- default y if MFD_TC6393XB
- default y if ARCH_W90X900
- default y if ARCH_DAVINCI_DA8XX
- default y if ARCH_CNS3XXX
- default y if PLAT_SPEAR
- default y if ARCH_EXYNOS
- # PPC:
- default y if STB03xxx
- default y if PPC_MPC52xx
- # MIPS:
- default y if MIPS_ALCHEMY
- default y if MACH_JZ4740
- # more:
- default PCI
+ bool
-# some non-PCI hcds implement EHCI
config USB_ARCH_HAS_EHCI
- boolean
- default y if FSL_SOC
- default y if PPC_MPC512x
- default y if ARCH_IXP4XX
- default y if ARCH_W90X900
- default y if ARCH_AT91
- default y if ARCH_MXC
- default y if ARCH_MXS
- default y if ARCH_OMAP3
- default y if ARCH_CNS3XXX
- default y if ARCH_VT8500
- default y if PLAT_SPEAR
- default y if PLAT_S5P
- default y if ARCH_MSM
- default y if MICROBLAZE
- default y if SPARC_LEON
- default y if ARCH_MMP
- default y if MACH_LOONGSON1
- default y if PLAT_ORION
- default PCI
+ bool
-# some non-PCI HCDs implement xHCI
config USB_ARCH_HAS_XHCI
- boolean
- default PCI
+ bool
menuconfig USB_SUPPORT
bool "USB support"
@@ -71,19 +27,8 @@
default y
depends on USB || USB_GADGET
-# Host-side USB depends on having a host controller
-# NOTE: dummy_hcd is always an option, but it's ignored here ...
-# NOTE: SL-811 option should be board-specific ...
config USB_ARCH_HAS_HCD
- boolean
- default y if USB_ARCH_HAS_OHCI
- default y if USB_ARCH_HAS_EHCI
- default y if USB_ARCH_HAS_XHCI
- default y if PCMCIA && !M32R # sl811_cs
- default y if ARM # SL-811
- default y if BLACKFIN # SL-811
- default y if SUPERH # r8a66597-hcd
- default PCI
+ def_bool y
# ARM SA1111 chips have a non-PCI based "OHCI-compatible" USB host interface.
config USB
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index b501346..f1cab42 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -103,7 +103,7 @@
do {
/* flush any pending transfer */
- hw_write(ci, OP_ENDPTFLUSH, BIT(n), BIT(n));
+ hw_write(ci, OP_ENDPTFLUSH, ~0, BIT(n));
while (hw_read(ci, OP_ENDPTFLUSH, BIT(n)))
cpu_relax();
} while (hw_read(ci, OP_ENDPTSTAT, BIT(n)));
@@ -203,7 +203,7 @@
if (is_ctrl && dir == RX && hw_read(ci, OP_ENDPTSETUPSTAT, BIT(num)))
return -EAGAIN;
- hw_write(ci, OP_ENDPTPRIME, BIT(n), BIT(n));
+ hw_write(ci, OP_ENDPTPRIME, ~0, BIT(n));
while (hw_read(ci, OP_ENDPTPRIME, BIT(n)))
cpu_relax();
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 9b1cbcf..2800776 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -122,13 +122,23 @@
static int acm_ctrl_msg(struct acm *acm, int request, int value,
void *buf, int len)
{
- int retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
+ int retval;
+
+ retval = usb_autopm_get_interface(acm->control);
+ if (retval)
+ return retval;
+
+ retval = usb_control_msg(acm->dev, usb_sndctrlpipe(acm->dev, 0),
request, USB_RT_ACM, value,
acm->control->altsetting[0].desc.bInterfaceNumber,
buf, len, 5000);
+
dev_dbg(&acm->control->dev,
"%s - rq 0x%02x, val %#x, len %#x, result %d\n",
__func__, request, value, len, retval);
+
+ usb_autopm_put_interface(acm->control);
+
return retval < 0 ? retval : 0;
}
@@ -233,12 +243,9 @@
acm->susp_count);
usb_autopm_get_interface_async(acm->control);
if (acm->susp_count) {
- if (!acm->delayed_wb)
- acm->delayed_wb = wb;
- else
- usb_autopm_put_interface_async(acm->control);
+ usb_anchor_urb(wb->urb, &acm->delayed);
spin_unlock_irqrestore(&acm->write_lock, flags);
- return 0; /* A white lie */
+ return 0;
}
usb_mark_last_busy(acm->dev);
@@ -516,6 +523,7 @@
{
struct acm *acm = container_of(port, struct acm, port);
int retval = -ENODEV;
+ int i;
dev_dbg(&acm->control->dev, "%s\n", __func__);
@@ -564,6 +572,8 @@
return 0;
error_submit_read_urbs:
+ for (i = 0; i < acm->rx_buflimit; i++)
+ usb_kill_urb(acm->read_urbs[i]);
acm->ctrlout = 0;
acm_set_control(acm, acm->ctrlout);
error_set_control:
@@ -591,21 +601,35 @@
static void acm_port_shutdown(struct tty_port *port)
{
struct acm *acm = container_of(port, struct acm, port);
+ struct urb *urb;
+ struct acm_wb *wb;
int i;
+ int pm_err;
dev_dbg(&acm->control->dev, "%s\n", __func__);
mutex_lock(&acm->mutex);
if (!acm->disconnected) {
- usb_autopm_get_interface(acm->control);
+ pm_err = usb_autopm_get_interface(acm->control);
acm_set_control(acm, acm->ctrlout = 0);
+
+ for (;;) {
+ urb = usb_get_from_anchor(&acm->delayed);
+ if (!urb)
+ break;
+ wb = urb->context;
+ wb->use = 0;
+ usb_autopm_put_interface_async(acm->control);
+ }
+
usb_kill_urb(acm->ctrlurb);
for (i = 0; i < ACM_NW; i++)
usb_kill_urb(acm->wb[i].urb);
for (i = 0; i < acm->rx_buflimit; i++)
usb_kill_urb(acm->read_urbs[i]);
acm->control->needs_remote_wakeup = 0;
- usb_autopm_put_interface(acm->control);
+ if (!pm_err)
+ usb_autopm_put_interface(acm->control);
}
mutex_unlock(&acm->mutex);
}
@@ -859,11 +883,12 @@
/* FIXME: Needs to clear unsupported bits in the termios */
acm->clocal = ((termios->c_cflag & CLOCAL) != 0);
- if (!newline.dwDTERate) {
+ if (C_BAUD(tty) == B0) {
newline.dwDTERate = acm->line.dwDTERate;
newctrl &= ~ACM_CTRL_DTR;
- } else
+ } else if (termios_old && (termios_old->c_cflag & CBAUD) == B0) {
newctrl |= ACM_CTRL_DTR;
+ }
if (newctrl != acm->ctrlout)
acm_set_control(acm, acm->ctrlout = newctrl);
@@ -1062,10 +1087,11 @@
} else {
control_interface = usb_ifnum_to_if(usb_dev, union_header->bMasterInterface0);
data_interface = usb_ifnum_to_if(usb_dev, (data_interface_num = union_header->bSlaveInterface0));
- if (!control_interface || !data_interface) {
- dev_dbg(&intf->dev, "no interfaces\n");
- return -ENODEV;
- }
+ }
+
+ if (!control_interface || !data_interface) {
+ dev_dbg(&intf->dev, "no interfaces\n");
+ return -ENODEV;
}
if (data_interface_num != call_interface_num)
@@ -1190,6 +1216,7 @@
acm->bInterval = epread->bInterval;
tty_port_init(&acm->port);
acm->port.ops = &acm_port_ops;
+ init_usb_anchor(&acm->delayed);
buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
if (!buf) {
@@ -1339,6 +1366,7 @@
&dev_attr_wCountryCodes);
device_remove_file(&acm->control->dev,
&dev_attr_iCountryCodeRelDate);
+ kfree(acm->country_codes);
}
device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
alloc_fail7:
@@ -1434,18 +1462,15 @@
struct acm *acm = usb_get_intfdata(intf);
int cnt;
- if (PMSG_IS_AUTO(message)) {
- int b;
-
- spin_lock_irq(&acm->write_lock);
- b = acm->transmitting;
- spin_unlock_irq(&acm->write_lock);
- if (b)
- return -EBUSY;
- }
-
spin_lock_irq(&acm->read_lock);
spin_lock(&acm->write_lock);
+ if (PMSG_IS_AUTO(message)) {
+ if (acm->transmitting) {
+ spin_unlock(&acm->write_lock);
+ spin_unlock_irq(&acm->read_lock);
+ return -EBUSY;
+ }
+ }
cnt = acm->susp_count++;
spin_unlock(&acm->write_lock);
spin_unlock_irq(&acm->read_lock);
@@ -1453,8 +1478,7 @@
if (cnt)
return 0;
- if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags))
- stop_data_traffic(acm);
+ stop_data_traffic(acm);
return 0;
}
@@ -1462,29 +1486,24 @@
static int acm_resume(struct usb_interface *intf)
{
struct acm *acm = usb_get_intfdata(intf);
- struct acm_wb *wb;
+ struct urb *urb;
int rv = 0;
- int cnt;
spin_lock_irq(&acm->read_lock);
- acm->susp_count -= 1;
- cnt = acm->susp_count;
- spin_unlock_irq(&acm->read_lock);
+ spin_lock(&acm->write_lock);
- if (cnt)
- return 0;
+ if (--acm->susp_count)
+ goto out;
if (test_bit(ASYNCB_INITIALIZED, &acm->port.flags)) {
- rv = usb_submit_urb(acm->ctrlurb, GFP_NOIO);
+ rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
- spin_lock_irq(&acm->write_lock);
- if (acm->delayed_wb) {
- wb = acm->delayed_wb;
- acm->delayed_wb = NULL;
- spin_unlock_irq(&acm->write_lock);
- acm_start_wb(acm, wb);
- } else {
- spin_unlock_irq(&acm->write_lock);
+ for (;;) {
+ urb = usb_get_from_anchor(&acm->delayed);
+ if (!urb)
+ break;
+
+ acm_start_wb(acm, urb->context);
}
/*
@@ -1492,12 +1511,14 @@
* do the write path at all cost
*/
if (rv < 0)
- goto err_out;
+ goto out;
- rv = acm_submit_read_urbs(acm, GFP_NOIO);
+ rv = acm_submit_read_urbs(acm, GFP_ATOMIC);
}
+out:
+ spin_unlock(&acm->write_lock);
+ spin_unlock_irq(&acm->read_lock);
-err_out:
return rv;
}
@@ -1529,6 +1550,8 @@
static const struct usb_device_id acm_ids[] = {
/* quirky and broken devices */
+ { USB_DEVICE(0x17ef, 0x7000), /* Lenovo USB modem */
+ .driver_info = NO_UNION_NORMAL, },/* has no union descriptor */
{ USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
@@ -1568,17 +1591,32 @@
{ USB_DEVICE(0x0572, 0x1328), /* Shiro / Aztech USB MODEM UM-3100 */
.driver_info = NO_UNION_NORMAL, /* has no union descriptor */
},
+ { USB_DEVICE(0x2184, 0x001c) }, /* GW Instek AFG-2225 */
{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
},
/* Motorola H24 HSPA module: */
{ USB_DEVICE(0x22b8, 0x2d91) }, /* modem */
- { USB_DEVICE(0x22b8, 0x2d92) }, /* modem + diagnostics */
- { USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port */
- { USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics */
- { USB_DEVICE(0x22b8, 0x2d96) }, /* modem + NMEA */
- { USB_DEVICE(0x22b8, 0x2d97) }, /* modem + diagnostics + NMEA */
- { USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port + NMEA */
- { USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d92), /* modem + diagnostics */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d93), /* modem + AT port */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d95), /* modem + AT port + diagnostics */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d96), /* modem + NMEA */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d97), /* modem + diagnostics + NMEA */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d99), /* modem + AT port + NMEA */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
+ { USB_DEVICE(0x22b8, 0x2d9a), /* modem + AT port + diagnostics + NMEA */
+ .driver_info = NO_UNION_NORMAL, /* handle only modem interface */
+ },
{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h
index 0f76e4a..1683ac1 100644
--- a/drivers/usb/class/cdc-acm.h
+++ b/drivers/usb/class/cdc-acm.h
@@ -117,7 +117,7 @@
unsigned int throttled:1; /* actually throttled */
unsigned int throttle_req:1; /* throttle requested */
u8 bInterval;
- struct acm_wb *delayed_wb; /* write queued for a device about to be woken */
+ struct usb_anchor delayed; /* writes queued for a device about to be woken */
};
#define CDC_DATA_INTERFACE_TYPE 0x0a
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 8a230f0e..07133d0 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -209,6 +209,7 @@
static void wdm_int_callback(struct urb *urb)
{
int rv = 0;
+ int responding;
int status = urb->status;
struct wdm_device *desc;
struct usb_cdc_notification *dr;
@@ -243,7 +244,7 @@
case USB_CDC_NOTIFY_RESPONSE_AVAILABLE:
dev_dbg(&desc->intf->dev,
"NOTIFY_RESPONSE_AVAILABLE received: index %d len %d",
- dr->wIndex, dr->wLength);
+ le16_to_cpu(dr->wIndex), le16_to_cpu(dr->wLength));
break;
case USB_CDC_NOTIFY_NETWORK_CONNECTION:
@@ -256,14 +257,16 @@
clear_bit(WDM_POLL_RUNNING, &desc->flags);
dev_err(&desc->intf->dev,
"unknown notification %d received: index %d len %d\n",
- dr->bNotificationType, dr->wIndex, dr->wLength);
+ dr->bNotificationType,
+ le16_to_cpu(dr->wIndex),
+ le16_to_cpu(dr->wLength));
goto exit;
}
spin_lock(&desc->iuspin);
clear_bit(WDM_READ, &desc->flags);
- set_bit(WDM_RESPONDING, &desc->flags);
- if (!test_bit(WDM_DISCONNECTING, &desc->flags)
+ responding = test_and_set_bit(WDM_RESPONDING, &desc->flags);
+ if (!responding && !test_bit(WDM_DISCONNECTING, &desc->flags)
&& !test_bit(WDM_SUSPENDING, &desc->flags)) {
rv = usb_submit_urb(desc->response, GFP_ATOMIC);
dev_dbg(&desc->intf->dev, "%s: usb_submit_urb %d",
@@ -402,7 +405,7 @@
USB_RECIP_INTERFACE);
req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND;
req->wValue = 0;
- req->wIndex = desc->inum;
+ req->wIndex = desc->inum; /* already converted */
req->wLength = cpu_to_le16(count);
set_bit(WDM_IN_USE, &desc->flags);
desc->outbuf = buf;
@@ -416,7 +419,7 @@
rv = usb_translate_errors(rv);
} else {
dev_dbg(&desc->intf->dev, "Tx URB has been submitted index=%d",
- req->wIndex);
+ le16_to_cpu(req->wIndex));
}
out:
usb_autopm_put_interface(desc->intf);
@@ -685,16 +688,20 @@
{
struct wdm_device *desc = container_of(work, struct wdm_device, rxwork);
unsigned long flags;
- int rv;
+ int rv = 0;
+ int responding;
spin_lock_irqsave(&desc->iuspin, flags);
if (test_bit(WDM_DISCONNECTING, &desc->flags)) {
spin_unlock_irqrestore(&desc->iuspin, flags);
} else {
+ responding = test_and_set_bit(WDM_RESPONDING, &desc->flags);
spin_unlock_irqrestore(&desc->iuspin, flags);
- rv = usb_submit_urb(desc->response, GFP_KERNEL);
+ if (!responding)
+ rv = usb_submit_urb(desc->response, GFP_KERNEL);
if (rv < 0 && rv != -EPERM) {
spin_lock_irqsave(&desc->iuspin, flags);
+ clear_bit(WDM_RESPONDING, &desc->flags);
if (!test_bit(WDM_DISCONNECTING, &desc->flags))
schedule_work(&desc->rxwork);
spin_unlock_irqrestore(&desc->iuspin, flags);
@@ -775,7 +782,7 @@
desc->irq->bRequestType = (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE);
desc->irq->bRequest = USB_CDC_GET_ENCAPSULATED_RESPONSE;
desc->irq->wValue = 0;
- desc->irq->wIndex = desc->inum;
+ desc->irq->wIndex = desc->inum; /* already converted */
desc->irq->wLength = cpu_to_le16(desc->wMaxCommand);
usb_fill_control_urb(
@@ -815,13 +822,11 @@
{
/* need autopm_get/put here to ensure the usbcore sees the new value */
int rv = usb_autopm_get_interface(intf);
- if (rv < 0)
- goto err;
intf->needs_remote_wakeup = on;
- usb_autopm_put_interface(intf);
-err:
- return rv;
+ if (!rv)
+ usb_autopm_put_interface(intf);
+ return 0;
}
static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id)
diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c
index b0585e6..19fa68a 100644
--- a/drivers/usb/core/buffer.c
+++ b/drivers/usb/core/buffer.c
@@ -22,17 +22,25 @@
*/
/* FIXME tune these based on pool statistics ... */
-static const size_t pool_max[HCD_BUFFER_POOLS] = {
- /* platforms without dma-friendly caches might need to
- * prevent cacheline sharing...
- */
- 32,
- 128,
- 512,
- PAGE_SIZE / 2
- /* bigger --> allocate pages */
+static size_t pool_max[HCD_BUFFER_POOLS] = {
+ 32, 128, 512, 2048,
};
+void __init usb_init_pool_max(void)
+{
+ /*
+ * The pool_max values must never be smaller than
+ * ARCH_KMALLOC_MINALIGN.
+ */
+ if (ARCH_KMALLOC_MINALIGN <= 32)
+ ; /* Original value is okay */
+ else if (ARCH_KMALLOC_MINALIGN <= 64)
+ pool_max[0] = 64;
+ else if (ARCH_KMALLOC_MINALIGN <= 128)
+ pool_max[0] = 0; /* Don't use this pool */
+ else
+ BUILD_BUG(); /* We don't allow this */
+}
/* SETUP primitives */
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 7199adc..6524383 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -424,7 +424,8 @@
memcpy(&config->desc, buffer, USB_DT_CONFIG_SIZE);
if (config->desc.bDescriptorType != USB_DT_CONFIG ||
- config->desc.bLength < USB_DT_CONFIG_SIZE) {
+ config->desc.bLength < USB_DT_CONFIG_SIZE ||
+ config->desc.bLength > size) {
dev_err(ddev, "invalid descriptor for config index %d: "
"type = 0x%X, length = %d\n", cfgidx,
config->desc.bDescriptorType, config->desc.bLength);
@@ -650,10 +651,6 @@
*
* hub-only!! ... and only in reset path, or usb_new_device()
* (used by real hubs and virtual root hubs)
- *
- * NOTE: if this is a WUSB device and is not authorized, we skip the
- * whole thing. A non-authorized USB device has no
- * configurations.
*/
int usb_get_configuration(struct usb_device *dev)
{
@@ -665,8 +662,6 @@
struct usb_config_descriptor *desc;
cfgno = 0;
- if (dev->authorized == 0) /* Not really an error */
- goto out_not_authorized;
result = -ENOMEM;
if (ncfg > USB_MAXCONFIG) {
dev_warn(ddev, "too many configurations: %d, "
@@ -723,6 +718,10 @@
result = -ENOMEM;
goto err;
}
+
+ if (dev->quirks & USB_QUIRK_DELAY_INIT)
+ msleep(100);
+
result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno,
bigbuffer, length);
if (result < 0) {
@@ -750,7 +749,6 @@
err:
kfree(desc);
-out_not_authorized:
dev->descriptor.bNumConfigurations = cfgno;
err2:
if (result == -ENOMEM)
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index c88c4fb..78ddfb4 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -501,6 +501,7 @@
as->status = urb->status;
signr = as->signr;
if (signr) {
+ memset(&sinfo, 0, sizeof(sinfo));
sinfo.si_signo = as->signr;
sinfo.si_errno = as->status;
sinfo.si_code = SI_ASYNCIO;
@@ -742,6 +743,22 @@
if ((index & ~USB_DIR_IN) == 0)
return 0;
ret = findintfep(ps->dev, index);
+ if (ret < 0) {
+ /*
+ * Some not fully compliant Win apps seem to get
+ * index wrong and have the endpoint number here
+ * rather than the endpoint address (with the
+ * correct direction). Win does let this through,
+ * so we'll not reject it here but leave it to
+ * the device to not break KVM. But we warn.
+ */
+ ret = findintfep(ps->dev, index ^ 0x80);
+ if (ret >= 0)
+ dev_info(&ps->dev->dev,
+ "%s: process %i (%s) requesting ep %02x but needs %02x\n",
+ __func__, task_pid_nr(current),
+ current->comm, index, index ^ 0x80);
+ }
if (ret >= 0)
ret = checkintf(ps, ret);
break;
@@ -2212,6 +2229,7 @@
wake_up_all(&ps->wait);
list_del_init(&ps->list);
if (ps->discsignr) {
+ memset(&sinfo, 0, sizeof(sinfo));
sinfo.si_signo = ps->discsignr;
sinfo.si_errno = EPIPE;
sinfo.si_code = SI_ASYNCIO;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 6eab440..2cdd507 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -953,8 +953,7 @@
* it doesn't support pre_reset/post_reset/reset_resume or
* because it doesn't support suspend/resume.
*
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
*/
void usb_forced_unbind_intf(struct usb_interface *intf)
{
@@ -967,16 +966,37 @@
intf->needs_binding = 1;
}
+/*
+ * Unbind drivers for @udev's marked interfaces. These interfaces have
+ * the needs_binding flag set, for example by usb_resume_interface().
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void unbind_marked_interfaces(struct usb_device *udev)
+{
+ struct usb_host_config *config;
+ int i;
+ struct usb_interface *intf;
+
+ config = udev->actconfig;
+ if (config) {
+ for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+ intf = config->interface[i];
+ if (intf->dev.driver && intf->needs_binding)
+ usb_forced_unbind_intf(intf);
+ }
+ }
+}
+
/* Delayed forced unbinding of a USB interface driver and scan
* for rebinding.
*
- * The caller must hold @intf's device's lock, but not its pm_mutex
- * and not @intf->dev.sem.
+ * The caller must hold @intf's device's lock, but not @intf's lock.
*
* Note: Rebinds will be skipped if a system sleep transition is in
* progress and the PM "complete" callback hasn't occurred yet.
*/
-void usb_rebind_intf(struct usb_interface *intf)
+static void usb_rebind_intf(struct usb_interface *intf)
{
int rc;
@@ -993,6 +1013,41 @@
}
}
+/*
+ * Rebind drivers to @udev's marked interfaces. These interfaces have
+ * the needs_binding flag set.
+ *
+ * The caller must hold @udev's device lock.
+ */
+static void rebind_marked_interfaces(struct usb_device *udev)
+{
+ struct usb_host_config *config;
+ int i;
+ struct usb_interface *intf;
+
+ config = udev->actconfig;
+ if (config) {
+ for (i = 0; i < config->desc.bNumInterfaces; ++i) {
+ intf = config->interface[i];
+ if (intf->needs_binding)
+ usb_rebind_intf(intf);
+ }
+ }
+}
+
+/*
+ * Unbind all of @udev's marked interfaces and then rebind all of them.
+ * This ordering is necessary because some drivers claim several interfaces
+ * when they are first probed.
+ *
+ * The caller must hold @udev's device lock.
+ */
+void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev)
+{
+ unbind_marked_interfaces(udev);
+ rebind_marked_interfaces(udev);
+}
+
#ifdef CONFIG_PM
/* Unbind drivers for @udev's interfaces that don't support suspend/resume
@@ -1022,43 +1077,6 @@
}
}
-/* Unbind drivers for @udev's interfaces that failed to support reset-resume.
- * These interfaces have the needs_binding flag set by usb_resume_interface().
- *
- * The caller must hold @udev's device lock.
- */
-static void unbind_no_reset_resume_drivers_interfaces(struct usb_device *udev)
-{
- struct usb_host_config *config;
- int i;
- struct usb_interface *intf;
-
- config = udev->actconfig;
- if (config) {
- for (i = 0; i < config->desc.bNumInterfaces; ++i) {
- intf = config->interface[i];
- if (intf->dev.driver && intf->needs_binding)
- usb_forced_unbind_intf(intf);
- }
- }
-}
-
-static void do_rebind_interfaces(struct usb_device *udev)
-{
- struct usb_host_config *config;
- int i;
- struct usb_interface *intf;
-
- config = udev->actconfig;
- if (config) {
- for (i = 0; i < config->desc.bNumInterfaces; ++i) {
- intf = config->interface[i];
- if (intf->needs_binding)
- usb_rebind_intf(intf);
- }
- }
-}
-
static int usb_suspend_device(struct usb_device *udev, pm_message_t msg)
{
struct usb_device_driver *udriver;
@@ -1379,7 +1397,7 @@
* whose needs_binding flag is set
*/
if (udev->state != USB_STATE_NOTATTACHED)
- do_rebind_interfaces(udev);
+ rebind_marked_interfaces(udev);
return 0;
}
@@ -1401,7 +1419,7 @@
pm_runtime_disable(dev);
pm_runtime_set_active(dev);
pm_runtime_enable(dev);
- unbind_no_reset_resume_drivers_interfaces(udev);
+ unbind_marked_interfaces(udev);
}
/* Avoid PM error messages for devices disconnected while suspended
@@ -1736,10 +1754,13 @@
if (status == -EAGAIN || status == -EBUSY)
usb_mark_last_busy(udev);
- /* The PM core reacts badly unless the return code is 0,
- * -EAGAIN, or -EBUSY, so always return -EBUSY on an error.
+ /*
+ * The PM core reacts badly unless the return code is 0,
+ * -EAGAIN, or -EBUSY, so always return -EBUSY on an error
+ * (except for root hubs, because they don't suspend through
+ * an upstream port like other USB devices).
*/
- if (status != 0)
+ if (status != 0 && udev->parent)
return -EBUSY;
return status;
}
diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index caeb8d6..4676917 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -75,7 +75,7 @@
PCI_SLOT(companion->devfn) != slot)
continue;
companion_hcd = pci_get_drvdata(companion);
- if (!companion_hcd)
+ if (!companion_hcd || !companion_hcd->self.root_hub)
continue;
fn(pdev, hcd, companion, companion_hcd);
}
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d53547d..cbfd3d1 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1593,6 +1593,7 @@
int usb_hcd_unlink_urb (struct urb *urb, int status)
{
struct usb_hcd *hcd;
+ struct usb_device *udev = urb->dev;
int retval = -EIDRM;
unsigned long flags;
@@ -1604,20 +1605,19 @@
spin_lock_irqsave(&hcd_urb_unlink_lock, flags);
if (atomic_read(&urb->use_count) > 0) {
retval = 0;
- usb_get_dev(urb->dev);
+ usb_get_dev(udev);
}
spin_unlock_irqrestore(&hcd_urb_unlink_lock, flags);
if (retval == 0) {
hcd = bus_to_hcd(urb->dev->bus);
retval = unlink1(hcd, urb, status);
- usb_put_dev(urb->dev);
+ if (retval == 0)
+ retval = -EINPROGRESS;
+ else if (retval != -EIDRM && retval != -EBUSY)
+ dev_dbg(&udev->dev, "hcd_unlink_urb %p fail %d\n",
+ urb, retval);
+ usb_put_dev(udev);
}
-
- if (retval == 0)
- retval = -EINPROGRESS;
- else if (retval != -EIDRM && retval != -EBUSY)
- dev_dbg(&urb->dev->dev, "hcd_unlink_urb %p fail %d\n",
- urb, retval);
return retval;
}
@@ -1947,6 +1947,8 @@
return -EINVAL;
if (dev->speed != USB_SPEED_SUPER)
return -EINVAL;
+ if (dev->state < USB_STATE_CONFIGURED)
+ return -ENODEV;
/* Streams only apply to bulk endpoints. */
for (i = 0; i < num_eps; i++)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index feef935..11a073c 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -668,6 +668,15 @@
static inline int
hub_clear_tt_buffer (struct usb_device *hdev, u16 devinfo, u16 tt)
{
+ /* Need to clear both directions for control ep */
+ if (((devinfo >> 11) & USB_ENDPOINT_XFERTYPE_MASK) ==
+ USB_ENDPOINT_XFER_CONTROL) {
+ int status = usb_control_msg(hdev, usb_sndctrlpipe(hdev, 0),
+ HUB_CLEAR_TT_BUFFER, USB_RT_PORT,
+ devinfo ^ 0x8000, tt, NULL, 0, 1000);
+ if (status)
+ return status;
+ }
return usb_control_msg(hdev, usb_sndctrlpipe(hdev, 0),
HUB_CLEAR_TT_BUFFER, USB_RT_PORT, devinfo,
tt, NULL, 0, 1000);
@@ -878,6 +887,25 @@
if (!hub_is_superspeed(hub->hdev))
return -EINVAL;
+ ret = hub_port_status(hub, port1, &portstatus, &portchange);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI
+ * Controller [1022:7814] will have spurious result making the following
+ * usb 3.0 device hotplugging route to the 2.0 root hub and recognized
+ * as high-speed device if we set the usb 3.0 port link state to
+ * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we
+ * check the state here to avoid the bug.
+ */
+ if ((portstatus & USB_PORT_STAT_LINK_STATE) ==
+ USB_SS_PORT_LS_RX_DETECT) {
+ dev_dbg(&hub->ports[port1 - 1]->dev,
+ "Not disabling port; link state is RxDetect\n");
+ return ret;
+ }
+
ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED);
if (ret)
return ret;
@@ -1115,6 +1143,11 @@
usb_clear_port_feature(hub->hdev, port1,
USB_PORT_FEAT_C_ENABLE);
}
+ if (portchange & USB_PORT_STAT_C_RESET) {
+ need_debounce_delay = true;
+ usb_clear_port_feature(hub->hdev, port1,
+ USB_PORT_FEAT_C_RESET);
+ }
if ((portchange & USB_PORT_STAT_C_BH_RESET) &&
hub_is_superspeed(hub->hdev)) {
need_debounce_delay = true;
@@ -1132,7 +1165,8 @@
/* Tell khubd to disconnect the device or
* check for a new connection
*/
- if (udev || (portstatus & USB_PORT_STAT_CONNECTION))
+ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
+ (portstatus & USB_PORT_STAT_OVERCURRENT))
set_bit(port1, hub->change_bits);
} else if (portstatus & USB_PORT_STAT_ENABLE) {
@@ -1548,10 +1582,15 @@
if (hub->has_indicators && blinkenlights)
hub->indicator [0] = INDICATOR_CYCLE;
- for (i = 0; i < hdev->maxchild; i++)
- if (usb_hub_create_port_device(hub, i + 1) < 0)
+ for (i = 0; i < hdev->maxchild; i++) {
+ ret = usb_hub_create_port_device(hub, i + 1);
+ if (ret < 0) {
dev_err(hub->intfdev,
"couldn't create port%d device.\n", i + 1);
+ hdev->maxchild = i;
+ goto fail_keep_maxchild;
+ }
+ }
usb_hub_adjust_deviceremovable(hdev, hub->descriptor);
@@ -1559,6 +1598,8 @@
return 0;
fail:
+ hdev->maxchild = 0;
+fail_keep_maxchild:
dev_err (hub_dev, "config failed, %s (err %d)\n",
message, ret);
/* hub_disconnect() frees urb and descriptor */
@@ -1579,7 +1620,7 @@
{
struct usb_hub *hub = usb_get_intfdata(intf);
struct usb_device *hdev = interface_to_usbdev(intf);
- int i;
+ int port1;
/* Take the hub off the event list and don't let it be added again */
spin_lock_irq(&hub_event_lock);
@@ -1594,11 +1635,15 @@
hub->error = 0;
hub_quiesce(hub, HUB_DISCONNECT);
- usb_set_intfdata (intf, NULL);
+ /* Avoid races with recursively_mark_NOTATTACHED() */
+ spin_lock_irq(&device_state_lock);
+ port1 = hdev->maxchild;
+ hdev->maxchild = 0;
+ usb_set_intfdata(intf, NULL);
+ spin_unlock_irq(&device_state_lock);
- for (i = 0; i < hdev->maxchild; i++)
- usb_hub_remove_port_device(hub, i + 1);
- hub->hdev->maxchild = 0;
+ for (; port1 > 0; --port1)
+ usb_hub_remove_port_device(hub, port1);
if (hub->hdev->speed == USB_SPEED_HIGH)
highspeed_hubs--;
@@ -1655,11 +1700,28 @@
* - Change autosuspend delay of hub can avoid unnecessary auto
* suspend timer for hub, also may decrease power consumption
* of USB bus.
+ *
+ * - If user has indicated to prevent autosuspend by passing
+ * usbcore.autosuspend = -1 then keep autosuspend disabled.
*/
- pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#ifdef CONFIG_PM_RUNTIME
+ if (hdev->dev.power.autosuspend_delay >= 0)
+ pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#endif
- /* Hubs have proper suspend/resume support. */
- usb_enable_autosuspend(hdev);
+ /*
+ * Hubs have proper suspend/resume support, except for root hubs
+ * where the controller driver doesn't have bus_suspend and
+ * bus_resume methods.
+ */
+ if (hdev->parent) { /* normal device */
+ usb_enable_autosuspend(hdev);
+ } else { /* root hub */
+ const struct hc_driver *drv = bus_to_hcd(hdev->bus)->driver;
+
+ if (drv->bus_suspend && drv->bus_resume)
+ usb_enable_autosuspend(hdev);
+ }
if (hdev->level == MAX_TOPO_LEVEL) {
dev_err(&intf->dev,
@@ -1889,8 +1951,10 @@
|| new_state == USB_STATE_SUSPENDED)
; /* No change to wakeup settings */
else if (new_state == USB_STATE_CONFIGURED)
- wakeup = udev->actconfig->desc.bmAttributes
- & USB_CONFIG_ATT_WAKEUP;
+ wakeup = (udev->quirks &
+ USB_QUIRK_IGNORE_REMOTE_WAKEUP) ? 0 :
+ udev->actconfig->desc.bmAttributes &
+ USB_CONFIG_ATT_WAKEUP;
else
wakeup = 0;
}
@@ -2201,18 +2265,13 @@
return err;
}
}
- if (udev->wusb == 1 && udev->authorized == 0) {
- udev->product = kstrdup("n/a (unauthorized)", GFP_KERNEL);
- udev->manufacturer = kstrdup("n/a (unauthorized)", GFP_KERNEL);
- udev->serial = kstrdup("n/a (unauthorized)", GFP_KERNEL);
- }
- else {
- /* read the standard strings and cache them if present */
- udev->product = usb_cache_string(udev, udev->descriptor.iProduct);
- udev->manufacturer = usb_cache_string(udev,
- udev->descriptor.iManufacturer);
- udev->serial = usb_cache_string(udev, udev->descriptor.iSerialNumber);
- }
+
+ /* read the standard strings and cache them if present */
+ udev->product = usb_cache_string(udev, udev->descriptor.iProduct);
+ udev->manufacturer = usb_cache_string(udev,
+ udev->descriptor.iManufacturer);
+ udev->serial = usb_cache_string(udev, udev->descriptor.iSerialNumber);
+
err = usb_enumerate_device_otg(udev);
if (err < 0)
return err;
@@ -2391,16 +2450,6 @@
usb_dev->authorized = 0;
usb_set_configuration(usb_dev, -1);
- kfree(usb_dev->product);
- usb_dev->product = kstrdup("n/a (unauthorized)", GFP_KERNEL);
- kfree(usb_dev->manufacturer);
- usb_dev->manufacturer = kstrdup("n/a (unauthorized)", GFP_KERNEL);
- kfree(usb_dev->serial);
- usb_dev->serial = kstrdup("n/a (unauthorized)", GFP_KERNEL);
-
- usb_destroy_configuration(usb_dev);
- usb_dev->descriptor.bNumConfigurations = 0;
-
out_unauthorized:
usb_unlock_device(usb_dev);
return 0;
@@ -2428,17 +2477,7 @@
goto error_device_descriptor;
}
- kfree(usb_dev->product);
- usb_dev->product = NULL;
- kfree(usb_dev->manufacturer);
- usb_dev->manufacturer = NULL;
- kfree(usb_dev->serial);
- usb_dev->serial = NULL;
-
usb_dev->authorized = 1;
- result = usb_enumerate_device(usb_dev);
- if (result < 0)
- goto error_enumerate;
/* Choose and set the configuration. This registers the interfaces
* with the driver core and lets interface drivers bind to them.
*/
@@ -2454,7 +2493,6 @@
}
dev_info(&usb_dev->dev, "authorized to connect\n");
-error_enumerate:
error_device_descriptor:
usb_autosuspend_device(usb_dev);
error_autoresume:
@@ -2846,6 +2884,15 @@
USB_CTRL_SET_TIMEOUT);
}
+/* Count of wakeup-enabled devices at or below udev */
+static unsigned wakeup_enabled_descendants(struct usb_device *udev)
+{
+ struct usb_hub *hub = usb_hub_to_struct_hub(udev);
+
+ return udev->do_remote_wakeup +
+ (hub ? hub->wakeup_enabled_descendants : 0);
+}
+
/*
* usb_port_suspend - suspend a usb device's upstream port
* @udev: device that's no longer in active use, not a root hub
@@ -2886,8 +2933,8 @@
* Linux (2.6) currently has NO mechanisms to initiate that: no khubd
* timer, no SRP, no requests through sysfs.
*
- * If Runtime PM isn't enabled or used, non-SuperSpeed devices really get
- * suspended only when their bus goes into global suspend (i.e., the root
+ * If Runtime PM isn't enabled or used, non-SuperSpeed devices may not get
+ * suspended until their bus goes into global suspend (i.e., the root
* hub is suspended). Nevertheless, we change @udev->state to
* USB_STATE_SUSPENDED as this is the device's "logical" state. The actual
* upstream port setting is stored in @udev->port_is_suspended.
@@ -2898,7 +2945,6 @@
{
struct usb_hub *hub = usb_hub_to_struct_hub(udev->parent);
struct usb_port *port_dev = hub->ports[udev->portnum - 1];
- enum pm_qos_flags_status pm_qos_stat;
int port1 = udev->portnum;
int status;
bool really_suspend = true;
@@ -2936,7 +2982,7 @@
status);
/* bail if autosuspend is requested */
if (PMSG_IS_AUTO(msg))
- return status;
+ goto err_wakeup;
}
}
@@ -2945,28 +2991,36 @@
usb_set_usb2_hardware_lpm(udev, 0);
if (usb_disable_ltm(udev)) {
- dev_err(&udev->dev, "%s Failed to disable LTM before suspend\n.",
- __func__);
- return -ENOMEM;
+ dev_err(&udev->dev, "Failed to disable LTM before suspend\n.");
+ status = -ENOMEM;
+ if (PMSG_IS_AUTO(msg))
+ goto err_ltm;
}
if (usb_unlocked_disable_lpm(udev)) {
- dev_err(&udev->dev, "%s Failed to disable LPM before suspend\n.",
- __func__);
- return -ENOMEM;
+ dev_err(&udev->dev, "Failed to disable LPM before suspend\n.");
+ status = -ENOMEM;
+ if (PMSG_IS_AUTO(msg))
+ goto err_lpm3;
}
/* see 7.1.7.6 */
if (hub_is_superspeed(hub->hdev))
status = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_U3);
- else if (PMSG_IS_AUTO(msg))
- status = set_port_feature(hub->hdev, port1,
- USB_PORT_FEAT_SUSPEND);
+
/*
* For system suspend, we do not need to enable the suspend feature
* on individual USB-2 ports. The devices will automatically go
* into suspend a few ms after the root hub stops sending packets.
* The USB 2.0 spec calls this "global suspend".
+ *
+ * However, many USB hubs have a bug: They don't relay wakeup requests
+ * from a downstream port if the port's suspend feature isn't on.
+ * Therefore we will turn on the suspend feature if udev or any of its
+ * descendants is enabled for remote wakeup.
*/
+ else if (PMSG_IS_AUTO(msg) || wakeup_enabled_descendants(udev) > 0)
+ status = set_port_feature(hub->hdev, port1,
+ USB_PORT_FEAT_SUSPEND);
else {
really_suspend = false;
status = 0;
@@ -2974,54 +3028,49 @@
if (status) {
dev_dbg(hub->intfdev, "can't suspend port %d, status %d\n",
port1, status);
- /* paranoia: "should not happen" */
- if (udev->do_remote_wakeup) {
- if (!hub_is_superspeed(hub->hdev)) {
- (void) usb_control_msg(udev,
- usb_sndctrlpipe(udev, 0),
- USB_REQ_CLEAR_FEATURE,
- USB_RECIP_DEVICE,
- USB_DEVICE_REMOTE_WAKEUP, 0,
- NULL, 0,
- USB_CTRL_SET_TIMEOUT);
- } else
- (void) usb_disable_function_remotewakeup(udev);
- }
-
+ /* Try to enable USB3 LPM and LTM again */
+ usb_unlocked_enable_lpm(udev);
+ err_lpm3:
+ usb_enable_ltm(udev);
+ err_ltm:
/* Try to enable USB2 hardware LPM again */
if (udev->usb2_hw_lpm_capable == 1)
usb_set_usb2_hardware_lpm(udev, 1);
- /* Try to enable USB3 LTM and LPM again */
- usb_enable_ltm(udev);
- usb_unlocked_enable_lpm(udev);
+ if (udev->do_remote_wakeup) {
+ if (udev->speed < USB_SPEED_SUPER)
+ usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+ USB_REQ_CLEAR_FEATURE,
+ USB_RECIP_DEVICE,
+ USB_DEVICE_REMOTE_WAKEUP, 0,
+ NULL, 0, USB_CTRL_SET_TIMEOUT);
+ else
+ usb_control_msg(udev, usb_sndctrlpipe(udev, 0),
+ USB_REQ_CLEAR_FEATURE,
+ USB_RECIP_INTERFACE,
+ USB_INTRF_FUNC_SUSPEND, 0,
+ NULL, 0, USB_CTRL_SET_TIMEOUT);
+ }
+ err_wakeup:
/* System sleep transitions should never fail */
if (!PMSG_IS_AUTO(msg))
status = 0;
} else {
- /* device has up to 10 msec to fully suspend */
dev_dbg(&udev->dev, "usb %ssuspend, wakeup %d\n",
(PMSG_IS_AUTO(msg) ? "auto-" : ""),
udev->do_remote_wakeup);
- usb_set_device_state(udev, USB_STATE_SUSPENDED);
if (really_suspend) {
udev->port_is_suspended = 1;
+
+ /* device has up to 10 msec to fully suspend */
msleep(10);
}
+ usb_set_device_state(udev, USB_STATE_SUSPENDED);
}
- /*
- * Check whether current status meets the requirement of
- * usb port power off mechanism
- */
- pm_qos_stat = dev_pm_qos_flags(&port_dev->dev,
- PM_QOS_FLAG_NO_POWER_OFF);
- if (!udev->do_remote_wakeup
- && pm_qos_stat != PM_QOS_FLAGS_ALL
- && udev->persist_enabled
- && !status) {
+ if (status == 0 && !udev->do_remote_wakeup && udev->persist_enabled) {
pm_runtime_put_sync(&port_dev->dev);
port_dev->did_runtime_put = true;
}
@@ -3126,6 +3175,43 @@
}
/*
+ * There are some SS USB devices which take longer time for link training.
+ * XHCI specs 4.19.4 says that when Link training is successful, port
+ * sets CSC bit to 1. So if SW reads port status before successful link
+ * training, then it will not find device to be present.
+ * USB Analyzer log with such buggy devices show that in some cases
+ * device switch on the RX termination after long delay of host enabling
+ * the VBUS. In few other cases it has been seen that device fails to
+ * negotiate link training in first attempt. It has been
+ * reported till now that few devices take as long as 2000 ms to train
+ * the link after host enabling its VBUS and termination. Following
+ * routine implements a 2000 ms timeout for link training. If in a case
+ * link trains before timeout, loop will exit earlier.
+ *
+ * FIXME: If a device was connected before suspend, but was removed
+ * while system was asleep, then the loop in the following routine will
+ * only exit at timeout.
+ *
+ * This routine should only be called when persist is enabled for a SS
+ * device.
+ */
+static int wait_for_ss_port_enable(struct usb_device *udev,
+ struct usb_hub *hub, int *port1,
+ u16 *portchange, u16 *portstatus)
+{
+ int status = 0, delay_ms = 0;
+
+ while (delay_ms < 2000) {
+ if (status || *portstatus & USB_PORT_STAT_CONNECTION)
+ break;
+ msleep(20);
+ delay_ms += 20;
+ status = hub_port_status(hub, *port1, portstatus, portchange);
+ }
+ return status;
+}
+
+/*
* usb_port_resume - re-activate a suspended usb device's upstream port
* @udev: device to re-activate, not a root hub
* Context: must be able to sleep; device not locked; pm locks held
@@ -3196,10 +3282,10 @@
dev_dbg(hub->intfdev, "can't resume port %d, status %d\n",
port1, status);
} else {
- /* drive resume for at least 20 msec */
+ /* drive resume for USB_RESUME_TIMEOUT msec */
dev_dbg(&udev->dev, "usb %sresume\n",
(PMSG_IS_AUTO(msg) ? "auto-" : ""));
- msleep(25);
+ msleep(USB_RESUME_TIMEOUT);
/* Virtual root hubs can trigger on GET_PORT_STATUS to
* stop resume signaling. Then finish the resume
@@ -3227,6 +3313,10 @@
clear_bit(port1, hub->busy_bits);
+ if (udev->persist_enabled && hub_is_superspeed(hub->hdev))
+ status = wait_for_ss_port_enable(udev, hub, &port1, &portchange,
+ &portstatus);
+
status = check_port_resume_type(udev,
hub, port1, status, portchange, portstatus);
if (status == 0)
@@ -3291,7 +3381,11 @@
unsigned port1;
int status;
- /* Warn if children aren't already suspended */
+ /*
+ * Warn if children aren't already suspended.
+ * Also, add up the number of wakeup-enabled descendants.
+ */
+ hub->wakeup_enabled_descendants = 0;
for (port1 = 1; port1 <= hdev->maxchild; port1++) {
struct usb_device *udev;
@@ -3301,6 +3395,9 @@
if (PMSG_IS_AUTO(msg))
return -EBUSY;
}
+ if (udev)
+ hub->wakeup_enabled_descendants +=
+ wakeup_enabled_descendants(udev);
}
if (hdev->do_remote_wakeup && hub->quirk_check_port_auto_suspend) {
@@ -4608,9 +4705,10 @@
hub = list_entry(tmp, struct usb_hub, event_list);
kref_get(&hub->kref);
+ hdev = hub->hdev;
+ usb_get_dev(hdev);
spin_unlock_irq(&hub_event_lock);
- hdev = hub->hdev;
hub_dev = hub->intfdev;
intf = to_usb_interface(hub_dev);
dev_dbg(hub_dev, "state %d ports %d chg %04x evt %04x\n",
@@ -4764,7 +4862,9 @@
hub->ports[i - 1]->child;
dev_dbg(hub_dev, "warm reset port %d\n", i);
- if (!udev) {
+ if (!udev ||
+ !(portstatus & USB_PORT_STAT_CONNECTION) ||
+ udev->state == USB_STATE_NOTATTACHED) {
status = hub_port_reset(hub, i,
NULL, HUB_BH_RESET_TIME,
true);
@@ -4774,8 +4874,8 @@
usb_lock_device(udev);
status = usb_reset_device(udev);
usb_unlock_device(udev);
+ connect_change = 0;
}
- connect_change = 0;
}
if (connect_change)
@@ -4823,6 +4923,7 @@
usb_autopm_put_interface(intf);
loop_disconnected:
usb_unlock_device(hdev);
+ usb_put_dev(hdev);
kref_put(&hub->kref, hub_release);
} /* end while (1) */
@@ -5233,10 +5334,11 @@
else if (cintf->condition ==
USB_INTERFACE_BOUND)
rebind = 1;
+ if (rebind)
+ cintf->needs_binding = 1;
}
- if (ret == 0 && rebind)
- usb_rebind_intf(cintf);
}
+ usb_unbind_and_rebind_marked_interfaces(udev);
}
usb_autosuspend_device(udev);
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index 80ab9ee..f608b39 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -59,6 +59,9 @@
struct usb_tt tt; /* Transaction Translator */
unsigned mA_per_port; /* current for each child */
+#ifdef CONFIG_PM
+ unsigned wakeup_enabled_descendants;
+#endif
unsigned limited_power:1;
unsigned quiescing:1;
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index b8bad29..ef07b35 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -89,22 +89,19 @@
retval = usb_hub_set_port_power(hdev, port1, true);
if (port_dev->child && !retval) {
/*
- * Wait for usb hub port to be reconnected in order to make
- * the resume procedure successful.
+ * Attempt to wait for usb hub port to be reconnected in order
+ * to make the resume procedure successful. The device may have
+ * disconnected while the port was powered off, so ignore the
+ * return status.
*/
retval = hub_port_debounce_be_connected(hub, port1);
- if (retval < 0) {
+ if (retval < 0)
dev_dbg(&port_dev->dev, "can't get reconnection after setting port power on, status %d\n",
retval);
- goto out;
- }
usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_ENABLE);
-
- /* Set return value to 0 if debounce successful */
retval = 0;
}
-out:
clear_bit(port1, hub->busy_bits);
usb_autopm_put_interface(intf);
return retval;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index a635988..b73f303 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -43,9 +43,16 @@
/* Creative SB Audigy 2 NX */
{ USB_DEVICE(0x041e, 0x3020), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Microsoft Wireless Laser Mouse 6000 Receiver */
+ { USB_DEVICE(0x045e, 0x00e1), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* Logitech HD Pro Webcams C920 and C930e */
+ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+
/* Logitech Quickcam Fusion */
{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
@@ -78,6 +85,12 @@
{ USB_DEVICE(0x04d8, 0x000c), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
+ /* CarrolTouch 4000U */
+ { USB_DEVICE(0x04e7, 0x0009), .driver_info = USB_QUIRK_RESET_RESUME },
+
+ /* CarrolTouch 4500U */
+ { USB_DEVICE(0x04e7, 0x0030), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Samsung Android phone modem - ID conflict with SPH-I500 */
{ USB_DEVICE(0x04e8, 0x6601), .driver_info =
USB_QUIRK_CONFIG_INTF_STRINGS },
@@ -91,6 +104,9 @@
/* Alcor Micro Corp. Hub */
{ USB_DEVICE(0x058f, 0x9254), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* MicroTouch Systems touchscreen */
+ { USB_DEVICE(0x0596, 0x051e), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* appletouch */
{ USB_DEVICE(0x05ac, 0x021a), .driver_info = USB_QUIRK_RESET_RESUME },
@@ -124,6 +140,9 @@
/* Broadcom BCM92035DGROM BT dongle */
{ USB_DEVICE(0x0a5c, 0x2021), .driver_info = USB_QUIRK_RESET_RESUME },
+ /* MAYA44USB sound device */
+ { USB_DEVICE(0x0a92, 0x0091), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Action Semiconductor flash disk */
{ USB_DEVICE(0x10d6, 0x2200), .driver_info =
USB_QUIRK_STRING_FETCH_255 },
@@ -146,6 +165,10 @@
{ USB_VENDOR_AND_INTERFACE_INFO(0x046d, USB_CLASS_VIDEO, 1, 0),
.driver_info = USB_QUIRK_RESET_RESUME },
+ /* ASUS Base Station(T100) */
+ { USB_DEVICE(0x0b05, 0x17e0), .driver_info =
+ USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
{ } /* terminating entry must be last */
};
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index b10da72..e54b1bd 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -1003,6 +1003,7 @@
pr_info("%s: USB support disabled\n", usbcore_name);
return 0;
}
+ usb_init_pool_max();
retval = usb_debugfs_init();
if (retval)
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 8238577..0923add7 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -55,7 +55,7 @@
extern int usb_match_device(struct usb_device *dev,
const struct usb_device_id *id);
extern void usb_forced_unbind_intf(struct usb_interface *intf);
-extern void usb_rebind_intf(struct usb_interface *intf);
+extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev);
extern int usb_hub_claim_port(struct usb_device *hdev, unsigned port,
struct dev_state *owner);
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index c35d49d..1d38603 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -450,7 +450,7 @@
}
if (IS_ERR(dwc->usb3_phy)) {
- ret = PTR_ERR(dwc->usb2_phy);
+ ret = PTR_ERR(dwc->usb3_phy);
/*
* if -ENXIO is returned, it means PHY layer wasn't
@@ -603,12 +603,6 @@
{
struct dwc3 *dwc = platform_get_drvdata(pdev);
- usb_phy_set_suspend(dwc->usb2_phy, 1);
- usb_phy_set_suspend(dwc->usb3_phy, 1);
-
- pm_runtime_put(&pdev->dev);
- pm_runtime_disable(&pdev->dev);
-
dwc3_debugfs_exit(dwc);
switch (dwc->mode) {
@@ -629,8 +623,15 @@
dwc3_event_buffers_cleanup(dwc);
dwc3_free_event_buffers(dwc);
+
+ usb_phy_set_suspend(dwc->usb2_phy, 1);
+ usb_phy_set_suspend(dwc->usb3_phy, 1);
+
dwc3_core_exit(dwc);
+ pm_runtime_put_sync(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+
return 0;
}
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index b69d322..7ab3c99 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -759,8 +759,8 @@
struct dwc3_event_type {
u32 is_devspec:1;
- u32 type:6;
- u32 reserved8_31:25;
+ u32 type:7;
+ u32 reserved8_31:24;
} __packed;
#define DWC3_DEPEVT_XFERCOMPLETE 0x01
@@ -836,15 +836,15 @@
* 12 - VndrDevTstRcved
* @reserved15_12: Reserved, not used
* @event_info: Information about this event
- * @reserved31_24: Reserved, not used
+ * @reserved31_25: Reserved, not used
*/
struct dwc3_event_devt {
u32 one_bit:1;
u32 device_event:7;
u32 type:4;
u32 reserved15_12:4;
- u32 event_info:8;
- u32 reserved31_24:8;
+ u32 event_info:9;
+ u32 reserved31_25:7;
} __packed;
/**
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 34638b9..cb5f8c4 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -395,9 +395,9 @@
struct dwc3_omap *omap = platform_get_drvdata(pdev);
dwc3_omap_disable_irqs(omap);
+ device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
- device_for_each_child(&pdev->dev, NULL, dwc3_omap_remove_core);
return 0;
}
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index eba9e2b..2357c4e 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -48,6 +48,8 @@
/* FIXME define these in <linux/pci_ids.h> */
#define PCI_VENDOR_ID_SYNOPSYS 0x16c3
#define PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3 0xabcd
+#define PCI_DEVICE_ID_INTEL_BYT 0x0f37
+#define PCI_DEVICE_ID_INTEL_MRFLD 0x119e
struct dwc3_pci {
struct device *dev;
@@ -208,6 +210,8 @@
PCI_DEVICE(PCI_VENDOR_ID_SYNOPSYS,
PCI_DEVICE_ID_SYNOPSYS_HAPSUSB3),
},
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BYT), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_MRFLD), },
{ } /* Terminating Entry */
};
MODULE_DEVICE_TABLE(pci, dwc3_pci_id_table);
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 5acbb94..6cd418f 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -270,7 +270,7 @@
/* stall is always issued on EP0 */
dep = dwc->eps[0];
- __dwc3_gadget_ep_set_halt(dep, 1);
+ __dwc3_gadget_ep_set_halt(dep, 1, false);
dep->flags = DWC3_EP_ENABLED;
dwc->delayed_status = false;
@@ -478,7 +478,9 @@
dep = dwc3_wIndex_to_dep(dwc, wIndex);
if (!dep)
return -EINVAL;
- ret = __dwc3_gadget_ep_set_halt(dep, set);
+ if (set == 0 && (dep->flags & DWC3_EP_WEDGE))
+ break;
+ ret = __dwc3_gadget_ep_set_halt(dep, set, true);
if (ret)
return -EINVAL;
break;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index b5e5b35..87f8fc6 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -550,12 +550,11 @@
if (!usb_endpoint_xfer_isoc(desc))
return 0;
- memset(&trb_link, 0, sizeof(trb_link));
-
/* Link TRB for ISOC. The HWO bit is never reset */
trb_st_hw = &dep->trb_pool[0];
trb_link = &dep->trb_pool[DWC3_TRB_NUM - 1];
+ memset(trb_link, 0, sizeof(*trb_link));
trb_link->bpl = lower_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
trb_link->bph = upper_32_bits(dwc3_trb_dma_offset(dep, trb_st_hw));
@@ -604,6 +603,10 @@
dwc3_remove_requests(dwc, dep);
+ /* make sure HW endpoint isn't stalled */
+ if (dep->flags & DWC3_EP_STALL)
+ __dwc3_gadget_ep_set_halt(dep, 0, false);
+
reg = dwc3_readl(dwc->regs, DWC3_DALEPENA);
reg &= ~DWC3_DALEPENA_EP(dep->number);
dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
@@ -904,8 +907,7 @@
if (i == (request->num_mapped_sgs - 1) ||
sg_is_last(s)) {
- if (list_is_last(&req->list,
- &dep->request_list))
+ if (list_empty(&dep->request_list))
last_one = true;
chain = false;
}
@@ -923,6 +925,9 @@
if (last_one)
break;
}
+
+ if (last_one)
+ break;
} else {
dma = req->request.dma;
length = req->request.length;
@@ -1202,7 +1207,7 @@
return ret;
}
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value)
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol)
{
struct dwc3_gadget_ep_cmd_params params;
struct dwc3 *dwc = dep->dwc;
@@ -1211,6 +1216,14 @@
memset(¶ms, 0x00, sizeof(params));
if (value) {
+ if (!protocol && ((dep->direction && dep->flags & DWC3_EP_BUSY) ||
+ (!list_empty(&dep->req_queued) ||
+ !list_empty(&dep->request_list)))) {
+ dev_dbg(dwc->dev, "%s: pending request, cannot halt\n",
+ dep->name);
+ return -EAGAIN;
+ }
+
ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
DWC3_DEPCMD_SETSTALL, ¶ms);
if (ret)
@@ -1220,9 +1233,6 @@
else
dep->flags |= DWC3_EP_STALL;
} else {
- if (dep->flags & DWC3_EP_WEDGE)
- return 0;
-
ret = dwc3_send_gadget_ep_cmd(dwc, dep->number,
DWC3_DEPCMD_CLEARSTALL, ¶ms);
if (ret)
@@ -1230,7 +1240,7 @@
value ? "set" : "clear",
dep->name);
else
- dep->flags &= ~DWC3_EP_STALL;
+ dep->flags &= ~(DWC3_EP_STALL | DWC3_EP_WEDGE);
}
return ret;
@@ -1253,7 +1263,7 @@
goto out;
}
- ret = __dwc3_gadget_ep_set_halt(dep, value);
+ ret = __dwc3_gadget_ep_set_halt(dep, value, false);
out:
spin_unlock_irqrestore(&dwc->lock, flags);
@@ -1273,7 +1283,7 @@
if (dep->number == 0 || dep->number == 1)
return dwc3_gadget_ep0_set_halt(ep, 1);
else
- return dwc3_gadget_ep_set_halt(ep, 1);
+ return __dwc3_gadget_ep_set_halt(dep, 1, false);
}
/* -------------------------------------------------------------------------- */
@@ -1508,6 +1518,15 @@
int irq;
u32 reg;
+ irq = platform_get_irq(to_platform_device(dwc->dev), 0);
+ ret = request_threaded_irq(irq, dwc3_interrupt, dwc3_thread_interrupt,
+ IRQF_SHARED | IRQF_ONESHOT, "dwc3", dwc);
+ if (ret) {
+ dev_err(dwc->dev, "failed to request irq #%d --> %d\n",
+ irq, ret);
+ goto err0;
+ }
+
spin_lock_irqsave(&dwc->lock, flags);
if (dwc->gadget_driver) {
@@ -1515,7 +1534,7 @@
dwc->gadget.name,
dwc->gadget_driver->driver.name);
ret = -EBUSY;
- goto err0;
+ goto err1;
}
dwc->gadget_driver = driver;
@@ -1551,41 +1570,38 @@
ret = __dwc3_gadget_ep_enable(dep, &dwc3_gadget_ep0_desc, NULL, false);
if (ret) {
dev_err(dwc->dev, "failed to enable %s\n", dep->name);
- goto err0;
+ goto err2;
}
dep = dwc->eps[1];
ret = __dwc3_gadget_ep_enable(dep, &dwc3_gadget_ep0_desc, NULL, false);
if (ret) {
dev_err(dwc->dev, "failed to enable %s\n", dep->name);
- goto err1;
+ goto err3;
}
/* begin to receive SETUP packets */
dwc->ep0state = EP0_SETUP_PHASE;
dwc3_ep0_out_start(dwc);
- irq = platform_get_irq(to_platform_device(dwc->dev), 0);
- ret = request_threaded_irq(irq, dwc3_interrupt, dwc3_thread_interrupt,
- IRQF_SHARED | IRQF_ONESHOT, "dwc3", dwc);
- if (ret) {
- dev_err(dwc->dev, "failed to request irq #%d --> %d\n",
- irq, ret);
- goto err1;
- }
-
dwc3_gadget_enable_irq(dwc);
spin_unlock_irqrestore(&dwc->lock, flags);
return 0;
-err1:
+err3:
__dwc3_gadget_ep_disable(dwc->eps[0]);
-err0:
+err2:
+ dwc->gadget_driver = NULL;
+
+err1:
spin_unlock_irqrestore(&dwc->lock, flags);
+ free_irq(irq, dwc);
+
+err0:
return ret;
}
@@ -1599,9 +1615,6 @@
spin_lock_irqsave(&dwc->lock, flags);
dwc3_gadget_disable_irq(dwc);
- irq = platform_get_irq(to_platform_device(dwc->dev), 0);
- free_irq(irq, dwc);
-
__dwc3_gadget_ep_disable(dwc->eps[0]);
__dwc3_gadget_ep_disable(dwc->eps[1]);
@@ -1609,6 +1622,9 @@
spin_unlock_irqrestore(&dwc->lock, flags);
+ irq = platform_get_irq(to_platform_device(dwc->dev), 0);
+ free_irq(irq, dwc);
+
return 0;
}
diff --git a/drivers/usb/dwc3/gadget.h b/drivers/usb/dwc3/gadget.h
index 99e6d72..b3f25c3 100644
--- a/drivers/usb/dwc3/gadget.h
+++ b/drivers/usb/dwc3/gadget.h
@@ -114,7 +114,7 @@
int dwc3_gadget_ep0_set_halt(struct usb_ep *ep, int value);
int dwc3_gadget_ep0_queue(struct usb_ep *ep, struct usb_request *request,
gfp_t gfp_flags);
-int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value);
+int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol);
int dwc3_send_gadget_ep_cmd(struct dwc3 *dwc, unsigned ep,
unsigned cmd, struct dwc3_gadget_ep_cmd_params *params);
int dwc3_send_gadget_generic_command(struct dwc3 *dwc, int cmd, u32 param);
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index 073b938..55e9613 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -1703,16 +1703,6 @@
return -ENODEV;
}
- if (pdev->num_resources != 2) {
- DBG("invalid num_resources\n");
- return -ENODEV;
- }
- if ((pdev->resource[0].flags != IORESOURCE_MEM)
- || (pdev->resource[1].flags != IORESOURCE_IRQ)) {
- DBG("invalid resource type\n");
- return -ENODEV;
- }
-
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res)
return -ENXIO;
diff --git a/drivers/usb/gadget/bcm63xx_udc.c b/drivers/usb/gadget/bcm63xx_udc.c
index fd24cb4..5396709 100644
--- a/drivers/usb/gadget/bcm63xx_udc.c
+++ b/drivers/usb/gadget/bcm63xx_udc.c
@@ -361,24 +361,30 @@
bcm_writel(val, udc->iudma_regs + off);
}
-static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off, int chan)
{
- return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+ return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+ int chan)
{
- bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off);
+ bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off)
+static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off, int chan)
{
- return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+ return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
-static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off)
+static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off,
+ int chan)
{
- bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off);
+ bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off +
+ (ENETDMA_CHAN_WIDTH * chan));
}
static inline void set_clocks(struct bcm63xx_udc *udc, bool is_enabled)
@@ -639,7 +645,7 @@
} while (!last_bd);
usb_dmac_writel(udc, ENETDMAC_CHANCFG_EN_MASK,
- ENETDMAC_CHANCFG_REG(iudma->ch_idx));
+ ENETDMAC_CHANCFG_REG, iudma->ch_idx);
}
/**
@@ -695,9 +701,9 @@
bcm63xx_fifo_reset_ep(udc, max(0, iudma->ep_num));
/* stop DMA, then wait for the hardware to wrap up */
- usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG(ch_idx));
+ usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG, ch_idx);
- while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)) &
+ while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx) &
ENETDMAC_CHANCFG_EN_MASK) {
udelay(1);
@@ -714,10 +720,10 @@
dev_warn(udc->dev, "forcibly halting IUDMA channel %d\n",
ch_idx);
usb_dmac_writel(udc, ENETDMAC_CHANCFG_BUFHALT_MASK,
- ENETDMAC_CHANCFG_REG(ch_idx));
+ ENETDMAC_CHANCFG_REG, ch_idx);
}
}
- usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG(ch_idx));
+ usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG, ch_idx);
/* don't leave "live" HW-owned entries for the next guy to step on */
for (d = iudma->bd_ring; d <= iudma->end_bd; d++)
@@ -729,11 +735,11 @@
/* set up IRQs, UBUS burst size, and BD base for this channel */
usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
- ENETDMAC_IRMASK_REG(ch_idx));
- usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG(ch_idx));
+ ENETDMAC_IRMASK_REG, ch_idx);
+ usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG, ch_idx);
- usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG(ch_idx));
- usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG(ch_idx));
+ usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG, ch_idx);
+ usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG, ch_idx);
}
/**
@@ -2036,7 +2042,7 @@
spin_lock(&udc->lock);
usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK,
- ENETDMAC_IR_REG(iudma->ch_idx));
+ ENETDMAC_IR_REG, iudma->ch_idx);
bep = iudma->bep;
rc = iudma_read(udc, iudma);
@@ -2176,18 +2182,18 @@
seq_printf(s, " [ep%d]:\n",
max_t(int, iudma_defaults[ch_idx].ep_num, 0));
seq_printf(s, " cfg: %08x; irqstat: %08x; irqmask: %08x; maxburst: %08x\n",
- usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_IR_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_IRMASK_REG(ch_idx)),
- usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG(ch_idx)));
+ usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_IR_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_IRMASK_REG, ch_idx),
+ usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG, ch_idx));
- sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG(ch_idx));
- sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG(ch_idx));
+ sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG, ch_idx);
+ sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG, ch_idx);
seq_printf(s, " base: %08x; index: %04x_%04x; desc: %04x_%04x %08x\n",
- usb_dmas_readl(udc, ENETDMAS_RSTART_REG(ch_idx)),
+ usb_dmas_readl(udc, ENETDMAS_RSTART_REG, ch_idx),
sram2 >> 16, sram2 & 0xffff,
sram3 >> 16, sram3 & 0xffff,
- usb_dmas_readl(udc, ENETDMAS_SRAM4_REG(ch_idx)));
+ usb_dmas_readl(udc, ENETDMAS_SRAM4_REG, ch_idx));
seq_printf(s, " desc: %d/%d used", iudma->n_bds_used,
iudma->n_bds);
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 55f4df6..a660716 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -528,7 +528,7 @@
usb_ext->bLength = USB_DT_USB_EXT_CAP_SIZE;
usb_ext->bDescriptorType = USB_DT_DEVICE_CAPABILITY;
usb_ext->bDevCapabilityType = USB_CAP_TYPE_EXT;
- usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT);
+ usb_ext->bmAttributes = cpu_to_le32(USB_LPM_SUPPORT | USB_BESL_SUPPORT);
/*
* The Superspeed USB Capability descriptor shall be implemented by all
@@ -593,6 +593,7 @@
bitmap_zero(f->endpoints, 32);
}
cdev->config = NULL;
+ cdev->delayed_status = 0;
}
static int set_config(struct usb_composite_dev *cdev,
diff --git a/drivers/usb/gadget/dummy_hcd.c b/drivers/usb/gadget/dummy_hcd.c
index c588e8e..ac0e79e 100644
--- a/drivers/usb/gadget/dummy_hcd.c
+++ b/drivers/usb/gadget/dummy_hcd.c
@@ -923,8 +923,9 @@
struct dummy_hcd *dum_hcd = gadget_to_dummy_hcd(g);
struct dummy *dum = dum_hcd->dum;
- dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n",
- driver->driver.name);
+ if (driver)
+ dev_dbg(udc_dev(dum), "unregister gadget driver '%s'\n",
+ driver->driver.name);
dum->driver = NULL;
@@ -1000,8 +1001,8 @@
{
struct dummy *dum = platform_get_drvdata(pdev);
- usb_del_gadget_udc(&dum->gadget);
device_remove_file(&dum->gadget.dev, &dev_attr_function);
+ usb_del_gadget_udc(&dum->gadget);
return 0;
}
diff --git a/drivers/usb/gadget/f_acm.c b/drivers/usb/gadget/f_acm.c
index 4b7e33e..3384486 100644
--- a/drivers/usb/gadget/f_acm.c
+++ b/drivers/usb/gadget/f_acm.c
@@ -285,6 +285,7 @@
[ACM_CTRL_IDX].s = "CDC Abstract Control Model (ACM)",
[ACM_DATA_IDX].s = "CDC ACM Data",
[ACM_IAD_IDX ].s = "CDC Serial",
+ { } /* end of list */
};
static struct usb_gadget_strings acm_string_table = {
@@ -429,11 +430,12 @@
if (acm->notify->driver_data) {
VDBG(cdev, "reset acm control interface %d\n", intf);
usb_ep_disable(acm->notify);
- } else {
- VDBG(cdev, "init acm ctrl interface %d\n", intf);
+ }
+
+ if (!acm->notify->desc)
if (config_ep_by_speed(cdev->gadget, f, acm->notify))
return -EINVAL;
- }
+
usb_ep_enable(acm->notify);
acm->notify->driver_data = acm;
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index f394f29..84219f6 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1034,37 +1034,19 @@
struct ffs_file_perms perms;
umode_t root_mode;
const char *dev_name;
- union {
- /* set by ffs_fs_mount(), read by ffs_sb_fill() */
- void *private_data;
- /* set by ffs_sb_fill(), read by ffs_fs_mount */
- struct ffs_data *ffs_data;
- };
+ struct ffs_data *ffs_data;
};
static int ffs_sb_fill(struct super_block *sb, void *_data, int silent)
{
struct ffs_sb_fill_data *data = _data;
struct inode *inode;
- struct ffs_data *ffs;
+ struct ffs_data *ffs = data->ffs_data;
ENTER();
- /* Initialise data */
- ffs = ffs_data_new();
- if (unlikely(!ffs))
- goto Enomem;
-
ffs->sb = sb;
- ffs->dev_name = kstrdup(data->dev_name, GFP_KERNEL);
- if (unlikely(!ffs->dev_name))
- goto Enomem;
- ffs->file_perms = data->perms;
- ffs->private_data = data->private_data;
-
- /* used by the caller of this function */
- data->ffs_data = ffs;
-
+ data->ffs_data = NULL;
sb->s_fs_info = ffs;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
@@ -1080,17 +1062,14 @@
&data->perms);
sb->s_root = d_make_root(inode);
if (unlikely(!sb->s_root))
- goto Enomem;
+ return -ENOMEM;
/* EP0 file */
if (unlikely(!ffs_sb_create_file(sb, "ep0", ffs,
&ffs_ep0_operations, NULL)))
- goto Enomem;
+ return -ENOMEM;
return 0;
-
-Enomem:
- return -ENOMEM;
}
static int ffs_fs_parse_opts(struct ffs_sb_fill_data *data, char *opts)
@@ -1193,6 +1172,7 @@
struct dentry *rv;
int ret;
void *ffs_dev;
+ struct ffs_data *ffs;
ENTER();
@@ -1200,18 +1180,30 @@
if (unlikely(ret < 0))
return ERR_PTR(ret);
+ ffs = ffs_data_new();
+ if (unlikely(!ffs))
+ return ERR_PTR(-ENOMEM);
+ ffs->file_perms = data.perms;
+
+ ffs->dev_name = kstrdup(dev_name, GFP_KERNEL);
+ if (unlikely(!ffs->dev_name)) {
+ ffs_data_put(ffs);
+ return ERR_PTR(-ENOMEM);
+ }
+
ffs_dev = functionfs_acquire_dev_callback(dev_name);
- if (IS_ERR(ffs_dev))
- return ffs_dev;
+ if (IS_ERR(ffs_dev)) {
+ ffs_data_put(ffs);
+ return ERR_CAST(ffs_dev);
+ }
+ ffs->private_data = ffs_dev;
+ data.ffs_data = ffs;
- data.dev_name = dev_name;
- data.private_data = ffs_dev;
rv = mount_nodev(t, flags, &data, ffs_sb_fill);
-
- /* data.ffs_data is set by ffs_sb_fill */
- if (IS_ERR(rv))
+ if (IS_ERR(rv) && data.ffs_data) {
functionfs_release_dev_callback(data.ffs_data);
-
+ ffs_data_put(data.ffs_data);
+ }
return rv;
}
@@ -1397,11 +1389,13 @@
ffs->ep0req->context = ffs;
lang = ffs->stringtabs;
- for (lang = ffs->stringtabs; *lang; ++lang) {
- struct usb_string *str = (*lang)->strings;
- int id = first_id;
- for (; str->s; ++id, ++str)
- str->id = id;
+ if (lang) {
+ for (; *lang; ++lang) {
+ struct usb_string *str = (*lang)->strings;
+ int id = first_id;
+ for (; str->s; ++id, ++str)
+ str->id = id;
+ }
}
ffs->gadget = cdev->gadget;
diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c
index 97666e8..c35a9ec 100644
--- a/drivers/usb/gadget/f_mass_storage.c
+++ b/drivers/usb/gadget/f_mass_storage.c
@@ -413,6 +413,7 @@
/* Caller must hold fsg->lock */
static void wakeup_thread(struct fsg_common *common)
{
+ smp_wmb(); /* ensure the write of bh->state is complete */
/* Tell the main thread that something has happened */
common->thread_wakeup_needed = 1;
if (common->thread_task)
@@ -632,6 +633,7 @@
}
__set_current_state(TASK_RUNNING);
common->thread_wakeup_needed = 0;
+ smp_rmb(); /* ensure the latest bh->state is visible */
return rc;
}
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index 570c005..42a3090 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -1509,7 +1509,7 @@
}
break;
-#ifndef CONFIG_USB_GADGET_PXA25X
+#ifndef CONFIG_USB_PXA25X
/* PXA automagically handles this request too */
case USB_REQ_GET_CONFIGURATION:
if (ctrl->bRequestType != 0x80)
diff --git a/drivers/usb/gadget/tcm_usb_gadget.c b/drivers/usb/gadget/tcm_usb_gadget.c
index 7cacd6a..e4d8d79 100644
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -1614,7 +1614,7 @@
return ERR_PTR(-ENOMEM);
}
tport->tport_wwpn = wwpn;
- snprintf(tport->tport_name, sizeof(tport->tport_name), wnn_name);
+ snprintf(tport->tport_name, sizeof(tport->tport_name), "%s", wnn_name);
return &tport->tport_wwn;
}
diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c
index ffd8fa5..817a26c 100644
--- a/drivers/usb/gadget/udc-core.c
+++ b/drivers/usb/gadget/udc-core.c
@@ -105,7 +105,7 @@
enum usb_device_state state)
{
gadget->state = state;
- sysfs_notify(&gadget->dev.kobj, NULL, "status");
+ sysfs_notify(&gadget->dev.kobj, NULL, "state");
}
EXPORT_SYMBOL_GPL(usb_gadget_set_state);
@@ -439,6 +439,11 @@
{
struct usb_udc *udc = container_of(dev, struct usb_udc, dev);
+ if (!udc->driver) {
+ dev_err(dev, "soft-connect without a gadget driver\n");
+ return -EOPNOTSUPP;
+ }
+
if (sysfs_streq(buf, "connect")) {
usb_gadget_udc_start(udc->gadget, udc->driver);
usb_gadget_connect(udc->gadget);
diff --git a/drivers/usb/gadget/uvc_queue.c b/drivers/usb/gadget/uvc_queue.c
index 7ce27e3..de456a5 100644
--- a/drivers/usb/gadget/uvc_queue.c
+++ b/drivers/usb/gadget/uvc_queue.c
@@ -177,12 +177,16 @@
mutex_lock(&queue->mutex);
ret = vb2_qbuf(&queue->queue, buf);
+ if (ret < 0)
+ goto done;
+
spin_lock_irqsave(&queue->irqlock, flags);
ret = (queue->flags & UVC_QUEUE_PAUSED) != 0;
queue->flags &= ~UVC_QUEUE_PAUSED;
spin_unlock_irqrestore(&queue->irqlock, flags);
- mutex_unlock(&queue->mutex);
+done:
+ mutex_unlock(&queue->mutex);
return ret;
}
diff --git a/drivers/usb/gadget/zero.c b/drivers/usb/gadget/zero.c
index 0deb9d6..d31814c 100644
--- a/drivers/usb/gadget/zero.c
+++ b/drivers/usb/gadget/zero.c
@@ -280,7 +280,7 @@
ss_opts->isoc_interval = gzero_options.isoc_interval;
ss_opts->isoc_maxpacket = gzero_options.isoc_maxpacket;
ss_opts->isoc_mult = gzero_options.isoc_mult;
- ss_opts->isoc_maxburst = gzero_options.isoc_maxpacket;
+ ss_opts->isoc_maxburst = gzero_options.isoc_maxburst;
ss_opts->bulk_buflen = gzero_options.bulk_buflen;
func_ss = usb_get_function(func_inst_ss);
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 344d5e2..8bc8e06 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -17,7 +17,6 @@
config USB_XHCI_HCD
tristate "xHCI HCD (USB 3.0) support"
- depends on USB_ARCH_HAS_XHCI
---help---
The eXtensible Host Controller Interface (xHCI) is standard for USB 3.0
"SuperSpeed" host controller hardware.
@@ -43,7 +42,6 @@
config USB_EHCI_HCD
tristate "EHCI HCD (USB 2.0) support"
- depends on USB_ARCH_HAS_EHCI
---help---
The Enhanced Host Controller Interface (EHCI) is standard for USB 2.0
"high speed" (480 Mbit/sec, 60 Mbyte/sec) host controller hardware.
@@ -177,6 +175,13 @@
Enables support for the on-chip EHCI controller on
ST SPEAr chips.
+config USB_EHCI_HCD_SYNOPSYS
+ tristate "Support for Synopsys Host-AHB USB 2.0 controller"
+ depends on USB_EHCI_HCD
+ ---help---
+ Enable support for onchip USB controllers based on DesignWare USB 2.0
+ Host-AHB Controller IP from Synopsys.
+
config USB_EHCI_HCD_AT91
tristate "Support for Atmel on-chip EHCI USB controller"
depends on USB_EHCI_HCD && ARCH_AT91
@@ -347,7 +352,6 @@
config USB_OHCI_HCD
tristate "OHCI HCD support"
- depends on USB_ARCH_HAS_OHCI
select ISP1301_OMAP if MACH_OMAP_H2 || MACH_OMAP_H3
depends on USB_ISP1301 || !ARCH_LPC32XX
---help---
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index 4fb73c1..70df7c8 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -31,6 +31,7 @@
obj-$(CONFIG_USB_EHCI_HCD_ORION) += ehci-orion.o
obj-$(CONFIG_USB_EHCI_HCD_SPEAR) += ehci-spear.o
obj-$(CONFIG_USB_EHCI_S5P) += ehci-s5p.o
+obj-$(CONFIG_USB_EHCI_HCD_SYNOPSYS) += ehci-h20ahb.o
obj-$(CONFIG_USB_EHCI_HCD_AT91) += ehci-atmel.o
obj-$(CONFIG_USB_EHCI_MSM) += ehci-msm.o
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 3be3df2..bfcf383 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -130,7 +130,7 @@
}
/* Enable USB controller, 83xx or 8536 */
- if (pdata->have_sysif_regs)
+ if (pdata->have_sysif_regs && pdata->controller_ver < FSL_USB_VER_1_6)
setbits32(hcd->regs + FSL_SOC_USB_CTRL, 0x4);
/* Don't need to set host mode here. It will be done by tdi_reset() */
@@ -232,15 +232,9 @@
case FSL_USB2_PHY_ULPI:
if (pdata->have_sysif_regs && pdata->controller_ver) {
/* controller version 1.6 or above */
+ clrbits32(non_ehci + FSL_SOC_USB_CTRL, UTMI_PHY_EN);
setbits32(non_ehci + FSL_SOC_USB_CTRL,
- ULPI_PHY_CLK_SEL);
- /*
- * Due to controller issue of PHY_CLK_VALID in ULPI
- * mode, we set USB_CTRL_USB_EN before checking
- * PHY_CLK_VALID, otherwise PHY_CLK_VALID doesn't work.
- */
- clrsetbits_be32(non_ehci + FSL_SOC_USB_CTRL,
- UTMI_PHY_EN, USB_CTRL_USB_EN);
+ ULPI_PHY_CLK_SEL | USB_CTRL_USB_EN);
}
portsc |= PORT_PTS_ULPI;
break;
@@ -267,7 +261,8 @@
break;
}
- if (pdata->have_sysif_regs && pdata->controller_ver &&
+ if (pdata->have_sysif_regs &&
+ pdata->controller_ver > FSL_USB_VER_1_6 &&
(phy_mode == FSL_USB2_PHY_ULPI)) {
/* check PHY_CLK_VALID to get phy clk valid */
if (!spin_event_timeout(in_be32(non_ehci + FSL_SOC_USB_CTRL) &
diff --git a/drivers/usb/host/ehci-h20ahb.c b/drivers/usb/host/ehci-h20ahb.c
new file mode 100644
index 0000000..7724bab
--- /dev/null
+++ b/drivers/usb/host/ehci-h20ahb.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright (C) 2007-2013 Texas Instruments, Inc.
+ * Author: Vikram Pandita <vikram.pandita@ti.com>
+ * Author: Anand Gadiyar <gadiyar@ti.com>
+ * Author: Keshava Munegowda <keshava_mgowda@ti.com>
+ * Author: Roger Quadros <rogerq@ti.com>
+ *
+ * Copyright (C) 2009 Nokia Corporation
+ * Contact: Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * Based on ehci-omap.c - driver for USBHOST on OMAP3/4 processors
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/usb/ulpi.h>
+#include <linux/pm_runtime.h>
+#include <linux/gpio.h>
+#include <linux/clk.h>
+#include <linux/usb.h>
+#include <linux/usb/hcd.h>
+#include <linux/of.h>
+#include <linux/dma-mapping.h>
+
+#include "ehci.h"
+
+#define H20AHB_HS_USB_PORTS 1
+
+/* EHCI Synopsys-specific Register Set */
+#define EHCI_INSNREG04 (0xA0)
+#define EHCI_INSNREG04_DISABLE_UNSUSPEND (1 << 5)
+#define EHCI_INSNREG05_ULPI (0xA4)
+#define EHCI_INSNREG05_ULPI_CONTROL_SHIFT 31
+#define EHCI_INSNREG05_ULPI_PORTSEL_SHIFT 24
+#define EHCI_INSNREG05_ULPI_OPSEL_SHIFT 22
+#define EHCI_INSNREG05_ULPI_REGADD_SHIFT 16
+#define EHCI_INSNREG05_ULPI_EXTREGADD_SHIFT 8
+#define EHCI_INSNREG05_ULPI_WRDATA_SHIFT 0
+
+#define DRIVER_DESC "H20AHB-EHCI Host Controller driver"
+
+static const char hcd_name[] = "ehci-h20ahb";
+
+/*-------------------------------------------------------------------------*/
+
+struct h20ahb_hcd {
+ struct usb_phy *phy[H20AHB_HS_USB_PORTS]; /* one PHY for each port */
+ int nports;
+};
+
+static inline void ehci_write(void __iomem *base, u32 reg, u32 val)
+{
+ writel_relaxed(val, base + reg);
+}
+
+static inline u32 ehci_read(void __iomem *base, u32 reg)
+{
+ return readl_relaxed(base + reg);
+}
+
+/* configure so an HC device and id are always provided */
+/* always called with process context; sleeping is OK */
+
+static struct hc_driver __read_mostly ehci_h20ahb_hc_driver;
+
+static const struct ehci_driver_overrides ehci_h20ahb_overrides __initdata = {
+ .extra_priv_size = sizeof(struct h20ahb_hcd),
+};
+
+static int ehci_h20ahb_phy_read(struct usb_phy *x, u32 reg)
+{
+ u32 val = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+ (1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+ (3 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+ (reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT);
+ ehci_write(x->io_priv, 0, val);
+ while ((val = ehci_read(x->io_priv, 0)) &
+ (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+ return val & 0xff;
+}
+
+static int ehci_h20ahb_phy_write(struct usb_phy *x, u32 val, u32 reg)
+{
+ u32 v = (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT) |
+ (1 << EHCI_INSNREG05_ULPI_PORTSEL_SHIFT) |
+ (2 << EHCI_INSNREG05_ULPI_OPSEL_SHIFT) |
+ (reg << EHCI_INSNREG05_ULPI_REGADD_SHIFT) |
+ (val & 0xff);
+ ehci_write(x->io_priv, 0, v);
+ while ((v = ehci_read(x->io_priv, 0)) &
+ (1 << EHCI_INSNREG05_ULPI_CONTROL_SHIFT));
+ return 0;
+}
+
+static struct usb_phy_io_ops ehci_h20ahb_phy_io_ops = {
+ .read = ehci_h20ahb_phy_read,
+ .write = ehci_h20ahb_phy_write,
+};
+
+
+/**
+ * ehci_hcd_h20ahb_probe - initialize Synopsis-based HCDs
+ *
+ * Allocates basic resources for this USB host controller, and
+ * then invokes the start() method for the HCD associated with it
+ * through the hotplug entry's driver_data.
+ */
+static int ehci_hcd_h20ahb_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+ struct usb_hcd *hcd;
+ void __iomem *regs;
+ int ret;
+ int irq;
+ int i;
+ struct h20ahb_hcd *h20ahb;
+
+ if (usb_disabled())
+ return -ENODEV;
+
+ /* if (!dev->parent) {
+ dev_err(dev, "Missing parent device\n");
+ return -ENODEV;
+ }*/
+
+ /* For DT boot, get platform data from parent. i.e. usbhshost */
+ /*if (dev->of_node) {
+ pdata = dev_get_platdata(dev->parent);
+ dev->platform_data = pdata;
+ }
+
+ if (!pdata) {
+ dev_err(dev, "Missing platform data\n");
+ return -ENODEV;
+ }*/
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(dev, "EHCI irq failed\n");
+ return -ENODEV;
+ }
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(regs))
+ return PTR_ERR(regs);
+
+ /*
+ * Right now device-tree probed devices don't get dma_mask set.
+ * Since shared usb code relies on it, set it here for now.
+ * Once we have dma capability bindings this can go away.
+ */
+ ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+ if (ret)
+ return ret;
+
+ ret = -ENODEV;
+ hcd = usb_create_hcd(&ehci_h20ahb_hc_driver, dev,
+ dev_name(dev));
+ if (!hcd) {
+ dev_err(dev, "Failed to create HCD\n");
+ return -ENOMEM;
+ }
+
+ hcd->rsrc_start = res->start;
+ hcd->rsrc_len = resource_size(res);
+ hcd->regs = regs;
+ hcd_to_ehci(hcd)->caps = regs;
+
+ h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+ h20ahb->nports = 1;
+
+ platform_set_drvdata(pdev, hcd);
+
+ /* get the PHY devices if needed */
+ for (i = 0 ; i < h20ahb->nports ; i++) {
+ struct usb_phy *phy;
+
+ /* get the PHY device */
+#if 0
+ if (dev->of_node)
+ phy = devm_usb_get_phy_by_phandle(dev, "phys", i);
+ else
+ phy = devm_usb_get_phy_dev(dev, i);
+#endif
+ phy = otg_ulpi_create(&ehci_h20ahb_phy_io_ops, 0);
+ if (IS_ERR(phy)) {
+ ret = PTR_ERR(phy);
+ dev_err(dev, "Can't get PHY device for port %d: %d\n",
+ i, ret);
+ goto err_phy;
+ }
+ phy->dev = dev;
+ usb_add_phy_dev(phy);
+
+ h20ahb->phy[i] = phy;
+ phy->io_priv = hcd->regs + EHCI_INSNREG05_ULPI;
+
+#if 0
+ usb_phy_init(h20ahb->phy[i]);
+ /* bring PHY out of suspend */
+ usb_phy_set_suspend(h20ahb->phy[i], 0);
+#endif
+ }
+
+ /* make the first port's phy the one used by hcd as well */
+ hcd->phy = h20ahb->phy[0];
+
+ pm_runtime_enable(dev);
+ pm_runtime_get_sync(dev);
+
+ /*
+ * An undocumented "feature" in the H20AHB EHCI controller,
+ * causes suspended ports to be taken out of suspend when
+ * the USBCMD.Run/Stop bit is cleared (for example when
+ * we do ehci_bus_suspend).
+ * This breaks suspend-resume if the root-hub is allowed
+ * to suspend. Writing 1 to this undocumented register bit
+ * disables this feature and restores normal behavior.
+ */
+ ehci_write(regs, EHCI_INSNREG04,
+ EHCI_INSNREG04_DISABLE_UNSUSPEND);
+
+ ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
+ if (ret) {
+ dev_err(dev, "failed to add hcd with err %d\n", ret);
+ goto err_pm_runtime;
+ }
+ device_wakeup_enable(hcd->self.controller);
+
+ /*
+ * Bring PHYs out of reset for non PHY modes.
+ * Even though HSIC mode is a PHY-less mode, the reset
+ * line exists between the chips and can be modelled
+ * as a PHY device for reset control.
+ */
+ for (i = 0; i < h20ahb->nports; i++) {
+ usb_phy_init(h20ahb->phy[i]);
+ /* bring PHY out of suspend */
+ usb_phy_set_suspend(h20ahb->phy[i], 0);
+ }
+
+ return 0;
+
+err_pm_runtime:
+ pm_runtime_put_sync(dev);
+
+err_phy:
+ for (i = 0; i < h20ahb->nports; i++) {
+ if (h20ahb->phy[i])
+ usb_phy_shutdown(h20ahb->phy[i]);
+ }
+
+ usb_put_hcd(hcd);
+
+ return ret;
+}
+
+
+/**
+ * ehci_hcd_h20ahb_remove - shutdown processing for EHCI HCDs
+ * @pdev: USB Host Controller being removed
+ *
+ * Reverses the effect of usb_ehci_hcd_h20ahb_probe(), first invoking
+ * the HCD's stop() method. It is always called from a thread
+ * context, normally "rmmod", "apmd", or something similar.
+ */
+static int ehci_hcd_h20ahb_remove(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct usb_hcd *hcd = dev_get_drvdata(dev);
+ struct h20ahb_hcd *h20ahb = (struct h20ahb_hcd *)hcd_to_ehci(hcd)->priv;
+ int i;
+
+ usb_remove_hcd(hcd);
+
+ for (i = 0; i < h20ahb->nports; i++) {
+ if (h20ahb->phy[i])
+ usb_phy_shutdown(h20ahb->phy[i]);
+ }
+
+ usb_put_hcd(hcd);
+ pm_runtime_put_sync(dev);
+ pm_runtime_disable(dev);
+
+ return 0;
+}
+
+static const struct of_device_id h20ahb_ehci_dt_ids[] = {
+ { .compatible = "snps,ehci-h20ahb" },
+ { }
+};
+
+MODULE_DEVICE_TABLE(of, h20ahb_ehci_dt_ids);
+
+static struct platform_driver ehci_hcd_h20ahb_driver = {
+ .probe = ehci_hcd_h20ahb_probe,
+ .remove = ehci_hcd_h20ahb_remove,
+ .shutdown = usb_hcd_platform_shutdown,
+ /*.suspend = ehci_hcd_h20ahb_suspend, */
+ /*.resume = ehci_hcd_h20ahb_resume, */
+ .driver = {
+ .name = hcd_name,
+ .of_match_table = h20ahb_ehci_dt_ids,
+ }
+};
+
+/*-------------------------------------------------------------------------*/
+
+static int __init ehci_h20ahb_init(void)
+{
+ if (usb_disabled())
+ return -ENODEV;
+
+ pr_info("%s: " DRIVER_DESC "\n", hcd_name);
+
+ ehci_init_driver(&ehci_h20ahb_hc_driver, &ehci_h20ahb_overrides);
+ return platform_driver_register(&ehci_hcd_h20ahb_driver);
+}
+module_init(ehci_h20ahb_init);
+
+static void __exit ehci_h20ahb_cleanup(void)
+{
+ platform_driver_unregister(&ehci_hcd_h20ahb_driver);
+}
+module_exit(ehci_h20ahb_cleanup);
+
+MODULE_ALIAS("platform:ehci-h20ahb");
+MODULE_AUTHOR("Liviu Dudau <Liviu.Dudau@arm.com>");
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 246e124..f1c3ad6 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -591,11 +591,16 @@
*/
hcc_params = ehci_readl(ehci, &ehci->caps->hcc_params);
if (HCC_64BIT_ADDR(hcc_params)) {
- ehci_writel(ehci, 0, &ehci->regs->segment);
-#if 0
-// this is deeply broken on almost all architectures
+#ifdef CONFIG_ARM64
+ ehci_writel(ehci, ehci->periodic_dma >> 32, &ehci->regs->segment);
+ /*
+ * this is deeply broken on almost all architectures
+ * but arm64 can use it so enable it
+ */
if (!dma_set_mask(hcd->self.controller, DMA_BIT_MASK(64)))
ehci_info(ehci, "enabled 64bit DMA\n");
+#else
+ ehci_writel(ehci, 0, &ehci->regs->segment);
#endif
}
@@ -686,8 +691,15 @@
struct ehci_hcd *ehci = hcd_to_ehci (hcd);
u32 status, masked_status, pcd_status = 0, cmd;
int bh;
+ unsigned long flags;
- spin_lock (&ehci->lock);
+ /*
+ * For threadirqs option we use spin_lock_irqsave() variant to prevent
+ * deadlock with ehci hrtimer callback, because hrtimer callbacks run
+ * in interrupt context even when threadirqs is specified. We can go
+ * back to spin_lock() variant when hrtimer callbacks become threaded.
+ */
+ spin_lock_irqsave(&ehci->lock, flags);
status = ehci_readl(ehci, &ehci->regs->status);
@@ -705,7 +717,7 @@
/* Shared IRQ? */
if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
- spin_unlock(&ehci->lock);
+ spin_unlock_irqrestore(&ehci->lock, flags);
return IRQ_NONE;
}
@@ -823,7 +835,7 @@
if (bh)
ehci_work (ehci);
- spin_unlock (&ehci->lock);
+ spin_unlock_irqrestore(&ehci->lock, flags);
if (pcd_status)
usb_hcd_poll_rh_status(hcd);
return IRQ_HANDLED;
@@ -965,8 +977,6 @@
}
qh->exception = 1;
- if (ehci->rh_state < EHCI_RH_RUNNING)
- qh->qh_state = QH_STATE_IDLE;
switch (qh->qh_state) {
case QH_STATE_LINKED:
case QH_STATE_COMPLETING:
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 9ab4a4d..ca6289b 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -858,6 +858,7 @@
ehci->reset_done[wIndex] = jiffies
+ msecs_to_jiffies(20);
usb_hcd_start_port_resume(&hcd->self, wIndex);
+ set_bit(wIndex, &ehci->resuming_ports);
/* check the port again */
mod_timer(&ehci_to_hcd(ehci)->rh_timer,
ehci->reset_done[wIndex]);
diff --git a/drivers/usb/host/ehci-mxc.c b/drivers/usb/host/ehci-mxc.c
index c369767..ec128bc 100644
--- a/drivers/usb/host/ehci-mxc.c
+++ b/drivers/usb/host/ehci-mxc.c
@@ -184,7 +184,7 @@
if (pdata && pdata->exit)
pdata->exit(pdev);
- if (pdata->otg)
+ if (pdata && pdata->otg)
usb_phy_shutdown(pdata->otg);
clk_disable_unprepare(priv->usbclk);
diff --git a/drivers/usb/host/ehci-omap.c b/drivers/usb/host/ehci-omap.c
index 16d7150..dda408f 100644
--- a/drivers/usb/host/ehci-omap.c
+++ b/drivers/usb/host/ehci-omap.c
@@ -187,6 +187,12 @@
}
omap->phy[i] = phy;
+
+ if (pdata->port_mode[i] == OMAP_EHCI_PORT_MODE_PHY) {
+ usb_phy_init(omap->phy[i]);
+ /* bring PHY out of suspend */
+ usb_phy_set_suspend(omap->phy[i], 0);
+ }
}
pm_runtime_enable(dev);
@@ -211,13 +217,14 @@
}
/*
- * Bring PHYs out of reset.
+ * Bring PHYs out of reset for non PHY modes.
* Even though HSIC mode is a PHY-less mode, the reset
* line exists between the chips and can be modelled
* as a PHY device for reset control.
*/
for (i = 0; i < omap->nports; i++) {
- if (!omap->phy[i])
+ if (!omap->phy[i] ||
+ pdata->port_mode[i] == OMAP_EHCI_PORT_MODE_PHY)
continue;
usb_phy_init(omap->phy[i]);
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 595d210..fe13156 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -35,6 +35,21 @@
#define PCI_DEVICE_ID_INTEL_CE4100_USB 0x2e70
/*-------------------------------------------------------------------------*/
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC 0x0939
+static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
+{
+ return pdev->vendor == PCI_VENDOR_ID_INTEL &&
+ pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC;
+}
+
+/*
+ * 0x84 is the offset of in/out threshold register,
+ * and it is the same offset as the register of 'hostpc'.
+ */
+#define intel_quark_x1000_insnreg01 hostpc
+
+/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */
+#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD 0x007f007f
/* called after powerup, by probe or system-pm "wakeup" */
static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
@@ -50,6 +65,16 @@
if (!retval)
ehci_dbg(ehci, "MWI active\n");
+ /* Reset the threshold limit */
+ if (is_intel_quark_x1000(pdev)) {
+ /*
+ * For the Intel QUARK X1000, raise the I/O threshold to the
+ * maximum usable value in order to improve performance.
+ */
+ ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD,
+ ehci->regs->intel_quark_x1000_insnreg01);
+ }
+
return 0;
}
@@ -403,7 +428,7 @@
.remove = usb_hcd_pci_remove,
.shutdown = usb_hcd_pci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
.driver = {
.pm = &usb_hcd_pci_pm_ops
},
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index f80d033..8e3c878 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -1391,21 +1391,20 @@
/* Behind the scheduling threshold? */
if (unlikely(start < next)) {
+ unsigned now2 = (now - base) & (mod - 1);
/* USB_ISO_ASAP: Round up to the first available slot */
if (urb->transfer_flags & URB_ISO_ASAP)
start += (next - start + period - 1) & -period;
/*
- * Not ASAP: Use the next slot in the stream. If
- * the entire URB falls before the threshold, fail.
+ * Not ASAP: Use the next slot in the stream,
+ * no matter what.
*/
- else if (start + span - period < next) {
- ehci_dbg(ehci, "iso urb late %p (%u+%u < %u)\n",
+ else if (start + span - period < now2) {
+ ehci_dbg(ehci, "iso underrun %p (%u+%u < %u)\n",
urb, start + base,
- span - period, next + base);
- status = -EXDEV;
- goto fail;
+ span - period, now2 + base);
}
}
diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h
index 7c978b2..03322d9 100644
--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -200,6 +200,7 @@
unsigned has_synopsys_hc_bug:1; /* Synopsys HC */
unsigned frame_index_bug:1; /* MosChip (AKA NetMos) */
unsigned need_oc_pp_cycle:1; /* MPC834X port power */
+ unsigned imx28_write_fix:1; /* For Freescale i.MX28 */
/* required for usb32 quirk */
#define OHCI_CTRL_HCFS (3 << 6)
@@ -675,6 +676,18 @@
#endif
}
+#ifdef CONFIG_SOC_IMX28
+static inline void imx28_ehci_writel(const unsigned int val,
+ volatile __u32 __iomem *addr)
+{
+ __asm__ ("swp %0, %0, [%1]" : : "r"(val), "r"(addr));
+}
+#else
+static inline void imx28_ehci_writel(const unsigned int val,
+ volatile __u32 __iomem *addr)
+{
+}
+#endif
static inline void ehci_writel(const struct ehci_hcd *ehci,
const unsigned int val, __u32 __iomem *regs)
{
@@ -683,7 +696,10 @@
writel_be(val, regs) :
writel(val, regs);
#else
- writel(val, regs);
+ if (ehci->imx28_write_fix)
+ imx28_ehci_writel(val, regs);
+ else
+ writel(val, regs);
#endif
}
diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index b64e661..baf2807 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -1488,7 +1488,7 @@
spin_unlock_irq(&isp116x->lock);
hcd->state = HC_STATE_RESUMING;
- msleep(20);
+ msleep(USB_RESUME_TIMEOUT);
/* Go operational */
spin_lock_irq(&isp116x->lock);
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index fc627fd..8c57e97 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -231,31 +231,26 @@
frame &= ~(ed->interval - 1);
frame |= ed->branch;
urb->start_frame = frame;
+ ed->last_iso = frame + ed->interval * (size - 1);
}
} else if (ed->type == PIPE_ISOCHRONOUS) {
u16 next = ohci_frame_no(ohci) + 1;
u16 frame = ed->last_iso + ed->interval;
+ u16 length = ed->interval * (size - 1);
/* Behind the scheduling threshold? */
if (unlikely(tick_before(frame, next))) {
- /* USB_ISO_ASAP: Round up to the first available slot */
+ /* URB_ISO_ASAP: Round up to the first available slot */
if (urb->transfer_flags & URB_ISO_ASAP) {
frame += (next - frame + ed->interval - 1) &
-ed->interval;
/*
- * Not ASAP: Use the next slot in the stream. If
- * the entire URB falls before the threshold, fail.
+ * Not ASAP: Use the next slot in the stream,
+ * no matter what.
*/
} else {
- if (tick_before(frame + ed->interval *
- (urb->number_of_packets - 1), next)) {
- retval = -EXDEV;
- usb_hcd_unlink_urb_from_ep(hcd, urb);
- goto fail;
- }
-
/*
* Some OHCI hardware doesn't handle late TDs
* correctly. After retiring them it proceeds
@@ -266,9 +261,16 @@
urb_priv->td_cnt = DIV_ROUND_UP(
(u16) (next - frame),
ed->interval);
+ if (urb_priv->td_cnt >= urb_priv->length) {
+ ++urb_priv->td_cnt; /* Mark it */
+ ohci_dbg(ohci, "iso underrun %p (%u+%u < %u)\n",
+ urb, frame, length,
+ next);
+ }
}
}
urb->start_frame = frame;
+ ed->last_iso = frame + length;
}
/* fill the TDs and link them to the ed; and
@@ -1194,25 +1196,6 @@
#define PLATFORM_DRIVER ohci_platform_driver
#endif
-#if !defined(PCI_DRIVER) && \
- !defined(PLATFORM_DRIVER) && \
- !defined(OMAP1_PLATFORM_DRIVER) && \
- !defined(OMAP3_PLATFORM_DRIVER) && \
- !defined(OF_PLATFORM_DRIVER) && \
- !defined(SA1111_DRIVER) && \
- !defined(PS3_SYSTEM_BUS_DRIVER) && \
- !defined(SM501_OHCI_DRIVER) && \
- !defined(TMIO_OHCI_DRIVER) && \
- !defined(S3C2410_PLATFORM_DRIVER) && \
- !defined(EXYNOS_PLATFORM_DRIVER) && \
- !defined(EP93XX_PLATFORM_DRIVER) && \
- !defined(AT91_PLATFORM_DRIVER) && \
- !defined(NXP_PLATFORM_DRIVER) && \
- !defined(DAVINCI_PLATFORM_DRIVER) && \
- !defined(SPEAR_PLATFORM_DRIVER)
-#error "missing bus glue for ohci-hcd"
-#endif
-
static int __init ohci_hcd_mod_init(void)
{
int retval = 0;
diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c
index 60ff422..cd90806 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -90,6 +90,24 @@
dl_done_list (ohci);
finish_unlinks (ohci, ohci_frame_no(ohci));
+ /*
+ * Some controllers don't handle "global" suspend properly if
+ * there are unsuspended ports. For these controllers, put all
+ * the enabled ports into suspend before suspending the root hub.
+ */
+ if (ohci->flags & OHCI_QUIRK_GLOBAL_SUSPEND) {
+ __hc32 __iomem *portstat = ohci->regs->roothub.portstatus;
+ int i;
+ unsigned temp;
+
+ for (i = 0; i < ohci->num_ports; (++i, ++portstat)) {
+ temp = ohci_readl(ohci, portstat);
+ if ((temp & (RH_PS_PES | RH_PS_PSS)) ==
+ RH_PS_PES)
+ ohci_writel(ohci, RH_PS_PSS, portstat);
+ }
+ }
+
/* maybe resume can wake root hub */
if (ohci_to_hcd(ohci)->self.root_hub->do_remote_wakeup || autostop) {
ohci->hc_control |= OHCI_CTRL_RWE;
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index 951514e..67af8ee 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -172,6 +172,7 @@
pci_dev_put(amd_smbus_dev);
amd_smbus_dev = NULL;
+ ohci->flags |= OHCI_QUIRK_GLOBAL_SUSPEND;
return 0;
}
@@ -371,7 +372,7 @@
.remove = usb_hcd_pci_remove,
.shutdown = usb_hcd_pci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
.driver = {
.pm = &usb_hcd_pci_pm_ops
},
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index 88731b7..1e1563d 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -41,8 +41,12 @@
__releases(ohci->lock)
__acquires(ohci->lock)
{
+ struct usb_host_endpoint *ep = urb->ep;
+ struct urb_priv *urb_priv;
+
// ASSERT (urb->hcpriv != 0);
+ restart:
urb_free_priv (ohci, urb->hcpriv);
urb->hcpriv = NULL;
if (likely(status == -EINPROGRESS))
@@ -79,6 +83,21 @@
ohci->hc_control &= ~(OHCI_CTRL_PLE|OHCI_CTRL_IE);
ohci_writel (ohci, ohci->hc_control, &ohci->regs->control);
}
+
+ /*
+ * An isochronous URB that is sumitted too late won't have any TDs
+ * (marked by the fact that the td_cnt value is larger than the
+ * actual number of TDs). If the next URB on this endpoint is like
+ * that, give it back now.
+ */
+ if (!list_empty(&ep->urb_list)) {
+ urb = list_first_entry(&ep->urb_list, struct urb, urb_list);
+ urb_priv = urb->hcpriv;
+ if (urb_priv->td_cnt > urb_priv->length) {
+ status = 0;
+ goto restart;
+ }
+ }
}
@@ -295,8 +314,7 @@
* - ED_OPER: when there's any request queued, the ED gets rescheduled
* immediately. HC should be working on them.
*
- * - ED_IDLE: when there's no TD queue. there's no reason for the HC
- * to care about this ED; safe to disable the endpoint.
+ * - ED_IDLE: when there's no TD queue or the HC isn't running.
*
* When finish_unlinks() runs later, after SOF interrupt, it will often
* complete one or more URB unlinks before making that state change.
@@ -545,7 +563,6 @@
td->hwCBP = cpu_to_hc32 (ohci, data & 0xFFFFF000);
*ohci_hwPSWp(ohci, td, 0) = cpu_to_hc16 (ohci,
(data & 0x0FFF) | 0xE000);
- td->ed->last_iso = info & 0xffff;
} else {
td->hwCBP = cpu_to_hc32 (ohci, data);
}
@@ -910,6 +927,10 @@
int completed, modified;
__hc32 *prev;
+ /* Is this ED already invisible to the hardware? */
+ if (ed->state == ED_IDLE)
+ goto ed_idle;
+
/* only take off EDs that the HC isn't using, accounting for
* frame counter wraps and EDs with partially retired TDs
*/
@@ -939,12 +960,20 @@
}
}
+ /* ED's now officially unlinked, hc doesn't see */
+ ed->state = ED_IDLE;
+ if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
+ ohci->eds_scheduled--;
+ ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
+ ed->hwNextED = 0;
+ wmb();
+ ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
+ed_idle:
+
/* reentrancy: if we drop the schedule lock, someone might
* have modified this list. normally it's just prepending
* entries (which we'd ignore), but paranoia won't hurt.
*/
- *last = ed->ed_next;
- ed->ed_next = NULL;
modified = 0;
/* unlink urbs as requested, but rescan the list after
@@ -994,7 +1023,7 @@
urb_priv->td_cnt++;
/* if URB is done, clean up */
- if (urb_priv->td_cnt == urb_priv->length) {
+ if (urb_priv->td_cnt >= urb_priv->length) {
modified = completed = 1;
finish_urb(ohci, urb, 0);
}
@@ -1002,19 +1031,20 @@
if (completed && !list_empty (&ed->td_list))
goto rescan_this;
- /* ED's now officially unlinked, hc doesn't see */
- ed->state = ED_IDLE;
- if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
- ohci->eds_scheduled--;
- ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
- ed->hwNextED = 0;
- wmb ();
- ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE);
-
- /* but if there's work queued, reschedule */
- if (!list_empty (&ed->td_list)) {
- if (ohci->rh_state == OHCI_RH_RUNNING)
- ed_schedule (ohci, ed);
+ /*
+ * If no TDs are queued, take ED off the ed_rm_list.
+ * Otherwise, if the HC is running, reschedule.
+ * If not, leave it on the list for further dequeues.
+ */
+ if (list_empty(&ed->td_list)) {
+ *last = ed->ed_next;
+ ed->ed_next = NULL;
+ } else if (ohci->rh_state == OHCI_RH_RUNNING) {
+ *last = ed->ed_next;
+ ed->ed_next = NULL;
+ ed_schedule(ohci, ed);
+ } else {
+ last = &ed->ed_next;
}
if (modified)
@@ -1084,7 +1114,7 @@
urb_priv->td_cnt++;
/* If all this urb's TDs are done, call complete() */
- if (urb_priv->td_cnt == urb_priv->length)
+ if (urb_priv->td_cnt >= urb_priv->length)
finish_urb(ohci, urb, status);
/* clean schedule: unlink EDs that are no longer busy */
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index d329914..f2521f3 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -405,6 +405,8 @@
#define OHCI_QUIRK_HUB_POWER 0x100 /* distrust firmware power/oc setup */
#define OHCI_QUIRK_AMD_PLL 0x200 /* AMD PLL quirk*/
#define OHCI_QUIRK_AMD_PREFETCH 0x400 /* pre-fetch for ISO transfer */
+#define OHCI_QUIRK_GLOBAL_SUSPEND 0x800 /* must suspend ports */
+
// there are also chip quirks/bugs in init logic
struct work_struct nec_work; /* Worker for NEC quirk */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 4c338ec..66c9058 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -470,7 +470,8 @@
{
void __iomem *base;
u32 control;
- u32 fminterval;
+ u32 fminterval = 0;
+ bool no_fminterval = false;
int cnt;
if (!mmio_resource_enabled(pdev, 0))
@@ -480,6 +481,13 @@
if (base == NULL)
return;
+ /*
+ * ULi M5237 OHCI controller locks the whole system when accessing
+ * the OHCI_FMINTERVAL offset.
+ */
+ if (pdev->vendor == PCI_VENDOR_ID_AL && pdev->device == 0x5237)
+ no_fminterval = true;
+
control = readl(base + OHCI_CONTROL);
/* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */
@@ -518,7 +526,9 @@
}
/* software reset of the controller, preserving HcFmInterval */
- fminterval = readl(base + OHCI_FMINTERVAL);
+ if (!no_fminterval)
+ fminterval = readl(base + OHCI_FMINTERVAL);
+
writel(OHCI_HCR, base + OHCI_CMDSTATUS);
/* reset requires max 10 us delay */
@@ -527,7 +537,9 @@
break;
udelay(1);
}
- writel(fminterval, base + OHCI_FMINTERVAL);
+
+ if (!no_fminterval)
+ writel(fminterval, base + OHCI_FMINTERVAL);
/* Now the controller is safely in SUSPEND and nothing can wake it up */
iounmap(base);
@@ -555,6 +567,14 @@
DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
},
},
+ {
+ /* HASEE E200 */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+ DMI_MATCH(DMI_BOARD_NAME, "E210"),
+ DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+ },
+ },
{ }
};
@@ -564,9 +584,14 @@
{
int try_handoff = 1, tried_handoff = 0;
- /* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
- * the handoff on its unused controller. Skip it. */
- if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+ /*
+ * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+ * the handoff on its unused controller. Skip it.
+ *
+ * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+ */
+ if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+ pdev->device == 0x27cc)) {
if (dmi_check_system(ehci_dmi_nohandoff_table))
try_handoff = 0;
}
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index a6fd8f53..6656dfd 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -2301,7 +2301,7 @@
rh->port &= ~USB_PORT_STAT_SUSPEND;
rh->port |= USB_PORT_STAT_C_SUSPEND << 16;
r8a66597_mdfy(r8a66597, RESUME, RESUME | UACT, dvstctr_reg);
- msleep(50);
+ msleep(USB_RESUME_TIMEOUT);
r8a66597_mdfy(r8a66597, UACT, RESUME | UACT, dvstctr_reg);
}
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index b2ec7fe..b4cad93 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -1251,7 +1251,7 @@
sl811_write(sl811, SL11H_CTLREG1, sl811->ctrl1);
mod_timer(&sl811->timer, jiffies
- + msecs_to_jiffies(20));
+ + msecs_to_jiffies(USB_RESUME_TIMEOUT));
break;
case USB_PORT_FEAT_POWER:
port_power(sl811, 0);
diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c
index c300bd2f7..0f228c4 100644
--- a/drivers/usb/host/uhci-pci.c
+++ b/drivers/usb/host/uhci-pci.c
@@ -293,7 +293,7 @@
.remove = usb_hcd_pci_remove,
.shutdown = uhci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
.driver = {
.pm = &usb_hcd_pci_pm_ops
},
diff --git a/drivers/usb/host/uhci-q.c b/drivers/usb/host/uhci-q.c
index 041c6dd..da6f56d 100644
--- a/drivers/usb/host/uhci-q.c
+++ b/drivers/usb/host/uhci-q.c
@@ -1303,7 +1303,7 @@
}
/* Fell behind? */
- if (uhci_frame_before_eq(frame, next)) {
+ if (!uhci_frame_before_eq(next, frame)) {
/* USB_ISO_ASAP: Round up to the first available slot */
if (urb->transfer_flags & URB_ISO_ASAP)
@@ -1311,13 +1311,17 @@
-qh->period;
/*
- * Not ASAP: Use the next slot in the stream. If
- * the entire URB falls before the threshold, fail.
+ * Not ASAP: Use the next slot in the stream,
+ * no matter what.
*/
else if (!uhci_frame_before_eq(next,
frame + (urb->number_of_packets - 1) *
qh->period))
- return -EXDEV;
+ dev_dbg(uhci_dev(uhci), "iso underrun %p (%u+%u < %u)\n",
+ urb, frame,
+ (urb->number_of_packets - 1) *
+ qh->period,
+ next);
}
}
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 187a3ec..d939376 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -286,7 +286,7 @@
if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue)
xhci_queue_stop_endpoint(xhci, slot_id, i, suspend);
}
- cmd->command_trb = xhci->cmd_ring->enqueue;
+ cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
list_add_tail(&cmd->cmd_list, &virt_dev->cmd_list);
xhci_queue_stop_endpoint(xhci, slot_id, 0, suspend);
xhci_ring_cmd_db(xhci);
@@ -462,7 +462,8 @@
}
/* Updates Link Status for super Speed port */
-static void xhci_hub_report_link_state(u32 *status, u32 status_reg)
+static void xhci_hub_report_link_state(struct xhci_hcd *xhci,
+ u32 *status, u32 status_reg)
{
u32 pls = status_reg & PORT_PLS_MASK;
@@ -501,7 +502,8 @@
* in which sometimes the port enters compliance mode
* caused by a delay on the host-device negotiation.
*/
- if (pls == USB_SS_PORT_LS_COMP_MOD)
+ if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) &&
+ (pls == USB_SS_PORT_LS_COMP_MOD))
pls |= USB_PORT_STAT_CONNECTION;
}
@@ -686,7 +688,7 @@
}
/* Update Port Link State for super speed ports*/
if (hcd->speed == HCD_USB3) {
- xhci_hub_report_link_state(&status, temp);
+ xhci_hub_report_link_state(xhci, &status, temp);
/*
* Verify if all USB3 Ports Have entered U0 already.
* Delete Compliance Mode Timer if so.
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index fbf75e5..677f032 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -369,6 +369,10 @@
ctx->size += CTX_SIZE(xhci->hcc_params);
ctx->bytes = dma_pool_alloc(xhci->device_pool, flags, &ctx->dma);
+ if (!ctx->bytes) {
+ kfree(ctx);
+ return NULL;
+ }
memset(ctx->bytes, 0, ctx->size);
return ctx;
}
@@ -1790,6 +1794,16 @@
kfree(cur_cd);
}
+ num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
+ for (i = 0; i < num_ports && xhci->rh_bw; i++) {
+ struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
+ for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
+ struct list_head *ep = &bwt->interval_bw[j].endpoints;
+ while (!list_empty(ep))
+ list_del_init(ep->next);
+ }
+ }
+
for (i = 1; i < MAX_HC_SLOTS; ++i)
xhci_free_virt_device(xhci, i);
@@ -1830,16 +1844,6 @@
if (!xhci->rh_bw)
goto no_bw;
- num_ports = HCS_MAX_PORTS(xhci->hcs_params1);
- for (i = 0; i < num_ports; i++) {
- struct xhci_interval_bw_table *bwt = &xhci->rh_bw[i].bw_table;
- for (j = 0; j < XHCI_MAX_INTERVAL; j++) {
- struct list_head *ep = &bwt->interval_bw[j].endpoints;
- while (!list_empty(ep))
- list_del_init(ep->next);
- }
- }
-
for (i = 0; i < num_ports; i++) {
struct xhci_tt_bw_info *tt, *n;
list_for_each_entry_safe(tt, n, &xhci->rh_bw[i].tts, tt_list) {
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index cc24e39..2320e20 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -87,13 +87,17 @@
/* AMD PLL quirk */
if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
xhci->quirks |= XHCI_AMD_PLL_FIX;
+
+ if (pdev->vendor == PCI_VENDOR_ID_AMD)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
xhci->quirks |= XHCI_LPM_SUPPORT;
xhci->quirks |= XHCI_INTEL_HOST;
+ xhci->quirks |= XHCI_AVOID_BEI;
}
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) {
- xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
xhci->quirks |= XHCI_EP_LIMIT_QUIRK;
xhci->limit_active_eps = 64;
xhci->quirks |= XHCI_SW_BW_CHECKING;
@@ -106,7 +110,6 @@
* PPT chipsets.
*/
xhci->quirks |= XHCI_SPURIOUS_REBOOT;
- xhci->quirks |= XHCI_AVOID_BEI;
}
if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
pdev->device == PCI_DEVICE_ID_ASROCK_P67) {
@@ -114,6 +117,9 @@
xhci_dbg(xhci, "QUIRK: Resetting on resume\n");
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0015)
+ xhci->quirks |= XHCI_RESET_ON_RESUME;
if (pdev->vendor == PCI_VENDOR_ID_VIA)
xhci->quirks |= XHCI_RESET_ON_RESUME;
}
@@ -157,6 +163,10 @@
struct usb_hcd *hcd;
driver = (struct hc_driver *)id->driver_data;
+
+ /* Prevent runtime suspending between USB-2 and USB-3 initialization */
+ pm_runtime_get_noresume(&dev->dev);
+
/* Register the USB 2.0 roothub.
* FIXME: USB core must know to register the USB 2.0 roothub first.
* This is sort of silly, because we could just set the HCD driver flags
@@ -166,7 +176,7 @@
retval = usb_hcd_pci_probe(dev, id);
if (retval)
- return retval;
+ goto put_runtime_pm;
/* USB 2.0 roothub is stored in the PCI device now. */
hcd = dev_get_drvdata(&dev->dev);
@@ -195,12 +205,17 @@
if (xhci->quirks & XHCI_LPM_SUPPORT)
hcd_to_bus(xhci->shared_hcd)->root_hub->lpm_capable = 1;
+ /* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
+ pm_runtime_put_noidle(&dev->dev);
+
return 0;
put_usb3_hcd:
usb_put_hcd(xhci->shared_hcd);
dealloc_usb2_hcd:
usb_hcd_pci_remove(dev);
+put_runtime_pm:
+ pm_runtime_put_noidle(&dev->dev);
return retval;
}
@@ -346,7 +361,7 @@
/* suspend and resume implemented later */
.shutdown = usb_hcd_pci_shutdown,
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
.driver = {
.pm = &usb_hcd_pci_pm_ops
},
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index df90fe5..6e70ce9 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -24,7 +24,7 @@
* here that the generic code does not try to make a pci_dev from our
* dev struct in order to setup MSI
*/
- xhci->quirks |= XHCI_BROKEN_MSI;
+ xhci->quirks |= XHCI_PLAT;
}
/* called during probe() after chip reset completes */
@@ -179,6 +179,7 @@
usb_remove_hcd(hcd);
iounmap(hcd->regs);
+ release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
usb_put_hcd(hcd);
kfree(xhci);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 1969c00..bc7a886 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -122,6 +122,16 @@
return TRB_TYPE_LINK_LE32(link->control);
}
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring)
+{
+ /* Enqueue pointer can be left pointing to the link TRB,
+ * we must handle that
+ */
+ if (TRB_TYPE_LINK_LE32(ring->enqueue->link.control))
+ return ring->enq_seg->next->trbs;
+ return ring->enqueue;
+}
+
/* Updates trb to point to the next TRB in the ring, and updates seg if the next
* TRB is in a new segment. This does not skip over link TRBs, and it does not
* effect the ring dequeue or enqueue pointers.
@@ -434,7 +444,7 @@
/* A ring has pending URBs if its TD list is not empty */
if (!(ep->ep_state & EP_HAS_STREAMS)) {
- if (!(list_empty(&ep->ring->td_list)))
+ if (ep->ring && !(list_empty(&ep->ring->td_list)))
xhci_ring_ep_doorbell(xhci, slot_id, ep_index, 0);
return;
}
@@ -847,8 +857,12 @@
/* Otherwise ring the doorbell(s) to restart queued transfers */
ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
}
- ep->stopped_td = NULL;
- ep->stopped_trb = NULL;
+
+ /* Clear stopped_td and stopped_trb if endpoint is not halted */
+ if (!(ep->ep_state & EP_HALTED)) {
+ ep->stopped_td = NULL;
+ ep->stopped_trb = NULL;
+ }
/*
* Drop the lock and complete the URBs in the cancelled TD list.
@@ -1164,9 +1178,8 @@
false);
xhci_ring_cmd_db(xhci);
} else {
- /* Clear our internal halted state and restart the ring(s) */
+ /* Clear our internal halted state */
xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_HALTED;
- ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
}
}
@@ -1390,6 +1403,12 @@
inc_deq(xhci, xhci->cmd_ring);
return;
}
+ /* There is no command to handle if we get a stop event when the
+ * command ring is empty, event->cmd_trb points to the next
+ * unset command
+ */
+ if (xhci->cmd_ring->dequeue == xhci->cmd_ring->enqueue)
+ return;
}
switch (le32_to_cpu(xhci->cmd_ring->dequeue->generic.field[3])
@@ -1678,7 +1697,7 @@
} else {
xhci_dbg(xhci, "resume HS port %d\n", port_id);
bus_state->resume_done[faked_port_index] = jiffies +
- msecs_to_jiffies(20);
+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
set_bit(faked_port_index, &bus_state->resuming_ports);
mod_timer(&hcd->rh_timer,
bus_state->resume_done[faked_port_index]);
@@ -2045,7 +2064,7 @@
if (event_trb != ep_ring->dequeue) {
/* The event was for the status stage */
if (event_trb == td->last_trb) {
- if (td->urb->actual_length != 0) {
+ if (td->urb_length_set) {
/* Don't overwrite a previously set error code
*/
if ((*status == -EINPROGRESS || *status == 0) &&
@@ -2059,7 +2078,13 @@
td->urb->transfer_buffer_length;
}
} else {
- /* Maybe the event was for the data stage? */
+ /*
+ * Maybe the event was for the data stage? If so, update
+ * already the actual_length of the URB and flag it as
+ * set, so that it is not overwritten in the event for
+ * the last TRB.
+ */
+ td->urb_length_set = true;
td->urb->actual_length =
td->urb->transfer_buffer_length -
EVENT_TRB_LEN(le32_to_cpu(event->transfer_len));
@@ -2512,7 +2537,8 @@
* last TRB of the previous TD. The command completion handle
* will take care the rest.
*/
- if (!event_seg && trb_comp_code == COMP_STOP_INVAL) {
+ if (!event_seg && (trb_comp_code == COMP_STOP ||
+ trb_comp_code == COMP_STOP_INVAL)) {
ret = 0;
goto cleanup;
}
@@ -3570,7 +3596,7 @@
return 0;
max_burst = urb->ep->ss_ep_comp.bMaxBurst;
- return roundup(total_packet_count, max_burst + 1) - 1;
+ return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1;
}
/*
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index d8f640b..10223f2 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -315,6 +315,9 @@
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
+ if (xhci->quirks & XHCI_PLAT)
+ return;
+
xhci_free_irq(xhci);
if (xhci->msix_entries) {
@@ -342,9 +345,14 @@
static int xhci_try_enable_msi(struct usb_hcd *hcd)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
- struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
+ struct pci_dev *pdev;
int ret;
+ /* The xhci platform device has set up IRQs through usb_add_hcd. */
+ if (xhci->quirks & XHCI_PLAT)
+ return 0;
+
+ pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller);
/*
* Some Fresco Logic host controllers advertise MSI, but fail to
* generate interrupts. Don't even try to enable MSI.
@@ -386,16 +394,16 @@
#else
-static int xhci_try_enable_msi(struct usb_hcd *hcd)
+static inline int xhci_try_enable_msi(struct usb_hcd *hcd)
{
return 0;
}
-static void xhci_cleanup_msix(struct xhci_hcd *xhci)
+static inline void xhci_cleanup_msix(struct xhci_hcd *xhci)
{
}
-static void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
+static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci)
{
}
@@ -952,7 +960,7 @@
*/
int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
{
- u32 command, temp = 0;
+ u32 command, temp = 0, status;
struct usb_hcd *hcd = xhci_to_hcd(xhci);
struct usb_hcd *secondary_hcd;
int retval = 0;
@@ -1076,8 +1084,12 @@
done:
if (retval == 0) {
- usb_hcd_resume_root_hub(hcd);
- usb_hcd_resume_root_hub(xhci->shared_hcd);
+ /* Resume root hubs only when have pending events. */
+ status = readl(&xhci->op_regs->status);
+ if (status & STS_EINT) {
+ usb_hcd_resume_root_hub(hcd);
+ usb_hcd_resume_root_hub(xhci->shared_hcd);
+ }
}
/*
@@ -1171,9 +1183,6 @@
}
xhci = hcd_to_xhci(hcd);
- if (xhci->xhc_state & XHCI_STATE_HALTED)
- return -ENODEV;
-
if (check_virt_dev) {
if (!udev->slot_id || !xhci->devs[udev->slot_id]) {
printk(KERN_DEBUG "xHCI %s called with unaddressed "
@@ -1189,6 +1198,9 @@
}
}
+ if (xhci->xhc_state & XHCI_STATE_HALTED)
+ return -ENODEV;
+
return 1;
}
@@ -2587,15 +2599,7 @@
if (command) {
cmd_completion = command->completion;
cmd_status = &command->status;
- command->command_trb = xhci->cmd_ring->enqueue;
-
- /* Enqueue pointer can be left pointing to the link TRB,
- * we must handle that
- */
- if (TRB_TYPE_LINK_LE32(command->command_trb->link.control))
- command->command_trb =
- xhci->cmd_ring->enq_seg->next->trbs;
-
+ command->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
list_add_tail(&command->cmd_list, &virt_dev->cmd_list);
} else {
cmd_completion = &virt_dev->cmd_completion;
@@ -2603,7 +2607,7 @@
}
init_completion(cmd_completion);
- cmd_trb = xhci->cmd_ring->dequeue;
+ cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
if (!ctx_change)
ret = xhci_queue_configure_endpoint(xhci, in_ctx->dma,
udev->slot_id, must_succeed);
@@ -3388,14 +3392,7 @@
/* Attempt to submit the Reset Device command to the command ring */
spin_lock_irqsave(&xhci->lock, flags);
- reset_device_cmd->command_trb = xhci->cmd_ring->enqueue;
-
- /* Enqueue pointer can be left pointing to the link TRB,
- * we must handle that
- */
- if (TRB_TYPE_LINK_LE32(reset_device_cmd->command_trb->link.control))
- reset_device_cmd->command_trb =
- xhci->cmd_ring->enq_seg->next->trbs;
+ reset_device_cmd->command_trb = xhci_find_next_enqueue(xhci->cmd_ring);
list_add_tail(&reset_device_cmd->cmd_list, &virt_dev->cmd_list);
ret = xhci_queue_reset_device(xhci, slot_id);
@@ -3506,10 +3503,21 @@
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct xhci_virt_device *virt_dev;
+ struct device *dev = hcd->self.controller;
unsigned long flags;
u32 state;
int i, ret;
+#ifndef CONFIG_USB_DEFAULT_PERSIST
+ /*
+ * We called pm_runtime_get_noresume when the device was attached.
+ * Decrement the counter here to allow controller to runtime suspend
+ * if no devices remain.
+ */
+ if (xhci->quirks & XHCI_RESET_ON_RESUME)
+ pm_runtime_put_noidle(dev);
+#endif
+
ret = xhci_check_args(hcd, udev, NULL, 0, true, __func__);
/* If the host is halted due to driver unload, we still need to free the
* device.
@@ -3581,13 +3589,14 @@
int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+ struct device *dev = hcd->self.controller;
unsigned long flags;
int timeleft;
int ret;
union xhci_trb *cmd_trb;
spin_lock_irqsave(&xhci->lock, flags);
- cmd_trb = xhci->cmd_ring->dequeue;
+ cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
ret = xhci_queue_slot_control(xhci, TRB_ENABLE_SLOT, 0);
if (ret) {
spin_unlock_irqrestore(&xhci->lock, flags);
@@ -3633,6 +3642,16 @@
goto disable_slot;
}
udev->slot_id = xhci->slot_id;
+
+#ifndef CONFIG_USB_DEFAULT_PERSIST
+ /*
+ * If resetting upon resume, we can't put the controller into runtime
+ * suspend if there is a device attached.
+ */
+ if (xhci->quirks & XHCI_RESET_ON_RESUME)
+ pm_runtime_get_noresume(dev);
+#endif
+
/* Is this a LS or FS device under a HS hub? */
/* Hub or peripherial? */
return 1;
@@ -3704,7 +3723,7 @@
xhci_dbg_ctx(xhci, virt_dev->in_ctx, 2);
spin_lock_irqsave(&xhci->lock, flags);
- cmd_trb = xhci->cmd_ring->dequeue;
+ cmd_trb = xhci_find_next_enqueue(xhci->cmd_ring);
ret = xhci_queue_address_device(xhci, virt_dev->in_ctx->dma,
udev->slot_id);
if (ret) {
@@ -4388,13 +4407,21 @@
int ret;
spin_lock_irqsave(&xhci->lock, flags);
- if (max_exit_latency == xhci->devs[udev->slot_id]->current_mel) {
+
+ virt_dev = xhci->devs[udev->slot_id];
+
+ /*
+ * virt_dev might not exists yet if xHC resumed from hibernate (S4) and
+ * xHC was re-initialized. Exit latency will be set later after
+ * hub_port_finish_reset() is done and xhci->devs[] are re-allocated
+ */
+
+ if (!virt_dev || max_exit_latency == virt_dev->current_mel) {
spin_unlock_irqrestore(&xhci->lock, flags);
return 0;
}
/* Attempt to issue an Evaluate Context command to change the MEL. */
- virt_dev = xhci->devs[udev->slot_id];
command = xhci->lpm_command;
xhci_slot_copy(xhci, command->in_ctx, virt_dev->out_ctx);
spin_unlock_irqrestore(&xhci->lock, flags);
@@ -4697,6 +4724,13 @@
get_quirks(dev, xhci);
+ /* In xhci controllers which follow xhci 1.0 spec gives a spurious
+ * success event after a short transfer. This quirk will ignore such
+ * spurious event.
+ */
+ if (xhci->hci_version > 0x96)
+ xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
+
/* Make sure the HC is halted. */
retval = xhci_halt(xhci);
if (retval)
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 77600ce..373d4da 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1,3 +1,4 @@
+
/*
* xHCI host controller driver
*
@@ -88,9 +89,10 @@
#define HCS_IST(p) (((p) >> 0) & 0xf)
/* bits 4:7, max number of Event Ring segments */
#define HCS_ERST_MAX(p) (((p) >> 4) & 0xf)
+/* bits 21:25 Hi 5 bits of Scratchpad buffers SW must allocate for the HW */
/* bit 26 Scratchpad restore - for save/restore HW state - not used yet */
-/* bits 27:31 number of Scratchpad buffers SW must allocate for the HW */
-#define HCS_MAX_SCRATCHPAD(p) (((p) >> 27) & 0x1f)
+/* bits 27:31 Lo 5 bits of Scratchpad buffers SW must allocate for the HW */
+#define HCS_MAX_SCRATCHPAD(p) ((((p) >> 16) & 0x3e0) | (((p) >> 27) & 0x1f))
/* HCSPARAMS3 - hcs_params3 - bitmasks */
/* bits 0:7, Max U1 to U0 latency for the roothub ports */
@@ -1258,6 +1260,8 @@
struct xhci_segment *start_seg;
union xhci_trb *first_trb;
union xhci_trb *last_trb;
+ /* actual_length of the URB has already been set */
+ bool urb_length_set;
};
/* xHCI command default timeout value */
@@ -1516,6 +1520,7 @@
#define XHCI_SPURIOUS_REBOOT (1 << 13)
#define XHCI_COMP_MODE_QUIRK (1 << 14)
#define XHCI_AVOID_BEI (1 << 15)
+#define XHCI_PLAT (1 << 16)
unsigned int num_active_eps;
unsigned int limit_active_eps;
/* There are two roothubs to keep track of bus suspend info for */
@@ -1820,6 +1825,7 @@
union xhci_trb *cmd_trb);
void xhci_ring_ep_doorbell(struct xhci_hcd *xhci, unsigned int slot_id,
unsigned int ep_index, unsigned int stream_id);
+union xhci_trb *xhci_find_next_enqueue(struct xhci_ring *ring);
/* xHCI roothub code */
void xhci_set_link_state(struct xhci_hcd *xhci, __le32 __iomem **port_array,
diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c
index c21386e..0aef801e 100644
--- a/drivers/usb/misc/sisusbvga/sisusb.c
+++ b/drivers/usb/misc/sisusbvga/sisusb.c
@@ -3247,6 +3247,8 @@
{ USB_DEVICE(0x0711, 0x0903) },
{ USB_DEVICE(0x0711, 0x0918) },
{ USB_DEVICE(0x0711, 0x0920) },
+ { USB_DEVICE(0x0711, 0x0950) },
+ { USB_DEVICE(0x0711, 0x5200) },
{ USB_DEVICE(0x182d, 0x021c) },
{ USB_DEVICE(0x182d, 0x0269) },
{ }
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 8b4ca1c..98438b9 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -7,9 +7,10 @@
#include <linux/moduleparam.h>
#include <linux/scatterlist.h>
#include <linux/mutex.h>
-
+#include <linux/timer.h>
#include <linux/usb.h>
+#define SIMPLE_IO_TIMEOUT 10000 /* in milliseconds */
/*-------------------------------------------------------------------------*/
@@ -366,6 +367,7 @@
int max = urb->transfer_buffer_length;
struct completion completion;
int retval = 0;
+ unsigned long expire;
urb->context = &completion;
while (retval == 0 && iterations-- > 0) {
@@ -378,9 +380,15 @@
if (retval != 0)
break;
- /* NOTE: no timeouts; can't be broken out of by interrupt */
- wait_for_completion(&completion);
- retval = urb->status;
+ expire = msecs_to_jiffies(SIMPLE_IO_TIMEOUT);
+ if (!wait_for_completion_timeout(&completion, expire)) {
+ usb_kill_urb(urb);
+ retval = (urb->status == -ENOENT ?
+ -ETIMEDOUT : urb->status);
+ } else {
+ retval = urb->status;
+ }
+
urb->dev = udev;
if (retval == 0 && usb_pipein(urb->pipe))
retval = simple_check_buf(tdev, urb);
@@ -476,6 +484,14 @@
return sg;
}
+static void sg_timeout(unsigned long _req)
+{
+ struct usb_sg_request *req = (struct usb_sg_request *) _req;
+
+ req->status = -ETIMEDOUT;
+ usb_sg_cancel(req);
+}
+
static int perform_sglist(
struct usbtest_dev *tdev,
unsigned iterations,
@@ -487,6 +503,9 @@
{
struct usb_device *udev = testdev_to_usbdev(tdev);
int retval = 0;
+ struct timer_list sg_timer;
+
+ setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req);
while (retval == 0 && iterations-- > 0) {
retval = usb_sg_init(req, udev, pipe,
@@ -497,7 +516,10 @@
if (retval)
break;
+ mod_timer(&sg_timer, jiffies +
+ msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
usb_sg_wait(req);
+ del_timer_sync(&sg_timer);
retval = req->status;
/* FIXME check resulting data pattern */
@@ -1149,6 +1171,11 @@
urb->context = &completion;
urb->complete = unlink1_callback;
+ if (usb_pipeout(urb->pipe)) {
+ simple_fill_buf(urb);
+ urb->transfer_flags |= URB_ZERO_PACKET;
+ }
+
/* keep the endpoint busy. there are lots of hc/hcd-internal
* states, and testing should get to all of them over time.
*
@@ -1279,6 +1306,11 @@
unlink_queued_callback, &ctx);
ctx.urbs[i]->transfer_dma = buf_dma;
ctx.urbs[i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
+
+ if (usb_pipeout(ctx.urbs[i]->pipe)) {
+ simple_fill_buf(ctx.urbs[i]);
+ ctx.urbs[i]->transfer_flags |= URB_ZERO_PACKET;
+ }
}
/* Submit all the URBs and then unlink URBs num - 4 and num - 2. */
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 37a261a..da0caf3 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -440,7 +440,6 @@
static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
u8 devctl)
{
- struct usb_otg *otg = musb->xceiv->otg;
irqreturn_t handled = IRQ_NONE;
dev_dbg(musb->controller, "<== DevCtl=%02x, int_usb=0x%x\n", devctl,
@@ -655,7 +654,7 @@
break;
case OTG_STATE_B_PERIPHERAL:
musb_g_suspend(musb);
- musb->is_active = otg->gadget->b_hnp_enable;
+ musb->is_active = musb->g.b_hnp_enable;
if (musb->is_active) {
musb->xceiv->state = OTG_STATE_B_WAIT_ACON;
dev_dbg(musb->controller, "HNP: Setting timer for b_ase0_brst\n");
@@ -671,7 +670,7 @@
break;
case OTG_STATE_A_HOST:
musb->xceiv->state = OTG_STATE_A_SUSPEND;
- musb->is_active = otg->host->b_hnp_enable;
+ musb->is_active = musb_to_hcd(musb)->self.b_hnp_enable;
break;
case OTG_STATE_B_HOST:
/* Transition to B_PERIPHERAL, see 6.8.2.6 p 44 */
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 2311b1e..be41733 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -198,7 +198,7 @@
config USB_ULPI
bool "Generic ULPI Transceiver Driver"
- depends on ARM
+ depends on ARM || ARM64
help
Enable this to support ULPI connected USB OTG transceivers which
are likely found on embedded boards.
diff --git a/drivers/usb/phy/phy-fsl-usb.h b/drivers/usb/phy/phy-fsl-usb.h
index ca26628..e1859b8 100644
--- a/drivers/usb/phy/phy-fsl-usb.h
+++ b/drivers/usb/phy/phy-fsl-usb.h
@@ -15,7 +15,7 @@
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include "otg_fsm.h"
+#include "phy-fsm-usb.h"
#include <linux/usb/otg.h>
#include <linux/ioctl.h>
diff --git a/drivers/usb/phy/phy-fsm-usb.c b/drivers/usb/phy/phy-fsm-usb.c
index c520b35..7f45966 100644
--- a/drivers/usb/phy/phy-fsm-usb.c
+++ b/drivers/usb/phy/phy-fsm-usb.c
@@ -29,7 +29,7 @@
#include <linux/usb/gadget.h>
#include <linux/usb/otg.h>
-#include "phy-otg-fsm.h"
+#include "phy-fsm-usb.h"
/* Change USB protocol when there is a protocol change */
static int otg_set_protocol(struct otg_fsm *fsm, int protocol)
diff --git a/drivers/usb/phy/phy-isp1301-omap.c b/drivers/usb/phy/phy-isp1301-omap.c
index ae481af..9201feb 100644
--- a/drivers/usb/phy/phy-isp1301-omap.c
+++ b/drivers/usb/phy/phy-isp1301-omap.c
@@ -1299,7 +1299,7 @@
return isp1301_otg_enable(isp);
return 0;
-#elif !defined(CONFIG_USB_GADGET_OMAP)
+#elif !IS_ENABLED(CONFIG_USB_OMAP)
// FIXME update its refcount
otg->host = host;
diff --git a/drivers/usb/phy/phy-ulpi.c b/drivers/usb/phy/phy-ulpi.c
index 217339d..4e3877c 100644
--- a/drivers/usb/phy/phy-ulpi.c
+++ b/drivers/usb/phy/phy-ulpi.c
@@ -47,6 +47,9 @@
static struct ulpi_info ulpi_ids[] = {
ULPI_INFO(ULPI_ID(0x04cc, 0x1504), "NXP ISP1504"),
ULPI_INFO(ULPI_ID(0x0424, 0x0006), "SMSC USB331x"),
+ ULPI_INFO(ULPI_ID(0x0424, 0x0007), "SMSC USB3320"),
+ ULPI_INFO(ULPI_ID(0x0424, 0x0009), "SMSC USB334x"),
+ ULPI_INFO(ULPI_ID(0x0451, 0x1507), "TI TUSB1210"),
};
static int ulpi_set_otg_flags(struct usb_phy *phy)
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index a9984c7..5f79d8e 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -78,7 +78,9 @@
static int devm_usb_phy_match(struct device *dev, void *res, void *match_data)
{
- return res == match_data;
+ struct usb_phy **phy = res;
+
+ return *phy == match_data;
}
/**
diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c
index 3c4db6d..5c56efe 100644
--- a/drivers/usb/serial/bus.c
+++ b/drivers/usb/serial/bus.c
@@ -76,7 +76,7 @@
retval = device_create_file(dev, &dev_attr_port_number);
if (retval) {
if (driver->port_remove)
- retval = driver->port_remove(port);
+ driver->port_remove(port);
goto exit_with_autopm;
}
@@ -98,13 +98,19 @@
struct usb_serial_port *port;
int retval = 0;
int minor;
+ int autopm_err;
port = to_usb_serial_port(dev);
if (!port)
return -ENODEV;
- /* make sure suspend/resume doesn't race against port_remove */
- usb_autopm_get_interface(port->serial->interface);
+ /*
+ * Make sure suspend/resume doesn't race against port_remove.
+ *
+ * Note that no further runtime PM callbacks will be made if
+ * autopm_get fails.
+ */
+ autopm_err = usb_autopm_get_interface(port->serial->interface);
minor = port->number;
tty_unregister_device(usb_serial_tty_driver, minor);
@@ -118,7 +124,9 @@
dev_info(dev, "%s converter now disconnected from ttyUSB%d\n",
driver->description, minor);
- usb_autopm_put_interface(port->serial->interface);
+ if (!autopm_err)
+ usb_autopm_put_interface(port->serial->interface);
+
return retval;
}
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 2c65955..79e9ea0 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -53,8 +53,10 @@
{ USB_DEVICE(0x0489, 0xE000) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */
{ USB_DEVICE(0x0489, 0xE003) }, /* Pirelli Broadband S.p.A, DP-L10 SIP/GSM Mobile */
{ USB_DEVICE(0x0745, 0x1000) }, /* CipherLab USB CCD Barcode Scanner 1000 */
+ { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */
{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
{ USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
+ { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */
{ USB_DEVICE(0x0BED, 0x1100) }, /* MEI (TM) Cashflow-SC Bill/Voucher Acceptor */
{ USB_DEVICE(0x0BED, 0x1101) }, /* MEI series 2000 Combo Acceptor */
{ USB_DEVICE(0x0FCF, 0x1003) }, /* Dynastream ANT development board */
@@ -103,6 +105,7 @@
{ USB_DEVICE(0x10C4, 0x8218) }, /* Lipowsky Industrie Elektronik GmbH, HARP-1 */
{ USB_DEVICE(0x10C4, 0x822B) }, /* Modem EDGE(GSM) Comander 2 */
{ USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */
+ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */
{ USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */
{ USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */
{ USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */
@@ -118,6 +121,12 @@
{ USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */
{ USB_DEVICE(0x10C4, 0x8664) }, /* AC-Services CAN-IF */
{ USB_DEVICE(0x10C4, 0x8665) }, /* AC-Services OBD-IF */
+ { USB_DEVICE(0x10C4, 0x8856) }, /* CEL EM357 ZigBee USB Stick - LR */
+ { USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */
+ { USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
+ { USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+ { USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
+ { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA61) }, /* Silicon Labs factory default */
{ USB_DEVICE(0x10C4, 0xEA70) }, /* Silicon Labs factory default */
@@ -138,6 +147,8 @@
{ USB_DEVICE(0x166A, 0x0305) }, /* Clipsal C-5000CT2 C-Bus Spectrum Colour Touchscreen */
{ USB_DEVICE(0x166A, 0x0401) }, /* Clipsal L51xx C-Bus Architectural Dimmer */
{ USB_DEVICE(0x166A, 0x0101) }, /* Clipsal 5560884 C-Bus Multi-room Audio Matrix Switcher */
+ { USB_DEVICE(0x16C0, 0x09B0) }, /* Lunatico Seletek */
+ { USB_DEVICE(0x16C0, 0x09B1) }, /* Lunatico Seletek */
{ USB_DEVICE(0x16D6, 0x0001) }, /* Jablotron serial interface */
{ USB_DEVICE(0x16DC, 0x0010) }, /* W-IE-NE-R Plein & Baus GmbH PL512 Power Supply */
{ USB_DEVICE(0x16DC, 0x0011) }, /* W-IE-NE-R Plein & Baus GmbH RCM Remote Control for MARATON Power Supply */
@@ -148,7 +159,11 @@
{ USB_DEVICE(0x17F4, 0xAAAA) }, /* Wavesense Jazz blood glucose meter */
{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
+ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
+ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
+ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */
{ USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */
+ { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */
{ USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */
{ USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */
{ USB_DEVICE(0x1FB9, 0x0100) }, /* Lake Shore Model 121 Current Source */
diff --git a/drivers/usb/serial/cypress_m8.h b/drivers/usb/serial/cypress_m8.h
index b461311..ce13e61 100644
--- a/drivers/usb/serial/cypress_m8.h
+++ b/drivers/usb/serial/cypress_m8.h
@@ -63,7 +63,7 @@
#define UART_DSR 0x20 /* data set ready - flow control - device to host */
#define CONTROL_RTS 0x10 /* request to send - flow control - host to device */
#define UART_CTS 0x10 /* clear to send - flow control - device to host */
-#define UART_RI 0x10 /* ring indicator - modem - device to host */
+#define UART_RI 0x80 /* ring indicator - modem - device to host */
#define UART_CD 0x40 /* carrier detect - modem - device to host */
#define CYP_ERROR 0x08 /* received from input report - device to host */
/* Note - the below has nothing to do with the "feature report" reset */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 7260ec6..4d918d5 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -148,13 +148,16 @@
* /sys/bus/usb/ftdi_sio/new_id, then send patch/report!
*/
static struct usb_device_id id_table_combined [] = {
+ { USB_DEVICE(FTDI_VID, FTDI_BRICK_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ZEITCONTROL_TAGTRACE_MIFARE_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CTI_MINI_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CTI_NANO_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_1_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_2_PID) },
@@ -194,6 +197,8 @@
{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) },
{ USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_SPROG_II) },
+ { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_LP101_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_P200X_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_LENZ_LIUSB_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_XF_632_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_XF_634_PID) },
@@ -481,6 +486,39 @@
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FD_PID) },
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FE_PID) },
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_01FF_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_4701_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9300_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9301_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9302_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9303_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9304_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9305_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9306_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9307_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9308_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9309_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930A_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930B_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930C_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930D_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930E_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_930F_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9310_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9311_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9312_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9313_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9314_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9315_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9316_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9317_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9318_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_9319_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931A_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931B_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931C_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931D_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931E_PID) },
+ { USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_931F_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PERLE_ULTRAPORT_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PIEGROUP_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_TNC_X_PID) },
@@ -580,6 +618,9 @@
{ USB_DEVICE(FTDI_VID, FTDI_TAVIR_STK500_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_TIAO_UMPA_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+ { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) },
/*
* ELV devices:
*/
@@ -671,6 +712,10 @@
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_AWINDA_DONGLE_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_AWINDA_STATION_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+ { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
@@ -718,7 +763,8 @@
{ USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) },
- { USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) },
+ { USB_DEVICE(TESTO_VID, TESTO_1_PID) },
+ { USB_DEVICE(TESTO_VID, TESTO_3_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) },
@@ -735,15 +781,43 @@
{ USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID),
.driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk },
{ USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) },
- { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_SERIAL_VX7_PID) },
- { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_CT29B_PID) },
- { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_RTS01_PID) },
+ { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S03_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_59_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57A_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_57B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_29A_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_29B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_29F_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_62B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S01_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_63_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_29C_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_81B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_82B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_K5D_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_K4Y_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_K5G_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_S05_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_60_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_61_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_62_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_63B_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_64_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_65_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_92_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_92D_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_W5R_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_A5R_PID) },
+ { USB_DEVICE(RTSYSTEMS_VID, RTSYSTEMS_USB_PW1_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_MAXSTREAM_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PHI_FISCO_PID) },
{ USB_DEVICE(TML_VID, TML_USB_SERIAL_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
+ { USB_DEVICE(FTDI_VID, CYBER_CORTEX_AV_PID),
+ .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
@@ -881,6 +955,46 @@
{ USB_DEVICE(FTDI_VID, FTDI_LUMEL_PD12_PID) },
/* Crucible Devices */
{ USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) },
+ /* Cressi Devices */
+ { USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) },
+ /* Brainboxes Devices */
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_001_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_012_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_023_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_VX_034_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_101_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_3_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_4_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_5_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_6_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_7_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_160_8_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_257_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_3_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_279_4_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_313_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_324_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_346_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_357_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_606_3_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_701_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_1_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) },
+ { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) },
+ /* ekey Devices */
+ { USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
+ /* Infineon Devices */
+ { USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
{ }, /* Optional parameter entry */
{ } /* Terminating entry */
};
@@ -1511,14 +1625,17 @@
struct usb_device *udev = serial->dev;
struct usb_interface *interface = serial->interface;
- struct usb_endpoint_descriptor *ep_desc = &interface->cur_altsetting->endpoint[1].desc;
+ struct usb_endpoint_descriptor *ep_desc;
unsigned num_endpoints;
- int i;
+ unsigned i;
num_endpoints = interface->cur_altsetting->desc.bNumEndpoints;
dev_info(&udev->dev, "Number of endpoints %d\n", num_endpoints);
+ if (!num_endpoints)
+ return;
+
/* NOTE: some customers have programmed FT232R/FT245R devices
* with an endpoint size of 0 - not good. In this case, we
* want to override the endpoint descriptor setting and use a
@@ -1783,8 +1900,12 @@
{
struct usb_device *udev = serial->dev;
- if ((udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems")) ||
- (udev->product && !strcmp(udev->product, "BeagleBone/XDS100V2")))
+ if (udev->manufacturer && !strcmp(udev->manufacturer, "CALAO Systems"))
+ return ftdi_jtag_probe(serial);
+
+ if (udev->product &&
+ (!strcmp(udev->product, "BeagleBone/XDS100V2") ||
+ !strcmp(udev->product, "SNAP Connect E10")))
return ftdi_jtag_probe(serial);
return 0;
@@ -2105,6 +2226,30 @@
termios->c_cflag |= CRTSCTS;
}
+ /*
+ * All FTDI UART chips are limited to CS7/8. We shouldn't pretend to
+ * support CS5/6 and revert the CSIZE setting instead.
+ *
+ * CS5 however is used to control some smartcard readers which abuse
+ * this limitation to switch modes. Original FTDI chips fall back to
+ * eight data bits.
+ *
+ * TODO: Implement a quirk to only allow this with mentioned
+ * readers. One I know of (Argolis Smartreader V1)
+ * returns "USB smartcard server" as iInterface string.
+ * The vendor didn't bother with a custom VID/PID of
+ * course.
+ */
+ if (C_CSIZE(tty) == CS6) {
+ dev_warn(ddev, "requested CSIZE setting not supported\n");
+
+ termios->c_cflag &= ~CSIZE;
+ if (old_termios)
+ termios->c_cflag |= old_termios->c_cflag & CSIZE;
+ else
+ termios->c_cflag |= CS8;
+ }
+
cflag = termios->c_cflag;
if (!old_termios)
@@ -2141,19 +2286,19 @@
} else {
urb_value |= FTDI_SIO_SET_DATA_PARITY_NONE;
}
- if (cflag & CSIZE) {
- switch (cflag & CSIZE) {
- case CS7:
- urb_value |= 7;
- dev_dbg(ddev, "Setting CS7\n");
- break;
- case CS8:
- urb_value |= 8;
- dev_dbg(ddev, "Setting CS8\n");
- break;
- default:
- dev_err(ddev, "CSIZE was set but not CS7-CS8\n");
- }
+ switch (cflag & CSIZE) {
+ case CS5:
+ dev_dbg(ddev, "Setting CS5 quirk\n");
+ break;
+ case CS7:
+ urb_value |= 7;
+ dev_dbg(ddev, "Setting CS7\n");
+ break;
+ default:
+ case CS8:
+ urb_value |= 8;
+ dev_dbg(ddev, "Setting CS8\n");
+ break;
}
/* This is needed by the break command since it uses the same command
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 6dd7925..e906b6a 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -30,8 +30,17 @@
/*** third-party PIDs (using FTDI_VID) ***/
+/*
+ * Certain versions of the official Windows FTDI driver reprogrammed
+ * counterfeit FTDI devices to PID 0. Support these devices anyway.
+ */
+#define FTDI_BRICK_PID 0x0000
+
#define FTDI_LUMEL_PD12_PID 0x6002
+/* Cyber Cortex AV by Fabulous Silicon (http://fabuloussilicon.com) */
+#define CYBER_CORTEX_AV_PID 0x8698
+
/*
* Marvell OpenRD Base, Client
* http://www.open-rd.org
@@ -42,6 +51,8 @@
/* www.candapter.com Ewert Energy Systems CANdapter device */
#define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */
+#define FTDI_BM_ATOM_NANO_PID 0xa559 /* Basic Micro ATOM Nano USB2Serial */
+
/*
* Texas Instruments XDS100v2 JTAG / BeagleBone A3
* http://processors.wiki.ti.com/index.php/XDS100
@@ -50,6 +61,7 @@
#define TI_XDS100V2_PID 0xa6d0
#define FTDI_NXTCAM_PID 0xABB8 /* NXTCam for Mindstorms NXT */
+#define FTDI_EV3CON_PID 0xABB9 /* Mindstorms EV3 Console Adapter */
/* US Interface Navigator (http://www.usinterface.com/) */
#define FTDI_USINT_CAT_PID 0xb810 /* Navigator CAT and 2nd PTT lines */
@@ -139,12 +151,19 @@
/*
* Xsens Technologies BV products (http://www.xsens.com).
*/
-#define XSENS_CONVERTER_0_PID 0xD388
-#define XSENS_CONVERTER_1_PID 0xD389
+#define XSENS_VID 0x2639
+#define XSENS_AWINDA_STATION_PID 0x0101
+#define XSENS_AWINDA_DONGLE_PID 0x0102
+#define XSENS_MTW_PID 0x0200 /* Xsens MTw */
+#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */
+
+/* Xsens devices using FTDI VID */
+#define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */
+#define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */
#define XSENS_CONVERTER_2_PID 0xD38A
-#define XSENS_CONVERTER_3_PID 0xD38B
-#define XSENS_CONVERTER_4_PID 0xD38C
-#define XSENS_CONVERTER_5_PID 0xD38D
+#define XSENS_CONVERTER_3_PID 0xD38B /* Xsens USB-serial converter */
+#define XSENS_CONVERTER_4_PID 0xD38C /* Xsens Wireless Receiver */
+#define XSENS_CONVERTER_5_PID 0xD38D /* Xsens Awinda Station */
#define XSENS_CONVERTER_6_PID 0xD38E
#define XSENS_CONVERTER_7_PID 0xD38F
@@ -363,6 +382,12 @@
/* Sprog II (Andrew Crosland's SprogII DCC interface) */
#define FTDI_SPROG_II 0xF0C8
+/*
+ * Two of the Tagsys RFID Readers
+ */
+#define FTDI_TAGSYS_LP101_PID 0xF0E9 /* Tagsys L-P101 RFID*/
+#define FTDI_TAGSYS_P200X_PID 0xF0EE /* Tagsys Medio P200x RFID*/
+
/* an infrared receiver for user access control with IR tags */
#define FTDI_PIEGROUP_PID 0xF208 /* Product Id */
@@ -531,6 +556,17 @@
*/
#define FTDI_TIAO_UMPA_PID 0x8a98 /* TIAO/DIYGADGET USB Multi-Protocol Adapter */
+/*
+ * NovaTech product ids (FTDI_VID)
+ */
+#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */
+
+/*
+ * Synapse Wireless product ids (FTDI_VID)
+ * http://www.synapse-wireless.com
+ */
+#define FTDI_SYNAPSE_SS200_PID 0x9090 /* SS200 - SNAP Stick 200 */
+
/********************************/
/** third-party VID/PID combos **/
@@ -572,6 +608,12 @@
#define RATOC_PRODUCT_ID_USB60F 0xb020
/*
+ * Infineon Technologies
+ */
+#define INFINEON_VID 0x058b
+#define INFINEON_TRIBOARD_PID 0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+
+/*
* Acton Research Corp.
*/
#define ACTON_VID 0x0647 /* Vendor ID */
@@ -786,7 +828,8 @@
* Submitted by Colin Leroy
*/
#define TESTO_VID 0x128D
-#define TESTO_USB_INTERFACE_PID 0x0001
+#define TESTO_1_PID 0x0001
+#define TESTO_3_PID 0x0003
/*
* Mobility Electronics products.
@@ -813,13 +856,43 @@
#define TELLDUS_TELLSTICK_PID 0x0C30 /* RF control dongle 433 MHz using FT232RL */
/*
+ * NOVITUS printers
+ */
+#define NOVITUS_VID 0x1a28
+#define NOVITUS_BONO_E_PID 0x6010
+
+/*
* RT Systems programming cables for various ham radios
*/
-#define RTSYSTEMS_VID 0x2100 /* Vendor ID */
-#define RTSYSTEMS_SERIAL_VX7_PID 0x9e52 /* Serial converter for VX-7 Radios using FT232RL */
-#define RTSYSTEMS_CT29B_PID 0x9e54 /* CT29B Radio Cable */
-#define RTSYSTEMS_RTS01_PID 0x9e57 /* USB-RTS01 Radio Cable */
-
+#define RTSYSTEMS_VID 0x2100 /* Vendor ID */
+#define RTSYSTEMS_USB_S03_PID 0x9001 /* RTS-03 USB to Serial Adapter */
+#define RTSYSTEMS_USB_59_PID 0x9e50 /* USB-59 USB to 8 pin plug */
+#define RTSYSTEMS_USB_57A_PID 0x9e51 /* USB-57A USB to 4pin 3.5mm plug */
+#define RTSYSTEMS_USB_57B_PID 0x9e52 /* USB-57B USB to extended 4pin 3.5mm plug */
+#define RTSYSTEMS_USB_29A_PID 0x9e53 /* USB-29A USB to 3.5mm stereo plug */
+#define RTSYSTEMS_USB_29B_PID 0x9e54 /* USB-29B USB to 6 pin mini din */
+#define RTSYSTEMS_USB_29F_PID 0x9e55 /* USB-29F USB to 6 pin modular plug */
+#define RTSYSTEMS_USB_62B_PID 0x9e56 /* USB-62B USB to 8 pin mini din plug*/
+#define RTSYSTEMS_USB_S01_PID 0x9e57 /* USB-RTS01 USB to 3.5 mm stereo plug*/
+#define RTSYSTEMS_USB_63_PID 0x9e58 /* USB-63 USB to 9 pin female*/
+#define RTSYSTEMS_USB_29C_PID 0x9e59 /* USB-29C USB to 4 pin modular plug*/
+#define RTSYSTEMS_USB_81B_PID 0x9e5A /* USB-81 USB to 8 pin mini din plug*/
+#define RTSYSTEMS_USB_82B_PID 0x9e5B /* USB-82 USB to 2.5 mm stereo plug*/
+#define RTSYSTEMS_USB_K5D_PID 0x9e5C /* USB-K5D USB to 8 pin modular plug*/
+#define RTSYSTEMS_USB_K4Y_PID 0x9e5D /* USB-K4Y USB to 2.5/3.5 mm plugs*/
+#define RTSYSTEMS_USB_K5G_PID 0x9e5E /* USB-K5G USB to 8 pin modular plug*/
+#define RTSYSTEMS_USB_S05_PID 0x9e5F /* USB-RTS05 USB to 2.5 mm stereo plug*/
+#define RTSYSTEMS_USB_60_PID 0x9e60 /* USB-60 USB to 6 pin din*/
+#define RTSYSTEMS_USB_61_PID 0x9e61 /* USB-61 USB to 6 pin mini din*/
+#define RTSYSTEMS_USB_62_PID 0x9e62 /* USB-62 USB to 8 pin mini din*/
+#define RTSYSTEMS_USB_63B_PID 0x9e63 /* USB-63 USB to 9 pin female*/
+#define RTSYSTEMS_USB_64_PID 0x9e64 /* USB-64 USB to 9 pin male*/
+#define RTSYSTEMS_USB_65_PID 0x9e65 /* USB-65 USB to 9 pin female null modem*/
+#define RTSYSTEMS_USB_92_PID 0x9e66 /* USB-92 USB to 12 pin plug*/
+#define RTSYSTEMS_USB_92D_PID 0x9e67 /* USB-92D USB to 12 pin plug data*/
+#define RTSYSTEMS_USB_W5R_PID 0x9e68 /* USB-W5R USB to 8 pin modular plug*/
+#define RTSYSTEMS_USB_A5R_PID 0x9e69 /* USB-A5R USB to 8 pin modular plug*/
+#define RTSYSTEMS_USB_PW1_PID 0x9e6A /* USB-PW1 USB to 8 pin modular plug*/
/*
* Physik Instrumente
@@ -862,8 +935,8 @@
#define BAYER_CONTOUR_CABLE_PID 0x6001
/*
- * The following are the values for the Matrix Orbital FTDI Range
- * Anything in this range will use an FT232RL.
+ * Matrix Orbital Intelligent USB displays.
+ * http://www.matrixorbital.com
*/
#define MTXORB_VID 0x1B3D
#define MTXORB_FTDI_RANGE_0100_PID 0x0100
@@ -1122,8 +1195,39 @@
#define MTXORB_FTDI_RANGE_01FD_PID 0x01FD
#define MTXORB_FTDI_RANGE_01FE_PID 0x01FE
#define MTXORB_FTDI_RANGE_01FF_PID 0x01FF
-
-
+#define MTXORB_FTDI_RANGE_4701_PID 0x4701
+#define MTXORB_FTDI_RANGE_9300_PID 0x9300
+#define MTXORB_FTDI_RANGE_9301_PID 0x9301
+#define MTXORB_FTDI_RANGE_9302_PID 0x9302
+#define MTXORB_FTDI_RANGE_9303_PID 0x9303
+#define MTXORB_FTDI_RANGE_9304_PID 0x9304
+#define MTXORB_FTDI_RANGE_9305_PID 0x9305
+#define MTXORB_FTDI_RANGE_9306_PID 0x9306
+#define MTXORB_FTDI_RANGE_9307_PID 0x9307
+#define MTXORB_FTDI_RANGE_9308_PID 0x9308
+#define MTXORB_FTDI_RANGE_9309_PID 0x9309
+#define MTXORB_FTDI_RANGE_930A_PID 0x930A
+#define MTXORB_FTDI_RANGE_930B_PID 0x930B
+#define MTXORB_FTDI_RANGE_930C_PID 0x930C
+#define MTXORB_FTDI_RANGE_930D_PID 0x930D
+#define MTXORB_FTDI_RANGE_930E_PID 0x930E
+#define MTXORB_FTDI_RANGE_930F_PID 0x930F
+#define MTXORB_FTDI_RANGE_9310_PID 0x9310
+#define MTXORB_FTDI_RANGE_9311_PID 0x9311
+#define MTXORB_FTDI_RANGE_9312_PID 0x9312
+#define MTXORB_FTDI_RANGE_9313_PID 0x9313
+#define MTXORB_FTDI_RANGE_9314_PID 0x9314
+#define MTXORB_FTDI_RANGE_9315_PID 0x9315
+#define MTXORB_FTDI_RANGE_9316_PID 0x9316
+#define MTXORB_FTDI_RANGE_9317_PID 0x9317
+#define MTXORB_FTDI_RANGE_9318_PID 0x9318
+#define MTXORB_FTDI_RANGE_9319_PID 0x9319
+#define MTXORB_FTDI_RANGE_931A_PID 0x931A
+#define MTXORB_FTDI_RANGE_931B_PID 0x931B
+#define MTXORB_FTDI_RANGE_931C_PID 0x931C
+#define MTXORB_FTDI_RANGE_931D_PID 0x931D
+#define MTXORB_FTDI_RANGE_931E_PID 0x931E
+#define MTXORB_FTDI_RANGE_931F_PID 0x931F
/*
* The Mobility Lab (TML)
@@ -1283,3 +1387,57 @@
* Manufacturer: Crucible Technologies
*/
#define FTDI_CT_COMET_PID 0x8e08
+
+/*
+ * Product: Z3X Box
+ * Manufacturer: Smart GSM Team
+ */
+#define FTDI_Z3X_PID 0x0011
+
+/*
+ * Product: Cressi PC Interface
+ * Manufacturer: Cressi
+ */
+#define FTDI_CRESSI_PID 0x87d0
+
+/*
+ * Brainboxes devices
+ */
+#define BRAINBOXES_VID 0x05d1
+#define BRAINBOXES_VX_001_PID 0x1001 /* VX-001 ExpressCard 1 Port RS232 */
+#define BRAINBOXES_VX_012_PID 0x1002 /* VX-012 ExpressCard 2 Port RS232 */
+#define BRAINBOXES_VX_023_PID 0x1003 /* VX-023 ExpressCard 1 Port RS422/485 */
+#define BRAINBOXES_VX_034_PID 0x1004 /* VX-034 ExpressCard 2 Port RS422/485 */
+#define BRAINBOXES_US_101_PID 0x1011 /* US-101 1xRS232 */
+#define BRAINBOXES_US_324_PID 0x1013 /* US-324 1xRS422/485 1Mbaud */
+#define BRAINBOXES_US_606_1_PID 0x2001 /* US-606 6 Port RS232 Serial Port 1 and 2 */
+#define BRAINBOXES_US_606_2_PID 0x2002 /* US-606 6 Port RS232 Serial Port 3 and 4 */
+#define BRAINBOXES_US_606_3_PID 0x2003 /* US-606 6 Port RS232 Serial Port 4 and 6 */
+#define BRAINBOXES_US_701_1_PID 0x2011 /* US-701 4xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_701_2_PID 0x2012 /* US-701 4xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_1_PID 0x2021 /* US-279 8xRS422 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_279_2_PID 0x2022 /* US-279 8xRS422 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_279_3_PID 0x2023 /* US-279 8xRS422 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_279_4_PID 0x2024 /* US-279 8xRS422 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_346_1_PID 0x3011 /* US-346 4xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_346_2_PID 0x3012 /* US-346 4xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_257_PID 0x5001 /* US-257 2xRS232 1Mbaud */
+#define BRAINBOXES_US_313_PID 0x6001 /* US-313 2xRS422/485 1Mbaud */
+#define BRAINBOXES_US_357_PID 0x7001 /* US_357 1xRS232/422/485 */
+#define BRAINBOXES_US_842_1_PID 0x8001 /* US-842 8xRS422/485 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_842_2_PID 0x8002 /* US-842 8xRS422/485 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_842_3_PID 0x8003 /* US-842 8xRS422/485 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_842_4_PID 0x8004 /* US-842 8xRS422/485 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_1_PID 0x9001 /* US-160 16xRS232 1Mbaud Port 1 and 2 */
+#define BRAINBOXES_US_160_2_PID 0x9002 /* US-160 16xRS232 1Mbaud Port 3 and 4 */
+#define BRAINBOXES_US_160_3_PID 0x9003 /* US-160 16xRS232 1Mbaud Port 5 and 6 */
+#define BRAINBOXES_US_160_4_PID 0x9004 /* US-160 16xRS232 1Mbaud Port 7 and 8 */
+#define BRAINBOXES_US_160_5_PID 0x9005 /* US-160 16xRS232 1Mbaud Port 9 and 10 */
+#define BRAINBOXES_US_160_6_PID 0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */
+#define BRAINBOXES_US_160_7_PID 0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */
+#define BRAINBOXES_US_160_8_PID 0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */
+
+/*
+ * ekey biometric systems GmbH (http://ekey.net/)
+ */
+#define FTDI_EKEY_CONV_USB_PID 0xCB08 /* Converter USB */
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index ba45170..a10648d 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -176,14 +176,7 @@
return result;
}
- /* Try sending off another urb, unless in irq context (in which case
- * there will be no free urb). */
- if (!in_irq())
- goto retry;
-
- clear_bit_unlock(USB_SERIAL_WRITE_BUSY, &port->flags);
-
- return 0;
+ goto retry; /* try sending off another urb */
}
/**
@@ -268,7 +261,8 @@
* character or at least one jiffy.
*/
period = max_t(unsigned long, (10 * HZ / bps), 1);
- period = min_t(unsigned long, period, timeout);
+ if (timeout)
+ period = min_t(unsigned long, period, timeout);
dev_dbg(&port->dev, "%s - timeout = %u ms, period = %u ms\n",
__func__, jiffies_to_msecs(timeout),
@@ -278,7 +272,7 @@
schedule_timeout_interruptible(period);
if (signal_pending(current))
break;
- if (time_after(jiffies, expire))
+ if (timeout && time_after(jiffies, expire))
break;
}
}
diff --git a/drivers/usb/serial/io_ti.c b/drivers/usb/serial/io_ti.c
index 1be6ba7..8cd6479 100644
--- a/drivers/usb/serial/io_ti.c
+++ b/drivers/usb/serial/io_ti.c
@@ -29,6 +29,7 @@
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/serial.h>
+#include <linux/swab.h>
#include <linux/kfifo.h>
#include <linux/ioctl.h>
#include <linux/firmware.h>
@@ -284,7 +285,7 @@
{
int status = 0;
__u8 read_length;
- __be16 be_start_address;
+ u16 be_start_address;
dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, length);
@@ -300,10 +301,14 @@
if (read_length > 1) {
dev_dbg(&dev->dev, "%s - @ %x for %d\n", __func__, start_address, read_length);
}
- be_start_address = cpu_to_be16(start_address);
+ /*
+ * NOTE: Must use swab as wIndex is sent in little-endian
+ * byte order regardless of host byte order.
+ */
+ be_start_address = swab16((u16)start_address);
status = ti_vread_sync(dev, UMPC_MEMORY_READ,
(__u16)address_type,
- (__force __u16)be_start_address,
+ be_start_address,
buffer, read_length);
if (status) {
@@ -400,7 +405,7 @@
struct device *dev = &serial->serial->dev->dev;
int status = 0;
int write_length;
- __be16 be_start_address;
+ u16 be_start_address;
/* We can only send a maximum of 1 aligned byte page at a time */
@@ -415,11 +420,16 @@
__func__, start_address, write_length);
usb_serial_debug_data(dev, __func__, write_length, buffer);
- /* Write first page */
- be_start_address = cpu_to_be16(start_address);
+ /*
+ * Write first page.
+ *
+ * NOTE: Must use swab as wIndex is sent in little-endian byte order
+ * regardless of host byte order.
+ */
+ be_start_address = swab16((u16)start_address);
status = ti_vsend_sync(serial->serial->dev,
UMPC_MEMORY_WRITE, (__u16)address_type,
- (__force __u16)be_start_address,
+ be_start_address,
buffer, write_length);
if (status) {
dev_dbg(dev, "%s - ERROR %d\n", __func__, status);
@@ -442,11 +452,16 @@
__func__, start_address, write_length);
usb_serial_debug_data(dev, __func__, write_length, buffer);
- /* Write next page */
- be_start_address = cpu_to_be16(start_address);
+ /*
+ * Write next page.
+ *
+ * NOTE: Must use swab as wIndex is sent in little-endian byte
+ * order regardless of host byte order.
+ */
+ be_start_address = swab16((u16)start_address);
status = ti_vsend_sync(serial->serial->dev, UMPC_MEMORY_WRITE,
(__u16)address_type,
- (__force __u16)be_start_address,
+ be_start_address,
buffer, write_length);
if (status) {
dev_err(dev, "%s - ERROR %d\n", __func__, status);
@@ -593,8 +608,8 @@
if (rom_desc->Type == desc_type)
return start_address;
- start_address = start_address + sizeof(struct ti_i2c_desc)
- + rom_desc->Size;
+ start_address = start_address + sizeof(struct ti_i2c_desc) +
+ le16_to_cpu(rom_desc->Size);
} while ((start_address < TI_MAX_I2C_SIZE) && rom_desc->Type);
@@ -607,7 +622,7 @@
__u16 i;
__u8 cs = 0;
- for (i = 0; i < rom_desc->Size; i++)
+ for (i = 0; i < le16_to_cpu(rom_desc->Size); i++)
cs = (__u8)(cs + buffer[i]);
if (cs != rom_desc->CheckSum) {
@@ -661,7 +676,7 @@
break;
if ((start_address + sizeof(struct ti_i2c_desc) +
- rom_desc->Size) > TI_MAX_I2C_SIZE) {
+ le16_to_cpu(rom_desc->Size)) > TI_MAX_I2C_SIZE) {
status = -ENODEV;
dev_dbg(dev, "%s - structure too big, erroring out.\n", __func__);
break;
@@ -676,7 +691,8 @@
/* Read the descriptor data */
status = read_rom(serial, start_address +
sizeof(struct ti_i2c_desc),
- rom_desc->Size, buffer);
+ le16_to_cpu(rom_desc->Size),
+ buffer);
if (status)
break;
@@ -685,7 +701,7 @@
break;
}
start_address = start_address + sizeof(struct ti_i2c_desc) +
- rom_desc->Size;
+ le16_to_cpu(rom_desc->Size);
} while ((rom_desc->Type != I2C_DESC_TYPE_ION) &&
(start_address < TI_MAX_I2C_SIZE));
@@ -724,7 +740,7 @@
/* Read the descriptor data */
status = read_rom(serial, start_address+sizeof(struct ti_i2c_desc),
- rom_desc->Size, buffer);
+ le16_to_cpu(rom_desc->Size), buffer);
if (status)
goto exit;
@@ -819,7 +835,7 @@
firmware_rec = (struct ti_i2c_firmware_rec*)i2c_header->Data;
i2c_header->Type = I2C_DESC_TYPE_FIRMWARE_BLANK;
- i2c_header->Size = (__u16)buffer_size;
+ i2c_header->Size = cpu_to_le16(buffer_size);
i2c_header->CheckSum = cs;
firmware_rec->Ver_Major = OperationalMajorVersion;
firmware_rec->Ver_Minor = OperationalMinorVersion;
diff --git a/drivers/usb/serial/io_usbvend.h b/drivers/usb/serial/io_usbvend.h
index 51f83fb..6f6a856 100644
--- a/drivers/usb/serial/io_usbvend.h
+++ b/drivers/usb/serial/io_usbvend.h
@@ -594,7 +594,7 @@
struct ti_i2c_desc {
__u8 Type; // Type of descriptor
- __u16 Size; // Size of data only not including header
+ __le16 Size; // Size of data only not including header
__u8 CheckSum; // Checksum (8 bit sum of data only)
__u8 Data[0]; // Data starts here
} __attribute__((packed));
diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index 3549d07..cec377b 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -308,24 +308,30 @@
if ((data[0] & 0x80) == 0) {
/* no errors on individual bytes, only
possible overrun err */
- if (data[0] & RXERROR_OVERRUN)
- err = TTY_OVERRUN;
- else
- err = 0;
+ if (data[0] & RXERROR_OVERRUN) {
+ tty_insert_flip_char(&port->port, 0,
+ TTY_OVERRUN);
+ }
for (i = 1; i < urb->actual_length ; ++i)
- tty_insert_flip_char(&port->port, data[i], err);
+ tty_insert_flip_char(&port->port, data[i],
+ TTY_NORMAL);
} else {
/* some bytes had errors, every byte has status */
dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
for (i = 0; i + 1 < urb->actual_length; i += 2) {
- int stat = data[i], flag = 0;
- if (stat & RXERROR_OVERRUN)
- flag |= TTY_OVERRUN;
- if (stat & RXERROR_FRAMING)
- flag |= TTY_FRAME;
- if (stat & RXERROR_PARITY)
- flag |= TTY_PARITY;
+ int stat = data[i];
+ int flag = TTY_NORMAL;
+
+ if (stat & RXERROR_OVERRUN) {
+ tty_insert_flip_char(&port->port, 0,
+ TTY_OVERRUN);
+ }
/* XXX should handle break (0x10) */
+ if (stat & RXERROR_PARITY)
+ flag = TTY_PARITY;
+ else if (stat & RXERROR_FRAMING)
+ flag = TTY_FRAME;
+
tty_insert_flip_char(&port->port, data[i+1],
flag);
}
@@ -412,6 +418,8 @@
}
port = serial->port[msg->port];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ goto resubmit;
/* Update handshaking pin state information */
old_dcd_state = p_priv->dcd_state;
@@ -422,7 +430,7 @@
if (old_dcd_state != p_priv->dcd_state)
tty_port_tty_hangup(&port->port, true);
-
+resubmit:
/* Resubmit urb so we continue receiving */
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err != 0)
@@ -537,6 +545,8 @@
}
port = serial->port[msg->port];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ goto resubmit;
/* Update handshaking pin state information */
old_dcd_state = p_priv->dcd_state;
@@ -547,7 +557,7 @@
if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
tty_port_tty_hangup(&port->port, true);
-
+resubmit:
/* Resubmit urb so we continue receiving */
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err != 0)
@@ -624,6 +634,8 @@
}
port = serial->port[msg->portNumber];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ goto resubmit;
/* Update handshaking pin state information */
old_dcd_state = p_priv->dcd_state;
@@ -634,7 +646,7 @@
if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
tty_port_tty_hangup(&port->port, true);
-
+resubmit:
/* Resubmit urb so we continue receiving */
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err != 0)
@@ -672,14 +684,19 @@
} else {
/* some bytes had errors, every byte has status */
for (i = 0; i + 1 < urb->actual_length; i += 2) {
- int stat = data[i], flag = 0;
- if (stat & RXERROR_OVERRUN)
- flag |= TTY_OVERRUN;
- if (stat & RXERROR_FRAMING)
- flag |= TTY_FRAME;
- if (stat & RXERROR_PARITY)
- flag |= TTY_PARITY;
+ int stat = data[i];
+ int flag = TTY_NORMAL;
+
+ if (stat & RXERROR_OVERRUN) {
+ tty_insert_flip_char(&port->port, 0,
+ TTY_OVERRUN);
+ }
/* XXX should handle break (0x10) */
+ if (stat & RXERROR_PARITY)
+ flag = TTY_PARITY;
+ else if (stat & RXERROR_FRAMING)
+ flag = TTY_FRAME;
+
tty_insert_flip_char(&port->port, data[i+1],
flag);
}
@@ -736,15 +753,19 @@
*/
for (x = 0; x + 1 < len &&
i + 1 < urb->actual_length; x += 2) {
- int stat = data[i], flag = 0;
+ int stat = data[i];
+ int flag = TTY_NORMAL;
- if (stat & RXERROR_OVERRUN)
- flag |= TTY_OVERRUN;
- if (stat & RXERROR_FRAMING)
- flag |= TTY_FRAME;
- if (stat & RXERROR_PARITY)
- flag |= TTY_PARITY;
+ if (stat & RXERROR_OVERRUN) {
+ tty_insert_flip_char(&port->port, 0,
+ TTY_OVERRUN);
+ }
/* XXX should handle break (0x10) */
+ if (stat & RXERROR_PARITY)
+ flag = TTY_PARITY;
+ else if (stat & RXERROR_FRAMING)
+ flag = TTY_FRAME;
+
tty_insert_flip_char(&port->port, data[i+1],
flag);
i += 2;
@@ -796,25 +817,31 @@
if ((data[0] & 0x80) == 0) {
/* no errors on individual bytes, only
possible overrun err*/
- if (data[0] & RXERROR_OVERRUN)
- err = TTY_OVERRUN;
- else
- err = 0;
+ if (data[0] & RXERROR_OVERRUN) {
+ tty_insert_flip_char(&port->port, 0,
+ TTY_OVERRUN);
+ }
for (i = 1; i < urb->actual_length ; ++i)
tty_insert_flip_char(&port->port,
- data[i], err);
+ data[i], TTY_NORMAL);
} else {
/* some bytes had errors, every byte has status */
dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__);
for (i = 0; i + 1 < urb->actual_length; i += 2) {
- int stat = data[i], flag = 0;
- if (stat & RXERROR_OVERRUN)
- flag |= TTY_OVERRUN;
- if (stat & RXERROR_FRAMING)
- flag |= TTY_FRAME;
- if (stat & RXERROR_PARITY)
- flag |= TTY_PARITY;
+ int stat = data[i];
+ int flag = TTY_NORMAL;
+
+ if (stat & RXERROR_OVERRUN) {
+ tty_insert_flip_char(
+ &port->port, 0,
+ TTY_OVERRUN);
+ }
/* XXX should handle break (0x10) */
+ if (stat & RXERROR_PARITY)
+ flag = TTY_PARITY;
+ else if (stat & RXERROR_FRAMING)
+ flag = TTY_FRAME;
+
tty_insert_flip_char(&port->port,
data[i+1], flag);
}
@@ -857,6 +884,8 @@
port = serial->port[0];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ goto resubmit;
/* Update handshaking pin state information */
old_dcd_state = p_priv->dcd_state;
@@ -867,7 +896,7 @@
if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
tty_port_tty_hangup(&port->port, true);
-
+resubmit:
/* Resubmit urb so we continue receiving */
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err != 0)
@@ -928,6 +957,8 @@
port = serial->port[msg->port];
p_priv = usb_get_serial_port_data(port);
+ if (!p_priv)
+ goto resubmit;
/* Update handshaking pin state information */
old_dcd_state = p_priv->dcd_state;
@@ -936,7 +967,7 @@
if (old_dcd_state != p_priv->dcd_state && old_dcd_state)
tty_port_tty_hangup(&port->port, true);
-
+resubmit:
/* Resubmit urb so we continue receiving */
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err != 0)
@@ -2315,7 +2346,7 @@
if (d_details == NULL) {
dev_err(&serial->dev->dev, "%s - unknown product id %x\n",
__func__, le16_to_cpu(serial->dev->descriptor.idProduct));
- return 1;
+ return -ENODEV;
}
/* Setup private data for serial driver */
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index f27c621..0f16bf6e 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -90,6 +90,7 @@
struct list_head urblist_entry;
struct kref ref_count;
struct urb *urb;
+ struct usb_ctrlrequest *setup;
};
enum mos7715_pp_modes {
@@ -271,6 +272,7 @@
struct mos7715_parport *mos_parport = urbtrack->mos_parport;
usb_free_urb(urbtrack->urb);
+ kfree(urbtrack->setup);
kfree(urbtrack);
kref_put(&mos_parport->ref_count, destroy_mos_parport);
}
@@ -355,7 +357,6 @@
struct urbtracker *urbtrack;
int ret_val;
unsigned long flags;
- struct usb_ctrlrequest setup;
struct usb_serial *serial = mos_parport->serial;
struct usb_device *usbdev = serial->dev;
@@ -373,14 +374,20 @@
kfree(urbtrack);
return -ENOMEM;
}
- setup.bRequestType = (__u8)0x40;
- setup.bRequest = (__u8)0x0e;
- setup.wValue = get_reg_value(reg, dummy);
- setup.wIndex = get_reg_index(reg);
- setup.wLength = 0;
+ urbtrack->setup = kmalloc(sizeof(*urbtrack->setup), GFP_ATOMIC);
+ if (!urbtrack->setup) {
+ usb_free_urb(urbtrack->urb);
+ kfree(urbtrack);
+ return -ENOMEM;
+ }
+ urbtrack->setup->bRequestType = (__u8)0x40;
+ urbtrack->setup->bRequest = (__u8)0x0e;
+ urbtrack->setup->wValue = cpu_to_le16(get_reg_value(reg, dummy));
+ urbtrack->setup->wIndex = cpu_to_le16(get_reg_index(reg));
+ urbtrack->setup->wLength = 0;
usb_fill_control_urb(urbtrack->urb, usbdev,
usb_sndctrlpipe(usbdev, 0),
- (unsigned char *)&setup,
+ (unsigned char *)urbtrack->setup,
NULL, 0, async_complete, urbtrack);
kref_init(&urbtrack->ref_count);
INIT_LIST_HEAD(&urbtrack->urblist_entry);
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index 7e99808..d060130 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -183,7 +183,10 @@
#define LED_ON_MS 500
#define LED_OFF_MS 500
-static int device_type;
+enum mos7840_flag {
+ MOS7840_FLAG_CTRL_BUSY,
+ MOS7840_FLAG_LED_BUSY,
+};
static const struct usb_device_id id_table[] = {
{USB_DEVICE(USB_VENDOR_ID_MOSCHIP, MOSCHIP_DEVICE_ID_7840)},
@@ -238,9 +241,12 @@
/* For device(s) with LED indicator */
bool has_led;
- bool led_flag;
struct timer_list led_timer1; /* Timer for LED on */
struct timer_list led_timer2; /* Timer for LED off */
+ struct urb *led_urb;
+ struct usb_ctrlrequest *led_dr;
+
+ unsigned long flags;
};
/*
@@ -467,10 +473,10 @@
case -ESHUTDOWN:
/* this urb is terminated, clean up */
dev_dbg(dev, "%s - urb shutting down with status: %d\n", __func__, status);
- return;
+ goto out;
default:
dev_dbg(dev, "%s - nonzero urb status received: %d\n", __func__, status);
- return;
+ goto out;
}
dev_dbg(dev, "%s urb buffer size is %d\n", __func__, urb->actual_length);
@@ -483,6 +489,8 @@
mos7840_handle_new_msr(mos7840_port, regval);
else if (mos7840_port->MsrLsr == 1)
mos7840_handle_new_lsr(mos7840_port, regval);
+out:
+ clear_bit_unlock(MOS7840_FLAG_CTRL_BUSY, &mos7840_port->flags);
}
static int mos7840_get_reg(struct moschip_port *mcs, __u16 Wval, __u16 reg,
@@ -493,6 +501,9 @@
unsigned char *buffer = mcs->ctrl_buf;
int ret;
+ if (test_and_set_bit_lock(MOS7840_FLAG_CTRL_BUSY, &mcs->flags))
+ return -EBUSY;
+
dr->bRequestType = MCS_RD_RTYPE;
dr->bRequest = MCS_RDREQ;
dr->wValue = cpu_to_le16(Wval); /* 0 */
@@ -504,6 +515,9 @@
mos7840_control_callback, mcs);
mcs->control_urb->transfer_buffer_length = 2;
ret = usb_submit_urb(mcs->control_urb, GFP_ATOMIC);
+ if (ret)
+ clear_bit_unlock(MOS7840_FLAG_CTRL_BUSY, &mcs->flags);
+
return ret;
}
@@ -530,7 +544,7 @@
__u16 reg)
{
struct usb_device *dev = mcs->port->serial->dev;
- struct usb_ctrlrequest *dr = mcs->dr;
+ struct usb_ctrlrequest *dr = mcs->led_dr;
dr->bRequestType = MCS_WR_RTYPE;
dr->bRequest = MCS_WRREQ;
@@ -538,10 +552,10 @@
dr->wIndex = cpu_to_le16(reg);
dr->wLength = cpu_to_le16(0);
- usb_fill_control_urb(mcs->control_urb, dev, usb_sndctrlpipe(dev, 0),
+ usb_fill_control_urb(mcs->led_urb, dev, usb_sndctrlpipe(dev, 0),
(unsigned char *)dr, NULL, 0, mos7840_set_led_callback, NULL);
- usb_submit_urb(mcs->control_urb, GFP_ATOMIC);
+ usb_submit_urb(mcs->led_urb, GFP_ATOMIC);
}
static void mos7840_set_led_sync(struct usb_serial_port *port, __u16 reg,
@@ -567,7 +581,19 @@
{
struct moschip_port *mcs = (struct moschip_port *) arg;
- mcs->led_flag = false;
+ clear_bit_unlock(MOS7840_FLAG_LED_BUSY, &mcs->flags);
+}
+
+static void mos7840_led_activity(struct usb_serial_port *port)
+{
+ struct moschip_port *mos7840_port = usb_get_serial_port_data(port);
+
+ if (test_and_set_bit_lock(MOS7840_FLAG_LED_BUSY, &mos7840_port->flags))
+ return;
+
+ mos7840_set_led_async(mos7840_port, 0x0301, MODEM_CONTROL_REGISTER);
+ mod_timer(&mos7840_port->led_timer1,
+ jiffies + msecs_to_jiffies(LED_ON_MS));
}
/*****************************************************************************
@@ -767,14 +793,8 @@
return;
}
- /* Turn on LED */
- if (mos7840_port->has_led && !mos7840_port->led_flag) {
- mos7840_port->led_flag = true;
- mos7840_set_led_async(mos7840_port, 0x0301,
- MODEM_CONTROL_REGISTER);
- mod_timer(&mos7840_port->led_timer1,
- jiffies + msecs_to_jiffies(LED_ON_MS));
- }
+ if (mos7840_port->has_led)
+ mos7840_led_activity(port);
mos7840_port->read_urb_busy = true;
retval = usb_submit_urb(mos7840_port->read_urb, GFP_ATOMIC);
@@ -825,18 +845,6 @@
/************************************************************************/
/* D R I V E R T T Y I N T E R F A C E F U N C T I O N S */
/************************************************************************/
-#ifdef MCSSerialProbe
-static int mos7840_serial_probe(struct usb_serial *serial,
- const struct usb_device_id *id)
-{
-
- /*need to implement the mode_reg reading and updating\
- structures usb_serial_ device_type\
- (i.e num_ports, num_bulkin,bulkout etc) */
- /* Also we can update the changes attach */
- return 1;
-}
-#endif
/*****************************************************************************
* mos7840_open
@@ -914,20 +922,20 @@
status = mos7840_get_reg_sync(port, mos7840_port->SpRegOffset, &Data);
if (status < 0) {
dev_dbg(&port->dev, "Reading Spreg failed\n");
- return -1;
+ goto err;
}
Data |= 0x80;
status = mos7840_set_reg_sync(port, mos7840_port->SpRegOffset, Data);
if (status < 0) {
dev_dbg(&port->dev, "writing Spreg failed\n");
- return -1;
+ goto err;
}
Data &= ~0x80;
status = mos7840_set_reg_sync(port, mos7840_port->SpRegOffset, Data);
if (status < 0) {
dev_dbg(&port->dev, "writing Spreg failed\n");
- return -1;
+ goto err;
}
/* End of block to be checked */
@@ -936,7 +944,7 @@
&Data);
if (status < 0) {
dev_dbg(&port->dev, "Reading Controlreg failed\n");
- return -1;
+ goto err;
}
Data |= 0x08; /* Driver done bit */
Data |= 0x20; /* rx_disable */
@@ -944,7 +952,7 @@
mos7840_port->ControlRegOffset, Data);
if (status < 0) {
dev_dbg(&port->dev, "writing Controlreg failed\n");
- return -1;
+ goto err;
}
/* do register settings here */
/* Set all regs to the device default values. */
@@ -955,21 +963,21 @@
status = mos7840_set_uart_reg(port, INTERRUPT_ENABLE_REGISTER, Data);
if (status < 0) {
dev_dbg(&port->dev, "disabling interrupts failed\n");
- return -1;
+ goto err;
}
/* Set FIFO_CONTROL_REGISTER to the default value */
Data = 0x00;
status = mos7840_set_uart_reg(port, FIFO_CONTROL_REGISTER, Data);
if (status < 0) {
dev_dbg(&port->dev, "Writing FIFO_CONTROL_REGISTER failed\n");
- return -1;
+ goto err;
}
Data = 0xcf;
status = mos7840_set_uart_reg(port, FIFO_CONTROL_REGISTER, Data);
if (status < 0) {
dev_dbg(&port->dev, "Writing FIFO_CONTROL_REGISTER failed\n");
- return -1;
+ goto err;
}
Data = 0x03;
@@ -1114,6 +1122,15 @@
/* mos7840_change_port_settings(mos7840_port,old_termios); */
return 0;
+err:
+ for (j = 0; j < NUM_URBS; ++j) {
+ urb = mos7840_port->write_urb_pool[j];
+ if (!urb)
+ continue;
+ kfree(urb->transfer_buffer);
+ usb_free_urb(urb);
+ }
+ return status;
}
/*****************************************************************************
@@ -1458,13 +1475,8 @@
data1 = urb->transfer_buffer;
dev_dbg(&port->dev, "bulkout endpoint is %d\n", port->bulk_out_endpointAddress);
- /* Turn on LED */
- if (mos7840_port->has_led && !mos7840_port->led_flag) {
- mos7840_port->led_flag = true;
- mos7840_set_led_sync(port, MODEM_CONTROL_REGISTER, 0x0301);
- mod_timer(&mos7840_port->led_timer1,
- jiffies + msecs_to_jiffies(LED_ON_MS));
- }
+ if (mos7840_port->has_led)
+ mos7840_led_activity(port);
/* send it down the pipe */
status = usb_submit_urb(urb, GFP_ATOMIC);
@@ -1581,7 +1593,11 @@
return -ENODEV;
status = mos7840_get_uart_reg(port, MODEM_STATUS_REGISTER, &msr);
+ if (status != 1)
+ return -EIO;
status = mos7840_get_uart_reg(port, MODEM_CONTROL_REGISTER, &mcr);
+ if (status != 1)
+ return -EIO;
result = ((mcr & MCR_DTR) ? TIOCM_DTR : 0)
| ((mcr & MCR_RTS) ? TIOCM_RTS : 0)
| ((mcr & MCR_LOOPBACK) ? TIOCM_LOOP : 0)
@@ -1859,25 +1875,25 @@
iflag = tty->termios.c_iflag;
/* Change the number of bits */
- if (cflag & CSIZE) {
- switch (cflag & CSIZE) {
- case CS5:
- lData = LCR_BITS_5;
- break;
+ switch (cflag & CSIZE) {
+ case CS5:
+ lData = LCR_BITS_5;
+ break;
- case CS6:
- lData = LCR_BITS_6;
- break;
+ case CS6:
+ lData = LCR_BITS_6;
+ break;
- case CS7:
- lData = LCR_BITS_7;
- break;
- default:
- case CS8:
- lData = LCR_BITS_8;
- break;
- }
+ case CS7:
+ lData = LCR_BITS_7;
+ break;
+
+ default:
+ case CS8:
+ lData = LCR_BITS_8;
+ break;
}
+
/* Change the Parity bit */
if (cflag & PARENB) {
if (cflag & PARODD) {
@@ -2193,38 +2209,48 @@
return 0;
}
-static int mos7840_calc_num_ports(struct usb_serial *serial)
+static int mos7840_probe(struct usb_serial *serial,
+ const struct usb_device_id *id)
{
- __u16 data = 0x00;
+ u16 product = le16_to_cpu(serial->dev->descriptor.idProduct);
u8 *buf;
- int mos7840_num_ports;
+ int device_type;
+
+ if (product == MOSCHIP_DEVICE_ID_7810 ||
+ product == MOSCHIP_DEVICE_ID_7820) {
+ device_type = product;
+ goto out;
+ }
buf = kzalloc(VENDOR_READ_LENGTH, GFP_KERNEL);
- if (buf) {
- usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
+ if (!buf)
+ return -ENOMEM;
+
+ usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
MCS_RDREQ, MCS_RD_RTYPE, 0, GPIO_REGISTER, buf,
VENDOR_READ_LENGTH, MOS_WDR_TIMEOUT);
- data = *buf;
- kfree(buf);
- }
- if (serial->dev->descriptor.idProduct == MOSCHIP_DEVICE_ID_7810 ||
- serial->dev->descriptor.idProduct == MOSCHIP_DEVICE_ID_7820) {
- device_type = serial->dev->descriptor.idProduct;
- } else {
- /* For a MCS7840 device GPIO0 must be set to 1 */
- if ((data & 0x01) == 1)
- device_type = MOSCHIP_DEVICE_ID_7840;
- else if (mos7810_check(serial))
- device_type = MOSCHIP_DEVICE_ID_7810;
- else
- device_type = MOSCHIP_DEVICE_ID_7820;
- }
+ /* For a MCS7840 device GPIO0 must be set to 1 */
+ if (buf[0] & 0x01)
+ device_type = MOSCHIP_DEVICE_ID_7840;
+ else if (mos7810_check(serial))
+ device_type = MOSCHIP_DEVICE_ID_7810;
+ else
+ device_type = MOSCHIP_DEVICE_ID_7820;
+
+ kfree(buf);
+out:
+ usb_set_serial_data(serial, (void *)(unsigned long)device_type);
+
+ return 0;
+}
+
+static int mos7840_calc_num_ports(struct usb_serial *serial)
+{
+ int device_type = (unsigned long)usb_get_serial_data(serial);
+ int mos7840_num_ports;
mos7840_num_ports = (device_type >> 4) & 0x000F;
- serial->num_bulk_in = mos7840_num_ports;
- serial->num_bulk_out = mos7840_num_ports;
- serial->num_ports = mos7840_num_ports;
return mos7840_num_ports;
}
@@ -2232,6 +2258,7 @@
static int mos7840_port_probe(struct usb_serial_port *port)
{
struct usb_serial *serial = port->serial;
+ int device_type = (unsigned long)usb_get_serial_data(serial);
struct moschip_port *mos7840_port;
int status;
int pnum;
@@ -2409,6 +2436,14 @@
if (device_type == MOSCHIP_DEVICE_ID_7810) {
mos7840_port->has_led = true;
+ mos7840_port->led_urb = usb_alloc_urb(0, GFP_KERNEL);
+ mos7840_port->led_dr = kmalloc(sizeof(*mos7840_port->led_dr),
+ GFP_KERNEL);
+ if (!mos7840_port->led_urb || !mos7840_port->led_dr) {
+ status = -ENOMEM;
+ goto error;
+ }
+
init_timer(&mos7840_port->led_timer1);
mos7840_port->led_timer1.function = mos7840_led_off;
mos7840_port->led_timer1.expires =
@@ -2421,8 +2456,6 @@
jiffies + msecs_to_jiffies(LED_OFF_MS);
mos7840_port->led_timer2.data = (unsigned long)mos7840_port;
- mos7840_port->led_flag = false;
-
/* Turn off LED */
mos7840_set_led_sync(port, MODEM_CONTROL_REGISTER, 0x0300);
}
@@ -2444,6 +2477,8 @@
}
return 0;
error:
+ kfree(mos7840_port->led_dr);
+ usb_free_urb(mos7840_port->led_urb);
kfree(mos7840_port->dr);
kfree(mos7840_port->ctrl_buf);
usb_free_urb(mos7840_port->control_urb);
@@ -2464,6 +2499,10 @@
del_timer_sync(&mos7840_port->led_timer1);
del_timer_sync(&mos7840_port->led_timer2);
+
+ usb_kill_urb(mos7840_port->led_urb);
+ usb_free_urb(mos7840_port->led_urb);
+ kfree(mos7840_port->led_dr);
}
usb_kill_urb(mos7840_port->control_urb);
usb_free_urb(mos7840_port->control_urb);
@@ -2490,9 +2529,7 @@
.throttle = mos7840_throttle,
.unthrottle = mos7840_unthrottle,
.calc_num_ports = mos7840_calc_num_ports,
-#ifdef MCSSerialProbe
- .probe = mos7840_serial_probe,
-#endif
+ .probe = mos7840_probe,
.ioctl = mos7840_ioctl,
.set_termios = mos7840_set_termios,
.break_ctl = mos7840_break,
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
index 5f4b0cd..b0eb1df 100644
--- a/drivers/usb/serial/opticon.c
+++ b/drivers/usb/serial/opticon.c
@@ -219,7 +219,7 @@
/* The conncected devices do not have a bulk write endpoint,
* to transmit data to de barcode device the control endpoint is used */
- dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_NOIO);
+ dr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_ATOMIC);
if (!dr) {
dev_err(&port->dev, "out of memory\n");
count = -ENOMEM;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index bd4323d..8b34841 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -81,9 +81,11 @@
#define HUAWEI_VENDOR_ID 0x12D1
#define HUAWEI_PRODUCT_E173 0x140C
+#define HUAWEI_PRODUCT_E1750 0x1406
#define HUAWEI_PRODUCT_K4505 0x1464
#define HUAWEI_PRODUCT_K3765 0x1465
#define HUAWEI_PRODUCT_K4605 0x14C6
+#define HUAWEI_PRODUCT_E173S6 0x1C07
#define QUANTA_VENDOR_ID 0x0408
#define QUANTA_PRODUCT_Q101 0xEA02
@@ -159,8 +161,7 @@
#define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_FULLSPEED 0x9000
#define NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED 0x9001
#define NOVATELWIRELESS_PRODUCT_E362 0x9010
-#define NOVATELWIRELESS_PRODUCT_G1 0xA001
-#define NOVATELWIRELESS_PRODUCT_G1_M 0xA002
+#define NOVATELWIRELESS_PRODUCT_E371 0x9011
#define NOVATELWIRELESS_PRODUCT_G2 0xA010
#define NOVATELWIRELESS_PRODUCT_MC551 0xB001
@@ -234,8 +235,31 @@
#define QUALCOMM_VENDOR_ID 0x05C6
#define CMOTECH_VENDOR_ID 0x16d8
-#define CMOTECH_PRODUCT_6008 0x6008
-#define CMOTECH_PRODUCT_6280 0x6280
+#define CMOTECH_PRODUCT_6001 0x6001
+#define CMOTECH_PRODUCT_CMU_300 0x6002
+#define CMOTECH_PRODUCT_6003 0x6003
+#define CMOTECH_PRODUCT_6004 0x6004
+#define CMOTECH_PRODUCT_6005 0x6005
+#define CMOTECH_PRODUCT_CGU_628A 0x6006
+#define CMOTECH_PRODUCT_CHE_628S 0x6007
+#define CMOTECH_PRODUCT_CMU_301 0x6008
+#define CMOTECH_PRODUCT_CHU_628 0x6280
+#define CMOTECH_PRODUCT_CHU_628S 0x6281
+#define CMOTECH_PRODUCT_CDU_680 0x6803
+#define CMOTECH_PRODUCT_CDU_685A 0x6804
+#define CMOTECH_PRODUCT_CHU_720S 0x7001
+#define CMOTECH_PRODUCT_7002 0x7002
+#define CMOTECH_PRODUCT_CHU_629K 0x7003
+#define CMOTECH_PRODUCT_7004 0x7004
+#define CMOTECH_PRODUCT_7005 0x7005
+#define CMOTECH_PRODUCT_CGU_629 0x7006
+#define CMOTECH_PRODUCT_CHU_629S 0x700a
+#define CMOTECH_PRODUCT_CHU_720I 0x7211
+#define CMOTECH_PRODUCT_7212 0x7212
+#define CMOTECH_PRODUCT_7213 0x7213
+#define CMOTECH_PRODUCT_7251 0x7251
+#define CMOTECH_PRODUCT_7252 0x7252
+#define CMOTECH_PRODUCT_7253 0x7253
#define TELIT_VENDOR_ID 0x1bc7
#define TELIT_PRODUCT_UC864E 0x1003
@@ -243,14 +267,21 @@
#define TELIT_PRODUCT_CC864_DUAL 0x1005
#define TELIT_PRODUCT_CC864_SINGLE 0x1006
#define TELIT_PRODUCT_DE910_DUAL 0x1010
+#define TELIT_PRODUCT_UE910_V2 0x1012
#define TELIT_PRODUCT_LE920 0x1200
+#define TELIT_PRODUCT_LE910 0x1201
/* ZTE PRODUCTS */
#define ZTE_VENDOR_ID 0x19d2
#define ZTE_PRODUCT_MF622 0x0001
#define ZTE_PRODUCT_MF628 0x0015
#define ZTE_PRODUCT_MF626 0x0031
+#define ZTE_PRODUCT_AC2726 0xfff1
+#define ZTE_PRODUCT_CDMA_TECH 0xfffe
+#define ZTE_PRODUCT_AC8710T 0xffff
#define ZTE_PRODUCT_MC2718 0xffe8
+#define ZTE_PRODUCT_AD3812 0xffeb
+#define ZTE_PRODUCT_MC2716 0xffed
#define BENQ_VENDOR_ID 0x04a5
#define BENQ_PRODUCT_H10 0x4068
@@ -285,6 +316,7 @@
#define ALCATEL_PRODUCT_X060S_X200 0x0000
#define ALCATEL_PRODUCT_X220_X500D 0x0017
#define ALCATEL_PRODUCT_L100V 0x011e
+#define ALCATEL_PRODUCT_L800MA 0x0203
#define PIRELLI_VENDOR_ID 0x1266
#define PIRELLI_PRODUCT_C100_1 0x1002
@@ -319,11 +351,18 @@
* It seems to contain a Qualcomm QSC6240/6290 chipset */
#define FOUR_G_SYSTEMS_PRODUCT_W14 0x9603
+/* iBall 3.5G connect wireless modem */
+#define IBALL_3_5G_CONNECT 0x9605
+
/* Zoom */
#define ZOOM_PRODUCT_4597 0x9607
+/* SpeedUp SU9800 usb 3g modem */
+#define SPEEDUP_PRODUCT_SU9800 0x9800
+
/* Haier products */
#define HAIER_VENDOR_ID 0x201e
+#define HAIER_PRODUCT_CE81B 0x10f8
#define HAIER_PRODUCT_CE100 0x2009
/* Cinterion (formerly Siemens) products */
@@ -342,18 +381,18 @@
/* Olivetti products */
#define OLIVETTI_VENDOR_ID 0x0b3c
#define OLIVETTI_PRODUCT_OLICARD100 0xc000
+#define OLIVETTI_PRODUCT_OLICARD120 0xc001
+#define OLIVETTI_PRODUCT_OLICARD140 0xc002
#define OLIVETTI_PRODUCT_OLICARD145 0xc003
+#define OLIVETTI_PRODUCT_OLICARD155 0xc004
+#define OLIVETTI_PRODUCT_OLICARD200 0xc005
+#define OLIVETTI_PRODUCT_OLICARD160 0xc00a
+#define OLIVETTI_PRODUCT_OLICARD500 0xc00b
/* Celot products */
#define CELOT_VENDOR_ID 0x211f
#define CELOT_PRODUCT_CT680M 0x6801
-/* ONDA Communication vendor id */
-#define ONDA_VENDOR_ID 0x1ee8
-
-/* ONDA MT825UP HSDPA 14.2 modem */
-#define ONDA_MT825UP 0x000b
-
/* Samsung products */
#define SAMSUNG_VENDOR_ID 0x04e8
#define SAMSUNG_PRODUCT_GT_B3730 0x6889
@@ -446,7 +485,8 @@
/* Hyundai Petatel Inc. products */
#define PETATEL_VENDOR_ID 0x1ff4
-#define PETATEL_PRODUCT_NP10T 0x600e
+#define PETATEL_PRODUCT_NP10T_600A 0x600a
+#define PETATEL_PRODUCT_NP10T_600E 0x600e
/* TP-LINK Incorporated products */
#define TPLINK_VENDOR_ID 0x2357
@@ -456,6 +496,14 @@
#define CHANGHONG_VENDOR_ID 0x2077
#define CHANGHONG_PRODUCT_CH690 0x7001
+/* Inovia */
+#define INOVIA_VENDOR_ID 0x20a6
+#define INOVIA_SEW858 0x1105
+
+/* VIA Telecom */
+#define VIATELECOM_VENDOR_ID 0x15eb
+#define VIATELECOM_PRODUCT_CDS7 0x0001
+
/* some devices interfaces need special handling due to a number of reasons */
enum option_blacklist_reason {
OPTION_BLACKLIST_NONE = 0,
@@ -489,14 +537,26 @@
.reserved = BIT(4),
};
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+ .sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
static const struct option_blacklist_info zte_mc2718_z_blacklist = {
.sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
};
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+ .sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
static const struct option_blacklist_info huawei_cdc12_blacklist = {
.reserved = BIT(1) | BIT(2),
};
+static const struct option_blacklist_info net_intf0_blacklist = {
+ .reserved = BIT(0),
+};
+
static const struct option_blacklist_info net_intf1_blacklist = {
.reserved = BIT(1),
};
@@ -530,6 +590,11 @@
.reserved = BIT(3) | BIT(4),
};
+static const struct option_blacklist_info telit_le910_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(1) | BIT(2),
+};
+
static const struct option_blacklist_info telit_le920_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(5),
@@ -573,6 +638,10 @@
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1c23, USB_CLASS_COMM, 0x02, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t) &net_intf1_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S6, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t) &net_intf1_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E1750, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t) &net_intf2_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1441, USB_CLASS_COMM, 0x02, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0x1442, USB_CLASS_COMM, 0x02, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff),
@@ -633,6 +702,10 @@
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6D) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6E) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x75) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x78) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x79) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x01, 0x7A) },
@@ -687,11 +760,247 @@
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6D) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6E) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x75) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x78) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x79) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7A) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7B) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x02, 0x7C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x01) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x02) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x03) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x04) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x05) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x06) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x0F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x10) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x12) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x13) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x14) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x15) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x17) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x18) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x19) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x1C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x31) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x32) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x33) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x34) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x35) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x36) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x3F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x48) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x49) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x4C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x61) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x62) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x63) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x64) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x65) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x66) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x75) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x78) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x79) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x03, 0x7C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x01) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x02) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x03) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x04) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x05) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x06) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x0F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x10) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x12) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x13) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x14) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x15) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x17) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x18) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x19) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x1C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x31) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x32) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x33) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x34) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x35) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x36) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x3F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x48) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x49) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x4C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x61) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x62) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x63) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x64) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x65) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x66) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x75) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x78) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x79) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x04, 0x7C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x01) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x02) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x03) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x04) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x05) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x06) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x0F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x10) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x12) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x13) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x14) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x15) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x17) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x18) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x19) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x1C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x31) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x32) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x33) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x34) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x35) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x36) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x3F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x48) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x49) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x4C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x61) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x62) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x63) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x64) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x65) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x66) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x75) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x78) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x79) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x05, 0x7C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x01) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x02) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x03) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x04) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x05) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x06) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x0F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x10) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x12) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x13) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x14) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x15) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x17) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x18) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x19) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x1C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x31) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x32) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x33) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x34) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x35) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x36) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x3F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x48) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x49) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x4C) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x61) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x62) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x63) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x64) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x65) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x66) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6D) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6E) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x6F) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x72) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x73) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x74) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x75) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x78) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x79) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7A) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7B) },
+ { USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7C) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
@@ -730,12 +1039,11 @@
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC547) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_EVDO_EMBEDDED_HIGHSPEED) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_HSPA_EMBEDDED_HIGHSPEED) },
- { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_G1) },
- { USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_G1_M) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_G2) },
/* Novatel Ovation MC551 a.k.a. Verizon USB551L */
{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_MC551, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E362, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_E371, 0xff, 0xff, 0xff) },
{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01) },
{ USB_DEVICE(AMOI_VENDOR_ID, AMOI_PRODUCT_H01A) },
@@ -785,15 +1093,59 @@
{ USB_DEVICE_INTERFACE_CLASS(BANDRICH_VENDOR_ID, BANDRICH_PRODUCT_1012, 0xff) },
{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) },
{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
- { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
- { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6004) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6005) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_628A) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHE_628S),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_301),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_628S) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_680) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CDU_685A) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720S),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7002),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629K),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7004),
+ .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7005) },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CGU_629),
+ .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_629S),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CHU_720I),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7212),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7213),
+ .driver_info = (kernel_ulong_t)&net_intf0_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7251),
+ .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7252),
+ .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
+ { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_7253),
+ .driver_info = (kernel_ulong_t)&net_intf1_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864G) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_DUAL) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_CC864_SINGLE) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_DE910_DUAL) },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UE910_V2) },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
+ .driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
@@ -821,7 +1173,8 @@
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0017, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0018, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0019, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0019, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&net_intf3_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0020, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0021, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1114,7 +1467,8 @@
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1267, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1268, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1269, 0xff, 0xff, 0xff) },
- { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&net_intf5_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1271, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) },
@@ -1159,6 +1513,25 @@
.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff), /* ZTE MF91 */
.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff), /* Telewell TW-LTE 4G v2 */
+ .driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1545, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1546, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1547, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1565, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1566, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1567, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1589, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1590, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1591, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1592, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1594, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1596, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1598, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1600, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2002, 0xff,
0xff, 0xff), .driver_info = (kernel_ulong_t)&zte_k3765_z_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x2003, 0xff, 0xff, 0xff) },
@@ -1185,10 +1558,27 @@
.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0178, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t)&net_intf3_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8b, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8c, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8d, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8e, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8f, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff90, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff91, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff92, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) },
- /* NOTE: most ZTE CDMA devices should be driven by zte_ev, not option */
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_CDMA_TECH, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
@@ -1220,13 +1610,18 @@
.driver_info = (kernel_ulong_t)&net_intf5_blacklist },
{ USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L100V),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_L800MA),
+ .driver_info = (kernel_ulong_t)&net_intf2_blacklist },
{ USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) },
{ USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) },
{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
.driver_info = (kernel_ulong_t)&four_g_w14_blacklist
},
+ { USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
+ { USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HAIER_VENDOR_ID, HAIER_PRODUCT_CE81B, 0xff, 0xff, 0xff) },
/* Pirelli */
{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_1, 0xff) },
{ USB_DEVICE_INTERFACE_CLASS(PIRELLI_VENDOR_ID, PIRELLI_PRODUCT_C100_2, 0xff) },
@@ -1247,7 +1642,8 @@
/* Cinterion */
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) },
- { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) },
+ { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) },
{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1257,11 +1653,22 @@
{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) },
{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */
{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
-
- { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD140),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD155),
+ .driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200),
+ .driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD160),
+ .driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+ { USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD500),
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */
- { USB_DEVICE(ONDA_VENDOR_ID, ONDA_MT825UP) }, /* ONDA MT825UP modem */
{ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/
{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) },
{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM610) },
@@ -1333,9 +1740,12 @@
{ USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM2, 0xff, 0x02, 0x01) },
{ USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, MEDIATEK_PRODUCT_DC_4COM2, 0xff, 0x00, 0x00) },
{ USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) },
- { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T) },
+ { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600A) },
+ { USB_DEVICE(PETATEL_VENDOR_ID, PETATEL_PRODUCT_NP10T_600E) },
{ USB_DEVICE(TPLINK_VENDOR_ID, TPLINK_PRODUCT_MA180),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ { USB_DEVICE(TPLINK_VENDOR_ID, 0x9000), /* TP-Link MA260 */
+ .driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE(CHANGHONG_VENDOR_ID, CHANGHONG_PRODUCT_CH690) },
{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d01, 0xff, 0x02, 0x01) }, /* D-Link DWM-156 (variant) */
{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d01, 0xff, 0x00, 0x00) }, /* D-Link DWM-156 (variant) */
@@ -1343,6 +1753,10 @@
{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d02, 0xff, 0x00, 0x00) },
{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x02, 0x01) },
{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
+ { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
@@ -1536,6 +1950,8 @@
dev_dbg(dev, "%s: type %x req %x\n", __func__,
req_pkt->bRequestType, req_pkt->bRequest);
}
+ } else if (status == -ENOENT || status == -ESHUTDOWN) {
+ dev_dbg(dev, "%s: urb stopped: %d\n", __func__, status);
} else
dev_err(dev, "%s: error %d\n", __func__, status);
@@ -1560,6 +1976,7 @@
struct option_private *priv = intfdata->private;
struct usb_wwan_port_private *portdata;
int val = 0;
+ int res;
portdata = usb_get_serial_port_data(port);
@@ -1568,9 +1985,17 @@
if (portdata->rts_state)
val |= 0x02;
- return usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
+ res = usb_autopm_get_interface(serial->interface);
+ if (res)
+ return res;
+
+ res = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
0x22, 0x21, val, priv->bInterfaceNumber, NULL,
0, USB_CTRL_SET_TIMEOUT);
+
+ usb_autopm_put_interface(serial->interface);
+
+ return res;
}
MODULE_AUTHOR(DRIVER_AUTHOR);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 048cd44..de3e15d 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -47,6 +47,7 @@
{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) },
{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) },
{ USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) },
+ { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) },
{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },
@@ -82,6 +83,9 @@
{ USB_DEVICE(YCCABLE_VENDOR_ID, YCCABLE_PRODUCT_ID) },
{ USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) },
{ USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) },
+ { USB_DEVICE(HP_VENDOR_ID, HP_LD960_PRODUCT_ID) },
+ { USB_DEVICE(HP_VENDOR_ID, HP_LCM220_PRODUCT_ID) },
+ { USB_DEVICE(HP_VENDOR_ID, HP_LCM960_PRODUCT_ID) },
{ USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) },
{ USB_DEVICE(ZEAGLE_VENDOR_ID, ZEAGLE_N2ITION3_PRODUCT_ID) },
{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
@@ -141,6 +145,8 @@
spinlock_t lock;
u8 line_control;
u8 line_status;
+
+ u8 line_settings[7];
};
static int pl2303_vendor_read(__u16 value, __u16 index,
@@ -280,10 +286,6 @@
int baud_floor, baud_ceil;
int k;
- /* The PL2303 is reported to lose bytes if you change
- serial settings even to the same values as before. Thus
- we actually need to filter in this specific case */
-
if (old_termios && !tty_termios_hw_change(&tty->termios, old_termios))
return;
@@ -304,24 +306,22 @@
dev_dbg(&port->dev, "0xa1:0x21:0:0 %d - %x %x %x %x %x %x %x\n", i,
buf[0], buf[1], buf[2], buf[3], buf[4], buf[5], buf[6]);
- if (cflag & CSIZE) {
- switch (cflag & CSIZE) {
- case CS5:
- buf[6] = 5;
- break;
- case CS6:
- buf[6] = 6;
- break;
- case CS7:
- buf[6] = 7;
- break;
- default:
- case CS8:
- buf[6] = 8;
- break;
- }
- dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
+ switch (cflag & CSIZE) {
+ case CS5:
+ buf[6] = 5;
+ break;
+ case CS6:
+ buf[6] = 6;
+ break;
+ case CS7:
+ buf[6] = 7;
+ break;
+ default:
+ case CS8:
+ buf[6] = 8;
+ break;
}
+ dev_dbg(&port->dev, "data bits = %d\n", buf[6]);
/* For reference buf[0]:buf[3] baud rate value */
/* NOTE: Only the values defined in baud_sup are supported !
@@ -424,10 +424,29 @@
dev_dbg(&port->dev, "parity = none\n");
}
- i = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0),
- SET_LINE_REQUEST, SET_LINE_REQUEST_TYPE,
- 0, 0, buf, 7, 100);
- dev_dbg(&port->dev, "0x21:0x20:0:0 %d\n", i);
+ /*
+ * Some PL2303 are known to lose bytes if you change serial settings
+ * even to the same values as before. Thus we actually need to filter
+ * in this specific case.
+ *
+ * Note that the tty_termios_hw_change check above is not sufficient
+ * as a previously requested baud rate may differ from the one
+ * actually used (and stored in old_termios).
+ *
+ * NOTE: No additional locking needed for line_settings as it is
+ * only used in set_termios, which is serialised against itself.
+ */
+ if (!old_termios || memcmp(buf, priv->line_settings, 7)) {
+ i = usb_control_msg(serial->dev,
+ usb_sndctrlpipe(serial->dev, 0),
+ SET_LINE_REQUEST, SET_LINE_REQUEST_TYPE,
+ 0, 0, buf, 7, 100);
+
+ dev_dbg(&port->dev, "0x21:0x20:0:0 %d\n", i);
+
+ if (i == 7)
+ memcpy(priv->line_settings, buf, 7);
+ }
/* change control lines if we are switching to or from B0 */
spin_lock_irqsave(&priv->lock, flags);
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index c38b8c0..71fd9da 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -22,6 +22,7 @@
#define PL2303_PRODUCT_ID_GPRS 0x0609
#define PL2303_PRODUCT_ID_HCR331 0x331a
#define PL2303_PRODUCT_ID_MOTOROLA 0x0307
+#define PL2303_PRODUCT_ID_ZTEK 0xe1f1
#define ATEN_VENDOR_ID 0x0557
#define ATEN_VENDOR_ID2 0x0547
@@ -121,8 +122,11 @@
#define SUPERIAL_VENDOR_ID 0x5372
#define SUPERIAL_PRODUCT_ID 0x2303
-/* Hewlett-Packard LD220-HP POS Pole Display */
+/* Hewlett-Packard POS Pole Displays */
#define HP_VENDOR_ID 0x03f0
+#define HP_LD960_PRODUCT_ID 0x0b39
+#define HP_LCM220_PRODUCT_ID 0x3139
+#define HP_LCM960_PRODUCT_ID 0x3239
#define HP_LD220_PRODUCT_ID 0x3524
/* Cressi Edy (diving computer) PC interface */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index bd794b4..43d93db 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -35,7 +35,13 @@
{DEVICE_G1K(0x04da, 0x250c)}, /* Panasonic Gobi QDL device */
{DEVICE_G1K(0x413c, 0x8172)}, /* Dell Gobi Modem device */
{DEVICE_G1K(0x413c, 0x8171)}, /* Dell Gobi QDL device */
- {DEVICE_G1K(0x1410, 0xa001)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa001)}, /* Novatel/Verizon USB-1000 */
+ {DEVICE_G1K(0x1410, 0xa002)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa003)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa004)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa005)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa006)}, /* Novatel Gobi Modem device */
+ {DEVICE_G1K(0x1410, 0xa007)}, /* Novatel Gobi Modem device */
{DEVICE_G1K(0x1410, 0xa008)}, /* Novatel Gobi QDL device */
{DEVICE_G1K(0x0b05, 0x1776)}, /* Asus Gobi Modem device */
{DEVICE_G1K(0x0b05, 0x1774)}, /* Asus Gobi QDL device */
@@ -130,9 +136,57 @@
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 0)}, /* Sierra Wireless MC7710 Device Management */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 2)}, /* Sierra Wireless MC7710 NMEA */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68a2, 3)}, /* Sierra Wireless MC7710 Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 0)}, /* Sierra Wireless MC73xx Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 2)}, /* Sierra Wireless MC73xx NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x68c0, 3)}, /* Sierra Wireless MC73xx Modem */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)}, /* Sierra Wireless EM7700 Device Management */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)}, /* Sierra Wireless EM7700 NMEA */
{USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)}, /* Sierra Wireless EM7700 Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 0)}, /* Sierra Wireless EM7355 Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 2)}, /* Sierra Wireless EM7355 NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901f, 3)}, /* Sierra Wireless EM7355 Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9040, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 0)}, /* Sierra Wireless MC7305/MC7355 Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 2)}, /* Sierra Wireless MC7305/MC7355 NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9041, 3)}, /* Sierra Wireless MC7305/MC7355 Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)}, /* Netgear AirCard 340U Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)}, /* Netgear AirCard 340U NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)}, /* Netgear AirCard 340U Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9053, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9054, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 0)}, /* Netgear AirCard 341U Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 2)}, /* Netgear AirCard 341U NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9055, 3)}, /* Netgear AirCard 341U Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9056, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9060, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 0)}, /* Sierra Wireless Modem Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 2)}, /* Sierra Wireless Modem NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9061, 3)}, /* Sierra Wireless Modem Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 0)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a2, 3)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 0)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 2)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a3, 3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 0)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 2)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a4, 3)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 0)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 2)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a8, 3)}, /* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card Modem */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 0)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Device Management */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 2)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card NMEA */
+ {USB_DEVICE_INTERFACE_NUMBER(0x413c, 0x81a9, 3)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card Modem */
{ } /* Terminating entry */
};
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 8894665..5aaa2b6 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -58,6 +58,7 @@
spinlock_t susp_lock;
unsigned int suspended:1;
int in_flight;
+ unsigned int open_ports;
};
static int sierra_set_power_state(struct usb_device *udev, __u16 swiState)
@@ -281,17 +282,21 @@
/* Sierra Wireless HSPA Non-Composite Device */
{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x6892, 0xFF, 0xFF, 0xFF)},
{ USB_DEVICE(0x1199, 0x6893) }, /* Sierra Wireless Device */
- { USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless Direct IP modems */
+ /* Sierra Wireless Direct IP modems */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68A3, 0xFF, 0xFF, 0xFF),
+ .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
+ },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF),
.driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
},
/* AT&T Direct IP LTE modems */
{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF),
.driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
},
- { USB_DEVICE(0x0f3d, 0x68A3), /* Airprime/Sierra Wireless Direct IP modems */
+ /* Airprime/Sierra Wireless Direct IP modems */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68A3, 0xFF, 0xFF, 0xFF),
.driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
},
- { USB_DEVICE(0x413C, 0x08133) }, /* Dell Computer Corp. Wireless 5720 VZW Mobile Broadband (EVDO Rev-A) Minicard GPS Port */
{ }
};
@@ -768,6 +773,7 @@
struct usb_serial *serial = port->serial;
struct sierra_port_private *portdata;
struct sierra_intf_private *intfdata = port->serial->private;
+ struct urb *urb;
portdata = usb_get_serial_port_data(port);
@@ -776,7 +782,6 @@
mutex_lock(&serial->disc_mutex);
if (!serial->disconnected) {
- serial->interface->needs_remote_wakeup = 0;
/* odd error handling due to pm counters */
if (!usb_autopm_get_interface(serial->interface))
sierra_send_setup(port);
@@ -787,8 +792,22 @@
mutex_unlock(&serial->disc_mutex);
spin_lock_irq(&intfdata->susp_lock);
portdata->opened = 0;
+ if (--intfdata->open_ports == 0)
+ serial->interface->needs_remote_wakeup = 0;
spin_unlock_irq(&intfdata->susp_lock);
+ for (;;) {
+ urb = usb_get_from_anchor(&portdata->delayed);
+ if (!urb)
+ break;
+ kfree(urb->transfer_buffer);
+ usb_free_urb(urb);
+ usb_autopm_put_interface_async(serial->interface);
+ spin_lock(&portdata->lock);
+ portdata->outstanding_urbs--;
+ spin_unlock(&portdata->lock);
+ }
+
sierra_stop_rx_urbs(port);
for (i = 0; i < portdata->num_in_urbs; i++) {
sierra_release_urb(portdata->in_urbs[i]);
@@ -825,23 +844,29 @@
usb_sndbulkpipe(serial->dev, endpoint) | USB_DIR_IN);
err = sierra_submit_rx_urbs(port, GFP_KERNEL);
- if (err) {
- /* get rid of everything as in close */
- sierra_close(port);
- /* restore balance for autopm */
- if (!serial->disconnected)
- usb_autopm_put_interface(serial->interface);
- return err;
- }
+ if (err)
+ goto err_submit;
+
sierra_send_setup(port);
- serial->interface->needs_remote_wakeup = 1;
spin_lock_irq(&intfdata->susp_lock);
portdata->opened = 1;
+ if (++intfdata->open_ports == 1)
+ serial->interface->needs_remote_wakeup = 1;
spin_unlock_irq(&intfdata->susp_lock);
usb_autopm_put_interface(serial->interface);
return 0;
+
+err_submit:
+ sierra_stop_rx_urbs(port);
+
+ for (i = 0; i < portdata->num_in_urbs; i++) {
+ sierra_release_urb(portdata->in_urbs[i]);
+ portdata->in_urbs[i] = NULL;
+ }
+
+ return err;
}
@@ -937,6 +962,7 @@
struct sierra_port_private *portdata;
portdata = usb_get_serial_port_data(port);
+ usb_set_serial_port_data(port, NULL);
kfree(portdata);
return 0;
@@ -953,6 +979,8 @@
for (i = 0; i < serial->num_ports; ++i) {
port = serial->port[i];
portdata = usb_get_serial_port_data(port);
+ if (!portdata)
+ continue;
sierra_stop_rx_urbs(port);
usb_kill_anchored_urbs(&portdata->active);
}
@@ -995,6 +1023,9 @@
port = serial->port[i];
portdata = usb_get_serial_port_data(port);
+ if (!portdata)
+ continue;
+
while ((urb = usb_get_from_anchor(&portdata->delayed))) {
usb_anchor_urb(urb, &portdata->active);
intfdata->in_flight++;
@@ -1002,8 +1033,12 @@
if (err < 0) {
intfdata->in_flight--;
usb_unanchor_urb(urb);
- usb_scuttle_anchored_urbs(&portdata->delayed);
- break;
+ kfree(urb->transfer_buffer);
+ usb_free_urb(urb);
+ spin_lock(&portdata->lock);
+ portdata->outstanding_urbs--;
+ spin_unlock(&portdata->lock);
+ continue;
}
}
diff --git a/drivers/usb/serial/spcp8x5.c b/drivers/usb/serial/spcp8x5.c
index ddf6c47..1694d4f 100644
--- a/drivers/usb/serial/spcp8x5.c
+++ b/drivers/usb/serial/spcp8x5.c
@@ -346,22 +346,20 @@
}
/* Set Data Length : 00:5bit, 01:6bit, 10:7bit, 11:8bit */
- if (cflag & CSIZE) {
- switch (cflag & CSIZE) {
- case CS5:
- buf[1] |= SET_UART_FORMAT_SIZE_5;
- break;
- case CS6:
- buf[1] |= SET_UART_FORMAT_SIZE_6;
- break;
- case CS7:
- buf[1] |= SET_UART_FORMAT_SIZE_7;
- break;
- default:
- case CS8:
- buf[1] |= SET_UART_FORMAT_SIZE_8;
- break;
- }
+ switch (cflag & CSIZE) {
+ case CS5:
+ buf[1] |= SET_UART_FORMAT_SIZE_5;
+ break;
+ case CS6:
+ buf[1] |= SET_UART_FORMAT_SIZE_6;
+ break;
+ case CS7:
+ buf[1] |= SET_UART_FORMAT_SIZE_7;
+ break;
+ default:
+ case CS8:
+ buf[1] |= SET_UART_FORMAT_SIZE_8;
+ break;
}
/* Set Stop bit2 : 0:1bit 1:2bit */
diff --git a/drivers/usb/serial/ssu100.c b/drivers/usb/serial/ssu100.c
index 5b62dbb..8f5f361 100644
--- a/drivers/usb/serial/ssu100.c
+++ b/drivers/usb/serial/ssu100.c
@@ -495,10 +495,9 @@
if (*tty_flag == TTY_NORMAL)
*tty_flag = TTY_FRAME;
}
- if (lsr & UART_LSR_OE){
+ if (lsr & UART_LSR_OE) {
port->icount.overrun++;
- if (*tty_flag == TTY_NORMAL)
- *tty_flag = TTY_OVERRUN;
+ tty_insert_flip_char(&port->port, 0, TTY_OVERRUN);
}
}
@@ -516,12 +515,8 @@
if ((len >= 4) &&
(packet[0] == 0x1b) && (packet[1] == 0x1b) &&
((packet[2] == 0x00) || (packet[2] == 0x01))) {
- if (packet[2] == 0x00) {
+ if (packet[2] == 0x00)
ssu100_update_lsr(port, packet[3], &flag);
- if (flag == TTY_OVERRUN)
- tty_insert_flip_char(&port->port, 0,
- TTY_OVERRUN);
- }
if (packet[2] == 0x01)
ssu100_update_msr(port, packet[3]);
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index e581c25..4cc84c0 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -203,6 +203,7 @@
{ USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) },
{ USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) },
{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) },
+ { USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) },
{ USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) },
{ }
};
@@ -371,7 +372,7 @@
usb_set_serial_data(serial, tdev);
/* determine device type */
- if (usb_match_id(serial->interface, ti_id_table_3410))
+ if (serial->type == &ti_1port_device)
tdev->td_is_3410 = 1;
dev_dbg(&dev->dev, "%s - device type is %s\n", __func__,
tdev->td_is_3410 ? "3410" : "5052");
@@ -1536,14 +1537,15 @@
char buf[32];
/* try ID specific firmware first, then try generic firmware */
- sprintf(buf, "ti_usb-v%04x-p%04x.fw", dev->descriptor.idVendor,
- dev->descriptor.idProduct);
+ sprintf(buf, "ti_usb-v%04x-p%04x.fw",
+ le16_to_cpu(dev->descriptor.idVendor),
+ le16_to_cpu(dev->descriptor.idProduct));
status = request_firmware(&fw_p, buf, &dev->dev);
if (status != 0) {
buf[0] = '\0';
- if (dev->descriptor.idVendor == MTS_VENDOR_ID) {
- switch (dev->descriptor.idProduct) {
+ if (le16_to_cpu(dev->descriptor.idVendor) == MTS_VENDOR_ID) {
+ switch (le16_to_cpu(dev->descriptor.idProduct)) {
case MTS_CDMA_PRODUCT_ID:
strcpy(buf, "mts_cdma.fw");
break;
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 5f6b1ff..80d689f 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -778,29 +778,39 @@
if (usb_endpoint_is_bulk_in(endpoint)) {
/* we found a bulk in endpoint */
dev_dbg(ddev, "found bulk in on endpoint %d\n", i);
- bulk_in_endpoint[num_bulk_in] = endpoint;
- ++num_bulk_in;
+ if (num_bulk_in < MAX_NUM_PORTS) {
+ bulk_in_endpoint[num_bulk_in] = endpoint;
+ ++num_bulk_in;
+ }
}
if (usb_endpoint_is_bulk_out(endpoint)) {
/* we found a bulk out endpoint */
dev_dbg(ddev, "found bulk out on endpoint %d\n", i);
- bulk_out_endpoint[num_bulk_out] = endpoint;
- ++num_bulk_out;
+ if (num_bulk_out < MAX_NUM_PORTS) {
+ bulk_out_endpoint[num_bulk_out] = endpoint;
+ ++num_bulk_out;
+ }
}
if (usb_endpoint_is_int_in(endpoint)) {
/* we found a interrupt in endpoint */
dev_dbg(ddev, "found interrupt in on endpoint %d\n", i);
- interrupt_in_endpoint[num_interrupt_in] = endpoint;
- ++num_interrupt_in;
+ if (num_interrupt_in < MAX_NUM_PORTS) {
+ interrupt_in_endpoint[num_interrupt_in] =
+ endpoint;
+ ++num_interrupt_in;
+ }
}
if (usb_endpoint_is_int_out(endpoint)) {
/* we found an interrupt out endpoint */
dev_dbg(ddev, "found interrupt out on endpoint %d\n", i);
- interrupt_out_endpoint[num_interrupt_out] = endpoint;
- ++num_interrupt_out;
+ if (num_interrupt_out < MAX_NUM_PORTS) {
+ interrupt_out_endpoint[num_interrupt_out] =
+ endpoint;
+ ++num_interrupt_out;
+ }
}
}
@@ -823,8 +833,10 @@
if (usb_endpoint_is_int_in(endpoint)) {
/* we found a interrupt in endpoint */
dev_dbg(ddev, "found interrupt in for Prolific device on separate interface\n");
- interrupt_in_endpoint[num_interrupt_in] = endpoint;
- ++num_interrupt_in;
+ if (num_interrupt_in < MAX_NUM_PORTS) {
+ interrupt_in_endpoint[num_interrupt_in] = endpoint;
+ ++num_interrupt_in;
+ }
}
}
}
@@ -864,6 +876,11 @@
num_ports = type->num_ports;
}
+ if (num_ports > MAX_NUM_PORTS) {
+ dev_warn(ddev, "too many ports requested: %d\n", num_ports);
+ num_ports = MAX_NUM_PORTS;
+ }
+
serial->num_ports = num_ports;
serial->num_bulk_in = num_bulk_in;
serial->num_bulk_out = num_bulk_out;
@@ -1367,10 +1384,12 @@
static void usb_serial_deregister(struct usb_serial_driver *device)
{
pr_info("USB Serial deregistering driver %s\n", device->description);
+
mutex_lock(&table_lock);
list_del(&device->driver_list);
- usb_serial_bus_deregister(device);
mutex_unlock(&table_lock);
+
+ usb_serial_bus_deregister(device);
}
/**
diff --git a/drivers/usb/serial/usb_wwan.c b/drivers/usb/serial/usb_wwan.c
index ece326e..36f6b6a 100644
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -228,8 +228,10 @@
usb_pipeendpoint(this_urb->pipe), i);
err = usb_autopm_get_interface_async(port->serial->interface);
- if (err < 0)
+ if (err < 0) {
+ clear_bit(i, &portdata->out_busy);
break;
+ }
/* send the data */
memcpy(this_urb->transfer_buffer, buf, todo);
@@ -291,18 +293,18 @@
tty_flip_buffer_push(&port->port);
} else
dev_dbg(dev, "%s: empty read urb received\n", __func__);
-
- /* Resubmit urb so we continue receiving */
- err = usb_submit_urb(urb, GFP_ATOMIC);
- if (err) {
- if (err != -EPERM) {
- dev_err(dev, "%s: resubmit read urb failed. (%d)\n", __func__, err);
- /* busy also in error unless we are killed */
- usb_mark_last_busy(port->serial->dev);
- }
- } else {
+ }
+ /* Resubmit urb so we continue receiving */
+ err = usb_submit_urb(urb, GFP_ATOMIC);
+ if (err) {
+ if (err != -EPERM) {
+ dev_err(dev, "%s: resubmit read urb failed. (%d)\n",
+ __func__, err);
+ /* busy also in error unless we are killed */
usb_mark_last_busy(port->serial->dev);
}
+ } else {
+ usb_mark_last_busy(port->serial->dev);
}
}
@@ -386,6 +388,14 @@
portdata = usb_get_serial_port_data(port);
intfdata = serial->private;
+ if (port->interrupt_in_urb) {
+ err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
+ if (err) {
+ dev_dbg(&port->dev, "%s: submit int urb failed: %d\n",
+ __func__, err);
+ }
+ }
+
/* Start reading from the IN endpoint */
for (i = 0; i < N_IN_URB; i++) {
urb = portdata->in_urbs[i];
@@ -412,12 +422,26 @@
}
EXPORT_SYMBOL(usb_wwan_open);
+static void unbusy_queued_urb(struct urb *urb,
+ struct usb_wwan_port_private *portdata)
+{
+ int i;
+
+ for (i = 0; i < N_OUT_URB; i++) {
+ if (urb == portdata->out_urbs[i]) {
+ clear_bit(i, &portdata->out_busy);
+ break;
+ }
+ }
+}
+
void usb_wwan_close(struct usb_serial_port *port)
{
int i;
struct usb_serial *serial = port->serial;
struct usb_wwan_port_private *portdata;
struct usb_wwan_intf_private *intfdata = port->serial->private;
+ struct urb *urb;
portdata = usb_get_serial_port_data(port);
@@ -426,10 +450,19 @@
portdata->opened = 0;
spin_unlock_irq(&intfdata->susp_lock);
+ for (;;) {
+ urb = usb_get_from_anchor(&portdata->delayed);
+ if (!urb)
+ break;
+ unbusy_queued_urb(urb, portdata);
+ usb_autopm_put_interface_async(serial->interface);
+ }
+
for (i = 0; i < N_IN_URB; i++)
usb_kill_urb(portdata->in_urbs[i]);
for (i = 0; i < N_OUT_URB; i++)
usb_kill_urb(portdata->out_urbs[i]);
+ usb_kill_urb(port->interrupt_in_urb);
/* balancing - important as an error cannot be handled*/
usb_autopm_get_interface_no_resume(serial->interface);
@@ -467,9 +500,11 @@
struct usb_wwan_port_private *portdata;
struct urb *urb;
u8 *buffer;
- int err;
int i;
+ if (!port->bulk_in_size || !port->bulk_out_size)
+ return -ENODEV;
+
portdata = kzalloc(sizeof(*portdata), GFP_KERNEL);
if (!portdata)
return -ENOMEM;
@@ -477,9 +512,6 @@
init_usb_anchor(&portdata->delayed);
for (i = 0; i < N_IN_URB; i++) {
- if (!port->bulk_in_size)
- break;
-
buffer = (u8 *)__get_free_page(GFP_KERNEL);
if (!buffer)
goto bail_out_error;
@@ -493,9 +525,6 @@
}
for (i = 0; i < N_OUT_URB; i++) {
- if (!port->bulk_out_size)
- break;
-
buffer = kmalloc(OUT_BUFLEN, GFP_KERNEL);
if (!buffer)
goto bail_out_error2;
@@ -510,13 +539,6 @@
usb_set_serial_port_data(port, portdata);
- if (port->interrupt_in_urb) {
- err = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL);
- if (err)
- dev_dbg(&port->dev, "%s: submit irq_in urb failed %d\n",
- __func__, err);
- }
-
return 0;
bail_out_error2:
@@ -584,44 +606,29 @@
int usb_wwan_suspend(struct usb_serial *serial, pm_message_t message)
{
struct usb_wwan_intf_private *intfdata = serial->private;
- int b;
-
- if (PMSG_IS_AUTO(message)) {
- spin_lock_irq(&intfdata->susp_lock);
- b = intfdata->in_flight;
- spin_unlock_irq(&intfdata->susp_lock);
-
- if (b)
- return -EBUSY;
- }
spin_lock_irq(&intfdata->susp_lock);
+ if (PMSG_IS_AUTO(message)) {
+ if (intfdata->in_flight) {
+ spin_unlock_irq(&intfdata->susp_lock);
+ return -EBUSY;
+ }
+ }
intfdata->suspended = 1;
spin_unlock_irq(&intfdata->susp_lock);
+
stop_read_write_urbs(serial);
return 0;
}
EXPORT_SYMBOL(usb_wwan_suspend);
-static void unbusy_queued_urb(struct urb *urb, struct usb_wwan_port_private *portdata)
-{
- int i;
-
- for (i = 0; i < N_OUT_URB; i++) {
- if (urb == portdata->out_urbs[i]) {
- clear_bit(i, &portdata->out_busy);
- break;
- }
- }
-}
-
-static void play_delayed(struct usb_serial_port *port)
+static int play_delayed(struct usb_serial_port *port)
{
struct usb_wwan_intf_private *data;
struct usb_wwan_port_private *portdata;
struct urb *urb;
- int err;
+ int err = 0;
portdata = usb_get_serial_port_data(port);
data = port->serial->private;
@@ -638,6 +645,8 @@
break;
}
}
+
+ return err;
}
int usb_wwan_resume(struct usb_serial *serial)
@@ -647,54 +656,51 @@
struct usb_wwan_intf_private *intfdata = serial->private;
struct usb_wwan_port_private *portdata;
struct urb *urb;
- int err = 0;
+ int err;
+ int err_count = 0;
- /* get the interrupt URBs resubmitted unconditionally */
- for (i = 0; i < serial->num_ports; i++) {
- port = serial->port[i];
- if (!port->interrupt_in_urb) {
- dev_dbg(&port->dev, "%s: No interrupt URB for port\n", __func__);
- continue;
- }
- err = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
- dev_dbg(&port->dev, "Submitted interrupt URB for port (result %d)\n", err);
- if (err < 0) {
- dev_err(&port->dev, "%s: Error %d for interrupt URB\n",
- __func__, err);
- goto err_out;
- }
- }
-
+ spin_lock_irq(&intfdata->susp_lock);
for (i = 0; i < serial->num_ports; i++) {
/* walk all ports */
port = serial->port[i];
portdata = usb_get_serial_port_data(port);
/* skip closed ports */
- spin_lock_irq(&intfdata->susp_lock);
- if (!portdata || !portdata->opened) {
- spin_unlock_irq(&intfdata->susp_lock);
+ if (!portdata || !portdata->opened)
continue;
+
+ if (port->interrupt_in_urb) {
+ err = usb_submit_urb(port->interrupt_in_urb,
+ GFP_ATOMIC);
+ if (err) {
+ dev_err(&port->dev,
+ "%s: submit int urb failed: %d\n",
+ __func__, err);
+ err_count++;
+ }
}
+ err = play_delayed(port);
+ if (err)
+ err_count++;
+
for (j = 0; j < N_IN_URB; j++) {
urb = portdata->in_urbs[j];
err = usb_submit_urb(urb, GFP_ATOMIC);
if (err < 0) {
dev_err(&port->dev, "%s: Error %d for bulk URB %d\n",
__func__, err, i);
- spin_unlock_irq(&intfdata->susp_lock);
- goto err_out;
+ err_count++;
}
}
- play_delayed(port);
- spin_unlock_irq(&intfdata->susp_lock);
}
- spin_lock_irq(&intfdata->susp_lock);
intfdata->suspended = 0;
spin_unlock_irq(&intfdata->susp_lock);
-err_out:
- return err;
+
+ if (err_count)
+ return -EIO;
+
+ return 0;
}
EXPORT_SYMBOL(usb_wwan_resume);
#endif
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 347caad..5e3dd9f 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -521,6 +521,10 @@
dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__);
return;
}
+ if (!urb->actual_length) {
+ dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__);
+ return;
+ }
if (status) {
dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status);
if (status != -ENOENT)
@@ -541,7 +545,8 @@
/* These are unsolicited reports from the firmware, hence no
waiting command to wakeup */
dev_dbg(&urb->dev->dev, "%s - event received\n", __func__);
- } else if (data[0] == WHITEHEAT_GET_DTR_RTS) {
+ } else if ((data[0] == WHITEHEAT_GET_DTR_RTS) &&
+ (urb->actual_length - 1 <= sizeof(command_info->result_buffer))) {
memcpy(command_info->result_buffer, &data[1],
urb->actual_length - 1);
command_info->command_finished = WHITEHEAT_CMD_COMPLETE;
diff --git a/drivers/usb/serial/zte_ev.c b/drivers/usb/serial/zte_ev.c
index fca4c75..d6a3fbd 100644
--- a/drivers/usb/serial/zte_ev.c
+++ b/drivers/usb/serial/zte_ev.c
@@ -273,29 +273,16 @@
}
static const struct usb_device_id id_table[] = {
- /* AC8710, AC8710T */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffff, 0xff, 0xff, 0xff) },
- /* AC8700 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfffe, 0xff, 0xff, 0xff) },
- /* MG880 */
- { USB_DEVICE(0x19d2, 0xfffd) },
- { USB_DEVICE(0x19d2, 0xfffc) },
- { USB_DEVICE(0x19d2, 0xfffb) },
- /* AC2726, AC8710_V3 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xfff1, 0xff, 0xff, 0xff) },
+ { USB_DEVICE(0x19d2, 0xffec) },
+ { USB_DEVICE(0x19d2, 0xffee) },
{ USB_DEVICE(0x19d2, 0xfff6) },
{ USB_DEVICE(0x19d2, 0xfff7) },
{ USB_DEVICE(0x19d2, 0xfff8) },
{ USB_DEVICE(0x19d2, 0xfff9) },
- { USB_DEVICE(0x19d2, 0xffee) },
- /* AC2716, MC2716 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffed, 0xff, 0xff, 0xff) },
- /* AD3812 */
- { USB_DEVICE_AND_INTERFACE_INFO(0x19d2, 0xffeb, 0xff, 0xff, 0xff) },
- { USB_DEVICE(0x19d2, 0xffec) },
- { USB_DEVICE(0x05C6, 0x3197) },
- { USB_DEVICE(0x05C6, 0x6000) },
- { USB_DEVICE(0x05C6, 0x9008) },
+ { USB_DEVICE(0x19d2, 0xfffb) },
+ { USB_DEVICE(0x19d2, 0xfffc) },
+ /* MG880 */
+ { USB_DEVICE(0x19d2, 0xfffd) },
{ },
};
MODULE_DEVICE_TABLE(usb, id_table);
diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig
index 8470e1b..1dd0604 100644
--- a/drivers/usb/storage/Kconfig
+++ b/drivers/usb/storage/Kconfig
@@ -18,7 +18,9 @@
This option depends on 'SCSI' support being enabled, but you
probably also need 'SCSI device support: SCSI disk support'
- (BLK_DEV_SD) for most USB storage devices.
+ (BLK_DEV_SD) for most USB storage devices. Some devices also
+ will require 'Probe all LUNs on each SCSI device'
+ (SCSI_MULTI_LUN).
To compile this driver as a module, choose M here: the
module will be called usb-storage.
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 92b05d9..bb7bf19 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -78,6 +78,8 @@
static int slave_alloc (struct scsi_device *sdev)
{
+ struct us_data *us = host_to_us(sdev->host);
+
/*
* Set the INQUIRY transfer length to 36. We don't use any of
* the extra data and many devices choke if asked for more or
@@ -102,6 +104,10 @@
*/
blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
+ /* Tell the SCSI layer if we know there is more than one LUN */
+ if (us->protocol == USB_PR_BULK && us->max_lun > 0)
+ sdev->sdev_bflags |= BLIST_FORCELUN;
+
return 0;
}
@@ -211,8 +217,11 @@
/*
* Many devices do not respond properly to READ_CAPACITY_16.
* Tell the SCSI layer to try READ_CAPACITY_10 first.
+ * However some USB 3.0 drive enclosures return capacity
+ * modulo 2TB. Those must use READ_CAPACITY_16
*/
- sdev->try_rc_10_first = 1;
+ if (!(us->fflags & US_FL_NEEDS_CAP16))
+ sdev->try_rc_10_first = 1;
/* assume SPC3 or latter devices support sense size > 18 */
if (sdev->scsi_level > SCSI_SPC_2)
diff --git a/drivers/usb/storage/shuttle_usbat.c b/drivers/usb/storage/shuttle_usbat.c
index 4ef2a80..008d805 100644
--- a/drivers/usb/storage/shuttle_usbat.c
+++ b/drivers/usb/storage/shuttle_usbat.c
@@ -1851,7 +1851,7 @@
us->transport_name = "Shuttle USBAT";
us->transport = usbat_flash_transport;
us->transport_reset = usb_stor_CB_reset;
- us->max_lun = 1;
+ us->max_lun = 0;
result = usb_stor_probe2(us);
return result;
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 22c7d43..b1d815e 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -1118,6 +1118,31 @@
*/
if (result == USB_STOR_XFER_LONG)
fake_sense = 1;
+
+ /*
+ * Sometimes a device will mistakenly skip the data phase
+ * and go directly to the status phase without sending a
+ * zero-length packet. If we get a 13-byte response here,
+ * check whether it really is a CSW.
+ */
+ if (result == USB_STOR_XFER_SHORT &&
+ srb->sc_data_direction == DMA_FROM_DEVICE &&
+ transfer_length - scsi_get_resid(srb) ==
+ US_BULK_CS_WRAP_LEN) {
+ struct scatterlist *sg = NULL;
+ unsigned int offset = 0;
+
+ if (usb_stor_access_xfer_buf((unsigned char *) bcs,
+ US_BULK_CS_WRAP_LEN, srb, &sg,
+ &offset, FROM_XFER_BUF) ==
+ US_BULK_CS_WRAP_LEN &&
+ bcs->Signature ==
+ cpu_to_le32(US_BULK_CS_SIGN)) {
+ usb_stor_dbg(us, "Device skipped data phase\n");
+ scsi_set_resid(srb, transfer_length);
+ goto skipped_data_phase;
+ }
+ }
}
/* See flow chart on pg 15 of the Bulk Only Transport spec for
@@ -1153,6 +1178,7 @@
if (result != USB_STOR_XFER_GOOD)
return USB_STOR_TRANSPORT_ERROR;
+ skipped_data_phase:
/* check bulk status */
residue = le32_to_cpu(bcs->Residue);
usb_stor_dbg(us, "Bulk Status S 0x%x T 0x%x R %u Stat 0x%x\n",
diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h
index 65a6a75..82e8ed0 100644
--- a/drivers/usb/storage/unusual_cypress.h
+++ b/drivers/usb/storage/unusual_cypress.h
@@ -31,7 +31,7 @@
"Cypress ISD-300LP",
USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
-UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x0219,
+UNUSUAL_DEV( 0x14cd, 0x6116, 0x0160, 0x0160,
"Super Top",
"USB 2.0 SATA BRIDGE",
USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0),
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 179933528..7f62530 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -101,6 +101,12 @@
"PhotoSmart R707",
USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY),
+UNUSUAL_DEV( 0x03f3, 0x0001, 0x0000, 0x9999,
+ "Adaptec",
+ "USBConnect 2000",
+ USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+ US_FL_SCM_MULT_TARG ),
+
/* Reported by Sebastian Kapfer <sebastian_kapfer@gmx.net>
* and Olaf Hering <olh@suse.de> (different bcd's, same vendor/product)
* for USB floppies that need the SINGLE_LUN enforcement.
@@ -234,6 +240,27 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_MAX_SECTORS_64 ),
+/* Reported by Daniele Forsi <dforsi@gmail.com> */
+UNUSUAL_DEV( 0x0421, 0x04b9, 0x0350, 0x0350,
+ "Nokia",
+ "5300",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_MAX_SECTORS_64 ),
+
+/* Patch submitted by Victor A. Santos <victoraur.santos@gmail.com> */
+UNUSUAL_DEV( 0x0421, 0x05af, 0x0742, 0x0742,
+ "Nokia",
+ "305",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_MAX_SECTORS_64),
+
+/* Patch submitted by Mikhail Zolotaryov <lebon@lebon.org.ua> */
+UNUSUAL_DEV( 0x0421, 0x06aa, 0x1110, 0x1110,
+ "Nokia",
+ "502",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_MAX_SECTORS_64 ),
+
#ifdef NO_SDDR09
UNUSUAL_DEV( 0x0436, 0x0005, 0x0100, 0x0100,
"Microtech",
@@ -665,6 +692,13 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_FIX_INQUIRY ),
+/* Submitted by Ren Bigcren <bigcren.ren@sonymobile.com> */
+UNUSUAL_DEV( 0x054c, 0x02a5, 0x0100, 0x0100,
+ "Sony Corp.",
+ "MicroVault Flash Drive",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NO_READ_CAPACITY_16 ),
+
/* floppy reports multiple luns */
UNUSUAL_DEV( 0x055d, 0x2020, 0x0000, 0x0210,
"SAMSUNG",
@@ -713,6 +747,12 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_SINGLE_LUN ),
+UNUSUAL_DEV( 0x059b, 0x0040, 0x0100, 0x0100,
+ "Iomega",
+ "Jaz USB Adapter",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_SINGLE_LUN ),
+
/* Reported by <Hendryk.Pfeiffer@gmx.de> */
UNUSUAL_DEV( 0x059f, 0x0643, 0x0000, 0x0000,
"LaCie",
@@ -1085,6 +1125,18 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NOT_LOCKABLE),
+UNUSUAL_DEV( 0x085a, 0x0026, 0x0100, 0x0133,
+ "Xircom",
+ "PortGear USB-SCSI (Mac USB Dock)",
+ USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+ US_FL_SCM_MULT_TARG ),
+
+UNUSUAL_DEV( 0x085a, 0x0028, 0x0100, 0x0133,
+ "Xircom",
+ "PortGear USB to SCSI Converter",
+ USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+ US_FL_SCM_MULT_TARG ),
+
/* Submitted by Jan De Luyck <lkml@kcore.org> */
UNUSUAL_DEV( 0x08bd, 0x1100, 0x0000, 0x0000,
"CITIZEN",
@@ -1441,6 +1493,13 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_FIX_CAPACITY ),
+/* Reported by Moritz Moeller-Herrmann <moritz-kernel@moeller-herrmann.de> */
+UNUSUAL_DEV( 0x0fca, 0x8004, 0x0201, 0x0201,
+ "Research In Motion",
+ "BlackBerry Bold 9000",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_MAX_SECTORS_64 ),
+
/* Reported by Michael Stattmann <michael@stattmann.com> */
UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000,
"Sony Ericsson",
@@ -1910,6 +1969,14 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
+/* Entrega Technologies U1-SC25 (later Xircom PortGear PGSCSI)
+ * and Mac USB Dock USB-SCSI */
+UNUSUAL_DEV( 0x1645, 0x0007, 0x0100, 0x0133,
+ "Entrega Technologies",
+ "USB to SCSI Converter",
+ USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+ US_FL_SCM_MULT_TARG ),
+
/* Reported by Robert Schedel <r.schedel@yahoo.de>
* Note: this is a 'super top' device like the above 14cd/6600 device */
UNUSUAL_DEV( 0x1652, 0x6600, 0x0201, 0x0201,
@@ -1918,6 +1985,13 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_IGNORE_RESIDUE ),
+/* Reported by Oliver Neukum <oneukum@suse.com> */
+UNUSUAL_DEV( 0x174c, 0x55aa, 0x0100, 0x0100,
+ "ASMedia",
+ "AS2105",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_NEEDS_CAP16),
+
/* Reported by Jesse Feddema <jdfeddema@gmail.com> */
UNUSUAL_DEV( 0x177f, 0x0400, 0x0000, 0x0000,
"Yarvik",
@@ -1925,6 +1999,12 @@
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_BULK_IGNORE_TAG | US_FL_MAX_SECTORS_64 ),
+UNUSUAL_DEV( 0x1822, 0x0001, 0x0000, 0x9999,
+ "Ariston Technologies",
+ "iConnect USB to SCSI adapter",
+ USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init,
+ US_FL_SCM_MULT_TARG ),
+
/* Reported by Hans de Goede <hdegoede@redhat.com>
* These Appotech controllers are found in Picture Frames, they provide a
* (buggy) emulation of a cdrom drive which contains the windows software
diff --git a/drivers/usb/wusbcore/wa-xfer.c b/drivers/usb/wusbcore/wa-xfer.c
index 6ef94bc..028fc83 100644
--- a/drivers/usb/wusbcore/wa-xfer.c
+++ b/drivers/usb/wusbcore/wa-xfer.c
@@ -1110,6 +1110,12 @@
}
spin_lock_irqsave(&xfer->lock, flags);
rpipe = xfer->ep->hcpriv;
+ if (rpipe == NULL) {
+ pr_debug("%s: xfer id 0x%08X has no RPIPE. %s",
+ __func__, wa_xfer_id(xfer),
+ "Probably already aborted.\n" );
+ goto out_unlock;
+ }
/* Check the delayed list -> if there, release and complete */
spin_lock_irqsave(&wa->xfer_list_lock, flags2);
if (!list_empty(&xfer->list_node) && xfer->seg == NULL)
@@ -1493,8 +1499,7 @@
break;
}
usb_status = xfer_result->bTransferStatus & 0x3f;
- if (usb_status == WA_XFER_STATUS_ABORTED
- || usb_status == WA_XFER_STATUS_NOT_FOUND)
+ if (usb_status == WA_XFER_STATUS_NOT_FOUND)
/* taken care of already */
break;
xfer_id = xfer_result->dwTransferID;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index ac37254..dc55bc2 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -519,13 +519,11 @@
static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
- u8 type;
struct vfio_pci_device *vdev;
struct iommu_group *group;
int ret;
- pci_read_config_byte(pdev, PCI_HEADER_TYPE, &type);
- if ((type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL)
+ if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
return -EINVAL;
group = iommu_group_get(&pdev->dev);
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 6f3fbc4..22080eb 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -138,12 +138,12 @@
if (pfn_valid(pfn)) {
bool reserved;
struct page *tail = pfn_to_page(pfn);
- struct page *head = compound_trans_head(tail);
+ struct page *head = compound_head(tail);
reserved = !!(PageReserved(head));
if (head != tail) {
/*
* "head" is not a dangling pointer
- * (compound_trans_head takes care of that)
+ * (compound_head takes care of that)
* but the hugepage may have been split
* from under us (and we may not hold a
* reference count on the head page so it can
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f80d3dd..c7fdabd 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -150,6 +150,11 @@
{
kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal);
wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+}
+
+static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
+{
+ vhost_net_ubuf_put_and_wait(ubufs);
kfree(ubufs);
}
@@ -302,6 +307,11 @@
struct vhost_virtqueue *vq = ubufs->vq;
int cnt = atomic_read(&ubufs->kref.refcount);
+ /* set len to mark this desc buffers done DMA */
+ vq->heads[ubuf->desc].len = success ?
+ VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
+ vhost_net_ubuf_put(ubufs);
+
/*
* Trigger polling thread if guest stopped submitting new buffers:
* in this case, the refcount after decrement will eventually reach 1
@@ -312,10 +322,6 @@
*/
if (cnt <= 2 || !(cnt % 16))
vhost_poll_queue(&vq->poll);
- /* set len to mark this desc buffers done DMA */
- vq->heads[ubuf->desc].len = success ?
- VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
- vhost_net_ubuf_put(ubufs);
}
/* Expects to be always run from workqueue - which acts as
@@ -507,9 +513,13 @@
r = -ENOBUFS;
goto err;
}
- d = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+ r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
+ if (unlikely(r < 0))
+ goto err;
+
+ d = r;
if (d == vq->num) {
r = 0;
goto err;
@@ -534,6 +544,12 @@
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
+
+ /* Detect overrun */
+ if (unlikely(datalen > 0)) {
+ r = UIO_MAXIOV + 1;
+ goto err;
+ }
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
@@ -589,6 +605,14 @@
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
+ /* On overrun, truncate and discard */
+ if (unlikely(headcount > UIO_MAXIOV)) {
+ msg.msg_iovlen = 1;
+ err = sock->ops->recvmsg(NULL, sock, &msg,
+ 1, MSG_DONTWAIT | MSG_TRUNC);
+ pr_debug("Discarded rx packet: len %zd\n", sock_len);
+ continue;
+ }
/* OK, now we need to know about added descriptors. */
if (!headcount) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@@ -948,7 +972,7 @@
mutex_unlock(&vq->mutex);
if (oldubufs) {
- vhost_net_ubuf_put_and_wait(oldubufs);
+ vhost_net_ubuf_put_wait_and_free(oldubufs);
mutex_lock(&vq->mutex);
vhost_zerocopy_signal_used(n, vq);
mutex_unlock(&vq->mutex);
@@ -966,7 +990,7 @@
rcu_assign_pointer(vq->private_data, oldsock);
vhost_net_enable_vq(n, vq);
if (ubufs)
- vhost_net_ubuf_put_and_wait(ubufs);
+ vhost_net_ubuf_put_wait_and_free(ubufs);
err_ubufs:
fput(sock->file);
err_vq:
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 7014202..fb97bc0 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -820,6 +820,23 @@
return 0;
}
+static int vhost_scsi_to_tcm_attr(int attr)
+{
+ switch (attr) {
+ case VIRTIO_SCSI_S_SIMPLE:
+ return MSG_SIMPLE_TAG;
+ case VIRTIO_SCSI_S_ORDERED:
+ return MSG_ORDERED_TAG;
+ case VIRTIO_SCSI_S_HEAD:
+ return MSG_HEAD_TAG;
+ case VIRTIO_SCSI_S_ACA:
+ return MSG_ACA_TAG;
+ default:
+ break;
+ }
+ return MSG_SIMPLE_TAG;
+}
+
static void tcm_vhost_submission_work(struct work_struct *work)
{
struct tcm_vhost_cmd *tv_cmd =
@@ -846,9 +863,9 @@
rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess,
tv_cmd->tvc_cdb, &tv_cmd->tvc_sense_buf[0],
tv_cmd->tvc_lun, tv_cmd->tvc_exp_data_len,
- tv_cmd->tvc_task_attr, tv_cmd->tvc_data_direction,
- 0, sg_ptr, tv_cmd->tvc_sgl_count,
- sg_bidi_ptr, sg_no_bidi);
+ vhost_scsi_to_tcm_attr(tv_cmd->tvc_task_attr),
+ tv_cmd->tvc_data_direction, 0, sg_ptr,
+ tv_cmd->tvc_sgl_count, sg_bidi_ptr, sg_no_bidi);
if (rc < 0) {
transport_send_check_condition_and_sense(se_cmd,
TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
@@ -1017,7 +1034,7 @@
if (data_direction != DMA_NONE) {
ret = vhost_scsi_map_iov_to_sgl(tv_cmd,
&vq->iov[data_first], data_num,
- data_direction == DMA_TO_DEVICE);
+ data_direction == DMA_FROM_DEVICE);
if (unlikely(ret)) {
vq_err(vq, "Failed to map iov to sgl\n");
goto err_free;
@@ -1150,6 +1167,7 @@
struct vhost_scsi *vs,
struct vhost_scsi_target *t)
{
+ struct se_portal_group *se_tpg;
struct tcm_vhost_tport *tv_tport;
struct tcm_vhost_tpg *tv_tpg;
struct tcm_vhost_tpg **vs_tpg;
@@ -1197,6 +1215,21 @@
ret = -EEXIST;
goto out;
}
+ /*
+ * In order to ensure individual vhost-scsi configfs
+ * groups cannot be removed while in use by vhost ioctl,
+ * go ahead and take an explicit se_tpg->tpg_group.cg_item
+ * dependency now.
+ */
+ se_tpg = &tv_tpg->se_tpg;
+ ret = configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys,
+ &se_tpg->tpg_group.cg_item);
+ if (ret) {
+ pr_warn("configfs_depend_item() failed: %d\n", ret);
+ kfree(vs_tpg);
+ mutex_unlock(&tv_tpg->tv_tpg_mutex);
+ goto out;
+ }
tv_tpg->tv_tpg_vhost_count++;
tv_tpg->vhost_scsi = vs;
vs_tpg[tv_tpg->tport_tpgt] = tv_tpg;
@@ -1240,6 +1273,7 @@
struct vhost_scsi *vs,
struct vhost_scsi_target *t)
{
+ struct se_portal_group *se_tpg;
struct tcm_vhost_tport *tv_tport;
struct tcm_vhost_tpg *tv_tpg;
struct vhost_virtqueue *vq;
@@ -1288,6 +1322,13 @@
vs->vs_tpg[target] = NULL;
match = true;
mutex_unlock(&tv_tpg->tv_tpg_mutex);
+ /*
+ * Release se_tpg->tpg_group.cg_item configfs dependency now
+ * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur.
+ */
+ se_tpg = &tv_tpg->se_tpg;
+ configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys,
+ &se_tpg->tpg_group.cg_item);
}
if (match) {
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 2e937bd..29a5121 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -39,6 +39,11 @@
config HDMI
bool
+config VEXPRESS_DVI_CONTROL
+ bool "Versatile Express DVI control"
+ depends on FB && VEXPRESS_CONFIG
+ default y
+
menuconfig FB
tristate "Support for frame buffer devices"
---help---
@@ -312,7 +317,8 @@
config FB_ARMCLCD
tristate "ARM PrimeCell PL110 support"
- depends on FB && ARM && ARM_AMBA
+ depends on ARM || ARM64 || COMPILE_TEST
+ depends on FB && ARM_AMBA
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
@@ -326,6 +332,21 @@
here and read <file:Documentation/kbuild/modules.txt>. The module
will be called amba-clcd.
+config FB_ARMHDLCD
+ tristate "ARM High Definition LCD support"
+ depends on FB && ARM
+ select FB_CFB_FILLRECT
+ select FB_CFB_COPYAREA
+ select FB_CFB_IMAGEBLIT
+ help
+ This framebuffer device driver is for the ARM High Definition
+ Colour LCD controller.
+
+ If you want to compile this as a module (=code which can be
+ inserted into and removed from the running kernel), say M
+ here and read <file:Documentation/kbuild/modules.txt>. The module
+ will be called arm-hdlcd.
+
config FB_ACORN
bool "Acorn VIDC support"
depends on (FB = y) && ARM && ARCH_ACORN
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index e8bae8d..33869ee 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -99,6 +99,7 @@
obj-$(CONFIG_FB_PVR2) += pvr2fb.o
obj-$(CONFIG_FB_VOODOO1) += sstfb.o
obj-$(CONFIG_FB_ARMCLCD) += amba-clcd.o
+obj-$(CONFIG_FB_ARMHDLCD) += arm-hdlcd.o
obj-$(CONFIG_FB_GOLDFISH) += goldfishfb.o
obj-$(CONFIG_FB_68328) += 68328fb.o
obj-$(CONFIG_FB_GBE) += gbefb.o
@@ -177,3 +178,6 @@
ifeq ($(CONFIG_OF),y)
obj-$(CONFIG_VIDEOMODE_HELPERS) += of_display_timing.o of_videomode.o
endif
+
+# platform specific output drivers
+obj-$(CONFIG_VEXPRESS_DVI_CONTROL) += vexpress-dvi.o
diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c
index 0a2cce7..dba653f 100644
--- a/drivers/video/amba-clcd.c
+++ b/drivers/video/amba-clcd.c
@@ -16,7 +16,10 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/memblock.h>
#include <linux/mm.h>
+#include <linux/of.h>
#include <linux/fb.h>
#include <linux/init.h>
#include <linux/ioport.h>
@@ -30,8 +33,20 @@
#define to_clcd(info) container_of(info, struct clcd_fb, fb)
+#ifdef CONFIG_ARM
+#define clcdfb_dma_alloc dma_alloc_writecombine
+#define clcdfb_dma_free dma_free_writecombine
+#define clcdfb_dma_mmap dma_mmap_writecombine
+#else
+#define clcdfb_dma_alloc dma_alloc_coherent
+#define clcdfb_dma_free dma_free_coherent
+#define clcdfb_dma_mmap dma_mmap_coherent
+#endif
+
/* This is limited to 16 characters when displayed by X startup */
static const char *clcd_name = "CLCD FB";
+static char *def_mode;
+module_param_named(mode, def_mode, charp, 0);
/*
* Unfortunately, the enable/disable functions may be called either from
@@ -392,6 +407,44 @@
return 0;
}
+int clcdfb_mmap_dma(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+ return clcdfb_dma_mmap(&fb->dev->dev, vma,
+ fb->fb.screen_base,
+ fb->fb.fix.smem_start,
+ fb->fb.fix.smem_len);
+}
+
+int clcdfb_mmap_io(struct clcd_fb *fb, struct vm_area_struct *vma)
+{
+ unsigned long user_count, count, pfn, off;
+
+ user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ count = PAGE_ALIGN(fb->fb.fix.smem_len) >> PAGE_SHIFT;
+ pfn = fb->fb.fix.smem_start >> PAGE_SHIFT;
+ off = vma->vm_pgoff;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ if (off < count && user_count <= (count - off))
+ return remap_pfn_range(vma, vma->vm_start, pfn + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+
+ return -ENXIO;
+}
+
+void clcdfb_remove_dma(struct clcd_fb *fb)
+{
+ clcdfb_dma_free(&fb->dev->dev, fb->fb.fix.smem_len,
+ fb->fb.screen_base, fb->fb.fix.smem_start);
+}
+
+void clcdfb_remove_io(struct clcd_fb *fb)
+{
+ iounmap(fb->fb.screen_base);
+}
+
static int clcdfb_mmap(struct fb_info *info,
struct vm_area_struct *vma)
{
@@ -542,14 +595,247 @@
return ret;
}
+struct string_lookup {
+ const char *string;
+ const u32 val;
+};
+
+static struct string_lookup vmode_lookups[] = {
+ { "FB_VMODE_NONINTERLACED", FB_VMODE_NONINTERLACED},
+ { "FB_VMODE_INTERLACED", FB_VMODE_INTERLACED},
+ { "FB_VMODE_DOUBLE", FB_VMODE_DOUBLE},
+ { "FB_VMODE_ODD_FLD_FIRST", FB_VMODE_ODD_FLD_FIRST},
+ { NULL, 0 },
+};
+
+static struct string_lookup tim2_lookups[] = {
+ { "TIM2_CLKSEL", TIM2_CLKSEL},
+ { "TIM2_IVS", TIM2_IVS},
+ { "TIM2_IHS", TIM2_IHS},
+ { "TIM2_IPC", TIM2_IPC},
+ { "TIM2_IOE", TIM2_IOE},
+ { "TIM2_BCD", TIM2_BCD},
+ { NULL, 0},
+};
+static struct string_lookup cntl_lookups[] = {
+ {"CNTL_LCDEN", CNTL_LCDEN},
+ {"CNTL_LCDBPP1", CNTL_LCDBPP1},
+ {"CNTL_LCDBPP2", CNTL_LCDBPP2},
+ {"CNTL_LCDBPP4", CNTL_LCDBPP4},
+ {"CNTL_LCDBPP8", CNTL_LCDBPP8},
+ {"CNTL_LCDBPP16", CNTL_LCDBPP16},
+ {"CNTL_LCDBPP16_565", CNTL_LCDBPP16_565},
+ {"CNTL_LCDBPP16_444", CNTL_LCDBPP16_444},
+ {"CNTL_LCDBPP24", CNTL_LCDBPP24},
+ {"CNTL_LCDBW", CNTL_LCDBW},
+ {"CNTL_LCDTFT", CNTL_LCDTFT},
+ {"CNTL_LCDMONO8", CNTL_LCDMONO8},
+ {"CNTL_LCDDUAL", CNTL_LCDDUAL},
+ {"CNTL_BGR", CNTL_BGR},
+ {"CNTL_BEBO", CNTL_BEBO},
+ {"CNTL_BEPO", CNTL_BEPO},
+ {"CNTL_LCDPWR", CNTL_LCDPWR},
+ {"CNTL_LCDVCOMP(1)", CNTL_LCDVCOMP(1)},
+ {"CNTL_LCDVCOMP(2)", CNTL_LCDVCOMP(2)},
+ {"CNTL_LCDVCOMP(3)", CNTL_LCDVCOMP(3)},
+ {"CNTL_LCDVCOMP(4)", CNTL_LCDVCOMP(4)},
+ {"CNTL_LCDVCOMP(5)", CNTL_LCDVCOMP(5)},
+ {"CNTL_LCDVCOMP(6)", CNTL_LCDVCOMP(6)},
+ {"CNTL_LCDVCOMP(7)", CNTL_LCDVCOMP(7)},
+ {"CNTL_LDMAFIFOTIME", CNTL_LDMAFIFOTIME},
+ {"CNTL_WATERMARK", CNTL_WATERMARK},
+ { NULL, 0},
+};
+static struct string_lookup caps_lookups[] = {
+ {"CLCD_CAP_RGB444", CLCD_CAP_RGB444},
+ {"CLCD_CAP_RGB5551", CLCD_CAP_RGB5551},
+ {"CLCD_CAP_RGB565", CLCD_CAP_RGB565},
+ {"CLCD_CAP_RGB888", CLCD_CAP_RGB888},
+ {"CLCD_CAP_BGR444", CLCD_CAP_BGR444},
+ {"CLCD_CAP_BGR5551", CLCD_CAP_BGR5551},
+ {"CLCD_CAP_BGR565", CLCD_CAP_BGR565},
+ {"CLCD_CAP_BGR888", CLCD_CAP_BGR888},
+ {"CLCD_CAP_444", CLCD_CAP_444},
+ {"CLCD_CAP_5551", CLCD_CAP_5551},
+ {"CLCD_CAP_565", CLCD_CAP_565},
+ {"CLCD_CAP_888", CLCD_CAP_888},
+ {"CLCD_CAP_RGB", CLCD_CAP_RGB},
+ {"CLCD_CAP_BGR", CLCD_CAP_BGR},
+ {"CLCD_CAP_ALL", CLCD_CAP_ALL},
+ { NULL, 0},
+};
+
+u32 parse_setting(struct string_lookup *lookup, const char *name)
+{
+ int i = 0;
+ while (lookup[i].string != NULL) {
+ if (strcmp(lookup[i].string, name) == 0)
+ return lookup[i].val;
+ ++i;
+ }
+ return -EINVAL;
+}
+
+u32 get_string_lookup(struct device_node *node, const char *name,
+ struct string_lookup *lookup)
+{
+ const char *string;
+ int count, i, ret = 0;
+
+ count = of_property_count_strings(node, name);
+ if (count >= 0)
+ for (i = 0; i < count; i++)
+ if (of_property_read_string_index(node, name, i,
+ &string) == 0)
+ ret |= parse_setting(lookup, string);
+ return ret;
+}
+
+int get_val(struct device_node *node, const char *string)
+{
+ u32 ret = 0;
+
+ if (of_property_read_u32(node, string, &ret))
+ ret = -1;
+ return ret;
+}
+
+struct clcd_panel *getPanel(struct device_node *node)
+{
+ static struct clcd_panel panel;
+
+ panel.mode.refresh = get_val(node, "refresh");
+ panel.mode.xres = get_val(node, "xres");
+ panel.mode.yres = get_val(node, "yres");
+ panel.mode.pixclock = get_val(node, "pixclock");
+ panel.mode.left_margin = get_val(node, "left_margin");
+ panel.mode.right_margin = get_val(node, "right_margin");
+ panel.mode.upper_margin = get_val(node, "upper_margin");
+ panel.mode.lower_margin = get_val(node, "lower_margin");
+ panel.mode.hsync_len = get_val(node, "hsync_len");
+ panel.mode.vsync_len = get_val(node, "vsync_len");
+ panel.mode.sync = get_val(node, "sync");
+ panel.bpp = get_val(node, "bpp");
+ panel.width = (signed short) get_val(node, "width");
+ panel.height = (signed short) get_val(node, "height");
+
+ panel.mode.vmode = get_string_lookup(node, "vmode", vmode_lookups);
+ panel.tim2 = get_string_lookup(node, "tim2", tim2_lookups);
+ panel.cntl = get_string_lookup(node, "cntl", cntl_lookups);
+ panel.caps = get_string_lookup(node, "caps", caps_lookups);
+
+ return &panel;
+}
+
+struct clcd_panel *clcdfb_get_panel(const char *name)
+{
+ struct device_node *node = NULL;
+ const char *mode;
+ struct clcd_panel *panel = NULL;
+
+ do {
+ node = of_find_compatible_node(node, NULL, "panel");
+ if (node)
+ if (of_property_read_string(node, "mode", &mode) == 0)
+ if (strcmp(mode, name) == 0) {
+ panel = getPanel(node);
+ panel->mode.name = name;
+ }
+ } while (node != NULL);
+
+ return panel;
+}
+
+#ifdef CONFIG_OF
+static int clcdfb_dt_init(struct clcd_fb *fb)
+{
+ int err = 0;
+ struct device_node *node;
+ const char *mode;
+ dma_addr_t dma;
+ u32 use_dma;
+ const __be32 *prop;
+ int len, na, ns;
+ phys_addr_t fb_base, fb_size;
+
+ node = fb->dev->dev.of_node;
+ if (!node)
+ return -ENODEV;
+
+ na = of_n_addr_cells(node);
+ ns = of_n_size_cells(node);
+
+ if (def_mode && strlen(def_mode) > 0) {
+ fb->panel = clcdfb_get_panel(def_mode);
+ if (!fb->panel)
+ printk(KERN_ERR "CLCD: invalid mode specified on the command line (%s)\n", def_mode);
+ }
+
+ if (!fb->panel) {
+ if (WARN_ON(of_property_read_string(node, "mode", &mode)))
+ return -ENODEV;
+ fb->panel = clcdfb_get_panel(mode);
+ }
+
+ if (!fb->panel)
+ return -EINVAL;
+ fb->fb.fix.smem_len = fb->panel->mode.xres * fb->panel->mode.yres * 2;
+
+ fb->board->name = "Device Tree CLCD PL111";
+ fb->board->caps = CLCD_CAP_5551 | CLCD_CAP_565;
+ fb->board->check = clcdfb_check;
+ fb->board->decode = clcdfb_decode;
+
+ if (of_property_read_u32(node, "use_dma", &use_dma))
+ use_dma = 0;
+
+ if (use_dma) {
+ fb->fb.screen_base = clcdfb_dma_alloc(&fb->dev->dev,
+ fb->fb.fix.smem_len,
+ &dma, GFP_KERNEL);
+ if (!fb->fb.screen_base) {
+ pr_err("CLCD: unable to map framebuffer\n");
+ return -ENOMEM;
+ }
+
+ fb->fb.fix.smem_start = dma;
+ fb->board->mmap = clcdfb_mmap_dma;
+ fb->board->remove = clcdfb_remove_dma;
+ } else {
+ prop = of_get_property(node, "framebuffer", &len);
+ if (WARN_ON(!prop || len < (na + ns) * sizeof(*prop)))
+ return -EINVAL;
+
+ fb_base = of_read_number(prop, na);
+ fb_size = of_read_number(prop + na, ns);
+
+ fb->fb.fix.smem_start = fb_base;
+ fb->fb.screen_base = ioremap_wc(fb_base, fb_size);
+ fb->board->mmap = clcdfb_mmap_io;
+ fb->board->remove = clcdfb_remove_io;
+ }
+
+ return err;
+}
+#endif /* CONFIG_OF */
+
static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id)
{
struct clcd_board *board = dev->dev.platform_data;
struct clcd_fb *fb;
int ret;
- if (!board)
- return -EINVAL;
+ if (!board) {
+#ifdef CONFIG_OF
+ if (dev->dev.of_node) {
+ board = kzalloc(sizeof(struct clcd_board), GFP_KERNEL);
+ if (!board)
+ return -ENOMEM;
+ board->setup = clcdfb_dt_init;
+ } else
+#endif
+ return -EINVAL;
+ }
ret = amba_request_regions(dev, NULL);
if (ret) {
diff --git a/drivers/video/arm-hdlcd.c b/drivers/video/arm-hdlcd.c
new file mode 100644
index 0000000..cfd631e
--- /dev/null
+++ b/drivers/video/arm-hdlcd.c
@@ -0,0 +1,844 @@
+/*
+ * drivers/video/arm-hdlcd.c
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ * ARM HDLCD Controller
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/fb.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/memblock.h>
+#include <linux/arm-hdlcd.h>
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
+
+#include "edid.h"
+
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+int get_edid(u8 *msgbuf);
+#else
+#endif
+
+#define to_hdlcd_device(info) container_of(info, struct hdlcd_device, fb)
+
+static struct of_device_id hdlcd_of_matches[] = {
+ { .compatible = "arm,hdlcd" },
+ {},
+};
+
+/* Framebuffer size. */
+static unsigned long framebuffer_size;
+
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+static unsigned long buffer_underrun_events;
+static DEFINE_SPINLOCK(hdlcd_underrun_lock);
+
+static void hdlcd_underrun_set(unsigned long val)
+{
+ spin_lock(&hdlcd_underrun_lock);
+ buffer_underrun_events = val;
+ spin_unlock(&hdlcd_underrun_lock);
+}
+
+static unsigned long hdlcd_underrun_get(void)
+{
+ unsigned long val;
+ spin_lock(&hdlcd_underrun_lock);
+ val = buffer_underrun_events;
+ spin_unlock(&hdlcd_underrun_lock);
+ return val;
+}
+
+#ifdef CONFIG_PROC_FS
+static int hdlcd_underrun_show(struct seq_file *m, void *v)
+{
+ unsigned char underrun_string[32];
+ snprintf(underrun_string, 32, "%lu\n", hdlcd_underrun_get());
+ seq_puts(m, underrun_string);
+ return 0;
+}
+
+static int proc_hdlcd_underrun_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, hdlcd_underrun_show, NULL);
+}
+
+static const struct file_operations proc_hdlcd_underrun_operations = {
+ .open = proc_hdlcd_underrun_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int hdlcd_underrun_init(void)
+{
+ hdlcd_underrun_set(0);
+ proc_create("hdlcd_underrun", 0, NULL, &proc_hdlcd_underrun_operations);
+ return 0;
+}
+static void hdlcd_underrun_close(void)
+{
+ remove_proc_entry("hdlcd_underrun", NULL);
+}
+#else
+static int hdlcd_underrun_init(void) { return 0; }
+static void hdlcd_underrun_close(void) { }
+#endif
+#endif
+
+static char *fb_mode = "1680x1050-32@60\0\0\0\0\0";
+
+static struct fb_var_screeninfo cached_var_screeninfo;
+
+static struct fb_videomode hdlcd_default_mode = {
+ .refresh = 60,
+ .xres = 1680,
+ .yres = 1050,
+ .pixclock = 8403,
+ .left_margin = 80,
+ .right_margin = 48,
+ .upper_margin = 21,
+ .lower_margin = 3,
+ .hsync_len = 32,
+ .vsync_len = 6,
+ .sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+ .vmode = FB_VMODE_NONINTERLACED
+};
+
+static inline void hdlcd_enable(struct hdlcd_device *hdlcd)
+{
+ dev_dbg(hdlcd->dev, "HDLCD: output enabled\n");
+ writel(1, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static inline void hdlcd_disable(struct hdlcd_device *hdlcd)
+{
+ dev_dbg(hdlcd->dev, "HDLCD: output disabled\n");
+ writel(0, hdlcd->base + HDLCD_REG_COMMAND);
+}
+
+static int hdlcd_set_bitfields(struct hdlcd_device *hdlcd,
+ struct fb_var_screeninfo *var)
+{
+ int ret = 0;
+
+ memset(&var->transp, 0, sizeof(var->transp));
+ var->red.msb_right = 0;
+ var->green.msb_right = 0;
+ var->blue.msb_right = 0;
+ var->blue.offset = 0;
+
+ switch (var->bits_per_pixel) {
+ case 8:
+ /* pseudocolor */
+ var->red.length = 8;
+ var->green.length = 8;
+ var->blue.length = 8;
+ break;
+ case 16:
+ /* 565 format */
+ var->red.length = 5;
+ var->green.length = 6;
+ var->blue.length = 5;
+ break;
+ case 32:
+ var->transp.length = 8;
+ case 24:
+ var->red.length = 8;
+ var->green.length = 8;
+ var->blue.length = 8;
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ if (!ret) {
+ if(var->bits_per_pixel != 32)
+ {
+ var->green.offset = var->blue.length;
+ var->red.offset = var->green.offset + var->green.length;
+ }
+ else
+ {
+ /* Previously, the byte ordering for 32-bit color was
+ * (msb)<alpha><red><green><blue>(lsb)
+ * but this does not match what android expects and
+ * the colors are odd. Instead, use
+ * <alpha><blue><green><red>
+ * Since we tell fb what we are doing, console
+ * , X and directfb access should work fine.
+ */
+ var->green.offset = var->red.length;
+ var->blue.offset = var->green.offset + var->green.length;
+ var->transp.offset = var->blue.offset + var->blue.length;
+ }
+ }
+
+ return ret;
+}
+
+static int hdlcd_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+ int bytes_per_pixel = var->bits_per_pixel / 8;
+
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+ var->yres_virtual = var->yres;
+#else
+ var->yres_virtual = 2 * var->yres;
+#endif
+
+ if ((var->xres_virtual * bytes_per_pixel * var->yres_virtual) > hdlcd->fb.fix.smem_len)
+ return -ENOMEM;
+
+ if (var->xres > HDLCD_MAX_XRES || var->yres > HDLCD_MAX_YRES)
+ return -EINVAL;
+
+ /* make sure the bitfields are set appropriately */
+ return hdlcd_set_bitfields(hdlcd, var);
+}
+
+/* prototype */
+static int hdlcd_pan_display(struct fb_var_screeninfo *var,
+ struct fb_info *info);
+
+#define WRITE_HDLCD_REG(reg, value) writel((value), hdlcd->base + (reg))
+#define READ_HDLCD_REG(reg) readl(hdlcd->base + (reg))
+
+static int hdlcd_set_par(struct fb_info *info)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+ int bytes_per_pixel = hdlcd->fb.var.bits_per_pixel / 8;
+ int polarities;
+ int old_yoffset;
+
+ /* check for shortcuts */
+ old_yoffset = cached_var_screeninfo.yoffset;
+ cached_var_screeninfo.yoffset = info->var.yoffset;
+ if (!memcmp(&info->var, &cached_var_screeninfo,
+ sizeof(struct fb_var_screeninfo))) {
+ if(old_yoffset != info->var.yoffset) {
+ /* we only changed yoffset, and we already
+ * already recorded it a couple lines up
+ */
+ hdlcd_pan_display(&info->var, info);
+ }
+ /* or no change */
+ return 0;
+ }
+
+ hdlcd->fb.fix.line_length = hdlcd->fb.var.xres * bytes_per_pixel;
+
+ if (hdlcd->fb.var.bits_per_pixel >= 16)
+ hdlcd->fb.fix.visual = FB_VISUAL_TRUECOLOR;
+ else
+ hdlcd->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR;
+
+ memcpy(&cached_var_screeninfo, &info->var, sizeof(struct fb_var_screeninfo));
+
+ polarities = HDLCD_POLARITY_DATAEN |
+#ifndef CONFIG_ARCH_TUSCAN
+ HDLCD_POLARITY_PIXELCLK |
+#endif
+ HDLCD_POLARITY_DATA;
+ polarities |= (hdlcd->fb.var.sync & FB_SYNC_HOR_HIGH_ACT) ? HDLCD_POLARITY_HSYNC : 0;
+ polarities |= (hdlcd->fb.var.sync & FB_SYNC_VERT_HIGH_ACT) ? HDLCD_POLARITY_VSYNC : 0;
+
+ hdlcd_disable(hdlcd);
+
+ WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_LENGTH, hdlcd->fb.var.xres * bytes_per_pixel);
+ WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_PITCH, hdlcd->fb.var.xres * bytes_per_pixel);
+ WRITE_HDLCD_REG(HDLCD_REG_FB_LINE_COUNT, hdlcd->fb.var.yres - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_V_SYNC, hdlcd->fb.var.vsync_len - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_V_BACK_PORCH, hdlcd->fb.var.upper_margin - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_V_DATA, hdlcd->fb.var.yres - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_V_FRONT_PORCH, hdlcd->fb.var.lower_margin - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_H_SYNC, hdlcd->fb.var.hsync_len - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_H_BACK_PORCH, hdlcd->fb.var.left_margin - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_H_DATA, hdlcd->fb.var.xres - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_H_FRONT_PORCH, hdlcd->fb.var.right_margin - 1);
+ WRITE_HDLCD_REG(HDLCD_REG_POLARITIES, polarities);
+ WRITE_HDLCD_REG(HDLCD_REG_PIXEL_FORMAT, (bytes_per_pixel - 1) << 3);
+#ifdef HDLCD_RED_DEFAULT_COLOUR
+ WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, (0x00ff0000 | (hdlcd->fb.var.red.length & 0xf) << 8) \
+ | hdlcd->fb.var.red.offset);
+#else
+ WRITE_HDLCD_REG(HDLCD_REG_RED_SELECT, ((hdlcd->fb.var.red.length & 0xf) << 8) | hdlcd->fb.var.red.offset);
+#endif
+ WRITE_HDLCD_REG(HDLCD_REG_GREEN_SELECT, ((hdlcd->fb.var.green.length & 0xf) << 8) | hdlcd->fb.var.green.offset);
+ WRITE_HDLCD_REG(HDLCD_REG_BLUE_SELECT, ((hdlcd->fb.var.blue.length & 0xf) << 8) | hdlcd->fb.var.blue.offset);
+
+ clk_set_rate(hdlcd->clk, (1000000000 / hdlcd->fb.var.pixclock) * 1000);
+ clk_enable(hdlcd->clk);
+
+ hdlcd_enable(hdlcd);
+
+ return 0;
+}
+
+static int hdlcd_setcolreg(unsigned int regno, unsigned int red, unsigned int green,
+ unsigned int blue, unsigned int transp, struct fb_info *info)
+{
+ if (regno < 16) {
+ u32 *pal = info->pseudo_palette;
+
+ pal[regno] = ((red >> 8) << info->var.red.offset) |
+ ((green >> 8) << info->var.green.offset) |
+ ((blue >> 8) << info->var.blue.offset);
+ }
+
+ return 0;
+}
+
+static irqreturn_t hdlcd_irq(int irq, void *data)
+{
+ struct hdlcd_device *hdlcd = data;
+ unsigned long irq_mask, irq_status;
+
+ irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+ irq_status = READ_HDLCD_REG(HDLCD_REG_INT_STATUS);
+
+ /* acknowledge interrupt(s) */
+ WRITE_HDLCD_REG(HDLCD_REG_INT_CLEAR, irq_status);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+ if (irq_status & HDLCD_INTERRUPT_UNDERRUN) {
+ /* increment the count */
+ hdlcd_underrun_set(hdlcd_underrun_get() + 1);
+ }
+#endif
+ if (irq_status & HDLCD_INTERRUPT_VSYNC) {
+ /* disable future VSYNC interrupts */
+ WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask & ~HDLCD_INTERRUPT_VSYNC);
+
+ complete(&hdlcd->vsync_completion);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static int hdlcd_wait_for_vsync(struct fb_info *info)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+ unsigned long irq_mask;
+ int err;
+
+ /* enable VSYNC interrupt */
+ irq_mask = READ_HDLCD_REG(HDLCD_REG_INT_MASK);
+ WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, irq_mask | HDLCD_INTERRUPT_VSYNC);
+
+ err = wait_for_completion_interruptible_timeout(&hdlcd->vsync_completion,
+ msecs_to_jiffies(100));
+
+ if (!err)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int hdlcd_blank(int blank_mode, struct fb_info *info)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+ switch (blank_mode) {
+ case FB_BLANK_POWERDOWN:
+ clk_disable(hdlcd->clk);
+ case FB_BLANK_NORMAL:
+ hdlcd_disable(hdlcd);
+ break;
+ case FB_BLANK_UNBLANK:
+ clk_enable(hdlcd->clk);
+ hdlcd_enable(hdlcd);
+ break;
+ case FB_BLANK_VSYNC_SUSPEND:
+ case FB_BLANK_HSYNC_SUSPEND:
+ default:
+ return 1;
+ }
+
+ return 0;
+}
+
+static void hdlcd_mmap_open(struct vm_area_struct *vma)
+{
+}
+
+static void hdlcd_mmap_close(struct vm_area_struct *vma)
+{
+}
+
+static struct vm_operations_struct hdlcd_mmap_ops = {
+ .open = hdlcd_mmap_open,
+ .close = hdlcd_mmap_close,
+};
+
+static int hdlcd_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+ unsigned long off;
+ unsigned long start;
+ unsigned long len = hdlcd->fb.fix.smem_len;
+
+ if (vma->vm_end - vma->vm_start == 0)
+ return 0;
+ if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
+ return -EINVAL;
+
+ off = vma->vm_pgoff << PAGE_SHIFT;
+ if ((off >= len) || (vma->vm_end - vma->vm_start + off) > len)
+ return -EINVAL;
+
+ start = hdlcd->fb.fix.smem_start;
+ off += start;
+
+ vma->vm_pgoff = off >> PAGE_SHIFT;
+ vma->vm_flags |= VM_IO;
+ vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+ vma->vm_ops = &hdlcd_mmap_ops;
+ if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
+ vma->vm_end - vma->vm_start,
+ vma->vm_page_prot))
+ return -EAGAIN;
+
+ return 0;
+}
+
+static int hdlcd_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
+{
+ struct hdlcd_device *hdlcd = to_hdlcd_device(info);
+
+ hdlcd->fb.var.yoffset = var->yoffset;
+ WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start +
+ (var->yoffset * hdlcd->fb.fix.line_length));
+
+ hdlcd_wait_for_vsync(info);
+
+ return 0;
+}
+
+static int hdlcd_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg)
+{
+ int err;
+
+ switch (cmd) {
+ case FBIO_WAITFORVSYNC:
+ err = hdlcd_wait_for_vsync(info);
+ break;
+ default:
+ err = -ENOIOCTLCMD;
+ break;
+ }
+
+ return err;
+}
+
+static struct fb_ops hdlcd_ops = {
+ .owner = THIS_MODULE,
+ .fb_check_var = hdlcd_check_var,
+ .fb_set_par = hdlcd_set_par,
+ .fb_setcolreg = hdlcd_setcolreg,
+ .fb_blank = hdlcd_blank,
+ .fb_fillrect = cfb_fillrect,
+ .fb_copyarea = cfb_copyarea,
+ .fb_imageblit = cfb_imageblit,
+ .fb_mmap = hdlcd_mmap,
+ .fb_pan_display = hdlcd_pan_display,
+ .fb_ioctl = hdlcd_ioctl,
+ .fb_compat_ioctl = hdlcd_ioctl
+};
+
+static int hdlcd_setup(struct hdlcd_device *hdlcd)
+{
+ u32 version;
+ int err = -EFAULT;
+
+ hdlcd->fb.device = hdlcd->dev;
+
+ hdlcd->clk = clk_get(hdlcd->dev, NULL);
+ if (IS_ERR(hdlcd->clk)) {
+ dev_err(hdlcd->dev, "HDLCD: unable to find clock data\n");
+ return PTR_ERR(hdlcd->clk);
+ }
+
+ err = clk_prepare(hdlcd->clk);
+ if (err)
+ goto clk_prepare_err;
+
+ hdlcd->base = ioremap_nocache(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+ if (!hdlcd->base) {
+ dev_err(hdlcd->dev, "HDLCD: unable to map registers\n");
+ goto remap_err;
+ }
+
+ hdlcd->fb.pseudo_palette = kmalloc(sizeof(u32) * 16, GFP_KERNEL);
+ if (!hdlcd->fb.pseudo_palette) {
+ dev_err(hdlcd->dev, "HDLCD: unable to allocate pseudo_palette memory\n");
+ err = -ENOMEM;
+ goto kmalloc_err;
+ }
+
+ version = readl(hdlcd->base + HDLCD_REG_VERSION);
+ if ((version & HDLCD_PRODUCT_MASK) != HDLCD_PRODUCT_ID) {
+ dev_err(hdlcd->dev, "HDLCD: unknown product id: 0x%x\n", version);
+ err = -EINVAL;
+ goto kmalloc_err;
+ }
+ dev_info(hdlcd->dev, "HDLCD: found ARM HDLCD version r%dp%d\n",
+ (version & HDLCD_VERSION_MAJOR_MASK) >> 8,
+ version & HDLCD_VERSION_MINOR_MASK);
+
+ strcpy(hdlcd->fb.fix.id, "hdlcd");
+ hdlcd->fb.fbops = &hdlcd_ops;
+ hdlcd->fb.flags = FBINFO_FLAG_DEFAULT/* | FBINFO_VIRTFB*/;
+
+ hdlcd->fb.fix.type = FB_TYPE_PACKED_PIXELS;
+ hdlcd->fb.fix.type_aux = 0;
+ hdlcd->fb.fix.xpanstep = 0;
+ hdlcd->fb.fix.ypanstep = 1;
+ hdlcd->fb.fix.ywrapstep = 0;
+ hdlcd->fb.fix.accel = FB_ACCEL_NONE;
+
+ hdlcd->fb.var.nonstd = 0;
+ hdlcd->fb.var.activate = FB_ACTIVATE_NOW;
+ hdlcd->fb.var.height = -1;
+ hdlcd->fb.var.width = -1;
+ hdlcd->fb.var.accel_flags = 0;
+
+ init_completion(&hdlcd->vsync_completion);
+
+ if (hdlcd->edid) {
+ /* build modedb from EDID */
+ fb_edid_to_monspecs(hdlcd->edid, &hdlcd->fb.monspecs);
+ fb_videomode_to_modelist(hdlcd->fb.monspecs.modedb,
+ hdlcd->fb.monspecs.modedb_len,
+ &hdlcd->fb.modelist);
+ fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode,
+ hdlcd->fb.monspecs.modedb,
+ hdlcd->fb.monspecs.modedb_len,
+ &hdlcd_default_mode, 32);
+ } else {
+ hdlcd->fb.monspecs.hfmin = 0;
+ hdlcd->fb.monspecs.hfmax = 100000;
+ hdlcd->fb.monspecs.vfmin = 0;
+ hdlcd->fb.monspecs.vfmax = 400;
+ hdlcd->fb.monspecs.dclkmin = 1000000;
+ hdlcd->fb.monspecs.dclkmax = 100000000;
+ fb_find_mode(&hdlcd->fb.var, &hdlcd->fb, fb_mode, NULL, 0, &hdlcd_default_mode, 32);
+ }
+
+ dev_info(hdlcd->dev, "using %dx%d-%d@%d mode\n", hdlcd->fb.var.xres,
+ hdlcd->fb.var.yres, hdlcd->fb.var.bits_per_pixel,
+ hdlcd->fb.mode ? hdlcd->fb.mode->refresh : 60);
+ hdlcd->fb.var.xres_virtual = hdlcd->fb.var.xres;
+#ifdef HDLCD_NO_VIRTUAL_SCREEN
+ hdlcd->fb.var.yres_virtual = hdlcd->fb.var.yres;
+#else
+ hdlcd->fb.var.yres_virtual = hdlcd->fb.var.yres * 2;
+#endif
+
+ /* initialise and set the palette */
+ if (fb_alloc_cmap(&hdlcd->fb.cmap, NR_PALETTE, 0)) {
+ dev_err(hdlcd->dev, "failed to allocate cmap memory\n");
+ err = -ENOMEM;
+ goto setup_err;
+ }
+ fb_set_cmap(&hdlcd->fb.cmap, &hdlcd->fb);
+
+ /* Allow max number of outstanding requests with the largest beat burst */
+ WRITE_HDLCD_REG(HDLCD_REG_BUS_OPTIONS, HDLCD_BUS_MAX_OUTSTAND | HDLCD_BUS_BURST_16);
+ /* Set the framebuffer base to start of allocated memory */
+ WRITE_HDLCD_REG(HDLCD_REG_FB_BASE, hdlcd->fb.fix.smem_start);
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+ /* turn on underrun interrupt for counting */
+ WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, HDLCD_INTERRUPT_UNDERRUN);
+#else
+ /* Ensure interrupts are disabled */
+ WRITE_HDLCD_REG(HDLCD_REG_INT_MASK, 0);
+#endif
+ fb_set_var(&hdlcd->fb, &hdlcd->fb.var);
+
+ if (!register_framebuffer(&hdlcd->fb)) {
+ return 0;
+ }
+
+ dev_err(hdlcd->dev, "HDLCD: cannot register framebuffer\n");
+
+ fb_dealloc_cmap(&hdlcd->fb.cmap);
+setup_err:
+ iounmap(hdlcd->base);
+kmalloc_err:
+ kfree(hdlcd->fb.pseudo_palette);
+remap_err:
+ clk_unprepare(hdlcd->clk);
+clk_prepare_err:
+ clk_put(hdlcd->clk);
+ return err;
+}
+
+static inline unsigned char atohex(u8 data)
+{
+ if (!isxdigit(data))
+ return 0;
+ /* truncate the upper nibble and add 9 to non-digit values */
+ return (data > 0x39) ? ((data & 0xf) + 9) : (data & 0xf);
+}
+
+/* EDID data is passed from devicetree in a literal string that can contain spaces and
+ the hexadecimal dump of the data */
+static int parse_edid_data(struct hdlcd_device *hdlcd, const u8 *edid_data, int data_len)
+{
+ int i, j;
+
+ if (!edid_data)
+ return -EINVAL;
+
+ hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+ if (!hdlcd->edid)
+ return -ENOMEM;
+
+ for (i = 0, j = 0; i < data_len; i++) {
+ if (isspace(edid_data[i]))
+ continue;
+ hdlcd->edid[j++] = atohex(edid_data[i]);
+ if (j >= EDID_LENGTH)
+ break;
+ }
+
+ if (j < EDID_LENGTH) {
+ kfree(hdlcd->edid);
+ hdlcd->edid = NULL;
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int hdlcd_probe(struct platform_device *pdev)
+{
+ int err = 0, i;
+ struct hdlcd_device *hdlcd;
+ struct resource *mem;
+#ifdef CONFIG_OF
+ struct device_node *of_node;
+#endif
+
+ memset(&cached_var_screeninfo, 0, sizeof(struct fb_var_screeninfo));
+
+ dev_dbg(&pdev->dev, "HDLCD: probing\n");
+
+ hdlcd = kzalloc(sizeof(*hdlcd), GFP_KERNEL);
+ if (!hdlcd)
+ return -ENOMEM;
+
+#ifdef CONFIG_OF
+ of_node = pdev->dev.of_node;
+ if (of_node) {
+ int len;
+ const u8 *edid;
+ const __be32 *prop = of_get_property(of_node, "mode", &len);
+ if (prop)
+ strncpy(fb_mode, (char *)prop, len);
+ prop = of_get_property(of_node, "framebuffer", &len);
+ if (prop) {
+ hdlcd->fb.fix.smem_start = of_read_ulong(prop,
+ of_n_addr_cells(of_node));
+ prop += of_n_addr_cells(of_node);
+ framebuffer_size = of_read_ulong(prop,
+ of_n_size_cells(of_node));
+ if (framebuffer_size > HDLCD_MAX_FRAMEBUFFER_SIZE)
+ framebuffer_size = HDLCD_MAX_FRAMEBUFFER_SIZE;
+ dev_dbg(&pdev->dev, "HDLCD: phys_addr = 0x%lx, size = 0x%lx\n",
+ hdlcd->fb.fix.smem_start, framebuffer_size);
+ }
+ edid = of_get_property(of_node, "edid", &len);
+ if (edid) {
+ err = parse_edid_data(hdlcd, edid, len);
+#ifdef CONFIG_SERIAL_AMBA_PCU_UART
+ } else {
+ /* ask the firmware to fetch the EDID */
+ dev_dbg(&pdev->dev, "HDLCD: Requesting EDID data\n");
+ hdlcd->edid = kzalloc(EDID_LENGTH, GFP_KERNEL);
+ if (!hdlcd->edid)
+ return -ENOMEM;
+ err = get_edid(hdlcd->edid);
+#endif /* CONFIG_SERIAL_AMBA_PCU_UART */
+ }
+ if (err)
+ dev_info(&pdev->dev, "HDLCD: Failed to parse EDID data\n");
+ }
+#endif /* CONFIG_OF */
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!mem) {
+ dev_err(&pdev->dev, "HDLCD: cannot get platform resources\n");
+ err = -EINVAL;
+ goto resource_err;
+ }
+
+ i = platform_get_irq(pdev, 0);
+ if (i < 0) {
+ dev_err(&pdev->dev, "HDLCD: no irq defined for vsync\n");
+ err = -ENOENT;
+ goto resource_err;
+ } else {
+ err = request_irq(i, hdlcd_irq, 0, dev_name(&pdev->dev), hdlcd);
+ if (err) {
+ dev_err(&pdev->dev, "HDLCD: unable to request irq\n");
+ goto resource_err;
+ }
+ hdlcd->irq = i;
+ }
+
+ if (!request_mem_region(mem->start, resource_size(mem), dev_name(&pdev->dev))) {
+ err = -ENXIO;
+ goto request_err;
+ }
+
+ if (!hdlcd->fb.fix.smem_start) {
+ dev_err(&pdev->dev, "platform did not allocate frame buffer memory\n");
+ err = -ENOMEM;
+ goto memalloc_err;
+ }
+ hdlcd->fb.screen_base = ioremap_wc(hdlcd->fb.fix.smem_start, framebuffer_size);
+ if (!hdlcd->fb.screen_base) {
+ dev_err(&pdev->dev, "unable to ioremap framebuffer\n");
+ err = -ENOMEM;
+ goto probe_err;
+ }
+
+ hdlcd->fb.screen_size = framebuffer_size;
+ hdlcd->fb.fix.smem_len = framebuffer_size;
+ hdlcd->fb.fix.mmio_start = mem->start;
+ hdlcd->fb.fix.mmio_len = resource_size(mem);
+
+ /* Clear the framebuffer */
+ memset(hdlcd->fb.screen_base, 0, framebuffer_size);
+
+ hdlcd->dev = &pdev->dev;
+
+ dev_dbg(&pdev->dev, "HDLCD: framebuffer virt base %p, phys base 0x%lX\n",
+ hdlcd->fb.screen_base, (unsigned long)hdlcd->fb.fix.smem_start);
+
+ err = hdlcd_setup(hdlcd);
+
+ if (err)
+ goto probe_err;
+
+ platform_set_drvdata(pdev, hdlcd);
+ return 0;
+
+probe_err:
+ iounmap(hdlcd->fb.screen_base);
+ memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+
+memalloc_err:
+ release_mem_region(mem->start, resource_size(mem));
+
+request_err:
+ free_irq(hdlcd->irq, hdlcd);
+
+resource_err:
+ kfree(hdlcd);
+
+ return err;
+}
+
+static int hdlcd_remove(struct platform_device *pdev)
+{
+ struct hdlcd_device *hdlcd = platform_get_drvdata(pdev);
+
+ clk_disable(hdlcd->clk);
+ clk_unprepare(hdlcd->clk);
+ clk_put(hdlcd->clk);
+
+ /* unmap memory */
+ iounmap(hdlcd->fb.screen_base);
+ iounmap(hdlcd->base);
+
+ /* deallocate fb memory */
+ fb_dealloc_cmap(&hdlcd->fb.cmap);
+ kfree(hdlcd->fb.pseudo_palette);
+ memblock_free(hdlcd->fb.fix.smem_start, hdlcd->fb.fix.smem_start);
+ release_mem_region(hdlcd->fb.fix.mmio_start, hdlcd->fb.fix.mmio_len);
+
+ free_irq(hdlcd->irq, NULL);
+ kfree(hdlcd);
+
+ return 0;
+}
+
+#ifdef CONFIG_PM
+static int hdlcd_suspend(struct platform_device *pdev, pm_message_t state)
+{
+ /* not implemented yet */
+ return 0;
+}
+
+static int hdlcd_resume(struct platform_device *pdev)
+{
+ /* not implemented yet */
+ return 0;
+}
+#else
+#define hdlcd_suspend NULL
+#define hdlcd_resume NULL
+#endif
+
+static struct platform_driver hdlcd_driver = {
+ .probe = hdlcd_probe,
+ .remove = hdlcd_remove,
+ .suspend = hdlcd_suspend,
+ .resume = hdlcd_resume,
+ .driver = {
+ .name = "hdlcd",
+ .owner = THIS_MODULE,
+ .of_match_table = hdlcd_of_matches,
+ },
+};
+
+static int __init hdlcd_init(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+ int err = platform_driver_register(&hdlcd_driver);
+ if (!err)
+ hdlcd_underrun_init();
+ return err;
+#else
+ return platform_driver_register(&hdlcd_driver);
+#endif
+}
+
+void __exit hdlcd_exit(void)
+{
+#ifdef HDLCD_COUNT_BUFFERUNDERRUNS
+ hdlcd_underrun_close();
+#endif
+ platform_driver_unregister(&hdlcd_driver);
+}
+
+module_init(hdlcd_init);
+module_exit(hdlcd_exit);
+
+MODULE_AUTHOR("Liviu Dudau");
+MODULE_DESCRIPTION("ARM HDLCD core driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c
index e45833c..182bd68 100644
--- a/drivers/video/aty/mach64_accel.c
+++ b/drivers/video/aty/mach64_accel.c
@@ -4,6 +4,7 @@
*/
#include <linux/delay.h>
+#include <asm/unaligned.h>
#include <linux/fb.h>
#include <video/mach64.h>
#include "atyfb.h"
@@ -419,7 +420,7 @@
u32 *pbitmap, dwords = (src_bytes + 3) / 4;
for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
wait_for_fifo(1, par);
- aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+ aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
}
}
diff --git a/drivers/video/aty/mach64_cursor.c b/drivers/video/aty/mach64_cursor.c
index 95ec042..0fe02e2 100644
--- a/drivers/video/aty/mach64_cursor.c
+++ b/drivers/video/aty/mach64_cursor.c
@@ -5,6 +5,7 @@
#include <linux/fb.h>
#include <linux/init.h>
#include <linux/string.h>
+#include "../fb_draw.h"
#include <asm/io.h>
@@ -157,24 +158,33 @@
for (i = 0; i < height; i++) {
for (j = 0; j < width; j++) {
+ u16 l = 0xaaaa;
b = *src++;
m = *msk++;
switch (cursor->rop) {
case ROP_XOR:
// Upper 4 bits of mask data
- fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+ l = cursor_bits_lookup[(b ^ m) >> 4] |
// Lower 4 bits of mask
- fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
- dst++);
+ (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
break;
case ROP_COPY:
// Upper 4 bits of mask data
- fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+ l = cursor_bits_lookup[(b & m) >> 4] |
// Lower 4 bits of mask
- fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
- dst++);
+ (cursor_bits_lookup[(b & m) & 0x0f] << 8);
break;
}
+ /*
+ * If cursor size is not a multiple of 8 characters
+ * we must pad it with transparent pattern (0xaaaa).
+ */
+ if ((j + 1) * 8 > cursor->image.width) {
+ l = comp(l, 0xaaaa,
+ (1 << ((cursor->image.width & 7) * 2)) - 1);
+ }
+ fb_writeb(l & 0xff, dst++);
+ fb_writeb(l >> 8, dst++);
}
dst += offset;
}
diff --git a/drivers/video/au1100fb.c b/drivers/video/au1100fb.c
index 700cac0..bdc515f 100644
--- a/drivers/video/au1100fb.c
+++ b/drivers/video/au1100fb.c
@@ -361,39 +361,13 @@
int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
{
struct au1100fb_device *fbdev;
- unsigned int len;
- unsigned long start=0, off;
fbdev = to_au1100fb_device(fbi);
- if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
- return -EINVAL;
- }
-
- start = fbdev->fb_phys & PAGE_MASK;
- len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
- off = vma->vm_pgoff << PAGE_SHIFT;
-
- if ((vma->vm_end - vma->vm_start + off) > len) {
- return -EINVAL;
- }
-
- off += start;
- vma->vm_pgoff = off >> PAGE_SHIFT;
-
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
pgprot_val(vma->vm_page_prot) |= (6 << 9); //CCA=6
- vma->vm_flags |= VM_IO;
-
- if (io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
- vma->vm_end - vma->vm_start,
- vma->vm_page_prot)) {
- return -EAGAIN;
- }
-
- return 0;
+ return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
}
static struct fb_ops au1100fb_ops =
diff --git a/drivers/video/au1200fb.c b/drivers/video/au1200fb.c
index 1b59054..1d02897 100644
--- a/drivers/video/au1200fb.c
+++ b/drivers/video/au1200fb.c
@@ -1233,38 +1233,13 @@
* method mainly to allow the use of the TLB streaming flag (CCA=6)
*/
static int au1200fb_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
-
{
- unsigned int len;
- unsigned long start=0, off;
struct au1200fb_device *fbdev = info->par;
- if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT)) {
- return -EINVAL;
- }
-
- start = fbdev->fb_phys & PAGE_MASK;
- len = PAGE_ALIGN((start & ~PAGE_MASK) + fbdev->fb_len);
-
- off = vma->vm_pgoff << PAGE_SHIFT;
-
- if ((vma->vm_end - vma->vm_start + off) > len) {
- return -EINVAL;
- }
-
- off += start;
- vma->vm_pgoff = off >> PAGE_SHIFT;
-
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
pgprot_val(vma->vm_page_prot) |= _CACHE_MASK; /* CCA=7 */
- vma->vm_flags |= VM_IO;
-
- return io_remap_pfn_range(vma, vma->vm_start, off >> PAGE_SHIFT,
- vma->vm_end - vma->vm_start,
- vma->vm_page_prot);
-
- return 0;
+ return vm_iomap_memory(vma, fbdev->fb_phys, fbdev->fb_len);
}
static void set_global(u_int cmd, struct au1200_lcd_global_regs_t *pdata)
diff --git a/drivers/video/backlight/atmel-pwm-bl.c b/drivers/video/backlight/atmel-pwm-bl.c
index a60d6af..27a14a0 100644
--- a/drivers/video/backlight/atmel-pwm-bl.c
+++ b/drivers/video/backlight/atmel-pwm-bl.c
@@ -70,7 +70,7 @@
static int atmel_pwm_bl_get_intensity(struct backlight_device *bd)
{
struct atmel_pwm_bl *pwmbl = bl_get_data(bd);
- u8 intensity;
+ u32 intensity;
if (pwmbl->pdata->pwm_active_low) {
intensity = pwm_channel_readl(&pwmbl->pwmc, PWM_CDTY) -
@@ -80,7 +80,7 @@
pwm_channel_readl(&pwmbl->pwmc, PWM_CDTY);
}
- return intensity;
+ return intensity & 0xffff;
}
static int atmel_pwm_bl_init_pwm(struct atmel_pwm_bl *pwmbl)
@@ -118,7 +118,7 @@
.update_status = atmel_pwm_bl_set_intensity,
};
-static int __init atmel_pwm_bl_probe(struct platform_device *pdev)
+static int atmel_pwm_bl_probe(struct platform_device *pdev)
{
struct backlight_properties props;
const struct atmel_pwm_bl_platform_data *pdata;
@@ -203,12 +203,14 @@
return retval;
}
-static int __exit atmel_pwm_bl_remove(struct platform_device *pdev)
+static int atmel_pwm_bl_remove(struct platform_device *pdev)
{
struct atmel_pwm_bl *pwmbl = platform_get_drvdata(pdev);
- if (pwmbl->gpio_on != -1)
- gpio_set_value(pwmbl->gpio_on, 0);
+ if (pwmbl->gpio_on != -1) {
+ gpio_set_value(pwmbl->gpio_on,
+ 0 ^ pwmbl->pdata->on_active_low);
+ }
pwm_channel_disable(&pwmbl->pwmc);
pwm_channel_free(&pwmbl->pwmc);
backlight_device_unregister(pwmbl->bldev);
@@ -222,10 +224,11 @@
.name = "atmel-pwm-bl",
},
/* REVISIT add suspend() and resume() */
- .remove = __exit_p(atmel_pwm_bl_remove),
+ .probe = atmel_pwm_bl_probe,
+ .remove = atmel_pwm_bl_remove,
};
-module_platform_driver_probe(atmel_pwm_bl_driver, atmel_pwm_bl_probe);
+module_platform_driver(atmel_pwm_bl_driver);
MODULE_AUTHOR("Hans-Christian egtvedt <hans-christian.egtvedt@atmel.com>");
MODULE_DESCRIPTION("Atmel PWM backlight driver");
diff --git a/drivers/video/cfbcopyarea.c b/drivers/video/cfbcopyarea.c
index bb5a96b..bcb5723 100644
--- a/drivers/video/cfbcopyarea.c
+++ b/drivers/video/cfbcopyarea.c
@@ -43,13 +43,22 @@
*/
static void
-bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
- const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+ const unsigned long __iomem *src, unsigned src_idx, int bits,
unsigned n, u32 bswapmask)
{
unsigned long first, last;
int const shift = dst_idx-src_idx;
- int left, right;
+
+#if 0
+ /*
+ * If you suspect bug in this function, compare it with this simple
+ * memmove implementation.
+ */
+ fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+ (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+ return;
+#endif
first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
@@ -98,9 +107,8 @@
unsigned long d0, d1;
int m;
- right = shift & (bits - 1);
- left = -shift & (bits - 1);
- bswapmask &= shift;
+ int const left = shift & (bits - 1);
+ int const right = -shift & (bits - 1);
if (dst_idx+n <= bits) {
// Single destination word
@@ -110,15 +118,15 @@
d0 = fb_rev_pixels_in_long(d0, bswapmask);
if (shift > 0) {
// Single source word
- d0 >>= right;
+ d0 <<= left;
} else if (src_idx+n <= bits) {
// Single source word
- d0 <<= left;
+ d0 >>= right;
} else {
// 2 source words
d1 = FB_READL(src + 1);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0<<left | d1>>right;
+ d0 = d0 >> right | d1 << left;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -135,60 +143,59 @@
if (shift > 0) {
// Single source word
d1 = d0;
- d0 >>= right;
- dst++;
+ d0 <<= left;
n -= bits - dst_idx;
} else {
// 2 source words
d1 = FB_READL(src++);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0<<left | d1>>right;
- dst++;
+ d0 = d0 >> right | d1 << left;
n -= bits - dst_idx;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
d0 = d1;
+ dst++;
// Main chunk
m = n % bits;
n /= bits;
while ((n >= 4) && !bswapmask) {
d1 = FB_READL(src++);
- FB_WRITEL(d0 << left | d1 >> right, dst++);
+ FB_WRITEL(d0 >> right | d1 << left, dst++);
d0 = d1;
d1 = FB_READL(src++);
- FB_WRITEL(d0 << left | d1 >> right, dst++);
+ FB_WRITEL(d0 >> right | d1 << left, dst++);
d0 = d1;
d1 = FB_READL(src++);
- FB_WRITEL(d0 << left | d1 >> right, dst++);
+ FB_WRITEL(d0 >> right | d1 << left, dst++);
d0 = d1;
d1 = FB_READL(src++);
- FB_WRITEL(d0 << left | d1 >> right, dst++);
+ FB_WRITEL(d0 >> right | d1 << left, dst++);
d0 = d1;
n -= 4;
}
while (n--) {
d1 = FB_READL(src++);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0 << left | d1 >> right;
+ d0 = d0 >> right | d1 << left;
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(d0, dst++);
d0 = d1;
}
// Trailing bits
- if (last) {
- if (m <= right) {
+ if (m) {
+ if (m <= bits - right) {
// Single source word
- d0 <<= left;
+ d0 >>= right;
} else {
// 2 source words
d1 = FB_READL(src);
d1 = fb_rev_pixels_in_long(d1,
bswapmask);
- d0 = d0<<left | d1>>right;
+ d0 = d0 >> right | d1 << left;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -202,43 +209,46 @@
*/
static void
-bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
- const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+ const unsigned long __iomem *src, unsigned src_idx, int bits,
unsigned n, u32 bswapmask)
{
unsigned long first, last;
int shift;
- dst += (n-1)/bits;
- src += (n-1)/bits;
- if ((n-1) % bits) {
- dst_idx += (n-1) % bits;
- dst += dst_idx >> (ffs(bits) - 1);
- dst_idx &= bits - 1;
- src_idx += (n-1) % bits;
- src += src_idx >> (ffs(bits) - 1);
- src_idx &= bits - 1;
- }
+#if 0
+ /*
+ * If you suspect bug in this function, compare it with this simple
+ * memmove implementation.
+ */
+ fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+ (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+ return;
+#endif
+
+ dst += (dst_idx + n - 1) / bits;
+ src += (src_idx + n - 1) / bits;
+ dst_idx = (dst_idx + n - 1) % bits;
+ src_idx = (src_idx + n - 1) % bits;
shift = dst_idx-src_idx;
- first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
- last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
- bswapmask);
+ first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask);
+ last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask);
if (!shift) {
// Same alignment for source and dest
if ((unsigned long)dst_idx+1 >= n) {
// Single word
- if (last)
- first &= last;
- FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
+ if (first)
+ last &= first;
+ FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
} else {
// Multiple destination words
// Leading bits
- if (first != ~0UL) {
+ if (first) {
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
dst--;
src--;
@@ -262,7 +272,7 @@
FB_WRITEL(FB_READL(src--), dst--);
// Trailing bits
- if (last)
+ if (last != -1UL)
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
}
} else {
@@ -270,29 +280,28 @@
unsigned long d0, d1;
int m;
- int const left = -shift & (bits-1);
- int const right = shift & (bits-1);
- bswapmask &= shift;
+ int const left = shift & (bits-1);
+ int const right = -shift & (bits-1);
if ((unsigned long)dst_idx+1 >= n) {
// Single destination word
- if (last)
- first &= last;
+ if (first)
+ last &= first;
d0 = FB_READL(src);
if (shift < 0) {
// Single source word
- d0 <<= left;
+ d0 >>= right;
} else if (1+(unsigned long)src_idx >= n) {
// Single source word
- d0 >>= right;
+ d0 <<= left;
} else {
// 2 source words
d1 = FB_READL(src - 1);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0>>right | d1<<left;
+ d0 = d0 << left | d1 >> right;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
- FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+ FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
} else {
// Multiple destination words
/** We must always remember the last value read, because in case
@@ -307,12 +316,12 @@
if (shift < 0) {
// Single source word
d1 = d0;
- d0 <<= left;
+ d0 >>= right;
} else {
// 2 source words
d1 = FB_READL(src--);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0>>right | d1<<left;
+ d0 = d0 << left | d1 >> right;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -325,39 +334,39 @@
n /= bits;
while ((n >= 4) && !bswapmask) {
d1 = FB_READL(src--);
- FB_WRITEL(d0 >> right | d1 << left, dst--);
+ FB_WRITEL(d0 << left | d1 >> right, dst--);
d0 = d1;
d1 = FB_READL(src--);
- FB_WRITEL(d0 >> right | d1 << left, dst--);
+ FB_WRITEL(d0 << left | d1 >> right, dst--);
d0 = d1;
d1 = FB_READL(src--);
- FB_WRITEL(d0 >> right | d1 << left, dst--);
+ FB_WRITEL(d0 << left | d1 >> right, dst--);
d0 = d1;
d1 = FB_READL(src--);
- FB_WRITEL(d0 >> right | d1 << left, dst--);
+ FB_WRITEL(d0 << left | d1 >> right, dst--);
d0 = d1;
n -= 4;
}
while (n--) {
d1 = FB_READL(src--);
d1 = fb_rev_pixels_in_long(d1, bswapmask);
- d0 = d0 >> right | d1 << left;
+ d0 = d0 << left | d1 >> right;
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(d0, dst--);
d0 = d1;
}
// Trailing bits
- if (last) {
- if (m <= left) {
+ if (m) {
+ if (m <= bits - left) {
// Single source word
- d0 >>= right;
+ d0 <<= left;
} else {
// 2 source words
d1 = FB_READL(src);
d1 = fb_rev_pixels_in_long(d1,
bswapmask);
- d0 = d0>>right | d1<<left;
+ d0 = d0 << left | d1 >> right;
}
d0 = fb_rev_pixels_in_long(d0, bswapmask);
FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -371,9 +380,9 @@
u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
u32 height = area->height, width = area->width;
unsigned long const bits_per_line = p->fix.line_length*8u;
- unsigned long __iomem *dst = NULL, *src = NULL;
+ unsigned long __iomem *base = NULL;
int bits = BITS_PER_LONG, bytes = bits >> 3;
- int dst_idx = 0, src_idx = 0, rev_copy = 0;
+ unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
u32 bswapmask = fb_compute_bswapmask(p);
if (p->state != FBINFO_STATE_RUNNING)
@@ -389,7 +398,7 @@
// split the base of the framebuffer into a long-aligned address and the
// index of the first bit
- dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
+ base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
// add offset of source and target area
dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
@@ -402,20 +411,14 @@
while (height--) {
dst_idx -= bits_per_line;
src_idx -= bits_per_line;
- dst += dst_idx >> (ffs(bits) - 1);
- dst_idx &= (bytes - 1);
- src += src_idx >> (ffs(bits) - 1);
- src_idx &= (bytes - 1);
- bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+ bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits,
+ base + (src_idx / bits), src_idx % bits, bits,
width*p->var.bits_per_pixel, bswapmask);
}
} else {
while (height--) {
- dst += dst_idx >> (ffs(bits) - 1);
- dst_idx &= (bytes - 1);
- src += src_idx >> (ffs(bits) - 1);
- src_idx &= (bytes - 1);
- bitcpy(p, dst, dst_idx, src, src_idx, bits,
+ bitcpy(p, base + (dst_idx / bits), dst_idx % bits,
+ base + (src_idx / bits), src_idx % bits, bits,
width*p->var.bits_per_pixel, bswapmask);
dst_idx += bits_per_line;
src_idx += bits_per_line;
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index bc922c4..37e62c7 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -6,7 +6,10 @@
config VGA_CONSOLE
bool "VGA text console" if EXPERT || !X86
- depends on !4xx && !8xx && !SPARC && !M68K && !PARISC && !FRV && !SUPERH && !BLACKFIN && !AVR32 && !MN10300 && (!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER)
+ depends on !4xx && !8xx && !SPARC && !M68K && !PARISC && !FRV && \
+ !SUPERH && !BLACKFIN && !AVR32 && !MN10300 && !CRIS && \
+ (!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER) && \
+ !ARM64
default y
help
Saying Y here will allow you to use Linux in text mode through a
diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c
index 61b182b..dbfe4ee 100644
--- a/drivers/video/console/bitblit.c
+++ b/drivers/video/console/bitblit.c
@@ -205,7 +205,6 @@
static void bit_clear_margins(struct vc_data *vc, struct fb_info *info,
int bottom_only)
{
- int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
unsigned int cw = vc->vc_font.width;
unsigned int ch = vc->vc_font.height;
unsigned int rw = info->var.xres - (vc->vc_cols*cw);
@@ -214,7 +213,7 @@
unsigned int bs = info->var.yres - bh;
struct fb_fillrect region;
- region.color = attr_bgcol_ec(bgshift, vc, info);
+ region.color = 0;
region.rop = ROP_COPY;
if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index a92783e..0d8f98c 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -404,7 +404,7 @@
struct fb_info *info = (struct fb_info *) dev_addr;
struct fbcon_ops *ops = info->fbcon_par;
- schedule_work(&info->queue);
+ queue_work(system_power_efficient_wq, &info->queue);
mod_timer(&ops->cursor_timer, jiffies + HZ/5);
}
diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c
index 41b32ae..5a3cbf6 100644
--- a/drivers/video/console/fbcon_ccw.c
+++ b/drivers/video/console/fbcon_ccw.c
@@ -197,9 +197,8 @@
unsigned int bh = info->var.xres - (vc->vc_rows*ch);
unsigned int bs = vc->vc_rows*ch;
struct fb_fillrect region;
- int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
- region.color = attr_bgcol_ec(bgshift,vc,info);
+ region.color = 0;
region.rop = ROP_COPY;
if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_cw.c b/drivers/video/console/fbcon_cw.c
index a93670e..e7ee44d 100644
--- a/drivers/video/console/fbcon_cw.c
+++ b/drivers/video/console/fbcon_cw.c
@@ -180,9 +180,8 @@
unsigned int bh = info->var.xres - (vc->vc_rows*ch);
unsigned int rs = info->var.yres - rw;
struct fb_fillrect region;
- int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
- region.color = attr_bgcol_ec(bgshift,vc,info);
+ region.color = 0;
region.rop = ROP_COPY;
if (rw && !bottom_only) {
diff --git a/drivers/video/console/fbcon_ud.c b/drivers/video/console/fbcon_ud.c
index ff0872c..19e3714 100644
--- a/drivers/video/console/fbcon_ud.c
+++ b/drivers/video/console/fbcon_ud.c
@@ -227,9 +227,8 @@
unsigned int rw = info->var.xres - (vc->vc_cols*cw);
unsigned int bh = info->var.yres - (vc->vc_rows*ch);
struct fb_fillrect region;
- int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
- region.color = attr_bgcol_ec(bgshift,vc,info);
+ region.color = 0;
region.rop = ROP_COPY;
if (rw && !bottom_only) {
diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c
index 35687fd..4ad24f2 100644
--- a/drivers/video/console/sticore.c
+++ b/drivers/video/console/sticore.c
@@ -3,7 +3,7 @@
* core code for console driver using HP's STI firmware
*
* Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
- * Copyright (C) 2001-2003 Helge Deller <deller@gmx.de>
+ * Copyright (C) 2001-2013 Helge Deller <deller@gmx.de>
* Copyright (C) 2001-2002 Thomas Bogendoerfer <tsbogend@alpha.franken.de>
*
* TODO:
@@ -30,7 +30,7 @@
#include "../sticore.h"
-#define STI_DRIVERVERSION "Version 0.9a"
+#define STI_DRIVERVERSION "Version 0.9b"
static struct sti_struct *default_sti __read_mostly;
@@ -73,28 +73,34 @@
static int sti_init_graph(struct sti_struct *sti)
{
- struct sti_init_inptr_ext inptr_ext = { 0, };
- struct sti_init_inptr inptr = {
- .text_planes = 3, /* # of text planes (max 3 for STI) */
- .ext_ptr = STI_PTR(&inptr_ext)
- };
- struct sti_init_outptr outptr = { 0, };
+ struct sti_init_inptr *inptr = &sti->sti_data->init_inptr;
+ struct sti_init_inptr_ext *inptr_ext = &sti->sti_data->init_inptr_ext;
+ struct sti_init_outptr *outptr = &sti->sti_data->init_outptr;
unsigned long flags;
- int ret;
+ int ret, err;
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->init_graph, &default_init_flags, &inptr,
- &outptr, sti->glob_cfg);
+ memset(inptr, 0, sizeof(*inptr));
+ inptr->text_planes = 3; /* # of text planes (max 3 for STI) */
+ memset(inptr_ext, 0, sizeof(*inptr_ext));
+ inptr->ext_ptr = STI_PTR(inptr_ext);
+ outptr->errno = 0;
+
+ ret = sti_call(sti, sti->init_graph, &default_init_flags, inptr,
+ outptr, sti->glob_cfg);
+
+ if (ret >= 0)
+ sti->text_planes = outptr->text_planes;
+ err = outptr->errno;
spin_unlock_irqrestore(&sti->lock, flags);
if (ret < 0) {
- printk(KERN_ERR "STI init_graph failed (ret %d, errno %d)\n",ret,outptr.errno);
+ pr_err("STI init_graph failed (ret %d, errno %d)\n", ret, err);
return -1;
}
- sti->text_planes = outptr.text_planes;
return 0;
}
@@ -104,16 +110,18 @@
static void sti_inq_conf(struct sti_struct *sti)
{
- struct sti_conf_inptr inptr = { 0, };
+ struct sti_conf_inptr *inptr = &sti->sti_data->inq_inptr;
+ struct sti_conf_outptr *outptr = &sti->sti_data->inq_outptr;
unsigned long flags;
s32 ret;
- sti->outptr.ext_ptr = STI_PTR(&sti->outptr_ext);
+ outptr->ext_ptr = STI_PTR(&sti->sti_data->inq_outptr_ext);
do {
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->inq_conf, &default_conf_flags,
- &inptr, &sti->outptr, sti->glob_cfg);
+ memset(inptr, 0, sizeof(*inptr));
+ ret = sti_call(sti, sti->inq_conf, &default_conf_flags,
+ inptr, outptr, sti->glob_cfg);
spin_unlock_irqrestore(&sti->lock, flags);
} while (ret == 1);
}
@@ -126,7 +134,8 @@
void
sti_putc(struct sti_struct *sti, int c, int y, int x)
{
- struct sti_font_inptr inptr = {
+ struct sti_font_inptr *inptr = &sti->sti_data->font_inptr;
+ struct sti_font_inptr inptr_default = {
.font_start_addr= STI_PTR(sti->font->raw),
.index = c_index(sti, c),
.fg_color = c_fg(sti, c),
@@ -134,14 +143,15 @@
.dest_x = x * sti->font_width,
.dest_y = y * sti->font_height,
};
- struct sti_font_outptr outptr = { 0, };
+ struct sti_font_outptr *outptr = &sti->sti_data->font_outptr;
s32 ret;
unsigned long flags;
do {
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->font_unpmv, &default_font_flags,
- &inptr, &outptr, sti->glob_cfg);
+ *inptr = inptr_default;
+ ret = sti_call(sti, sti->font_unpmv, &default_font_flags,
+ inptr, outptr, sti->glob_cfg);
spin_unlock_irqrestore(&sti->lock, flags);
} while (ret == 1);
}
@@ -156,7 +166,8 @@
sti_set(struct sti_struct *sti, int src_y, int src_x,
int height, int width, u8 color)
{
- struct sti_blkmv_inptr inptr = {
+ struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+ struct sti_blkmv_inptr inptr_default = {
.fg_color = color,
.bg_color = color,
.src_x = src_x,
@@ -166,14 +177,15 @@
.width = width,
.height = height,
};
- struct sti_blkmv_outptr outptr = { 0, };
+ struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
s32 ret;
unsigned long flags;
do {
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->block_move, &clear_blkmv_flags,
- &inptr, &outptr, sti->glob_cfg);
+ *inptr = inptr_default;
+ ret = sti_call(sti, sti->block_move, &clear_blkmv_flags,
+ inptr, outptr, sti->glob_cfg);
spin_unlock_irqrestore(&sti->lock, flags);
} while (ret == 1);
}
@@ -182,7 +194,8 @@
sti_clear(struct sti_struct *sti, int src_y, int src_x,
int height, int width, int c)
{
- struct sti_blkmv_inptr inptr = {
+ struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+ struct sti_blkmv_inptr inptr_default = {
.fg_color = c_fg(sti, c),
.bg_color = c_bg(sti, c),
.src_x = src_x * sti->font_width,
@@ -192,14 +205,15 @@
.width = width * sti->font_width,
.height = height* sti->font_height,
};
- struct sti_blkmv_outptr outptr = { 0, };
+ struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
s32 ret;
unsigned long flags;
do {
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->block_move, &clear_blkmv_flags,
- &inptr, &outptr, sti->glob_cfg);
+ *inptr = inptr_default;
+ ret = sti_call(sti, sti->block_move, &clear_blkmv_flags,
+ inptr, outptr, sti->glob_cfg);
spin_unlock_irqrestore(&sti->lock, flags);
} while (ret == 1);
}
@@ -212,7 +226,8 @@
sti_bmove(struct sti_struct *sti, int src_y, int src_x,
int dst_y, int dst_x, int height, int width)
{
- struct sti_blkmv_inptr inptr = {
+ struct sti_blkmv_inptr *inptr = &sti->sti_data->blkmv_inptr;
+ struct sti_blkmv_inptr inptr_default = {
.src_x = src_x * sti->font_width,
.src_y = src_y * sti->font_height,
.dest_x = dst_x * sti->font_width,
@@ -220,14 +235,15 @@
.width = width * sti->font_width,
.height = height* sti->font_height,
};
- struct sti_blkmv_outptr outptr = { 0, };
+ struct sti_blkmv_outptr *outptr = &sti->sti_data->blkmv_outptr;
s32 ret;
unsigned long flags;
do {
spin_lock_irqsave(&sti->lock, flags);
- ret = STI_CALL(sti->block_move, &default_blkmv_flags,
- &inptr, &outptr, sti->glob_cfg);
+ *inptr = inptr_default;
+ ret = sti_call(sti, sti->block_move, &default_blkmv_flags,
+ inptr, outptr, sti->glob_cfg);
spin_unlock_irqrestore(&sti->lock, flags);
} while (ret == 1);
}
@@ -284,7 +300,7 @@
-static char *font_name[MAX_STI_ROMS] = { "VGA8x16", };
+static char *font_name[MAX_STI_ROMS];
static int font_index[MAX_STI_ROMS],
font_height[MAX_STI_ROMS],
font_width[MAX_STI_ROMS];
@@ -389,10 +405,10 @@
"%d used bits\n"
"%d planes\n"
"attributes %08x\n",
- sti->outptr.bits_per_pixel,
- sti->outptr.bits_used,
- sti->outptr.planes,
- sti->outptr.attributes));
+ sti->sti_data->inq_outptr.bits_per_pixel,
+ sti->sti_data->inq_outptr.bits_used,
+ sti->sti_data->inq_outptr.planes,
+ sti->sti_data->inq_outptr.attributes));
}
static int sti_init_glob_cfg(struct sti_struct *sti, unsigned long rom_address,
@@ -402,24 +418,21 @@
struct sti_glob_cfg_ext *glob_cfg_ext;
void *save_addr;
void *sti_mem_addr;
- const int save_addr_size = 1024; /* XXX */
- int i;
+ int i, size;
- if (!sti->sti_mem_request)
+ if (sti->sti_mem_request < 256)
sti->sti_mem_request = 256; /* STI default */
- glob_cfg = kzalloc(sizeof(*sti->glob_cfg), GFP_KERNEL);
- glob_cfg_ext = kzalloc(sizeof(*glob_cfg_ext), GFP_KERNEL);
- save_addr = kzalloc(save_addr_size, GFP_KERNEL);
- sti_mem_addr = kzalloc(sti->sti_mem_request, GFP_KERNEL);
+ size = sizeof(struct sti_all_data) + sti->sti_mem_request - 256;
- if (!(glob_cfg && glob_cfg_ext && save_addr && sti_mem_addr)) {
- kfree(glob_cfg);
- kfree(glob_cfg_ext);
- kfree(save_addr);
- kfree(sti_mem_addr);
+ sti->sti_data = kzalloc(size, STI_LOWMEM);
+ if (!sti->sti_data)
return -ENOMEM;
- }
+
+ glob_cfg = &sti->sti_data->glob_cfg;
+ glob_cfg_ext = &sti->sti_data->glob_cfg_ext;
+ save_addr = &sti->sti_data->save_addr;
+ sti_mem_addr = &sti->sti_data->sti_mem_addr;
glob_cfg->ext_ptr = STI_PTR(glob_cfg_ext);
glob_cfg->save_addr = STI_PTR(save_addr);
@@ -475,32 +488,31 @@
return 0;
}
-#ifdef CONFIG_FB
+#ifdef CONFIG_FONTS
static struct sti_cooked_font *
sti_select_fbfont(struct sti_cooked_rom *cooked_rom, const char *fbfont_name)
{
- const struct font_desc *fbfont;
+ const struct font_desc *fbfont = NULL;
unsigned int size, bpc;
void *dest;
struct sti_rom_font *nf;
struct sti_cooked_font *cooked_font;
- if (!fbfont_name || !strlen(fbfont_name))
- return NULL;
- fbfont = find_font(fbfont_name);
+ if (fbfont_name && strlen(fbfont_name))
+ fbfont = find_font(fbfont_name);
if (!fbfont)
fbfont = get_default_font(1024,768, ~(u32)0, ~(u32)0);
if (!fbfont)
return NULL;
- DPRINTK((KERN_DEBUG "selected %dx%d fb-font %s\n",
- fbfont->width, fbfont->height, fbfont->name));
+ pr_info("STI selected %dx%d framebuffer font %s for sticon\n",
+ fbfont->width, fbfont->height, fbfont->name);
bpc = ((fbfont->width+7)/8) * fbfont->height;
size = bpc * 256;
size += sizeof(struct sti_rom_font);
- nf = kzalloc(size, GFP_KERNEL);
+ nf = kzalloc(size, STI_LOWMEM);
if (!nf)
return NULL;
@@ -637,7 +649,7 @@
unsigned char *n, *p, *q;
int size = f->raw->bytes_per_char*256+sizeof(struct sti_rom_font);
- n = kzalloc (4*size, GFP_KERNEL);
+ n = kzalloc(4*size, STI_LOWMEM);
if (!n)
return NULL;
p = n + 3;
@@ -673,7 +685,7 @@
sti_bmode_rom_copy(address + BMODE_LAST_ADDR_OFFS, sizeof(size), &size);
size = (size+3) / 4;
- raw = kmalloc(size, GFP_KERNEL);
+ raw = kmalloc(size, STI_LOWMEM);
if (raw) {
sti_bmode_rom_copy(address, size, raw);
memmove (&raw->res004, &raw->type[0], 0x3c);
@@ -707,7 +719,7 @@
/* read the ROM size directly from the struct in ROM */
size = gsc_readl(address + offsetof(struct sti_rom,last_addr));
- raw = kmalloc(size, GFP_KERNEL);
+ raw = kmalloc(size, STI_LOWMEM);
if (raw)
sti_rom_copy(address, size, raw);
@@ -743,6 +755,10 @@
address = (unsigned long) STI_PTR(raw);
+ pr_info("STI ROM supports 32 %sbit firmware functions.\n",
+ raw->alt_code_type == ALT_CODE_TYPE_PA_RISC_64
+ ? "and 64 " : "");
+
sti->font_unpmv = address + (raw->font_unpmv & 0x03ffffff);
sti->block_move = address + (raw->block_move & 0x03ffffff);
sti->init_graph = address + (raw->init_graph & 0x03ffffff);
@@ -901,7 +917,8 @@
sti_dump_globcfg(sti->glob_cfg, sti->sti_mem_request);
sti_dump_outptr(sti);
- printk(KERN_INFO " graphics card name: %s\n", sti->outptr.dev_name );
+ pr_info(" graphics card name: %s\n",
+ sti->sti_data->inq_outptr.dev_name);
sti_roms[num_sti_roms] = sti;
num_sti_roms++;
@@ -1073,6 +1090,29 @@
}
EXPORT_SYMBOL(sti_get_rom);
+
+int sti_call(const struct sti_struct *sti, unsigned long func,
+ const void *flags, void *inptr, void *outptr,
+ struct sti_glob_cfg *glob_cfg)
+{
+ unsigned long _flags = STI_PTR(flags);
+ unsigned long _inptr = STI_PTR(inptr);
+ unsigned long _outptr = STI_PTR(outptr);
+ unsigned long _glob_cfg = STI_PTR(glob_cfg);
+ int ret;
+
+#ifdef CONFIG_64BIT
+ /* Check for overflow when using 32bit STI on 64bit kernel. */
+ if (WARN_ONCE(_flags>>32 || _inptr>>32 || _outptr>>32 || _glob_cfg>>32,
+ "Out of 32bit-range pointers!"))
+ return -1;
+#endif
+
+ ret = pdc_sti_call(func, _flags, _inptr, _outptr, _glob_cfg);
+
+ return ret;
+}
+
MODULE_AUTHOR("Philipp Rumpf, Helge Deller, Thomas Bogendoerfer");
MODULE_DESCRIPTION("Core STI driver for HP's NGLE series graphics cards in HP PARISC machines");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/fb-puv3.c b/drivers/video/fb-puv3.c
index 27fc956..5201125 100644
--- a/drivers/video/fb-puv3.c
+++ b/drivers/video/fb-puv3.c
@@ -18,8 +18,10 @@
#include <linux/fb.h>
#include <linux/init.h>
#include <linux/console.h>
+#include <linux/mm.h>
#include <asm/sizes.h>
+#include <asm/pgtable.h>
#include <mach/hardware.h>
/* Platform_data reserved for unifb registers. */
diff --git a/drivers/video/hyperv_fb.c b/drivers/video/hyperv_fb.c
index d4d2c5f..0f3b33c 100644
--- a/drivers/video/hyperv_fb.c
+++ b/drivers/video/hyperv_fb.c
@@ -795,12 +795,21 @@
}
+static DEFINE_PCI_DEVICE_TABLE(pci_stub_id_table) = {
+ {
+ .vendor = PCI_VENDOR_ID_MICROSOFT,
+ .device = PCI_DEVICE_ID_HYPERV_VIDEO,
+ },
+ { /* end of list */ }
+};
+
static const struct hv_vmbus_device_id id_table[] = {
/* Synthetic Video Device GUID */
{HV_SYNTHVID_GUID},
{}
};
+MODULE_DEVICE_TABLE(pci, pci_stub_id_table);
MODULE_DEVICE_TABLE(vmbus, id_table);
static struct hv_driver hvfb_drv = {
@@ -810,14 +819,43 @@
.remove = hvfb_remove,
};
+static int hvfb_pci_stub_probe(struct pci_dev *pdev,
+ const struct pci_device_id *ent)
+{
+ return 0;
+}
+
+static void hvfb_pci_stub_remove(struct pci_dev *pdev)
+{
+}
+
+static struct pci_driver hvfb_pci_stub_driver = {
+ .name = KBUILD_MODNAME,
+ .id_table = pci_stub_id_table,
+ .probe = hvfb_pci_stub_probe,
+ .remove = hvfb_pci_stub_remove,
+};
static int __init hvfb_drv_init(void)
{
- return vmbus_driver_register(&hvfb_drv);
+ int ret;
+
+ ret = vmbus_driver_register(&hvfb_drv);
+ if (ret != 0)
+ return ret;
+
+ ret = pci_register_driver(&hvfb_pci_stub_driver);
+ if (ret != 0) {
+ vmbus_driver_unregister(&hvfb_drv);
+ return ret;
+ }
+
+ return 0;
}
static void __exit hvfb_drv_exit(void)
{
+ pci_unregister_driver(&hvfb_pci_stub_driver);
vmbus_driver_unregister(&hvfb_drv);
}
diff --git a/drivers/video/kyro/fbdev.c b/drivers/video/kyro/fbdev.c
index 6157f74..ec7fc87 100644
--- a/drivers/video/kyro/fbdev.c
+++ b/drivers/video/kyro/fbdev.c
@@ -625,15 +625,15 @@
}
break;
case KYRO_IOCTL_UVSTRIDE:
- if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(unsigned long)))
+ if (copy_to_user(argp, &deviceInfo.ulOverlayUVStride, sizeof(deviceInfo.ulOverlayUVStride)))
return -EFAULT;
break;
case KYRO_IOCTL_STRIDE:
- if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(unsigned long)))
+ if (copy_to_user(argp, &deviceInfo.ulOverlayStride, sizeof(deviceInfo.ulOverlayStride)))
return -EFAULT;
break;
case KYRO_IOCTL_OVERLAY_OFFSET:
- if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(unsigned long)))
+ if (copy_to_user(argp, &deviceInfo.ulOverlayOffset, sizeof(deviceInfo.ulOverlayOffset)))
return -EFAULT;
break;
}
diff --git a/drivers/video/logo/logo.c b/drivers/video/logo/logo.c
index 080c35b..cc5dbb5 100644
--- a/drivers/video/logo/logo.c
+++ b/drivers/video/logo/logo.c
@@ -25,6 +25,21 @@
module_param(nologo, bool, 0);
MODULE_PARM_DESC(nologo, "Disables startup logo");
+/*
+ * Logos are located in the initdata, and will be freed in kernel_init.
+ * Use late_init to mark the logos as freed to prevent any further use.
+ */
+
+static bool logos_freed;
+
+static int __init fb_logo_late_init(void)
+{
+ logos_freed = true;
+ return 0;
+}
+
+late_initcall(fb_logo_late_init);
+
/* logo's are marked __initdata. Use __init_refok to tell
* modpost that it is intended that this function uses data
* marked __initdata.
@@ -33,7 +48,7 @@
{
const struct linux_logo *logo = NULL;
- if (nologo)
+ if (nologo || logos_freed)
return NULL;
if (depth >= 1) {
diff --git a/drivers/video/matrox/matroxfb_accel.c b/drivers/video/matrox/matroxfb_accel.c
index 8335a6f..0d5cb85 100644
--- a/drivers/video/matrox/matroxfb_accel.c
+++ b/drivers/video/matrox/matroxfb_accel.c
@@ -192,10 +192,18 @@
minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
minfo->accel.m_opmode = mopmode;
+ minfo->accel.m_access = maccess;
+ minfo->accel.m_pitch = mpitch;
}
EXPORT_SYMBOL(matrox_cfbX_init);
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+ mga_outl(M_MACCESS, minfo->accel.m_access);
+ mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
int sx, int dy, int dx, int height, int width)
{
@@ -207,7 +215,8 @@
CRITBEGIN
if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
- mga_fifo(2);
+ mga_fifo(4);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
M_DWG_BFCOL | M_DWG_REPLACE);
mga_outl(M_AR5, vxres);
@@ -215,7 +224,8 @@
start = sy*vxres+sx+curr_ydstorg(minfo);
end = start+width;
} else {
- mga_fifo(3);
+ mga_fifo(5);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
mga_outl(M_SGN, 5);
mga_outl(M_AR5, -vxres);
@@ -224,7 +234,8 @@
start = end+width;
dy += height-1;
}
- mga_fifo(4);
+ mga_fifo(6);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_AR0, end);
mga_outl(M_AR3, start);
mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -246,7 +257,8 @@
CRITBEGIN
if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
- mga_fifo(2);
+ mga_fifo(4);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
M_DWG_BFCOL | M_DWG_REPLACE);
mga_outl(M_AR5, vxres);
@@ -254,7 +266,8 @@
start = sy*vxres+sx+curr_ydstorg(minfo);
end = start+width;
} else {
- mga_fifo(3);
+ mga_fifo(5);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
mga_outl(M_SGN, 5);
mga_outl(M_AR5, -vxres);
@@ -263,7 +276,8 @@
start = end+width;
dy += height-1;
}
- mga_fifo(5);
+ mga_fifo(7);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_AR0, end);
mga_outl(M_AR3, start);
mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -298,7 +312,8 @@
CRITBEGIN
- mga_fifo(5);
+ mga_fifo(7);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
mga_outl(M_FCOL, color);
mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -341,7 +356,8 @@
width >>= 1;
sx >>= 1;
if (width) {
- mga_fifo(5);
+ mga_fifo(7);
+ matrox_accel_restore_maccess(minfo);
mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
mga_outl(M_FCOL, bgx);
mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -415,7 +431,8 @@
CRITBEGIN
- mga_fifo(3);
+ mga_fifo(5);
+ matrox_accel_restore_maccess(minfo);
if (easy)
mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
else
@@ -425,7 +442,8 @@
fxbndry = ((xx + width - 1) << 16) | xx;
mmio = minfo->mmio.vbase;
- mga_fifo(6);
+ mga_fifo(8);
+ matrox_accel_restore_maccess(minfo);
mga_writel(mmio, M_FXBNDRY, fxbndry);
mga_writel(mmio, M_AR0, ar0);
mga_writel(mmio, M_AR3, 0);
diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h
index 11ed57b..89a8a89a 100644
--- a/drivers/video/matrox/matroxfb_base.h
+++ b/drivers/video/matrox/matroxfb_base.h
@@ -307,6 +307,8 @@
#endif
u_int32_t m_dwg_rect;
u_int32_t m_opmode;
+ u_int32_t m_access;
+ u_int32_t m_pitch;
};
struct v4l2_queryctrl;
@@ -696,7 +698,7 @@
#define mga_fifo(n) do {} while ((mga_inl(M_FIFOSTATUS) & 0xFF) < (n))
-#define WaitTillIdle() do {} while (mga_inl(M_STATUS) & 0x10000)
+#define WaitTillIdle() do { mga_inl(M_STATUS); do {} while (mga_inl(M_STATUS) & 0x10000); } while (0)
/* code speedup */
#ifdef CONFIG_FB_MATROX_MILLENIUM
diff --git a/drivers/video/sticore.h b/drivers/video/sticore.h
index addf7b6..af16195 100644
--- a/drivers/video/sticore.h
+++ b/drivers/video/sticore.h
@@ -18,6 +18,9 @@
#define STI_FONT_HPROMAN8 1
#define STI_FONT_KANA8 2
+#define ALT_CODE_TYPE_UNKNOWN 0x00 /* alt code type values */
+#define ALT_CODE_TYPE_PA_RISC_64 0x01
+
/* The latency of the STI functions cannot really be reduced by setting
* this to 0; STI doesn't seem to be designed to allow calling a different
* function (or the same function with different arguments) after a
@@ -40,14 +43,6 @@
#define STI_PTR(p) ( virt_to_phys(p) )
#define PTR_STI(p) ( phys_to_virt((unsigned long)p) )
-#define STI_CALL(func, flags, inptr, outptr, glob_cfg) \
- ({ \
- pdc_sti_call( func, STI_PTR(flags), \
- STI_PTR(inptr), \
- STI_PTR(outptr), \
- STI_PTR(glob_cfg)); \
- })
-
#define sti_onscreen_x(sti) (sti->glob_cfg->onscreen_x)
#define sti_onscreen_y(sti) (sti->glob_cfg->onscreen_y)
@@ -56,6 +51,12 @@
#define sti_font_x(sti) (PTR_STI(sti->font)->width)
#define sti_font_y(sti) (PTR_STI(sti->font)->height)
+#ifdef CONFIG_64BIT
+#define STI_LOWMEM (GFP_KERNEL | GFP_DMA)
+#else
+#define STI_LOWMEM (GFP_KERNEL)
+#endif
+
/* STI function configuration structs */
@@ -306,6 +307,34 @@
};
+/* sti_all_data is an internal struct which needs to be allocated in
+ * low memory (< 4GB) if STI is used with 32bit STI on a 64bit kernel */
+
+struct sti_all_data {
+ struct sti_glob_cfg glob_cfg;
+ struct sti_glob_cfg_ext glob_cfg_ext;
+
+ struct sti_conf_inptr inq_inptr;
+ struct sti_conf_outptr inq_outptr; /* configuration */
+ struct sti_conf_outptr_ext inq_outptr_ext;
+
+ struct sti_init_inptr_ext init_inptr_ext;
+ struct sti_init_inptr init_inptr;
+ struct sti_init_outptr init_outptr;
+
+ struct sti_blkmv_inptr blkmv_inptr;
+ struct sti_blkmv_outptr blkmv_outptr;
+
+ struct sti_font_inptr font_inptr;
+ struct sti_font_outptr font_outptr;
+
+ /* leave as last entries */
+ unsigned long save_addr[1024 / sizeof(unsigned long)];
+ /* min 256 bytes which is STI default, max sti->sti_mem_request */
+ unsigned long sti_mem_addr[256 / sizeof(unsigned long)];
+ /* do not add something below here ! */
+};
+
/* internal generic STI struct */
struct sti_struct {
@@ -330,11 +359,9 @@
region_t regions[STI_REGION_MAX];
unsigned long regions_phys[STI_REGION_MAX];
- struct sti_glob_cfg *glob_cfg;
- struct sti_cooked_font *font; /* ptr to selected font (cooked) */
+ struct sti_glob_cfg *glob_cfg; /* points into sti_all_data */
- struct sti_conf_outptr outptr; /* configuration */
- struct sti_conf_outptr_ext outptr_ext;
+ struct sti_cooked_font *font; /* ptr to selected font (cooked) */
struct pci_dev *pd;
@@ -343,6 +370,9 @@
/* pointer to the fb_info where this STI device is used */
struct fb_info *info;
+
+ /* pointer to all internal data */
+ struct sti_all_data *sti_data;
};
@@ -350,6 +380,14 @@
struct sti_struct *sti_get_rom(unsigned int index); /* 0: default sti */
+
+/* sticore main function to call STI firmware */
+
+int sti_call(const struct sti_struct *sti, unsigned long func,
+ const void *flags, void *inptr, void *outptr,
+ struct sti_glob_cfg *glob_cfg);
+
+
/* functions to call the STI ROM directly */
void sti_putc(struct sti_struct *sti, int c, int y, int x);
diff --git a/drivers/video/stifb.c b/drivers/video/stifb.c
index 876648e..019a1fe 100644
--- a/drivers/video/stifb.c
+++ b/drivers/video/stifb.c
@@ -1101,6 +1101,7 @@
var = &info->var;
fb->sti = sti;
+ dev_name = sti->sti_data->inq_outptr.dev_name;
/* store upper 32bits of the graphics id */
fb->id = fb->sti->graphics_id[0];
@@ -1114,11 +1115,11 @@
Since this driver only supports standard mode, we check
if the device name contains the string "DX" and tell the
user how to reconfigure the card. */
- if (strstr(sti->outptr.dev_name, "DX")) {
+ if (strstr(dev_name, "DX")) {
printk(KERN_WARNING
"WARNING: stifb framebuffer driver does not support '%s' in double-buffer mode.\n"
"WARNING: Please disable the double-buffer mode in IPL menu (the PARISC-BIOS).\n",
- sti->outptr.dev_name);
+ dev_name);
goto out_err0;
}
/* fall though */
@@ -1130,7 +1131,7 @@
break;
default:
printk(KERN_WARNING "stifb: '%s' (id: 0x%08x) not supported.\n",
- sti->outptr.dev_name, fb->id);
+ dev_name, fb->id);
goto out_err0;
}
@@ -1154,7 +1155,6 @@
fb->id = S9000_ID_A1659A;
break;
case S9000_ID_TIMBER: /* HP9000/710 Any (may be a grayscale device) */
- dev_name = fb->sti->outptr.dev_name;
if (strstr(dev_name, "GRAYSCALE") ||
strstr(dev_name, "Grayscale") ||
strstr(dev_name, "grayscale"))
@@ -1290,7 +1290,7 @@
var->xres,
var->yres,
var->bits_per_pixel,
- sti->outptr.dev_name,
+ dev_name,
fb->id,
fix->mmio_start);
diff --git a/drivers/video/tgafb.c b/drivers/video/tgafb.c
index c9c8e5a..a78ca6a 100644
--- a/drivers/video/tgafb.c
+++ b/drivers/video/tgafb.c
@@ -188,6 +188,8 @@
if (var->xres_virtual != var->xres || var->yres_virtual != var->yres)
return -EINVAL;
+ if (var->xres * var->yres * (var->bits_per_pixel >> 3) > info->fix.smem_len)
+ return -EINVAL;
if (var->nonstd)
return -EINVAL;
if (1000000000 / var->pixclock > TGA_PLL_MAX_FREQ)
@@ -268,6 +270,7 @@
par->yres = info->var.yres;
par->pll_freq = pll_freq = 1000000000 / info->var.pixclock;
par->bits_per_pixel = info->var.bits_per_pixel;
+ info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
tga_type = par->tga_type;
@@ -1142,222 +1145,57 @@
__raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
}
-/* The general case of forward copy in 8bpp mode. */
-static inline void
-copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
- u32 height, u32 width, u32 line_length)
-{
- struct tga_par *par = (struct tga_par *) info->par;
- unsigned long i, copied, left;
- unsigned long dpos, spos, dalign, salign, yincr;
- u32 smask_first, dmask_first, dmask_last;
- int pixel_shift, need_prime, need_second;
- unsigned long n64, n32, xincr_first;
- void __iomem *tga_regs;
- void __iomem *tga_fb;
-
- yincr = line_length;
- if (dy > sy) {
- dy += height - 1;
- sy += height - 1;
- yincr = -yincr;
- }
-
- /* Compute the offsets and alignments in the frame buffer.
- More than anything else, these control how we do copies. */
- dpos = dy * line_length + dx;
- spos = sy * line_length + sx;
- dalign = dpos & 7;
- salign = spos & 7;
- dpos &= -8;
- spos &= -8;
-
- /* Compute the value for the PIXELSHIFT register. This controls
- both non-co-aligned source and destination and copy direction. */
- if (dalign >= salign)
- pixel_shift = dalign - salign;
- else
- pixel_shift = 8 - (salign - dalign);
-
- /* Figure out if we need an additional priming step for the
- residue register. */
- need_prime = (salign > dalign);
- if (need_prime)
- dpos -= 8;
-
- /* Begin by copying the leading unaligned destination. Copy enough
- to make the next destination address 32-byte aligned. */
- copied = 32 - (dalign + (dpos & 31));
- if (copied == 32)
- copied = 0;
- xincr_first = (copied + 7) & -8;
- smask_first = dmask_first = (1ul << copied) - 1;
- smask_first <<= salign;
- dmask_first <<= dalign + need_prime*8;
- if (need_prime && copied > 24)
- copied -= 8;
- left = width - copied;
-
- /* Care for small copies. */
- if (copied > width) {
- u32 t;
- t = (1ul << width) - 1;
- t <<= dalign + need_prime*8;
- dmask_first &= t;
- left = 0;
- }
-
- /* Attempt to use 64-byte copies. This is only possible if the
- source and destination are co-aligned at 64 bytes. */
- n64 = need_second = 0;
- if ((dpos & 63) == (spos & 63)
- && (height == 1 || line_length % 64 == 0)) {
- /* We may need a 32-byte copy to ensure 64 byte alignment. */
- need_second = (dpos + xincr_first) & 63;
- if ((need_second & 32) != need_second)
- printk(KERN_ERR "tgafb: need_second wrong\n");
- if (left >= need_second + 64) {
- left -= need_second;
- n64 = left / 64;
- left %= 64;
- } else
- need_second = 0;
- }
-
- /* Copy trailing full 32-byte sections. This will be the main
- loop if the 64 byte loop can't be used. */
- n32 = left / 32;
- left %= 32;
-
- /* Copy the trailing unaligned destination. */
- dmask_last = (1ul << left) - 1;
-
- tga_regs = par->tga_regs_base;
- tga_fb = par->tga_fb_base;
-
- /* Set up the MODE and PIXELSHIFT registers. */
- __raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG);
- __raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG);
- wmb();
-
- for (i = 0; i < height; ++i) {
- unsigned long j;
- void __iomem *sfb;
- void __iomem *dfb;
-
- sfb = tga_fb + spos;
- dfb = tga_fb + dpos;
- if (dmask_first) {
- __raw_writel(smask_first, sfb);
- wmb();
- __raw_writel(dmask_first, dfb);
- wmb();
- sfb += xincr_first;
- dfb += xincr_first;
- }
-
- if (need_second) {
- __raw_writel(0xffffffff, sfb);
- wmb();
- __raw_writel(0xffffffff, dfb);
- wmb();
- sfb += 32;
- dfb += 32;
- }
-
- if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63))
- printk(KERN_ERR
- "tgafb: misaligned copy64 (s:%p, d:%p)\n",
- sfb, dfb);
-
- for (j = 0; j < n64; ++j) {
- __raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
- wmb();
- __raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
- wmb();
- sfb += 64;
- dfb += 64;
- }
-
- for (j = 0; j < n32; ++j) {
- __raw_writel(0xffffffff, sfb);
- wmb();
- __raw_writel(0xffffffff, dfb);
- wmb();
- sfb += 32;
- dfb += 32;
- }
-
- if (dmask_last) {
- __raw_writel(0xffffffff, sfb);
- wmb();
- __raw_writel(dmask_last, dfb);
- wmb();
- }
-
- spos += yincr;
- dpos += yincr;
- }
-
- /* Reset the MODE register to normal. */
- __raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
-}
-
/* The (almost) general case of backward copy in 8bpp mode. */
static inline void
-copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
- u32 height, u32 width, u32 line_length,
- const struct fb_copyarea *area)
+copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
+ u32 height, u32 width, u32 line_length,
+ const struct fb_copyarea *area)
{
struct tga_par *par = (struct tga_par *) info->par;
- unsigned long i, left, yincr;
- unsigned long depos, sepos, dealign, sealign;
- u32 mask_first, mask_last;
- unsigned long n32;
+ unsigned i, yincr;
+ int depos, sepos, backward, last_step, step;
+ u32 mask_last;
+ unsigned n32;
void __iomem *tga_regs;
void __iomem *tga_fb;
- yincr = line_length;
- if (dy > sy) {
- dy += height - 1;
- sy += height - 1;
- yincr = -yincr;
- }
-
- /* Compute the offsets and alignments in the frame buffer.
- More than anything else, these control how we do copies. */
- depos = dy * line_length + dx + width;
- sepos = sy * line_length + sx + width;
- dealign = depos & 7;
- sealign = sepos & 7;
-
- /* ??? The documentation appears to be incorrect (or very
- misleading) wrt how pixel shifting works in backward copy
- mode, i.e. when PIXELSHIFT is negative. I give up for now.
- Do handle the common case of co-aligned backward copies,
- but frob everything else back on generic code. */
- if (dealign != sealign) {
+ /* Do acceleration only if we are aligned on 8 pixels */
+ if ((dx | sx | width) & 7) {
cfb_copyarea(info, area);
return;
}
- /* We begin the copy with the trailing pixels of the
- unaligned destination. */
- mask_first = (1ul << dealign) - 1;
- left = width - dealign;
-
- /* Care for small copies. */
- if (dealign > width) {
- mask_first ^= (1ul << (dealign - width)) - 1;
- left = 0;
+ yincr = line_length;
+ if (dy > sy) {
+ dy += height - 1;
+ sy += height - 1;
+ yincr = -yincr;
}
+ backward = dy == sy && dx > sx && dx < sx + width;
+
+ /* Compute the offsets and alignments in the frame buffer.
+ More than anything else, these control how we do copies. */
+ depos = dy * line_length + dx;
+ sepos = sy * line_length + sx;
+ if (backward)
+ depos += width, sepos += width;
/* Next copy full words at a time. */
- n32 = left / 32;
- left %= 32;
+ n32 = width / 32;
+ last_step = width % 32;
/* Finally copy the unaligned head of the span. */
- mask_last = -1 << (32 - left);
+ mask_last = (1ul << last_step) - 1;
+
+ if (!backward) {
+ step = 32;
+ last_step = 32;
+ } else {
+ step = -32;
+ last_step = -last_step;
+ sepos -= 32;
+ depos -= 32;
+ }
tga_regs = par->tga_regs_base;
tga_fb = par->tga_fb_base;
@@ -1374,25 +1212,33 @@
sfb = tga_fb + sepos;
dfb = tga_fb + depos;
- if (mask_first) {
- __raw_writel(mask_first, sfb);
- wmb();
- __raw_writel(mask_first, dfb);
- wmb();
- }
- for (j = 0; j < n32; ++j) {
- sfb -= 32;
- dfb -= 32;
+ for (j = 0; j < n32; j++) {
+ if (j < 2 && j + 1 < n32 && !backward &&
+ !(((unsigned long)sfb | (unsigned long)dfb) & 63)) {
+ do {
+ __raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
+ wmb();
+ __raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
+ wmb();
+ sfb += 64;
+ dfb += 64;
+ j += 2;
+ } while (j + 1 < n32);
+ j--;
+ continue;
+ }
__raw_writel(0xffffffff, sfb);
wmb();
__raw_writel(0xffffffff, dfb);
wmb();
+ sfb += step;
+ dfb += step;
}
if (mask_last) {
- sfb -= 32;
- dfb -= 32;
+ sfb += last_step - step;
+ dfb += last_step - step;
__raw_writel(mask_last, sfb);
wmb();
__raw_writel(mask_last, dfb);
@@ -1453,14 +1299,9 @@
else if (bpp == 32)
cfb_copyarea(info, area);
- /* Detect overlapping source and destination that requires
- a backward copy. */
- else if (dy == sy && dx > sx && dx < sx + width)
- copyarea_backward_8bpp(info, dx, dy, sx, sy, height,
- width, line_length, area);
else
- copyarea_foreward_8bpp(info, dx, dy, sx, sy, height,
- width, line_length);
+ copyarea_8bpp(info, dx, dy, sx, sy, height,
+ width, line_length, area);
}
@@ -1476,6 +1317,7 @@
int tga_bus_tc = TGA_BUS_TC(par->dev);
u8 tga_type = par->tga_type;
const char *tga_type_name = NULL;
+ unsigned memory_size;
switch (tga_type) {
case TGA_TYPE_8PLANE:
@@ -1483,21 +1325,25 @@
tga_type_name = "Digital ZLXp-E1";
if (tga_bus_tc)
tga_type_name = "Digital ZLX-E1";
+ memory_size = 2097152;
break;
case TGA_TYPE_24PLANE:
if (tga_bus_pci)
tga_type_name = "Digital ZLXp-E2";
if (tga_bus_tc)
tga_type_name = "Digital ZLX-E2";
+ memory_size = 8388608;
break;
case TGA_TYPE_24PLUSZ:
if (tga_bus_pci)
tga_type_name = "Digital ZLXp-E3";
if (tga_bus_tc)
tga_type_name = "Digital ZLX-E3";
+ memory_size = 16777216;
break;
default:
tga_type_name = "Unknown";
+ memory_size = 16777216;
break;
}
@@ -1509,9 +1355,8 @@
? FB_VISUAL_PSEUDOCOLOR
: FB_VISUAL_DIRECTCOLOR);
- info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
info->fix.smem_start = (size_t) par->tga_fb_base;
- info->fix.smem_len = info->fix.line_length * par->yres;
+ info->fix.smem_len = memory_size;
info->fix.mmio_start = (size_t) par->tga_regs_base;
info->fix.mmio_len = 512;
@@ -1635,6 +1480,9 @@
modedb_tga = &modedb_tc;
modedbsize_tga = 1;
}
+
+ tgafb_init_fix(info);
+
ret = fb_find_mode(&info->var, info,
mode_option ? mode_option : mode_option_tga,
modedb_tga, modedbsize_tga, NULL,
@@ -1652,7 +1500,6 @@
}
tgafb_set_par(info);
- tgafb_init_fix(info);
if (register_framebuffer(info) < 0) {
printk(KERN_ERR "tgafb: Could not register framebuffer\n");
diff --git a/drivers/video/vexpress-dvi.c b/drivers/video/vexpress-dvi.c
new file mode 100644
index 0000000..f087534
--- /dev/null
+++ b/drivers/video/vexpress-dvi.c
@@ -0,0 +1,220 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#define pr_fmt(fmt) "vexpress-dvi: " fmt
+
+#include <linux/fb.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/vexpress.h>
+
+
+static struct vexpress_config_func *vexpress_dvimode_func;
+
+static struct {
+ u32 xres, yres, mode;
+} vexpress_dvi_dvimodes[] = {
+ { 640, 480, 0 }, /* VGA */
+ { 800, 600, 1 }, /* SVGA */
+ { 1024, 768, 2 }, /* XGA */
+ { 1280, 1024, 3 }, /* SXGA */
+ { 1600, 1200, 4 }, /* UXGA */
+ { 1920, 1080, 5 }, /* HD1080 */
+};
+
+static void vexpress_dvi_mode_set(struct fb_info *info, u32 xres, u32 yres)
+{
+ int err = -ENOENT;
+ int i;
+
+ if (!vexpress_dvimode_func)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(vexpress_dvi_dvimodes); i++) {
+ if (vexpress_dvi_dvimodes[i].xres == xres &&
+ vexpress_dvi_dvimodes[i].yres == yres) {
+ pr_debug("mode: %ux%u = %d\n", xres, yres,
+ vexpress_dvi_dvimodes[i].mode);
+ err = vexpress_config_write(vexpress_dvimode_func, 0,
+ vexpress_dvi_dvimodes[i].mode);
+ break;
+ }
+ }
+
+ if (err)
+ pr_warn("Failed to set %ux%u mode! (%d)\n", xres, yres, err);
+}
+
+
+static struct vexpress_config_func *vexpress_muxfpga_func;
+static int vexpress_dvi_fb = -1;
+
+static int vexpress_dvi_mux_set(struct fb_info *info)
+{
+ int err;
+ u32 site = vexpress_get_site_by_dev(info->device);
+
+ if (!vexpress_muxfpga_func)
+ return -ENXIO;
+
+ err = vexpress_config_write(vexpress_muxfpga_func, 0, site);
+ if (!err) {
+ pr_debug("Selected MUXFPGA input %d (fb%d)\n", site,
+ info->node);
+ vexpress_dvi_fb = info->node;
+ vexpress_dvi_mode_set(info, info->var.xres,
+ info->var.yres);
+ } else {
+ pr_warn("Failed to select MUXFPGA input %d (fb%d)! (%d)\n",
+ site, info->node, err);
+ }
+
+ return err;
+}
+
+static int vexpress_dvi_fb_select(int fb)
+{
+ int err;
+ struct fb_info *info;
+
+ /* fb0 is the default */
+ if (fb < 0)
+ fb = 0;
+
+ info = registered_fb[fb];
+ if (!info || !lock_fb_info(info))
+ return -ENODEV;
+
+ err = vexpress_dvi_mux_set(info);
+
+ unlock_fb_info(info);
+
+ return err;
+}
+
+static ssize_t vexpress_dvi_fb_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%d\n", vexpress_dvi_fb);
+}
+
+static ssize_t vexpress_dvi_fb_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+ long value;
+ int err = kstrtol(buf, 0, &value);
+
+ if (!err)
+ err = vexpress_dvi_fb_select(value);
+
+ return err ? err : count;
+}
+
+DEVICE_ATTR(fb, S_IRUGO | S_IWUSR, vexpress_dvi_fb_show,
+ vexpress_dvi_fb_store);
+
+
+static int vexpress_dvi_fb_event_notify(struct notifier_block *self,
+ unsigned long action, void *data)
+{
+ struct fb_event *event = data;
+ struct fb_info *info = event->info;
+ struct fb_videomode *mode = event->data;
+
+ switch (action) {
+ case FB_EVENT_FB_REGISTERED:
+ if (vexpress_dvi_fb < 0)
+ vexpress_dvi_mux_set(info);
+ break;
+ case FB_EVENT_MODE_CHANGE:
+ case FB_EVENT_MODE_CHANGE_ALL:
+ if (info->node == vexpress_dvi_fb)
+ vexpress_dvi_mode_set(info, mode->xres, mode->yres);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block vexpress_dvi_fb_notifier = {
+ .notifier_call = vexpress_dvi_fb_event_notify,
+};
+static bool vexpress_dvi_fb_notifier_registered;
+
+
+enum vexpress_dvi_func { FUNC_MUXFPGA, FUNC_DVIMODE };
+
+static struct of_device_id vexpress_dvi_of_match[] = {
+ {
+ .compatible = "arm,vexpress-muxfpga",
+ .data = (void *)FUNC_MUXFPGA,
+ }, {
+ .compatible = "arm,vexpress-dvimode",
+ .data = (void *)FUNC_DVIMODE,
+ },
+ {}
+};
+
+static int vexpress_dvi_probe(struct platform_device *pdev)
+{
+ enum vexpress_dvi_func func;
+ const struct of_device_id *match =
+ of_match_device(vexpress_dvi_of_match, &pdev->dev);
+
+ if (match)
+ func = (enum vexpress_dvi_func)match->data;
+ else
+ func = pdev->id_entry->driver_data;
+
+ switch (func) {
+ case FUNC_MUXFPGA:
+ vexpress_muxfpga_func =
+ vexpress_config_func_get_by_dev(&pdev->dev);
+ device_create_file(&pdev->dev, &dev_attr_fb);
+ break;
+ case FUNC_DVIMODE:
+ vexpress_dvimode_func =
+ vexpress_config_func_get_by_dev(&pdev->dev);
+ break;
+ }
+
+ if (!vexpress_dvi_fb_notifier_registered) {
+ fb_register_client(&vexpress_dvi_fb_notifier);
+ vexpress_dvi_fb_notifier_registered = true;
+ }
+
+ vexpress_dvi_fb_select(vexpress_dvi_fb);
+
+ return 0;
+}
+
+static const struct platform_device_id vexpress_dvi_id_table[] = {
+ { .name = "vexpress-muxfpga", .driver_data = FUNC_MUXFPGA, },
+ { .name = "vexpress-dvimode", .driver_data = FUNC_DVIMODE, },
+ {}
+};
+
+static struct platform_driver vexpress_dvi_driver = {
+ .probe = vexpress_dvi_probe,
+ .driver = {
+ .name = "vexpress-dvi",
+ .of_match_table = vexpress_dvi_of_match,
+ },
+ .id_table = vexpress_dvi_id_table,
+};
+
+static int __init vexpress_dvi_init(void)
+{
+ return platform_driver_register(&vexpress_dvi_driver);
+}
+device_initcall(vexpress_dvi_init);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index bd3ae32..7d7add5 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -191,7 +191,8 @@
* virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
* is true, we *have* to do it in this order
*/
- tell_host(vb, vb->deflate_vq);
+ if (vb->num_pfns != 0)
+ tell_host(vb, vb->deflate_vq);
mutex_unlock(&vb->balloon_lock);
release_pages_by_pfn(vb->pfns, vb->num_pfns);
}
@@ -310,6 +311,12 @@
else if (diff < 0)
leak_balloon(vb, -diff);
update_balloon_size(vb);
+
+ /*
+ * For large balloon changes, we could spend a lot of time
+ * and always have work to do. Be nice if preempt disabled.
+ */
+ cond_resched();
}
return 0;
}
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index a7ce730..933241a 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -791,6 +791,7 @@
struct pci_dev *pci_dev = to_pci_dev(dev);
struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
struct virtio_driver *drv;
+ unsigned status = 0;
int ret;
drv = container_of(vp_dev->vdev.dev.driver,
@@ -801,14 +802,40 @@
return ret;
pci_set_master(pci_dev);
+ /* We always start by resetting the device, in case a previous
+ * driver messed it up. */
+ vp_reset(&vp_dev->vdev);
+
+ /* Acknowledge that we've seen the device. */
+ status |= VIRTIO_CONFIG_S_ACKNOWLEDGE;
+ vp_set_status(&vp_dev->vdev, status);
+
+ /* Maybe driver failed before freeze.
+ * Restore the failed status, for debugging. */
+ status |= vp_dev->saved_status & VIRTIO_CONFIG_S_FAILED;
+ vp_set_status(&vp_dev->vdev, status);
+
+ if (!drv)
+ return 0;
+
+ /* We have a driver! */
+ status |= VIRTIO_CONFIG_S_DRIVER;
+ vp_set_status(&vp_dev->vdev, status);
+
vp_finalize_features(&vp_dev->vdev);
- if (drv && drv->restore)
+ if (drv->restore) {
ret = drv->restore(&vp_dev->vdev);
+ if (ret) {
+ status |= VIRTIO_CONFIG_S_FAILED;
+ vp_set_status(&vp_dev->vdev, status);
+ return ret;
+ }
+ }
/* Finally, tell the device we're all set */
- if (!ret)
- vp_set_status(&vp_dev->vdev, vp_dev->saved_status);
+ status |= VIRTIO_CONFIG_S_DRIVER_OK;
+ vp_set_status(&vp_dev->vdev, status);
return ret;
}
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 5217baf5..37d58f8 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -607,6 +607,55 @@
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
/**
+ * virtqueue_enable_cb_prepare - restart callbacks after disable_cb
+ * @vq: the struct virtqueue we're talking about.
+ *
+ * This re-enables callbacks; it returns current queue state
+ * in an opaque unsigned value. This value should be later tested by
+ * virtqueue_poll, to detect a possible race between the driver checking for
+ * more work, and enabling callbacks.
+ *
+ * Caller must ensure we don't call this with other virtqueue
+ * operations at the same time (except where noted).
+ */
+unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 last_used_idx;
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always do both to keep code simple. */
+ vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ vring_used_event(&vq->vring) = last_used_idx = vq->last_used_idx;
+ END_USE(vq);
+ return last_used_idx;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
+
+/**
+ * virtqueue_poll - query pending used buffers
+ * @vq: the struct virtqueue we're talking about.
+ * @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
+ *
+ * Returns "true" if there are pending used buffers in the queue.
+ *
+ * This does not need to be serialized.
+ */
+bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ virtio_mb(vq->weak_barriers);
+ return (u16)last_used_idx != vq->vring.used->idx;
+}
+EXPORT_SYMBOL_GPL(virtqueue_poll);
+
+/**
* virtqueue_enable_cb - restart callbacks after disable_cb.
* @vq: the struct virtqueue we're talking about.
*
@@ -619,25 +668,8 @@
*/
bool virtqueue_enable_cb(struct virtqueue *_vq)
{
- struct vring_virtqueue *vq = to_vvq(_vq);
-
- START_USE(vq);
-
- /* We optimistically turn back on interrupts, then check if there was
- * more to do. */
- /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
- * either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
- vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
- vring_used_event(&vq->vring) = vq->last_used_idx;
- virtio_mb(vq->weak_barriers);
- if (unlikely(more_used(vq))) {
- END_USE(vq);
- return false;
- }
-
- END_USE(vq);
- return true;
+ unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
+ return !virtqueue_poll(_vq, last_used_idx);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c
index 64bfea3..8ca1030 100644
--- a/drivers/vme/bridges/vme_ca91cx42.c
+++ b/drivers/vme/bridges/vme_ca91cx42.c
@@ -880,7 +880,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
*(u8 *)(buf + done) = ioread8(addr + done);
done += 1;
@@ -934,7 +934,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
iowrite8(*(u8 *)(buf + done), addr + done);
done += 1;
diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c
index 9c1aa4d..6342406 100644
--- a/drivers/vme/bridges/vme_tsi148.c
+++ b/drivers/vme/bridges/vme_tsi148.c
@@ -1283,7 +1283,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
*(u8 *)(buf + done) = ioread8(addr + done);
done += 1;
@@ -1365,7 +1365,7 @@
if (done == count)
goto out;
}
- if ((uintptr_t)addr & 0x2) {
+ if ((uintptr_t)(addr + done) & 0x2) {
if ((count - done) < 2) {
iowrite8(*(u8 *)(buf + done), addr + done);
done += 1;
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index 40788c9..73705af 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -54,28 +54,29 @@
struct w1_netlink_msg *hdr = (struct w1_netlink_msg *)(msg + 1);
struct w1_netlink_cmd *cmd = (struct w1_netlink_cmd *)(hdr + 1);
int avail;
+ u64 *data;
/* update kernel slave list */
w1_slave_found(dev, rn);
avail = dev->priv_size - cmd->len;
- if (avail > 8) {
- u64 *data = (void *)(cmd + 1) + cmd->len;
+ if (avail < 8) {
+ msg->ack++;
+ cn_netlink_send(msg, 0, GFP_KERNEL);
- *data = rn;
- cmd->len += 8;
- hdr->len += 8;
- msg->len += 8;
- return;
+ msg->len = sizeof(struct w1_netlink_msg) +
+ sizeof(struct w1_netlink_cmd);
+ hdr->len = sizeof(struct w1_netlink_cmd);
+ cmd->len = 0;
}
- msg->ack++;
- cn_netlink_send(msg, 0, GFP_KERNEL);
+ data = (void *)(cmd + 1) + cmd->len;
- msg->len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd);
- hdr->len = sizeof(struct w1_netlink_cmd);
- cmd->len = 0;
+ *data = rn;
+ cmd->len += 8;
+ hdr->len += 8;
+ msg->len += 8;
}
static int w1_process_search_command(struct w1_master *dev, struct cn_msg *msg,
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 37cb09b..c97a47c 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -20,6 +20,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/bitops.h>
+#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/init.h>
@@ -91,6 +92,15 @@
static inline void ath79_wdt_enable(void)
{
ath79_wdt_keepalive();
+
+ /*
+ * Updating the TIMER register requires a few microseconds
+ * on the AR934x SoCs at least. Use a small delay to ensure
+ * that the TIMER register is updated within the hardware
+ * before enabling the watchdog.
+ */
+ udelay(2);
+
ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR);
/* flush write */
ath79_wdt_rr(WDOG_REG_CTRL);
diff --git a/drivers/watchdog/sc1200wdt.c b/drivers/watchdog/sc1200wdt.c
index 3fb83b0..ab6d3f5 100644
--- a/drivers/watchdog/sc1200wdt.c
+++ b/drivers/watchdog/sc1200wdt.c
@@ -409,8 +409,9 @@
#if defined CONFIG_PNP
/* now that the user has specified an IO port and we haven't detected
* any devices, disable pnp support */
+ if (isapnp)
+ pnp_unregister_driver(&scl200wdt_pnp_driver);
isapnp = 0;
- pnp_unregister_driver(&scl200wdt_pnp_driver);
#endif
if (!request_region(io, io_len, SC1200_MODULE_NAME)) {
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 8872642..e421182 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -60,7 +60,6 @@
* @adev: amba device structure of wdt
* @status: current status of wdt
* @load_val: load value to be set for current timeout
- * @timeout: current programmed timeout
*/
struct sp805_wdt {
struct watchdog_device wdd;
@@ -69,7 +68,6 @@
struct clk *clk;
struct amba_device *adev;
unsigned int load_val;
- unsigned int timeout;
};
static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -99,7 +97,7 @@
spin_lock(&wdt->lock);
wdt->load_val = load;
/* roundup timeout to closest positive integer value */
- wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
+ wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
spin_unlock(&wdt->lock);
return 0;
diff --git a/drivers/watchdog/ts72xx_wdt.c b/drivers/watchdog/ts72xx_wdt.c
index b8a9245..9ad2bd3 100644
--- a/drivers/watchdog/ts72xx_wdt.c
+++ b/drivers/watchdog/ts72xx_wdt.c
@@ -310,7 +310,8 @@
case WDIOC_GETSTATUS:
case WDIOC_GETBOOTSTATUS:
- return put_user(0, p);
+ error = put_user(0, p);
+ break;
case WDIOC_KEEPALIVE:
ts72xx_wdt_kick(wdt);
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 6a6bbe4..1faa130 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -346,7 +346,7 @@
for_each_possible_cpu(i)
memset(per_cpu(cpu_evtchn_mask, i),
- (i == 0) ? ~0 : 0, sizeof(*per_cpu(cpu_evtchn_mask, i)));
+ (i == 0) ? ~0 : 0, NR_EVENT_CHANNELS/8);
}
static inline void clear_evtchn(int port)
@@ -1492,8 +1492,10 @@
/* Rebind an evtchn so that it gets delivered to a specific cpu */
static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu)
{
+ struct shared_info *s = HYPERVISOR_shared_info;
struct evtchn_bind_vcpu bind_vcpu;
int evtchn = evtchn_from_irq(irq);
+ int masked;
if (!VALID_EVTCHN(evtchn))
return -1;
@@ -1510,6 +1512,12 @@
bind_vcpu.vcpu = tcpu;
/*
+ * Mask the event while changing the VCPU binding to prevent
+ * it being delivered on an unexpected VCPU.
+ */
+ masked = sync_test_and_set_bit(evtchn, BM(s->evtchn_mask));
+
+ /*
* If this fails, it usually just indicates that we're dealing with a
* virq or IPI channel, which don't actually need to be rebound. Ignore
* it, but don't do the xenlinux-level rebind in that case.
@@ -1517,6 +1525,9 @@
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
bind_evtchn_to_cpu(evtchn, tcpu);
+ if (!masked)
+ unmask_evtchn(evtchn);
+
return 0;
}
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 45c8efa..34924fb 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -377,18 +377,12 @@
if (unbind.port >= NR_EVENT_CHANNELS)
break;
- spin_lock_irq(&port_user_lock);
-
rc = -ENOTCONN;
- if (get_port_user(unbind.port) != u) {
- spin_unlock_irq(&port_user_lock);
+ if (get_port_user(unbind.port) != u)
break;
- }
disable_irq(irq_from_evtchn(unbind.port));
- spin_unlock_irq(&port_user_lock);
-
evtchn_unbind_from_user(u, unbind.port);
rc = 0;
@@ -488,26 +482,15 @@
int i;
struct per_user_data *u = filp->private_data;
- spin_lock_irq(&port_user_lock);
-
- free_page((unsigned long)u->ring);
-
for (i = 0; i < NR_EVENT_CHANNELS; i++) {
if (get_port_user(i) != u)
continue;
disable_irq(irq_from_evtchn(i));
- }
-
- spin_unlock_irq(&port_user_lock);
-
- for (i = 0; i < NR_EVENT_CHANNELS; i++) {
- if (get_port_user(i) != u)
- continue;
-
evtchn_unbind_from_user(get_port_user(i), i);
}
+ free_page((unsigned long)u->ring);
kfree(u->name);
kfree(u);
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 04c1b2d..840604e 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -729,9 +729,18 @@
void (*fn)(void *), void *arg, u16 count)
{
unsigned long flags;
+ struct gnttab_free_callback *cb;
+
spin_lock_irqsave(&gnttab_list_lock, flags);
- if (callback->next)
- goto out;
+
+ /* Check if the callback is already on the list */
+ cb = gnttab_free_callback_list;
+ while (cb) {
+ if (cb == callback)
+ goto out;
+ cb = cb->next;
+ }
+
callback->fn = fn;
callback->arg = arg;
callback->count = count;
@@ -911,9 +920,10 @@
ret = m2p_add_override(mfn, pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
- return ret;
+ goto out;
}
+ out:
if (lazy)
arch_leave_lazy_mmu_mode();
@@ -944,9 +954,10 @@
ret = m2p_remove_override(pages[i], kmap_ops ?
&kmap_ops[i] : NULL);
if (ret)
- return ret;
+ goto out;
}
+ out:
if (lazy)
arch_leave_lazy_mmu_mode();
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 46ae0f9..75fe3d4 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -16,7 +16,7 @@
#include "conf_space.h"
#include "conf_space_quirks.h"
-static bool permissive;
+bool permissive;
module_param(permissive, bool, 0644);
/* This is where xen_pcibk_read_config_byte, xen_pcibk_read_config_word,
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
index e56c934..2e1d73d 100644
--- a/drivers/xen/xen-pciback/conf_space.h
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -64,6 +64,8 @@
void *data;
};
+extern bool permissive;
+
#define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
/* Add fields to a device - the add_fields macro expects to get a pointer to
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index 3daf862..a5bb81a 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -9,6 +9,10 @@
#include "pciback.h"
#include "conf_space.h"
+struct pci_cmd_info {
+ u16 val;
+};
+
struct pci_bar_info {
u32 val;
u32 len_val;
@@ -18,21 +22,35 @@
#define is_enable_cmd(value) ((value)&(PCI_COMMAND_MEMORY|PCI_COMMAND_IO))
#define is_master_cmd(value) ((value)&PCI_COMMAND_MASTER)
+/* Bits guests are allowed to control in permissive mode. */
+#define PCI_COMMAND_GUEST (PCI_COMMAND_MASTER|PCI_COMMAND_SPECIAL| \
+ PCI_COMMAND_INVALIDATE|PCI_COMMAND_VGA_PALETTE| \
+ PCI_COMMAND_WAIT|PCI_COMMAND_FAST_BACK)
+
+static void *command_init(struct pci_dev *dev, int offset)
+{
+ struct pci_cmd_info *cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+ int err;
+
+ if (!cmd)
+ return ERR_PTR(-ENOMEM);
+
+ err = pci_read_config_word(dev, PCI_COMMAND, &cmd->val);
+ if (err) {
+ kfree(cmd);
+ return ERR_PTR(err);
+ }
+
+ return cmd;
+}
+
static int command_read(struct pci_dev *dev, int offset, u16 *value, void *data)
{
- int i;
- int ret;
+ int ret = pci_read_config_word(dev, offset, value);
+ const struct pci_cmd_info *cmd = data;
- ret = xen_pcibk_read_config_word(dev, offset, value, data);
- if (!pci_is_enabled(dev))
- return ret;
-
- for (i = 0; i < PCI_ROM_RESOURCE; i++) {
- if (dev->resource[i].flags & IORESOURCE_IO)
- *value |= PCI_COMMAND_IO;
- if (dev->resource[i].flags & IORESOURCE_MEM)
- *value |= PCI_COMMAND_MEMORY;
- }
+ *value &= PCI_COMMAND_GUEST;
+ *value |= cmd->val & ~PCI_COMMAND_GUEST;
return ret;
}
@@ -41,6 +59,8 @@
{
struct xen_pcibk_dev_data *dev_data;
int err;
+ u16 val;
+ struct pci_cmd_info *cmd = data;
dev_data = pci_get_drvdata(dev);
if (!pci_is_enabled(dev) && is_enable_cmd(value)) {
@@ -83,6 +103,19 @@
}
}
+ cmd->val = value;
+
+ if (!permissive && (!dev_data || !dev_data->permissive))
+ return 0;
+
+ /* Only allow the guest to control certain bits. */
+ err = pci_read_config_word(dev, offset, &val);
+ if (err || val == value)
+ return err;
+
+ value &= PCI_COMMAND_GUEST;
+ value |= val & ~PCI_COMMAND_GUEST;
+
return pci_write_config_word(dev, offset, value);
}
@@ -282,6 +315,8 @@
{
.offset = PCI_COMMAND,
.size = 2,
+ .init = command_init,
+ .release = bar_release,
.u.w.read = command_read,
.u.w.write = command_write,
},
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index d9a4367..9cca0ea 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -126,7 +126,7 @@
{
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
if (entry_ino == (u32)(long)dentry->d_fsdata) {
dentry->d_fsdata = (void *)inode->i_ino;
break;
diff --git a/fs/aio.c b/fs/aio.c
index 2bbcacf..ded94c4 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -310,7 +310,6 @@
avail = (head <= ctx->tail ? ctx->tail : ctx->nr_events) - head;
- atomic_sub(avail, &ctx->reqs_active);
head += avail;
head %= ctx->nr_events;
}
@@ -423,10 +422,12 @@
* when the processes owning a context have all exited to encourage
* the rapid destruction of the kioctx.
*/
-static void kill_ioctx(struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
{
if (!atomic_xchg(&ctx->dead, 1)) {
+ spin_lock(&mm->ioctx_lock);
hlist_del_rcu(&ctx->list);
+ spin_unlock(&mm->ioctx_lock);
/*
* It'd be more correct to do this in free_ioctx(), after all
@@ -494,7 +495,7 @@
*/
ctx->mmap_size = 0;
- kill_ioctx(ctx);
+ kill_ioctx(mm, ctx);
}
}
@@ -676,6 +677,7 @@
put_rq:
/* everything turned out well, dispose of the aiocb. */
aio_put_req(iocb);
+ atomic_dec(&ctx->reqs_active);
/*
* We have to order our ring_info tail store above and test
@@ -715,6 +717,8 @@
if (head == ctx->tail)
goto out;
+ head %= ctx->nr_events;
+
while (ret < nr) {
long avail;
struct io_event *ev;
@@ -753,8 +757,6 @@
flush_dcache_page(ctx->ring_pages[0]);
pr_debug("%li h%u t%u\n", ret, head, ctx->tail);
-
- atomic_sub(ret, &ctx->reqs_active);
out:
mutex_unlock(&ctx->ring_lock);
@@ -852,7 +854,7 @@
if (!IS_ERR(ioctx)) {
ret = put_user(ioctx->user_id, ctxp);
if (ret)
- kill_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
put_ioctx(ioctx);
}
@@ -870,7 +872,7 @@
{
struct kioctx *ioctx = lookup_ioctx(ctx);
if (likely(NULL != ioctx)) {
- kill_ioctx(ioctx);
+ kill_ioctx(current->mm, ioctx);
put_ioctx(ioctx);
return 0;
}
diff --git a/fs/attr.c b/fs/attr.c
index 1449adb..66fa625 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@
if ((ia_valid & ATTR_UID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
!uid_eq(attr->ia_uid, inode->i_uid)) &&
- !inode_capable(inode, CAP_CHOWN))
+ !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) &&
(!uid_eq(current_fsuid(), inode->i_uid) ||
(!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
- !inode_capable(inode, CAP_CHOWN))
+ !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
return -EPERM;
/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@
/* Also check the setgid bit! */
if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
inode->i_gid) &&
- !inode_capable(inode, CAP_FSETID))
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
@@ -160,7 +160,7 @@
umode_t mode = attr->ia_mode;
if (!in_group_p(inode->i_gid) &&
- !inode_capable(inode, CAP_FSETID))
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
mode &= ~S_ISGID;
inode->i_mode = mode;
}
@@ -182,11 +182,6 @@
return -EPERM;
}
- if ((ia_valid & ATTR_SIZE) && IS_I_VERSION(inode)) {
- if (attr->ia_size != inode->i_size)
- inode_inc_iversion(inode);
- }
-
if ((ia_valid & ATTR_MODE)) {
umode_t amode = attr->ia_mode;
/* Flag setting protected by i_mutex */
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 743c7c2..6aa8312 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -95,7 +95,7 @@
*/
static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in)
{
- struct autofs_dev_ioctl tmp;
+ struct autofs_dev_ioctl tmp, *res;
if (copy_from_user(&tmp, in, sizeof(tmp)))
return ERR_PTR(-EFAULT);
@@ -103,7 +103,11 @@
if (tmp.size < sizeof(tmp))
return ERR_PTR(-EINVAL);
- return memdup_user(in, tmp.size);
+ res = memdup_user(in, tmp.size);
+ if (!IS_ERR(res))
+ res->size = tmp.size;
+
+ return res;
}
static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 13ddec9..8ad2779 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -91,7 +91,7 @@
spin_lock(&root->d_lock);
if (prev)
- next = prev->d_u.d_child.next;
+ next = prev->d_child.next;
else {
prev = dget_dlock(root);
next = prev->d_subdirs.next;
@@ -105,13 +105,13 @@
return NULL;
}
- q = list_entry(next, struct dentry, d_u.d_child);
+ q = list_entry(next, struct dentry, d_child);
spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
/* Already gone or negative dentry (under construction) - try next */
if (q->d_count == 0 || !simple_positive(q)) {
spin_unlock(&q->d_lock);
- next = q->d_u.d_child.next;
+ next = q->d_child.next;
goto cont;
}
dget_dlock(q);
@@ -161,13 +161,13 @@
goto relock;
}
spin_unlock(&p->d_lock);
- next = p->d_u.d_child.next;
+ next = p->d_child.next;
p = parent;
if (next != &parent->d_subdirs)
break;
}
}
- ret = list_entry(next, struct dentry, d_u.d_child);
+ ret = list_entry(next, struct dentry, d_child);
spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED);
/* Negative dentry - try next */
@@ -447,7 +447,7 @@
spin_lock(&sbi->lookup_lock);
spin_lock(&expired->d_parent->d_lock);
spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
+ list_move(&expired->d_parent->d_subdirs, &expired->d_child);
spin_unlock(&expired->d_lock);
spin_unlock(&expired->d_parent->d_lock);
spin_unlock(&sbi->lookup_lock);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 085da86..79ab4cb3 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -655,7 +655,7 @@
/* only consider parents below dentrys in the root */
if (IS_ROOT(parent->d_parent))
return;
- d_child = &dentry->d_u.d_child;
+ d_child = &dentry->d_child;
/* Set parent managed if it's becoming empty */
if (d_child->next == &parent->d_subdirs &&
d_child->prev == &parent->d_subdirs)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f8a0b0e..53f620a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -552,11 +552,12 @@
static unsigned long randomize_stack_top(unsigned long stack_top)
{
- unsigned int random_variable = 0;
+ unsigned long random_variable = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
- random_variable = get_random_int() & STACK_RND_MASK;
+ random_variable = (unsigned long) get_random_int();
+ random_variable &= STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
#ifdef CONFIG_STACK_GROWSUP
@@ -755,6 +756,7 @@
i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long k, vaddr;
+ unsigned long total_size = 0;
if (elf_ppnt->p_type != PT_LOAD)
continue;
@@ -819,10 +821,16 @@
#else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#endif
+ total_size = total_mapping_size(elf_phdata,
+ loc->elf_ex.e_phnum);
+ if (!total_size) {
+ error = -EINVAL;
+ goto out_free_dentry;
+ }
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
- elf_prot, elf_flags, 0);
+ elf_prot, elf_flags, total_size);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
retval = IS_ERR((void *)error) ?
@@ -1415,7 +1423,7 @@
* long file_ofs
* followed by COUNT filenames in ASCII: "FILE1" NUL "FILE2" NUL...
*/
-static void fill_files_note(struct memelfnote *note)
+static int fill_files_note(struct memelfnote *note)
{
struct vm_area_struct *vma;
unsigned count, size, names_ofs, remaining, n;
@@ -1430,11 +1438,11 @@
names_ofs = (2 + 3 * count) * sizeof(data[0]);
alloc:
if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
- goto err;
+ return -EINVAL;
size = round_up(size, PAGE_SIZE);
data = vmalloc(size);
if (!data)
- goto err;
+ return -ENOMEM;
start_end_ofs = data + 2;
name_base = name_curpos = ((char *)data) + names_ofs;
@@ -1487,7 +1495,7 @@
size = name_curpos - (char *)data;
fill_note(note, "CORE", NT_FILE, size, data);
- err: ;
+ return 0;
}
#ifdef CORE_DUMP_USE_REGSET
@@ -1688,8 +1696,8 @@
fill_auxv_note(&info->auxv, current->mm);
info->size += notesize(&info->auxv);
- fill_files_note(&info->files);
- info->size += notesize(&info->files);
+ if (fill_files_note(&info->files) == 0)
+ info->size += notesize(&info->files);
return 1;
}
@@ -1721,7 +1729,8 @@
return 0;
if (first && !writenote(&info->auxv, file, foffset))
return 0;
- if (first && !writenote(&info->files, file, foffset))
+ if (first && info->files.data &&
+ !writenote(&info->files, file, foffset))
return 0;
for (i = 1; i < info->thread_notes; ++i)
@@ -1808,6 +1817,7 @@
struct elf_note_info {
struct memelfnote *notes;
+ struct memelfnote *notes_files;
struct elf_prstatus *prstatus; /* NT_PRSTATUS */
struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */
struct list_head thread_list;
@@ -1898,9 +1908,12 @@
fill_siginfo_note(info->notes + 2, &info->csigdata, siginfo);
fill_auxv_note(info->notes + 3, current->mm);
- fill_files_note(info->notes + 4);
+ info->numnote = 4;
- info->numnote = 5;
+ if (fill_files_note(info->notes + info->numnote) == 0) {
+ info->notes_files = info->notes + info->numnote;
+ info->numnote++;
+ }
/* Try to dump the FPU. */
info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs,
@@ -1962,8 +1975,9 @@
kfree(list_entry(tmp, struct elf_thread_status, list));
}
- /* Free data allocated by fill_files_note(): */
- vfree(info->notes[4].data);
+ /* Free data possibly allocated by fill_files_note(): */
+ if (info->notes_files)
+ vfree(info->notes_files->data);
kfree(info->prstatus);
kfree(info->psinfo);
@@ -2046,7 +2060,7 @@
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff, foffset;
- struct elf_note_info info;
+ struct elf_note_info info = { };
struct elf_phdr *phdr4note = NULL;
struct elf_shdr *shdr4extnum = NULL;
Elf_Half e_phnum;
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 8fb42916..433c3b8 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -114,6 +114,14 @@
}
EXPORT_SYMBOL(bio_integrity_free);
+static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
+{
+ if (bip->bip_slab == BIO_POOL_NONE)
+ return BIP_INLINE_VECS;
+
+ return bvec_nr_vecs(bip->bip_slab);
+}
+
/**
* bio_integrity_add_page - Attach integrity metadata
* @bio: bio to update
@@ -129,7 +137,7 @@
struct bio_integrity_payload *bip = bio->bi_integrity;
struct bio_vec *iv;
- if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
+ if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
printk(KERN_ERR "%s: bip_vec full\n", __func__);
return 0;
}
@@ -450,7 +458,7 @@
bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
bix.sector_size = bi->sector_size;
- bio_for_each_segment(bv, bio, i) {
+ bio_for_each_segment_all(bv, bio, i) {
void *kaddr = kmap_atomic(bv->bv_page);
bix.data_buf = kaddr + bv->bv_offset;
bix.data_size = bv->bv_len;
@@ -734,7 +742,7 @@
mempool_destroy(bs->bio_integrity_pool);
if (bs->bvec_integrity_pool)
- mempool_destroy(bs->bio_integrity_pool);
+ mempool_destroy(bs->bvec_integrity_pool);
}
EXPORT_SYMBOL(bioset_integrity_free);
diff --git a/fs/bio.c b/fs/bio.c
index 94bbc04..5e7507d 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -917,8 +917,8 @@
src_p = kmap_atomic(src_bv->bv_page);
dst_p = kmap_atomic(dst_bv->bv_page);
- memcpy(dst_p + dst_bv->bv_offset,
- src_p + src_bv->bv_offset,
+ memcpy(dst_p + dst_offset,
+ src_p + src_offset,
bytes);
kunmap_atomic(dst_p);
@@ -1045,12 +1045,22 @@
int bio_uncopy_user(struct bio *bio)
{
struct bio_map_data *bmd = bio->bi_private;
- int ret = 0;
+ struct bio_vec *bvec;
+ int ret = 0, i;
- if (!bio_flagged(bio, BIO_NULL_MAPPED))
- ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
- bmd->nr_sgvecs, bio_data_dir(bio) == READ,
- 0, bmd->is_our_pages);
+ if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+ /*
+ * if we're in a workqueue, the request is orphaned, so
+ * don't copy into a random user address space, just free.
+ */
+ if (current->mm)
+ ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+ bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+ 0, bmd->is_our_pages);
+ else if (bmd->is_our_pages)
+ bio_for_each_segment_all(bvec, bio, i)
+ __free_page(bvec->bv_page);
+ }
bio_free_map_data(bmd);
bio_put(bio);
return ret;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2091db8..85f5c85 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -58,17 +58,24 @@
struct backing_dev_info *dst)
{
struct backing_dev_info *old = inode->i_data.backing_dev_info;
+ bool wakeup_bdi = false;
if (unlikely(dst == old)) /* deadlock avoidance */
return;
bdi_lock_two(&old->wb, &dst->wb);
spin_lock(&inode->i_lock);
inode->i_data.backing_dev_info = dst;
- if (inode->i_state & I_DIRTY)
+ if (inode->i_state & I_DIRTY) {
+ if (bdi_cap_writeback_dirty(dst) && !wb_has_dirty_io(&dst->wb))
+ wakeup_bdi = true;
list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+ }
spin_unlock(&inode->i_lock);
spin_unlock(&old->wb.list_lock);
spin_unlock(&dst->wb.list_lock);
+
+ if (wakeup_bdi)
+ bdi_wakeup_thread_delayed(dst);
}
/* Kill _all_ buffers and pagecache , dirty or not.. */
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index e15d2b0..0890c83 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -229,7 +229,7 @@
if (ret > 0) {
/* we need an acl */
ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS);
- } else {
+ } else if (ret < 0) {
cache_no_acl(inode);
}
} else {
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 290e347..d85f90c 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1347,9 +1347,10 @@
* returns <0 on error
*/
static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- struct btrfs_extent_inline_ref **out_eiref,
- int *out_type)
+ struct btrfs_key *key,
+ struct btrfs_extent_item *ei, u32 item_size,
+ struct btrfs_extent_inline_ref **out_eiref,
+ int *out_type)
{
unsigned long end;
u64 flags;
@@ -1359,19 +1360,26 @@
/* first call */
flags = btrfs_extent_flags(eb, ei);
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
- info = (struct btrfs_tree_block_info *)(ei + 1);
- *out_eiref =
- (struct btrfs_extent_inline_ref *)(info + 1);
+ if (key->type == BTRFS_METADATA_ITEM_KEY) {
+ /* a skinny metadata extent */
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(ei + 1);
+ } else {
+ WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+ info = (struct btrfs_tree_block_info *)(ei + 1);
+ *out_eiref =
+ (struct btrfs_extent_inline_ref *)(info + 1);
+ }
} else {
*out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
}
*ptr = (unsigned long)*out_eiref;
- if ((void *)*ptr >= (void *)ei + item_size)
+ if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
return -ENOENT;
}
end = (unsigned long)ei + item_size;
- *out_eiref = (struct btrfs_extent_inline_ref *)*ptr;
+ *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
*out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
*ptr += btrfs_extent_inline_ref_size(*out_type);
@@ -1390,8 +1398,8 @@
* <0 on error.
*/
int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- u64 *out_root, u8 *out_level)
+ struct btrfs_key *key, struct btrfs_extent_item *ei,
+ u32 item_size, u64 *out_root, u8 *out_level)
{
int ret;
int type;
@@ -1402,8 +1410,8 @@
return 1;
while (1) {
- ret = __get_extent_inline_ref(ptr, eb, ei, item_size,
- &eiref, &type);
+ ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+ &eiref, &type);
if (ret < 0)
return ret;
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 0f446d7..526d09e 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -42,8 +42,8 @@
u64 *flags);
int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
- struct btrfs_extent_item *ei, u32 item_size,
- u64 *out_root, u8 *out_level);
+ struct btrfs_key *key, struct btrfs_extent_item *ei,
+ u32 item_size, u64 *out_root, u8 *out_level);
int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
u64 extent_item_objectid,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b189bd1..ce70678 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1009,6 +1009,8 @@
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+ if (*pg_index == (vcnt - 1) && *pg_offset == 0)
+ memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
kunmap_atomic(kaddr);
flush_dcache_page(page_out);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 02fae7f..7fb054b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1089,7 +1089,8 @@
btrfs_set_node_ptr_generation(parent, parent_slot,
trans->transid);
btrfs_mark_buffer_dirty(parent);
- tree_mod_log_free_eb(root->fs_info, buf);
+ if (last_ref)
+ tree_mod_log_free_eb(root->fs_info, buf);
btrfs_free_tree_block(trans, root, buf, parent_start,
last_ref);
}
@@ -1161,8 +1162,8 @@
* time_seq).
*/
static void
-__tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq,
- struct tree_mod_elem *first_tm)
+__tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
+ u64 time_seq, struct tree_mod_elem *first_tm)
{
u32 n;
struct rb_node *next;
@@ -1172,6 +1173,7 @@
unsigned long p_size = sizeof(struct btrfs_key_ptr);
n = btrfs_header_nritems(eb);
+ tree_mod_log_read_lock(fs_info);
while (tm && tm->seq >= time_seq) {
/*
* all the operations are recorded with the operator used for
@@ -1226,6 +1228,7 @@
if (tm->index != first_tm->index)
break;
}
+ tree_mod_log_read_unlock(fs_info);
btrfs_set_header_nritems(eb, n);
}
@@ -1274,7 +1277,7 @@
extent_buffer_get(eb_rewin);
btrfs_tree_read_lock(eb_rewin);
- __tree_mod_log_rewind(eb_rewin, time_seq, tm);
+ __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm);
WARN_ON(btrfs_header_nritems(eb_rewin) >
BTRFS_NODEPTRS_PER_BLOCK(fs_info->tree_root));
@@ -1350,7 +1353,7 @@
btrfs_set_header_generation(eb, old_generation);
}
if (tm)
- __tree_mod_log_rewind(eb, time_seq, tm);
+ __tree_mod_log_rewind(root->fs_info, eb, time_seq, tm);
else
WARN_ON(btrfs_header_level(eb) != 0);
WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(root));
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index f26f38c..019fc5a 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1843,6 +1843,14 @@
struct btrfs_delayed_node *delayed_node;
int ret = 0;
+ /*
+ * we don't do delayed inode updates during log recovery because it
+ * leads to enospc problems. This means we also can't do
+ * delayed inode refs
+ */
+ if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+ return -EAGAIN;
+
delayed_node = btrfs_get_or_create_delayed_node(inode);
if (IS_ERR(delayed_node))
return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b8b60b6..7360f03 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3161,6 +3161,8 @@
/* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_send++;
continue;
@@ -3175,6 +3177,8 @@
/* wait for all the barriers */
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_wait++;
continue;
@@ -3514,6 +3518,11 @@
btrfs_free_block_groups(fs_info);
+ /*
+ * we must make sure there is not any read request to
+ * submit after we stopping all workers.
+ */
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
del_fs_roots(fs_info);
@@ -3848,12 +3857,6 @@
if (ret)
break;
- /* opt_discard */
- if (btrfs_test_opt(root, DISCARD))
- ret = btrfs_error_discard_extent(root, start,
- end + 1 - start,
- NULL);
-
clear_extent_dirty(unpin, start, end, GFP_NOFS);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index df472ab..07f167a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2402,6 +2402,8 @@
default:
WARN_ON(1);
}
+ } else {
+ list_del_init(&locked_ref->cluster);
}
spin_unlock(&delayed_refs->lock);
@@ -2424,7 +2426,6 @@
* list before we release it.
*/
if (btrfs_delayed_ref_is_head(ref)) {
- list_del_init(&locked_ref->cluster);
btrfs_delayed_ref_unlock(locked_ref);
locked_ref = NULL;
}
@@ -5276,7 +5277,8 @@
update_global_block_rsv(fs_info);
}
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+ const bool return_free_space)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_block_group_cache *cache = NULL;
@@ -5300,7 +5302,8 @@
if (start < cache->last_byte_to_unpin) {
len = min(len, cache->last_byte_to_unpin - start);
- btrfs_add_free_space(cache, start, len);
+ if (return_free_space)
+ btrfs_add_free_space(cache, start, len);
}
start += len;
@@ -5363,7 +5366,7 @@
end + 1 - start, NULL);
clear_extent_dirty(unpin, start, end, GFP_NOFS);
- unpin_extent_range(root, start, end);
+ unpin_extent_range(root, start, end, true);
cond_resched();
}
@@ -6360,12 +6363,11 @@
return -ENOSPC;
}
- if (btrfs_test_opt(root, DISCARD))
- ret = btrfs_discard_extent(root, start, len, NULL);
-
if (pin)
pin_down_extent(root, cache, start, len, 1);
else {
+ if (btrfs_test_opt(root, DISCARD))
+ ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
btrfs_update_reserved_bytes(cache, len, RESERVE_FREE);
}
@@ -7298,6 +7300,7 @@
int err = 0;
int ret;
int level;
+ bool root_dropped = false;
path = btrfs_alloc_path();
if (!path) {
@@ -7355,6 +7358,7 @@
while (1) {
btrfs_tree_lock(path->nodes[level]);
btrfs_set_lock_blocking(path->nodes[level]);
+ path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
ret = btrfs_lookup_extent_info(trans, root,
path->nodes[level]->start,
@@ -7370,6 +7374,7 @@
break;
btrfs_tree_unlock(path->nodes[level]);
+ path->locks[level] = 0;
WARN_ON(wc->refs[level] != 1);
level--;
}
@@ -7471,13 +7476,23 @@
free_extent_buffer(root->commit_root);
kfree(root);
}
+ root_dropped = true;
out_end_trans:
btrfs_end_transaction_throttle(trans, tree_root);
out_free:
kfree(wc);
btrfs_free_path(path);
out:
- if (err)
+ /*
+ * So if we need to stop dropping the snapshot for whatever reason we
+ * need to make sure to add it back to the dead root list so that we
+ * keep trying to do the work later. This also cleans up roots if we
+ * don't have it in the radix (like when we recover after a power fail
+ * or unmount) so we don't leak memory.
+ */
+ if (root_dropped == false)
+ btrfs_add_dead_root(root);
+ if (err && err != -EAGAIN)
btrfs_std_error(root->fs_info, err);
return err;
}
@@ -8550,7 +8565,7 @@
int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
{
- return unpin_extent_range(root, start, end);
+ return unpin_extent_range(root, start, end, false);
}
int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e7e7afb..84ceff6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1624,6 +1624,7 @@
* shortening the size of the delalloc range we're searching
*/
free_extent_state(cached_state);
+ cached_state = NULL;
if (!loops) {
unsigned long offset = (*start) & (PAGE_CACHE_SIZE - 1);
max_bytes = PAGE_CACHE_SIZE - offset;
@@ -2356,7 +2357,7 @@
{
int uptodate = (err == 0);
struct extent_io_tree *tree;
- int ret;
+ int ret = 0;
tree = &BTRFS_I(page->mapping->host)->io_tree;
@@ -2370,6 +2371,8 @@
if (!uptodate) {
ClearPageUptodate(page);
SetPageError(page);
+ ret = ret < 0 ? ret : -EIO;
+ mapping_set_error(page->mapping, ret);
}
return 0;
}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a4a7a1a..0a38095 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -263,8 +263,6 @@
if (!em)
goto out;
- if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
- list_move(&em->list, &tree->modified_extents);
em->generation = gen;
clear_bit(EXTENT_FLAG_PINNED, &em->flags);
em->mod_start = em->start;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index b193bf3..e4bcfec 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -403,7 +403,7 @@
ret = 0;
fail:
while (ret < 0 && !list_empty(&tmplist)) {
- sums = list_entry(&tmplist, struct btrfs_ordered_sum, list);
+ sums = list_entry(tmplist.next, struct btrfs_ordered_sum, list);
list_del(&sums->list);
kfree(sums);
}
@@ -754,7 +754,7 @@
found_next = 1;
if (ret != 0)
goto insert;
- slot = 0;
+ slot = path->slots[0];
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4205ba7..caaf30f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1593,22 +1593,10 @@
mutex_unlock(&inode->i_mutex);
/*
- * we want to make sure fsync finds this change
- * but we haven't joined a transaction running right now.
- *
- * Later on, someone is sure to update the inode and get the
- * real transid recorded.
- *
- * We set last_trans now to the fs_info generation + 1,
- * this will either be one more than the running transaction
- * or the generation used for the next transaction if there isn't
- * one running right now.
- *
* We also have to set last_sub_trans to the current log transid,
* otherwise subsequent syncs to a file that's been synced in this
* transaction will appear to have already occured.
*/
- BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
BTRFS_I(inode)->last_sub_trans = root->log_transid;
if (num_written > 0 || num_written == -EIOCBQUEUED) {
err = generic_write_sync(file, pos, num_written);
@@ -1706,25 +1694,37 @@
atomic_inc(&root->log_batch);
/*
- * check the transaction that last modified this inode
- * and see if its already been committed
- */
- if (!BTRFS_I(inode)->last_trans) {
- mutex_unlock(&inode->i_mutex);
- goto out;
- }
-
- /*
- * if the last transaction that changed this file was before
- * the current transaction, we can bail out now without any
- * syncing
+ * If the last transaction that changed this file was before the current
+ * transaction and we have the full sync flag set in our inode, we can
+ * bail out now without any syncing.
+ *
+ * Note that we can't bail out if the full sync flag isn't set. This is
+ * because when the full sync flag is set we start all ordered extents
+ * and wait for them to fully complete - when they complete they update
+ * the inode's last_trans field through:
+ *
+ * btrfs_finish_ordered_io() ->
+ * btrfs_update_inode_fallback() ->
+ * btrfs_update_inode() ->
+ * btrfs_set_inode_last_trans()
+ *
+ * So we are sure that last_trans is up to date and can do this check to
+ * bail out safely. For the fast path, when the full sync flag is not
+ * set in our inode, we can not do it because we start only our ordered
+ * extents and don't wait for them to complete (that is when
+ * btrfs_finish_ordered_io runs), so here at this point their last_trans
+ * value might be less than or equals to fs_info->last_trans_committed,
+ * and setting a speculative last_trans for an inode when a buffered
+ * write is made (such as fs_info->generation + 1 for example) would not
+ * be reliable since after setting the value and before fsync is called
+ * any number of transactions can start and commit (transaction kthread
+ * commits the current transaction periodically), and a transaction
+ * commit does not start nor waits for ordered extents to complete.
*/
smp_mb();
if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
- BTRFS_I(inode)->last_trans <=
- root->fs_info->last_trans_committed) {
- BTRFS_I(inode)->last_trans = 0;
-
+ (full_sync && BTRFS_I(inode)->last_trans <=
+ root->fs_info->last_trans_committed)) {
/*
* We'v had everything committed since the last time we were
* modified so clear this flag in case it was set for whatever
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e530096..0cbe95d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -835,7 +835,7 @@
if (!matched) {
__btrfs_remove_free_space_cache(ctl);
- btrfs_err(fs_info, "block group %llu has wrong amount of free space",
+ btrfs_warn(fs_info, "block group %llu has wrong amount of free space",
block_group->key.objectid);
ret = -1;
}
@@ -847,7 +847,7 @@
spin_unlock(&block_group->lock);
ret = 0;
- btrfs_err(fs_info, "failed to load free space cache for block group %llu",
+ btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
block_group->key.objectid);
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17f3064..d20db64 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2419,10 +2419,23 @@
return ret;
}
+static void free_sa_defrag_extent(struct new_sa_defrag_extent *new)
+{
+ struct old_sa_defrag_extent *old, *tmp;
+
+ if (!new)
+ return;
+
+ list_for_each_entry_safe(old, tmp, &new->head, list) {
+ list_del(&old->list);
+ kfree(old);
+ }
+ kfree(new);
+}
+
static void relink_file_extents(struct new_sa_defrag_extent *new)
{
struct btrfs_path *path;
- struct old_sa_defrag_extent *old, *tmp;
struct sa_defrag_extent_backref *backref;
struct sa_defrag_extent_backref *prev = NULL;
struct inode *inode;
@@ -2465,16 +2478,11 @@
kfree(prev);
btrfs_free_path(path);
-
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- list_del(&old->list);
- kfree(old);
- }
out:
+ free_sa_defrag_extent(new);
+
atomic_dec(&root->fs_info->defrag_running);
wake_up(&root->fs_info->transaction_wait);
-
- kfree(new);
}
static struct new_sa_defrag_extent *
@@ -2484,7 +2492,7 @@
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
struct btrfs_key key;
- struct old_sa_defrag_extent *old, *tmp;
+ struct old_sa_defrag_extent *old;
struct new_sa_defrag_extent *new;
int ret;
@@ -2532,7 +2540,7 @@
if (slot >= btrfs_header_nritems(l)) {
ret = btrfs_next_leaf(root, path);
if (ret < 0)
- goto out_free_list;
+ goto out_free_path;
else if (ret > 0)
break;
continue;
@@ -2561,7 +2569,7 @@
old = kmalloc(sizeof(*old), GFP_NOFS);
if (!old)
- goto out_free_list;
+ goto out_free_path;
offset = max(new->file_pos, key.offset);
end = min(new->file_pos + new->len, key.offset + num_bytes);
@@ -2583,15 +2591,10 @@
return new;
-out_free_list:
- list_for_each_entry_safe(old, tmp, &new->head, list) {
- list_del(&old->list);
- kfree(old);
- }
out_free_path:
btrfs_free_path(path);
out_kfree:
- kfree(new);
+ free_sa_defrag_extent(new);
return NULL;
}
@@ -2652,7 +2655,7 @@
EXTENT_DEFRAG, 1, cached_state);
if (ret) {
u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
- if (last_snapshot >= BTRFS_I(inode)->generation)
+ if (0 && last_snapshot >= BTRFS_I(inode)->generation)
/* the inode is shared */
new = record_old_file_extents(inode, ordered_extent);
@@ -2743,8 +2746,14 @@
btrfs_remove_ordered_extent(inode, ordered_extent);
/* for snapshot-aware defrag */
- if (new)
- relink_file_extents(new);
+ if (new) {
+ if (ret) {
+ free_sa_defrag_extent(new);
+ atomic_dec(&root->fs_info->defrag_running);
+ } else {
+ relink_file_extents(new);
+ }
+ }
/* once for us */
btrfs_put_ordered_extent(ordered_extent);
@@ -3536,7 +3545,8 @@
* without delay
*/
if (!btrfs_is_free_space_inode(inode)
- && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+ && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
+ && !root->fs_info->log_root_recovering) {
btrfs_update_root_times(trans, root);
ret = btrfs_delayed_update_inode(trans, root, inode);
@@ -4518,8 +4528,12 @@
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
- inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+ if (newsize != oldsize) {
+ inode_inc_iversion(inode);
+ if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
+ inode->i_ctime = inode->i_mtime =
+ current_fs_time(inode->i_sb);
+ }
if (newsize > oldsize) {
truncate_pagecache(inode, oldsize, newsize);
@@ -6811,7 +6825,6 @@
((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
em->block_start != EXTENT_MAP_HOLE)) {
int type;
- int ret;
u64 block_start, orig_start, orig_block_len, ram_bytes;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -8146,7 +8159,7 @@
/* check for collisions, even if the name isn't there */
- ret = btrfs_check_dir_item_collision(root, new_dir->i_ino,
+ ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino,
new_dentry->d_name.name,
new_dentry->d_name.len);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0f81d67..dbefa6c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1528,6 +1528,12 @@
printk(KERN_INFO "btrfs: Snapshot src from "
"another FS\n");
ret = -EINVAL;
+ } else if (!inode_owner_or_capable(src_inode)) {
+ /*
+ * Subvolume creation is not restricted, but snapshots
+ * are limited to own subvolumes only
+ */
+ ret = -EPERM;
} else {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
@@ -2093,7 +2099,7 @@
err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
if (err == -EINTR)
- goto out;
+ goto out_drop_write;
dentry = lookup_one_len(vol_args->name, parent, namelen);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
@@ -2235,6 +2241,7 @@
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
+out_drop_write:
mnt_drop_write_file(file);
out:
kfree(vol_args);
@@ -2565,6 +2572,11 @@
if (off + len == src->i_size)
len = ALIGN(src->i_size, bs) - off;
+ if (len == 0) {
+ ret = 0;
+ goto out_unlock;
+ }
+
/* verify the end result is block aligned */
if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) ||
!IS_ALIGNED(destoff, bs))
@@ -3299,6 +3311,9 @@
switch (p->cmd) {
case BTRFS_IOCTL_DEV_REPLACE_CMD_START:
+ if (root->fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
if (atomic_xchg(
&root->fs_info->mutually_exclusive_operation_running,
1)) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4febca4..0e7f776 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -691,6 +691,7 @@
int cowonly;
int ret;
int err = 0;
+ bool need_check = true;
path1 = btrfs_alloc_path();
path2 = btrfs_alloc_path();
@@ -914,6 +915,7 @@
cur->bytenr);
lower = cur;
+ need_check = true;
for (; level < BTRFS_MAX_LEVEL; level++) {
if (!path2->nodes[level]) {
BUG_ON(btrfs_root_bytenr(&root->root_item) !=
@@ -957,18 +959,19 @@
/*
* add the block to pending list if we
- * need check its backrefs. only block
- * at 'cur->level + 1' is added to the
- * tail of pending list. this guarantees
- * we check backrefs from lower level
- * blocks to upper level blocks.
+ * need check its backrefs, we only do this once
+ * while walking up a tree as we will catch
+ * anything else later on.
*/
- if (!upper->checked &&
- level == cur->level + 1) {
+ if (!upper->checked && need_check) {
+ need_check = false;
list_add_tail(&edge->list[UPPER],
&list);
- } else
+ } else {
+ if (upper->checked)
+ need_check = true;
INIT_LIST_HEAD(&edge->list[UPPER]);
+ }
} else {
upper = rb_entry(rb_node, struct backref_node,
rb_node);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 79bd479..e4f69e3 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -545,8 +545,9 @@
if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
do {
- ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
- &ref_root, &ref_level);
+ ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
+ item_size, &ref_root,
+ &ref_level);
printk_in_rcu(KERN_WARNING
"btrfs: %s at logical %llu on dev %s, "
"sector %llu: metadata %s (level %d) in tree "
@@ -2501,7 +2502,7 @@
ret = scrub_extent(sctx, extent_logical, extent_len,
extent_physical, extent_dev, flags,
generation, extent_mirror_num,
- extent_physical);
+ extent_logical - logical + physical);
if (ret)
goto out;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ff40f1c..414c1b9 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1550,6 +1550,10 @@
goto out;
}
btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+ if (key.type == BTRFS_ROOT_ITEM_KEY) {
+ ret = -ENOENT;
+ goto out;
+ }
*found_inode = key.objectid;
*found_type = btrfs_dir_type(path->nodes[0], di);
@@ -2524,7 +2528,8 @@
di = btrfs_item_ptr(eb, slot, struct btrfs_dir_item);
btrfs_dir_item_key_to_cpu(eb, di, &di_key);
- if (di_key.objectid < sctx->send_progress) {
+ if (di_key.type != BTRFS_ROOT_ITEM_KEY &&
+ di_key.objectid < sctx->send_progress) {
ret = 1;
goto out;
}
@@ -4579,6 +4584,41 @@
send_root = BTRFS_I(file_inode(mnt_file))->root;
fs_info = send_root->fs_info;
+ /*
+ * This is done when we lookup the root, it should already be complete
+ * by the time we get here.
+ */
+ WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE);
+
+ /*
+ * If we just created this root we need to make sure that the orphan
+ * cleanup has been done and committed since we search the commit root,
+ * so check its commit root transid with our otransid and if they match
+ * commit the transaction to make sure everything is updated.
+ */
+ down_read(&send_root->fs_info->extent_commit_sem);
+ if (btrfs_header_generation(send_root->commit_root) ==
+ btrfs_root_otransid(&send_root->root_item)) {
+ struct btrfs_trans_handle *trans;
+
+ up_read(&send_root->fs_info->extent_commit_sem);
+
+ trans = btrfs_attach_transaction_barrier(send_root);
+ if (IS_ERR(trans)) {
+ if (PTR_ERR(trans) != -ENOENT) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+ /* ENOENT means theres no transaction */
+ } else {
+ ret = btrfs_commit_transaction(trans, send_root);
+ if (ret)
+ goto out;
+ }
+ } else {
+ up_read(&send_root->fs_info->extent_commit_sem);
+ }
+
arg = memdup_user(arg_, sizeof(*arg));
if (IS_ERR(arg)) {
ret = PTR_ERR(arg);
@@ -4587,8 +4627,8 @@
}
if (!access_ok(VERIFY_READ, arg->clone_sources,
- sizeof(*arg->clone_sources *
- arg->clone_sources_count))) {
+ sizeof(*arg->clone_sources) *
+ arg->clone_sources_count)) {
ret = -EFAULT;
goto out;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0544587..1f21468 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -524,7 +524,6 @@
if (transid <= root->fs_info->last_trans_committed)
goto out;
- ret = -EINVAL;
/* find specified transaction */
spin_lock(&root->fs_info->trans_lock);
list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -540,9 +539,16 @@
}
}
spin_unlock(&root->fs_info->trans_lock);
- /* The specified transaction doesn't exist */
- if (!cur_trans)
+
+ /*
+ * The specified transaction doesn't exist, or we
+ * raced with btrfs_commit_transaction
+ */
+ if (!cur_trans) {
+ if (transid > root->fs_info->last_trans_committed)
+ ret = -EINVAL;
goto out;
+ }
} else {
/* find newest transaction that is committing | committed */
spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c276ac9..7d3331c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -943,7 +943,7 @@
base = btrfs_item_ptr_offset(leaf, path->slots[0]);
while (cur_offset < item_size) {
- extref = (struct btrfs_inode_extref *)base + cur_offset;
+ extref = (struct btrfs_inode_extref *)(base + cur_offset);
victim_name_len = btrfs_inode_extref_name_len(leaf, extref);
@@ -3314,7 +3314,7 @@
btrfs_set_token_file_extent_type(leaf, fi,
BTRFS_FILE_EXTENT_REG,
&token);
- if (em->block_start == 0)
+ if (em->block_start == EXTENT_MAP_HOLE)
skip_csum = true;
}
@@ -3728,8 +3728,9 @@
}
log_extents:
+ btrfs_release_path(path);
+ btrfs_release_path(dst_path);
if (fast_search) {
- btrfs_release_path(dst_path);
ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
if (ret) {
err = ret;
@@ -3746,8 +3747,6 @@
}
if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
- btrfs_release_path(path);
- btrfs_release_path(dst_path);
ret = log_directory_changes(trans, root, inode, path, dst_path);
if (ret) {
err = ret;
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index 7b417e2..b0a523b2 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -205,6 +205,10 @@
u64 new_alloced = ulist->nodes_alloced + 128;
struct ulist_node *new_nodes;
void *old = NULL;
+ int i;
+
+ for (i = 0; i < ulist->nnodes; i++)
+ rb_erase(&ulist->nodes[i].rb_node, &ulist->root);
/*
* if nodes_alloced == ULIST_SIZE no memory has been allocated
@@ -224,6 +228,17 @@
ulist->nodes = new_nodes;
ulist->nodes_alloced = new_alloced;
+
+ /*
+ * krealloc actually uses memcpy, which does not copy rb_node
+ * pointers, so we have to do it ourselves. Otherwise we may
+ * be bitten by crashes.
+ */
+ for (i = 0; i < ulist->nnodes; i++) {
+ ret = ulist_rbtree_insert(ulist, &ulist->nodes[i]);
+ if (ret < 0)
+ return ret;
+ }
}
ulist->nodes[ulist->nnodes].val = val;
ulist->nodes[ulist->nnodes].aux = aux;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8bffb91..7fc7746 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1384,6 +1384,22 @@
return ret;
}
+/*
+ * Function to update ctime/mtime for a given device path.
+ * Mainly used for ctime/mtime based probe like libblkid.
+ */
+static void update_dev_time(char *path_name)
+{
+ struct file *filp;
+
+ filp = filp_open(path_name, O_RDWR, 0);
+ if (!filp)
+ return;
+ file_update_time(filp);
+ filp_close(filp, NULL);
+ return;
+}
+
static int btrfs_rm_dev_item(struct btrfs_root *root,
struct btrfs_device *device)
{
@@ -1612,11 +1628,12 @@
struct btrfs_fs_devices *fs_devices;
fs_devices = root->fs_info->fs_devices;
while (fs_devices) {
- if (fs_devices->seed == cur_devices)
+ if (fs_devices->seed == cur_devices) {
+ fs_devices->seed = cur_devices->seed;
break;
+ }
fs_devices = fs_devices->seed;
}
- fs_devices->seed = cur_devices->seed;
cur_devices->seed = NULL;
lock_chunks(root);
__btrfs_close_devices(cur_devices);
@@ -1642,10 +1659,14 @@
ret = 0;
- /* Notify udev that device has changed */
- if (bdev)
+ if (bdev) {
+ /* Notify udev that device has changed */
btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
+ /* Update ctime/mtime for device path for libblkid */
+ update_dev_time(device_path);
+ }
+
error_brelse:
brelse(bh);
if (bdev)
@@ -1817,7 +1838,6 @@
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
- fs_devices->total_devices = 0;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
@@ -2089,6 +2109,8 @@
ret = btrfs_commit_transaction(trans, root);
}
+ /* Update ctime/mtime for libblkid */
+ update_dev_time(device_path);
return ret;
error_trans:
@@ -4248,6 +4270,7 @@
btrfs_emerg(fs_info, "Invalid mapping for %Lu-%Lu, got "
"%Lu-%Lu\n", logical, logical+len, em->start,
em->start + em->len);
+ free_extent_map(em);
return 1;
}
@@ -4429,6 +4452,7 @@
btrfs_crit(fs_info, "found a bad mapping, wanted %Lu, "
"found %Lu-%Lu\n", logical, em->start,
em->start + em->len);
+ free_extent_map(em);
return -EINVAL;
}
diff --git a/fs/buffer.c b/fs/buffer.c
index d2a4d1b..83fedaa 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -620,14 +620,16 @@
static void __set_page_dirty(struct page *page,
struct address_space *mapping, int warn)
{
- spin_lock_irq(&mapping->tree_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
- spin_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
@@ -983,7 +985,8 @@
bh = page_buffers(page);
if (bh->b_size == size) {
end_block = init_page_buffers(page, bdev,
- index << sizebits, size);
+ (sector_t)index << sizebits,
+ size);
goto done;
}
if (!try_to_free_buffers(page))
@@ -1004,7 +1007,8 @@
*/
spin_lock(&inode->i_mapping->private_lock);
link_dev_buffers(page, bh);
- end_block = init_page_buffers(page, bdev, index << sizebits, size);
+ end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits,
+ size);
spin_unlock(&inode->i_mapping->private_lock);
done:
ret = (block < end_block) ? 1 : -ENXIO;
@@ -2014,6 +2018,7 @@
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
+ loff_t old_size = inode->i_size;
int i_size_changed = 0;
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
@@ -2033,6 +2038,8 @@
unlock_page(page);
page_cache_release(page);
+ if (old_size < pos)
+ pagecache_isize_extended(inode, old_size, pos);
/*
* Don't mark the inode dirty under page lock. First, it unnecessarily
* makes the holding time of page lock longer. Second, it forces lock
@@ -2250,6 +2257,11 @@
err = 0;
balance_dirty_pages_ratelimited(mapping);
+
+ if (unlikely(fatal_signal_pending(current))) {
+ err = -EINTR;
+ goto out;
+ }
}
/* page covers the boundary, find the boundary offset */
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 3e68ac1..5da06f0 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -213,9 +213,13 @@
if (err < 0) {
SetPageError(page);
goto out;
- } else if (err < PAGE_CACHE_SIZE) {
+ } else {
+ if (err < PAGE_CACHE_SIZE) {
/* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ } else {
+ flush_dcache_page(page);
+ }
}
SetPageUptodate(page);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index f02d82b..ccb4329 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -103,7 +103,7 @@
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
- * d_u.d_child when we initially get results back from the MDS, and
+ * d_child when we initially get results back from the MDS, and
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
@@ -139,11 +139,11 @@
p = parent->d_subdirs.prev;
dout(" initial p %p/%p\n", p->prev, p->next);
} else {
- p = last->d_u.d_child.prev;
+ p = last->d_child.prev;
}
more:
- dentry = list_entry(p, struct dentry, d_u.d_child);
+ dentry = list_entry(p, struct dentry, d_child);
di = ceph_dentry(dentry);
while (1) {
dout(" p %p/%p %s d_subdirs %p/%p\n", p->prev, p->next,
@@ -165,7 +165,7 @@
!dentry->d_inode ? " null" : "");
spin_unlock(&dentry->d_lock);
p = p->prev;
- dentry = list_entry(p, struct dentry, d_u.d_child);
+ dentry = list_entry(p, struct dentry, d_child);
di = ceph_dentry(dentry);
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 656e169..5de16f5 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -313,9 +313,9 @@
{
struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
struct ceph_inode_info *ci = ceph_inode(inode);
- u64 pos, this_len;
+ u64 pos, this_len, left;
int io_align, page_align;
- int left, pages_left;
+ int pages_left;
int read;
struct page **page_pos;
int ret;
@@ -346,47 +346,40 @@
ret = 0;
hit_stripe = this_len < left;
was_short = ret >= 0 && ret < this_len;
- dout("striped_read %llu~%u (read %u) got %d%s%s\n", pos, left, read,
+ dout("striped_read %llu~%llu (read %u) got %d%s%s\n", pos, left, read,
ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : "");
- if (ret > 0) {
- int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
-
- if (read < pos - off) {
- dout(" zero gap %llu to %llu\n", off + read, pos);
- ceph_zero_page_vector_range(page_align + read,
- pos - off - read, pages);
+ if (ret >= 0) {
+ int didpages;
+ if (was_short && (pos + ret < inode->i_size)) {
+ u64 tmp = min(this_len - ret,
+ inode->i_size - pos - ret);
+ dout(" zero gap %llu to %llu\n",
+ pos + ret, pos + ret + tmp);
+ ceph_zero_page_vector_range(page_align + read + ret,
+ tmp, pages);
+ ret += tmp;
}
+
+ didpages = (page_align + ret) >> PAGE_CACHE_SHIFT;
pos += ret;
read = pos - off;
left -= ret;
page_pos += didpages;
pages_left -= didpages;
- /* hit stripe? */
- if (left && hit_stripe)
+ /* hit stripe and need continue*/
+ if (left && hit_stripe && pos < inode->i_size)
goto more;
}
- if (was_short) {
+ if (read > 0) {
+ ret = read;
/* did we bounce off eof? */
if (pos + left > inode->i_size)
*checkeof = 1;
-
- /* zero trailing bytes (inside i_size) */
- if (left > 0 && pos < inode->i_size) {
- if (pos + left > inode->i_size)
- left = inode->i_size - pos;
-
- dout("zero tail %d\n", left);
- ceph_zero_page_vector_range(page_align + read, left,
- pages);
- read += left;
- }
}
- if (ret >= 0)
- ret = read;
dout("striped_read returns %d\n", ret);
return ret;
}
@@ -618,6 +611,8 @@
if (check_caps)
ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY,
NULL);
+ } else if (ret != -EOLDSNAPC && written > 0) {
+ ret = written;
}
return ret;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index be0f7e2..0cf23a7 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -867,9 +867,9 @@
spin_lock(&dir->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&dn->d_u.d_child, &dir->d_subdirs);
+ list_move(&dn->d_child, &dir->d_subdirs);
dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
- dn->d_u.d_child.prev, dn->d_u.d_child.next);
+ dn->d_child.prev, dn->d_child.next);
spin_unlock(&dn->d_lock);
spin_unlock(&dir->d_lock);
}
@@ -1296,7 +1296,7 @@
/* reorder parent's d_subdirs */
spin_lock(&parent->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
- list_move(&dn->d_u.d_child, &parent->d_subdirs);
+ list_move(&dn->d_child, &parent->d_subdirs);
spin_unlock(&dn->d_lock);
spin_unlock(&parent->d_lock);
}
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index e0b4ef3..669622f 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -196,8 +196,10 @@
r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, len,
&dl.object_no, &dl.object_offset,
&olen);
- if (r < 0)
+ if (r < 0) {
+ up_read(&osdc->map_sem);
return -EIO;
+ }
dl.file_offset -= dl.object_offset;
dl.object_size = ceph_file_layout_object_size(ci->i_layout);
dl.block_size = ceph_file_layout_su(ci->i_layout);
@@ -209,8 +211,12 @@
snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
ceph_ino(inode), dl.object_no);
- ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
- ceph_file_layout_pg_pool(ci->i_layout));
+ r = ceph_calc_ceph_pg(&pgid, dl.object_name, osdc->osdmap,
+ ceph_file_layout_pg_pool(ci->i_layout));
+ if (r < 0) {
+ up_read(&osdc->map_sem);
+ return r;
+ }
dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
if (dl.osd >= 0) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4d29203..d6a5368 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -414,6 +414,9 @@
{
struct ceph_mds_session *s;
+ if (mds >= mdsc->mdsmap->m_max_mds)
+ return ERR_PTR(-EINVAL);
+
s = kzalloc(sizeof(*s), GFP_NOFS);
if (!s)
return ERR_PTR(-ENOMEM);
@@ -639,6 +642,8 @@
req->r_unsafe_dir = NULL;
}
+ complete_all(&req->r_safe_completion);
+
ceph_mdsc_put_request(req);
}
@@ -1840,8 +1845,11 @@
int mds = -1;
int err = -EAGAIN;
- if (req->r_err || req->r_got_result)
+ if (req->r_err || req->r_got_result) {
+ if (req->r_aborted)
+ __unregister_request(mdsc, req);
goto out;
+ }
if (req->r_timeout &&
time_after_eq(jiffies, req->r_started + req->r_timeout)) {
@@ -2151,7 +2159,6 @@
if (head->safe) {
req->r_got_safe = true;
__unregister_request(mdsc, req);
- complete_all(&req->r_safe_completion);
if (req->r_got_unsafe) {
/*
@@ -3040,8 +3047,10 @@
fsc->mdsc = mdsc;
mutex_init(&mdsc->mutex);
mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
- if (mdsc->mdsmap == NULL)
+ if (mdsc->mdsmap == NULL) {
+ kfree(mdsc);
return -ENOMEM;
+ }
init_completion(&mdsc->safe_umount_waiters);
init_waitqueue_head(&mdsc->session_close_wq);
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 9278dec..d4d3897 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -138,6 +138,8 @@
m->m_info[mds].export_targets =
kcalloc(num_export_targets, sizeof(u32),
GFP_NOFS);
+ if (m->m_info[mds].export_targets == NULL)
+ goto badmem;
for (j = 0; j < num_export_targets; j++)
m->m_info[mds].export_targets[j] =
ceph_decode_32(&pexport_targets);
@@ -170,7 +172,7 @@
DUMP_PREFIX_OFFSET, 16, 1,
start, end - start, true);
ceph_mdsmap_destroy(m);
- return ERR_PTR(-EINVAL);
+ return ERR_PTR(err);
}
void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 7d377c9..6627b26 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -357,7 +357,7 @@
}
err = -EINVAL;
dev_name_end--; /* back up to ':' separator */
- if (*dev_name_end != ':') {
+ if (dev_name_end < dev_name || *dev_name_end != ':') {
pr_err("device name is missing path (no : separator in %s)\n",
dev_name);
goto out;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9b6b2b6d..be661d8 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -675,17 +675,18 @@
if (!ceph_is_valid_xattr(name))
return -ENODATA;
- spin_lock(&ci->i_ceph_lock);
- dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
- ci->i_xattrs.version, ci->i_xattrs.index_version);
/* let's see if a virtual xattr was requested */
vxattr = ceph_match_vxattr(inode, name);
if (vxattr && !(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
err = vxattr->getxattr_cb(ci, value, size);
- goto out;
+ return err;
}
+ spin_lock(&ci->i_ceph_lock);
+ dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
+ ci->i_xattrs.version, ci->i_xattrs.index_version);
+
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 1) &&
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto get_xattr;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45..15e9505 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@
cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
const struct nls_table *cp, int mapChars)
{
- int i, j, charlen;
+ int i, charlen;
+ int j = 0;
char src_char;
__le16 dst_char;
wchar_t tmp;
@@ -298,12 +299,11 @@
if (!mapChars)
return cifs_strtoUTF16(target, source, PATH_MAX, cp);
- for (i = 0, j = 0; i < srclen; j++) {
+ for (i = 0; i < srclen; j++) {
src_char = source[i];
charlen = 1;
switch (src_char) {
case 0:
- put_unaligned(0, &target[j]);
goto ctoUTF16_out;
case ':':
dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@
}
ctoUTF16_out:
+ put_unaligned(0, &target[j]); /* Null terminate target unicode string */
return j;
}
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 4fb0974..fe8d627 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -327,14 +327,14 @@
/*
* UniStrupr: Upper case a unicode string
*/
-static inline wchar_t *
-UniStrupr(register wchar_t *upin)
+static inline __le16 *
+UniStrupr(register __le16 *upin)
{
- register wchar_t *up;
+ register __le16 *up;
up = upin;
while (*up) { /* For all characters */
- *up = UniToupper(*up);
+ *up = cpu_to_le16(UniToupper(le16_to_cpu(*up)));
up++;
}
return upin; /* Return input pointer */
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 51f5e0e..494b683 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1027,15 +1027,30 @@
__u32 secdesclen = 0;
struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_tcon *tcon;
+
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
/* Get the security descriptor */
- pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
+
+ if (tcon->ses->server->ops->get_acl == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+ &secdesclen);
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
- goto out;
+ cifs_put_tlink(tlink);
+ return rc;
}
/*
@@ -1048,6 +1063,7 @@
pnntsd = kmalloc(secdesclen, GFP_KERNEL);
if (!pnntsd) {
kfree(pntsd);
+ cifs_put_tlink(tlink);
return -ENOMEM;
}
@@ -1056,14 +1072,18 @@
cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
+ if (tcon->ses->server->ops->set_acl == NULL)
+ rc = -EOPNOTSUPP;
+
if (!rc) {
/* Set the security descriptor */
- rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag);
+ rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
+ path, aclflag);
cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
}
+ cifs_put_tlink(tlink);
kfree(pnntsd);
kfree(pntsd);
-out:
return rc;
}
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 71436d1..5c807b2 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -389,7 +389,7 @@
if (blobptr + attrsize > blobend)
break;
if (type == NTLMSSP_AV_NB_DOMAIN_NAME) {
- if (!attrsize)
+ if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN)
break;
if (!ses->domainName) {
ses->domainName =
@@ -414,7 +414,7 @@
int rc = 0;
int len;
char nt_hash[CIFS_NTHASH_SIZE];
- wchar_t *user;
+ __le16 *user;
wchar_t *domain;
wchar_t *server;
@@ -439,7 +439,7 @@
return rc;
}
- /* convert ses->user_name to unicode and uppercase */
+ /* convert ses->user_name to unicode */
len = ses->user_name ? strlen(ses->user_name) : 0;
user = kmalloc(2 + (len * 2), GFP_KERNEL);
if (user == NULL) {
@@ -448,7 +448,7 @@
}
if (len) {
- len = cifs_strtoUTF16((__le16 *)user, ses->user_name, len, nls_cp);
+ len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp);
UniStrupr(user);
} else {
memset(user, '\0', 2);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 4f07f6f..f74dfa8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -44,6 +44,7 @@
#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1)
#define MAX_SERVER_SIZE 15
#define MAX_SHARE_SIZE 80
+#define CIFS_MAX_DOMAINNAME_LEN 256 /* max domain name length */
#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */
#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */
@@ -73,11 +74,6 @@
#define SERVER_NAME_LENGTH 40
#define SERVER_NAME_LEN_WITH_NULL (SERVER_NAME_LENGTH + 1)
-/* used to define string lengths for reversing unicode strings */
-/* (256+1)*2 = 514 */
-/* (max path length + 1 for null) * 2 for unicode */
-#define MAX_NAME 514
-
/* SMB echo "timeout" -- FIXME: tunable? */
#define SMB_ECHO_INTERVAL (60 * HZ)
@@ -369,6 +365,18 @@
void (*new_lease_key)(struct cifs_fid *fid);
int (*calc_signature)(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
+ ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
+ const unsigned char *, const unsigned char *, char *,
+ size_t, const struct nls_table *, int);
+ int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
+ const char *, const void *, const __u16,
+ const struct nls_table *, int);
+ struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
+ const char *, u32 *);
+ int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
+ int);
+ /* check if we need to issue closedir */
+ bool (*dir_needs_close)(struct cifsFileInfo *);
};
struct smb_version_values {
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index a58dc77..d17c5d7 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -3306,11 +3306,13 @@
return 0;
}
cifs_acl->version = cpu_to_le16(1);
- if (acl_type == ACL_TYPE_ACCESS)
+ if (acl_type == ACL_TYPE_ACCESS) {
cifs_acl->access_entry_count = cpu_to_le16(count);
- else if (acl_type == ACL_TYPE_DEFAULT)
+ cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+ } else if (acl_type == ACL_TYPE_DEFAULT) {
cifs_acl->default_entry_count = cpu_to_le16(count);
- else {
+ cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+ } else {
cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
return 0;
}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e3bc39b..d05a300 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -377,6 +377,7 @@
try_to_freeze();
/* we should try only the port we connected to before */
+ mutex_lock(&server->srv_mutex);
rc = generic_ip_connect(server);
if (rc) {
cifs_dbg(FYI, "reconnect error %d\n", rc);
@@ -388,6 +389,7 @@
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
}
+ mutex_unlock(&server->srv_mutex);
} while (server->tcpStatus == CifsNeedReconnect);
return rc;
@@ -1662,7 +1664,8 @@
if (string == NULL)
goto out_nomem;
- if (strnlen(string, 256) == 256) {
+ if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN)
+ == CIFS_MAX_DOMAINNAME_LEN) {
printk(KERN_WARNING "CIFS: domain name too"
" long\n");
goto cifs_parse_mount_err;
@@ -2288,8 +2291,8 @@
#ifdef CONFIG_KEYS
-/* strlen("cifs:a:") + INET6_ADDRSTRLEN + 1 */
-#define CIFSCREDS_DESC_SIZE (7 + INET6_ADDRSTRLEN + 1)
+/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */
+#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1)
/* Populate username and pw fields from keyring if possible */
static int
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 5699b50..0c2425b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -491,6 +491,7 @@
if (server->ops->close)
server->ops->close(xid, tcon, &fid);
cifs_del_pending_open(&open);
+ fput(file);
rc = -ENOMEM;
}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 48b29d2..f4a8577 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -553,11 +553,10 @@
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
int rc = 0;
- /* we are going to update can_cache_brlcks here - need a write access */
- down_write(&cinode->lock_sem);
+ down_read(&cinode->lock_sem);
if (cinode->can_cache_brlcks) {
- /* can cache locks - no need to push them */
- up_write(&cinode->lock_sem);
+ /* can cache locks - no need to relock */
+ up_read(&cinode->lock_sem);
return rc;
}
@@ -568,7 +567,7 @@
else
rc = tcon->ses->server->ops->push_mand_locks(cfile);
- up_write(&cinode->lock_sem);
+ up_read(&cinode->lock_sem);
return rc;
}
@@ -736,7 +735,7 @@
cifs_dbg(FYI, "Freeing private data in close dir\n");
spin_lock(&cifs_file_list_lock);
- if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+ if (server->ops->dir_needs_close(cfile)) {
cfile->invalidHandle = true;
spin_unlock(&cifs_file_list_lock);
if (server->ops->close_dir)
@@ -1790,6 +1789,7 @@
cifsFileInfo_put(inv_file);
spin_lock(&cifs_file_list_lock);
++refind;
+ inv_file = NULL;
goto refind_writable;
}
}
@@ -2354,7 +2354,7 @@
unsigned long nr_segs, loff_t *poffset)
{
unsigned long nr_pages, i;
- size_t copied, len, cur_len;
+ size_t bytes, copied, len, cur_len;
ssize_t total_written = 0;
loff_t offset;
struct iov_iter it;
@@ -2409,14 +2409,45 @@
save_len = cur_len;
for (i = 0; i < nr_pages; i++) {
- copied = min_t(const size_t, cur_len, PAGE_SIZE);
+ bytes = min_t(const size_t, cur_len, PAGE_SIZE);
copied = iov_iter_copy_from_user(wdata->pages[i], &it,
- 0, copied);
+ 0, bytes);
cur_len -= copied;
iov_iter_advance(&it, copied);
+ /*
+ * If we didn't copy as much as we expected, then that
+ * may mean we trod into an unmapped area. Stop copying
+ * at that point. On the next pass through the big
+ * loop, we'll likely end up getting a zero-length
+ * write and bailing out of it.
+ */
+ if (copied < bytes)
+ break;
}
cur_len = save_len - cur_len;
+ /*
+ * If we have no data to send, then that probably means that
+ * the copy above failed altogether. That's most likely because
+ * the address in the iovec was bogus. Set the rc to -EFAULT,
+ * free anything we allocated and bail out.
+ */
+ if (!cur_len) {
+ for (i = 0; i < nr_pages; i++)
+ put_page(wdata->pages[i]);
+ kfree(wdata);
+ rc = -EFAULT;
+ break;
+ }
+
+ /*
+ * i + 1 now represents the number of pages we actually used in
+ * the copy phase above. Bring nr_pages down to that, and free
+ * any pages that we didn't use.
+ */
+ for ( ; nr_pages > i + 1; nr_pages--)
+ put_page(wdata->pages[nr_pages - 1]);
+
wdata->sync_mode = WB_SYNC_ALL;
wdata->nr_pages = nr_pages;
wdata->offset = (__u64)offset;
@@ -2779,7 +2810,7 @@
total_read += result;
}
- return total_read > 0 ? total_read : result;
+ return total_read > 0 && result != -EAGAIN ? total_read : result;
}
static ssize_t
@@ -3202,7 +3233,7 @@
total_read += result;
}
- return total_read > 0 ? total_read : result;
+ return total_read > 0 && result != -EAGAIN ? total_read : result;
}
static int cifs_readpages(struct file *file, struct address_space *mapping,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 20efd81..54304cc 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -490,10 +490,15 @@
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
- rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS",
- ea_value, 4 /* size of buf */, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (tcon->ses->server->ops->query_all_EAs == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
+ "SETFILEBITS", ea_value, 4 /* size of buf */,
+ cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
cifs_put_tlink(tlink);
if (rc < 0)
return (int)rc;
@@ -558,6 +563,11 @@
fattr->cf_mode &= ~(S_IWUGO);
fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+ if (fattr->cf_nlink < 1) {
+ cifs_dbg(1, "replacing bogus file nlink value %u\n",
+ fattr->cf_nlink);
+ fattr->cf_nlink = 1;
+ }
}
fattr->cf_uid = cifs_sb->mnt_uid;
@@ -822,7 +832,7 @@
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
@@ -1630,13 +1640,22 @@
unlink_target:
/* Try unlinking the target dentry if it's not negative */
if (target_dentry->d_inode && (rc == -EACCES || rc == -EEXIST)) {
- tmprc = cifs_unlink(target_dir, target_dentry);
+ if (S_ISDIR(target_dentry->d_inode->i_mode))
+ tmprc = cifs_rmdir(target_dir, target_dentry);
+ else
+ tmprc = cifs_unlink(target_dir, target_dentry);
if (tmprc)
goto cifs_rename_exit;
rc = cifs_do_rename(xid, source_dentry, from_name,
target_dentry, to_name);
}
+ /* force revalidate to go get info when needed */
+ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0;
+
+ source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime =
+ target_dir->i_mtime = current_fs_time(source_dir->i_sb);
+
cifs_rename_exit:
kfree(info_buf_source);
kfree(from_name);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 770d5a9..85ebdaa 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -111,6 +111,14 @@
return;
}
+ /*
+ * If we know that the inode will need to be revalidated immediately,
+ * then don't create a new dentry for it. We'll end up doing an on
+ * the wire call either way and this spares us an invalidation.
+ */
+ if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
+ return;
+
dentry = d_alloc(parent, name);
if (!dentry)
return;
@@ -574,11 +582,11 @@
/* close and restart search */
cifs_dbg(FYI, "search backing up - close and restart search\n");
spin_lock(&cifs_file_list_lock);
- if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
+ if (server->ops->dir_needs_close(cfile)) {
cfile->invalidHandle = true;
spin_unlock(&cifs_file_list_lock);
- if (server->ops->close)
- server->ops->close(xid, tcon, &cfile->fid);
+ if (server->ops->close_dir)
+ server->ops->close_dir(xid, tcon, &cfile->fid);
} else
spin_unlock(&cifs_file_list_lock);
if (cfile->srch_inf.ntwrk_buf_start) {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index f230571..8edc9eb 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -198,7 +198,7 @@
bytes_ret = 0;
} else
bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->domainName,
- 256, nls_cp);
+ CIFS_MAX_DOMAINNAME_LEN, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null terminator */
@@ -256,8 +256,8 @@
/* copy domain */
if (ses->domainName != NULL) {
- strncpy(bcc_ptr, ses->domainName, 256);
- bcc_ptr += strnlen(ses->domainName, 256);
+ strncpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ bcc_ptr += strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
} /* else we will send a null domain name
so the server will default to its own domain */
*bcc_ptr = 0;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 3efdb9d..610c6c2 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -885,6 +885,12 @@
(__u8)type, wait, 0);
}
+static bool
+cifs_dir_needs_close(struct cifsFileInfo *cfile)
+{
+ return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
@@ -948,6 +954,15 @@
.mand_lock = cifs_mand_lock,
.mand_unlock_range = cifs_unlock_range,
.push_mand_locks = cifs_push_mandatory_locks,
+ .dir_needs_close = cifs_dir_needs_close,
+#ifdef CONFIG_CIFS_XATTR
+ .query_all_EAs = CIFSSMBQAllEAs,
+ .set_EA = CIFSSMBSetEA,
+#endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+ .get_acl = get_cifs_acl,
+ .set_acl = set_cifs_acl,
+#endif /* CIFS_ACL */
};
struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 5da1b55..d801f63 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -73,7 +73,7 @@
goto out;
}
- smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+ smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
GFP_KERNEL);
if (smb2_data == NULL) {
rc = -ENOMEM;
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 7c0e214..cc592ef 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -55,4 +55,7 @@
#define SMB2_NTLMV2_SESSKEY_SIZE (16)
#define SMB2_HMACSHA256_SIZE (32)
+/* Maximum buffer size value we can send with 1 credit */
+#define SMB2_MAX_BUFFER_SIZE 65536
+
#endif /* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index fff6dfb..6d53579 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -123,7 +123,7 @@
*adjust_tz = false;
- smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+ smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
GFP_KERNEL);
if (smb2_data == NULL)
return -ENOMEM;
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 7c2f45c..4768cf8 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -214,7 +214,7 @@
{STATUS_BREAKPOINT, -EIO, "STATUS_BREAKPOINT"},
{STATUS_SINGLE_STEP, -EIO, "STATUS_SINGLE_STEP"},
{STATUS_BUFFER_OVERFLOW, -EIO, "STATUS_BUFFER_OVERFLOW"},
- {STATUS_NO_MORE_FILES, -EIO, "STATUS_NO_MORE_FILES"},
+ {STATUS_NO_MORE_FILES, -ENODATA, "STATUS_NO_MORE_FILES"},
{STATUS_WAKE_SYSTEM_DEBUGGER, -EIO, "STATUS_WAKE_SYSTEM_DEBUGGER"},
{STATUS_HANDLES_CLOSED, -EIO, "STATUS_HANDLES_CLOSED"},
{STATUS_NO_INHERITANCE, -EIO, "STATUS_NO_INHERITANCE"},
@@ -605,7 +605,7 @@
{STATUS_MAPPED_FILE_SIZE_ZERO, -EIO, "STATUS_MAPPED_FILE_SIZE_ZERO"},
{STATUS_TOO_MANY_OPENED_FILES, -EMFILE, "STATUS_TOO_MANY_OPENED_FILES"},
{STATUS_CANCELLED, -EIO, "STATUS_CANCELLED"},
- {STATUS_CANNOT_DELETE, -EIO, "STATUS_CANNOT_DELETE"},
+ {STATUS_CANNOT_DELETE, -EACCES, "STATUS_CANNOT_DELETE"},
{STATUS_INVALID_COMPUTER_NAME, -EIO, "STATUS_INVALID_COMPUTER_NAME"},
{STATUS_FILE_DELETED, -EIO, "STATUS_FILE_DELETED"},
{STATUS_SPECIAL_ACCOUNT, -EIO, "STATUS_SPECIAL_ACCOUNT"},
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 10383d8..4f791e0 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -413,19 +413,76 @@
}
static bool
-smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
+smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
+ struct smb2_lease_break_work *lw)
+{
+ bool found;
+ __u8 lease_state;
+ struct list_head *tmp;
+ struct cifsFileInfo *cfile;
+ struct cifs_pending_open *open;
+ struct cifsInodeInfo *cinode;
+ int ack_req = le32_to_cpu(rsp->Flags &
+ SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
+
+ lease_state = smb2_map_lease_to_oplock(rsp->NewLeaseState);
+
+ list_for_each(tmp, &tcon->openFileList) {
+ cfile = list_entry(tmp, struct cifsFileInfo, tlist);
+ cinode = CIFS_I(cfile->dentry->d_inode);
+
+ if (memcmp(cinode->lease_key, rsp->LeaseKey,
+ SMB2_LEASE_KEY_SIZE))
+ continue;
+
+ cifs_dbg(FYI, "found in the open list\n");
+ cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
+ le32_to_cpu(rsp->NewLeaseState));
+
+ smb2_set_oplock_level(cinode, lease_state);
+
+ if (ack_req)
+ cfile->oplock_break_cancelled = false;
+ else
+ cfile->oplock_break_cancelled = true;
+
+ queue_work(cifsiod_wq, &cfile->oplock_break);
+ kfree(lw);
+ return true;
+ }
+
+ found = false;
+ list_for_each_entry(open, &tcon->pending_opens, olist) {
+ if (memcmp(open->lease_key, rsp->LeaseKey,
+ SMB2_LEASE_KEY_SIZE))
+ continue;
+
+ if (!found && ack_req) {
+ found = true;
+ memcpy(lw->lease_key, open->lease_key,
+ SMB2_LEASE_KEY_SIZE);
+ lw->tlink = cifs_get_tlink(open->tlink);
+ queue_work(cifsiod_wq, &lw->lease_break);
+ }
+
+ cifs_dbg(FYI, "found in the pending open list\n");
+ cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
+ le32_to_cpu(rsp->NewLeaseState));
+
+ open->oplock = lease_state;
+ }
+ return found;
+}
+
+static bool
+smb2_is_valid_lease_break(char *buffer)
{
struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer;
struct list_head *tmp, *tmp1, *tmp2;
+ struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
- struct cifsInodeInfo *cinode;
- struct cifsFileInfo *cfile;
- struct cifs_pending_open *open;
struct smb2_lease_break_work *lw;
- bool found;
- int ack_req = le32_to_cpu(rsp->Flags &
- SMB2_NOTIFY_BREAK_LEASE_FLAG_ACK_REQUIRED);
lw = kmalloc(sizeof(struct smb2_lease_break_work), GFP_KERNEL);
if (!lw)
@@ -438,71 +495,26 @@
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each(tmp, &server->smb_ses_list) {
- ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+ list_for_each(tmp, &cifs_tcp_ses_list) {
+ server = list_entry(tmp, struct TCP_Server_Info, tcp_ses_list);
- spin_lock(&cifs_file_list_lock);
- list_for_each(tmp1, &ses->tcon_list) {
- tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
+ list_for_each(tmp1, &server->smb_ses_list) {
+ ses = list_entry(tmp1, struct cifs_ses, smb_ses_list);
- cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
- list_for_each(tmp2, &tcon->openFileList) {
- cfile = list_entry(tmp2, struct cifsFileInfo,
- tlist);
- cinode = CIFS_I(cfile->dentry->d_inode);
-
- if (memcmp(cinode->lease_key, rsp->LeaseKey,
- SMB2_LEASE_KEY_SIZE))
- continue;
-
- cifs_dbg(FYI, "found in the open list\n");
- cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
- le32_to_cpu(rsp->NewLeaseState));
-
- smb2_set_oplock_level(cinode,
- smb2_map_lease_to_oplock(rsp->NewLeaseState));
-
- if (ack_req)
- cfile->oplock_break_cancelled = false;
- else
- cfile->oplock_break_cancelled = true;
-
- queue_work(cifsiod_wq, &cfile->oplock_break);
-
- spin_unlock(&cifs_file_list_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
-
- found = false;
- list_for_each_entry(open, &tcon->pending_opens, olist) {
- if (memcmp(open->lease_key, rsp->LeaseKey,
- SMB2_LEASE_KEY_SIZE))
- continue;
-
- if (!found && ack_req) {
- found = true;
- memcpy(lw->lease_key, open->lease_key,
- SMB2_LEASE_KEY_SIZE);
- lw->tlink = cifs_get_tlink(open->tlink);
- queue_work(cifsiod_wq,
- &lw->lease_break);
+ spin_lock(&cifs_file_list_lock);
+ list_for_each(tmp2, &ses->tcon_list) {
+ tcon = list_entry(tmp2, struct cifs_tcon,
+ tcon_list);
+ cifs_stats_inc(
+ &tcon->stats.cifs_stats.num_oplock_brks);
+ if (smb2_tcon_has_lease(tcon, rsp, lw)) {
+ spin_unlock(&cifs_file_list_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
}
-
- cifs_dbg(FYI, "found in the pending open list\n");
- cifs_dbg(FYI, "lease key match, lease break 0x%d\n",
- le32_to_cpu(rsp->NewLeaseState));
-
- open->oplock =
- smb2_map_lease_to_oplock(rsp->NewLeaseState);
}
- if (found) {
- spin_unlock(&cifs_file_list_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
+ spin_unlock(&cifs_file_list_lock);
}
- spin_unlock(&cifs_file_list_lock);
}
spin_unlock(&cifs_tcp_ses_lock);
kfree(lw);
@@ -528,7 +540,7 @@
if (rsp->StructureSize !=
smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) {
if (le16_to_cpu(rsp->StructureSize) == 44)
- return smb2_is_valid_lease_break(buffer, server);
+ return smb2_is_valid_lease_break(buffer);
else
return false;
}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f2e76f3..e12f258 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -181,11 +181,8 @@
/* start with specified wsize, or default */
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
wsize = min_t(unsigned int, wsize, server->max_write);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- wsize = min_t(unsigned int, wsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
return wsize;
}
@@ -199,11 +196,8 @@
/* start with specified rsize, or default */
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
rsize = min_t(unsigned int, rsize, server->max_read);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- rsize = min_t(unsigned int, rsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
return rsize;
}
@@ -249,7 +243,7 @@
int rc;
struct smb2_file_all_info *smb2_data;
- smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+ smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
GFP_KERNEL);
if (smb2_data == NULL)
return -ENOMEM;
@@ -560,6 +554,12 @@
get_random_bytes(fid->lease_key, SMB2_LEASE_KEY_SIZE);
}
+static bool
+smb2_dir_needs_close(struct cifsFileInfo *cfile)
+{
+ return !cfile->invalidHandle;
+}
+
struct smb_version_operations smb21_operations = {
.compare_fids = smb2_compare_fids,
.setup_request = smb2_setup_request,
@@ -624,6 +624,7 @@
.set_lease_key = smb2_set_lease_key,
.new_lease_key = smb2_new_lease_key,
.calc_signature = smb2_calc_signature,
+ .dir_needs_close = smb2_dir_needs_close,
};
@@ -691,6 +692,7 @@
.set_lease_key = smb2_set_lease_key,
.new_lease_key = smb2_new_lease_key,
.calc_signature = smb3_calc_signature,
+ .dir_needs_close = smb2_dir_needs_close,
};
struct smb_version_values smb20_values = {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2b95ce2b..eb0de4c 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -408,6 +408,9 @@
server->dialect = le16_to_cpu(rsp->DialectRevision);
server->maxBuf = le32_to_cpu(rsp->MaxTransactSize);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize),
+ SMB2_MAX_BUFFER_SIZE);
server->max_read = le32_to_cpu(rsp->MaxReadSize);
server->max_write = le32_to_cpu(rsp->MaxWriteSize);
/* BB Do we need to validate the SecurityMode? */
@@ -806,7 +809,8 @@
tcon_error_exit:
if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
- tcon->bad_network_name = true;
+ if (tcon)
+ tcon->bad_network_name = true;
}
goto tcon_exit;
}
@@ -1200,7 +1204,7 @@
{
return query_info(xid, tcon, persistent_fid, volatile_fid,
FILE_ALL_INFORMATION,
- sizeof(struct smb2_file_all_info) + MAX_NAME * 2,
+ sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
sizeof(struct smb2_file_all_info), data);
}
@@ -1796,6 +1800,10 @@
rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base;
if (rc) {
+ if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
+ srch_inf->endOfSearch = true;
+ rc = 0;
+ }
cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE);
goto qdir_exit;
}
@@ -1833,11 +1841,6 @@
else
cifs_dbg(VFS, "illegal search buffer type\n");
- if (rsp->hdr.Status == STATUS_NO_MORE_FILES)
- srch_inf->endOfSearch = 1;
- else
- srch_inf->endOfSearch = 0;
-
return rc;
qdir_exit:
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 09afda4..5ac836a 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -82,9 +82,11 @@
goto remove_ea_exit;
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, NULL,
- (__u16)0, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, NULL, (__u16)0,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
}
remove_ea_exit:
kfree(full_path);
@@ -149,18 +151,22 @@
cifs_dbg(FYI, "attempt to set cifs inode metadata\n");
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
- (__u16)value_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, ea_value, (__u16)value_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)
== 0) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
goto set_ea_exit;
ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
- (__u16)value_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, ea_value, (__u16)value_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
#ifdef CONFIG_CIFS_ACL
@@ -170,8 +176,12 @@
rc = -ENOMEM;
} else {
memcpy(pacl, ea_value, value_size);
- rc = set_cifs_acl(pacl, value_size,
- direntry->d_inode, full_path, CIFS_ACL_DACL);
+ if (pTcon->ses->server->ops->set_acl)
+ rc = pTcon->ses->server->ops->set_acl(pacl,
+ value_size, direntry->d_inode,
+ full_path, CIFS_ACL_DACL);
+ else
+ rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
CIFS_I(direntry->d_inode)->time = 0;
kfree(pacl);
@@ -272,17 +282,21 @@
/* revalidate/getattr then populate from inode */
} /* BB add else when above is implemented */
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, ea_name, ea_value, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
goto get_ea_exit;
ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, ea_name, ea_value, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
#ifdef CONFIG_CIFS_POSIX
@@ -313,8 +327,11 @@
u32 acllen;
struct cifs_ntsd *pacl;
- pacl = get_cifs_acl(cifs_sb, direntry->d_inode,
- full_path, &acllen);
+ if (pTcon->ses->server->ops->get_acl == NULL)
+ goto get_ea_exit; /* rc already EOPNOTSUPP */
+
+ pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+ direntry->d_inode, full_path, &acllen);
if (IS_ERR(pacl)) {
rc = PTR_ERR(pacl);
cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
@@ -400,11 +417,12 @@
/* if proc/fs/cifs/streamstoxattr is set then
search server for EAs or streams to
returns as xattrs */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, NULL, data,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, NULL, data, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
list_ea_exit:
kfree(full_path);
free_xid(xid);
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 1da168c..9bc1147 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -92,7 +92,7 @@
struct dentry *de;
spin_lock(&parent->d_lock);
- list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(de, &parent->d_subdirs, d_child) {
/* don't know what to do with negative dentries */
if (de->d_inode )
coda_flag_inode(de->d_inode, flag);
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index a81147e..4d24d17 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -88,6 +88,11 @@
#define ELF_HWCAP COMPAT_ELF_HWCAP
#endif
+#ifdef COMPAT_ELF_HWCAP2
+#undef ELF_HWCAP2
+#define ELF_HWCAP2 COMPAT_ELF_HWCAP2
+#endif
+
#ifdef COMPAT_ARCH_DLINFO
#undef ARCH_DLINFO
#define ARCH_DLINFO COMPAT_ARCH_DLINFO
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 7aabc6a..fa38d07 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -56,10 +56,19 @@
struct configfs_dirent *sd = dentry->d_fsdata;
if (sd) {
- BUG_ON(sd->s_dentry != dentry);
/* Coordinate with configfs_readdir */
spin_lock(&configfs_dirent_lock);
- sd->s_dentry = NULL;
+ /* Coordinate with configfs_attach_attr where will increase
+ * sd->s_count and update sd->s_dentry to new allocated one.
+ * Only set sd->dentry to null when this dentry is the only
+ * sd owner.
+ * If not do so, configfs_d_iput may run just after
+ * configfs_attach_attr and set sd->s_dentry to null
+ * even it's still in use.
+ */
+ if (atomic_read(&sd->s_count) <= 2)
+ sd->s_dentry = NULL;
+
spin_unlock(&configfs_dirent_lock);
configfs_put(sd);
}
@@ -426,8 +435,11 @@
struct configfs_attribute * attr = sd->s_element;
int error;
+ spin_lock(&configfs_dirent_lock);
dentry->d_fsdata = configfs_get(sd);
sd->s_dentry = dentry;
+ spin_unlock(&configfs_dirent_lock);
+
error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG,
configfs_init_file);
if (error) {
diff --git a/fs/coredump.c b/fs/coredump.c
index dafafba..1d402ce 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -299,7 +299,7 @@
if (unlikely(nr < 0))
return nr;
- tsk->flags = PF_DUMPCORE;
+ tsk->flags |= PF_DUMPCORE;
if (atomic_read(&mm->mm_users) == nr + 1)
goto done;
/*
diff --git a/fs/dcache.c b/fs/dcache.c
index f09b908..efa4602 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -43,7 +43,7 @@
/*
* Usage:
* dcache->d_inode->i_lock protects:
- * - i_dentry, d_alias, d_inode of aliases
+ * - i_dentry, d_u.d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* s_anon bl list spinlock protects:
@@ -58,7 +58,7 @@
* - d_unhashed()
* - d_parent and d_subdirs
* - childrens' d_child and d_parent
- * - d_alias, d_inode
+ * - d_u.d_alias, d_inode
*
* Ordering:
* dentry->d_inode->i_lock
@@ -96,8 +96,6 @@
* This hash-function tries to avoid losing too many bits of hash
* information, yet avoid using a prime hash-size or similar.
*/
-#define D_HASHBITS d_hash_shift
-#define D_HASHMASK d_hash_mask
static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
@@ -108,8 +106,7 @@
unsigned int hash)
{
hash += (unsigned long) parent / L1_CACHE_BYTES;
- hash = hash + (hash >> D_HASHBITS);
- return dentry_hashtable + (hash & D_HASHMASK);
+ return dentry_hashtable + hash_32(hash, d_hash_shift);
}
/* Statistics gathering. */
@@ -218,7 +215,6 @@
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- WARN_ON(!hlist_unhashed(&dentry->d_alias));
if (dname_external(dentry))
kfree(dentry->d_name.name);
kmem_cache_free(dentry_cache, dentry);
@@ -229,6 +225,7 @@
*/
static void d_free(struct dentry *dentry)
{
+ WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias));
BUG_ON(dentry->d_count);
this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
@@ -267,7 +264,7 @@
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- hlist_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
@@ -291,7 +288,7 @@
{
struct inode *inode = dentry->d_inode;
dentry->d_inode = NULL;
- hlist_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
@@ -367,9 +364,9 @@
__releases(parent->d_lock)
__releases(dentry->d_inode->i_lock)
{
- list_del(&dentry->d_u.d_child);
+ __list_del_entry(&dentry->d_child);
/*
- * Inform try_to_ascend() that we are no longer attached to the
+ * Inform ascending readers that we are no longer attached to the
* dentry tree
*/
dentry->d_flags |= DCACHE_DENTRY_KILLED;
@@ -663,7 +660,7 @@
again:
discon_alias = NULL;
- hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
@@ -716,7 +713,7 @@
struct dentry *dentry;
restart:
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
@@ -896,7 +893,7 @@
/* descend to the first leaf in the current subtree */
while (!list_empty(&dentry->d_subdirs))
dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_u.d_child);
+ struct dentry, d_child);
/* consume the dentries from this leaf up through its parents
* until we find one with children or run out altogether */
@@ -930,17 +927,17 @@
if (IS_ROOT(dentry)) {
parent = NULL;
- list_del(&dentry->d_u.d_child);
+ list_del(&dentry->d_child);
} else {
parent = dentry->d_parent;
parent->d_count--;
- list_del(&dentry->d_u.d_child);
+ list_del(&dentry->d_child);
}
inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- hlist_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_u.d_alias);
if (dentry->d_op && dentry->d_op->d_iput)
dentry->d_op->d_iput(dentry, inode);
else
@@ -958,7 +955,7 @@
} while (list_empty(&dentry->d_subdirs));
dentry = list_entry(dentry->d_subdirs.next,
- struct dentry, d_u.d_child);
+ struct dentry, d_child);
}
}
@@ -991,35 +988,6 @@
}
/*
- * This tries to ascend one level of parenthood, but
- * we can race with renaming, so we need to re-check
- * the parenthood after dropping the lock and check
- * that the sequence number still matches.
- */
-static struct dentry *try_to_ascend(struct dentry *old, int locked, unsigned seq)
-{
- struct dentry *new = old->d_parent;
-
- rcu_read_lock();
- spin_unlock(&old->d_lock);
- spin_lock(&new->d_lock);
-
- /*
- * might go back up the wrong parent if we have had a rename
- * or deletion
- */
- if (new != old->d_parent ||
- (old->d_flags & DCACHE_DENTRY_KILLED) ||
- (!locked && read_seqretry(&rename_lock, seq))) {
- spin_unlock(&new->d_lock);
- new = NULL;
- }
- rcu_read_unlock();
- return new;
-}
-
-
-/*
* Search for at least 1 mount point in the dentry's subdirs.
* We descend to the next level whenever the d_subdirs
* list is non-empty and continue searching.
@@ -1051,7 +1019,7 @@
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1073,30 +1041,48 @@
/*
* All done at this level ... ascend and resume the search.
*/
+ rcu_read_lock();
+ascend:
if (this_parent != parent) {
struct dentry *child = this_parent;
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ next = child->d_child.next;
+ while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ next = next->next;
+ }
+ rcu_read_unlock();
goto resume;
}
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return 0; /* No mount points found in tree */
positive:
if (!locked && read_seqretry(&rename_lock, seq))
- goto rename_retry;
+ goto rename_retry_unlocked;
if (locked)
write_sequnlock(&rename_lock);
return 1;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
goto again;
+rename_retry_unlocked:
locked = 1;
write_seqlock(&rename_lock);
goto again;
@@ -1134,7 +1120,7 @@
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1161,6 +1147,7 @@
*/
if (found && need_resched()) {
spin_unlock(&dentry->d_lock);
+ rcu_read_lock();
goto out;
}
@@ -1180,23 +1167,40 @@
/*
* All done at this level ... ascend and resume the search.
*/
+ rcu_read_lock();
+ascend:
if (this_parent != parent) {
struct dentry *child = this_parent;
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ next = child->d_child.next;
+ while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ next = next->next;
+ }
+ rcu_read_unlock();
goto resume;
}
out:
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return found;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (found)
return found;
if (locked)
@@ -1281,8 +1285,8 @@
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
- INIT_HLIST_NODE(&dentry->d_alias);
- INIT_LIST_HEAD(&dentry->d_u.d_child);
+ INIT_HLIST_NODE(&dentry->d_u.d_alias);
+ INIT_LIST_HEAD(&dentry->d_child);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
this_cpu_inc(nr_dentry);
@@ -1312,7 +1316,7 @@
*/
__dget_dlock(parent);
dentry->d_parent = parent;
- list_add(&dentry->d_u.d_child, &parent->d_subdirs);
+ list_add(&dentry->d_child, &parent->d_subdirs);
spin_unlock(&parent->d_lock);
return dentry;
@@ -1372,7 +1376,7 @@
if (inode) {
if (unlikely(IS_AUTOMOUNT(inode)))
dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
- hlist_add_head(&dentry->d_alias, &inode->i_dentry);
+ hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
}
dentry->d_inode = inode;
dentry_rcuwalk_barrier(dentry);
@@ -1397,7 +1401,7 @@
void d_instantiate(struct dentry *entry, struct inode * inode)
{
- BUG_ON(!hlist_unhashed(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
@@ -1436,7 +1440,7 @@
return NULL;
}
- hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
@@ -1462,7 +1466,7 @@
{
struct dentry *result;
- BUG_ON(!hlist_unhashed(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode)
spin_lock(&inode->i_lock);
@@ -1505,7 +1509,7 @@
if (hlist_empty(&inode->i_dentry))
return NULL;
- alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
__dget(alias);
return alias;
}
@@ -1579,7 +1583,7 @@
spin_lock(&tmp->d_lock);
tmp->d_inode = inode;
tmp->d_flags |= DCACHE_DISCONNECTED;
- hlist_add_head(&tmp->d_alias, &inode->i_dentry);
+ hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -2022,7 +2026,7 @@
struct dentry *child;
spin_lock(&dparent->d_lock);
- list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &dparent->d_subdirs, d_child) {
if (dentry == child) {
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
__dget_dlock(dentry);
@@ -2269,8 +2273,8 @@
/* Unhash the target: dput() will then get rid of it */
__d_drop(target);
- list_del(&dentry->d_u.d_child);
- list_del(&target->d_u.d_child);
+ list_del(&dentry->d_child);
+ list_del(&target->d_child);
/* Switch the names.. */
switch_names(dentry, target);
@@ -2280,15 +2284,15 @@
if (IS_ROOT(dentry)) {
dentry->d_parent = target->d_parent;
target->d_parent = target;
- INIT_LIST_HEAD(&target->d_u.d_child);
+ INIT_LIST_HEAD(&target->d_child);
} else {
swap(dentry->d_parent, target->d_parent);
/* And add them back to the (new) parent lists */
- list_add(&target->d_u.d_child, &target->d_parent->d_subdirs);
+ list_add(&target->d_child, &target->d_parent->d_subdirs);
}
- list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+ list_add(&dentry->d_child, &dentry->d_parent->d_subdirs);
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
@@ -2395,9 +2399,9 @@
swap(dentry->d_name.hash, anon->d_name.hash);
dentry->d_parent = dentry;
- list_del_init(&dentry->d_u.d_child);
+ list_del_init(&dentry->d_child);
anon->d_parent = dparent;
- list_move(&anon->d_u.d_child, &dparent->d_subdirs);
+ list_move(&anon->d_child, &dparent->d_subdirs);
write_seqcount_end(&dentry->d_seq);
write_seqcount_end(&anon->d_seq);
@@ -2686,8 +2690,13 @@
* thus don't need to be hashed. They also don't need a name until a
* user wants to identify the object in /proc/pid/fd/. The little hack
* below allows us to generate a name for these objects on demand:
+ *
+ * Some pseudo inodes are mountable. When they are mounted
+ * path->dentry == path->mnt->mnt_root. In that case don't call d_dname
+ * and instead have d_path return the mounted path.
*/
- if (path->dentry->d_op && path->dentry->d_op->d_dname)
+ if (path->dentry->d_op && path->dentry->d_op->d_dname &&
+ (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
get_fs_root(current->fs, &root);
@@ -2724,6 +2733,17 @@
return memcpy(buffer, temp, sz);
}
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ char *end = buffer + buflen;
+ /* these dentries are never renamed, so d_lock is not needed */
+ if (prepend(&end, &buflen, " (deleted)", 11) ||
+ prepend_name(&end, &buflen, &dentry->d_name) ||
+ prepend(&end, &buflen, "/", 1))
+ end = ERR_PTR(-ENAMETOOLONG);
+ return end;
+}
+
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
@@ -2920,7 +2940,7 @@
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
- struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
@@ -2941,26 +2961,43 @@
}
spin_unlock(&dentry->d_lock);
}
+ rcu_read_lock();
+ascend:
if (this_parent != root) {
struct dentry *child = this_parent;
if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
this_parent->d_flags |= DCACHE_GENOCIDE;
this_parent->d_count--;
}
- this_parent = try_to_ascend(this_parent, locked, seq);
- if (!this_parent)
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* might go back up the wrong parent if we have had a rename. */
+ if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
- next = child->d_u.d_child.next;
+ next = child->d_child.next;
+ while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ next = next->next;
+ }
+ rcu_read_unlock();
goto resume;
}
- spin_unlock(&this_parent->d_lock);
if (!locked && read_seqretry(&rename_lock, seq))
goto rename_retry;
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
write_sequnlock(&rename_lock);
return;
rename_retry:
+ spin_unlock(&this_parent->d_lock);
+ rcu_read_unlock();
if (locked)
goto again;
locked = 1;
diff --git a/fs/dcookies.c b/fs/dcookies.c
index ab5954b..ac44a69 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -204,7 +204,7 @@
}
#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, size_t, len)
+COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len)
{
#ifdef __BIG_ENDIAN
return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 4888cb3..26d7fff 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -245,10 +245,19 @@
return 0;
}
+static void debugfs_evict_inode(struct inode *inode)
+{
+ truncate_inode_pages(&inode->i_data, 0);
+ clear_inode(inode);
+ if (S_ISLNK(inode->i_mode))
+ kfree(inode->i_private);
+}
+
static const struct super_operations debugfs_super_operations = {
.statfs = simple_statfs,
.remount_fs = debugfs_remount,
.show_options = debugfs_show_options,
+ .evict_inode = debugfs_evict_inode,
};
static int debug_fill_super(struct super_block *sb, void *data, int silent)
@@ -465,23 +474,14 @@
int ret = 0;
if (debugfs_positive(dentry)) {
- if (dentry->d_inode) {
- dget(dentry);
- switch (dentry->d_inode->i_mode & S_IFMT) {
- case S_IFDIR:
- ret = simple_rmdir(parent->d_inode, dentry);
- break;
- case S_IFLNK:
- kfree(dentry->d_inode->i_private);
- /* fall through */
- default:
- simple_unlink(parent->d_inode, dentry);
- break;
- }
- if (!ret)
- d_delete(dentry);
- dput(dentry);
- }
+ dget(dentry);
+ if (S_ISDIR(dentry->d_inode->i_mode))
+ ret = simple_rmdir(parent->d_inode, dentry);
+ else
+ simple_unlink(parent->d_inode, dentry);
+ if (!ret)
+ d_delete(dentry);
+ dput(dentry);
}
return ret;
}
@@ -533,8 +533,7 @@
*/
void debugfs_remove_recursive(struct dentry *dentry)
{
- struct dentry *child;
- struct dentry *parent;
+ struct dentry *child, *next, *parent;
if (IS_ERR_OR_NULL(dentry))
return;
@@ -544,61 +543,37 @@
return;
parent = dentry;
+ down:
mutex_lock(&parent->d_inode->i_mutex);
+ list_for_each_entry_safe(child, next, &parent->d_subdirs, d_child) {
+ if (!debugfs_positive(child))
+ continue;
- while (1) {
- /*
- * When all dentries under "parent" has been removed,
- * walk up the tree until we reach our starting point.
- */
- if (list_empty(&parent->d_subdirs)) {
- mutex_unlock(&parent->d_inode->i_mutex);
- if (parent == dentry)
- break;
- parent = parent->d_parent;
- mutex_lock(&parent->d_inode->i_mutex);
- }
- child = list_entry(parent->d_subdirs.next, struct dentry,
- d_u.d_child);
- next_sibling:
-
- /*
- * If "child" isn't empty, walk down the tree and
- * remove all its descendants first.
- */
+ /* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
mutex_unlock(&parent->d_inode->i_mutex);
parent = child;
- mutex_lock(&parent->d_inode->i_mutex);
- continue;
+ goto down;
}
- __debugfs_remove(child, parent);
- if (parent->d_subdirs.next == &child->d_u.d_child) {
- /*
- * Try the next sibling.
- */
- if (child->d_u.d_child.next != &parent->d_subdirs) {
- child = list_entry(child->d_u.d_child.next,
- struct dentry,
- d_u.d_child);
- goto next_sibling;
- }
-
- /*
- * Avoid infinite loop if we fail to remove
- * one dentry.
- */
- mutex_unlock(&parent->d_inode->i_mutex);
- break;
- }
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ up:
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
- parent = dentry->d_parent;
- mutex_lock(&parent->d_inode->i_mutex);
- __debugfs_remove(dentry, parent);
mutex_unlock(&parent->d_inode->i_mutex);
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ child = parent;
+ parent = parent->d_parent;
+ mutex_lock(&parent->d_inode->i_mutex);
+
+ if (child != dentry) {
+ next = list_entry(child->d_child.next, struct dentry,
+ d_child);
+ goto up;
+ }
+
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ mutex_unlock(&parent->d_inode->i_mutex);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 073d30b..a726b9f 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -498,6 +498,7 @@
{
struct pts_fs_info *fsi = DEVPTS_SB(sb);
+ ida_destroy(&fsi->allocated_ptys);
kfree(fsi);
kill_litter_super(sb);
}
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index f71ec12..1da2446 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -2102,7 +2102,6 @@
break;
case 2:
dst[dst_byte_offset++] |= (src_byte);
- dst[dst_byte_offset] = 0;
current_bit_offset = 0;
break;
}
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index a7abbea..9ff3664 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -196,23 +196,11 @@
{
int rc = 0;
struct ecryptfs_crypt_stat *crypt_stat = NULL;
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *ecryptfs_dentry = file->f_path.dentry;
/* Private value of ecryptfs_dentry allocated in
* ecryptfs_lookup() */
struct ecryptfs_file_info *file_info;
- mount_crypt_stat = &ecryptfs_superblock_to_private(
- ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
- && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
- || (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
- || (file->f_flags & O_APPEND))) {
- printk(KERN_WARNING "Mount has encrypted view enabled; "
- "files may only be read\n");
- rc = -EPERM;
- goto out;
- }
/* Released in ecryptfs_release or end of function if failure */
file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
ecryptfs_set_file_private(file, file_info);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 5eab400..41baf8b 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1051,7 +1051,7 @@
}
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
- if (!rc)
+ if (!rc && dentry->d_inode)
fsstack_copy_attr_all(dentry->d_inode, lower_dentry->d_inode);
out:
return rc;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 7d52806..4725a07 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1149,7 +1149,7 @@
struct ecryptfs_msg_ctx *msg_ctx;
struct ecryptfs_message *msg = NULL;
char *auth_tok_sig;
- char *payload;
+ char *payload = NULL;
size_t payload_len = 0;
int rc;
@@ -1203,6 +1203,7 @@
}
out:
kfree(msg);
+ kfree(payload);
return rc;
}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index e924cf4..329a9cc 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -494,6 +494,7 @@
{
struct super_block *s;
struct ecryptfs_sb_info *sbi;
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct ecryptfs_dentry_info *root_info;
const char *err = "Getting sb failed";
struct inode *inode;
@@ -512,6 +513,7 @@
err = "Error parsing options";
goto out;
}
+ mount_crypt_stat = &sbi->mount_crypt_stat;
s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s)) {
@@ -558,11 +560,19 @@
/**
* Set the POSIX ACL flag based on whether they're enabled in the lower
- * mount. Force a read-only eCryptfs mount if the lower mount is ro.
- * Allow a ro eCryptfs mount even when the lower mount is rw.
+ * mount.
*/
s->s_flags = flags & ~MS_POSIXACL;
- s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+ s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+ /**
+ * Force a read-only eCryptfs mount when:
+ * 1) The lower mount is ro
+ * 2) The ecryptfs_encrypted_view mount option is specified
+ */
+ if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+ mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+ s->s_flags |= MS_RDONLY;
s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
s->s_blocksize = path.dentry->d_sb->s_blocksize;
diff --git a/fs/exec.c b/fs/exec.c
index ffd7a81..dd6aa61 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -607,7 +607,7 @@
return -ENOMEM;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, old_start, old_end);
if (new_end > old_start) {
/*
* when the old and new regions overlap clear from new_end.
@@ -624,7 +624,7 @@
free_pgd_range(&tlb, old_start, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
}
- tlb_finish_mmu(&tlb, new_end, old_end);
+ tlb_finish_mmu(&tlb, old_start, old_end);
/*
* Shrink the vma to just the new range. Always succeeds.
@@ -654,10 +654,10 @@
unsigned long rlim_stack;
#ifdef CONFIG_STACK_GROWSUP
- /* Limit stack size to 1GB */
+ /* Limit stack size */
stack_base = rlimit_max(RLIMIT_STACK);
- if (stack_base > (1 << 30))
- stack_base = 1 << 30;
+ if (stack_base > STACK_SIZE_MAX)
+ stack_base = STACK_SIZE_MAX;
/* Make sure we didn't let the argument array grow too large. */
if (vma->vm_end - vma->vm_start > stack_base)
@@ -1669,6 +1669,12 @@
return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret;
}
+/*
+ * This returns the actual value of the suid_dumpable flag. For things
+ * that are using this for checking for privilege transitions, it must
+ * test against SUID_DUMP_USER rather than treating it as a boolean
+ * value.
+ */
int get_dumpable(struct mm_struct *mm)
{
return __get_dumpable(mm->flags);
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index b744228..85cde3e 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -103,7 +103,7 @@
layout->max_io_length =
(BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
- layout->group_width;
+ (layout->group_width - layout->parity);
if (layout->parity) {
unsigned stripe_length =
(layout->group_width - layout->parity) *
@@ -286,7 +286,8 @@
if (length) {
ore_calc_stripe_info(layout, offset, length, &ios->si);
ios->length = ios->si.length;
- ios->nr_pages = (ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
+ ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
+ ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
if (layout->parity)
_ore_post_alloc_raid_stuff(ios);
}
@@ -536,6 +537,7 @@
u64 H = LmodS - G * T;
u32 N = div_u64(H, U);
+ u32 Nlast;
/* "H - (N * U)" is just "H % U" so it's bound to u32 */
u32 C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
@@ -568,6 +570,10 @@
si->length = T - H;
if (si->length > length)
si->length = length;
+
+ Nlast = div_u64(H + si->length + U - 1, U);
+ si->maxdevUnits = Nlast - N;
+
si->M = M;
}
EXPORT_SYMBOL(ore_calc_stripe_info);
@@ -583,13 +589,16 @@
int ret;
if (per_dev->bio == NULL) {
- unsigned pages_in_stripe = ios->layout->group_width *
- (ios->layout->stripe_unit / PAGE_SIZE);
- unsigned nr_pages = ios->nr_pages * ios->layout->group_width /
- (ios->layout->group_width -
- ios->layout->parity);
- unsigned bio_size = (nr_pages + pages_in_stripe) /
- ios->layout->group_width;
+ unsigned bio_size;
+
+ if (!ios->reading) {
+ bio_size = ios->si.maxdevUnits;
+ } else {
+ bio_size = (ios->si.maxdevUnits + 1) *
+ (ios->layout->group_width - ios->layout->parity) /
+ ios->layout->group_width;
+ }
+ bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
if (unlikely(!per_dev->bio)) {
@@ -609,8 +618,12 @@
added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
pglen, pgbase);
if (unlikely(pglen != added_len)) {
- ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=%u\n",
- per_dev->bio->bi_vcnt);
+ /* If bi_vcnt == bi_max then this is a SW BUG */
+ ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
+ "bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
+ per_dev->bio->bi_vcnt,
+ per_dev->bio->bi_max_vecs,
+ BIO_MAX_PAGES_KMALLOC, cur_len);
ret = -ENOMEM;
goto out;
}
@@ -1098,7 +1111,7 @@
size_attr->attr = g_attr_logical_length;
size_attr->attr.val_ptr = &size_attr->newsize;
- ORE_DBGMSG("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
+ ORE_DBGMSG2("trunc(0x%llx) obj_offset=0x%llx dev=%d\n",
_LLU(oc->comps->obj.id), _LLU(obj_size), i);
ret = _truncate_mirrors(ios, i * ios->layout->mirrors_p1,
&size_attr->attr);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 262fc99..b4eec4c 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -50,7 +50,7 @@
inode = result->d_inode;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
dget(dentry);
spin_unlock(&inode->i_lock);
if (toput)
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0a87bb1..99d84ce 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -632,6 +632,8 @@
int count = 0;
ext2_fsblk_t first_block = 0;
+ BUG_ON(maxblocks == 0);
+
depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary);
if (depth == 0)
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 2885349..20d6697 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1493,6 +1493,7 @@
sb->s_blocksize - offset : towrite;
tmp_bh.b_state = 0;
+ tmp_bh.b_size = sb->s_blocksize;
err = ext2_get_block(inode, blk, &tmp_bh, 1);
if (err < 0)
goto out;
diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index 1c33128..e98171a 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -35,6 +35,7 @@
int rc;
memset(&tmp, 0, sizeof(struct buffer_head));
+ tmp.b_size = 1 << inode->i_blkbits;
rc = ext2_get_block(inode, pgoff, &tmp, create);
*result = tmp.b_blocknr;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 692de13..cea8ecf 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -576,11 +576,8 @@
if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
+((char *)de - bh->b_data))) {
- /* On error, skip the f_pos to the next block. */
- dir_file->f_pos = (dir_file->f_pos |
- (dir->i_sb->s_blocksize - 1)) + 1;
- brelse (bh);
- return count;
+ /* silently ignore the rest of the block */
+ break;
}
ext3fs_dirhash(de->name, de->name_len, hinfo);
if ((hinfo->hash < start_hash) ||
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 6356665..882d4bd 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -1300,13 +1300,6 @@
"not specified.");
return 0;
}
- } else {
- if (sbi->s_jquota_fmt) {
- ext3_msg(sb, KERN_ERR, "error: journaled quota format "
- "specified with no journaling "
- "enabled.");
- return 0;
- }
}
#endif
return 1;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index d0f13ea..3742e4c 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -38,8 +38,8 @@
ext4_group_t group;
if (test_opt2(sb, STD_GROUP_SIZE))
- group = (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
- block) >>
+ group = (block -
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) >>
(EXT4_BLOCK_SIZE_BITS(sb) + EXT4_CLUSTER_BITS(sb) + 3);
else
ext4_get_group_no_and_offset(sb, block, &group, NULL);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5aae3d1..2a71466 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -280,6 +280,16 @@
/* Translate # of blks to # of clusters */
#define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \
(sbi)->s_cluster_bits)
+/* Mask out the low bits to get the starting block of the cluster */
+#define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \
+ ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \
+ ~((ext4_lblk_t) (s)->s_cluster_ratio - 1))
+/* Get the cluster offset */
+#define EXT4_PBLK_COFF(s, pblk) ((pblk) & \
+ ((ext4_fsblk_t) (s)->s_cluster_ratio - 1))
+#define EXT4_LBLK_COFF(s, lblk) ((lblk) & \
+ ((ext4_lblk_t) (s)->s_cluster_ratio - 1))
/*
* Structure of a blocks group descriptor
@@ -579,6 +589,7 @@
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+#define EXT4_FREE_BLOCKS_RESERVE 0x0040
/*
* Flags used by ext4_discard_partial_page_buffers
@@ -764,6 +775,8 @@
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
(einode)->xtime.tv_sec = \
(signed)le32_to_cpu((raw_inode)->xtime); \
+ else \
+ (einode)->xtime.tv_sec = 0; \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
@@ -2076,6 +2089,7 @@
#define CONVERT_INLINE_DATA 2
extern struct inode *ext4_iget(struct super_block *, unsigned long);
+extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
extern int ext4_write_inode(struct inode *, struct writeback_control *);
extern int ext4_setattr(struct dentry *, struct iattr *);
extern int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
@@ -2248,8 +2262,8 @@
static inline int ext4_has_group_desc_csum(struct super_block *sb)
{
return EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_GDT_CSUM |
- EXT4_FEATURE_RO_COMPAT_METADATA_CSUM);
+ EXT4_FEATURE_RO_COMPAT_GDT_CSUM) ||
+ (EXT4_SB(sb)->s_chksum_driver != NULL);
}
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 451eb40..1be3996 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -219,10 +219,19 @@
set_buffer_prio(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
- if (err) {
- /* Errors can only happen if there is a bug */
- handle->h_err = err;
- __ext4_journal_stop(where, line, handle);
+ /* Errors can only happen if there is a bug */
+ if (WARN_ON_ONCE(err)) {
+ ext4_journal_abort_handle(where, line, __func__, bh,
+ handle, err);
+ ext4_error_inode(inode, where, line,
+ bh->b_blocknr,
+ "journal_dirty_metadata failed: "
+ "handle type %u started at line %u, "
+ "credits %u/%u, errcode %d",
+ handle->h_type,
+ handle->h_line_no,
+ handle->h_requested_credits,
+ handle->h_buffer_credits, err);
}
} else {
if (inode)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index bc0f1910..7fbd1c5 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -360,8 +360,10 @@
{
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
+ ext4_lblk_t last = lblock + len - 1;
- if (len == 0)
+ if (lblock > last)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
@@ -387,11 +389,26 @@
if (depth == 0) {
/* leaf entries */
struct ext4_extent *ext = EXT_FIRST_EXTENT(eh);
+ struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ ext4_fsblk_t pblock = 0;
+ ext4_lblk_t lblock = 0;
+ ext4_lblk_t prev = 0;
+ int len = 0;
while (entries) {
if (!ext4_valid_extent(inode, ext))
return 0;
+
+ /* Check for overlapping extents */
+ lblock = le32_to_cpu(ext->ee_block);
+ len = ext4_ext_get_actual_len(ext);
+ if ((lblock <= prev) && prev) {
+ pblock = ext4_ext_pblock(ext);
+ es->s_last_error_block = cpu_to_le64(pblock);
+ return 0;
+ }
ext++;
entries--;
+ prev = lblock + len - 1;
}
} else {
struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh);
@@ -1705,7 +1722,8 @@
brelse(path[1].p_bh);
ext4_free_blocks(handle, inode, NULL, blk, 1,
- EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET |
+ EXT4_FREE_BLOCKS_RESERVE);
}
/*
@@ -1755,8 +1773,7 @@
depth = ext_depth(inode);
if (!path[depth].p_ext)
goto out;
- b2 = le32_to_cpu(path[depth].p_ext->ee_block);
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block));
/*
* get the next allocated block if the extent in the path
@@ -1766,7 +1783,7 @@
b2 = ext4_ext_next_allocated_block(path);
if (b2 == EXT_MAX_BLOCKS)
goto out;
- b2 &= ~(sbi->s_cluster_ratio - 1);
+ b2 = EXT4_LBLK_CMASK(sbi, b2);
}
/* check for wrap through zero on extent logical start block*/
@@ -2427,7 +2444,7 @@
* truncate operation has removed all of the blocks in
* the cluster.
*/
- if (pblk & (sbi->s_cluster_ratio - 1) &&
+ if (EXT4_PBLK_COFF(sbi, pblk) &&
(ee_len == num))
*partial_cluster = EXT4_B2C(sbi, pblk);
else
@@ -2495,6 +2512,27 @@
ex_ee_block = le32_to_cpu(ex->ee_block);
ex_ee_len = ext4_ext_get_actual_len(ex);
+ /*
+ * If we're starting with an extent other than the last one in the
+ * node, we need to see if it shares a cluster with the extent to
+ * the right (towards the end of the file). If its leftmost cluster
+ * is this extent's rightmost cluster and it is not cluster aligned,
+ * we'll mark it as a partial that is not to be deallocated.
+ */
+
+ if (ex != EXT_LAST_EXTENT(eh)) {
+ ext4_fsblk_t current_pblk, right_pblk;
+ long long current_cluster, right_cluster;
+
+ current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
+ current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
+ right_pblk = ext4_ext_pblock(ex + 1);
+ right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
+ if (current_cluster == right_cluster &&
+ EXT4_PBLK_COFF(sbi, right_pblk))
+ *partial_cluster = -right_cluster;
+ }
+
trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
while (ex >= EXT_FIRST_EXTENT(eh) &&
@@ -3658,7 +3696,7 @@
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t lblk_start, lblk_end;
- lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
+ lblk_start = EXT4_LBLK_CMASK(sbi, lblk);
lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
@@ -3717,9 +3755,9 @@
trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks);
/* Check towards left side */
- c_offset = lblk_start & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start);
if (c_offset) {
- lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
+ lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start);
lblk_to = lblk_from + c_offset - 1;
if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
@@ -3727,7 +3765,7 @@
}
/* Now check towards right. */
- c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1);
+ c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks);
if (allocated_clusters && c_offset) {
lblk_from = lblk_start + num_blks;
lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
@@ -3935,7 +3973,7 @@
struct ext4_ext_path *path)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ext4_lblk_t ex_cluster_start, ex_cluster_end;
ext4_lblk_t rr_cluster_start;
ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block);
@@ -3953,8 +3991,7 @@
(rr_cluster_start == ex_cluster_start)) {
if (rr_cluster_start == ex_cluster_end)
ee_start += ee_len - 1;
- map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) +
- c_offset;
+ map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset;
map->m_len = min(map->m_len,
(unsigned) sbi->s_cluster_ratio - c_offset);
/*
@@ -4017,7 +4054,7 @@
struct ext4_extent newex, *ex, *ex2;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_fsblk_t newblock = 0;
- int free_on_err = 0, err = 0, depth;
+ int free_on_err = 0, err = 0, depth, ret;
unsigned int allocated = 0, offset = 0;
unsigned int allocated_clusters = 0;
struct ext4_allocation_request ar;
@@ -4078,9 +4115,13 @@
if (!ext4_ext_is_uninitialized(ex))
goto out;
- allocated = ext4_ext_handle_uninitialized_extents(
+ ret = ext4_ext_handle_uninitialized_extents(
handle, inode, map, path, flags,
allocated, newblock);
+ if (ret < 0)
+ err = ret;
+ else
+ allocated = ret;
goto out3;
}
}
@@ -4108,7 +4149,7 @@
*/
map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
newex.ee_block = cpu_to_le32(map->m_lblk);
- cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1);
+ cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
/*
* If we are doing bigalloc, check to see if the extent returned
@@ -4176,7 +4217,7 @@
* needed so that future calls to get_implied_cluster_alloc()
* work correctly.
*/
- offset = map->m_lblk & (sbi->s_cluster_ratio - 1);
+ offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
ar.len = EXT4_NUM_B2C(sbi, offset+allocated);
ar.goal -= offset;
ar.logical -= offset;
@@ -4386,9 +4427,20 @@
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
+retry:
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
+ if (err == -ENOMEM) {
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+ if (err) {
+ ext4_std_error(inode->i_sb, err);
+ return;
+ }
err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
+ ext4_std_error(inode->i_sb, err);
}
static void ext4_falloc_update_inode(struct inode *inode,
@@ -4659,7 +4711,7 @@
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
- physical = iloc.bh->b_blocknr << blockbits;
+ physical = (__u64)iloc.bh->b_blocknr << blockbits;
offset = EXT4_GOOD_OLD_INODE_SIZE +
EXT4_I(inode)->i_extra_isize;
physical += offset;
@@ -4667,7 +4719,7 @@
flags |= FIEMAP_EXTENT_DATA_INLINE;
brelse(iloc.bh);
} else { /* external block */
- physical = EXT4_I(inode)->i_file_acl << blockbits;
+ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits;
length = inode->i_sb->s_blocksize;
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b1b4d51..ec9770f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -82,7 +82,7 @@
size_t count = iov_length(iov, nr_segs);
loff_t final_size = pos + count;
- if (pos >= inode->i_size)
+ if (pos >= i_size_read(inode))
return 0;
if ((pos & blockmask) || (final_size & blockmask))
@@ -100,7 +100,7 @@
struct blk_plug plug;
int unaligned_aio = 0;
ssize_t ret;
- int overwrite = 0;
+ int *overwrite = iocb->private;
size_t length = iov_length(iov, nr_segs);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
@@ -118,8 +118,6 @@
mutex_lock(&inode->i_mutex);
blk_start_plug(&plug);
- iocb->private = &overwrite;
-
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
@@ -143,7 +141,7 @@
* So we should check these two conditions.
*/
if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
- overwrite = 1;
+ *overwrite = 1;
}
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
@@ -170,6 +168,7 @@
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ int overwrite = 0;
/*
* If we have encountered a bitmap-format file, the size limit
@@ -190,6 +189,7 @@
}
}
+ iocb->private = &overwrite;
if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
else
@@ -312,7 +312,7 @@
blkbits = inode->i_sb->s_blocksize_bits;
startoff = *offset;
lastoff = startoff;
- endoff = (map->m_lblk + map->m_len) << blkbits;
+ endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
index = startoff >> PAGE_CACHE_SHIFT;
end = endoff >> PAGE_CACHE_SHIFT;
@@ -457,7 +457,7 @@
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
if (last != start)
- dataoff = last << blkbits;
+ dataoff = (loff_t)last << blkbits;
break;
}
@@ -468,7 +468,7 @@
ext4_es_find_delayed_extent_range(inode, last, last, &es);
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
if (last != start)
- dataoff = last << blkbits;
+ dataoff = (loff_t)last << blkbits;
break;
}
@@ -486,7 +486,7 @@
}
last++;
- dataoff = last << blkbits;
+ dataoff = (loff_t)last << blkbits;
} while (last <= end);
mutex_unlock(&inode->i_mutex);
@@ -540,7 +540,7 @@
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
last += ret;
- holeoff = last << blkbits;
+ holeoff = (loff_t)last << blkbits;
continue;
}
@@ -551,7 +551,7 @@
ext4_es_find_delayed_extent_range(inode, last, last, &es);
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
last = es.es_lblk + es.es_len;
- holeoff = last << blkbits;
+ holeoff = (loff_t)last << blkbits;
continue;
}
@@ -566,7 +566,7 @@
&map, &holeoff);
if (!unwritten) {
last += ret;
- holeoff = last << blkbits;
+ holeoff = (loff_t)last << blkbits;
continue;
}
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 00a818d..4d4718c 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -734,11 +734,8 @@
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
EXT4_INODES_PER_GROUP(sb), ino);
- if (ino >= EXT4_INODES_PER_GROUP(sb)) {
- if (++group == ngroups)
- group = 0;
- continue;
- }
+ if (ino >= EXT4_INODES_PER_GROUP(sb))
+ goto next_group;
if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
ext4_error(sb, "reserved inode found cleared - "
"inode=%lu", ino + 1);
@@ -768,6 +765,9 @@
goto got; /* we grabbed the inode! */
if (ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
+next_group:
+ if (++group == ngroups)
+ group = 0;
}
err = -ENOSPC;
goto out;
@@ -780,12 +780,23 @@
goto out;
}
+ BUFFER_TRACE(group_desc_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, group_desc_bh);
+ if (err) {
+ ext4_std_error(sb, err);
+ goto out;
+ }
+
/* We may have to initialize the block bitmap if it isn't already */
if (ext4_has_group_desc_csum(sb) &&
gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
struct buffer_head *block_bitmap_bh;
block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (!block_bitmap_bh) {
+ err = -EIO;
+ goto out;
+ }
BUFFER_TRACE(block_bitmap_bh, "get block bitmap access");
err = ext4_journal_get_write_access(handle, block_bitmap_bh);
if (err) {
@@ -816,13 +827,6 @@
}
}
- BUFFER_TRACE(group_desc_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, group_desc_bh);
- if (err) {
- ext4_std_error(sb, err);
- goto out;
- }
-
/* Update the relevant bg descriptor fields */
if (ext4_has_group_desc_csum(sb)) {
int free;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8d5d35..5890614 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -390,7 +390,13 @@
return 0;
failed:
for (; i >= 0; i--) {
- if (i != indirect_blks && branch[i].bh)
+ /*
+ * We want to ext4_forget() only freshly allocated indirect
+ * blocks. Buffer for new_blocks[i-1] is at branch[i].bh and
+ * buffer at branch[0].bh is indirect block / inode already
+ * existing before ext4_alloc_branch() was called.
+ */
+ if (i > 0 && i != indirect_blks && branch[i].bh)
ext4_forget(handle, 1, inode, branch[i].bh,
branch[i].bh->b_blocknr);
ext4_free_blocks(handle, inode, NULL, new_blocks[i],
@@ -1325,16 +1331,24 @@
blk = *i_data;
if (level > 0) {
ext4_lblk_t first2;
+ ext4_lblk_t count2;
+
bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
if (!bh) {
EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
"Read failure");
return -EIO;
}
- first2 = (first > offset) ? first - offset : 0;
+ if (first > offset) {
+ first2 = first - offset;
+ count2 = count;
+ } else {
+ first2 = 0;
+ count2 = count - (offset - first);
+ }
ret = free_hole_blocks(handle, inode, bh,
(__le32 *)bh->b_data, level - 1,
- first2, count - offset,
+ first2, count2,
inode->i_sb->s_blocksize >> 2);
if (ret) {
brelse(bh);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 3e2bf87..e350be6 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1842,7 +1842,7 @@
if (error)
goto out;
- physical = iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits;
+ physical = (__u64)iloc.bh->b_blocknr << inode->i_sb->s_blocksize_bits;
physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data;
physical += offsetof(struct ext4_inode, i_block);
length = i_size_read(inode);
@@ -1957,9 +1957,11 @@
}
/* Clear the content within i_blocks. */
- if (i_size < EXT4_MIN_INLINE_DATA_SIZE)
- memset(ext4_raw_inode(&is.iloc)->i_block + i_size, 0,
- EXT4_MIN_INLINE_DATA_SIZE - i_size);
+ if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
+ void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
+ memset(p + i_size, 0,
+ EXT4_MIN_INLINE_DATA_SIZE - i_size);
+ }
EXT4_I(inode)->i_inline_size = i_size <
EXT4_MIN_INLINE_DATA_SIZE ?
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d6382b8..e48bd5a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -38,6 +38,7 @@
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/aio.h>
+#include <linux/bitops.h>
#include "ext4_jbd2.h"
#include "xattr.h"
@@ -1118,10 +1119,13 @@
}
}
- if (ext4_has_inline_data(inode))
- copied = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- else
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_write_inline_data_end(inode, pos, len,
+ copied, page);
+ if (ret < 0)
+ goto errout;
+ copied = ret;
+ } else
copied = block_write_end(file, mapping, pos,
len, copied, page, fsdata);
@@ -1260,7 +1264,6 @@
*/
static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock)
{
- int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
@@ -1272,7 +1275,6 @@
* in order to allocate nrblocks
* worse case is one extent per block
*/
-repeat:
spin_lock(&ei->i_block_reservation_lock);
/*
* ext4_calc_metadata_amount() has side effects, which we have
@@ -1292,10 +1294,6 @@
ei->i_da_metadata_calc_len = save_len;
ei->i_da_metadata_calc_last_lblock = save_last_lblock;
spin_unlock(&ei->i_block_reservation_lock);
- if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
- cond_resched();
- goto repeat;
- }
return -ENOSPC;
}
ei->i_reserved_meta_blocks += md_needed;
@@ -1309,7 +1307,6 @@
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
- int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int md_needed;
@@ -1331,7 +1328,6 @@
* in order to allocate nrblocks
* worse case is one extent per block
*/
-repeat:
spin_lock(&ei->i_block_reservation_lock);
/*
* ext4_calc_metadata_amount() has side effects, which we have
@@ -1351,10 +1347,6 @@
ei->i_da_metadata_calc_len = save_len;
ei->i_da_metadata_calc_last_lblock = save_last_lblock;
spin_unlock(&ei->i_block_reservation_lock);
- if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
- cond_resched();
- goto repeat;
- }
dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
return -ENOSPC;
}
@@ -2655,6 +2647,20 @@
return 0;
}
+/* We always reserve for an inode update; the superblock could be there too */
+static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len)
+{
+ if (likely(EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_RO_COMPAT_LARGE_FILE)))
+ return 1;
+
+ if (pos + len <= 0x7fffffffULL)
+ return 1;
+
+ /* We might need to update the superblock to set LARGE_FILE */
+ return 2;
+}
+
static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
@@ -2705,7 +2711,8 @@
* of file which has an already mapped buffer.
*/
retry_journal:
- handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, 1);
+ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE,
+ ext4_da_write_credits(inode, pos, len));
if (IS_ERR(handle)) {
page_cache_release(page);
return PTR_ERR(handle);
@@ -4053,18 +4060,20 @@
void ext4_set_inode_flags(struct inode *inode)
{
unsigned int flags = EXT4_I(inode)->i_flags;
+ unsigned int new_fl = 0;
- inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
if (flags & EXT4_SYNC_FL)
- inode->i_flags |= S_SYNC;
+ new_fl |= S_SYNC;
if (flags & EXT4_APPEND_FL)
- inode->i_flags |= S_APPEND;
+ new_fl |= S_APPEND;
if (flags & EXT4_IMMUTABLE_FL)
- inode->i_flags |= S_IMMUTABLE;
+ new_fl |= S_IMMUTABLE;
if (flags & EXT4_NOATIME_FL)
- inode->i_flags |= S_NOATIME;
+ new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
- inode->i_flags |= S_DIRSYNC;
+ new_fl |= S_DIRSYNC;
+ set_mask_bits(&inode->i_flags,
+ S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
}
/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
@@ -4357,6 +4366,13 @@
return ERR_PTR(ret);
}
+struct inode *ext4_iget_normal(struct super_block *sb, unsigned long ino)
+{
+ if (ino < EXT4_FIRST_INO(sb) && ino != EXT4_ROOT_INO)
+ return ERR_PTR(-EIO);
+ return ext4_iget(sb, ino);
+}
+
static int ext4_inode_blocks_set(handle_t *handle,
struct ext4_inode *raw_inode,
struct ext4_inode_info *ei)
@@ -4703,7 +4719,9 @@
ext4_journal_stop(handle);
}
- if (attr->ia_valid & ATTR_SIZE) {
+ if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
+ handle_t *handle;
+ loff_t oldsize = inode->i_size;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -4711,73 +4729,64 @@
if (attr->ia_size > sbi->s_bitmap_maxbytes)
return -EFBIG;
}
- }
- if (S_ISREG(inode->i_mode) &&
- attr->ia_valid & ATTR_SIZE &&
- (attr->ia_size < inode->i_size)) {
- handle_t *handle;
+ if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
+ inode_inc_iversion(inode);
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- goto err_out;
- }
- if (ext4_handle_valid(handle)) {
- error = ext4_orphan_add(handle, inode);
- orphan = 1;
- }
- EXT4_I(inode)->i_disksize = attr->ia_size;
- rc = ext4_mark_inode_dirty(handle, inode);
- if (!error)
- error = rc;
- ext4_journal_stop(handle);
-
- if (ext4_should_order_data(inode)) {
- error = ext4_begin_ordered_truncate(inode,
+ if (S_ISREG(inode->i_mode) &&
+ (attr->ia_size < inode->i_size)) {
+ if (ext4_should_order_data(inode)) {
+ error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
- if (error) {
- /* Do as much error cleanup as possible */
- handle = ext4_journal_start(inode,
- EXT4_HT_INODE, 3);
- if (IS_ERR(handle)) {
- ext4_orphan_del(NULL, inode);
+ if (error)
goto err_out;
- }
- ext4_orphan_del(handle, inode);
- orphan = 0;
- ext4_journal_stop(handle);
+ }
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
+ goto err_out;
+ }
+ if (ext4_handle_valid(handle)) {
+ error = ext4_orphan_add(handle, inode);
+ orphan = 1;
+ }
+ EXT4_I(inode)->i_disksize = attr->ia_size;
+ rc = ext4_mark_inode_dirty(handle, inode);
+ if (!error)
+ error = rc;
+ ext4_journal_stop(handle);
+ if (error) {
+ ext4_orphan_del(NULL, inode);
goto err_out;
}
}
- }
- if (attr->ia_valid & ATTR_SIZE) {
- if (attr->ia_size != inode->i_size) {
- loff_t oldsize = inode->i_size;
-
- i_size_write(inode, attr->ia_size);
- /*
- * Blocks are going to be removed from the inode. Wait
- * for dio in flight. Temporarily disable
- * dioread_nolock to prevent livelock.
- */
- if (orphan) {
- if (!ext4_should_journal_data(inode)) {
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
- ext4_inode_resume_unlocked_dio(inode);
- } else
- ext4_wait_for_tail_page_commit(inode);
- }
- /*
- * Truncate pagecache after we've waited for commit
- * in data=journal mode to make pages freeable.
- */
- truncate_pagecache(inode, oldsize, inode->i_size);
+ i_size_write(inode, attr->ia_size);
+ /*
+ * Blocks are going to be removed from the inode. Wait
+ * for dio in flight. Temporarily disable
+ * dioread_nolock to prevent livelock.
+ */
+ if (orphan) {
+ if (!ext4_should_journal_data(inode)) {
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+ ext4_inode_resume_unlocked_dio(inode);
+ } else
+ ext4_wait_for_tail_page_commit(inode);
}
- ext4_truncate(inode);
+ /*
+ * Truncate pagecache after we've waited for commit
+ * in data=journal mode to make pages freeable.
+ */
+ truncate_pagecache(inode, oldsize, inode->i_size);
}
+ /*
+ * We want to call ext4_truncate() even if attr->ia_size ==
+ * inode->i_size for cases like truncation of fallocated space
+ */
+ if (attr->ia_valid & ATTR_SIZE)
+ ext4_truncate(inode);
if (!rc) {
setattr_copy(inode, attr);
@@ -4805,7 +4814,7 @@
struct kstat *stat)
{
struct inode *inode;
- unsigned long delalloc_blocks;
+ unsigned long long delalloc_blocks;
inode = dentry->d_inode;
generic_fillattr(inode, stat);
@@ -4823,7 +4832,7 @@
delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
EXT4_I(inode)->i_reserved_data_blocks);
- stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9;
+ stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
return 0;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 9491ac0..d4fd81c 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -77,8 +77,10 @@
memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
- memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
- memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+ ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
+ ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
+ ext4_es_lru_del(inode1);
+ ext4_es_lru_del(inode2);
isize = i_size_read(inode1);
i_size_write(inode1, i_size_read(inode2));
@@ -143,7 +145,7 @@
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
- goto swap_boot_out;
+ goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
@@ -201,6 +203,7 @@
ext4_double_up_write_data_sem(inode, inode_bl);
+journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
@@ -546,9 +549,17 @@
}
case EXT4_IOC_SWAP_BOOT:
+ {
+ int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
- return swap_inode_boot_loader(sb, inode);
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+ err = swap_inode_boot_loader(sb, inode);
+ mnt_drop_write_file(filp);
+ return err;
+ }
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index def8408..df5050f 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1396,6 +1396,8 @@
int last = first + count - 1;
struct super_block *sb = e4b->bd_sb;
+ if (WARN_ON(count == 0))
+ return;
BUG_ON(last >= (sb->s_blocksize << 3));
assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
mb_check_buddy(e4b);
@@ -3116,7 +3118,7 @@
}
BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
start > ac->ac_o_ex.fe_logical);
- BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+ BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
/* now prepare goal request */
@@ -3177,8 +3179,30 @@
static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
{
struct ext4_prealloc_space *pa = ac->ac_pa;
+ struct ext4_buddy e4b;
+ int err;
- if (pa && pa->pa_type == MB_INODE_PA)
+ if (pa == NULL) {
+ if (ac->ac_f_ex.fe_len == 0)
+ return;
+ err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
+ if (err) {
+ /*
+ * This should never happen since we pin the
+ * pages in the ext4_allocation_context so
+ * ext4_mb_load_buddy() should never fail.
+ */
+ WARN(1, "mb_load_buddy failed (%d)", err);
+ return;
+ }
+ ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+ mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
+ ac->ac_f_ex.fe_len);
+ ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+ ext4_mb_unload_buddy(&e4b);
+ return;
+ }
+ if (pa->pa_type == MB_INODE_PA)
pa->pa_free += ac->ac_b_ex.fe_len;
}
@@ -3423,6 +3447,9 @@
{
struct ext4_prealloc_space *pa;
pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu);
+
+ BUG_ON(atomic_read(&pa->pa_count));
+ BUG_ON(pa->pa_deleted == 0);
kmem_cache_free(ext4_pspace_cachep, pa);
}
@@ -3436,11 +3463,13 @@
ext4_group_t grp;
ext4_fsblk_t grp_blk;
- if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0)
- return;
-
/* in this short window concurrent discard can set pa_deleted */
spin_lock(&pa->pa_lock);
+ if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) {
+ spin_unlock(&pa->pa_lock);
+ return;
+ }
+
if (pa->pa_deleted == 1) {
spin_unlock(&pa->pa_lock);
return;
@@ -4102,7 +4131,7 @@
ext4_get_group_no_and_offset(sb, goal, &group, &block);
/* set up allocation goals */
- ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1);
+ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical);
ac->ac_status = AC_STATUS_CONTINUE;
ac->ac_sb = sb;
ac->ac_inode = ar->inode;
@@ -4581,6 +4610,7 @@
struct buffer_head *gd_bh;
ext4_group_t block_group;
struct ext4_sb_info *sbi;
+ struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_buddy e4b;
unsigned int count_clusters;
int err = 0;
@@ -4639,7 +4669,7 @@
* blocks at the beginning or the end unless we are explicitly
* requested to avoid doing so.
*/
- overflow = block & (sbi->s_cluster_ratio - 1);
+ overflow = EXT4_PBLK_COFF(sbi, block);
if (overflow) {
if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
overflow = sbi->s_cluster_ratio - overflow;
@@ -4653,7 +4683,7 @@
count += overflow;
}
}
- overflow = count & (sbi->s_cluster_ratio - 1);
+ overflow = EXT4_LBLK_COFF(sbi, count);
if (overflow) {
if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
if (count > overflow)
@@ -4735,11 +4765,16 @@
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
*/
+ retry:
new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
if (!new_entry) {
- ext4_mb_unload_buddy(&e4b);
- err = -ENOMEM;
- goto error_return;
+ /*
+ * We use a retry loop because
+ * ext4_free_blocks() is not allowed to fail.
+ */
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
}
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
@@ -4761,8 +4796,8 @@
" group:%d block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
- }
-
+ } else
+ EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
@@ -4774,7 +4809,6 @@
ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
@@ -4782,10 +4816,23 @@
&sbi->s_flex_groups[flex_group].free_clusters);
}
- ext4_mb_unload_buddy(&e4b);
-
- if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ if (flags & EXT4_FREE_BLOCKS_RESERVE && ei->i_reserved_data_blocks) {
+ percpu_counter_add(&sbi->s_dirtyclusters_counter,
+ count_clusters);
+ spin_lock(&ei->i_block_reservation_lock);
+ if (flags & EXT4_FREE_BLOCKS_METADATA)
+ ei->i_reserved_meta_blocks += count_clusters;
+ else
+ ei->i_reserved_data_blocks += count_clusters;
+ spin_unlock(&ei->i_block_reservation_lock);
+ if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ dquot_reclaim_block(inode,
+ EXT4_C2B(sbi, count_clusters));
+ } else if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+ percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
+
+ ext4_mb_unload_buddy(&e4b);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 6653fc3..facf8590 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -918,11 +918,8 @@
bh->b_data, bh->b_size,
(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
+ ((char *)de - bh->b_data))) {
- /* On error, skip the f_pos to the next block. */
- dir_file->f_pos = (dir_file->f_pos |
- (dir->i_sb->s_blocksize - 1)) + 1;
- brelse(bh);
- return count;
+ /* silently ignore the rest of the block */
+ break;
}
ext4fs_dirhash(de->name, de->name_len, hinfo);
if ((hinfo->hash < start_hash) ||
@@ -1433,7 +1430,7 @@
dentry->d_name.name);
return ERR_PTR(-EIO);
}
- inode = ext4_iget(dir->i_sb, ino);
+ inode = ext4_iget_normal(dir->i_sb, ino);
if (inode == ERR_PTR(-ESTALE)) {
EXT4_ERROR_INODE(dir,
"deleted inode referenced: %u",
@@ -1464,7 +1461,7 @@
return ERR_PTR(-EIO);
}
- return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino));
+ return d_obtain_alias(ext4_iget_normal(child->d_inode->i_sb, ino));
}
/*
@@ -1883,7 +1880,7 @@
struct inode *inode)
{
struct inode *dir = dentry->d_parent->d_inode;
- struct buffer_head *bh;
+ struct buffer_head *bh = NULL;
struct ext4_dir_entry_2 *de;
struct ext4_dir_entry_tail *t;
struct super_block *sb;
@@ -1908,14 +1905,14 @@
return retval;
if (retval == 1) {
retval = 0;
- return retval;
+ goto out;
}
}
if (is_dx(dir)) {
retval = ext4_dx_add_entry(handle, dentry, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
- return retval;
+ goto out;
ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
dx_fallback++;
ext4_mark_inode_dirty(handle, dir);
@@ -1927,14 +1924,15 @@
return PTR_ERR(bh);
retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
- if (retval != -ENOSPC) {
- brelse(bh);
- return retval;
- }
+ if (retval != -ENOSPC)
+ goto out;
if (blocks == 1 && !dx_fallback &&
- EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
- return make_indexed_dir(handle, dentry, inode, bh);
+ EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ retval = make_indexed_dir(handle, dentry, inode, bh);
+ bh = NULL; /* make_indexed_dir releases bh */
+ goto out;
+ }
brelse(bh);
}
bh = ext4_append(handle, dir, &block);
@@ -1950,6 +1948,7 @@
}
retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+out:
brelse(bh);
if (retval == 0)
ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 4acf1f7..b12a4427 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -384,6 +384,17 @@
ClearPageError(page);
/*
+ * Comments copied from block_write_full_page_endio:
+ *
+ * The page straddles i_size. It must be zeroed out on each and every
+ * writepage invocation because it may be mmapped. "A file is mapped
+ * in multiples of the page size. For a file that is not a multiple of
+ * the page size, the remaining memory is zeroed when mapped, and
+ * writes to that region are not written out to the file."
+ */
+ if (len < PAGE_CACHE_SIZE)
+ zero_user_segment(page, len, PAGE_CACHE_SIZE);
+ /*
* In the first loop we prepare and mark buffers to submit. We have to
* mark all buffers in the page before submitting so that
* end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -394,19 +405,6 @@
do {
block_start = bh_offset(bh);
if (block_start >= len) {
- /*
- * Comments copied from block_write_full_page_endio:
- *
- * The page straddles i_size. It must be zeroed out on
- * each and every writepage invocation because it may
- * be mmapped. "A file is mapped in multiples of the
- * page size. For a file that is not a multiple of
- * the page size, the remaining memory is zeroed when
- * mapped, and writes to that region are not written
- * out to the file."
- */
- zero_user_segment(page, block_start,
- block_start + blocksize);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index b27c96d..a69bd74 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -238,6 +238,7 @@
ext4_group_t group;
ext4_group_t last_group;
unsigned overhead;
+ __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
BUG_ON(flex_gd->count == 0 || group_data == NULL);
@@ -261,7 +262,7 @@
src_group++;
for (; src_group <= last_group; src_group++) {
overhead = ext4_group_overhead_blocks(sb, src_group);
- if (overhead != 0)
+ if (overhead == 0)
last_blk += group_data[src_group - group].blocks_count;
else
break;
@@ -275,8 +276,7 @@
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode bitmaps */
@@ -287,22 +287,30 @@
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode tables */
for (; it_index < flex_gd->count; it_index++) {
- if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+ unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+ ext4_fsblk_t next_group_start;
+
+ if (start_blk + itb > last_blk)
goto next_group;
group_data[it_index].inode_table = start_blk;
- group = ext4_get_group_number(sb, start_blk - 1);
+ group = ext4_get_group_number(sb, start_blk);
+ next_group_start = ext4_group_first_block_no(sb, group + 1);
group -= group_data[0].group;
- group_data[group].free_blocks_count -=
- EXT4_SB(sb)->s_itb_per_group;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ if (start_blk + itb > next_group_start) {
+ flex_gd->bg_flags[group + 1] &= uninit_mask;
+ overhead = start_blk + itb - next_group_start;
+ group_data[group + 1].free_blocks_count -= overhead;
+ itb -= overhead;
+ }
+
+ group_data[group].free_blocks_count -= itb;
+ flex_gd->bg_flags[group] &= uninit_mask;
start_blk += EXT4_SB(sb)->s_itb_per_group;
}
@@ -396,7 +404,7 @@
start = ext4_group_first_block_no(sb, group);
group -= flex_gd->groups[0].group;
- count2 = sb->s_blocksize * 8 - (block - start);
+ count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start);
if (count2 > count)
count2 = count;
@@ -615,7 +623,7 @@
if (err)
goto out;
count = group_table_count[j];
- start = group_data[i].block_bitmap;
+ start = (&group_data[i].block_bitmap)[j];
block = start;
}
@@ -1058,7 +1066,7 @@
break;
if (meta_bg == 0)
- backup_block = group * bpg + blk_off;
+ backup_block = ((ext4_fsblk_t)group) * bpg + blk_off;
else
backup_block = (ext4_group_first_block_no(sb, group) +
ext4_bg_has_super(sb, group));
@@ -1656,12 +1664,10 @@
err = err2;
if (!err) {
- ext4_fsblk_t first_block;
- first_block = ext4_group_first_block_no(sb, 0);
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: extended group to %llu "
"blocks\n", ext4_blocks_count(es));
- update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr - first_block,
+ update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr,
(char *)es, sizeof(struct ext4_super_block), 0);
}
return err;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94cc84d..21a0b43 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -964,7 +964,7 @@
* Currently we don't know the generation for parent directory, so
* a generation of 0 means "accept any"
*/
- inode = ext4_iget(sb, ino);
+ inode = ext4_iget_normal(sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
if (generation && inode->i_generation != generation) {
@@ -1341,7 +1341,7 @@
{Opt_delalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
- MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+ MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
@@ -1483,8 +1483,6 @@
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
} else if (token == Opt_max_batch_time) {
- if (arg == 0)
- arg = EXT4_DEF_MAX_BATCH_TIME;
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
sbi->s_min_batch_time = arg;
@@ -1634,13 +1632,6 @@
"not specified");
return 0;
}
- } else {
- if (sbi->s_jquota_fmt) {
- ext4_msg(sb, KERN_ERR, "journaled quota format "
- "specified with no journaling "
- "enabled");
- return 0;
- }
}
#endif
if (test_opt(sb, DIOREAD_NOLOCK)) {
@@ -1684,12 +1675,6 @@
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
- if (test_opt(sb, USRQUOTA))
- seq_puts(seq, ",usrquota");
-
- if (test_opt(sb, GRPQUOTA))
- seq_puts(seq, ",grpquota");
#endif
}
@@ -1965,6 +1950,10 @@
}
/* old crc16 code */
+ if (!(sbi->s_es->s_feature_ro_compat &
+ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)))
+ return 0;
+
offset = offsetof(struct ext4_group_desc, bg_checksum);
crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
@@ -2693,10 +2682,11 @@
es = sbi->s_es;
if (es->s_error_count)
- ext4_msg(sb, KERN_NOTICE, "error count: %u",
+ /* fsck newer than v1.41.13 is needed to clean this condition. */
+ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
@@ -2710,7 +2700,7 @@
printk("\n");
}
if (es->s_last_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
@@ -3219,11 +3209,19 @@
}
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
/*
+ * There's no need to reserve anything when we aren't using extents.
+ * The space estimates are exact, there are no unwritten extents,
+ * hole punching doesn't need new metadata... This is needed especially
+ * to keep ext2/3 backward compatibility.
+ */
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+ return 0;
+ /*
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
@@ -3231,7 +3229,8 @@
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
- resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+ resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+ EXT4_SB(sb)->s_cluster_bits;
do_div(resv_clusters, 50);
resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -3451,7 +3450,7 @@
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and delalloc");
+ "both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DELALLOC))
@@ -3586,23 +3585,25 @@
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
- /* Do we have standard group size of blocksize * 8 blocks ? */
- if (sbi->s_blocks_per_group == blocksize << 3)
- set_opt2(sb, STD_GROUP_SIZE);
-
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
- i = le32_to_cpu(es->s_flags);
- if (i & EXT2_FLAGS_UNSIGNED_HASH)
- sbi->s_hash_unsigned = 3;
- else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
- sbi->s_hash_unsigned = 3;
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
#else
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
+ }
}
/* Handle clustersize */
@@ -3659,6 +3660,10 @@
goto failed_mount;
}
+ /* Do we have standard group size of clustersize * 8 blocks ? */
+ if (sbi->s_blocks_per_group == clustersize << 3)
+ set_opt2(sb, STD_GROUP_SIZE);
+
/*
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
@@ -3975,10 +3980,10 @@
"available");
}
- err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+ err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
if (err) {
ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
- "reserved pool", ext4_calculate_resv_clusters(sbi));
+ "reserved pool", ext4_calculate_resv_clusters(sb));
goto failed_mount4a;
}
@@ -4652,6 +4657,21 @@
goto restore_opts;
}
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dioread_nolock");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
@@ -5406,6 +5426,7 @@
kset_unregister(ext4_kset);
ext4_exit_system_zone();
ext4_exit_pageio();
+ ext4_exit_es();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c081e34..a20816e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -189,14 +189,28 @@
}
static int
-ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end)
+ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
+ void *value_start)
{
- while (!IS_LAST_ENTRY(entry)) {
- struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(entry);
+ struct ext4_xattr_entry *e = entry;
+
+ while (!IS_LAST_ENTRY(e)) {
+ struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
if ((void *)next >= end)
return -EIO;
- entry = next;
+ e = next;
}
+
+ while (!IS_LAST_ENTRY(entry)) {
+ if (entry->e_value_size != 0 &&
+ (value_start + le16_to_cpu(entry->e_value_offs) <
+ (void *)e + sizeof(__u32) ||
+ value_start + le16_to_cpu(entry->e_value_offs) +
+ le32_to_cpu(entry->e_value_size) > end))
+ return -EIO;
+ entry = EXT4_XATTR_NEXT(entry);
+ }
+
return 0;
}
@@ -213,7 +227,8 @@
return -EIO;
if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
return -EIO;
- error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size);
+ error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
+ bh->b_data);
if (!error)
set_buffer_verified(bh);
return error;
@@ -329,7 +344,7 @@
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- error = ext4_xattr_check_names(entry, end);
+ error = ext4_xattr_check_names(entry, end, entry);
if (error)
goto cleanup;
error = ext4_xattr_find_entry(&entry, name_index, name,
@@ -457,7 +472,7 @@
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
- error = ext4_xattr_check_names(IFIRST(header), end);
+ error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
if (error)
goto cleanup;
error = ext4_xattr_list_entries(dentry, IFIRST(header),
@@ -517,8 +532,8 @@
}
/*
- * Release the xattr block BH: If the reference count is > 1, decrement
- * it; otherwise free the block.
+ * Release the xattr block BH: If the reference count is > 1, decrement it;
+ * otherwise free the block.
*/
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
@@ -538,16 +553,31 @@
if (ce)
mb_cache_entry_free(ce);
get_bh(bh);
+ unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
- unlock_buffer(bh);
} else {
le32_add_cpu(&BHDR(bh)->h_refcount, -1);
if (ce)
mb_cache_entry_release(ce);
+ /*
+ * Beware of this ugliness: Releasing of xattr block references
+ * from different inodes can race and so we have to protect
+ * from a race where someone else frees the block (and releases
+ * its journal_head) before we are done dirtying the buffer. In
+ * nojournal mode this race is harmless and we actually cannot
+ * call ext4_handle_dirty_xattr_block() with locked buffer as
+ * that function can call sync_dirty_buffer() so for that case
+ * we handle the dirtying after unlocking the buffer.
+ */
+ if (ext4_handle_valid(handle))
+ error = ext4_handle_dirty_xattr_block(handle, inode,
+ bh);
unlock_buffer(bh);
- error = ext4_handle_dirty_xattr_block(handle, inode, bh);
+ if (!ext4_handle_valid(handle))
+ error = ext4_handle_dirty_xattr_block(handle, inode,
+ bh);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -957,7 +987,8 @@
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
- error = ext4_xattr_check_names(IFIRST(header), is->s.end);
+ error = ext4_xattr_check_names(IFIRST(header), is->s.end,
+ IFIRST(header));
if (error)
return error;
/* Find the named attribute. */
@@ -1350,6 +1381,9 @@
s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
+ kfree(is); is = NULL;
+ kfree(bs); bs = NULL;
+ brelse(bh);
goto retry;
}
error = -1;
diff --git a/fs/file.c b/fs/file.c
index 4a78f98..9de2026 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@
* vmalloc() if the allocation size will be considered "large" by the VM.
*/
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
- void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
if (data != NULL)
return data;
}
diff --git a/fs/file_table.c b/fs/file_table.c
index 485dc0e..54a34be 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -211,10 +211,10 @@
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = dentry->d_inode;
- put_write_access(inode);
-
if (special_file(inode->i_mode))
return;
+
+ put_write_access(inode);
if (file_check_writeable(file) != 0)
return;
__mnt_drop_write(mnt);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 3be5718..b443063 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -87,16 +87,29 @@
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+ spin_lock_bh(&bdi->wb_lock);
+ if (test_bit(BDI_registered, &bdi->state))
+ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+ spin_unlock_bh(&bdi->wb_lock);
+}
+
static void bdi_queue_work(struct backing_dev_info *bdi,
struct wb_writeback_work *work)
{
trace_writeback_queue(bdi, work);
spin_lock_bh(&bdi->wb_lock);
+ if (!test_bit(BDI_registered, &bdi->state)) {
+ if (work->done)
+ complete(work->done);
+ goto out_unlock;
+ }
list_add_tail(&work->list, &bdi->work_list);
- spin_unlock_bh(&bdi->wb_lock);
-
mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+ spin_unlock_bh(&bdi->wb_lock);
}
static void
@@ -112,7 +125,7 @@
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work) {
trace_writeback_nowork(bdi);
- mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+ bdi_wakeup_thread(bdi);
return;
}
@@ -159,7 +172,7 @@
* writeback as soon as there is no other work to do.
*/
trace_writeback_wake_background(bdi);
- mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+ bdi_wakeup_thread(bdi);
}
/*
@@ -457,12 +470,28 @@
* write_inode()
*/
spin_lock(&inode->i_lock);
- /* Clear I_DIRTY_PAGES if we've written out all dirty pages */
- if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
- inode->i_state &= ~I_DIRTY_PAGES;
+
dirty = inode->i_state & I_DIRTY;
- inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+ inode->i_state &= ~I_DIRTY;
+
+ /*
+ * Paired with smp_mb() in __mark_inode_dirty(). This allows
+ * __mark_inode_dirty() to test i_state without grabbing i_lock -
+ * either they see the I_DIRTY bits cleared or we see the dirtied
+ * inode.
+ *
+ * I_DIRTY_PAGES is always cleared together above even if @mapping
+ * still has dirty pages. The flag is reinstated after smp_mb() if
+ * necessary. This guarantees that either __mark_inode_dirty()
+ * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
+ */
+ smp_mb();
+
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ inode->i_state |= I_DIRTY_PAGES;
+
spin_unlock(&inode->i_lock);
+
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
int err = write_inode(inode, wbc);
@@ -505,13 +534,16 @@
}
WARN_ON(inode->i_state & I_SYNC);
/*
- * Skip inode if it is clean. We don't want to mess with writeback
- * lists in this function since flusher thread may be doing for example
- * sync in parallel and if we move the inode, it could get skipped. So
- * here we make sure inode is on some writeback list and leave it there
- * unless we have completely cleaned the inode.
+ * Skip inode if it is clean and we have no outstanding writeback in
+ * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+ * function since flusher thread may be doing for example sync in
+ * parallel and if we move the inode, it could get skipped. So here we
+ * make sure inode is on some writeback list and leave it there unless
+ * we have completely cleaned the inode.
*/
- if (!(inode->i_state & I_DIRTY))
+ if (!(inode->i_state & I_DIRTY) &&
+ (wbc->sync_mode != WB_SYNC_ALL ||
+ !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
goto out;
inode->i_state |= I_SYNC;
spin_unlock(&inode->i_lock);
@@ -1013,7 +1045,7 @@
current->flags |= PF_SWAPWRITE;
if (likely(!current_is_workqueue_rescuer() ||
- list_empty(&bdi->bdi_list))) {
+ !test_bit(BDI_registered, &bdi->state))) {
/*
* The normal path. Keep writing back @bdi until its
* work_list is empty. Note that this path is also taken
@@ -1035,10 +1067,10 @@
trace_writeback_pages_written(pages_written);
}
- if (!list_empty(&bdi->work_list) ||
- (wb_has_dirty_io(wb) && dirty_writeback_interval))
- queue_delayed_work(bdi_wq, &wb->dwork,
- msecs_to_jiffies(dirty_writeback_interval * 10));
+ if (!list_empty(&bdi->work_list))
+ mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
+ bdi_wakeup_thread_delayed(bdi);
current->flags &= ~PF_SWAPWRITE;
}
@@ -1130,12 +1162,11 @@
}
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * Paired with smp_mb() in __writeback_single_inode() for the
+ * following lockless i_state test. See there for details.
*/
smp_mb();
- /* avoid the locking if we can */
if ((inode->i_state & flags) == flags)
return;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1d55f94..b535008 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -819,8 +819,8 @@
newpage = buf->page;
- if (WARN_ON(!PageUptodate(newpage)))
- return -EIO;
+ if (!PageUptodate(newpage))
+ SetPageUptodate(newpage);
ClearPageMappedToDisk(newpage);
@@ -1296,22 +1296,6 @@
return fuse_dev_do_read(fc, file, &cs, iov_length(iov, nr_segs));
}
-static int fuse_dev_pipe_buf_steal(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- return 1;
-}
-
-static const struct pipe_buf_operations fuse_dev_pipe_buf_ops = {
- .can_merge = 0,
- .map = generic_pipe_buf_map,
- .unmap = generic_pipe_buf_unmap,
- .confirm = generic_pipe_buf_confirm,
- .release = generic_pipe_buf_release,
- .steal = fuse_dev_pipe_buf_steal,
- .get = generic_pipe_buf_get,
-};
-
static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)
@@ -1358,7 +1342,11 @@
buf->page = bufs[page_nr].page;
buf->offset = bufs[page_nr].offset;
buf->len = bufs[page_nr].len;
- buf->ops = &fuse_dev_pipe_buf_ops;
+ /*
+ * Need to be careful about this. Having buf->ops in module
+ * code can Oops if the buffer persists after module unload.
+ */
+ buf->ops = &nosteal_pipe_buf_ops;
pipe->nrbufs++;
page_nr++;
@@ -1737,6 +1725,9 @@
static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
unsigned int size, struct fuse_copy_state *cs)
{
+ /* Don't try to move pages (yet) */
+ cs->move_pages = 0;
+
switch (code) {
case FUSE_NOTIFY_POLL:
return fuse_notify_poll(fc, size, cs);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index f3f783d..e67b13d 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1175,6 +1175,8 @@
return -EIO;
if (reclen > nbytes)
break;
+ if (memchr(dirent->name, '/', dirent->namelen) != NULL)
+ return -EIO;
over = filldir(dstbuf, dirent->name, dirent->namelen,
file->f_pos, dirent->ino, dirent->type);
@@ -1225,13 +1227,29 @@
if (name.name[1] == '.' && name.len == 2)
return 0;
}
+
+ if (invalid_nodeid(o->nodeid))
+ return -EIO;
+ if (!fuse_valid_type(o->attr.mode))
+ return -EIO;
+
fc = get_fuse_conn(dir);
name.hash = full_name_hash(name.name, name.len);
dentry = d_lookup(parent, &name);
- if (dentry && dentry->d_inode) {
+ if (dentry) {
inode = dentry->d_inode;
- if (get_node_id(inode) == o->nodeid) {
+ if (!inode) {
+ d_drop(dentry);
+ } else if (get_node_id(inode) != o->nodeid ||
+ ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
+ err = d_invalidate(dentry);
+ if (err)
+ goto out;
+ } else if (is_bad_inode(inode)) {
+ err = -EIO;
+ goto out;
+ } else {
struct fuse_inode *fi;
fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
@@ -1244,9 +1262,6 @@
*/
goto found;
}
- err = d_invalidate(dentry);
- if (err)
- goto out;
dput(dentry);
dentry = NULL;
}
@@ -1261,10 +1276,19 @@
if (!inode)
goto out;
- alias = d_materialise_unique(dentry, inode);
- err = PTR_ERR(alias);
- if (IS_ERR(alias))
- goto out;
+ if (S_ISDIR(inode->i_mode)) {
+ mutex_lock(&fc->inst_mutex);
+ alias = fuse_d_add_directory(dentry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ err = PTR_ERR(alias);
+ if (IS_ERR(alias)) {
+ iput(inode);
+ goto out;
+ }
+ } else {
+ alias = d_splice_alias(inode, dentry);
+ }
+
if (alias) {
dput(dentry);
dentry = alias;
@@ -1301,6 +1325,8 @@
return -EIO;
if (reclen > nbytes)
break;
+ if (memchr(dirent->name, '/', dirent->namelen) != NULL)
+ return -EIO;
if (!over) {
/* We fill entries into dstbuf only as much as
@@ -1572,6 +1598,7 @@
struct file *file)
{
struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_req *req;
struct fuse_setattr_in inarg;
struct fuse_attr_out outarg;
@@ -1599,8 +1626,10 @@
if (IS_ERR(req))
return PTR_ERR(req);
- if (is_truncate)
+ if (is_truncate) {
fuse_set_nowrite(inode);
+ set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+ }
memset(&inarg, 0, sizeof(inarg));
memset(&outarg, 0, sizeof(outarg));
@@ -1662,12 +1691,14 @@
invalidate_inode_pages2(inode->i_mapping);
}
+ clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return 0;
error:
if (is_truncate)
fuse_release_nowrite(inode);
+ clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
return err;
}
@@ -1731,6 +1762,8 @@
fc->no_setxattr = 1;
err = -EOPNOTSUPP;
}
+ if (!err)
+ fuse_invalidate_attr(inode);
return err;
}
@@ -1860,6 +1893,8 @@
fc->no_removexattr = 1;
err = -EOPNOTSUPP;
}
+ if (!err)
+ fuse_invalidate_attr(inode);
return err;
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 35f2810..4fafb84 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -630,7 +630,8 @@
struct fuse_inode *fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
- if (attr_ver == fi->attr_version && size < inode->i_size) {
+ if (attr_ver == fi->attr_version && size < inode->i_size &&
+ !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
fi->attr_version = ++fc->attr_version;
i_size_write(inode, size);
}
@@ -1033,12 +1034,16 @@
{
struct inode *inode = mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
int err = 0;
ssize_t res = 0;
if (is_bad_inode(inode))
return -EIO;
+ if (inode->i_size < pos + iov_iter_count(ii))
+ set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
do {
struct fuse_req *req;
ssize_t count;
@@ -1074,6 +1079,7 @@
if (res > 0)
fuse_write_update_size(inode, pos);
+ clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
fuse_invalidate_attr(inode);
return res > 0 ? res : err;
@@ -1530,7 +1536,6 @@
inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
- end_page_writeback(page);
spin_lock(&fc->lock);
list_add(&req->writepages_entry, &fi->writepages);
@@ -1538,6 +1543,8 @@
fuse_flush_writepages(inode);
spin_unlock(&fc->lock);
+ end_page_writeback(page);
+
return 0;
err_free:
@@ -2461,6 +2468,7 @@
{
struct fuse_file *ff = file->private_data;
struct inode *inode = file->f_inode;
+ struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = ff->fc;
struct fuse_req *req;
struct fuse_fallocate_in inarg = {
@@ -2478,10 +2486,20 @@
if (lock_inode) {
mutex_lock(&inode->i_mutex);
- if (mode & FALLOC_FL_PUNCH_HOLE)
- fuse_set_nowrite(inode);
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ loff_t endbyte = offset + length - 1;
+ err = filemap_write_and_wait_range(inode->i_mapping,
+ offset, endbyte);
+ if (err)
+ goto out;
+
+ fuse_sync_writes(inode);
+ }
}
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
req = fuse_get_req_nopages(fc);
if (IS_ERR(req)) {
err = PTR_ERR(req);
@@ -2514,11 +2532,11 @@
fuse_invalidate_attr(inode);
out:
- if (lock_inode) {
- if (mode & FALLOC_FL_PUNCH_HOLE)
- fuse_release_nowrite(inode);
+ if (!(mode & FALLOC_FL_KEEP_SIZE))
+ clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
+
+ if (lock_inode)
mutex_unlock(&inode->i_mutex);
- }
return err;
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index fde7249..5ced199 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -115,6 +115,8 @@
enum {
/** Advise readdirplus */
FUSE_I_ADVISE_RDPLUS,
+ /** An operation changing file size is in progress */
+ FUSE_I_SIZE_UNSTABLE,
};
struct fuse_conn;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 9a0cdde..39a986e 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -201,7 +201,8 @@
struct timespec old_mtime;
spin_lock(&fc->lock);
- if (attr_version != 0 && fi->attr_version > attr_version) {
+ if ((attr_version != 0 && fi->attr_version > attr_version) ||
+ test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
spin_unlock(&fc->lock);
return;
}
@@ -460,6 +461,17 @@
{OPT_ERR, NULL}
};
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+ int err = -ENOMEM;
+ char *buf = match_strdup(s);
+ if (buf) {
+ err = kstrtouint(buf, 10, res);
+ kfree(buf);
+ }
+ return err;
+}
+
static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
{
char *p;
@@ -470,6 +482,7 @@
while ((p = strsep(&opt, ",")) != NULL) {
int token;
int value;
+ unsigned uv;
substring_t args[MAX_OPT_ARGS];
if (!*p)
continue;
@@ -493,18 +506,18 @@
break;
case OPT_USER_ID:
- if (match_int(&args[0], &value))
+ if (fuse_match_uint(&args[0], &uv))
return 0;
- d->user_id = make_kuid(current_user_ns(), value);
+ d->user_id = make_kuid(current_user_ns(), uv);
if (!uid_valid(d->user_id))
return 0;
d->user_id_present = 1;
break;
case OPT_GROUP_ID:
- if (match_int(&args[0], &value))
+ if (fuse_match_uint(&args[0], &uv))
return 0;
- d->group_id = make_kgid(current_user_ns(), value);
+ d->group_id = make_kgid(current_user_ns(), uv);
if (!gid_valid(d->group_id))
return 0;
d->group_id_present = 1;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 0bad69e..7625160 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -999,6 +999,7 @@
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
@@ -1019,6 +1020,35 @@
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
+ /*
+ * Now since we are holding a deferred (CW) lock at this point, you
+ * might be wondering why this is ever needed. There is a case however
+ * where we've granted a deferred local lock against a cached exclusive
+ * glock. That is ok provided all granted local locks are deferred, but
+ * it also means that it is possible to encounter pages which are
+ * cached and possibly also mapped. So here we check for that and sort
+ * them out ahead of the dio. The glock state machine will take care of
+ * everything else.
+ *
+ * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+ * the first place, mapping->nr_pages will always be zero.
+ */
+ if (mapping->nrpages) {
+ loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+ loff_t len = iov_length(iov, nr_segs);
+ loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+ rv = 0;
+ if (len == 0)
+ goto out;
+ if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+ unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+ rv = filemap_write_and_wait_range(mapping, lstart, end);
+ if (rv)
+ return rv;
+ truncate_inode_pages_range(mapping, lstart, end);
+ }
+
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block_direct,
NULL, NULL, 0);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 62b484e..bc5dac4 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1536,10 +1536,22 @@
if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
ogid = ngid = NO_GID_QUOTA_CHANGE;
- error = gfs2_quota_lock(ip, nuid, ngid);
+ error = get_write_access(inode);
if (error)
return error;
+ error = gfs2_rs_alloc(ip);
+ if (error)
+ goto out;
+
+ error = gfs2_rindex_update(sdp);
+ if (error)
+ goto out;
+
+ error = gfs2_quota_lock(ip, nuid, ngid);
+ if (error)
+ goto out;
+
if (!uid_eq(ouid, NO_UID_QUOTA_CHANGE) ||
!gid_eq(ogid, NO_GID_QUOTA_CHANGE)) {
error = gfs2_quota_check(ip, nuid, ngid);
@@ -1566,6 +1578,8 @@
gfs2_trans_end(sdp);
out_gunlock_q:
gfs2_quota_unlock(ip);
+out:
+ put_write_access(inode);
return error;
}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 60ede2a..f7dd3b4 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1317,8 +1317,18 @@
if (IS_ERR(s))
goto error_bdev;
- if (s->s_root)
+ if (s->s_root) {
+ /*
+ * s_umount nests inside bd_mutex during
+ * __invalidate_device(). blkdev_put() acquires
+ * bd_mutex and can't be called under s_umount. Drop
+ * s_umount temporarily. This is safe as we're
+ * holding an active reference.
+ */
+ up_write(&s->s_umount);
blkdev_put(bdev, mode);
+ down_write(&s->s_umount);
+ }
memset(&args, 0, sizeof(args));
args.ar_quota = GFS2_QUOTA_DEFAULT;
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index 6e560d5..754fdf8 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -131,13 +131,16 @@
hfs_bnode_write(node, entry, data_off + key_len, entry_len);
hfs_bnode_dump(node);
- if (new_node) {
- /* update parent key if we inserted a key
- * at the start of the first node
- */
- if (!rec && new_node != node)
- hfs_brec_update_parent(fd);
+ /*
+ * update parent key if we inserted a key
+ * at the start of the node and it is not the new node
+ */
+ if (!rec && new_node != node) {
+ hfs_bnode_read_key(node, fd->search_key, data_off + size);
+ hfs_brec_update_parent(fd);
+ }
+ if (new_node) {
hfs_bnode_put(fd->bnode);
if (!new_node->parent) {
hfs_btree_inc_height(tree);
@@ -168,9 +171,6 @@
goto again;
}
- if (!rec)
- hfs_brec_update_parent(fd);
-
return 0;
}
@@ -370,6 +370,8 @@
if (IS_ERR(parent))
return PTR_ERR(parent);
__hfs_brec_find(parent, fd, hfs_find_rec_by_key);
+ if (fd->record < 0)
+ return -ENOENT;
hfs_bnode_dump(parent);
rec = fd->record;
diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c
index 4acb19d..803d3da 100644
--- a/fs/hpfs/map.c
+++ b/fs/hpfs/map.c
@@ -17,7 +17,8 @@
struct quad_buffer_head *qbh, char *id)
{
secno sec;
- if (hpfs_sb(s)->sb_chk) if (bmp_block * 16384 > hpfs_sb(s)->sb_fs_size) {
+ unsigned n_bands = (hpfs_sb(s)->sb_fs_size + 0x3fff) >> 14;
+ if (hpfs_sb(s)->sb_chk) if (bmp_block >= n_bands) {
hpfs_error(s, "hpfs_map_bitmap called with bad parameter: %08x at %s", bmp_block, id);
return NULL;
}
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index a0617e7..962e90c 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -558,7 +558,13 @@
sbi->sb_cp_table = NULL;
sbi->sb_c_bitmap = -1;
sbi->sb_max_fwd_alloc = 0xffffff;
-
+
+ if (sbi->sb_fs_size >= 0x80000000) {
+ hpfs_error(s, "invalid size in superblock: %08x",
+ (unsigned)sbi->sb_fs_size);
+ goto bail4;
+ }
+
/* Load bitmap directory */
if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps))))
goto bail4;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a3f868a..4e5f332 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -916,14 +916,8 @@
return h - hstates;
}
-static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
-{
- return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
- dentry->d_name.name);
-}
-
static struct dentry_operations anon_ops = {
- .d_dname = hugetlb_dname
+ .d_dname = simple_dname
};
/*
diff --git a/fs/inode.c b/fs/inode.c
index 00d5fc3..1b300a0 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1837,14 +1837,18 @@
* inode_owner_or_capable - check current task permissions to inode
* @inode: inode being checked
*
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
*/
bool inode_owner_or_capable(const struct inode *inode)
{
+ struct user_namespace *ns;
+
if (uid_eq(current_fsuid(), inode->i_uid))
return true;
- if (inode_capable(inode, CAP_FOWNER))
+
+ ns = current_user_ns();
+ if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
return true;
return false;
}
diff --git a/fs/ioprio.c b/fs/ioprio.c
index e50170c..31666c9 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -157,14 +157,16 @@
int ioprio_best(unsigned short aprio, unsigned short bprio)
{
- unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
- unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+ unsigned short aclass;
+ unsigned short bclass;
- if (aclass == IOPRIO_CLASS_NONE)
- aclass = IOPRIO_CLASS_BE;
- if (bclass == IOPRIO_CLASS_NONE)
- bclass = IOPRIO_CLASS_BE;
+ if (!ioprio_valid(aprio))
+ aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+ if (!ioprio_valid(bprio))
+ bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+ aclass = IOPRIO_PRIO_CLASS(aprio);
+ bclass = IOPRIO_PRIO_CLASS(bprio);
if (aclass == bclass)
return min(aprio, bprio);
if (aclass > bclass)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d9b8aeb..10489bb 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -69,7 +69,7 @@
return;
}
-static int isofs_read_inode(struct inode *);
+static int isofs_read_inode(struct inode *, int relocated);
static int isofs_statfs (struct dentry *, struct kstatfs *);
static struct kmem_cache *isofs_inode_cachep;
@@ -125,8 +125,8 @@
static int isofs_remount(struct super_block *sb, int *flags, char *data)
{
- /* we probably want a lot more here */
- *flags |= MS_RDONLY;
+ if (!(*flags & MS_RDONLY))
+ return -EROFS;
return 0;
}
@@ -779,15 +779,6 @@
*/
s->s_maxbytes = 0x80000000000LL;
- /*
- * The CDROM is read-only, has no nodes (devices) on it, and since
- * all of the files appear to be owned by root, we really do not want
- * to allow suid. (suid or devices will not show up unless we have
- * Rock Ridge extensions)
- */
-
- s->s_flags |= MS_RDONLY /* | MS_NODEV | MS_NOSUID */;
-
/* Set this for reference. Its not currently used except on write
which we don't have .. */
@@ -1283,7 +1274,7 @@
goto out;
}
-static int isofs_read_inode(struct inode *inode)
+static int isofs_read_inode(struct inode *inode, int relocated)
{
struct super_block *sb = inode->i_sb;
struct isofs_sb_info *sbi = ISOFS_SB(sb);
@@ -1428,7 +1419,7 @@
*/
if (!high_sierra) {
- parse_rock_ridge_inode(de, inode);
+ parse_rock_ridge_inode(de, inode, relocated);
/* if we want uid/gid set, override the rock ridge setting */
if (sbi->s_uid_set)
inode->i_uid = sbi->s_uid;
@@ -1507,9 +1498,10 @@
* offset that point to the underlying meta-data for the inode. The
* code below is otherwise similar to the iget() code in
* include/linux/fs.h */
-struct inode *isofs_iget(struct super_block *sb,
- unsigned long block,
- unsigned long offset)
+struct inode *__isofs_iget(struct super_block *sb,
+ unsigned long block,
+ unsigned long offset,
+ int relocated)
{
unsigned long hashval;
struct inode *inode;
@@ -1531,7 +1523,7 @@
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- ret = isofs_read_inode(inode);
+ ret = isofs_read_inode(inode, relocated);
if (ret < 0) {
iget_failed(inode);
inode = ERR_PTR(ret);
@@ -1546,6 +1538,9 @@
static struct dentry *isofs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
+ /* We don't support read-write mounts */
+ if (!(flags & MS_RDONLY))
+ return ERR_PTR(-EACCES);
return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super);
}
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 9916723..0ac4c1f 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -107,7 +107,7 @@
struct inode; /* To make gcc happy */
-extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *);
+extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated);
extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *);
extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *);
@@ -118,9 +118,24 @@
extern struct buffer_head *isofs_bread(struct inode *, sector_t);
extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
-extern struct inode *isofs_iget(struct super_block *sb,
- unsigned long block,
- unsigned long offset);
+struct inode *__isofs_iget(struct super_block *sb,
+ unsigned long block,
+ unsigned long offset,
+ int relocated);
+
+static inline struct inode *isofs_iget(struct super_block *sb,
+ unsigned long block,
+ unsigned long offset)
+{
+ return __isofs_iget(sb, block, offset, 0);
+}
+
+static inline struct inode *isofs_iget_reloc(struct super_block *sb,
+ unsigned long block,
+ unsigned long offset)
+{
+ return __isofs_iget(sb, block, offset, 1);
+}
/* Because the inode number is no longer relevant to finding the
* underlying meta-data for an inode, we are free to choose a more
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c0bf424..735d752 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -30,6 +30,7 @@
int cont_size;
int cont_extent;
int cont_offset;
+ int cont_loops;
struct inode *inode;
};
@@ -73,6 +74,9 @@
rs->inode = inode;
}
+/* Maximum number of Rock Ridge continuation entries */
+#define RR_MAX_CE_ENTRIES 32
+
/*
* Returns 0 if the caller should continue scanning, 1 if the scan must end
* and -ve on error.
@@ -105,6 +109,8 @@
goto out;
}
ret = -EIO;
+ if (++rs->cont_loops >= RR_MAX_CE_ENTRIES)
+ goto out;
bh = sb_bread(rs->inode->i_sb, rs->cont_extent);
if (bh) {
memcpy(rs->buffer, bh->b_data + rs->cont_offset,
@@ -288,12 +294,16 @@
goto out;
}
+#define RR_REGARD_XA 1
+#define RR_RELOC_DE 2
+
static int
parse_rock_ridge_inode_internal(struct iso_directory_record *de,
- struct inode *inode, int regard_xa)
+ struct inode *inode, int flags)
{
int symlink_len = 0;
int cnt, sig;
+ unsigned int reloc_block;
struct inode *reloc;
struct rock_ridge *rr;
int rootflag;
@@ -305,7 +315,7 @@
init_rock_state(&rs, inode);
setup_rock_ridge(de, inode, &rs);
- if (regard_xa) {
+ if (flags & RR_REGARD_XA) {
rs.chr += 14;
rs.len -= 14;
if (rs.len < 0)
@@ -352,6 +362,9 @@
rs.cont_size = isonum_733(rr->u.CE.size);
break;
case SIG('E', 'R'):
+ /* Invalid length of ER tag id? */
+ if (rr->u.ER.len_id + offsetof(struct rock_ridge, u.ER.data) > rr->len)
+ goto out;
ISOFS_SB(inode->i_sb)->s_rock = 1;
printk(KERN_DEBUG "ISO 9660 Extensions: ");
{
@@ -485,12 +498,22 @@
"relocated directory\n");
goto out;
case SIG('C', 'L'):
- ISOFS_I(inode)->i_first_extent =
- isonum_733(rr->u.CL.location);
- reloc =
- isofs_iget(inode->i_sb,
- ISOFS_I(inode)->i_first_extent,
- 0);
+ if (flags & RR_RELOC_DE) {
+ printk(KERN_ERR
+ "ISOFS: Recursive directory relocation "
+ "is not supported\n");
+ goto eio;
+ }
+ reloc_block = isonum_733(rr->u.CL.location);
+ if (reloc_block == ISOFS_I(inode)->i_iget5_block &&
+ ISOFS_I(inode)->i_iget5_offset == 0) {
+ printk(KERN_ERR
+ "ISOFS: Directory relocation points to "
+ "itself\n");
+ goto eio;
+ }
+ ISOFS_I(inode)->i_first_extent = reloc_block;
+ reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0);
if (IS_ERR(reloc)) {
ret = PTR_ERR(reloc);
goto out;
@@ -637,9 +660,11 @@
return rpnt;
}
-int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
+int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode,
+ int relocated)
{
- int result = parse_rock_ridge_inode_internal(de, inode, 0);
+ int flags = relocated ? RR_RELOC_DE : 0;
+ int result = parse_rock_ridge_inode_internal(de, inode, flags);
/*
* if rockridge flag was reset and we didn't look for attributes
@@ -647,7 +672,8 @@
*/
if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1)
&& (ISOFS_SB(inode->i_sb)->s_rock == 2)) {
- result = parse_rock_ridge_inode_internal(de, inode, 14);
+ result = parse_rock_ridge_inode_internal(de, inode,
+ flags | RR_REGARD_XA);
}
return result;
}
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9545757..aaa1a3f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1318,6 +1318,7 @@
static void jbd2_write_superblock(journal_t *journal, int write_op)
{
struct buffer_head *bh = journal->j_sb_buffer;
+ journal_superblock_t *sb = journal->j_superblock;
int ret;
trace_jbd2_write_superblock(journal, write_op);
@@ -1339,6 +1340,7 @@
clear_buffer_write_io_error(bh);
set_buffer_uptodate(bh);
}
+ jbd2_superblock_csum_set(journal, sb);
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
ret = submit_bh(write_op, bh);
@@ -1435,7 +1437,6 @@
jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
journal->j_errno);
sb->s_errno = cpu_to_be32(journal->j_errno);
- jbd2_superblock_csum_set(journal, sb);
read_unlock(&journal->j_state_lock);
jbd2_write_superblock(journal, WRITE_SYNC);
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 626846b..6e2fb5c 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -427,6 +427,7 @@
int tag_bytes = journal_tag_bytes(journal);
__u32 crc32_sum = ~0; /* Transactional Checksums */
int descr_csum_size = 0;
+ int block_error = 0;
/*
* First thing is to establish what we expect to find in the log
@@ -521,6 +522,7 @@
!jbd2_descr_block_csum_verify(journal,
bh->b_data)) {
err = -EIO;
+ brelse(bh);
goto failed;
}
@@ -599,7 +601,8 @@
"checksum recovering "
"block %llu in log\n",
blocknr);
- continue;
+ block_error = 1;
+ goto skip_write;
}
/* Find a buffer for the new
@@ -798,7 +801,8 @@
success = -EIO;
}
}
-
+ if (block_error && success == 0)
+ success = -EIO;
return success;
failed:
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 10f524c..ec34e11 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -517,10 +517,10 @@
&transaction->t_outstanding_credits);
if (atomic_dec_and_test(&transaction->t_updates))
wake_up(&journal->j_wait_updates);
+ tid = transaction->t_tid;
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
- tid = transaction->t_tid;
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
@@ -1151,7 +1151,10 @@
* once a transaction -bzzz
*/
jh->b_modified = 1;
- J_ASSERT_JH(jh, handle->h_buffer_credits > 0);
+ if (handle->h_buffer_credits <= 0) {
+ ret = -ENOSPC;
+ goto out_unlock_bh;
+ }
handle->h_buffer_credits--;
}
@@ -1234,7 +1237,6 @@
jbd2_journal_put_journal_head(jh);
out:
JBUFFER_TRACE(jh, "exit");
- WARN_ON(ret); /* All errors are bugs, so dump the stack */
return ret;
}
@@ -1440,9 +1442,12 @@
* to perform a synchronous write. We do this to detect the
* case where a single process is doing a stream of sync
* writes. No point in waiting for joiners in that case.
+ *
+ * Setting max_batch_time to 0 disables this completely.
*/
pid = current->pid;
- if (handle->h_sync && journal->j_last_sync_writer != pid) {
+ if (handle->h_sync && journal->j_last_sync_writer != pid &&
+ journal->j_max_batch_time) {
u64 commit_time, trans_time;
journal->j_last_sync_writer = pid;
diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c
index 16a5047..406d9cc 100644
--- a/fs/jffs2/compr_rtime.c
+++ b/fs/jffs2/compr_rtime.c
@@ -33,7 +33,7 @@
unsigned char *cpage_out,
uint32_t *sourcelen, uint32_t *dstlen)
{
- short positions[256];
+ unsigned short positions[256];
int outpos = 0;
int pos=0;
@@ -74,7 +74,7 @@
unsigned char *cpage_out,
uint32_t srclen, uint32_t destlen)
{
- short positions[256];
+ unsigned short positions[256];
int outpos = 0;
int pos=0;
diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h
index 413ef89..046fee8 100644
--- a/fs/jffs2/jffs2_fs_sb.h
+++ b/fs/jffs2/jffs2_fs_sb.h
@@ -134,8 +134,6 @@
struct rw_semaphore wbuf_sem; /* Protects the write buffer */
struct delayed_work wbuf_dwork; /* write-buffer write-out work */
- int wbuf_queued; /* non-zero delayed work is queued */
- spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */
unsigned char *oobbuf;
int oobavail; /* How many bytes are available for JFFS2 in OOB */
diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
index e4619b0..fa35ff7 100644
--- a/fs/jffs2/nodelist.h
+++ b/fs/jffs2/nodelist.h
@@ -231,7 +231,7 @@
uint32_t version;
uint32_t data_crc;
uint32_t partial_crc;
- uint16_t csize;
+ uint32_t csize;
uint16_t overlapped;
};
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 0331072..b6bd4af 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -179,6 +179,7 @@
spin_unlock(&c->erase_completion_lock);
schedule();
+ remove_wait_queue(&c->erase_wait, &wait);
} else
spin_unlock(&c->erase_completion_lock);
} else if (ret)
@@ -211,20 +212,25 @@
int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
uint32_t *len, uint32_t sumsize)
{
- int ret = -EAGAIN;
+ int ret;
minsize = PAD(minsize);
jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
- spin_lock(&c->erase_completion_lock);
- while(ret == -EAGAIN) {
+ while (true) {
+ spin_lock(&c->erase_completion_lock);
ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
if (ret) {
jffs2_dbg(1, "%s(): looping, ret is %d\n",
__func__, ret);
}
+ spin_unlock(&c->erase_completion_lock);
+
+ if (ret == -EAGAIN)
+ cond_resched();
+ else
+ break;
}
- spin_unlock(&c->erase_completion_lock);
if (!ret)
ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c
index 7654e87..9ad5ba4 100644
--- a/fs/jffs2/scan.c
+++ b/fs/jffs2/scan.c
@@ -510,6 +510,10 @@
sumlen = c->sector_size - je32_to_cpu(sm->offset);
sumptr = buf + buf_size - sumlen;
+ /* sm->offset maybe wrong but MAGIC maybe right */
+ if (sumlen > c->sector_size)
+ goto full_scan;
+
/* Now, make sure the summary itself is available */
if (sumlen > buf_size) {
/* Need to kmalloc for this. */
@@ -544,6 +548,7 @@
}
}
+full_scan:
buf_ofs = jeb->offset;
if (!buf_size) {
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index a6597d6..09ed551 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1162,10 +1162,6 @@
struct jffs2_sb_info *c = work_to_sb(work);
struct super_block *sb = OFNI_BS_2SFFJ(c);
- spin_lock(&c->wbuf_dwork_lock);
- c->wbuf_queued = 0;
- spin_unlock(&c->wbuf_dwork_lock);
-
if (!(sb->s_flags & MS_RDONLY)) {
jffs2_dbg(1, "%s()\n", __func__);
jffs2_flush_wbuf_gc(c, 0);
@@ -1180,14 +1176,9 @@
if (sb->s_flags & MS_RDONLY)
return;
- spin_lock(&c->wbuf_dwork_lock);
- if (!c->wbuf_queued) {
+ delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+ if (queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay))
jffs2_dbg(1, "%s()\n", __func__);
- delay = msecs_to_jiffies(dirty_writeback_interval * 10);
- queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay);
- c->wbuf_queued = 1;
- }
- spin_unlock(&c->wbuf_dwork_lock);
}
int jffs2_nand_flash_setup(struct jffs2_sb_info *c)
@@ -1211,7 +1202,6 @@
/* Initialise write buffer */
init_rwsem(&c->wbuf_sem);
- spin_lock_init(&c->wbuf_dwork_lock);
INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
c->wbuf_pagesize = c->mtd->writesize;
c->wbuf_ofs = 0xFFFFFFFF;
@@ -1251,7 +1241,6 @@
/* Initialize write buffer */
init_rwsem(&c->wbuf_sem);
- spin_lock_init(&c->wbuf_dwork_lock);
INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
c->wbuf_pagesize = c->mtd->erasesize;
@@ -1311,7 +1300,6 @@
/* Initialize write buffer */
init_rwsem(&c->wbuf_sem);
- spin_lock_init(&c->wbuf_dwork_lock);
INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
c->wbuf_pagesize = c->mtd->writesize;
@@ -1346,7 +1334,6 @@
return 0;
init_rwsem(&c->wbuf_sem);
- spin_lock_init(&c->wbuf_dwork_lock);
INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync);
c->wbuf_pagesize = c->mtd->writesize;
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 0ddbece..5d876b1 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3047,6 +3047,14 @@
dir_index = (u32) filp->f_pos;
+ /*
+ * NFSv4 reserves cookies 1 and 2 for . and .. so we add
+ * the value we return to the vfs is one greater than the
+ * one we use internally.
+ */
+ if (dir_index)
+ dir_index--;
+
if (dir_index > 1) {
struct dir_table_slot dirtab_slot;
@@ -3086,7 +3094,7 @@
if (p->header.flag & BT_INTERNAL) {
jfs_err("jfs_readdir: bad index table");
DT_PUTPAGE(mp);
- filp->f_pos = -1;
+ filp->f_pos = DIREND;
return 0;
}
} else {
@@ -3094,16 +3102,16 @@
/*
* self "."
*/
- filp->f_pos = 0;
- if (filldir(dirent, ".", 1, 0, ip->i_ino,
+ filp->f_pos = 1;
+ if (filldir(dirent, ".", 1, 1, ip->i_ino,
DT_DIR))
return 0;
}
/*
* parent ".."
*/
- filp->f_pos = 1;
- if (filldir(dirent, "..", 2, 1, PARENT(ip), DT_DIR))
+ filp->f_pos = 2;
+ if (filldir(dirent, "..", 2, 2, PARENT(ip), DT_DIR))
return 0;
/*
@@ -3123,24 +3131,25 @@
/*
* Legacy filesystem - OS/2 & Linux JFS < 0.3.6
*
- * pn = index = 0: First entry "."
- * pn = 0; index = 1: Second entry ".."
+ * pn = 0; index = 1: First entry "."
+ * pn = 0; index = 2: Second entry ".."
* pn > 0: Real entries, pn=1 -> leftmost page
* pn = index = -1: No more entries
*/
dtpos = filp->f_pos;
- if (dtpos == 0) {
+ if (dtpos < 2) {
/* build "." entry */
+ filp->f_pos = 1;
if (filldir(dirent, ".", 1, filp->f_pos, ip->i_ino,
DT_DIR))
return 0;
- dtoffset->index = 1;
+ dtoffset->index = 2;
filp->f_pos = dtpos;
}
if (dtoffset->pn == 0) {
- if (dtoffset->index == 1) {
+ if (dtoffset->index == 2) {
/* build ".." entry */
if (filldir(dirent, "..", 2, filp->f_pos,
@@ -3233,6 +3242,12 @@
}
jfs_dirent->position = unique_pos++;
}
+ /*
+ * We add 1 to the index because we may
+ * use a value of 2 internally, and NFSv4
+ * doesn't like that.
+ */
+ jfs_dirent->position++;
} else {
jfs_dirent->position = dtpos;
len = min(d_namleft, DTLHDRDATALEN_LEGACY);
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index c1a3e60..7f464c5 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -95,7 +95,7 @@
if (insert_inode_locked(inode) < 0) {
rc = -EINVAL;
- goto fail_unlock;
+ goto fail_put;
}
inode_init_owner(inode, parent, mode);
@@ -156,7 +156,6 @@
fail_drop:
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
-fail_unlock:
clear_nlink(inode);
unlock_new_inode(inode);
fail_put:
diff --git a/fs/libfs.c b/fs/libfs.c
index 916da8c..1299bd5 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -104,18 +104,18 @@
spin_lock(&dentry->d_lock);
/* d_lock not required for cursor */
- list_del(&cursor->d_u.d_child);
+ list_del(&cursor->d_child);
p = dentry->d_subdirs.next;
while (n && p != &dentry->d_subdirs) {
struct dentry *next;
- next = list_entry(p, struct dentry, d_u.d_child);
+ next = list_entry(p, struct dentry, d_child);
spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(next))
n--;
spin_unlock(&next->d_lock);
p = p->next;
}
- list_add_tail(&cursor->d_u.d_child, p);
+ list_add_tail(&cursor->d_child, p);
spin_unlock(&dentry->d_lock);
}
}
@@ -139,7 +139,7 @@
{
struct dentry *dentry = filp->f_path.dentry;
struct dentry *cursor = filp->private_data;
- struct list_head *p, *q = &cursor->d_u.d_child;
+ struct list_head *p, *q = &cursor->d_child;
ino_t ino;
int i = filp->f_pos;
@@ -165,7 +165,7 @@
for (p=q->next; p != &dentry->d_subdirs; p=p->next) {
struct dentry *next;
- next = list_entry(p, struct dentry, d_u.d_child);
+ next = list_entry(p, struct dentry, d_child);
spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
if (!simple_positive(next)) {
spin_unlock(&next->d_lock);
@@ -289,7 +289,7 @@
int ret = 0;
spin_lock(&dentry->d_lock);
- list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &dentry->d_subdirs, d_child) {
spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
if (simple_positive(child)) {
spin_unlock(&child->d_lock);
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 01bfe766..41e491b 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -64,12 +64,17 @@
nlm_init->protocol, nlm_version,
nlm_init->hostname, nlm_init->noresvport,
nlm_init->net);
- if (host == NULL) {
- lockd_down(nlm_init->net);
- return ERR_PTR(-ENOLCK);
- }
+ if (host == NULL)
+ goto out_nohost;
+ if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
+ goto out_nobind;
return host;
+out_nobind:
+ nlmclnt_release_host(host);
+out_nohost:
+ lockd_down(nlm_init->net);
+ return ERR_PTR(-ENOLCK);
}
EXPORT_SYMBOL_GPL(nlmclnt_init);
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 9760ecb..acd3947 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -125,14 +125,15 @@
{
struct nlm_args *argp = &req->a_args;
struct nlm_lock *lock = &argp->lock;
+ char *nodename = req->a_host->h_rpcclnt->cl_nodename;
nlmclnt_next_cookie(&argp->cookie);
memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
- lock->caller = utsname()->nodename;
+ lock->caller = nodename;
lock->oh.data = req->a_owner;
lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
(unsigned int)fl->fl_u.nfs_fl.owner->pid,
- utsname()->nodename);
+ nodename);
lock->svid = fl->fl_u.nfs_fl.owner->pid;
lock->fl.fl_start = fl->fl_start;
lock->fl.fl_end = fl->fl_end;
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1812f02..6ae664b 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -159,6 +159,12 @@
msg.rpc_proc = &clnt->cl_procinfo[proc];
status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+ if (status == -ECONNREFUSED) {
+ dprintk("lockd: NSM upcall RPC failed, status=%d, forcing rebind\n",
+ status);
+ rpc_force_rebind(clnt);
+ status = rpc_call_sync(clnt, &msg, RPC_TASK_SOFTCONN);
+ }
if (status < 0)
dprintk("lockd: NSM upcall RPC failed, status=%d\n",
status);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index a2aa97d..7a31848 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -137,10 +137,6 @@
dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
- if (!nlm_timeout)
- nlm_timeout = LOCKD_DFLT_TIMEO;
- nlmsvc_timeout = nlm_timeout * HZ;
-
/*
* The main request loop. We don't terminate until the last
* NFS mount or NFS daemon has gone away.
@@ -235,6 +231,7 @@
if (warned++ == 0)
printk(KERN_WARNING
"lockd_up: makesock failed, error=%d\n", err);
+ svc_shutdown_net(serv, net);
return err;
}
@@ -252,13 +249,11 @@
error = make_socks(serv, net);
if (error < 0)
- goto err_socks;
+ goto err_bind;
set_grace_period(net);
dprintk("lockd_up_net: per-net data created; net=%p\n", net);
return 0;
-err_socks:
- svc_rpcb_cleanup(serv, net);
err_bind:
ln->nlmsvc_users--;
return error;
@@ -347,6 +342,10 @@
printk(KERN_WARNING
"lockd_up: no pid, %d users??\n", nlmsvc_users);
+ if (!nlm_timeout)
+ nlm_timeout = LOCKD_DFLT_TIMEO;
+ nlmsvc_timeout = nlm_timeout * HZ;
+
serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL);
if (!serv) {
printk(KERN_WARNING "lockd_up: create service failed\n");
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e703318..ffc4045 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -767,6 +767,7 @@
struct nlm_file *file = block->b_file;
struct nlm_lock *lock = &block->b_call->a_args.lock;
int error;
+ loff_t fl_start, fl_end;
dprintk("lockd: grant blocked lock %p\n", block);
@@ -784,9 +785,16 @@
}
/* Try the lock operation again */
+ /* vfs_lock_file() can mangle fl_start and fl_end, but we need
+ * them unchanged for the GRANT_MSG
+ */
lock->fl.fl_flags |= FL_SLEEP;
+ fl_start = lock->fl.fl_start;
+ fl_end = lock->fl.fl_end;
error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
lock->fl.fl_flags &= ~FL_SLEEP;
+ lock->fl.fl_start = fl_start;
+ lock->fl.fl_end = fl_end;
switch (error) {
case 0:
@@ -939,6 +947,7 @@
unsigned long timeout = MAX_SCHEDULE_TIMEOUT;
struct nlm_block *block;
+ spin_lock(&nlm_blocked_lock);
while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
@@ -948,6 +957,7 @@
timeout = block->b_when - jiffies;
break;
}
+ spin_unlock(&nlm_blocked_lock);
dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
block, block->b_when);
@@ -957,7 +967,9 @@
retry_deferred_block(block);
} else
nlmsvc_grant_blocked(block);
+ spin_lock(&nlm_blocked_lock);
}
+ spin_unlock(&nlm_blocked_lock);
return timeout;
}
diff --git a/fs/locks.c b/fs/locks.c
index cb424a4..0274c95 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1243,11 +1243,10 @@
restart:
break_time = flock->fl_break_time;
- if (break_time != 0) {
+ if (break_time != 0)
break_time -= jiffies;
- if (break_time == 0)
- break_time++;
- }
+ if (break_time == 0)
+ break_time++;
locks_insert_block(flock, new_fl);
unlock_flocks();
error = wait_event_interruptible_timeout(new_fl->fl_wait,
diff --git a/fs/mount.h b/fs/mount.h
index 64a8581..68d80bd 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -73,7 +73,7 @@
static inline int is_mounted(struct vfsmount *mnt)
{
/* neither detached nor internal? */
- return !IS_ERR_OR_NULL(real_mount(mnt));
+ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns);
}
extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
diff --git a/fs/namei.c b/fs/namei.c
index 9ed9361..036c212 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -34,6 +34,7 @@
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <linux/posix_acl.h>
+#include <linux/hash.h>
#include <asm/uaccess.h>
#include "internal.h"
@@ -321,10 +322,11 @@
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
- if (inode_capable(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
if (!(mask & MAY_WRITE))
- if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+ if (capable_wrt_inode_uidgid(inode,
+ CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
}
@@ -334,7 +336,7 @@
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
- if (inode_capable(inode, CAP_DAC_OVERRIDE))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
/*
@@ -342,7 +344,7 @@
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ)
- if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
@@ -1540,7 +1542,8 @@
if (should_follow_link(inode, follow)) {
if (nd->flags & LOOKUP_RCU) {
- if (unlikely(unlazy_walk(nd, path->dentry))) {
+ if (unlikely(nd->path.mnt != path->mnt ||
+ unlazy_walk(nd, path->dentry))) {
err = -ECHILD;
goto out_err;
}
@@ -1646,8 +1649,7 @@
static inline unsigned int fold_hash(unsigned long hash)
{
- hash += hash >> (8*sizeof(int));
- return hash;
+ return hash_64(hash, 32);
}
#else /* 32-bit case */
@@ -2199,7 +2201,7 @@
return 0;
if (uid_eq(dir->i_uid, fsuid))
return 0;
- return !inode_capable(inode, CAP_FOWNER);
+ return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
}
/*
@@ -2263,6 +2265,7 @@
*/
static inline int may_create(struct inode *dir, struct dentry *child)
{
+ audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
@@ -2822,7 +2825,8 @@
if (should_follow_link(inode, !symlink_ok)) {
if (nd->flags & LOOKUP_RCU) {
- if (unlikely(unlazy_walk(nd, path->dentry))) {
+ if (unlikely(nd->path.mnt != path->mnt ||
+ unlazy_walk(nd, path->dentry))) {
error = -ECHILD;
goto out;
}
@@ -3654,6 +3658,7 @@
out_dput:
done_path_create(&new_path, new_dentry);
if (retry_estale(error, how)) {
+ path_put(&old_path);
how |= LOOKUP_REVAL;
goto retry;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 7b1ca9b..d0244c8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -828,8 +828,21 @@
mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
/* Don't allow unprivileged users to change mount flags */
- if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
- mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+ if (flag & CL_UNPRIVILEGED) {
+ mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+ if (mnt->mnt.mnt_flags & MNT_READONLY)
+ mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+ if (mnt->mnt.mnt_flags & MNT_NODEV)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+ if (mnt->mnt.mnt_flags & MNT_NOSUID)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+ if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+ }
atomic_inc(&sb->s_active);
mnt->mnt.mnt_sb = sb;
@@ -1261,6 +1274,8 @@
* Special case for "unmounting" root ...
* we just try to remount it readonly.
*/
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
down_write(&sb->s_umount);
if (!(sb->s_flags & MS_RDONLY))
retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
@@ -1327,6 +1342,9 @@
goto dput_and_out;
if (!check_mnt(mnt))
goto dput_and_out;
+ retval = -EPERM;
+ if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+ goto dput_and_out;
retval = do_umount(mnt, flags);
dput_and_out:
@@ -1429,7 +1447,7 @@
CL_COPY_ALL | CL_PRIVATE);
namespace_unlock();
if (IS_ERR(tree))
- return NULL;
+ return ERR_CAST(tree);
return &tree->mnt;
}
@@ -1764,9 +1782,6 @@
if (readonly_request == __mnt_is_readonly(mnt))
return 0;
- if (mnt->mnt_flags & MNT_LOCK_READONLY)
- return -EPERM;
-
if (readonly_request)
error = mnt_make_readonly(real_mount(mnt));
else
@@ -1792,6 +1807,39 @@
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
+ /* Don't allow changing of locked mnt flags.
+ *
+ * No locks need to be held here while testing the various
+ * MNT_LOCK flags because those flags can never be cleared
+ * once they are set.
+ */
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+ !(mnt_flags & MNT_READONLY)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+ !(mnt_flags & MNT_NODEV)) {
+ /* Was the nodev implicitly added in mount? */
+ if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+ !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+ mnt_flags |= MNT_NODEV;
+ } else {
+ return -EPERM;
+ }
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+ !(mnt_flags & MNT_NOSUID)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+ !(mnt_flags & MNT_NOEXEC)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+ ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+ return -EPERM;
+ }
+
err = security_sb_remount(sb, data);
if (err)
return err;
@@ -1805,7 +1853,7 @@
err = do_remount_sb(sb, flags, data, 0);
if (!err) {
br_write_lock(&vfsmount_lock);
- mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+ mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
mnt->mnt.mnt_flags = mnt_flags;
br_write_unlock(&vfsmount_lock);
}
@@ -1991,7 +2039,7 @@
*/
if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
flags |= MS_NODEV;
- mnt_flags |= MNT_NODEV;
+ mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
}
}
@@ -2309,6 +2357,14 @@
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
+ /* The default atime for remount is preservation */
+ if ((flags & MS_REMOUNT) &&
+ ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+ MS_STRICTATIME)) == 0)) {
+ mnt_flags &= ~MNT_ATIME_MASK;
+ mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+ }
+
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
MS_STRICTATIME);
@@ -2649,6 +2705,9 @@
/* make sure we can reach put_old from new_root */
if (!is_path_reachable(old_mnt, old.dentry, &new))
goto out4;
+ /* make certain new is below the root */
+ if (!is_path_reachable(new_mnt, new.dentry, &root))
+ goto out4;
root_mp->m_count++; /* pin it so it won't go away */
br_write_lock(&vfsmount_lock);
detach_mnt(new_mnt, &parent_path);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 6792ce1..c578ba9 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -391,7 +391,7 @@
spin_lock(&parent->d_lock);
next = parent->d_subdirs.next;
while (next != &parent->d_subdirs) {
- dent = list_entry(next, struct dentry, d_u.d_child);
+ dent = list_entry(next, struct dentry, d_child);
if ((unsigned long)dent->d_fsdata == fpos) {
if (dent->d_inode)
dget(dent);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 60426cc..2f970de 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -448,7 +448,6 @@
result = -EIO;
}
}
- result = 0;
}
mutex_unlock(&server->root_setup_lock);
diff --git a/fs/ncpfs/ncplib_kernel.h b/fs/ncpfs/ncplib_kernel.h
index 32c0658..6d5e7c5 100644
--- a/fs/ncpfs/ncplib_kernel.h
+++ b/fs/ncpfs/ncplib_kernel.h
@@ -194,7 +194,7 @@
spin_lock(&parent->d_lock);
next = parent->d_subdirs.next;
while (next != &parent->d_subdirs) {
- dentry = list_entry(next, struct dentry, d_u.d_child);
+ dentry = list_entry(next, struct dentry, d_child);
if (dentry->d_fsdata == NULL)
ncp_age_dentry(server, dentry);
@@ -216,7 +216,7 @@
spin_lock(&parent->d_lock);
next = parent->d_subdirs.next;
while (next != &parent->d_subdirs) {
- dentry = list_entry(next, struct dentry, d_u.d_child);
+ dentry = list_entry(next, struct dentry, d_child);
dentry->d_fsdata = NULL;
ncp_age_dentry(server, dentry);
next = next->next;
diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c
index 9c3e117..4d01614 100644
--- a/fs/nfs/blocklayout/extents.c
+++ b/fs/nfs/blocklayout/extents.c
@@ -44,7 +44,7 @@
static inline sector_t normalize(sector_t s, int base)
{
sector_t tmp = s; /* Since do_div modifies its argument */
- return s - do_div(tmp, base);
+ return s - sector_div(tmp, base);
}
static inline sector_t normalize_up(sector_t s, int base)
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index cff089a..e05c96e 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -128,22 +128,24 @@
if (try_to_freeze())
continue;
- prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+ prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
spin_lock_bh(&serv->sv_cb_lock);
if (!list_empty(&serv->sv_cb_list)) {
req = list_first_entry(&serv->sv_cb_list,
struct rpc_rqst, rq_bc_list);
list_del(&req->rq_bc_list);
spin_unlock_bh(&serv->sv_cb_lock);
+ finish_wait(&serv->sv_cb_waitq, &wq);
dprintk("Invoking bc_svc_process()\n");
error = bc_svc_process(serv, req, rqstp);
dprintk("bc_svc_process() returned w/ error code= %d\n",
error);
} else {
spin_unlock_bh(&serv->sv_cb_lock);
- schedule();
+ /* schedule_timeout to game the hung task watchdog */
+ schedule_timeout(60 * HZ);
+ finish_wait(&serv->sv_cb_waitq, &wq);
}
- finish_wait(&serv->sv_cb_waitq, &wq);
}
return 0;
}
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index a35582c..e98ecf8 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -464,8 +464,10 @@
for (i = 0; i < args->csa_nrclists; i++) {
status = decode_rc_list(xdr, &args->csa_rclists[i]);
- if (status)
+ if (status) {
+ args->csa_nrclists = i;
goto out_free;
+ }
}
}
status = 0;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 57db324..ef0c394 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -108,6 +108,8 @@
continue;
if (!test_bit(NFS_DELEGATED_STATE, &state->flags))
continue;
+ if (!nfs4_valid_open_stateid(state))
+ continue;
if (!nfs4_stateid_match(&state->stateid, stateid))
continue;
get_nfs_open_context(ctx);
@@ -175,7 +177,11 @@
{
int res = 0;
- res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync);
+ if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ res = nfs4_proc_delegreturn(inode,
+ delegation->cred,
+ &delegation->stateid,
+ issync);
nfs_free_delegation(delegation);
return res;
}
@@ -361,11 +367,13 @@
{
struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
struct nfs_inode *nfsi = NFS_I(inode);
- int err;
+ int err = 0;
if (delegation == NULL)
return 0;
do {
+ if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
+ break;
err = nfs_delegation_claim_opens(inode, &delegation->stateid);
if (!issync || err != -EAGAIN)
break;
@@ -586,10 +594,23 @@
rcu_read_unlock();
}
+static void nfs_revoke_delegation(struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+ rcu_read_lock();
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation != NULL) {
+ set_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
+ nfs_mark_return_delegation(NFS_SERVER(inode), delegation);
+ }
+ rcu_read_unlock();
+}
+
void nfs_remove_bad_delegation(struct inode *inode)
{
struct nfs_delegation *delegation;
+ nfs_revoke_delegation(inode);
delegation = nfs_inode_detach_delegation(inode);
if (delegation) {
nfs_inode_find_state_and_recover(inode, &delegation->stateid);
@@ -656,16 +677,19 @@
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation == NULL)
+ goto out_enoent;
- if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
- rcu_read_unlock();
- return -ENOENT;
- }
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+ goto out_enoent;
nfs_mark_return_delegation(server, delegation);
rcu_read_unlock();
nfs_delegation_run_state_manager(clp);
return 0;
+out_enoent:
+ rcu_read_unlock();
+ return -ENOENT;
}
static struct inode *
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9a79c7a..e02b090 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -31,6 +31,7 @@
NFS_DELEGATION_RETURN_IF_CLOSED,
NFS_DELEGATION_REFERENCED,
NFS_DELEGATION_RETURNING,
+ NFS_DELEGATION_REVOKED,
};
int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0bd7a55..615c507 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -123,6 +123,12 @@
*/
ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
{
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+
+ /* we only support swap file calling nfs_direct_IO */
+ if (!IS_SWAPFILE(inode))
+ return 0;
+
#ifndef CONFIG_NFS_SWAP
dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n",
iocb->ki_filp->f_path.dentry->d_name.name,
@@ -180,6 +186,7 @@
{
struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
+ nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo);
if (dreq->l_ctx != NULL)
nfs_put_lock_context(dreq->l_ctx);
if (dreq->ctx != NULL)
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 44efaa8..0fe3ced 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -58,7 +58,7 @@
*/
spin_lock(&sb->s_root->d_inode->i_lock);
spin_lock(&sb->s_root->d_lock);
- hlist_del_init(&sb->s_root->d_alias);
+ hlist_del_init(&sb->s_root->d_u.d_alias);
spin_unlock(&sb->s_root->d_lock);
spin_unlock(&sb->s_root->d_inode->i_lock);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c1c7a9d..e9be01b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -519,7 +519,7 @@
{
struct inode *inode = dentry->d_inode;
int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
- int err;
+ int err = 0;
/* Flush out writes to the server in order to update c/mtime. */
if (S_ISREG(inode->i_mode)) {
@@ -1382,18 +1382,20 @@
inode->i_version = fattr->change_attr;
}
} else if (server->caps & NFS_CAP_CHANGE_ATTR)
- invalid |= save_cache_validity;
+ nfsi->cache_validity |= save_cache_validity;
if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
} else if (server->caps & NFS_CAP_MTIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
} else if (server->caps & NFS_CAP_CTIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
/* Check if our cached file size is stale */
@@ -1416,7 +1418,8 @@
(long long)new_isize);
}
} else
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_PAGECACHE
| NFS_INO_REVAL_FORCED);
@@ -1424,7 +1427,8 @@
if (fattr->valid & NFS_ATTR_FATTR_ATIME)
memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
else if (server->caps & NFS_CAP_ATIME)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATIME
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1435,7 +1439,8 @@
invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
}
} else if (server->caps & NFS_CAP_MODE)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1446,7 +1451,8 @@
inode->i_uid = fattr->uid;
}
} else if (server->caps & NFS_CAP_OWNER)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1457,7 +1463,8 @@
inode->i_gid = fattr->gid;
}
} else if (server->caps & NFS_CAP_OWNER_GROUP)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_FORCED);
@@ -1470,7 +1477,8 @@
set_nlink(inode, fattr->nlink);
}
} else if (server->caps & NFS_CAP_NLINK)
- invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+ nfsi->cache_validity |= save_cache_validity &
+ (NFS_INO_INVALID_ATTR
| NFS_INO_REVAL_FORCED);
if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 4a1aafb..8c34f57 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -305,7 +305,10 @@
.rpc_argp = &args,
.rpc_resp = &fattr,
};
- int status;
+ int status = 0;
+
+ if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+ goto out;
status = -EOPNOTSUPP;
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 4cbad5d..5f8d5ff 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -240,13 +240,11 @@
error = nfs4_discover_server_trunking(clp, &old);
if (error < 0)
goto error;
- nfs_put_client(clp);
- if (clp != old) {
- clp->cl_preserve_clid = true;
- clp = old;
- }
- return clp;
+ if (clp != old)
+ clp->cl_preserve_clid = true;
+ nfs_put_client(clp);
+ return old;
error:
nfs_mark_client_ready(clp, error);
@@ -313,6 +311,16 @@
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+ if (pos->rpc_ops != new->rpc_ops)
+ continue;
+
+ if (pos->cl_proto != new->cl_proto)
+ continue;
+
+ if (pos->cl_minorversion != new->cl_minorversion)
+ continue;
+
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos" */
if (pos->cl_cons_state > NFS_CS_READY) {
@@ -324,22 +332,14 @@
prev = pos;
status = nfs_wait_client_init_complete(pos);
- spin_lock(&nn->nfs_client_lock);
if (status < 0)
- continue;
+ goto out;
+ status = -NFS4ERR_STALE_CLIENTID;
+ spin_lock(&nn->nfs_client_lock);
}
if (pos->cl_cons_state != NFS_CS_READY)
continue;
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_proto != new->cl_proto)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
if (pos->cl_clientid != new->cl_clientid)
continue;
@@ -394,20 +394,14 @@
}
/*
- * Returns true if the server owners match
+ * Returns true if the server major ids match
*/
static bool
-nfs4_match_serverowners(struct nfs_client *a, struct nfs_client *b)
+nfs4_check_clientid_trunking(struct nfs_client *a, struct nfs_client *b)
{
struct nfs41_server_owner *o1 = a->cl_serverowner;
struct nfs41_server_owner *o2 = b->cl_serverowner;
- if (o1->minor_id != o2->minor_id) {
- dprintk("NFS: --> %s server owner minor IDs do not match\n",
- __func__);
- return false;
- }
-
if (o1->major_id_sz != o2->major_id_sz)
goto out_major_mismatch;
if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
@@ -445,6 +439,16 @@
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+ if (pos->rpc_ops != new->rpc_ops)
+ continue;
+
+ if (pos->cl_proto != new->cl_proto)
+ continue;
+
+ if (pos->cl_minorversion != new->cl_minorversion)
+ continue;
+
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos", especially the client
* ID and serverowner fields. Wait for CREATE_SESSION
@@ -458,30 +462,27 @@
prev = pos;
status = nfs_wait_client_init_complete(pos);
- if (status == 0) {
+ if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
nfs4_schedule_lease_recovery(pos);
status = nfs4_wait_clnt_recover(pos);
}
spin_lock(&nn->nfs_client_lock);
if (status < 0)
- continue;
+ break;
+ status = -NFS4ERR_STALE_CLIENTID;
}
if (pos->cl_cons_state != NFS_CS_READY)
continue;
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_proto != new->cl_proto)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
if (!nfs4_match_clientids(pos, new))
continue;
- if (!nfs4_match_serverowners(pos, new))
+ /*
+ * Note that session trunking is just a special subcase of
+ * client id trunking. In either case, we want to fall back
+ * to using the existing nfs_client.
+ */
+ if (!nfs4_check_clientid_trunking(pos, new))
continue;
atomic_inc(&pos->cl_count);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 22d1062..b039f7f 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -1300,7 +1300,7 @@
struct nfs4_filelayout *flo;
flo = kzalloc(sizeof(*flo), gfp_flags);
- return &flo->generic_hdr;
+ return flo != NULL ? &flo->generic_hdr : NULL;
}
static void
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 661a0f6..678cb89 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -797,34 +797,34 @@
struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
-
- if (filelayout_test_devid_unavailable(devid))
- return NULL;
+ struct nfs4_pnfs_ds *ret = ds;
if (ds == NULL) {
printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
__func__, ds_idx);
filelayout_mark_devid_invalid(devid);
- return NULL;
+ goto out;
}
if (ds->ds_clp)
- return ds;
+ goto out_test_devid;
if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
int err;
err = nfs4_ds_connect(s, ds);
- if (err) {
+ if (err)
nfs4_mark_deviceid_unavailable(devid);
- ds = NULL;
- }
nfs4_clear_ds_conn_bit(ds);
} else {
/* Either ds is connected, or ds is NULL */
nfs4_wait_ds_connect(ds);
}
- return ds;
+out_test_devid:
+ if (filelayout_test_devid_unavailable(devid))
+ ret = NULL;
+out:
+ return ret;
}
module_param(dataserver_retrans, uint, 0644);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d7ba561..20ebcfa 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1160,29 +1160,24 @@
int ret;
if (!data->rpc_done) {
- ret = data->rpc_status;
- goto err;
+ if (data->rpc_status) {
+ ret = data->rpc_status;
+ goto err;
+ }
+ /* cached opens have already been processed */
+ goto update;
}
- ret = -ESTALE;
- if (!(data->f_attr.valid & NFS_ATTR_FATTR_TYPE) ||
- !(data->f_attr.valid & NFS_ATTR_FATTR_FILEID) ||
- !(data->f_attr.valid & NFS_ATTR_FATTR_CHANGE))
- goto err;
-
- ret = -ENOMEM;
- state = nfs4_get_open_state(inode, data->owner);
- if (state == NULL)
- goto err;
-
ret = nfs_refresh_inode(inode, &data->f_attr);
if (ret)
goto err;
if (data->o_res.delegation_type != 0)
nfs4_opendata_check_deleg(data, state);
+update:
update_open_stateid(state, &data->o_res.stateid, NULL,
data->o_arg.fmode);
+ atomic_inc(&state->count);
return state;
err:
@@ -1421,7 +1416,7 @@
nfs_inode_find_state_and_recover(state->inode,
stateid);
nfs4_schedule_stateid_recovery(server, state);
- return 0;
+ return -EAGAIN;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
set_bit(NFS_DELEGATED_STATE, &state->flags);
@@ -1850,6 +1845,28 @@
return ret;
}
+static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+{
+ nfs_remove_bad_delegation(state->inode);
+ write_seqlock(&state->seqlock);
+ nfs4_stateid_copy(&state->stateid, &state->open_stateid);
+ write_sequnlock(&state->seqlock);
+ clear_bit(NFS_DELEGATED_STATE, &state->flags);
+}
+
+static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
+{
+ if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
+ nfs_finish_clear_delegation_stateid(state);
+}
+
+static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+ /* NFSv4.0 doesn't allow for delegation recovery on open expire */
+ nfs40_clear_delegation_stateid(state);
+ return nfs4_open_expired(sp, state);
+}
+
#if defined(CONFIG_NFS_V4_1)
static void nfs41_clear_delegation_stateid(struct nfs4_state *state)
{
@@ -2292,6 +2309,7 @@
struct nfs4_closedata *calldata = data;
struct nfs4_state *state = calldata->state;
struct inode *inode = calldata->inode;
+ bool is_rdonly, is_wronly, is_rdwr;
int call_close = 0;
dprintk("%s: begin!\n", __func__);
@@ -2299,21 +2317,27 @@
goto out_wait;
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
- calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
spin_lock(&state->owner->so_lock);
+ is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+ is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+ is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
/* Calculate the change in open mode */
+ calldata->arg.fmode = 0;
if (state->n_rdwr == 0) {
- if (state->n_rdonly == 0) {
- call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
- call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
- calldata->arg.fmode &= ~FMODE_READ;
- }
- if (state->n_wronly == 0) {
- call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
- call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
- calldata->arg.fmode &= ~FMODE_WRITE;
- }
- }
+ if (state->n_rdonly == 0)
+ call_close |= is_rdonly;
+ else if (is_rdonly)
+ calldata->arg.fmode |= FMODE_READ;
+ if (state->n_wronly == 0)
+ call_close |= is_wronly;
+ else if (is_wronly)
+ calldata->arg.fmode |= FMODE_WRITE;
+ } else if (is_rdwr)
+ calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
+
+ if (calldata->arg.fmode == 0)
+ call_close |= is_rdwr;
+
if (!nfs4_valid_open_stateid(state))
call_close = 0;
spin_unlock(&state->owner->so_lock);
@@ -3612,8 +3636,9 @@
{
nfs4_stateid current_stateid;
- if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode))
- return false;
+ /* If the current stateid represents a lost lock, then exit */
+ if (nfs4_set_rw_stateid(¤t_stateid, ctx, l_ctx, fmode) == -EIO)
+ return true;
return nfs4_stateid_match(stateid, ¤t_stateid);
}
@@ -4227,8 +4252,7 @@
dprintk("%s ERROR %d, Reset session\n", __func__,
task->tk_status);
nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
- task->tk_status = 0;
- return -EAGAIN;
+ goto wait_on_recovery;
#endif /* CONFIG_NFS_V4_1 */
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
@@ -4406,11 +4430,17 @@
return;
switch (task->tk_status) {
- case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_EXPIRED:
case 0:
renew_lease(data->res.server, data->timestamp);
break;
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_OLD_STATEID:
+ case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_EXPIRED:
+ task->tk_status = 0;
+ break;
default:
if (nfs4_async_handle_error(task, data->res.server, NULL) ==
-EAGAIN) {
@@ -4572,6 +4602,7 @@
status = 0;
}
request->fl_ops->fl_release_private(request);
+ request->fl_ops = NULL;
out:
return status;
}
@@ -6058,7 +6089,7 @@
int ret = 0;
if ((renew_flags & NFS4_RENEW_TIMEOUT) == 0)
- return 0;
+ return -EAGAIN;
task = _nfs41_proc_sequence(clp, cred, false);
if (IS_ERR(task))
ret = PTR_ERR(task);
@@ -6231,9 +6262,9 @@
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
struct nfs4_state *state = NULL;
- unsigned long timeo, giveup;
+ unsigned long timeo, now, giveup;
- dprintk("--> %s\n", __func__);
+ dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
if (!nfs41_sequence_done(task, &lgp->res.seq_res))
goto out;
@@ -6241,12 +6272,38 @@
switch (task->tk_status) {
case 0:
goto out;
+ /*
+ * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+ * (or clients) writing to the same RAID stripe
+ */
case -NFS4ERR_LAYOUTTRYLATER:
+ /*
+ * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+ * existing layout before getting a new one).
+ */
case -NFS4ERR_RECALLCONFLICT:
timeo = rpc_get_timeout(task->tk_client);
giveup = lgp->args.timestamp + timeo;
- if (time_after(giveup, jiffies))
- task->tk_status = -NFS4ERR_DELAY;
+ now = jiffies;
+ if (time_after(giveup, now)) {
+ unsigned long delay;
+
+ /* Delay for:
+ * - Not less then NFS4_POLL_RETRY_MIN.
+ * - One last time a jiffie before we give up
+ * - exponential backoff (time_now minus start_attempt)
+ */
+ delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+ min((giveup - now - 1),
+ now - lgp->args.timestamp));
+
+ dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+ __func__, delay);
+ rpc_delay(task, delay);
+ task->tk_status = 0;
+ rpc_restart_call_prepare(task);
+ goto out; /* Do not call nfs4_async_handle_error() */
+ }
break;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
@@ -6361,6 +6418,9 @@
dprintk("--> %s\n", __func__);
+ /* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+ pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
if (!lgp->args.layout.pages) {
nfs4_layoutget_release(lgp);
@@ -6373,9 +6433,6 @@
lgp->res.seq_res.sr_slot = NULL;
nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
- /* nfs4_layoutget_release calls pnfs_put_layout_hdr */
- pnfs_get_layout_hdr(NFS_I(inode)->layout);
-
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return ERR_CAST(task);
@@ -6682,7 +6739,7 @@
switch (err) {
case 0:
case -NFS4ERR_WRONGSEC:
- case -NFS4ERR_NOTSUPP:
+ case -ENOTSUPP:
goto out;
default:
err = nfs4_handle_exception(server, err, &exception);
@@ -6714,7 +6771,7 @@
* Fall back on "guess and check" method if
* the server doesn't support SECINFO_NO_NAME
*/
- if (err == -NFS4ERR_WRONGSEC || err == -NFS4ERR_NOTSUPP) {
+ if (err == -NFS4ERR_WRONGSEC || err == -ENOTSUPP) {
err = nfs4_find_root_sec(server, fhandle, info);
goto out_freepage;
}
@@ -6939,7 +6996,7 @@
static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = {
.owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE,
.state_flag_bit = NFS_STATE_RECLAIM_NOGRACE,
- .recover_open = nfs4_open_expired,
+ .recover_open = nfs40_open_expired,
.recover_lock = nfs4_lock_expired,
.establish_clid = nfs4_init_clientid,
.get_clid_cred = nfs4_get_setclientid_cred,
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 1720d32..e1ba58c 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -88,10 +88,18 @@
}
nfs_expire_all_delegations(clp);
} else {
+ int ret;
+
/* Queue an asynchronous RENEW. */
- ops->sched_state_renewal(clp, cred, renew_flags);
+ ret = ops->sched_state_renewal(clp, cred, renew_flags);
put_rpccred(cred);
- goto out_exp;
+ switch (ret) {
+ default:
+ goto out_exp;
+ case -EAGAIN:
+ case -ENOMEM:
+ break;
+ }
}
} else {
dprintk("%s: failed to call renewd. Reason: lease not expired \n",
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1fab140..d482b86 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -228,19 +228,8 @@
return status;
}
-/*
- * Back channel returns NFS4ERR_DELAY for new requests when
- * NFS4_SESSION_DRAINING is set so there is no work to be done when draining
- * is ended.
- */
-static void nfs4_end_drain_session(struct nfs_client *clp)
+static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl)
{
- struct nfs4_session *ses = clp->cl_session;
- struct nfs4_slot_table *tbl;
-
- if (ses == NULL)
- return;
- tbl = &ses->fc_slot_table;
if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
spin_lock(&tbl->slot_tbl_lock);
nfs41_wake_slot_table(tbl);
@@ -248,6 +237,16 @@
}
}
+static void nfs4_end_drain_session(struct nfs_client *clp)
+{
+ struct nfs4_session *ses = clp->cl_session;
+
+ if (ses != NULL) {
+ nfs4_end_drain_slot_table(&ses->bc_slot_table);
+ nfs4_end_drain_slot_table(&ses->fc_slot_table);
+ }
+}
+
/*
* Signal state manager thread if session fore channel is drained
*/
@@ -1700,7 +1699,8 @@
if (status < 0) {
set_bit(ops->owner_flag_bit, &sp->so_flags);
nfs4_put_state_owner(sp);
- return nfs4_recovery_handle_error(clp, status);
+ status = nfs4_recovery_handle_error(clp, status);
+ return (status != 0) ? status : -EAGAIN;
}
nfs4_put_state_owner(sp);
@@ -1709,7 +1709,7 @@
spin_unlock(&clp->cl_lock);
}
rcu_read_unlock();
- return status;
+ return 0;
}
static int nfs4_check_lease(struct nfs_client *clp)
@@ -1756,7 +1756,6 @@
break;
case -NFS4ERR_STALE_CLIENTID:
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
- nfs4_state_clear_reclaim_reboot(clp);
nfs4_state_start_reclaim_reboot(clp);
break;
case -NFS4ERR_CLID_INUSE:
@@ -2175,14 +2174,11 @@
section = "reclaim reboot";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->reboot_recovery_ops);
- if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
- test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
- continue;
- nfs4_state_end_reclaim_reboot(clp);
- if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state))
+ if (status == -EAGAIN)
continue;
if (status < 0)
goto out_error;
+ nfs4_state_end_reclaim_reboot(clp);
}
/* Now recover expired state... */
@@ -2190,9 +2186,7 @@
section = "reclaim nograce";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->nograce_recovery_ops);
- if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
- test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
- test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
+ if (status == -EAGAIN)
continue;
if (status < 0)
goto out_error;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 4be8d13..988efb4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3002,7 +3002,8 @@
return -EIO;
}
-static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+static bool __decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected,
+ int *nfs_retval)
{
__be32 *p;
uint32_t opnum;
@@ -3012,19 +3013,32 @@
if (unlikely(!p))
goto out_overflow;
opnum = be32_to_cpup(p++);
- if (opnum != expected) {
- dprintk("nfs: Server returned operation"
- " %d but we issued a request for %d\n",
- opnum, expected);
- return -EIO;
- }
+ if (unlikely(opnum != expected))
+ goto out_bad_operation;
nfserr = be32_to_cpup(p);
- if (nfserr != NFS_OK)
- return nfs4_stat_to_errno(nfserr);
- return 0;
+ if (nfserr == NFS_OK)
+ *nfs_retval = 0;
+ else
+ *nfs_retval = nfs4_stat_to_errno(nfserr);
+ return true;
+out_bad_operation:
+ dprintk("nfs: Server returned operation"
+ " %d but we issued a request for %d\n",
+ opnum, expected);
+ *nfs_retval = -EREMOTEIO;
+ return false;
out_overflow:
print_overflow_msg(__func__, xdr);
- return -EIO;
+ *nfs_retval = -EIO;
+ return false;
+}
+
+static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
+{
+ int retval;
+
+ __decode_op_hdr(xdr, expected, &retval);
+ return retval;
}
/* Dummy routine */
@@ -4842,11 +4856,12 @@
uint32_t savewords, bmlen, i;
int status;
- status = decode_op_hdr(xdr, OP_OPEN);
- if (status != -EIO)
- nfs_increment_open_seqid(status, res->seqid);
- if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ if (!__decode_op_hdr(xdr, OP_OPEN, &status))
+ return status;
+ nfs_increment_open_seqid(status, res->seqid);
+ if (status)
+ return status;
+ status = decode_stateid(xdr, &res->stateid);
if (unlikely(status))
return status;
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 5f38ea3..af51cf9 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -536,16 +536,12 @@
if (err)
goto out3;
exp.ex_anon_uid= make_kuid(&init_user_ns, an_int);
- if (!uid_valid(exp.ex_anon_uid))
- goto out3;
/* anon gid */
err = get_int(&mesg, &an_int);
if (err)
goto out3;
exp.ex_anon_gid= make_kgid(&init_user_ns, an_int);
- if (!gid_valid(exp.ex_anon_gid))
- goto out3;
/* fsid */
err = get_int(&mesg, &an_int);
@@ -583,6 +579,17 @@
exp.ex_uuid);
if (err)
goto out4;
+ /*
+ * For some reason exportfs has been passing down an
+ * invalid (-1) uid & gid on the "dummy" export which it
+ * uses to test export support. To make sure exportfs
+ * sees errors from check_export we therefore need to
+ * delay these checks till after check_export:
+ */
+ if (!uid_valid(exp.ex_anon_uid))
+ goto out4;
+ if (!gid_valid(exp.ex_anon_gid))
+ goto out4;
}
expp = svc_export_lookup(&exp);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 8a50b3c..e15bcbd 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -385,8 +385,10 @@
* by uid/gid. */
int i, j;
- if (pacl->a_count <= 4)
- return; /* no users or groups */
+ /* no users or groups */
+ if (!pacl || pacl->a_count <= 4)
+ return;
+
i = 1;
while (pacl->a_entries[i].e_tag == ACL_USER)
i++;
@@ -513,13 +515,12 @@
/*
* ACLs with no ACEs are treated differently in the inheritable
- * and effective cases: when there are no inheritable ACEs, we
- * set a zero-length default posix acl:
+ * and effective cases: when there are no inheritable ACEs,
+ * calls ->set_acl with a NULL ACL structure.
*/
- if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) {
- pacl = posix_acl_alloc(0, GFP_KERNEL);
- return pacl ? pacl : ERR_PTR(-ENOMEM);
- }
+ if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+ return NULL;
+
/*
* When there are no effective ACEs, the following will end
* up setting a 3-element effective posix ACL with all
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7f05cd1..f42bbe5 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -637,9 +637,11 @@
static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
{
+ int maxtime = max_cb_time(clp->net);
struct rpc_timeout timeparms = {
- .to_initval = max_cb_time(clp->net),
+ .to_initval = maxtime,
.to_retries = 0,
+ .to_maxval = maxtime,
};
struct rpc_create_args args = {
.net = clp->net,
@@ -670,7 +672,8 @@
clp->cl_cb_session = ses;
args.bc_xprt = conn->cb_xprt;
args.prognumber = clp->cl_cb_session->se_cb_prog;
- args.protocol = XPRT_TRANSPORT_BC_TCP;
+ args.protocol = conn->cb_xprt->xpt_class->xcl_ident |
+ XPRT_TRANSPORT_BC;
args.authflavor = ses->se_cb_sec.flavor;
}
/* Create RPC client */
@@ -781,8 +784,12 @@
{
if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
rpc_sleep_on(&clp->cl_cb_waitq, task, NULL);
- dprintk("%s slot is busy\n", __func__);
- return false;
+ /* Race breaker */
+ if (test_and_set_bit(0, &clp->cl_cb_slot_busy) != 0) {
+ dprintk("%s slot is busy\n", __func__);
+ return false;
+ }
+ rpc_wake_up_queued_task(&clp->cl_cb_waitq, task);
}
return true;
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 27d74a2..9240dd1 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -576,15 +576,6 @@
switch (create->cr_type) {
case NF4LNK:
- /* ugh! we have to null-terminate the linktext, or
- * vfs_symlink() will choke. it is always safe to
- * null-terminate by brute force, since at worst we
- * will overwrite the first byte of the create namelen
- * in the XDR buffer, which has already been extracted
- * during XDR decode.
- */
- create->cr_linkname[create->cr_linklen] = 0;
-
status = nfsd_symlink(rqstp, &cstate->current_fh,
create->cr_name, create->cr_namelen,
create->cr_linkname, create->cr_linklen,
@@ -1200,7 +1191,8 @@
*/
if (argp->opcnt == resp->opcnt)
return false;
-
+ if (next->opnum == OP_ILLEGAL)
+ return false;
nextd = OPDESC(next);
/*
* Rest of 2.6.3.1.1: certain operations will return WRONGSEC
@@ -1307,6 +1299,12 @@
/* If op is non-idempotent */
if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
plen = opdesc->op_rsize_bop(rqstp, op);
+ /*
+ * If there's still another operation, make sure
+ * we'll have space to at least encode an error:
+ */
+ if (resp->opcnt < args->opcnt)
+ plen += COMPOUND_ERR_SLACK_SPACE;
op->status = nfsd4_check_resp_size(resp, plen);
}
@@ -1471,7 +1469,8 @@
static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
- return (op_encode_hdr_size + 2 + 1024) * sizeof(__be32);
+ return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
+ sizeof(__be32);
}
static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 316ec843..4a58afa 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -367,7 +367,6 @@
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh, u32 type)
{
struct nfs4_delegation *dp;
- struct nfs4_file *fp = stp->st_file;
dprintk("NFSD alloc_init_deleg\n");
/*
@@ -377,8 +376,6 @@
*/
if (type != NFS4_OPEN_DELEGATE_READ)
return NULL;
- if (fp->fi_had_conflict)
- return NULL;
if (num_delegations > max_delegations)
return NULL;
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
@@ -395,8 +392,7 @@
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
- get_nfs4_file(fp);
- dp->dl_file = fp;
+ dp->dl_file = NULL;
dp->dl_type = type;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
@@ -1081,6 +1077,18 @@
return NULL;
}
clp->cl_name.len = name.len;
+ INIT_LIST_HEAD(&clp->cl_sessions);
+ idr_init(&clp->cl_stateids);
+ atomic_set(&clp->cl_refcount, 0);
+ clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+ INIT_LIST_HEAD(&clp->cl_idhash);
+ INIT_LIST_HEAD(&clp->cl_openowners);
+ INIT_LIST_HEAD(&clp->cl_delegations);
+ INIT_LIST_HEAD(&clp->cl_lru);
+ INIT_LIST_HEAD(&clp->cl_callbacks);
+ INIT_LIST_HEAD(&clp->cl_revoked);
+ spin_lock_init(&clp->cl_lock);
+ rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
return clp;
}
@@ -1098,6 +1106,7 @@
WARN_ON_ONCE(atomic_read(&ses->se_ref));
free_session(ses);
}
+ rpc_destroy_wait_queue(&clp->cl_cb_waitq);
free_svc_cred(&clp->cl_cred);
kfree(clp->cl_name.data);
idr_destroy(&clp->cl_stateids);
@@ -1191,15 +1200,14 @@
return 0;
}
-static long long
+static int
compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2)
{
- long long res;
-
- res = o1->len - o2->len;
- if (res)
- return res;
- return (long long)memcmp(o1->data, o2->data, o1->len);
+ if (o1->len < o2->len)
+ return -1;
+ if (o1->len > o2->len)
+ return 1;
+ return memcmp(o1->data, o2->data, o1->len);
}
static int same_name(const char *n1, const char *n2)
@@ -1315,7 +1323,6 @@
if (clp == NULL)
return NULL;
- INIT_LIST_HEAD(&clp->cl_sessions);
ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
if (ret) {
spin_lock(&nn->client_lock);
@@ -1323,20 +1330,9 @@
spin_unlock(&nn->client_lock);
return NULL;
}
- idr_init(&clp->cl_stateids);
- atomic_set(&clp->cl_refcount, 0);
- clp->cl_cb_state = NFSD4_CB_UNKNOWN;
- INIT_LIST_HEAD(&clp->cl_idhash);
- INIT_LIST_HEAD(&clp->cl_openowners);
- INIT_LIST_HEAD(&clp->cl_delegations);
- INIT_LIST_HEAD(&clp->cl_lru);
- INIT_LIST_HEAD(&clp->cl_callbacks);
- INIT_LIST_HEAD(&clp->cl_revoked);
- spin_lock_init(&clp->cl_lock);
nfsd4_init_callback(&clp->cl_cb_null);
clp->cl_time = get_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
- rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
copy_verf(clp, verf);
rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
gen_confirm(clp);
@@ -1368,7 +1364,7 @@
static struct nfs4_client *
find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root)
{
- long long cmp;
+ int cmp;
struct rb_node *node = root->rb_node;
struct nfs4_client *clp;
@@ -2964,22 +2960,35 @@
return 0;
}
-static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
+static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag, struct nfs4_file *fp)
{
- struct nfs4_file *fp = dp->dl_file;
+ int status;
- if (!fp->fi_lease)
- return nfs4_setlease(dp, flag);
+ if (fp->fi_had_conflict)
+ return -EAGAIN;
+ get_nfs4_file(fp);
+ dp->dl_file = fp;
+ if (!fp->fi_lease) {
+ status = nfs4_setlease(dp, flag);
+ if (status)
+ goto out_free;
+ return 0;
+ }
spin_lock(&recall_lock);
if (fp->fi_had_conflict) {
spin_unlock(&recall_lock);
- return -EAGAIN;
+ status = -EAGAIN;
+ goto out_free;
}
atomic_inc(&fp->fi_delegees);
list_add(&dp->dl_perfile, &fp->fi_delegations);
spin_unlock(&recall_lock);
list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
return 0;
+out_free:
+ put_nfs4_file(fp);
+ dp->dl_file = fp;
+ return status;
}
static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
@@ -3045,7 +3054,7 @@
dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh, flag);
if (dp == NULL)
goto out_no_deleg;
- status = nfs4_set_delegation(dp, flag);
+ status = nfs4_set_delegation(dp, flag, stp->st_file);
if (status)
goto out_free;
@@ -3598,9 +3607,16 @@
static __be32
nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
{
- if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner)))
+ struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
+
+ if (check_for_locks(stp->st_file, lo))
return nfserr_locks_held;
- release_lock_stateid(stp);
+ /*
+ * Currently there's a 1-1 lock stateid<->lockowner
+ * correspondance, and we have to delete the lockowner when we
+ * delete the lock stateid:
+ */
+ release_lockowner(lo);
return nfs_ok;
}
@@ -4044,6 +4060,10 @@
if (!same_owner_str(&lo->lo_owner, owner, clid))
return false;
+ if (list_empty(&lo->lo_owner.so_stateids)) {
+ WARN_ON_ONCE(1);
+ return false;
+ }
lst = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
return lst->st_file->fi_inode == inode;
@@ -4958,7 +4978,6 @@
int i;
struct nfs4_client *clp = NULL;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- struct rb_node *node, *tmp;
for (i = 0; i < CLIENT_HASH_SIZE; i++) {
while (!list_empty(&nn->conf_id_hashtbl[i])) {
@@ -4967,13 +4986,11 @@
}
}
- node = rb_first(&nn->unconf_name_tree);
- while (node != NULL) {
- tmp = node;
- node = rb_next(tmp);
- clp = rb_entry(tmp, struct nfs4_client, cl_namenode);
- rb_erase(tmp, &nn->unconf_name_tree);
- destroy_client(clp);
+ for (i = 0; i < CLIENT_HASH_SIZE; i++) {
+ while (!list_empty(&nn->unconf_id_hashtbl[i])) {
+ clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
+ destroy_client(clp);
+ }
}
kfree(nn->sessionid_hashtbl);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 6cd86e0..acf179d 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -162,8 +162,8 @@
*/
memcpy(p, argp->p, avail);
/* step to next page */
- argp->p = page_address(argp->pagelist[0]);
argp->pagelist++;
+ argp->p = page_address(argp->pagelist[0]);
if (argp->pagelen < PAGE_SIZE) {
argp->end = argp->p + (argp->pagelen>>2);
argp->pagelen = 0;
@@ -553,7 +553,18 @@
READ_BUF(4);
READ32(create->cr_linklen);
READ_BUF(create->cr_linklen);
- SAVEMEM(create->cr_linkname, create->cr_linklen);
+ /*
+ * The VFS will want a null-terminated string, and
+ * null-terminating in place isn't safe since this might
+ * end on a page boundary:
+ */
+ create->cr_linkname =
+ kmalloc(create->cr_linklen + 1, GFP_KERNEL);
+ if (!create->cr_linkname)
+ return nfserr_jukebox;
+ memcpy(create->cr_linkname, p, create->cr_linklen);
+ create->cr_linkname[create->cr_linklen] = '\0';
+ defer_free(argp, kfree, create->cr_linkname);
break;
case NF4BLK:
case NF4CHR:
@@ -1732,6 +1743,9 @@
}
else
end++;
+ if (found_esc)
+ end = next;
+
str = end;
}
*pp = p;
@@ -2035,8 +2049,8 @@
err = vfs_getattr(&path, &stat);
if (err)
goto out_nfserr;
- if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
- FATTR4_WORD0_MAXNAME)) ||
+ if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+ FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
(bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
FATTR4_WORD1_SPACE_TOTAL))) {
err = vfs_statfs(&path, &statfs);
@@ -2401,6 +2415,8 @@
WRITE64(stat.ino);
}
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+ if ((buflen -= 16) < 0)
+ goto out_resource;
WRITE32(3);
WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
@@ -3382,6 +3398,9 @@
struct nfsd4_test_stateid_id *stateid, *next;
__be32 *p;
+ if (nfserr)
+ return nfserr;
+
RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
*p++ = htonl(test_stateid->ts_num_ids);
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index e76244e..e5e4675 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -221,13 +221,6 @@
hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits));
}
-static inline bool
-nfsd_cache_entry_expired(struct svc_cacherep *rp)
-{
- return rp->c_state != RC_INPROG &&
- time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
-}
-
/*
* Walk the LRU list and prune off entries that are older than RC_EXPIRE.
* Also prune the oldest ones when the total exceeds the max number of entries.
@@ -238,8 +231,14 @@
struct svc_cacherep *rp, *tmp;
list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
- if (!nfsd_cache_entry_expired(rp) &&
- num_drc_entries <= max_drc_entries)
+ /*
+ * Don't free entries attached to calls that are still
+ * in-progress, but do keep scanning the list.
+ */
+ if (rp->c_state == RC_INPROG)
+ continue;
+ if (num_drc_entries <= max_drc_entries &&
+ time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
break;
nfsd_reply_cache_free_locked(rp);
}
@@ -395,22 +394,8 @@
/*
* Since the common case is a cache miss followed by an insert,
- * preallocate an entry. First, try to reuse the first entry on the LRU
- * if it works, then go ahead and prune the LRU list.
+ * preallocate an entry.
*/
- spin_lock(&cache_lock);
- if (!list_empty(&lru_head)) {
- rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
- if (nfsd_cache_entry_expired(rp) ||
- num_drc_entries >= max_drc_entries) {
- lru_put_end(rp);
- prune_cache_entries();
- goto search_cache;
- }
- }
-
- /* No expired ones available, allocate a new one. */
- spin_unlock(&cache_lock);
rp = nfsd_reply_cache_alloc();
spin_lock(&cache_lock);
if (likely(rp)) {
@@ -418,7 +403,9 @@
drc_mem_usage += sizeof(*rp);
}
-search_cache:
+ /* go ahead and prune the cache */
+ prune_cache_entries();
+
found = nfsd_cache_search(rqstp, csum);
if (found) {
if (likely(rp))
@@ -432,15 +419,6 @@
goto out;
}
- /*
- * We're keeping the one we just allocated. Are we now over the
- * limit? Prune one off the tip of the LRU in trade for the one we
- * just allocated if so.
- */
- if (num_drc_entries >= max_drc_entries)
- nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
- struct svc_cacherep, c_lru));
-
nfsdstats.rcmisses++;
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7f55517..f34d9de 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -699,6 +699,11 @@
if (err != 0 || fd < 0)
return -EINVAL;
+ if (svc_alien_sock(net, fd)) {
+ printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__);
+ return -EINVAL;
+ }
+
err = nfsd_create_serv(net);
if (err != 0)
return err;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 262df5c..8016892 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -220,7 +220,8 @@
*/
ret = nfsd_racache_init(2*nrservs);
if (ret)
- return ret;
+ goto dec_users;
+
ret = nfs4_state_start();
if (ret)
goto out_racache;
@@ -228,6 +229,8 @@
out_racache:
nfsd_racache_shutdown();
+dec_users:
+ nfsd_users--;
return ret;
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 84ce601..81325ba 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -297,41 +297,12 @@
}
/*
- * Set various file attributes.
- * N.B. After this call fhp needs an fh_put
+ * Go over the attributes and take care of the small differences between
+ * NFS semantics and what Linux expects.
*/
-__be32
-nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
- int check_guard, time_t guardtime)
+static void
+nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
{
- struct dentry *dentry;
- struct inode *inode;
- int accmode = NFSD_MAY_SATTR;
- umode_t ftype = 0;
- __be32 err;
- int host_err;
- int size_change = 0;
-
- if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
- accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
- if (iap->ia_valid & ATTR_SIZE)
- ftype = S_IFREG;
-
- /* Get inode */
- err = fh_verify(rqstp, fhp, ftype, accmode);
- if (err)
- goto out;
-
- dentry = fhp->fh_dentry;
- inode = dentry->d_inode;
-
- /* Ignore any mode updates on symlinks */
- if (S_ISLNK(inode->i_mode))
- iap->ia_valid &= ~ATTR_MODE;
-
- if (!iap->ia_valid)
- goto out;
-
/*
* NFSv2 does not differentiate between "set-[ac]time-to-now"
* which only requires access, and "set-[ac]time-to-X" which
@@ -341,8 +312,7 @@
* convert to "set to now" instead of "set to explicit time"
*
* We only call inode_change_ok as the last test as technically
- * it is not an interface that we should be using. It is only
- * valid if the filesystem does not define it's own i_op->setattr.
+ * it is not an interface that we should be using.
*/
#define BOTH_TIME_SET (ATTR_ATIME_SET | ATTR_MTIME_SET)
#define MAX_TOUCH_TIME_ERROR (30*60)
@@ -368,30 +338,6 @@
iap->ia_valid &= ~BOTH_TIME_SET;
}
}
-
- /*
- * The size case is special.
- * It changes the file as well as the attributes.
- */
- if (iap->ia_valid & ATTR_SIZE) {
- if (iap->ia_size < inode->i_size) {
- err = nfsd_permission(rqstp, fhp->fh_export, dentry,
- NFSD_MAY_TRUNC|NFSD_MAY_OWNER_OVERRIDE);
- if (err)
- goto out;
- }
-
- host_err = get_write_access(inode);
- if (host_err)
- goto out_nfserr;
-
- size_change = 1;
- host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
- if (host_err) {
- put_write_access(inode);
- goto out_nfserr;
- }
- }
/* sanitize the mode change */
if (iap->ia_valid & ATTR_MODE) {
@@ -414,32 +360,120 @@
iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
}
}
+}
- /* Change the attributes. */
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ struct iattr *iap)
+{
+ struct inode *inode = fhp->fh_dentry->d_inode;
+ int host_err;
+
+ if (iap->ia_size < inode->i_size) {
+ __be32 err;
+
+ err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+ NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+ if (err)
+ return err;
+ }
+
+ host_err = get_write_access(inode);
+ if (host_err)
+ goto out_nfserrno;
+
+ host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+ if (host_err)
+ goto out_put_write_access;
+ return 0;
+
+out_put_write_access:
+ put_write_access(inode);
+out_nfserrno:
+ return nfserrno(host_err);
+}
+
+/*
+ * Set various file attributes. After this call fhp needs an fh_put.
+ */
+__be32
+nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
+ int check_guard, time_t guardtime)
+{
+ struct dentry *dentry;
+ struct inode *inode;
+ int accmode = NFSD_MAY_SATTR;
+ umode_t ftype = 0;
+ __be32 err;
+ int host_err;
+ bool get_write_count;
+ int size_change = 0;
+
+ if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+ accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
+ if (iap->ia_valid & ATTR_SIZE)
+ ftype = S_IFREG;
+
+ /* Callers that do fh_verify should do the fh_want_write: */
+ get_write_count = !fhp->fh_dentry;
+
+ /* Get inode */
+ err = fh_verify(rqstp, fhp, ftype, accmode);
+ if (err)
+ goto out;
+ if (get_write_count) {
+ host_err = fh_want_write(fhp);
+ if (host_err)
+ return nfserrno(host_err);
+ }
+
+ dentry = fhp->fh_dentry;
+ inode = dentry->d_inode;
+
+ /* Ignore any mode updates on symlinks */
+ if (S_ISLNK(inode->i_mode))
+ iap->ia_valid &= ~ATTR_MODE;
+
+ if (!iap->ia_valid)
+ goto out;
+
+ nfsd_sanitize_attrs(inode, iap);
+
+ /*
+ * The size case is special, it changes the file in addition to the
+ * attributes.
+ */
+ if (iap->ia_valid & ATTR_SIZE) {
+ err = nfsd_get_write_access(rqstp, fhp, iap);
+ if (err)
+ goto out;
+ size_change = 1;
+ }
iap->ia_valid |= ATTR_CTIME;
- err = nfserr_notsync;
- if (!check_guard || guardtime == inode->i_ctime.tv_sec) {
- host_err = nfsd_break_lease(inode);
- if (host_err)
- goto out_nfserr;
- fh_lock(fhp);
-
- host_err = notify_change(dentry, iap);
- err = nfserrno(host_err);
- fh_unlock(fhp);
+ if (check_guard && guardtime != inode->i_ctime.tv_sec) {
+ err = nfserr_notsync;
+ goto out_put_write_access;
}
+
+ host_err = nfsd_break_lease(inode);
+ if (host_err)
+ goto out_put_write_access_nfserror;
+
+ fh_lock(fhp);
+ host_err = notify_change(dentry, iap);
+ fh_unlock(fhp);
+
+out_put_write_access_nfserror:
+ err = nfserrno(host_err);
+out_put_write_access:
if (size_change)
put_write_access(inode);
if (!err)
commit_metadata(fhp);
out:
return err;
-
-out_nfserr:
- err = nfserrno(host_err);
- goto out;
}
#if defined(CONFIG_NFSD_V2_ACL) || \
@@ -474,6 +508,9 @@
char *buf = NULL;
int error = 0;
+ if (!pacl)
+ return vfs_setxattr(dentry, key, NULL, 0, 0);
+
buflen = posix_acl_xattr_size(pacl->a_count);
buf = kmalloc(buflen, GFP_KERNEL);
error = -ENOMEM;
@@ -802,9 +839,10 @@
flags = O_WRONLY|O_LARGEFILE;
}
*filp = dentry_open(&path, flags, current_cred());
- if (IS_ERR(*filp))
+ if (IS_ERR(*filp)) {
host_err = PTR_ERR(*filp);
- else {
+ *filp = NULL;
+ } else {
host_err = ima_file_check(*filp, may_flags);
if (may_flags & NFSD_MAY_64BIT_COOKIE)
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b2e3ff3..ecdbae1 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -31,6 +31,8 @@
#include "alloc.h"
#include "dat.h"
+static void __nilfs_btree_init(struct nilfs_bmap *bmap);
+
static struct nilfs_btree_path *nilfs_btree_alloc_path(void)
{
struct nilfs_btree_path *path;
@@ -368,6 +370,34 @@
return ret;
}
+/**
+ * nilfs_btree_root_broken - verify consistency of btree root node
+ * @node: btree root node to be examined
+ * @ino: inode number
+ *
+ * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ */
+static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+ unsigned long ino)
+{
+ int level, flags, nchildren;
+ int ret = 0;
+
+ level = nilfs_btree_node_get_level(node);
+ flags = nilfs_btree_node_get_flags(node);
+ nchildren = nilfs_btree_node_get_nchildren(node);
+
+ if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+ level > NILFS_BTREE_LEVEL_MAX ||
+ nchildren < 0 ||
+ nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
+ pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
+ ino, level, flags, nchildren);
+ ret = 1;
+ }
+ return ret;
+}
+
int nilfs_btree_broken_node_block(struct buffer_head *bh)
{
int ret;
@@ -1713,7 +1743,7 @@
/* convert and insert */
dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL;
- nilfs_btree_init(btree);
+ __nilfs_btree_init(btree);
if (nreq != NULL) {
nilfs_bmap_commit_alloc_ptr(btree, dreq, dat);
nilfs_bmap_commit_alloc_ptr(btree, nreq, dat);
@@ -2294,12 +2324,23 @@
.bop_gather_data = NULL,
};
-int nilfs_btree_init(struct nilfs_bmap *bmap)
+static void __nilfs_btree_init(struct nilfs_bmap *bmap)
{
bmap->b_ops = &nilfs_btree_ops;
bmap->b_nchildren_per_block =
NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap));
- return 0;
+}
+
+int nilfs_btree_init(struct nilfs_bmap *bmap)
+{
+ int ret = 0;
+
+ __nilfs_btree_init(bmap);
+
+ if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
+ bmap->b_inode->i_ino))
+ ret = -EIO;
+ return ret;
}
void nilfs_btree_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index bccfec8..587d699 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -24,6 +24,7 @@
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
+#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/aio.h>
#include "nilfs.h"
@@ -48,6 +49,8 @@
int for_gc;
};
+static int nilfs_iget_test(struct inode *inode, void *opaque);
+
void nilfs_inode_add_blocks(struct inode *inode, int n)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
@@ -219,10 +222,10 @@
static int nilfs_set_page_dirty(struct page *page)
{
+ struct inode *inode = page->mapping->host;
int ret = __set_page_dirty_nobuffers(page);
if (page_has_buffers(page)) {
- struct inode *inode = page->mapping->host;
unsigned nr_dirty = 0;
struct buffer_head *bh, *head;
@@ -245,6 +248,10 @@
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
+ } else if (ret) {
+ unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
@@ -342,6 +349,17 @@
.is_partially_uptodate = block_is_partially_uptodate,
};
+static int nilfs_insert_inode_locked(struct inode *inode,
+ struct nilfs_root *root,
+ unsigned long ino)
+{
+ struct nilfs_iget_args args = {
+ .ino = ino, .root = root, .cno = 0, .for_gc = 0
+ };
+
+ return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
+}
+
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
@@ -377,7 +395,7 @@
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
- goto failed_bmap;
+ goto failed_after_creation;
set_bit(NILFS_I_BMAP, &ii->i_state);
/* No lock is needed; iget() ensures it. */
@@ -393,21 +411,24 @@
spin_lock(&nilfs->ns_next_gen_lock);
inode->i_generation = nilfs->ns_next_generation++;
spin_unlock(&nilfs->ns_next_gen_lock);
- insert_inode_hash(inode);
+ if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
+ err = -EIO;
+ goto failed_after_creation;
+ }
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
- goto failed_acl; /* never occur. When supporting
+ goto failed_after_creation; /* never occur. When supporting
nilfs_init_acl(), proper cancellation of
above jobs should be considered */
return inode;
- failed_acl:
- failed_bmap:
+ failed_after_creation:
clear_nlink(inode);
+ unlock_new_inode(inode);
iput(inode); /* raw_inode will be deleted through
- generic_delete_inode() */
+ nilfs_evict_inode() */
goto failed;
failed_ifile_create_inode:
@@ -455,8 +476,8 @@
inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- if (inode->i_nlink == 0 && inode->i_mode == 0)
- return -EINVAL; /* this inode is deleted */
+ if (inode->i_nlink == 0)
+ return -ESTALE; /* this inode is deleted */
inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
ii->i_flags = le32_to_cpu(raw_inode->i_flags);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9de78f0..0f84b25 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -51,9 +51,11 @@
int err = nilfs_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
return 0;
}
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -182,6 +184,7 @@
out_fail:
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
+ unlock_new_inode(inode);
iput(inode);
goto out;
}
@@ -201,11 +204,15 @@
inode_inc_link_count(inode);
ihold(inode);
- err = nilfs_add_nondir(dentry, inode);
- if (!err)
+ err = nilfs_add_link(dentry, inode);
+ if (!err) {
+ d_instantiate(dentry, inode);
err = nilfs_transaction_commit(dir->i_sb);
- else
+ } else {
+ inode_dec_link_count(inode);
+ iput(inode);
nilfs_transaction_abort(dir->i_sb);
+ }
return err;
}
@@ -243,6 +250,7 @@
nilfs_mark_inode_dirty(inode);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
@@ -255,6 +263,7 @@
drop_nlink(inode);
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
+ unlock_new_inode(inode);
iput(inode);
out_dir:
drop_nlink(dir);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 9bc72de..b02c202 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -141,7 +141,6 @@
* @ti_save: Backup of journal_info field of task_struct
* @ti_flags: Flags
* @ti_count: Nest level
- * @ti_garbage: List of inode to be put when releasing semaphore
*/
struct nilfs_transaction_info {
u32 ti_magic;
@@ -150,7 +149,6 @@
one of other filesystems has a bug. */
unsigned short ti_flags;
unsigned short ti_count;
- struct list_head ti_garbage;
};
/* ti_magic */
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 0ba6798..da27664 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -94,6 +94,7 @@
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_checked(bh);
clear_buffer_nilfs_redirected(bh);
+ clear_buffer_async_write(bh);
clear_buffer_dirty(bh);
if (nilfs_page_buffers_clean(page))
__nilfs_clear_page_dirty(page);
@@ -429,6 +430,7 @@
"discard block %llu, size %zu",
(u64)bh->b_blocknr, bh->b_size);
}
+ clear_buffer_async_write(bh);
clear_buffer_dirty(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_checked(bh);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index dc9a913..2d8be51 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -345,8 +345,7 @@
if (err == -EOPNOTSUPP) {
set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
- bio_put(bio);
- /* to be detected by submit_seg_bio() */
+ /* to be detected by nilfs_segbuf_submit_bio() */
}
if (!uptodate)
@@ -377,12 +376,12 @@
bio->bi_private = segbuf;
bio_get(bio);
submit_bio(mode, bio);
+ segbuf->sb_nbio++;
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
bio_put(bio);
err = -EOPNOTSUPP;
goto failed;
}
- segbuf->sb_nbio++;
bio_put(bio);
wi->bio = NULL;
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a5752a58..99294a28 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -305,7 +305,6 @@
ti->ti_count = 0;
ti->ti_save = cur_ti;
ti->ti_magic = NILFS_TI_MAGIC;
- INIT_LIST_HEAD(&ti->ti_garbage);
current->journal_info = ti;
for (;;) {
@@ -332,8 +331,6 @@
up_write(&nilfs->ns_segctor_sem);
current->journal_info = ti->ti_save;
- if (!list_empty(&ti->ti_garbage))
- nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
}
static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -665,7 +662,7 @@
bh = head = page_buffers(page);
do {
- if (!buffer_dirty(bh))
+ if (!buffer_dirty(bh) || buffer_async_write(bh))
continue;
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers, listp);
@@ -699,7 +696,8 @@
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
- if (buffer_dirty(bh)) {
+ if (buffer_dirty(bh) &&
+ !buffer_async_write(bh)) {
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers,
listp);
@@ -745,6 +743,15 @@
}
}
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+ struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+ sc_iput_work);
+ struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+ nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
struct nilfs_root *root)
{
@@ -1439,17 +1446,19 @@
nilfs_clear_logs(&sci->sc_segbufs);
- err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
- if (unlikely(err))
- return err;
-
if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
sci->sc_freesegs,
sci->sc_nfreesegs,
NULL);
WARN_ON(err); /* do not happen */
+ sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
}
+
+ err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+ if (unlikely(err))
+ return err;
+
nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
sci->sc_stage = prev_stage;
}
@@ -1579,6 +1588,7 @@
list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
+ set_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page) {
lock_page(bd_page);
@@ -1592,6 +1602,7 @@
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ set_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
lock_page(bd_page);
@@ -1677,6 +1688,7 @@
list_for_each_entry(segbuf, logs, sb_list) {
list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
+ clear_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page)
end_page_writeback(bd_page);
@@ -1686,6 +1698,7 @@
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ clear_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
end_page_writeback(bd_page);
@@ -1755,6 +1768,7 @@
b_assoc_buffers) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
+ clear_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page)
end_page_writeback(bd_page);
@@ -1776,6 +1790,7 @@
b_assoc_buffers) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
+ clear_buffer_async_write(bh);
clear_buffer_delay(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_redirected(bh);
@@ -1890,8 +1905,9 @@
static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
struct the_nilfs *nilfs)
{
- struct nilfs_transaction_info *ti = current->journal_info;
struct nilfs_inode_info *ii, *n;
+ int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
+ int defer_iput = false;
spin_lock(&nilfs->ns_inode_lock);
list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
@@ -1902,9 +1918,24 @@
clear_bit(NILFS_I_BUSY, &ii->i_state);
brelse(ii->i_bh);
ii->i_bh = NULL;
- list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+ list_del_init(&ii->i_dirty);
+ if (!ii->vfs_inode.i_nlink || during_mount) {
+ /*
+ * Defer calling iput() to avoid deadlocks if
+ * i_nlink == 0 or mount is not yet finished.
+ */
+ list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+ defer_iput = true;
+ } else {
+ spin_unlock(&nilfs->ns_inode_lock);
+ iput(&ii->vfs_inode);
+ spin_lock(&nilfs->ns_inode_lock);
+ }
}
spin_unlock(&nilfs->ns_inode_lock);
+
+ if (defer_iput)
+ schedule_work(&sci->sc_iput_work);
}
/*
@@ -2571,6 +2602,8 @@
INIT_LIST_HEAD(&sci->sc_segbufs);
INIT_LIST_HEAD(&sci->sc_write_logs);
INIT_LIST_HEAD(&sci->sc_gc_inodes);
+ INIT_LIST_HEAD(&sci->sc_iput_queue);
+ INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
init_timer(&sci->sc_timer);
sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
@@ -2597,6 +2630,8 @@
ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
nilfs_transaction_unlock(sci->sc_super);
+ flush_work(&sci->sc_iput_work);
+
} while (ret && retrycount-- > 0);
}
@@ -2621,6 +2656,9 @@
|| sci->sc_seq_request != sci->sc_seq_done);
spin_unlock(&sci->sc_state_lock);
+ if (flush_work(&sci->sc_iput_work))
+ flag = true;
+
if (flag || !nilfs_segctor_confirm(sci))
nilfs_segctor_write_out(sci);
@@ -2630,6 +2668,12 @@
nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
}
+ if (!list_empty(&sci->sc_iput_queue)) {
+ nilfs_warning(sci->sc_super, __func__,
+ "iput queue is not empty\n");
+ nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+ }
+
WARN_ON(!list_empty(&sci->sc_segbufs));
WARN_ON(!list_empty(&sci->sc_write_logs));
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 38a1d00..a48d6de 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -26,6 +26,7 @@
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
+#include <linux/workqueue.h>
#include <linux/nilfs2_fs.h>
#include "nilfs.h"
@@ -92,6 +93,8 @@
* @sc_nblk_inc: Block count of current generation
* @sc_dirty_files: List of files to be written
* @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
* @sc_freesegs: array of segment numbers to be freed
* @sc_nfreesegs: number of segments on @sc_freesegs
* @sc_dsync_inode: inode whose data pages are written for a sync operation
@@ -135,6 +138,8 @@
struct list_head sc_dirty_files;
struct list_head sc_gc_inodes;
+ struct list_head sc_iput_queue;
+ struct work_struct sc_iput_work;
__u64 *sc_freesegs;
size_t sc_nfreesegs;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 6c80083..9be6b41 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -69,7 +69,7 @@
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- client_fd = get_unused_fd();
+ client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
if (client_fd < 0)
return client_fd;
@@ -122,6 +122,7 @@
metadata->event_len = FAN_EVENT_METADATA_LEN;
metadata->metadata_len = FAN_EVENT_METADATA_LEN;
metadata->vers = FANOTIFY_METADATA_VERSION;
+ metadata->reserved = 0;
metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
metadata->pid = pid_vnr(event->tgid);
if (unlikely(event->mask & FAN_Q_OVERFLOW))
@@ -866,9 +867,9 @@
{
return sys_fanotify_mark(fanotify_fd, flags,
#ifdef __BIG_ENDIAN
- ((__u64)mask1 << 32) | mask0,
-#else
((__u64)mask0 << 32) | mask1,
+#else
+ ((__u64)mask1 << 32) | mask0,
#endif
dfd, pathname);
}
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 238a593..9d7e2b9 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -42,7 +42,7 @@
{
struct {
struct file_handle handle;
- u8 pad[64];
+ u8 pad[MAX_HANDLE_SZ];
} f;
int size, ret, i;
@@ -50,7 +50,7 @@
size = f.handle.handle_bytes >> 2;
ret = exportfs_encode_inode_fh(inode, (struct fid *)f.handle.f_handle, &size, 0);
- if ((ret == 255) || (ret == -ENOSPC)) {
+ if ((ret == FILEID_INVALID) || (ret < 0)) {
WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
return 0;
}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 4bb21d6..a3153e2 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -63,14 +63,14 @@
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
- hlist_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
struct dentry *child;
/* run all of the children of the original inode and fix their
* d_flags to indicate parental interest (their parent is the
* original inode) */
spin_lock(&alias->d_lock);
- list_for_each_entry(child, &alias->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &alias->d_subdirs, d_child) {
if (!child->d_inode)
continue;
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 74825be..fbb9dfb 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -288,20 +288,25 @@
spin_unlock(&inode->i_lock);
/* In case the dropping of a reference would nuke next_i. */
- if ((&next_i->i_sb_list != list) &&
- atomic_read(&next_i->i_count)) {
+ while (&next_i->i_sb_list != list) {
spin_lock(&next_i->i_lock);
- if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+ if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
+ atomic_read(&next_i->i_count)) {
__iget(next_i);
need_iput = next_i;
+ spin_unlock(&next_i->i_lock);
+ break;
}
spin_unlock(&next_i->i_lock);
+ next_i = list_entry(next_i->i_sb_list.next,
+ struct inode, i_sb_list);
}
/*
- * We can safely drop inode_sb_list_lock here because we hold
- * references on both inode and next_i. Also no new inodes
- * will be added since the umount has begun.
+ * We can safely drop inode_sb_list_lock here because either
+ * we actually hold references on both inode and next_i or
+ * end of list. Also no new inodes will be added since the
+ * umount has begun.
*/
spin_unlock(&inode_sb_list_lock);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 20dfec7..f998c60 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -917,7 +917,7 @@
}
}
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
{
int i;
@@ -938,7 +938,11 @@
page_cache_release(wc->w_target_page);
}
ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+ ocfs2_unlock_pages(wc);
brelse(wc->w_di_bh);
kfree(wc);
}
@@ -2060,11 +2064,19 @@
di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
ocfs2_journal_dirty(handle, wc->w_di_bh);
+ /* unlock pages before dealloc since it needs acquiring j_trans_barrier
+ * lock, or it will cause a deadlock since journal commit threads holds
+ * this lock and will ask for the page lock when flushing the data.
+ * put it here to preserve the unlock order.
+ */
+ ocfs2_unlock_pages(wc);
+
ocfs2_commit_trans(osb, handle);
ocfs2_run_deallocs(osb, &wc->w_dealloc);
- ocfs2_free_write_ctxt(wc);
+ brelse(wc->w_di_bh);
+ kfree(wc);
return copied;
}
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 5d18ad1..4f66e00 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -90,7 +90,6 @@
* information for this bh as it's not marked locally
* uptodate. */
ret = -EIO;
- put_bh(bh);
mlog_errno(ret);
}
@@ -420,7 +419,6 @@
if (!buffer_uptodate(bh)) {
ret = -EIO;
- put_bh(bh);
mlog_errno(ret);
}
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index ef99972..ce37013 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -172,7 +172,7 @@
struct dentry *dentry;
spin_lock(&inode->i_lock);
- hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
trace_ocfs2_find_local_alias(dentry->d_name.len,
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 33ecbe0..2b94111 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -653,12 +653,9 @@
clear_bit(bit, res->refmap);
}
-
-void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+static void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
struct dlm_lock_resource *res)
{
- assert_spin_locked(&res->spinlock);
-
res->inflight_locks++;
mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
@@ -666,6 +663,13 @@
__builtin_return_address(0));
}
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+ struct dlm_lock_resource *res)
+{
+ assert_spin_locked(&res->spinlock);
+ __dlm_lockres_grab_inflight_ref(dlm, res);
+}
+
void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
struct dlm_lock_resource *res)
{
@@ -855,10 +859,8 @@
/* finally add the lockres to its hash bucket */
__dlm_insert_lockres(dlm, res);
- /* Grab inflight ref to pin the resource */
- spin_lock(&res->spinlock);
- dlm_lockres_grab_inflight_ref(dlm, res);
- spin_unlock(&res->spinlock);
+ /* since this lockres is new it doesn't not require the spinlock */
+ __dlm_lockres_grab_inflight_ref(dlm, res);
/* get an extra ref on the mle in case this is a BLOCK
* if so, the creator of the BLOCK may try to put the last
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index e68588e..9bd981c 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -540,7 +540,10 @@
/* success! see if any other nodes need recovery */
mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n",
dlm->name, dlm->reco.dead_node, dlm->node_num);
- dlm_reset_recovery(dlm);
+ spin_lock(&dlm->spinlock);
+ __dlm_reset_recovery(dlm);
+ dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+ spin_unlock(&dlm->spinlock);
}
dlm_end_recovery(dlm);
@@ -698,6 +701,14 @@
if (all_nodes_done) {
int ret;
+ /* Set this flag on recovery master to avoid
+ * a new recovery for another dead node start
+ * before the recovery is not done. That may
+ * cause recovery hung.*/
+ spin_lock(&dlm->spinlock);
+ dlm->reco.state |= DLM_RECO_STATE_FINALIZE;
+ spin_unlock(&dlm->spinlock);
+
/* all nodes are now in DLM_RECO_NODE_DATA_DONE state
* just send a finalize message to everyone and
* clean up */
@@ -1751,13 +1762,13 @@
struct dlm_migratable_lockres *mres)
{
struct dlm_migratable_lock *ml;
- struct list_head *queue;
+ struct list_head *queue, *iter;
struct list_head *tmpq = NULL;
struct dlm_lock *newlock = NULL;
struct dlm_lockstatus *lksb = NULL;
int ret = 0;
int i, j, bad;
- struct dlm_lock *lock = NULL;
+ struct dlm_lock *lock;
u8 from = O2NM_MAX_NODES;
unsigned int added = 0;
__be64 c;
@@ -1792,14 +1803,16 @@
/* MIGRATION ONLY! */
BUG_ON(!(mres->flags & DLM_MRES_MIGRATION));
+ lock = NULL;
spin_lock(&res->spinlock);
for (j = DLM_GRANTED_LIST; j <= DLM_BLOCKED_LIST; j++) {
tmpq = dlm_list_idx_to_ptr(res, j);
- list_for_each_entry(lock, tmpq, list) {
- if (lock->ml.cookie != ml->cookie)
- lock = NULL;
- else
+ list_for_each(iter, tmpq) {
+ lock = list_entry(iter,
+ struct dlm_lock, list);
+ if (lock->ml.cookie == ml->cookie)
break;
+ lock = NULL;
}
if (lock)
break;
@@ -2867,8 +2880,8 @@
BUG();
}
dlm->reco.state &= ~DLM_RECO_STATE_FINALIZE;
+ __dlm_reset_recovery(dlm);
spin_unlock(&dlm->spinlock);
- dlm_reset_recovery(dlm);
dlm_kick_recovery_thread(dlm);
break;
default:
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 2487116..8460647 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -781,7 +781,6 @@
cpos = map_start >> osb->s_clustersize_bits;
mapping_end = ocfs2_clusters_for_bytes(inode->i_sb,
map_start + map_len);
- mapping_end -= cpos;
is_last = 0;
while (cpos < mapping_end && !is_last) {
u32 fe_flags;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ff54014..d0e8c0b 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2372,10 +2372,14 @@
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
+ if (unlikely(written <= 0))
+ goto no_sync;
+
if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
((file->f_flags & O_DIRECT) && !direct_io)) {
- ret = filemap_fdatawrite_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawrite_range(file->f_mapping,
+ iocb->ki_pos - written,
+ iocb->ki_pos - 1);
if (ret < 0)
written = ret;
@@ -2388,10 +2392,12 @@
}
if (!ret)
- ret = filemap_fdatawait_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawait_range(file->f_mapping,
+ iocb->ki_pos - written,
+ iocb->ki_pos - 1);
}
+no_sync:
/*
* deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
* function pointer which is called when o_direct io completes so that
@@ -2453,12 +2459,14 @@
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
struct splice_desc sd = {
- .total_len = len,
.flags = flags,
- .pos = *ppos,
.u.file = out,
};
-
+ ret = generic_write_checks(out, ppos, &len, 0);
+ if(ret)
+ return ret;
+ sd.total_len = len;
+ sd.pos = *ppos;
trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 332a281..e49b4f1 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@
*/
if (status < 0)
mlog_errno(status);
+ /*
+ * Clear dq_off so that we search for the structure in quota file next
+ * time we acquire it. The structure might be deleted and reallocated
+ * elsewhere by another node while our dquot structure is on freelist.
+ */
+ dquot->dq_off = 0;
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_trans:
ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@
status = ocfs2_lock_global_qf(info, 1);
if (status < 0)
goto out;
- if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
- status = ocfs2_qinfo_lock(info, 0);
- if (status < 0)
- goto out_dq;
- status = qtree_read_dquot(&info->dqi_gi, dquot);
- ocfs2_qinfo_unlock(info, 0);
- if (status < 0)
- goto out_dq;
- }
- set_bit(DQ_READ_B, &dquot->dq_flags);
+ status = ocfs2_qinfo_lock(info, 0);
+ if (status < 0)
+ goto out_dq;
+ /*
+ * We always want to read dquot structure from disk because we don't
+ * know what happened with it while it was on freelist.
+ */
+ status = qtree_read_dquot(&info->dqi_gi, dquot);
+ ocfs2_qinfo_unlock(info, 0);
+ if (status < 0)
+ goto out_dq;
OCFS2_DQUOT(dquot)->dq_use_count++;
OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 27fe7ee..d0f323d 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@
ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
out:
- /* Clear the read bit so that next time someone uses this
- * dquot he reads fresh info from disk and allocates local
- * dquot structure */
- clear_bit(DQ_READ_B, &dquot->dq_flags);
return status;
}
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 2e3ea30..5b8d944 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -6499,6 +6499,16 @@
}
new_oi = OCFS2_I(args->new_inode);
+ /*
+ * Adjust extent record count to reserve space for extended attribute.
+ * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+ */
+ if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+ !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
+ struct ocfs2_extent_list *el = &new_di->id2.i_list;
+ le16_add_cpu(&el->l_count, -(inline_size /
+ sizeof(struct ocfs2_extent_rec)));
+ }
spin_lock(&new_oi->ip_lock);
new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);
diff --git a/fs/open.c b/fs/open.c
index 8c74100..86092bd 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -628,23 +628,12 @@
static inline int __get_file_write_access(struct inode *inode,
struct vfsmount *mnt)
{
- int error;
- error = get_write_access(inode);
+ int error = get_write_access(inode);
if (error)
return error;
- /*
- * Do not take mount writer counts on
- * special files since no writes to
- * the mount itself will occur.
- */
- if (!special_file(inode->i_mode)) {
- /*
- * Balanced in __fput()
- */
- error = __mnt_want_write(mnt);
- if (error)
- put_write_access(inode);
- }
+ error = __mnt_want_write(mnt);
+ if (error)
+ put_write_access(inode);
return error;
}
@@ -677,12 +666,11 @@
path_get(&f->f_path);
inode = f->f_inode = f->f_path.dentry->d_inode;
- if (f->f_mode & FMODE_WRITE) {
+ if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
error = __get_file_write_access(inode, f->f_path.mnt);
if (error)
goto cleanup_file;
- if (!special_file(inode->i_mode))
- file_take_write(f);
+ file_take_write(f);
}
f->f_mapping = inode->i_mapping;
@@ -723,7 +711,6 @@
fops_put(f->f_op);
file_sb_list_del(f);
if (f->f_mode & FMODE_WRITE) {
- put_write_access(inode);
if (!special_file(inode->i_mode)) {
/*
* We don't consider this a real
@@ -731,6 +718,7 @@
* because it all happenend right
* here, so just reset the state.
*/
+ put_write_access(inode);
file_reset_write(f);
__mnt_drop_write(f->f_path.mnt);
}
diff --git a/fs/pipe.c b/fs/pipe.c
index d2c45e1..0e0752e 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -726,11 +726,25 @@
return mask;
}
+static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe)
+{
+ int kill = 0;
+
+ spin_lock(&inode->i_lock);
+ if (!--pipe->files) {
+ inode->i_pipe = NULL;
+ kill = 1;
+ }
+ spin_unlock(&inode->i_lock);
+
+ if (kill)
+ free_pipe_info(pipe);
+}
+
static int
pipe_release(struct inode *inode, struct file *file)
{
- struct pipe_inode_info *pipe = inode->i_pipe;
- int kill = 0;
+ struct pipe_inode_info *pipe = file->private_data;
__pipe_lock(pipe);
if (file->f_mode & FMODE_READ)
@@ -743,17 +757,9 @@
kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT);
}
- spin_lock(&inode->i_lock);
- if (!--pipe->files) {
- inode->i_pipe = NULL;
- kill = 1;
- }
- spin_unlock(&inode->i_lock);
__pipe_unlock(pipe);
- if (kill)
- free_pipe_info(pipe);
-
+ put_pipe_info(inode, pipe);
return 0;
}
@@ -1014,7 +1020,6 @@
{
struct pipe_inode_info *pipe;
bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC;
- int kill = 0;
int ret;
filp->f_version = 0;
@@ -1130,15 +1135,9 @@
goto err;
err:
- spin_lock(&inode->i_lock);
- if (!--pipe->files) {
- inode->i_pipe = NULL;
- kill = 1;
- }
- spin_unlock(&inode->i_lock);
__pipe_unlock(pipe);
- if (kill)
- free_pipe_info(pipe);
+
+ put_pipe_info(inode, pipe);
return ret;
}
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 8bd2135..3542f1f 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -158,6 +158,12 @@
umode_t mode = 0;
int not_equiv = 0;
+ /*
+ * A null ACL can always be presented as mode bits.
+ */
+ if (!acl)
+ return 0;
+
FOREACH_ACL_ENTRY(pa, acl, pe) {
switch (pa->e_tag) {
case ACL_USER_OBJ:
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index ab30716..239493e 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -27,6 +27,5 @@
proc-$(CONFIG_NET) += proc_net.o
proc-$(CONFIG_PROC_KCORE) += kcore.o
proc-$(CONFIG_PROC_VMCORE) += vmcore.o
-proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o
proc-$(CONFIG_PRINTK) += kmsg.o
proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cbd0f1b..09f0d9c 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -304,15 +304,11 @@
seq_puts(m, header);
CAP_FOR_EACH_U32(__capi) {
seq_printf(m, "%08x",
- a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+ a->cap[CAP_LAST_U32 - __capi]);
}
seq_putc(m, '\n');
}
-/* Remove non-existent capabilities */
-#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \
- CAP_TO_MASK(CAP_LAST_CAP + 1) - 1)
-
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
const struct cred *cred;
@@ -326,11 +322,6 @@
cap_bset = cred->cap_bset;
rcu_read_unlock();
- NORM_CAPS(cap_inheritable);
- NORM_CAPS(cap_permitted);
- NORM_CAPS(cap_effective);
- NORM_CAPS(cap_bset);
-
render_cap_t(m, "CapInh:\t", &cap_inheritable);
render_cap_t(m, "CapPrm:\t", &cap_permitted);
render_cap_t(m, "CapEff:\t", &cap_effective);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c3834da..8fc784a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1825,6 +1825,7 @@
if (rc)
goto out_mmput;
+ rc = -ENOENT;
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
@@ -2611,6 +2612,57 @@
.llseek = seq_lseek,
.release = proc_id_map_release,
};
+
+static int proc_setgroups_open(struct inode *inode, struct file *file)
+{
+ struct user_namespace *ns = NULL;
+ struct task_struct *task;
+ int ret;
+
+ ret = -ESRCH;
+ task = get_proc_task(inode);
+ if (task) {
+ rcu_read_lock();
+ ns = get_user_ns(task_cred_xxx(task, user_ns));
+ rcu_read_unlock();
+ put_task_struct(task);
+ }
+ if (!ns)
+ goto err;
+
+ if (file->f_mode & FMODE_WRITE) {
+ ret = -EACCES;
+ if (!ns_capable(ns, CAP_SYS_ADMIN))
+ goto err_put_ns;
+ }
+
+ ret = single_open(file, &proc_setgroups_show, ns);
+ if (ret)
+ goto err_put_ns;
+
+ return 0;
+err_put_ns:
+ put_user_ns(ns);
+err:
+ return ret;
+}
+
+static int proc_setgroups_release(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq = file->private_data;
+ struct user_namespace *ns = seq->private;
+ int ret = single_release(inode, file);
+ put_user_ns(ns);
+ return ret;
+}
+
+static const struct file_operations proc_setgroups_operations = {
+ .open = proc_setgroups_open,
+ .write = proc_setgroups_write,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = proc_setgroups_release,
+};
#endif /* CONFIG_USER_NS */
static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
@@ -2719,6 +2771,7 @@
REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations),
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+ REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
#endif
#ifdef CONFIG_CHECKPOINT_RESTORE
REG("timers", S_IRUGO, proc_timers_operations),
@@ -3072,6 +3125,7 @@
REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations),
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
+ REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
#endif
};
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a2596af..846b1d7 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -19,7 +19,6 @@
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/idr.h>
-#include <linux/namei.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
@@ -163,17 +162,6 @@
spin_unlock_irqrestore(&proc_inum_lock, flags);
}
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- nd_set_link(nd, __PDE_DATA(dentry->d_inode));
- return NULL;
-}
-
-static const struct inode_operations proc_link_inode_operations = {
- .readlink = generic_readlink,
- .follow_link = proc_follow_link,
-};
-
/*
* As some entries in /proc are volatile, we want to
* get rid of unused dentries. This could be made
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 073aea60..843b8ef 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -23,6 +23,7 @@
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/magic.h>
+#include <linux/namei.h>
#include <asm/uaccess.h>
@@ -373,6 +374,26 @@
};
#endif
+static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct proc_dir_entry *pde = PDE(dentry->d_inode);
+ if (unlikely(!use_pde(pde)))
+ return ERR_PTR(-EINVAL);
+ nd_set_link(nd, pde->data);
+ return pde;
+}
+
+static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+ unuse_pde(p);
+}
+
+const struct inode_operations proc_link_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = proc_follow_link,
+ .put_link = proc_put_link,
+};
+
struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
{
struct inode *inode = new_inode_pseudo(sb);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index d600fb0..e833df4 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -202,6 +202,7 @@
int closing;
struct completion *c;
};
+extern const struct inode_operations proc_link_inode_operations;
extern const struct inode_operations proc_pid_link_inode_operations;
@@ -211,13 +212,6 @@
extern void proc_entry_rundown(struct proc_dir_entry *);
/*
- * proc_devtree.c
- */
-#ifdef CONFIG_PROC_DEVICETREE
-extern void proc_device_tree_init(void);
-#endif
-
-/*
* proc_namespaces.c
*/
extern const struct inode_operations proc_ns_dir_inode_operations;
diff --git a/fs/proc/page.c b/fs/proc/page.c
index b8730d9..2a8cc94 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,7 +121,7 @@
* just checks PG_head/PG_tail, so we need to check PageLRU to make
* sure a given page is a thp, not a non-huge compound page.
*/
- else if (PageTransCompound(page) && PageLRU(compound_trans_head(page)))
+ else if (PageTransCompound(page) && PageLRU(compound_head(page)))
u |= 1 << KPF_THP;
/*
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
deleted file mode 100644
index 106a835..0000000
--- a/fs/proc/proc_devtree.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * proc_devtree.c - handles /proc/device-tree
- *
- * Copyright 1997 Paul Mackerras
- */
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/printk.h>
-#include <linux/stat.h>
-#include <linux/string.h>
-#include <linux/of.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <asm/prom.h>
-#include <asm/uaccess.h>
-#include "internal.h"
-
-static inline void set_node_proc_entry(struct device_node *np,
- struct proc_dir_entry *de)
-{
-#ifdef HAVE_ARCH_DEVTREE_FIXUPS
- np->pde = de;
-#endif
-}
-
-static struct proc_dir_entry *proc_device_tree;
-
-/*
- * Supply data on a read from /proc/device-tree/node/property.
- */
-static int property_proc_show(struct seq_file *m, void *v)
-{
- struct property *pp = m->private;
-
- seq_write(m, pp->value, pp->length);
- return 0;
-}
-
-static int property_proc_open(struct inode *inode, struct file *file)
-{
- return single_open(file, property_proc_show, __PDE_DATA(inode));
-}
-
-static const struct file_operations property_proc_fops = {
- .owner = THIS_MODULE,
- .open = property_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-/*
- * For a node with a name like "gc@10", we make symlinks called "gc"
- * and "@10" to it.
- */
-
-/*
- * Add a property to a node
- */
-static struct proc_dir_entry *
-__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp,
- const char *name)
-{
- struct proc_dir_entry *ent;
-
- /*
- * Unfortunately proc_register puts each new entry
- * at the beginning of the list. So we rearrange them.
- */
- ent = proc_create_data(name,
- strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR,
- de, &property_proc_fops, pp);
- if (ent == NULL)
- return NULL;
-
- if (!strncmp(name, "security-", 9))
- ent->size = 0; /* don't leak number of password chars */
- else
- ent->size = pp->length;
-
- return ent;
-}
-
-
-void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop)
-{
- __proc_device_tree_add_prop(pde, prop, prop->name);
-}
-
-void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
- struct property *prop)
-{
- remove_proc_entry(prop->name, pde);
-}
-
-void proc_device_tree_update_prop(struct proc_dir_entry *pde,
- struct property *newprop,
- struct property *oldprop)
-{
- struct proc_dir_entry *ent;
-
- if (!oldprop) {
- proc_device_tree_add_prop(pde, newprop);
- return;
- }
-
- for (ent = pde->subdir; ent != NULL; ent = ent->next)
- if (ent->data == oldprop)
- break;
- if (ent == NULL) {
- pr_warn("device-tree: property \"%s\" does not exist\n",
- oldprop->name);
- } else {
- ent->data = newprop;
- ent->size = newprop->length;
- }
-}
-
-/*
- * Various dodgy firmware might give us nodes and/or properties with
- * conflicting names. That's generally ok, except for exporting via /proc,
- * so munge names here to ensure they're unique.
- */
-
-static int duplicate_name(struct proc_dir_entry *de, const char *name)
-{
- struct proc_dir_entry *ent;
- int found = 0;
-
- spin_lock(&proc_subdir_lock);
-
- for (ent = de->subdir; ent != NULL; ent = ent->next) {
- if (strcmp(ent->name, name) == 0) {
- found = 1;
- break;
- }
- }
-
- spin_unlock(&proc_subdir_lock);
-
- return found;
-}
-
-static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de,
- const char *name)
-{
- char *fixed_name;
- int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */
- int i = 1, size;
-
-realloc:
- fixed_name = kmalloc(fixup_len, GFP_KERNEL);
- if (fixed_name == NULL) {
- pr_err("device-tree: Out of memory trying to fixup "
- "name \"%s\"\n", name);
- return name;
- }
-
-retry:
- size = snprintf(fixed_name, fixup_len, "%s#%d", name, i);
- size++; /* account for NULL */
-
- if (size > fixup_len) {
- /* We ran out of space, free and reallocate. */
- kfree(fixed_name);
- fixup_len = size;
- goto realloc;
- }
-
- if (duplicate_name(de, fixed_name)) {
- /* Multiple duplicates. Retry with a different offset. */
- i++;
- goto retry;
- }
-
- pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
- np->full_name, fixed_name);
-
- return fixed_name;
-}
-
-/*
- * Process a node, adding entries for its children and its properties.
- */
-void proc_device_tree_add_node(struct device_node *np,
- struct proc_dir_entry *de)
-{
- struct property *pp;
- struct proc_dir_entry *ent;
- struct device_node *child;
- const char *p;
-
- set_node_proc_entry(np, de);
- for (child = NULL; (child = of_get_next_child(np, child));) {
- /* Use everything after the last slash, or the full name */
- p = kbasename(child->full_name);
-
- if (duplicate_name(de, p))
- p = fixup_name(np, de, p);
-
- ent = proc_mkdir(p, de);
- if (ent == NULL)
- break;
- proc_device_tree_add_node(child, ent);
- }
- of_node_put(child);
-
- for (pp = np->properties; pp != NULL; pp = pp->next) {
- p = pp->name;
-
- if (strchr(p, '/'))
- continue;
-
- if (duplicate_name(de, p))
- p = fixup_name(np, de, p);
-
- ent = __proc_device_tree_add_prop(de, pp, p);
- if (ent == NULL)
- break;
- }
-}
-
-/*
- * Called on initialization to set up the /proc/device-tree subtree
- */
-void __init proc_device_tree_init(void)
-{
- struct device_node *root;
-
- proc_device_tree = proc_mkdir("device-tree", NULL);
- if (proc_device_tree == NULL)
- return;
- root = of_find_node_by_path("/");
- if (root == NULL) {
- pr_debug("/proc/device-tree: can't find root\n");
- return;
- }
- proc_device_tree_add_node(root, proc_device_tree);
- of_node_put(root);
-}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 41a6ea9..9459710 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -110,7 +110,8 @@
ns = task_active_pid_ns(current);
options = data;
- if (!current_user_ns()->may_mount_proc)
+ if (!current_user_ns()->may_mount_proc ||
+ !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
}
@@ -179,9 +180,6 @@
proc_mkdir("openprom", NULL);
#endif
proc_tty_init();
-#ifdef CONFIG_PROC_DEVICETREE
- proc_device_tree_init();
-#endif
proc_mkdir("bus", NULL);
proc_sys_init();
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3e636d8..9f285fb 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -792,14 +792,14 @@
} pagemap_entry_t;
struct pagemapread {
- int pos, len;
+ int pos, len; /* units: PM_ENTRY_BYTES, not bytes */
pagemap_entry_t *buffer;
};
#define PAGEMAP_WALK_SIZE (PMD_SIZE)
#define PAGEMAP_WALK_MASK (PMD_MASK)
-#define PM_ENTRY_BYTES sizeof(u64)
+#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
#define PM_STATUS_BITS 3
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
@@ -1038,8 +1038,8 @@
if (!count)
goto out_task;
- pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
- pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+ pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+ pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
ret = -ENOMEM;
if (!pm.buffer)
goto out_task;
@@ -1110,9 +1110,19 @@
return ret;
}
+static int pagemap_open(struct inode *inode, struct file *file)
+{
+ /* do not disclose physical addresses to unprivileged
+ userspace (closes a rowhammer attack vector) */
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ return 0;
+}
+
const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
+ .open = pagemap_open,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index e4bcb2c..66c8c2f 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -178,6 +178,8 @@
if (p->psi->erase)
p->psi->erase(p->type, p->id, p->count,
dentry->d_inode->i_ctime, p->psi);
+ else
+ return -EPERM;
return simple_unlink(dir, dentry);
}
@@ -316,10 +318,10 @@
sprintf(name, "dmesg-%s-%lld", psname, id);
break;
case PSTORE_TYPE_CONSOLE:
- sprintf(name, "console-%s", psname);
+ sprintf(name, "console-%s-%lld", psname, id);
break;
case PSTORE_TYPE_FTRACE:
- sprintf(name, "ftrace-%s", psname);
+ sprintf(name, "ftrace-%s-%lld", psname, id);
break;
case PSTORE_TYPE_MCE:
sprintf(name, "mce-%s-%lld", psname, id);
@@ -334,9 +336,8 @@
mutex_lock(&root->d_inode->i_mutex);
- rc = -ENOSPC;
dentry = d_alloc_name(root, name);
- if (IS_ERR(dentry))
+ if (!dentry)
goto fail_lockedalloc;
memcpy(private->data, data, size);
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 1376e5a..d3d3714 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -61,6 +61,11 @@
MODULE_PARM_DESC(mem_size,
"size of reserved RAM used to store oops/panic logs");
+static unsigned int mem_type;
+module_param(mem_type, uint, 0600);
+MODULE_PARM_DESC(mem_type,
+ "set to 1 to try to use unbuffered memory (default 0)");
+
static int dump_oops = 1;
module_param(dump_oops, int, 0600);
MODULE_PARM_DESC(dump_oops,
@@ -79,6 +84,7 @@
struct persistent_ram_zone *fprz;
phys_addr_t phys_addr;
unsigned long size;
+ unsigned int memtype;
size_t record_size;
size_t console_size;
size_t ftrace_size;
@@ -86,6 +92,7 @@
struct persistent_ram_ecc_info ecc_info;
unsigned int max_dump_cnt;
unsigned int dump_write_cnt;
+ /* _read_cnt need clear on ramoops_pstore_open */
unsigned int dump_read_cnt;
unsigned int console_read_cnt;
unsigned int ftrace_read_cnt;
@@ -101,6 +108,7 @@
cxt->dump_read_cnt = 0;
cxt->console_read_cnt = 0;
+ cxt->ftrace_read_cnt = 0;
return 0;
}
@@ -117,13 +125,15 @@
return NULL;
prz = przs[i];
+ if (!prz)
+ return NULL;
- if (update) {
- /* Update old/shadowed buffer. */
+ /* Update old/shadowed buffer. */
+ if (update)
persistent_ram_save_old(prz);
- if (!persistent_ram_old_size(prz))
- return NULL;
- }
+
+ if (!persistent_ram_old_size(prz))
+ return NULL;
*typep = type;
*id = i;
@@ -331,7 +341,8 @@
size_t sz = cxt->record_size;
cxt->przs[i] = persistent_ram_new(*paddr, sz, 0,
- &cxt->ecc_info);
+ &cxt->ecc_info,
+ cxt->memtype);
if (IS_ERR(cxt->przs[i])) {
err = PTR_ERR(cxt->przs[i]);
dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n",
@@ -361,7 +372,7 @@
return -ENOMEM;
}
- *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info);
+ *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype);
if (IS_ERR(*prz)) {
int err = PTR_ERR(*prz);
@@ -408,9 +419,9 @@
if (!is_power_of_2(pdata->ftrace_size))
pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
- cxt->dump_read_cnt = 0;
cxt->size = pdata->mem_size;
cxt->phys_addr = pdata->mem_address;
+ cxt->memtype = pdata->mem_type;
cxt->record_size = pdata->record_size;
cxt->console_size = pdata->console_size;
cxt->ftrace_size = pdata->ftrace_size;
@@ -541,6 +552,7 @@
dummy_data->mem_size = mem_size;
dummy_data->mem_address = mem_address;
+ dummy_data->mem_type = 0;
dummy_data->record_size = record_size;
dummy_data->console_size = ramoops_console_size;
dummy_data->ftrace_size = ramoops_ftrace_size;
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index 5933732..bda61a7 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -46,7 +46,7 @@
}
/* increase and wrap the start pointer, returning the old value */
-static inline size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a)
+static size_t buffer_start_add_atomic(struct persistent_ram_zone *prz, size_t a)
{
int old;
int new;
@@ -62,7 +62,7 @@
}
/* increase the size counter until it hits the max size */
-static inline void buffer_size_add(struct persistent_ram_zone *prz, size_t a)
+static void buffer_size_add_atomic(struct persistent_ram_zone *prz, size_t a)
{
size_t old;
size_t new;
@@ -78,6 +78,53 @@
} while (atomic_cmpxchg(&prz->buffer->size, old, new) != old);
}
+static DEFINE_RAW_SPINLOCK(buffer_lock);
+
+/* increase and wrap the start pointer, returning the old value */
+static size_t buffer_start_add_locked(struct persistent_ram_zone *prz, size_t a)
+{
+ int old;
+ int new;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&buffer_lock, flags);
+
+ old = atomic_read(&prz->buffer->start);
+ new = old + a;
+ while (unlikely(new > prz->buffer_size))
+ new -= prz->buffer_size;
+ atomic_set(&prz->buffer->start, new);
+
+ raw_spin_unlock_irqrestore(&buffer_lock, flags);
+
+ return old;
+}
+
+/* increase the size counter until it hits the max size */
+static void buffer_size_add_locked(struct persistent_ram_zone *prz, size_t a)
+{
+ size_t old;
+ size_t new;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&buffer_lock, flags);
+
+ old = atomic_read(&prz->buffer->size);
+ if (old == prz->buffer_size)
+ goto exit;
+
+ new = old + a;
+ if (new > prz->buffer_size)
+ new = prz->buffer_size;
+ atomic_set(&prz->buffer->size, new);
+
+exit:
+ raw_spin_unlock_irqrestore(&buffer_lock, flags);
+}
+
+static size_t (*buffer_start_add)(struct persistent_ram_zone *, size_t) = buffer_start_add_atomic;
+static void (*buffer_size_add)(struct persistent_ram_zone *, size_t) = buffer_size_add_atomic;
+
static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz,
uint8_t *data, size_t len, uint8_t *ecc)
{
@@ -333,7 +380,8 @@
persistent_ram_update_header_ecc(prz);
}
-static void *persistent_ram_vmap(phys_addr_t start, size_t size)
+static void *persistent_ram_vmap(phys_addr_t start, size_t size,
+ unsigned int memtype)
{
struct page **pages;
phys_addr_t page_start;
@@ -345,7 +393,10 @@
page_start = start - offset_in_page(start);
page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE);
- prot = pgprot_noncached(PAGE_KERNEL);
+ if (memtype)
+ prot = pgprot_noncached(PAGE_KERNEL);
+ else
+ prot = pgprot_writecombine(PAGE_KERNEL);
pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL);
if (!pages) {
@@ -364,27 +415,38 @@
return vaddr;
}
-static void *persistent_ram_iomap(phys_addr_t start, size_t size)
+static void *persistent_ram_iomap(phys_addr_t start, size_t size,
+ unsigned int memtype)
{
+ void *va;
+
if (!request_mem_region(start, size, "persistent_ram")) {
pr_err("request mem region (0x%llx@0x%llx) failed\n",
(unsigned long long)size, (unsigned long long)start);
return NULL;
}
- return ioremap(start, size);
+ buffer_start_add = buffer_start_add_locked;
+ buffer_size_add = buffer_size_add_locked;
+
+ if (memtype)
+ va = ioremap(start, size);
+ else
+ va = ioremap_wc(start, size);
+
+ return va;
}
static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
- struct persistent_ram_zone *prz)
+ struct persistent_ram_zone *prz, int memtype)
{
prz->paddr = start;
prz->size = size;
if (pfn_valid(start >> PAGE_SHIFT))
- prz->vaddr = persistent_ram_vmap(start, size);
+ prz->vaddr = persistent_ram_vmap(start, size, memtype);
else
- prz->vaddr = persistent_ram_iomap(start, size);
+ prz->vaddr = persistent_ram_iomap(start, size, memtype);
if (!prz->vaddr) {
pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__,
@@ -452,7 +514,8 @@
}
struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
- u32 sig, struct persistent_ram_ecc_info *ecc_info)
+ u32 sig, struct persistent_ram_ecc_info *ecc_info,
+ unsigned int memtype)
{
struct persistent_ram_zone *prz;
int ret = -ENOMEM;
@@ -463,7 +526,7 @@
goto err;
}
- ret = persistent_ram_buffer_map(start, size, prz);
+ ret = persistent_ram_buffer_map(start, size, prz, memtype);
if (ret)
goto err;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 3e64169..4f7f451 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@
dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
- ret = fn(dquot, priv);
- if (ret < 0)
- goto out;
+ /*
+ * ->release_dquot() can be racing with us. Our reference
+ * protects us from new calls to it so just wait for any
+ * outstanding call and recheck the DQ_ACTIVE_B after that.
+ */
+ wait_on_dquot(dquot);
+ if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ ret = fn(dquot, priv);
+ if (ret < 0)
+ goto out;
+ }
spin_lock(&dq_list_lock);
/* We are safe to continue now because our dquot could not
* be moved out of the inuse list while we hold the reference */
@@ -629,7 +637,7 @@
dqstats_inc(DQST_LOOKUPS);
err = sb->dq_op->write_dquot(dquot);
if (!ret && err)
- err = ret;
+ ret = err;
dqput(dquot);
spin_lock(&dq_list_lock);
}
@@ -1094,6 +1102,14 @@
dquot->dq_dqb.dqb_rsvspace -= number;
}
+static void dquot_reclaim_reserved_space(struct dquot *dquot, qsize_t number)
+{
+ if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
+ number = dquot->dq_dqb.dqb_curspace;
+ dquot->dq_dqb.dqb_rsvspace += number;
+ dquot->dq_dqb.dqb_curspace -= number;
+}
+
static inline
void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
{
@@ -1528,6 +1544,15 @@
}
EXPORT_SYMBOL(inode_claim_rsv_space);
+void inode_reclaim_rsv_space(struct inode *inode, qsize_t number)
+{
+ spin_lock(&inode->i_lock);
+ *inode_reserved_space(inode) += number;
+ __inode_sub_bytes(inode, number);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(inode_reclaim_rsv_space);
+
void inode_sub_rsv_space(struct inode *inode, qsize_t number)
{
spin_lock(&inode->i_lock);
@@ -1702,6 +1727,35 @@
EXPORT_SYMBOL(dquot_claim_space_nodirty);
/*
+ * Convert allocated space back to in-memory reserved quotas
+ */
+void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
+{
+ int cnt;
+
+ if (!dquot_active(inode)) {
+ inode_reclaim_rsv_space(inode, number);
+ return;
+ }
+
+ down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ spin_lock(&dq_data_lock);
+ /* Claim reserved quotas to allocated quotas */
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+ if (inode->i_dquot[cnt])
+ dquot_reclaim_reserved_space(inode->i_dquot[cnt],
+ number);
+ }
+ /* Update inode bytes */
+ inode_reclaim_rsv_space(inode, number);
+ spin_unlock(&dq_data_lock);
+ mark_all_dquot_dirty(inode->i_dquot);
+ up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ return;
+}
+EXPORT_SYMBOL(dquot_reclaim_space_nodirty);
+
+/*
* This operation can block, but only after everything is updated
*/
void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
diff --git a/fs/read_write.c b/fs/read_write.c
index 2cefa41..f6b7c60 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -947,9 +947,9 @@
return ret;
}
-COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen)
+ compat_ulong_t, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
@@ -983,9 +983,9 @@
return ret;
}
-COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen, u32, pos_low, u32, pos_high)
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return compat_sys_preadv64(fd, vec, vlen, pos);
@@ -1013,9 +1013,9 @@
return ret;
}
-COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
const struct compat_iovec __user *, vec,
- unsigned long, vlen)
+ compat_ulong_t, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
@@ -1049,9 +1049,9 @@
return ret;
}
-COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen, u32, pos_low, u32, pos_high)
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return compat_sys_pwritev64(fd, vec, vlen, pos);
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index 6c2d136..2b96b59 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -128,6 +128,7 @@
char *d_name;
off_t d_off;
ino_t d_ino;
+ loff_t cur_pos = deh_offset(deh);
if (!de_visible(deh))
/* it is hidden entry */
@@ -200,8 +201,9 @@
if (local_buf != small_buf) {
kfree(local_buf);
}
- // next entry should be looked for with such offset
- next_pos = deh_offset(deh) + 1;
+
+ /* deh_offset(deh) may be invalid now. */
+ next_pos = cur_pos + 1;
if (item_moved(&tmp_ih, &path_to_entry)) {
set_cpu_key_k_offset(&pos_key,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index f844533..36166443 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3211,8 +3211,14 @@
attr->ia_size != i_size_read(inode)) {
error = inode_newsize_ok(inode, attr->ia_size);
if (!error) {
+ /*
+ * Could race against reiserfs_file_release
+ * if called from NFS, so take tailpack mutex.
+ */
+ mutex_lock(&REISERFS_I(inode)->tailpack);
truncate_setsize(inode, attr->ia_size);
- reiserfs_vfs_truncate_file(inode);
+ reiserfs_truncate_file(inode, 1);
+ mutex_unlock(&REISERFS_I(inode)->tailpack);
}
}
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 33532f7..1d48974 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -19,12 +19,13 @@
/*
* LOCKING:
*
- * We rely on new Alexander Viro's super-block locking.
+ * These guys are evicted from procfs as the very first step in ->kill_sb().
*
*/
-static int show_version(struct seq_file *m, struct super_block *sb)
+static int show_version(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
char *format;
if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
@@ -66,8 +67,9 @@
#define DJP( x ) le32_to_cpu( jp -> x )
#define JF( x ) ( r -> s_journal -> x )
-static int show_super(struct seq_file *m, struct super_block *sb)
+static int show_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "state: \t%s\n"
@@ -128,8 +130,9 @@
return 0;
}
-static int show_per_level(struct seq_file *m, struct super_block *sb)
+static int show_per_level(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
int level;
@@ -186,8 +189,9 @@
return 0;
}
-static int show_bitmap(struct seq_file *m, struct super_block *sb)
+static int show_bitmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "free_block: %lu\n"
@@ -218,8 +222,9 @@
return 0;
}
-static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+static int show_on_disk_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
int hash_code = DFL(s_hash_function_code);
@@ -261,8 +266,9 @@
return 0;
}
-static int show_oidmap(struct seq_file *m, struct super_block *sb)
+static int show_oidmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
@@ -291,8 +297,9 @@
return 0;
}
-static int show_journal(struct seq_file *m, struct super_block *sb)
+static int show_journal(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
struct reiserfs_super_block *rs = r->s_rs;
struct journal_params *jp = &rs->s_v1.s_journal;
@@ -383,92 +390,24 @@
return 0;
}
-/* iterator */
-static int test_sb(struct super_block *sb, void *data)
-{
- return data == sb;
-}
-
-static int set_sb(struct super_block *sb, void *data)
-{
- return -ENOENT;
-}
-
-struct reiserfs_seq_private {
- struct super_block *sb;
- int (*show) (struct seq_file *, struct super_block *);
-};
-
-static void *r_start(struct seq_file *m, loff_t * pos)
-{
- struct reiserfs_seq_private *priv = m->private;
- loff_t l = *pos;
-
- if (l)
- return NULL;
-
- if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb)))
- return NULL;
-
- up_write(&priv->sb->s_umount);
- return priv->sb;
-}
-
-static void *r_next(struct seq_file *m, void *v, loff_t * pos)
-{
- ++*pos;
- if (v)
- deactivate_super(v);
- return NULL;
-}
-
-static void r_stop(struct seq_file *m, void *v)
-{
- if (v)
- deactivate_super(v);
-}
-
-static int r_show(struct seq_file *m, void *v)
-{
- struct reiserfs_seq_private *priv = m->private;
- return priv->show(m, v);
-}
-
-static const struct seq_operations r_ops = {
- .start = r_start,
- .next = r_next,
- .stop = r_stop,
- .show = r_show,
-};
-
static int r_open(struct inode *inode, struct file *file)
{
- struct reiserfs_seq_private *priv;
- int ret = seq_open_private(file, &r_ops,
- sizeof(struct reiserfs_seq_private));
-
- if (!ret) {
- struct seq_file *m = file->private_data;
- priv = m->private;
- priv->sb = proc_get_parent_data(inode);
- priv->show = PDE_DATA(inode);
- }
- return ret;
+ return single_open(file, PDE_DATA(inode),
+ proc_get_parent_data(inode));
}
static const struct file_operations r_file_operations = {
.open = r_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
- .owner = THIS_MODULE,
+ .release = single_release,
};
static struct proc_dir_entry *proc_info_root = NULL;
static const char proc_info_root_name[] = "fs/reiserfs";
static void add_file(struct super_block *sb, char *name,
- int (*func) (struct seq_file *, struct super_block *))
+ int (*func) (struct seq_file *, void *))
{
proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
&r_file_operations, func);
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 157e474..635a142 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -1954,8 +1954,6 @@
#define MAX_US_INT 0xffff
// reiserfs version 2 has max offset 60 bits. Version 1 - 32 bit offset
-#define U32_MAX (~(__u32)0)
-
static inline loff_t max_reiserfs_offset(struct inode *inode)
{
if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5)
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index f8a23c3..e2e202a 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -499,6 +499,7 @@
static void reiserfs_kill_sb(struct super_block *s)
{
if (REISERFS_SB(s)) {
+ reiserfs_proc_info_done(s);
/*
* Force any pending inode evictions to occur now. Any
* inodes to be removed that have extended attributes
@@ -554,8 +555,6 @@
REISERFS_SB(s)->reserved_blocks);
}
- reiserfs_proc_info_done(s);
-
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
kfree(s->s_fs_info);
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 774c1eb..3dd44db 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -328,6 +328,8 @@
m->read_pos = offset;
retval = file->f_pos = offset;
}
+ } else {
+ file->f_pos = offset;
}
}
file->f_version = m->version;
diff --git a/fs/splice.c b/fs/splice.c
index d37431d..f183f13 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -555,6 +555,24 @@
.get = generic_pipe_buf_get,
};
+static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+/* Pipe buffer operations for a socket and similar. */
+const struct pipe_buf_operations nosteal_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = generic_pipe_buf_map,
+ .unmap = generic_pipe_buf_unmap,
+ .confirm = generic_pipe_buf_confirm,
+ .release = generic_pipe_buf_release,
+ .steal = generic_pipe_buf_nosteal,
+ .get = generic_pipe_buf_get,
+};
+EXPORT_SYMBOL(nosteal_pipe_buf_ops);
+
static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
unsigned long vlen, loff_t offset)
{
@@ -994,13 +1012,17 @@
struct address_space *mapping = out->f_mapping;
struct inode *inode = mapping->host;
struct splice_desc sd = {
- .total_len = len,
.flags = flags,
- .pos = *ppos,
.u.file = out,
};
ssize_t ret;
+ ret = generic_write_checks(out, ppos, &len, S_ISBLK(inode->i_mode));
+ if (ret)
+ return ret;
+ sd.total_len = len;
+ sd.pos = *ppos;
+
pipe_lock(pipe);
splice_from_pipe_begin(&sd);
diff --git a/fs/stat.c b/fs/stat.c
index 04ce1ac..d0ea7ef 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -447,9 +447,8 @@
EXPORT_SYMBOL(inode_add_bytes);
-void inode_sub_bytes(struct inode *inode, loff_t bytes)
+void __inode_sub_bytes(struct inode *inode, loff_t bytes)
{
- spin_lock(&inode->i_lock);
inode->i_blocks -= bytes >> 9;
bytes &= 511;
if (inode->i_bytes < bytes) {
@@ -457,6 +456,14 @@
inode->i_bytes += 512;
}
inode->i_bytes -= bytes;
+}
+
+EXPORT_SYMBOL(__inode_sub_bytes);
+
+void inode_sub_bytes(struct inode *inode, loff_t bytes)
+{
+ spin_lock(&inode->i_lock);
+ __inode_sub_bytes(inode, bytes);
spin_unlock(&inode->i_lock);
}
diff --git a/fs/statfs.c b/fs/statfs.c
index c219e733..083dc0a 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -94,7 +94,7 @@
int fd_statfs(int fd, struct kstatfs *st)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_raw(fd);
int error = -EBADF;
if (f.file) {
error = vfs_statfs(&f.file->f_path, st);
diff --git a/fs/super.c b/fs/super.c
index 7465d43..e028b50 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -76,6 +76,8 @@
total_objects = sb->s_nr_dentry_unused +
sb->s_nr_inodes_unused + fs_objects + 1;
+ if (!total_objects)
+ total_objects = 1;
if (sc->nr_to_scan) {
int dentries;
@@ -336,19 +338,19 @@
* and want to turn it into a full-blown active reference. grab_super()
* is called with sb_lock held and drops it. Returns 1 in case of
* success, 0 if we had failed (superblock contents was already dead or
- * dying when grab_super() had been called).
+ * dying when grab_super() had been called). Note that this is only
+ * called for superblocks not in rundown mode (== ones still on ->fs_supers
+ * of their type), so increment of ->s_count is OK here.
*/
static int grab_super(struct super_block *s) __releases(sb_lock)
{
- if (atomic_inc_not_zero(&s->s_active)) {
- spin_unlock(&sb_lock);
- return 1;
- }
- /* it's going away */
s->s_count++;
spin_unlock(&sb_lock);
- /* wait for it to die */
down_write(&s->s_umount);
+ if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) {
+ put_super(s);
+ return 1;
+ }
up_write(&s->s_umount);
put_super(s);
return 0;
@@ -463,11 +465,6 @@
destroy_super(s);
s = NULL;
}
- down_write(&old->s_umount);
- if (unlikely(!(old->s_flags & MS_BORN))) {
- deactivate_locked_super(old);
- goto retry;
- }
return old;
}
}
@@ -660,10 +657,10 @@
if (hlist_unhashed(&sb->s_instances))
continue;
if (sb->s_bdev == bdev) {
- if (grab_super(sb)) /* drops sb_lock */
- return sb;
- else
+ if (!grab_super(sb))
goto restart;
+ up_write(&sb->s_umount);
+ return sb;
}
}
spin_unlock(&sb_lock);
diff --git a/fs/sysv/super.c b/fs/sysv/super.c
index d0c6a00..eda1095 100644
--- a/fs/sysv/super.c
+++ b/fs/sysv/super.c
@@ -487,6 +487,7 @@
sbi->s_sb = sb;
sbi->s_block_base = 0;
sbi->s_type = FSTYPE_V7;
+ mutex_init(&sbi->s_lock);
sb->s_fs_info = sbi;
sb_set_blocksize(sb, 512);
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index ff822934..26b69b2 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -166,15 +166,10 @@
err = ubifs_orphan_end_commit(c);
if (err)
goto out;
- old_ltail_lnum = c->ltail_lnum;
- err = ubifs_log_end_commit(c, new_ltail_lnum);
- if (err)
- goto out;
err = dbg_check_old_index(c, &zroot);
if (err)
goto out;
- mutex_lock(&c->mst_mutex);
c->mst_node->cmt_no = cpu_to_le64(c->cmt_no);
c->mst_node->log_lnum = cpu_to_le32(new_ltail_lnum);
c->mst_node->root_lnum = cpu_to_le32(zroot.lnum);
@@ -203,8 +198,9 @@
c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS);
else
c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_NO_ORPHS);
- err = ubifs_write_master(c);
- mutex_unlock(&c->mst_mutex);
+
+ old_ltail_lnum = c->ltail_lnum;
+ err = ubifs_log_end_commit(c, new_ltail_lnum);
if (err)
goto out;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 1437453..881324c 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1524,8 +1524,7 @@
}
wait_for_stable_page(page);
- unlock_page(page);
- return 0;
+ return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c
index 36bd4ef..06649d2 100644
--- a/fs/ubifs/log.c
+++ b/fs/ubifs/log.c
@@ -106,10 +106,14 @@
h = (long long)c->lhead_lnum * c->leb_size + c->lhead_offs;
t = (long long)c->ltail_lnum * c->leb_size;
- if (h >= t)
+ if (h > t)
return c->log_bytes - h + t;
- else
+ else if (h != t)
return t - h;
+ else if (c->lhead_lnum != c->ltail_lnum)
+ return 0;
+ else
+ return c->log_bytes;
}
/**
@@ -447,9 +451,9 @@
* @ltail_lnum: new log tail LEB number
*
* This function is called on when the commit operation was finished. It
- * moves log tail to new position and unmaps LEBs which contain obsolete data.
- * Returns zero in case of success and a negative error code in case of
- * failure.
+ * moves log tail to new position and updates the master node so that it stores
+ * the new log tail LEB number. Returns zero in case of success and a negative
+ * error code in case of failure.
*/
int ubifs_log_end_commit(struct ubifs_info *c, int ltail_lnum)
{
@@ -477,7 +481,12 @@
spin_unlock(&c->buds_lock);
err = dbg_check_bud_bytes(c);
+ if (err)
+ goto out;
+ err = ubifs_write_master(c);
+
+out:
mutex_unlock(&c->log_mutex);
return err;
}
diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c
index ab83ace..1a4bb9e 100644
--- a/fs/ubifs/master.c
+++ b/fs/ubifs/master.c
@@ -352,10 +352,9 @@
* ubifs_write_master - write master node.
* @c: UBIFS file-system description object
*
- * This function writes the master node. The caller has to take the
- * @c->mst_mutex lock before calling this function. Returns zero in case of
- * success and a negative error code in case of failure. The master node is
- * written twice to enable recovery.
+ * This function writes the master node. Returns zero in case of success and a
+ * negative error code in case of failure. The master node is written twice to
+ * enable recovery.
*/
int ubifs_write_master(struct ubifs_info *c)
{
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 9e1d056..e0a7a76 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@
freed = ubifs_destroy_tnc_subtree(znode);
atomic_long_sub(freed, &ubifs_clean_zn_cnt);
atomic_long_sub(freed, &c->clean_zn_cnt);
- ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
total_freed += freed;
znode = zprev;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index f21acf0..05115d7 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1412,7 +1412,7 @@
ubifs_msg("mounted UBI device %d, volume %d, name \"%s\"%s",
c->vi.ubi_num, c->vi.vol_id, c->vi.name,
- c->ro_mount ? ", R/O mode" : NULL);
+ c->ro_mount ? ", R/O mode" : "");
x = (long long)c->main_lebs * c->leb_size;
y = (long long)c->log_lebs * c->leb_size + c->max_bud_bytes;
ubifs_msg("LEB size: %d bytes (%d KiB), min./max. I/O unit sizes: %d bytes/%d bytes",
@@ -1970,7 +1970,6 @@
mutex_init(&c->lp_mutex);
mutex_init(&c->tnc_mutex);
mutex_init(&c->log_mutex);
- mutex_init(&c->mst_mutex);
mutex_init(&c->umount_mutex);
mutex_init(&c->bu_mutex);
mutex_init(&c->write_reserve_mutex);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index b2babce..bd51277 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -1042,7 +1042,6 @@
*
* @mst_node: master node
* @mst_offs: offset of valid master node
- * @mst_mutex: protects the master node area, @mst_node, and @mst_offs
*
* @max_bu_buf_len: maximum bulk-read buffer length
* @bu_mutex: protects the pre-allocated bulk-read buffer and @c->bu
@@ -1282,7 +1281,6 @@
struct ubifs_mst_node *mst_node;
int mst_offs;
- struct mutex mst_mutex;
int max_bu_buf_len;
struct mutex bu_mutex;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index b6d15d3..aa02328 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1270,13 +1270,22 @@
return 0;
}
+/*
+ * Maximum length of linked list formed by ICB hierarchy. The chosen number is
+ * arbitrary - just that we hopefully don't limit any real use of rewritten
+ * inode on write-once media but avoid looping for too long on corrupted media.
+ */
+#define UDF_MAX_ICB_NESTING 1024
+
static void __udf_read_inode(struct inode *inode)
{
struct buffer_head *bh = NULL;
struct fileEntry *fe;
uint16_t ident;
struct udf_inode_info *iinfo = UDF_I(inode);
+ unsigned int indirections = 0;
+reread:
/*
* Set defaults, but the inode is still incomplete!
* Note: get_new_inode() sets the following on a new inode:
@@ -1313,28 +1322,26 @@
ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
&ident);
if (ident == TAG_IDENT_IE && ibh) {
- struct buffer_head *nbh = NULL;
struct kernel_lb_addr loc;
struct indirectEntry *ie;
ie = (struct indirectEntry *)ibh->b_data;
loc = lelb_to_cpu(ie->indirectICB.extLocation);
- if (ie->indirectICB.extLength &&
- (nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
- &ident))) {
- if (ident == TAG_IDENT_FE ||
- ident == TAG_IDENT_EFE) {
- memcpy(&iinfo->i_location,
- &loc,
- sizeof(struct kernel_lb_addr));
- brelse(bh);
- brelse(ibh);
- brelse(nbh);
- __udf_read_inode(inode);
+ if (ie->indirectICB.extLength) {
+ brelse(bh);
+ brelse(ibh);
+ memcpy(&iinfo->i_location, &loc,
+ sizeof(struct kernel_lb_addr));
+ if (++indirections > UDF_MAX_ICB_NESTING) {
+ udf_err(inode->i_sb,
+ "too many ICBs in ICB hierarchy"
+ " (max %d supported)\n",
+ UDF_MAX_ICB_NESTING);
+ make_bad_inode(inode);
return;
}
- brelse(nbh);
+ goto reread;
}
}
brelse(ibh);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 9ac4057..839a2ba 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -630,6 +630,12 @@
struct udf_sb_info *sbi = UDF_SB(sb);
int error = 0;
+ if (sbi->s_lvid_bh) {
+ int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
+ if (write_rev > UDF_MAX_WRITE_VERSION && !(*flags & MS_RDONLY))
+ return -EACCES;
+ }
+
uopt.flags = sbi->s_flags;
uopt.uid = sbi->s_uid;
uopt.gid = sbi->s_gid;
@@ -649,12 +655,6 @@
sbi->s_dmode = uopt.dmode;
write_unlock(&sbi->s_cred_lock);
- if (sbi->s_lvid_bh) {
- int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
- if (write_rev > UDF_MAX_WRITE_VERSION)
- *flags |= MS_RDONLY;
- }
-
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
goto out_unlock;
@@ -843,27 +843,38 @@
return 1;
}
+/*
+ * Load primary Volume Descriptor Sequence
+ *
+ * Return <0 on error, 0 on success. -EAGAIN is special meaning next sequence
+ * should be tried.
+ */
static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
{
struct primaryVolDesc *pvoldesc;
struct ustr *instr, *outstr;
struct buffer_head *bh;
uint16_t ident;
- int ret = 1;
+ int ret = -ENOMEM;
instr = kmalloc(sizeof(struct ustr), GFP_NOFS);
if (!instr)
- return 1;
+ return -ENOMEM;
outstr = kmalloc(sizeof(struct ustr), GFP_NOFS);
if (!outstr)
goto out1;
bh = udf_read_tagged(sb, block, block, &ident);
- if (!bh)
+ if (!bh) {
+ ret = -EAGAIN;
goto out2;
+ }
- BUG_ON(ident != TAG_IDENT_PVD);
+ if (ident != TAG_IDENT_PVD) {
+ ret = -EIO;
+ goto out_bh;
+ }
pvoldesc = (struct primaryVolDesc *)bh->b_data;
@@ -889,8 +900,9 @@
if (udf_CS0toUTF8(outstr, instr))
udf_debug("volSetIdent[] = '%s'\n", outstr->u_name);
- brelse(bh);
ret = 0;
+out_bh:
+ brelse(bh);
out2:
kfree(outstr);
out1:
@@ -947,7 +959,7 @@
if (mdata->s_mirror_fe == NULL) {
udf_err(sb, "Both metadata and mirror metadata inode efe can not found\n");
- goto error_exit;
+ return -EIO;
}
}
@@ -964,23 +976,18 @@
addr.logicalBlockNum, addr.partitionReferenceNum);
mdata->s_bitmap_fe = udf_iget(sb, &addr);
-
if (mdata->s_bitmap_fe == NULL) {
if (sb->s_flags & MS_RDONLY)
udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n");
else {
udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n");
- goto error_exit;
+ return -EIO;
}
}
}
udf_debug("udf_load_metadata_files Ok\n");
-
return 0;
-
-error_exit:
- return 1;
}
static void udf_load_fileset(struct super_block *sb, struct buffer_head *bh,
@@ -1069,7 +1076,7 @@
if (!map->s_uspace.s_table) {
udf_debug("cannot load unallocSpaceTable (part %d)\n",
p_index);
- return 1;
+ return -EIO;
}
map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_TABLE;
udf_debug("unallocSpaceTable (part %d) @ %ld\n",
@@ -1079,7 +1086,7 @@
if (phd->unallocSpaceBitmap.extLength) {
struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index);
if (!bitmap)
- return 1;
+ return -ENOMEM;
map->s_uspace.s_bitmap = bitmap;
bitmap->s_extPosition = le32_to_cpu(
phd->unallocSpaceBitmap.extPosition);
@@ -1102,7 +1109,7 @@
if (!map->s_fspace.s_table) {
udf_debug("cannot load freedSpaceTable (part %d)\n",
p_index);
- return 1;
+ return -EIO;
}
map->s_partition_flags |= UDF_PART_FLAG_FREED_TABLE;
@@ -1113,7 +1120,7 @@
if (phd->freedSpaceBitmap.extLength) {
struct udf_bitmap *bitmap = udf_sb_alloc_bitmap(sb, p_index);
if (!bitmap)
- return 1;
+ return -ENOMEM;
map->s_fspace.s_bitmap = bitmap;
bitmap->s_extPosition = le32_to_cpu(
phd->freedSpaceBitmap.extPosition);
@@ -1165,7 +1172,7 @@
udf_find_vat_block(sb, p_index, type1_index, blocks - 1);
}
if (!sbi->s_vat_inode)
- return 1;
+ return -EIO;
if (map->s_partition_type == UDF_VIRTUAL_MAP15) {
map->s_type_specific.s_virtual.s_start_offset = 0;
@@ -1177,7 +1184,7 @@
pos = udf_block_map(sbi->s_vat_inode, 0);
bh = sb_bread(sb, pos);
if (!bh)
- return 1;
+ return -EIO;
vat20 = (struct virtualAllocationTable20 *)bh->b_data;
} else {
vat20 = (struct virtualAllocationTable20 *)
@@ -1195,6 +1202,12 @@
return 0;
}
+/*
+ * Load partition descriptor block
+ *
+ * Returns <0 on error, 0 on success, -EAGAIN is special - try next descriptor
+ * sequence.
+ */
static int udf_load_partdesc(struct super_block *sb, sector_t block)
{
struct buffer_head *bh;
@@ -1204,13 +1217,15 @@
int i, type1_idx;
uint16_t partitionNumber;
uint16_t ident;
- int ret = 0;
+ int ret;
bh = udf_read_tagged(sb, block, block, &ident);
if (!bh)
- return 1;
- if (ident != TAG_IDENT_PD)
+ return -EAGAIN;
+ if (ident != TAG_IDENT_PD) {
+ ret = 0;
goto out_bh;
+ }
p = (struct partitionDesc *)bh->b_data;
partitionNumber = le16_to_cpu(p->partitionNumber);
@@ -1229,10 +1244,13 @@
if (i >= sbi->s_partitions) {
udf_debug("Partition (%d) not found in partition map\n",
partitionNumber);
+ ret = 0;
goto out_bh;
}
ret = udf_fill_partdesc_info(sb, p, i);
+ if (ret < 0)
+ goto out_bh;
/*
* Now rescan for VIRTUAL or METADATA partitions when SPARABLE and
@@ -1249,32 +1267,37 @@
break;
}
- if (i >= sbi->s_partitions)
+ if (i >= sbi->s_partitions) {
+ ret = 0;
goto out_bh;
+ }
ret = udf_fill_partdesc_info(sb, p, i);
- if (ret)
+ if (ret < 0)
goto out_bh;
if (map->s_partition_type == UDF_METADATA_MAP25) {
ret = udf_load_metadata_files(sb, i);
- if (ret) {
+ if (ret < 0) {
udf_err(sb, "error loading MetaData partition map %d\n",
i);
goto out_bh;
}
} else {
- ret = udf_load_vat(sb, i, type1_idx);
- if (ret)
- goto out_bh;
/*
- * Mark filesystem read-only if we have a partition with
- * virtual map since we don't handle writing to it (we
- * overwrite blocks instead of relocating them).
+ * If we have a partition with virtual map, we don't handle
+ * writing to it (we overwrite blocks instead of relocating
+ * them).
*/
- sb->s_flags |= MS_RDONLY;
- pr_notice("Filesystem marked read-only because writing to pseudooverwrite partition is not implemented\n");
+ if (!(sb->s_flags & MS_RDONLY)) {
+ ret = -EACCES;
+ goto out_bh;
+ }
+ ret = udf_load_vat(sb, i, type1_idx);
+ if (ret < 0)
+ goto out_bh;
}
+ ret = 0;
out_bh:
/* In case loading failed, we handle cleanup in udf_fill_super */
brelse(bh);
@@ -1340,11 +1363,11 @@
uint16_t ident;
struct buffer_head *bh;
unsigned int table_len;
- int ret = 0;
+ int ret;
bh = udf_read_tagged(sb, block, block, &ident);
if (!bh)
- return 1;
+ return -EAGAIN;
BUG_ON(ident != TAG_IDENT_LVD);
lvd = (struct logicalVolDesc *)bh->b_data;
table_len = le32_to_cpu(lvd->mapTableLength);
@@ -1352,7 +1375,7 @@
udf_err(sb, "error loading logical volume descriptor: "
"Partition table too long (%u > %lu)\n", table_len,
sb->s_blocksize - sizeof(*lvd));
- ret = 1;
+ ret = -EIO;
goto out_bh;
}
@@ -1396,11 +1419,10 @@
} else if (!strncmp(upm2->partIdent.ident,
UDF_ID_SPARABLE,
strlen(UDF_ID_SPARABLE))) {
- if (udf_load_sparable_map(sb, map,
- (struct sparablePartitionMap *)gpm) < 0) {
- ret = 1;
+ ret = udf_load_sparable_map(sb, map,
+ (struct sparablePartitionMap *)gpm);
+ if (ret < 0)
goto out_bh;
- }
} else if (!strncmp(upm2->partIdent.ident,
UDF_ID_METADATA,
strlen(UDF_ID_METADATA))) {
@@ -1465,7 +1487,7 @@
}
if (lvd->integritySeqExt.extLength)
udf_load_logicalvolint(sb, leea_to_cpu(lvd->integritySeqExt));
-
+ ret = 0;
out_bh:
brelse(bh);
return ret;
@@ -1503,22 +1525,18 @@
}
/*
- * udf_process_sequence
+ * Process a main/reserve volume descriptor sequence.
+ * @block First block of first extent of the sequence.
+ * @lastblock Lastblock of first extent of the sequence.
+ * @fileset There we store extent containing root fileset
*
- * PURPOSE
- * Process a main/reserve volume descriptor sequence.
- *
- * PRE-CONDITIONS
- * sb Pointer to _locked_ superblock.
- * block First block of first extent of the sequence.
- * lastblock Lastblock of first extent of the sequence.
- *
- * HISTORY
- * July 1, 1997 - Andrew E. Mileski
- * Written, tested, and released.
+ * Returns <0 on error, 0 on success. -EAGAIN is special - try next descriptor
+ * sequence
*/
-static noinline int udf_process_sequence(struct super_block *sb, long block,
- long lastblock, struct kernel_lb_addr *fileset)
+static noinline int udf_process_sequence(
+ struct super_block *sb,
+ sector_t block, sector_t lastblock,
+ struct kernel_lb_addr *fileset)
{
struct buffer_head *bh = NULL;
struct udf_vds_record vds[VDS_POS_LENGTH];
@@ -1529,6 +1547,7 @@
uint32_t vdsn;
uint16_t ident;
long next_s = 0, next_e = 0;
+ int ret;
memset(vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH);
@@ -1543,7 +1562,7 @@
udf_err(sb,
"Block %llu of volume descriptor sequence is corrupted or we could not read it\n",
(unsigned long long)block);
- return 1;
+ return -EAGAIN;
}
/* Process each descriptor (ISO 13346 3/8.3-8.4) */
@@ -1616,14 +1635,19 @@
*/
if (!vds[VDS_POS_PRIMARY_VOL_DESC].block) {
udf_err(sb, "Primary Volume Descriptor not found!\n");
- return 1;
+ return -EAGAIN;
}
- if (udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block))
- return 1;
+ ret = udf_load_pvoldesc(sb, vds[VDS_POS_PRIMARY_VOL_DESC].block);
+ if (ret < 0)
+ return ret;
- if (vds[VDS_POS_LOGICAL_VOL_DESC].block && udf_load_logicalvol(sb,
- vds[VDS_POS_LOGICAL_VOL_DESC].block, fileset))
- return 1;
+ if (vds[VDS_POS_LOGICAL_VOL_DESC].block) {
+ ret = udf_load_logicalvol(sb,
+ vds[VDS_POS_LOGICAL_VOL_DESC].block,
+ fileset);
+ if (ret < 0)
+ return ret;
+ }
if (vds[VDS_POS_PARTITION_DESC].block) {
/*
@@ -1632,19 +1656,27 @@
*/
for (block = vds[VDS_POS_PARTITION_DESC].block;
block < vds[VDS_POS_TERMINATING_DESC].block;
- block++)
- if (udf_load_partdesc(sb, block))
- return 1;
+ block++) {
+ ret = udf_load_partdesc(sb, block);
+ if (ret < 0)
+ return ret;
+ }
}
return 0;
}
+/*
+ * Load Volume Descriptor Sequence described by anchor in bh
+ *
+ * Returns <0 on error, 0 on success
+ */
static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh,
struct kernel_lb_addr *fileset)
{
struct anchorVolDescPtr *anchor;
- long main_s, main_e, reserve_s, reserve_e;
+ sector_t main_s, main_e, reserve_s, reserve_e;
+ int ret;
anchor = (struct anchorVolDescPtr *)bh->b_data;
@@ -1662,18 +1694,26 @@
/* Process the main & reserve sequences */
/* responsible for finding the PartitionDesc(s) */
- if (!udf_process_sequence(sb, main_s, main_e, fileset))
- return 1;
+ ret = udf_process_sequence(sb, main_s, main_e, fileset);
+ if (ret != -EAGAIN)
+ return ret;
udf_sb_free_partitions(sb);
- if (!udf_process_sequence(sb, reserve_s, reserve_e, fileset))
- return 1;
- udf_sb_free_partitions(sb);
- return 0;
+ ret = udf_process_sequence(sb, reserve_s, reserve_e, fileset);
+ if (ret < 0) {
+ udf_sb_free_partitions(sb);
+ /* No sequence was OK, return -EIO */
+ if (ret == -EAGAIN)
+ ret = -EIO;
+ }
+ return ret;
}
/*
* Check whether there is an anchor block in the given block and
* load Volume Descriptor Sequence if so.
+ *
+ * Returns <0 on error, 0 on success, -EAGAIN is special - try next anchor
+ * block
*/
static int udf_check_anchor_block(struct super_block *sb, sector_t block,
struct kernel_lb_addr *fileset)
@@ -1685,33 +1725,40 @@
if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
udf_fixed_to_variable(block) >=
sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
- return 0;
+ return -EAGAIN;
bh = udf_read_tagged(sb, block, block, &ident);
if (!bh)
- return 0;
+ return -EAGAIN;
if (ident != TAG_IDENT_AVDP) {
brelse(bh);
- return 0;
+ return -EAGAIN;
}
ret = udf_load_sequence(sb, bh, fileset);
brelse(bh);
return ret;
}
-/* Search for an anchor volume descriptor pointer */
-static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock,
- struct kernel_lb_addr *fileset)
+/*
+ * Search for an anchor volume descriptor pointer.
+ *
+ * Returns < 0 on error, 0 on success. -EAGAIN is special - try next set
+ * of anchors.
+ */
+static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock,
+ struct kernel_lb_addr *fileset)
{
sector_t last[6];
int i;
struct udf_sb_info *sbi = UDF_SB(sb);
int last_count = 0;
+ int ret;
/* First try user provided anchor */
if (sbi->s_anchor) {
- if (udf_check_anchor_block(sb, sbi->s_anchor, fileset))
- return lastblock;
+ ret = udf_check_anchor_block(sb, sbi->s_anchor, fileset);
+ if (ret != -EAGAIN)
+ return ret;
}
/*
* according to spec, anchor is in either:
@@ -1720,39 +1767,46 @@
* lastblock
* however, if the disc isn't closed, it could be 512.
*/
- if (udf_check_anchor_block(sb, sbi->s_session + 256, fileset))
- return lastblock;
+ ret = udf_check_anchor_block(sb, sbi->s_session + 256, fileset);
+ if (ret != -EAGAIN)
+ return ret;
/*
* The trouble is which block is the last one. Drives often misreport
* this so we try various possibilities.
*/
- last[last_count++] = lastblock;
- if (lastblock >= 1)
- last[last_count++] = lastblock - 1;
- last[last_count++] = lastblock + 1;
- if (lastblock >= 2)
- last[last_count++] = lastblock - 2;
- if (lastblock >= 150)
- last[last_count++] = lastblock - 150;
- if (lastblock >= 152)
- last[last_count++] = lastblock - 152;
+ last[last_count++] = *lastblock;
+ if (*lastblock >= 1)
+ last[last_count++] = *lastblock - 1;
+ last[last_count++] = *lastblock + 1;
+ if (*lastblock >= 2)
+ last[last_count++] = *lastblock - 2;
+ if (*lastblock >= 150)
+ last[last_count++] = *lastblock - 150;
+ if (*lastblock >= 152)
+ last[last_count++] = *lastblock - 152;
for (i = 0; i < last_count; i++) {
if (last[i] >= sb->s_bdev->bd_inode->i_size >>
sb->s_blocksize_bits)
continue;
- if (udf_check_anchor_block(sb, last[i], fileset))
- return last[i];
+ ret = udf_check_anchor_block(sb, last[i], fileset);
+ if (ret != -EAGAIN) {
+ if (!ret)
+ *lastblock = last[i];
+ return ret;
+ }
if (last[i] < 256)
continue;
- if (udf_check_anchor_block(sb, last[i] - 256, fileset))
- return last[i];
+ ret = udf_check_anchor_block(sb, last[i] - 256, fileset);
+ if (ret != -EAGAIN) {
+ if (!ret)
+ *lastblock = last[i];
+ return ret;
+ }
}
/* Finally try block 512 in case media is open */
- if (udf_check_anchor_block(sb, sbi->s_session + 512, fileset))
- return last[0];
- return 0;
+ return udf_check_anchor_block(sb, sbi->s_session + 512, fileset);
}
/*
@@ -1760,54 +1814,59 @@
* area specified by it. The function expects sbi->s_lastblock to be the last
* block on the media.
*
- * Return 1 if ok, 0 if not found.
- *
+ * Return <0 on error, 0 if anchor found. -EAGAIN is special meaning anchor
+ * was not found.
*/
static int udf_find_anchor(struct super_block *sb,
struct kernel_lb_addr *fileset)
{
- sector_t lastblock;
struct udf_sb_info *sbi = UDF_SB(sb);
+ sector_t lastblock = sbi->s_last_block;
+ int ret;
- lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
- if (lastblock)
+ ret = udf_scan_anchors(sb, &lastblock, fileset);
+ if (ret != -EAGAIN)
goto out;
/* No anchor found? Try VARCONV conversion of block numbers */
UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
+ lastblock = udf_variable_to_fixed(sbi->s_last_block);
/* Firstly, we try to not convert number of the last block */
- lastblock = udf_scan_anchors(sb,
- udf_variable_to_fixed(sbi->s_last_block),
- fileset);
- if (lastblock)
+ ret = udf_scan_anchors(sb, &lastblock, fileset);
+ if (ret != -EAGAIN)
goto out;
+ lastblock = sbi->s_last_block;
/* Secondly, we try with converted number of the last block */
- lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
- if (!lastblock) {
+ ret = udf_scan_anchors(sb, &lastblock, fileset);
+ if (ret < 0) {
/* VARCONV didn't help. Clear it. */
UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV);
- return 0;
}
out:
- sbi->s_last_block = lastblock;
- return 1;
+ if (ret == 0)
+ sbi->s_last_block = lastblock;
+ return ret;
}
/*
* Check Volume Structure Descriptor, find Anchor block and load Volume
- * Descriptor Sequence
+ * Descriptor Sequence.
+ *
+ * Returns < 0 on error, 0 on success. -EAGAIN is special meaning anchor
+ * block was not found.
*/
static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
int silent, struct kernel_lb_addr *fileset)
{
struct udf_sb_info *sbi = UDF_SB(sb);
loff_t nsr_off;
+ int ret;
if (!sb_set_blocksize(sb, uopt->blocksize)) {
if (!silent)
udf_warn(sb, "Bad block size\n");
- return 0;
+ return -EINVAL;
}
sbi->s_last_block = uopt->lastblock;
if (!uopt->novrs) {
@@ -1828,12 +1887,13 @@
/* Look for anchor block and load Volume Descriptor Sequence */
sbi->s_anchor = uopt->anchor;
- if (!udf_find_anchor(sb, fileset)) {
- if (!silent)
+ ret = udf_find_anchor(sb, fileset);
+ if (ret < 0) {
+ if (!silent && ret == -EAGAIN)
udf_warn(sb, "No anchor found\n");
- return 0;
+ return ret;
}
- return 1;
+ return 0;
}
static void udf_open_lvid(struct super_block *sb)
@@ -1939,7 +1999,7 @@
static int udf_fill_super(struct super_block *sb, void *options, int silent)
{
- int ret;
+ int ret = -EINVAL;
struct inode *inode = NULL;
struct udf_options uopt;
struct kernel_lb_addr rootdir, fileset;
@@ -2011,7 +2071,7 @@
} else {
uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
- if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
+ if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
if (!silent)
pr_notice("Rescanning with blocksize %d\n",
UDF_DEFAULT_BLOCKSIZE);
@@ -2021,8 +2081,11 @@
ret = udf_load_vrs(sb, &uopt, silent, &fileset);
}
}
- if (!ret) {
- udf_warn(sb, "No partition found (1)\n");
+ if (ret < 0) {
+ if (ret == -EAGAIN) {
+ udf_warn(sb, "No partition found (1)\n");
+ ret = -EINVAL;
+ }
goto error_out;
}
@@ -2040,9 +2103,13 @@
udf_err(sb, "minUDFReadRev=%x (max is %x)\n",
le16_to_cpu(lvidiu->minUDFReadRev),
UDF_MAX_READ_VERSION);
+ ret = -EINVAL;
goto error_out;
- } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION)
- sb->s_flags |= MS_RDONLY;
+ } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION &&
+ !(sb->s_flags & MS_RDONLY)) {
+ ret = -EACCES;
+ goto error_out;
+ }
sbi->s_udfrev = minUDFWriteRev;
@@ -2054,17 +2121,20 @@
if (!sbi->s_partitions) {
udf_warn(sb, "No partition found (2)\n");
+ ret = -EINVAL;
goto error_out;
}
if (sbi->s_partmaps[sbi->s_partition].s_partition_flags &
- UDF_PART_FLAG_READ_ONLY) {
- pr_notice("Partition marked readonly; forcing readonly mount\n");
- sb->s_flags |= MS_RDONLY;
+ UDF_PART_FLAG_READ_ONLY &&
+ !(sb->s_flags & MS_RDONLY)) {
+ ret = -EACCES;
+ goto error_out;
}
if (udf_find_fileset(sb, &fileset, &rootdir)) {
udf_warn(sb, "No fileset found\n");
+ ret = -EINVAL;
goto error_out;
}
@@ -2086,6 +2156,7 @@
if (!inode) {
udf_err(sb, "Error in udf_iget, block=%d, partition=%d\n",
rootdir.logicalBlockNum, rootdir.partitionReferenceNum);
+ ret = -EIO;
goto error_out;
}
@@ -2093,6 +2164,7 @@
sb->s_root = d_make_root(inode);
if (!sb->s_root) {
udf_err(sb, "Couldn't allocate root dentry\n");
+ ret = -ENOMEM;
goto error_out;
}
sb->s_maxbytes = MAX_LFS_FILESIZE;
@@ -2113,7 +2185,7 @@
kfree(sbi);
sb->s_fs_info = NULL;
- return -EINVAL;
+ return ret;
}
void _udf_err(struct super_block *sb, const char *function,
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index d7c6dbe..d89f324 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -80,11 +80,17 @@
struct inode *inode = page->mapping->host;
struct buffer_head *bh = NULL;
unsigned char *symlink;
- int err = -EIO;
+ int err;
unsigned char *p = kmap(page);
struct udf_inode_info *iinfo;
uint32_t pos;
+ /* We don't support symlinks longer than one block */
+ if (inode->i_size > inode->i_sb->s_blocksize) {
+ err = -ENAMETOOLONG;
+ goto out_unmap;
+ }
+
iinfo = UDF_I(inode);
pos = udf_block_map(inode, 0);
@@ -94,8 +100,10 @@
} else {
bh = sb_bread(inode->i_sb, pos);
- if (!bh)
- goto out;
+ if (!bh) {
+ err = -EIO;
+ goto out_unlock_inode;
+ }
symlink = bh->b_data;
}
@@ -109,9 +117,10 @@
unlock_page(page);
return 0;
-out:
+out_unlock_inode:
up_read(&iinfo->i_data_sem);
SetPageError(page);
+out_unmap:
kunmap(page);
unlock_page(page);
return err;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 41a6950..cfbb4c1 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1661,11 +1661,72 @@
return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
}
+/*
+ * This is basically a copy of __set_page_dirty_buffers() with one
+ * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
+ * dirty, we'll never be able to clean them because we don't write buffers
+ * beyond EOF, and that means we can't invalidate pages that span EOF
+ * that have been marked dirty. Further, the dirty state can leak into
+ * the file interior if the file is extended, resulting in all sorts of
+ * bad things happening as the state does not match the underlying data.
+ *
+ * XXX: this really indicates that bufferheads in XFS need to die. Warts like
+ * this only exist because of bufferheads and how the generic code manages them.
+ */
+STATIC int
+xfs_vm_set_page_dirty(
+ struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct inode *inode = mapping->host;
+ loff_t end_offset;
+ loff_t offset;
+ int newly_dirty;
+
+ if (unlikely(!mapping))
+ return !TestSetPageDirty(page);
+
+ end_offset = i_size_read(inode);
+ offset = page_offset(page);
+
+ spin_lock(&mapping->private_lock);
+ if (page_has_buffers(page)) {
+ struct buffer_head *head = page_buffers(page);
+ struct buffer_head *bh = head;
+
+ do {
+ if (offset < end_offset)
+ set_buffer_dirty(bh);
+ bh = bh->b_this_page;
+ offset += 1 << inode->i_blkbits;
+ } while (bh != head);
+ }
+ newly_dirty = !TestSetPageDirty(page);
+ spin_unlock(&mapping->private_lock);
+
+ if (newly_dirty) {
+ /* sigh - __set_page_dirty() is static, so copy it here, too */
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ if (page->mapping) { /* Race with truncate? */
+ WARN_ON_ONCE(!PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ }
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ }
+ return newly_dirty;
+}
+
const struct address_space_operations xfs_address_space_operations = {
.readpage = xfs_vm_readpage,
.readpages = xfs_vm_readpages,
.writepage = xfs_vm_writepage,
.writepages = xfs_vm_writepages,
+ .set_page_dirty = xfs_vm_set_page_dirty,
.releasepage = xfs_vm_releasepage,
.invalidatepage = xfs_vm_invalidatepage,
.write_begin = xfs_vm_write_begin,
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 4ec4317..e0451f4 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -296,6 +296,10 @@
ASSERT(atomic_read(&bip->bli_refcount) > 0);
ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
(bip->bli_flags & XFS_BLI_STALE));
+ ASSERT((bip->bli_flags & XFS_BLI_STALE) ||
+ (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF
+ && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF));
+
/*
* If it is an inode buffer, transfer the in-memory state to the
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 0b8b2a1..79ddbaf 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1223,6 +1223,7 @@
/* start with smaller blk num */
forward = nodehdr.forw < nodehdr.back;
for (i = 0; i < 2; forward = !forward, i++) {
+ struct xfs_da3_icnode_hdr thdr;
if (forward)
blkno = nodehdr.forw;
else
@@ -1235,10 +1236,10 @@
return(error);
node = bp->b_addr;
- xfs_da3_node_hdr_from_disk(&nodehdr, node);
+ xfs_da3_node_hdr_from_disk(&thdr, node);
xfs_trans_brelse(state->args->trans, bp);
- if (count - nodehdr.count >= 0)
+ if (count - thdr.count >= 0)
break; /* fits with at least 25% to spare */
}
if (i >= 2) {
@@ -1333,7 +1334,7 @@
node = blk->bp->b_addr;
xfs_da3_node_hdr_from_disk(&nodehdr, node);
btree = xfs_da3_node_tree_p(node);
- if (be32_to_cpu(btree->hashval) == lasthash)
+ if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
break;
blk->hashval = lasthash;
btree[blk->index].hashval = cpu_to_be32(lasthash);
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 044e97a..bac3e16 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1104,7 +1104,8 @@
* Get the buffer containing the on-disk dquot
*/
error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
+ mp->m_quotainfo->qi_dqchunklen, 0, &bp,
+ &xfs_dquot_buf_ops);
if (error)
goto out_unlock;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a5f2042..9f457fe 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -298,7 +298,16 @@
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
- truncate_pagecache_range(VFS_I(ip), pos, -1);
+
+ /*
+ * Invalidate whole pages. This can return an error if
+ * we fail to invalidate a page, but this should never
+ * happen on XFS. Warn if it does fail.
+ */
+ ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+ pos >> PAGE_CACHE_SHIFT, -1);
+ WARN_ON_ONCE(ret);
+ ret = 0;
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
@@ -677,7 +686,15 @@
pos, -1);
if (ret)
goto out;
- truncate_pagecache_range(VFS_I(ip), pos, -1);
+ /*
+ * Invalidate whole pages. This can return an error if
+ * we fail to invalidate a page, but this should never
+ * happen on XFS. Warn if it does fail.
+ */
+ ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
+ pos >> PAGE_CACHE_SHIFT, -1);
+ WARN_ON_ONCE(ret);
+ ret = 0;
}
/*
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 3c3644e..2288db4 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -216,6 +216,8 @@
*/
nfree = 0;
for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
+ __be32 *agfl_bno;
+
/*
* AG freespace header block
*/
@@ -275,8 +277,10 @@
agfl->agfl_seqno = cpu_to_be32(agno);
uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_uuid);
}
+
+ agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, bp);
for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
- agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+ agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
error = xfs_bwrite(bp);
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7f7be5f..f010ab45 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1655,6 +1655,7 @@
agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
offset = offsetof(xfs_agi_t, agi_unlinked) +
(sizeof(xfs_agino_t) * bucket_index);
+ xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
xfs_trans_log_buf(tp, agibp, offset,
(offset + sizeof(xfs_agino_t) - 1));
return 0;
@@ -1746,6 +1747,7 @@
agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
offset = offsetof(xfs_agi_t, agi_unlinked) +
(sizeof(xfs_agino_t) * bucket_index);
+ xfs_trans_buf_set_type(tp, agibp, XFS_BLFT_AGI_BUF);
xfs_trans_log_buf(tp, agibp, offset,
(offset + sizeof(xfs_agino_t) - 1));
} else {
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5e99968..83dfe6e 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -409,7 +409,8 @@
return -XFS_ERROR(EPERM);
if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
return -XFS_ERROR(EFAULT);
- if (al_hreq.buflen > XATTR_LIST_MAX)
+ if (al_hreq.buflen < sizeof(struct attrlist) ||
+ al_hreq.buflen > XATTR_LIST_MAX)
return -XFS_ERROR(EINVAL);
/*
@@ -1612,6 +1613,12 @@
case XFS_IOC_FREE_EOFBLOCKS: {
struct xfs_eofblocks eofb;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (mp->m_flags & XFS_MOUNT_RDONLY)
+ return -XFS_ERROR(EROFS);
+
if (copy_from_user(&eofb, arg, sizeof(eofb)))
return -XFS_ERROR(EFAULT);
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c0c6625..68799d7 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -359,7 +359,8 @@
if (copy_from_user(&al_hreq, arg,
sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
return -XFS_ERROR(EFAULT);
- if (al_hreq.buflen > XATTR_LIST_MAX)
+ if (al_hreq.buflen < sizeof(struct attrlist) ||
+ al_hreq.buflen > XATTR_LIST_MAX)
return -XFS_ERROR(EINVAL);
/*
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b75c9bb..29d1ca5 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -935,6 +935,12 @@
if (error)
break;
+ /*
+ * A corrupt buffer might not have a verifier attached, so
+ * make sure we have the correct one attached before writeback
+ * occurs.
+ */
+ bp->b_ops = &xfs_dquot_buf_ops;
xfs_qm_reset_dqcounts(mp, bp, firstid, type);
xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
@@ -1018,7 +1024,7 @@
xfs_buf_readahead(mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, rablkno),
mp->m_quotainfo->qi_dqchunklen,
- NULL);
+ &xfs_dquot_buf_ops);
rablkno++;
}
}
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 2fd7c1f..b5d5beb 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1100,6 +1100,7 @@
whole = 1;
}
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
if (whole)
/*
* Log the whole thing, the fields are noncontiguous.
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index c13c919..6b66efd 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -97,6 +97,7 @@
struct acpi_hotplug_profile {
struct kobject kobj;
bool enabled:1;
+ bool ignore:1;
enum acpi_hotplug_mode mode;
};
@@ -455,7 +456,11 @@
};
/* helper */
-acpi_handle acpi_get_child(acpi_handle, u64);
+acpi_handle acpi_find_child(acpi_handle, u64, bool);
+static inline acpi_handle acpi_get_child(acpi_handle handle, u64 addr)
+{
+ return acpi_find_child(handle, addr, false);
+}
int acpi_is_root_bridge(acpi_handle);
struct acpi_pci_root *acpi_pci_find_root(acpi_handle handle);
#define DEVICE_ACPI_HANDLE(dev) ((acpi_handle)ACPI_HANDLE(dev))
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index a64adcc..f819e81 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -198,9 +198,29 @@
typedef s32 acpi_native_int;
typedef u32 acpi_size;
+
+#ifdef ACPI_32BIT_PHYSICAL_ADDRESS
+
+/*
+ * OSPMs can define this to shrink the size of the structures for 32-bit
+ * none PAE environment. ASL compiler may always define this to generate
+ * 32-bit OSPM compliant tables.
+ */
typedef u32 acpi_io_address;
typedef u32 acpi_physical_address;
+#else /* ACPI_32BIT_PHYSICAL_ADDRESS */
+
+/*
+ * It is reported that, after some calculations, the physical addresses can
+ * wrap over the 32-bit boundary on 32-bit PAE environment.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=87971
+ */
+typedef u64 acpi_io_address;
+typedef u64 acpi_physical_address;
+
+#endif /* ACPI_32BIT_PHYSICAL_ADDRESS */
+
#define ACPI_MAX_PTR ACPI_UINT32_MAX
#define ACPI_SIZE_MAX ACPI_UINT32_MAX
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index ef04b36..f7db107 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -76,6 +76,7 @@
#define ACPI_LARGE_NAMESPACE_NODE
#define ACPI_DATA_TABLE_DISASSEMBLY
#define ACPI_SINGLE_THREADED
+#define ACPI_32BIT_PHYSICAL_ADDRESS
#endif
/* acpi_exec configuration. Multithreaded with full AML debugger */
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index 294b1e7..0000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef ASM_DMA_CONTIGUOUS_H
-#define ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_CMA
-
-#include <linux/device.h>
-#include <linux/dma-contiguous.h>
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
- if (dev && dev->cma_area)
- return dev->cma_area;
- return dma_contiguous_default_area;
-}
-
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
- if (dev)
- dev->cma_area = cma;
- if (!dev && !dma_contiguous_default_area)
- dma_contiguous_default_area = cma;
-}
-
-#endif
-#endif
-
-#endif
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index de8bf89..a9fd248 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -179,6 +179,15 @@
extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
void *cpu_addr, dma_addr_t dma_addr, size_t size);
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+ unsigned long vm_flags,
+ pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+ unsigned long vm_flags, pgprot_t prot,
+ const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
/**
* dma_mmap_attrs - map a coherent DMA allocation into user space
* @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h
new file mode 100644
index 0000000..a5de55c
--- /dev/null
+++ b/include/asm-generic/early_ioremap.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_EARLY_IOREMAP_H_
+#define _ASM_EARLY_IOREMAP_H_
+
+#include <linux/types.h>
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ */
+extern void __iomem *early_ioremap(resource_size_t phys_addr,
+ unsigned long size);
+extern void *early_memremap(resource_size_t phys_addr,
+ unsigned long size);
+extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void early_memunmap(void *addr, unsigned long size);
+
+/*
+ * Weak function called by early_ioremap_reset(). It does nothing, but
+ * architectures may provide their own version to do any needed cleanups.
+ */
+extern void early_ioremap_shutdown(void);
+
+#if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU)
+/* Arch-specific initialization */
+extern void early_ioremap_init(void);
+
+/* Generic initialization called by architecture code */
+extern void early_ioremap_setup(void);
+
+/*
+ * Called as last step in paging_init() so library can act
+ * accordingly for subsequent map/unmap requests.
+ */
+extern void early_ioremap_reset(void);
+
+#else
+static inline void early_ioremap_init(void) { }
+static inline void early_ioremap_setup(void) { }
+static inline void early_ioremap_reset(void) { }
+#endif
+
+#endif /* _ASM_EARLY_IOREMAP_H_ */
diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h
new file mode 100644
index 0000000..5a64ca4
--- /dev/null
+++ b/include/asm-generic/fixmap.h
@@ -0,0 +1,97 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009
+ * Break out common bits to asm-generic by Mark Salter, November 2013
+ */
+
+#ifndef __ASM_GENERIC_FIXMAP_H
+#define __ASM_GENERIC_FIXMAP_H
+
+#include <linux/bug.h>
+
+#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+#ifndef __ASSEMBLY__
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+ BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
+ return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+ BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+ return __virt_to_fix(vaddr);
+}
+
+/*
+ * Provide some reasonable defaults for page flags.
+ * Not all architectures use all of these different types and some
+ * architectures use different names.
+ */
+#ifndef FIXMAP_PAGE_NORMAL
+#define FIXMAP_PAGE_NORMAL PAGE_KERNEL
+#endif
+#ifndef FIXMAP_PAGE_NOCACHE
+#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NOCACHE
+#endif
+#ifndef FIXMAP_PAGE_IO
+#define FIXMAP_PAGE_IO PAGE_KERNEL_IO
+#endif
+#ifndef FIXMAP_PAGE_CLEAR
+#define FIXMAP_PAGE_CLEAR __pgprot(0)
+#endif
+
+#ifndef set_fixmap
+#define set_fixmap(idx, phys) \
+ __set_fixmap(idx, phys, FIXMAP_PAGE_NORMAL)
+#endif
+
+#ifndef clear_fixmap
+#define clear_fixmap(idx) \
+ __set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR)
+#endif
+
+/* Return a pointer with offset calculated */
+#define __set_fixmap_offset(idx, phys, flags) \
+({ \
+ unsigned long addr; \
+ __set_fixmap(idx, phys, flags); \
+ addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1)); \
+ addr; \
+})
+
+#define set_fixmap_offset(idx, phys) \
+ __set_fixmap_offset(idx, phys, FIXMAP_PAGE_NORMAL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+ __set_fixmap(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+#define set_fixmap_offset_nocache(idx, phys) \
+ __set_fixmap_offset(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+/*
+ * Some fixmaps are for IO
+ */
+#define set_fixmap_io(idx, phys) \
+ __set_fixmap(idx, phys, FIXMAP_PAGE_IO)
+
+#endif /* __ASSEMBLY__ */
+#endif /* __ASM_GENERIC_FIXMAP_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index d06079c..99b490b 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -6,12 +6,12 @@
return mk_pte(page, pgprot);
}
-static inline int huge_pte_write(pte_t pte)
+static inline unsigned long huge_pte_write(pte_t pte)
{
return pte_write(pte);
}
-static inline int huge_pte_dirty(pte_t pte)
+static inline unsigned long huge_pte_dirty(pte_t pte)
{
return pte_dirty(pte);
}
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index a59ff51..dd6d9b8 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -220,7 +220,7 @@
#endif
#ifndef pte_accessible
-# define pte_accessible(pte) ((void)(pte),1)
+# define pte_accessible(mm, pte) ((void)(pte), 1)
#endif
#ifndef flush_tlb_fix_spurious_fault
@@ -550,11 +550,10 @@
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
barrier();
#endif
- if (pmd_none(pmdval))
+ if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
return 1;
if (unlikely(pmd_bad(pmdval))) {
- if (!pmd_trans_huge(pmdval))
- pmd_clear_bad(pmd);
+ pmd_clear_bad(pmd);
return 1;
}
return 0;
@@ -620,32 +619,47 @@
#ifndef pte_mknonnuma
static inline pte_t pte_mknonnuma(pte_t pte)
{
- pte = pte_clear_flags(pte, _PAGE_NUMA);
- return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+ pteval_t val = pte_val(pte);
+
+ val &= ~_PAGE_NUMA;
+ val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+ return __pte(val);
}
#endif
#ifndef pmd_mknonnuma
static inline pmd_t pmd_mknonnuma(pmd_t pmd)
{
- pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
- return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+ pmdval_t val = pmd_val(pmd);
+
+ val &= ~_PAGE_NUMA;
+ val |= (_PAGE_PRESENT|_PAGE_ACCESSED);
+
+ return __pmd(val);
}
#endif
#ifndef pte_mknuma
static inline pte_t pte_mknuma(pte_t pte)
{
- pte = pte_set_flags(pte, _PAGE_NUMA);
- return pte_clear_flags(pte, _PAGE_PRESENT);
+ pteval_t val = pte_val(pte);
+
+ val &= ~_PAGE_PRESENT;
+ val |= _PAGE_NUMA;
+
+ return __pte(val);
}
#endif
#ifndef pmd_mknuma
static inline pmd_t pmd_mknuma(pmd_t pmd)
{
- pmd = pmd_set_flags(pmd, _PAGE_NUMA);
- return pmd_clear_flags(pmd, _PAGE_PRESENT);
+ pmdval_t val = pmd_val(pmd);
+
+ val &= ~_PAGE_PRESENT;
+ val |= _PAGE_NUMA;
+
+ return __pmd(val);
}
#endif
#else
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index bb1e2cd..d48bf5a 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_POWERPC_RWSEM_H
-#define _ASM_POWERPC_RWSEM_H
+#ifndef _ASM_GENERIC_RWSEM_H
+#define _ASM_GENERIC_RWSEM_H
#ifndef _LINUX_RWSEM_H
#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
@@ -8,7 +8,7 @@
#ifdef __KERNEL__
/*
- * R/W semaphores for PPC using the stuff in lib/rwsem.c.
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
* Adapted largely from include/asm-i386/rwsem.h
* by Paul Mackerras <paulus@samba.org>.
*/
@@ -16,7 +16,7 @@
/*
* the semaphore definition
*/
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_64BIT
# define RWSEM_ACTIVE_MASK 0xffffffffL
#else
# define RWSEM_ACTIVE_MASK 0x0000ffffL
@@ -129,4 +129,4 @@
}
#endif /* __KERNEL__ */
-#endif /* _ASM_POWERPC_RWSEM_H */
+#endif /* _ASM_GENERIC_RWSEM_H */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c1a1216..87b2726 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -3,6 +3,8 @@
/* References to section boundaries */
+#include <linux/compiler.h>
+
extern char _text[], _stext[], _etext[];
extern char _data[], _sdata[], _edata[];
extern char __bss_start[], __bss_stop[];
@@ -18,6 +20,8 @@
/* Start and end of .ctors section - used for constructor calls. */
extern char __ctors_start[], __ctors_end[];
+extern __visible const void __nosave_begin, __nosave_end;
+
/* function descriptor handling (if any). Override
* in asm/sections.h */
#ifndef dereference_function_descriptor
diff --git a/include/asm-generic/simd.h b/include/asm-generic/simd.h
new file mode 100644
index 0000000..f57eb7b
--- /dev/null
+++ b/include/asm-generic/simd.h
@@ -0,0 +1,14 @@
+
+#include <linux/hardirq.h>
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ * instructions or access the SIMD register file
+ *
+ * As architectures typically don't preserve the SIMD register file when
+ * taking an interrupt, !in_interrupt() should be a reasonable default.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+ return !in_interrupt();
+}
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 13821c3..5672d7e 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -112,7 +112,7 @@
#define HAVE_GENERIC_MMU_GATHER
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);
void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
unsigned long end);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index eb58d2d..7dd0ebe 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -171,6 +171,16 @@
#define CLK_OF_TABLES()
#endif
+#ifdef CONFIG_OF_RESERVED_MEM
+#define RESERVEDMEM_OF_TABLES() \
+ . = ALIGN(8); \
+ VMLINUX_SYMBOL(__reservedmem_of_table) = .; \
+ *(__reservedmem_of_table) \
+ *(__reservedmem_of_table_end)
+#else
+#define RESERVEDMEM_OF_TABLES()
+#endif
+
#define KERNEL_DTB() \
STRUCT_ALIGN(); \
VMLINUX_SYMBOL(__dtb_start) = .; \
@@ -495,6 +505,7 @@
#define KERNEL_CTORS() . = ALIGN(8); \
VMLINUX_SYMBOL(__ctors_start) = .; \
*(.ctors) \
+ *(.init_array) \
VMLINUX_SYMBOL(__ctors_end) = .;
#else
#define KERNEL_CTORS()
@@ -515,6 +526,7 @@
CPU_DISCARD(init.rodata) \
MEM_DISCARD(init.rodata) \
CLK_OF_TABLES() \
+ RESERVEDMEM_OF_TABLES() \
CLKSRC_OF_TABLES() \
KERNEL_DTB() \
IRQCHIP_OF_MATCH_TABLE()
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index 3f21f1b..94f9ea8 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -49,4 +49,8 @@
return (val + c->high_bits) & ~rhs;
}
+#ifndef zero_bytemask
+#define zero_bytemask(mask) (~1ul << __fls(mask))
+#endif
+
#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index e6c9c4c..6d26b40 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -23,11 +23,25 @@
#define ARCH_TIMER_CTRL_IT_MASK (1 << 1)
#define ARCH_TIMER_CTRL_IT_STAT (1 << 2)
-#define ARCH_TIMER_REG_CTRL 0
-#define ARCH_TIMER_REG_TVAL 1
+enum arch_timer_reg {
+ ARCH_TIMER_REG_CTRL,
+ ARCH_TIMER_REG_TVAL,
+};
#define ARCH_TIMER_PHYS_ACCESS 0
#define ARCH_TIMER_VIRT_ACCESS 1
+#define ARCH_TIMER_MEM_PHYS_ACCESS 2
+#define ARCH_TIMER_MEM_VIRT_ACCESS 3
+
+#define ARCH_TIMER_USR_PCT_ACCESS_EN (1 << 0) /* physical counter */
+#define ARCH_TIMER_USR_VCT_ACCESS_EN (1 << 1) /* virtual counter */
+#define ARCH_TIMER_VIRT_EVT_EN (1 << 2)
+#define ARCH_TIMER_EVT_TRIGGER_SHIFT (4)
+#define ARCH_TIMER_EVT_TRIGGER_MASK (0xF << ARCH_TIMER_EVT_TRIGGER_SHIFT)
+#define ARCH_TIMER_USR_VT_ACCESS_EN (1 << 8) /* virtual timer registers */
+#define ARCH_TIMER_USR_PT_ACCESS_EN (1 << 9) /* physical timer registers */
+
+#define ARCH_TIMER_EVT_STREAM_FREQ 10000 /* 100us */
#ifdef CONFIG_ARM_ARCH_TIMER
diff --git a/include/crypto/ablk_helper.h b/include/crypto/ablk_helper.h
new file mode 100644
index 0000000..4f93df5
--- /dev/null
+++ b/include/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+ struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+ unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 418d270..063f8ef 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -100,9 +100,12 @@
void *page;
u8 *buffer;
u8 *iv;
+ unsigned int ivsize;
int flags;
- unsigned int blocksize;
+ unsigned int walk_blocksize;
+ unsigned int cipher_blocksize;
+ unsigned int alignmask;
};
struct ablkcipher_walk {
@@ -192,6 +195,10 @@
int blkcipher_walk_virt_block(struct blkcipher_desc *desc,
struct blkcipher_walk *walk,
unsigned int blocksize);
+int blkcipher_aead_walk_virt_block(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk,
+ struct crypto_aead *tfm,
+ unsigned int blocksize);
int ablkcipher_walk_done(struct ablkcipher_request *req,
struct ablkcipher_walk *walk, int err);
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 3744d2a..2cddd2b 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -36,6 +36,7 @@
{
sg_set_page(&sg1[num - 1], (void *)sg2, 0, 0);
sg1[num - 1].page_link &= ~0x02;
+ sg1[num - 1].page_link |= 0x01;
}
static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg)
@@ -43,7 +44,7 @@
if (sg_is_last(sg))
return NULL;
- return (++sg)->length ? sg : (void *)sg_page(sg);
+ return (++sg)->length ? sg : sg_chain_ptr(sg);
}
static inline void scatterwalk_crypto_chain(struct scatterlist *head,
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index bb1bc48..d7b7170 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -52,7 +52,6 @@
{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
- {0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
@@ -143,8 +142,11 @@
{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
@@ -256,6 +258,7 @@
{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -559,7 +562,7 @@
{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
- {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+ {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/dt-bindings/thermal/thermal.h b/include/dt-bindings/thermal/thermal.h
new file mode 100644
index 0000000..59822a9
--- /dev/null
+++ b/include/dt-bindings/thermal/thermal.h
@@ -0,0 +1,17 @@
+/*
+ * This header provides constants for most thermal bindings.
+ *
+ * Copyright (C) 2013 Texas Instruments
+ * Eduardo Valentin <eduardo.valentin@ti.com>
+ *
+ * GPLv2 only
+ */
+
+#ifndef _DT_BINDINGS_THERMAL_THERMAL_H
+#define _DT_BINDINGS_THERMAL_THERMAL_H
+
+/* On cooling devices upper and lower limits */
+#define THERMAL_NO_LIMIT (-1UL)
+
+#endif
+
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
new file mode 100644
index 0000000..ad9db60
--- /dev/null
+++ b/include/kvm/arm_arch_timer.h
@@ -0,0 +1,103 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_ARM_KVM_ARCH_TIMER_H
+#define __ASM_ARM_KVM_ARCH_TIMER_H
+
+#include <linux/clocksource.h>
+#include <linux/hrtimer.h>
+#include <linux/workqueue.h>
+
+struct arch_timer_kvm {
+#ifdef CONFIG_KVM_ARM_TIMER
+ /* Is the timer enabled */
+ bool enabled;
+
+ /* Virtual offset */
+ cycle_t cntvoff;
+#endif
+};
+
+struct arch_timer_cpu {
+#ifdef CONFIG_KVM_ARM_TIMER
+ /* Registers: control register, timer value */
+ u32 cntv_ctl; /* Saved/restored */
+ cycle_t cntv_cval; /* Saved/restored */
+
+ /*
+ * Anything that is not used directly from assembly code goes
+ * here.
+ */
+
+ /* Background timer used when the guest is not running */
+ struct hrtimer timer;
+
+ /* Work queued with the above timer expires */
+ struct work_struct expired;
+
+ /* Background timer active */
+ bool armed;
+
+ /* Timer IRQ */
+ const struct kvm_irq_level *irq;
+#endif
+};
+
+#ifdef CONFIG_KVM_ARM_TIMER
+int kvm_timer_hyp_init(void);
+int kvm_timer_init(struct kvm *kvm);
+void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
+ const struct kvm_irq_level *irq);
+void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
+int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
+
+#else
+static inline int kvm_timer_hyp_init(void)
+{
+ return 0;
+};
+
+static inline int kvm_timer_init(struct kvm *kvm)
+{
+ return 0;
+}
+
+static inline void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
+ const struct kvm_irq_level *irq) {}
+static inline void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) {}
+static inline void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) {}
+
+static inline int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+ return 0;
+}
+
+static inline u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+ return 0;
+}
+#endif
+
+#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
new file mode 100644
index 0000000..2f2aac8
--- /dev/null
+++ b/include/kvm/arm_vgic.h
@@ -0,0 +1,370 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __ASM_ARM_KVM_VGIC_H
+#define __ASM_ARM_KVM_VGIC_H
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/irqreturn.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#define VGIC_NR_IRQS_LEGACY 256
+#define VGIC_NR_SGIS 16
+#define VGIC_NR_PPIS 16
+#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
+
+#define VGIC_V2_MAX_LRS (1 << 6)
+#define VGIC_V3_MAX_LRS 16
+#define VGIC_MAX_IRQS 1024
+
+/* Sanity checks... */
+#if (KVM_MAX_VCPUS > 8)
+#error Invalid number of CPU interfaces
+#endif
+
+#if (VGIC_NR_IRQS_LEGACY & 31)
+#error "VGIC_NR_IRQS must be a multiple of 32"
+#endif
+
+#if (VGIC_NR_IRQS_LEGACY > VGIC_MAX_IRQS)
+#error "VGIC_NR_IRQS must be <= 1024"
+#endif
+
+/*
+ * The GIC distributor registers describing interrupts have two parts:
+ * - 32 per-CPU interrupts (SGI + PPI)
+ * - a bunch of shared interrupts (SPI)
+ */
+struct vgic_bitmap {
+ /*
+ * - One UL per VCPU for private interrupts (assumes UL is at
+ * least 32 bits)
+ * - As many UL as necessary for shared interrupts.
+ *
+ * The private interrupts are accessed via the "private"
+ * field, one UL per vcpu (the state for vcpu n is in
+ * private[n]). The shared interrupts are accessed via the
+ * "shared" pointer (IRQn state is at bit n-32 in the bitmap).
+ */
+ unsigned long *private;
+ unsigned long *shared;
+};
+
+struct vgic_bytemap {
+ /*
+ * - 8 u32 per VCPU for private interrupts
+ * - As many u32 as necessary for shared interrupts.
+ *
+ * The private interrupts are accessed via the "private"
+ * field, (the state for vcpu n is in private[n*8] to
+ * private[n*8 + 7]). The shared interrupts are accessed via
+ * the "shared" pointer (IRQn state is at byte (n-32)%4 of the
+ * shared[(n-32)/4] word).
+ */
+ u32 *private;
+ u32 *shared;
+};
+
+struct kvm_vcpu;
+
+enum vgic_type {
+ VGIC_V2, /* Good ol' GICv2 */
+ VGIC_V3, /* New fancy GICv3 */
+};
+
+#define LR_STATE_PENDING (1 << 0)
+#define LR_STATE_ACTIVE (1 << 1)
+#define LR_STATE_MASK (3 << 0)
+#define LR_EOI_INT (1 << 2)
+
+struct vgic_lr {
+ u16 irq;
+ u8 source;
+ u8 state;
+};
+
+struct vgic_vmcr {
+ u32 ctlr;
+ u32 abpr;
+ u32 bpr;
+ u32 pmr;
+};
+
+struct vgic_ops {
+ struct vgic_lr (*get_lr)(const struct kvm_vcpu *, int);
+ void (*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
+ void (*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
+ u64 (*get_elrsr)(const struct kvm_vcpu *vcpu);
+ u64 (*get_eisr)(const struct kvm_vcpu *vcpu);
+ u32 (*get_interrupt_status)(const struct kvm_vcpu *vcpu);
+ void (*enable_underflow)(struct kvm_vcpu *vcpu);
+ void (*disable_underflow)(struct kvm_vcpu *vcpu);
+ void (*get_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+ void (*set_vmcr)(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+ void (*enable)(struct kvm_vcpu *vcpu);
+};
+
+struct vgic_params {
+ /* vgic type */
+ enum vgic_type type;
+ /* Physical address of vgic virtual cpu interface */
+ phys_addr_t vcpu_base;
+ /* Number of list registers */
+ u32 nr_lr;
+ /* Interrupt number */
+ unsigned int maint_irq;
+ /* Virtual control interface base address */
+ void __iomem *vctrl_base;
+};
+
+struct vgic_dist {
+#ifdef CONFIG_KVM_ARM_VGIC
+ spinlock_t lock;
+ bool in_kernel;
+ bool ready;
+
+ int nr_cpus;
+ int nr_irqs;
+
+ /* Virtual control interface mapping */
+ void __iomem *vctrl_base;
+
+ /* Distributor and vcpu interface mapping in the guest */
+ phys_addr_t vgic_dist_base;
+ phys_addr_t vgic_cpu_base;
+
+ /* Distributor enabled */
+ u32 enabled;
+
+ /* Interrupt enabled (one bit per IRQ) */
+ struct vgic_bitmap irq_enabled;
+
+ /* Level-triggered interrupt external input is asserted */
+ struct vgic_bitmap irq_level;
+
+ /*
+ * Interrupt state is pending on the distributor
+ */
+ struct vgic_bitmap irq_pending;
+
+ /*
+ * Tracks writes to GICD_ISPENDRn and GICD_ICPENDRn for level-triggered
+ * interrupts. Essentially holds the state of the flip-flop in
+ * Figure 4-10 on page 4-101 in ARM IHI 0048B.b.
+ * Once set, it is only cleared for level-triggered interrupts on
+ * guest ACKs (when we queue it) or writes to GICD_ICPENDRn.
+ */
+ struct vgic_bitmap irq_soft_pend;
+
+ /* Level-triggered interrupt queued on VCPU interface */
+ struct vgic_bitmap irq_queued;
+
+ /* Interrupt priority. Not used yet. */
+ struct vgic_bytemap irq_priority;
+
+ /* Level/edge triggered */
+ struct vgic_bitmap irq_cfg;
+
+ /*
+ * Source CPU per SGI and target CPU:
+ *
+ * Each byte represent a SGI observable on a VCPU, each bit of
+ * this byte indicating if the corresponding VCPU has
+ * generated this interrupt. This is a GICv2 feature only.
+ *
+ * For VCPUn (n < 8), irq_sgi_sources[n*16] to [n*16 + 15] are
+ * the SGIs observable on VCPUn.
+ */
+ u8 *irq_sgi_sources;
+
+ /*
+ * Target CPU for each SPI:
+ *
+ * Array of available SPI, each byte indicating the target
+ * VCPU for SPI. IRQn (n >=32) is at irq_spi_cpu[n-32].
+ */
+ u8 *irq_spi_cpu;
+
+ /*
+ * Reverse lookup of irq_spi_cpu for faster compute pending:
+ *
+ * Array of bitmaps, one per VCPU, describing if IRQn is
+ * routed to a particular VCPU.
+ */
+ struct vgic_bitmap *irq_spi_target;
+
+ /* Bitmap indicating which CPU has something pending */
+ unsigned long *irq_pending_on_cpu;
+#endif
+};
+
+struct vgic_v2_cpu_if {
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_misr; /* Saved only */
+ u32 vgic_eisr[2]; /* Saved only */
+ u32 vgic_elrsr[2]; /* Saved only */
+ u32 vgic_apr;
+ u32 vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_ARM_GIC_V3
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_misr; /* Saved only */
+ u32 vgic_eisr; /* Saved only */
+ u32 vgic_elrsr; /* Saved only */
+ u32 vgic_ap0r[4];
+ u32 vgic_ap1r[4];
+ u64 vgic_lr[VGIC_V3_MAX_LRS];
+#endif
+};
+
+struct vgic_cpu {
+#ifdef CONFIG_KVM_ARM_VGIC
+ /* per IRQ to LR mapping */
+ u8 *vgic_irq_lr_map;
+
+ /* Pending interrupts on this VCPU */
+ DECLARE_BITMAP( pending_percpu, VGIC_NR_PRIVATE_IRQS);
+ unsigned long *pending_shared;
+
+ /* Bitmap of used/free list registers */
+ DECLARE_BITMAP( lr_used, VGIC_V2_MAX_LRS);
+
+ /* Number of list registers on this CPU */
+ int nr_lr;
+
+ /* CPU vif control registers for world switch */
+ union {
+ struct vgic_v2_cpu_if vgic_v2;
+ struct vgic_v3_cpu_if vgic_v3;
+ };
+#endif
+};
+
+#define LR_EMPTY 0xff
+
+#define INT_STATUS_EOI (1 << 0)
+#define INT_STATUS_UNDERFLOW (1 << 1)
+
+struct kvm;
+struct kvm_vcpu;
+struct kvm_run;
+struct kvm_exit_mmio;
+
+#ifdef CONFIG_KVM_ARM_VGIC
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
+int kvm_vgic_hyp_init(void);
+int kvm_vgic_init(struct kvm *kvm);
+int kvm_vgic_create(struct kvm *kvm);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
+ bool level);
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ struct kvm_exit_mmio *mmio);
+
+#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
+#define vgic_initialized(k) ((k)->arch.vgic.ready)
+
+int vgic_v2_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params);
+#ifdef CONFIG_ARM_GIC_V3
+int vgic_v3_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params);
+#else
+static inline int vgic_v3_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
+{
+ return -ENODEV;
+}
+#endif
+
+#else
+static inline int kvm_vgic_hyp_init(void)
+{
+ return 0;
+}
+
+static inline int kvm_vgic_set_addr(struct kvm *kvm, unsigned long type, u64 addr)
+{
+ return 0;
+}
+
+static inline int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+ return -ENXIO;
+}
+
+static inline int kvm_vgic_init(struct kvm *kvm)
+{
+ return 0;
+}
+
+static inline int kvm_vgic_create(struct kvm *kvm)
+{
+ return 0;
+}
+
+static inline int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+static inline void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) {}
+
+static inline int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid,
+ unsigned int irq_num, bool level)
+{
+ return 0;
+}
+
+static inline int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
+{
+ return 0;
+}
+
+static inline bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ struct kvm_exit_mmio *mmio)
+{
+ return false;
+}
+
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+ return 0;
+}
+
+static inline bool vgic_initialized(struct kvm *kvm)
+{
+ return true;
+}
+#endif
+
+#endif
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 43ec7e2..aafb89c 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -23,6 +23,7 @@
#define AMBA_NR_IRQS 2
#define AMBA_CID 0xb105f00d
+#define CORESIGHT_CID 0xb105900d
struct clk;
diff --git a/include/linux/arm-cci.h b/include/linux/arm-cci.h
new file mode 100644
index 0000000..79d6edf
--- /dev/null
+++ b/include/linux/arm-cci.h
@@ -0,0 +1,61 @@
+/*
+ * CCI cache coherent interconnect support
+ *
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __LINUX_ARM_CCI_H
+#define __LINUX_ARM_CCI_H
+
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct device_node;
+
+#ifdef CONFIG_ARM_CCI
+extern bool cci_probed(void);
+extern int cci_ace_get_port(struct device_node *dn);
+extern int cci_disable_port_by_cpu(u64 mpidr);
+extern int __cci_control_port_by_device(struct device_node *dn, bool enable);
+extern int __cci_control_port_by_index(u32 port, bool enable);
+#else
+static inline bool cci_probed(void) { return false; }
+static inline int cci_ace_get_port(struct device_node *dn)
+{
+ return -ENODEV;
+}
+static inline int cci_disable_port_by_cpu(u64 mpidr) { return -ENODEV; }
+static inline int __cci_control_port_by_device(struct device_node *dn,
+ bool enable)
+{
+ return -ENODEV;
+}
+static inline int __cci_control_port_by_index(u32 port, bool enable)
+{
+ return -ENODEV;
+}
+#endif
+#define cci_disable_port_by_device(dev) \
+ __cci_control_port_by_device(dev, false)
+#define cci_enable_port_by_device(dev) \
+ __cci_control_port_by_device(dev, true)
+#define cci_disable_port_by_index(dev) \
+ __cci_control_port_by_index(dev, false)
+#define cci_enable_port_by_index(dev) \
+ __cci_control_port_by_index(dev, true)
+
+#endif
diff --git a/include/linux/arm-hdlcd.h b/include/linux/arm-hdlcd.h
new file mode 100644
index 0000000..939f3a8
--- /dev/null
+++ b/include/linux/arm-hdlcd.h
@@ -0,0 +1,122 @@
+/*
+ * include/linux/arm-hdlcd.h
+ *
+ * Copyright (C) 2011 ARM Limited
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details.
+ *
+ * ARM HDLCD Controller register definition
+ */
+
+#include <linux/fb.h>
+#include <linux/completion.h>
+
+/* register offsets */
+#define HDLCD_REG_VERSION 0x0000 /* ro */
+#define HDLCD_REG_INT_RAWSTAT 0x0010 /* rw */
+#define HDLCD_REG_INT_CLEAR 0x0014 /* wo */
+#define HDLCD_REG_INT_MASK 0x0018 /* rw */
+#define HDLCD_REG_INT_STATUS 0x001c /* ro */
+#define HDLCD_REG_USER_OUT 0x0020 /* rw */
+#define HDLCD_REG_FB_BASE 0x0100 /* rw */
+#define HDLCD_REG_FB_LINE_LENGTH 0x0104 /* rw */
+#define HDLCD_REG_FB_LINE_COUNT 0x0108 /* rw */
+#define HDLCD_REG_FB_LINE_PITCH 0x010c /* rw */
+#define HDLCD_REG_BUS_OPTIONS 0x0110 /* rw */
+#define HDLCD_REG_V_SYNC 0x0200 /* rw */
+#define HDLCD_REG_V_BACK_PORCH 0x0204 /* rw */
+#define HDLCD_REG_V_DATA 0x0208 /* rw */
+#define HDLCD_REG_V_FRONT_PORCH 0x020c /* rw */
+#define HDLCD_REG_H_SYNC 0x0210 /* rw */
+#define HDLCD_REG_H_BACK_PORCH 0x0214 /* rw */
+#define HDLCD_REG_H_DATA 0x0218 /* rw */
+#define HDLCD_REG_H_FRONT_PORCH 0x021c /* rw */
+#define HDLCD_REG_POLARITIES 0x0220 /* rw */
+#define HDLCD_REG_COMMAND 0x0230 /* rw */
+#define HDLCD_REG_PIXEL_FORMAT 0x0240 /* rw */
+#define HDLCD_REG_BLUE_SELECT 0x0244 /* rw */
+#define HDLCD_REG_GREEN_SELECT 0x0248 /* rw */
+#define HDLCD_REG_RED_SELECT 0x024c /* rw */
+
+/* version */
+#define HDLCD_PRODUCT_ID 0x1CDC0000
+#define HDLCD_PRODUCT_MASK 0xFFFF0000
+#define HDLCD_VERSION_MAJOR_MASK 0x0000FF00
+#define HDLCD_VERSION_MINOR_MASK 0x000000FF
+
+/* interrupts */
+#define HDLCD_INTERRUPT_DMA_END (1 << 0)
+#define HDLCD_INTERRUPT_BUS_ERROR (1 << 1)
+#define HDLCD_INTERRUPT_VSYNC (1 << 2)
+#define HDLCD_INTERRUPT_UNDERRUN (1 << 3)
+
+/* polarity */
+#define HDLCD_POLARITY_VSYNC (1 << 0)
+#define HDLCD_POLARITY_HSYNC (1 << 1)
+#define HDLCD_POLARITY_DATAEN (1 << 2)
+#define HDLCD_POLARITY_DATA (1 << 3)
+#define HDLCD_POLARITY_PIXELCLK (1 << 4)
+
+/* commands */
+#define HDLCD_COMMAND_DISABLE (0 << 0)
+#define HDLCD_COMMAND_ENABLE (1 << 0)
+
+/* pixel format */
+#define HDLCD_PIXEL_FMT_LITTLE_ENDIAN (0 << 31)
+#define HDLCD_PIXEL_FMT_BIG_ENDIAN (1 << 31)
+#define HDLCD_BYTES_PER_PIXEL_MASK (3 << 3)
+
+/* bus options */
+#define HDLCD_BUS_BURST_MASK 0x01f
+#define HDLCD_BUS_MAX_OUTSTAND 0xf00
+#define HDLCD_BUS_BURST_NONE (0 << 0)
+#define HDLCD_BUS_BURST_1 (1 << 0)
+#define HDLCD_BUS_BURST_2 (1 << 1)
+#define HDLCD_BUS_BURST_4 (1 << 2)
+#define HDLCD_BUS_BURST_8 (1 << 3)
+#define HDLCD_BUS_BURST_16 (1 << 4)
+
+/* Max resolution supported is 4096x4096, 8 bit per color component,
+ 8 bit alpha, but we are going to choose the usual hardware default
+ (2048x2048, 32 bpp) and enable double buffering */
+#define HDLCD_MAX_XRES 2048
+#define HDLCD_MAX_YRES 2048
+#define HDLCD_MAX_FRAMEBUFFER_SIZE (HDLCD_MAX_XRES * HDLCD_MAX_YRES << 2)
+
+#define HDLCD_MEM_BASE (CONFIG_PAGE_OFFSET - 0x1000000)
+
+#define NR_PALETTE 256
+
+/* OEMs using HDLCD may wish to enable these settings if
+ * display disruption is apparent and you suspect HDLCD
+ * access to RAM may be starved.
+ */
+/* Turn HDLCD default color red instead of black so
+ * that it's easy to see pixel clock data underruns
+ * (compared to other visual disruption)
+ */
+//#define HDLCD_RED_DEFAULT_COLOUR
+/* Add a counter in the IRQ handler to count buffer underruns
+ * and /proc/hdlcd_underrun to read the counter
+ */
+//#define HDLCD_COUNT_BUFFERUNDERRUNS
+/* Restrict height to 1x screen size
+ *
+ */
+//#define HDLCD_NO_VIRTUAL_SCREEN
+
+#ifdef CONFIG_ANDROID
+#define HDLCD_NO_VIRTUAL_SCREEN
+#endif
+
+struct hdlcd_device {
+ struct fb_info fb;
+ struct device *dev;
+ struct clk *clk;
+ void __iomem *base;
+ int irq;
+ struct completion vsync_completion;
+ unsigned char *edid;
+};
diff --git a/include/linux/audit.h b/include/linux/audit.h
index b20b038..4fb28b2 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -103,8 +103,11 @@
extern struct filename *__audit_reusename(const __user char *uptr);
extern void __audit_getname(struct filename *name);
extern void audit_putname(struct filename *name);
+
+#define AUDIT_INODE_PARENT 1 /* dentry represents the parent */
+#define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */
extern void __audit_inode(struct filename *name, const struct dentry *dentry,
- unsigned int parent);
+ unsigned int flags);
extern void __audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const unsigned char type);
@@ -132,7 +135,7 @@
{
if (unlikely(current->audit_context)) {
int success = is_syscall_success(pt_regs);
- int return_code = regs_return_value(pt_regs);
+ long return_code = regs_return_value(pt_regs);
__audit_syscall_exit(success, return_code);
}
@@ -148,10 +151,22 @@
if (unlikely(!audit_dummy_context()))
__audit_getname(name);
}
-static inline void audit_inode(struct filename *name, const struct dentry *dentry,
+static inline void audit_inode(struct filename *name,
+ const struct dentry *dentry,
unsigned int parent) {
+ if (unlikely(!audit_dummy_context())) {
+ unsigned int flags = 0;
+ if (parent)
+ flags |= AUDIT_INODE_PARENT;
+ __audit_inode(name, dentry, flags);
+ }
+}
+static inline void audit_inode_parent_hidden(struct filename *name,
+ const struct dentry *dentry)
+{
if (unlikely(!audit_dummy_context()))
- __audit_inode(name, dentry, parent);
+ __audit_inode(name, dentry,
+ AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN);
}
static inline void audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
@@ -311,7 +326,7 @@
{ }
static inline void __audit_inode(struct filename *name,
const struct dentry *dentry,
- unsigned int parent)
+ unsigned int flags)
{ }
static inline void __audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
@@ -321,6 +336,9 @@
const struct dentry *dentry,
unsigned int parent)
{ }
+static inline void audit_inode_parent_hidden(struct filename *name,
+ const struct dentry *dentry)
+{ }
static inline void audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const unsigned char type)
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 669fef5..3e0fbe4 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -3,6 +3,6 @@
#include <uapi/linux/auxvec.h>
-#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */
/* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
#endif /* _LINUX_AUXVEC_H */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c388155..4cfdbf2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -95,7 +95,7 @@
unsigned int max_ratio, max_prop_frac;
struct bdi_writeback wb; /* default writeback info for this bdi */
- spinlock_t wb_lock; /* protects work_list */
+ spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */
struct list_head work_list;
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index f7f1d71..089743a 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -159,6 +159,26 @@
}
/*
+ * isolated_balloon_page - identify an isolated balloon page on private
+ * compaction/migration page lists.
+ *
+ * After a compaction thread isolates a balloon page for migration, it raises
+ * the page refcount to prevent concurrent compaction threads from re-isolating
+ * the same page. For that reason putback_movable_pages(), or other routines
+ * that need to identify isolated balloon pages on private pagelists, cannot
+ * rely on balloon_page_movable() to accomplish the task.
+ */
+static inline bool isolated_balloon_page(struct page *page)
+{
+ /* Already isolated balloon pages, by default, have a raised refcount */
+ if (page_flags_cleared(page) && !page_mapped(page) &&
+ page_count(page) >= 2)
+ return __is_movable_balloon_page(page);
+
+ return false;
+}
+
+/*
* balloon_page_insert - insert a page into the balloon's page list and make
* the page->mapping assignment accordingly.
* @page : page to be assigned as a 'balloon page'
@@ -243,6 +263,11 @@
return false;
}
+static inline bool isolated_balloon_page(struct page *page)
+{
+ return false;
+}
+
static inline bool balloon_page_isolate(struct page *page)
{
return false;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 70cf138..df97ca4 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -99,9 +99,6 @@
extern void would_dump(struct linux_binprm *, struct file *);
extern int suid_dumpable;
-#define SUID_DUMP_DISABLE 0 /* No setuid dumping */
-#define SUID_DUMP_USER 1 /* Dump as user of process */
-#define SUID_DUMP_ROOT 2 /* Dump as root */
/* Stack area protections */
#define EXSTACK_DEFAULT 0 /* Whatever the arch defaults to */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3b6b82..be3a228 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -10,6 +10,14 @@
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
#endif
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) (((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l) (((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
extern unsigned int __sw_hweight32(unsigned int w);
@@ -185,6 +193,21 @@
#ifdef __KERNEL__
+#ifndef set_mask_bits
+#define set_mask_bits(ptr, _mask, _bits) \
+({ \
+ const typeof(*ptr) mask = (_mask), bits = (_bits); \
+ typeof(*ptr) old, new; \
+ \
+ do { \
+ old = ACCESS_ONCE(*ptr); \
+ new = (old & ~mask) | bits; \
+ } while (cmpxchg(ptr, old, new) != old); \
+ \
+ new; \
+})
+#endif
+
#ifndef find_last_bit
/**
* find_last_bit - find the last set bit in a memory region
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index fa1abeb..49c48dd 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -170,7 +170,9 @@
__REQ_ELVPRIV, /* elevator private data attached */
__REQ_FAILED, /* set if the request failed */
__REQ_QUIET, /* don't worry about errors */
- __REQ_PREEMPT, /* set for "ide_preempt" requests */
+ __REQ_PREEMPT, /* set for "ide_preempt" requests and also
+ for requests for which the SCSI "quiesce"
+ state must be ignored. */
__REQ_ALLOCED, /* request came from our alloc pool */
__REQ_COPY_USER, /* contains copies of user pages */
__REQ_FLUSH_SEQ, /* request for flush sequence */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2fdb4a4..494d228 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1187,10 +1187,9 @@
static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
{
unsigned int granularity = max(lim->physical_block_size, lim->io_min);
- unsigned int alignment = (sector << 9) & (granularity - 1);
+ unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
- return (granularity + lim->alignment_offset - alignment)
- & (granularity - 1);
+ return (granularity + lim->alignment_offset - alignment) % granularity;
}
static inline int bdev_alignment_offset(struct block_device *bdev)
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index 2f0543f..f9bbbb4 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -11,7 +11,9 @@
#define CAN_SKB_H
#include <linux/types.h>
+#include <linux/skbuff.h>
#include <linux/can.h>
+#include <net/sock.h>
/*
* The struct can_skb_priv is used to transport additional information along
@@ -42,4 +44,40 @@
skb_reserve(skb, sizeof(struct can_skb_priv));
}
+static inline void can_skb_destructor(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+
+static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
+{
+ if (sk) {
+ sock_hold(sk);
+ skb->destructor = can_skb_destructor;
+ skb->sk = sk;
+ }
+}
+
+/*
+ * returns an unshared skb owned by the original sock to be echo'ed back
+ */
+static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
+{
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ can_skb_set_owner(nskb, skb->sk);
+ consume_skb(skb);
+ return nskb;
+ } else {
+ kfree_skb(skb);
+ return NULL;
+ }
+ }
+
+ /* we can assume to have an unshared skb with proper owner */
+ return skb;
+}
+
#endif /* CAN_SKB_H */
diff --git a/include/linux/capability.h b/include/linux/capability.h
index d9a4f7f4..9b4378a 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -78,8 +78,11 @@
# error Fix up hand-coded capability macro initializers
#else /* HAND-CODED capability initializers */
+#define CAP_LAST_U32 ((_KERNEL_CAPABILITY_U32S) - 1)
+#define CAP_LAST_U32_VALID_MASK (CAP_TO_MASK(CAP_LAST_CAP + 1) -1)
+
# define CAP_EMPTY_SET ((kernel_cap_t){{ 0, 0 }})
-# define CAP_FULL_SET ((kernel_cap_t){{ ~0, ~0 }})
+# define CAP_FULL_SET ((kernel_cap_t){{ ~0, CAP_LAST_U32_VALID_MASK }})
# define CAP_FS_SET ((kernel_cap_t){{ CAP_FS_MASK_B0 \
| CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
CAP_FS_MASK_B1 } })
@@ -211,7 +214,7 @@
extern bool capable(int cap);
extern bool ns_capable(struct user_namespace *ns, int cap);
extern bool nsown_capable(int cap);
-extern bool inode_capable(const struct inode *inode, int cap);
+extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
/* audit system wants to get cap info from files as well */
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 379f715..a6ef9cc 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -8,23 +8,6 @@
#include <linux/ceph/types.h>
-/* This seemed to be the easiest place to define these */
-
-#define U8_MAX ((u8)(~0U))
-#define U16_MAX ((u16)(~0U))
-#define U32_MAX ((u32)(~0U))
-#define U64_MAX ((u64)(~0ULL))
-
-#define S8_MAX ((s8)(U8_MAX >> 1))
-#define S16_MAX ((s16)(U16_MAX >> 1))
-#define S32_MAX ((s32)(U32_MAX >> 1))
-#define S64_MAX ((s64)(U64_MAX >> 1LL))
-
-#define S8_MIN ((s8)(-S8_MAX - 1))
-#define S16_MIN ((s16)(-S16_MAX - 1))
-#define S32_MIN ((s32)(-S32_MAX - 1))
-#define S64_MIN ((s64)(-S64_MAX - 1LL))
-
/*
* in all cases,
* void **p pointer to position pointer
@@ -160,11 +143,6 @@
static inline void ceph_encode_timespec(struct ceph_timespec *tv,
const struct timespec *ts)
{
- BUG_ON(ts->tv_sec < 0);
- BUG_ON(ts->tv_sec > (__kernel_time_t)U32_MAX);
- BUG_ON(ts->tv_nsec < 0);
- BUG_ON(ts->tv_nsec > (long)U32_MAX);
-
tv->tv_sec = cpu_to_le32((u32)ts->tv_sec);
tv->tv_nsec = cpu_to_le32((u32)ts->tv_nsec);
}
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 7c1420b..6ade97de 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -157,7 +157,7 @@
bool front_is_vmalloc;
bool more_to_follow;
bool needs_out_seq;
- int front_max;
+ int front_alloc_len;
unsigned long ack_stamp; /* tx: when we were acked */
struct ceph_msgpool *pool;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 186db0b..4fb6a89 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -138,6 +138,7 @@
__le64 *r_request_pool;
void *r_request_pgid;
__le32 *r_request_attempts;
+ bool r_paused;
struct ceph_eversion *r_request_reassert_version;
int r_result;
@@ -145,7 +146,6 @@
s32 r_reply_op_result[CEPH_OSD_MAX_OP];
int r_got_reply;
int r_linger;
- int r_completed;
struct ceph_osd_client *r_osdc;
struct kref r_kref;
@@ -336,6 +336,8 @@
struct ceph_osd_request *req);
extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
+extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
+
extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
struct ceph_vino vino,
struct ceph_file_layout *layout,
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8bda129..8852d37 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -646,22 +646,60 @@
return cgrp->subsys[subsys_id];
}
-/*
- * function to get the cgroup_subsys_state which allows for extra
- * rcu_dereference_check() conditions, such as locks used during the
- * cgroup_subsys::attach() methods.
+/**
+ * task_css_set_check - obtain a task's css_set with extra access conditions
+ * @task: the task to obtain css_set for
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
+ *
+ * A task's css_set is RCU protected, initialized and exited while holding
+ * task_lock(), and can only be modified while holding both cgroup_mutex
+ * and task_lock() while the task is alive. This macro verifies that the
+ * caller is inside proper critical section and returns @task's css_set.
+ *
+ * The caller can also specify additional allowed conditions via @__c, such
+ * as locks used during the cgroup_subsys::attach() methods.
*/
#ifdef CONFIG_PROVE_RCU
extern struct mutex cgroup_mutex;
-#define task_subsys_state_check(task, subsys_id, __c) \
- rcu_dereference_check((task)->cgroups->subsys[(subsys_id)], \
- lockdep_is_held(&(task)->alloc_lock) || \
- lockdep_is_held(&cgroup_mutex) || (__c))
+#define task_css_set_check(task, __c) \
+ rcu_dereference_check((task)->cgroups, \
+ lockdep_is_held(&(task)->alloc_lock) || \
+ lockdep_is_held(&cgroup_mutex) || (__c))
#else
-#define task_subsys_state_check(task, subsys_id, __c) \
- rcu_dereference((task)->cgroups->subsys[(subsys_id)])
+#define task_css_set_check(task, __c) \
+ rcu_dereference((task)->cgroups)
#endif
+/**
+ * task_subsys_state_check - obtain css for (task, subsys) w/ extra access conds
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ * @__c: extra condition expression to be passed to rcu_dereference_check()
+ *
+ * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The
+ * synchronization rules are the same as task_css_set_check().
+ */
+#define task_subsys_state_check(task, subsys_id, __c) \
+ task_css_set_check((task), (__c))->subsys[(subsys_id)]
+
+/**
+ * task_css_set - obtain a task's css_set
+ * @task: the task to obtain css_set for
+ *
+ * See task_css_set_check().
+ */
+static inline struct css_set *task_css_set(struct task_struct *task)
+{
+ return task_css_set_check(task, false);
+}
+
+/**
+ * task_subsys_state - obtain css for (task, subsys)
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * See task_subsys_state_check().
+ */
static inline struct cgroup_subsys_state *
task_subsys_state(struct task_struct *task, int subsys_id)
{
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 1186098..89b7cee 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -257,6 +257,8 @@
* Some hardware implementations gracefully handle this case and allow a
* zero divisor by not modifying their input clock
* (divide by one / bypass).
+ * CLK_DIVIDER_ROUND_CLOSEST - Makes the best calculated divider to be rounded
+ * to the closest integer instead of the up one.
*/
struct clk_divider {
struct clk_hw hw;
@@ -271,6 +273,7 @@
#define CLK_DIVIDER_ONE_BASED BIT(0)
#define CLK_DIVIDER_POWER_OF_TWO BIT(1)
#define CLK_DIVIDER_ALLOW_ZERO BIT(2)
+#define CLK_DIVIDER_ROUND_CLOSEST BIT(4)
extern const struct clk_ops clk_divider_ops;
struct clk *clk_register_divider(struct device *dev, const char *name,
@@ -435,6 +438,7 @@
unsigned int clk_num;
};
struct clk *of_clk_src_onecell_get(struct of_phandle_args *clkspec, void *data);
+int of_clk_get_parent_count(struct device_node *np);
const char *of_clk_get_parent_name(struct device_node *np, int index);
void of_clk_init(const struct of_device_id *matches);
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 963d714..3abe1e9 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -30,6 +30,7 @@
#include <linux/notifier.h>
struct clock_event_device;
+struct module;
/* Clock event mode commands */
enum clock_event_mode {
@@ -60,6 +61,11 @@
*/
#define CLOCK_EVT_FEAT_DYNIRQ 0x000020
+/*
+ * Clockevent device is based on a hrtimer for broadcast
+ */
+#define CLOCK_EVT_FEAT_HRTIMER 0x000080
+
/**
* struct clock_event_device - clock event device descriptor
* @event_handler: Assigned by the framework to be called by the low
@@ -81,8 +87,10 @@
* @name: ptr to clock event name
* @rating: variable to rate clock event devices
* @irq: IRQ number (only for non CPU local devices)
+ * @bound_on: Bound on CPU
* @cpumask: cpumask to indicate for which CPUs this device works
* @list: list head for the management code
+ * @owner: module reference
*/
struct clock_event_device {
void (*event_handler)(struct clock_event_device *);
@@ -110,8 +118,10 @@
const char *name;
int rating;
int irq;
+ int bound_on;
const struct cpumask *cpumask;
struct list_head list;
+ struct module *owner;
} ____cacheline_aligned;
/*
@@ -150,7 +160,6 @@
struct clock_event_device *new);
extern void clockevents_set_mode(struct clock_event_device *dev,
enum clock_event_mode mode);
-extern int clockevents_register_notifier(struct notifier_block *nb);
extern int clockevents_program_event(struct clock_event_device *dev,
ktime_t expires, bool force);
@@ -176,15 +185,17 @@
#endif
#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+extern void tick_setup_hrtimer_broadcast(void);
extern int tick_check_broadcast_expired(void);
#else
static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
#endif
#ifdef CONFIG_GENERIC_CLOCKEVENTS
-extern void clockevents_notify(unsigned long reason, void *arg);
+extern int clockevents_notify(unsigned long reason, void *arg);
#else
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
#endif
#else /* CONFIG_GENERIC_CLOCKEVENTS_BUILD */
@@ -192,8 +203,9 @@
static inline void clockevents_suspend(void) {}
static inline void clockevents_resume(void) {}
-static inline void clockevents_notify(unsigned long reason, void *arg) {}
+static inline int clockevents_notify(unsigned long reason, void *arg) { return 0; }
static inline int tick_check_broadcast_expired(void) { return 0; }
+static inline void tick_setup_hrtimer_broadcast(void) {};
#endif
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7279b94..91aa89e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -285,7 +285,7 @@
extern void clocksource_change_rating(struct clocksource *cs, int rating);
extern void clocksource_suspend(void);
extern void clocksource_resume(void);
-extern struct clocksource * __init __weak clocksource_default_clock(void);
+extern struct clocksource * __init clocksource_default_clock(void);
extern void clocksource_mark_unstable(struct clocksource *cs);
extern void
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7f0c1dd..df70600 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -326,16 +326,16 @@
u32 arg2, u32 arg3, u32 arg4, u32 arg5);
asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
-asmlinkage ssize_t compat_sys_readv(unsigned long fd,
- const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_writev(unsigned long fd,
- const struct compat_iovec __user *vec, unsigned long vlen);
-asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
+asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd,
+ const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd,
+ const struct compat_iovec __user *vec, compat_ulong_t vlen);
+asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, u32 pos_low, u32 pos_high);
-asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, u32 pos_low, u32 pos_high);
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high);
asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int);
asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
@@ -421,7 +421,7 @@
asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
compat_long_t addr, compat_long_t data);
-asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, size_t);
+asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
/*
* epoll (fs/eventpoll.c) compat bits follow ...
*/
@@ -669,6 +669,13 @@
int compat_restore_altstack(const compat_stack_t __user *uss);
int __compat_save_altstack(compat_stack_t __user *, unsigned long);
+#define compat_save_altstack_ex(uss, sp) do { \
+ compat_stack_t __user *__uss = uss; \
+ struct task_struct *t = current; \
+ put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \
+ put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \
+ put_user_ex(t->sas_ss_size, &__uss->ss_size); \
+} while (0);
asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid,
struct compat_timespec __user *interval);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 24545cd..02ae99e 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -37,6 +37,9 @@
__asm__ ("" : "=r"(__ptr) : "0"(ptr)); \
(typeof(ptr)) (__ptr + (off)); })
+/* Make the optimizer believe the variable can be manipulated arbitrarily. */
+#define OPTIMIZER_HIDE_VAR(var) __asm__ ("" : "=r" (var) : "0" (var))
+
#ifdef __CHECKER__
#define __must_be_array(arr) 0
#else
diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index 842de22..2507fd2 100644
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -65,6 +65,17 @@
#define __visible __attribute__((externally_visible))
#endif
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
#if GCC_VERSION >= 40400
diff --git a/include/linux/compiler-gcc5.h b/include/linux/compiler-gcc5.h
new file mode 100644
index 0000000..cdd1cc2
--- /dev/null
+++ b/include/linux/compiler-gcc5.h
@@ -0,0 +1,66 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-gcc5.h> directly, include <linux/compiler.h> instead."
+#endif
+
+#define __used __attribute__((__used__))
+#define __must_check __attribute__((warn_unused_result))
+#define __compiler_offsetof(a, b) __builtin_offsetof(a, b)
+
+/* Mark functions as cold. gcc will assume any path leading to a call
+ to them will be unlikely. This means a lot of manual unlikely()s
+ are unnecessary now for any paths leading to the usual suspects
+ like BUG(), printk(), panic() etc. [but let's keep them for now for
+ older compilers]
+
+ Early snapshots of gcc 4.3 don't support this and we can't detect this
+ in the preprocessor, but we can live with this because they're unreleased.
+ Maketime probing would be overkill here.
+
+ gcc also has a __attribute__((__hot__)) to move hot functions into
+ a special section, but I don't see any sense in this right now in
+ the kernel context */
+#define __cold __attribute__((__cold__))
+
+#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+
+#ifndef __CHECKER__
+# define __compiletime_warning(message) __attribute__((warning(message)))
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* __CHECKER__ */
+
+/*
+ * Mark a position in code as unreachable. This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ *
+ * Early snapshots of gcc 4.5 don't support this and we can't detect
+ * this in the preprocessor, but we can live with this because they're
+ * unreleased. Really, we need to have autoconf for the kernel.
+ */
+#define unreachable() __builtin_unreachable()
+
+/* Mark a function definition as prohibited from being cloned. */
+#define __noclone __attribute__((__noclone__))
+
+/*
+ * Tell the optimizer that something else uses this function or variable.
+ */
+#define __visible __attribute__((externally_visible))
+
+/*
+ * GCC 'asm goto' miscompiles certain code sequences:
+ *
+ * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * Work it around via a compiler barrier quirk suggested by Jakub Jelinek.
+ * Fixed in GCC 4.8.2 and later versions.
+ *
+ * (asm goto is automatically volatile - the naming reflects this.)
+ */
+#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
+
+#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h
index 973ce10..5529c52 100644
--- a/include/linux/compiler-intel.h
+++ b/include/linux/compiler-intel.h
@@ -15,6 +15,7 @@
*/
#undef barrier
#undef RELOC_HIDE
+#undef OPTIMIZER_HIDE_VAR
#define barrier() __memory_barrier()
@@ -23,13 +24,17 @@
__ptr = (unsigned long) (ptr); \
(typeof(ptr)) (__ptr + (off)); })
+/* This should act as an optimization barrier on var.
+ * Given that this compiler does not have inline assembly, a compiler barrier
+ * is the best we can do.
+ */
+#define OPTIMIZER_HIDE_VAR(var) barrier()
+
/* Intel ECC compiler doesn't support __builtin_types_compatible_p() */
#define __must_be_array(a) 0
#endif
-#define uninitialized_var(x) x
-
#ifndef __HAVE_BUILTIN_BSWAP16__
/* icc has this, but it's called _bswap16 */
#define __HAVE_BUILTIN_BSWAP16__
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 92669cd..a2329c5 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -170,6 +170,10 @@
(typeof(ptr)) (__ptr + (off)); })
#endif
+#ifndef OPTIMIZER_HIDE_VAR
+#define OPTIMIZER_HIDE_VAR(var) barrier()
+#endif
+
/* Not-quite-unique ID. */
#ifndef __UNIQUE_ID
# define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
new file mode 100644
index 0000000..44c1597
--- /dev/null
+++ b/include/linux/coresight.h
@@ -0,0 +1,251 @@
+/* Copyright (c) 2012, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _LINUX_CORESIGHT_H
+#define _LINUX_CORESIGHT_H
+
+#include <linux/device.h>
+
+/* Peripheral id registers (0xFD0-0xFEC) */
+#define CORESIGHT_PERIPHIDR4 0xfd0
+#define CORESIGHT_PERIPHIDR5 0xfd4
+#define CORESIGHT_PERIPHIDR6 0xfd8
+#define CORESIGHT_PERIPHIDR7 0xfdC
+#define CORESIGHT_PERIPHIDR0 0xfe0
+#define CORESIGHT_PERIPHIDR1 0xfe4
+#define CORESIGHT_PERIPHIDR2 0xfe8
+#define CORESIGHT_PERIPHIDR3 0xfeC
+/* Component id registers (0xFF0-0xFFC) */
+#define CORESIGHT_COMPIDR0 0xff0
+#define CORESIGHT_COMPIDR1 0xff4
+#define CORESIGHT_COMPIDR2 0xff8
+#define CORESIGHT_COMPIDR3 0xffC
+
+#define ETM_ARCH_V3_3 0x23
+#define ETM_ARCH_V3_5 0x25
+#define PFT_ARCH_V1_0 0x30
+#define PFT_ARCH_V1_1 0x31
+
+#define CORESIGHT_UNLOCK 0xc5acce55
+
+extern struct bus_type coresight_bustype;
+
+enum coresight_dev_type {
+ CORESIGHT_DEV_TYPE_NONE,
+ CORESIGHT_DEV_TYPE_SINK,
+ CORESIGHT_DEV_TYPE_LINK,
+ CORESIGHT_DEV_TYPE_LINKSINK,
+ CORESIGHT_DEV_TYPE_SOURCE,
+};
+
+enum coresight_dev_subtype_sink {
+ CORESIGHT_DEV_SUBTYPE_SINK_NONE,
+ CORESIGHT_DEV_SUBTYPE_SINK_PORT,
+ CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
+};
+
+enum coresight_dev_subtype_link {
+ CORESIGHT_DEV_SUBTYPE_LINK_NONE,
+ CORESIGHT_DEV_SUBTYPE_LINK_MERG,
+ CORESIGHT_DEV_SUBTYPE_LINK_SPLIT,
+ CORESIGHT_DEV_SUBTYPE_LINK_FIFO,
+};
+
+enum coresight_dev_subtype_source {
+ CORESIGHT_DEV_SUBTYPE_SOURCE_NONE,
+ CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
+ CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
+ CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+};
+
+/**
+ * struct coresight_dev_subtype - further characterisation of a type
+ * @sink_subtype: type of sink this component is, as defined
+ by @coresight_dev_subtype_sink.
+ * @link_subtype: type of link this component is, as defined
+ by @coresight_dev_subtype_link.
+ * @source_subtype: type of source this component is, as defined
+ by @coresight_dev_subtype_source.
+ */
+struct coresight_dev_subtype {
+ enum coresight_dev_subtype_sink sink_subtype;
+ enum coresight_dev_subtype_link link_subtype;
+ enum coresight_dev_subtype_source source_subtype;
+};
+
+/**
+ * struct coresight_platform_data - data harvested from the DT specification
+ * @cpu: the CPU a source belongs to. Only applicable for ETM/PTMs.
+ * @name: name of the component as shown under sysfs.
+ * @nr_inport: number of input ports for this component.
+ * @outports: list of remote enpoint port number.
+ * @child_names:name of all child components connected to this device.
+ * @child_ports:child component port number the current component is
+ connected to.
+ * @nr_outport: number of output ports for this component.
+ * @clk: The clock this component is associated to.
+ */
+struct coresight_platform_data {
+ int cpu;
+ const char *name;
+ int nr_inport;
+ int *outports;
+ const char **child_names;
+ int *child_ports;
+ int nr_outport;
+ struct clk *clk;
+};
+
+/**
+ * struct coresight_desc - description of a component required from drivers
+ * @type: as defined by @coresight_dev_type.
+ * @subtype: as defined by @coresight_dev_subtype.
+ * @ops: generic operations for this component, as defined
+ by @coresight_ops.
+ * @pdata: platform data collected from DT.
+ * @dev: The device entity associated to this component.
+ * @groups :operations specific to this component. These will end up
+ in the component's sysfs sub-directory.
+ */
+struct coresight_desc {
+ enum coresight_dev_type type;
+ struct coresight_dev_subtype subtype;
+ const struct coresight_ops *ops;
+ struct coresight_platform_data *pdata;
+ struct device *dev;
+ const struct attribute_group **groups;
+};
+
+/**
+ * struct coresight_connection - representation of a single connection
+ * @ref_count: keeping count a port' references.
+ * @outport: a connection's output port number.
+ * @chid_name: remote component's name.
+ * @child_port: remote component's port number @output is connected to.
+ * @child_dev: a @coresight_device representation of the component
+ connected to @outport.
+ */
+struct coresight_connection {
+ int outport;
+ const char *child_name;
+ int child_port;
+ struct coresight_device *child_dev;
+};
+
+/**
+ * struct coresight_device - representation of a device as used by the framework
+ * @nr_inport: number of input port associated to this component.
+ * @nr_outport: number of output port associated to this component.
+ * @type: as defined by @coresight_dev_type.
+ * @subtype: as defined by @coresight_dev_subtype.
+ * @ops: generic operations for this component, as defined
+ by @coresight_ops.
+ * @dev: The device entity associated to this component.
+ * @refcnt: keep track of what is in use.
+ * @path_link: link of current component into the path being enabled.
+ * @orphan: true if the component has connections that haven't been linked.
+ * @enable: 'true' if component is currently part of an active path.
+ * @activated: 'true' only if a _sink_ has been activated. A sink can be
+ activated but not yet enabled. Enabling for a _sink_
+ happens when a source has been selected for that it.
+ */
+struct coresight_device {
+ struct coresight_connection *conns;
+ int nr_inport;
+ int nr_outport;
+ enum coresight_dev_type type;
+ struct coresight_dev_subtype subtype;
+ const struct coresight_ops *ops;
+ struct device dev;
+ atomic_t *refcnt;
+ struct list_head path_link;
+ bool orphan;
+ bool enable; /* true only if configured as part of a path */
+ bool activated; /* true only if a sink is part of a path */
+};
+
+#define to_coresight_device(d) container_of(d, struct coresight_device, dev)
+
+#define source_ops(csdev) csdev->ops->source_ops
+#define sink_ops(csdev) csdev->ops->sink_ops
+#define link_ops(csdev) csdev->ops->link_ops
+
+/**
+ * struct coresight_ops_sink - basic operations for a sink
+ * Operations available for sinks
+ * @enable: enables the sink.
+ * @disable: disables the sink.
+ */
+struct coresight_ops_sink {
+ int (*enable)(struct coresight_device *csdev);
+ void (*disable)(struct coresight_device *csdev);
+};
+
+/**
+ * struct coresight_ops_link - basic operations for a link
+ * Operations available for links.
+ * @enable: enables flow between iport and oport.
+ * @disable: disables flow between iport and oport.
+ */
+struct coresight_ops_link {
+ int (*enable)(struct coresight_device *csdev, int iport, int oport);
+ void (*disable)(struct coresight_device *csdev, int iport, int oport);
+};
+
+/**
+ * struct coresight_ops_source - basic operations for a source
+ * Operations available for sources.
+ * @trace_id: returns the value of the component's trace ID as known
+ to the HW.
+ * @enable: enables tracing from a source.
+ * @disable: disables tracing for a source.
+ */
+struct coresight_ops_source {
+ int (*trace_id)(struct coresight_device *csdev);
+ int (*enable)(struct coresight_device *csdev);
+ void (*disable)(struct coresight_device *csdev);
+};
+
+struct coresight_ops {
+ const struct coresight_ops_sink *sink_ops;
+ const struct coresight_ops_link *link_ops;
+ const struct coresight_ops_source *source_ops;
+};
+
+#ifdef CONFIG_CORESIGHT
+extern struct coresight_device *
+coresight_register(struct coresight_desc *desc);
+extern void coresight_unregister(struct coresight_device *csdev);
+extern int coresight_enable(struct coresight_device *csdev);
+extern void coresight_disable(struct coresight_device *csdev);
+extern int coresight_timeout(void __iomem *addr, u32 offset,
+ int position, int value);
+#else
+static inline struct coresight_device *
+coresight_register(struct coresight_desc *desc) { return NULL; }
+static inline void coresight_unregister(struct coresight_device *csdev) {}
+static inline int
+coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
+static inline void coresight_disable(struct coresight_device *csdev) {}
+static inline int coresight_timeout(void __iomem *addr, u32 offset,
+ int position, int value) { return 1; }
+#endif
+
+#ifdef CONFIG_OF
+extern struct coresight_platform_data *of_get_coresight_platform_data(
+ struct device *dev, struct device_node *node);
+#else
+static inline struct coresight_platform_data *of_get_coresight_platform_data(
+ struct device *dev, struct device_node *node) { return NULL; }
+#endif
+
+#endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 9f3c7e8..770c804 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -29,6 +29,7 @@
extern int register_cpu(struct cpu *cpu, int num);
extern struct device *get_cpu_device(unsigned cpu);
extern bool cpu_is_hotpluggable(unsigned cpu);
+extern bool arch_match_cpu_phys_id(int cpu, u64 phys_id);
extern int cpu_add_dev_attr(struct device_attribute *attr);
extern void cpu_remove_dev_attr(struct device_attribute *attr);
@@ -119,26 +120,46 @@
{ .notifier_call = fn, .priority = pri }; \
register_cpu_notifier(&fn##_nb); \
}
+
+#define __cpu_notifier(fn, pri) { \
+ static struct notifier_block fn##_nb = \
+ { .notifier_call = fn, .priority = pri }; \
+ __register_cpu_notifier(&fn##_nb); \
+}
#else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0)
#endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+
#ifdef CONFIG_HOTPLUG_CPU
extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
extern void unregister_cpu_notifier(struct notifier_block *nb);
+extern void __unregister_cpu_notifier(struct notifier_block *nb);
#else
#ifndef MODULE
extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
#else
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
+
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
#endif
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
+
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
#endif
int cpu_up(unsigned int cpu);
@@ -146,19 +167,32 @@
extern void cpu_maps_update_begin(void);
extern void cpu_maps_update_done(void);
+#define cpu_notifier_register_begin cpu_maps_update_begin
+#define cpu_notifier_register_done cpu_maps_update_done
+
#else /* CONFIG_SMP */
#define cpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri) do { (void)(fn); } while (0)
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+ return 0;
+}
+
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
+
static inline void cpu_maps_update_begin(void)
{
}
@@ -167,6 +201,14 @@
{
}
+static inline void cpu_notifier_register_begin(void)
+{
+}
+
+static inline void cpu_notifier_register_done(void)
+{
+}
+
#endif /* CONFIG_SMP */
extern struct bus_type cpu_subsys;
@@ -178,8 +220,11 @@
extern void cpu_hotplug_disable(void);
extern void cpu_hotplug_enable(void);
#define hotcpu_notifier(fn, pri) cpu_notifier(fn, pri)
+#define __hotcpu_notifier(fn, pri) __cpu_notifier(fn, pri)
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
+#define __register_hotcpu_notifier(nb) __register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
+#define __unregister_hotcpu_notifier(nb) __unregister_cpu_notifier(nb)
void clear_tasks_mm_cpumask(int cpu);
int cpu_down(unsigned int cpu);
@@ -203,9 +248,12 @@
#define cpu_hotplug_disable() do { } while (0)
#define cpu_hotplug_enable() do { } while (0)
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
+#define __hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
+#define __register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotcpu_notifier(nb) ({ (void)(nb); })
+#define __unregister_hotcpu_notifier(nb) ({ (void)(nb); })
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index 282e270..c303d38 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -24,6 +24,7 @@
#ifndef __CPU_COOLING_H__
#define __CPU_COOLING_H__
+#include <linux/of.h>
#include <linux/thermal.h>
#include <linux/cpumask.h>
@@ -36,25 +37,49 @@
cpufreq_cooling_register(const struct cpumask *clip_cpus);
/**
+ * of_cpufreq_cooling_register - create cpufreq cooling device based on DT.
+ * @np: a valid struct device_node to the cooling device device tree node.
+ * @clip_cpus: cpumask of cpus where the frequency constraints will happen
+ */
+#ifdef CONFIG_THERMAL_OF
+struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus);
+#else
+static inline struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus)
+{
+ return NULL;
+}
+#endif
+
+/**
* cpufreq_cooling_unregister - function to remove cpufreq cooling device.
* @cdev: thermal cooling device pointer.
*/
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev);
-unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int);
+unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq);
#else /* !CONFIG_CPU_THERMAL */
static inline struct thermal_cooling_device *
cpufreq_cooling_register(const struct cpumask *clip_cpus)
{
return NULL;
}
+static inline struct thermal_cooling_device *
+of_cpufreq_cooling_register(struct device_node *np,
+ const struct cpumask *clip_cpus)
+{
+ return NULL;
+}
static inline
void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
{
return;
}
static inline
-unsigned long cpufreq_cooling_get_level(unsigned int, unsigned int)
+unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq)
{
return THERMAL_CSTATE_INVALID;
}
diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h
new file mode 100644
index 0000000..c4d4eb8
--- /dev/null
+++ b/include/linux/cpufeature.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CPUFEATURE_H
+#define __LINUX_CPUFEATURE_H
+
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+
+#include <linux/mod_devicetable.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Macros imported from <asm/cpufeature.h>:
+ * - cpu_feature(x) ordinal value of feature called 'x'
+ * - cpu_have_feature(u32 n) whether feature #n is available
+ * - MAX_CPU_FEATURES upper bound for feature ordinal values
+ * Optional:
+ * - CPU_FEATURE_TYPEFMT format string fragment for printing the cpu type
+ * - CPU_FEATURE_TYPEVAL set of values matching the format string above
+ */
+
+#ifndef CPU_FEATURE_TYPEFMT
+#define CPU_FEATURE_TYPEFMT "%s"
+#endif
+
+#ifndef CPU_FEATURE_TYPEVAL
+#define CPU_FEATURE_TYPEVAL ELF_PLATFORM
+#endif
+
+/*
+ * Use module_cpu_feature_match(feature, module_init_function) to
+ * declare that
+ * a) the module shall be probed upon discovery of CPU feature 'feature'
+ * (typically at boot time using udev)
+ * b) the module must not be loaded if CPU feature 'feature' is not present
+ * (not even by manual insmod).
+ *
+ * For a list of legal values for 'feature', please consult the file
+ * 'asm/cpufeature.h' of your favorite architecture.
+ */
+#define module_cpu_feature_match(x, __init) \
+static struct cpu_feature const cpu_feature_match_ ## x[] = \
+ { { .feature = cpu_feature(x) }, { } }; \
+MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x); \
+ \
+static int cpu_feature_match_ ## x ## _init(void) \
+{ \
+ if (!cpu_have_feature(cpu_feature(x))) \
+ return -ENODEV; \
+ return __init(); \
+} \
+module_init(cpu_feature_match_ ## x ## _init)
+
+#endif
+#endif
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 037d36a..1a81b74 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -107,6 +107,7 @@
unsigned int policy; /* see above */
struct cpufreq_governor *governor; /* see below */
void *governor_data;
+ bool governor_enabled; /* governor start/stop flag */
struct work_struct update; /* if update_policy() needs to be
* called, but you're in IRQ context */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 8f04062..1312cde 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -111,6 +111,7 @@
struct cpuidle_state states[CPUIDLE_STATE_MAX];
int state_count;
int safe_state_index;
+ struct cpumask *cpumask;
};
#ifdef CONFIG_CPU_IDLE
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 04421e8..6c58dd7 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -68,6 +68,7 @@
extern int set_current_groups(struct group_info *);
extern int set_groups(struct cred *, struct group_info *);
extern int groups_search(const struct group_info *, kgid_t);
+extern bool may_setgroups(void);
/* access the groups "array" with this macro */
#define GROUP_AT(gi, i) \
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index b92eadf..2b00d92 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -26,6 +26,19 @@
#include <linux/uaccess.h>
/*
+ * Autoloaded crypto modules should only use a prefixed name to avoid allowing
+ * arbitrary modules to be loaded. Loading from userspace may still need the
+ * unprefixed names, so retains those aliases as well.
+ * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3
+ * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro
+ * expands twice on the same line. Instead, use a separate base name for the
+ * alias.
+ */
+#define MODULE_ALIAS_CRYPTO(name) \
+ __MODULE_INFO(alias, alias_userspace, name); \
+ __MODULE_INFO(alias, alias_crypto, "crypto-" name)
+
+/*
* Algorithm masks and types.
*/
#define CRYPTO_ALG_TYPE_MASK 0x0000000f
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1a6bb81f..c1999d1 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -120,15 +120,15 @@
void *d_fsdata; /* fs-specific data */
struct list_head d_lru; /* LRU list */
+ struct list_head d_child; /* child of parent list */
+ struct list_head d_subdirs; /* our children */
/*
- * d_child and d_rcu can share memory
+ * d_alias and d_rcu can share memory
*/
union {
- struct list_head d_child; /* child of parent list */
+ struct hlist_node d_alias; /* inode alias list */
struct rcu_head d_rcu;
} d_u;
- struct list_head d_subdirs; /* our children */
- struct hlist_node d_alias; /* inode alias list */
};
/*
@@ -332,6 +332,7 @@
* helper function for dentry_operations.d_dname() members
*/
extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
+extern char *simple_dname(struct dentry *, char *, int);
extern char *__d_path(const struct path *, const struct path *, char *, int);
extern char *d_absolute_path(const struct path *, char *, int);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 3cd3247..ef5bd3f 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -405,13 +405,14 @@
union map_info *dm_get_mapinfo(struct bio *bio);
union map_info *dm_get_rq_mapinfo(struct request *rq);
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
+
/*
* Geometry functions.
*/
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo);
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
-
/*-----------------------------------------------------------------
* Functions for manipulating device-mapper tables.
*---------------------------------------------------------------*/
diff --git a/include/linux/device.h b/include/linux/device.h
index c0a1261..3425de2 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -26,6 +26,7 @@
#include <linux/atomic.h>
#include <linux/ratelimit.h>
#include <linux/uidgid.h>
+#include <linux/gfp.h>
#include <asm/device.h>
struct device;
@@ -47,7 +48,11 @@
};
#define BUS_ATTR(_name, _mode, _show, _store) \
-struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
+ struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define BUS_ATTR_RW(_name) \
+ struct bus_attribute bus_attr_##_name = __ATTR_RW(_name)
+#define BUS_ATTR_RO(_name) \
+ struct bus_attribute bus_attr_##_name = __ATTR_RO(_name)
extern int __must_check bus_create_file(struct bus_type *,
struct bus_attribute *);
@@ -253,9 +258,14 @@
size_t count);
};
-#define DRIVER_ATTR(_name, _mode, _show, _store) \
-struct driver_attribute driver_attr_##_name = \
- __ATTR(_name, _mode, _show, _store)
+#define DRIVER_ATTR(_name, _mode, _show, _store) \
+ struct driver_attribute driver_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define DRIVER_ATTR_RW(_name) \
+ struct driver_attribute driver_attr_##_name = __ATTR_RW(_name)
+#define DRIVER_ATTR_RO(_name) \
+ struct driver_attribute driver_attr_##_name = __ATTR_RO(_name)
+#define DRIVER_ATTR_WO(_name) \
+ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name)
extern int __must_check driver_create_file(struct device_driver *driver,
const struct driver_attribute *attr);
@@ -406,8 +416,12 @@
const struct class_attribute *attr);
};
-#define CLASS_ATTR(_name, _mode, _show, _store) \
-struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define CLASS_ATTR(_name, _mode, _show, _store) \
+ struct class_attribute class_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define CLASS_ATTR_RW(_name) \
+ struct class_attribute class_attr_##_name = __ATTR_RW(_name)
+#define CLASS_ATTR_RO(_name) \
+ struct class_attribute class_attr_##_name = __ATTR_RO(_name)
extern int __must_check class_create_file(struct class *class,
const struct class_attribute *attr);
@@ -415,7 +429,6 @@
const struct class_attribute *attr);
/* Simple class attribute that is just a static string */
-
struct class_attribute_string {
struct class_attribute attr;
char *str;
@@ -504,6 +517,12 @@
#define DEVICE_ATTR(_name, _mode, _show, _store) \
struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
+#define DEVICE_ATTR_RW(_name) \
+ struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
+#define DEVICE_ATTR_RO(_name) \
+ struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
+#define DEVICE_ATTR_WO(_name) \
+ struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
#define DEVICE_ULONG_ATTR(_name, _mode, _var) \
struct dev_ext_attribute dev_attr_##_name = \
{ __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) }
@@ -568,8 +587,24 @@
extern void devres_remove_group(struct device *dev, void *id);
extern int devres_release_group(struct device *dev, void *id);
-/* managed kzalloc/kfree for device drivers, no kmalloc, always use kzalloc */
-extern void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp);
+/* managed devm_k.alloc/kfree for device drivers */
+extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
+static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+{
+ return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+static inline void *devm_kmalloc_array(struct device *dev,
+ size_t n, size_t size, gfp_t flags)
+{
+ if (size != 0 && n > SIZE_MAX / size)
+ return NULL;
+ return devm_kmalloc(dev, n * size, flags);
+}
+static inline void *devm_kcalloc(struct device *dev,
+ size_t n, size_t size, gfp_t flags)
+{
+ return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
extern void devm_kfree(struct device *dev, void *p);
void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res);
@@ -698,7 +733,7 @@
struct dma_coherent_mem *dma_mem; /* internal for coherent mem
override */
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
struct cma *cma_area; /* contiguous memory area for dma
allocations */
#endif
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index 01b5c84..3b28f93 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -57,7 +57,7 @@
struct page;
struct device;
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
/*
* There is always at least global CMA area and a few optional device
@@ -67,9 +67,53 @@
extern struct cma *dma_contiguous_default_area;
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+ if (dev && dev->cma_area)
+ return dev->cma_area;
+ return dma_contiguous_default_area;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
+{
+ if (dev)
+ dev->cma_area = cma;
+}
+
+static inline void dma_contiguous_set_default(struct cma *cma)
+{
+ dma_contiguous_default_area = cma;
+}
+
void dma_contiguous_reserve(phys_addr_t addr_limit);
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
- phys_addr_t base, phys_addr_t limit);
+
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+ phys_addr_t limit, struct cma **res_cma);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ * for particular device
+ * @dev: Pointer to device structure.
+ * @size: Size of the reserved memory.
+ * @base: Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+
+static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
+ phys_addr_t base, phys_addr_t limit)
+{
+ struct cma *cma;
+ int ret;
+ ret = dma_contiguous_reserve_area(size, base, limit, &cma);
+ if (ret == 0)
+ dev_set_cma_area(dev, cma);
+
+ return ret;
+}
struct page *dma_alloc_from_contiguous(struct device *dev, int count,
unsigned int order);
@@ -80,8 +124,22 @@
#define MAX_CMA_AREAS (0)
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+ return NULL;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
+
+static inline void dma_contiguous_set_default(struct cma *cma) { }
+
static inline void dma_contiguous_reserve(phys_addr_t limit) { }
+static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+ phys_addr_t limit, struct cma **res_cma) {
+ return -ENOSYS;
+}
+
static inline
int dma_declare_contiguous(struct device *dev, phys_addr_t size,
phys_addr_t base, phys_addr_t limit)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 94af418..48ef6f5 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -97,6 +97,30 @@
}
#endif
+/*
+ * Set both the DMA mask and the coherent DMA mask to the same thing.
+ * Note that we don't check the return value from dma_set_coherent_mask()
+ * as the DMA API guarantees that the coherent DMA mask can be set to
+ * the same or smaller than the streaming DMA mask.
+ */
+static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask)
+{
+ int rc = dma_set_mask(dev, mask);
+ if (rc == 0)
+ dma_set_coherent_mask(dev, mask);
+ return rc;
+}
+
+/*
+ * Similar to the above, except it deals with the case where the device
+ * does not have dev->dma_mask appropriately setup.
+ */
+static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
+{
+ dev->dma_mask = &dev->coherent_dma_mask;
+ return dma_set_mask_and_coherent(dev, mask);
+}
+
extern u64 dma_get_required_mask(struct device *dev);
static inline unsigned int dma_get_max_seg_size(struct device *dev)
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 0b76327..5c6d7fb 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -622,7 +622,7 @@
*/
struct mem_ctl_info {
struct device dev;
- struct bus_type bus;
+ struct bus_type *bus;
struct list_head link; /* for global list of mem_ctl_info structs */
@@ -742,4 +742,9 @@
#endif
};
+/*
+ * Maximum number of memory controllers in the coherent fabric.
+ */
+#define EDAC_MAX_MCS 16
+
#endif
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 2bc0ad7..ae3426a 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -39,6 +39,8 @@
typedef unsigned long efi_status_t;
typedef u8 efi_bool_t;
typedef u16 efi_char16_t; /* UNICODE character */
+typedef u64 efi_physical_addr_t;
+typedef void *efi_handle_t;
typedef struct {
@@ -96,6 +98,7 @@
#define EFI_MEMORY_DESCRIPTOR_VERSION 1
#define EFI_PAGE_SHIFT 12
+#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
typedef struct {
u32 type;
@@ -150,6 +153,102 @@
u8 sets_to_zero;
} efi_time_cap_t;
+typedef struct {
+ efi_table_hdr_t hdr;
+ u32 raise_tpl;
+ u32 restore_tpl;
+ u32 allocate_pages;
+ u32 free_pages;
+ u32 get_memory_map;
+ u32 allocate_pool;
+ u32 free_pool;
+ u32 create_event;
+ u32 set_timer;
+ u32 wait_for_event;
+ u32 signal_event;
+ u32 close_event;
+ u32 check_event;
+ u32 install_protocol_interface;
+ u32 reinstall_protocol_interface;
+ u32 uninstall_protocol_interface;
+ u32 handle_protocol;
+ u32 __reserved;
+ u32 register_protocol_notify;
+ u32 locate_handle;
+ u32 locate_device_path;
+ u32 install_configuration_table;
+ u32 load_image;
+ u32 start_image;
+ u32 exit;
+ u32 unload_image;
+ u32 exit_boot_services;
+ u32 get_next_monotonic_count;
+ u32 stall;
+ u32 set_watchdog_timer;
+ u32 connect_controller;
+ u32 disconnect_controller;
+ u32 open_protocol;
+ u32 close_protocol;
+ u32 open_protocol_information;
+ u32 protocols_per_handle;
+ u32 locate_handle_buffer;
+ u32 locate_protocol;
+ u32 install_multiple_protocol_interfaces;
+ u32 uninstall_multiple_protocol_interfaces;
+ u32 calculate_crc32;
+ u32 copy_mem;
+ u32 set_mem;
+ u32 create_event_ex;
+} __packed efi_boot_services_32_t;
+
+typedef struct {
+ efi_table_hdr_t hdr;
+ u64 raise_tpl;
+ u64 restore_tpl;
+ u64 allocate_pages;
+ u64 free_pages;
+ u64 get_memory_map;
+ u64 allocate_pool;
+ u64 free_pool;
+ u64 create_event;
+ u64 set_timer;
+ u64 wait_for_event;
+ u64 signal_event;
+ u64 close_event;
+ u64 check_event;
+ u64 install_protocol_interface;
+ u64 reinstall_protocol_interface;
+ u64 uninstall_protocol_interface;
+ u64 handle_protocol;
+ u64 __reserved;
+ u64 register_protocol_notify;
+ u64 locate_handle;
+ u64 locate_device_path;
+ u64 install_configuration_table;
+ u64 load_image;
+ u64 start_image;
+ u64 exit;
+ u64 unload_image;
+ u64 exit_boot_services;
+ u64 get_next_monotonic_count;
+ u64 stall;
+ u64 set_watchdog_timer;
+ u64 connect_controller;
+ u64 disconnect_controller;
+ u64 open_protocol;
+ u64 close_protocol;
+ u64 open_protocol_information;
+ u64 protocols_per_handle;
+ u64 locate_handle_buffer;
+ u64 locate_protocol;
+ u64 install_multiple_protocol_interfaces;
+ u64 uninstall_multiple_protocol_interfaces;
+ u64 calculate_crc32;
+ u64 copy_mem;
+ u64 set_mem;
+ u64 create_event_ex;
+} __packed efi_boot_services_64_t;
+
/*
* EFI Boot Services table
*/
@@ -157,11 +256,13 @@
efi_table_hdr_t hdr;
void *raise_tpl;
void *restore_tpl;
- void *allocate_pages;
- void *free_pages;
- void *get_memory_map;
- void *allocate_pool;
- void *free_pool;
+ efi_status_t (*allocate_pages)(int, int, unsigned long,
+ efi_physical_addr_t *);
+ efi_status_t (*free_pages)(efi_physical_addr_t, unsigned long);
+ efi_status_t (*get_memory_map)(unsigned long *, void *, unsigned long *,
+ unsigned long *, u32 *);
+ efi_status_t (*allocate_pool)(int, unsigned long, void **);
+ efi_status_t (*free_pool)(void *);
void *create_event;
void *set_timer;
void *wait_for_event;
@@ -171,7 +272,7 @@
void *install_protocol_interface;
void *reinstall_protocol_interface;
void *uninstall_protocol_interface;
- void *handle_protocol;
+ efi_status_t (*handle_protocol)(efi_handle_t, efi_guid_t *, void **);
void *__reserved;
void *register_protocol_notify;
void *locate_handle;
@@ -181,7 +282,7 @@
void *start_image;
void *exit;
void *unload_image;
- void *exit_boot_services;
+ efi_status_t (*exit_boot_services)(efi_handle_t, unsigned long);
void *get_next_monotonic_count;
void *stall;
void *set_watchdog_timer;
@@ -226,6 +327,15 @@
EfiPciIoAttributeOperationMaximum
} EFI_PCI_IO_PROTOCOL_ATTRIBUTE_OPERATION;
+typedef struct {
+ u32 read;
+ u32 write;
+} efi_pci_io_protocol_access_32_t;
+
+typedef struct {
+ u64 read;
+ u64 write;
+} efi_pci_io_protocol_access_64_t;
typedef struct {
void *read;
@@ -233,6 +343,46 @@
} efi_pci_io_protocol_access_t;
typedef struct {
+ u32 poll_mem;
+ u32 poll_io;
+ efi_pci_io_protocol_access_32_t mem;
+ efi_pci_io_protocol_access_32_t io;
+ efi_pci_io_protocol_access_32_t pci;
+ u32 copy_mem;
+ u32 map;
+ u32 unmap;
+ u32 allocate_buffer;
+ u32 free_buffer;
+ u32 flush;
+ u32 get_location;
+ u32 attributes;
+ u32 get_bar_attributes;
+ u32 set_bar_attributes;
+ uint64_t romsize;
+ void *romimage;
+} efi_pci_io_protocol_32;
+
+typedef struct {
+ u64 poll_mem;
+ u64 poll_io;
+ efi_pci_io_protocol_access_64_t mem;
+ efi_pci_io_protocol_access_64_t io;
+ efi_pci_io_protocol_access_64_t pci;
+ u64 copy_mem;
+ u64 map;
+ u64 unmap;
+ u64 allocate_buffer;
+ u64 free_buffer;
+ u64 flush;
+ u64 get_location;
+ u64 attributes;
+ u64 get_bar_attributes;
+ u64 set_bar_attributes;
+ uint64_t romsize;
+ void *romimage;
+} efi_pci_io_protocol_64;
+
+typedef struct {
void *poll_mem;
void *poll_io;
efi_pci_io_protocol_access_t mem;
@@ -287,20 +437,56 @@
typedef struct {
efi_table_hdr_t hdr;
- unsigned long get_time;
- unsigned long set_time;
- unsigned long get_wakeup_time;
- unsigned long set_wakeup_time;
- unsigned long set_virtual_address_map;
- unsigned long convert_pointer;
- unsigned long get_variable;
- unsigned long get_next_variable;
- unsigned long set_variable;
- unsigned long get_next_high_mono_count;
- unsigned long reset_system;
- unsigned long update_capsule;
- unsigned long query_capsule_caps;
- unsigned long query_variable_info;
+ u32 get_time;
+ u32 set_time;
+ u32 get_wakeup_time;
+ u32 set_wakeup_time;
+ u32 set_virtual_address_map;
+ u32 convert_pointer;
+ u32 get_variable;
+ u32 get_next_variable;
+ u32 set_variable;
+ u32 get_next_high_mono_count;
+ u32 reset_system;
+ u32 update_capsule;
+ u32 query_capsule_caps;
+ u32 query_variable_info;
+} efi_runtime_services_32_t;
+
+typedef struct {
+ efi_table_hdr_t hdr;
+ u64 get_time;
+ u64 set_time;
+ u64 get_wakeup_time;
+ u64 set_wakeup_time;
+ u64 set_virtual_address_map;
+ u64 convert_pointer;
+ u64 get_variable;
+ u64 get_next_variable;
+ u64 set_variable;
+ u64 get_next_high_mono_count;
+ u64 reset_system;
+ u64 update_capsule;
+ u64 query_capsule_caps;
+ u64 query_variable_info;
+} efi_runtime_services_64_t;
+
+typedef struct {
+ efi_table_hdr_t hdr;
+ void *get_time;
+ void *set_time;
+ void *get_wakeup_time;
+ void *set_wakeup_time;
+ void *set_virtual_address_map;
+ void *convert_pointer;
+ void *get_variable;
+ void *get_next_variable;
+ void *set_variable;
+ void *get_next_high_mono_count;
+ void *reset_system;
+ void *update_capsule;
+ void *query_capsule_caps;
+ void *query_variable_info;
} efi_runtime_services_t;
typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc);
@@ -389,6 +575,9 @@
#define EFI_FILE_SYSTEM_GUID \
EFI_GUID( 0x964e5b22, 0x6459, 0x11d2, 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b )
+#define DEVICE_TREE_GUID \
+ EFI_GUID( 0xb1b621d5, 0xf19c, 0x41a5, 0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0 )
+
typedef struct {
efi_guid_t guid;
u64 table;
@@ -404,6 +593,12 @@
unsigned long table;
} efi_config_table_t;
+typedef struct {
+ efi_guid_t guid;
+ const char *name;
+ unsigned long *ptr;
+} efi_config_table_type_t;
+
#define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL)
#define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30))
@@ -472,6 +667,46 @@
unsigned long desc_size;
};
+struct efi_fdt_params {
+ u64 system_table;
+ u64 mmap;
+ u32 mmap_size;
+ u32 desc_size;
+ u32 desc_ver;
+};
+
+typedef struct {
+ u32 revision;
+ u32 parent_handle;
+ u32 system_table;
+ u32 device_handle;
+ u32 file_path;
+ u32 reserved;
+ u32 load_options_size;
+ u32 load_options;
+ u32 image_base;
+ __aligned_u64 image_size;
+ unsigned int image_code_type;
+ unsigned int image_data_type;
+ unsigned long unload;
+} efi_loaded_image_32_t;
+
+typedef struct {
+ u32 revision;
+ u64 parent_handle;
+ u64 system_table;
+ u64 device_handle;
+ u64 file_path;
+ u64 reserved;
+ u32 load_options_size;
+ u64 load_options;
+ u64 image_base;
+ __aligned_u64 image_size;
+ unsigned int image_code_type;
+ unsigned int image_data_type;
+ unsigned long unload;
+} efi_loaded_image_64_t;
+
typedef struct {
u32 revision;
void *parent_handle;
@@ -488,10 +723,6 @@
unsigned long unload;
} efi_loaded_image_t;
-typedef struct {
- u64 revision;
- void *open_volume;
-} efi_file_io_interface_t;
typedef struct {
u64 size;
@@ -506,18 +737,56 @@
typedef struct {
u64 revision;
- void *open;
- void *close;
+ u32 open;
+ u32 close;
+ u32 delete;
+ u32 read;
+ u32 write;
+ u32 get_position;
+ u32 set_position;
+ u32 get_info;
+ u32 set_info;
+ u32 flush;
+} efi_file_handle_32_t;
+
+typedef struct {
+ u64 revision;
+ u64 open;
+ u64 close;
+ u64 delete;
+ u64 read;
+ u64 write;
+ u64 get_position;
+ u64 set_position;
+ u64 get_info;
+ u64 set_info;
+ u64 flush;
+} efi_file_handle_64_t;
+
+typedef struct _efi_file_handle {
+ u64 revision;
+ efi_status_t (*open)(struct _efi_file_handle *,
+ struct _efi_file_handle **,
+ efi_char16_t *, u64, u64);
+ efi_status_t (*close)(struct _efi_file_handle *);
void *delete;
- void *read;
+ efi_status_t (*read)(struct _efi_file_handle *, unsigned long *,
+ void *);
void *write;
void *get_position;
void *set_position;
- void *get_info;
+ efi_status_t (*get_info)(struct _efi_file_handle *, efi_guid_t *,
+ unsigned long *, void *);
void *set_info;
void *flush;
} efi_file_handle_t;
+typedef struct _efi_file_io_interface {
+ u64 revision;
+ int (*open_volume)(struct _efi_file_io_interface *,
+ efi_file_handle_t **);
+} efi_file_io_interface_t;
+
#define EFI_FILE_MODE_READ 0x0000000000000001
#define EFI_FILE_MODE_WRITE 0x0000000000000002
#define EFI_FILE_MODE_CREATE 0x8000000000000000
@@ -552,6 +821,8 @@
efi_get_next_high_mono_count_t *get_next_high_mono_count;
efi_reset_system_t *reset_system;
efi_set_virtual_address_map_t *set_virtual_address_map;
+ struct efi_memory_map *memmap;
+ unsigned long flags;
} efi;
static inline int
@@ -587,6 +858,7 @@
}
#endif
extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
+extern int efi_config_init(efi_config_table_type_t *arch_tables);
extern u64 efi_get_iobase (void);
extern u32 efi_mem_type (unsigned long phys_addr);
extern u64 efi_mem_attributes (unsigned long phys_addr);
@@ -597,8 +869,15 @@
extern unsigned long efi_get_time(void);
extern int efi_set_rtc_mmss(unsigned long nowtime);
extern void efi_reserve_boot_services(void);
+extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose);
extern struct efi_memory_map memmap;
+/* Iterate through an efi_memory_map */
+#define for_each_efi_memory_desc(m, md) \
+ for ((md) = (m)->map; \
+ (md) <= (efi_memory_desc_t *)((m)->map_end - (m)->desc_size); \
+ (md) = (void *)(md) + (m)->desc_size)
+
/**
* efi_range_is_wc - check the WC bit on an address range
* @start: starting kvirt address
@@ -636,18 +915,17 @@
#define EFI_64BIT 5 /* Is the firmware 64-bit? */
#ifdef CONFIG_EFI
-# ifdef CONFIG_X86
-extern int efi_enabled(int facility);
-# else
-static inline int efi_enabled(int facility)
+/*
+ * Test whether the above EFI_* bits are enabled.
+ */
+static inline bool efi_enabled(int feature)
{
- return 1;
+ return test_bit(feature, &efi.flags) != 0;
}
-# endif
#else
-static inline int efi_enabled(int facility)
+static inline bool efi_enabled(int feature)
{
- return 0;
+ return false;
}
#endif
@@ -769,8 +1047,10 @@
* and we use a page for reading/writing.
*/
+#define EFI_VAR_NAME_LEN 1024
+
struct efi_variable {
- efi_char16_t VariableName[1024/sizeof(efi_char16_t)];
+ efi_char16_t VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)];
efi_guid_t VendorGuid;
unsigned long DataSize;
__u8 Data[1024];
@@ -782,6 +1062,26 @@
struct efi_variable var;
struct list_head list;
struct kobject kobj;
+ bool scanning;
+ bool deleting;
+};
+
+struct efi_simple_text_output_protocol_32 {
+ u32 reset;
+ u32 output_string;
+ u32 test_string;
+};
+
+struct efi_simple_text_output_protocol_64 {
+ u64 reset;
+ u64 output_string;
+ u64 test_string;
+};
+
+struct efi_simple_text_output_protocol {
+ void *reset;
+ efi_status_t (*output_string)(void *, void *);
+ void *test_string;
};
extern struct list_head efivar_sysfs_list;
@@ -832,7 +1132,7 @@
struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
struct list_head *head, bool remove);
-bool efivar_validate(struct efi_variable *var, u8 *data, unsigned long len);
+bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
extern struct work_struct efivar_work;
void efivar_run_worker(void);
@@ -840,6 +1140,8 @@
#if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE)
int efivars_sysfs_init(void);
+#define EFIVARS_DATA_SIZE_MAX 1024
+
#endif /* CONFIG_EFI_VARS */
#endif /* _LINUX_EFI_H */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index acd0312..306dd8c 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -7,6 +7,7 @@
#ifdef CONFIG_BLOCK
struct io_cq;
+struct elevator_type;
typedef int (elevator_merge_fn) (struct request_queue *, struct request **,
struct bio *);
@@ -35,7 +36,8 @@
typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *);
typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *);
-typedef int (elevator_init_fn) (struct request_queue *);
+typedef int (elevator_init_fn) (struct request_queue *,
+ struct elevator_type *e);
typedef void (elevator_exit_fn) (struct elevator_queue *);
struct elevator_ops
@@ -155,6 +157,8 @@
extern void elevator_exit(struct elevator_queue *);
extern int elevator_change(struct request_queue *, const char *);
extern bool elv_rq_merge_ok(struct request *, struct bio *);
+extern struct elevator_queue *elevator_alloc(struct request_queue *,
+ struct elevator_type *);
/*
* Helper functions.
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 191501a..5d838bf 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -200,6 +200,7 @@
unsigned irmc:1;
unsigned bc_implemented:2;
+ work_func_t workfn;
struct delayed_work work;
struct fw_attribute_group attribute_group;
};
@@ -434,6 +435,7 @@
int type;
int channel;
int speed;
+ bool drop_overflow_headers;
size_t header_size;
union {
fw_iso_callback_t sc;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65c2be2..d57bc5d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2489,6 +2489,7 @@
extern int vfs_getattr(struct path *, struct kstat *);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes);
+void __inode_sub_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index a78680a..661c0ae 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -101,8 +101,10 @@
new_dir_mask |= FS_ISDIR;
}
- fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
- fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+ fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name,
+ fs_cookie);
+ fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name,
+ fs_cookie);
if (target)
fsnotify_link_count(target);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 99d0fbc..38eb5db 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -524,6 +524,7 @@
extern int ftrace_arch_read_dyn_info(char *buf, int size);
extern int skip_trace(unsigned long ip);
+extern void ftrace_module_init(struct module *mod);
extern void ftrace_disable_daemon(void);
extern void ftrace_enable_daemon(void);
@@ -533,6 +534,7 @@
static inline void ftrace_disable_daemon(void) { }
static inline void ftrace_enable_daemon(void) { }
static inline void ftrace_release_mod(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) {}
static inline int register_ftrace_command(struct ftrace_func_command *cmd)
{
return -EINVAL;
@@ -609,25 +611,27 @@
#endif
}
-#ifndef HAVE_ARCH_CALLER_ADDR
+/* All archs should have this, but we define it for consistency */
+#ifndef ftrace_return_address0
+# define ftrace_return_address0 __builtin_return_address(0)
+#endif
+
+/* Archs may use other ways for ADDR1 and beyond */
+#ifndef ftrace_return_address
# ifdef CONFIG_FRAME_POINTER
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+# define ftrace_return_address(n) __builtin_return_address(n)
# else
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 0UL
-# define CALLER_ADDR2 0UL
-# define CALLER_ADDR3 0UL
-# define CALLER_ADDR4 0UL
-# define CALLER_ADDR5 0UL
-# define CALLER_ADDR6 0UL
+# define ftrace_return_address(n) 0UL
# endif
-#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
+#endif
+
+#define CALLER_ADDR0 ((unsigned long)ftrace_return_address0)
+#define CALLER_ADDR1 ((unsigned long)ftrace_return_address(1))
+#define CALLER_ADDR2 ((unsigned long)ftrace_return_address(2))
+#define CALLER_ADDR3 ((unsigned long)ftrace_return_address(3))
+#define CALLER_ADDR4 ((unsigned long)ftrace_return_address(4))
+#define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
+#define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
#ifdef CONFIG_IRQSOFF_TRACER
extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4372658..b5e3601 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -78,6 +78,11 @@
/* trace_seq for __print_flags() and __print_symbolic() etc. */
struct trace_seq tmp_seq;
+ cpumask_var_t started;
+
+ /* it's true when current open file is snapshot */
+ bool snapshot;
+
/* The below is zeroed out in pipe_read */
struct trace_seq seq;
struct trace_entry *ent;
@@ -90,10 +95,7 @@
loff_t pos;
long idx;
- cpumask_var_t started;
-
- /* it's true when current open file is snapshot */
- bool snapshot;
+ /* All new field here will be zeroed out in pipe_read */
};
enum trace_iter_flags {
@@ -323,16 +325,12 @@
FILTER_TRACE_FN,
};
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
extern int trace_event_raw_init(struct ftrace_event_call *call);
extern int trace_define_field(struct ftrace_event_call *call, const char *type,
const char *name, int offset, int size,
int is_signed, int filter_type);
extern int trace_add_event_call(struct ftrace_event_call *call);
-extern void trace_remove_event_call(struct ftrace_event_call *call);
+extern int trace_remove_event_call(struct ftrace_event_call *call);
#define is_signed_type(type) (((type)(-1)) < (type)1)
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b0d95ca..6435f46 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,7 +55,11 @@
#ifdef CONFIG_FUTEX
extern void exit_robust_list(struct task_struct *curr);
extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
extern int futex_cmpxchg_enabled;
+#endif
#else
static inline void exit_robust_list(struct task_struct *curr)
{
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index 661d374..9e8986a 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -66,8 +66,8 @@
struct list_head next_chunk; /* next chunk in pool */
atomic_t avail;
phys_addr_t phys_addr; /* physical starting address of memory chunk */
- unsigned long start_addr; /* starting address of memory chunk */
- unsigned long end_addr; /* ending address of memory chunk */
+ unsigned long start_addr; /* start address of memory chunk */
+ unsigned long end_addr; /* end address of memory chunk (inclusive) */
unsigned long bits[0]; /* bitmap for allocating memory chunk */
};
@@ -106,6 +106,10 @@
extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr, void *data);
+extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+ unsigned long size, unsigned long start, unsigned int nr,
+ void *data);
+
extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
unsigned long start, unsigned int nr, void *data);
@@ -113,6 +117,9 @@
int min_alloc_order, int nid);
extern struct gen_pool *dev_get_gen_pool(struct device *dev);
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+ size_t size);
+
#ifdef CONFIG_OF
extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
const char *propname, int index);
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 0c48991..4f8aa47 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -393,10 +393,12 @@
struct hid_device *device; /* associated device */
};
+#define HID_MAX_IDS 256
+
struct hid_report_enum {
unsigned numbered;
struct list_head report_list;
- struct hid_report *report_id_hash[256];
+ struct hid_report *report_id_hash[HID_MAX_IDS];
};
#define HID_REPORT_TYPES 3
@@ -744,9 +746,14 @@
unsigned int hidinput_count_leds(struct hid_device *hid);
__s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code);
void hid_output_report(struct hid_report *report, __u8 *data);
+u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags);
struct hid_device *hid_allocate_device(void);
struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id);
int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size);
+struct hid_report *hid_validate_values(struct hid_device *hid,
+ unsigned int type, unsigned int id,
+ unsigned int field_index,
+ unsigned int report_counts);
int hid_open_report(struct hid_device *device);
int hid_check_keys_pressed(struct hid_device *hid);
int hid_connect(struct hid_device *hid, unsigned int connect_mask);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 528454c..3d36eb0 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -123,7 +123,7 @@
} while (0)
extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
pmd_t *pmd);
-#if HPAGE_PMD_ORDER > MAX_ORDER
+#if HPAGE_PMD_ORDER >= MAX_ORDER
#error "hugepages can't be allocated by the buddy allocator"
#endif
extern int hugepage_madvise(struct vm_area_struct *vma,
@@ -159,23 +159,6 @@
return HPAGE_PMD_NR;
return 1;
}
-static inline struct page *compound_trans_head(struct page *page)
-{
- if (PageTail(page)) {
- struct page *head;
- head = page->first_page;
- smp_rmb();
- /*
- * head may be a dangling pointer.
- * __split_huge_page_refcount clears PageTail before
- * overwriting first_page, so if PageTail is still
- * there it means the head pointer isn't dangling.
- */
- if (PageTail(page))
- return head;
- }
- return page;
-}
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
@@ -205,7 +188,6 @@
do { } while (0)
#define split_huge_page_pmd_mm(__mm, __address, __pmd) \
do { } while (0)
-#define compound_trans_head(page) compound_head(page)
static inline int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
{
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6b4890f..dca09c0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -31,6 +31,7 @@
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page_head);
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -69,6 +70,10 @@
int dequeue_hwpoisoned_huge_page(struct page *page);
void copy_huge_page(struct page *dst, struct page *src);
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
+#endif
+
extern unsigned long hugepages_treat_as_movable;
extern const unsigned long hugetlb_zero, hugetlb_infinity;
extern int sysctl_hugetlb_shm_group;
@@ -98,6 +103,11 @@
return 0;
}
+static inline int PageHeadHuge(struct page *page_head)
+{
+ return 0;
+}
+
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
@@ -358,6 +368,17 @@
return h - hstates;
}
+pgoff_t __basepage_index(struct page *page);
+
+/* Return page->index in PAGE_SIZE units */
+static inline pgoff_t basepage_index(struct page *page)
+{
+ if (!PageCompound(page))
+ return page->index;
+
+ return __basepage_index(page);
+}
+
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
@@ -378,6 +399,11 @@
}
#define hstate_index_to_shift(index) 0
#define hstate_index(h) 0
+
+static inline pgoff_t basepage_index(struct page *page)
+{
+ return page->index;
+}
#endif /* CONFIG_HUGETLB_PAGE */
#endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c255984..422eac8 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -483,15 +483,18 @@
* 0 . 13 (Windows Server 2008)
* 1 . 1 (Windows 7)
* 2 . 4 (Windows 8)
+ * 3 . 0 (Windows 8 R2)
*/
#define VERSION_WS2008 ((0 << 16) | (13))
#define VERSION_WIN7 ((1 << 16) | (1))
#define VERSION_WIN8 ((2 << 16) | (4))
+#define VERSION_WIN8_1 ((3 << 16) | (0))
+
#define VERSION_INVAL -1
-#define VERSION_CURRENT VERSION_WIN8
+#define VERSION_CURRENT VERSION_WIN8_1
/* Make maximum size of pipe payload of 16K */
#define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384)
@@ -894,7 +897,7 @@
struct vmbus_channel_initiate_contact {
struct vmbus_channel_message_header header;
u32 vmbus_version_requested;
- u32 padding2;
+ u32 target_vcpu; /* The VCPU the host should respond to */
u64 interrupt_page;
u64 monitor_page1;
u64 monitor_page2;
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index e988fa9..2189189 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -542,6 +542,26 @@
#endif /* I2C */
+#if IS_ENABLED(CONFIG_OF)
+/* must call put_device() when done with returned i2c_client device */
+extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node);
+
+/* must call put_device() when done with returned i2c_adapter device */
+extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node);
+
+#else
+
+static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
+{
+ return NULL;
+}
+
+static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node)
+{
+ return NULL;
+}
+#endif /* CONFIG_OF */
+
#if IS_ENABLED(CONFIG_ACPI_I2C)
extern void acpi_i2c_register_devices(struct i2c_adapter *adap);
#else
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 16fae64..25b8b15 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -193,6 +193,7 @@
bool user_carrier_enabled;
bool queue_override_enabled;
struct list_head *qom_lists; /* array of queue override mapping lists */
+ bool port_mtu_change_allowed;
long mode_priv[TEAM_MODE_PRIV_LONGS];
};
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 637fa71d..0b34988 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -79,9 +79,8 @@
}
#define vlan_tx_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT)
-#define vlan_tx_nonzero_tag_present(__skb) \
- (vlan_tx_tag_present(__skb) && ((__skb)->vlan_tci & VLAN_VID_MASK))
#define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
+#define vlan_tx_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK)
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h
index 13ce220..593ae7c 100644
--- a/include/linux/iio/events.h
+++ b/include/linux/iio/events.h
@@ -90,7 +90,7 @@
#define IIO_EVENT_CODE_EXTRACT_TYPE(mask) ((mask >> 56) & 0xFF)
-#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0xCF)
+#define IIO_EVENT_CODE_EXTRACT_DIR(mask) ((mask >> 48) & 0x7F)
#define IIO_EVENT_CODE_EXTRACT_CHAN_TYPE(mask) ((mask >> 32) & 0xFF)
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 8d171f4..3d35b70 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -211,8 +211,8 @@
static inline bool iio_channel_has_info(const struct iio_chan_spec *chan,
enum iio_chan_info_enum type)
{
- return (chan->info_mask_separate & type) |
- (chan->info_mask_shared_by_type & type);
+ return (chan->info_mask_separate & BIT(type)) |
+ (chan->info_mask_shared_by_type & BIT(type));
}
#define IIO_ST(si, rb, sb, sh) \
diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index 3869c52..545deb1 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -83,10 +83,12 @@
put_device(&trig->dev);
}
-static inline void iio_trigger_get(struct iio_trigger *trig)
+static inline struct iio_trigger *iio_trigger_get(struct iio_trigger *trig)
{
get_device(&trig->dev);
__module_get(trig->ops->owner);
+
+ return trig;
}
/**
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ea1e3b8..770ecc9 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -261,7 +261,7 @@
static __inline__ __be32 inet_make_mask(int logmask)
{
if (logmask)
- return htonl(~((1<<(32-logmask))-1));
+ return htonl(~((1U<<(32-logmask))-1));
return 0;
}
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 5cd0f09..998f4df 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -40,6 +40,7 @@
#define INIT_SIGNALS(sig) { \
.nr_threads = 1, \
+ .thread_head = LIST_HEAD_INIT(init_task.thread_node), \
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
@@ -213,6 +214,7 @@
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
}, \
.thread_group = LIST_HEAD_INIT(tsk.thread_group), \
+ .thread_node = LIST_HEAD_INIT(init_signals.thread_head), \
INIT_IDS \
INIT_PERF_EVENTS(tsk) \
INIT_TRACE_IRQFLAGS \
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5fa5afe..6de0f2c 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -239,7 +239,40 @@
extern cpumask_var_t irq_default_affinity;
-extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+/* Internal implementation. Use the helpers below */
+extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
+ bool force);
+
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq: Interrupt to set affinity
+ * @mask: cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+static inline int
+irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+ return __irq_set_affinity(irq, cpumask, false);
+}
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq: Interrupt to set affinity
+ * @mask: cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+static inline int
+irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+ return __irq_set_affinity(irq, cpumask, true);
+}
+
extern int irq_can_set_affinity(unsigned int irq);
extern int irq_select_affinity(unsigned int irq);
@@ -275,6 +308,11 @@
return -EINVAL;
}
+static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+ return 0;
+}
+
static inline int irq_can_set_affinity(unsigned int irq)
{
return 0;
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index c4d870b..d6ad91f 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -22,7 +22,7 @@
int in_use;
unsigned short seq;
unsigned short seq_max;
- struct rw_semaphore rw_mutex;
+ struct rw_semaphore rwsem;
struct idr ipcs_idr;
int next_id;
};
@@ -34,9 +34,9 @@
int sem_ctls[4];
int used_sems;
- int msg_ctlmax;
- int msg_ctlmnb;
- int msg_ctlmni;
+ unsigned int msg_ctlmax;
+ unsigned int msg_ctlmnb;
+ unsigned int msg_ctlmni;
atomic_t msg_bytes;
atomic_t msg_hdrs;
int auto_msgmni;
@@ -119,9 +119,7 @@
* the new maximum will handle anyone else. I may have to revisit this
* in the future.
*/
-#define MIN_QUEUESMAX 1
#define DFLT_QUEUESMAX 256
-#define HARD_QUEUESMAX 1024
#define MIN_MSGMAX 1
#define DFLT_MSG 10U
#define DFLT_MSGMAX 10
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 850e95b..b8b7dc7 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -101,6 +101,7 @@
#define IP6SKB_FORWARDED 2
#define IP6SKB_REROUTED 4
#define IP6SKB_ROUTERALERT 8
+#define IP6SKB_FRAGMENTED 16
};
#define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb))
diff --git a/include/linux/irq.h b/include/linux/irq.h
index bc4e066..d591bfe 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -375,7 +375,8 @@
extern void irq_cpu_online(void);
extern void irq_cpu_offline(void);
-extern int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask);
+extern int irq_set_affinity_locked(struct irq_data *data,
+ const struct cpumask *cpumask, bool force);
#ifdef CONFIG_GENERIC_HARDIRQS
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
new file mode 100644
index 0000000..03a4ea3
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
+ */
+#define GICD_CTLR 0x0000
+#define GICD_TYPER 0x0004
+#define GICD_IIDR 0x0008
+#define GICD_STATUSR 0x0010
+#define GICD_SETSPI_NSR 0x0040
+#define GICD_CLRSPI_NSR 0x0048
+#define GICD_SETSPI_SR 0x0050
+#define GICD_CLRSPI_SR 0x0058
+#define GICD_SEIR 0x0068
+#define GICD_ISENABLER 0x0100
+#define GICD_ICENABLER 0x0180
+#define GICD_ISPENDR 0x0200
+#define GICD_ICPENDR 0x0280
+#define GICD_ISACTIVER 0x0300
+#define GICD_ICACTIVER 0x0380
+#define GICD_IPRIORITYR 0x0400
+#define GICD_ICFGR 0x0C00
+#define GICD_IROUTER 0x6000
+#define GICD_PIDR2 0xFFE8
+
+#define GICD_CTLR_RWP (1U << 31)
+#define GICD_CTLR_ARE_NS (1U << 4)
+#define GICD_CTLR_ENABLE_G1A (1U << 1)
+#define GICD_CTLR_ENABLE_G1 (1U << 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE (0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY (1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK 0xf0
+#define GIC_PIDR2_ARCH_GICv3 0x30
+#define GIC_PIDR2_ARCH_GICv4 0x40
+
+/*
+ * Re-Distributor registers, offsets from RD_base
+ */
+#define GICR_CTLR GICD_CTLR
+#define GICR_IIDR 0x0004
+#define GICR_TYPER 0x0008
+#define GICR_STATUSR GICD_STATUSR
+#define GICR_WAKER 0x0014
+#define GICR_SETLPIR 0x0040
+#define GICR_CLRLPIR 0x0048
+#define GICR_SEIR GICD_SEIR
+#define GICR_PROPBASER 0x0070
+#define GICR_PENDBASER 0x0078
+#define GICR_INVLPIR 0x00A0
+#define GICR_INVALLR 0x00B0
+#define GICR_SYNCR 0x00C0
+#define GICR_MOVLPIR 0x0100
+#define GICR_MOVALLR 0x0110
+#define GICR_PIDR2 GICD_PIDR2
+
+#define GICR_WAKER_ProcessorSleep (1U << 1)
+#define GICR_WAKER_ChildrenAsleep (1U << 2)
+
+/*
+ * Re-Distributor registers, offsets from SGI_base
+ */
+#define GICR_ISENABLER0 GICD_ISENABLER
+#define GICR_ICENABLER0 GICD_ICENABLER
+#define GICR_ISPENDR0 GICD_ISPENDR
+#define GICR_ICPENDR0 GICD_ICPENDR
+#define GICR_ISACTIVER0 GICD_ISACTIVER
+#define GICR_ICACTIVER0 GICD_ICACTIVER
+#define GICR_IPRIORITYR0 GICD_IPRIORITYR
+#define GICR_ICFGR0 GICD_ICFGR
+
+#define GICR_TYPER_VLPIS (1U << 1)
+#define GICR_TYPER_LAST (1U << 4)
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_drop_dir (0U << 1)
+#define ICC_CTLR_EL1_EOImode_drop (1U << 1)
+#define ICC_SRE_EL1_SRE (1U << 0)
+
+/*
+ * Hypervisor interface registers (SRE only)
+ */
+#define ICH_LR_VIRTUAL_ID_MASK ((1UL << 32) - 1)
+
+#define ICH_LR_EOI (1UL << 41)
+#define ICH_LR_GROUP (1UL << 60)
+#define ICH_LR_STATE (3UL << 62)
+#define ICH_LR_PENDING_BIT (1UL << 62)
+#define ICH_LR_ACTIVE_BIT (1UL << 63)
+
+#define ICH_MISR_EOI (1 << 0)
+#define ICH_MISR_U (1 << 1)
+
+#define ICH_HCR_EN (1 << 0)
+#define ICH_HCR_UIE (1 << 1)
+
+#define ICH_VMCR_CTLR_SHIFT 0
+#define ICH_VMCR_CTLR_MASK (0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT 18
+#define ICH_VMCR_BPR1_MASK (7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT 21
+#define ICH_VMCR_BPR0_MASK (7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT 24
+#define ICH_VMCR_PMR_MASK (0xffUL << ICH_VMCR_PMR_SHIFT)
+
+#define ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_IAR1_EL1_SPURIOUS 0x3ff
+
+#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
+
+#define ICC_SRE_EL2_SRE (1 << 0)
+#define ICC_SRE_EL2_ENABLE (1 << 3)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x) sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x) sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2 __LR0_EL2(0)
+#define ICH_LR1_EL2 __LR0_EL2(1)
+#define ICH_LR2_EL2 __LR0_EL2(2)
+#define ICH_LR3_EL2 __LR0_EL2(3)
+#define ICH_LR4_EL2 __LR0_EL2(4)
+#define ICH_LR5_EL2 __LR0_EL2(5)
+#define ICH_LR6_EL2 __LR0_EL2(6)
+#define ICH_LR7_EL2 __LR0_EL2(7)
+#define ICH_LR8_EL2 __LR8_EL2(0)
+#define ICH_LR9_EL2 __LR8_EL2(1)
+#define ICH_LR10_EL2 __LR8_EL2(2)
+#define ICH_LR11_EL2 __LR8_EL2(3)
+#define ICH_LR12_EL2 __LR8_EL2(4)
+#define ICH_LR13_EL2 __LR8_EL2(5)
+#define ICH_LR14_EL2 __LR8_EL2(6)
+#define ICH_LR15_EL2 __LR8_EL2(7)
+
+#define __AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2 __AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2 __AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2 __AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2 __AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2 __AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2 __AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2 __AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2 __AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+static inline void gic_write_eoir(u64 irq)
+{
+ asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
+ isb();
+}
+
+#endif
+
+#endif
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 3e203eb..1f004b1 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -17,6 +17,11 @@
#define GIC_CPU_EOI 0x10
#define GIC_CPU_RUNNINGPRI 0x14
#define GIC_CPU_HIGHPRI 0x18
+#define GIC_CPU_ALIAS_BINPOINT 0x1c
+#define GIC_CPU_ACTIVEPRIO 0xd0
+#define GIC_CPU_IDENT 0xfc
+
+#define GICC_IAR_INT_ID_MASK 0x3ff
#define GIC_DIST_CTRL 0x000
#define GIC_DIST_CTR 0x004
@@ -31,6 +36,8 @@
#define GIC_DIST_TARGET 0x800
#define GIC_DIST_CONFIG 0xc00
#define GIC_DIST_SOFTINT 0xf00
+#define GIC_DIST_SGI_PENDING_CLEAR 0xf10
+#define GIC_DIST_SGI_PENDING_SET 0xf20
#define GICH_HCR 0x0
#define GICH_VTR 0x4
@@ -54,6 +61,15 @@
#define GICH_LR_ACTIVE_BIT (1 << 29)
#define GICH_LR_EOI (1 << 19)
+#define GICH_VMCR_CTRL_SHIFT 0
+#define GICH_VMCR_CTRL_MASK (0x21f << GICH_VMCR_CTRL_SHIFT)
+#define GICH_VMCR_PRIMASK_SHIFT 27
+#define GICH_VMCR_PRIMASK_MASK (0x1f << GICH_VMCR_PRIMASK_SHIFT)
+#define GICH_VMCR_BINPOINT_SHIFT 21
+#define GICH_VMCR_BINPOINT_MASK (0x7 << GICH_VMCR_BINPOINT_SHIFT)
+#define GICH_VMCR_ALIAS_BINPOINT_SHIFT 18
+#define GICH_VMCR_ALIAS_BINPOINT_MASK (0x7 << GICH_VMCR_ALIAS_BINPOINT_SHIFT)
+
#define GICH_MISR_EOI (1 << 0)
#define GICH_MISR_U (1 << 1)
@@ -66,6 +82,9 @@
void gic_init_bases(unsigned int, int, void __iomem *, void __iomem *,
u32 offset, struct device_node *);
void gic_cascade_irq(unsigned int gic_nr, unsigned int irq);
+void gic_cpu_if_down(void);
+
+void gic_cpu_if_down(void);
static inline void gic_init(unsigned int nr, int start,
void __iomem *dist , void __iomem *cpu)
@@ -73,6 +92,16 @@
gic_init_bases(nr, start, dist, cpu, 0, NULL);
}
-#endif /* __ASSEMBLY */
+void gic_send_sgi(unsigned int cpu_id, unsigned int irq);
+int gic_get_cpu_id(unsigned int cpu);
+void gic_migrate_target(unsigned int new_cpu_id);
+unsigned long gic_get_sgir_physaddr(void);
+extern const struct irq_domain_ops *gic_routable_irq_domain_ops;
+static inline void __init register_routable_domain_ops
+ (const struct irq_domain_ops *ops)
+{
+ gic_routable_irq_domain_ops = ops;
+}
+#endif /* __ASSEMBLY */
#endif
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 623325e..a8cc2fc 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -27,6 +27,8 @@
* @irq_count: stats field to detect stalled irqs
* @last_unhandled: aging timer for unhandled count
* @irqs_unhandled: stats field for spurious unhandled interrupts
+ * @threads_handled: stats field for deferred spurious detection of threaded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
* @lock: locking for SMP
* @affinity_hint: hint to user space for preferred irq affinity
* @affinity_notify: context for notification of affinity changes
@@ -52,6 +54,8 @@
unsigned int irq_count; /* For detecting broken IRQs */
unsigned long last_unhandled; /* Aging timer for unhandled count */
unsigned int irqs_unhandled;
+ atomic_t threads_handled;
+ int threads_handled_last;
raw_spinlock_t lock;
struct cpumask *percpu_enabled;
#ifdef CONFIG_SMP
@@ -154,6 +158,14 @@
return desc->status_use_accessors & IRQ_NO_BALANCING_MASK;
}
+static inline int irq_is_percpu(unsigned int irq)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+ return desc->status_use_accessors & IRQ_PER_CPU;
+}
+
static inline void
irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class)
{
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 8fb8edf..c039fe1 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -101,13 +101,13 @@
#define time_after(a,b) \
(typecheck(unsigned long, a) && \
typecheck(unsigned long, b) && \
- ((long)(b) - (long)(a) < 0))
+ ((long)((b) - (a)) < 0))
#define time_before(a,b) time_after(b,a)
#define time_after_eq(a,b) \
(typecheck(unsigned long, a) && \
typecheck(unsigned long, b) && \
- ((long)(a) - (long)(b) >= 0))
+ ((long)((a) - (b)) >= 0))
#define time_before_eq(a,b) time_after_eq(b,a)
/*
@@ -130,13 +130,13 @@
#define time_after64(a,b) \
(typecheck(__u64, a) && \
typecheck(__u64, b) && \
- ((__s64)(b) - (__s64)(a) < 0))
+ ((__s64)((b) - (a)) < 0))
#define time_before64(a,b) time_after64(b,a)
#define time_after_eq64(a,b) \
(typecheck(__u64, a) && \
typecheck(__u64, b) && \
- ((__s64)(a) - (__s64)(b) >= 0))
+ ((__s64)((a) - (b)) >= 0))
#define time_before_eq64(a,b) time_after_eq64(b,a)
/*
@@ -254,23 +254,11 @@
#define SEC_JIFFIE_SC (32 - SHIFT_HZ)
#endif
#define NSEC_JIFFIE_SC (SEC_JIFFIE_SC + 29)
-#define USEC_JIFFIE_SC (SEC_JIFFIE_SC + 19)
#define SEC_CONVERSION ((unsigned long)((((u64)NSEC_PER_SEC << SEC_JIFFIE_SC) +\
TICK_NSEC -1) / (u64)TICK_NSEC))
#define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
TICK_NSEC -1) / (u64)TICK_NSEC))
-#define USEC_CONVERSION \
- ((unsigned long)((((u64)NSEC_PER_USEC << USEC_JIFFIE_SC) +\
- TICK_NSEC -1) / (u64)TICK_NSEC))
-/*
- * USEC_ROUND is used in the timeval to jiffie conversion. See there
- * for more details. It is the scaled resolution rounding value. Note
- * that it is a 64-bit value. Since, when it is applied, we are already
- * in jiffies (albit scaled), it is nothing but the bits we will shift
- * off.
- */
-#define USEC_ROUND (u64)(((u64)1 << USEC_JIFFIE_SC) - 1)
/*
* The maximum jiffie value is (MAX_INT >> 1). Here we translate that
* into seconds. The 64-bit case will overflow if we are not careful,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e9ef6d6..341551c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -29,6 +29,19 @@
#define ULLONG_MAX (~0ULL)
#define SIZE_MAX (~(size_t)0)
+#define U8_MAX ((u8)~0U)
+#define S8_MAX ((s8)(U8_MAX>>1))
+#define S8_MIN ((s8)(-S8_MAX - 1))
+#define U16_MAX ((u16)~0U)
+#define S16_MAX ((s16)(U16_MAX>>1))
+#define S16_MIN ((s16)(-S16_MAX - 1))
+#define U32_MAX ((u32)~0U)
+#define S32_MAX ((s32)(U32_MAX>>1))
+#define S32_MIN ((s32)(-S32_MAX - 1))
+#define U64_MAX ((u64)~0ULL)
+#define S64_MAX ((s64)(U64_MAX>>1))
+#define S64_MIN ((s64)(-S64_MAX - 1))
+
#define STACK_MAGIC 0xdeadbeef
#define REPEAT_BYTE(x) ((~0ul / 0xff) * (x))
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d78d28a..5fd33dc 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -198,6 +198,9 @@
extern size_t vmcoreinfo_size;
extern size_t vmcoreinfo_max_size;
+/* flag to track if kexec reboot is in progress */
+extern bool kexec_in_progress;
+
int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
unsigned long long *crash_size, unsigned long long *crash_base);
int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index c6e091b..bdfc95b 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -283,7 +283,7 @@
extern struct kgdb_arch arch_kgdb_ops;
-extern unsigned long __weak kgdb_arch_pc(int exception, struct pt_regs *regs);
+extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
#ifdef CONFIG_SERIAL_KGDB_NMI
extern int kgdb_register_nmi_console(void);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8db53cf..f64e941 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -129,11 +129,9 @@
#define KVM_USERSPACE_IRQ_SOURCE_ID 0
#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1
-struct kvm;
-struct kvm_vcpu;
extern struct kmem_cache *kvm_vcpu_cache;
-extern raw_spinlock_t kvm_lock;
+extern spinlock_t kvm_lock;
extern struct list_head vm_list;
struct kvm_io_range {
@@ -175,13 +173,12 @@
gva_t gva;
unsigned long addr;
struct kvm_arch_async_pf arch;
- struct page *page;
- bool done;
+ bool wakeup_all;
};
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#endif
@@ -302,25 +299,6 @@
struct hlist_node link;
};
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
-
-struct kvm_irq_routing_table {
- int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
- struct kvm_kernel_irq_routing_entry *rt_entries;
- u32 nr_rt_entries;
- /*
- * Array indexed by gsi. Each entry contains list of irq chips
- * the gsi is connected to.
- */
- struct hlist_head map[0];
-};
-
-#else
-
-struct kvm_irq_routing_table {};
-
-#endif
-
#ifndef KVM_PRIVATE_MEM_SLOTS
#define KVM_PRIVATE_MEM_SLOTS 0
#endif
@@ -347,6 +325,7 @@
struct mm_struct *mm; /* userspace tied to this vm */
struct kvm_memslots *memslots;
struct srcu_struct srcu;
+ struct srcu_struct irq_srcu;
#ifdef CONFIG_KVM_APIC_ARCHITECTURE
u32 bsp_vcpu_id;
#endif
@@ -377,11 +356,12 @@
struct mutex irq_lock;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
/*
- * Update side is protected by irq_lock and,
- * if configured, irqfds.lock.
+ * Update side is protected by irq_lock.
*/
struct kvm_irq_routing_table __rcu *irq_routing;
struct hlist_head mask_notifier_list;
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
struct hlist_head irq_ack_notifier_list;
#endif
@@ -431,7 +411,7 @@
int __must_check vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd_init(void);
void kvm_irqfd_exit(void);
#else
@@ -450,8 +430,6 @@
void kvm_get_kvm(struct kvm *kvm);
void kvm_put_kvm(struct kvm *kvm);
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new,
- u64 last_generation);
static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
{
@@ -494,9 +472,11 @@
struct kvm_userspace_memory_region *mem);
int __kvm_set_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem);
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+ unsigned long npages);
+void kvm_arch_memslots_updated(struct kvm *kvm);
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -518,10 +498,12 @@
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
+ bool *writable);
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
-void kvm_set_page_dirty(struct page *page);
void kvm_set_page_accessed(struct page *page);
pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
@@ -533,7 +515,6 @@
pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_release_pfn_dirty(pfn_t pfn);
void kvm_release_pfn_clean(pfn_t pfn);
void kvm_set_pfn_dirty(pfn_t pfn);
void kvm_set_pfn_accessed(pfn_t pfn);
@@ -560,14 +541,11 @@
int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
-void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
- gfn_t gfn);
void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
-void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
@@ -582,15 +560,13 @@
unsigned int ioctl, unsigned long arg);
int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
-int kvm_dev_ioctl_check_extension(long ext);
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
int kvm_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log, int *is_dirty);
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log);
-int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem);
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
bool line_status);
long kvm_arch_vm_ioctl(struct file *filp,
@@ -622,6 +598,8 @@
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
+
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
@@ -630,16 +608,14 @@
int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
int kvm_arch_hardware_setup(void);
void kvm_arch_hardware_unsetup(void);
void kvm_arch_check_processor_compat(void *rtn);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
-void kvm_free_physmem(struct kvm *kvm);
-
void *kvm_kvzalloc(unsigned long size);
void kvm_kvfree(const void *addr);
@@ -717,6 +693,10 @@
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
bool mask);
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi);
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin);
+
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
bool line_status);
int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
@@ -773,7 +753,7 @@
/* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
- * is very similar to exiting to userspase from rcu point of view. In
+ * is very similar to exiting to userspace from rcu point of view. In
* addition CPU may stay in a guest mode for quite a long time (up to
* one time slice). Lets treat guest mode as quiescent state, just like
* we do with user-mode execution.
@@ -826,13 +806,6 @@
return gfn_to_memslot(kvm, gfn)->id;
}
-static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
-{
- /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
- return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
- (base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
-}
-
static inline gfn_t
hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
{
@@ -856,6 +829,13 @@
return (hpa_t)pfn << PAGE_SHIFT;
}
+static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+{
+ unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
+
+ return kvm_is_error_hva(hva);
+}
+
static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
@@ -906,28 +886,27 @@
const struct kvm_irq_routing_entry *entries,
unsigned nr,
unsigned flags);
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
- struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue);
void kvm_free_irq_routing(struct kvm *kvm);
-int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
-
#else
static inline void kvm_free_irq_routing(struct kvm *kvm) {}
#endif
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
#ifdef CONFIG_HAVE_KVM_EVENTFD
void kvm_eventfd_init(struct kvm *kvm);
int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef CONFIG_HAVE_KVM_IRQFD
int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
void kvm_irqfd_release(struct kvm *kvm);
-void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
+void kvm_irq_routing_update(struct kvm *);
#else
static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
@@ -949,10 +928,8 @@
static inline void kvm_irqfd_release(struct kvm *kvm) {}
#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm,
- struct kvm_irq_routing_table *irq_rt)
+static inline void kvm_irq_routing_update(struct kvm *kvm)
{
- rcu_assign_pointer(kvm->irq_routing, irq_rt);
}
#endif
@@ -1013,8 +990,6 @@
extern bool kvm_rebooting;
-struct kvm_device_ops;
-
struct kvm_device {
struct kvm_device_ops *ops;
struct kvm *kvm;
@@ -1047,6 +1022,7 @@
void kvm_device_get(struct kvm_device *dev);
void kvm_device_put(struct kvm_device *dev);
struct kvm_device *kvm_device_from_filp(struct file *filp);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
extern struct kvm_device_ops kvm_mpic_ops;
extern struct kvm_device_ops kvm_xics_ops;
@@ -1071,12 +1047,6 @@
static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
{
}
-
-static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
-{
- return true;
-}
-
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
#endif
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b0bcce0..b606bb6 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -17,6 +17,20 @@
#ifndef __KVM_TYPES_H__
#define __KVM_TYPES_H__
+struct kvm;
+struct kvm_async_pf;
+struct kvm_device_ops;
+struct kvm_interrupt;
+struct kvm_irq_routing_table;
+struct kvm_memory_slot;
+struct kvm_one_reg;
+struct kvm_run;
+struct kvm_userspace_memory_region;
+struct kvm_vcpu;
+struct kvm_vcpu_init;
+
+enum kvm_mr_change;
+
#include <asm/types.h>
/*
diff --git a/include/linux/libata.h b/include/linux/libata.h
index eae7a05..cc82cfb 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -399,6 +399,9 @@
ATA_HORKAGE_BROKEN_FPDMA_AA = (1 << 15), /* skip AA */
ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */
ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */
+ ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */
+ ATA_HORKAGE_NOLPM = (1 << 20), /* don't use LPM */
+ ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21), /* some WDs have broken LPM */
/* DMA mask for user DMA control: User visible values; DO NOT
renumber */
@@ -544,6 +547,7 @@
struct device *dev;
void __iomem * const *iomap;
unsigned int n_ports;
+ unsigned int n_tags; /* nr of NCQ tags */
void *private_data;
struct ata_port_operations *ops;
unsigned long flags;
@@ -769,6 +773,7 @@
unsigned long qc_allocated;
unsigned int qc_active;
int nr_active_links; /* #links with active qcs */
+ unsigned int last_tag; /* track next tag hw expects */
struct ata_link link; /* host default link */
struct ata_link *slave_link; /* see ata_slave_link_init() */
diff --git a/include/linux/list.h b/include/linux/list.h
index b83e565..83a9576 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -373,6 +373,22 @@
(!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
/**
+ * list_next_entry - get the next element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_struct within the struct.
+ */
+#define list_next_entry(pos, member) \
+ list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_struct within the struct.
+ */
+#define list_prev_entry(pos, member) \
+ list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+/**
* list_for_each - iterate over a list
* @pos: the &struct list_head to use as a loop cursor.
* @head: the head for your list.
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
new file mode 100644
index 0000000..4356686
--- /dev/null
+++ b/include/linux/lz4.h
@@ -0,0 +1,87 @@
+#ifndef __LZ4_H__
+#define __LZ4_H__
+/*
+ * LZ4 Kernel Interface
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define LZ4_MEM_COMPRESS (4096 * sizeof(unsigned char *))
+#define LZ4HC_MEM_COMPRESS (65538 * sizeof(unsigned char *))
+
+/*
+ * lz4_compressbound()
+ * Provides the maximum size that LZ4 may output in a "worst case" scenario
+ * (input data not compressible)
+ */
+static inline size_t lz4_compressbound(size_t isize)
+{
+ return isize + (isize / 255) + 16;
+}
+
+/*
+ * lz4_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+ /*
+ * lz4hc_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+/*
+ * lz4_decompress()
+ * src : source address of the compressed data
+ * src_len : is the input size, whcih is returned after decompress done
+ * dest : output buffer address of the decompressed data
+ * actual_dest_len: is the size of uncompressed data, supposing it's known
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ * slightly faster than lz4_decompress_unknownoutputsize()
+ */
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len);
+
+/*
+ * lz4_decompress_unknownoutputsize()
+ * src : source address of the compressed data
+ * src_len : is the input size, therefore the compressed size
+ * dest : output buffer address of the decompressed data
+ * dest_len: is the max size of the destination buffer, which is
+ * returned with actual size of decompressed data after
+ * decompress done
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ */
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len);
+#endif
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
new file mode 100644
index 0000000..307d9ca
--- /dev/null
+++ b/include/linux/mailbox_client.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2013-2014 Linaro Ltd.
+ * Author: Jassi Brar <jassisinghbrar@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CLIENT_H
+#define __MAILBOX_CLIENT_H
+
+#include <linux/of.h>
+#include <linux/device.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_client - User of a mailbox
+ * @dev: The client device
+ * @tx_block: If the mbox_send_message should block until data is
+ * transmitted.
+ * @tx_tout: Max block period in ms before TX is assumed failure
+ * @knows_txdone: If the client could run the TX state machine. Usually
+ * if the client receives some ACK packet for transmission.
+ * Unused if the controller already has TX_Done/RTR IRQ.
+ * @rx_callback: Atomic callback to provide client the data received
+ * @tx_done: Atomic callback to tell client of data transmission
+ */
+struct mbox_client {
+ struct device *dev;
+ bool tx_block;
+ unsigned long tx_tout;
+ bool knows_txdone;
+
+ void (*rx_callback)(struct mbox_client *cl, void *mssg);
+ void (*tx_done)(struct mbox_client *cl, void *mssg, int r);
+};
+
+struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index);
+int mbox_send_message(struct mbox_chan *chan, void *mssg);
+void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */
+bool mbox_client_peek_data(struct mbox_chan *chan); /* atomic */
+void mbox_free_channel(struct mbox_chan *chan); /* may sleep */
+
+#endif /* __MAILBOX_CLIENT_H */
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
new file mode 100644
index 0000000..d4cf96f
--- /dev/null
+++ b/include/linux/mailbox_controller.h
@@ -0,0 +1,133 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MAILBOX_CONTROLLER_H
+#define __MAILBOX_CONTROLLER_H
+
+#include <linux/of.h>
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/device.h>
+#include <linux/completion.h>
+
+struct mbox_chan;
+
+/**
+ * struct mbox_chan_ops - methods to control mailbox channels
+ * @send_data: The API asks the MBOX controller driver, in atomic
+ * context try to transmit a message on the bus. Returns 0 if
+ * data is accepted for transmission, -EBUSY while rejecting
+ * if the remote hasn't yet read the last data sent. Actual
+ * transmission of data is reported by the controller via
+ * mbox_chan_txdone (if it has some TX ACK irq). It must not
+ * sleep.
+ * @startup: Called when a client requests the chan. The controller
+ * could ask clients for additional parameters of communication
+ * to be provided via client's chan_data. This call may
+ * block. After this call the Controller must forward any
+ * data received on the chan by calling mbox_chan_received_data.
+ * The controller may do stuff that need to sleep.
+ * @shutdown: Called when a client relinquishes control of a chan.
+ * This call may block too. The controller must not forward
+ * any received data anymore.
+ * The controller may do stuff that need to sleep.
+ * @last_tx_done: If the controller sets 'txdone_poll', the API calls
+ * this to poll status of last TX. The controller must
+ * give priority to IRQ method over polling and never
+ * set both txdone_poll and txdone_irq. Only in polling
+ * mode 'send_data' is expected to return -EBUSY.
+ * The controller may do stuff that need to sleep/block.
+ * Used only if txdone_poll:=true && txdone_irq:=false
+ * @peek_data: Atomic check for any received data. Return true if controller
+ * has some data to push to the client. False otherwise.
+ */
+struct mbox_chan_ops {
+ int (*send_data)(struct mbox_chan *chan, void *data);
+ int (*startup)(struct mbox_chan *chan);
+ void (*shutdown)(struct mbox_chan *chan);
+ bool (*last_tx_done)(struct mbox_chan *chan);
+ bool (*peek_data)(struct mbox_chan *chan);
+};
+
+/**
+ * struct mbox_controller - Controller of a class of communication channels
+ * @dev: Device backing this controller
+ * @ops: Operators that work on each communication chan
+ * @chans: Array of channels
+ * @num_chans: Number of channels in the 'chans' array.
+ * @txdone_irq: Indicates if the controller can report to API when
+ * the last transmitted data was read by the remote.
+ * Eg, if it has some TX ACK irq.
+ * @txdone_poll: If the controller can read but not report the TX
+ * done. Ex, some register shows the TX status but
+ * no interrupt rises. Ignored if 'txdone_irq' is set.
+ * @txpoll_period: If 'txdone_poll' is in effect, the API polls for
+ * last TX's status after these many millisecs
+ * @of_xlate: Controller driver specific mapping of channel via DT
+ * @poll: API private. Used to poll for TXDONE on all channels.
+ * @node: API private. To hook into list of controllers.
+ */
+struct mbox_controller {
+ struct device *dev;
+ struct mbox_chan_ops *ops;
+ struct mbox_chan *chans;
+ int num_chans;
+ bool txdone_irq;
+ bool txdone_poll;
+ unsigned txpoll_period;
+ struct mbox_chan *(*of_xlate)(struct mbox_controller *mbox,
+ const struct of_phandle_args *sp);
+ /* Internal to API */
+ struct timer_list poll;
+ struct list_head node;
+};
+
+/*
+ * The length of circular buffer for queuing messages from a client.
+ * 'msg_count' tracks the number of buffered messages while 'msg_free'
+ * is the index where the next message would be buffered.
+ * We shouldn't need it too big because every transfer is interrupt
+ * triggered and if we have lots of data to transfer, the interrupt
+ * latencies are going to be the bottleneck, not the buffer length.
+ * Besides, mbox_send_message could be called from atomic context and
+ * the client could also queue another message from the notifier 'tx_done'
+ * of the last transfer done.
+ * REVISIT: If too many platforms see the "Try increasing MBOX_TX_QUEUE_LEN"
+ * print, it needs to be taken from config option or somesuch.
+ */
+#define MBOX_TX_QUEUE_LEN 20
+
+/**
+ * struct mbox_chan - s/w representation of a communication chan
+ * @mbox: Pointer to the parent/provider of this channel
+ * @txdone_method: Way to detect TXDone chosen by the API
+ * @cl: Pointer to the current owner of this channel
+ * @tx_complete: Transmission completion
+ * @active_req: Currently active request hook
+ * @msg_count: No. of mssg currently queued
+ * @msg_free: Index of next available mssg slot
+ * @msg_data: Hook for data packet
+ * @lock: Serialise access to the channel
+ * @con_priv: Hook for controller driver to attach private data
+ */
+struct mbox_chan {
+ struct mbox_controller *mbox;
+ unsigned txdone_method;
+ struct mbox_client *cl;
+ struct completion tx_complete;
+ void *active_req;
+ unsigned msg_count, msg_free;
+ void *msg_data[MBOX_TX_QUEUE_LEN];
+ spinlock_t lock; /* Serialise access to the channel */
+ void *con_priv;
+};
+
+int mbox_controller_register(struct mbox_controller *mbox); /* can sleep */
+void mbox_controller_unregister(struct mbox_controller *mbox); /* can sleep */
+void mbox_chan_received_data(struct mbox_chan *chan, void *data); /* atomic */
+void mbox_chan_txdone(struct mbox_chan *chan, int r); /* atomic */
+
+#endif /* __MAILBOX_CONTROLLER_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d6183f0..a3b4812 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -124,6 +124,25 @@
extern void mem_cgroup_replace_page_cache(struct page *oldpage,
struct page *newpage);
+static inline void mem_cgroup_oom_enable(void)
+{
+ WARN_ON(current->memcg_oom.may_oom);
+ current->memcg_oom.may_oom = 1;
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+ WARN_ON(!current->memcg_oom.may_oom);
+ current->memcg_oom.may_oom = 0;
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return p->memcg_oom.memcg;
+}
+
+bool mem_cgroup_oom_synchronize(bool wait);
+
#ifdef CONFIG_MEMCG_SWAP
extern int do_swap_account;
#endif
@@ -347,6 +366,24 @@
{
}
+static inline void mem_cgroup_oom_enable(void)
+{
+}
+
+static inline void mem_cgroup_oom_disable(void)
+{
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+ return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(bool wait)
+{
+ return false;
+}
+
static inline void mem_cgroup_inc_page_stat(struct page *page,
enum mem_cgroup_page_stat_item idx)
{
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 09c2300..cb35835 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -45,6 +45,7 @@
#define MAPPER_CTRL_MINOR 236
#define LOOP_CTRL_MINOR 237
#define VHOST_NET_MINOR 238
+#define UHID_MINOR 239
#define MISC_DYNAMIC_MINOR 255
struct device;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e0c8528..0ea351d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -52,6 +52,9 @@
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
+/* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */
+#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)addr, PAGE_SIZE)
+
/*
* Linux kernel virtual memory manager primitives.
* The idea being to have a "virtual" mm in the same way
@@ -167,6 +170,7 @@
#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */
#define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */
#define FAULT_FLAG_TRIED 0x40 /* second try */
+#define FAULT_FLAG_USER 0x80 /* The fault originated in userspace */
/*
* vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -361,8 +365,18 @@
static inline struct page *compound_head(struct page *page)
{
- if (unlikely(PageTail(page)))
- return page->first_page;
+ if (unlikely(PageTail(page))) {
+ struct page *head = page->first_page;
+
+ /*
+ * page->first_page may be a dangling pointer to an old
+ * compound page, so recheck that it is still a tail
+ * page before returning.
+ */
+ smp_rmb();
+ if (likely(PageTail(page)))
+ return head;
+ }
return page;
}
@@ -766,11 +780,14 @@
#endif
#if defined(WANT_PAGE_VIRTUAL)
-#define page_address(page) ((page)->virtual)
-#define set_page_address(page, address) \
- do { \
- (page)->virtual = (address); \
- } while(0)
+static inline void *page_address(const struct page *page)
+{
+ return page->virtual;
+}
+static inline void set_page_address(struct page *page, void *address)
+{
+ page->virtual = address;
+}
#define page_address_init() do { } while(0)
#endif
@@ -877,6 +894,7 @@
#define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */
#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */
#define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */
+#define VM_FAULT_SIGSEGV 0x0040
#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
@@ -884,8 +902,8 @@
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
-#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
- VM_FAULT_HWPOISON_LARGE)
+#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
+ VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)
/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
@@ -991,6 +1009,7 @@
extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
extern void truncate_setsize(struct inode *inode, loff_t newsize);
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
int truncate_inode_page(struct address_space *mapping, struct page *page);
int generic_error_remove_page(struct address_space *mapping, struct page *page);
@@ -1615,7 +1634,7 @@
#if VM_GROWSUP
extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
#else
- #define expand_upwards(vma, address) do { } while (0)
+ #define expand_upwards(vma, address) (0)
#endif
/* Look up the first VMA which satisfies addr < vm_end, NULL if none. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ace9a5f..10a9a17 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -333,6 +333,7 @@
void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
#endif
unsigned long mmap_base; /* base of mmap area */
+ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
unsigned long task_size; /* size of task vm space */
unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */
unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */
@@ -436,6 +437,14 @@
*/
int first_nid;
#endif
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+ /*
+ * An operation with batched TLB flushing is going on. Anything that
+ * can move process memory needs to flush the TLB when moving a
+ * PROT_NONE or PROT_NUMA mapped page.
+ */
+ bool tlb_flush_pending;
+#endif
struct uprobes_state uprobes_state;
};
@@ -456,4 +465,45 @@
return mm->cpu_vm_mask_var;
}
+#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+/*
+ * Memory barriers to keep this state in sync are graciously provided by
+ * the page table locks, outside of which no page table modifications happen.
+ * The barriers below prevent the compiler from re-ordering the instructions
+ * around the memory barriers that are already present in the code.
+ */
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ return mm->tlb_flush_pending;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+ mm->tlb_flush_pending = true;
+
+ /*
+ * Guarantee that the tlb_flush_pending store does not leak into the
+ * critical section updating the page tables
+ */
+ smp_mb__before_spinlock();
+}
+/* Clearing is done after a TLB flush, which also provides a barrier. */
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+ barrier();
+ mm->tlb_flush_pending = false;
+}
+#else
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+ return false;
+}
+static inline void set_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+#endif
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index b508016..08450a6 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -456,7 +456,8 @@
};
struct dmi_strmatch {
- unsigned char slot;
+ unsigned char slot:7;
+ unsigned char exact_match:1;
char substr[79];
};
@@ -474,7 +475,8 @@
*/
#define dmi_device_id dmi_system_id
-#define DMI_MATCH(a, b) { a, b }
+#define DMI_MATCH(a, b) { .slot = a, .substr = b }
+#define DMI_EXACT_MATCH(a, b) { .slot = a, .substr = b, .exact_match = 1 }
#define PLATFORM_NAME_SIZE 20
#define PLATFORM_MODULE_PREFIX "platform:"
@@ -561,6 +563,15 @@
#define X86_MODEL_ANY 0
#define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */
+/*
+ * Generic table type for matching CPU features.
+ * @feature: the bit number of the feature (0 - 65535)
+ */
+
+struct cpu_feature {
+ __u16 feature;
+};
+
#define IPACK_ANY_FORMAT 0xff
#define IPACK_ANY_ID (~0)
struct ipack_device_id {
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 73005f9..8eeb8f6 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -42,11 +42,18 @@
* flag, consider how it interacts with shared mounts.
*/
#define MNT_SHARED_MASK (MNT_UNBINDABLE)
-#define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE)
+#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
+ | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
+ | MNT_READONLY)
+#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
#define MNT_INTERNAL 0x4000
+#define MNT_LOCK_ATIME 0x040000
+#define MNT_LOCK_NOEXEC 0x080000
+#define MNT_LOCK_NOSUID 0x100000
+#define MNT_LOCK_NODEV 0x200000
#define MNT_LOCK_READONLY 0x400000
struct vfsmount {
diff --git a/include/linux/msg.h b/include/linux/msg.h
index 391af8d..e21f9d4 100644
--- a/include/linux/msg.h
+++ b/include/linux/msg.h
@@ -6,9 +6,9 @@
/* one msg_msg structure for each message */
struct msg_msg {
- struct list_head m_list;
- long m_type;
- int m_ts; /* message text size */
+ struct list_head m_list;
+ long m_type;
+ size_t m_ts; /* message text size */
struct msg_msgseg* next;
void *security;
/* the actual message follows immediately */
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 4b02512..5f487d7 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -365,7 +365,7 @@
bitpos = (map_bankwidth(map)-1-i)*8;
#endif
orig.x[0] &= ~(0xff << bitpos);
- orig.x[0] |= buf[i-start] << bitpos;
+ orig.x[0] |= (unsigned long)buf[i-start] << bitpos;
}
}
return orig;
@@ -384,7 +384,7 @@
if (map_bankwidth(map) < MAP_FF_LIMIT) {
int bw = 8 * map_bankwidth(map);
- r.x[0] = (1 << bw) - 1;
+ r.x[0] = (1UL << bw) - 1;
} else {
for (i=0; i<map_words(map); i++)
r.x[i] = ~0UL;
diff --git a/include/linux/nbd.h b/include/linux/nbd.h
index 4871170..ae4981e 100644
--- a/include/linux/nbd.h
+++ b/include/linux/nbd.h
@@ -41,6 +41,7 @@
u64 bytesize;
pid_t pid; /* pid of nbd-client, if attached */
int xmit_timeout;
+ int disconnect; /* a disconnect has been requested by user */
};
#endif
diff --git a/include/linux/net.h b/include/linux/net.h
index 99c9f0c..65545ac 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -163,6 +163,14 @@
#endif
int (*sendmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len);
+ /* Notes for implementing recvmsg:
+ * ===============================
+ * msg->msg_namelen should get updated by the recvmsg handlers
+ * iff msg_name != NULL. It is by default 0 to prevent
+ * returning uninitialized memory to user space. The recvfrom
+ * handlers can assume that msg.msg_name is either NULL or has
+ * a minimum size of sizeof(struct sockaddr_storage).
+ */
int (*recvmsg) (struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags);
@@ -172,7 +180,7 @@
int offset, size_t size, int flags);
ssize_t (*splice_read)(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len, unsigned int flags);
- void (*set_peek_off)(struct sock *sk, int val);
+ int (*set_peek_off)(struct sock *sk, int val);
};
#define DECLARE_SOCKADDR(type, dst, src) \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 96e4c21..4d2e041 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1772,6 +1772,15 @@
return dev->header_ops->parse(skb, haddr);
}
+static inline int dev_rebuild_header(struct sk_buff *skb)
+{
+ const struct net_device *dev = skb->dev;
+
+ if (!dev->header_ops || !dev->header_ops->rebuild)
+ return 0;
+ return dev->header_ops->rebuild(skb);
+}
+
typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
extern int register_gifconf(unsigned int family, gifconf_func_t * gifconf);
static inline int unregister_gifconf(unsigned int family)
@@ -2752,7 +2761,12 @@
void netif_stacked_transfer_operstate(const struct net_device *rootdev,
struct net_device *dev);
-netdev_features_t netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev);
+static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
+{
+ return netif_skb_dev_features(skb, skb->dev);
+}
static inline bool net_gso_ok(netdev_features_t features, int gso_type)
{
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 6358da5..9516dad 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -16,9 +16,10 @@
}
enum netlink_skb_flags {
- NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */
- NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */
- NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */
+ NETLINK_SKB_MMAPED = 0x1, /* Packet data is mmaped */
+ NETLINK_SKB_TX = 0x2, /* Packet was sent by userspace */
+ NETLINK_SKB_DELIVERED = 0x4, /* Packet was delivered */
+ NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */
};
struct netlink_skb_parms {
@@ -144,4 +145,11 @@
return __netlink_dump_start(ssk, skb, nlh, control);
}
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+ struct user_namespace *ns, int cap);
+bool netlink_ns_capable(const struct sk_buff *skb,
+ struct user_namespace *ns, int cap);
+bool netlink_capable(const struct sk_buff *skb, int cap);
+bool netlink_net_capable(const struct sk_buff *skb, int cap);
+
#endif /* __LINUX_NETLINK_H */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 104b62f..54e351a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1184,11 +1184,22 @@
unsigned int status;
};
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+ kfree(cinfo->buckets);
+}
+
#else
struct pnfs_ds_commit_info {
};
+static inline void
+nfs_free_pnfs_ds_cinfo(struct pnfs_ds_commit_info *cinfo)
+{
+}
+
#endif /* CONFIG_NFS_V4_1 */
struct nfs_page;
diff --git a/include/linux/of.h b/include/linux/of.h
index 1fd08ca..c00415c 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -18,11 +18,12 @@
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/errno.h>
-#include <linux/kref.h>
+#include <linux/kobject.h>
#include <linux/mod_devicetable.h>
#include <linux/spinlock.h>
#include <linux/topology.h>
#include <linux/notifier.h>
+#include <linux/list.h>
#include <asm/byteorder.h>
#include <asm/errno.h>
@@ -37,6 +38,7 @@
struct property *next;
unsigned long _flags;
unsigned int unique_id;
+ struct bin_attribute attr;
};
#if defined(CONFIG_SPARC)
@@ -56,8 +58,7 @@
struct device_node *sibling;
struct device_node *next; /* next device of same type */
struct device_node *allnext; /* next in list of all nodes */
- struct proc_dir_entry *pde; /* this node's proc directory */
- struct kref kref;
+ struct kobject kobj;
unsigned long _flags;
void *data;
#if defined(CONFIG_SPARC)
@@ -74,6 +75,31 @@
uint32_t args[MAX_PHANDLE_ARGS];
};
+struct of_reconfig_data {
+ struct device_node *dn;
+ struct property *prop;
+ struct property *old_prop;
+};
+
+/* initialize a node */
+extern struct kobj_type of_node_ktype;
+static inline void of_node_init(struct device_node *node)
+{
+ kobject_init(&node->kobj, &of_node_ktype);
+}
+
+/* true when node is initialized */
+static inline int of_node_is_initialized(struct device_node *node)
+{
+ return node && node->kobj.state_initialized;
+}
+
+/* true when node is attached (i.e. present on sysfs) */
+static inline int of_node_is_attached(struct device_node *node)
+{
+ return node && node->kobj.state_in_sysfs;
+}
+
#ifdef CONFIG_OF_DYNAMIC
extern struct device_node *of_node_get(struct device_node *node);
extern void of_node_put(struct device_node *node);
@@ -109,11 +135,37 @@
return test_bit(flag, &n->_flags);
}
+static inline int of_node_test_and_set_flag(struct device_node *n,
+ unsigned long flag)
+{
+ return test_and_set_bit(flag, &n->_flags);
+}
+
static inline void of_node_set_flag(struct device_node *n, unsigned long flag)
{
set_bit(flag, &n->_flags);
}
+static inline void of_node_clear_flag(struct device_node *n, unsigned long flag)
+{
+ clear_bit(flag, &n->_flags);
+}
+
+static inline int of_property_check_flag(struct property *p, unsigned long flag)
+{
+ return test_bit(flag, &p->_flags);
+}
+
+static inline void of_property_set_flag(struct property *p, unsigned long flag)
+{
+ set_bit(flag, &p->_flags);
+}
+
+static inline void of_property_clear_flag(struct property *p, unsigned long flag)
+{
+ clear_bit(flag, &p->_flags);
+}
+
extern struct device_node *of_find_all_nodes(struct device_node *prev);
/*
@@ -154,6 +206,8 @@
/* flag descriptions */
#define OF_DYNAMIC 1 /* node and properties were allocated via kmalloc */
#define OF_DETACHED 2 /* node has been detached from the device tree */
+#define OF_POPULATED 3 /* device already created for the node */
+#define OF_POPULATED_BUS 4 /* of_platform_populate recursed to children of this node */
#define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags)
#define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags)
@@ -165,6 +219,8 @@
return np ? np->full_name : "<no-node>";
}
+#define for_each_of_allnodes(dn) \
+ for (dn = of_allnodes; dn; dn = dn->allnext)
extern struct device_node *of_find_node_by_name(struct device_node *from,
const char *name);
#define for_each_node_by_name(dn, name) \
@@ -235,6 +291,8 @@
extern struct property *of_find_property(const struct device_node *np,
const char *name,
int *lenp);
+extern int of_property_count_elems_of_size(const struct device_node *np,
+ const char *propname, int elem_size);
extern int of_property_read_u32_index(const struct device_node *np,
const char *propname,
u32 index, u32 *out_value);
@@ -252,20 +310,19 @@
extern int of_property_read_string(struct device_node *np,
const char *propname,
const char **out_string);
-extern int of_property_read_string_index(struct device_node *np,
- const char *propname,
- int index, const char **output);
extern int of_property_match_string(struct device_node *np,
const char *propname,
const char *string);
-extern int of_property_count_strings(struct device_node *np,
- const char *propname);
+extern int of_property_read_string_helper(struct device_node *np,
+ const char *propname,
+ const char **out_strs, size_t sz, int index);
extern int of_device_is_compatible(const struct device_node *device,
const char *);
extern int of_device_is_available(const struct device_node *device);
extern const void *of_get_property(const struct device_node *node,
const char *name,
int *lenp);
+extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
#define for_each_property_of_node(dn, pp) \
for (pp = dn->properties; pp != NULL; pp = pp->next)
@@ -280,6 +337,9 @@
extern int of_parse_phandle_with_args(const struct device_node *np,
const char *list_name, const char *cells_name, int index,
struct of_phandle_args *out_args);
+extern int of_parse_phandle_with_fixed_args(const struct device_node *np,
+ const char *list_name, int cells_count, int index,
+ struct of_phandle_args *out_args);
extern int of_count_phandle_with_args(const struct device_node *np,
const char *list_name, const char *cells_name);
@@ -299,15 +359,6 @@
#define OF_RECONFIG_REMOVE_PROPERTY 0x0004
#define OF_RECONFIG_UPDATE_PROPERTY 0x0005
-struct of_prop_reconfig {
- struct device_node *dn;
- struct property *prop;
-};
-
-extern int of_reconfig_notifier_register(struct notifier_block *);
-extern int of_reconfig_notifier_unregister(struct notifier_block *);
-extern int of_reconfig_notify(unsigned long, void *);
-
extern int of_attach_node(struct device_node *);
extern int of_detach_node(struct device_node *);
@@ -343,6 +394,8 @@
s; \
s = of_prop_next_string(prop, s))
+int of_device_is_stdout_path(struct device_node *dn);
+
#else /* CONFIG_OF */
static inline const char* of_node_full_name(struct device_node *np)
@@ -407,6 +460,12 @@
return NULL;
}
+static inline int of_property_count_elems_of_size(const struct device_node *np,
+ const char *propname, int elem_size)
+{
+ return -ENOSYS;
+}
+
static inline int of_property_read_u32_index(const struct device_node *np,
const char *propname, u32 index, u32 *out_value)
{
@@ -439,15 +498,9 @@
return -ENOSYS;
}
-static inline int of_property_read_string_index(struct device_node *np,
- const char *propname, int index,
- const char **out_string)
-{
- return -ENOSYS;
-}
-
-static inline int of_property_count_strings(struct device_node *np,
- const char *propname)
+static inline int of_property_read_string_helper(struct device_node *np,
+ const char *propname,
+ const char **out_strs, size_t sz, int index)
{
return -ENOSYS;
}
@@ -459,6 +512,12 @@
return NULL;
}
+static inline struct device_node *of_get_cpu_node(int cpu,
+ unsigned int *thread)
+{
+ return NULL;
+}
+
static inline int of_property_read_u64(const struct device_node *np,
const char *propname, u64 *out_value)
{
@@ -488,6 +547,13 @@
return -ENOSYS;
}
+static inline int of_parse_phandle_with_fixed_args(const struct device_node *np,
+ const char *list_name, int cells_count, int index,
+ struct of_phandle_args *out_args)
+{
+ return -ENOSYS;
+}
+
static inline int of_count_phandle_with_args(struct device_node *np,
const char *list_name,
const char *cells_name)
@@ -505,6 +571,11 @@
return 0;
}
+static inline int of_device_is_stdout_path(struct device_node *dn)
+{
+ return 0;
+}
+
#define of_match_ptr(_ptr) NULL
#define of_match_node(_matches, _node) NULL
#define of_property_for_each_u32(np, propname, prop, p, u) \
@@ -523,6 +594,138 @@
#endif
/**
+ * of_property_read_string_array() - Read an array of strings from a multiple
+ * strings property.
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @out_strs: output array of string pointers.
+ * @sz: number of array elements to read.
+ *
+ * Search for a property in a device tree node and retrieve a list of
+ * terminated string values (pointer to data, not a copy) in that property.
+ *
+ * If @out_strs is NULL, the number of strings in the property is returned.
+ */
+static inline int of_property_read_string_array(struct device_node *np,
+ const char *propname, const char **out_strs,
+ size_t sz)
+{
+ return of_property_read_string_helper(np, propname, out_strs, sz, 0);
+}
+
+/**
+ * of_property_count_strings() - Find and return the number of strings from a
+ * multiple strings property.
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ *
+ * Search for a property in a device tree node and retrieve the number of null
+ * terminated string contain in it. Returns the number of strings on
+ * success, -EINVAL if the property does not exist, -ENODATA if property
+ * does not have a value, and -EILSEQ if the string is not null-terminated
+ * within the length of the property data.
+ */
+static inline int of_property_count_strings(struct device_node *np,
+ const char *propname)
+{
+ return of_property_read_string_helper(np, propname, NULL, 0, 0);
+}
+
+/**
+ * of_property_read_string_index() - Find and read a string from a multiple
+ * strings property.
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ * @index: index of the string in the list of strings
+ * @out_string: pointer to null terminated return string, modified only if
+ * return value is 0.
+ *
+ * Search for a property in a device tree node and retrieve a null
+ * terminated string value (pointer to data, not a copy) in the list of strings
+ * contained in that property.
+ * Returns 0 on success, -EINVAL if the property does not exist, -ENODATA if
+ * property does not have a value, and -EILSEQ if the string is not
+ * null-terminated within the length of the property data.
+ *
+ * The out_string pointer is modified only if a valid string can be decoded.
+ */
+static inline int of_property_read_string_index(struct device_node *np,
+ const char *propname,
+ int index, const char **output)
+{
+ int rc = of_property_read_string_helper(np, propname, output, 1, index);
+ return rc < 0 ? rc : 0;
+}
+
+/*
+ * of_property_count_u8_elems - Count the number of u8 elements in a property
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u8 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u8 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u8_elems(const struct device_node *np,
+ const char *propname)
+{
+ return of_property_count_elems_of_size(np, propname, sizeof(u8));
+}
+
+/**
+ * of_property_count_u16_elems - Count the number of u16 elements in a property
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u16 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u16 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u16_elems(const struct device_node *np,
+ const char *propname)
+{
+ return of_property_count_elems_of_size(np, propname, sizeof(u16));
+}
+
+/**
+ * of_property_count_u32_elems - Count the number of u32 elements in a property
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u32 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u32 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u32_elems(const struct device_node *np,
+ const char *propname)
+{
+ return of_property_count_elems_of_size(np, propname, sizeof(u32));
+}
+
+/**
+ * of_property_count_u64_elems - Count the number of u64 elements in a property
+ *
+ * @np: device node from which the property value is to be read.
+ * @propname: name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u64 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u64 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u64_elems(const struct device_node *np,
+ const char *propname)
+{
+ return of_property_count_elems_of_size(np, propname, sizeof(u64));
+}
+
+/**
* of_property_read_bool - Findfrom a property
* @np: device node from which the property value is to be read.
* @propname: name of the property to be searched.
@@ -559,14 +762,144 @@
return of_property_read_u32_array(np, propname, out_value, 1);
}
-#if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE)
-extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
-extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
-extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
- struct property *prop);
-extern void proc_device_tree_update_prop(struct proc_dir_entry *pde,
- struct property *newprop,
- struct property *oldprop);
+/**
+ * struct of_changeset_entry - Holds a changeset entry
+ *
+ * @node: list_head for the log list
+ * @action: notifier action
+ * @np: pointer to the device node affected
+ * @prop: pointer to the property affected
+ * @old_prop: hold a pointer to the original property
+ *
+ * Every modification of the device tree during a changeset
+ * is held in a list of of_changeset_entry structures.
+ * That way we can recover from a partial application, or we can
+ * revert the changeset
+ */
+struct of_changeset_entry {
+ struct list_head node;
+ unsigned long action;
+ struct device_node *np;
+ struct property *prop;
+ struct property *old_prop;
+};
+
+/**
+ * struct of_changeset - changeset tracker structure
+ *
+ * @entries: list_head for the changeset entries
+ *
+ * changesets are a convenient way to apply bulk changes to the
+ * live tree. In case of an error, changes are rolled-back.
+ * changesets live on after initial application, and if not
+ * destroyed after use, they can be reverted in one single call.
+ */
+struct of_changeset {
+ struct list_head entries;
+};
+
+enum of_reconfig_change {
+ OF_RECONFIG_NO_CHANGE = 0,
+ OF_RECONFIG_CHANGE_ADD,
+ OF_RECONFIG_CHANGE_REMOVE,
+};
+
+#ifdef CONFIG_OF_DYNAMIC
+extern int of_reconfig_notifier_register(struct notifier_block *);
+extern int of_reconfig_notifier_unregister(struct notifier_block *);
+extern int of_reconfig_notify(unsigned long, struct of_reconfig_data *rd);
+extern int of_reconfig_get_state_change(unsigned long action,
+ struct of_reconfig_data *arg);
+
+extern void of_changeset_init(struct of_changeset *ocs);
+extern void of_changeset_destroy(struct of_changeset *ocs);
+extern int of_changeset_apply(struct of_changeset *ocs);
+extern int of_changeset_revert(struct of_changeset *ocs);
+extern int of_changeset_action(struct of_changeset *ocs,
+ unsigned long action, struct device_node *np,
+ struct property *prop);
+
+static inline int of_changeset_attach_node(struct of_changeset *ocs,
+ struct device_node *np)
+{
+ return of_changeset_action(ocs, OF_RECONFIG_ATTACH_NODE, np, NULL);
+}
+
+static inline int of_changeset_detach_node(struct of_changeset *ocs,
+ struct device_node *np)
+{
+ return of_changeset_action(ocs, OF_RECONFIG_DETACH_NODE, np, NULL);
+}
+
+static inline int of_changeset_add_property(struct of_changeset *ocs,
+ struct device_node *np, struct property *prop)
+{
+ return of_changeset_action(ocs, OF_RECONFIG_ADD_PROPERTY, np, prop);
+}
+
+static inline int of_changeset_remove_property(struct of_changeset *ocs,
+ struct device_node *np, struct property *prop)
+{
+ return of_changeset_action(ocs, OF_RECONFIG_REMOVE_PROPERTY, np, prop);
+}
+
+static inline int of_changeset_update_property(struct of_changeset *ocs,
+ struct device_node *np, struct property *prop)
+{
+ return of_changeset_action(ocs, OF_RECONFIG_UPDATE_PROPERTY, np, prop);
+}
+#else /* CONFIG_OF_DYNAMIC */
+static inline int of_reconfig_notifier_register(struct notifier_block *nb)
+{
+ return -EINVAL;
+}
+static inline int of_reconfig_notifier_unregister(struct notifier_block *nb)
+{
+ return -EINVAL;
+}
+static inline int of_reconfig_notify(unsigned long action,
+ struct of_reconfig_data *arg)
+{
+ return -EINVAL;
+}
+static inline int of_reconfig_get_state_change(unsigned long action,
+ struct of_reconfig_data *arg)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_OF_DYNAMIC */
+
+/* CONFIG_OF_RESOLVE api */
+extern int of_resolve_phandles(struct device_node *tree);
+
+/**
+ * Overlay support
+ */
+
+#ifdef CONFIG_OF_OVERLAY
+
+/* ID based overlays; the API for external users */
+int of_overlay_create(struct device_node *tree);
+int of_overlay_destroy(int id);
+int of_overlay_destroy_all(void);
+
+#else
+
+static inline int of_overlay_create(struct device_node *tree)
+{
+ return -ENOTSUPP;
+}
+
+static inline int of_overlay_destroy(int id)
+{
+ return -ENOTSUPP;
+}
+
+static inline int of_overlay_destroy_all(void)
+{
+ return -ENOTSUPP;
+}
+
#endif
#endif /* _LINUX_OF_H */
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 901b743..192c783 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -1,6 +1,7 @@
#ifndef _LINUX_OF_DEVICE_H
#define _LINUX_OF_DEVICE_H
+#include <linux/cpu.h>
#include <linux/platform_device.h>
#include <linux/of_platform.h> /* temporary until merge */
@@ -43,6 +44,15 @@
of_node_put(dev->of_node);
}
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+ struct device *cpu_dev;
+ cpu_dev = get_cpu_device(cpu);
+ if (!cpu_dev)
+ return NULL;
+ return of_node_get(cpu_dev->of_node);
+}
+
#else /* CONFIG_OF_DEVICE */
static inline int of_driver_match_device(struct device *dev,
@@ -67,6 +77,11 @@
{
return NULL;
}
+
+static inline struct device_node *of_cpu_device_node_get(int cpu)
+{
+ return NULL;
+}
#endif /* CONFIG_OF_DEVICE */
#endif /* _LINUX_OF_DEVICE_H */
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index ed136ad..c9722fd 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -66,7 +66,7 @@
extern void *of_fdt_get_property(struct boot_param_header *blob,
unsigned long node,
const char *name,
- unsigned long *size);
+ int *size);
extern int of_fdt_is_compatible(struct boot_param_header *blob,
unsigned long node,
const char *compat);
@@ -81,12 +81,11 @@
extern struct boot_param_header *initial_boot_params;
/* For scanning the flat device-tree at boot time */
-extern char *find_flat_dt_string(u32 offset);
extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
int depth, void *data),
void *data);
-extern void *of_get_flat_dt_prop(unsigned long node, const char *name,
- unsigned long *size);
+extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
+ int *size);
extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
extern int of_flat_dt_match(unsigned long node, const char *const *matches);
extern unsigned long of_get_flat_dt_root(void);
@@ -96,9 +95,12 @@
extern void early_init_dt_check_for_initrd(unsigned long node);
extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
int depth, void *data);
+extern void early_init_fdt_scan_reserved_mem(void);
extern void early_init_dt_add_memory_arch(u64 base, u64 size);
+extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+ bool no_map);
extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
-extern u64 dt_mem_next_cell(int s, __be32 **cellp);
+extern u64 dt_mem_next_cell(int s, const __be32 **cellp);
/*
* If BLK_DEV_INITRD, the fdt early init code will call this function,
@@ -106,8 +108,7 @@
* physical addresses.
*/
#ifdef CONFIG_BLK_DEV_INITRD
-extern void early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end);
+extern void early_init_dt_setup_initrd_arch(u64 start, u64 end);
#endif
/* Early flat tree scan hooks */
@@ -118,6 +119,8 @@
extern void unflatten_device_tree(void);
extern void early_init_devtree(void *);
#else /* CONFIG_OF_FLATTREE */
+static inline void early_init_fdt_scan_reserved_mem(void) {}
+static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
static inline void unflatten_device_tree(void) {}
#endif /* CONFIG_OF_FLATTREE */
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
new file mode 100644
index 0000000..56e0507
--- /dev/null
+++ b/include/linux/of_graph.h
@@ -0,0 +1,65 @@
+/*
+ * OF graph binding parsing helpers
+ *
+ * Copyright (C) 2012 - 2013 Samsung Electronics Co., Ltd.
+ * Author: Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * Copyright (C) 2012 Renesas Electronics Corp.
+ * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_OF_GRAPH_H
+#define __LINUX_OF_GRAPH_H
+
+/**
+ * struct of_endpoint - the OF graph endpoint data structure
+ * @port: identifier (value of reg property) of a port this endpoint belongs to
+ * @id: identifier (value of reg property) of this endpoint
+ * @local_node: pointer to device_node of this endpoint
+ */
+struct of_endpoint {
+ unsigned int port;
+ unsigned int id;
+ const struct device_node *local_node;
+};
+
+#ifdef CONFIG_OF
+int of_graph_parse_endpoint(const struct device_node *node,
+ struct of_endpoint *endpoint);
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+ struct device_node *previous);
+struct device_node *of_graph_get_remote_port_parent(
+ const struct device_node *node);
+struct device_node *of_graph_get_remote_port(const struct device_node *node);
+#else
+
+static inline int of_graph_parse_endpoint(const struct device_node *node,
+ struct of_endpoint *endpoint)
+{
+ return -ENOSYS;
+}
+static inline struct device_node *of_graph_get_next_endpoint(
+ const struct device_node *parent,
+ struct device_node *previous)
+{
+ return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port_parent(
+ const struct device_node *node)
+{
+ return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port(
+ const struct device_node *node)
+{
+ return NULL;
+}
+
+#endif /* CONFIG_OF */
+
+#endif /* __LINUX_OF_GRAPH_H */
diff --git a/include/linux/of_i2c.h b/include/linux/of_i2c.h
index cfb545c..686786c 100644
--- a/include/linux/of_i2c.h
+++ b/include/linux/of_i2c.h
@@ -12,35 +12,8 @@
#ifndef __LINUX_OF_I2C_H
#define __LINUX_OF_I2C_H
-#if defined(CONFIG_OF_I2C) || defined(CONFIG_OF_I2C_MODULE)
#include <linux/i2c.h>
-extern void of_i2c_register_devices(struct i2c_adapter *adap);
-
-/* must call put_device() when done with returned i2c_client device */
-extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node);
-
-/* must call put_device() when done with returned i2c_adapter device */
-extern struct i2c_adapter *of_find_i2c_adapter_by_node(
- struct device_node *node);
-
-#else
-static inline void of_i2c_register_devices(struct i2c_adapter *adap)
-{
- return;
-}
-
-static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
-{
- return NULL;
-}
-
-/* must call put_device() when done with returned i2c_adapter device */
-static inline struct i2c_adapter *of_find_i2c_adapter_by_node(
- struct device_node *node)
-{
- return NULL;
-}
-#endif /* CONFIG_OF_I2C */
+static inline void of_i2c_register_devices(struct i2c_adapter *adap) { };
#endif /* __LINUX_OF_I2C_H */
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index 2a93b64..30ebd76 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -95,6 +95,7 @@
const struct of_device_id *matches,
const struct of_dev_auxdata *lookup,
struct device *parent);
+extern void of_platform_depopulate(struct device *parent);
#endif /* CONFIG_OF_ADDRESS */
#endif /* CONFIG_OF_DEVICE */
@@ -109,6 +110,13 @@
{
return -ENODEV;
}
-#endif /* !CONFIG_OF_ADDRESS */
+static inline void of_platform_depopulate(struct device *parent) { }
+#endif
+
+#ifdef CONFIG_OF_DYNAMIC
+extern void of_platform_register_reconfig_notifier(void);
+#else
+static inline void of_platform_register_reconfig_notifier(void) { }
+#endif
#endif /* _LINUX_OF_PLATFORM_H */
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
new file mode 100644
index 0000000..9b1fbb7
--- /dev/null
+++ b/include/linux/of_reserved_mem.h
@@ -0,0 +1,53 @@
+#ifndef __OF_RESERVED_MEM_H
+#define __OF_RESERVED_MEM_H
+
+struct device;
+struct of_phandle_args;
+struct reserved_mem_ops;
+
+struct reserved_mem {
+ const char *name;
+ unsigned long fdt_node;
+ const struct reserved_mem_ops *ops;
+ phys_addr_t base;
+ phys_addr_t size;
+ void *priv;
+};
+
+struct reserved_mem_ops {
+ void (*device_init)(struct reserved_mem *rmem,
+ struct device *dev);
+ void (*device_release)(struct reserved_mem *rmem,
+ struct device *dev);
+};
+
+typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem,
+ unsigned long node, const char *uname);
+
+#ifdef CONFIG_OF_RESERVED_MEM
+void fdt_init_reserved_mem(void);
+void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+ phys_addr_t base, phys_addr_t size);
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init) \
+ static const struct of_device_id __reservedmem_of_table_##name \
+ __used __section(__reservedmem_of_table) \
+ = { .compatible = compat, \
+ .data = (init == (reservedmem_of_init_fn)NULL) ? \
+ init : init }
+
+#else
+static inline void fdt_init_reserved_mem(void) { }
+static inline void fdt_reserved_mem_save_node(unsigned long node,
+ const char *uname, phys_addr_t base, phys_addr_t size) { }
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init) \
+ static const struct of_device_id __reservedmem_of_table_##name \
+ __attribute__((unused)) \
+ = { .compatible = compat, \
+ .data = (init == (reservedmem_of_init_fn)NULL) ? \
+ init : init }
+
+#endif
+
+#endif /* __OF_RESERVED_MEM_H */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index da60007..297cda5 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -50,6 +50,9 @@
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
+
+extern int oom_kills_count(void);
+extern void note_oom_kill(void);
extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
unsigned int points, unsigned long totalpages,
struct mem_cgroup *memcg, nodemask_t *nodemask,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 3a24e4f..102136a 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -310,6 +310,7 @@
unsigned int is_added:1;
unsigned int is_busmaster:1; /* device is busmaster */
unsigned int no_msi:1; /* device may not use msi */
+ unsigned int no_64bit_msi:1; /* device may only use 32-bit MSIs */
unsigned int block_cfg_access:1; /* config space access is blocked */
unsigned int broken_parity_status:1; /* Device generates false positive parity */
unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index c129162..6c7bb35 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -518,6 +518,8 @@
#define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303
#define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304
#define PCI_DEVICE_ID_AMD_15H_M10H_F3 0x1403
+#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F3 0x141d
+#define PCI_DEVICE_ID_AMD_15H_M30H_NB_F4 0x141e
#define PCI_DEVICE_ID_AMD_15H_NB_F0 0x1600
#define PCI_DEVICE_ID_AMD_15H_NB_F1 0x1601
#define PCI_DEVICE_ID_AMD_15H_NB_F2 0x1602
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c5b6dbf..229a757 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -695,10 +695,17 @@
extern int sysctl_perf_event_paranoid;
extern int sysctl_perf_event_mlock;
extern int sysctl_perf_event_sample_rate;
+extern int sysctl_perf_cpu_time_max_percent;
+
+extern void perf_sample_event_took(u64 sample_len_ns);
extern int perf_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
+extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+
static inline bool perf_paranoid_tracepoint_raw(void)
{
diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h
index 4aad3ce..04c760d 100644
--- a/include/linux/pinctrl/consumer.h
+++ b/include/linux/pinctrl/consumer.h
@@ -158,47 +158,4 @@
return devm_pinctrl_get_select(dev, PINCTRL_STATE_DEFAULT);
}
-#ifdef CONFIG_PINCONF
-
-extern int pin_config_get(const char *dev_name, const char *name,
- unsigned long *config);
-extern int pin_config_set(const char *dev_name, const char *name,
- unsigned long config);
-extern int pin_config_group_get(const char *dev_name,
- const char *pin_group,
- unsigned long *config);
-extern int pin_config_group_set(const char *dev_name,
- const char *pin_group,
- unsigned long config);
-
-#else
-
-static inline int pin_config_get(const char *dev_name, const char *name,
- unsigned long *config)
-{
- return 0;
-}
-
-static inline int pin_config_set(const char *dev_name, const char *name,
- unsigned long config)
-{
- return 0;
-}
-
-static inline int pin_config_group_get(const char *dev_name,
- const char *pin_group,
- unsigned long *config)
-{
- return 0;
-}
-
-static inline int pin_config_group_set(const char *dev_name,
- const char *pin_group,
- unsigned long config)
-{
- return 0;
-}
-
-#endif
-
#endif /* __LINUX_PINCTRL_CONSUMER_H */
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index 6aa2380..201e68d 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -29,12 +29,21 @@
* if for example some other pin is going to drive the signal connected
* to it for a while. Pins used for input are usually always high
* impedance.
+ * @PIN_CONFIG_BIAS_BUS_HOLD: the pin will be set to weakly latch so that it
+ * weakly drives the last value on a tristate bus, also known as a "bus
+ * holder", "bus keeper" or "repeater". This allows another device on the
+ * bus to change the value by driving the bus high or low and switching to
+ * tristate. The argument is ignored.
* @PIN_CONFIG_BIAS_PULL_UP: the pin will be pulled up (usually with high
* impedance to VDD). If the argument is != 0 pull-up is enabled,
* if it is 0, pull-up is disabled.
* @PIN_CONFIG_BIAS_PULL_DOWN: the pin will be pulled down (usually with high
* impedance to GROUND). If the argument is != 0 pull-down is enabled,
* if it is 0, pull-down is disabled.
+ * @PIN_CONFIG_BIAS_PULL_PIN_DEFAULT: the pin will be pulled up or down based
+ * on embedded knowledge of the controller, like current mux function.
+ * If the argument is != 0 pull up/down is enabled, if it is 0,
+ * the pull is disabled.
* @PIN_CONFIG_DRIVE_PUSH_PULL: the pin will be driven actively high and
* low, this is the most typical case and is typically achieved with two
* active transistors on the output. Setting this config will enable
@@ -48,6 +57,9 @@
* argument is ignored.
* @PIN_CONFIG_DRIVE_STRENGTH: the pin will sink or source at most the current
* passed as argument. The argument is in mA.
+ * @PIN_CONFIG_INPUT_ENABLE: enable the pin's input. Note that this does not
+ * affect the pin's ability to drive output. 1 enables input, 0 disables
+ * input.
* @PIN_CONFIG_INPUT_SCHMITT_ENABLE: control schmitt-trigger mode on the pin.
* If the argument != 0, schmitt-trigger mode is enabled. If it's 0,
* schmitt-trigger mode is disabled.
@@ -57,7 +69,7 @@
* setting pins to this mode.
* @PIN_CONFIG_INPUT_DEBOUNCE: this will configure the pin to debounce mode,
* which means it will wait for signals to settle when reading inputs. The
- * argument gives the debounce time on a custom format. Setting the
+ * argument gives the debounce time in usecs. Setting the
* argument to zero turns debouncing off.
* @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power
* supplies, the argument to this parameter (on a custom format) tells
@@ -78,12 +90,15 @@
enum pin_config_param {
PIN_CONFIG_BIAS_DISABLE,
PIN_CONFIG_BIAS_HIGH_IMPEDANCE,
+ PIN_CONFIG_BIAS_BUS_HOLD,
PIN_CONFIG_BIAS_PULL_UP,
PIN_CONFIG_BIAS_PULL_DOWN,
+ PIN_CONFIG_BIAS_PULL_PIN_DEFAULT,
PIN_CONFIG_DRIVE_PUSH_PULL,
PIN_CONFIG_DRIVE_OPEN_DRAIN,
PIN_CONFIG_DRIVE_OPEN_SOURCE,
PIN_CONFIG_DRIVE_STRENGTH,
+ PIN_CONFIG_INPUT_ENABLE,
PIN_CONFIG_INPUT_SCHMITT_ENABLE,
PIN_CONFIG_INPUT_SCHMITT,
PIN_CONFIG_INPUT_DEBOUNCE,
@@ -122,6 +137,58 @@
return PIN_CONF_PACKED(param, argument);
}
+#ifdef CONFIG_OF
+
+#include <linux/device.h>
+#include <linux/pinctrl/machine.h>
+struct pinctrl_dev;
+struct pinctrl_map;
+
+int pinconf_generic_dt_subnode_to_map_new(struct pinctrl_dev *pctldev,
+ struct device_node *np, struct pinctrl_map **map,
+ unsigned *reserved_maps, unsigned *num_maps,
+ enum pinctrl_map_type type);
+int pinconf_generic_dt_node_to_map_new(struct pinctrl_dev *pctldev,
+ struct device_node *np_config, struct pinctrl_map **map,
+ unsigned *num_maps, enum pinctrl_map_type type);
+
+static inline int pinconf_generic_dt_node_to_map_group(
+ struct pinctrl_dev *pctldev, struct device_node *np_config,
+ struct pinctrl_map **map, unsigned *num_maps)
+{
+ return pinconf_generic_dt_node_to_map_new(pctldev, np_config, map, num_maps,
+ PIN_MAP_TYPE_CONFIGS_GROUP);
+}
+
+static inline int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
+ struct device_node *np, struct pinctrl_map **map,
+ unsigned *reserved_maps, unsigned *num_maps)
+{
+ return pinconf_generic_dt_subnode_to_map_new(pctldev, np, map,
+ reserved_maps, num_maps,
+ PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+static inline int pinconf_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
+ struct device_node *np_config, struct pinctrl_map **map,
+ unsigned *num_maps)
+{
+ return pinconf_generic_dt_node_to_map_new(pctldev, np_config,
+ map, num_maps,
+ PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+
+static inline int pinconf_generic_dt_node_to_map_pin(
+ struct pinctrl_dev *pctldev, struct device_node *np_config,
+ struct pinctrl_map **map, unsigned *num_maps)
+{
+ return pinconf_generic_dt_node_to_map_new(pctldev, np_config, map, num_maps,
+ PIN_MAP_TYPE_CONFIGS_PIN);
+}
+
+#endif
+
#endif /* CONFIG_GENERIC_PINCONF */
#endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */
diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index 1ad4f31..e6a68e4 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -48,12 +48,20 @@
int (*pin_config_set) (struct pinctrl_dev *pctldev,
unsigned pin,
unsigned long config);
+ int (*pin_config_set_bulk) (struct pinctrl_dev *pctldev,
+ unsigned pin,
+ unsigned long *configs,
+ unsigned num_configs);
int (*pin_config_group_get) (struct pinctrl_dev *pctldev,
unsigned selector,
unsigned long *config);
int (*pin_config_group_set) (struct pinctrl_dev *pctldev,
unsigned selector,
unsigned long config);
+ int (*pin_config_group_set_bulk) (struct pinctrl_dev *pctldev,
+ unsigned selector,
+ unsigned long *configs,
+ unsigned num_configs);
int (*pin_config_dbg_parse_modify) (struct pinctrl_dev *pctldev,
const char *arg,
unsigned long *config);
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 2c2a9e8..9adb106 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -32,10 +32,12 @@
* pins, pads or other muxable units in this struct
* @number: unique pin number from the global pin number space
* @name: a name for this pin
+ * @drv_data: driver-defined per-pin data. pinctrl core does not touch this
*/
struct pinctrl_pin_desc {
unsigned number;
const char *name;
+ void *drv_data;
};
/* Convenience macro to define a single named or anonymous pin descriptor */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index b8809fe..ab57526 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -157,6 +157,8 @@
int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
+extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
+
/* for F_SETPIPE_SZ and F_GETPIPE_SZ */
long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
struct pipe_inode_info *get_pipe_info(struct file *file);
diff --git a/include/linux/mailbox.h b/include/linux/pl320-ipc.h
similarity index 100%
rename from include/linux/mailbox.h
rename to include/linux/pl320-ipc.h
diff --git a/include/linux/pm.h b/include/linux/pm.h
index a224c7f..b876060 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -575,6 +575,7 @@
*/
struct dev_pm_domain {
struct dev_pm_ops ops;
+ void (*detach)(struct device *dev, bool power_off);
};
/*
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 7c1d252..66cfa1a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -310,4 +310,56 @@
pm_genpd_syscore_switch(dev, false);
}
+/* OF PM domain providers */
+struct of_device_id;
+
+struct genpd_onecell_data {
+ struct generic_pm_domain **domains;
+ unsigned int num_domains;
+};
+
+typedef struct generic_pm_domain *(*genpd_xlate_t)(struct of_phandle_args *args,
+ void *data);
+
+#ifdef CONFIG_PM_GENERIC_DOMAINS_OF
+int __of_genpd_add_provider(struct device_node *np, genpd_xlate_t xlate,
+ void *data);
+void of_genpd_del_provider(struct device_node *np);
+
+struct generic_pm_domain *__of_genpd_xlate_simple(
+ struct of_phandle_args *genpdspec,
+ void *data);
+struct generic_pm_domain *__of_genpd_xlate_onecell(
+ struct of_phandle_args *genpdspec,
+ void *data);
+
+int genpd_dev_pm_attach(struct device *dev);
+#else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
+static inline int __of_genpd_add_provider(struct device_node *np,
+ genpd_xlate_t xlate, void *data)
+{
+ return 0;
+}
+static inline void of_genpd_del_provider(struct device_node *np) {}
+
+#define __of_genpd_xlate_simple NULL
+#define __of_genpd_xlate_onecell NULL
+
+static inline int genpd_dev_pm_attach(struct device *dev)
+{
+ return -ENODEV;
+}
+#endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
+
+static inline int of_genpd_add_provider_simple(struct device_node *np,
+ struct generic_pm_domain *genpd)
+{
+ return __of_genpd_add_provider(np, __of_genpd_xlate_simple, genpd);
+}
+static inline int of_genpd_add_provider_onecell(struct device_node *np,
+ struct genpd_onecell_data *data)
+{
+ return __of_genpd_add_provider(np, __of_genpd_xlate_onecell, data);
+}
+
#endif /* _LINUX_PM_DOMAIN_H */
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 22c7052..708b8a8 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -124,9 +124,9 @@
int printk(const char *fmt, ...);
/*
- * Special printk facility for scheduler use only, _DO_NOT_USE_ !
+ * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ !
*/
-__printf(1, 2) __cold int printk_sched(const char *fmt, ...);
+__printf(1, 2) __cold int printk_deferred(const char *fmt, ...);
/*
* Please don't use printk_ratelimit(), because it shares ratelimiting state
@@ -161,7 +161,7 @@
return 0;
}
static inline __printf(1, 2) __cold
-int printk_sched(const char *s, ...)
+int printk_deferred(const char *s, ...)
{
return 0;
}
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 9974975..4af3fdc 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -53,7 +53,8 @@
};
struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
- u32 sig, struct persistent_ram_ecc_info *ecc_info);
+ u32 sig, struct persistent_ram_ecc_info *ecc_info,
+ unsigned int memtype);
void persistent_ram_free(struct persistent_ram_zone *prz);
void persistent_ram_zap(struct persistent_ram_zone *prz);
@@ -76,6 +77,7 @@
struct ramoops_platform_data {
unsigned long mem_size;
unsigned long mem_address;
+ unsigned int mem_type;
unsigned long record_size;
unsigned long console_size;
unsigned long ftrace_size;
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 89573a3..bb980ae 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -5,6 +5,7 @@
#include <linux/sched.h> /* For struct task_struct. */
#include <linux/err.h> /* for IS_ERR_VALUE */
#include <linux/bug.h> /* For BUG_ON. */
+#include <linux/pid_namespace.h> /* For task_active_pid_ns. */
#include <uapi/linux/ptrace.h>
/*
@@ -129,6 +130,37 @@
}
/**
+ * ptrace_event_pid - possibly stop for a ptrace event notification
+ * @event: %PTRACE_EVENT_* value to report
+ * @pid: process identifier for %PTRACE_GETEVENTMSG to return
+ *
+ * Check whether @event is enabled and, if so, report @event and @pid
+ * to the ptrace parent. @pid is reported as the pid_t seen from the
+ * the ptrace parent's pid namespace.
+ *
+ * Called without locks.
+ */
+static inline void ptrace_event_pid(int event, struct pid *pid)
+{
+ /*
+ * FIXME: There's a potential race if a ptracer in a different pid
+ * namespace than parent attaches between computing message below and
+ * when we acquire tasklist_lock in ptrace_stop(). If this happens,
+ * the ptracer will get a bogus pid from PTRACE_GETEVENTMSG.
+ */
+ unsigned long message = 0;
+ struct pid_namespace *ns;
+
+ rcu_read_lock();
+ ns = task_active_pid_ns(rcu_dereference(current->parent));
+ if (ns)
+ message = pid_nr_ns(pid, ns);
+ rcu_read_unlock();
+
+ ptrace_event(event, message);
+}
+
+/**
* ptrace_init_task - initialize ptrace state for a new child
* @child: new child task
* @ptrace: true if child should be ptrace'd by parent's tracer
@@ -305,6 +337,9 @@
* calling arch_ptrace_stop() when it would be superfluous. For example,
* if the thread has not been back to user mode since the last stop, the
* thread state might indicate that nothing needs to be done.
+ *
+ * This is guaranteed to be invoked once before a task stops for ptrace and
+ * may include arch-specific operations necessary prior to a ptrace stop.
*/
#define arch_ptrace_stop_needed(code, info) (0)
#endif
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 1c50093..6965fe3 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -41,6 +41,7 @@
void inode_add_rsv_space(struct inode *inode, qsize_t number);
void inode_claim_rsv_space(struct inode *inode, qsize_t number);
void inode_sub_rsv_space(struct inode *inode, qsize_t number);
+void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
void dquot_initialize(struct inode *inode);
void dquot_drop(struct inode *inode);
@@ -59,6 +60,7 @@
int dquot_claim_space_nodirty(struct inode *inode, qsize_t number);
void dquot_free_inode(const struct inode *inode);
+void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number);
int dquot_disable(struct super_block *sb, int type, unsigned int flags);
/* Suspend quotas on remount RO */
@@ -238,6 +240,13 @@
return 0;
}
+static inline int dquot_reclaim_space_nodirty(struct inode *inode,
+ qsize_t number)
+{
+ inode_sub_bytes(inode, number);
+ return 0;
+}
+
static inline int dquot_disable(struct super_block *sb, int type,
unsigned int flags)
{
@@ -336,6 +345,12 @@
return ret;
}
+static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr)
+{
+ dquot_reclaim_space_nodirty(inode, nr << inode->i_blkbits);
+ mark_inode_dirty_sync(inode);
+}
+
static inline void dquot_free_space_nodirty(struct inode *inode, qsize_t nr)
{
__dquot_free_space(inode, nr, 0);
diff --git a/include/linux/random.h b/include/linux/random.h
index 3b9377d..bf9085e 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -17,6 +17,7 @@
extern void get_random_bytes(void *buf, int nbytes);
extern void get_random_bytes_arch(void *buf, int nbytes);
void generate_random_uuid(unsigned char uuid_out[16]);
+extern int random_int_secret_init(void);
#ifndef MODULE
extern const struct file_operations random_fops, urandom_fops;
@@ -49,9 +50,9 @@
{
u32 i = (seed >> 32) ^ (seed << 10) ^ seed;
- state->s1 = __seed(i, 1);
- state->s2 = __seed(i, 7);
- state->s3 = __seed(i, 15);
+ state->s1 = __seed(i, 2);
+ state->s2 = __seed(i, 8);
+ state->s3 = __seed(i, 16);
}
#ifdef CONFIG_ARCH_RANDOM
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index f4b1001..4106721 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -267,8 +267,9 @@
*/
#define list_first_or_null_rcu(ptr, type, member) \
({struct list_head *__ptr = (ptr); \
- struct list_head __rcu *__next = list_next_rcu(__ptr); \
- likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \
+ struct list_head *__next = ACCESS_ONCE(__ptr->next); \
+ likely(__ptr != __next) ? \
+ list_entry_rcu(__next, type, member) : NULL; \
})
/**
diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 23b3630..2ca9ed7 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -10,6 +10,11 @@
#define SYS_HALT 0x0002 /* Notify of system halt */
#define SYS_POWER_OFF 0x0003 /* Notify of system power off */
+enum reboot_mode {
+ REBOOT_COLD = 0,
+ REBOOT_WARM,
+};
+
extern int register_reboot_notifier(struct notifier_block *);
extern int unregister_reboot_notifier(struct notifier_block *);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 02d84e2..98c470ce 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -15,6 +15,8 @@
#include <linux/list.h>
#include <linux/rbtree.h>
+#include <linux/err.h>
+#include <linux/bug.h>
struct module;
struct device;
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d69cf63..49a4d6f 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -97,7 +97,7 @@
__ring_buffer_alloc((size), (flags), &__key); \
})
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu);
int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
struct file *filp, poll_table *poll_table);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 178a8d9..6ca9630 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -332,6 +332,10 @@
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
+#define SUID_DUMP_DISABLE 0 /* No setuid dumping */
+#define SUID_DUMP_USER 1 /* Dump as user of process */
+#define SUID_DUMP_ROOT 2 /* Dump as root */
+
/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
@@ -476,6 +480,7 @@
atomic_t sigcnt;
atomic_t live;
int nr_threads;
+ struct list_head thread_head;
wait_queue_head_t wait_chldexit; /* for wait4() */
@@ -885,6 +890,13 @@
bool cpus_share_cache(int this_cpu, int that_cpu);
+#ifdef CONFIG_SCHED_HMP
+struct hmp_domain {
+ struct cpumask cpus;
+ struct cpumask possible_cpus;
+ struct list_head hmp_domains;
+};
+#endif /* CONFIG_SCHED_HMP */
#else /* CONFIG_SMP */
struct sched_domain_attr;
@@ -931,8 +943,22 @@
u64 last_runnable_update;
s64 decay_count;
unsigned long load_avg_contrib;
+ unsigned long load_avg_ratio;
+#ifdef CONFIG_SCHED_HMP
+ u64 hmp_last_up_migration;
+ u64 hmp_last_down_migration;
+#endif
+ u32 usage_avg_sum;
};
+#ifdef CONFIG_SCHED_HMP
+/*
+ * We want to avoid boosting any processes forked from init (PID 1)
+ * and kthreadd (assumed to be PID 2).
+ */
+#define hmp_task_should_forkboost(task) ((task->parent && task->parent->pid > 2))
+#endif
+
#ifdef CONFIG_SCHEDSTATS
struct sched_statistics {
u64 wait_start;
@@ -1156,6 +1182,7 @@
/* PID/PID hash table linkage. */
struct pid_link pids[PIDTYPE_MAX];
struct list_head thread_group;
+ struct list_head thread_node;
struct completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
@@ -1405,6 +1432,12 @@
unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
} memcg_batch;
unsigned int memcg_kmem_skip_account;
+ struct memcg_oom_info {
+ struct mem_cgroup *memcg;
+ gfp_t gfp_mask;
+ int order;
+ unsigned int may_oom:1;
+ } memcg_oom;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
atomic_t ptrace_bp_refcnt;
@@ -1664,11 +1697,13 @@
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
-/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags */
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
static inline gfp_t memalloc_noio_flags(gfp_t flags)
{
if (unlikely(current->flags & PF_MEMALLOC_NOIO))
- flags &= ~__GFP_IO;
+ flags &= ~(__GFP_IO | __GFP_FS);
return flags;
}
@@ -2163,6 +2198,16 @@
#define while_each_thread(g, t) \
while ((t = next_thread(t)) != g)
+#define __for_each_thread(signal, t) \
+ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t) \
+ __for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t) \
+ for_each_process(p) for_each_thread(p, t)
+
static inline int get_nr_threads(struct task_struct *tsk)
{
return tsk->signal->nr_threads;
@@ -2469,34 +2514,98 @@
{
return task_thread_info(p)->status & TS_POLLING;
}
-static inline void current_set_polling(void)
+static inline void __current_set_polling(void)
{
current_thread_info()->status |= TS_POLLING;
}
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+ __current_set_polling();
+
+ /*
+ * Polling state must be visible before we test NEED_RESCHED,
+ * paired by resched_task()
+ */
+ smp_mb();
+
+ return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
{
current_thread_info()->status &= ~TS_POLLING;
- smp_mb__after_clear_bit();
+}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+ __current_clr_polling();
+
+ /*
+ * Polling state must be visible before we test NEED_RESCHED,
+ * paired by resched_task()
+ */
+ smp_mb();
+
+ return unlikely(tif_need_resched());
}
#elif defined(TIF_POLLING_NRFLAG)
static inline int tsk_is_polling(struct task_struct *p)
{
return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
}
-static inline void current_set_polling(void)
+
+static inline void __current_set_polling(void)
{
set_thread_flag(TIF_POLLING_NRFLAG);
}
-static inline void current_clr_polling(void)
+static inline bool __must_check current_set_polling_and_test(void)
+{
+ __current_set_polling();
+
+ /*
+ * Polling state must be visible before we test NEED_RESCHED,
+ * paired by resched_task()
+ *
+ * XXX: assumes set/clear bit are identical barrier wise.
+ */
+ smp_mb__after_clear_bit();
+
+ return unlikely(tif_need_resched());
+}
+
+static inline void __current_clr_polling(void)
{
clear_thread_flag(TIF_POLLING_NRFLAG);
}
+
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+ __current_clr_polling();
+
+ /*
+ * Polling state must be visible before we test NEED_RESCHED,
+ * paired by resched_task()
+ */
+ smp_mb__after_clear_bit();
+
+ return unlikely(tif_need_resched());
+}
+
#else
static inline int tsk_is_polling(struct task_struct *p) { return 0; }
-static inline void current_set_polling(void) { }
-static inline void current_clr_polling(void) { }
+static inline void __current_set_polling(void) { }
+static inline void __current_clr_polling(void) { }
+
+static inline bool __must_check current_set_polling_and_test(void)
+{
+ return unlikely(tif_need_resched());
+}
+static inline bool __must_check current_clr_polling_and_test(void)
+{
+ return unlikely(tif_need_resched());
+}
#endif
/*
diff --git a/include/linux/sem.h b/include/linux/sem.h
index 53d4265..976ce3a 100644
--- a/include/linux/sem.h
+++ b/include/linux/sem.h
@@ -12,10 +12,12 @@
struct sem_array {
struct kern_ipc_perm ____cacheline_aligned_in_smp
sem_perm; /* permissions .. see ipc.h */
- time_t sem_otime; /* last semop time */
time_t sem_ctime; /* last change time */
struct sem *sem_base; /* ptr to first semaphore in array */
- struct list_head sem_pending; /* pending operations to be processed */
+ struct list_head pending_alter; /* pending operations */
+ /* that alter the array */
+ struct list_head pending_const; /* pending complex operations */
+ /* that do not alter semvals */
struct list_head list_id; /* undo requests on this array */
int sem_nsems; /* no. of semaphores in array */
int complex_count; /* pending complex operations */
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 87d4bbc..c2b355f 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -279,6 +279,22 @@
/*
* Console helpers.
*/
+struct earlycon_device {
+ struct console *con;
+ struct uart_port port;
+ char options[16]; /* e.g., 115200n8 */
+ unsigned int baud;
+};
+int setup_earlycon(char *buf, const char *match,
+ int (*setup)(struct earlycon_device *, const char *));
+
+#define EARLYCON_DECLARE(name, func) \
+static int __init name ## _setup_earlycon(char *buf) \
+{ \
+ return setup_earlycon(buf, __stringify(name), func); \
+} \
+early_param("earlycon", name ## _setup_earlycon);
+
struct uart_port *uart_get_console(struct uart_port *ports, int nr,
struct console *c);
void uart_parse_options(char *options, int *baud, int *parity, int *bits,
diff --git a/include/linux/signal.h b/include/linux/signal.h
index d897484..2ac423b 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -434,6 +434,14 @@
int restore_altstack(const stack_t __user *);
int __save_altstack(stack_t __user *, unsigned long);
+#define save_altstack_ex(uss, sp) do { \
+ stack_t __user *__uss = uss; \
+ struct task_struct *t = current; \
+ put_user_ex((void __user *)t->sas_ss_sp, &__uss->ss_sp); \
+ put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \
+ put_user_ex(t->sas_ss_size, &__uss->ss_size); \
+} while (0);
+
#ifdef CONFIG_PROC_FS
struct seq_file;
extern void render_sigset_t(struct seq_file *, const char *, sigset_t *);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index dec1748..478120a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -331,11 +331,6 @@
typedef unsigned char *sk_buff_data_t;
#endif
-#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \
- defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-#define NET_SKBUFF_NF_DEFRAG_NEEDED 1
-#endif
-
/**
* struct sk_buff - socket buffer
* @next: Next buffer in list
@@ -368,7 +363,6 @@
* @protocol: Packet protocol from driver
* @destructor: Destruct function
* @nfct: Associated connection, if any
- * @nfct_reasm: netfilter conntrack re-assembly pointer
* @nf_bridge: Saved data about a bridged frame - see br_netfilter.c
* @skb_iif: ifindex of device we arrived on
* @tc_index: Traffic control index
@@ -455,9 +449,6 @@
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
struct nf_conntrack *nfct;
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- struct sk_buff *nfct_reasm;
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
struct nf_bridge_info *nf_bridge;
#endif
@@ -1308,6 +1299,11 @@
return len + skb_headlen(skb);
}
+static inline bool skb_has_frags(const struct sk_buff *skb)
+{
+ return skb_shinfo(skb)->nr_frags;
+}
+
/**
* __skb_fill_page_desc - initialise a paged fragment in an skb
* @skb: buffer containing fragment to be initialised
@@ -1745,6 +1741,11 @@
}
#endif /* NET_SKBUFF_DATA_USES_OFFSET */
+static inline void skb_pop_mac_header(struct sk_buff *skb)
+{
+ skb->mac_header = skb->network_header;
+}
+
static inline void skb_probe_transport_header(struct sk_buff *skb,
const int offset_hint)
{
@@ -2487,6 +2488,8 @@
extern struct sk_buff *skb_segment(struct sk_buff *skb,
netdev_features_t features);
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
+
static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
int len, void *buffer)
{
@@ -2695,18 +2698,6 @@
atomic_inc(&nfct->use);
}
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
-static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
-{
- if (skb)
- atomic_inc(&skb->users);
-}
-static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
-{
- if (skb)
- kfree_skb(skb);
-}
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge)
{
@@ -2725,10 +2716,6 @@
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- nf_conntrack_put_reasm(skb->nfct_reasm);
- skb->nfct_reasm = NULL;
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
skb->nf_bridge = NULL;
@@ -2750,10 +2737,6 @@
nf_conntrack_get(src->nfct);
dst->nfctinfo = src->nfctinfo;
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- dst->nfct_reasm = src->nfct_reasm;
- nf_conntrack_get_reasm(src->nfct_reasm);
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
dst->nf_bridge = src->nf_bridge;
nf_bridge_get(src->nf_bridge);
@@ -2765,9 +2748,6 @@
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
nf_conntrack_put(dst->nfct);
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- nf_conntrack_put_reasm(dst->nfct_reasm);
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(dst->nf_bridge);
#endif
@@ -2933,5 +2913,22 @@
{
return !skb->head_frag || skb_cloned(skb);
}
+
+/**
+ * skb_gso_network_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_network_seglen is used to determine the real size of the
+ * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
+ *
+ * The MAC/L2 header is not accounted for.
+ */
+static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
+{
+ unsigned int hdr_len = skb_transport_header(skb) -
+ skb_network_header(skb);
+ return hdr_len + skb_gso_transport_seglen(skb);
+}
#endif /* __KERNEL__ */
#endif /* _LINUX_SKBUFF_H */
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index 54f91d3..46cca4c 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -23,7 +23,7 @@
void sock_diag_save_cookie(void *sk, __u32 *cookie);
int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr);
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype);
#endif
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 7d537ce..75f3494 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -117,9 +117,17 @@
#endif /*arch_spin_is_contended*/
#endif
-/* The lock does not imply full memory barrier. */
-#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
-static inline void smp_mb__after_lock(void) { smp_mb(); }
+/*
+ * Despite its name it doesn't necessarily has to be a full barrier.
+ * It should only guarantee that a STORE before the critical section
+ * can not be reordered with a LOAD inside this section.
+ * spin_lock() is the one-way barrier, this LOAD can not escape out
+ * of the region. So the default implementation simply ensures that
+ * a STORE can not move into the critical section, smp_wmb() should
+ * serialize it with another STORE done by spin_lock().
+ */
+#ifndef smp_mb__before_spinlock
+#define smp_mb__before_spinlock() smp_wmb()
#endif
/**
diff --git a/include/linux/string.h b/include/linux/string.h
index ac889c5..0ed878d 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -129,7 +129,7 @@
#endif
extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
- const void *from, size_t available);
+ const void *from, size_t available);
/**
* strstarts - does @str start with @prefix?
@@ -141,7 +141,8 @@
return strncmp(str, prefix, strlen(prefix)) == 0;
}
-extern size_t memweight(const void *ptr, size_t bytes);
+size_t memweight(const void *ptr, size_t bytes);
+void memzero_explicit(void *s, size_t count);
/**
* kbasename - return the last part of a pathname.
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 84ca436..9faf0f4 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -130,6 +130,7 @@
#define RPC_TASK_SOFTCONN 0x0400 /* Fail if can't connect */
#define RPC_TASK_SENT 0x0800 /* message was sent */
#define RPC_TASK_TIMEOUT 0x1000 /* fail with ETIMEDOUT on timeout */
+#define RPC_TASK_NOCONNECT 0x2000 /* return ENOTCONN if not connected */
#define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC)
#define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER)
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b05963f..f5bfb1a 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -32,6 +32,7 @@
struct svc_xprt_ops *xcl_ops;
struct list_head xcl_list;
u32 xcl_max_payload;
+ int xcl_ident;
};
/*
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 62fd1b7..947009e 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -56,6 +56,7 @@
int svc_send(struct svc_rqst *);
void svc_drop(struct svc_rqst *);
void svc_sock_update_bufs(struct svc_serv *serv);
+bool svc_alien_sock(struct net *net, int fd);
int svc_addsock(struct svc_serv *serv, const int fd,
char *name_return, const size_t len);
void svc_init_xprt_sock(void);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 4147d70..84662ec 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -802,9 +802,14 @@
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int,
int __user *);
#else
+#ifdef CONFIG_CLONE_BACKWARDS3
+asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *,
+ int __user *, int);
+#else
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
int __user *, int);
#endif
+#endif
asmlinkage long sys_execve(const char __user *filename,
const char __user *const __user *argv,
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index e2cee22..7dd65cb 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -17,6 +17,7 @@
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/kobject_ns.h>
+#include <linux/stat.h>
#include <linux/atomic.h>
struct kobject;
@@ -68,17 +69,25 @@
* for examples..
*/
-#define __ATTR(_name,_mode,_show,_store) { \
- .attr = {.name = __stringify(_name), .mode = _mode }, \
- .show = _show, \
- .store = _store, \
+#define __ATTR(_name,_mode,_show,_store) { \
+ .attr = {.name = __stringify(_name), .mode = _mode }, \
+ .show = _show, \
+ .store = _store, \
}
-#define __ATTR_RO(_name) { \
- .attr = { .name = __stringify(_name), .mode = 0444 }, \
- .show = _name##_show, \
+#define __ATTR_RO(_name) { \
+ .attr = { .name = __stringify(_name), .mode = S_IRUGO }, \
+ .show = _name##_show, \
}
+#define __ATTR_WO(_name) { \
+ .attr = { .name = __stringify(_name), .mode = S_IWUSR }, \
+ .store = _name##_store, \
+}
+
+#define __ATTR_RW(_name) __ATTR(_name, (S_IWUSR | S_IRUGO), \
+ _name##_show, _name##_store)
+
#define __ATTR_NULL { .attr = { .name = NULL } }
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -92,6 +101,18 @@
#define __ATTR_IGNORE_LOCKDEP __ATTR
#endif
+#define __ATTRIBUTE_GROUPS(_name) \
+static const struct attribute_group *_name##_groups[] = { \
+ &_name##_group, \
+ NULL, \
+}
+
+#define ATTRIBUTE_GROUPS(_name) \
+static const struct attribute_group _name##_group = { \
+ .attrs = _name##_attrs, \
+}; \
+__ATTRIBUTE_GROUPS(_name)
+
#define attr_name(_attr) (_attr).attr.name
struct file;
@@ -121,6 +142,36 @@
*/
#define sysfs_bin_attr_init(bin_attr) sysfs_attr_init(&(bin_attr)->attr)
+/* macros to create static binary attributes easier */
+#define __BIN_ATTR(_name, _mode, _read, _write, _size) { \
+ .attr = { .name = __stringify(_name), .mode = _mode }, \
+ .read = _read, \
+ .write = _write, \
+ .size = _size, \
+}
+
+#define __BIN_ATTR_RO(_name, _size) { \
+ .attr = { .name = __stringify(_name), .mode = S_IRUGO }, \
+ .read = _name##_read, \
+ .size = _size, \
+}
+
+#define __BIN_ATTR_RW(_name, _size) __BIN_ATTR(_name, \
+ (S_IWUSR | S_IRUGO), _name##_read, \
+ _name##_write)
+
+#define __BIN_ATTR_NULL __ATTR_NULL
+
+#define BIN_ATTR(_name, _mode, _read, _write, _size) \
+struct bin_attribute bin_attr_##_name = __BIN_ATTR(_name, _mode, _read, \
+ _write, _size)
+
+#define BIN_ATTR_RO(_name, _size) \
+struct bin_attribute bin_attr_##_name = __BIN_ATTR_RO(_name, _size)
+
+#define BIN_ATTR_RW(_name, _size) \
+struct bin_attribute bin_attr_##_name = __BIN_ATTR_RW(_name, _size)
+
struct sysfs_ops {
ssize_t (*show)(struct kobject *, struct attribute *,char *);
ssize_t (*store)(struct kobject *,struct attribute *,const char *, size_t);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index a386a1c..55fce47 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -25,6 +25,7 @@
#ifndef __THERMAL_H__
#define __THERMAL_H__
+#include <linux/of.h>
#include <linux/idr.h>
#include <linux/device.h>
#include <linux/workqueue.h>
@@ -143,6 +144,7 @@
int id;
char type[THERMAL_NAME_LENGTH];
struct device device;
+ struct device_node *np;
void *devdata;
const struct thermal_cooling_device_ops *ops;
bool updated; /* true if the cooling device does not need update */
@@ -172,7 +174,7 @@
int emul_temperature;
int passive;
unsigned int forced_passive;
- const struct thermal_zone_device_ops *ops;
+ struct thermal_zone_device_ops *ops;
const struct thermal_zone_params *tzp;
struct thermal_governor *governor;
struct list_head thermal_instances;
@@ -214,6 +216,14 @@
/* Structure to define Thermal Zone parameters */
struct thermal_zone_params {
char governor_name[THERMAL_NAME_LENGTH];
+
+ /*
+ * a boolean to indicate if the thermal to hwmon sysfs interface
+ * is required. when no_hwmon == false, a hwmon sysfs interface
+ * will be created. when no_hwmon == true, nothing will be done
+ */
+ bool no_hwmon;
+
int num_tbps; /* Number of tbp entries */
struct thermal_bind_params *tbp;
};
@@ -224,8 +234,31 @@
};
/* Function declarations */
+#ifdef CONFIG_THERMAL_OF
+struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int id,
+ void *data, int (*get_temp)(void *, long *),
+ int (*get_trend)(void *, long *));
+void thermal_zone_of_sensor_unregister(struct device *dev,
+ struct thermal_zone_device *tz);
+#else
+static inline struct thermal_zone_device *
+thermal_zone_of_sensor_register(struct device *dev, int id,
+ void *data, int (*get_temp)(void *, long *),
+ int (*get_trend)(void *, long *))
+{
+ return NULL;
+}
+
+static inline
+void thermal_zone_of_sensor_unregister(struct device *dev,
+ struct thermal_zone_device *tz)
+{
+}
+
+#endif
struct thermal_zone_device *thermal_zone_device_register(const char *, int, int,
- void *, const struct thermal_zone_device_ops *,
+ void *, struct thermal_zone_device_ops *,
const struct thermal_zone_params *, int, int);
void thermal_zone_device_unregister(struct thermal_zone_device *);
@@ -238,6 +271,9 @@
struct thermal_cooling_device *thermal_cooling_device_register(char *, void *,
const struct thermal_cooling_device_ops *);
+struct thermal_cooling_device *
+thermal_of_cooling_device_register(struct device_node *np, char *, void *,
+ const struct thermal_cooling_device_ops *);
void thermal_cooling_device_unregister(struct thermal_cooling_device *);
struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name);
int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp);
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e7e0473..4ae6f32 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -107,6 +107,8 @@
#define set_need_resched() set_thread_flag(TIF_NEED_RESCHED)
#define clear_need_resched() clear_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+
#if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
/*
* An arch can define its own version of set_restore_sigmask() to get the
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 9180f4b..62bd8b7 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -174,10 +174,4 @@
#endif
-# ifdef CONFIG_CPU_IDLE_GOV_MENU
-extern void menu_hrtimer_cancel(void);
-# else
-static inline void menu_hrtimer_cancel(void) {}
-# endif /* CONFIG_CPU_IDLE_GOV_MENU */
-
#endif
diff --git a/include/linux/time.h b/include/linux/time.h
index d5d229b..7d532a3 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -173,6 +173,19 @@
extern void monotonic_to_bootbased(struct timespec *ts);
extern void get_monotonic_boottime(struct timespec *ts);
+static inline bool timeval_valid(const struct timeval *tv)
+{
+ /* Dates before 1970 are bogus */
+ if (tv->tv_sec < 0)
+ return false;
+
+ /* Can't have more microseconds then a second */
+ if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+ return false;
+
+ return true;
+}
+
extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
extern int timekeeping_valid_for_hres(void);
extern u64 timekeeping_max_deferment(void);
diff --git a/include/linux/timex.h b/include/linux/timex.h
index b3726e6..dd3edd7 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -141,6 +141,7 @@
extern void hardpps(const struct timespec *, const struct timespec *);
int read_current_timer(unsigned long *timer_val);
+void ntp_notify_cmos_timer(void);
/* The clock frequency of the i8253/i8254 PIT */
#define PIT_TICK_RATE 1193182ul
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index f8e084d..ba60501 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -60,6 +60,12 @@
unsigned int num_tracepoints;
struct tracepoint * const *tracepoints_ptrs;
};
+bool trace_module_has_bad_taint(struct module *mod);
+#else
+static inline bool trace_module_has_bad_taint(struct module *mod)
+{
+ return false;
+}
#endif /* CONFIG_MODULES */
struct tracepoint_iter {
diff --git a/include/linux/usb.h b/include/linux/usb.h
index a0bee5a..28bd3a8 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -206,6 +206,32 @@
#define USB_MAXINTERFACES 32
#define USB_MAXIADS (USB_MAXINTERFACES/2)
+/*
+ * USB Resume Timer: Every Host controller driver should drive the resume
+ * signalling on the bus for the amount of time defined by this macro.
+ *
+ * That way we will have a 'stable' behavior among all HCDs supported by Linux.
+ *
+ * Note that the USB Specification states we should drive resume for *at least*
+ * 20 ms, but it doesn't give an upper bound. This creates two possible
+ * situations which we want to avoid:
+ *
+ * (a) sometimes an msleep(20) might expire slightly before 20 ms, which causes
+ * us to fail USB Electrical Tests, thus failing Certification
+ *
+ * (b) Some (many) devices actually need more than 20 ms of resume signalling,
+ * and while we can argue that's against the USB Specification, we don't have
+ * control over which devices a certification laboratory will be using for
+ * certification. If CertLab uses a device which was tested against Windows and
+ * that happens to have relaxed resume signalling rules, we might fall into
+ * situations where we fail interoperability and electrical tests.
+ *
+ * In order to avoid both conditions, we're using a 40 ms resume timeout, which
+ * should cope with both LPJ calibration errors and devices not following every
+ * detail of the USB Specification.
+ */
+#define USB_RESUME_TIMEOUT 40 /* ms */
+
/**
* struct usb_interface_cache - long-term representation of a device interface
* @num_altsetting: number of altsettings defined.
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index f5f5c7d..287b906 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -410,12 +410,13 @@
extern void usb_hcd_pci_remove(struct pci_dev *dev);
extern void usb_hcd_pci_shutdown(struct pci_dev *dev);
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
extern const struct dev_pm_ops usb_hcd_pci_pm_ops;
#endif
#endif /* CONFIG_PCI */
/* pci-ish (pdev null is ok) buffer alloc/mapping support */
+void usb_init_pool_max(void);
int hcd_buffer_create(struct usb_hcd *hcd);
void hcd_buffer_destroy(struct usb_hcd *hcd);
diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h
index 52f944d..49587dc 100644
--- a/include/linux/usb/quirks.h
+++ b/include/linux/usb/quirks.h
@@ -30,4 +30,7 @@
descriptor */
#define USB_QUIRK_DELAY_INIT 0x00000040
+/* device generates spurious wakeup, ignore remote wakeup capability */
+#define USB_QUIRK_IGNORE_REMOTE_WAKEUP 0x00000200
+
#endif /* __LINUX_USB_QUIRKS_H */
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index f18d641..123b21b 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -30,7 +30,7 @@
struct driver_info *driver_info;
const char *driver_name;
void *driver_priv;
- wait_queue_head_t *wait;
+ wait_queue_head_t wait;
struct mutex phy_mutex;
unsigned char suspend_count;
unsigned char pkt_cnt, pkt_err;
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index bf99cd0..6303568 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -66,7 +66,9 @@
US_FLAG(INITIAL_READ10, 0x00100000) \
/* Initial READ(10) (and others) must be retried */ \
US_FLAG(WRITE_CACHE, 0x00200000) \
- /* Write Cache status is not available */
+ /* Write Cache status is not available */ \
+ US_FLAG(NEEDS_CAP16, 0x00400000)
+ /* cannot handle READ_CAPACITY_10 */
#define US_FLAG(name, value) US_FL_##name = value ,
enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index b6b215f..a37081c 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -17,15 +17,21 @@
} extent[UID_GID_MAP_MAX_EXTENTS];
};
+#define USERNS_SETGROUPS_ALLOWED 1UL
+
+#define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
+
struct user_namespace {
struct uid_gid_map uid_map;
struct uid_gid_map gid_map;
struct uid_gid_map projid_map;
atomic_t count;
struct user_namespace *parent;
+ int level;
kuid_t owner;
kgid_t group;
unsigned int proc_inum;
+ unsigned long flags;
bool may_mount_sysfs;
bool may_mount_proc;
};
@@ -58,6 +64,9 @@
extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *);
+extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *);
+extern int proc_setgroups_show(struct seq_file *m, void *v);
+extern bool userns_may_setgroups(const struct user_namespace *ns);
#else
static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
@@ -82,6 +91,10 @@
{
}
+static inline bool userns_may_setgroups(const struct user_namespace *ns)
+{
+ return true;
+}
#endif
void update_mnt_policy(struct user_namespace *userns);
diff --git a/include/linux/vexpress.h b/include/linux/vexpress.h
index ea7168a..c1191ab 100644
--- a/include/linux/vexpress.h
+++ b/include/linux/vexpress.h
@@ -68,7 +68,8 @@
*/
struct vexpress_config_bridge_info {
const char *name;
- void *(*func_get)(struct device *dev, struct device_node *node);
+ void *(*func_get)(struct device *dev, struct device_node *node,
+ const char *id);
void (*func_put)(void *func);
int (*func_exec)(void *func, int offset, bool write, u32 *data);
};
@@ -87,12 +88,17 @@
struct vexpress_config_func;
-struct vexpress_config_func *__vexpress_config_func_get(struct device *dev,
- struct device_node *node);
+struct vexpress_config_func *__vexpress_config_func_get(
+ struct vexpress_config_bridge *bridge,
+ struct device *dev,
+ struct device_node *node,
+ const char *id);
+#define vexpress_config_func_get(bridge, id) \
+ __vexpress_config_func_get(bridge, NULL, NULL, id)
#define vexpress_config_func_get_by_dev(dev) \
- __vexpress_config_func_get(dev, NULL)
+ __vexpress_config_func_get(NULL, dev, NULL, NULL)
#define vexpress_config_func_get_by_node(node) \
- __vexpress_config_func_get(NULL, node)
+ __vexpress_config_func_get(NULL, NULL, node, NULL)
void vexpress_config_func_put(struct vexpress_config_func *func);
/* Both may sleep! */
@@ -120,7 +126,53 @@
struct clk *vexpress_osc_setup(struct device *dev);
void vexpress_osc_of_setup(struct device_node *node);
+struct clk *vexpress_clk_register_spc(const char *name, int cluster_id);
+void vexpress_clk_of_register_spc(void);
+
void vexpress_clk_init(void __iomem *sp810_base);
void vexpress_clk_of_init(void);
+/* SPC */
+
+#define VEXPRESS_SPC_WAKE_INTR_IRQ(cluster, cpu) \
+ (1 << (4 * (cluster) + (cpu)))
+#define VEXPRESS_SPC_WAKE_INTR_FIQ(cluster, cpu) \
+ (1 << (7 * (cluster) + (cpu)))
+#define VEXPRESS_SPC_WAKE_INTR_SWDOG (1 << 10)
+#define VEXPRESS_SPC_WAKE_INTR_GTIMER (1 << 11)
+#define VEXPRESS_SPC_WAKE_INTR_MASK 0xFFF
+
+#ifdef CONFIG_VEXPRESS_SPC
+extern bool vexpress_spc_check_loaded(void);
+extern void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster, bool set);
+extern void vexpress_spc_set_global_wakeup_intr(bool set);
+extern int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr);
+extern int vexpress_spc_get_performance(u32 cluster, u32 *freq);
+extern int vexpress_spc_set_performance(u32 cluster, u32 freq);
+extern void vexpress_spc_write_resume_reg(u32 cluster, u32 cpu, u32 addr);
+extern int vexpress_spc_get_nb_cpus(u32 cluster);
+extern void vexpress_spc_powerdown_enable(u32 cluster, bool enable);
+#else
+static inline bool vexpress_spc_check_loaded(void) { return false; }
+static inline void vexpress_spc_set_cpu_wakeup_irq(u32 cpu, u32 cluster,
+ bool set) { }
+static inline void vexpress_spc_set_global_wakeup_intr(bool set) { }
+static inline int vexpress_spc_get_freq_table(u32 cluster, u32 **fptr)
+{
+ return -ENODEV;
+}
+static inline int vexpress_spc_get_performance(u32 cluster, u32 *freq)
+{
+ return -ENODEV;
+}
+static inline int vexpress_spc_set_performance(u32 cluster, u32 freq)
+{
+ return -ENODEV;
+}
+static inline void vexpress_spc_write_resume_reg(u32 cluster,
+ u32 cpu, u32 addr) { }
+static inline int vexpress_spc_get_nb_cpus(u32 cluster) { return -ENODEV; }
+static inline void vexpress_spc_powerdown_enable(u32 cluster, bool enable) { }
+#endif
+
#endif
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 9ff8645..72398ee 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -70,6 +70,10 @@
bool virtqueue_enable_cb(struct virtqueue *vq);
+unsigned virtqueue_enable_cb_prepare(struct virtqueue *vq);
+
+bool virtqueue_poll(struct virtqueue *vq, unsigned);
+
bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
void *virtqueue_detach_unused_buf(struct virtqueue *vq);
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index bd6cf61..8c0f6cb 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -39,6 +39,7 @@
PAGEOUTRUN, ALLOCSTALL, PGROTATED,
#ifdef CONFIG_NUMA_BALANCING
NUMA_PTE_UPDATES,
+ NUMA_HUGE_PTE_UPDATES,
NUMA_HINT_FAULTS,
NUMA_HINT_FAULTS_LOCAL,
NUMA_PAGE_MIGRATE,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index c586679..2d4e3d7 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -142,9 +142,6 @@
return x;
}
-extern unsigned long global_reclaimable_pages(void);
-extern unsigned long zone_reclaimable_pages(struct zone *zone);
-
#ifdef CONFIG_NUMA
/*
* Determine the per node value of a stat item. This function
@@ -198,7 +195,7 @@
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
-void refresh_cpu_vm_stats(int);
+bool refresh_cpu_vm_stats(int);
void refresh_zone_stat_thresholds(void);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 1133695..c8e5760 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -805,6 +805,63 @@
__ret; \
})
+#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \
+ lock, ret) \
+do { \
+ DEFINE_WAIT(__wait); \
+ \
+ for (;;) { \
+ prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \
+ if (condition) \
+ break; \
+ if (signal_pending(current)) { \
+ ret = -ERESTARTSYS; \
+ break; \
+ } \
+ spin_unlock_irq(&lock); \
+ ret = schedule_timeout(ret); \
+ spin_lock_irq(&lock); \
+ if (!ret) \
+ break; \
+ } \
+ finish_wait(&wq, &__wait); \
+} while (0)
+
+/**
+ * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses.
+ * The condition is checked under the lock. This is expected
+ * to be called with the lock taken.
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @lock: a locked spinlock_t, which will be released before schedule()
+ * and reacquired afterwards.
+ * @timeout: timeout, in jiffies
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true or signal is received. The @condition is
+ * checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * This is supposed to be called while holding the lock. The lock is
+ * dropped before going to sleep and is reacquired afterwards.
+ *
+ * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it
+ * was interrupted by a signal, and the remaining jiffies otherwise
+ * if the condition evaluated to true before the timeout elapsed.
+ */
+#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \
+ timeout) \
+({ \
+ int __ret = timeout; \
+ \
+ if (!(condition)) \
+ __wait_event_interruptible_lock_irq_timeout( \
+ wq, condition, lock, __ret); \
+ __ret; \
+})
+
/*
* These are the old interfaces to sleep waiting for an event.
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 623488f..ac14ece 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -71,7 +71,8 @@
/* data contains off-queue information when !WORK_STRUCT_PWQ */
WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT,
- WORK_OFFQ_CANCELING = (1 << WORK_OFFQ_FLAG_BASE),
+ __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE,
+ WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING),
/*
* When a work item is off queue, its high bits point to the last
@@ -303,6 +304,33 @@
WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */
WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */
+ /*
+ * Per-cpu workqueues are generally preferred because they tend to
+ * show better performance thanks to cache locality. Per-cpu
+ * workqueues exclude the scheduler from choosing the CPU to
+ * execute the worker threads, which has an unfortunate side effect
+ * of increasing power consumption.
+ *
+ * The scheduler considers a CPU idle if it doesn't have any task
+ * to execute and tries to keep idle cores idle to conserve power;
+ * however, for example, a per-cpu work item scheduled from an
+ * interrupt handler on an idle CPU will force the scheduler to
+ * excute the work item on that CPU breaking the idleness, which in
+ * turn may lead to more scheduling choices which are sub-optimal
+ * in terms of power consumption.
+ *
+ * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default
+ * but become unbound if workqueue.power_efficient kernel param is
+ * specified. Per-cpu workqueues which are identified to
+ * contribute significantly to power-consumption are identified and
+ * marked with this flag and enabling the power_efficient mode
+ * leads to noticeable power saving at the cost of small
+ * performance disadvantage.
+ *
+ * http://thread.gmane.org/gmane.linux.kernel/1480396
+ */
+ WQ_POWER_EFFICIENT = 1 << 7,
+
__WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */
__WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
@@ -333,11 +361,19 @@
*
* system_freezable_wq is equivalent to system_wq except that it's
* freezable.
+ *
+ * *_power_efficient_wq are inclined towards saving power and converted
+ * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise,
+ * they are same as their non-power-efficient counterparts - e.g.
+ * system_power_efficient_wq is identical to system_wq if
+ * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info.
*/
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_long_wq;
extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *system_freezable_wq;
+extern struct workqueue_struct *system_power_efficient_wq;
+extern struct workqueue_struct *system_freezable_power_efficient_wq;
static inline struct workqueue_struct * __deprecated __system_nrt_wq(void)
{
@@ -414,7 +450,7 @@
#define create_freezable_workqueue(name) \
alloc_workqueue((name), WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
#define create_singlethread_workqueue(name) \
- alloc_workqueue((name), WQ_UNBOUND | WQ_MEM_RECLAIM, 1)
+ alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
extern void destroy_workqueue(struct workqueue_struct *wq);
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
new file mode 100644
index 0000000..f14bd75
--- /dev/null
+++ b/include/linux/zpool.h
@@ -0,0 +1,106 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for the zbud and zsmalloc memory
+ * storage pool implementations. Typically, this is used to
+ * store compressed memory.
+ */
+
+#ifndef _ZPOOL_H_
+#define _ZPOOL_H_
+
+struct zpool;
+
+struct zpool_ops {
+ int (*evict)(struct zpool *pool, unsigned long handle);
+};
+
+/*
+ * Control how a handle is mapped. It will be ignored if the
+ * implementation does not support it. Its use is optional.
+ * Note that this does not refer to memory protection, it
+ * refers to how the memory will be copied in/out if copying
+ * is necessary during mapping; read-write is the safest as
+ * it copies the existing memory in on map, and copies the
+ * changed memory back out on unmap. Write-only does not copy
+ * in the memory and should only be used for initialization.
+ * If in doubt, use ZPOOL_MM_DEFAULT which is read-write.
+ */
+enum zpool_mapmode {
+ ZPOOL_MM_RW, /* normal read-write mapping */
+ ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */
+ ZPOOL_MM_WO, /* write-only (no copy-in at map time) */
+
+ ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
+};
+
+struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+
+char *zpool_get_type(struct zpool *pool);
+
+void zpool_destroy_pool(struct zpool *pool);
+
+int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp,
+ unsigned long *handle);
+
+void zpool_free(struct zpool *pool, unsigned long handle);
+
+int zpool_shrink(struct zpool *pool, unsigned int pages,
+ unsigned int *reclaimed);
+
+void *zpool_map_handle(struct zpool *pool, unsigned long handle,
+ enum zpool_mapmode mm);
+
+void zpool_unmap_handle(struct zpool *pool, unsigned long handle);
+
+u64 zpool_get_total_size(struct zpool *pool);
+
+
+/**
+ * struct zpool_driver - driver implementation for zpool
+ * @type: name of the driver.
+ * @list: entry in the list of zpool drivers.
+ * @create: create a new pool.
+ * @destroy: destroy a pool.
+ * @malloc: allocate mem from a pool.
+ * @free: free mem from a pool.
+ * @shrink: shrink the pool.
+ * @map: map a handle.
+ * @unmap: unmap a handle.
+ * @total_size: get total size of a pool.
+ *
+ * This is created by a zpool implementation and registered
+ * with zpool.
+ */
+struct zpool_driver {
+ char *type;
+ struct module *owner;
+ atomic_t refcount;
+ struct list_head list;
+
+ void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+ void (*destroy)(void *pool);
+
+ int (*malloc)(void *pool, size_t size, gfp_t gfp,
+ unsigned long *handle);
+ void (*free)(void *pool, unsigned long handle);
+
+ int (*shrink)(void *pool, unsigned int pages,
+ unsigned int *reclaimed);
+
+ void *(*map)(void *pool, unsigned long handle,
+ enum zpool_mapmode mm);
+ void (*unmap)(void *pool, unsigned long handle);
+
+ u64 (*total_size)(void *pool);
+};
+
+void zpool_register_driver(struct zpool_driver *driver);
+
+int zpool_unregister_driver(struct zpool_driver *driver);
+
+int zpool_evict(void *pool, unsigned long handle);
+
+#endif
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
new file mode 100644
index 0000000..ebb2841
--- /dev/null
+++ b/include/linux/zsmalloc.h
@@ -0,0 +1,44 @@
+/*
+ * zsmalloc memory allocator
+ *
+ * Copyright (C) 2011 Nitin Gupta
+ * Copyright (C) 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the license that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+#ifndef _ZS_MALLOC_H_
+#define _ZS_MALLOC_H_
+
+#include <linux/types.h>
+
+/*
+ * zsmalloc mapping modes
+ *
+ * NOTE: These only make a difference when a mapped object spans pages
+*/
+enum zs_mapmode {
+ ZS_MM_RW, /* normal read-write mapping */
+ ZS_MM_RO, /* read-only (no copy-out at unmap time) */
+ ZS_MM_WO /* write-only (no copy-in at map time) */
+};
+
+struct zs_pool;
+
+struct zs_pool *zs_create_pool(gfp_t flags);
+void zs_destroy_pool(struct zs_pool *pool);
+
+unsigned long zs_malloc(struct zs_pool *pool, size_t size);
+void zs_free(struct zs_pool *pool, unsigned long obj);
+
+void *zs_map_object(struct zs_pool *pool, unsigned long handle,
+ enum zs_mapmode mm);
+void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
+
+unsigned long zs_get_total_pages(struct zs_pool *pool);
+
+#endif
diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index 7343a27..47ada23 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -22,6 +22,7 @@
#define _V4L2_CTRLS_H
#include <linux/list.h>
+#include <linux/mutex.h>
#include <linux/videodev2.h>
/* forward references */
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index d88a098..2cc4e0d 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -318,6 +318,9 @@
* @done_wq: waitqueue for processes waiting for buffers ready to be dequeued
* @alloc_ctx: memory type/allocator-specific contexts for each plane
* @streaming: current streaming state
+ * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for
+ * buffers. Only set for capture queues if qbuf has not yet been
+ * called since poll() needs to return POLLERR in that situation.
* @fileio: file io emulator internal data, used only if emulator is active
*/
struct vb2_queue {
@@ -350,6 +353,7 @@
unsigned int plane_sizes[VIDEO_MAX_PLANES];
unsigned int streaming:1;
+ unsigned int waiting_for_buffers:1;
struct vb2_fileio_data *fileio;
};
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 21f70270..2510068 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -73,6 +73,10 @@
const struct in6_addr *addr);
#endif
+bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
+ const unsigned int prefix_len,
+ struct net_device *dev);
+
extern int ipv6_chk_prefix(const struct in6_addr *addr,
struct net_device *dev);
@@ -86,6 +90,9 @@
const struct in6_addr *daddr,
unsigned int srcprefs,
struct in6_addr *saddr);
+extern int __ipv6_get_lladdr(struct inet6_dev *idev,
+ struct in6_addr *addr,
+ unsigned char banned_flags);
extern int ipv6_get_lladdr(struct net_device *dev,
struct in6_addr *addr,
unsigned char banned_flags);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e0512aa..0ef0006 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -104,6 +104,7 @@
enum {
HCI_SETUP,
HCI_AUTO_OFF,
+ HCI_RFKILLED,
HCI_MGMT,
HCI_PAIRABLE,
HCI_SERVICE_CACHE,
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index a7a683e..a8c2ef6 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -290,6 +290,7 @@
unsigned char err_offset = 0;
u8 opt_len = opt[1];
u8 opt_iter;
+ u8 tag_len;
if (opt_len < 8) {
err_offset = 1;
@@ -302,11 +303,12 @@
}
for (opt_iter = 6; opt_iter < opt_len;) {
- if (opt[opt_iter + 1] > (opt_len - opt_iter)) {
+ tag_len = opt[opt_iter + 1];
+ if ((tag_len == 0) || (opt[opt_iter + 1] > (opt_len - opt_iter))) {
err_offset = opt_iter + 1;
goto out;
}
- opt_iter += opt[opt_iter + 1];
+ opt_iter += tag_len;
}
out:
diff --git a/include/net/dst.h b/include/net/dst.h
index 1f8fd10..e0c97f5 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -477,10 +477,22 @@
{
return dst_orig;
}
+
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
+{
+ return NULL;
+}
+
#else
extern struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
const struct flowi *fl, struct sock *sk,
int flags);
+
+/* skb attached with this dst needs transformation if dst->xfrm is valid */
+static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
+{
+ return dst->xfrm;
+}
#endif
#endif /* _NET_DST_H */
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 93024a4..8e0b6c8 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -61,6 +61,7 @@
struct list_head ops_list; /* private */
struct list_head family_list; /* private */
struct list_head mcast_groups; /* private */
+ struct module *module;
};
/**
@@ -121,9 +122,24 @@
struct list_head ops_list;
};
-extern int genl_register_family(struct genl_family *family);
-extern int genl_register_family_with_ops(struct genl_family *family,
+extern int __genl_register_family(struct genl_family *family);
+
+static inline int genl_register_family(struct genl_family *family)
+{
+ family->module = THIS_MODULE;
+ return __genl_register_family(family);
+}
+
+extern int __genl_register_family_with_ops(struct genl_family *family,
struct genl_ops *ops, size_t n_ops);
+
+static inline int genl_register_family_with_ops(struct genl_family *family,
+ struct genl_ops *ops, size_t n_ops)
+{
+ family->module = THIS_MODULE;
+ return __genl_register_family_with_ops(family, ops, n_ops);
+}
+
extern int genl_unregister_family(struct genl_family *family);
extern int genl_register_ops(struct genl_family *, struct genl_ops *ops);
extern int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index de2c785..0a8f6f9 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -62,6 +62,7 @@
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
int (*bind_conflict)(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax);
+ void (*mtu_reduced)(struct sock *sk);
};
/** inet_connection_sock - INET connection oriented sock
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 53f464d..bb06fd2 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@
struct rcu_head gc_rcu;
};
/*
- * Once inet_peer is queued for deletion (refcnt == -1), following fields
- * are not available: rid, ip_id_count
+ * Once inet_peer is queued for deletion (refcnt == -1), following field
+ * is not available: rid
* We can share memory with rcu_head to help keep inet_peer small.
*/
union {
struct {
atomic_t rid; /* Frag reception counter */
- atomic_t ip_id_count; /* IP ID for the next packet */
};
struct rcu_head rcu;
struct inet_peer *gc_next;
@@ -166,7 +165,7 @@
extern void inetpeer_invalidate_family(int family);
/*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
* tcp_ts_stamp if no refcount is taken on inet_peer
*/
static inline void inet_peer_refcheck(const struct inet_peer *p)
@@ -174,20 +173,4 @@
WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
}
-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
- int old, new;
- more++;
- inet_peer_refcheck(p);
- do {
- old = atomic_read(&p->ip_id_count);
- new = old + more;
- if (!new)
- new = 1;
- } while (atomic_cmpxchg(&p->ip_id_count, old, new) != old);
- return new;
-}
-
#endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index a68f838..0a62365 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -37,11 +37,12 @@
struct ip_options opt; /* Compiled IP options */
unsigned char flags;
-#define IPSKB_FORWARDED 1
-#define IPSKB_XFRM_TUNNEL_SIZE 2
-#define IPSKB_XFRM_TRANSFORMED 4
-#define IPSKB_FRAG_COMPLETE 8
-#define IPSKB_REROUTED 16
+#define IPSKB_FORWARDED BIT(0)
+#define IPSKB_XFRM_TUNNEL_SIZE BIT(1)
+#define IPSKB_XFRM_TRANSFORMED BIT(2)
+#define IPSKB_FRAG_COMPLETE BIT(3)
+#define IPSKB_REROUTED BIT(4)
+#define IPSKB_DOREDIRECT BIT(5)
u16 frag_max_size;
};
@@ -162,7 +163,7 @@
return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
}
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
__be32 saddr, const struct ip_reply_arg *arg,
unsigned int len);
@@ -252,32 +253,33 @@
!(dst_metric_locked(dst, RTAX_MTU)));
}
-extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);
-static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
{
- if (iph->frag_off & htons(IP_DF)) {
+ struct iphdr *iph = ip_hdr(skb);
+
+ if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
/* This is only to work around buggy Windows95/2000
* VJ compression implementations. If the ID field
* does not change, they drop every other packet in
* a TCP stream using header compression.
*/
- iph->id = (sk && inet_sk(sk)->inet_daddr) ?
- htons(inet_sk(sk)->inet_id++) : 0;
- } else
- __ip_select_ident(iph, dst, 0);
-}
-
-static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more)
-{
- if (iph->frag_off & htons(IP_DF)) {
if (sk && inet_sk(sk)->inet_daddr) {
iph->id = htons(inet_sk(sk)->inet_id);
- inet_sk(sk)->inet_id += 1 + more;
- } else
+ inet_sk(sk)->inet_id += segs;
+ } else {
iph->id = 0;
- } else
- __ip_select_ident(iph, dst, more);
+ }
+ } else {
+ __ip_select_ident(iph, segs);
+ }
+}
+
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
+{
+ ip_select_ident_segs(skb, sk, 1);
}
/*
@@ -450,7 +452,7 @@
int optname, char __user *optval, int __user *optlen);
extern int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *));
-extern int ip_recv_error(struct sock *sk, struct msghdr *msg, int len);
+extern int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len);
extern void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload);
extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 2a601e7..665e0ce 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -165,6 +165,7 @@
static inline void rt6_clean_expires(struct rt6_info *rt)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
+ rt->dst.expires = 0;
}
static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 260f83f..8d977b3 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -32,6 +32,11 @@
#define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010
#define RT6_LOOKUP_F_SRCPREF_COA 0x00000020
+/* We do not (yet ?) support IPv6 jumbograms (RFC 2675)
+ * Unlike IPv4, hdr->seg_len doesn't include the IPv6 header
+ */
+#define IP6_MAX_MTU (0xFFFF + sizeof(struct ipv6hdr))
+
/*
* rt6_srcprefs2flags() and rt6_flags2srcprefs() translate
* between IPV6_ADDR_PREFERENCES socket option values
@@ -194,11 +199,9 @@
skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}
-static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, struct in6_addr *dest)
+static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
{
- if (rt->rt6i_flags & RTF_GATEWAY)
- return &rt->rt6i_gateway;
- return dest;
+ return &rt->rt6i_gateway;
}
#endif
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 09b1360..7ac7f91 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -113,7 +113,7 @@
__be32 key);
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
- const struct tnl_ptk_info *tpi, bool log_ecn_error);
+ const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p);
int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
@@ -141,20 +141,6 @@
return INET_ECN_encapsulate(tos, inner);
}
-static inline void tunnel_ip_select_ident(struct sk_buff *skb,
- const struct iphdr *old_iph,
- struct dst_entry *dst)
-{
- struct iphdr *iph = ip_hdr(skb);
-
- /* Use inner packet iph-id if possible. */
- if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
- iph->id = old_iph->id;
- else
- __ip_select_ident(iph, dst,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
-}
-
static inline void iptunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
int err;
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4c062cc..f0c13a3 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -109,7 +109,6 @@
struct ip_vs_iphdr {
__u32 len; /* IPv4 simply where L4 starts
IPv6 where L4 Transport Header starts */
- __u32 thoff_reasm; /* Transport Header Offset in nfct_reasm skb */
__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
__s16 protocol;
__s32 flags;
@@ -117,34 +116,12 @@
union nf_inet_addr daddr;
};
-/* Dependency to module: nf_defrag_ipv6 */
-#if defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE)
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
- return skb->nfct_reasm;
-}
-static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
- int len, void *buffer,
- const struct ip_vs_iphdr *ipvsh)
-{
- if (unlikely(ipvsh->fragoffs && skb_nfct_reasm(skb)))
- return skb_header_pointer(skb_nfct_reasm(skb),
- ipvsh->thoff_reasm, len, buffer);
-
- return skb_header_pointer(skb, offset, len, buffer);
-}
-#else
-static inline struct sk_buff *skb_nfct_reasm(const struct sk_buff *skb)
-{
- return NULL;
-}
static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
int len, void *buffer,
const struct ip_vs_iphdr *ipvsh)
{
return skb_header_pointer(skb, offset, len, buffer);
}
-#endif
static inline void
ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr)
@@ -171,19 +148,12 @@
(struct ipv6hdr *)skb_network_header(skb);
iphdr->saddr.in6 = iph->saddr;
iphdr->daddr.in6 = iph->daddr;
- /* ipv6_find_hdr() updates len, flags, thoff_reasm */
- iphdr->thoff_reasm = 0;
+ /* ipv6_find_hdr() updates len, flags */
iphdr->len = 0;
iphdr->flags = 0;
iphdr->protocol = ipv6_find_hdr(skb, &iphdr->len, -1,
&iphdr->fragoffs,
&iphdr->flags);
- /* get proto from re-assembled packet and it's offset */
- if (skb_nfct_reasm(skb))
- iphdr->protocol = ipv6_find_hdr(skb_nfct_reasm(skb),
- &iphdr->thoff_reasm,
- -1, NULL, NULL);
-
} else
#endif
{
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 0810aa5..087370f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -530,14 +530,19 @@
}
/* more secured version of ipv6_addr_hash() */
-static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval)
{
u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
return jhash_3words(v,
(__force u32)a->s6_addr32[2],
(__force u32)a->s6_addr32[3],
- ipv6_hash_secret);
+ initval);
+}
+
+static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+{
+ return __ipv6_addr_jhash(a, ipv6_hash_secret);
}
static inline bool ipv6_addr_loopback(const struct in6_addr *a)
@@ -649,8 +654,6 @@
return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
}
-extern void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
-
/*
* Header manipulation
*/
@@ -793,8 +796,10 @@
extern int ip6_datagram_connect(struct sock *sk,
struct sockaddr *addr, int addr_len);
-extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
-extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
+extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len);
+extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len);
extern void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
u32 info, u8 *payload);
extern void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 885898a..4e50d36 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1484,6 +1484,7 @@
IEEE80211_HW_SUPPORTS_RC_TABLE = 1<<24,
IEEE80211_HW_P2P_DEV_ADDR_FOR_INTF = 1<<25,
IEEE80211_HW_TIMING_BEACON_ONLY = 1<<26,
+ IEEE80211_HW_SUPPORTS_HT_CCK_RATES = 1<<27,
};
/**
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 745bf74..5043f8b 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -119,7 +119,7 @@
* if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may
* also need a pad of 2.
*/
-static int ndisc_addr_option_pad(unsigned short type)
+static inline int ndisc_addr_option_pad(unsigned short type)
{
switch (type) {
case ARPHRD_INFINIBAND: return 2;
diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
index fd79c9a..17920d8 100644
--- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -6,10 +6,7 @@
extern int nf_ct_frag6_init(void);
extern void nf_ct_frag6_cleanup(void);
extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user);
-extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
- struct net_device *in,
- struct net_device *out,
- int (*okfn)(struct sk_buff *));
+extern void nf_ct_frag6_consume_orig(struct sk_buff *skb);
struct inet_frags_ctl;
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 977bc8a..86dd7dd 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -41,8 +41,8 @@
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {
struct rcu_head rcu;
- u8 offset[NF_CT_EXT_NUM];
- u8 len;
+ u16 offset[NF_CT_EXT_NUM];
+ u16 len;
char data[0];
};
@@ -80,7 +80,7 @@
static inline void nf_ct_ext_free(struct nf_conn *ct)
{
if (ct->ext)
- kfree(ct->ext);
+ kfree_rcu(ct->ext, rcu);
}
/* Add this type, returns pointer to data or NULL. */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2ba9de8..03e6378 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -43,6 +43,7 @@
struct inet_peer_base *peers;
struct tcpm_hash_bucket *tcp_metrics_hash;
unsigned int tcp_metrics_hash_log;
+ struct sock * __percpu *tcp_sk;
struct netns_frags frags;
#ifdef CONFIG_NETFILTER
struct xt_table *iptable_filter;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e7f4e21..63ed1d1 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -682,13 +682,19 @@
u64 rate_bps;
u32 mult;
u16 overhead;
+ u8 linklayer;
u8 shift;
};
static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
unsigned int len)
{
- return ((u64)(len + r->overhead) * r->mult) >> r->shift;
+ len += r->overhead;
+
+ if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
+ return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
+
+ return ((u64)len * r->mult) >> r->shift;
}
extern void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf);
@@ -699,6 +705,7 @@
memset(res, 0, sizeof(*res));
res->rate = r->rate_bps >> 3;
res->overhead = r->overhead;
+ res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
}
#endif
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 3524727..5f39c1c 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -118,7 +118,7 @@
* analysis of the state functions, but in reality just taken from
* thin air in the hopes othat we don't trigger a kernel panic.
*/
-#define SCTP_MAX_NUM_COMMANDS 14
+#define SCTP_MAX_NUM_COMMANDS 20
typedef union {
__s32 i32;
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index cd89510..845ab6d 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -540,6 +540,11 @@
asoc->pmtu_pending = 0;
}
+static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk)
+{
+ return !list_empty(&chunk->list);
+}
+
/* Walk through a list of TLV parameters. Don't trust the
* individual parameter lengths and instead depend on
* the chunk length to indicate when to stop. Make sure
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2a82d13..c4c9458 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -255,9 +255,9 @@
int, __be16);
struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc,
union sctp_addr *addr);
-int sctp_verify_asconf(const struct sctp_association *asoc,
- struct sctp_paramhdr *param_hdr, void *chunk_end,
- struct sctp_paramhdr **errp);
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+ struct sctp_chunk *chunk, bool addr_param_needed,
+ struct sctp_paramhdr **errp);
struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
struct sctp_chunk *asconf);
int sctp_process_asconf_ack(struct sctp_association *asoc,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 1bd4c41..da6b9a0 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1252,6 +1252,7 @@
/* SCTP-AUTH: endpoint shared keys */
struct list_head endpoint_shared_keys;
__u16 active_key_id;
+ __u8 auth_enable;
};
/* Recover the outter endpoint structure. */
@@ -1280,7 +1281,8 @@
int sctp_has_association(struct net *net, const union sctp_addr *laddr,
const union sctp_addr *paddr);
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
sctp_cid_t, sctp_init_chunk_t *peer_init,
struct sctp_chunk *chunk, struct sctp_chunk **err_chunk);
int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk,
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index 6ca975b..b1c3d1c 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,9 +3,6 @@
#include <linux/types.h>
-extern void net_secret_init(void);
-extern __u32 secure_ip_id(__be32 daddr);
-extern __u32 secure_ipv6_id(const __be32 daddr[4]);
extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport);
diff --git a/include/net/sock.h b/include/net/sock.h
index 66772cf..c0aad07 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -230,6 +230,7 @@
* @sk_wmem_queued: persistent queue size
* @sk_forward_alloc: space allocated forward
* @sk_allocation: allocation mode
+ * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
* @sk_sndbuf: size of send buffer in bytes
* @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
* %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
@@ -355,6 +356,7 @@
kmemcheck_bitfield_end(flags);
int sk_wmem_queued;
gfp_t sk_allocation;
+ u32 sk_pacing_rate; /* bytes per second */
netdev_features_t sk_route_caps;
netdev_features_t sk_route_nocaps;
int sk_gso_type;
@@ -930,7 +932,6 @@
struct sk_buff *skb);
void (*release_cb)(struct sock *sk);
- void (*mtu_reduced)(struct sock *sk);
/* Keeping track of sk's, looking them up, and port selection methods. */
void (*hash)(struct sock *sk);
@@ -1435,6 +1436,11 @@
*/
#define sock_owned_by_user(sk) ((sk)->sk_lock.owned)
+static inline void sock_release_ownership(struct sock *sk)
+{
+ sk->sk_lock.owned = 0;
+}
+
/*
* Macro so as to not evaluate some arguments when
* lockdep is not enabled.
@@ -1720,8 +1726,8 @@
rcu_read_lock();
dst = rcu_dereference(sk->sk_dst_cache);
- if (dst)
- dst_hold(dst);
+ if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+ dst = NULL;
rcu_read_unlock();
return dst;
}
@@ -1760,9 +1766,11 @@
static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_set(sk, dst);
- spin_unlock(&sk->sk_dst_lock);
+ struct dst_entry *old_dst;
+
+ sk_tx_queue_clear(sk);
+ old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+ dst_release(old_dst);
}
static inline void
@@ -1774,9 +1782,7 @@
static inline void
sk_dst_reset(struct sock *sk)
{
- spin_lock(&sk->sk_dst_lock);
- __sk_dst_reset(sk);
- spin_unlock(&sk->sk_dst_lock);
+ sk_dst_set(sk, NULL);
}
extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
@@ -2241,6 +2247,11 @@
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
extern int sock_get_timestampns(struct sock *, struct timespec __user *);
+bool sk_ns_capable(const struct sock *sk,
+ struct user_namespace *user_ns, int cap);
+bool sk_capable(const struct sock *sk, int cap);
+bool sk_net_capable(const struct sock *sk, int cap);
+
/*
* Enable debug/info messages
*/
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5bba80f..29a1a63 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -287,6 +287,7 @@
extern int sysctl_tcp_early_retrans;
extern int sysctl_tcp_limit_output_bytes;
extern int sysctl_tcp_challenge_ack_limit;
+extern int sysctl_tcp_min_tso_segs;
extern atomic_long_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -459,6 +460,7 @@
*/
extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb);
+void tcp_v4_mtu_reduced(struct sock *sk);
extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
extern struct sock * tcp_create_openreq_child(struct sock *sk,
struct request_sock *req,
@@ -1307,7 +1309,8 @@
/* Fast Open cookie. Size 0 means a cookie request */
struct tcp_fastopen_cookie cookie;
struct msghdr *data; /* data in MSG_FASTOPEN */
- u16 copied; /* queued in tcp_connect() */
+ size_t size;
+ int copied; /* queued in tcp_connect() */
};
void tcp_free_fastopen_req(struct tcp_sock *tp);
diff --git a/include/net/udp.h b/include/net/udp.h
index 065f379..ad99eed 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -181,6 +181,7 @@
extern void udp_err(struct sk_buff *, u32);
extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len);
+extern int udp_push_pending_frames(struct sock *sk);
extern void udp_flush_pending_frames(struct sock *sk);
extern int udp_rcv(struct sk_buff *skb);
extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
diff --git a/include/scsi/osd_ore.h b/include/scsi/osd_ore.h
index a5f9b96..6ca3265 100644
--- a/include/scsi/osd_ore.h
+++ b/include/scsi/osd_ore.h
@@ -102,6 +102,7 @@
unsigned unit_off;
unsigned cur_pg;
unsigned cur_comp;
+ unsigned maxdevUnits;
};
struct ore_io_state;
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index cc64587..cc92ef3 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -248,7 +248,7 @@
struct list_head siblings;
struct list_head devices;
struct device dev;
- unsigned int reap_ref; /* protected by the host lock */
+ struct kref reap_ref; /* last put renders target invisible */
unsigned int channel;
unsigned int id; /* target id ... replace
* scsi_device.id eventually */
@@ -272,7 +272,6 @@
#define SCSI_DEFAULT_TARGET_BLOCKED 3
char scsi_level;
- struct execute_work ew;
enum scsi_target_state state;
void *hostdata; /* available to low-level driver */
unsigned long starget_data[0]; /* for the transport */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 7552435..50769a7 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -475,6 +475,9 @@
*/
unsigned ordered_tag:1;
+ /* True if the controller does not support WRITE SAME */
+ unsigned no_write_same:1;
+
/*
* Countdown for host blocking with no commands outstanding.
*/
@@ -674,6 +677,9 @@
/* Don't resume host in EH */
unsigned eh_noresume:1;
+ /* The controller does not support WRITE SAME */
+ unsigned no_write_same:1;
+
/*
* Optional work queue to be utilized by the transport
*/
diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 2609048..3a34f6e 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -286,7 +286,7 @@
ak4113_write_t *write;
ak4113_read_t *read;
void *private_data;
- unsigned int init:1;
+ atomic_t wq_processing;
spinlock_t lock;
unsigned char regmap[AK4113_WRITABLE_REGS];
struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 3ce69fd..6944116 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -168,7 +168,7 @@
ak4114_write_t * write;
ak4114_read_t * read;
void * private_data;
- unsigned int init: 1;
+ atomic_t wq_processing;
spinlock_t lock;
unsigned char regmap[7];
unsigned char txcsb[5];
diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 9031a26..ae6c3b8 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -171,4 +171,13 @@
wake_up(&stream->runtime->sleep);
}
+static inline void snd_compr_drain_notify(struct snd_compr_stream *stream)
+{
+ if (snd_BUG_ON(!stream))
+ return;
+
+ stream->runtime->state = SNDRV_PCM_STATE_SETUP;
+ wake_up(&stream->runtime->sleep);
+}
+
#endif
diff --git a/include/sound/core.h b/include/sound/core.h
index 5bfe513..97cd9c3 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -120,6 +120,8 @@
int user_ctl_count; /* count of all user controls */
struct list_head controls; /* all controls for this card */
struct list_head ctl_files; /* active control files */
+ struct mutex user_ctl_lock; /* protects user controls against
+ concurrent access */
struct snd_info_entry *proc_root; /* root for soundcard specific files */
struct snd_info_entry *proc_id; /* the card id */
diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index cf15b821..54aff2d 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -103,7 +103,7 @@
{
struct snd_sg_buf *sgbuf = dmab->private_data;
dma_addr_t addr = sgbuf->table[offset >> PAGE_SHIFT].addr;
- addr &= PAGE_MASK;
+ addr &= ~((dma_addr_t)PAGE_SIZE - 1);
return addr + offset % PAGE_SIZE;
}
diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index 04598f1..a2e15ca 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -11,6 +11,7 @@
#ifndef __LINUX_SND_SOC_DPCM_H
#define __LINUX_SND_SOC_DPCM_H
+#include <linux/slab.h>
#include <linux/list.h>
#include <sound/pcm.h>
@@ -135,4 +136,25 @@
int soc_dpcm_debugfs_add(struct snd_soc_pcm_runtime *rtd);
int soc_dpcm_runtime_update(struct snd_soc_dapm_widget *);
+int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
+ int stream, struct snd_soc_dapm_widget_list **list_);
+int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
+ int stream, struct snd_soc_dapm_widget_list **list, int new);
+int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream);
+void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream);
+void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int tream);
+int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream, int cmd);
+int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream);
+int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
+ int event);
+
+static inline void dpcm_path_put(struct snd_soc_dapm_widget_list **list)
+{
+ kfree(*list);
+}
+
+
#endif
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 85c1522..5bbdc65 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1063,6 +1063,7 @@
/* Dynamic PCM BE runtime data */
struct snd_soc_dpcm_runtime dpcm[2];
+ int fe_compr;
long pmdown_time;
unsigned char pop_wait:1;
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 23a87d0..4a5f00e 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -11,6 +11,7 @@
int (*iscsit_setup_np)(struct iscsi_np *, struct __kernel_sockaddr_storage *);
int (*iscsit_accept_np)(struct iscsi_np *, struct iscsi_conn *);
void (*iscsit_free_np)(struct iscsi_np *);
+ void (*iscsit_wait_conn)(struct iscsi_conn *);
void (*iscsit_free_conn)(struct iscsi_conn *);
struct iscsi_cmd *(*iscsit_alloc_cmd)(struct iscsi_conn *, gfp_t);
int (*iscsit_get_login_rx)(struct iscsi_conn *, struct iscsi_login *);
@@ -34,8 +35,6 @@
/*
* From iscsi_target.c
*/
-extern int iscsit_add_reject_from_cmd(u8, int, int, unsigned char *,
- struct iscsi_cmd *);
extern int iscsit_setup_scsi_cmd(struct iscsi_conn *, struct iscsi_cmd *,
unsigned char *);
extern void iscsit_set_unsoliticed_dataout(struct iscsi_cmd *);
@@ -67,6 +66,10 @@
*/
extern void iscsit_increment_maxcmdsn(struct iscsi_cmd *, struct iscsi_session *);
/*
+ * From iscsi_target_erl0.c
+ */
+extern void iscsit_cause_connection_reinstatement(struct iscsi_conn *, int);
+/*
* From iscsi_target_erl1.c
*/
extern void iscsit_stop_dataout_timer(struct iscsi_cmd *);
@@ -80,4 +83,5 @@
* From iscsi_target_util.c
*/
extern struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *, gfp_t);
-extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *, __be32);
+extern int iscsit_sequence_cmd(struct iscsi_conn *, struct iscsi_cmd *,
+ unsigned char *, __be32);
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index ffa2696..a63529a 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -50,6 +50,7 @@
void transport_subsystem_release(struct se_subsystem_api *);
void target_complete_cmd(struct se_cmd *, u8);
+void target_complete_cmd_with_length(struct se_cmd *, u8, int);
sense_reason_t spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
sense_reason_t spc_emulate_report_luns(struct se_cmd *cmd);
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 4ea4f98..7d99c0b 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -614,6 +614,7 @@
u32 unmap_granularity;
u32 unmap_granularity_alignment;
u32 max_write_same_len;
+ u32 max_bytes_per_io;
struct se_device *da_dev;
struct config_group da_group;
};
diff --git a/include/trace/events/arm-ipi.h b/include/trace/events/arm-ipi.h
new file mode 100644
index 0000000..5d3bd21
--- /dev/null
+++ b/include/trace/events/arm-ipi.h
@@ -0,0 +1,100 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM arm-ipi
+
+#if !defined(_TRACE_ARM_IPI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_ARM_IPI_H
+
+#include <linux/tracepoint.h>
+
+#define show_arm_ipi_name(val) \
+ __print_symbolic(val, \
+ { 0, "IPI_WAKEUP" }, \
+ { 1, "IPI_TIMER" }, \
+ { 2, "IPI_RESCHEDULE" }, \
+ { 3, "IPI_CALL_FUNC" }, \
+ { 4, "IPI_CALL_FUNC_SINGLE" }, \
+ { 5, "IPI_CPU_STOP" }, \
+ { 6, "IPI_COMPLETION" }, \
+ { 7, "IPI_CPU_BACKTRACE" })
+
+DECLARE_EVENT_CLASS(arm_ipi,
+
+ TP_PROTO(unsigned int ipi_nr),
+
+ TP_ARGS(ipi_nr),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ipi )
+ ),
+
+ TP_fast_assign(
+ __entry->ipi = ipi_nr;
+ ),
+
+ TP_printk("ipi=%u [action=%s]", __entry->ipi,
+ show_arm_ipi_name(__entry->ipi))
+);
+
+/**
+ * arm_ipi_entry - called in the arm-generic ipi handler immediately before
+ * entering ipi-type handler
+ * @ipi_nr: ipi number
+ *
+ * When used in combination with the arm_ipi_exit tracepoint
+ * we can determine the ipi handler runtine.
+ */
+DEFINE_EVENT(arm_ipi, arm_ipi_entry,
+
+ TP_PROTO(unsigned int ipi_nr),
+
+ TP_ARGS(ipi_nr)
+);
+
+/**
+ * arm_ipi_exit - called in the arm-generic ipi handler immediately
+ * after the ipi-type handler returns
+ * @ipi_nr: ipi number
+ *
+ * When used in combination with the arm_ipi_entry tracepoint
+ * we can determine the ipi handler runtine.
+ */
+DEFINE_EVENT(arm_ipi, arm_ipi_exit,
+
+ TP_PROTO(unsigned int ipi_nr),
+
+ TP_ARGS(ipi_nr)
+);
+
+/**
+ * arm_ipi_send - called as the ipi target mask is built, immediately
+ * before the register is written
+ * @ipi_nr: ipi number
+ * @dest: cpu to send to
+ *
+ * When used in combination with the arm_ipi_entry tracepoint
+ * we can determine the ipi raise to run latency.
+ */
+TRACE_EVENT(arm_ipi_send,
+
+ TP_PROTO(unsigned int ipi_nr, int dest),
+
+ TP_ARGS(ipi_nr, dest),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, ipi )
+ __field( int , dest )
+ ),
+
+ TP_fast_assign(
+ __entry->ipi = ipi_nr;
+ __entry->dest = dest;
+ ),
+
+ TP_printk("dest=%d ipi=%u [action=%s]", __entry->dest,
+ __entry->ipi, show_arm_ipi_name(__entry->ipi))
+);
+
+#endif /* _TRACE_ARM_IPI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 60ae7c3..2e96e2b 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -132,6 +132,7 @@
* block_rq_complete - block IO operation completed by device driver
* @q: queue containing the block operation request
* @rq: block operations request
+ * @nr_bytes: number of completed bytes
*
* The block_rq_complete tracepoint event indicates that some portion
* of operation request has been completed by the device driver. If
@@ -139,11 +140,37 @@
* do for the request. If @rq->bio is non-NULL then there is
* additional work required to complete the request.
*/
-DEFINE_EVENT(block_rq_with_error, block_rq_complete,
+TRACE_EVENT(block_rq_complete,
- TP_PROTO(struct request_queue *q, struct request *rq),
+ TP_PROTO(struct request_queue *q, struct request *rq,
+ unsigned int nr_bytes),
- TP_ARGS(q, rq)
+ TP_ARGS(q, rq, nr_bytes),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( sector_t, sector )
+ __field( unsigned int, nr_sector )
+ __field( int, errors )
+ __array( char, rwbs, RWBS_LEN )
+ __dynamic_array( char, cmd, blk_cmd_buf_len(rq) )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+ __entry->sector = blk_rq_pos(rq);
+ __entry->nr_sector = nr_bytes >> 9;
+ __entry->errors = rq->errors;
+
+ blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
+ blk_dump_cmd(__get_str(cmd), rq);
+ ),
+
+ TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->rwbs, __get_str(cmd),
+ (unsigned long long)__entry->sector,
+ __entry->nr_sector, __entry->errors)
);
DECLARE_EVENT_CLASS(block_rq,
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 7005d11..908925a 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -37,7 +37,7 @@
__entry->errno < 0 ? -__entry->errno : __entry->reason)
);
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
TRACE_EVENT(kvm_set_irq,
TP_PROTO(unsigned int gsi, int level, int irq_source_id),
TP_ARGS(gsi, level, irq_source_id),
@@ -57,7 +57,7 @@
TP_printk("gsi %u level %d source %d",
__entry->gsi, __entry->level, __entry->irq_source_id)
);
-#endif
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
#if defined(__KVM_HAVE_IOAPIC)
#define kvm_deliver_mode \
@@ -124,7 +124,7 @@
#endif /* defined(__KVM_HAVE_IOAPIC) */
-#if defined(CONFIG_HAVE_KVM_IRQCHIP)
+#if defined(CONFIG_HAVE_KVM_IRQFD)
TRACE_EVENT(kvm_ack_irq,
TP_PROTO(unsigned int irqchip, unsigned int pin),
@@ -149,7 +149,7 @@
#endif
);
-#endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
+#endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
@@ -296,23 +296,21 @@
TRACE_EVENT(
kvm_async_pf_completed,
- TP_PROTO(unsigned long address, struct page *page, u64 gva),
- TP_ARGS(address, page, gva),
+ TP_PROTO(unsigned long address, u64 gva),
+ TP_ARGS(address, gva),
TP_STRUCT__entry(
__field(unsigned long, address)
- __field(pfn_t, pfn)
__field(u64, gva)
),
TP_fast_assign(
__entry->address = address;
- __entry->pfn = page ? page_to_pfn(page) : 0;
__entry->gva = gva;
),
- TP_printk("gva %#llx address %#lx pfn %#llx", __entry->gva,
- __entry->address, __entry->pfn)
+ TP_printk("gva %#llx address %#lx", __entry->gva,
+ __entry->address)
);
#endif
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 1619327..ca298c7 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -78,7 +78,7 @@
TP_fast_assign(
__entry->ip = ip;
- __entry->refcnt = __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
+ __entry->refcnt = __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs);
__assign_str(name, mod->name);
),
diff --git a/include/trace/events/power_cpu_migrate.h b/include/trace/events/power_cpu_migrate.h
new file mode 100644
index 0000000..f76dd4d
--- /dev/null
+++ b/include/trace/events/power_cpu_migrate.h
@@ -0,0 +1,67 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_CPU_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_CPU_MIGRATE_H
+
+#include <linux/tracepoint.h>
+
+#define __cpu_migrate_proto \
+ TP_PROTO(u64 timestamp, \
+ u32 cpu_hwid)
+#define __cpu_migrate_args \
+ TP_ARGS(timestamp, \
+ cpu_hwid)
+
+DECLARE_EVENT_CLASS(cpu_migrate,
+
+ __cpu_migrate_proto,
+ __cpu_migrate_args,
+
+ TP_STRUCT__entry(
+ __field(u64, timestamp )
+ __field(u32, cpu_hwid )
+ ),
+
+ TP_fast_assign(
+ __entry->timestamp = timestamp;
+ __entry->cpu_hwid = cpu_hwid;
+ ),
+
+ TP_printk("timestamp=%llu cpu_hwid=0x%08lX",
+ (unsigned long long)__entry->timestamp,
+ (unsigned long)__entry->cpu_hwid
+ )
+);
+
+#define __define_cpu_migrate_event(name) \
+ DEFINE_EVENT(cpu_migrate, cpu_migrate_##name, \
+ __cpu_migrate_proto, \
+ __cpu_migrate_args \
+ )
+
+__define_cpu_migrate_event(begin);
+__define_cpu_migrate_event(finish);
+__define_cpu_migrate_event(current);
+
+#undef __define_cpu_migrate
+#undef __cpu_migrate_proto
+#undef __cpu_migrate_args
+
+/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
+#ifndef _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+#define _PWR_CPU_MIGRATE_EVENT_AVOID_DOUBLE_DEFINING
+
+/*
+ * Set from_phys_cpu and to_phys_cpu to CPU_MIGRATE_ALL_CPUS to indicate
+ * a whole-cluster migration:
+ */
+#define CPU_MIGRATE_ALL_CPUS 0x80000000U
+#endif
+
+#endif /* _TRACE_POWER_CPU_MIGRATE_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE power_cpu_migrate
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index e5586ca..2afcb71 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -430,6 +430,280 @@
__entry->oldprio, __entry->newprio)
);
+/*
+ * Tracepoint for showing tracked load contribution.
+ */
+TRACE_EVENT(sched_task_load_contrib,
+
+ TP_PROTO(struct task_struct *tsk, unsigned long load_contrib),
+
+ TP_ARGS(tsk, load_contrib),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(unsigned long, load_contrib)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->load_contrib = load_contrib;
+ ),
+
+ TP_printk("comm=%s pid=%d load_contrib=%lu",
+ __entry->comm, __entry->pid,
+ __entry->load_contrib)
+);
+
+/*
+ * Tracepoint for showing tracked task runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_runnable_ratio,
+
+ TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+ TP_ARGS(tsk, ratio),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(unsigned long, ratio)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->ratio = ratio;
+ ),
+
+ TP_printk("comm=%s pid=%d ratio=%lu",
+ __entry->comm, __entry->pid,
+ __entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable ratio [0..1023].
+ */
+TRACE_EVENT(sched_rq_runnable_ratio,
+
+ TP_PROTO(int cpu, unsigned long ratio),
+
+ TP_ARGS(cpu, ratio),
+
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(unsigned long, ratio)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->ratio = ratio;
+ ),
+
+ TP_printk("cpu=%d ratio=%lu",
+ __entry->cpu,
+ __entry->ratio)
+);
+
+/*
+ * Tracepoint for showing tracked rq runnable load.
+ */
+TRACE_EVENT(sched_rq_runnable_load,
+
+ TP_PROTO(int cpu, u64 load),
+
+ TP_ARGS(cpu, load),
+
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(u64, load)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->load = load;
+ ),
+
+ TP_printk("cpu=%d load=%llu",
+ __entry->cpu,
+ __entry->load)
+);
+
+TRACE_EVENT(sched_rq_nr_running,
+
+ TP_PROTO(int cpu, unsigned int nr_running, int nr_iowait),
+
+ TP_ARGS(cpu, nr_running, nr_iowait),
+
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(unsigned int, nr_running)
+ __field(int, nr_iowait)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->nr_running = nr_running;
+ __entry->nr_iowait = nr_iowait;
+ ),
+
+ TP_printk("cpu=%d nr_running=%u nr_iowait=%d",
+ __entry->cpu,
+ __entry->nr_running, __entry->nr_iowait)
+);
+
+/*
+ * Tracepoint for showing tracked task cpu usage ratio [0..1023].
+ */
+TRACE_EVENT(sched_task_usage_ratio,
+
+ TP_PROTO(struct task_struct *tsk, unsigned long ratio),
+
+ TP_ARGS(tsk, ratio),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(unsigned long, ratio)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->ratio = ratio;
+ ),
+
+ TP_printk("comm=%s pid=%d ratio=%lu",
+ __entry->comm, __entry->pid,
+ __entry->ratio)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running tasks.
+ */
+TRACE_EVENT(sched_hmp_migrate_force_running,
+
+ TP_PROTO(struct task_struct *tsk, int running),
+
+ TP_ARGS(tsk, running),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(int, running)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->running = running;
+ ),
+
+ TP_printk("running=%d comm=%s",
+ __entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations,
+ * marking the forced transition of runnable or running
+ * tasks when a task is about to go idle.
+ */
+TRACE_EVENT(sched_hmp_migrate_idle_running,
+
+ TP_PROTO(struct task_struct *tsk, int running),
+
+ TP_ARGS(tsk, running),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(int, running)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->running = running;
+ ),
+
+ TP_printk("running=%d comm=%s",
+ __entry->running, __entry->comm)
+);
+
+/*
+ * Tracepoint for HMP (CONFIG_SCHED_HMP) task migrations.
+ */
+#define HMP_MIGRATE_WAKEUP 0
+#define HMP_MIGRATE_FORCE 1
+#define HMP_MIGRATE_OFFLOAD 2
+#define HMP_MIGRATE_IDLE_PULL 3
+TRACE_EVENT(sched_hmp_migrate,
+
+ TP_PROTO(struct task_struct *tsk, int dest, int force),
+
+ TP_ARGS(tsk, dest, force),
+
+ TP_STRUCT__entry(
+ __array(char, comm, TASK_COMM_LEN)
+ __field(pid_t, pid)
+ __field(int, dest)
+ __field(int, force)
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->dest = dest;
+ __entry->force = force;
+ ),
+
+ TP_printk("comm=%s pid=%d dest=%d force=%d",
+ __entry->comm, __entry->pid,
+ __entry->dest, __entry->force)
+);
+
+TRACE_EVENT(sched_hmp_offload_abort,
+
+ TP_PROTO(int cpu, int data, char *label),
+
+ TP_ARGS(cpu,data,label),
+
+ TP_STRUCT__entry(
+ __array(char, label, 64)
+ __field(int, cpu)
+ __field(int, data)
+ ),
+
+ TP_fast_assign(
+ strncpy(__entry->label, label, 64);
+ __entry->cpu = cpu;
+ __entry->data = data;
+ ),
+
+ TP_printk("cpu=%d data=%d label=%63s",
+ __entry->cpu, __entry->data,
+ __entry->label)
+);
+
+TRACE_EVENT(sched_hmp_offload_succeed,
+
+ TP_PROTO(int cpu, int dest_cpu),
+
+ TP_ARGS(cpu,dest_cpu),
+
+ TP_STRUCT__entry(
+ __field(int, cpu)
+ __field(int, dest_cpu)
+ ),
+
+ TP_fast_assign(
+ __entry->cpu = cpu;
+ __entry->dest_cpu = dest_cpu;
+ ),
+
+ TP_printk("cpu=%d dest=%d",
+ __entry->cpu,
+ __entry->dest_cpu)
+);
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/include/trace/events/smp.h b/include/trace/events/smp.h
new file mode 100644
index 0000000..da0baf2
--- /dev/null
+++ b/include/trace/events/smp.h
@@ -0,0 +1,90 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM smp
+
+#if !defined(_TRACE_SMP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SMP_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(smp_call_class,
+
+ TP_PROTO(void * fnc),
+
+ TP_ARGS(fnc),
+
+ TP_STRUCT__entry(
+ __field( void *, func )
+ ),
+
+ TP_fast_assign(
+ __entry->func = fnc;
+ ),
+
+ TP_printk("func=%pf", __entry->func)
+);
+
+/**
+ * smp_call_func_entry - called in the generic smp-cross-call-handler
+ * immediately before calling the destination
+ * function
+ * @func: function pointer
+ *
+ * When used in combination with the smp_call_func_exit tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_entry,
+
+ TP_PROTO(void * fnc),
+
+ TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_exit - called in the generic smp-cross-call-handler
+ * immediately after the destination function
+ * returns
+ * @func: function pointer
+ *
+ * When used in combination with the smp_call_entry tracepoint
+ * we can determine the cross-call runtime.
+ */
+DEFINE_EVENT(smp_call_class, smp_call_func_exit,
+
+ TP_PROTO(void * fnc),
+
+ TP_ARGS(fnc)
+);
+
+/**
+ * smp_call_func_send - called as destination function is set
+ * in the per-cpu storage
+ * @func: function pointer
+ * @dest: cpu to send to
+ *
+ * When used in combination with the smp_cross_call_entry tracepoint
+ * we can determine the call-to-run latency.
+ */
+TRACE_EVENT(smp_call_func_send,
+
+ TP_PROTO(void * func, int dest),
+
+ TP_ARGS(func, dest),
+
+ TP_STRUCT__entry(
+ __field( void * , func )
+ __field( int , dest )
+ ),
+
+ TP_fast_assign(
+ __entry->func = func;
+ __entry->dest = dest;
+ ),
+
+ TP_printk("dest=%d func=%pf", __entry->dest,
+ __entry->func)
+);
+
+#endif /* _TRACE_SMP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 19edd7f..dbb4741 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -299,15 +299,12 @@
#undef __array
#define __array(type, item, len) \
do { \
- mutex_lock(&event_storage_mutex); \
+ char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- snprintf(event_storage, sizeof(event_storage), \
- "%s[%d]", #type, len); \
- ret = trace_define_field(event_call, event_storage, #item, \
+ ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
- mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
} while (0);
@@ -368,7 +365,8 @@
__data_size += (len) * sizeof(type);
#undef __string
-#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)
+#define __string(item, src) __dynamic_array(char, item, \
+ strlen((src) ? (const char *)(src) : "(null)") + 1)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
@@ -498,7 +496,7 @@
#undef __assign_str
#define __assign_str(dst, src) \
- strcpy(__get_str(dst), src);
+ strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
#undef TP_fast_assign
#define TP_fast_assign(args...) args
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 84bc419..0a5b495 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -4,6 +4,7 @@
#include <linux/tracepoint.h>
#include <linux/unistd.h>
#include <linux/ftrace_event.h>
+#include <linux/thread_info.h>
#include <asm/ptrace.h>
@@ -31,4 +32,18 @@
struct ftrace_event_call *exit_event;
};
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+ if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+ set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+ else
+ clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
#endif /* _TRACE_SYSCALL_H */
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 090e533..cc2e00e 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -223,6 +223,8 @@
__u32 connection;
__u32 mm_width, mm_height; /**< HxW in millimeters */
__u32 subpixel;
+
+ __u32 pad;
};
#define DRM_MODE_PROP_PENDING (1<<0)
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 321d4ac..fa8b3ad 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -979,6 +979,8 @@
#define RADEON_INFO_RING_WORKING 0x15
/* SI tile mode array */
#define RADEON_INFO_SI_TILE_MODE_ARRAY 0x16
+/* query if CP DMA is supported on the compute ring */
+#define RADEON_INFO_SI_CP_DMA_COMPUTE 0x17
struct drm_radeon_info {
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 6e132a2..86b1f99 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -103,7 +103,6 @@
__u32 num_waitchks;
__u32 waitchk_mask;
__u32 timeout;
- __u32 pad;
__u64 syncpts;
__u64 cmdbufs;
__u64 relocs;
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index bdc6e87..405887b 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -311,6 +311,7 @@
header-y += ppp_defs.h
header-y += pps.h
header-y += prctl.h
+header-y += psci.h
header-y += ptp_clock.h
header-y += ptrace.h
header-y += qnx4_fs.h
diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h
index 8e2b7ba..59c17a2 100644
--- a/include/uapi/linux/elf-em.h
+++ b/include/uapi/linux/elf-em.h
@@ -22,6 +22,7 @@
#define EM_PPC 20 /* PowerPC */
#define EM_PPC64 21 /* PowerPC64 */
#define EM_SPU 23 /* Cell BE SPU */
+#define EM_ARM 40 /* ARM 32 bit */
#define EM_SH 42 /* SuperH */
#define EM_SPARCV9 43 /* SPARC v9 64-bit */
#define EM_IA_64 50 /* HP/Intel IA-64 */
@@ -34,6 +35,7 @@
#define EM_MN10300 89 /* Panasonic/MEI MN10300, AM33 */
#define EM_BLACKFIN 106 /* ADI Blackfin Processor */
#define EM_TI_C6000 140 /* TI C6X DSPs */
+#define EM_AARCH64 183 /* ARM 64 bit */
#define EM_FRV 0x5441 /* Fujitsu FR-V */
#define EM_AVR32 0x18ad /* Atmel AVR32 */
diff --git a/include/uapi/linux/firewire-cdev.h b/include/uapi/linux/firewire-cdev.h
index d500369..1db453e 100644
--- a/include/uapi/linux/firewire-cdev.h
+++ b/include/uapi/linux/firewire-cdev.h
@@ -215,8 +215,8 @@
* with the %FW_CDEV_ISO_INTERRUPT bit set, when explicitly requested with
* %FW_CDEV_IOC_FLUSH_ISO, or when there have been so many completed packets
* without the interrupt bit set that the kernel's internal buffer for @header
- * is about to overflow. (In the last case, kernels with ABI version < 5 drop
- * header data up to the next interrupt packet.)
+ * is about to overflow. (In the last case, ABI versions < 5 drop header data
+ * up to the next interrupt packet.)
*
* Isochronous transmit events (context type %FW_CDEV_ISO_CONTEXT_TRANSMIT):
*
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index e0133c7..590beda 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -115,6 +115,8 @@
#define ICMPV6_NOT_NEIGHBOUR 2
#define ICMPV6_ADDR_UNREACH 3
#define ICMPV6_PORT_UNREACH 4
+#define ICMPV6_POLICY_FAIL 5
+#define ICMPV6_REJECT_ROUTE 6
/*
* Codes for Time Exceeded
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index 0b46fd5..e36a4ae 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -135,11 +135,11 @@
struct pppoe_hdr {
#if defined(__LITTLE_ENDIAN_BITFIELD)
- __u8 ver : 4;
__u8 type : 4;
+ __u8 ver : 4;
#elif defined(__BIG_ENDIAN_BITFIELD)
- __u8 type : 4;
__u8 ver : 4;
+ __u8 type : 4;
#else
#error "Please fix <asm/byteorder.h>"
#endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d88c8ee..00d2c69 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -171,6 +171,7 @@
#define KVM_EXIT_WATCHDOG 21
#define KVM_EXIT_S390_TSCH 22
#define KVM_EXIT_EPR 23
+#define KVM_EXIT_SYSTEM_EVENT 24
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -301,6 +302,13 @@
struct {
__u32 epr;
} epr;
+ /* KVM_EXIT_SYSTEM_EVENT */
+ struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN 1
+#define KVM_SYSTEM_EVENT_RESET 2
+ __u32 type;
+ __u64 flags;
+ } system_event;
/* Fix the size of the union. */
char padding[256];
};
@@ -391,8 +399,9 @@
__u64 vapic_addr;
};
-/* for KVM_SET_MPSTATE */
+/* for KVM_SET_MP_STATE */
+/* not all states are valid on all architectures */
#define KVM_MP_STATE_RUNNABLE 0
#define KVM_MP_STATE_UNINITIALIZED 1
#define KVM_MP_STATE_INIT_RECEIVED 2
@@ -541,6 +550,7 @@
#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06
#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07
#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
/*
* Extension capability list.
@@ -568,9 +578,7 @@
#endif
/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
-#ifdef __KVM_HAVE_USER_NMI
#define KVM_CAP_USER_NMI 22
-#endif
#ifdef __KVM_HAVE_GUEST_DEBUG
#define KVM_CAP_SET_GUEST_DEBUG 23
#endif
@@ -652,9 +660,7 @@
#define KVM_CAP_PPC_GET_SMMU_INFO 78
#define KVM_CAP_S390_COW 79
#define KVM_CAP_PPC_ALLOC_HTAB 80
-#ifdef __KVM_HAVE_READONLY_MEM
#define KVM_CAP_READONLY_MEM 81
-#endif
#define KVM_CAP_IRQFD_RESAMPLE 82
#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
#define KVM_CAP_PPC_HTAB_FD 84
@@ -666,6 +672,10 @@
#define KVM_CAP_IRQ_MPIC 90
#define KVM_CAP_PPC_RTAS 91
#define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_ARM_EL1_32BIT 93
+#define KVM_CAP_EXT_EMUL_CPUID 95
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_CHECK_EXTENSION_VM 105
#ifdef KVM_CAP_IRQ_ROUTING
@@ -783,6 +793,7 @@
#define KVM_REG_IA64 0x3000000000000000ULL
#define KVM_REG_ARM 0x4000000000000000ULL
#define KVM_REG_S390 0x5000000000000000ULL
+#define KVM_REG_ARM64 0x6000000000000000ULL
#define KVM_REG_MIPS 0x7000000000000000ULL
#define KVM_REG_SIZE_SHIFT 52
@@ -837,9 +848,25 @@
__u64 addr; /* userspace address of attr data */
};
-#define KVM_DEV_TYPE_FSL_MPIC_20 1
-#define KVM_DEV_TYPE_FSL_MPIC_42 2
-#define KVM_DEV_TYPE_XICS 3
+#define KVM_DEV_VFIO_GROUP 1
+#define KVM_DEV_VFIO_GROUP_ADD 1
+#define KVM_DEV_VFIO_GROUP_DEL 2
+
+enum kvm_device_type {
+ KVM_DEV_TYPE_FSL_MPIC_20 = 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20 KVM_DEV_TYPE_FSL_MPIC_20
+ KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42 KVM_DEV_TYPE_FSL_MPIC_42
+ KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS KVM_DEV_TYPE_XICS
+ KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO KVM_DEV_TYPE_VFIO
+ KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2
+ KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC
+ KVM_DEV_TYPE_MAX,
+};
/*
* ioctls for VM fds
@@ -977,7 +1004,7 @@
#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97)
#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state)
#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state)
-/* Available with KVM_CAP_NMI */
+/* Available with KVM_CAP_USER_NMI */
#define KVM_NMI _IO(KVMIO, 0x9a)
/* Available with KVM_CAP_SET_GUEST_DEBUG */
#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug)
@@ -1009,6 +1036,7 @@
/* VM is being stopped by host */
#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad)
#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init)
#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index 5dda450..2ec9fbc 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -6,6 +6,8 @@
#define XT_BPF_MAX_NUM_INSTR 64
+struct sk_filter;
+
struct xt_bpf_info {
__u16 bpf_program_num_elem;
struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR];
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index fb104e5..9e59950 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -425,13 +425,15 @@
/*
* Control data for the mmap() data buffer.
*
- * User-space reading the @data_head value should issue an rmb(), on
- * SMP capable platforms, after reading this value -- see
- * perf_event_wakeup().
+ * User-space reading the @data_head value should issue an smp_rmb(),
+ * after reading this value.
*
* When the mapping is PROT_WRITE the @data_tail value should be
- * written by userspace to reflect the last read data. In this case
- * the kernel will not over-write unread data.
+ * written by userspace to reflect the last read data, after issueing
+ * an smp_mb() to separate the data read from the ->data_tail store.
+ * In this case the kernel will not over-write unread data.
+ *
+ * See perf_output_put_handle() for the data ordering.
*/
__u64 data_head; /* head in the data section */
__u64 data_tail; /* user-space written tail */
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index dbd71b0..09d62b92 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -73,9 +73,17 @@
#define TC_H_ROOT (0xFFFFFFFFU)
#define TC_H_INGRESS (0xFFFFFFF1U)
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+ TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+ TC_LINKLAYER_ETHERNET,
+ TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
struct tc_ratespec {
unsigned char cell_log;
- unsigned char __reserved;
+ __u8 linklayer; /* lower 4 bits */
unsigned short overhead;
short cell_align;
unsigned short mpu;
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
new file mode 100644
index 0000000..310d83e
--- /dev/null
+++ b/include/uapi/linux/psci.h
@@ -0,0 +1,90 @@
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <anup.patel@linaro.org>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE 0x84000000
+#define PSCI_0_2_FN(n) (PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT 0x40000000
+#define PSCI_0_2_FN64_BASE \
+ (PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n) (PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT 0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT 16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK \
+ (0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT 24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK \
+ (0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON 0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF 1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING 2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE 0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE 1
+#define PSCI_0_2_TOS_MP 2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT 16
+#define PSCI_VERSION_MINOR_MASK \
+ ((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK ~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver) \
+ (((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver) \
+ ((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS 0
+#define PSCI_RET_NOT_SUPPORTED -1
+#define PSCI_RET_INVALID_PARAMS -2
+#define PSCI_RET_DENIED -3
+#define PSCI_RET_ALREADY_ON -4
+#define PSCI_RET_ON_PENDING -5
+#define PSCI_RET_INTERNAL_FAILURE -6
+#define PSCI_RET_NOT_PRESENT -7
+#define PSCI_RET_DISABLED -8
+
+#endif /* _UAPI_LINUX_PSCI_H */
diff --git a/include/uapi/linux/usb/Kbuild b/include/uapi/linux/usb/Kbuild
index 6cb4ea8..4cc4d6e 100644
--- a/include/uapi/linux/usb/Kbuild
+++ b/include/uapi/linux/usb/Kbuild
@@ -1,6 +1,7 @@
# UAPI Header export list
header-y += audio.h
header-y += cdc.h
+header-y += cdc-wdm.h
header-y += ch11.h
header-y += ch9.h
header-y += functionfs.h
diff --git a/include/uapi/linux/usb/cdc-wdm.h b/include/uapi/linux/usb/cdc-wdm.h
index f03134f..0dc132e 100644
--- a/include/uapi/linux/usb/cdc-wdm.h
+++ b/include/uapi/linux/usb/cdc-wdm.h
@@ -9,6 +9,8 @@
#ifndef _UAPI__LINUX_USB_CDC_WDM_H
#define _UAPI__LINUX_USB_CDC_WDM_H
+#include <linux/types.h>
+
/*
* This IOCTL is used to retrieve the wMaxCommand for the device,
* defining the message limit for both reading and writing.
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index d630163..21eed48 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -30,7 +30,7 @@
#include <sound/compress_params.h>
-#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 1)
+#define SNDRV_COMPRESS_VERSION SNDRV_PROTOCOL_VERSION(0, 1, 2)
/**
* struct snd_compressed_buffer: compressed buffer
* @fragment_size: size of buffer fragment in bytes
@@ -67,8 +67,8 @@
struct snd_compr_tstamp {
__u32 byte_offset;
__u32 copied_total;
- snd_pcm_uframes_t pcm_frames;
- snd_pcm_uframes_t pcm_io_frames;
+ __u32 pcm_frames;
+ __u32 pcm_io_frames;
__u32 sampling_rate;
};
@@ -80,7 +80,7 @@
struct snd_compr_avail {
__u64 avail;
struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed));
enum snd_compr_direction {
SND_COMPRESS_PLAYBACK = 0,
diff --git a/init/Kconfig b/init/Kconfig
index 2d9b831..8fa4f75 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1365,6 +1365,14 @@
support for "fast userspace mutexes". The resulting kernel may not
run glibc-based applications correctly.
+config HAVE_FUTEX_CMPXCHG
+ bool
+ depends on FUTEX
+ help
+ Architectures should select this if futex_atomic_cmpxchg_inatomic()
+ is implemented and always working. This removes a couple of runtime
+ checks.
+
config EPOLL
bool "Enable eventpoll support" if EXPERT
default y
diff --git a/init/main.c b/init/main.c
index 9484f4b..2132ffd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -74,6 +74,7 @@
#include <linux/ptrace.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
+#include <linux/random.h>
#include <asm/io.h>
#include <asm/bugs.h>
@@ -605,6 +606,10 @@
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi_enter_virtual_mode();
#endif
+#ifdef CONFIG_X86_ESPFIX64
+ /* Should be run before the first non-init thread is created */
+ init_espfix_bsp();
+#endif
thread_info_cache_init();
cred_init();
fork_init(totalram_pages);
@@ -777,6 +782,7 @@
do_ctors();
usermodehelper_enable();
do_initcalls();
+ random_int_secret_init();
}
static void __init do_pre_smp_initcalls(void)
diff --git a/ipc/compat.c b/ipc/compat.c
index 892f658..d3b3760 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -381,7 +381,7 @@
uptr = compat_ptr(ipck.msgp);
fifth = ipck.msgtyp;
}
- return do_msgrcv(first, uptr, second, fifth, third,
+ return do_msgrcv(first, uptr, second, (s32)fifth, third,
compat_do_msg_fill);
}
case MSGGET:
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 130dfec..a0f0ab2 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,7 +62,7 @@
return err;
}
-static int proc_ipc_callback_dointvec(ctl_table *table, int write,
+static int proc_ipc_callback_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
@@ -72,7 +72,7 @@
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
- rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
+ rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
if (write && !rc && lenp_bef == *lenp)
/*
@@ -123,7 +123,6 @@
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
- size_t lenp_bef = *lenp;
int oldval;
int rc;
@@ -133,7 +132,7 @@
rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
- if (write && !rc && lenp_bef == *lenp) {
+ if (write && !rc) {
int newval = *((int *)(ipc_table.data));
/*
* The file "auto_msgmni" has correctly been set.
@@ -152,15 +151,13 @@
#define proc_ipc_dointvec NULL
#define proc_ipc_dointvec_minmax NULL
#define proc_ipc_dointvec_minmax_orphans NULL
-#define proc_ipc_callback_dointvec NULL
+#define proc_ipc_callback_dointvec_minmax NULL
#define proc_ipcauto_dointvec_minmax NULL
#endif
static int zero;
static int one = 1;
-#ifdef CONFIG_CHECKPOINT_RESTORE
static int int_max = INT_MAX;
-#endif
static struct ctl_table ipc_kern_table[] = {
{
@@ -198,21 +195,27 @@
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof (init_ipc_ns.msg_ctlmax),
.mode = 0644,
- .proc_handler = proc_ipc_dointvec,
+ .proc_handler = proc_ipc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "msgmni",
.data = &init_ipc_ns.msg_ctlmni,
.maxlen = sizeof (init_ipc_ns.msg_ctlmni),
.mode = 0644,
- .proc_handler = proc_ipc_callback_dointvec,
+ .proc_handler = proc_ipc_callback_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "msgmnb",
.data = &init_ipc_ns.msg_ctlmnb,
.maxlen = sizeof (init_ipc_ns.msg_ctlmnb),
.mode = 0644,
- .proc_handler = proc_ipc_dointvec,
+ .proc_handler = proc_ipc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &int_max,
},
{
.procname = "sem",
diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c
index 383d638..5bb8bfe 100644
--- a/ipc/mq_sysctl.c
+++ b/ipc/mq_sysctl.c
@@ -22,6 +22,16 @@
return which;
}
+static int proc_mq_dointvec(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table mq_table;
+ memcpy(&mq_table, table, sizeof(mq_table));
+ mq_table.data = get_mq(table);
+
+ return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
static int proc_mq_dointvec_minmax(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -33,12 +43,10 @@
lenp, ppos);
}
#else
+#define proc_mq_dointvec NULL
#define proc_mq_dointvec_minmax NULL
#endif
-static int msg_queues_limit_min = MIN_QUEUESMAX;
-static int msg_queues_limit_max = HARD_QUEUESMAX;
-
static int msg_max_limit_min = MIN_MSGMAX;
static int msg_max_limit_max = HARD_MSGMAX;
@@ -51,9 +59,7 @@
.data = &init_ipc_ns.mq_queues_max,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_mq_dointvec_minmax,
- .extra1 = &msg_queues_limit_min,
- .extra2 = &msg_queues_limit_max,
+ .proc_handler = proc_mq_dointvec,
},
{
.procname = "msg_max",
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index e4e47f6..bb0248f 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -433,9 +433,9 @@
error = -EACCES;
goto out_unlock;
}
- if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
- (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
- !capable(CAP_SYS_RESOURCE))) {
+
+ if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+ !capable(CAP_SYS_RESOURCE)) {
error = -ENOSPC;
goto out_unlock;
}
@@ -823,6 +823,7 @@
error = ro;
goto out;
}
+ audit_inode_parent_hidden(name, root);
filp = do_create(ipc_ns, root->d_inode,
&path, oflag, mode,
u_attr ? &attr : NULL);
@@ -868,6 +869,7 @@
if (IS_ERR(name))
return PTR_ERR(name);
+ audit_inode_parent_hidden(name, mnt->mnt_root);
err = mnt_want_write(mnt);
if (err)
goto out_name;
diff --git a/ipc/msg.c b/ipc/msg.c
index d0c6d96..52770bf 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -70,8 +70,6 @@
#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS])
-#define msg_unlock(msq) ipc_unlock(&(msq)->q_perm)
-
static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
static int newque(struct ipc_namespace *, struct ipc_params *);
#ifdef CONFIG_PROC_FS
@@ -141,27 +139,23 @@
IPC_MSG_IDS, sysvipc_msg_proc_show);
}
-/*
- * msg_lock_(check_) routines are called in the paths where the rw_mutex
- * is not held.
- */
-static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
{
- struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
-static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
- int id)
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+ int id)
{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
@@ -171,12 +165,21 @@
ipc_rmid(&msg_ids(ns), &s->q_perm);
}
+static void msg_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct msg_queue *msq = ipc_rcu_to_struct(p);
+
+ security_msg_queue_free(msq);
+ ipc_rcu_free(head);
+}
+
/**
* newque - Create a new msg queue
* @ns: namespace
* @params: ptr to the structure that contains the key and msgflg
*
- * Called with msg_ids.rw_mutex held (writer)
+ * Called with msg_ids.rwsem held (writer)
*/
static int newque(struct ipc_namespace *ns, struct ipc_params *params)
{
@@ -195,17 +198,14 @@
msq->q_perm.security = NULL;
retval = security_msg_queue_alloc(msq);
if (retval) {
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, ipc_rcu_free);
return retval;
}
- /*
- * ipc_addid() locks msq
- */
+ /* ipc_addid() locks msq upon success. */
id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
if (id < 0) {
- security_msg_queue_free(msq);
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, msg_rcu_free);
return id;
}
@@ -218,7 +218,8 @@
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
return msq->q_perm.id;
}
@@ -264,8 +265,8 @@
* removes the message queue from message queue ID IDR, and cleans up all the
* messages associated with this queue.
*
- * msg_ids.rw_mutex (writer) and the spinlock for this message queue are held
- * before freeque() is called. msg_ids.rw_mutex remains locked on exit.
+ * msg_ids.rwsem (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rwsem remains locked on exit.
*/
static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -275,19 +276,19 @@
expunge_all(msq, -EIDRM);
ss_wakeup(&msq->q_senders, 1);
msg_rmid(ns, msq);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
atomic_dec(&ns->msg_hdrs);
free_msg(msg);
}
atomic_sub(msq->q_cbytes, &ns->msg_bytes);
- security_msg_queue_free(msq);
- ipc_rcu_putref(msq);
+ ipc_rcu_putref(msq, msg_rcu_free);
}
/*
- * Called with msg_ids.rw_mutex and ipcp locked.
+ * Called with msg_ids.rwsem and ipcp locked.
*/
static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
{
@@ -391,9 +392,9 @@
}
/*
- * This function handles some msgctl commands which require the rw_mutex
+ * This function handles some msgctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
struct msqid_ds __user *buf, int version)
@@ -408,31 +409,39 @@
return -EFAULT;
}
- ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
- &msqid64.msg_perm, msqid64.msg_qbytes);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ down_write(&msg_ids(ns).rwsem);
+ rcu_read_lock();
+
+ ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+ &msqid64.msg_perm, msqid64.msg_qbytes);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
msq = container_of(ipcp, struct msg_queue, q_perm);
err = security_msg_queue_msgctl(msq, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&msq->q_perm);
+ /* freeque unlocks the ipc object and rcu */
freeque(ns, ipcp);
goto out_up;
case IPC_SET:
if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
!capable(CAP_SYS_RESOURCE)) {
err = -EPERM;
- goto out_unlock;
+ goto out_unlock1;
}
+ ipc_lock_object(&msq->q_perm);
err = ipc_update_perm(&msqid64.msg_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
msq->q_qbytes = msqid64.msg_qbytes;
@@ -448,25 +457,23 @@
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
-out_unlock:
- msg_unlock(msq);
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
- up_write(&msg_ids(ns).rw_mutex);
+ up_write(&msg_ids(ns).rwsem);
return err;
}
-SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct msg_queue *msq;
- int err, version;
- struct ipc_namespace *ns;
-
- if (msqid < 0 || cmd < 0)
- return -EINVAL;
-
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
switch (cmd) {
case IPC_INFO:
@@ -477,6 +484,7 @@
if (!buf)
return -EFAULT;
+
/*
* We must not return kernel stack data.
* due to padding, it's not enough
@@ -492,7 +500,7 @@
msginfo.msgmnb = ns->msg_ctlmnb;
msginfo.msgssz = MSGSSZ;
msginfo.msgseg = MSGSEG;
- down_read(&msg_ids(ns).rw_mutex);
+ down_read(&msg_ids(ns).rwsem);
if (cmd == MSG_INFO) {
msginfo.msgpool = msg_ids(ns).in_use;
msginfo.msgmap = atomic_read(&ns->msg_hdrs);
@@ -503,12 +511,13 @@
msginfo.msgtql = MSGTQL;
}
max_id = ipc_get_maxid(&msg_ids(ns));
- up_read(&msg_ids(ns).rw_mutex);
+ up_read(&msg_ids(ns).rwsem);
if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
- case MSG_STAT: /* msqid is an index rather than a msg queue id */
+
+ case MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
@@ -517,17 +526,25 @@
if (!buf)
return -EFAULT;
+ memset(&tbuf, 0, sizeof(tbuf));
+
+ rcu_read_lock();
if (cmd == MSG_STAT) {
- msq = msg_lock(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = msq->q_perm.id;
} else {
- msq = msg_lock_check(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object_check(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
goto out_unlock;
@@ -536,8 +553,6 @@
if (err)
goto out_unlock;
- memset(&tbuf, 0, sizeof(tbuf));
-
kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
tbuf.msg_stime = msq->q_stime;
tbuf.msg_rtime = msq->q_rtime;
@@ -547,22 +562,46 @@
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
- msg_unlock(msq);
+ rcu_read_unlock();
+
if (copy_msqid_to_user(buf, &tbuf, version))
return -EFAULT;
return success_return;
}
+
+ default:
+ return -EINVAL;
+ }
+
+ return err;
+out_unlock:
+ rcu_read_unlock();
+ return err;
+}
+
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+ int version;
+ struct ipc_namespace *ns;
+
+ if (msqid < 0 || cmd < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case MSG_INFO:
+ case MSG_STAT: /* msqid is an index rather than a msg queue id */
+ case IPC_STAT:
+ return msgctl_nolock(ns, msqid, cmd, version, buf);
case IPC_SET:
case IPC_RMID:
- err = msgctl_down(ns, msqid, cmd, buf, version);
- return err;
+ return msgctl_down(ns, msqid, cmd, buf, version);
default:
return -EINVAL;
}
-
-out_unlock:
- msg_unlock(msq);
- return err;
}
static int testmsg(struct msg_msg *msg, long type, int mode)
@@ -640,22 +679,31 @@
msg->m_type = mtype;
msg->m_ts = msgsz;
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
- goto out_free;
+ goto out_unlock1;
}
+ ipc_lock_object(&msq->q_perm);
+
for (;;) {
struct msg_sender s;
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IWUGO))
- goto out_unlock_free;
+ goto out_unlock0;
+
+ /* raced with RMID? */
+ if (msq->q_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
err = security_msg_queue_msgsnd(msq, msg, msgflg);
if (err)
- goto out_unlock_free;
+ goto out_unlock0;
if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
1 + msq->q_qnum <= msq->q_qbytes) {
@@ -665,32 +713,37 @@
/* queue full, wait: */
if (msgflg & IPC_NOWAIT) {
err = -EAGAIN;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
ss_add(msq, &s);
if (!ipc_rcu_getref(msq)) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
- ipc_lock_by_ptr(&msq->q_perm);
- ipc_rcu_putref(msq);
+ rcu_read_lock();
+ ipc_lock_object(&msq->q_perm);
+
+ ipc_rcu_putref(msq, ipc_rcu_free);
if (msq->q_perm.deleted) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
ss_del(&s);
if (signal_pending(current)) {
err = -ERESTARTNOHAND;
- goto out_unlock_free;
+ goto out_unlock0;
}
- }
+ }
msq->q_lspid = task_tgid_vnr(current);
msq->q_stime = get_seconds();
@@ -706,9 +759,10 @@
err = 0;
msg = NULL;
-out_unlock_free:
- msg_unlock(msq);
-out_free:
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (msg != NULL)
free_msg(msg);
return err;
@@ -795,7 +849,7 @@
static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
{
- struct msg_msg *msg;
+ struct msg_msg *msg, *found = NULL;
long count = 0;
list_for_each_entry(msg, &msq->q_messages, m_list) {
@@ -804,6 +858,7 @@
*msgtyp, mode)) {
if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
*msgtyp = msg->m_type - 1;
+ found = msg;
} else if (mode == SEARCH_NUMBER) {
if (*msgtyp == count)
return msg;
@@ -813,33 +868,35 @@
}
}
- return ERR_PTR(-EAGAIN);
+ return found ?: ERR_PTR(-EAGAIN);
}
-
-long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
- int msgflg,
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
long (*msg_handler)(void __user *, struct msg_msg *, size_t))
{
- struct msg_queue *msq;
- struct msg_msg *msg;
int mode;
+ struct msg_queue *msq;
struct ipc_namespace *ns;
- struct msg_msg *copy = NULL;
+ struct msg_msg *msg, *copy = NULL;
ns = current->nsproxy->ipc_ns;
if (msqid < 0 || (long) bufsz < 0)
return -EINVAL;
+
if (msgflg & MSG_COPY) {
+ if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+ return -EINVAL;
copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
if (IS_ERR(copy))
return PTR_ERR(copy);
}
mode = convert_mode(&msgtyp, msgflg);
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
+ rcu_read_unlock();
free_copy(copy);
return PTR_ERR(msq);
}
@@ -849,10 +906,17 @@
msg = ERR_PTR(-EACCES);
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
- goto out_unlock;
+ goto out_unlock1;
+
+ ipc_lock_object(&msq->q_perm);
+
+ /* raced with RMID? */
+ if (msq->q_perm.deleted) {
+ msg = ERR_PTR(-EIDRM);
+ goto out_unlock0;
+ }
msg = find_msg(msq, &msgtyp, mode);
-
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
@@ -860,7 +924,7 @@
*/
if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
msg = ERR_PTR(-E2BIG);
- goto out_unlock;
+ goto out_unlock0;
}
/*
* If we are copying, then do not unlink message and do
@@ -868,8 +932,9 @@
*/
if (msgflg & MSG_COPY) {
msg = copy_msg(msg, copy);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
@@ -878,14 +943,16 @@
atomic_sub(msg->m_ts, &ns->msg_bytes);
atomic_dec(&ns->msg_hdrs);
ss_wakeup(&msq->q_senders, 0);
- msg_unlock(msq);
- break;
+
+ goto out_unlock0;
}
+
/* No message waiting. Wait for a message */
if (msgflg & IPC_NOWAIT) {
msg = ERR_PTR(-ENOMSG);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_add_tail(&msr_d.r_list, &msq->q_receivers);
msr_d.r_tsk = current;
msr_d.r_msgtype = msgtyp;
@@ -896,8 +963,9 @@
msr_d.r_maxsize = bufsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
current->state = TASK_INTERRUPTIBLE;
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
/* Lockless receive, part 1:
@@ -908,7 +976,7 @@
* Prior to destruction, expunge_all(-EIRDM) changes r_msg.
* Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
* rcu_read_lock() prevents preemption between reading r_msg
- * and the spin_lock() inside ipc_lock_by_ptr().
+ * and acquiring the q_perm.lock in ipc_lock_object().
*/
rcu_read_lock();
@@ -927,32 +995,34 @@
* If there is a message or an error then accept it without
* locking.
*/
- if (msg != ERR_PTR(-EAGAIN)) {
- rcu_read_unlock();
- break;
- }
+ if (msg != ERR_PTR(-EAGAIN))
+ goto out_unlock1;
/* Lockless receive, part 3:
* Acquire the queue spinlock.
*/
- ipc_lock_by_ptr(&msq->q_perm);
- rcu_read_unlock();
+ ipc_lock_object(&msq->q_perm);
/* Lockless receive, part 4:
* Repeat test after acquiring the spinlock.
*/
msg = (struct msg_msg*)msr_d.r_msg;
if (msg != ERR_PTR(-EAGAIN))
- goto out_unlock;
+ goto out_unlock0;
list_del(&msr_d.r_list);
if (signal_pending(current)) {
msg = ERR_PTR(-ERESTARTNOHAND);
-out_unlock:
- msg_unlock(msq);
- break;
+ goto out_unlock0;
}
+
+ ipc_unlock_object(&msq->q_perm);
}
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (IS_ERR(msg)) {
free_copy(copy);
return PTR_ERR(msg);
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 491e71f..7e70959 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -41,15 +41,15 @@
/* the next part of the message follows immediately */
};
-#define DATALEN_MSG (int)(PAGE_SIZE-sizeof(struct msg_msg))
-#define DATALEN_SEG (int)(PAGE_SIZE-sizeof(struct msg_msgseg))
+#define DATALEN_MSG ((size_t)PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG ((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
-static struct msg_msg *alloc_msg(int len)
+static struct msg_msg *alloc_msg(size_t len)
{
struct msg_msg *msg;
struct msg_msgseg **pseg;
- int alen;
+ size_t alen;
alen = min(len, DATALEN_MSG);
msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
@@ -80,12 +80,12 @@
return NULL;
}
-struct msg_msg *load_msg(const void __user *src, int len)
+struct msg_msg *load_msg(const void __user *src, size_t len)
{
struct msg_msg *msg;
struct msg_msgseg *seg;
int err = -EFAULT;
- int alen;
+ size_t alen;
msg = alloc_msg(len);
if (msg == NULL)
@@ -117,8 +117,8 @@
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
struct msg_msgseg *dst_pseg, *src_pseg;
- int len = src->m_ts;
- int alen;
+ size_t len = src->m_ts;
+ size_t alen;
BUG_ON(dst == NULL);
if (src->m_ts > dst->m_ts)
@@ -147,9 +147,9 @@
return ERR_PTR(-ENOSYS);
}
#endif
-int store_msg(void __user *dest, struct msg_msg *msg, int len)
+int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
{
- int alen;
+ size_t alen;
struct msg_msgseg *seg;
alen = min(len, DATALEN_MSG);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 7ee61bf..aba9a58 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -81,7 +81,7 @@
int next_id;
int total, in_use;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
in_use = ids->in_use;
@@ -89,11 +89,12 @@
perm = idr_find(&ids->ipcs_idr, next_id);
if (perm == NULL)
continue;
- ipc_lock_by_ptr(perm);
+ rcu_read_lock();
+ ipc_lock_object(perm);
free(ns, perm);
total++;
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
}
static void free_ipc_ns(struct ipc_namespace *ns)
diff --git a/ipc/sem.c b/ipc/sem.c
index 70480a3..db9d241 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -95,8 +95,12 @@
int semval; /* current value */
int sempid; /* pid of last operation */
spinlock_t lock; /* spinlock for fine-grained semtimedop */
- struct list_head sem_pending; /* pending single-sop operations */
-};
+ struct list_head pending_alter; /* pending single-sop operations */
+ /* that alter the semaphore */
+ struct list_head pending_const; /* pending single-sop operations */
+ /* that do not alter the semaphore*/
+ time_t sem_otime; /* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
/* One queue for each sleeping process in the system. */
struct sem_queue {
@@ -150,12 +154,15 @@
#define SEMOPM_FAST 64 /* ~ 372 bytes on stack */
/*
- * linked list protection:
+ * Locking:
* sem_undo.id_next,
- * sem_array.sem_pending{,last},
- * sem_array.sem_undo: sem_lock() for read/write
+ * sem_array.complex_count,
+ * sem_array.pending{_alter,_cont},
+ * sem_array.sem_undo: global sem_lock() for read/write
* sem_undo.proc_next: only "current" is allowed to read/write that field.
*
+ * sem_array.sem_base[i].pending_{const,alter}:
+ * global or semaphore sem_lock() for read/write
*/
#define sc_semmsl sem_ctls[0]
@@ -189,77 +196,176 @@
IPC_SEM_IDS, sysvipc_sem_proc_show);
}
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+ struct sem_queue *q, *tq;
+
+ /* complex operations still around? */
+ if (sma->complex_count)
+ return;
+ /*
+ * We will switch back to simple mode.
+ * Move all pending operation back into the per-semaphore
+ * queues.
+ */
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+ struct sem *curr;
+ curr = &sma->sem_base[q->sops[0].sem_num];
+
+ list_add_tail(&q->list, &curr->pending_alter);
+ }
+ INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - Merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+ int i;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ struct sem *sem = sma->sem_base + i;
+
+ list_splice_init(&sem->pending_alter, &sma->pending_alter);
+ }
+}
+
+static void sem_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct sem_array *sma = ipc_rcu_to_struct(p);
+
+ security_sem_free(sma);
+ ipc_rcu_free(head);
+}
+
+/*
+ * Wait until all currently ongoing simple ops have completed.
+ * Caller must own sem_perm.lock.
+ * New simple ops cannot start, because simple ops first check
+ * that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
+ */
+static void sem_wait_array(struct sem_array *sma)
+{
+ int i;
+ struct sem *sem;
+
+ if (sma->complex_count) {
+ /* The thread that increased sma->complex_count waited on
+ * all sem->lock locks. Thus we don't need to wait again.
+ */
+ return;
+ }
+
+ for (i = 0; i < sma->sem_nsems; i++) {
+ sem = sma->sem_base + i;
+ spin_unlock_wait(&sem->lock);
+ }
+}
+
/*
* If the request contains only one semaphore operation, and there are
* no complex transactions pending, lock only the semaphore involved.
* Otherwise, lock the entire semaphore array, since we either have
* multiple semaphores in our own semops, or we need to look at
* semaphores from other pending complex operations.
- *
- * Carefully guard against sma->complex_count changing between zero
- * and non-zero while we are spinning for the lock. The value of
- * sma->complex_count cannot change while we are holding the lock,
- * so sem_unlock should be fine.
- *
- * The global lock path checks that all the local locks have been released,
- * checking each local lock once. This means that the local lock paths
- * cannot start their critical sections while the global lock is held.
*/
static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
int nsops)
{
- int locknum;
- again:
- if (nsops == 1 && !sma->complex_count) {
- struct sem *sem = sma->sem_base + sops->sem_num;
+ struct sem *sem;
- /* Lock just the semaphore we are interested in. */
+ if (nsops != 1) {
+ /* Complex operation - acquire a full lock */
+ ipc_lock_object(&sma->sem_perm);
+
+ /* And wait until all simple ops that are processed
+ * right now have dropped their locks.
+ */
+ sem_wait_array(sma);
+ return -1;
+ }
+
+ /*
+ * Only one semaphore affected - try to optimize locking.
+ * The rules are:
+ * - optimized locking is possible if no complex operation
+ * is either enqueued or processed right now.
+ * - The test for enqueued complex ops is simple:
+ * sma->complex_count != 0
+ * - Testing for complex ops that are processed right now is
+ * a bit more difficult. Complex ops acquire the full lock
+ * and first wait that the running simple ops have completed.
+ * (see above)
+ * Thus: If we own a simple lock and the global lock is free
+ * and complex_count is now 0, then it will stay 0 and
+ * thus just locking sem->lock is sufficient.
+ */
+ sem = sma->sem_base + sops->sem_num;
+
+ if (sma->complex_count == 0) {
+ /*
+ * It appears that no complex operation is around.
+ * Acquire the per-semaphore lock.
+ */
spin_lock(&sem->lock);
- /*
- * If sma->complex_count was set while we were spinning,
- * we may need to look at things we did not lock here.
- */
- if (unlikely(sma->complex_count)) {
- spin_unlock(&sem->lock);
- goto lock_array;
- }
+ /* Then check that the global lock is free */
+ if (!spin_is_locked(&sma->sem_perm.lock)) {
+ /* spin_is_locked() is not a memory barrier */
+ smp_mb();
- /*
- * Another process is holding the global lock on the
- * sem_array; we cannot enter our critical section,
- * but have to wait for the global lock to be released.
- */
- if (unlikely(spin_is_locked(&sma->sem_perm.lock))) {
- spin_unlock(&sem->lock);
- spin_unlock_wait(&sma->sem_perm.lock);
- goto again;
+ /* Now repeat the test of complex_count:
+ * It can't change anymore until we drop sem->lock.
+ * Thus: if is now 0, then it will stay 0.
+ */
+ if (sma->complex_count == 0) {
+ /* fast path successful! */
+ return sops->sem_num;
+ }
}
-
- locknum = sops->sem_num;
- } else {
- int i;
- /*
- * Lock the semaphore array, and wait for all of the
- * individual semaphore locks to go away. The code
- * above ensures no new single-lock holders will enter
- * their critical section while the array lock is held.
- */
- lock_array:
- spin_lock(&sma->sem_perm.lock);
- for (i = 0; i < sma->sem_nsems; i++) {
- struct sem *sem = sma->sem_base + i;
- spin_unlock_wait(&sem->lock);
- }
- locknum = -1;
+ spin_unlock(&sem->lock);
}
- return locknum;
+
+ /* slow path: acquire the full lock */
+ ipc_lock_object(&sma->sem_perm);
+
+ if (sma->complex_count == 0) {
+ /* False alarm:
+ * There is no complex operation, thus we can switch
+ * back to the fast path.
+ */
+ spin_lock(&sem->lock);
+ ipc_unlock_object(&sma->sem_perm);
+ return sops->sem_num;
+ } else {
+ /* Not a false alarm, thus complete the sequence for a
+ * full lock.
+ */
+ sem_wait_array(sma);
+ return -1;
+ }
}
static inline void sem_unlock(struct sem_array *sma, int locknum)
{
if (locknum == -1) {
- spin_unlock(&sma->sem_perm.lock);
+ unmerge_queues(sma);
+ ipc_unlock_object(&sma->sem_perm);
} else {
struct sem *sem = sma->sem_base + locknum;
spin_unlock(&sem->lock);
@@ -267,7 +373,7 @@
}
/*
- * sem_lock_(check_) routines are called in the paths where the rw_mutex
+ * sem_lock_(check_) routines are called in the paths where the rwsem
* is not held.
*
* The caller holds the RCU read lock.
@@ -319,12 +425,7 @@
static inline void sem_lock_and_putref(struct sem_array *sma)
{
sem_lock(sma, NULL, -1);
- ipc_rcu_putref(sma);
-}
-
-static inline void sem_putref(struct sem_array *sma)
-{
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
}
static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -337,7 +438,7 @@
* Without the check/retry algorithm a lockless wakeup is possible:
* - queue.status is initialized to -EINTR before blocking.
* - wakeup is performed by
- * * unlinking the queue entry from sma->sem_pending
+ * * unlinking the queue entry from the pending list
* * setting queue.status to IN_WAKEUP
* This is the notification for the blocked thread that a
* result value is imminent.
@@ -371,7 +472,7 @@
* @ns: namespace
* @params: ptr to the structure that contains key, semflg and nsems
*
- * Called with sem_ids.rw_mutex held (as a writer)
+ * Called with sem_ids.rwsem held (as a writer)
*/
static int newary(struct ipc_namespace *ns, struct ipc_params *params)
@@ -403,14 +504,13 @@
sma->sem_perm.security = NULL;
retval = security_sem_alloc(sma);
if (retval) {
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return retval;
}
id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
if (id < 0) {
- security_sem_free(sma);
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, sem_rcu_free);
return id;
}
ns->used_sems += nsems;
@@ -418,12 +518,14 @@
sma->sem_base = (struct sem *) &sma[1];
for (i = 0; i < nsems; i++) {
- INIT_LIST_HEAD(&sma->sem_base[i].sem_pending);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
spin_lock_init(&sma->sem_base[i].lock);
}
sma->complex_count = 0;
- INIT_LIST_HEAD(&sma->sem_pending);
+ INIT_LIST_HEAD(&sma->pending_alter);
+ INIT_LIST_HEAD(&sma->pending_const);
INIT_LIST_HEAD(&sma->list_id);
sma->sem_nsems = nsems;
sma->sem_ctime = get_seconds();
@@ -435,7 +537,7 @@
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
{
@@ -446,7 +548,7 @@
}
/*
- * Called with sem_ids.rw_mutex and ipcp locked.
+ * Called with sem_ids.rwsem and ipcp locked.
*/
static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -482,12 +584,19 @@
return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
}
-/*
- * Determine whether a sequence of semaphore operations would succeed
- * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
+/** perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @sops: array with operations that should be checked
+ * @nsems: number of sops
+ * @un: undo array
+ * @pid: pid that did the change
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
*/
-static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
+static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
int nsops, struct sem_undo *un, int pid)
{
int result, sem_op;
@@ -609,60 +718,132 @@
* update_queue is O(N^2) when it restarts scanning the whole queue of
* waiting operations. Therefore this function checks if the restart is
* really necessary. It is called after a previously waiting operation
- * was completed.
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
*/
static int check_restart(struct sem_array *sma, struct sem_queue *q)
{
- struct sem *curr;
- struct sem_queue *h;
-
- /* if the operation didn't modify the array, then no restart */
- if (q->alter == 0)
- return 0;
-
- /* pending complex operations are too difficult to analyse */
- if (sma->complex_count)
+ /* pending complex alter operations are too difficult to analyse */
+ if (!list_empty(&sma->pending_alter))
return 1;
/* we were a sleeping complex operation. Too difficult */
if (q->nsops > 1)
return 1;
- curr = sma->sem_base + q->sops[0].sem_num;
+ /* It is impossible that someone waits for the new value:
+ * - complex operations always restart.
+ * - wait-for-zero are handled seperately.
+ * - q is a previously sleeping simple operation that
+ * altered the array. It must be a decrement, because
+ * simple increments never sleep.
+ * - If there are older (higher priority) decrements
+ * in the queue, then they have observed the original
+ * semval value and couldn't proceed. The operation
+ * decremented to value - thus they won't proceed either.
+ */
+ return 0;
+}
- /* No-one waits on this queue */
- if (list_empty(&curr->sem_pending))
- return 0;
+/**
+ * wake_const_ops(sma, semnum, pt) - Wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+ struct list_head *pt)
+{
+ struct sem_queue *q;
+ struct list_head *walk;
+ struct list_head *pending_list;
+ int semop_completed = 0;
- /* the new semaphore value */
- if (curr->semval) {
- /* It is impossible that someone waits for the new value:
- * - q is a previously sleeping simple operation that
- * altered the array. It must be a decrement, because
- * simple increments never sleep.
- * - The value is not 0, thus wait-for-zero won't proceed.
- * - If there are older (higher priority) decrements
- * in the queue, then they have observed the original
- * semval value and couldn't proceed. The operation
- * decremented to value - thus they won't proceed either.
+ if (semnum == -1)
+ pending_list = &sma->pending_const;
+ else
+ pending_list = &sma->sem_base[semnum].pending_const;
+
+ walk = pending_list->next;
+ while (walk != pending_list) {
+ int error;
+
+ q = container_of(walk, struct sem_queue, list);
+ walk = walk->next;
+
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
+ q->undo, q->pid);
+
+ if (error <= 0) {
+ /* operation completed, remove from queue & wakeup */
+
+ unlink_queue(sma, q);
+
+ wake_up_sem_queue_prepare(pt, q, error);
+ if (error == 0)
+ semop_completed = 1;
+ }
+ }
+ return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero(sma, sops, nsops, pt) - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_wakeup_zero() checks all required queue for wait-for-zero
+ * operations, based on the actual changes that were performed on the
+ * semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+ int nsops, struct list_head *pt)
+{
+ int i;
+ int semop_completed = 0;
+ int got_zero = 0;
+
+ /* first: the per-semaphore queues, if known */
+ if (sops) {
+ for (i = 0; i < nsops; i++) {
+ int num = sops[i].sem_num;
+
+ if (sma->sem_base[num].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, num, pt);
+ }
+ }
+ } else {
+ /*
+ * No sops means modified semaphores not known.
+ * Assume all were changed.
*/
- BUG_ON(q->sops[0].sem_op >= 0);
- return 0;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ if (sma->sem_base[i].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, i, pt);
+ }
+ }
}
/*
- * semval is 0. Check if there are wait-for-zero semops.
- * They must be the first entries in the per-semaphore queue
+ * If one of the modified semaphores got 0,
+ * then check the global queue, too.
*/
- h = list_first_entry(&curr->sem_pending, struct sem_queue, list);
- BUG_ON(h->nsops != 1);
- BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num);
+ if (got_zero)
+ semop_completed |= wake_const_ops(sma, -1, pt);
- /* Yes, there is a wait-for-zero semop. Restart */
- if (h->sops[0].sem_op == 0)
- return 1;
-
- /* Again - no-one is waiting for the new value. */
- return 0;
+ return semop_completed;
}
@@ -678,6 +859,8 @@
* semaphore.
* The tasks that must be woken up are added to @pt. The return code
* is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
* The function return 1 if at least one semop was completed successfully.
*/
static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
@@ -688,9 +871,9 @@
int semop_completed = 0;
if (semnum == -1)
- pending_list = &sma->sem_pending;
+ pending_list = &sma->pending_alter;
else
- pending_list = &sma->sem_base[semnum].sem_pending;
+ pending_list = &sma->sem_base[semnum].pending_alter;
again:
walk = pending_list->next;
@@ -702,16 +885,15 @@
/* If we are scanning the single sop, per-semaphore list of
* one semaphore and that semaphore is 0, then it is not
- * necessary to scan the "alter" entries: simple increments
+ * necessary to scan further: simple increments
* that affect only one entry succeed immediately and cannot
* be in the per semaphore pending queue, and decrements
* cannot be successful if the value is already 0.
*/
- if (semnum != -1 && sma->sem_base[semnum].semval == 0 &&
- q->alter)
+ if (semnum != -1 && sma->sem_base[semnum].semval == 0)
break;
- error = try_atomic_semop(sma, q->sops, q->nsops,
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
q->undo, q->pid);
/* Does q->sleeper still need to sleep? */
@@ -724,6 +906,7 @@
restart = 0;
} else {
semop_completed = 1;
+ do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
restart = check_restart(sma, q);
}
@@ -735,6 +918,24 @@
}
/**
+ * set_semotime(sma, sops) - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+ if (sops == NULL) {
+ sma->sem_base[0].sem_otime = get_seconds();
+ } else {
+ sma->sem_base[sops[0].sem_num].sem_otime =
+ get_seconds();
+ }
+}
+
+/**
* do_smart_update(sma, sops, nsops, otime, pt) - optimized update_queue
* @sma: semaphore array
* @sops: operations that were performed
@@ -742,8 +943,8 @@
* @otime: force setting otime
* @pt: list head of the tasks that must be woken up.
*
- * do_smart_update() does the required called to update_queue, based on the
- * actual changes that were performed on the semaphore array.
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
* Note that the function does not do the actual wake-up: the caller is
* responsible for calling wake_up_sem_queue_do(@pt).
* It is safe to perform this call after dropping all locks.
@@ -752,52 +953,42 @@
int otime, struct list_head *pt)
{
int i;
- int progress;
- progress = 1;
-retry_global:
- if (sma->complex_count) {
- if (update_queue(sma, -1, pt)) {
- progress = 1;
- otime = 1;
- sops = NULL;
- }
- }
- if (!progress)
- goto done;
+ otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
- if (!sops) {
- /* No semops; something special is going on. */
- for (i = 0; i < sma->sem_nsems; i++) {
- if (update_queue(sma, i, pt)) {
- otime = 1;
- progress = 1;
+ if (!list_empty(&sma->pending_alter)) {
+ /* semaphore array uses the global queue - just process it. */
+ otime |= update_queue(sma, -1, pt);
+ } else {
+ if (!sops) {
+ /*
+ * No sops, thus the modified semaphores are not
+ * known. Check all.
+ */
+ for (i = 0; i < sma->sem_nsems; i++)
+ otime |= update_queue(sma, i, pt);
+ } else {
+ /*
+ * Check the semaphores that were increased:
+ * - No complex ops, thus all sleeping ops are
+ * decrease.
+ * - if we decreased the value, then any sleeping
+ * semaphore ops wont be able to run: If the
+ * previous value was too small, then the new
+ * value will be too small, too.
+ */
+ for (i = 0; i < nsops; i++) {
+ if (sops[i].sem_op > 0) {
+ otime |= update_queue(sma,
+ sops[i].sem_num, pt);
+ }
}
}
- goto done_checkretry;
}
-
- /* Check the semaphores that were modified. */
- for (i = 0; i < nsops; i++) {
- if (sops[i].sem_op > 0 ||
- (sops[i].sem_op < 0 &&
- sma->sem_base[sops[i].sem_num].semval == 0))
- if (update_queue(sma, sops[i].sem_num, pt)) {
- otime = 1;
- progress = 1;
- }
- }
-done_checkretry:
- if (progress) {
- progress = 0;
- goto retry_global;
- }
-done:
if (otime)
- sma->sem_otime = get_seconds();
+ set_semotime(sma, sops);
}
-
/* The following counts are associated to each semaphore:
* semncnt number of tasks waiting on semval being nonzero
* semzcnt number of tasks waiting on semval being zero
@@ -813,14 +1004,14 @@
struct sem_queue * q;
semncnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
semncnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_alter, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
@@ -839,14 +1030,14 @@
struct sem_queue * q;
semzcnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
semzcnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_const, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
@@ -859,8 +1050,8 @@
return semzcnt;
}
-/* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
- * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
+/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
+ * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
* remains locked on exit.
*/
static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
@@ -872,7 +1063,7 @@
int i;
/* Free the existing undo structures for this semaphore set. */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
list_del(&un->list_id);
spin_lock(&un->ulp->lock);
@@ -884,13 +1075,22 @@
/* Wake up all pending processes and let them fail with EIDRM. */
INIT_LIST_HEAD(&tasks);
- list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
for (i = 0; i < sma->sem_nsems; i++) {
struct sem *sem = sma->sem_base + i;
- list_for_each_entry_safe(q, tq, &sem->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+ list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
@@ -903,8 +1103,7 @@
wake_up_sem_queue_do(&tasks);
ns->used_sems -= sma->sem_nsems;
- security_sem_free(sma);
- ipc_rcu_putref(sma);
+ ipc_rcu_putref(sma, sem_rcu_free);
}
static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
@@ -931,6 +1130,21 @@
}
}
+static time_t get_semotime(struct sem_array *sma)
+{
+ int i;
+ time_t res;
+
+ res = sma->sem_base[0].sem_otime;
+ for (i = 1; i < sma->sem_nsems; i++) {
+ time_t to = sma->sem_base[i].sem_otime;
+
+ if (to > res)
+ res = to;
+ }
+ return res;
+}
+
static int semctl_nolock(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
{
@@ -957,7 +1171,7 @@
seminfo.semmnu = SEMMNU;
seminfo.semmap = SEMMAP;
seminfo.semume = SEMUME;
- down_read(&sem_ids(ns).rw_mutex);
+ down_read(&sem_ids(ns).rwsem);
if (cmd == SEM_INFO) {
seminfo.semusz = sem_ids(ns).in_use;
seminfo.semaem = ns->used_sems;
@@ -966,7 +1180,7 @@
seminfo.semaem = SEMAEM;
}
max_id = ipc_get_maxid(&sem_ids(ns));
- up_read(&sem_ids(ns).rw_mutex);
+ up_read(&sem_ids(ns).rwsem);
if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
return -EFAULT;
return (max_id < 0) ? 0: max_id;
@@ -1004,9 +1218,9 @@
goto out_unlock;
kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
- tbuf.sem_otime = sma->sem_otime;
- tbuf.sem_ctime = sma->sem_ctime;
- tbuf.sem_nsems = sma->sem_nsems;
+ tbuf.sem_otime = get_semotime(sma);
+ tbuf.sem_ctime = sma->sem_ctime;
+ tbuf.sem_nsems = sma->sem_nsems;
rcu_read_unlock();
if (copy_semid_to_user(p, &tbuf, version))
return -EFAULT;
@@ -1068,9 +1282,15 @@
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ return -EIDRM;
+ }
+
curr = &sma->sem_base[semnum];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id)
un->semadj[semnum] = 0;
@@ -1122,28 +1342,28 @@
int i;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
if(nsems > SEMMSL_FAST) {
if (!ipc_rcu_getref(sma)) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
sem_unlock(sma, -1);
rcu_read_unlock();
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if(sem_io == NULL) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return -ENOMEM;
}
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
}
for (i = 0; i < sma->sem_nsems; i++)
@@ -1161,28 +1381,28 @@
struct sem_undo *un;
if (!ipc_rcu_getref(sma)) {
- rcu_read_unlock();
- return -EIDRM;
+ err = -EIDRM;
+ goto out_rcu_wakeup;
}
rcu_read_unlock();
if(nsems > SEMMSL_FAST) {
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if(sem_io == NULL) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return -ENOMEM;
}
}
if (copy_from_user (sem_io, p, nsems*sizeof(ushort))) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
err = -EFAULT;
goto out_free;
}
for (i = 0; i < nsems; i++) {
if (sem_io[i] > SEMVMX) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
err = -ERANGE;
goto out_free;
}
@@ -1190,16 +1410,14 @@
rcu_read_lock();
sem_lock_and_putref(sma);
if (sma->sem_perm.deleted) {
- sem_unlock(sma, -1);
- rcu_read_unlock();
err = -EIDRM;
- goto out_free;
+ goto out_unlock;
}
for (i = 0; i < nsems; i++)
sma->sem_base[i].semval = sem_io[i];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id) {
for (i = 0; i < nsems; i++)
un->semadj[i] = 0;
@@ -1217,6 +1435,10 @@
goto out_rcu_wakeup;
sem_lock(sma, NULL, -1);
+ if (sma->sem_perm.deleted) {
+ err = -EIDRM;
+ goto out_unlock;
+ }
curr = &sma->sem_base[semnum];
switch (cmd) {
@@ -1272,9 +1494,9 @@
}
/*
- * This function handles some semctl commands which require the rw_mutex
+ * This function handles some semctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int semctl_down(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
@@ -1289,42 +1511,46 @@
return -EFAULT;
}
+ down_write(&sem_ids(ns).rwsem);
+ rcu_read_lock();
+
ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
&semid64.sem_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
sma = container_of(ipcp, struct sem_array, sem_perm);
err = security_sem_semctl(sma, cmd);
- if (err) {
- rcu_read_unlock();
- goto out_up;
- }
+ if (err)
+ goto out_unlock1;
- switch(cmd){
+ switch (cmd) {
case IPC_RMID:
sem_lock(sma, NULL, -1);
+ /* freeary unlocks the ipc object and rcu */
freeary(ns, ipcp);
goto out_up;
case IPC_SET:
sem_lock(sma, NULL, -1);
err = ipc_update_perm(&semid64.sem_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
sma->sem_ctime = get_seconds();
break;
default:
- rcu_read_unlock();
err = -EINVAL;
- goto out_up;
+ goto out_unlock1;
}
-out_unlock:
+out_unlock0:
sem_unlock(sma, -1);
+out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&sem_ids(ns).rw_mutex);
+ up_write(&sem_ids(ns).rwsem);
return err;
}
@@ -1466,7 +1692,7 @@
/* step 2: allocate new undo structure */
new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
if (!new) {
- sem_putref(sma);
+ ipc_rcu_putref(sma, ipc_rcu_free);
return ERR_PTR(-ENOMEM);
}
@@ -1496,7 +1722,7 @@
new->semid = semid;
assert_spin_locked(&ulp->lock);
list_add_rcu(&new->list_proc, &ulp->list_proc);
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_add(&new->list_id, &sma->list_id);
un = new;
@@ -1533,7 +1759,6 @@
return error;
}
-
SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
unsigned, nsops, const struct timespec __user *, timeout)
{
@@ -1619,6 +1844,10 @@
if (error)
goto out_rcu_wakeup;
+ error = -EIDRM;
+ locknum = sem_lock(sma, sops, nsops);
+ if (sma->sem_perm.deleted)
+ goto out_unlock_free;
/*
* semid identifiers are not unique - find_alloc_undo may have
* allocated an undo structure, it was invalidated by an RMID
@@ -1626,18 +1855,22 @@
* This case can be detected checking un->semid. The existence of
* "un" itself is guaranteed by rcu.
*/
- error = -EIDRM;
- locknum = sem_lock(sma, sops, nsops);
if (un && un->semid == -1)
goto out_unlock_free;
- error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
- if (error <= 0) {
- if (alter && error == 0)
+ error = perform_atomic_semop(sma, sops, nsops, un,
+ task_tgid_vnr(current));
+ if (error == 0) {
+ /* If the operation was successful, then do
+ * the required updates.
+ */
+ if (alter)
do_smart_update(sma, sops, nsops, 1, &tasks);
-
- goto out_unlock_free;
+ else
+ set_semotime(sma, sops);
}
+ if (error <= 0)
+ goto out_unlock_free;
/* We need to sleep on this operation, so we put the current
* task into the pending queue and go to sleep.
@@ -1653,15 +1886,27 @@
struct sem *curr;
curr = &sma->sem_base[sops->sem_num];
- if (alter)
- list_add_tail(&queue.list, &curr->sem_pending);
- else
- list_add(&queue.list, &curr->sem_pending);
+ if (alter) {
+ if (sma->complex_count) {
+ list_add_tail(&queue.list,
+ &sma->pending_alter);
+ } else {
+
+ list_add_tail(&queue.list,
+ &curr->pending_alter);
+ }
+ } else {
+ list_add_tail(&queue.list, &curr->pending_const);
+ }
} else {
+ if (!sma->complex_count)
+ merge_queues(sma);
+
if (alter)
- list_add_tail(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_alter);
else
- list_add(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_const);
+
sma->complex_count++;
}
@@ -1822,6 +2067,12 @@
}
sem_lock(sma, NULL, -1);
+ /* exit_sem raced with IPC_RMID, nothing to do */
+ if (sma->sem_perm.deleted) {
+ sem_unlock(sma, -1);
+ rcu_read_unlock();
+ continue;
+ }
un = __lookup_undo(ulp, semid);
if (un == NULL) {
/* exit_sem raced with IPC_RMID+semget() that created
@@ -1833,7 +2084,7 @@
}
/* remove un from the linked lists */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_del(&un->list_id);
spin_lock(&ulp->lock);
@@ -1882,6 +2133,17 @@
{
struct user_namespace *user_ns = seq_user_ns(s);
struct sem_array *sma = it;
+ time_t sem_otime;
+
+ /*
+ * The proc interface isn't aware of sem_lock(), it calls
+ * ipc_lock_object() directly (in sysvipc_find_ipc).
+ * In order to stay compatible with sem_lock(), we must wait until
+ * all simple semop() calls have left their critical regions.
+ */
+ sem_wait_array(sma);
+
+ sem_otime = get_semotime(sma);
return seq_printf(s,
"%10d %10d %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
@@ -1893,7 +2155,7 @@
from_kgid_munged(user_ns, sma->sem_perm.gid),
from_kuid_munged(user_ns, sma->sem_perm.cuid),
from_kgid_munged(user_ns, sma->sem_perm.cgid),
- sma->sem_otime,
+ sem_otime,
sma->sem_ctime);
}
#endif
diff --git a/ipc/shm.c b/ipc/shm.c
index 7e199fa..6dc55af 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -19,6 +19,9 @@
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
*/
#include <linux/slab.h>
@@ -80,8 +83,8 @@
}
/*
- * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
- * Only shm_ids.rw_mutex remains locked on exit.
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
*/
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -124,8 +127,28 @@
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
/*
- * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * shm_lock_(check_) routines are called in the paths where the rwsem
* is not necessarily held.
*/
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
@@ -141,18 +164,16 @@
static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
{
rcu_read_lock();
- spin_lock(&ipcp->shm_perm.lock);
+ ipc_lock_object(&ipcp->shm_perm);
}
-static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
- int id)
+static void shm_rcu_free(struct rcu_head *head)
{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id);
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+ struct shmid_kernel *shp = ipc_rcu_to_struct(p);
- if (IS_ERR(ipcp))
- return (struct shmid_kernel *)ipcp;
-
- return container_of(ipcp, struct shmid_kernel, shm_perm);
+ security_shm_free(shp);
+ ipc_rcu_free(head);
}
static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
@@ -182,22 +203,24 @@
* @ns: namespace
* @shp: struct to free
*
- * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
+ struct file *shm_file;
+
+ shm_file = shp->shm_file;
+ shp->shm_file = NULL;
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
shm_rmid(ns, shp);
shm_unlock(shp);
- if (!is_file_hugepages(shp->shm_file))
- shmem_lock(shp->shm_file, 0, shp->mlock_user);
+ if (!is_file_hugepages(shm_file))
+ shmem_lock(shm_file, 0, shp->mlock_user);
else if (shp->mlock_user)
- user_shm_unlock(file_inode(shp->shm_file)->i_size,
- shp->mlock_user);
- fput (shp->shm_file);
- security_shm_free(shp);
- ipc_rcu_putref(shp);
+ user_shm_unlock(file_inode(shm_file)->i_size, shp->mlock_user);
+ fput(shm_file);
+ ipc_rcu_putref(shp, shm_rcu_free);
}
/*
@@ -230,7 +253,7 @@
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
/* remove from the list of attaches of the shm segment */
shp = shm_lock(ns, sfd->id);
BUG_ON(IS_ERR(shp));
@@ -241,10 +264,10 @@
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_current(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -275,7 +298,7 @@
return 0;
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -286,7 +309,7 @@
* We want to destroy segments without users and with already
* exit'ed originating process.
*
- * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
+ * As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
if (shp->shm_creator != NULL)
return 0;
@@ -300,10 +323,10 @@
void shm_destroy_orphaned(struct ipc_namespace *ns)
{
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
@@ -315,10 +338,10 @@
return;
/* Destroy all already created segments, but not mapped yet */
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -452,7 +475,7 @@
* @ns: namespace
* @params: ptr to the structure that contains key, size and shmflg
*
- * Called with shm_ids.rw_mutex held as a writer.
+ * Called with shm_ids.rwsem held as a writer.
*/
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
@@ -485,7 +508,7 @@
shp->shm_perm.security = NULL;
error = security_shm_alloc(shp);
if (error) {
- ipc_rcu_putref(shp);
+ ipc_rcu_putref(shp, ipc_rcu_free);
return error;
}
@@ -535,6 +558,7 @@
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
+
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
* proc-ps tools use this. Changing this will break them.
@@ -543,7 +567,9 @@
ns->shm_tot += numpages;
error = shp->shm_perm.id;
- shm_unlock(shp);
+
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
return error;
no_id:
@@ -551,13 +577,12 @@
user_shm_unlock(size, shp->mlock_user);
fput(file);
no_file:
- security_shm_free(shp);
- ipc_rcu_putref(shp);
+ ipc_rcu_putref(shp, shm_rcu_free);
return error;
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
@@ -568,7 +593,7 @@
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -681,7 +706,7 @@
/*
* Calculate and add used RSS and swap pages of a shm.
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
@@ -708,7 +733,7 @@
}
/*
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
@@ -737,9 +762,9 @@
}
/*
- * This function handles some shmctl commands which require the rw_mutex
+ * This function handles some shmctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid_ds __user *buf, int version)
@@ -754,58 +779,66 @@
return -EFAULT;
}
- ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
- &shmid64.shm_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ down_write(&shm_ids(ns).rwsem);
+ rcu_read_lock();
+
+ ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+ &shmid64.shm_perm, 0);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
+
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&shp->shm_perm);
+ /* do_shm_rmid unlocks the ipc object and rcu */
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
+ ipc_lock_object(&shp->shm_perm);
err = ipc_update_perm(&shmid64.shm_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
shp->shm_ctim = get_seconds();
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
-out_unlock:
- shm_unlock(shp);
+
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
return err;
}
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct shmid_kernel *shp;
- int err, version;
- struct ipc_namespace *ns;
- if (cmd < 0 || shmid < 0) {
- err = -EINVAL;
- goto out;
- }
-
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
-
- switch (cmd) { /* replace with proc interface ? */
- case IPC_INFO:
- {
- struct shminfo64 shminfo;
-
+ /* preliminary security checks for *_INFO */
+ if (cmd == IPC_INFO || cmd == SHM_INFO) {
err = security_shm_shmctl(NULL, cmd);
if (err)
return err;
+ }
+
+ switch (cmd) {
+ case IPC_INFO:
+ {
+ struct shminfo64 shminfo;
memset(&shminfo, 0, sizeof(shminfo));
shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
@@ -816,9 +849,9 @@
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if(err<0)
err = 0;
@@ -828,19 +861,15 @@
{
struct shm_info shm_info;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shm_info, 0, sizeof(shm_info));
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
shm_info.used_ids = shm_ids(ns).in_use;
shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp);
shm_info.shm_tot = ns->shm_tot;
shm_info.swap_attempts = 0;
shm_info.swap_successes = 0;
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
goto out;
@@ -855,27 +884,31 @@
struct shmid64_ds tbuf;
int result;
+ rcu_read_lock();
if (cmd == SHM_STAT) {
- shp = shm_lock(ns, shmid);
+ shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = shp->shm_perm.id;
} else {
- shp = shm_lock_check(ns, shmid);
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
+
err = security_shm_shmctl(shp, cmd);
if (err)
goto out_unlock;
+
memset(&tbuf, 0, sizeof(tbuf));
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
tbuf.shm_segsz = shp->shm_segsz;
@@ -885,43 +918,86 @@
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
tbuf.shm_nattch = shp->shm_nattch;
- shm_unlock(shp);
- if(copy_shmid_to_user (buf, &tbuf, version))
+ rcu_read_unlock();
+
+ if (copy_shmid_to_user(buf, &tbuf, version))
err = -EFAULT;
else
err = result;
goto out;
}
+ default:
+ return -EINVAL;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+ struct shmid_kernel *shp;
+ int err, version;
+ struct ipc_namespace *ns;
+
+ if (cmd < 0 || shmid < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case SHM_INFO:
+ case SHM_STAT:
+ case IPC_STAT:
+ return shmctl_nolock(ns, shmid, cmd, version, buf);
+ case IPC_RMID:
+ case IPC_SET:
+ return shmctl_down(ns, shmid, cmd, buf, version);
case SHM_LOCK:
case SHM_UNLOCK:
{
struct file *shm_file;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
-
- if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
- kuid_t euid = current_euid();
- err = -EPERM;
- if (!uid_eq(euid, shp->shm_perm.uid) &&
- !uid_eq(euid, shp->shm_perm.cuid))
- goto out_unlock;
- if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
- goto out_unlock;
- }
-
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
+
+ ipc_lock_object(&shp->shm_perm);
+ if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
+ kuid_t euid = current_euid();
+ if (!uid_eq(euid, shp->shm_perm.uid) &&
+ !uid_eq(euid, shp->shm_perm.cuid)) {
+ err = -EPERM;
+ goto out_unlock0;
+ }
+ if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
+ err = -EPERM;
+ goto out_unlock0;
+ }
+ }
shm_file = shp->shm_file;
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shm_file == NULL) {
+ err = -EIDRM;
+ goto out_unlock0;
+ }
+
if (is_file_hugepages(shm_file))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK) {
struct user_struct *user = current_user();
@@ -930,32 +1006,31 @@
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
- goto out_unlock;
+ goto out_unlock0;
}
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
- goto out_unlock;
+ goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_user);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_user = NULL;
get_file(shm_file);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
+
fput(shm_file);
- goto out;
- }
- case IPC_RMID:
- case IPC_SET:
- err = shmctl_down(ns, shmid, cmd, buf, version);
return err;
+ }
default:
return -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
-out:
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
return err;
}
@@ -1023,10 +1098,11 @@
* additional creator id...
*/
ns = current->nsproxy->ipc_ns;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
err = -EACCES;
@@ -1037,24 +1113,39 @@
if (err)
goto out_unlock;
+ ipc_lock_object(&shp->shm_perm);
+
+ /* check if shm_destroy() is tearing down shp */
+ if (shp->shm_file == NULL) {
+ ipc_unlock_object(&shp->shm_perm);
+ err = -EIDRM;
+ goto out_unlock;
+ }
+
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
size = i_size_read(path.dentry->d_inode);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
- if (!sfd)
- goto out_put_dentry;
+ if (!sfd) {
+ path_put(&path);
+ goto out_nattch;
+ }
file = alloc_file(&path, f_mode,
is_file_hugepages(shp->shm_file) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_free;
+ if (IS_ERR(file)) {
+ kfree(sfd);
+ path_put(&path);
+ goto out_nattch;
+ }
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
@@ -1080,7 +1171,7 @@
addr > current->mm->start_stack - size - PAGE_SIZE * 5)
goto invalid;
}
-
+
addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
*raddr = addr;
err = 0;
@@ -1095,7 +1186,7 @@
fput(file);
out_nattch:
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
@@ -1103,20 +1194,13 @@
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
-
-out:
+ up_write(&shm_ids(ns).rwsem);
return err;
out_unlock:
- shm_unlock(shp);
- goto out;
-
-out_free:
- kfree(sfd);
-out_put_dentry:
- path_put(&path);
- goto out_nattch;
+ rcu_read_unlock();
+out:
+ return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
@@ -1221,8 +1305,7 @@
#else /* CONFIG_MMU */
/* under NOMMU conditions, the exact address to be destroyed must be
* given */
- retval = -EINVAL;
- if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
retval = 0;
}
diff --git a/ipc/util.c b/ipc/util.c
index 809ec5e..7684f41 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -15,6 +15,29 @@
* Jun 2006 - namespaces ssupport
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ * rcu_read_lock()
+ * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr
+ * tree.
+ * - perform initial checks (capabilities, auditing and permission,
+ * etc).
+ * - perform read-only operations, such as STAT, INFO commands.
+ * acquire the ipc lock (kern_ipc_perm.lock) through
+ * ipc_lock_object()
+ * - perform data updates, such as SET, RMID commands and
+ * mechanism-specific operations (semop/semtimedop,
+ * msgsnd/msgrcv, shmat/shmdt).
+ * drop the ipc lock, through ipc_unlock_object().
+ * rcu_read_unlock()
+ *
+ * The ids->rwsem must be taken when:
+ * - creating, removing and iterating the existing entries in ipc
+ * identifier sets.
+ * - iterating through files under /proc/sysvipc/
+ *
+ * Note that sems have a special fast path that avoids kern_ipc_perm.lock -
+ * see sem_lock().
*/
#include <linux/mm.h>
@@ -119,7 +142,7 @@
void ipc_init_ids(struct ipc_ids *ids)
{
- init_rwsem(&ids->rw_mutex);
+ init_rwsem(&ids->rwsem);
ids->in_use = 0;
ids->seq = 0;
@@ -174,7 +197,7 @@
* @ids: Identifier set
* @key: The key to find
*
- * Requires ipc_ids.rw_mutex locked.
+ * Requires ipc_ids.rwsem locked.
* Returns the LOCKED pointer to the ipc structure if found or NULL
* if not.
* If key is found ipc points to the owning ipc structure
@@ -197,7 +220,8 @@
continue;
}
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
@@ -208,7 +232,7 @@
* ipc_get_maxid - get the last assigned id
* @ids: IPC identifier set
*
- * Called with ipc_ids.rw_mutex held.
+ * Called with ipc_ids.rwsem held.
*/
int ipc_get_maxid(struct ipc_ids *ids)
@@ -246,9 +270,8 @@
* is returned. The 'new' entry is returned in a locked state on success.
* On failure the entry is not locked and a negative err-code is returned.
*
- * Called with ipc_ids.rw_mutex held as a writer.
+ * Called with writer ipc_ids.rwsem held.
*/
-
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
kuid_t euid;
@@ -313,9 +336,9 @@
{
int err;
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
err = ops->getnew(ns, params);
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -332,7 +355,7 @@
*
* On success, the IPC id is returned.
*
- * It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ * It is called with ipc_ids.rwsem and ipcp->lock held.
*/
static int ipc_check_perms(struct ipc_namespace *ns,
struct kern_ipc_perm *ipcp,
@@ -377,7 +400,7 @@
* Take the lock as a writer since we are potentially going to add
* a new entry + read locks are not "upgradable"
*/
- down_write(&ids->rw_mutex);
+ down_write(&ids->rwsem);
ipcp = ipc_findkey(ids, params->key);
if (ipcp == NULL) {
/* key not used */
@@ -403,7 +426,7 @@
}
ipc_unlock(ipcp);
}
- up_write(&ids->rw_mutex);
+ up_write(&ids->rwsem);
return err;
}
@@ -414,7 +437,7 @@
* @ids: IPC identifier set
* @ipcp: ipc perm structure containing the identifier to remove
*
- * ipc_ids.rw_mutex (as a writer) and the spinlock for this ID are held
+ * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
* before this function is called, and remain locked on the exit.
*/
@@ -466,13 +489,6 @@
kfree(ptr);
}
-struct ipc_rcu {
- struct rcu_head rcu;
- atomic_t refcount;
- /* "void *" makes sure alignment of following data is sane. */
- void *data[0];
-};
-
/**
* ipc_rcu_alloc - allocate ipc and rcu space
* @size: size desired
@@ -489,35 +505,34 @@
if (unlikely(!out))
return NULL;
atomic_set(&out->refcount, 1);
- return out->data;
+ return out + 1;
}
int ipc_rcu_getref(void *ptr)
{
- return atomic_inc_not_zero(&container_of(ptr, struct ipc_rcu, data)->refcount);
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
+
+ return atomic_inc_not_zero(&p->refcount);
}
-/**
- * ipc_schedule_free - free ipc + rcu space
- * @head: RCU callback structure for queued work
- */
-static void ipc_schedule_free(struct rcu_head *head)
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
{
- vfree(container_of(head, struct ipc_rcu, rcu));
-}
-
-void ipc_rcu_putref(void *ptr)
-{
- struct ipc_rcu *p = container_of(ptr, struct ipc_rcu, data);
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
if (!atomic_dec_and_test(&p->refcount))
return;
- if (is_vmalloc_addr(ptr)) {
- call_rcu(&p->rcu, ipc_schedule_free);
- } else {
- kfree_rcu(p, rcu);
- }
+ call_rcu(&p->rcu, func);
+}
+
+void ipc_rcu_free(struct rcu_head *head)
+{
+ struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+
+ if (is_vmalloc_addr(p))
+ vfree(p);
+ else
+ kfree(p);
}
/**
@@ -622,7 +637,7 @@
}
/**
- * ipc_lock - Lock an ipc structure without rw_mutex held
+ * ipc_lock - Lock an ipc structure without rwsem held
* @ids: IPC identifier set
* @id: ipc id to look for
*
@@ -678,22 +693,6 @@
return out;
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
-{
- struct kern_ipc_perm *out;
-
- out = ipc_lock(ids, id);
- if (IS_ERR(out))
- return out;
-
- if (ipc_checkid(out, id)) {
- ipc_unlock(out);
- return ERR_PTR(-EIDRM);
- }
-
- return out;
-}
-
/**
* ipcget - Common sys_*get() code
* @ns : namsepace
@@ -734,7 +733,7 @@
}
/**
- * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
* @ns: the ipc namespace
* @ids: the table of ids where to look for the ipc
* @id: the id of the ipc to retrieve
@@ -747,39 +746,22 @@
* It must be called without any lock held and
* - retrieves the ipc with the given id in the given table.
* - performs some audit and permission check, depending on the given cmd
- * - returns the ipc with both ipc and rw_mutex locks held in case of success
- * or an err-code without any lock held otherwise.
+ * - returns a pointer to the ipc object or otherwise, the corresponding error.
+ *
+ * Call holding the both the rwsem and the rcu read lock.
*/
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
-{
- struct kern_ipc_perm *ipcp;
-
- ipcp = ipcctl_pre_down_nolock(ns, ids, id, cmd, perm, extra_perm);
- if (IS_ERR(ipcp))
- goto out;
-
- spin_lock(&ipcp->lock);
-out:
- return ipcp;
-}
-
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm)
+ struct ipc_ids *ids, int id, int cmd,
+ struct ipc64_perm *perm, int extra_perm)
{
kuid_t euid;
int err = -EPERM;
struct kern_ipc_perm *ipcp;
- down_write(&ids->rw_mutex);
- rcu_read_lock();
-
ipcp = ipc_obtain_object_check(ids, id);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- goto out_up;
+ goto err;
}
audit_ipc_obj(ipcp);
@@ -790,16 +772,8 @@
euid = current_euid();
if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) ||
ns_capable(ns->user_ns, CAP_SYS_ADMIN))
- return ipcp;
-
-out_up:
- /*
- * Unsuccessful lookup, unlock and return
- * the corresponding error.
- */
- rcu_read_unlock();
- up_write(&ids->rw_mutex);
-
+ return ipcp; /* successful lookup */
+err:
return ERR_PTR(err);
}
@@ -856,7 +830,8 @@
ipc = idr_find(&ids->ipcs_idr, pos);
if (ipc != NULL) {
*new_pos = pos + 1;
- ipc_lock_by_ptr(ipc);
+ rcu_read_lock();
+ ipc_lock_object(ipc);
return ipc;
}
}
@@ -894,7 +869,7 @@
* Take the lock - this will be released by the corresponding
* call to stop().
*/
- down_read(&ids->rw_mutex);
+ down_read(&ids->rwsem);
/* pos < 0 is invalid */
if (*pos < 0)
@@ -921,7 +896,7 @@
ids = &iter->ns->ids[iface->ids];
/* Release the lock we took in start() */
- up_read(&ids->rw_mutex);
+ up_read(&ids->rwsem);
}
static int sysvipc_proc_show(struct seq_file *s, void *it)
diff --git a/ipc/util.h b/ipc/util.h
index 2b0bdd5..59d78aa 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -47,6 +47,13 @@
static inline void shm_exit_ns(struct ipc_namespace *ns) { }
#endif
+struct ipc_rcu {
+ struct rcu_head rcu;
+ atomic_t refcount;
+} ____cacheline_aligned_in_smp;
+
+#define ipc_rcu_to_struct(p) ((void *)(p+1))
+
/*
* Structure that holds the parameters needed by the ipc operations
* (see after)
@@ -94,10 +101,10 @@
#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
-/* must be called with ids->rw_mutex acquired for writing */
+/* must be called with ids->rwsem acquired for writing */
int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
-/* must be called with ids->rw_mutex acquired for reading */
+/* must be called with ids->rwsem acquired for reading */
int ipc_get_maxid(struct ipc_ids *);
/* must be called with both locks acquired. */
@@ -120,7 +127,8 @@
*/
void* ipc_rcu_alloc(int size);
int ipc_rcu_getref(void *ptr);
-void ipc_rcu_putref(void *ptr);
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *head);
struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
@@ -131,9 +139,6 @@
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
struct ipc64_perm *perm, int extra_perm);
-struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
- struct ipc_ids *ids, int id, int cmd,
- struct ipc64_perm *perm, int extra_perm);
#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
/* On IA-64, we always use the "64-bit version" of the IPC structures. */
@@ -143,9 +148,9 @@
#endif
extern void free_msg(struct msg_msg *msg);
-extern struct msg_msg *load_msg(const void __user *src, int len);
+extern struct msg_msg *load_msg(const void __user *src, size_t len);
extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
-extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
extern void recompute_msgmni(struct ipc_namespace *);
@@ -159,24 +164,27 @@
return uid / SEQ_MULTIPLIER != ipcp->seq;
}
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
-{
- rcu_read_lock();
- spin_lock(&perm->lock);
-}
-
-static inline void ipc_unlock(struct kern_ipc_perm *perm)
-{
- spin_unlock(&perm->lock);
- rcu_read_unlock();
-}
-
static inline void ipc_lock_object(struct kern_ipc_perm *perm)
{
spin_lock(&perm->lock);
}
-struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
+{
+ spin_unlock(&perm->lock);
+}
+
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
+{
+ assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+ ipc_unlock_object(perm);
+ rcu_read_unlock();
+}
+
struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
struct ipc_ops *ops, struct ipc_params *params);
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 44511d1..e4d3053 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,6 +220,9 @@
endif
+config ARCH_SUPPORTS_ATOMIC_RMW
+ bool
+
config MUTEX_SPIN_ON_OWNER
def_bool y
- depends on SMP && !DEBUG_MUTEXES
+ depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
diff --git a/kernel/audit.c b/kernel/audit.c
index 91e53d0..4dd7529 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -103,7 +103,8 @@
/* Number of outstanding audit_buffers allowed. */
static int audit_backlog_limit = 64;
-static int audit_backlog_wait_time = 60 * HZ;
+#define AUDIT_BACKLOG_WAIT_TIME (60 * HZ)
+static int audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
static int audit_backlog_wait_overflow = 0;
/* The identity of the user shutting down the audit system. */
@@ -592,13 +593,13 @@
case AUDIT_TTY_SET:
case AUDIT_TRIM:
case AUDIT_MAKE_EQUIV:
- if (!capable(CAP_AUDIT_CONTROL))
+ if (!netlink_capable(skb, CAP_AUDIT_CONTROL))
err = -EPERM;
break;
case AUDIT_USER:
case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG:
case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
- if (!capable(CAP_AUDIT_WRITE))
+ if (!netlink_capable(skb, CAP_AUDIT_WRITE))
err = -EPERM;
break;
default: /* bad msg */
@@ -613,7 +614,7 @@
int rc = 0;
uid_t uid = from_kuid(&init_user_ns, current_uid());
- if (!audit_enabled) {
+ if (!audit_enabled && msg_type != AUDIT_USER_AVC) {
*ab = NULL;
return rc;
}
@@ -659,6 +660,7 @@
switch (msg_type) {
case AUDIT_GET:
+ status_set.mask = 0;
status_set.enabled = audit_enabled;
status_set.failure = audit_failure;
status_set.pid = audit_pid;
@@ -670,7 +672,7 @@
&status_set, sizeof(status_set));
break;
case AUDIT_SET:
- if (nlh->nlmsg_len < sizeof(struct audit_status))
+ if (nlmsg_len(nlh) < sizeof(struct audit_status))
return -EINVAL;
status_get = (struct audit_status *)data;
if (status_get->mask & AUDIT_STATUS_ENABLED) {
@@ -832,7 +834,7 @@
memset(&s, 0, sizeof(s));
/* guard against past and future API changes */
- memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len));
+ memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh)));
if ((s.enabled != 0 && s.enabled != 1) ||
(s.log_passwd != 0 && s.log_passwd != 1))
return -EINVAL;
@@ -1117,9 +1119,10 @@
sleep_time = timeout_start + audit_backlog_wait_time -
jiffies;
- if ((long)sleep_time > 0)
+ if ((long)sleep_time > 0) {
wait_for_auditd(sleep_time);
- continue;
+ continue;
+ }
}
if (audit_rate_check() && printk_ratelimit())
printk(KERN_WARNING
@@ -1133,6 +1136,8 @@
return NULL;
}
+ audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME;
+
ab = audit_buffer_alloc(ctx, gfp_mask, type);
if (!ab) {
audit_log_lost("out of memory in audit_log_start");
@@ -1407,7 +1412,7 @@
audit_log_format(ab, " %s=", prefix);
CAP_FOR_EACH_U32(i) {
audit_log_format(ab, "%08x",
- cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]);
+ cap->cap[CAP_LAST_U32 - i]);
}
}
@@ -1535,6 +1540,26 @@
}
}
+ /* log the audit_names record type */
+ audit_log_format(ab, " nametype=");
+ switch(n->type) {
+ case AUDIT_TYPE_NORMAL:
+ audit_log_format(ab, "NORMAL");
+ break;
+ case AUDIT_TYPE_PARENT:
+ audit_log_format(ab, "PARENT");
+ break;
+ case AUDIT_TYPE_CHILD_DELETE:
+ audit_log_format(ab, "DELETE");
+ break;
+ case AUDIT_TYPE_CHILD_CREATE:
+ audit_log_format(ab, "CREATE");
+ break;
+ default:
+ audit_log_format(ab, "UNKNOWN");
+ break;
+ }
+
audit_log_fcaps(ab, n);
audit_log_end(ab);
}
diff --git a/kernel/audit.h b/kernel/audit.h
index 1c95131..123c9b7 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -85,6 +85,7 @@
struct filename *name;
int name_len; /* number of chars to log */
+ bool hidden; /* don't log this record */
bool name_put; /* call __putname()? */
unsigned long ino;
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 43c307d..00c4459 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -154,6 +154,7 @@
chunk->owners[i].index = i;
}
fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+ chunk->mark.mask = FS_IN_IGNORED;
return chunk;
}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 6bd4a90..4d230ea 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -423,7 +423,7 @@
f->lsm_rule = NULL;
/* Support legacy tests for a valid loginuid */
- if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) {
+ if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
f->type = AUDIT_LOGINUID_SET;
f->val = 0;
}
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 3c8a601..03a3af8 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -733,6 +733,22 @@
return AUDIT_BUILD_CONTEXT;
}
+static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
+{
+ int word, bit;
+
+ if (val > 0xffffffff)
+ return false;
+
+ word = AUDIT_WORD(val);
+ if (word >= AUDIT_BITMASK_SIZE)
+ return false;
+
+ bit = AUDIT_BIT(val);
+
+ return rule->mask[word] & bit;
+}
+
/* At syscall entry and exit time, this filter is called if the
* audit_state is not low enough that auditing cannot take place, but is
* also not high enough that we already know we have to write an audit
@@ -750,11 +766,8 @@
rcu_read_lock();
if (!list_empty(list)) {
- int word = AUDIT_WORD(ctx->major);
- int bit = AUDIT_BIT(ctx->major);
-
list_for_each_entry_rcu(e, list, list) {
- if ((e->rule.mask[word] & bit) == bit &&
+ if (audit_in_mask(&e->rule, ctx->major) &&
audit_filter_rules(tsk, &e->rule, ctx, NULL,
&state, false)) {
rcu_read_unlock();
@@ -774,20 +787,16 @@
static int audit_filter_inode_name(struct task_struct *tsk,
struct audit_names *n,
struct audit_context *ctx) {
- int word, bit;
int h = audit_hash_ino((u32)n->ino);
struct list_head *list = &audit_inode_hash[h];
struct audit_entry *e;
enum audit_state state;
- word = AUDIT_WORD(ctx->major);
- bit = AUDIT_BIT(ctx->major);
-
if (list_empty(list))
return 0;
list_for_each_entry_rcu(e, list, list) {
- if ((e->rule.mask[word] & bit) == bit &&
+ if (audit_in_mask(&e->rule, ctx->major) &&
audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
ctx->current_state = state;
return 1;
@@ -1399,8 +1408,11 @@
}
i = 0;
- list_for_each_entry(n, &context->names_list, list)
+ list_for_each_entry(n, &context->names_list, list) {
+ if (n->hidden)
+ continue;
audit_log_name(context, n, NULL, i++, &call_panic);
+ }
/* Send end of event record to help user space know we are finished */
ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
@@ -1769,14 +1781,15 @@
* __audit_inode - store the inode and device from a lookup
* @name: name being audited
* @dentry: dentry being audited
- * @parent: does this dentry represent the parent?
+ * @flags: attributes for this particular entry
*/
void __audit_inode(struct filename *name, const struct dentry *dentry,
- unsigned int parent)
+ unsigned int flags)
{
struct audit_context *context = current->audit_context;
const struct inode *inode = dentry->d_inode;
struct audit_names *n;
+ bool parent = flags & AUDIT_INODE_PARENT;
if (!context->in_syscall)
return;
@@ -1831,6 +1844,8 @@
if (parent) {
n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_PARENT;
+ if (flags & AUDIT_INODE_HIDDEN)
+ n->hidden = true;
} else {
n->name_len = AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_NORMAL;
diff --git a/kernel/capability.c b/kernel/capability.c
index f6c2ce5..1339806 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -268,6 +268,10 @@
i++;
}
+ effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
new = prepare_creds();
if (!new)
return -ENOMEM;
@@ -445,22 +449,18 @@
}
/**
- * inode_capable - Check superior capability over inode
+ * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
* @inode: The inode in question
* @cap: The capability in question
*
- * Return true if the current task has the given superior capability
- * targeted at it's own user namespace and that the given inode is owned
- * by the current user namespace or a child namespace.
- *
- * Currently we check to see if an inode is owned by the current
- * user namespace by seeing if the inode's owner maps into the
- * current user namespace.
- *
+ * Return true if the current task has the given capability targeted at
+ * its own user namespace and that the given inode's uid and gid are
+ * mapped into the current user namespace.
*/
-bool inode_capable(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
- return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+ return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
+ kgid_has_mapping(ns, inode->i_gid);
}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a7c9e6d..ef13060 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -92,6 +92,14 @@
static DEFINE_MUTEX(cgroup_root_mutex);
/*
+ * cgroup destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions. Use a separate workqueue so that cgroup
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_destroy_wq;
+
+/*
* Generate an array of cgroup subsystem pointers. At boot time, this is
* populated with the built in subsystems, and modular subsystems are
* registered after that. The mutable section of this array is protected by
@@ -873,7 +881,7 @@
{
struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
- schedule_work(&cgrp->free_work);
+ queue_work(cgroup_destroy_wq, &cgrp->free_work);
}
static void cgroup_diput(struct dentry *dentry, struct inode *inode)
@@ -976,7 +984,7 @@
parent = dentry->d_parent;
spin_lock(&parent->d_lock);
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- list_del_init(&dentry->d_u.d_child);
+ list_del_init(&dentry->d_child);
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
remove_dir(dentry);
@@ -1995,7 +2003,7 @@
/* @tsk either already exited or can't exit until the end */
if (tsk->flags & PF_EXITING)
- continue;
+ goto next;
/* as per above, nr_threads may decrease, but not increase. */
BUG_ON(i >= group_size);
@@ -2003,7 +2011,7 @@
ent.cgrp = task_cgroup_from_root(tsk, root);
/* nothing to do if this task is already in the cgroup */
if (ent.cgrp == cgrp)
- continue;
+ goto next;
/*
* saying GFP_ATOMIC has no effect here because we did prealloc
* earlier, but it's good form to communicate our expectations.
@@ -2011,7 +2019,7 @@
retval = flex_array_put(group, i, &ent, GFP_ATOMIC);
BUG_ON(retval != 0);
i++;
-
+ next:
if (!threadgroup)
break;
} while_each_thread(leader, tsk);
@@ -2769,13 +2777,17 @@
{
LIST_HEAD(pending);
struct cgroup *cgrp, *n;
+ struct super_block *sb = ss->root->sb;
/* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
- if (cfts && ss->root != &rootnode) {
+ if (cfts && ss->root != &rootnode &&
+ atomic_inc_not_zero(&sb->s_active)) {
list_for_each_entry(cgrp, &ss->root->allcg_list, allcg_node) {
dget(cgrp->dentry);
list_add_tail(&cgrp->cft_q_node, &pending);
}
+ } else {
+ sb = NULL;
}
mutex_unlock(&cgroup_mutex);
@@ -2798,6 +2810,9 @@
dput(cgrp->dentry);
}
+ if (sb)
+ deactivate_super(sb);
+
mutex_unlock(&cgroup_cft_mutex);
}
@@ -3727,6 +3742,23 @@
}
/*
+ * When dput() is called asynchronously, if umount has been done and
+ * then deactivate_super() in cgroup_free_fn() kills the superblock,
+ * there's a small window that vfs will see the root dentry with non-zero
+ * refcnt and trigger BUG().
+ *
+ * That's why we hold a reference before dput() and drop it right after.
+ */
+static void cgroup_dput(struct cgroup *cgrp)
+{
+ struct super_block *sb = cgrp->root->sb;
+
+ atomic_inc(&sb->s_active);
+ dput(cgrp->dentry);
+ deactivate_super(sb);
+}
+
+/*
* Unregister event and free resources.
*
* Gets called from workqueue.
@@ -3746,7 +3778,7 @@
eventfd_ctx_put(event->eventfd);
kfree(event);
- dput(cgrp->dentry);
+ cgroup_dput(cgrp);
}
/*
@@ -4031,12 +4063,8 @@
{
struct cgroup_subsys_state *css =
container_of(work, struct cgroup_subsys_state, dput_work);
- struct dentry *dentry = css->cgroup->dentry;
- struct super_block *sb = dentry->d_sb;
- atomic_inc(&sb->s_active);
- dput(dentry);
- deactivate_super(sb);
+ cgroup_dput(css->cgroup);
}
static void init_cgroup_css(struct cgroup_subsys_state *css,
@@ -4666,6 +4694,22 @@
return err;
}
+static int __init cgroup_wq_init(void)
+{
+ /*
+ * There isn't much point in executing destruction path in
+ * parallel. Good chunk is serialized with cgroup_mutex anyway.
+ * Use 1 for @max_active.
+ *
+ * We would prefer to do this in cgroup_init() above, but that
+ * is called before init_workqueues(): so leave this until after.
+ */
+ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+ BUG_ON(!cgroup_destroy_wq);
+ return 0;
+}
+core_initcall(cgroup_wq_init);
+
/*
* proc_cgroup_show()
* - Print task's cgroup paths into seq_file, one line for each hierarchy
@@ -4976,7 +5020,7 @@
v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));
if (v == 0)
- schedule_work(&css->dput_work);
+ queue_work(cgroup_destroy_wq, &css->dput_work);
}
EXPORT_SYMBOL_GPL(__css_put);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 198a388..5fbcbdd 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -27,18 +27,23 @@
static DEFINE_MUTEX(cpu_add_remove_lock);
/*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_begin);
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL(cpu_notifier_register_done);
static RAW_NOTIFIER_HEAD(cpu_chain);
@@ -169,6 +174,11 @@
return ret;
}
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+ return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
int *nr_calls)
{
@@ -192,6 +202,7 @@
BUG_ON(cpu_notify(val, v));
}
EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
void __ref unregister_cpu_notifier(struct notifier_block *nb)
{
@@ -201,6 +212,12 @@
}
EXPORT_SYMBOL(unregister_cpu_notifier);
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+ raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
@@ -698,10 +715,12 @@
void set_cpu_online(unsigned int cpu, bool online)
{
- if (online)
+ if (online) {
cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
- else
+ cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+ } else {
cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+ }
}
void set_cpu_active(unsigned int cpu, bool active)
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index e695c0a..c261409 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -44,7 +44,7 @@
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
local_irq_enable();
- while (!need_resched())
+ while (!tif_need_resched())
cpu_relax();
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
rcu_idle_exit();
@@ -92,8 +92,7 @@
if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
cpu_idle_poll();
} else {
- current_clr_polling();
- if (!need_resched()) {
+ if (!current_clr_polling_and_test()) {
stop_critical_timings();
rcu_idle_enter();
arch_cpu_idle();
@@ -103,7 +102,7 @@
} else {
local_irq_enable();
}
- current_set_polling();
+ __current_set_polling();
}
arch_cpu_idle_exit();
}
@@ -129,7 +128,7 @@
*/
boot_init_stack_canary();
#endif
- current_set_polling();
+ __current_set_polling();
arch_cpu_idle_prepare();
cpu_idle_loop();
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 64b3f79..067750b 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -984,8 +984,10 @@
need_loop = task_has_mempolicy(tsk) ||
!nodes_intersects(*newmems, tsk->mems_allowed);
- if (need_loop)
+ if (need_loop) {
+ local_irq_disable();
write_seqcount_begin(&tsk->mems_allowed_seq);
+ }
nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -993,8 +995,10 @@
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
tsk->mems_allowed = *newmems;
- if (need_loop)
+ if (need_loop) {
write_seqcount_end(&tsk->mems_allowed_seq);
+ local_irq_enable();
+ }
task_unlock(tsk);
}
@@ -1149,7 +1153,13 @@
int current_cpuset_is_being_rebound(void)
{
- return task_cs(current) == cpuset_being_rebound;
+ int ret;
+
+ rcu_read_lock();
+ ret = task_cs(current) == cpuset_being_rebound;
+ rcu_read_unlock();
+
+ return ret;
}
static int update_relax_domain_level(struct cpuset *cs, s64 val)
@@ -1502,11 +1512,13 @@
{
struct cpuset *cs = cgroup_cs(cgrp);
cpuset_filetype_t type = cft->private;
- int retval = -ENODEV;
+ int retval = 0;
mutex_lock(&cpuset_mutex);
- if (!is_cpuset_online(cs))
+ if (!is_cpuset_online(cs)) {
+ retval = -ENODEV;
goto out_unlock;
+ }
switch (type) {
case FILE_CPU_EXCLUSIVE:
@@ -2416,9 +2428,9 @@
task_lock(current);
cs = nearest_hardwall_ancestor(task_cs(current));
+ allowed = node_isset(node, cs->mems_allowed);
task_unlock(current);
- allowed = node_isset(node, cs->mems_allowed);
mutex_unlock(&callback_mutex);
return allowed;
}
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 00eb8f7..545241d 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -2532,7 +2532,7 @@
#define K(x) ((x) << (PAGE_SHIFT - 10))
kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n"
"Buffers: %8lu kB\n",
- val.totalram, val.freeram, val.bufferram);
+ K(val.totalram), K(val.freeram), K(val.bufferram));
return 0;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b391907..7daf52c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -39,6 +39,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/mm_types.h>
#include <linux/cgroup.h>
+#include <linux/compat.h>
#include "internal.h"
@@ -165,25 +166,109 @@
/*
* max perf event sample rate
*/
-#define DEFAULT_MAX_SAMPLE_RATE 100000
-int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
-static int max_samples_per_tick __read_mostly =
- DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+#define DEFAULT_MAX_SAMPLE_RATE 100000
+#define DEFAULT_SAMPLE_PERIOD_NS (NSEC_PER_SEC / DEFAULT_MAX_SAMPLE_RATE)
+#define DEFAULT_CPU_TIME_MAX_PERCENT 25
+
+int sysctl_perf_event_sample_rate __read_mostly = DEFAULT_MAX_SAMPLE_RATE;
+
+static int max_samples_per_tick __read_mostly = DIV_ROUND_UP(DEFAULT_MAX_SAMPLE_RATE, HZ);
+static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS;
+
+static atomic_t perf_sample_allowed_ns __read_mostly =
+ ATOMIC_INIT( DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100);
+
+void update_perf_cpu_limits(void)
+{
+ u64 tmp = perf_sample_period_ns;
+
+ tmp *= sysctl_perf_cpu_time_max_percent;
+ do_div(tmp, 100);
+ atomic_set(&perf_sample_allowed_ns, tmp);
+}
int perf_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+ if (ret || !write)
+ return ret;
+
+ max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+ perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
+ update_perf_cpu_limits();
+
+ return 0;
+}
+
+int sysctl_perf_cpu_time_max_percent __read_mostly = DEFAULT_CPU_TIME_MAX_PERCENT;
+
+int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
int ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
- max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
+ update_perf_cpu_limits();
return 0;
}
+/*
+ * perf samples are done in some very critical code paths (NMIs).
+ * If they take too much CPU time, the system can lock up and not
+ * get any real work done. This will drop the sample rate when
+ * we detect that events are taking too long.
+ */
+#define NR_ACCUMULATED_SAMPLES 128
+DEFINE_PER_CPU(u64, running_sample_length);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
+ u64 avg_local_sample_len;
+ u64 local_samples_len;
+
+ if (atomic_read(&perf_sample_allowed_ns) == 0)
+ return;
+
+ /* decay the counter by 1 average sample */
+ local_samples_len = __get_cpu_var(running_sample_length);
+ local_samples_len -= local_samples_len/NR_ACCUMULATED_SAMPLES;
+ local_samples_len += sample_len_ns;
+ __get_cpu_var(running_sample_length) = local_samples_len;
+
+ /*
+ * note: this will be biased artifically low until we have
+ * seen NR_ACCUMULATED_SAMPLES. Doing it this way keeps us
+ * from having to maintain a count.
+ */
+ avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+ if (avg_local_sample_len <= atomic_read(&perf_sample_allowed_ns))
+ return;
+
+ if (max_samples_per_tick <= 1)
+ return;
+
+ max_samples_per_tick = DIV_ROUND_UP(max_samples_per_tick, 2);
+ sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
+ perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
+
+ printk_ratelimited(KERN_WARNING
+ "perf samples too long (%lld > %d), lowering "
+ "kernel.perf_event_max_sample_rate to %d\n",
+ avg_local_sample_len,
+ atomic_read(&perf_sample_allowed_ns),
+ sysctl_perf_event_sample_rate);
+
+ update_perf_cpu_limits();
+}
+
static atomic64_t perf_event_id;
static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
@@ -761,8 +846,18 @@
{
struct perf_event_context *ctx;
- rcu_read_lock();
retry:
+ /*
+ * One of the few rules of preemptible RCU is that one cannot do
+ * rcu_read_unlock() while holding a scheduler (or nested) lock when
+ * part of the read side critical section was preemptible -- see
+ * rcu_read_unlock_special().
+ *
+ * Since ctx->lock nests under rq->lock we must ensure the entire read
+ * side critical section is non-preemptible.
+ */
+ preempt_disable();
+ rcu_read_lock();
ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
if (ctx) {
/*
@@ -778,6 +873,8 @@
raw_spin_lock_irqsave(&ctx->lock, *flags);
if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+ rcu_read_unlock();
+ preempt_enable();
goto retry;
}
@@ -787,6 +884,7 @@
}
}
rcu_read_unlock();
+ preempt_enable();
return ctx;
}
@@ -1224,6 +1322,11 @@
cpuctx->exclusive = 0;
}
+struct remove_event {
+ struct perf_event *event;
+ bool detach_group;
+};
+
/*
* Cross CPU call to remove a performance event
*
@@ -1232,12 +1335,15 @@
*/
static int __perf_remove_from_context(void *info)
{
- struct perf_event *event = info;
+ struct remove_event *re = info;
+ struct perf_event *event = re->event;
struct perf_event_context *ctx = event->ctx;
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
raw_spin_lock(&ctx->lock);
event_sched_out(event, cpuctx, ctx);
+ if (re->detach_group)
+ perf_group_detach(event);
list_del_event(event, ctx);
if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
ctx->is_active = 0;
@@ -1262,10 +1368,14 @@
* When called from perf_event_exit_task, it's OK because the
* context has been detached from its task.
*/
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
+ struct remove_event re = {
+ .event = event,
+ .detach_group = detach_group,
+ };
lockdep_assert_held(&ctx->mutex);
@@ -1274,12 +1384,12 @@
* Per cpu events are removed via an smp call and
* the removal is always successful.
*/
- cpu_function_call(event->cpu, __perf_remove_from_context, event);
+ cpu_function_call(event->cpu, __perf_remove_from_context, &re);
return;
}
retry:
- if (!task_function_call(task, __perf_remove_from_context, event))
+ if (!task_function_call(task, __perf_remove_from_context, &re))
return;
raw_spin_lock_irq(&ctx->lock);
@@ -1289,6 +1399,11 @@
*/
if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
goto retry;
}
@@ -1296,6 +1411,8 @@
* Since the task isn't running, its safe to remove the event, us
* holding the ctx->lock ensures the task won't get scheduled in.
*/
+ if (detach_group)
+ perf_group_detach(event);
list_del_event(event, ctx);
raw_spin_unlock_irq(&ctx->lock);
}
@@ -1718,6 +1835,11 @@
*/
if (ctx->is_active) {
raw_spin_unlock_irq(&ctx->lock);
+ /*
+ * Reload the task pointer, it might have been changed by
+ * a concurrent perf_event_context_sched_out().
+ */
+ task = ctx->task;
goto retry;
}
@@ -1761,7 +1883,16 @@
struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
int err;
- if (WARN_ON_ONCE(!ctx->is_active))
+ /*
+ * There's a time window between 'ctx->is_active' check
+ * in perf_event_enable function and this place having:
+ * - IRQs on
+ * - ctx->lock unlocked
+ *
+ * where the task could be killed and 'ctx' deactivated
+ * by perf_event_exit_task.
+ */
+ if (!ctx->is_active)
return -EINVAL;
raw_spin_lock(&ctx->lock);
@@ -1994,9 +2125,6 @@
perf_event_update_userpage(next_event);
}
-#define list_next_entry(pos, member) \
- list_entry(pos->member.next, typeof(*pos), member)
-
static void perf_event_sync_stat(struct perf_event_context *ctx,
struct perf_event_context *next_ctx)
{
@@ -2996,10 +3124,7 @@
* to trigger the AB-BA case.
*/
mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
- raw_spin_lock_irq(&ctx->lock);
- perf_group_detach(event);
- raw_spin_unlock_irq(&ctx->lock);
- perf_remove_from_context(event);
+ perf_remove_from_context(event, true);
mutex_unlock(&ctx->mutex);
free_event(event);
@@ -3366,6 +3491,25 @@
return 0;
}
+#ifdef CONFIG_COMPAT
+static long perf_compat_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ switch (_IOC_NR(cmd)) {
+ case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
+ /* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
+ if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
+ cmd &= ~IOCSIZE_MASK;
+ cmd |= sizeof(void *) << IOCSIZE_SHIFT;
+ }
+ break;
+ }
+ return perf_ioctl(file, cmd, arg);
+}
+#else
+# define perf_compat_ioctl NULL
+#endif
+
int perf_event_task_enable(void)
{
struct perf_event *event;
@@ -3837,7 +3981,7 @@
.read = perf_read,
.poll = perf_poll,
.unlocked_ioctl = perf_ioctl,
- .compat_ioctl = perf_ioctl,
+ .compat_ioctl = perf_compat_ioctl,
.mmap = perf_mmap,
.fasync = perf_fasync,
};
@@ -3863,6 +4007,13 @@
{
struct perf_event *event = container_of(entry,
struct perf_event, pending);
+ int rctx;
+
+ rctx = perf_swevent_get_recursion_context();
+ /*
+ * If we 'fail' here, that's OK, it means recursion is already disabled
+ * and we won't recurse 'further'.
+ */
if (event->pending_disable) {
event->pending_disable = 0;
@@ -3873,6 +4024,9 @@
event->pending_wakeup = 0;
perf_event_wakeup(event);
}
+
+ if (rctx >= 0)
+ perf_swevent_put_recursion_context(rctx);
}
/*
@@ -5025,6 +5179,9 @@
/* Recursion avoidance in each contexts */
int recursion[PERF_NR_CONTEXTS];
+
+ /* Keeps track of cpu being initialized/exited */
+ bool online;
};
static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5271,8 +5428,14 @@
hwc->state = !(flags & PERF_EF_START);
head = find_swevent_head(swhash, event);
- if (WARN_ON_ONCE(!head))
+ if (!head) {
+ /*
+ * We can race with cpu hotplug code. Do not
+ * WARN if the cpu just got unplugged.
+ */
+ WARN_ON_ONCE(swhash->online);
return -EINVAL;
+ }
hlist_add_head_rcu(&event->hlist_entry, head);
@@ -6562,6 +6725,9 @@
if (attr.freq) {
if (attr.sample_freq > sysctl_perf_event_sample_rate)
return -EINVAL;
+ } else {
+ if (attr.sample_period & (1ULL << 63))
+ return -EINVAL;
}
/*
@@ -6708,7 +6874,7 @@
struct perf_event_context *gctx = group_leader->ctx;
mutex_lock(&gctx->mutex);
- perf_remove_from_context(group_leader);
+ perf_remove_from_context(group_leader, false);
/*
* Removing from the context ends up with disabled
@@ -6718,7 +6884,7 @@
perf_event__state_init(group_leader);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_remove_from_context(sibling);
+ perf_remove_from_context(sibling, false);
perf_event__state_init(sibling);
put_ctx(gctx);
}
@@ -6731,11 +6897,11 @@
if (move_group) {
synchronize_rcu();
- perf_install_in_context(ctx, group_leader, event->cpu);
+ perf_install_in_context(ctx, group_leader, group_leader->cpu);
get_ctx(ctx);
list_for_each_entry(sibling, &group_leader->sibling_list,
group_entry) {
- perf_install_in_context(ctx, sibling, event->cpu);
+ perf_install_in_context(ctx, sibling, sibling->cpu);
get_ctx(ctx);
}
}
@@ -6848,7 +7014,7 @@
mutex_lock(&src_ctx->mutex);
list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
event_entry) {
- perf_remove_from_context(event);
+ perf_remove_from_context(event, false);
put_ctx(src_ctx);
list_add(&event->event_entry, &events);
}
@@ -6908,13 +7074,7 @@
struct perf_event_context *child_ctx,
struct task_struct *child)
{
- if (child_event->parent) {
- raw_spin_lock_irq(&child_ctx->lock);
- perf_group_detach(child_event);
- raw_spin_unlock_irq(&child_ctx->lock);
- }
-
- perf_remove_from_context(child_event);
+ perf_remove_from_context(child_event, !!child_event->parent);
/*
* It can happen that the parent exits first, and has events
@@ -7228,7 +7388,7 @@
* child.
*/
- child_ctx = alloc_perf_context(event->pmu, child);
+ child_ctx = alloc_perf_context(parent_ctx->pmu, child);
if (!child_ctx)
return -ENOMEM;
@@ -7352,8 +7512,10 @@
for_each_task_context_nr(ctxn) {
ret = perf_event_init_context(child, ctxn);
- if (ret)
+ if (ret) {
+ perf_event_free_task(child);
return ret;
+ }
}
return 0;
@@ -7376,6 +7538,7 @@
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
mutex_lock(&swhash->hlist_mutex);
+ swhash->online = true;
if (swhash->hlist_refcount > 0) {
struct swevent_hlist *hlist;
@@ -7398,15 +7561,15 @@
static void __perf_event_exit_context(void *__info)
{
+ struct remove_event re = { .detach_group = false };
struct perf_event_context *ctx = __info;
- struct perf_event *event, *tmp;
perf_pmu_rotate_stop(ctx->pmu);
- list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry)
- __perf_remove_from_context(event);
- list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry)
- __perf_remove_from_context(event);
+ rcu_read_lock();
+ list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+ __perf_remove_from_context(&re);
+ rcu_read_unlock();
}
static void perf_event_exit_cpu_context(int cpu)
@@ -7430,11 +7593,12 @@
{
struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
+ perf_event_exit_cpu_context(cpu);
+
mutex_lock(&swhash->hlist_mutex);
+ swhash->online = false;
swevent_hlist_release(swhash);
mutex_unlock(&swhash->hlist_mutex);
-
- perf_event_exit_cpu_context(cpu);
}
#else
static inline void perf_event_exit_cpu(int cpu) { }
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index cd55144..9c2ddfb 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -87,10 +87,31 @@
goto out;
/*
- * Publish the known good head. Rely on the full barrier implied
- * by atomic_dec_and_test() order the rb->head read and this
- * write.
+ * Since the mmap() consumer (userspace) can run on a different CPU:
+ *
+ * kernel user
+ *
+ * READ ->data_tail READ ->data_head
+ * smp_mb() (A) smp_rmb() (C)
+ * WRITE $data READ $data
+ * smp_wmb() (B) smp_mb() (D)
+ * STORE ->data_head WRITE ->data_tail
+ *
+ * Where A pairs with D, and B pairs with C.
+ *
+ * I don't think A needs to be a full barrier because we won't in fact
+ * write data until we see the store from userspace. So we simply don't
+ * issue the data WRITE until we observe it. Be conservative for now.
+ *
+ * OTOH, D needs to be a full barrier since it separates the data READ
+ * from the tail WRITE.
+ *
+ * For B a WMB is sufficient since it separates two WRITEs, and for C
+ * an RMB is sufficient since it separates two READs.
+ *
+ * See perf_output_begin().
*/
+ smp_wmb();
rb->user_page->data_head = head;
/*
@@ -154,9 +175,11 @@
* Userspace could choose to issue a mb() before updating the
* tail pointer. So that all reads will be completed before the
* write is issued.
+ *
+ * See perf_output_put_handle().
*/
tail = ACCESS_ONCE(rb->user_page->data_tail);
- smp_rmb();
+ smp_mb();
offset = head = local_read(&rb->head);
head += size;
if (unlikely(!perf_output_space(rb, tail, offset, head)))
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index f356974..8176caf 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1511,7 +1511,6 @@
if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) {
utask->state = UTASK_SSTEP_TRAPPED;
set_tsk_thread_flag(t, TIF_UPROBE);
- set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
}
}
@@ -1682,12 +1681,10 @@
tmp = ri;
ri = ri->next;
kfree(tmp);
+ utask->depth--;
if (!chained)
break;
-
- utask->depth--;
-
BUG_ON(!ri);
}
diff --git a/kernel/exit.c b/kernel/exit.c
index 7bb73f9..717efbd 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@
__this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_group);
+ list_del_rcu(&p->thread_node);
}
/*
@@ -570,9 +571,6 @@
struct list_head *dead)
{
list_move_tail(&p->sibling, &p->real_parent->children);
-
- if (p->exit_state == EXIT_DEAD)
- return;
/*
* If this is a threaded reparent there is no need to
* notify anyone anything has happened.
@@ -580,9 +578,19 @@
if (same_thread_group(p->real_parent, father))
return;
- /* We don't want people slaying init. */
+ /*
+ * We don't want people slaying init.
+ *
+ * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
+ * can change ->exit_state to EXIT_ZOMBIE. If this is the final
+ * state, do_notify_parent() was already called and ->exit_signal
+ * doesn't matter.
+ */
p->exit_signal = SIGCHLD;
+ if (p->exit_state == EXIT_DEAD)
+ return;
+
/* If it has exited notify the new parent about this child's death. */
if (!p->ptrace &&
p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
@@ -794,6 +802,8 @@
exit_shm(tsk);
exit_files(tsk);
exit_fs(tsk);
+ if (group_dead)
+ disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
check_stack_usage();
@@ -809,13 +819,9 @@
cgroup_exit(tsk, 1);
- if (group_dead)
- disassociate_ctty(1);
-
module_put(task_thread_info(tsk)->exec_domain->module);
proc_exit_connector(tsk);
-
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
diff --git a/kernel/fork.c b/kernel/fork.c
index 987b28a..514dbc4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -544,6 +544,7 @@
mm->cached_hole_size = ~0UL;
mm_init_aio(mm);
mm_init_owner(mm, p);
+ clear_tlb_flush_pending(mm);
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
@@ -1044,6 +1045,11 @@
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
atomic_set(&sig->sigcnt, 1);
+
+ /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+ tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
@@ -1171,10 +1177,11 @@
return ERR_PTR(-EINVAL);
/*
- * If the new process will be in a different pid namespace
- * don't allow the creation of threads.
+ * If the new process will be in a different pid namespace don't
+ * allow it to share a thread group or signal handlers with the
+ * forking task.
*/
- if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
+ if ((clone_flags & (CLONE_SIGHAND | CLONE_NEWPID)) &&
(task_active_pid_ns(current) != current->nsproxy->pid_ns))
return ERR_PTR(-EINVAL);
@@ -1317,7 +1324,7 @@
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
if (retval)
- goto bad_fork_cleanup_policy;
+ goto bad_fork_cleanup_perf;
/* copy all the process information */
retval = copy_semundo(clone_flags, p);
if (retval)
@@ -1446,14 +1453,6 @@
goto bad_fork_free_pid;
}
- if (clone_flags & CLONE_THREAD) {
- current->signal->nr_threads++;
- atomic_inc(¤t->signal->live);
- atomic_inc(¤t->signal->sigcnt);
- p->group_leader = current->group_leader;
- list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
- }
-
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1470,6 +1469,15 @@
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
__this_cpu_inc(process_counts);
+ } else {
+ current->signal->nr_threads++;
+ atomic_inc(¤t->signal->live);
+ atomic_inc(¤t->signal->sigcnt);
+ p->group_leader = current->group_leader;
+ list_add_tail_rcu(&p->thread_group,
+ &p->group_leader->thread_group);
+ list_add_tail_rcu(&p->thread_node,
+ &p->signal->thread_head);
}
attach_pid(p, PIDTYPE_PID, pid);
nr_threads++;
@@ -1477,7 +1485,9 @@
total_forks++;
spin_unlock(¤t->sighand->siglock);
+ syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
+
proc_fork_connector(p);
cgroup_post_fork(p);
if (clone_flags & CLONE_THREAD)
@@ -1512,8 +1522,9 @@
exit_sem(p);
bad_fork_cleanup_audit:
audit_free(p);
-bad_fork_cleanup_policy:
+bad_fork_cleanup_perf:
perf_event_free_task(p);
+bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_cgroup:
@@ -1605,10 +1616,12 @@
*/
if (!IS_ERR(p)) {
struct completion vfork;
+ struct pid *pid;
trace_sched_process_fork(current, p);
- nr = task_pid_vnr(p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
@@ -1623,12 +1636,14 @@
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
- ptrace_event(trace, nr);
+ ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
- ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
} else {
nr = PTR_ERR(p);
}
@@ -1675,6 +1690,12 @@
int __user *, parent_tidptr,
int __user *, child_tidptr,
int, tls_val)
+#elif defined(CONFIG_CLONE_BACKWARDS3)
+SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
+ int, stack_size,
+ int __user *, parent_tidptr,
+ int __user *, child_tidptr,
+ int, tls_val)
#else
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c38893b..bd733f6 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -19,6 +19,12 @@
bool pm_freezing;
bool pm_nosig_freezing;
+/*
+ * Temporary export for the deadlock workaround in ata_scsi_hotplug().
+ * Remove once the hack becomes unnecessary.
+ */
+EXPORT_SYMBOL_GPL(pm_freezing);
+
/* protects freezing and frozen transitions */
static DEFINE_SPINLOCK(freezer_lock);
@@ -36,6 +42,9 @@
if (p->flags & PF_NOFREEZE)
return false;
+ if (test_thread_flag(TIF_MEMDIE))
+ return false;
+
if (pm_nosig_freezing || cgroup_freezing(p))
return true;
diff --git a/kernel/futex.c b/kernel/futex.c
index b26dcfc..625a4e6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -61,12 +61,15 @@
#include <linux/nsproxy.h>
#include <linux/ptrace.h>
#include <linux/sched/rt.h>
+#include <linux/hugetlb.h>
#include <asm/futex.h>
#include "rtmutex_common.h"
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
int __read_mostly futex_cmpxchg_enabled;
+#endif
#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
@@ -286,7 +289,7 @@
put_page(page);
/* serialize against __split_huge_page_splitting() */
local_irq_disable();
- if (likely(__get_user_pages_fast(address, 1, 1, &page) == 1)) {
+ if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) {
page_head = compound_head(page);
/*
* page_head is valid pointer but we must pin
@@ -365,7 +368,7 @@
} else {
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
key->shared.inode = page_head->mapping->host;
- key->shared.pgoff = page_head->index;
+ key->shared.pgoff = basepage_index(page);
}
get_futex_key_refs(key);
@@ -589,6 +592,55 @@
raw_spin_unlock_irq(&curr->pi_lock);
}
+/*
+ * We need to check the following states:
+ *
+ * Waiter | pi_state | pi->owner | uTID | uODIED | ?
+ *
+ * [1] NULL | --- | --- | 0 | 0/1 | Valid
+ * [2] NULL | --- | --- | >0 | 0/1 | Valid
+ *
+ * [3] Found | NULL | -- | Any | 0/1 | Invalid
+ *
+ * [4] Found | Found | NULL | 0 | 1 | Valid
+ * [5] Found | Found | NULL | >0 | 1 | Invalid
+ *
+ * [6] Found | Found | task | 0 | 1 | Valid
+ *
+ * [7] Found | Found | NULL | Any | 0 | Invalid
+ *
+ * [8] Found | Found | task | ==taskTID | 0/1 | Valid
+ * [9] Found | Found | task | 0 | 0 | Invalid
+ * [10] Found | Found | task | !=taskTID | 0/1 | Invalid
+ *
+ * [1] Indicates that the kernel can acquire the futex atomically. We
+ * came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *
+ * [2] Valid, if TID does not belong to a kernel thread. If no matching
+ * thread is found then it indicates that the owner TID has died.
+ *
+ * [3] Invalid. The waiter is queued on a non PI futex
+ *
+ * [4] Valid state after exit_robust_list(), which sets the user space
+ * value to FUTEX_WAITERS | FUTEX_OWNER_DIED.
+ *
+ * [5] The user space value got manipulated between exit_robust_list()
+ * and exit_pi_state_list()
+ *
+ * [6] Valid state after exit_pi_state_list() which sets the new owner in
+ * the pi_state but cannot access the user space value.
+ *
+ * [7] pi_state->owner can only be NULL when the OWNER_DIED bit is set.
+ *
+ * [8] Owner and user space value match
+ *
+ * [9] There is no transient state which sets the user space TID to 0
+ * except exit_robust_list(), but this is indicated by the
+ * FUTEX_OWNER_DIED bit. See [4]
+ *
+ * [10] There is no transient state which leaves owner and user space
+ * TID out of sync.
+ */
static int
lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
union futex_key *key, struct futex_pi_state **ps)
@@ -604,12 +656,13 @@
plist_for_each_entry_safe(this, next, head, list) {
if (match_futex(&this->key, key)) {
/*
- * Another waiter already exists - bump up
- * the refcount and return its pi_state:
+ * Sanity check the waiter before increasing
+ * the refcount and attaching to it.
*/
pi_state = this->pi_state;
/*
- * Userspace might have messed up non-PI and PI futexes
+ * Userspace might have messed up non-PI and
+ * PI futexes [3]
*/
if (unlikely(!pi_state))
return -EINVAL;
@@ -617,34 +670,70 @@
WARN_ON(!atomic_read(&pi_state->refcount));
/*
- * When pi_state->owner is NULL then the owner died
- * and another waiter is on the fly. pi_state->owner
- * is fixed up by the task which acquires
- * pi_state->rt_mutex.
- *
- * We do not check for pid == 0 which can happen when
- * the owner died and robust_list_exit() cleared the
- * TID.
+ * Handle the owner died case:
*/
- if (pid && pi_state->owner) {
+ if (uval & FUTEX_OWNER_DIED) {
/*
- * Bail out if user space manipulated the
- * futex value.
+ * exit_pi_state_list sets owner to NULL and
+ * wakes the topmost waiter. The task which
+ * acquires the pi_state->rt_mutex will fixup
+ * owner.
*/
- if (pid != task_pid_vnr(pi_state->owner))
+ if (!pi_state->owner) {
+ /*
+ * No pi state owner, but the user
+ * space TID is not 0. Inconsistent
+ * state. [5]
+ */
+ if (pid)
+ return -EINVAL;
+ /*
+ * Take a ref on the state and
+ * return. [4]
+ */
+ goto out_state;
+ }
+
+ /*
+ * If TID is 0, then either the dying owner
+ * has not yet executed exit_pi_state_list()
+ * or some waiter acquired the rtmutex in the
+ * pi state, but did not yet fixup the TID in
+ * user space.
+ *
+ * Take a ref on the state and return. [6]
+ */
+ if (!pid)
+ goto out_state;
+ } else {
+ /*
+ * If the owner died bit is not set,
+ * then the pi_state must have an
+ * owner. [7]
+ */
+ if (!pi_state->owner)
return -EINVAL;
}
+ /*
+ * Bail out if user space manipulated the
+ * futex value. If pi state exists then the
+ * owner TID must be the same as the user
+ * space TID. [9/10]
+ */
+ if (pid != task_pid_vnr(pi_state->owner))
+ return -EINVAL;
+
+ out_state:
atomic_inc(&pi_state->refcount);
*ps = pi_state;
-
return 0;
}
}
/*
* We are the first waiter - try to look up the real owner and attach
- * the new pi_state to it, but bail out when TID = 0
+ * the new pi_state to it, but bail out when TID = 0 [1]
*/
if (!pid)
return -ESRCH;
@@ -652,6 +741,11 @@
if (!p)
return -ESRCH;
+ if (!p->mm) {
+ put_task_struct(p);
+ return -EPERM;
+ }
+
/*
* We need to look at the task state flags to figure out,
* whether the task is exiting. To protect against the do_exit
@@ -672,6 +766,9 @@
return ret;
}
+ /*
+ * No existing pi state. First waiter. [2]
+ */
pi_state = alloc_pi_state();
/*
@@ -743,10 +840,18 @@
return -EDEADLK;
/*
- * Surprise - we got the lock. Just return to userspace:
+ * Surprise - we got the lock, but we do not trust user space at all.
*/
- if (unlikely(!curval))
- return 1;
+ if (unlikely(!curval)) {
+ /*
+ * We verify whether there is kernel state for this
+ * futex. If not, we can safely assume, that the 0 ->
+ * TID transition is correct. If state exists, we do
+ * not bother to fixup the user space state as it was
+ * corrupted already.
+ */
+ return futex_top_waiter(hb, key) ? -EINVAL : 1;
+ }
uval = curval;
@@ -876,6 +981,7 @@
struct task_struct *new_owner;
struct futex_pi_state *pi_state = this->pi_state;
u32 uninitialized_var(curval), newval;
+ int ret = 0;
if (!pi_state)
return -EINVAL;
@@ -899,23 +1005,19 @@
new_owner = this->task;
/*
- * We pass it to the next owner. (The WAITERS bit is always
- * kept enabled while there is PI state around. We must also
- * preserve the owner died bit.)
+ * We pass it to the next owner. The WAITERS bit is always
+ * kept enabled while there is PI state around. We cleanup the
+ * owner died bit, because we are the owner.
*/
- if (!(uval & FUTEX_OWNER_DIED)) {
- int ret = 0;
+ newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
- newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
-
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
- ret = -EFAULT;
- else if (curval != uval)
- ret = -EINVAL;
- if (ret) {
- raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
- return ret;
- }
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
+ ret = -EFAULT;
+ else if (curval != uval)
+ ret = -EINVAL;
+ if (ret) {
+ raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+ return ret;
}
raw_spin_lock_irq(&pi_state->owner->pi_lock);
@@ -1194,7 +1296,7 @@
*
* Return:
* 0 - failed to acquire the lock atomically;
- * 1 - acquired the lock;
+ * >0 - acquired the lock, return value is vpid of the top_waiter
* <0 - error
*/
static int futex_proxy_trylock_atomic(u32 __user *pifutex,
@@ -1205,7 +1307,7 @@
{
struct futex_q *top_waiter = NULL;
u32 curval;
- int ret;
+ int ret, vpid;
if (get_futex_value_locked(&curval, pifutex))
return -EFAULT;
@@ -1233,11 +1335,13 @@
* the contended case or if set_waiters is 1. The pi_state is returned
* in ps in contended cases.
*/
+ vpid = task_pid_vnr(top_waiter->task);
ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
set_waiters);
- if (ret == 1)
+ if (ret == 1) {
requeue_pi_wake_futex(top_waiter, key2, hb2);
-
+ return vpid;
+ }
return ret;
}
@@ -1269,10 +1373,16 @@
struct futex_hash_bucket *hb1, *hb2;
struct plist_head *head1;
struct futex_q *this, *next;
- u32 curval2;
if (requeue_pi) {
/*
+ * Requeue PI only works on two distinct uaddrs. This
+ * check is only valid for private futexes. See below.
+ */
+ if (uaddr1 == uaddr2)
+ return -EINVAL;
+
+ /*
* requeue_pi requires a pi_state, try to allocate it now
* without any locks in case it fails.
*/
@@ -1310,6 +1420,15 @@
if (unlikely(ret != 0))
goto out_put_key1;
+ /*
+ * The check above which compares uaddrs is not sufficient for
+ * shared futexes. We need to compare the keys:
+ */
+ if (requeue_pi && match_futex(&key1, &key2)) {
+ ret = -EINVAL;
+ goto out_put_keys;
+ }
+
hb1 = hash_futex(&key1);
hb2 = hash_futex(&key2);
@@ -1355,16 +1474,25 @@
* At this point the top_waiter has either taken uaddr2 or is
* waiting on it. If the former, then the pi_state will not
* exist yet, look it up one more time to ensure we have a
- * reference to it.
+ * reference to it. If the lock was taken, ret contains the
+ * vpid of the top waiter task.
*/
- if (ret == 1) {
+ if (ret > 0) {
WARN_ON(pi_state);
drop_count++;
task_count++;
- ret = get_futex_value_locked(&curval2, uaddr2);
- if (!ret)
- ret = lookup_pi_state(curval2, hb2, &key2,
- &pi_state);
+ /*
+ * If we acquired the lock, then the user
+ * space value of uaddr2 should be vpid. It
+ * cannot be changed by the top waiter as it
+ * is blocked on hb2 lock if it tries to do
+ * so. If something fiddled with it behind our
+ * back the pi state lookup might unearth
+ * it. So we rather use the known value than
+ * rereading and handing potential crap to
+ * lookup_pi_state.
+ */
+ ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
}
switch (ret) {
@@ -2134,9 +2262,10 @@
/*
* To avoid races, try to do the TID -> 0 atomic transition
* again. If it succeeds then we can return without waking
- * anyone else up:
+ * anyone else up. We only try this if neither the waiters nor
+ * the owner died bit are set.
*/
- if (!(uval & FUTEX_OWNER_DIED) &&
+ if (!(uval & ~FUTEX_TID_MASK) &&
cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
goto pi_faulted;
/*
@@ -2168,11 +2297,9 @@
/*
* No waiters - kernel unlocks the futex:
*/
- if (!(uval & FUTEX_OWNER_DIED)) {
- ret = unlock_futex_pi(uaddr, uval);
- if (ret == -EFAULT)
- goto pi_faulted;
- }
+ ret = unlock_futex_pi(uaddr, uval);
+ if (ret == -EFAULT)
+ goto pi_faulted;
out_unlock:
spin_unlock(&hb->lock);
@@ -2331,6 +2458,15 @@
if (ret)
goto out_key2;
+ /*
+ * The check above which compares uaddrs is not sufficient for
+ * shared futexes. We need to compare the keys:
+ */
+ if (match_futex(&q.key, &key2)) {
+ ret = -EINVAL;
+ goto out_put_keys;
+ }
+
/* Queue the futex_q, drop the hb lock, wait for wakeup. */
futex_wait_queue_me(hb, &q, to);
@@ -2728,10 +2864,10 @@
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
{
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
u32 curval;
- int i;
/*
* This will fail and we want it. Some arch implementations do
@@ -2745,6 +2881,14 @@
*/
if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
+ int i;
+
+ futex_detect_cmpxchg();
for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
plist_head_init(&futex_queues[i].chain);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index d4da55d..c92e448 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -32,10 +32,13 @@
Note that the debugfs filesystem has to be mounted to access
profiling data.
+config ARCH_HAS_GCOV_PROFILE_ALL
+ def_bool n
+
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
depends on GCOV_KERNEL
- depends on SUPERH || S390 || X86 || PPC || MICROBLAZE
+ depends on ARCH_HAS_GCOV_PROFILE_ALL
default n
---help---
This options activates profiling for the entire kernel.
@@ -46,4 +49,34 @@
larger and run slower. Also be sure to exclude files from profiling
which are not linked to the kernel image to prevent linker errors.
+choice
+ prompt "Specify GCOV format"
+ depends on GCOV_KERNEL
+ default GCOV_FORMAT_AUTODETECT
+ ---help---
+ The gcov format is usually determined by the GCC version, but there are
+ exceptions where format changes are integrated in lower-version GCCs.
+ In such a case use this option to adjust the format used in the kernel
+ accordingly.
+
+ If unsure, choose "Autodetect".
+
+config GCOV_FORMAT_AUTODETECT
+ bool "Autodetect"
+ ---help---
+ Select this option to use the format that corresponds to your GCC
+ version.
+
+config GCOV_FORMAT_3_4
+ bool "GCC 3.4 format"
+ ---help---
+ Select this option to use the format defined by GCC 3.4.
+
+config GCOV_FORMAT_4_7
+ bool "GCC 4.7 format"
+ ---help---
+ Select this option to use the format defined by GCC 4.7.
+
+endchoice
+
endmenu
diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile
index e97ca59..52aa7e8 100644
--- a/kernel/gcov/Makefile
+++ b/kernel/gcov/Makefile
@@ -1,3 +1,33 @@
ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
-obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o
+# if-lt
+# Usage VAR := $(call if-lt, $(a), $(b))
+# Returns 1 if (a < b)
+if-lt = $(shell [ $(1) -lt $(2) ] && echo 1)
+
+ifeq ($(CONFIG_GCOV_FORMAT_3_4),y)
+ cc-ver := 0304
+else ifeq ($(CONFIG_GCOV_FORMAT_4_7),y)
+ cc-ver := 0407
+else
+# Use cc-version if available, otherwise set 0
+#
+# scripts/Kbuild.include, which contains cc-version function, is not included
+# during make clean "make -f scripts/Makefile.clean obj=kernel/gcov"
+# Meaning cc-ver is empty causing if-lt test to fail with
+# "/bin/sh: line 0: [: -lt: unary operator expected" error mesage.
+# This has no affect on the clean phase, but the error message could be
+# confusing/annoying. So this dummy workaround sets cc-ver to zero if cc-version
+# is not available. We can probably move if-lt to Kbuild.include, so it's also
+# not defined during clean or to include Kbuild.include in
+# scripts/Makefile.clean. But the following workaround seems least invasive.
+ cc-ver := $(if $(call cc-version),$(call cc-version),0)
+endif
+
+obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o
+
+ifeq ($(call if-lt, $(cc-ver), 0407),1)
+ obj-$(CONFIG_GCOV_KERNEL) += gcc_3_4.o
+else
+ obj-$(CONFIG_GCOV_KERNEL) += gcc_4_7.o
+endif
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 9b22d03..b358a80 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -20,7 +20,6 @@
#include <linux/mutex.h>
#include "gcov.h"
-static struct gcov_info *gcov_info_head;
static int gcov_events_enabled;
static DEFINE_MUTEX(gcov_lock);
@@ -34,7 +33,7 @@
mutex_lock(&gcov_lock);
if (gcov_version == 0) {
- gcov_version = info->version;
+ gcov_version = gcov_info_version(info);
/*
* Printing gcc's version magic may prove useful for debugging
* incompatibility reports.
@@ -45,8 +44,7 @@
* Add new profiling data structure to list and inform event
* listener.
*/
- info->next = gcov_info_head;
- gcov_info_head = info;
+ gcov_info_link(info);
if (gcov_events_enabled)
gcov_event(GCOV_ADD, info);
mutex_unlock(&gcov_lock);
@@ -81,6 +79,18 @@
}
EXPORT_SYMBOL(__gcov_merge_delta);
+void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_ior);
+
+void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_time_profile);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
@@ -91,13 +101,15 @@
*/
void gcov_enable_events(void)
{
- struct gcov_info *info;
+ struct gcov_info *info = NULL;
mutex_lock(&gcov_lock);
gcov_events_enabled = 1;
+
/* Perform event callback for previously registered entries. */
- for (info = gcov_info_head; info; info = info->next)
+ while ((info = gcov_info_next(info)))
gcov_event(GCOV_ADD, info);
+
mutex_unlock(&gcov_lock);
}
@@ -112,25 +124,23 @@
void *data)
{
struct module *mod = data;
- struct gcov_info *info;
- struct gcov_info *prev;
+ struct gcov_info *info = NULL;
+ struct gcov_info *prev = NULL;
if (event != MODULE_STATE_GOING)
return NOTIFY_OK;
mutex_lock(&gcov_lock);
- prev = NULL;
+
/* Remove entries located in module from linked list. */
- for (info = gcov_info_head; info; info = info->next) {
+ while ((info = gcov_info_next(info))) {
if (within(info, mod->module_core, mod->core_size)) {
- if (prev)
- prev->next = info->next;
- else
- gcov_info_head = info->next;
+ gcov_info_unlink(prev, info);
if (gcov_events_enabled)
gcov_event(GCOV_REMOVE, info);
} else
prev = info;
}
+
mutex_unlock(&gcov_lock);
return NOTIFY_OK;
diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c
index 9bd0934..27e12ce 100644
--- a/kernel/gcov/fs.c
+++ b/kernel/gcov/fs.c
@@ -242,7 +242,7 @@
list_for_each_entry(node, &all_head, all) {
info = get_node_info(node);
- if (info && (strcmp(info->filename, name) == 0))
+ if (info && (strcmp(gcov_info_filename(info), name) == 0))
return node;
}
@@ -279,7 +279,7 @@
seq = file->private_data;
info = gcov_iter_get_info(seq->private);
mutex_lock(&node_lock);
- node = get_node_by_name(info->filename);
+ node = get_node_by_name(gcov_info_filename(info));
if (node) {
/* Reset counts or remove node for unloaded modules. */
if (node->num_loaded == 0)
@@ -376,8 +376,9 @@
if (!node->links)
return;
for (i = 0; i < num; i++) {
- target = get_link_target(get_node_info(node)->filename,
- &gcov_link[i]);
+ target = get_link_target(
+ gcov_info_filename(get_node_info(node)),
+ &gcov_link[i]);
if (!target)
goto out_err;
basename = strrchr(target, '/');
@@ -576,7 +577,7 @@
struct gcov_node *parent;
struct gcov_node *node;
- filename = kstrdup(info->filename, GFP_KERNEL);
+ filename = kstrdup(gcov_info_filename(info), GFP_KERNEL);
if (!filename)
return;
parent = &root_node;
@@ -631,7 +632,7 @@
loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL);
if (!loaded_info) {
pr_warning("could not add '%s' (out of memory)\n",
- info->filename);
+ gcov_info_filename(info));
return;
}
memcpy(loaded_info, node->loaded_info,
@@ -645,7 +646,8 @@
*/
if (!gcov_info_is_compatible(node->unloaded_info, info)) {
pr_warning("discarding saved data for %s "
- "(incompatible version)\n", info->filename);
+ "(incompatible version)\n",
+ gcov_info_filename(info));
gcov_info_free(node->unloaded_info);
node->unloaded_info = NULL;
}
@@ -656,7 +658,7 @@
*/
if (!gcov_info_is_compatible(node->loaded_info[0], info)) {
pr_warning("could not add '%s' (incompatible "
- "version)\n", info->filename);
+ "version)\n", gcov_info_filename(info));
kfree(loaded_info);
return;
}
@@ -692,7 +694,8 @@
node->unloaded_info = gcov_info_dup(info);
if (!node->unloaded_info) {
pr_warning("could not save data for '%s' "
- "(out of memory)\n", info->filename);
+ "(out of memory)\n",
+ gcov_info_filename(info));
}
}
}
@@ -708,7 +711,7 @@
i = get_info_index(node, info);
if (i < 0) {
pr_warning("could not remove '%s' (not found)\n",
- info->filename);
+ gcov_info_filename(info));
return;
}
if (gcov_persist)
@@ -735,7 +738,7 @@
struct gcov_node *node;
mutex_lock(&node_lock);
- node = get_node_by_name(info->filename);
+ node = get_node_by_name(gcov_info_filename(info));
switch (action) {
case GCOV_ADD:
if (node)
@@ -748,7 +751,7 @@
remove_info(node, info);
else {
pr_warning("could not remove '%s' (not found)\n",
- info->filename);
+ gcov_info_filename(info));
}
break;
}
diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c
index ae5bb42..27bc88a 100644
--- a/kernel/gcov/gcc_3_4.c
+++ b/kernel/gcov/gcc_3_4.c
@@ -21,6 +21,121 @@
#include <linux/vmalloc.h>
#include "gcov.h"
+#define GCOV_COUNTERS 5
+
+static struct gcov_info *gcov_info_head;
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @ident: object file-unique function identifier
+ * @checksum: function checksum
+ * @n_ctrs: number of values per counter type belonging to this function
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ */
+struct gcov_fn_info {
+ unsigned int ident;
+ unsigned int checksum;
+ unsigned int n_ctrs[0];
+};
+
+/**
+ * struct gcov_ctr_info - profiling data per counter type
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ * @merge: merge function for counter values of this type (unused)
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+ unsigned int num;
+ gcov_type *values;
+ void (*merge)(gcov_type *, unsigned int);
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: time stamp
+ * @filename: name of the associated gcov data file
+ * @n_functions: number of instrumented functions
+ * @functions: function data
+ * @ctr_mask: mask specifying which counter types are active
+ * @counts: counter data per counter type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+ unsigned int version;
+ struct gcov_info *next;
+ unsigned int stamp;
+ const char *filename;
+ unsigned int n_functions;
+ const struct gcov_fn_info *functions;
+ unsigned int ctr_mask;
+ struct gcov_ctr_info counts[0];
+};
+
+/**
+ * gcov_info_filename - return info filename
+ * @info: profiling data set
+ */
+const char *gcov_info_filename(struct gcov_info *info)
+{
+ return info->filename;
+}
+
+/**
+ * gcov_info_version - return info version
+ * @info: profiling data set
+ */
+unsigned int gcov_info_version(struct gcov_info *info)
+{
+ return info->version;
+}
+
+/**
+ * gcov_info_next - return next profiling data set
+ * @info: profiling data set
+ *
+ * Returns next gcov_info following @info or first gcov_info in the chain if
+ * @info is %NULL.
+ */
+struct gcov_info *gcov_info_next(struct gcov_info *info)
+{
+ if (!info)
+ return gcov_info_head;
+
+ return info->next;
+}
+
+/**
+ * gcov_info_link - link/add profiling data set to the list
+ * @info: profiling data set
+ */
+void gcov_info_link(struct gcov_info *info)
+{
+ info->next = gcov_info_head;
+ gcov_info_head = info;
+}
+
+/**
+ * gcov_info_unlink - unlink/remove profiling data set from the list
+ * @prev: previous profiling data set
+ * @info: profiling data set
+ */
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info)
+{
+ if (prev)
+ prev->next = info->next;
+ else
+ gcov_info_head = info->next;
+}
+
/* Symbolic links to be created for each profiling data file. */
const struct gcov_link gcov_link[] = {
{ OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
new file mode 100644
index 0000000..826ba9f
--- /dev/null
+++ b/kernel/gcov/gcc_4_7.c
@@ -0,0 +1,565 @@
+/*
+ * This code provides functions to handle gcc's profiling data format
+ * introduced with gcc 4.7.
+ *
+ * This file is based heavily on gcc_3_4.c file.
+ *
+ * For a better understanding, refer to gcc source:
+ * gcc/gcov-io.h
+ * libgcc/libgcov.c
+ *
+ * Uses gcc-internal data definitions.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include "gcov.h"
+
+#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9
+#define GCOV_COUNTERS 9
+#else
+#define GCOV_COUNTERS 8
+#endif
+
+#define GCOV_TAG_FUNCTION_LENGTH 3
+
+static struct gcov_info *gcov_info_head;
+
+/**
+ * struct gcov_ctr_info - information about counters for a single function
+ * @num: number of counter values for this type
+ * @values: array of counter values for this type
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the values array.
+ */
+struct gcov_ctr_info {
+ unsigned int num;
+ gcov_type *values;
+};
+
+/**
+ * struct gcov_fn_info - profiling meta data per function
+ * @key: comdat key
+ * @ident: unique ident of function
+ * @lineno_checksum: function lineo_checksum
+ * @cfg_checksum: function cfg checksum
+ * @ctrs: instrumented counters
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time.
+ *
+ * Information about a single function. This uses the trailing array
+ * idiom. The number of counters is determined from the merge pointer
+ * array in gcov_info. The key is used to detect which of a set of
+ * comdat functions was selected -- it points to the gcov_info object
+ * of the object file containing the selected comdat function.
+ */
+struct gcov_fn_info {
+ const struct gcov_info *key;
+ unsigned int ident;
+ unsigned int lineno_checksum;
+ unsigned int cfg_checksum;
+ struct gcov_ctr_info ctrs[0];
+};
+
+/**
+ * struct gcov_info - profiling data per object file
+ * @version: gcov version magic indicating the gcc version used for compilation
+ * @next: list head for a singly-linked list
+ * @stamp: uniquifying time stamp
+ * @filename: name of the associated gcov data file
+ * @merge: merge functions (null for unused counter type)
+ * @n_functions: number of instrumented functions
+ * @functions: pointer to pointers to function information
+ *
+ * This data is generated by gcc during compilation and doesn't change
+ * at run-time with the exception of the next pointer.
+ */
+struct gcov_info {
+ unsigned int version;
+ struct gcov_info *next;
+ unsigned int stamp;
+ const char *filename;
+ void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int);
+ unsigned int n_functions;
+ struct gcov_fn_info **functions;
+};
+
+/**
+ * gcov_info_filename - return info filename
+ * @info: profiling data set
+ */
+const char *gcov_info_filename(struct gcov_info *info)
+{
+ return info->filename;
+}
+
+/**
+ * gcov_info_version - return info version
+ * @info: profiling data set
+ */
+unsigned int gcov_info_version(struct gcov_info *info)
+{
+ return info->version;
+}
+
+/**
+ * gcov_info_next - return next profiling data set
+ * @info: profiling data set
+ *
+ * Returns next gcov_info following @info or first gcov_info in the chain if
+ * @info is %NULL.
+ */
+struct gcov_info *gcov_info_next(struct gcov_info *info)
+{
+ if (!info)
+ return gcov_info_head;
+
+ return info->next;
+}
+
+/**
+ * gcov_info_link - link/add profiling data set to the list
+ * @info: profiling data set
+ */
+void gcov_info_link(struct gcov_info *info)
+{
+ info->next = gcov_info_head;
+ gcov_info_head = info;
+}
+
+/**
+ * gcov_info_unlink - unlink/remove profiling data set from the list
+ * @prev: previous profiling data set
+ * @info: profiling data set
+ */
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info)
+{
+ if (prev)
+ prev->next = info->next;
+ else
+ gcov_info_head = info->next;
+}
+
+/* Symbolic links to be created for each profiling data file. */
+const struct gcov_link gcov_link[] = {
+ { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */
+ { 0, NULL},
+};
+
+/*
+ * Determine whether a counter is active. Doesn't change at run-time.
+ */
+static int counter_active(struct gcov_info *info, unsigned int type)
+{
+ return info->merge[type] ? 1 : 0;
+}
+
+/* Determine number of active counters. Based on gcc magic. */
+static unsigned int num_counter_active(struct gcov_info *info)
+{
+ unsigned int i;
+ unsigned int result = 0;
+
+ for (i = 0; i < GCOV_COUNTERS; i++) {
+ if (counter_active(info, i))
+ result++;
+ }
+ return result;
+}
+
+/**
+ * gcov_info_reset - reset profiling data to zero
+ * @info: profiling data set
+ */
+void gcov_info_reset(struct gcov_info *info)
+{
+ struct gcov_ctr_info *ci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ ci_ptr = info->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(info, ct_idx))
+ continue;
+
+ memset(ci_ptr->values, 0,
+ sizeof(gcov_type) * ci_ptr->num);
+ ci_ptr++;
+ }
+ }
+}
+
+/**
+ * gcov_info_is_compatible - check if profiling data can be added
+ * @info1: first profiling data set
+ * @info2: second profiling data set
+ *
+ * Returns non-zero if profiling data can be added, zero otherwise.
+ */
+int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2)
+{
+ return (info1->stamp == info2->stamp);
+}
+
+/**
+ * gcov_info_add - add up profiling data
+ * @dest: profiling data set to which data is added
+ * @source: profiling data set which is added
+ *
+ * Adds profiling counts of @source to @dest.
+ */
+void gcov_info_add(struct gcov_info *dst, struct gcov_info *src)
+{
+ struct gcov_ctr_info *dci_ptr;
+ struct gcov_ctr_info *sci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ unsigned int val_idx;
+
+ for (fi_idx = 0; fi_idx < src->n_functions; fi_idx++) {
+ dci_ptr = dst->functions[fi_idx]->ctrs;
+ sci_ptr = src->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(src, ct_idx))
+ continue;
+
+ for (val_idx = 0; val_idx < sci_ptr->num; val_idx++)
+ dci_ptr->values[val_idx] +=
+ sci_ptr->values[val_idx];
+
+ dci_ptr++;
+ sci_ptr++;
+ }
+ }
+}
+
+/**
+ * gcov_info_dup - duplicate profiling data set
+ * @info: profiling data set to duplicate
+ *
+ * Return newly allocated duplicate on success, %NULL on error.
+ */
+struct gcov_info *gcov_info_dup(struct gcov_info *info)
+{
+ struct gcov_info *dup;
+ struct gcov_ctr_info *dci_ptr; /* dst counter info */
+ struct gcov_ctr_info *sci_ptr; /* src counter info */
+ unsigned int active;
+ unsigned int fi_idx; /* function info idx */
+ unsigned int ct_idx; /* counter type idx */
+ size_t fi_size; /* function info size */
+ size_t cv_size; /* counter values size */
+
+ dup = kmemdup(info, sizeof(*dup), GFP_KERNEL);
+ if (!dup)
+ return NULL;
+
+ dup->next = NULL;
+ dup->filename = NULL;
+ dup->functions = NULL;
+
+ dup->filename = kstrdup(info->filename, GFP_KERNEL);
+ if (!dup->filename)
+ goto err_free;
+
+ dup->functions = kcalloc(info->n_functions,
+ sizeof(struct gcov_fn_info *), GFP_KERNEL);
+ if (!dup->functions)
+ goto err_free;
+
+ active = num_counter_active(info);
+ fi_size = sizeof(struct gcov_fn_info);
+ fi_size += sizeof(struct gcov_ctr_info) * active;
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ dup->functions[fi_idx] = kzalloc(fi_size, GFP_KERNEL);
+ if (!dup->functions[fi_idx])
+ goto err_free;
+
+ *(dup->functions[fi_idx]) = *(info->functions[fi_idx]);
+
+ sci_ptr = info->functions[fi_idx]->ctrs;
+ dci_ptr = dup->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < active; ct_idx++) {
+
+ cv_size = sizeof(gcov_type) * sci_ptr->num;
+
+ dci_ptr->values = vmalloc(cv_size);
+
+ if (!dci_ptr->values)
+ goto err_free;
+
+ dci_ptr->num = sci_ptr->num;
+ memcpy(dci_ptr->values, sci_ptr->values, cv_size);
+
+ sci_ptr++;
+ dci_ptr++;
+ }
+ }
+
+ return dup;
+err_free:
+ gcov_info_free(dup);
+ return NULL;
+}
+
+/**
+ * gcov_info_free - release memory for profiling data set duplicate
+ * @info: profiling data set duplicate to free
+ */
+void gcov_info_free(struct gcov_info *info)
+{
+ unsigned int active;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ struct gcov_ctr_info *ci_ptr;
+
+ if (!info->functions)
+ goto free_info;
+
+ active = num_counter_active(info);
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ if (!info->functions[fi_idx])
+ continue;
+
+ ci_ptr = info->functions[fi_idx]->ctrs;
+
+ for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++)
+ vfree(ci_ptr->values);
+
+ kfree(info->functions[fi_idx]);
+ }
+
+free_info:
+ kfree(info->functions);
+ kfree(info->filename);
+ kfree(info);
+}
+
+#define ITER_STRIDE PAGE_SIZE
+
+/**
+ * struct gcov_iterator - specifies current file position in logical records
+ * @info: associated profiling data
+ * @buffer: buffer containing file data
+ * @size: size of buffer
+ * @pos: current position in file
+ */
+struct gcov_iterator {
+ struct gcov_info *info;
+ void *buffer;
+ size_t size;
+ loff_t pos;
+};
+
+/**
+ * store_gcov_u32 - store 32 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't
+ * store anything.
+ */
+static size_t store_gcov_u32(void *buffer, size_t off, u32 v)
+{
+ u32 *data;
+
+ if (buffer) {
+ data = buffer + off;
+ *data = v;
+ }
+
+ return sizeof(*data);
+}
+
+/**
+ * store_gcov_u64 - store 64 bit number in gcov format to buffer
+ * @buffer: target buffer or NULL
+ * @off: offset into the buffer
+ * @v: value to be stored
+ *
+ * Number format defined by gcc: numbers are recorded in the 32 bit
+ * unsigned binary form of the endianness of the machine generating the
+ * file. 64 bit numbers are stored as two 32 bit numbers, the low part
+ * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store
+ * anything.
+ */
+static size_t store_gcov_u64(void *buffer, size_t off, u64 v)
+{
+ u32 *data;
+
+ if (buffer) {
+ data = buffer + off;
+
+ data[0] = (v & 0xffffffffUL);
+ data[1] = (v >> 32);
+ }
+
+ return sizeof(*data) * 2;
+}
+
+/**
+ * convert_to_gcda - convert profiling data set to gcda file format
+ * @buffer: the buffer to store file data or %NULL if no data should be stored
+ * @info: profiling data set to be converted
+ *
+ * Returns the number of bytes that were/would have been stored into the buffer.
+ */
+static size_t convert_to_gcda(char *buffer, struct gcov_info *info)
+{
+ struct gcov_fn_info *fi_ptr;
+ struct gcov_ctr_info *ci_ptr;
+ unsigned int fi_idx;
+ unsigned int ct_idx;
+ unsigned int cv_idx;
+ size_t pos = 0;
+
+ /* File header. */
+ pos += store_gcov_u32(buffer, pos, GCOV_DATA_MAGIC);
+ pos += store_gcov_u32(buffer, pos, info->version);
+ pos += store_gcov_u32(buffer, pos, info->stamp);
+
+ for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) {
+ fi_ptr = info->functions[fi_idx];
+
+ /* Function record. */
+ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
+ pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum);
+ pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+
+ ci_ptr = fi_ptr->ctrs;
+
+ for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) {
+ if (!counter_active(info, ct_idx))
+ continue;
+
+ /* Counter record. */
+ pos += store_gcov_u32(buffer, pos,
+ GCOV_TAG_FOR_COUNTER(ct_idx));
+ pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2);
+
+ for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) {
+ pos += store_gcov_u64(buffer, pos,
+ ci_ptr->values[cv_idx]);
+ }
+
+ ci_ptr++;
+ }
+ }
+
+ return pos;
+}
+
+/**
+ * gcov_iter_new - allocate and initialize profiling data iterator
+ * @info: profiling data set to be iterated
+ *
+ * Return file iterator on success, %NULL otherwise.
+ */
+struct gcov_iterator *gcov_iter_new(struct gcov_info *info)
+{
+ struct gcov_iterator *iter;
+
+ iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL);
+ if (!iter)
+ goto err_free;
+
+ iter->info = info;
+ /* Dry-run to get the actual buffer size. */
+ iter->size = convert_to_gcda(NULL, info);
+ iter->buffer = vmalloc(iter->size);
+ if (!iter->buffer)
+ goto err_free;
+
+ convert_to_gcda(iter->buffer, info);
+
+ return iter;
+
+err_free:
+ kfree(iter);
+ return NULL;
+}
+
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+void gcov_iter_free(struct gcov_iterator *iter)
+{
+ vfree(iter->buffer);
+ kfree(iter);
+}
+
+/**
+ * gcov_iter_get_info - return profiling data set for given file iterator
+ * @iter: file iterator
+ */
+struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter)
+{
+ return iter->info;
+}
+
+/**
+ * gcov_iter_start - reset file iterator to starting position
+ * @iter: file iterator
+ */
+void gcov_iter_start(struct gcov_iterator *iter)
+{
+ iter->pos = 0;
+}
+
+/**
+ * gcov_iter_next - advance file iterator to next logical record
+ * @iter: file iterator
+ *
+ * Return zero if new position is valid, non-zero if iterator has reached end.
+ */
+int gcov_iter_next(struct gcov_iterator *iter)
+{
+ if (iter->pos < iter->size)
+ iter->pos += ITER_STRIDE;
+
+ if (iter->pos >= iter->size)
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * gcov_iter_write - write data for current pos to seq_file
+ * @iter: file iterator
+ * @seq: seq_file handle
+ *
+ * Return zero on success, non-zero otherwise.
+ */
+int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq)
+{
+ size_t len;
+
+ if (iter->pos >= iter->size)
+ return -EINVAL;
+
+ len = ITER_STRIDE;
+ if (iter->pos + len > iter->size)
+ len = iter->size - iter->pos;
+
+ seq_write(seq, iter->buffer + iter->pos, len);
+
+ return 0;
+}
diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h
index 060073e..92c8e22 100644
--- a/kernel/gcov/gcov.h
+++ b/kernel/gcov/gcov.h
@@ -21,7 +21,6 @@
* gcc and need to be kept as close to the original definition as possible to
* remain compatible.
*/
-#define GCOV_COUNTERS 5
#define GCOV_DATA_MAGIC ((unsigned int) 0x67636461)
#define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000)
#define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000)
@@ -34,60 +33,18 @@
typedef long long gcov_type;
#endif
-/**
- * struct gcov_fn_info - profiling meta data per function
- * @ident: object file-unique function identifier
- * @checksum: function checksum
- * @n_ctrs: number of values per counter type belonging to this function
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time.
- */
-struct gcov_fn_info {
- unsigned int ident;
- unsigned int checksum;
- unsigned int n_ctrs[0];
-};
+/* Opaque gcov_info. The gcov structures can change as for example in gcc 4.7 so
+ * we cannot use full definition here and they need to be placed in gcc specific
+ * implementation of gcov. This also means no direct access to the members in
+ * generic code and usage of the interface below.*/
+struct gcov_info;
-/**
- * struct gcov_ctr_info - profiling data per counter type
- * @num: number of counter values for this type
- * @values: array of counter values for this type
- * @merge: merge function for counter values of this type (unused)
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the values array.
- */
-struct gcov_ctr_info {
- unsigned int num;
- gcov_type *values;
- void (*merge)(gcov_type *, unsigned int);
-};
-
-/**
- * struct gcov_info - profiling data per object file
- * @version: gcov version magic indicating the gcc version used for compilation
- * @next: list head for a singly-linked list
- * @stamp: time stamp
- * @filename: name of the associated gcov data file
- * @n_functions: number of instrumented functions
- * @functions: function data
- * @ctr_mask: mask specifying which counter types are active
- * @counts: counter data per counter type
- *
- * This data is generated by gcc during compilation and doesn't change
- * at run-time with the exception of the next pointer.
- */
-struct gcov_info {
- unsigned int version;
- struct gcov_info *next;
- unsigned int stamp;
- const char *filename;
- unsigned int n_functions;
- const struct gcov_fn_info *functions;
- unsigned int ctr_mask;
- struct gcov_ctr_info counts[0];
-};
+/* Interface to access gcov_info data */
+const char *gcov_info_filename(struct gcov_info *info);
+unsigned int gcov_info_version(struct gcov_info *info);
+struct gcov_info *gcov_info_next(struct gcov_info *info);
+void gcov_info_link(struct gcov_info *info);
+void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info);
/* Base interface. */
enum gcov_action {
diff --git a/kernel/groups.c b/kernel/groups.c
index 6b2588d..67b4ba3 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/security.h>
#include <linux/syscalls.h>
+#include <linux/user_namespace.h>
#include <asm/uaccess.h>
/* init to 2 - one for init_task, one to ensure it is never freed */
@@ -223,6 +224,14 @@
return i;
}
+bool may_setgroups(void)
+{
+ struct user_namespace *user_ns = current_user_ns();
+
+ return ns_capable(user_ns, CAP_SETGID) &&
+ userns_may_setgroups(user_ns);
+}
+
/*
* SMP: Our groups are copy-on-write. We can set them safely
* without another task interfering.
@@ -233,7 +242,7 @@
struct group_info *group_info;
int retval;
- if (!nsown_capable(CAP_SETGID))
+ if (!may_setgroups())
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index fd4b13b..aadf4b7 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -245,6 +245,11 @@
goto again;
}
timer->base = new_base;
+ } else {
+ if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+ cpu = this_cpu;
+ goto again;
+ }
}
return new_base;
}
@@ -580,6 +585,23 @@
cpu_base->expires_next.tv64 = expires_next.tv64;
+ /*
+ * If a hang was detected in the last timer interrupt then we
+ * leave the hang delay active in the hardware. We want the
+ * system to make progress. That also prevents the following
+ * scenario:
+ * T1 expires 50ms from now
+ * T2 expires 5s from now
+ *
+ * T1 is removed, so this code is called and would reprogram
+ * the hardware to 5s from now. Any hrtimer_start after that
+ * will not reprogram the hardware due to hang_detected being
+ * set. So we'd effectivly block all timers until the T2 event
+ * fires.
+ */
+ if (cpu_base->hang_detected)
+ return;
+
if (cpu_base->expires_next.tv64 != KTIME_MAX)
tick_program_event(cpu_base->expires_next, 1);
}
@@ -721,17 +743,20 @@
return 1;
}
+static void clock_was_set_work(struct work_struct *work)
+{
+ clock_was_set();
+}
+
+static DECLARE_WORK(hrtimer_work, clock_was_set_work);
+
/*
- * Called from timekeeping code to reprogramm the hrtimer interrupt
- * device. If called from the timer interrupt context we defer it to
- * softirq context.
+ * Called from timekeeping and resume code to reprogramm the hrtimer
+ * interrupt device on all cpus.
*/
void clock_was_set_delayed(void)
{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
- cpu_base->clock_was_set = 1;
- __raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+ schedule_work(&hrtimer_work);
}
#else
@@ -780,8 +805,10 @@
WARN_ONCE(!irqs_disabled(),
KERN_INFO "hrtimers_resume() called with IRQs enabled!");
+ /* Retrigger on the local CPU */
retrigger_next_event(NULL);
- timerfd_clock_was_set();
+ /* And schedule a retrigger for all others */
+ clock_was_set_delayed();
}
static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
@@ -972,11 +999,8 @@
/* Remove an active timer from the queue: */
ret = remove_hrtimer(timer, base);
- /* Switch the timer base, if necessary: */
- new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
if (mode & HRTIMER_MODE_REL) {
- tim = ktime_add_safe(tim, new_base->get_time());
+ tim = ktime_add_safe(tim, base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
* to signal that they simply return xtime in
@@ -991,6 +1015,9 @@
hrtimer_set_expires_range_ns(timer, tim, delta_ns);
+ /* Switch the timer base, if necessary: */
+ new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
timer_stats_hrtimer_set_start_info(timer);
leftmost = enqueue_hrtimer(timer, new_base);
@@ -1432,13 +1459,6 @@
static void run_hrtimer_softirq(struct softirq_action *h)
{
- struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
- if (cpu_base->clock_was_set) {
- cpu_base->clock_was_set = 0;
- clock_was_set();
- }
-
hrtimer_peek_ahead_timers();
}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302..3fcb6fa 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -23,10 +23,35 @@
static struct lock_class_key irq_desc_lock_class;
#if defined(CONFIG_SMP)
+static int __init irq_affinity_setup(char *str)
+{
+ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+ cpulist_parse(str, irq_default_affinity);
+ /*
+ * Set at least the boot cpu. We don't want to end up with
+ * bugreports caused by random comandline masks
+ */
+ cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
+ return 1;
+}
+__setup("irqaffinity=", irq_affinity_setup);
+
+extern struct cpumask hmp_slow_cpu_mask;
+
static void __init init_irq_default_affinity(void)
{
- alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
- cpumask_setall(irq_default_affinity);
+#ifdef CONFIG_CPUMASK_OFFSTACK
+ if (!irq_default_affinity)
+ zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+#endif
+#ifdef CONFIG_SCHED_HMP
+ if (!cpumask_empty(&hmp_slow_cpu_mask)) {
+ cpumask_copy(irq_default_affinity, &hmp_slow_cpu_mask);
+ return;
+ }
+#endif
+ if (cpumask_empty(irq_default_affinity))
+ cpumask_setall(irq_default_affinity);
}
#else
static void __init init_irq_default_affinity(void)
@@ -274,6 +299,7 @@
{
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
}
+EXPORT_SYMBOL(irq_to_desc);
static void free_desc(unsigned int irq)
{
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index fa17855..a79d267 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -150,7 +150,7 @@
struct irq_chip *chip = irq_data_get_irq_chip(data);
int ret;
- ret = chip->irq_set_affinity(data, mask, false);
+ ret = chip->irq_set_affinity(data, mask, force);
switch (ret) {
case IRQ_SET_MASK_OK:
cpumask_copy(data->affinity, mask);
@@ -162,7 +162,8 @@
return ret;
}
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+ bool force)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
struct irq_desc *desc = irq_data_to_desc(data);
@@ -172,7 +173,7 @@
return -EINVAL;
if (irq_can_move_pcntxt(data)) {
- ret = irq_do_set_affinity(data, mask, false);
+ ret = irq_do_set_affinity(data, mask, force);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
@@ -187,13 +188,7 @@
return ret;
}
-/**
- * irq_set_affinity - Set the irq affinity of a given irq
- * @irq: Interrupt to set affinity
- * @mask: cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
{
struct irq_desc *desc = irq_to_desc(irq);
unsigned long flags;
@@ -203,7 +198,7 @@
return -EINVAL;
raw_spin_lock_irqsave(&desc->lock, flags);
- ret = __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+ ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
raw_spin_unlock_irqrestore(&desc->lock, flags);
return ret;
}
@@ -555,9 +550,9 @@
return 0;
if (irq_settings_can_request(desc)) {
- if (desc->action)
- if (irqflags & desc->action->flags & IRQF_SHARED)
- canrequest =1;
+ if (!desc->action ||
+ irqflags & desc->action->flags & IRQF_SHARED)
+ canrequest = 1;
}
irq_put_desc_unlock(desc, flags);
return canrequest;
@@ -802,8 +797,7 @@
static void wake_threads_waitq(struct irq_desc *desc)
{
- if (atomic_dec_and_test(&desc->threads_active) &&
- waitqueue_active(&desc->wait_for_threads))
+ if (atomic_dec_and_test(&desc->threads_active))
wake_up(&desc->wait_for_threads);
}
@@ -867,8 +861,8 @@
irq_thread_check_affinity(desc, action);
action_ret = handler_fn(desc, action);
- if (!noirqdebug)
- note_interrupt(action->irq, desc, action_ret);
+ if (action_ret == IRQ_HANDLED)
+ atomic_inc(&desc->threads_handled);
wake_threads_waitq(desc);
}
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index cb228bf..abcd6ca 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -50,7 +50,7 @@
bool is_early = desc->action &&
desc->action->flags & IRQF_EARLY_RESUME;
- if (is_early != want_early)
+ if (!is_early && want_early)
continue;
raw_spin_lock_irqsave(&desc->lock, flags);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 7b5f012..febcee3c 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -265,21 +265,119 @@
return action && (action->flags & IRQF_IRQPOLL);
}
+#define SPURIOUS_DEFERRED 0x80000000
+
void note_interrupt(unsigned int irq, struct irq_desc *desc,
irqreturn_t action_ret)
{
if (desc->istate & IRQS_POLL_INPROGRESS)
return;
- /* we get here again via the threaded handler */
- if (action_ret == IRQ_WAKE_THREAD)
- return;
-
if (bad_action_ret(action_ret)) {
report_bad_irq(irq, desc, action_ret);
return;
}
+ /*
+ * We cannot call note_interrupt from the threaded handler
+ * because we need to look at the compound of all handlers
+ * (primary and threaded). Aside of that in the threaded
+ * shared case we have no serialization against an incoming
+ * hardware interrupt while we are dealing with a threaded
+ * result.
+ *
+ * So in case a thread is woken, we just note the fact and
+ * defer the analysis to the next hardware interrupt.
+ *
+ * The threaded handlers store whether they sucessfully
+ * handled an interrupt and we check whether that number
+ * changed versus the last invocation.
+ *
+ * We could handle all interrupts with the delayed by one
+ * mechanism, but for the non forced threaded case we'd just
+ * add pointless overhead to the straight hardirq interrupts
+ * for the sake of a few lines less code.
+ */
+ if (action_ret & IRQ_WAKE_THREAD) {
+ /*
+ * There is a thread woken. Check whether one of the
+ * shared primary handlers returned IRQ_HANDLED. If
+ * not we defer the spurious detection to the next
+ * interrupt.
+ */
+ if (action_ret == IRQ_WAKE_THREAD) {
+ int handled;
+ /*
+ * We use bit 31 of thread_handled_last to
+ * denote the deferred spurious detection
+ * active. No locking necessary as
+ * thread_handled_last is only accessed here
+ * and we have the guarantee that hard
+ * interrupts are not reentrant.
+ */
+ if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) {
+ desc->threads_handled_last |= SPURIOUS_DEFERRED;
+ return;
+ }
+ /*
+ * Check whether one of the threaded handlers
+ * returned IRQ_HANDLED since the last
+ * interrupt happened.
+ *
+ * For simplicity we just set bit 31, as it is
+ * set in threads_handled_last as well. So we
+ * avoid extra masking. And we really do not
+ * care about the high bits of the handled
+ * count. We just care about the count being
+ * different than the one we saw before.
+ */
+ handled = atomic_read(&desc->threads_handled);
+ handled |= SPURIOUS_DEFERRED;
+ if (handled != desc->threads_handled_last) {
+ action_ret = IRQ_HANDLED;
+ /*
+ * Note: We keep the SPURIOUS_DEFERRED
+ * bit set. We are handling the
+ * previous invocation right now.
+ * Keep it for the current one, so the
+ * next hardware interrupt will
+ * account for it.
+ */
+ desc->threads_handled_last = handled;
+ } else {
+ /*
+ * None of the threaded handlers felt
+ * responsible for the last interrupt
+ *
+ * We keep the SPURIOUS_DEFERRED bit
+ * set in threads_handled_last as we
+ * need to account for the current
+ * interrupt as well.
+ */
+ action_ret = IRQ_NONE;
+ }
+ } else {
+ /*
+ * One of the primary handlers returned
+ * IRQ_HANDLED. So we don't care about the
+ * threaded handlers on the same line. Clear
+ * the deferred detection bit.
+ *
+ * In theory we could/should check whether the
+ * deferred bit is set and take the result of
+ * the previous run into account here as
+ * well. But it's really not worth the
+ * trouble. If every other interrupt is
+ * handled we never trigger the spurious
+ * detector. And if this is just the one out
+ * of 100k unhandled ones which is handled
+ * then we merily delay the spurious detection
+ * by one hard interrupt. Not a real problem.
+ */
+ desc->threads_handled_last &= ~SPURIOUS_DEFERRED;
+ }
+ }
+
if (unlikely(action_ret == IRQ_NONE)) {
/*
* If we are seeing only the odd spurious IRQ caused by
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index e30ac0f..0aa69ea 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -44,11 +44,12 @@
*/
static int kcmp_ptr(void *v1, void *v2, enum kcmp_type type)
{
- long ret;
+ long t1, t2;
- ret = kptr_obfuscate((long)v1, type) - kptr_obfuscate((long)v2, type);
+ t1 = kptr_obfuscate((long)v1, type);
+ t2 = kptr_obfuscate((long)v2, type);
- return (ret < 0) | ((ret > 0) << 1);
+ return (t1 < t2) | ((t1 > t2) << 1);
}
/* The caller must have pinned the task */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 59f7b55..1f8d938 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -47,6 +47,9 @@
size_t vmcoreinfo_size;
size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
/* Location of the reserved area for the crash kernel */
struct resource crashk_res = {
.name = "Crash kernel",
@@ -1678,6 +1681,7 @@
} else
#endif
{
+ kexec_in_progress = true;
kernel_restart_prepare(NULL);
printk(KERN_EMERG "Starting new kernel\n");
machine_shutdown();
diff --git a/kernel/module.c b/kernel/module.c
index cab4bce..a6f1de8 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1866,7 +1866,9 @@
/* We leave it in list to prevent duplicate loads, but make sure
* that noone uses it while it's being deconstructed. */
+ mutex_lock(&module_mutex);
mod->state = MODULE_STATE_UNFORMED;
+ mutex_unlock(&module_mutex);
/* Remove dynamic debug info */
ddebug_remove_module(mod->name);
@@ -2723,7 +2725,7 @@
return 0;
}
-static void find_module_sections(struct module *mod, struct load_info *info)
+static int find_module_sections(struct module *mod, struct load_info *info)
{
mod->kp = section_objs(info, "__param",
sizeof(*mod->kp), &mod->num_kp);
@@ -2753,6 +2755,18 @@
#ifdef CONFIG_CONSTRUCTORS
mod->ctors = section_objs(info, ".ctors",
sizeof(*mod->ctors), &mod->num_ctors);
+ if (!mod->ctors)
+ mod->ctors = section_objs(info, ".init_array",
+ sizeof(*mod->ctors), &mod->num_ctors);
+ else if (find_sec(info, ".init_array")) {
+ /*
+ * This shouldn't happen with same compiler and binutils
+ * building all parts of the module.
+ */
+ printk(KERN_WARNING "%s: has both .ctors and .init_array.\n",
+ mod->name);
+ return -EINVAL;
+ }
#endif
#ifdef CONFIG_TRACEPOINTS
@@ -2791,6 +2805,8 @@
info->debug = section_objs(info, "__verbose",
sizeof(*info->debug), &info->num_debug);
+
+ return 0;
}
static int move_module(struct module *mod, struct load_info *info)
@@ -2927,7 +2943,6 @@
{
/* Module within temporary copy. */
struct module *mod;
- Elf_Shdr *pcpusec;
int err;
mod = setup_load_info(info, flags);
@@ -2942,17 +2957,10 @@
err = module_frob_arch_sections(info->hdr, info->sechdrs,
info->secstrings, mod);
if (err < 0)
- goto out;
+ return ERR_PTR(err);
- pcpusec = &info->sechdrs[info->index.pcpu];
- if (pcpusec->sh_size) {
- /* We have a special allocation for this section. */
- err = percpu_modalloc(mod,
- pcpusec->sh_size, pcpusec->sh_addralign);
- if (err)
- goto out;
- pcpusec->sh_flags &= ~(unsigned long)SHF_ALLOC;
- }
+ /* We will do a special allocation for per-cpu sections later. */
+ info->sechdrs[info->index.pcpu].sh_flags &= ~(unsigned long)SHF_ALLOC;
/* Determine total sizes, and put offsets in sh_entsize. For now
this is done generically; there doesn't appear to be any
@@ -2963,17 +2971,22 @@
/* Allocate and move to the final place */
err = move_module(mod, info);
if (err)
- goto free_percpu;
+ return ERR_PTR(err);
/* Module has been copied to its final place now: return it. */
mod = (void *)info->sechdrs[info->index.mod].sh_addr;
kmemleak_load_module(mod, info);
return mod;
+}
-free_percpu:
- percpu_modfree(mod);
-out:
- return ERR_PTR(err);
+static int alloc_module_percpu(struct module *mod, struct load_info *info)
+{
+ Elf_Shdr *pcpusec = &info->sechdrs[info->index.pcpu];
+ if (!pcpusec->sh_size)
+ return 0;
+
+ /* We have a special allocation for this section. */
+ return percpu_modalloc(mod, pcpusec->sh_size, pcpusec->sh_addralign);
}
/* mod is no longer valid after this! */
@@ -3237,6 +3250,11 @@
}
#endif
+ /* To avoid stressing percpu allocator, do this once we're unique. */
+ err = alloc_module_percpu(mod, info);
+ if (err)
+ goto unlink_mod;
+
/* Now module is in final location, initialize linked lists, etc. */
err = module_unload_init(mod);
if (err)
@@ -3244,7 +3262,9 @@
/* Now we've got everything in the final locations, we can
* find optional sections. */
- find_module_sections(mod, info);
+ err = find_module_sections(mod, info);
+ if (err)
+ goto free_unload;
err = check_module_license_and_versions(mod);
if (err)
@@ -3277,6 +3297,9 @@
dynamic_debug_setup(info->debug, info->num_debug);
+ /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+ ftrace_module_init(mod);
+
/* Finally it's fully formed, ready to start executing. */
err = complete_formation(mod, info);
if (err)
diff --git a/kernel/pid.c b/kernel/pid.c
index 0db3e79..3cdba51 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -264,6 +264,7 @@
struct pid_namespace *ns = upid->ns;
hlist_del_rcu(&upid->pid_chain);
switch(--ns->nr_hashed) {
+ case 2:
case 1:
/* When all that is left in the pid namespace
* is the reaper wake up the reaper. The reaper
@@ -334,6 +335,8 @@
out_unlock:
spin_unlock_irq(&pidmap_lock);
+ put_pid_ns(ns);
+
out_free:
while (++i <= ns->level)
free_pidmap(pid->numbers + i);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 6917e8e..e32703d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -312,7 +312,9 @@
struct pid_namespace *ns;
rcu_read_lock();
- ns = get_pid_ns(task_active_pid_ns(task));
+ ns = task_active_pid_ns(task);
+ if (ns)
+ get_pid_ns(ns);
rcu_read_unlock();
return ns;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 424c2d4..77e6b83 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -634,6 +634,7 @@
goto out;
}
} else {
+ memset(&event.sigev_value, 0, sizeof(event.sigev_value));
event.sigev_notify = SIGEV_SIGNAL;
event.sigev_signo = SIGALRM;
event.sigev_value.sival_int = new_timer->it_id;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 5dfdc9e..52423b5 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -263,6 +263,26 @@
bool
depends on PM
+config WQ_POWER_EFFICIENT_DEFAULT
+ bool "Enable workqueue power-efficient mode by default"
+ depends on PM
+ default n
+ help
+ Per-cpu workqueues are generally preferred because they show
+ better performance thanks to cache locality; unfortunately,
+ per-cpu workqueues tend to be more power hungry than unbound
+ workqueues.
+
+ Enabling workqueue.power_efficient kernel parameter makes the
+ per-cpu workqueues which were observed to contribute
+ significantly to power consumption unbound, leading to measurably
+ lower power usage at the cost of small performance overhead.
+
+ This config option determines whether workqueue.power_efficient
+ is enabled by default.
+
+ If in doubt, say N.
+
config PM_GENERIC_DOMAINS_SLEEP
def_bool y
depends on PM_SLEEP && PM_GENERIC_DOMAINS
@@ -271,6 +291,10 @@
def_bool y
depends on PM_RUNTIME && PM_GENERIC_DOMAINS
+config PM_GENERIC_DOMAINS_OF
+ def_bool y
+ depends on PM_GENERIC_DOMAINS && OF && !ARCH_EXYNOS
+
config CPU_PM
bool
depends on SUSPEND || CPU_IDLE
diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c
index c6422ff..9012ecf 100644
--- a/kernel/power/autosleep.c
+++ b/kernel/power/autosleep.c
@@ -32,7 +32,8 @@
mutex_lock(&autosleep_lock);
- if (!pm_save_wakeup_count(initial_count)) {
+ if (!pm_save_wakeup_count(initial_count) ||
+ system_state != SYSTEM_RUNNING) {
mutex_unlock(&autosleep_lock);
goto out;
}
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b26f5f1..1634dc6 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -491,8 +491,14 @@
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
- dpm_resume_end(PMSG_RECOVER);
+ /*
+ * The above should either succeed and jump to the new kernel,
+ * or return with an error. Otherwise things are just
+ * undefined, so let's be paranoid.
+ */
+ BUG_ON(!error);
}
+ dpm_resume_end(PMSG_RECOVER);
pm_restore_gfp_mask();
ftrace_start();
resume_console();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d77663b..312c1b2 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -293,12 +293,12 @@
{
char *s = buf;
#ifdef CONFIG_SUSPEND
- int i;
+ suspend_state_t i;
- for (i = 0; i < PM_SUSPEND_MAX; i++) {
- if (pm_states[i] && valid_state(i))
- s += sprintf(s,"%s ", pm_states[i]);
- }
+ for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+ if (pm_states[i].state)
+ s += sprintf(s,"%s ", pm_states[i].label);
+
#endif
#ifdef CONFIG_HIBERNATION
s += sprintf(s, "%s\n", "disk");
@@ -314,7 +314,7 @@
{
#ifdef CONFIG_SUSPEND
suspend_state_t state = PM_SUSPEND_MIN;
- const char * const *s;
+ struct pm_sleep_state *s;
#endif
char *p;
int len;
@@ -328,8 +328,9 @@
#ifdef CONFIG_SUSPEND
for (s = &pm_states[state]; state < PM_SUSPEND_MAX; s++, state++)
- if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
- return state;
+ if (s->state && len == strlen(s->label)
+ && !strncmp(buf, s->label, len))
+ return s->state;
#endif
return PM_SUSPEND_ON;
@@ -445,8 +446,8 @@
#ifdef CONFIG_SUSPEND
if (state < PM_SUSPEND_MAX)
- return sprintf(buf, "%s\n", valid_state(state) ?
- pm_states[state] : "error");
+ return sprintf(buf, "%s\n", pm_states[state].state ?
+ pm_states[state].label : "error");
#endif
#ifdef CONFIG_HIBERNATION
return sprintf(buf, "disk\n");
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 7d4b7ff..f770cad3 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -175,17 +175,20 @@
unsigned int, char *);
#ifdef CONFIG_SUSPEND
-/* kernel/power/suspend.c */
-extern const char *const pm_states[];
+struct pm_sleep_state {
+ const char *label;
+ suspend_state_t state;
+};
-extern bool valid_state(suspend_state_t state);
+/* kernel/power/suspend.c */
+extern struct pm_sleep_state pm_states[];
+
extern int suspend_devices_and_enter(suspend_state_t state);
#else /* !CONFIG_SUSPEND */
static inline int suspend_devices_and_enter(suspend_state_t state)
{
return -ENOSYS;
}
-static inline bool valid_state(suspend_state_t state) { return false; }
#endif /* !CONFIG_SUSPEND */
#ifdef CONFIG_PM_TEST_SUSPEND
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 98088e0..0695319 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -103,6 +103,28 @@
return todo ? -EBUSY : 0;
}
+/*
+ * Returns true if all freezable tasks (except for current) are frozen already
+ */
+static bool check_frozen_processes(void)
+{
+ struct task_struct *g, *p;
+ bool ret = true;
+
+ read_lock(&tasklist_lock);
+ for_each_process_thread(g, p) {
+ if (p != current && !freezer_should_skip(p) &&
+ !frozen(p)) {
+ ret = false;
+ goto done;
+ }
+ }
+done:
+ read_unlock(&tasklist_lock);
+
+ return ret;
+}
+
/**
* freeze_processes - Signal user space processes to enter the refrigerator.
*
@@ -111,6 +133,7 @@
int freeze_processes(void)
{
int error;
+ int oom_kills_saved;
error = __usermodehelper_disable(UMH_FREEZING);
if (error)
@@ -121,12 +144,27 @@
printk("Freezing user space processes ... ");
pm_freezing = true;
+ oom_kills_saved = oom_kills_count();
error = try_to_freeze_tasks(true);
if (!error) {
- printk("done.");
__usermodehelper_set_disable_depth(UMH_DISABLED);
oom_killer_disable();
+
+ /*
+ * There might have been an OOM kill while we were
+ * freezing tasks and the killed task might be still
+ * on the way out so we have to double check for race.
+ */
+ if (oom_kills_count() != oom_kills_saved &&
+ !check_frozen_processes()) {
+ __usermodehelper_set_disable_depth(UMH_ENABLED);
+ printk("OOM in progress.");
+ error = -EBUSY;
+ goto done;
+ }
+ printk("done.");
}
+done:
printk("\n");
BUG_ON(in_atomic());
@@ -174,6 +212,7 @@
printk("Restarting tasks ... ");
+ __usermodehelper_set_disable_depth(UMH_FREEZING);
thaw_workqueues();
read_lock(&tasklist_lock);
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 587ddde..8703fc7 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -293,6 +293,15 @@
}
EXPORT_SYMBOL_GPL(pm_qos_request_active);
+static void __pm_qos_update_request(struct pm_qos_request *req,
+ s32 new_value)
+{
+ if (new_value != req->node.prio)
+ pm_qos_update_target(
+ pm_qos_array[req->pm_qos_class]->constraints,
+ &req->node, PM_QOS_UPDATE_REQ, new_value);
+}
+
/**
* pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
* @work: work struct for the delayed work (timeout)
@@ -305,7 +314,7 @@
struct pm_qos_request,
work);
- pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+ __pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
}
/**
@@ -360,11 +369,7 @@
}
cancel_delayed_work_sync(&req->work);
-
- if (new_value != req->node.prio)
- pm_qos_update_target(
- pm_qos_array[req->pm_qos_class]->constraints,
- &req->node, PM_QOS_UPDATE_REQ, new_value);
+ __pm_qos_update_request(req, new_value);
}
EXPORT_SYMBOL_GPL(pm_qos_update_request);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0de2857..91c04f1 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1398,7 +1398,11 @@
* highmem and non-highmem zones separately.
*/
pages_highmem = preallocate_image_highmem(highmem / 2);
- alloc = (count - max_size) - pages_highmem;
+ alloc = count - max_size;
+ if (alloc > pages_highmem)
+ alloc -= pages_highmem;
+ else
+ alloc = 0;
pages = preallocate_image_memory(alloc, avail_normal);
if (pages < alloc) {
/* We have exhausted non-highmem pages, try highmem. */
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index bef86d1..903c517 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -29,10 +29,10 @@
#include "power.h"
-const char *const pm_states[PM_SUSPEND_MAX] = {
- [PM_SUSPEND_FREEZE] = "freeze",
- [PM_SUSPEND_STANDBY] = "standby",
- [PM_SUSPEND_MEM] = "mem",
+struct pm_sleep_state pm_states[PM_SUSPEND_MAX] = {
+ [PM_SUSPEND_FREEZE] = { .label = "freeze", .state = PM_SUSPEND_FREEZE },
+ [PM_SUSPEND_STANDBY] = { .label = "standby", },
+ [PM_SUSPEND_MEM] = { .label = "mem", },
};
static const struct platform_suspend_ops *suspend_ops;
@@ -62,42 +62,34 @@
}
EXPORT_SYMBOL_GPL(freeze_wake);
+static bool valid_state(suspend_state_t state)
+{
+ /*
+ * PM_SUSPEND_STANDBY and PM_SUSPEND_MEM states need low level
+ * support and need to be valid to the low level
+ * implementation, no valid callback implies that none are valid.
+ */
+ return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
+}
+
/**
* suspend_set_ops - Set the global suspend method table.
* @ops: Suspend operations to use.
*/
void suspend_set_ops(const struct platform_suspend_ops *ops)
{
+ suspend_state_t i;
+
lock_system_sleep();
+
suspend_ops = ops;
+ for (i = PM_SUSPEND_STANDBY; i <= PM_SUSPEND_MEM; i++)
+ pm_states[i].state = valid_state(i) ? i : 0;
+
unlock_system_sleep();
}
EXPORT_SYMBOL_GPL(suspend_set_ops);
-bool valid_state(suspend_state_t state)
-{
- if (state == PM_SUSPEND_FREEZE) {
-#ifdef CONFIG_PM_DEBUG
- if (pm_test_level != TEST_NONE &&
- pm_test_level != TEST_FREEZER &&
- pm_test_level != TEST_DEVICES &&
- pm_test_level != TEST_PLATFORM) {
- printk(KERN_WARNING "Unsupported pm_test mode for "
- "freeze state, please choose "
- "none/freezer/devices/platform.\n");
- return false;
- }
-#endif
- return true;
- }
- /*
- * PM_SUSPEND_STANDBY and PM_SUSPEND_MEMORY states need lowlevel
- * support and need to be valid to the lowlevel
- * implementation, no valid callback implies that none are valid.
- */
- return suspend_ops && suspend_ops->valid && suspend_ops->valid(state);
-}
-
/**
* suspend_valid_only_mem - Generic memory-only valid callback.
*
@@ -324,9 +316,17 @@
{
int error;
- if (!valid_state(state))
- return -ENODEV;
-
+ if (state == PM_SUSPEND_FREEZE) {
+#ifdef CONFIG_PM_DEBUG
+ if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
+ pr_warning("PM: Unsupported test mode for freeze state,"
+ "please choose none/freezer/devices/platform.\n");
+ return -EAGAIN;
+ }
+#endif
+ } else if (!valid_state(state)) {
+ return -EINVAL;
+ }
if (!mutex_trylock(&pm_mutex))
return -EBUSY;
@@ -337,7 +337,7 @@
sys_sync();
printk("done.\n");
- pr_debug("PM: Preparing system for %s sleep\n", pm_states[state]);
+ pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
error = suspend_prepare(state);
if (error)
goto Unlock;
@@ -345,7 +345,7 @@
if (suspend_test(TEST_FREEZER))
goto Finish;
- pr_debug("PM: Entering %s sleep\n", pm_states[state]);
+ pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
pm_restrict_gfp_mask();
error = suspend_devices_and_enter(state);
pm_restore_gfp_mask();
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 9b2a1d5..269b097 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -92,13 +92,13 @@
}
if (state == PM_SUSPEND_MEM) {
- printk(info_test, pm_states[state]);
+ printk(info_test, pm_states[state].label);
status = pm_suspend(state);
if (status == -ENODEV)
state = PM_SUSPEND_STANDBY;
}
if (state == PM_SUSPEND_STANDBY) {
- printk(info_test, pm_states[state]);
+ printk(info_test, pm_states[state].label);
status = pm_suspend(state);
}
if (status < 0)
@@ -136,18 +136,16 @@
static int __init setup_test_suspend(char *value)
{
- unsigned i;
+ suspend_state_t i;
/* "=mem" ==> "mem" */
value++;
- for (i = 0; i < PM_SUSPEND_MAX; i++) {
- if (!pm_states[i])
- continue;
- if (strcmp(pm_states[i], value) != 0)
- continue;
- test_state = (__force suspend_state_t) i;
- return 0;
- }
+ for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+ if (!strcmp(pm_states[i].label, value)) {
+ test_state = pm_states[i].state;
+ return 0;
+ }
+
printk(warn_bad_state, value);
return 0;
}
@@ -164,8 +162,8 @@
/* PM is initialized by now; is that state testable? */
if (test_state == PM_SUSPEND_ON)
goto done;
- if (!valid_state(test_state)) {
- printk(warn_bad_state, pm_states[test_state]);
+ if (!pm_states[test_state].state) {
+ printk(warn_bad_state, pm_states[test_state].label);
goto done;
}
diff --git a/kernel/printk.c b/kernel/printk.c
index 8212c1a..fd0154a 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -107,7 +107,7 @@
*/
struct console_cmdline
{
- char name[8]; /* Name of the driver */
+ char name[16]; /* Name of the driver */
int index; /* Minor dev. to use */
char *options; /* Options for the driver */
#ifdef CONFIG_A11Y_BRAILLE_CONSOLE
@@ -1369,9 +1369,9 @@
}
}
logbuf_cpu = UINT_MAX;
+ raw_spin_unlock(&logbuf_lock);
if (wake)
up(&console_sem);
- raw_spin_unlock(&logbuf_lock);
return retval;
}
@@ -2290,6 +2290,8 @@
*/
for (i = 0; i < MAX_CMDLINECONSOLES && console_cmdline[i].name[0];
i++) {
+ BUILD_BUG_ON(sizeof(console_cmdline[i].name) !=
+ sizeof(newcon->name));
if (strcmp(console_cmdline[i].name, newcon->name) != 0)
continue;
if (newcon->index >= 0 &&
@@ -2485,7 +2487,7 @@
preempt_enable();
}
-int printk_sched(const char *fmt, ...)
+int printk_deferred(const char *fmt, ...)
{
unsigned long flags;
va_list args;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 335a7ae..118323b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -257,7 +257,8 @@
if (task->mm)
dumpable = get_dumpable(task->mm);
rcu_read_lock();
- if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
+ if (dumpable != SUID_DUMP_USER &&
+ !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
rcu_read_unlock();
return -EPERM;
}
@@ -719,6 +720,8 @@
static int ptrace_resume(struct task_struct *child, long request,
unsigned long data)
{
+ bool need_siglock;
+
if (!valid_signal(data))
return -EIO;
@@ -746,8 +749,26 @@
user_disable_single_step(child);
}
+ /*
+ * Change ->exit_code and ->state under siglock to avoid the race
+ * with wait_task_stopped() in between; a non-zero ->exit_code will
+ * wrongly look like another report from tracee.
+ *
+ * Note that we need siglock even if ->exit_code == data and/or this
+ * status was not reported yet, the new status must not be cleared by
+ * wait_task_stopped() after resume.
+ *
+ * If data == 0 we do not care if wait_task_stopped() reports the old
+ * status and clears the code too; this can't race with the tracee, it
+ * takes siglock after resume.
+ */
+ need_siglock = data && !thread_group_empty(current);
+ if (need_siglock)
+ spin_lock_irq(&child->sighand->siglock);
child->exit_code = data;
wake_up_state(child, __TASK_TRACED);
+ if (need_siglock)
+ spin_unlock_irq(&child->sighand->siglock);
return 0;
}
diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h
index 14193d5..ab29b6a 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/rtmutex-debug.h
@@ -31,3 +31,8 @@
{
return (waiter != NULL);
}
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+ debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 1e09308..d9ca207 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -82,6 +82,47 @@
owner = *p;
} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
}
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+ __releases(lock->wait_lock)
+{
+ struct task_struct *owner = rt_mutex_owner(lock);
+
+ clear_rt_mutex_waiters(lock);
+ raw_spin_unlock(&lock->wait_lock);
+ /*
+ * If a new waiter comes in between the unlock and the cmpxchg
+ * we have two situations:
+ *
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * cmpxchg(p, owner, 0) == owner
+ * mark_rt_mutex_waiters(lock);
+ * acquire(lock);
+ * or:
+ *
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * mark_rt_mutex_waiters(lock);
+ *
+ * cmpxchg(p, owner, 0) != owner
+ * enqueue_waiter();
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * wake waiter();
+ * unlock(wait_lock);
+ * lock(wait_lock);
+ * acquire(lock);
+ */
+ return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
#else
# define rt_mutex_cmpxchg(l,c,n) (0)
static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -89,6 +130,17 @@
lock->owner = (struct task_struct *)
((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
}
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+ __releases(lock->wait_lock)
+{
+ lock->owner = NULL;
+ raw_spin_unlock(&lock->wait_lock);
+ return true;
+}
#endif
/*
@@ -142,6 +194,11 @@
*/
int max_lock_depth = 1024;
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+ return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
/*
* Adjust the priority chain. Also used for deadlock detection.
* Decreases task's usage by one - may thus free the task.
@@ -150,6 +207,7 @@
static int rt_mutex_adjust_prio_chain(struct task_struct *task,
int deadlock_detect,
struct rt_mutex *orig_lock,
+ struct rt_mutex *next_lock,
struct rt_mutex_waiter *orig_waiter,
struct task_struct *top_task)
{
@@ -183,7 +241,7 @@
}
put_task_struct(task);
- return deadlock_detect ? -EDEADLK : 0;
+ return -EDEADLK;
}
retry:
/*
@@ -208,13 +266,32 @@
goto out_unlock_pi;
/*
+ * We dropped all locks after taking a refcount on @task, so
+ * the task might have moved on in the lock chain or even left
+ * the chain completely and blocks now on an unrelated lock or
+ * on @orig_lock.
+ *
+ * We stored the lock on which @task was blocked in @next_lock,
+ * so we can detect the chain change.
+ */
+ if (next_lock != waiter->lock)
+ goto out_unlock_pi;
+
+ /*
* Drop out, when the task has no waiters. Note,
* top_waiter can be NULL, when we are in the deboosting
* mode!
*/
- if (top_waiter && (!task_has_pi_waiters(task) ||
- top_waiter != task_top_pi_waiter(task)))
- goto out_unlock_pi;
+ if (top_waiter) {
+ if (!task_has_pi_waiters(task))
+ goto out_unlock_pi;
+ /*
+ * If deadlock detection is off, we stop here if we
+ * are not the top pi waiter of the task.
+ */
+ if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
+ goto out_unlock_pi;
+ }
/*
* When deadlock detection is off then we check, if further
@@ -230,11 +307,16 @@
goto retry;
}
- /* Deadlock detection */
+ /*
+ * Deadlock detection. If the lock is the same as the original
+ * lock which caused us to walk the lock chain or if the
+ * current lock is owned by the task which initiated the chain
+ * walk, we detected a deadlock.
+ */
if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
raw_spin_unlock(&lock->wait_lock);
- ret = deadlock_detect ? -EDEADLK : 0;
+ ret = -EDEADLK;
goto out_unlock_pi;
}
@@ -281,11 +363,26 @@
__rt_mutex_adjust_prio(task);
}
+ /*
+ * Check whether the task which owns the current lock is pi
+ * blocked itself. If yes we store a pointer to the lock for
+ * the lock chain change detection above. After we dropped
+ * task->pi_lock next_lock cannot be dereferenced anymore.
+ */
+ next_lock = task_blocked_on_lock(task);
+
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
top_waiter = rt_mutex_top_waiter(lock);
raw_spin_unlock(&lock->wait_lock);
+ /*
+ * We reached the end of the lock chain. Stop right here. No
+ * point to go back just to figure that out.
+ */
+ if (!next_lock)
+ goto out_put_task;
+
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
@@ -396,8 +493,21 @@
{
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex_waiter *top_waiter = waiter;
- unsigned long flags;
+ struct rt_mutex *next_lock;
int chain_walk = 0, res;
+ unsigned long flags;
+
+ /*
+ * Early deadlock detection. We really don't want the task to
+ * enqueue on itself just to untangle the mess later. It's not
+ * only an optimization. We drop the locks, so another waiter
+ * can come in before the chain walk detects the deadlock. So
+ * the other will detect the deadlock and return -EDEADLOCK,
+ * which is wrong, as the other waiter is not in a deadlock
+ * situation.
+ */
+ if (owner == task)
+ return -EDEADLK;
raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
@@ -418,20 +528,28 @@
if (!owner)
return 0;
+ raw_spin_lock_irqsave(&owner->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
- raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
- raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
- }
- else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+ } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
chain_walk = 1;
+ }
- if (!chain_walk)
+ /* Store the lock on which owner is blocked or NULL */
+ next_lock = task_blocked_on_lock(owner);
+
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ /*
+ * Even if full deadlock detection is on, if the owner is not
+ * blocked itself, we can avoid finding this out in the chain
+ * walk.
+ */
+ if (!chain_walk || !next_lock)
return 0;
/*
@@ -443,8 +561,8 @@
raw_spin_unlock(&lock->wait_lock);
- res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
- task);
+ res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+ next_lock, waiter, task);
raw_spin_lock(&lock->wait_lock);
@@ -454,7 +572,8 @@
/*
* Wake up the next waiter on the lock.
*
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
*
* Called with lock->wait_lock held.
*/
@@ -475,10 +594,23 @@
*/
plist_del(&waiter->pi_list_entry, ¤t->pi_waiters);
- rt_mutex_set_owner(lock, NULL);
+ /*
+ * As we are waking up the top waiter, and the waiter stays
+ * queued on the lock until it gets the lock, this lock
+ * obviously has waiters. Just set the bit here and this has
+ * the added benefit of forcing all new tasks into the
+ * slow path making sure no task of lower priority than
+ * the top waiter can steal this lock.
+ */
+ lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
+ /*
+ * It's safe to dereference waiter as it cannot go away as
+ * long as we hold lock->wait_lock. The waiter task needs to
+ * acquire it in order to dequeue the waiter.
+ */
wake_up_process(waiter->task);
}
@@ -493,8 +625,8 @@
{
int first = (waiter == rt_mutex_top_waiter(lock));
struct task_struct *owner = rt_mutex_owner(lock);
+ struct rt_mutex *next_lock = NULL;
unsigned long flags;
- int chain_walk = 0;
raw_spin_lock_irqsave(¤t->pi_lock, flags);
plist_del(&waiter->list_entry, &lock->wait_list);
@@ -518,15 +650,15 @@
}
__rt_mutex_adjust_prio(owner);
- if (owner->pi_blocked_on)
- chain_walk = 1;
+ /* Store the lock on which owner is blocked or NULL */
+ next_lock = task_blocked_on_lock(owner);
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
- if (!chain_walk)
+ if (!next_lock)
return;
/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -534,7 +666,7 @@
raw_spin_unlock(&lock->wait_lock);
- rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+ rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
raw_spin_lock(&lock->wait_lock);
}
@@ -547,6 +679,7 @@
void rt_mutex_adjust_pi(struct task_struct *task)
{
struct rt_mutex_waiter *waiter;
+ struct rt_mutex *next_lock;
unsigned long flags;
raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -556,12 +689,13 @@
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
-
+ next_lock = waiter->lock;
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(task);
- rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+ rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
}
/**
@@ -613,6 +747,26 @@
return ret;
}
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+ struct rt_mutex_waiter *w)
+{
+ /*
+ * If the result is not -EDEADLOCK or the caller requested
+ * deadlock detection, nothing to do here.
+ */
+ if (res != -EDEADLOCK || detect_deadlock)
+ return;
+
+ /*
+ * Yell lowdly and stop the task right here.
+ */
+ rt_mutex_print_deadlock(w);
+ while (1) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+ }
+}
+
/*
* Slow path lock function:
*/
@@ -650,8 +804,10 @@
set_current_state(TASK_RUNNING);
- if (unlikely(ret))
+ if (unlikely(ret)) {
remove_waiter(lock, &waiter);
+ rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+ }
/*
* try_to_take_rt_mutex() sets the waiter bit
@@ -707,12 +863,49 @@
rt_mutex_deadlock_account_unlock(current);
- if (!rt_mutex_has_waiters(lock)) {
- lock->owner = NULL;
- raw_spin_unlock(&lock->wait_lock);
- return;
+ /*
+ * We must be careful here if the fast path is enabled. If we
+ * have no waiters queued we cannot set owner to NULL here
+ * because of:
+ *
+ * foo->lock->owner = NULL;
+ * rtmutex_lock(foo->lock); <- fast path
+ * free = atomic_dec_and_test(foo->refcnt);
+ * rtmutex_unlock(foo->lock); <- fast path
+ * if (free)
+ * kfree(foo);
+ * raw_spin_unlock(foo->lock->wait_lock);
+ *
+ * So for the fastpath enabled kernel:
+ *
+ * Nothing can set the waiters bit as long as we hold
+ * lock->wait_lock. So we do the following sequence:
+ *
+ * owner = rt_mutex_owner(lock);
+ * clear_rt_mutex_waiters(lock);
+ * raw_spin_unlock(&lock->wait_lock);
+ * if (cmpxchg(&lock->owner, owner, 0) == owner)
+ * return;
+ * goto retry;
+ *
+ * The fastpath disabled variant is simple as all access to
+ * lock->owner is serialized by lock->wait_lock:
+ *
+ * lock->owner = NULL;
+ * raw_spin_unlock(&lock->wait_lock);
+ */
+ while (!rt_mutex_has_waiters(lock)) {
+ /* Drops lock->wait_lock ! */
+ if (unlock_rt_mutex_safe(lock) == true)
+ return;
+ /* Relock the rtmutex and try again */
+ raw_spin_lock(&lock->wait_lock);
}
+ /*
+ * The wakeup next waiter path does not suffer from the above
+ * race. See the comments there.
+ */
wakeup_next_waiter(lock);
raw_spin_unlock(&lock->wait_lock);
@@ -959,7 +1152,8 @@
return 1;
}
- ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+ /* We enforce deadlock detection for futexes */
+ ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
if (ret && !rt_mutex_owner(lock)) {
/*
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
index a1a1dd0..f6a1f3c 100644
--- a/kernel/rtmutex.h
+++ b/kernel/rtmutex.h
@@ -24,3 +24,8 @@
#define debug_rt_mutex_print_deadlock(w) do { } while (0)
#define debug_rt_mutex_detect_deadlock(w,d) (d)
#define debug_rt_mutex_reset_waiter(w) do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+ WARN(1, "rtmutex deadlock detected\n");
+}
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 64de5f8..4a07353 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -77,8 +77,6 @@
if (IS_ERR(tg))
goto out_free;
- sched_online_group(tg, &root_task_group);
-
kref_init(&ag->kref);
init_rwsem(&ag->lock);
ag->id = atomic_inc_return(&autogroup_seq_nr);
@@ -98,6 +96,7 @@
#endif
tg->autogroup = ag;
+ sched_online_group(tg, &root_task_group);
return ag;
out_free:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e8b3350..aa08f64 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1235,7 +1235,7 @@
* leave kernel.
*/
if (p->mm && printk_ratelimit()) {
- printk_sched("process %d (%s) no longer affine to cpu%d\n",
+ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
task_pid_nr(p), p->comm, cpu);
}
}
@@ -1407,7 +1407,11 @@
{
if (llist_empty(&this_rq()->wake_list)
&& !tick_nohz_full_cpu(smp_processor_id())
- && !got_nohz_idle_kick())
+ && !got_nohz_idle_kick()
+#ifdef CONFIG_SCHED_HMP
+ && !this_rq()->wake_for_idle_pull
+#endif
+ )
return;
/*
@@ -1434,6 +1438,11 @@
this_rq()->idle_balance = 1;
raise_softirq_irqoff(SCHED_SOFTIRQ);
}
+#ifdef CONFIG_SCHED_HMP
+ else if (unlikely(this_rq()->wake_for_idle_pull))
+ raise_softirq_irqoff(SCHED_SOFTIRQ);
+#endif
+
irq_exit();
}
@@ -1487,7 +1496,13 @@
unsigned long flags;
int cpu, success = 0;
- smp_wmb();
+ /*
+ * If we are going to wake up a thread waiting for CONDITION we
+ * need to ensure that CONDITION=1 done by the caller can not be
+ * reordered with p->state check below. This pairs with mb() in
+ * set_current_state() the waiting thread does.
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irqsave(&p->pi_lock, flags);
if (!(p->state & state))
goto out;
@@ -1617,6 +1632,20 @@
#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
p->se.avg.runnable_avg_period = 0;
p->se.avg.runnable_avg_sum = 0;
+#ifdef CONFIG_SCHED_HMP
+ /* keep LOAD_AVG_MAX in sync with fair.c if load avg series is changed */
+#define LOAD_AVG_MAX 47742
+ p->se.avg.hmp_last_up_migration = 0;
+ p->se.avg.hmp_last_down_migration = 0;
+ if (hmp_task_should_forkboost(p)) {
+ p->se.avg.load_avg_ratio = 1023;
+ p->se.avg.load_avg_contrib =
+ (1023 * scale_load_down(p->se.load.weight));
+ p->se.avg.runnable_avg_period = LOAD_AVG_MAX;
+ p->se.avg.runnable_avg_sum = LOAD_AVG_MAX;
+ p->se.avg.usage_avg_sum = LOAD_AVG_MAX;
+ }
+#endif
#endif
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2966,6 +2995,12 @@
if (sched_feat(HRTICK))
hrtick_clear(rq);
+ /*
+ * Make sure that signal_pending_state()->signal_pending() below
+ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
+ * done by the caller to avoid the race with signal_wake_up().
+ */
+ smp_mb__before_spinlock();
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
@@ -3813,6 +3848,8 @@
return pid ? find_task_by_vpid(pid) : current;
}
+extern struct cpumask hmp_slow_cpu_mask;
+
/* Actually do priority change: must hold rq lock. */
static void
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
@@ -3822,8 +3859,17 @@
p->normal_prio = normal_prio(p);
/* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
- if (rt_prio(p->prio))
+ if (rt_prio(p->prio)) {
p->sched_class = &rt_sched_class;
+#ifdef CONFIG_SCHED_HMP
+ if (!cpumask_empty(&hmp_slow_cpu_mask))
+ if (cpumask_equal(&p->cpus_allowed, cpu_all_mask)) {
+ p->nr_cpus_allowed =
+ cpumask_weight(&hmp_slow_cpu_mask);
+ do_set_cpus_allowed(p, &hmp_slow_cpu_mask);
+ }
+#endif
+ }
else
p->sched_class = &fair_sched_class;
set_load_weight(p);
@@ -5258,7 +5304,6 @@
unsigned long action, void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
- case CPU_STARTING:
case CPU_DOWN_FAILED:
set_cpu_active((long)hcpu, true);
return NOTIFY_OK;
@@ -7800,7 +7845,12 @@
runtime_enabled = quota != RUNTIME_INF;
runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
- account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled);
+ /*
+ * If we need to toggle cfs_bandwidth_used, off->on must occur
+ * before making related changes, and on->off must occur afterwards
+ */
+ if (runtime_enabled && !runtime_was_enabled)
+ cfs_bandwidth_usage_inc();
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
@@ -7826,6 +7876,8 @@
unthrottle_cfs_rq(cfs_rq);
raw_spin_unlock_irq(&rq->lock);
}
+ if (runtime_was_enabled && !runtime_enabled)
+ cfs_bandwidth_usage_dec();
out_unlock:
mutex_unlock(&cfs_constraints_mutex);
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 1095e87..b3f0a27 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@
int idx = 0;
int task_pri = convert_prio(p->prio);
- if (task_pri >= MAX_RT_PRIO)
- return 0;
+ BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
for (idx = 0; idx < task_pri; idx++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index b5ccba2..c23a8fd 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -326,50 +326,50 @@
* softirq as those do not count in task exec_runtime any more.
*/
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq)
+ struct rq *rq, int ticks)
{
- cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+ u64 cputime = (__force u64) cputime_one_jiffy;
u64 *cpustat = kcpustat_this_cpu->cpustat;
if (steal_account_process_tick())
return;
+ cputime *= ticks;
+ scaled *= ticks;
+
if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_IRQ] += cputime;
} else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+ cpustat[CPUTIME_SOFTIRQ] += cputime;
} else if (this_cpu_ksoftirqd() == p) {
/*
* ksoftirqd time do not get accounted in cpu_softirq_time.
* So, we have to handle it separately here.
* Also, p->stime needs to be updated for ksoftirqd.
*/
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SOFTIRQ);
+ __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
} else if (user_tick) {
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ account_user_time(p, cputime, scaled);
} else if (p == rq->idle) {
- account_idle_time(cputime_one_jiffy);
+ account_idle_time(cputime);
} else if (p->flags & PF_VCPU) { /* System time or guest time */
- account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ account_guest_time(p, cputime, scaled);
} else {
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SYSTEM);
+ __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM);
}
}
static void irqtime_account_idle_ticks(int ticks)
{
- int i;
struct rq *rq = this_rq();
- for (i = 0; i < ticks; i++)
- irqtime_account_process_tick(current, 0, rq);
+ irqtime_account_process_tick(current, 0, rq, ticks);
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
static inline void irqtime_account_idle_ticks(int ticks) {}
static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq) {}
+ struct rq *rq, int nr_ticks) {}
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
/*
@@ -464,7 +464,7 @@
return;
if (sched_clock_irqtime) {
- irqtime_account_process_tick(p, user_tick, rq);
+ irqtime_account_process_tick(p, user_tick, rq, 1);
return;
}
@@ -558,7 +558,7 @@
struct cputime *prev,
cputime_t *ut, cputime_t *st)
{
- cputime_t rtime, stime, utime, total;
+ cputime_t rtime, stime, utime;
if (vtime_accounting_enabled()) {
*ut = curr->utime;
@@ -566,9 +566,6 @@
return;
}
- stime = curr->stime;
- total = stime + curr->utime;
-
/*
* Tick based cputime accounting depend on random scheduling
* timeslices of a task to be interrupted or not by the timer.
@@ -589,13 +586,19 @@
if (prev->stime + prev->utime >= rtime)
goto out;
- if (total) {
+ stime = curr->stime;
+ utime = curr->utime;
+
+ if (utime == 0) {
+ stime = rtime;
+ } else if (stime == 0) {
+ utime = rtime;
+ } else {
+ cputime_t total = stime + utime;
+
stime = scale_stime((__force u64)stime,
(__force u64)rtime, (__force u64)total);
utime = rtime - stime;
- } else {
- stime = rtime;
- utime = 0;
}
/*
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 75024a6..1e23284 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -94,6 +94,7 @@
#ifdef CONFIG_SMP
P(se->avg.runnable_avg_sum);
P(se->avg.runnable_avg_period);
+ P(se->avg.usage_avg_sum);
P(se->avg.load_avg_contrib);
P(se->avg.decay_count);
#endif
@@ -223,6 +224,16 @@
cfs_rq->tg_runnable_contrib);
SEQ_printf(m, " .%-30s: %d\n", "tg->runnable_avg",
atomic_read(&cfs_rq->tg->runnable_avg));
+ SEQ_printf(m, " .%-30s: %d\n", "tg->usage_avg",
+ atomic_read(&cfs_rq->tg->usage_avg));
+#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+ SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+ cfs_rq->tg->cfs_bandwidth.timer_active);
+ SEQ_printf(m, " .%-30s: %d\n", "throttled",
+ cfs_rq->throttled);
+ SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
+ cfs_rq->throttle_count);
#endif
print_cfs_group_stats(m, cpu, cfs_rq->tg);
@@ -543,7 +554,7 @@
avg_atom = p->se.sum_exec_runtime;
if (nr_switches)
- do_div(avg_atom, nr_switches);
+ avg_atom = div64_ul(avg_atom, nr_switches);
else
avg_atom = -1LL;
@@ -566,6 +577,12 @@
"nr_involuntary_switches", (long long)p->nivcsw);
P(se.load.weight);
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+ P(se.avg.runnable_avg_sum);
+ P(se.avg.runnable_avg_period);
+ P(se.avg.load_avg_contrib);
+ P(se.avg.decay_count);
+#endif
P(policy);
P(prio);
#undef PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c61a614..1baf641 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -31,9 +31,21 @@
#include <linux/task_work.h>
#include <trace/events/sched.h>
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Include cpufreq header to add a notifier so that cpu frequency
+ * scaling can track the current CPU frequency
+ */
+#include <linux/cpufreq.h>
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#ifdef CONFIG_SCHED_HMP
+#include <linux/cpuidle.h>
+#endif
#include "sched.h"
+
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
@@ -936,6 +948,13 @@
if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
continue;
+ /*
+ * Skip inaccessible VMAs to avoid any confusion between
+ * PROT_NONE and NUMA hinting ptes
+ */
+ if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+ continue;
+
do {
start = max(start, vma->vm_start);
end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE);
@@ -1201,8 +1220,91 @@
return contrib + runnable_avg_yN_sum[n];
}
-/*
- * We can represent the historical contribution to runnable average as the
+#ifdef CONFIG_SCHED_HMP
+#define HMP_VARIABLE_SCALE_SHIFT 16ULL
+struct hmp_global_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct kobject *kobj,
+ struct attribute *attr, char *buf);
+ ssize_t (*store)(struct kobject *a, struct attribute *b,
+ const char *c, size_t count);
+ int *value;
+ int (*to_sysfs)(int);
+ int (*from_sysfs)(int);
+ ssize_t (*to_sysfs_text)(char *buf, int buf_size);
+};
+
+#define HMP_DATA_SYSFS_MAX 8
+
+struct hmp_data_struct {
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ int freqinvar_load_scale_enabled;
+#endif
+ int multiplier; /* used to scale the time delta */
+ struct attribute_group attr_group;
+ struct attribute *attributes[HMP_DATA_SYSFS_MAX + 1];
+ struct hmp_global_attr attr[HMP_DATA_SYSFS_MAX];
+} hmp_data;
+
+static u64 hmp_variable_scale_convert(u64 delta);
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+/* Frequency-Invariant Load Modification:
+ * Loads are calculated as in PJT's patch however we also scale the current
+ * contribution in line with the frequency of the CPU that the task was
+ * executed on.
+ * In this version, we use a simple linear scale derived from the maximum
+ * frequency reported by CPUFreq. As an example:
+ *
+ * Consider that we ran a task for 100% of the previous interval.
+ *
+ * Our CPU was under asynchronous frequency control through one of the
+ * CPUFreq governors.
+ *
+ * The CPUFreq governor reports that it is able to scale the CPU between
+ * 500MHz and 1GHz.
+ *
+ * During the period, the CPU was running at 1GHz.
+ *
+ * In this case, our load contribution for that period is calculated as
+ * 1 * (number_of_active_microseconds)
+ *
+ * This results in our task being able to accumulate maximum load as normal.
+ *
+ *
+ * Consider now that our CPU was executing at 500MHz.
+ *
+ * We now scale the load contribution such that it is calculated as
+ * 0.5 * (number_of_active_microseconds)
+ *
+ * Our task can only record 50% maximum load during this period.
+ *
+ * This represents the task consuming 50% of the CPU's *possible* compute
+ * capacity. However the task did consume 100% of the CPU's *available*
+ * compute capacity which is the value seen by the CPUFreq governor and
+ * user-side CPU Utilization tools.
+ *
+ * Restricting tracked load to be scaled by the CPU's frequency accurately
+ * represents the consumption of possible compute capacity and allows the
+ * HMP migration's simple threshold migration strategy to interact more
+ * predictably with CPUFreq's asynchronous compute capacity changes.
+ */
+#define SCHED_FREQSCALE_SHIFT 10
+struct cpufreq_extents {
+ u32 curr_scale;
+ u32 min;
+ u32 max;
+ u32 flags;
+};
+/* Flag set when the governor in use only allows one frequency.
+ * Disables scaling.
+ */
+#define SCHED_LOAD_FREQINVAR_SINGLEFREQ 0x01
+
+static struct cpufreq_extents freq_scale[CONFIG_NR_CPUS];
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+#endif /* CONFIG_SCHED_HMP */
+
+/* We can represent the historical contribution to runnable average as the
* coefficients of a geometric series. To do this we sub-divide our runnable
* history into segments of approximately 1ms (1024us); label the segment that
* occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
@@ -1231,13 +1333,24 @@
*/
static __always_inline int __update_entity_runnable_avg(u64 now,
struct sched_avg *sa,
- int runnable)
+ int runnable,
+ int running,
+ int cpu)
{
u64 delta, periods;
u32 runnable_contrib;
int delta_w, decayed = 0;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ u64 scaled_delta;
+ u32 scaled_runnable_contrib;
+ int scaled_delta_w;
+ u32 curr_scale = 1024;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
delta = now - sa->last_runnable_update;
+#ifdef CONFIG_SCHED_HMP
+ delta = hmp_variable_scale_convert(delta);
+#endif
/*
* This should only happen when time goes backwards, which it
* unfortunately does during sched clock init when we swap over to TSC.
@@ -1256,6 +1369,12 @@
return 0;
sa->last_runnable_update = now;
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ /* retrieve scale factor for load */
+ if (hmp_data.freqinvar_load_scale_enabled)
+ curr_scale = freq_scale[cpu].curr_scale;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
+
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->runnable_avg_period % 1024;
if (delta + delta_w >= 1024) {
@@ -1268,8 +1387,20 @@
* period and accrue it.
*/
delta_w = 1024 - delta_w;
+ /* scale runnable time if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_delta_w = (delta_w * curr_scale)
+ >> SCHED_FREQSCALE_SHIFT;
+ if (runnable)
+ sa->runnable_avg_sum += scaled_delta_w;
+ if (running)
+ sa->usage_avg_sum += scaled_delta_w;
+#else
if (runnable)
sa->runnable_avg_sum += delta_w;
+ if (running)
+ sa->usage_avg_sum += delta_w;
+#endif /* #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += delta_w;
delta -= delta_w;
@@ -1277,22 +1408,49 @@
/* Figure out how many additional periods this update spans */
periods = delta / 1024;
delta %= 1024;
-
+ /* decay the load we have accumulated so far */
sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
periods + 1);
sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
periods + 1);
-
+ sa->usage_avg_sum = decay_load(sa->usage_avg_sum, periods + 1);
+ /* add the contribution from this period */
/* Efficiently calculate \sum (1..n_period) 1024*y^i */
runnable_contrib = __compute_runnable_contrib(periods);
+ /* Apply load scaling if necessary.
+ * Note that multiplying the whole series is same as
+ * multiplying all terms
+ */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_runnable_contrib = (runnable_contrib * curr_scale)
+ >> SCHED_FREQSCALE_SHIFT;
+ if (runnable)
+ sa->runnable_avg_sum += scaled_runnable_contrib;
+ if (running)
+ sa->usage_avg_sum += scaled_runnable_contrib;
+#else
if (runnable)
sa->runnable_avg_sum += runnable_contrib;
+ if (running)
+ sa->usage_avg_sum += runnable_contrib;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += runnable_contrib;
}
/* Remainder of delta accrued against u_0` */
+ /* scale if necessary */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ scaled_delta = ((delta * curr_scale) >> SCHED_FREQSCALE_SHIFT);
+ if (runnable)
+ sa->runnable_avg_sum += scaled_delta;
+ if (running)
+ sa->usage_avg_sum += scaled_delta;
+#else
if (runnable)
sa->runnable_avg_sum += delta;
+ if (running)
+ sa->usage_avg_sum += delta;
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
sa->runnable_avg_period += delta;
return decayed;
@@ -1305,12 +1463,9 @@
u64 decays = atomic64_read(&cfs_rq->decay_counter);
decays -= se->avg.decay_count;
- if (!decays)
- return 0;
-
- se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+ if (decays)
+ se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
se->avg.decay_count = 0;
-
return decays;
}
@@ -1338,16 +1493,28 @@
struct cfs_rq *cfs_rq)
{
struct task_group *tg = cfs_rq->tg;
- long contrib;
+ long contrib, usage_contrib;
/* The fraction of a cpu used by this cfs_rq */
contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT,
sa->runnable_avg_period + 1);
contrib -= cfs_rq->tg_runnable_contrib;
- if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
+ usage_contrib = div_u64(sa->usage_avg_sum << NICE_0_SHIFT,
+ sa->runnable_avg_period + 1);
+ usage_contrib -= cfs_rq->tg_usage_contrib;
+
+ /*
+ * contrib/usage at this point represent deltas, only update if they
+ * are substantive.
+ */
+ if ((abs(contrib) > cfs_rq->tg_runnable_contrib / 64) ||
+ (abs(usage_contrib) > cfs_rq->tg_usage_contrib / 64)) {
atomic_add(contrib, &tg->runnable_avg);
cfs_rq->tg_runnable_contrib += contrib;
+
+ atomic_add(usage_contrib, &tg->usage_avg);
+ cfs_rq->tg_usage_contrib += usage_contrib;
}
}
@@ -1408,12 +1575,18 @@
contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
contrib /= (se->avg.runnable_avg_period + 1);
se->avg.load_avg_contrib = scale_load(contrib);
+ trace_sched_task_load_contrib(task_of(se), se->avg.load_avg_contrib);
+ contrib = se->avg.runnable_avg_sum * scale_load_down(NICE_0_LOAD);
+ contrib /= (se->avg.runnable_avg_period + 1);
+ se->avg.load_avg_ratio = scale_load(contrib);
+ trace_sched_task_runnable_ratio(task_of(se), se->avg.load_avg_ratio);
}
/* Compute the current contribution to load_avg by se, return any delta */
-static long __update_entity_load_avg_contrib(struct sched_entity *se)
+static long __update_entity_load_avg_contrib(struct sched_entity *se, long *ratio)
{
long old_contrib = se->avg.load_avg_contrib;
+ long old_ratio = se->avg.load_avg_ratio;
if (entity_is_task(se)) {
__update_task_entity_contrib(se);
@@ -1422,6 +1595,8 @@
__update_group_entity_contrib(se);
}
+ if (ratio)
+ *ratio = se->avg.load_avg_ratio - old_ratio;
return se->avg.load_avg_contrib - old_contrib;
}
@@ -1441,9 +1616,13 @@
int update_cfs_rq)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
- long contrib_delta;
+ long contrib_delta, ratio_delta;
u64 now;
+ int cpu = -1; /* not used in normal case */
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ cpu = cfs_rq->rq->cpu;
+#endif
/*
* For a group entity we need to use their owned cfs_rq_clock_task() in
* case they are the parent of a throttled hierarchy.
@@ -1453,18 +1632,21 @@
else
now = cfs_rq_clock_task(group_cfs_rq(se));
- if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+ if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
+ cfs_rq->curr == se, cpu))
return;
- contrib_delta = __update_entity_load_avg_contrib(se);
+ contrib_delta = __update_entity_load_avg_contrib(se, &ratio_delta);
if (!update_cfs_rq)
return;
- if (se->on_rq)
+ if (se->on_rq) {
cfs_rq->runnable_load_avg += contrib_delta;
- else
+ rq_of(cfs_rq)->avg.load_avg_ratio += ratio_delta;
+ } else {
subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+ }
}
/*
@@ -1497,8 +1679,17 @@
static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
{
- __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+ int cpu = -1; /* not used in normal case */
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ cpu = rq->cpu;
+#endif
+ __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable,
+ runnable, cpu);
__update_tg_runnable_avg(&rq->avg, &rq->cfs);
+ trace_sched_rq_runnable_ratio(cpu_of(rq), rq->avg.load_avg_ratio);
+ trace_sched_rq_runnable_load(cpu_of(rq), rq->cfs.runnable_load_avg);
+ trace_sched_rq_nr_running(cpu_of(rq), rq->nr_running, rq->nr_iowait.counter);
}
/* Add the load generated by se into cfs_rq's child load-average */
@@ -1540,6 +1731,8 @@
}
cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+ rq_of(cfs_rq)->avg.load_avg_ratio += se->avg.load_avg_ratio;
+
/* we force update consideration on load-balancer moves */
update_cfs_rq_blocked_load(cfs_rq, !wakeup);
}
@@ -1558,6 +1751,8 @@
update_cfs_rq_blocked_load(cfs_rq, !sleep);
cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+ rq_of(cfs_rq)->avg.load_avg_ratio -= se->avg.load_avg_ratio;
+
if (sleep) {
cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -1886,6 +2081,7 @@
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
+ update_entity_load_avg(se, 1);
}
update_stats_curr_start(cfs_rq, se);
@@ -1984,6 +2180,7 @@
*/
update_entity_load_avg(curr, 1);
update_cfs_rq_blocked_load(cfs_rq, 1);
+ update_cfs_shares(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -2021,13 +2218,14 @@
return static_key_false(&__cfs_bandwidth_used);
}
-void account_cfs_bandwidth_used(int enabled, int was_enabled)
+void cfs_bandwidth_usage_inc(void)
{
- /* only need to count groups transitioning between enabled/!enabled */
- if (enabled && !was_enabled)
- static_key_slow_inc(&__cfs_bandwidth_used);
- else if (!enabled && was_enabled)
- static_key_slow_dec(&__cfs_bandwidth_used);
+ static_key_slow_inc(&__cfs_bandwidth_used);
+}
+
+void cfs_bandwidth_usage_dec(void)
+{
+ static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
@@ -2035,7 +2233,8 @@
return true;
}
-void account_cfs_bandwidth_used(int enabled, int was_enabled) {}
+void cfs_bandwidth_usage_inc(void) {}
+void cfs_bandwidth_usage_dec(void) {}
#endif /* HAVE_JUMP_LABEL */
/*
@@ -2287,6 +2486,8 @@
cfs_rq->throttled_clock = rq->clock;
raw_spin_lock(&cfs_b->lock);
list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (!cfs_b->timer_active)
+ __start_cfs_bandwidth(cfs_b);
raw_spin_unlock(&cfs_b->lock);
}
@@ -2398,6 +2599,13 @@
if (idle)
goto out_unlock;
+ /*
+ * if we have relooped after returning idle once, we need to update our
+ * status as actually running, so that other cpus doing
+ * __start_cfs_bandwidth will stop trying to cancel us.
+ */
+ cfs_b->timer_active = 1;
+
__refill_cfs_bandwidth_runtime(cfs_b);
if (!throttled) {
@@ -2458,7 +2666,13 @@
/* how long we wait to gather additional slack before distributing */
static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC;
-/* are we near the end of the current quota period? */
+/*
+ * Are we near the end of the current quota period?
+ *
+ * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the
+ * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of
+ * migrate_hrtimers, base is never cleared, so we are fine.
+ */
static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire)
{
struct hrtimer *refresh_timer = &cfs_b->period_timer;
@@ -2534,10 +2748,12 @@
u64 expires;
/* confirm we're still not at a refresh boundary */
- if (runtime_refresh_within(cfs_b, min_bandwidth_expiration))
- return;
-
raw_spin_lock(&cfs_b->lock);
+ if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
+ raw_spin_unlock(&cfs_b->lock);
+ return;
+ }
+
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
runtime = cfs_b->runtime;
cfs_b->runtime = 0;
@@ -2662,11 +2878,11 @@
* (timer_active==0 becomes visible before the hrtimer call-back
* terminates). In either case we ensure that it's re-programmed
*/
- while (unlikely(hrtimer_active(&cfs_b->period_timer))) {
+ while (unlikely(hrtimer_active(&cfs_b->period_timer)) &&
+ hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) {
+ /* bounce the lock to allow do_sched_cfs_period_timer to run */
raw_spin_unlock(&cfs_b->lock);
- /* ensure cfs_b->lock is available while we wait */
- hrtimer_cancel(&cfs_b->period_timer);
-
+ cpu_relax();
raw_spin_lock(&cfs_b->lock);
/* if someone else restarted the timer then we're done */
if (cfs_b->timer_active)
@@ -3314,6 +3530,835 @@
return target;
}
+#ifdef CONFIG_SCHED_HMP
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * The cpu types are distinguished using a list of hmp_domains
+ * which each represent one cpu type using a cpumask.
+ * The list is assumed ordered by compute capacity with the
+ * fastest domain first.
+ */
+DEFINE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+static const int hmp_max_tasks = 5;
+
+extern void __init arch_get_hmp_domains(struct list_head *hmp_domains_list);
+
+#ifdef CONFIG_CPU_IDLE
+/*
+ * hmp_idle_pull:
+ *
+ * In this version we have stopped using forced up migrations when we
+ * detect that a task running on a little CPU should be moved to a bigger
+ * CPU. In most cases, the bigger CPU is in a deep sleep state and a forced
+ * migration means we stop the task immediately but need to wait for the
+ * target CPU to wake up before we can restart the task which is being
+ * moved. Instead, we now wake a big CPU with an IPI and ask it to pull
+ * a task when ready. This allows the task to continue executing on its
+ * current CPU, reducing the amount of time that the task is stalled for.
+ *
+ * keepalive timers:
+ *
+ * The keepalive timer is used as a way to keep a CPU engaged in an
+ * idle pull operation out of idle while waiting for the source
+ * CPU to stop and move the task. Ideally this would not be necessary
+ * and we could impose a temporary zero-latency requirement on the
+ * current CPU, but in the current QoS framework this will result in
+ * all CPUs in the system being unable to enter idle states which is
+ * not desirable. The timer does not perform any work when it expires.
+ */
+struct hmp_keepalive {
+ bool init;
+ ktime_t delay; /* if zero, no need for timer */
+ struct hrtimer timer;
+};
+DEFINE_PER_CPU(struct hmp_keepalive, hmp_cpu_keepalive);
+
+/* setup per-cpu keepalive timers */
+static enum hrtimer_restart hmp_cpu_keepalive_notify(struct hrtimer *hrtimer)
+{
+ return HRTIMER_NORESTART;
+}
+
+/*
+ * Work out if any of the idle states have an exit latency too high for us.
+ * ns_delay is passed in containing the max we are willing to tolerate.
+ * If there are none, set ns_delay to zero.
+ * If there are any, set ns_delay to
+ * ('target_residency of state with shortest too-big latency' - 1) * 1000.
+ */
+static void hmp_keepalive_delay(int cpu, unsigned int *ns_delay)
+{
+ struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
+ struct cpuidle_driver *drv;
+
+ drv = cpuidle_get_cpu_driver(dev);
+ if (drv) {
+ unsigned int us_delay = UINT_MAX;
+ unsigned int us_max_delay = *ns_delay / 1000;
+ int idx;
+ /* if cpuidle states are guaranteed to be sorted we
+ * could stop at the first match.
+ */
+ for (idx = 0; idx < drv->state_count; idx++) {
+ if (drv->states[idx].exit_latency > us_max_delay &&
+ drv->states[idx].target_residency < us_delay) {
+ us_delay = drv->states[idx].target_residency;
+ }
+ }
+ if (us_delay == UINT_MAX)
+ *ns_delay = 0; /* no timer required */
+ else
+ *ns_delay = 1000 * (us_delay - 1);
+ }
+}
+
+static void hmp_cpu_keepalive_trigger(void)
+{
+ int cpu = smp_processor_id();
+ struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+ if (!keepalive->init) {
+ unsigned int ns_delay = 100000; /* tolerate 100usec delay */
+
+ hrtimer_init(&keepalive->timer,
+ CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+ keepalive->timer.function = hmp_cpu_keepalive_notify;
+
+ hmp_keepalive_delay(cpu, &ns_delay);
+ keepalive->delay = ns_to_ktime(ns_delay);
+ keepalive->init = true;
+ }
+ if (ktime_to_ns(keepalive->delay))
+ hrtimer_start(&keepalive->timer,
+ keepalive->delay, HRTIMER_MODE_REL_PINNED);
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+ struct hmp_keepalive *keepalive = &per_cpu(hmp_cpu_keepalive, cpu);
+ if (keepalive->init)
+ hrtimer_cancel(&keepalive->timer);
+}
+#else /* !CONFIG_CPU_IDLE */
+static void hmp_cpu_keepalive_trigger(void)
+{
+}
+
+static void hmp_cpu_keepalive_cancel(int cpu)
+{
+}
+#endif
+
+/* Setup hmp_domains */
+static int __init hmp_cpu_mask_setup(void)
+{
+ char buf[64];
+ struct hmp_domain *domain;
+ struct list_head *pos;
+ int dc, cpu;
+
+ pr_debug("Initializing HMP scheduler:\n");
+
+ /* Initialize hmp_domains using platform code */
+ arch_get_hmp_domains(&hmp_domains);
+ if (list_empty(&hmp_domains)) {
+ pr_debug("HMP domain list is empty!\n");
+ return 0;
+ }
+
+ /* Print hmp_domains */
+ dc = 0;
+ list_for_each(pos, &hmp_domains) {
+ domain = list_entry(pos, struct hmp_domain, hmp_domains);
+ cpulist_scnprintf(buf, 64, &domain->possible_cpus);
+ pr_debug(" HMP domain %d: %s\n", dc, buf);
+
+ for_each_cpu_mask(cpu, domain->possible_cpus) {
+ per_cpu(hmp_cpu_domain, cpu) = domain;
+ }
+ dc++;
+ }
+
+ return 1;
+}
+
+static struct hmp_domain *hmp_get_hmp_domain_for_cpu(int cpu)
+{
+ struct hmp_domain *domain;
+ struct list_head *pos;
+
+ list_for_each(pos, &hmp_domains) {
+ domain = list_entry(pos, struct hmp_domain, hmp_domains);
+ if(cpumask_test_cpu(cpu, &domain->possible_cpus))
+ return domain;
+ }
+ return NULL;
+}
+
+static void hmp_online_cpu(int cpu)
+{
+ struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+ if(domain)
+ cpumask_set_cpu(cpu, &domain->cpus);
+}
+
+static void hmp_offline_cpu(int cpu)
+{
+ struct hmp_domain *domain = hmp_get_hmp_domain_for_cpu(cpu);
+
+ if(domain)
+ cpumask_clear_cpu(cpu, &domain->cpus);
+
+ hmp_cpu_keepalive_cancel(cpu);
+}
+/*
+ * Needed to determine heaviest tasks etc.
+ */
+static inline unsigned int hmp_cpu_is_fastest(int cpu);
+static inline unsigned int hmp_cpu_is_slowest(int cpu);
+static inline struct hmp_domain *hmp_slower_domain(int cpu);
+static inline struct hmp_domain *hmp_faster_domain(int cpu);
+
+/* must hold runqueue lock for queue se is currently on */
+static struct sched_entity *hmp_get_heaviest_task(
+ struct sched_entity *se, int target_cpu)
+{
+ int num_tasks = hmp_max_tasks;
+ struct sched_entity *max_se = se;
+ unsigned long int max_ratio = se->avg.load_avg_ratio;
+ const struct cpumask *hmp_target_mask = NULL;
+ struct hmp_domain *hmp;
+
+ if (hmp_cpu_is_fastest(cpu_of(se->cfs_rq->rq)))
+ return max_se;
+
+ hmp = hmp_faster_domain(cpu_of(se->cfs_rq->rq));
+ hmp_target_mask = &hmp->cpus;
+ if (target_cpu >= 0) {
+ /* idle_balance gets run on a CPU while
+ * it is in the middle of being hotplugged
+ * out. Bail early in that case.
+ */
+ if(!cpumask_test_cpu(target_cpu, hmp_target_mask))
+ return NULL;
+ hmp_target_mask = cpumask_of(target_cpu);
+ }
+ /* The currently running task is not on the runqueue */
+ se = __pick_first_entity(cfs_rq_of(se));
+
+ while (num_tasks && se) {
+ if (entity_is_task(se) &&
+ se->avg.load_avg_ratio > max_ratio &&
+ cpumask_intersects(hmp_target_mask,
+ tsk_cpus_allowed(task_of(se)))) {
+ max_se = se;
+ max_ratio = se->avg.load_avg_ratio;
+ }
+ se = __pick_next_entity(se);
+ num_tasks--;
+ }
+ return max_se;
+}
+
+static struct sched_entity *hmp_get_lightest_task(
+ struct sched_entity *se, int migrate_down)
+{
+ int num_tasks = hmp_max_tasks;
+ struct sched_entity *min_se = se;
+ unsigned long int min_ratio = se->avg.load_avg_ratio;
+ const struct cpumask *hmp_target_mask = NULL;
+
+ if (migrate_down) {
+ struct hmp_domain *hmp;
+ if (hmp_cpu_is_slowest(cpu_of(se->cfs_rq->rq)))
+ return min_se;
+ hmp = hmp_slower_domain(cpu_of(se->cfs_rq->rq));
+ hmp_target_mask = &hmp->cpus;
+ }
+ /* The currently running task is not on the runqueue */
+ se = __pick_first_entity(cfs_rq_of(se));
+
+ while (num_tasks && se) {
+ if (entity_is_task(se) &&
+ (se->avg.load_avg_ratio < min_ratio &&
+ hmp_target_mask &&
+ cpumask_intersects(hmp_target_mask,
+ tsk_cpus_allowed(task_of(se))))) {
+ min_se = se;
+ min_ratio = se->avg.load_avg_ratio;
+ }
+ se = __pick_next_entity(se);
+ num_tasks--;
+ }
+ return min_se;
+}
+
+/*
+ * Migration thresholds should be in the range [0..1023]
+ * hmp_up_threshold: min. load required for migrating tasks to a faster cpu
+ * hmp_down_threshold: max. load allowed for tasks migrating to a slower cpu
+ *
+ * hmp_up_prio: Only up migrate task with high priority (<hmp_up_prio)
+ * hmp_next_up_threshold: Delay before next up migration (1024 ~= 1 ms)
+ * hmp_next_down_threshold: Delay before next down migration (1024 ~= 1 ms)
+ *
+ * Small Task Packing:
+ * We can choose to fill the littlest CPUs in an HMP system rather than
+ * the typical spreading mechanic. This behavior is controllable using
+ * two variables.
+ * hmp_packing_enabled: runtime control over pack/spread
+ * hmp_full_threshold: Consider a CPU with this much unweighted load full
+ */
+unsigned int hmp_up_threshold = 700;
+unsigned int hmp_down_threshold = 512;
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+unsigned int hmp_up_prio = NICE_TO_PRIO(CONFIG_SCHED_HMP_PRIO_FILTER_VAL);
+#endif
+unsigned int hmp_next_up_threshold = 4096;
+unsigned int hmp_next_down_threshold = 4096;
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Set the default packing threshold to try to keep little
+ * CPUs at no more than 80% of their maximum frequency if only
+ * packing a small number of small tasks. Bigger tasks will
+ * raise frequency as normal.
+ * In order to pack a task onto a CPU, the sum of the
+ * unweighted runnable_avg load of existing tasks plus the
+ * load of the new task must be less than hmp_full_threshold.
+ *
+ * This works in conjunction with frequency-invariant load
+ * and DVFS governors. Since most DVFS governors aim for 80%
+ * utilisation, we arrive at (0.8*0.8*(max_load=1024))=655
+ * and use a value slightly lower to give a little headroom
+ * in the decision.
+ * Note that the most efficient frequency is different for
+ * each system so /sys/kernel/hmp/packing_limit should be
+ * configured at runtime for any given platform to achieve
+ * optimal energy usage. Some systems may not benefit from
+ * packing, so this feature can also be disabled at runtime
+ * with /sys/kernel/hmp/packing_enable
+ */
+unsigned int hmp_packing_enabled = 1;
+unsigned int hmp_full_threshold = 650;
+#endif
+
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se);
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se);
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+ int *min_cpu, struct cpumask *affinity);
+
+static inline struct hmp_domain *hmp_smallest_domain(void)
+{
+ return list_entry(hmp_domains.prev, struct hmp_domain, hmp_domains);
+}
+
+/* Check if cpu is in fastest hmp_domain */
+static inline unsigned int hmp_cpu_is_fastest(int cpu)
+{
+ struct list_head *pos;
+
+ pos = &hmp_cpu_domain(cpu)->hmp_domains;
+ return pos == hmp_domains.next;
+}
+
+/* Check if cpu is in slowest hmp_domain */
+static inline unsigned int hmp_cpu_is_slowest(int cpu)
+{
+ struct list_head *pos;
+
+ pos = &hmp_cpu_domain(cpu)->hmp_domains;
+ return list_is_last(pos, &hmp_domains);
+}
+
+/* Next (slower) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_slower_domain(int cpu)
+{
+ struct list_head *pos;
+
+ pos = &hmp_cpu_domain(cpu)->hmp_domains;
+ return list_entry(pos->next, struct hmp_domain, hmp_domains);
+}
+
+/* Previous (faster) hmp_domain relative to cpu */
+static inline struct hmp_domain *hmp_faster_domain(int cpu)
+{
+ struct list_head *pos;
+
+ pos = &hmp_cpu_domain(cpu)->hmp_domains;
+ return list_entry(pos->prev, struct hmp_domain, hmp_domains);
+}
+
+/*
+ * Selects a cpu in previous (faster) hmp_domain
+ */
+static inline unsigned int hmp_select_faster_cpu(struct task_struct *tsk,
+ int cpu)
+{
+ int lowest_cpu=NR_CPUS;
+ __always_unused int lowest_ratio;
+ struct hmp_domain *hmp;
+
+ if (hmp_cpu_is_fastest(cpu))
+ hmp = hmp_cpu_domain(cpu);
+ else
+ hmp = hmp_faster_domain(cpu);
+
+ lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+ tsk_cpus_allowed(tsk));
+
+ return lowest_cpu;
+}
+
+/*
+ * Selects a cpu in next (slower) hmp_domain
+ * Note that cpumask_any_and() returns the first cpu in the cpumask
+ */
+static inline unsigned int hmp_select_slower_cpu(struct task_struct *tsk,
+ int cpu)
+{
+ int lowest_cpu=NR_CPUS;
+ struct hmp_domain *hmp;
+ __always_unused int lowest_ratio;
+
+ if (hmp_cpu_is_slowest(cpu))
+ hmp = hmp_cpu_domain(cpu);
+ else
+ hmp = hmp_slower_domain(cpu);
+
+ lowest_ratio = hmp_domain_min_load(hmp, &lowest_cpu,
+ tsk_cpus_allowed(tsk));
+
+ return lowest_cpu;
+}
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Select the 'best' candidate little CPU to wake up on.
+ * Implements a packing strategy which examines CPU in
+ * logical CPU order, and selects the first which will
+ * be loaded less than hmp_full_threshold according to
+ * the sum of the tracked load of the runqueue and the task.
+ */
+static inline unsigned int hmp_best_little_cpu(struct task_struct *tsk,
+ int cpu) {
+ int tmp_cpu;
+ unsigned long estimated_load;
+ struct hmp_domain *hmp;
+ struct sched_avg *avg;
+ struct cpumask allowed_hmp_cpus;
+
+ if(!hmp_packing_enabled ||
+ tsk->se.avg.load_avg_ratio > ((NICE_0_LOAD * 90)/100))
+ return hmp_select_slower_cpu(tsk, cpu);
+
+ if (hmp_cpu_is_slowest(cpu))
+ hmp = hmp_cpu_domain(cpu);
+ else
+ hmp = hmp_slower_domain(cpu);
+
+ /* respect affinity */
+ cpumask_and(&allowed_hmp_cpus, &hmp->cpus,
+ tsk_cpus_allowed(tsk));
+
+ for_each_cpu_mask(tmp_cpu, allowed_hmp_cpus) {
+ avg = &cpu_rq(tmp_cpu)->avg;
+ /* estimate new rq load if we add this task */
+ estimated_load = avg->load_avg_ratio +
+ tsk->se.avg.load_avg_ratio;
+ if (estimated_load <= hmp_full_threshold) {
+ cpu = tmp_cpu;
+ break;
+ }
+ }
+ /* if no match was found, the task uses the initial value */
+ return cpu;
+}
+#endif
+static inline void hmp_next_up_delay(struct sched_entity *se, int cpu)
+{
+ /* hack - always use clock from first online CPU */
+ u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+ se->avg.hmp_last_up_migration = now;
+ se->avg.hmp_last_down_migration = 0;
+ cpu_rq(cpu)->avg.hmp_last_up_migration = now;
+ cpu_rq(cpu)->avg.hmp_last_down_migration = 0;
+}
+
+static inline void hmp_next_down_delay(struct sched_entity *se, int cpu)
+{
+ /* hack - always use clock from first online CPU */
+ u64 now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+ se->avg.hmp_last_down_migration = now;
+ se->avg.hmp_last_up_migration = 0;
+ cpu_rq(cpu)->avg.hmp_last_down_migration = now;
+ cpu_rq(cpu)->avg.hmp_last_up_migration = 0;
+}
+
+/*
+ * Heterogenous multiprocessor (HMP) optimizations
+ *
+ * These functions allow to change the growing speed of the load_avg_ratio
+ * by default it goes from 0 to 0.5 in LOAD_AVG_PERIOD = 32ms
+ * This can now be changed with /sys/kernel/hmp/load_avg_period_ms.
+ *
+ * These functions also allow to change the up and down threshold of HMP
+ * using /sys/kernel/hmp/{up,down}_threshold.
+ * Both must be between 0 and 1023. The threshold that is compared
+ * to the load_avg_ratio is up_threshold/1024 and down_threshold/1024.
+ *
+ * For instance, if load_avg_period = 64 and up_threshold = 512, an idle
+ * task with a load of 0 will reach the threshold after 64ms of busy loop.
+ *
+ * Changing load_avg_periods_ms has the same effect than changing the
+ * default scaling factor Y=1002/1024 in the load_avg_ratio computation to
+ * (1002/1024.0)^(LOAD_AVG_PERIOD/load_avg_period_ms), but the last one
+ * could trigger overflows.
+ * For instance, with Y = 1023/1024 in __update_task_entity_contrib()
+ * "contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);"
+ * could be overflowed for a weight > 2^12 even is the load_avg_contrib
+ * should still be a 32bits result. This would not happen by multiplicating
+ * delta time by 1/22 and setting load_avg_period_ms = 706.
+ */
+
+/*
+ * By scaling the delta time it end-up increasing or decrease the
+ * growing speed of the per entity load_avg_ratio
+ * The scale factor hmp_data.multiplier is a fixed point
+ * number: (32-HMP_VARIABLE_SCALE_SHIFT).HMP_VARIABLE_SCALE_SHIFT
+ */
+static inline u64 hmp_variable_scale_convert(u64 delta)
+{
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+ u64 high = delta >> 32ULL;
+ u64 low = delta & 0xffffffffULL;
+ low *= hmp_data.multiplier;
+ high *= hmp_data.multiplier;
+ return (low >> HMP_VARIABLE_SCALE_SHIFT)
+ + (high << (32ULL - HMP_VARIABLE_SCALE_SHIFT));
+#else
+ return delta;
+#endif
+}
+
+static ssize_t hmp_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct hmp_global_attr *hmp_attr =
+ container_of(attr, struct hmp_global_attr, attr);
+ int temp;
+
+ if (hmp_attr->to_sysfs_text != NULL)
+ return hmp_attr->to_sysfs_text(buf, PAGE_SIZE);
+
+ temp = *(hmp_attr->value);
+ if (hmp_attr->to_sysfs != NULL)
+ temp = hmp_attr->to_sysfs(temp);
+
+ return (ssize_t)sprintf(buf, "%d\n", temp);
+}
+
+static ssize_t hmp_store(struct kobject *a, struct attribute *attr,
+ const char *buf, size_t count)
+{
+ int temp;
+ ssize_t ret = count;
+ struct hmp_global_attr *hmp_attr =
+ container_of(attr, struct hmp_global_attr, attr);
+ char *str = vmalloc(count + 1);
+ if (str == NULL)
+ return -ENOMEM;
+ memcpy(str, buf, count);
+ str[count] = 0;
+ if (sscanf(str, "%d", &temp) < 1)
+ ret = -EINVAL;
+ else {
+ if (hmp_attr->from_sysfs != NULL)
+ temp = hmp_attr->from_sysfs(temp);
+ if (temp < 0)
+ ret = -EINVAL;
+ else
+ *(hmp_attr->value) = temp;
+ }
+ vfree(str);
+ return ret;
+}
+
+static ssize_t hmp_print_domains(char *outbuf, int outbufsize)
+{
+ char buf[64];
+ const char nospace[] = "%s", space[] = " %s";
+ const char *fmt = nospace;
+ struct hmp_domain *domain;
+ struct list_head *pos;
+ int outpos = 0;
+ list_for_each(pos, &hmp_domains) {
+ domain = list_entry(pos, struct hmp_domain, hmp_domains);
+ if (cpumask_scnprintf(buf, 64, &domain->possible_cpus)) {
+ outpos += sprintf(outbuf+outpos, fmt, buf);
+ fmt = space;
+ }
+ }
+ strcat(outbuf, "\n");
+ return outpos+1;
+}
+
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+static int hmp_period_tofrom_sysfs(int value)
+{
+ return (LOAD_AVG_PERIOD << HMP_VARIABLE_SCALE_SHIFT) / value;
+}
+#endif
+/* max value for threshold is 1024 */
+static int hmp_theshold_from_sysfs(int value)
+{
+ if (value > 1024)
+ return -1;
+ return value;
+}
+#if defined(CONFIG_SCHED_HMP_LITTLE_PACKING) || \
+ defined(CONFIG_HMP_FREQUENCY_INVARIANT_SCALE)
+/* toggle control is only 0,1 off/on */
+static int hmp_toggle_from_sysfs(int value)
+{
+ if (value < 0 || value > 1)
+ return -1;
+ return value;
+}
+#endif
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/* packing value must be non-negative */
+static int hmp_packing_from_sysfs(int value)
+{
+ if (value < 0)
+ return -1;
+ return value;
+}
+#endif
+static void hmp_attr_add(
+ const char *name,
+ int *value,
+ int (*to_sysfs)(int),
+ int (*from_sysfs)(int),
+ ssize_t (*to_sysfs_text)(char *, int),
+ umode_t mode)
+{
+ int i = 0;
+ while (hmp_data.attributes[i] != NULL) {
+ i++;
+ if (i >= HMP_DATA_SYSFS_MAX)
+ return;
+ }
+ if (mode)
+ hmp_data.attr[i].attr.mode = mode;
+ else
+ hmp_data.attr[i].attr.mode = 0644;
+ hmp_data.attr[i].show = hmp_show;
+ hmp_data.attr[i].store = hmp_store;
+ hmp_data.attr[i].attr.name = name;
+ hmp_data.attr[i].value = value;
+ hmp_data.attr[i].to_sysfs = to_sysfs;
+ hmp_data.attr[i].from_sysfs = from_sysfs;
+ hmp_data.attr[i].to_sysfs_text = to_sysfs_text;
+ hmp_data.attributes[i] = &hmp_data.attr[i].attr;
+ hmp_data.attributes[i + 1] = NULL;
+}
+
+static int hmp_attr_init(void)
+{
+ int ret;
+ memset(&hmp_data, sizeof(hmp_data), 0);
+ hmp_attr_add("hmp_domains",
+ NULL,
+ NULL,
+ NULL,
+ hmp_print_domains,
+ 0444);
+ hmp_attr_add("up_threshold",
+ &hmp_up_threshold,
+ NULL,
+ hmp_theshold_from_sysfs,
+ NULL,
+ 0);
+ hmp_attr_add("down_threshold",
+ &hmp_down_threshold,
+ NULL,
+ hmp_theshold_from_sysfs,
+ NULL,
+ 0);
+#ifdef CONFIG_HMP_VARIABLE_SCALE
+ /* by default load_avg_period_ms == LOAD_AVG_PERIOD
+ * meaning no change
+ */
+ hmp_data.multiplier = hmp_period_tofrom_sysfs(LOAD_AVG_PERIOD);
+ hmp_attr_add("load_avg_period_ms",
+ &hmp_data.multiplier,
+ hmp_period_tofrom_sysfs,
+ hmp_period_tofrom_sysfs,
+ NULL,
+ 0);
+#endif
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+ /* default frequency-invariant scaling ON */
+ hmp_data.freqinvar_load_scale_enabled = 1;
+ hmp_attr_add("frequency_invariant_load_scale",
+ &hmp_data.freqinvar_load_scale_enabled,
+ NULL,
+ hmp_toggle_from_sysfs,
+ NULL,
+ 0);
+#endif
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+ hmp_attr_add("packing_enable",
+ &hmp_packing_enabled,
+ NULL,
+ hmp_toggle_from_sysfs,
+ NULL,
+ 0);
+ hmp_attr_add("packing_limit",
+ &hmp_full_threshold,
+ NULL,
+ hmp_packing_from_sysfs,
+ NULL,
+ 0);
+#endif
+ hmp_data.attr_group.name = "hmp";
+ hmp_data.attr_group.attrs = hmp_data.attributes;
+ ret = sysfs_create_group(kernel_kobj,
+ &hmp_data.attr_group);
+ return 0;
+}
+late_initcall(hmp_attr_init);
+/*
+ * return the load of the lowest-loaded CPU in a given HMP domain
+ * min_cpu optionally points to an int to receive the CPU.
+ * affinity optionally points to a cpumask containing the
+ * CPUs to be considered. note:
+ * + min_cpu = NR_CPUS only if no CPUs are in the set of
+ * affinity && hmp_domain cpus
+ * + min_cpu will always otherwise equal one of the CPUs in
+ * the hmp domain
+ * + when more than one CPU has the same load, the one which
+ * is least-recently-disturbed by an HMP migration will be
+ * selected
+ * + if all CPUs are equally loaded or idle and the times are
+ * all the same, the first in the set will be used
+ * + if affinity is not set, cpu_online_mask is used
+ */
+static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd,
+ int *min_cpu, struct cpumask *affinity)
+{
+ int cpu;
+ int min_cpu_runnable_temp = NR_CPUS;
+ u64 min_target_last_migration = ULLONG_MAX;
+ u64 curr_last_migration;
+ unsigned long min_runnable_load = INT_MAX;
+ unsigned long contrib;
+ struct sched_avg *avg;
+ struct cpumask temp_cpumask;
+ /*
+ * only look at CPUs allowed if specified,
+ * otherwise look at all online CPUs in the
+ * right HMP domain
+ */
+ cpumask_and(&temp_cpumask, &hmpd->cpus, affinity ? affinity : cpu_online_mask);
+
+ for_each_cpu_mask(cpu, temp_cpumask) {
+ avg = &cpu_rq(cpu)->avg;
+ /* used for both up and down migration */
+ curr_last_migration = avg->hmp_last_up_migration ?
+ avg->hmp_last_up_migration : avg->hmp_last_down_migration;
+
+ contrib = avg->load_avg_ratio;
+ /*
+ * Consider a runqueue completely busy if there is any load
+ * on it. Definitely not the best for overall fairness, but
+ * does well in typical Android use cases.
+ */
+ if (contrib)
+ contrib = 1023;
+
+ if ((contrib < min_runnable_load) ||
+ (contrib == min_runnable_load &&
+ curr_last_migration < min_target_last_migration)) {
+ /*
+ * if the load is the same target the CPU with
+ * the longest time since a migration.
+ * This is to spread migration load between
+ * members of a domain more evenly when the
+ * domain is fully loaded
+ */
+ min_runnable_load = contrib;
+ min_cpu_runnable_temp = cpu;
+ min_target_last_migration = curr_last_migration;
+ }
+ }
+
+ if (min_cpu)
+ *min_cpu = min_cpu_runnable_temp;
+
+ return min_runnable_load;
+}
+
+/*
+ * Calculate the task starvation
+ * This is the ratio of actually running time vs. runnable time.
+ * If the two are equal the task is getting the cpu time it needs or
+ * it is alone on the cpu and the cpu is fully utilized.
+ */
+static inline unsigned int hmp_task_starvation(struct sched_entity *se)
+{
+ u32 starvation;
+
+ starvation = se->avg.usage_avg_sum * scale_load_down(NICE_0_LOAD);
+ starvation /= (se->avg.runnable_avg_sum + 1);
+
+ return scale_load(starvation);
+}
+
+static inline unsigned int hmp_offload_down(int cpu, struct sched_entity *se)
+{
+ int min_usage;
+ int dest_cpu = NR_CPUS;
+
+ if (hmp_cpu_is_slowest(cpu))
+ return NR_CPUS;
+
+ /* Is there an idle CPU in the current domain */
+ min_usage = hmp_domain_min_load(hmp_cpu_domain(cpu), NULL, NULL);
+ if (min_usage == 0) {
+ trace_sched_hmp_offload_abort(cpu, min_usage, "load");
+ return NR_CPUS;
+ }
+
+ /* Is the task alone on the cpu? */
+ if (cpu_rq(cpu)->cfs.h_nr_running < 2) {
+ trace_sched_hmp_offload_abort(cpu,
+ cpu_rq(cpu)->cfs.h_nr_running, "nr_running");
+ return NR_CPUS;
+ }
+
+ /* Is the task actually starving? */
+ /* >=25% ratio running/runnable = starving */
+ if (hmp_task_starvation(se) > 768) {
+ trace_sched_hmp_offload_abort(cpu, hmp_task_starvation(se),
+ "starvation");
+ return NR_CPUS;
+ }
+
+ /* Does the slower domain have any idle CPUs? */
+ min_usage = hmp_domain_min_load(hmp_slower_domain(cpu), &dest_cpu,
+ tsk_cpus_allowed(task_of(se)));
+
+ if (min_usage == 0) {
+ trace_sched_hmp_offload_succeed(cpu, dest_cpu);
+ return dest_cpu;
+ } else
+ trace_sched_hmp_offload_abort(cpu,min_usage,"slowdomain");
+ return NR_CPUS;
+}
+#endif /* CONFIG_SCHED_HMP */
+
/*
* sched_balance_self: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
@@ -3338,6 +4383,19 @@
if (p->nr_cpus_allowed == 1)
return prev_cpu;
+#ifdef CONFIG_SCHED_HMP
+ /* always put non-kernel forking tasks on a big domain */
+ if (unlikely(sd_flag & SD_BALANCE_FORK) && hmp_task_should_forkboost(p)) {
+ new_cpu = hmp_select_faster_cpu(p, prev_cpu);
+ if (new_cpu != NR_CPUS) {
+ hmp_next_up_delay(&p->se, new_cpu);
+ return new_cpu;
+ }
+ /* failed to perform HMP fork balance, use normal balance */
+ new_cpu = cpu;
+ }
+#endif
+
if (sd_flag & SD_BALANCE_WAKE) {
if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
want_affine = 1;
@@ -3412,6 +4470,35 @@
unlock:
rcu_read_unlock();
+#ifdef CONFIG_SCHED_HMP
+ prev_cpu = task_cpu(p);
+
+ if (hmp_up_migration(prev_cpu, &new_cpu, &p->se)) {
+ hmp_next_up_delay(&p->se, new_cpu);
+ trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+ return new_cpu;
+ }
+ if (hmp_down_migration(prev_cpu, &p->se)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+ new_cpu = hmp_best_little_cpu(p, prev_cpu);
+#else
+ new_cpu = hmp_select_slower_cpu(p, prev_cpu);
+#endif
+ /*
+ * we might have no suitable CPU
+ * in which case new_cpu == NR_CPUS
+ */
+ if (new_cpu < NR_CPUS && new_cpu != prev_cpu) {
+ hmp_next_down_delay(&p->se, new_cpu);
+ trace_sched_hmp_migrate(p, new_cpu, HMP_MIGRATE_WAKEUP);
+ return new_cpu;
+ }
+ }
+ /* Make sure that the task stays in its previous hmp domain */
+ if (!cpumask_test_cpu(new_cpu, &hmp_cpu_domain(prev_cpu)->cpus))
+ return prev_cpu;
+#endif
+
return new_cpu;
}
@@ -3421,6 +4508,16 @@
* load-balance).
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
+
+#ifdef CONFIG_NO_HZ_COMMON
+static int nohz_test_cpu(int cpu);
+#else
+static inline int nohz_test_cpu(int cpu)
+{
+ return 0;
+}
+#endif
+
/*
* Called immediately before a task is migrated to a new cpu; task_cpu(p) and
* cfs_rq_of(p) references at time of call are still valid and identify the
@@ -3440,6 +4537,25 @@
* be negative here since on-rq tasks have decay-count == 0.
*/
if (se->avg.decay_count) {
+ /*
+ * If we migrate a sleeping task away from a CPU
+ * which has the tick stopped, then both the clock_task
+ * and decay_counter will be out of date for that CPU
+ * and we will not decay load correctly.
+ */
+ if (!se->on_rq && nohz_test_cpu(task_cpu(p))) {
+ struct rq *rq = cpu_rq(task_cpu(p));
+ unsigned long flags;
+ /*
+ * Current CPU cannot be holding rq->lock in this
+ * circumstance, but another might be. We must hold
+ * rq->lock before we go poking around in its clocks
+ */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+ update_cfs_rq_blocked_load(cfs_rq, 0);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
se->avg.decay_count = -__synchronize_entity_decay(se);
atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
}
@@ -3945,7 +5061,6 @@
* 1) task is cache cold, or
* 2) too many balance attempts have failed.
*/
-
tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
if (!tsk_cache_hot ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
@@ -5231,6 +6346,16 @@
return ld_moved;
}
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_idle_pull(int this_cpu);
+static int move_specific_task(struct lb_env *env, struct task_struct *pm);
+#else
+static int move_specific_task(struct lb_env *env, struct task_struct *pm)
+{
+ return 0;
+}
+#endif
+
/*
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
@@ -5275,7 +6400,10 @@
}
}
rcu_read_unlock();
-
+#ifdef CONFIG_SCHED_HMP
+ if (!pulled_task)
+ pulled_task = hmp_idle_pull(this_cpu);
+#endif
raw_spin_lock(&this_rq->lock);
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
@@ -5287,22 +6415,19 @@
}
}
-/*
- * active_load_balance_cpu_stop is run by cpu stopper. It pushes
- * running tasks off the busiest CPU onto idle CPUs. It requires at
- * least 1 task to be running on each physical CPU where possible, and
- * avoids physical / logical imbalances.
- */
-static int active_load_balance_cpu_stop(void *data)
+static int __do_active_load_balance_cpu_stop(void *data, bool check_sd_lb_flag)
{
struct rq *busiest_rq = data;
int busiest_cpu = cpu_of(busiest_rq);
int target_cpu = busiest_rq->push_cpu;
struct rq *target_rq = cpu_rq(target_cpu);
struct sched_domain *sd;
+ struct task_struct *p = NULL;
raw_spin_lock_irq(&busiest_rq->lock);
-
+#ifdef CONFIG_SCHED_HMP
+ p = busiest_rq->migrate_task;
+#endif
/* make sure the requested cpu hasn't gone down in the meantime */
if (unlikely(busiest_cpu != smp_processor_id() ||
!busiest_rq->active_balance))
@@ -5312,6 +6437,11 @@
if (busiest_rq->nr_running <= 1)
goto out_unlock;
+ if (!check_sd_lb_flag) {
+ /* Task has migrated meanwhile, abort forced migration */
+ if (task_rq(p) != busiest_rq)
+ goto out_unlock;
+ }
/*
* This condition is "impossible", if it occurs
* we need to fix it. Originally reported by
@@ -5325,12 +6455,14 @@
/* Search for an sd spanning us and the target CPU. */
rcu_read_lock();
for_each_domain(target_cpu, sd) {
- if ((sd->flags & SD_LOAD_BALANCE) &&
- cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+ if (((check_sd_lb_flag && sd->flags & SD_LOAD_BALANCE) ||
+ !check_sd_lb_flag) &&
+ cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
break;
}
if (likely(sd)) {
+ bool success = false;
struct lb_env env = {
.sd = sd,
.dst_cpu = target_cpu,
@@ -5342,7 +6474,14 @@
schedstat_inc(sd, alb_count);
- if (move_one_task(&env))
+ if (check_sd_lb_flag) {
+ if (move_one_task(&env))
+ success = true;
+ } else {
+ if (move_specific_task(&env, p))
+ success = true;
+ }
+ if (success)
schedstat_inc(sd, alb_pushed);
else
schedstat_inc(sd, alb_failed);
@@ -5352,9 +6491,22 @@
out_unlock:
busiest_rq->active_balance = 0;
raw_spin_unlock_irq(&busiest_rq->lock);
+ if (!check_sd_lb_flag)
+ put_task_struct(p);
return 0;
}
+/*
+ * active_load_balance_cpu_stop is run by cpu stopper. It pushes
+ * running tasks off the busiest CPU onto idle CPUs. It requires at
+ * least 1 task to be running on each physical CPU where possible, and
+ * avoids physical / logical imbalances.
+ */
+static int active_load_balance_cpu_stop(void *data)
+{
+ return __do_active_load_balance_cpu_stop(data, true);
+}
+
#ifdef CONFIG_NO_HZ_COMMON
/*
* idle load balancing details
@@ -5368,12 +6520,80 @@
unsigned long next_balance; /* in jiffy units */
} nohz ____cacheline_aligned;
+/*
+ * nohz_test_cpu used when load tracking is enabled. FAIR_GROUP_SCHED
+ * dependency below may be removed when load tracking guards are
+ * removed.
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int nohz_test_cpu(int cpu)
+{
+ return cpumask_test_cpu(cpu, nohz.idle_cpus_mask);
+}
+#endif
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+/*
+ * Decide if the tasks on the busy CPUs in the
+ * littlest domain would benefit from an idle balance
+ */
+static int hmp_packing_ilb_needed(int cpu, int ilb_needed)
+{
+ struct hmp_domain *hmp;
+ /* allow previous decision on non-slowest domain */
+ if (!hmp_cpu_is_slowest(cpu))
+ return ilb_needed;
+
+ /* if disabled, use normal ILB behaviour */
+ if (!hmp_packing_enabled)
+ return ilb_needed;
+
+ hmp = hmp_cpu_domain(cpu);
+ for_each_cpu_and(cpu, &hmp->cpus, nohz.idle_cpus_mask) {
+ /* only idle balance if a CPU is loaded over threshold */
+ if (cpu_rq(cpu)->avg.load_avg_ratio > hmp_full_threshold)
+ return 1;
+ }
+ return 0;
+}
+#endif
+
+DEFINE_PER_CPU(cpumask_var_t, ilb_tmpmask);
+
static inline int find_new_ilb(int call_cpu)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
+#ifdef CONFIG_SCHED_HMP
+ int ilb_needed = 0;
+ int cpu;
+ struct cpumask* tmp = per_cpu(ilb_tmpmask, smp_processor_id());
+ /* restrict nohz balancing to occur in the same hmp domain */
+ ilb = cpumask_first_and(nohz.idle_cpus_mask,
+ &((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus);
+
+ /* check to see if it's necessary within this domain */
+ cpumask_andnot(tmp,
+ &((struct hmp_domain *)hmp_cpu_domain(call_cpu))->cpus,
+ nohz.idle_cpus_mask);
+ for_each_cpu(cpu, tmp) {
+ if (cpu_rq(cpu)->nr_running > 1) {
+ ilb_needed = 1;
+ break;
+ }
+ }
+
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+ if (ilb < nr_cpu_ids)
+ ilb_needed = hmp_packing_ilb_needed(ilb, ilb_needed);
+#endif
+
+ if (ilb_needed && ilb < nr_cpu_ids && idle_cpu(ilb))
+ return ilb;
+#else
if (ilb < nr_cpu_ids && idle_cpu(ilb))
return ilb;
+#endif
return nr_cpu_ids;
}
@@ -5650,6 +6870,18 @@
if (time_before(now, nohz.next_balance))
return 0;
+#ifdef CONFIG_SCHED_HMP
+ /*
+ * Bail out if there are no nohz CPUs in our
+ * HMP domain, since we will move tasks between
+ * domains through wakeup and force balancing
+ * as necessary based upon task load.
+ */
+ if (cpumask_first_and(nohz.idle_cpus_mask,
+ &((struct hmp_domain *)hmp_cpu_domain(cpu))->cpus) >= nr_cpu_ids)
+ return 0;
+#endif
+
if (rq->nr_running >= 2)
goto need_kick;
@@ -5682,6 +6914,442 @@
static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
#endif
+#ifdef CONFIG_SCHED_HMP
+static unsigned int hmp_task_eligible_for_up_migration(struct sched_entity *se)
+{
+ /* below hmp_up_threshold, never eligible */
+ if (se->avg.load_avg_ratio < hmp_up_threshold)
+ return 0;
+ return 1;
+}
+
+/* Check if task should migrate to a faster cpu */
+static unsigned int hmp_up_migration(int cpu, int *target_cpu, struct sched_entity *se)
+{
+ struct task_struct *p = task_of(se);
+ int temp_target_cpu;
+ u64 now;
+
+ if (hmp_cpu_is_fastest(cpu))
+ return 0;
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+ /* Filter by task priority */
+ if (p->prio >= hmp_up_prio)
+ return 0;
+#endif
+ if (!hmp_task_eligible_for_up_migration(se))
+ return 0;
+
+ /* Let the task load settle before doing another up migration */
+ /* hack - always use clock from first online CPU */
+ now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+ if (((now - se->avg.hmp_last_up_migration) >> 10)
+ < hmp_next_up_threshold)
+ return 0;
+
+ /* hmp_domain_min_load only returns 0 for an
+ * idle CPU or 1023 for any partly-busy one.
+ * Be explicit about requirement for an idle CPU.
+ */
+ if (hmp_domain_min_load(hmp_faster_domain(cpu), &temp_target_cpu,
+ tsk_cpus_allowed(p)) == 0 && temp_target_cpu != NR_CPUS) {
+ if(target_cpu)
+ *target_cpu = temp_target_cpu;
+ return 1;
+ }
+ return 0;
+}
+
+/* Check if task should migrate to a slower cpu */
+static unsigned int hmp_down_migration(int cpu, struct sched_entity *se)
+{
+ struct task_struct *p = task_of(se);
+ u64 now;
+
+ if (hmp_cpu_is_slowest(cpu)) {
+#ifdef CONFIG_SCHED_HMP_LITTLE_PACKING
+ if(hmp_packing_enabled)
+ return 1;
+ else
+#endif
+ return 0;
+ }
+
+#ifdef CONFIG_SCHED_HMP_PRIO_FILTER
+ /* Filter by task priority */
+ if ((p->prio >= hmp_up_prio) &&
+ cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+ tsk_cpus_allowed(p))) {
+ return 1;
+ }
+#endif
+
+ /* Let the task load settle before doing another down migration */
+ /* hack - always use clock from first online CPU */
+ now = cpu_rq(cpumask_first(cpu_online_mask))->clock_task;
+ if (((now - se->avg.hmp_last_down_migration) >> 10)
+ < hmp_next_down_threshold)
+ return 0;
+
+ if (cpumask_intersects(&hmp_slower_domain(cpu)->cpus,
+ tsk_cpus_allowed(p))
+ && se->avg.load_avg_ratio < hmp_down_threshold) {
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * hmp_can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ * Ideally this function should be merged with can_migrate_task() to avoid
+ * redundant code.
+ */
+static int hmp_can_migrate_task(struct task_struct *p, struct lb_env *env)
+{
+ int tsk_cache_hot = 0;
+
+ /*
+ * We do not migrate tasks that are:
+ * 1) running (obviously), or
+ * 2) cannot be migrated to this CPU due to cpus_allowed
+ */
+ if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) {
+ schedstat_inc(p, se.statistics.nr_failed_migrations_affine);
+ return 0;
+ }
+ env->flags &= ~LBF_ALL_PINNED;
+
+ if (task_running(env->src_rq, p)) {
+ schedstat_inc(p, se.statistics.nr_failed_migrations_running);
+ return 0;
+ }
+
+ /*
+ * Aggressive migration if:
+ * 1) task is cache cold, or
+ * 2) too many balance attempts have failed.
+ */
+
+ tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+ if (!tsk_cache_hot ||
+ env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+ if (tsk_cache_hot) {
+ schedstat_inc(env->sd, lb_hot_gained[env->idle]);
+ schedstat_inc(p, se.statistics.nr_forced_migrations);
+ }
+#endif
+ return 1;
+ }
+
+ return 1;
+}
+
+/*
+ * move_specific_task tries to move a specific task.
+ * Returns 1 if successful and 0 otherwise.
+ * Called with both runqueues locked.
+ */
+static int move_specific_task(struct lb_env *env, struct task_struct *pm)
+{
+ struct task_struct *p, *n;
+
+ list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) {
+ if (throttled_lb_pair(task_group(p), env->src_rq->cpu,
+ env->dst_cpu))
+ continue;
+
+ if (!hmp_can_migrate_task(p, env))
+ continue;
+ /* Check if we found the right task */
+ if (p != pm)
+ continue;
+
+ move_task(p, env);
+ /*
+ * Right now, this is only the third place move_task()
+ * is called, so we can safely collect move_task()
+ * stats here rather than inside move_task().
+ */
+ schedstat_inc(env->sd, lb_gained[env->idle]);
+ return 1;
+ }
+ return 0;
+}
+
+/*
+ * hmp_active_task_migration_cpu_stop is run by cpu stopper and used to
+ * migrate a specific task from one runqueue to another.
+ * hmp_force_up_migration uses this to push a currently running task
+ * off a runqueue. hmp_idle_pull uses this to pull a currently
+ * running task to an idle runqueue.
+ * Reuses __do_active_load_balance_cpu_stop to actually do the work.
+ */
+static int hmp_active_task_migration_cpu_stop(void *data)
+{
+ return __do_active_load_balance_cpu_stop(data, false);
+}
+
+/*
+ * Move task in a runnable state to another CPU.
+ *
+ * Tailored on 'active_load_balance_cpu_stop' with slight
+ * modification to locking and pre-transfer checks. Note
+ * rq->lock must be held before calling.
+ */
+static void hmp_migrate_runnable_task(struct rq *rq)
+{
+ struct sched_domain *sd;
+ int src_cpu = cpu_of(rq);
+ struct rq *src_rq = rq;
+ int dst_cpu = rq->push_cpu;
+ struct rq *dst_rq = cpu_rq(dst_cpu);
+ struct task_struct *p = rq->migrate_task;
+ /*
+ * One last check to make sure nobody else is playing
+ * with the source rq.
+ */
+ if (src_rq->active_balance)
+ goto out;
+
+ if (src_rq->nr_running <= 1)
+ goto out;
+
+ if (task_rq(p) != src_rq)
+ goto out;
+ /*
+ * Not sure if this applies here but one can never
+ * be too cautious
+ */
+ BUG_ON(src_rq == dst_rq);
+
+ double_lock_balance(src_rq, dst_rq);
+
+ rcu_read_lock();
+ for_each_domain(dst_cpu, sd) {
+ if (cpumask_test_cpu(src_cpu, sched_domain_span(sd)))
+ break;
+ }
+
+ if (likely(sd)) {
+ struct lb_env env = {
+ .sd = sd,
+ .dst_cpu = dst_cpu,
+ .dst_rq = dst_rq,
+ .src_cpu = src_cpu,
+ .src_rq = src_rq,
+ .idle = CPU_IDLE,
+ };
+
+ schedstat_inc(sd, alb_count);
+
+ if (move_specific_task(&env, p))
+ schedstat_inc(sd, alb_pushed);
+ else
+ schedstat_inc(sd, alb_failed);
+ }
+
+ rcu_read_unlock();
+ double_unlock_balance(src_rq, dst_rq);
+out:
+ put_task_struct(p);
+}
+
+static DEFINE_SPINLOCK(hmp_force_migration);
+
+/*
+ * hmp_force_up_migration checks runqueues for tasks that need to
+ * be actively migrated to a faster cpu.
+ */
+static void hmp_force_up_migration(int this_cpu)
+{
+ int cpu, target_cpu;
+ struct sched_entity *curr, *orig;
+ struct rq *target;
+ unsigned long flags;
+ unsigned int force, got_target;
+ struct task_struct *p;
+
+ if (!spin_trylock(&hmp_force_migration))
+ return;
+ for_each_online_cpu(cpu) {
+ force = 0;
+ got_target = 0;
+ target = cpu_rq(cpu);
+ raw_spin_lock_irqsave(&target->lock, flags);
+ curr = target->cfs.curr;
+ if (!curr || target->active_balance) {
+ raw_spin_unlock_irqrestore(&target->lock, flags);
+ continue;
+ }
+ if (!entity_is_task(curr)) {
+ struct cfs_rq *cfs_rq;
+
+ cfs_rq = group_cfs_rq(curr);
+ while (cfs_rq) {
+ curr = cfs_rq->curr;
+ cfs_rq = group_cfs_rq(curr);
+ }
+ }
+ orig = curr;
+ curr = hmp_get_heaviest_task(curr, -1);
+ if (!curr) {
+ raw_spin_unlock_irqrestore(&target->lock, flags);
+ continue;
+ }
+ p = task_of(curr);
+ if (hmp_up_migration(cpu, &target_cpu, curr)) {
+ cpu_rq(target_cpu)->wake_for_idle_pull = 1;
+ raw_spin_unlock_irqrestore(&target->lock, flags);
+ spin_unlock(&hmp_force_migration);
+ smp_send_reschedule(target_cpu);
+ return;
+ }
+ if (!got_target) {
+ /*
+ * For now we just check the currently running task.
+ * Selecting the lightest task for offloading will
+ * require extensive book keeping.
+ */
+ curr = hmp_get_lightest_task(orig, 1);
+ p = task_of(curr);
+ target->push_cpu = hmp_offload_down(cpu, curr);
+ if (target->push_cpu < NR_CPUS) {
+ get_task_struct(p);
+ target->migrate_task = p;
+ got_target = 1;
+ trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_OFFLOAD);
+ hmp_next_down_delay(&p->se, target->push_cpu);
+ }
+ }
+ /*
+ * We have a target with no active_balance. If the task
+ * is not currently running move it, otherwise let the
+ * CPU stopper take care of it.
+ */
+ if (got_target) {
+ if (!task_running(target, p)) {
+ trace_sched_hmp_migrate_force_running(p, 0);
+ hmp_migrate_runnable_task(target);
+ } else {
+ target->active_balance = 1;
+ force = 1;
+ }
+ }
+
+ raw_spin_unlock_irqrestore(&target->lock, flags);
+
+ if (force)
+ stop_one_cpu_nowait(cpu_of(target),
+ hmp_active_task_migration_cpu_stop,
+ target, &target->active_balance_work);
+ }
+ spin_unlock(&hmp_force_migration);
+}
+/*
+ * hmp_idle_pull looks at little domain runqueues to see
+ * if a task should be pulled.
+ *
+ * Reuses hmp_force_migration spinlock.
+ *
+ */
+static unsigned int hmp_idle_pull(int this_cpu)
+{
+ int cpu;
+ struct sched_entity *curr, *orig;
+ struct hmp_domain *hmp_domain = NULL;
+ struct rq *target = NULL, *rq;
+ unsigned long flags, ratio = 0;
+ unsigned int force = 0;
+ struct task_struct *p = NULL;
+
+ if (!hmp_cpu_is_slowest(this_cpu))
+ hmp_domain = hmp_slower_domain(this_cpu);
+ if (!hmp_domain)
+ return 0;
+
+ if (!spin_trylock(&hmp_force_migration))
+ return 0;
+
+ /* first select a task */
+ for_each_cpu(cpu, &hmp_domain->cpus) {
+ rq = cpu_rq(cpu);
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ curr = rq->cfs.curr;
+ if (!curr) {
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ continue;
+ }
+ if (!entity_is_task(curr)) {
+ struct cfs_rq *cfs_rq;
+
+ cfs_rq = group_cfs_rq(curr);
+ while (cfs_rq) {
+ curr = cfs_rq->curr;
+ if (!entity_is_task(curr))
+ cfs_rq = group_cfs_rq(curr);
+ else
+ cfs_rq = NULL;
+ }
+ }
+ orig = curr;
+ curr = hmp_get_heaviest_task(curr, this_cpu);
+ /* check if heaviest eligible task on this
+ * CPU is heavier than previous task
+ */
+ if (curr && hmp_task_eligible_for_up_migration(curr) &&
+ curr->avg.load_avg_ratio > ratio &&
+ cpumask_test_cpu(this_cpu,
+ tsk_cpus_allowed(task_of(curr)))) {
+ p = task_of(curr);
+ target = rq;
+ ratio = curr->avg.load_avg_ratio;
+ }
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
+
+ if (!p)
+ goto done;
+
+ /* now we have a candidate */
+ raw_spin_lock_irqsave(&target->lock, flags);
+ if (!target->active_balance && task_rq(p) == target) {
+ get_task_struct(p);
+ target->push_cpu = this_cpu;
+ target->migrate_task = p;
+ trace_sched_hmp_migrate(p, target->push_cpu, HMP_MIGRATE_IDLE_PULL);
+ hmp_next_up_delay(&p->se, target->push_cpu);
+ /*
+ * if the task isn't running move it right away.
+ * Otherwise setup the active_balance mechanic and let
+ * the CPU stopper do its job.
+ */
+ if (!task_running(target, p)) {
+ trace_sched_hmp_migrate_idle_running(p, 0);
+ hmp_migrate_runnable_task(target);
+ } else {
+ target->active_balance = 1;
+ force = 1;
+ }
+ }
+ raw_spin_unlock_irqrestore(&target->lock, flags);
+
+ if (force) {
+ /* start timer to keep us awake */
+ hmp_cpu_keepalive_trigger();
+ stop_one_cpu_nowait(cpu_of(target),
+ hmp_active_task_migration_cpu_stop,
+ target, &target->active_balance_work);
+ }
+done:
+ spin_unlock(&hmp_force_migration);
+ return force;
+}
+#else
+static void hmp_force_up_migration(int this_cpu) { }
+#endif /* CONFIG_SCHED_HMP */
+
/*
* run_rebalance_domains is triggered when needed from the scheduler tick.
* Also triggered for nohz idle balancing (with nohz_balancing_kick set).
@@ -5693,6 +7361,20 @@
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
+#ifdef CONFIG_SCHED_HMP
+ /* shortcut for hmp idle pull wakeups */
+ if (unlikely(this_rq->wake_for_idle_pull)) {
+ this_rq->wake_for_idle_pull = 0;
+ if (hmp_idle_pull(this_cpu)) {
+ /* break out unless running nohz idle as well */
+ if (idle != CPU_IDLE)
+ return;
+ }
+ }
+#endif
+
+ hmp_force_up_migration(this_cpu);
+
rebalance_domains(this_cpu, idle);
/*
@@ -5725,11 +7407,17 @@
static void rq_online_fair(struct rq *rq)
{
+#ifdef CONFIG_SCHED_HMP
+ hmp_online_cpu(rq->cpu);
+#endif
update_sysctl();
}
static void rq_offline_fair(struct rq *rq)
{
+#ifdef CONFIG_SCHED_HMP
+ hmp_offline_cpu(rq->cpu);
+#endif
update_sysctl();
/* Ensure any throttled groups are reachable by pick_next_task */
@@ -5777,11 +7465,15 @@
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
- if (unlikely(task_cpu(p) != this_cpu)) {
- rcu_read_lock();
- __set_task_cpu(p, this_cpu);
- rcu_read_unlock();
- }
+ /*
+ * Not only the cpu but also the task_group of the parent might have
+ * been changed after parent->se.parent,cfs_rq were copied to
+ * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
+ * of child point to valid ones.
+ */
+ rcu_read_lock();
+ __set_task_cpu(p, this_cpu);
+ rcu_read_unlock();
update_curr(cfs_rq);
@@ -5831,15 +7523,15 @@
struct cfs_rq *cfs_rq = cfs_rq_of(se);
/*
- * Ensure the task's vruntime is normalized, so that when its
+ * Ensure the task's vruntime is normalized, so that when it's
* switched back to the fair class the enqueue_entity(.flags=0) will
* do the right thing.
*
- * If it was on_rq, then the dequeue_entity(.flags=0) will already
- * have normalized the vruntime, if it was !on_rq, then only when
+ * If it's on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it's !on_rq, then only when
* the task is sleeping will it still have non-normalized vruntime.
*/
- if (!se->on_rq && p->state != TASK_RUNNING) {
+ if (!p->on_rq && p->state != TASK_RUNNING) {
/*
* Fix up our vruntime so that the current sleep doesn't
* cause 'unlimited' sleep bonus.
@@ -6060,7 +7752,8 @@
se->cfs_rq = parent->my_q;
se->my_q = cfs_rq;
- update_load_set(&se->load, 0);
+ /* guarantee group entities always have weight */
+ update_load_set(&se->load, NICE_0_LOAD);
se->parent = parent;
}
@@ -6192,6 +7885,139 @@
zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
cpu_notifier(sched_ilb_notifier, 0);
#endif
+
+#ifdef CONFIG_SCHED_HMP
+ hmp_cpu_mask_setup();
+#endif
#endif /* SMP */
}
+
+#ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE
+static u32 cpufreq_calc_scale(u32 min, u32 max, u32 curr)
+{
+ u32 result = curr / max;
+ return result;
+}
+
+/* Called when the CPU Frequency is changed.
+ * Once for each CPU.
+ */
+static int cpufreq_callback(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct cpufreq_freqs *freq = data;
+ int cpu = freq->cpu;
+ struct cpufreq_extents *extents;
+
+ if (freq->flags & CPUFREQ_CONST_LOOPS)
+ return NOTIFY_OK;
+
+ if (val != CPUFREQ_POSTCHANGE)
+ return NOTIFY_OK;
+
+ /* if dynamic load scale is disabled, set the load scale to 1.0 */
+ if (!hmp_data.freqinvar_load_scale_enabled) {
+ freq_scale[cpu].curr_scale = 1024;
+ return NOTIFY_OK;
+ }
+
+ extents = &freq_scale[cpu];
+ if (extents->flags & SCHED_LOAD_FREQINVAR_SINGLEFREQ) {
+ /* If our governor was recognised as a single-freq governor,
+ * use 1.0
+ */
+ extents->curr_scale = 1024;
+ } else {
+ extents->curr_scale = cpufreq_calc_scale(extents->min,
+ extents->max, freq->new);
+ }
+
+ return NOTIFY_OK;
+}
+
+/* Called when the CPUFreq governor is changed.
+ * Only called for the CPUs which are actually changed by the
+ * userspace.
+ */
+static int cpufreq_policy_callback(struct notifier_block *nb,
+ unsigned long event, void *data)
+{
+ struct cpufreq_policy *policy = data;
+ struct cpufreq_extents *extents;
+ int cpu, singleFreq = 0;
+ static const char performance_governor[] = "performance";
+ static const char powersave_governor[] = "powersave";
+
+ if (event == CPUFREQ_START)
+ return 0;
+
+ if (event != CPUFREQ_INCOMPATIBLE)
+ return 0;
+
+ /* CPUFreq governors do not accurately report the range of
+ * CPU Frequencies they will choose from.
+ * We recognise performance and powersave governors as
+ * single-frequency only.
+ */
+ if (!strncmp(policy->governor->name, performance_governor,
+ strlen(performance_governor)) ||
+ !strncmp(policy->governor->name, powersave_governor,
+ strlen(powersave_governor)))
+ singleFreq = 1;
+
+ /* Make sure that all CPUs impacted by this policy are
+ * updated since we will only get a notification when the
+ * user explicitly changes the policy on a CPU.
+ */
+ for_each_cpu(cpu, policy->cpus) {
+ extents = &freq_scale[cpu];
+ extents->max = policy->max >> SCHED_FREQSCALE_SHIFT;
+ extents->min = policy->min >> SCHED_FREQSCALE_SHIFT;
+ if (!hmp_data.freqinvar_load_scale_enabled) {
+ extents->curr_scale = 1024;
+ } else if (singleFreq) {
+ extents->flags |= SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+ extents->curr_scale = 1024;
+ } else {
+ extents->flags &= ~SCHED_LOAD_FREQINVAR_SINGLEFREQ;
+ extents->curr_scale = cpufreq_calc_scale(extents->min,
+ extents->max, policy->cur);
+ }
+ }
+
+ return 0;
+}
+
+static struct notifier_block cpufreq_notifier = {
+ .notifier_call = cpufreq_callback,
+};
+static struct notifier_block cpufreq_policy_notifier = {
+ .notifier_call = cpufreq_policy_callback,
+};
+
+static int __init register_sched_cpufreq_notifier(void)
+{
+ int ret = 0;
+
+ /* init safe defaults since there are no policies at registration */
+ for (ret = 0; ret < CONFIG_NR_CPUS; ret++) {
+ /* safe defaults */
+ freq_scale[ret].max = 1024;
+ freq_scale[ret].min = 1024;
+ freq_scale[ret].curr_scale = 1024;
+ }
+
+ pr_info("sched: registering cpufreq notifiers for scale-invariant loads\n");
+ ret = cpufreq_register_notifier(&cpufreq_policy_notifier,
+ CPUFREQ_POLICY_NOTIFIER);
+
+ if (ret != -EINVAL)
+ ret = cpufreq_register_notifier(&cpufreq_notifier,
+ CPUFREQ_TRANSITION_NOTIFIER);
+
+ return ret;
+}
+
+core_initcall(register_sched_cpufreq_notifier);
+#endif /* CONFIG_HMP_FREQUENCY_INVARIANT_SCALE */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 127a2c4..2dffc7b 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -892,7 +892,7 @@
if (!once) {
once = true;
- printk_sched("sched: RT throttling activated\n");
+ printk_deferred("sched: RT throttling activated\n");
}
} else {
/*
@@ -964,6 +964,13 @@
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && prio < prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, prio);
}
@@ -973,6 +980,13 @@
{
struct rq *rq = rq_of_rt_rq(rt_rq);
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Change rq's cpupri only if rt_rq is the top queue.
+ */
+ if (&rq->rt != rt_rq)
+ return;
+#endif
if (rq->online && rt_rq->highest_prio.curr != prev_prio)
cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ce39224d..0d19ede 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -142,7 +142,7 @@
atomic_t load_weight;
atomic64_t load_avg;
- atomic_t runnable_avg;
+ atomic_t runnable_avg, usage_avg;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
@@ -279,7 +279,7 @@
#endif /* CONFIG_FAIR_GROUP_SCHED */
/* These always depend on CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_FAIR_GROUP_SCHED
- u32 tg_runnable_contrib;
+ u32 tg_runnable_contrib, tg_usage_contrib;
u64 tg_load_contrib;
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -464,6 +464,10 @@
int active_balance;
int push_cpu;
struct cpu_stop_work active_balance_work;
+#ifdef CONFIG_SCHED_HMP
+ struct task_struct *migrate_task;
+ int wake_for_idle_pull;
+#endif
/* cpu of this runqueue: */
int cpu;
int online;
@@ -642,6 +646,12 @@
extern int group_balance_cpu(struct sched_group *sg);
+#ifdef CONFIG_SCHED_HMP
+static LIST_HEAD(hmp_domains);
+DECLARE_PER_CPU(struct hmp_domain *, hmp_cpu_domain);
+#define hmp_cpu_domain(cpu) (per_cpu(hmp_cpu_domain, (cpu)))
+#endif /* CONFIG_SCHED_HMP */
+
#endif /* CONFIG_SMP */
#include "stats.h"
@@ -1318,7 +1328,8 @@
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
-extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
+extern void cfs_bandwidth_usage_inc(void);
+extern void cfs_bandwidth_usage_dec(void);
#ifdef CONFIG_NO_HZ_COMMON
enum rq_nohz_flag_bits {
diff --git a/kernel/smp.c b/kernel/smp.c
index 4dba0f7..74ba5e2 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -12,6 +12,8 @@
#include <linux/gfp.h>
#include <linux/smp.h>
#include <linux/cpu.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/smp.h>
#include "smpboot.h"
@@ -159,8 +161,10 @@
* locking and barrier primitives. Generic code isn't really
* equipped to do the right thing...
*/
- if (ipi)
+ if (ipi) {
+ trace_smp_call_func_send(csd->func, cpu);
arch_send_call_function_single_ipi(cpu);
+ }
if (wait)
csd_lock_wait(csd);
@@ -197,8 +201,9 @@
* so save them away before making the call:
*/
csd_flags = csd->flags;
-
+ trace_smp_call_func_entry(csd->func);
csd->func(csd->info);
+ trace_smp_call_func_exit(csd->func);
/*
* Unlocked CSDs are valid through generic_exec_single():
@@ -228,6 +233,7 @@
int this_cpu;
int err = 0;
+ trace_smp_call_func_send(func, cpu);
/*
* prevent preemption and reschedule on another processor,
* as well as CPU removal
@@ -245,7 +251,9 @@
if (cpu == this_cpu) {
local_irq_save(flags);
+ trace_smp_call_func_entry(func);
func(info);
+ trace_smp_call_func_exit(func);
local_irq_restore(flags);
} else {
if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
@@ -658,7 +666,7 @@
if (cond_func(cpu, info)) {
ret = smp_call_function_single(cpu, func,
info, wait);
- WARN_ON_ONCE(!ret);
+ WARN_ON_ONCE(ret);
}
preempt_enable();
}
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 02fc5c9..7020eec 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -279,6 +279,7 @@
unsigned int cpu;
int ret = 0;
+ get_online_cpus();
mutex_lock(&smpboot_threads_lock);
for_each_online_cpu(cpu) {
ret = __smpboot_create_thread(plug_thread, cpu);
@@ -291,6 +292,7 @@
list_add(&plug_thread->list, &hotplug_threads);
out:
mutex_unlock(&smpboot_threads_lock);
+ put_online_cpus();
return ret;
}
EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 3d6833f..21956f0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -330,10 +330,19 @@
static inline void invoke_softirq(void)
{
- if (!force_irqthreads)
- __do_softirq();
- else
+ if (!force_irqthreads) {
+ /*
+ * We can safely execute softirq on the current stack if
+ * it is the irq stack, because it should be near empty
+ * at this stage. But we have no way to know if the arch
+ * calls irq_exit() on the irq stack. So call softirq
+ * in its own stack to prevent from any overrun on top
+ * of a potentially deep task stack.
+ */
+ do_softirq();
+ } else {
wakeup_softirqd();
+ }
}
static inline void tick_irq_exit(void)
@@ -765,9 +774,13 @@
local_irq_disable();
if (local_softirq_pending()) {
__do_softirq();
- rcu_note_context_switch(cpu);
local_irq_enable();
cond_resched();
+
+ preempt_disable();
+ rcu_note_context_switch(cpu);
+ preempt_enable();
+
return;
}
local_irq_enable();
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9edcf45..9469f4c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -144,6 +144,11 @@
static int ngroups_max = NGROUPS_MAX;
static const int cap_last_cap = CAP_LAST_CAP;
+/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+#ifdef CONFIG_DETECT_HUNG_TASK
+static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
+#endif
+
#ifdef CONFIG_INOTIFY_USER
#include <linux/inotify.h>
#endif
@@ -966,6 +971,7 @@
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dohung_task_timeout_secs,
+ .extra2 = &hung_task_timeout_max,
},
{
.procname = "hung_task_warnings",
@@ -1043,6 +1049,16 @@
.maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = perf_proc_update_handler,
+ .extra1 = &one,
+ },
+ {
+ .procname = "perf_cpu_time_max_percent",
+ .data = &sysctl_perf_cpu_time_max_percent,
+ .maxlen = sizeof(sysctl_perf_cpu_time_max_percent),
+ .mode = 0644,
+ .proc_handler = perf_cpu_time_max_percent_handler,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
},
#endif
#ifdef CONFIG_KMEMCHECK
diff --git a/kernel/time.c b/kernel/time.c
index d3617db..31ec845 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -195,6 +195,10 @@
if (tv) {
if (copy_from_user(&user_tv, tv, sizeof(*tv)))
return -EFAULT;
+
+ if (!timeval_valid(&user_tv))
+ return -EINVAL;
+
new_ts.tv_sec = user_tv.tv_sec;
new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
}
@@ -496,17 +500,20 @@
* that a remainder subtract here would not do the right thing as the
* resolution values don't fall on second boundries. I.e. the line:
* nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
+ * Note that due to the small error in the multiplier here, this
+ * rounding is incorrect for sufficiently large values of tv_nsec, but
+ * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're
+ * OK.
*
* Rather, we just shift the bits off the right.
*
* The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
* value to a scaled second value.
*/
-unsigned long
-timespec_to_jiffies(const struct timespec *value)
+static unsigned long
+__timespec_to_jiffies(unsigned long sec, long nsec)
{
- unsigned long sec = value->tv_sec;
- long nsec = value->tv_nsec + TICK_NSEC - 1;
+ nsec = nsec + TICK_NSEC - 1;
if (sec >= MAX_SEC_IN_JIFFIES){
sec = MAX_SEC_IN_JIFFIES;
@@ -517,6 +524,13 @@
(NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
}
+
+unsigned long
+timespec_to_jiffies(const struct timespec *value)
+{
+ return __timespec_to_jiffies(value->tv_sec, value->tv_nsec);
+}
+
EXPORT_SYMBOL(timespec_to_jiffies);
void
@@ -533,31 +547,27 @@
}
EXPORT_SYMBOL(jiffies_to_timespec);
-/* Same for "timeval"
+/*
+ * We could use a similar algorithm to timespec_to_jiffies (with a
+ * different multiplier for usec instead of nsec). But this has a
+ * problem with rounding: we can't exactly add TICK_NSEC - 1 to the
+ * usec value, since it's not necessarily integral.
*
- * Well, almost. The problem here is that the real system resolution is
- * in nanoseconds and the value being converted is in micro seconds.
- * Also for some machines (those that use HZ = 1024, in-particular),
- * there is a LARGE error in the tick size in microseconds.
-
- * The solution we use is to do the rounding AFTER we convert the
- * microsecond part. Thus the USEC_ROUND, the bits to be shifted off.
- * Instruction wise, this should cost only an additional add with carry
- * instruction above the way it was done above.
+ * We could instead round in the intermediate scaled representation
+ * (i.e. in units of 1/2^(large scale) jiffies) but that's also
+ * perilous: the scaling introduces a small positive error, which
+ * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1
+ * units to the intermediate before shifting) leads to accidental
+ * overflow and overestimates.
+ *
+ * At the cost of one additional multiplication by a constant, just
+ * use the timespec implementation.
*/
unsigned long
timeval_to_jiffies(const struct timeval *value)
{
- unsigned long sec = value->tv_sec;
- long usec = value->tv_usec;
-
- if (sec >= MAX_SEC_IN_JIFFIES){
- sec = MAX_SEC_IN_JIFFIES;
- usec = 0;
- }
- return (((u64)sec * SEC_CONVERSION) +
- (((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
- (USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
+ return __timespec_to_jiffies(value->tv_sec,
+ value->tv_usec * NSEC_PER_USEC);
}
EXPORT_SYMBOL(timeval_to_jiffies);
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index ff7d9d2..a64e0de 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o
+endif
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
obj-$(CONFIG_TIMER_STATS) += timer_stats.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index f11d83b..7d19fca 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -419,18 +419,26 @@
static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
ktime_t now)
{
+ unsigned long flags;
struct k_itimer *ptr = container_of(alarm, struct k_itimer,
it.alarm.alarmtimer);
- if (posix_timer_event(ptr, 0) != 0)
- ptr->it_overrun++;
+ enum alarmtimer_restart result = ALARMTIMER_NORESTART;
+
+ spin_lock_irqsave(&ptr->it_lock, flags);
+ if ((ptr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) {
+ if (posix_timer_event(ptr, 0) != 0)
+ ptr->it_overrun++;
+ }
/* Re-add periodic timers */
if (ptr->it.alarm.interval.tv64) {
ptr->it_overrun += alarm_forward(alarm, now,
ptr->it.alarm.interval);
- return ALARMTIMER_RESTART;
+ result = ALARMTIMER_RESTART;
}
- return ALARMTIMER_NORESTART;
+ spin_unlock_irqrestore(&ptr->it_lock, flags);
+
+ return result;
}
/**
@@ -445,7 +453,7 @@
clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid;
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EINVAL;
return hrtimer_get_res(baseid, tp);
}
@@ -462,7 +470,7 @@
struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
if (!alarmtimer_get_rtcdev())
- return -ENOTSUPP;
+ return -EINVAL;
*tp = ktime_to_timespec(base->gettime());
return 0;
@@ -540,9 +548,14 @@
struct itimerspec *new_setting,
struct itimerspec *old_setting)
{
+ ktime_t exp;
+
if (!rtcdev)
return -ENOTSUPP;
+ if (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
if (old_setting)
alarm_timer_get(timr, old_setting);
@@ -552,8 +565,16 @@
/* start the timer */
timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
- alarm_start(&timr->it.alarm.alarmtimer,
- timespec_to_ktime(new_setting->it_value));
+ exp = timespec_to_ktime(new_setting->it_value);
+ /* Convert (if necessary) to absolute time */
+ if (flags != TIMER_ABSTIME) {
+ ktime_t now;
+
+ now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+ exp = ktime_add(now, exp);
+ }
+
+ alarm_start(&timr->it.alarm.alarmtimer, exp);
return 0;
}
@@ -685,6 +706,9 @@
if (!alarmtimer_get_rtcdev())
return -ENOTSUPP;
+ if (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
if (!capable(CAP_WAKE_ALARM))
return -EPERM;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c6d6400..378613b 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -15,7 +15,6 @@
#include <linux/hrtimer.h>
#include <linux/init.h>
#include <linux/module.h>
-#include <linux/notifier.h>
#include <linux/smp.h>
#include "tick-internal.h"
@@ -23,13 +22,57 @@
/* The registered clock event devices */
static LIST_HEAD(clockevent_devices);
static LIST_HEAD(clockevents_released);
-
-/* Notification for clock events */
-static RAW_NOTIFIER_HEAD(clockevents_chain);
-
/* Protection for the above */
static DEFINE_RAW_SPINLOCK(clockevents_lock);
+static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt,
+ bool ismax)
+{
+ u64 clc = (u64) latch << evt->shift;
+ u64 rnd;
+
+ if (unlikely(!evt->mult)) {
+ evt->mult = 1;
+ WARN_ON(1);
+ }
+ rnd = (u64) evt->mult - 1;
+
+ /*
+ * Upper bound sanity check. If the backwards conversion is
+ * not equal latch, we know that the above shift overflowed.
+ */
+ if ((clc >> evt->shift) != (u64)latch)
+ clc = ~0ULL;
+
+ /*
+ * Scaled math oddities:
+ *
+ * For mult <= (1 << shift) we can safely add mult - 1 to
+ * prevent integer rounding loss. So the backwards conversion
+ * from nsec to device ticks will be correct.
+ *
+ * For mult > (1 << shift), i.e. device frequency is > 1GHz we
+ * need to be careful. Adding mult - 1 will result in a value
+ * which when converted back to device ticks can be larger
+ * than latch by up to (mult - 1) >> shift. For the min_delta
+ * calculation we still want to apply this in order to stay
+ * above the minimum device ticks limit. For the upper limit
+ * we would end up with a latch value larger than the upper
+ * limit of the device, so we omit the add to stay below the
+ * device upper boundary.
+ *
+ * Also omit the add if it would overflow the u64 boundary.
+ */
+ if ((~0ULL - clc > rnd) &&
+ (!ismax || evt->mult <= (1U << evt->shift)))
+ clc += rnd;
+
+ do_div(clc, evt->mult);
+
+ /* Deltas less than 1usec are pointless noise */
+ return clc > 1000 ? clc : 1000;
+}
+
/**
* clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds
* @latch: value to convert
@@ -39,20 +82,7 @@
*/
u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt)
{
- u64 clc = (u64) latch << evt->shift;
-
- if (unlikely(!evt->mult)) {
- evt->mult = 1;
- WARN_ON(1);
- }
-
- do_div(clc, evt->mult);
- if (clc < 1000)
- clc = 1000;
- if (clc > KTIME_MAX)
- clc = KTIME_MAX;
-
- return clc;
+ return cev_delta2ns(latch, evt, false);
}
EXPORT_SYMBOL_GPL(clockevent_delta2ns);
@@ -108,7 +138,8 @@
{
/* Nothing to do if we already reached the limit */
if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
- printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+ printk_deferred(KERN_WARNING
+ "CE: Reprogramming failure. Giving up\n");
dev->next_event.tv64 = KTIME_MAX;
return -ETIME;
}
@@ -121,9 +152,10 @@
if (dev->min_delta_ns > MIN_DELTA_LIMIT)
dev->min_delta_ns = MIN_DELTA_LIMIT;
- printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
- dev->name ? dev->name : "?",
- (unsigned long long) dev->min_delta_ns);
+ printk_deferred(KERN_WARNING
+ "CE: %s increased min_delta_ns to %llu nsec\n",
+ dev->name ? dev->name : "?",
+ (unsigned long long) dev->min_delta_ns);
return 0;
}
@@ -232,30 +264,6 @@
return (rc && force) ? clockevents_program_min_delta(dev) : rc;
}
-/**
- * clockevents_register_notifier - register a clock events change listener
- */
-int clockevents_register_notifier(struct notifier_block *nb)
-{
- unsigned long flags;
- int ret;
-
- raw_spin_lock_irqsave(&clockevents_lock, flags);
- ret = raw_notifier_chain_register(&clockevents_chain, nb);
- raw_spin_unlock_irqrestore(&clockevents_lock, flags);
-
- return ret;
-}
-
-/*
- * Notify about a clock event change. Called with clockevents_lock
- * held.
- */
-static void clockevents_do_notify(unsigned long reason, void *dev)
-{
- raw_notifier_call_chain(&clockevents_chain, reason, dev);
-}
-
/*
* Called after a notify add to make devices available which were
* released from the notifier call.
@@ -269,7 +277,7 @@
struct clock_event_device, list);
list_del(&dev->list);
list_add(&dev->list, &clockevent_devices);
- clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+ tick_check_new_device(dev);
}
}
@@ -290,7 +298,7 @@
raw_spin_lock_irqsave(&clockevents_lock, flags);
list_add(&dev->list, &clockevent_devices);
- clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev);
+ tick_check_new_device(dev);
clockevents_notify_released();
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
@@ -317,8 +325,8 @@
sec = 600;
clockevents_calc_mult_shift(dev, freq, sec);
- dev->min_delta_ns = clockevent_delta2ns(dev->min_delta_ticks, dev);
- dev->max_delta_ns = clockevent_delta2ns(dev->max_delta_ticks, dev);
+ dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false);
+ dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true);
}
/**
@@ -386,6 +394,7 @@
* released list and do a notify add later.
*/
if (old) {
+ module_put(old->owner);
clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
list_del(&old->list);
list_add(&old->list, &clockevents_released);
@@ -425,18 +434,45 @@
#ifdef CONFIG_GENERIC_CLOCKEVENTS
/**
* clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
*/
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
{
struct clock_event_device *dev, *tmp;
unsigned long flags;
- int cpu;
+ int cpu, ret = 0;
raw_spin_lock_irqsave(&clockevents_lock, flags);
- clockevents_do_notify(reason, arg);
switch (reason) {
+ case CLOCK_EVT_NOTIFY_BROADCAST_ON:
+ case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
+ case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+ tick_broadcast_on_off(reason, arg);
+ break;
+
+ case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
+ case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
+ ret = tick_broadcast_oneshot_control(reason);
+ break;
+
+ case CLOCK_EVT_NOTIFY_CPU_DYING:
+ tick_handover_do_timer(arg);
+ break;
+
+ case CLOCK_EVT_NOTIFY_SUSPEND:
+ tick_suspend();
+ tick_suspend_broadcast();
+ break;
+
+ case CLOCK_EVT_NOTIFY_RESUME:
+ tick_resume();
+ break;
+
case CLOCK_EVT_NOTIFY_CPU_DEAD:
+ tick_shutdown_broadcast_oneshot(arg);
+ tick_shutdown_broadcast(arg);
+ tick_shutdown(arg);
/*
* Unregister the clock event devices which were
* released from the users in the notify chain.
@@ -460,6 +496,7 @@
break;
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ return ret;
}
EXPORT_SYMBOL_GPL(clockevents_notify);
#endif
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba..a6a5bf5 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
* HZ shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
+#if HZ < 34
+#define JIFFIES_SHIFT 6
+#elif HZ < 67
+#define JIFFIES_SHIFT 7
+#else
#define JIFFIES_SHIFT 8
+#endif
static cycle_t jiffies_read(struct clocksource *cs)
{
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8f5b3b9..6211d5d 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -475,6 +475,7 @@
* called as close as possible to 500 ms before the new second starts.
* This code is run on a timer. If the clock is set, that timer
* may not expire at the correct time. Thus, we adjust...
+ * We want the clock to be within a couple of ticks from the target.
*/
if (!ntp_synced()) {
/*
@@ -485,7 +486,7 @@
}
getnstimeofday(&now);
- if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2) {
+ if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
struct timespec adjust = now;
fail = -ENODEV;
@@ -516,13 +517,13 @@
schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
}
-static void notify_cmos_timer(void)
+void ntp_notify_cmos_timer(void)
{
schedule_delayed_work(&sync_cmos_work, 0);
}
#else
-static inline void notify_cmos_timer(void) { }
+void ntp_notify_cmos_timer(void) { }
#endif
@@ -630,6 +631,17 @@
if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
return -EPERM;
+ /*
+ * Check for potential multiplication overflows that can
+ * only happen on 64-bit systems:
+ */
+ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) {
+ if (LLONG_MIN / PPM_SCALE > txc->freq)
+ return -EINVAL;
+ if (LLONG_MAX / PPM_SCALE < txc->freq)
+ return -EINVAL;
+ }
+
return 0;
}
@@ -687,8 +699,6 @@
if (!(time_status & STA_NANO))
txc->time.tv_usec /= NSEC_PER_USEC;
- notify_cmos_timer();
-
return result;
}
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 0000000..eb682d5
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *bc)
+{
+ switch (mode) {
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ /*
+ * Note, we cannot cancel the timer here as we might
+ * run into the following live lock scenario:
+ *
+ * cpu 0 cpu1
+ * lock(broadcast_lock);
+ * hrtimer_interrupt()
+ * bc_handler()
+ * tick_handle_oneshot_broadcast();
+ * lock(broadcast_lock);
+ * hrtimer_cancel()
+ * wait_for_callback()
+ */
+ hrtimer_try_to_cancel(&bctimer);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+ /*
+ * We try to cancel the timer first. If the callback is on
+ * flight on some other cpu then we let it handle it. If we
+ * were able to cancel the timer nothing can rearm it as we
+ * own broadcast_lock.
+ *
+ * However we can also be called from the event handler of
+ * ce_broadcast_hrtimer itself when it expires. We cannot
+ * restart the timer because we are in the callback, but we
+ * can set the expiry time and let the callback return
+ * HRTIMER_RESTART.
+ */
+ if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ /* Bind the "device" to the cpu */
+ bc->bound_on = smp_processor_id();
+ } else if (bc->bound_on == smp_processor_id()) {
+ hrtimer_set_expires(&bctimer, expires);
+ }
+ return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+ .set_mode = bc_set_mode,
+ .set_next_ktime = bc_set_next,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_KTIME |
+ CLOCK_EVT_FEAT_HRTIMER,
+ .rating = 0,
+ .bound_on = -1,
+ .min_delta_ns = 1,
+ .max_delta_ns = KTIME_MAX,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = ULONG_MAX,
+ .mult = 1,
+ .shift = 0,
+ .cpumask = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+ ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+ if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ return HRTIMER_NORESTART;
+
+ return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ bctimer.function = bc_handler;
+ clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 20d6fba..16f4830 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -19,6 +19,7 @@
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/module.h>
#include "tick-internal.h"
@@ -29,6 +30,7 @@
static struct tick_device tick_broadcast_device;
static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tick_broadcast_on;
static cpumask_var_t tmpmask;
static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
@@ -64,17 +66,34 @@
/*
* Check, if the device can be utilized as broadcast device:
*/
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
+{
+ if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+ (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+ return false;
+
+ if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+ !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return false;
+
+ return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
{
struct clock_event_device *cur = tick_broadcast_device.evtdev;
- if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
- (tick_broadcast_device.evtdev &&
- tick_broadcast_device.evtdev->rating >= dev->rating) ||
- (dev->features & CLOCK_EVT_FEAT_C3STOP))
- return 0;
+ if (!tick_check_broadcast_device(cur, dev))
+ return;
- clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+ if (!try_module_get(dev->owner))
+ return;
+
+ clockevents_exchange_device(cur, dev);
if (cur)
cur->event_handler = clockevents_handle_noop;
tick_broadcast_device.evtdev = dev;
@@ -90,7 +109,6 @@
*/
if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_clock_notify();
- return 1;
}
/*
@@ -123,8 +141,9 @@
*/
int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
unsigned long flags;
- int ret = 0;
+ int ret;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
@@ -138,20 +157,59 @@
dev->event_handler = tick_handle_periodic;
tick_device_setup_broadcast_func(dev);
cpumask_set_cpu(cpu, tick_broadcast_mask);
- tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+ tick_broadcast_start_periodic(bc);
ret = 1;
} else {
/*
- * When the new device is not affected by the stop
- * feature and the cpu is marked in the broadcast mask
- * then clear the broadcast bit.
+ * Clear the broadcast bit for this cpu if the
+ * device is not power state affected.
*/
- if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
- int cpu = smp_processor_id();
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
cpumask_clear_cpu(cpu, tick_broadcast_mask);
- tick_broadcast_clear_oneshot(cpu);
- } else {
+ else
tick_device_setup_broadcast_func(dev);
+
+ /*
+ * Clear the broadcast bit if the CPU is not in
+ * periodic broadcast on state.
+ */
+ if (!cpumask_test_cpu(cpu, tick_broadcast_on))
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
+
+ switch (tick_broadcast_device.mode) {
+ case TICKDEV_MODE_ONESHOT:
+ /*
+ * If the system is in oneshot mode we can
+ * unconditionally clear the oneshot mask bit,
+ * because the CPU is running and therefore
+ * not in an idle state which causes the power
+ * state affected device to stop. Let the
+ * caller initialize the device.
+ */
+ tick_broadcast_clear_oneshot(cpu);
+ ret = 0;
+ break;
+
+ case TICKDEV_MODE_PERIODIC:
+ /*
+ * If the system is in periodic mode, check
+ * whether the broadcast device can be
+ * switched off now.
+ */
+ if (cpumask_empty(tick_broadcast_mask) && bc)
+ clockevents_shutdown(bc);
+ /*
+ * If we kept the cpu in the broadcast mask,
+ * tell the caller to leave the per cpu device
+ * in shutdown state. The periodic interrupt
+ * is delivered by the broadcast device.
+ */
+ ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+ break;
+ default:
+ /* Nothing to do */
+ ret = 0;
+ break;
}
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
@@ -281,6 +339,7 @@
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+ cpumask_set_cpu(cpu, tick_broadcast_on);
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
@@ -290,8 +349,12 @@
tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (!tick_broadcast_force &&
- cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
+ if (tick_broadcast_force)
+ break;
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
+ if (!tick_device_is_functional(dev))
+ break;
+ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
@@ -349,6 +412,7 @@
bc = tick_broadcast_device.evtdev;
cpumask_clear_cpu(cpu, tick_broadcast_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
if (bc && cpumask_empty(tick_broadcast_mask))
@@ -475,7 +539,15 @@
if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
- clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+ /*
+ * We might be in the middle of switching over from
+ * periodic to oneshot. If the CPU has not yet
+ * switched over, leave the device alone.
+ */
+ if (td->mode == TICKDEV_MODE_ONESHOT) {
+ clockevents_set_mode(td->evtdev,
+ CLOCK_EVT_MODE_ONESHOT);
+ }
}
}
@@ -522,6 +594,13 @@
cpumask_clear(tick_broadcast_force_mask);
/*
+ * Sanity check. Catch the case where we try to broadcast to
+ * offline cpus.
+ */
+ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+ cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+ /*
* Wakeup the cpus which have an expired event.
*/
tick_do_broadcast(tmpmask);
@@ -547,24 +626,61 @@
raw_spin_unlock(&tick_broadcast_lock);
}
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+ return 0;
+ if (bc->next_event.tv64 == KTIME_MAX)
+ return 0;
+ return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+ struct clock_event_device *dev)
+{
+ /*
+ * For hrtimer based broadcasting we cannot shutdown the cpu
+ * local device if our own event is the first one to expire or
+ * if we own the broadcast timer.
+ */
+ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+ if (broadcast_needs_cpu(bc, smp_processor_id()))
+ return;
+ if (dev->next_event.tv64 < bc->next_event.tv64)
+ return;
+ }
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+ return;
+ /* This moves the broadcast assignment to this cpu */
+ clockevents_program_event(bc, bc->next_event, 1);
+}
+
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
*/
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags;
ktime_t now;
- int cpu;
+ int cpu, ret = 0;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
- return;
+ return 0;
/*
* We are called with preemtion disabled from the depth of the
@@ -575,7 +691,7 @@
dev = td->evtdev;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
- return;
+ return 0;
bc = tick_broadcast_device.evtdev;
@@ -583,7 +699,7 @@
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
- clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+ broadcast_shutdown_local(bc, dev);
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
@@ -596,6 +712,16 @@
dev->next_event.tv64 < bc->next_event.tv64)
tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
+ /*
+ * If the current CPU owns the hrtimer broadcast
+ * mechanism, it cannot go deep idle and we remove the
+ * CPU from the broadcast mask. We don't have to go
+ * through the EXIT path as the local timer is not
+ * shutdown.
+ */
+ ret = broadcast_needs_cpu(bc, cpu);
+ if (ret)
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -663,6 +789,7 @@
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ return ret;
}
/*
@@ -673,6 +800,7 @@
static void tick_broadcast_clear_oneshot(int cpu)
{
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -761,10 +889,14 @@
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
- * Clear the broadcast mask flag for the dead cpu, but do not
- * stop the broadcast device!
+ * Clear the broadcast masks for the dead cpu, but do not stop
+ * the broadcast device!
*/
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+
+ broadcast_move_bc(cpu);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -792,6 +924,7 @@
void __init tick_broadcast_init(void)
{
zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT);
zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
#ifdef CONFIG_TICK_ONESHOT
zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 5d3fb10..21711bc 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -18,6 +18,7 @@
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
+#include <linux/module.h>
#include <asm/irq_regs.h>
@@ -194,7 +195,8 @@
* When global broadcasting is active, check if the current
* device is registered as a placeholder for broadcast mode.
* This allows us to handle this x86 misfeature in a generic
- * way.
+ * way. This function also returns !=0 when we keep the
+ * current active broadcast state for this CPU.
*/
if (tick_device_uses_broadcast(newdev, cpu))
return;
@@ -205,14 +207,50 @@
tick_setup_oneshot(newdev, handler, next_event);
}
+static bool tick_check_percpu(struct clock_event_device *curdev,
+ struct clock_event_device *newdev, int cpu)
+{
+ if (!cpumask_test_cpu(cpu, newdev->cpumask))
+ return false;
+ if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
+ return true;
+ /* Check if irq affinity can be set */
+ if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
+ return false;
+ /* Prefer an existing cpu local device */
+ if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
+ return false;
+ return true;
+}
+
+static bool tick_check_preferred(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
+{
+ /* Prefer oneshot capable device */
+ if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
+ if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return false;
+ if (tick_oneshot_mode_active())
+ return false;
+ }
+
+ /*
+ * Use the higher rated one, but prefer a CPU local device with a lower
+ * rating than a non-CPU local device
+ */
+ return !curdev ||
+ newdev->rating > curdev->rating ||
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
+}
+
/*
* Check, if the new registered device should be used.
*/
-static int tick_check_new_device(struct clock_event_device *newdev)
+void tick_check_new_device(struct clock_event_device *newdev)
{
struct clock_event_device *curdev;
struct tick_device *td;
- int cpu, ret = NOTIFY_OK;
+ int cpu;
unsigned long flags;
raw_spin_lock_irqsave(&tick_device_lock, flags);
@@ -225,40 +263,15 @@
curdev = td->evtdev;
/* cpu local device ? */
- if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
+ if (!tick_check_percpu(curdev, newdev, cpu))
+ goto out_bc;
- /*
- * If the cpu affinity of the device interrupt can not
- * be set, ignore it.
- */
- if (!irq_can_set_affinity(newdev->irq))
- goto out_bc;
+ /* Preference decision */
+ if (!tick_check_preferred(curdev, newdev))
+ goto out_bc;
- /*
- * If we have a cpu local device already, do not replace it
- * by a non cpu local device
- */
- if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
- goto out_bc;
- }
-
- /*
- * If we have an active device, then check the rating and the oneshot
- * feature.
- */
- if (curdev) {
- /*
- * Prefer one shot capable devices !
- */
- if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) &&
- !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
- goto out_bc;
- /*
- * Check the rating
- */
- if (curdev->rating >= newdev->rating)
- goto out_bc;
- }
+ if (!try_module_get(newdev->owner))
+ return;
/*
* Replace the eventually existing device by the new
@@ -275,18 +288,14 @@
tick_oneshot_notify();
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
- return NOTIFY_STOP;
+ return;
out_bc:
/*
* Can the new device be used as a broadcast device ?
*/
- if (tick_check_broadcast_device(newdev))
- ret = NOTIFY_STOP;
-
+ tick_install_broadcast_device(newdev);
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
-
- return ret;
}
/*
@@ -294,7 +303,7 @@
*
* Called with interrupts disabled.
*/
-static void tick_handover_do_timer(int *cpup)
+void tick_handover_do_timer(int *cpup)
{
if (*cpup == tick_do_timer_cpu) {
int cpu = cpumask_first(cpu_online_mask);
@@ -311,7 +320,7 @@
* access the hardware device itself.
* We just set the mode and remove it from the lists.
*/
-static void tick_shutdown(unsigned int *cpup)
+void tick_shutdown(unsigned int *cpup)
{
struct tick_device *td = &per_cpu(tick_cpu_device, *cpup);
struct clock_event_device *dev = td->evtdev;
@@ -332,7 +341,7 @@
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
-static void tick_suspend(void)
+void tick_suspend(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
unsigned long flags;
@@ -342,7 +351,7 @@
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
-static void tick_resume(void)
+void tick_resume(void)
{
struct tick_device *td = &__get_cpu_var(tick_cpu_device);
unsigned long flags;
@@ -360,65 +369,10 @@
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
}
-/*
- * Notification about clock event devices
- */
-static int tick_notify(struct notifier_block *nb, unsigned long reason,
- void *dev)
-{
- switch (reason) {
-
- case CLOCK_EVT_NOTIFY_ADD:
- return tick_check_new_device(dev);
-
- case CLOCK_EVT_NOTIFY_BROADCAST_ON:
- case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
- tick_broadcast_on_off(reason, dev);
- break;
-
- case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
- case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
- tick_broadcast_oneshot_control(reason);
- break;
-
- case CLOCK_EVT_NOTIFY_CPU_DYING:
- tick_handover_do_timer(dev);
- break;
-
- case CLOCK_EVT_NOTIFY_CPU_DEAD:
- tick_shutdown_broadcast_oneshot(dev);
- tick_shutdown_broadcast(dev);
- tick_shutdown(dev);
- break;
-
- case CLOCK_EVT_NOTIFY_SUSPEND:
- tick_suspend();
- tick_suspend_broadcast();
- break;
-
- case CLOCK_EVT_NOTIFY_RESUME:
- tick_resume();
- break;
-
- default:
- break;
- }
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block tick_notifier = {
- .notifier_call = tick_notify,
-};
-
/**
* tick_init - initialize the tick control
- *
- * Register the notifier with the clockevents framework
*/
void __init tick_init(void)
{
- clockevents_register_notifier(&tick_notifier);
tick_broadcast_init();
}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index f0299ea..c85edb1 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -18,6 +18,11 @@
extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast);
extern void tick_handle_periodic(struct clock_event_device *dev);
+extern void tick_check_new_device(struct clock_event_device *dev);
+extern void tick_handover_do_timer(int *cpup);
+extern void tick_shutdown(unsigned int *cpup);
+extern void tick_suspend(void);
+extern void tick_resume(void);
extern void clockevents_shutdown(struct clock_event_device *dev);
@@ -34,7 +39,7 @@
extern void tick_resume_oneshot(void);
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -46,7 +51,7 @@
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
@@ -75,7 +80,7 @@
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
@@ -90,7 +95,7 @@
*/
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
-extern int tick_check_broadcast_device(struct clock_event_device *dev);
+extern void tick_install_broadcast_device(struct clock_event_device *dev);
extern int tick_is_broadcast_device(struct clock_event_device *dev);
extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
extern void tick_shutdown_broadcast(unsigned int *cpup);
@@ -102,9 +107,8 @@
#else /* !BROADCAST */
-static inline int tick_check_broadcast_device(struct clock_event_device *dev)
+static inline void tick_install_broadcast_device(struct clock_event_device *dev)
{
- return 0;
}
static inline int tick_is_broadcast_device(struct clock_event_device *dev)
@@ -141,6 +145,8 @@
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
#endif
extern void do_timer(unsigned long ticks);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 0cf1c14..67f7a2d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -720,8 +720,10 @@
return false;
}
- if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+ if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+ ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
return false;
+ }
if (need_resched())
return false;
@@ -832,13 +834,10 @@
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
- if (ts->inidle) {
- /* Cancel the timer because CPU already waken up from the C-states*/
- menu_hrtimer_cancel();
+ if (ts->inidle)
__tick_nohz_idle_enter(ts);
- } else {
+ else
tick_nohz_full_stop_tick(ts);
- }
}
/**
@@ -936,8 +935,6 @@
ts->inidle = 0;
- /* Cancel the timer because CPU already waken up from the C-states*/
- menu_hrtimer_cancel();
if (ts->idle_active || ts->tick_stopped)
now = ktime_get();
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index baeeb5c8..76fefb1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -72,7 +72,7 @@
tk->wall_to_monotonic = wtm;
set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
tk->offs_real = timespec_to_ktime(tmp);
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -590,7 +590,7 @@
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
tk->tai_offset = tai_offset;
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}
/**
@@ -605,6 +605,7 @@
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
__timekeeping_set_tai_offset(tk, tai_offset);
+ timekeeping_update(tk, false, true);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clock_was_set();
@@ -1007,6 +1008,8 @@
timekeeping_suspend_time =
timespec_add(timekeeping_suspend_time, delta_delta);
}
+
+ timekeeping_update(tk, false, true);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1236,9 +1239,10 @@
* It also calls into the NTP code to handle leapsecond processing.
*
*/
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+ unsigned int clock_set = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
@@ -1260,9 +1264,10 @@
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
- clock_was_set_delayed();
+ clock_set = 1;
}
}
+ return clock_set;
}
/**
@@ -1275,7 +1280,8 @@
* Returns the unconsumed cycles.
*/
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
- u32 shift)
+ u32 shift,
+ unsigned int *clock_set)
{
cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
@@ -1289,7 +1295,7 @@
tk->cycle_last += interval;
tk->xtime_nsec += tk->xtime_interval << shift;
- accumulate_nsecs_to_secs(tk);
+ *clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1328,7 +1334,7 @@
tk->xtime_nsec -= remainder;
tk->xtime_nsec += 1ULL << tk->shift;
tk->ntp_error += remainder << tk->ntp_error_shift;
-
+ tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
}
#else
#define old_vsyscall_fixup(tk)
@@ -1347,6 +1353,7 @@
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
+ unsigned int clock_set = 0;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1381,7 +1388,8 @@
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
- offset = logarithmic_accumulation(tk, offset, shift);
+ offset = logarithmic_accumulation(tk, offset, shift,
+ &clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
@@ -1399,7 +1407,7 @@
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
- accumulate_nsecs_to_secs(tk);
+ clock_set |= accumulate_nsecs_to_secs(tk);
write_seqcount_begin(&timekeeper_seq);
/* Update clock->cycle_last with the new value */
@@ -1419,6 +1427,10 @@
write_seqcount_end(&timekeeper_seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (clock_set)
+ /* have to call outside the timekeeper_seq */
+ clock_was_set_delayed();
+
}
/**
@@ -1677,11 +1689,16 @@
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
- clock_was_set_delayed();
+ timekeeping_update(tk, false, true);
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (tai != orig_tai)
+ clock_was_set();
+
+ ntp_notify_cmos_timer();
+
return ret;
}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 3bdf283..61ed862 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -265,10 +265,9 @@
static int timer_list_show(struct seq_file *m, void *v)
{
struct timer_list_iter *iter = v;
- u64 now = ktime_to_ns(ktime_get());
if (iter->cpu == -1 && !iter->second_pass)
- timer_list_header(m, now);
+ timer_list_header(m, iter->now);
else if (!iter->second_pass)
print_cpu(m, iter->cpu, iter->now);
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -298,33 +297,41 @@
return;
}
+static void *move_iter(struct timer_list_iter *iter, loff_t offset)
+{
+ for (; offset; offset--) {
+ iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+ if (iter->cpu >= nr_cpu_ids) {
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ if (!iter->second_pass) {
+ iter->cpu = -1;
+ iter->second_pass = true;
+ } else
+ return NULL;
+#else
+ return NULL;
+#endif
+ }
+ }
+ return iter;
+}
+
static void *timer_list_start(struct seq_file *file, loff_t *offset)
{
struct timer_list_iter *iter = file->private;
- if (!*offset) {
- iter->cpu = -1;
+ if (!*offset)
iter->now = ktime_to_ns(ktime_get());
- } else if (iter->cpu >= nr_cpu_ids) {
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
- if (!iter->second_pass) {
- iter->cpu = -1;
- iter->second_pass = true;
- } else
- return NULL;
-#else
- return NULL;
-#endif
- }
- return iter;
+ iter->cpu = -1;
+ iter->second_pass = false;
+ return move_iter(iter, *offset);
}
static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
{
struct timer_list_iter *iter = file->private;
- iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
++*offset;
- return timer_list_start(file, offset);
+ return move_iter(iter, 1);
}
static void timer_list_stop(struct seq_file *seq, void *v)
diff --git a/kernel/timer.c b/kernel/timer.c
index 15ffdb3..20f45ea 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -149,9 +149,11 @@
/* now that we have rounded, subtract the extra skew again */
j -= cpu * 3;
- if (j <= jiffies) /* rounding ate our timeout entirely; */
- return original;
- return j;
+ /*
+ * Make sure j is still in the future. Otherwise return the
+ * unmodified value.
+ */
+ return time_is_after_jiffies(j) ? j : original;
}
/**
@@ -820,7 +822,7 @@
bit = find_last_bit(&mask, BITS_PER_LONG);
- mask = (1 << bit) - 1;
+ mask = (1UL << bit) - 1;
expires_limit = expires_limit & ~(mask);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b8b8560..686417b 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -685,6 +685,7 @@
* blk_add_trace_rq - Add a trace for a request oriented action
* @q: queue the io is for
* @rq: the source request
+ * @nr_bytes: number of completed bytes
* @what: the action
*
* Description:
@@ -692,7 +693,7 @@
*
**/
static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
- u32 what)
+ unsigned int nr_bytes, u32 what)
{
struct blk_trace *bt = q->blk_trace;
@@ -701,11 +702,11 @@
if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
what |= BLK_TC_ACT(BLK_TC_PC);
- __blk_add_trace(bt, 0, blk_rq_bytes(rq), rq->cmd_flags,
+ __blk_add_trace(bt, 0, nr_bytes, rq->cmd_flags,
what, rq->errors, rq->cmd_len, rq->cmd);
} else {
what |= BLK_TC_ACT(BLK_TC_FS);
- __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
+ __blk_add_trace(bt, blk_rq_pos(rq), nr_bytes,
rq->cmd_flags, what, rq->errors, 0, NULL);
}
}
@@ -713,33 +714,34 @@
static void blk_add_trace_rq_abort(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
}
static void blk_add_trace_rq_insert(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
}
static void blk_add_trace_rq_issue(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
}
static void blk_add_trace_rq_requeue(void *ignore,
struct request_queue *q,
struct request *rq)
{
- blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+ blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
}
static void blk_add_trace_rq_complete(void *ignore,
struct request_queue *q,
- struct request *rq)
+ struct request *rq,
+ unsigned int nr_bytes)
{
- blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+ blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
}
/**
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6c508ff..401d9bd 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -85,6 +85,8 @@
/* Current function tracing op */
struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* What to set function_trace_op to */
+static struct ftrace_ops *set_function_trace_op;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
@@ -278,6 +280,29 @@
global_ops.func = func;
}
+static void ftrace_sync(struct work_struct *work)
+{
+ /*
+ * This function is just a stub to implement a hard force
+ * of synchronize_sched(). This requires synchronizing
+ * tasks even in userspace and idle.
+ *
+ * Yes, function tracing is rude.
+ */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+ /* Probably not needed, but do it anyway */
+ smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
static void update_ftrace_function(void)
{
ftrace_func_t func;
@@ -296,16 +321,61 @@
!FTRACE_FORCE_LIST_FUNC)) {
/* Set the ftrace_ops that the arch callback uses */
if (ftrace_ops_list == &global_ops)
- function_trace_op = ftrace_global_list;
+ set_function_trace_op = ftrace_global_list;
else
- function_trace_op = ftrace_ops_list;
+ set_function_trace_op = ftrace_ops_list;
func = ftrace_ops_list->func;
} else {
/* Just use the default ftrace_ops */
- function_trace_op = &ftrace_list_end;
+ set_function_trace_op = &ftrace_list_end;
func = ftrace_ops_list_func;
}
+ update_function_graph_func();
+
+ /* If there's no change, then do nothing more here */
+ if (ftrace_trace_function == func)
+ return;
+
+ /*
+ * If we are using the list function, it doesn't care
+ * about the function_trace_ops.
+ */
+ if (func == ftrace_ops_list_func) {
+ ftrace_trace_function = func;
+ /*
+ * Don't even bother setting function_trace_ops,
+ * it would be racy to do so anyway.
+ */
+ return;
+ }
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+ /*
+ * For static tracing, we need to be a bit more careful.
+ * The function change takes affect immediately. Thus,
+ * we need to coorditate the setting of the function_trace_ops
+ * with the setting of the ftrace_trace_function.
+ *
+ * Set the function to the list ops, which will call the
+ * function we want, albeit indirectly, but it handles the
+ * ftrace_ops and doesn't depend on function_trace_op.
+ */
+ ftrace_trace_function = ftrace_ops_list_func;
+ /*
+ * Make sure all CPUs see this. Yes this is slow, but static
+ * tracing is slow and nasty to have enabled.
+ */
+ schedule_on_each_cpu(ftrace_sync);
+ /* Now all cpus are using the list ops. */
+ function_trace_op = set_function_trace_op;
+ /* Make sure the function_trace_op is visible on all CPUs */
+ smp_wmb();
+ /* Nasty way to force a rmb on all cpus */
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
+ /* OK, we are all set to update the ftrace_trace_function now! */
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
ftrace_trace_function = func;
}
@@ -367,9 +437,6 @@
static int __register_ftrace_function(struct ftrace_ops *ops)
{
- if (unlikely(ftrace_disabled))
- return -ENODEV;
-
if (FTRACE_WARN_ON(ops == &global_ops))
return -EINVAL;
@@ -417,9 +484,6 @@
{
int ret;
- if (ftrace_disabled)
- return -ENODEV;
-
if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
return -EBUSY;
@@ -434,16 +498,6 @@
} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
ret = remove_ftrace_list_ops(&ftrace_control_list,
&control_ops, ops);
- if (!ret) {
- /*
- * The ftrace_ops is now removed from the list,
- * so there'll be no new users. We must ensure
- * all current users are done before we free
- * the control data.
- */
- synchronize_sched();
- control_ops_free(ops);
- }
} else
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
@@ -453,13 +507,6 @@
if (ftrace_enabled)
update_ftrace_function();
- /*
- * Dynamic ops may be freed, we must make sure that all
- * callers are done before leaving this function.
- */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- synchronize_sched();
-
return 0;
}
@@ -756,7 +803,7 @@
int cpu;
int ret = 0;
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
ret = ftrace_profile_init_cpu(cpu);
if (ret)
break;
@@ -1416,12 +1463,22 @@
* the hashes are freed with call_rcu_sched().
*/
static int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
{
struct ftrace_hash *filter_hash;
struct ftrace_hash *notrace_hash;
int ret;
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+ /*
+ * There's a small race when adding ops that the ftrace handler
+ * that wants regs, may be called without them. We can not
+ * allow that handler to be called if regs is NULL.
+ */
+ if (regs == NULL && (ops->flags & FTRACE_OPS_FL_SAVE_REGS))
+ return 0;
+#endif
+
filter_hash = rcu_dereference_raw_notrace(ops->filter_hash);
notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash);
@@ -1948,8 +2005,14 @@
else if (command & FTRACE_DISABLE_CALLS)
ftrace_replace_code(0);
- if (command & FTRACE_UPDATE_TRACE_FUNC)
+ if (command & FTRACE_UPDATE_TRACE_FUNC) {
+ function_trace_op = set_function_trace_op;
+ smp_wmb();
+ /* If irqs are disabled, we are in stop machine */
+ if (!irqs_disabled())
+ smp_call_function(ftrace_sync_ipi, NULL, 1);
ftrace_update_ftrace_func(ftrace_trace_function);
+ }
if (command & FTRACE_START_FUNC_RET)
ftrace_enable_ftrace_graph_caller();
@@ -2038,10 +2101,15 @@
static int ftrace_startup(struct ftrace_ops *ops, int command)
{
bool hash_enable = true;
+ int ret;
if (unlikely(ftrace_disabled))
return -ENODEV;
+ ret = __register_ftrace_function(ops);
+ if (ret)
+ return ret;
+
ftrace_start_up++;
command |= FTRACE_UPDATE_CALLS;
@@ -2063,12 +2131,17 @@
return 0;
}
-static void ftrace_shutdown(struct ftrace_ops *ops, int command)
+static int ftrace_shutdown(struct ftrace_ops *ops, int command)
{
bool hash_disable = true;
+ int ret;
if (unlikely(ftrace_disabled))
- return;
+ return -ENODEV;
+
+ ret = __unregister_ftrace_function(ops);
+ if (ret)
+ return ret;
ftrace_start_up--;
/*
@@ -2102,10 +2175,42 @@
command |= FTRACE_UPDATE_TRACE_FUNC;
}
- if (!command || !ftrace_enabled)
- return;
+ if (!command || !ftrace_enabled) {
+ /*
+ * If these are control ops, they still need their
+ * per_cpu field freed. Since, function tracing is
+ * not currently active, we can just free them
+ * without synchronizing all CPUs.
+ */
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
+ return 0;
+ }
ftrace_run_update_code(command);
+
+ /*
+ * Dynamic ops may be freed, we must make sure that all
+ * callers are done before leaving this function.
+ * The same goes for freeing the per_cpu data of the control
+ * ops.
+ *
+ * Again, normal synchronize_sched() is not good enough.
+ * We need to do a hard force of sched synchronization.
+ * This is because we use preempt_disable() to do RCU, but
+ * the function tracers can be called where RCU is not watching
+ * (like before user_exit()). We can not rely on the RCU
+ * infrastructure to do the synchronization, thus we must do it
+ * ourselves.
+ */
+ if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+ schedule_on_each_cpu(ftrace_sync);
+
+ if (ops->flags & FTRACE_OPS_FL_CONTROL)
+ control_ops_free(ops);
+ }
+
+ return 0;
}
static void ftrace_startup_sysctl(void)
@@ -2134,12 +2239,57 @@
static unsigned long ftrace_update_cnt;
unsigned long ftrace_update_tot_cnt;
-static int ops_traces_mod(struct ftrace_ops *ops)
+static inline int ops_traces_mod(struct ftrace_ops *ops)
{
- struct ftrace_hash *hash;
+ /*
+ * Filter_hash being empty will default to trace module.
+ * But notrace hash requires a test of individual module functions.
+ */
+ return ftrace_hash_empty(ops->filter_hash) &&
+ ftrace_hash_empty(ops->notrace_hash);
+}
- hash = ops->filter_hash;
- return ftrace_hash_empty(hash);
+/*
+ * Check if the current ops references the record.
+ *
+ * If the ops traces all functions, then it was already accounted for.
+ * If the ops does not trace the current record function, skip it.
+ * If the ops ignores the function via notrace filter, skip it.
+ */
+static inline bool
+ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+ /* If ops isn't enabled, ignore it */
+ if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
+ return 0;
+
+ /* If ops traces all mods, we already accounted for it */
+ if (ops_traces_mod(ops))
+ return 0;
+
+ /* The function must be in the filter */
+ if (!ftrace_hash_empty(ops->filter_hash) &&
+ !ftrace_lookup_ip(ops->filter_hash, rec->ip))
+ return 0;
+
+ /* If in notrace hash, we ignore it too */
+ if (ftrace_lookup_ip(ops->notrace_hash, rec->ip))
+ return 0;
+
+ return 1;
+}
+
+static int referenced_filters(struct dyn_ftrace *rec)
+{
+ struct ftrace_ops *ops;
+ int cnt = 0;
+
+ for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
+ if (ops_references_rec(ops, rec))
+ cnt++;
+ }
+
+ return cnt;
}
static int ftrace_update_code(struct module *mod)
@@ -2148,6 +2298,7 @@
struct dyn_ftrace *p;
cycle_t start, stop;
unsigned long ref = 0;
+ bool test = false;
int i;
/*
@@ -2161,9 +2312,12 @@
for (ops = ftrace_ops_list;
ops != &ftrace_list_end; ops = ops->next) {
- if (ops->flags & FTRACE_OPS_FL_ENABLED &&
- ops_traces_mod(ops))
- ref++;
+ if (ops->flags & FTRACE_OPS_FL_ENABLED) {
+ if (ops_traces_mod(ops))
+ ref++;
+ else
+ test = true;
+ }
}
}
@@ -2173,12 +2327,16 @@
for (pg = ftrace_new_pgs; pg; pg = pg->next) {
for (i = 0; i < pg->index; i++) {
+ int cnt = ref;
+
/* If something went wrong, bail without enabling anything */
if (unlikely(ftrace_disabled))
return -1;
p = &pg->records[i];
- p->flags = ref;
+ if (test)
+ cnt += referenced_filters(p);
+ p->flags = cnt;
/*
* Do the initial record conversion from mcount jump
@@ -2198,7 +2356,7 @@
* conversion puts the module to the correct state, thus
* passing the ftrace_make_call check.
*/
- if (ftrace_start_up && ref) {
+ if (ftrace_start_up && cnt) {
int failed = __ftrace_replace_code(p, 1);
if (failed)
ftrace_bug(failed, p->ip);
@@ -2957,16 +3115,13 @@
if (i == FTRACE_FUNC_HASHSIZE)
return;
- ret = __register_ftrace_function(&trace_probe_ops);
- if (!ret)
- ret = ftrace_startup(&trace_probe_ops, 0);
+ ret = ftrace_startup(&trace_probe_ops, 0);
ftrace_probe_registered = 1;
}
static void __disable_ftrace_function_probe(void)
{
- int ret;
int i;
if (!ftrace_probe_registered)
@@ -2979,9 +3134,7 @@
}
/* no more funcs left */
- ret = __unregister_ftrace_function(&trace_probe_ops);
- if (!ret)
- ftrace_shutdown(&trace_probe_ops, 0);
+ ftrace_shutdown(&trace_probe_ops, 0);
ftrace_probe_registered = 0;
}
@@ -4069,16 +4222,11 @@
ftrace_process_locs(mod, start, end);
}
-static int ftrace_module_notify_enter(struct notifier_block *self,
- unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
{
- struct module *mod = data;
-
- if (val == MODULE_STATE_COMING)
- ftrace_init_module(mod, mod->ftrace_callsites,
- mod->ftrace_callsites +
- mod->num_ftrace_callsites);
- return 0;
+ ftrace_init_module(mod, mod->ftrace_callsites,
+ mod->ftrace_callsites +
+ mod->num_ftrace_callsites);
}
static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4092,11 +4240,6 @@
return 0;
}
#else
-static int ftrace_module_notify_enter(struct notifier_block *self,
- unsigned long val, void *data)
-{
- return 0;
-}
static int ftrace_module_notify_exit(struct notifier_block *self,
unsigned long val, void *data)
{
@@ -4104,11 +4247,6 @@
}
#endif /* CONFIG_MODULES */
-struct notifier_block ftrace_module_enter_nb = {
- .notifier_call = ftrace_module_notify_enter,
- .priority = INT_MAX, /* Run before anything that can use kprobes */
-};
-
struct notifier_block ftrace_module_exit_nb = {
.notifier_call = ftrace_module_notify_exit,
.priority = INT_MIN, /* Run after anything that can remove kprobes */
@@ -4145,10 +4283,6 @@
__start_mcount_loc,
__stop_mcount_loc);
- ret = register_module_notifier(&ftrace_module_enter_nb);
- if (ret)
- pr_warning("Failed to register trace ftrace module enter notifier\n");
-
ret = register_module_notifier(&ftrace_module_exit_nb);
if (ret)
pr_warning("Failed to register trace ftrace module exit notifier\n");
@@ -4178,17 +4312,20 @@
static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
static inline void ftrace_startup_enable(int command) { }
/* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command) \
- ({ \
- (ops)->flags |= FTRACE_OPS_FL_ENABLED; \
- 0; \
+# define ftrace_startup(ops, command) \
+ ({ \
+ int ___ret = __register_ftrace_function(ops); \
+ if (!___ret) \
+ (ops)->flags |= FTRACE_OPS_FL_ENABLED; \
+ ___ret; \
})
-# define ftrace_shutdown(ops, command) do { } while (0)
+# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops)
+
# define ftrace_startup_sysctl() do { } while (0)
# define ftrace_shutdown_sysctl() do { } while (0)
static inline int
-ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
+ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
{
return 1;
}
@@ -4211,7 +4348,7 @@
do_for_each_ftrace_op(op, ftrace_control_list) {
if (!(op->flags & FTRACE_OPS_FL_STUB) &&
!ftrace_function_local_disabled(op) &&
- ftrace_ops_test(op, ip))
+ ftrace_ops_test(op, ip, regs))
op->func(ip, parent_ip, op, regs);
} while_for_each_ftrace_op(op);
trace_recursion_clear(TRACE_CONTROL_BIT);
@@ -4244,7 +4381,7 @@
*/
preempt_disable_notrace();
do_for_each_ftrace_op(op, ftrace_ops_list) {
- if (ftrace_ops_test(op, ip))
+ if (ftrace_ops_test(op, ip, regs))
op->func(ip, parent_ip, op, regs);
} while_for_each_ftrace_op(op);
preempt_enable_notrace();
@@ -4583,9 +4720,7 @@
mutex_lock(&ftrace_lock);
- ret = __register_ftrace_function(ops);
- if (!ret)
- ret = ftrace_startup(ops, 0);
+ ret = ftrace_startup(ops, 0);
mutex_unlock(&ftrace_lock);
@@ -4604,9 +4739,7 @@
int ret;
mutex_lock(&ftrace_lock);
- ret = __unregister_ftrace_function(ops);
- if (!ret)
- ftrace_shutdown(ops, 0);
+ ret = ftrace_shutdown(ops, 0);
mutex_unlock(&ftrace_lock);
return ret;
@@ -4666,6 +4799,7 @@
trace_func_graph_ret_t ftrace_graph_return =
(trace_func_graph_ret_t)ftrace_stub;
trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -4800,6 +4934,37 @@
return NOTIFY_DONE;
}
+/* Just a place holder for function graph */
+static struct ftrace_ops fgraph_ops __read_mostly = {
+ .func = ftrace_stub,
+ .flags = FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
+ FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+ if (!ftrace_ops_test(&global_ops, trace->func, NULL))
+ return 0;
+ return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+ if (ftrace_ops_list == &ftrace_list_end ||
+ (ftrace_ops_list == &global_ops &&
+ global_ops.next == &ftrace_list_end))
+ ftrace_graph_entry = __ftrace_graph_entry;
+ else
+ ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
int register_ftrace_graph(trace_func_graph_ret_t retfunc,
trace_func_graph_ent_t entryfunc)
{
@@ -4824,9 +4989,18 @@
}
ftrace_graph_return = retfunc;
- ftrace_graph_entry = entryfunc;
- ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+ /*
+ * Update the indirect function to the entryfunc, and the
+ * function that gets called to the entry_test first. Then
+ * call the update fgraph entry function to determine if
+ * the entryfunc should be called directly or not.
+ */
+ __ftrace_graph_entry = entryfunc;
+ ftrace_graph_entry = ftrace_graph_entry_test;
+ update_function_graph_func();
+
+ ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
out:
mutex_unlock(&ftrace_lock);
@@ -4843,7 +5017,8 @@
ftrace_graph_active--;
ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
ftrace_graph_entry = ftrace_graph_entry_stub;
- ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+ __ftrace_graph_entry = ftrace_graph_entry_stub;
+ ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index e444ff8..ab21b8c 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -543,7 +543,7 @@
* as data is added to any of the @buffer's cpu buffers. Otherwise
* it will wait for data to be added to a specific cpu buffer.
*/
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
{
struct ring_buffer_per_cpu *cpu_buffer;
DEFINE_WAIT(wait);
@@ -557,6 +557,8 @@
if (cpu == RING_BUFFER_ALL_CPUS)
work = &buffer->irq_work;
else {
+ if (!cpumask_test_cpu(cpu, buffer->cpumask))
+ return -ENODEV;
cpu_buffer = buffer->buffers[cpu];
work = &cpu_buffer->irq_work;
}
@@ -591,6 +593,7 @@
schedule();
finish_wait(&work->waiters, &wait);
+ return 0;
}
/**
@@ -613,10 +616,6 @@
struct ring_buffer_per_cpu *cpu_buffer;
struct rb_irq_work *work;
- if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
- (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
- return POLLIN | POLLRDNORM;
-
if (cpu == RING_BUFFER_ALL_CPUS)
work = &buffer->irq_work;
else {
@@ -627,8 +626,22 @@
work = &cpu_buffer->irq_work;
}
- work->waiters_pending = true;
poll_wait(filp, &work->waiters, poll_table);
+ work->waiters_pending = true;
+ /*
+ * There's a tight race between setting the waiters_pending and
+ * checking if the ring buffer is empty. Once the waiters_pending bit
+ * is set, the next event will wake the task up, but we can get stuck
+ * if there's only a single event in.
+ *
+ * FIXME: Ideally, we need a memory barrier on the writer side as well,
+ * but adding a memory barrier to all events will cause too much of a
+ * performance hit in the fast path. We only need a memory barrier when
+ * the buffer goes from empty to having content. But as this race is
+ * extremely small, and it's not a problem if another event comes in, we
+ * will fix it later.
+ */
+ smp_mb();
if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
(cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
@@ -1981,7 +1994,7 @@
/**
* rb_update_event - update event type and data
- * @event: the even to update
+ * @event: the event to update
* @type: the type of event
* @length: the size of the event field in the ring buffer
*
@@ -2396,6 +2409,13 @@
write &= RB_WRITE_MASK;
tail = write - length;
+ /*
+ * If this is the first commit on the page, then it has the same
+ * timestamp as the page itself.
+ */
+ if (!tail)
+ delta = 0;
+
/* See if we shot pass the end of this buffer page */
if (unlikely(write > BUF_PAGE_SIZE))
return rb_move_tail(cpu_buffer, length, tail,
@@ -2630,7 +2650,7 @@
static __always_inline int trace_recursive_lock(void)
{
- unsigned int val = this_cpu_read(current_context);
+ unsigned int val = __this_cpu_read(current_context);
int bit;
if (in_interrupt()) {
@@ -2647,18 +2667,17 @@
return 1;
val |= (1 << bit);
- this_cpu_write(current_context, val);
+ __this_cpu_write(current_context, val);
return 0;
}
static __always_inline void trace_recursive_unlock(void)
{
- unsigned int val = this_cpu_read(current_context);
+ unsigned int val = __this_cpu_read(current_context);
- val--;
- val &= this_cpu_read(current_context);
- this_cpu_write(current_context, val);
+ val &= val & (val - 1);
+ __this_cpu_write(current_context, val);
}
#else
@@ -3347,21 +3366,16 @@
struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
/* Iterator usage is expected to have record disabled */
- if (list_empty(&cpu_buffer->reader_page->list)) {
- iter->head_page = rb_set_head_page(cpu_buffer);
- if (unlikely(!iter->head_page))
- return;
- iter->head = iter->head_page->read;
- } else {
- iter->head_page = cpu_buffer->reader_page;
- iter->head = cpu_buffer->reader_page->read;
- }
+ iter->head_page = cpu_buffer->reader_page;
+ iter->head = cpu_buffer->reader_page->read;
+
+ iter->cache_reader_page = iter->head_page;
+ iter->cache_read = cpu_buffer->read;
+
if (iter->head)
iter->read_stamp = cpu_buffer->read_stamp;
else
iter->read_stamp = iter->head_page->page->time_stamp;
- iter->cache_reader_page = cpu_buffer->reader_page;
- iter->cache_read = cpu_buffer->read;
}
/**
@@ -3754,12 +3768,14 @@
return NULL;
/*
- * We repeat when a time extend is encountered.
- * Since the time extend is always attached to a data event,
- * we should never loop more than once.
- * (We never hit the following condition more than twice).
+ * We repeat when a time extend is encountered or we hit
+ * the end of the page. Since the time extend is always attached
+ * to a data event, we should never loop more than three times.
+ * Once for going to next page, once on time extend, and
+ * finally once to get the event.
+ * (We never hit the following condition more than thrice).
*/
- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
+ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
return NULL;
if (rb_per_cpu_empty(cpu_buffer))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e71a8be..640e4c4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -193,6 +193,37 @@
LIST_HEAD(ftrace_trace_arrays);
+int trace_array_get(struct trace_array *this_tr)
+{
+ struct trace_array *tr;
+ int ret = -ENODEV;
+
+ mutex_lock(&trace_types_lock);
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (tr == this_tr) {
+ tr->ref++;
+ ret = 0;
+ break;
+ }
+ }
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
+}
+
+static void __trace_array_put(struct trace_array *this_tr)
+{
+ WARN_ON(!this_tr->ref);
+ this_tr->ref--;
+}
+
+void trace_array_put(struct trace_array *this_tr)
+{
+ mutex_lock(&trace_types_lock);
+ __trace_array_put(this_tr);
+ mutex_unlock(&trace_types_lock);
+}
+
int filter_current_check_discard(struct ring_buffer *buffer,
struct ftrace_event_call *call, void *rec,
struct ring_buffer_event *event)
@@ -201,23 +232,43 @@
}
EXPORT_SYMBOL_GPL(filter_current_check_discard);
-cycle_t ftrace_now(int cpu)
+cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
{
u64 ts;
/* Early boot up does not have a buffer yet */
- if (!global_trace.trace_buffer.buffer)
+ if (!buf->buffer)
return trace_clock_local();
- ts = ring_buffer_time_stamp(global_trace.trace_buffer.buffer, cpu);
- ring_buffer_normalize_time_stamp(global_trace.trace_buffer.buffer, cpu, &ts);
+ ts = ring_buffer_time_stamp(buf->buffer, cpu);
+ ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts);
return ts;
}
+cycle_t ftrace_now(int cpu)
+{
+ return buffer_ftrace_now(&global_trace.trace_buffer, cpu);
+}
+
+/**
+ * tracing_is_enabled - Show if global_trace has been disabled
+ *
+ * Shows if the global trace has been enabled or not. It uses the
+ * mirror flag "buffer_disabled" to be used in fast paths such as for
+ * the irqsoff tracer. But it may be inaccurate due to races. If you
+ * need to know the accurate state, use tracing_is_on() which is a little
+ * slower, but accurate.
+ */
int tracing_is_enabled(void)
{
- return tracing_is_on();
+ /*
+ * For quick access (irqsoff uses this in fast path), just
+ * return the mirror variable of the state of the ring buffer.
+ * It's a little racy, but we don't really care.
+ */
+ smp_rmb();
+ return !global_trace.buffer_disabled;
}
/*
@@ -240,7 +291,7 @@
/*
* trace_types_lock is used to protect the trace_types list.
*/
-static DEFINE_MUTEX(trace_types_lock);
+DEFINE_MUTEX(trace_types_lock);
/*
* serialize the access of the ring buffer
@@ -330,6 +381,23 @@
TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | TRACE_ITER_FUNCTION;
+void tracer_tracing_on(struct trace_array *tr)
+{
+ if (tr->trace_buffer.buffer)
+ ring_buffer_record_on(tr->trace_buffer.buffer);
+ /*
+ * This flag is looked at when buffers haven't been allocated
+ * yet, or by some tracers (like irqsoff), that just want to
+ * know if the ring buffer has been disabled, but it can handle
+ * races of where it gets disabled but we still do a record.
+ * As the check is in the fast path of the tracers, it is more
+ * important to be fast than accurate.
+ */
+ tr->buffer_disabled = 0;
+ /* Make the flag seen by readers */
+ smp_wmb();
+}
+
/**
* tracing_on - enable tracing buffers
*
@@ -338,15 +406,7 @@
*/
void tracing_on(void)
{
- if (global_trace.trace_buffer.buffer)
- ring_buffer_record_on(global_trace.trace_buffer.buffer);
- /*
- * This flag is only looked at when buffers haven't been
- * allocated yet. We don't really care about the race
- * between setting this flag and actually turning
- * on the buffer.
- */
- global_trace.buffer_disabled = 0;
+ tracer_tracing_on(&global_trace);
}
EXPORT_SYMBOL_GPL(tracing_on);
@@ -363,13 +423,19 @@
struct print_entry *entry;
unsigned long irq_flags;
int alloc;
+ int pc;
+
+ pc = preempt_count();
+
+ if (unlikely(tracing_selftest_running || tracing_disabled))
+ return 0;
alloc = sizeof(*entry) + size + 2; /* possible \n added */
local_save_flags(irq_flags);
buffer = global_trace.trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
- irq_flags, preempt_count());
+ irq_flags, pc);
if (!event)
return 0;
@@ -386,6 +452,7 @@
entry->buf[size] = '\0';
__buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, irq_flags, 4, pc);
return size;
}
@@ -403,11 +470,17 @@
struct bputs_entry *entry;
unsigned long irq_flags;
int size = sizeof(struct bputs_entry);
+ int pc;
+
+ pc = preempt_count();
+
+ if (unlikely(tracing_selftest_running || tracing_disabled))
+ return 0;
local_save_flags(irq_flags);
buffer = global_trace.trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
- irq_flags, preempt_count());
+ irq_flags, pc);
if (!event)
return 0;
@@ -416,6 +489,7 @@
entry->str = str;
__buffer_unlock_commit(buffer, event);
+ ftrace_trace_stack(buffer, irq_flags, 4, pc);
return 1;
}
@@ -540,6 +614,23 @@
EXPORT_SYMBOL_GPL(tracing_snapshot_alloc);
#endif /* CONFIG_TRACER_SNAPSHOT */
+void tracer_tracing_off(struct trace_array *tr)
+{
+ if (tr->trace_buffer.buffer)
+ ring_buffer_record_off(tr->trace_buffer.buffer);
+ /*
+ * This flag is looked at when buffers haven't been allocated
+ * yet, or by some tracers (like irqsoff), that just want to
+ * know if the ring buffer has been disabled, but it can handle
+ * races of where it gets disabled but we still do a record.
+ * As the check is in the fast path of the tracers, it is more
+ * important to be fast than accurate.
+ */
+ tr->buffer_disabled = 1;
+ /* Make the flag seen by readers */
+ smp_wmb();
+}
+
/**
* tracing_off - turn off tracing buffers
*
@@ -550,26 +641,29 @@
*/
void tracing_off(void)
{
- if (global_trace.trace_buffer.buffer)
- ring_buffer_record_off(global_trace.trace_buffer.buffer);
- /*
- * This flag is only looked at when buffers haven't been
- * allocated yet. We don't really care about the race
- * between setting this flag and actually turning
- * on the buffer.
- */
- global_trace.buffer_disabled = 1;
+ tracer_tracing_off(&global_trace);
}
EXPORT_SYMBOL_GPL(tracing_off);
/**
+ * tracer_tracing_is_on - show real state of ring buffer enabled
+ * @tr : the trace array to know if ring buffer is enabled
+ *
+ * Shows real state of the ring buffer if it is enabled or not.
+ */
+int tracer_tracing_is_on(struct trace_array *tr)
+{
+ if (tr->trace_buffer.buffer)
+ return ring_buffer_record_is_on(tr->trace_buffer.buffer);
+ return !tr->buffer_disabled;
+}
+
+/**
* tracing_is_on - show state of ring buffers enabled
*/
int tracing_is_on(void)
{
- if (global_trace.trace_buffer.buffer)
- return ring_buffer_record_is_on(global_trace.trace_buffer.buffer);
- return !global_trace.buffer_disabled;
+ return tracer_tracing_is_on(&global_trace);
}
EXPORT_SYMBOL_GPL(tracing_is_on);
@@ -647,7 +741,7 @@
{ trace_clock_local, "local", 1 },
{ trace_clock_global, "global", 1 },
{ trace_clock_counter, "counter", 0 },
- { trace_clock_jiffies, "uptime", 1 },
+ { trace_clock_jiffies, "uptime", 0 },
{ trace_clock, "perf", 1 },
ARCH_TRACE_CLOCKS
};
@@ -746,9 +840,12 @@
if (isspace(ch)) {
parser->buffer[parser->idx] = 0;
parser->cont = false;
- } else {
+ } else if (parser->idx < parser->size - 1) {
parser->cont = true;
parser->buffer[parser->idx++] = ch;
+ } else {
+ ret = -EINVAL;
+ goto out;
}
*ppos += read;
@@ -938,13 +1035,13 @@
}
#endif /* CONFIG_TRACER_MAX_TRACE */
-static void default_wait_pipe(struct trace_iterator *iter)
+static int default_wait_pipe(struct trace_iterator *iter)
{
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
- return;
+ return 0;
- ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+ return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1119,7 +1216,7 @@
/* Make sure all commits have finished */
synchronize_sched();
- buf->time_start = ftrace_now(buf->cpu);
+ buf->time_start = buffer_ftrace_now(buf, buf->cpu);
for_each_online_cpu(cpu)
ring_buffer_reset_cpu(buffer, cpu);
@@ -1127,23 +1224,17 @@
ring_buffer_record_enable(buffer);
}
-void tracing_reset_current(int cpu)
-{
- tracing_reset(&global_trace.trace_buffer, cpu);
-}
-
+/* Must have trace_types_lock held */
void tracing_reset_all_online_cpus(void)
{
struct trace_array *tr;
- mutex_lock(&trace_types_lock);
list_for_each_entry(tr, &ftrace_trace_arrays, list) {
tracing_reset_online_cpus(&tr->trace_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
tracing_reset_online_cpus(&tr->max_buffer);
#endif
}
- mutex_unlock(&trace_types_lock);
}
#define SAVED_CMDLINES 128
@@ -1223,7 +1314,6 @@
arch_spin_unlock(&ftrace_max_lock);
- ftrace_start();
out:
raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
}
@@ -1270,7 +1360,6 @@
struct ring_buffer *buffer;
unsigned long flags;
- ftrace_stop();
raw_spin_lock_irqsave(&global_trace.start_lock, flags);
if (global_trace.stop_count++)
goto out;
@@ -1317,12 +1406,12 @@
void trace_stop_cmdline_recording(void);
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
{
unsigned pid, idx;
if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
- return;
+ return 0;
/*
* It's not the end of the world if we don't get
@@ -1331,7 +1420,7 @@
* so if we miss here, then better luck next time.
*/
if (!arch_spin_trylock(&trace_cmdline_lock))
- return;
+ return 0;
idx = map_pid_to_cmdline[tsk->pid];
if (idx == NO_CMDLINE_MAP) {
@@ -1356,6 +1445,8 @@
memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
arch_spin_unlock(&trace_cmdline_lock);
+
+ return 1;
}
void trace_find_cmdline(int pid, char comm[])
@@ -1397,9 +1488,8 @@
if (!__this_cpu_read(trace_cmdline_save))
return;
- __this_cpu_write(trace_cmdline_save, false);
-
- trace_save_cmdline(tsk);
+ if (trace_save_cmdline(tsk))
+ __this_cpu_write(trace_cmdline_save, false);
}
void
@@ -2760,6 +2850,17 @@
return 0;
}
+/*
+ * Should be used after trace_array_get(), trace_types_lock
+ * ensures that i_cdev was already initialized.
+ */
+static inline int tracing_get_cpu(struct inode *inode)
+{
+ if (inode->i_cdev) /* See trace_create_cpu_file() */
+ return (long)inode->i_cdev - 1;
+ return RING_BUFFER_ALL_CPUS;
+}
+
static const struct seq_operations tracer_seq_ops = {
.start = s_start,
.next = s_next,
@@ -2770,8 +2871,7 @@
static struct trace_iterator *
__tracing_open(struct inode *inode, struct file *file, bool snapshot)
{
- struct trace_cpu *tc = inode->i_private;
- struct trace_array *tr = tc->tr;
+ struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
int cpu;
@@ -2812,8 +2912,8 @@
iter->trace_buffer = &tr->trace_buffer;
iter->snapshot = snapshot;
iter->pos = -1;
+ iter->cpu_file = tracing_get_cpu(inode);
mutex_init(&iter->mutex);
- iter->cpu_file = tc->cpu;
/* Notify the tracer early; before we stop tracing. */
if (iter->trace && iter->trace->open)
@@ -2850,8 +2950,6 @@
tracing_iter_reset(iter, cpu);
}
- tr->ref++;
-
mutex_unlock(&trace_types_lock);
return iter;
@@ -2874,24 +2972,41 @@
return 0;
}
+/*
+ * Open and update trace_array ref count.
+ * Must have the current trace_array passed to it.
+ */
+int tracing_open_generic_tr(struct inode *inode, struct file *filp)
+{
+ struct trace_array *tr = inode->i_private;
+
+ if (tracing_disabled)
+ return -ENODEV;
+
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
+ filp->private_data = inode->i_private;
+
+ return 0;
+}
+
static int tracing_release(struct inode *inode, struct file *file)
{
+ struct trace_array *tr = inode->i_private;
struct seq_file *m = file->private_data;
struct trace_iterator *iter;
- struct trace_array *tr;
int cpu;
- if (!(file->f_mode & FMODE_READ))
+ if (!(file->f_mode & FMODE_READ)) {
+ trace_array_put(tr);
return 0;
+ }
+ /* Writes do not use seq_file */
iter = m->private;
- tr = iter->tr;
-
mutex_lock(&trace_types_lock);
- WARN_ON(!tr->ref);
- tr->ref--;
-
for_each_tracing_cpu(cpu) {
if (iter->buffer_iter[cpu])
ring_buffer_read_finish(iter->buffer_iter[cpu]);
@@ -2903,6 +3018,9 @@
if (!iter->snapshot)
/* reenable tracing if it was previously enabled */
tracing_start_tr(tr);
+
+ __trace_array_put(tr);
+
mutex_unlock(&trace_types_lock);
mutex_destroy(&iter->mutex);
@@ -2910,24 +3028,44 @@
kfree(iter->trace);
kfree(iter->buffer_iter);
seq_release_private(inode, file);
+
return 0;
}
+static int tracing_release_generic_tr(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+
+ trace_array_put(tr);
+ return 0;
+}
+
+static int tracing_single_release_tr(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+
+ trace_array_put(tr);
+
+ return single_release(inode, file);
+}
+
static int tracing_open(struct inode *inode, struct file *file)
{
+ struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
int ret = 0;
- /* If this file was open for write, then erase contents */
- if ((file->f_mode & FMODE_WRITE) &&
- (file->f_flags & O_TRUNC)) {
- struct trace_cpu *tc = inode->i_private;
- struct trace_array *tr = tc->tr;
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
- if (tc->cpu == RING_BUFFER_ALL_CPUS)
+ /* If this file was open for write, then erase contents */
+ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+ int cpu = tracing_get_cpu(inode);
+
+ if (cpu == RING_BUFFER_ALL_CPUS)
tracing_reset_online_cpus(&tr->trace_buffer);
else
- tracing_reset(&tr->trace_buffer, tc->cpu);
+ tracing_reset(&tr->trace_buffer, cpu);
}
if (file->f_mode & FMODE_READ) {
@@ -2937,6 +3075,10 @@
else if (trace_flags & TRACE_ITER_LATENCY_FMT)
iter->iter_flags |= TRACE_FILE_LAT_FMT;
}
+
+ if (ret < 0)
+ trace_array_put(tr);
+
return ret;
}
@@ -3293,17 +3435,27 @@
static int tracing_trace_options_open(struct inode *inode, struct file *file)
{
+ struct trace_array *tr = inode->i_private;
+ int ret;
+
if (tracing_disabled)
return -ENODEV;
- return single_open(file, tracing_trace_options_show, inode->i_private);
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
+ ret = single_open(file, tracing_trace_options_show, inode->i_private);
+ if (ret < 0)
+ trace_array_put(tr);
+
+ return ret;
}
static const struct file_operations tracing_iter_fops = {
.open = tracing_trace_options_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_tr,
.write = tracing_trace_options_write,
};
@@ -3783,20 +3935,23 @@
static int tracing_open_pipe(struct inode *inode, struct file *filp)
{
- struct trace_cpu *tc = inode->i_private;
- struct trace_array *tr = tc->tr;
+ struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
int ret = 0;
if (tracing_disabled)
return -ENODEV;
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
mutex_lock(&trace_types_lock);
/* create a buffer to store the information to pass to userspace */
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
ret = -ENOMEM;
+ __trace_array_put(tr);
goto out;
}
@@ -3826,9 +3981,9 @@
if (trace_clocks[tr->clock_id].in_ns)
iter->iter_flags |= TRACE_FILE_TIME_IN_NS;
- iter->cpu_file = tc->cpu;
- iter->tr = tc->tr;
- iter->trace_buffer = &tc->tr->trace_buffer;
+ iter->tr = tr;
+ iter->trace_buffer = &tr->trace_buffer;
+ iter->cpu_file = tracing_get_cpu(inode);
mutex_init(&iter->mutex);
filp->private_data = iter;
@@ -3843,6 +3998,7 @@
fail:
kfree(iter->trace);
kfree(iter);
+ __trace_array_put(tr);
mutex_unlock(&trace_types_lock);
return ret;
}
@@ -3850,6 +4006,7 @@
static int tracing_release_pipe(struct inode *inode, struct file *file)
{
struct trace_iterator *iter = file->private_data;
+ struct trace_array *tr = inode->i_private;
mutex_lock(&trace_types_lock);
@@ -3863,6 +4020,8 @@
kfree(iter->trace);
kfree(iter);
+ trace_array_put(tr);
+
return 0;
}
@@ -3903,17 +4062,19 @@
*
* Anyway, this is really very primitive wakeup.
*/
-void poll_wait_pipe(struct trace_iterator *iter)
+int poll_wait_pipe(struct trace_iterator *iter)
{
set_current_state(TASK_INTERRUPTIBLE);
/* sleep for 100 msecs, and try again. */
schedule_timeout(HZ / 10);
+ return 0;
}
/* Must be called with trace_types_lock mutex held. */
static int tracing_wait_pipe(struct file *filp)
{
struct trace_iterator *iter = filp->private_data;
+ int ret;
while (trace_empty(iter)) {
@@ -3923,10 +4084,13 @@
mutex_unlock(&iter->mutex);
- iter->trace->wait_pipe(iter);
+ ret = iter->trace->wait_pipe(iter);
mutex_lock(&iter->mutex);
+ if (ret)
+ return ret;
+
if (signal_pending(current))
return -EINTR;
@@ -3939,7 +4103,7 @@
*
* iter->pos will be 0 if we haven't read anything.
*/
- if (!tracing_is_enabled() && iter->pos)
+ if (!tracing_is_on() && iter->pos)
break;
}
@@ -4000,6 +4164,7 @@
memset(&iter->seq, 0,
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
+ cpumask_clear(iter->started);
iter->pos = -1;
trace_event_read_lock();
@@ -4200,15 +4365,16 @@
tracing_entries_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct trace_cpu *tc = filp->private_data;
- struct trace_array *tr = tc->tr;
+ struct inode *inode = file_inode(filp);
+ struct trace_array *tr = inode->i_private;
+ int cpu = tracing_get_cpu(inode);
char buf[64];
int r = 0;
ssize_t ret;
mutex_lock(&trace_types_lock);
- if (tc->cpu == RING_BUFFER_ALL_CPUS) {
+ if (cpu == RING_BUFFER_ALL_CPUS) {
int cpu, buf_size_same;
unsigned long size;
@@ -4235,7 +4401,7 @@
} else
r = sprintf(buf, "X\n");
} else
- r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, tc->cpu)->entries >> 10);
+ r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10);
mutex_unlock(&trace_types_lock);
@@ -4247,7 +4413,8 @@
tracing_entries_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- struct trace_cpu *tc = filp->private_data;
+ struct inode *inode = file_inode(filp);
+ struct trace_array *tr = inode->i_private;
unsigned long val;
int ret;
@@ -4261,8 +4428,7 @@
/* value is in KB */
val <<= 10;
-
- ret = tracing_resize_ring_buffer(tc->tr, val, tc->cpu);
+ ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode));
if (ret < 0)
return ret;
@@ -4316,10 +4482,12 @@
/* disable tracing ? */
if (trace_flags & TRACE_ITER_STOP_ON_FREE)
- tracing_off();
+ tracer_tracing_off(tr);
/* resize the ring buffer to 0 */
tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS);
+ trace_array_put(tr);
+
return 0;
}
@@ -4328,6 +4496,7 @@
size_t cnt, loff_t *fpos)
{
unsigned long addr = (unsigned long)ubuf;
+ struct trace_array *tr = filp->private_data;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
struct print_entry *entry;
@@ -4387,7 +4556,7 @@
local_save_flags(irq_flags);
size = sizeof(*entry) + cnt + 2; /* possible \n added */
- buffer = global_trace.trace_buffer.buffer;
+ buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
irq_flags, preempt_count());
if (!event) {
@@ -4419,7 +4588,7 @@
*fpos += written;
out_unlock:
- for (i = 0; i < nr_pages; i++){
+ for (i = nr_pages - 1; i >= 0; i--) {
kunmap_atomic(map_page[i]);
put_page(pages[i]);
}
@@ -4478,12 +4647,12 @@
* New clock may not be consistent with the previous clock.
* Reset the buffer so that it doesn't have incomparable timestamps.
*/
- tracing_reset_online_cpus(&global_trace.trace_buffer);
+ tracing_reset_online_cpus(&tr->trace_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
- tracing_reset_online_cpus(&global_trace.max_buffer);
+ tracing_reset_online_cpus(&tr->max_buffer);
#endif
mutex_unlock(&trace_types_lock);
@@ -4495,10 +4664,20 @@
static int tracing_clock_open(struct inode *inode, struct file *file)
{
+ struct trace_array *tr = inode->i_private;
+ int ret;
+
if (tracing_disabled)
return -ENODEV;
- return single_open(file, tracing_clock_show, inode->i_private);
+ if (trace_array_get(tr))
+ return -ENODEV;
+
+ ret = single_open(file, tracing_clock_show, inode->i_private);
+ if (ret < 0)
+ trace_array_put(tr);
+
+ return ret;
}
struct ftrace_buffer_info {
@@ -4510,31 +4689,40 @@
#ifdef CONFIG_TRACER_SNAPSHOT
static int tracing_snapshot_open(struct inode *inode, struct file *file)
{
- struct trace_cpu *tc = inode->i_private;
+ struct trace_array *tr = inode->i_private;
struct trace_iterator *iter;
struct seq_file *m;
int ret = 0;
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
if (file->f_mode & FMODE_READ) {
iter = __tracing_open(inode, file, true);
if (IS_ERR(iter))
ret = PTR_ERR(iter);
} else {
/* Writes still need the seq_file to hold the private data */
+ ret = -ENOMEM;
m = kzalloc(sizeof(*m), GFP_KERNEL);
if (!m)
- return -ENOMEM;
+ goto out;
iter = kzalloc(sizeof(*iter), GFP_KERNEL);
if (!iter) {
kfree(m);
- return -ENOMEM;
+ goto out;
}
- iter->tr = tc->tr;
- iter->trace_buffer = &tc->tr->max_buffer;
- iter->cpu_file = tc->cpu;
+ ret = 0;
+
+ iter->tr = tr;
+ iter->trace_buffer = &tr->max_buffer;
+ iter->cpu_file = tracing_get_cpu(inode);
m->private = iter;
file->private_data = m;
}
+out:
+ if (ret < 0)
+ trace_array_put(tr);
return ret;
}
@@ -4616,9 +4804,12 @@
static int tracing_snapshot_release(struct inode *inode, struct file *file)
{
struct seq_file *m = file->private_data;
+ int ret;
+
+ ret = tracing_release(inode, file);
if (file->f_mode & FMODE_READ)
- return tracing_release(inode, file);
+ return ret;
/* If write only, the seq_file is just a stub */
if (m)
@@ -4684,34 +4875,38 @@
};
static const struct file_operations tracing_entries_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = tracing_entries_read,
.write = tracing_entries_write,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
static const struct file_operations tracing_total_entries_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = tracing_total_entries_read,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
static const struct file_operations tracing_free_buffer_fops = {
+ .open = tracing_open_generic_tr,
.write = tracing_free_buffer_write,
.release = tracing_free_buffer_release,
};
static const struct file_operations tracing_mark_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.write = tracing_mark_write,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
static const struct file_operations trace_clock_fops = {
.open = tracing_clock_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = tracing_single_release_tr,
.write = tracing_clock_write,
};
@@ -4736,23 +4931,26 @@
static int tracing_buffers_open(struct inode *inode, struct file *filp)
{
- struct trace_cpu *tc = inode->i_private;
- struct trace_array *tr = tc->tr;
+ struct trace_array *tr = inode->i_private;
struct ftrace_buffer_info *info;
+ int ret;
if (tracing_disabled)
return -ENODEV;
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
info = kzalloc(sizeof(*info), GFP_KERNEL);
- if (!info)
+ if (!info) {
+ trace_array_put(tr);
return -ENOMEM;
+ }
mutex_lock(&trace_types_lock);
- tr->ref++;
-
info->iter.tr = tr;
- info->iter.cpu_file = tc->cpu;
+ info->iter.cpu_file = tracing_get_cpu(inode);
info->iter.trace = tr->current_trace;
info->iter.trace_buffer = &tr->trace_buffer;
info->spare = NULL;
@@ -4763,7 +4961,11 @@
mutex_unlock(&trace_types_lock);
- return nonseekable_open(inode, filp);
+ ret = nonseekable_open(inode, filp);
+ if (ret < 0)
+ trace_array_put(tr);
+
+ return ret;
}
static unsigned int
@@ -4822,8 +5024,12 @@
goto out_unlock;
}
mutex_unlock(&trace_types_lock);
- iter->trace->wait_pipe(iter);
+ ret = iter->trace->wait_pipe(iter);
mutex_lock(&trace_types_lock);
+ if (ret) {
+ size = ret;
+ goto out_unlock;
+ }
if (signal_pending(current)) {
size = -EINTR;
goto out_unlock;
@@ -4863,8 +5069,7 @@
mutex_lock(&trace_types_lock);
- WARN_ON(!iter->tr->ref);
- iter->tr->ref--;
+ __trace_array_put(iter->tr);
if (info->spare)
ring_buffer_free_read_page(iter->trace_buffer->buffer, info->spare);
@@ -5036,8 +5241,10 @@
goto out;
}
mutex_unlock(&trace_types_lock);
- iter->trace->wait_pipe(iter);
+ ret = iter->trace->wait_pipe(iter);
mutex_lock(&trace_types_lock);
+ if (ret)
+ goto out;
if (signal_pending(current)) {
ret = -EINTR;
goto out;
@@ -5066,14 +5273,14 @@
tracing_stats_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
- struct trace_cpu *tc = filp->private_data;
- struct trace_array *tr = tc->tr;
+ struct inode *inode = file_inode(filp);
+ struct trace_array *tr = inode->i_private;
struct trace_buffer *trace_buf = &tr->trace_buffer;
+ int cpu = tracing_get_cpu(inode);
struct trace_seq *s;
unsigned long cnt;
unsigned long long t;
unsigned long usec_rem;
- int cpu = tc->cpu;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
@@ -5126,9 +5333,10 @@
}
static const struct file_operations tracing_stats_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = tracing_stats_read,
.llseek = generic_file_llseek,
+ .release = tracing_release_generic_tr,
};
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -5317,10 +5525,20 @@
return tr->percpu_dir;
}
+static struct dentry *
+trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
+ void *data, long cpu, const struct file_operations *fops)
+{
+ struct dentry *ret = trace_create_file(name, mode, parent, data, fops);
+
+ if (ret) /* See tracing_get_cpu() */
+ ret->d_inode->i_cdev = (void *)(cpu + 1);
+ return ret;
+}
+
static void
tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
{
- struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, cpu);
struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
struct dentry *d_cpu;
char cpu_dir[30]; /* 30 characters should be more than enough */
@@ -5336,28 +5554,28 @@
}
/* per cpu trace_pipe */
- trace_create_file("trace_pipe", 0444, d_cpu,
- (void *)&data->trace_cpu, &tracing_pipe_fops);
+ trace_create_cpu_file("trace_pipe", 0444, d_cpu,
+ tr, cpu, &tracing_pipe_fops);
/* per cpu trace */
- trace_create_file("trace", 0644, d_cpu,
- (void *)&data->trace_cpu, &tracing_fops);
+ trace_create_cpu_file("trace", 0644, d_cpu,
+ tr, cpu, &tracing_fops);
- trace_create_file("trace_pipe_raw", 0444, d_cpu,
- (void *)&data->trace_cpu, &tracing_buffers_fops);
+ trace_create_cpu_file("trace_pipe_raw", 0444, d_cpu,
+ tr, cpu, &tracing_buffers_fops);
- trace_create_file("stats", 0444, d_cpu,
- (void *)&data->trace_cpu, &tracing_stats_fops);
+ trace_create_cpu_file("stats", 0444, d_cpu,
+ tr, cpu, &tracing_stats_fops);
- trace_create_file("buffer_size_kb", 0444, d_cpu,
- (void *)&data->trace_cpu, &tracing_entries_fops);
+ trace_create_cpu_file("buffer_size_kb", 0444, d_cpu,
+ tr, cpu, &tracing_entries_fops);
#ifdef CONFIG_TRACER_SNAPSHOT
- trace_create_file("snapshot", 0644, d_cpu,
- (void *)&data->trace_cpu, &snapshot_fops);
+ trace_create_cpu_file("snapshot", 0644, d_cpu,
+ tr, cpu, &snapshot_fops);
- trace_create_file("snapshot_raw", 0444, d_cpu,
- (void *)&data->trace_cpu, &snapshot_raw_fops);
+ trace_create_cpu_file("snapshot_raw", 0444, d_cpu,
+ tr, cpu, &snapshot_raw_fops);
#endif
}
@@ -5612,15 +5830,10 @@
size_t cnt, loff_t *ppos)
{
struct trace_array *tr = filp->private_data;
- struct ring_buffer *buffer = tr->trace_buffer.buffer;
char buf[64];
int r;
- if (buffer)
- r = ring_buffer_record_is_on(buffer);
- else
- r = 0;
-
+ r = tracer_tracing_is_on(tr);
r = sprintf(buf, "%d\n", r);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
@@ -5642,11 +5855,11 @@
if (buffer) {
mutex_lock(&trace_types_lock);
if (val) {
- ring_buffer_record_on(buffer);
+ tracer_tracing_on(tr);
if (tr->current_trace->start)
tr->current_trace->start(tr);
} else {
- ring_buffer_record_off(buffer);
+ tracer_tracing_off(tr);
if (tr->current_trace->stop)
tr->current_trace->stop(tr);
}
@@ -5659,9 +5872,10 @@
}
static const struct file_operations rb_simple_fops = {
- .open = tracing_open_generic,
+ .open = tracing_open_generic_tr,
.read = rb_simple_read,
.write = rb_simple_write,
+ .release = tracing_release_generic_tr,
.llseek = default_llseek,
};
@@ -5688,6 +5902,8 @@
rb_flags = trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0;
+ buf->tr = tr;
+
buf->buffer = ring_buffer_alloc(size, rb_flags);
if (!buf->buffer)
return -ENOMEM;
@@ -5775,8 +5991,10 @@
goto out_free_tr;
ret = event_trace_add_tracer(tr->dir, tr);
- if (ret)
+ if (ret) {
+ debugfs_remove_recursive(tr->dir);
goto out_free_tr;
+ }
init_tracer_debugfs(tr, tr->dir);
@@ -5845,7 +6063,7 @@
int ret;
/* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
if (WARN_ON_ONCE(parent != trace_instance_dir))
return -ENOENT;
@@ -5872,7 +6090,7 @@
int ret;
/* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
if (WARN_ON_ONCE(parent != trace_instance_dir))
return -ENOENT;
@@ -5922,13 +6140,13 @@
tr, &tracing_iter_fops);
trace_create_file("trace", 0644, d_tracer,
- (void *)&tr->trace_cpu, &tracing_fops);
+ tr, &tracing_fops);
trace_create_file("trace_pipe", 0444, d_tracer,
- (void *)&tr->trace_cpu, &tracing_pipe_fops);
+ tr, &tracing_pipe_fops);
trace_create_file("buffer_size_kb", 0644, d_tracer,
- (void *)&tr->trace_cpu, &tracing_entries_fops);
+ tr, &tracing_entries_fops);
trace_create_file("buffer_total_size_kb", 0444, d_tracer,
tr, &tracing_total_entries_fops);
@@ -5943,11 +6161,11 @@
&trace_clock_fops);
trace_create_file("tracing_on", 0644, d_tracer,
- tr, &rb_simple_fops);
+ tr, &rb_simple_fops);
#ifdef CONFIG_TRACER_SNAPSHOT
trace_create_file("snapshot", 0644, d_tracer,
- (void *)&tr->trace_cpu, &snapshot_fops);
+ tr, &snapshot_fops);
#endif
for_each_tracing_cpu(cpu)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 20572ed..aa0e736 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -224,6 +224,11 @@
extern struct list_head ftrace_trace_arrays;
+extern struct mutex trace_types_lock;
+
+extern int trace_array_get(struct trace_array *tr);
+extern void trace_array_put(struct trace_array *tr);
+
/*
* The global tracer (top) should be the first trace array added,
* but we check the flag anyway.
@@ -337,7 +342,7 @@
void (*stop)(struct trace_array *tr);
void (*open)(struct trace_iterator *iter);
void (*pipe_open)(struct trace_iterator *iter);
- void (*wait_pipe)(struct trace_iterator *iter);
+ int (*wait_pipe)(struct trace_iterator *iter);
void (*close)(struct trace_iterator *iter);
void (*pipe_close)(struct trace_iterator *iter);
ssize_t (*read)(struct trace_iterator *iter,
@@ -552,7 +557,7 @@
void tracing_iter_reset(struct trace_iterator *iter, int cpu);
-void poll_wait_pipe(struct trace_iterator *iter);
+int poll_wait_pipe(struct trace_iterator *iter);
void ftrace(struct trace_array *tr,
struct trace_array_cpu *data,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 26dc348..57b67b1 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -59,13 +59,14 @@
/*
* trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
*/
u64 notrace trace_clock_jiffies(void)
{
- u64 jiffy = jiffies - INITIAL_JIFFIES;
-
- /* Return nsecs */
- return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+ return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
}
/*
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 84b1e04..8354dc8 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -26,7 +26,7 @@
{
/* The ftrace function trace is allowed only for root. */
if (ftrace_event_is_function(tp_event) &&
- perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+ perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
return -EPERM;
/* No tracing, just counting, so no obvious leak */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 27963e2..5a898f1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
DEFINE_MUTEX(event_mutex);
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_common_fields);
@@ -41,6 +35,23 @@
static struct kmem_cache *field_cachep;
static struct kmem_cache *file_cachep;
+#define SYSTEM_FL_FREE_NAME (1 << 31)
+
+static inline int system_refcount(struct event_subsystem *system)
+{
+ return system->ref_count & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_inc(struct event_subsystem *system)
+{
+ return (system->ref_count++) & ~SYSTEM_FL_FREE_NAME;
+}
+
+static int system_refcount_dec(struct event_subsystem *system)
+{
+ return (--system->ref_count) & ~SYSTEM_FL_FREE_NAME;
+}
+
/* Double loops, do not use break, only goto's work */
#define do_for_each_event_file(tr, file) \
list_for_each_entry(tr, &ftrace_trace_arrays, list) { \
@@ -97,7 +108,7 @@
field = kmem_cache_alloc(field_cachep, GFP_TRACE);
if (!field)
- goto err;
+ return -ENOMEM;
field->name = name;
field->type = type;
@@ -114,11 +125,6 @@
list_add(&field->link, head);
return 0;
-
-err:
- kmem_cache_free(field_cachep, field);
-
- return -ENOMEM;
}
int trace_define_field(struct ftrace_event_call *call, const char *type,
@@ -349,8 +355,8 @@
{
struct event_filter *filter = system->filter;
- WARN_ON_ONCE(system->ref_count == 0);
- if (--system->ref_count)
+ WARN_ON_ONCE(system_refcount(system) == 0);
+ if (system_refcount_dec(system))
return;
list_del(&system->list);
@@ -359,13 +365,15 @@
kfree(filter->filter_string);
kfree(filter);
}
+ if (system->ref_count & SYSTEM_FL_FREE_NAME)
+ kfree(system->name);
kfree(system);
}
static void __get_system(struct event_subsystem *system)
{
- WARN_ON_ONCE(system->ref_count == 0);
- system->ref_count++;
+ WARN_ON_ONCE(system_refcount(system) == 0);
+ system_refcount_inc(system);
}
static void __get_system_dir(struct ftrace_subsystem_dir *dir)
@@ -379,7 +387,7 @@
{
WARN_ON_ONCE(dir->ref_count == 0);
/* If the subsystem is about to be freed, the dir must be too */
- WARN_ON_ONCE(dir->subsystem->ref_count == 1 && dir->ref_count != 1);
+ WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1);
__put_system(dir->subsystem);
if (!--dir->ref_count)
@@ -393,17 +401,55 @@
mutex_unlock(&event_mutex);
}
+static void remove_subsystem(struct ftrace_subsystem_dir *dir)
+{
+ if (!dir)
+ return;
+
+ if (!--dir->nr_events) {
+ debugfs_remove_recursive(dir->entry);
+ list_del(&dir->list);
+ __put_system_dir(dir);
+ }
+}
+
+static void *event_file_data(struct file *filp)
+{
+ return ACCESS_ONCE(file_inode(filp)->i_private);
+}
+
+static void remove_event_file_dir(struct ftrace_event_file *file)
+{
+ struct dentry *dir = file->dir;
+ struct dentry *child;
+
+ if (dir) {
+ spin_lock(&dir->d_lock); /* probably unneeded */
+ list_for_each_entry(child, &dir->d_subdirs, d_child) {
+ if (child->d_inode) /* probably unneeded */
+ child->d_inode->i_private = NULL;
+ }
+ spin_unlock(&dir->d_lock);
+
+ debugfs_remove_recursive(dir);
+ }
+
+ list_del(&file->list);
+ remove_subsystem(file->system);
+ kmem_cache_free(file_cachep, file);
+}
+
/*
* __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
*/
-static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
- const char *sub, const char *event, int set)
+static int
+__ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match,
+ const char *sub, const char *event, int set)
{
struct ftrace_event_file *file;
struct ftrace_event_call *call;
int ret = -EINVAL;
- mutex_lock(&event_mutex);
list_for_each_entry(file, &tr->events, list) {
call = file->event_call;
@@ -429,6 +475,17 @@
ret = 0;
}
+
+ return ret;
+}
+
+static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
+ const char *sub, const char *event, int set)
+{
+ int ret;
+
+ mutex_lock(&event_mutex);
+ ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set);
mutex_unlock(&event_mutex);
return ret;
@@ -623,13 +680,23 @@
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_file *file = filp->private_data;
+ struct ftrace_event_file *file;
+ unsigned long flags;
char *buf;
- if (file->flags & FTRACE_EVENT_FL_ENABLED) {
- if (file->flags & FTRACE_EVENT_FL_SOFT_DISABLED)
+ mutex_lock(&event_mutex);
+ file = event_file_data(filp);
+ if (likely(file))
+ flags = file->flags;
+ mutex_unlock(&event_mutex);
+
+ if (!file)
+ return -ENODEV;
+
+ if (flags & FTRACE_EVENT_FL_ENABLED) {
+ if (flags & FTRACE_EVENT_FL_SOFT_DISABLED)
buf = "0*\n";
- else if (file->flags & FTRACE_EVENT_FL_SOFT_MODE)
+ else if (flags & FTRACE_EVENT_FL_SOFT_MODE)
buf = "1*\n";
else
buf = "1\n";
@@ -643,13 +710,10 @@
event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_file *file = filp->private_data;
+ struct ftrace_event_file *file;
unsigned long val;
int ret;
- if (!file)
- return -EINVAL;
-
ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
if (ret)
return ret;
@@ -661,8 +725,11 @@
switch (val) {
case 0:
case 1:
+ ret = -ENODEV;
mutex_lock(&event_mutex);
- ret = ftrace_event_enable_disable(file, val);
+ file = event_file_data(filp);
+ if (likely(file))
+ ret = ftrace_event_enable_disable(file, val);
mutex_unlock(&event_mutex);
break;
@@ -769,7 +836,7 @@
static void *f_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct ftrace_event_call *call = m->private;
+ struct ftrace_event_call *call = event_file_data(m->private);
struct ftrace_event_field *field;
struct list_head *common_head = &ftrace_common_fields;
struct list_head *head = trace_get_fields(call);
@@ -813,6 +880,11 @@
loff_t l = 0;
void *p;
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+ if (!event_file_data(m->private))
+ return ERR_PTR(-ENODEV);
+
/* Start by showing the header */
if (!*pos)
return (void *)FORMAT_HEADER;
@@ -827,7 +899,7 @@
static int f_show(struct seq_file *m, void *v)
{
- struct ftrace_event_call *call = m->private;
+ struct ftrace_event_call *call = event_file_data(m->private);
struct ftrace_event_field *field;
const char *array_descriptor;
@@ -878,6 +950,7 @@
static void f_stop(struct seq_file *m, void *p)
{
+ mutex_unlock(&event_mutex);
}
static const struct seq_operations trace_format_seq_ops = {
@@ -889,7 +962,6 @@
static int trace_format_open(struct inode *inode, struct file *file)
{
- struct ftrace_event_call *call = inode->i_private;
struct seq_file *m;
int ret;
@@ -898,7 +970,7 @@
return ret;
m = file->private_data;
- m->private = call;
+ m->private = file;
return 0;
}
@@ -906,19 +978,22 @@
static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ int id = (long)event_file_data(filp);
struct trace_seq *s;
int r;
if (*ppos)
return 0;
+ if (unlikely(!id))
+ return -ENODEV;
+
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
trace_seq_init(s);
- trace_seq_printf(s, "%d\n", call->event.type);
+ trace_seq_printf(s, "%d\n", id);
r = simple_read_from_buffer(ubuf, cnt, ppos,
s->buffer, s->len);
@@ -930,21 +1005,28 @@
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_call *call;
struct trace_seq *s;
- int r;
+ int r = -ENODEV;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
+
if (!s)
return -ENOMEM;
trace_seq_init(s);
- print_event_filter(call, s);
- r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+ mutex_lock(&event_mutex);
+ call = event_file_data(filp);
+ if (call)
+ print_event_filter(call, s);
+ mutex_unlock(&event_mutex);
+
+ if (call)
+ r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
@@ -955,9 +1037,9 @@
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
- struct ftrace_event_call *call = filp->private_data;
+ struct ftrace_event_call *call;
char *buf;
- int err;
+ int err = -ENODEV;
if (cnt >= PAGE_SIZE)
return -EINVAL;
@@ -972,7 +1054,12 @@
}
buf[cnt] = '\0';
- err = apply_event_filter(call, buf);
+ mutex_lock(&event_mutex);
+ call = event_file_data(filp);
+ if (call)
+ err = apply_event_filter(call, buf);
+ mutex_unlock(&event_mutex);
+
free_page((unsigned long) buf);
if (err < 0)
return err;
@@ -992,6 +1079,7 @@
int ret;
/* Make sure the system still exists */
+ mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
list_for_each_entry(tr, &ftrace_trace_arrays, list) {
list_for_each_entry(dir, &tr->systems, list) {
@@ -1007,6 +1095,7 @@
}
exit_loop:
mutex_unlock(&event_mutex);
+ mutex_unlock(&trace_types_lock);
if (!system)
return -ENODEV;
@@ -1014,9 +1103,17 @@
/* Some versions of gcc think dir can be uninitialized here */
WARN_ON(!dir);
- ret = tracing_open_generic(inode, filp);
- if (ret < 0)
+ /* Still need to increment the ref count of the system */
+ if (trace_array_get(tr) < 0) {
put_system(dir);
+ return -ENODEV;
+ }
+
+ ret = tracing_open_generic(inode, filp);
+ if (ret < 0) {
+ trace_array_put(tr);
+ put_system(dir);
+ }
return ret;
}
@@ -1027,16 +1124,23 @@
struct trace_array *tr = inode->i_private;
int ret;
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
+
/* Make a temporary dir that has no system but points to tr */
dir = kzalloc(sizeof(*dir), GFP_KERNEL);
- if (!dir)
+ if (!dir) {
+ trace_array_put(tr);
return -ENOMEM;
+ }
dir->tr = tr;
ret = tracing_open_generic(inode, filp);
- if (ret < 0)
+ if (ret < 0) {
+ trace_array_put(tr);
kfree(dir);
+ }
filp->private_data = dir;
@@ -1047,6 +1151,8 @@
{
struct ftrace_subsystem_dir *dir = file->private_data;
+ trace_array_put(dir->tr);
+
/*
* If dir->subsystem is NULL, then this is a temporary
* descriptor that was made for a trace_array to enable
@@ -1143,6 +1249,7 @@
static int ftrace_event_avail_open(struct inode *inode, struct file *file);
static int ftrace_event_set_open(struct inode *inode, struct file *file);
+static int ftrace_event_release(struct inode *inode, struct file *file);
static const struct seq_operations show_event_seq_ops = {
.start = t_start,
@@ -1170,7 +1277,7 @@
.read = seq_read,
.write = ftrace_event_write,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = ftrace_event_release,
};
static const struct file_operations ftrace_enable_fops = {
@@ -1188,7 +1295,6 @@
};
static const struct file_operations ftrace_event_id_fops = {
- .open = tracing_open_generic,
.read = event_id_read,
.llseek = default_llseek,
};
@@ -1247,6 +1353,15 @@
return ret;
}
+static int ftrace_event_release(struct inode *inode, struct file *file)
+{
+ struct trace_array *tr = inode->i_private;
+
+ trace_array_put(tr);
+
+ return seq_release(inode, file);
+}
+
static int
ftrace_event_avail_open(struct inode *inode, struct file *file)
{
@@ -1260,12 +1375,19 @@
{
const struct seq_operations *seq_ops = &show_set_event_seq_ops;
struct trace_array *tr = inode->i_private;
+ int ret;
+
+ if (trace_array_get(tr) < 0)
+ return -ENODEV;
if ((file->f_mode & FMODE_WRITE) &&
(file->f_flags & O_TRUNC))
ftrace_clear_events(tr);
- return ftrace_event_open(inode, file, seq_ops);
+ ret = ftrace_event_open(inode, file, seq_ops);
+ if (ret < 0)
+ trace_array_put(tr);
+ return ret;
}
static struct event_subsystem *
@@ -1279,7 +1401,15 @@
return NULL;
system->ref_count = 1;
- system->name = name;
+
+ /* Only allocate if dynamic (kprobes and modules) */
+ if (!core_kernel_data((unsigned long)name)) {
+ system->ref_count |= SYSTEM_FL_FREE_NAME;
+ system->name = kstrdup(name, GFP_KERNEL);
+ if (!system->name)
+ goto out_free;
+ } else
+ system->name = name;
system->filter = NULL;
@@ -1292,6 +1422,8 @@
return system;
out_free:
+ if (system->ref_count & SYSTEM_FL_FREE_NAME)
+ kfree(system->name);
kfree(system);
return NULL;
}
@@ -1410,8 +1542,8 @@
#ifdef CONFIG_PERF_EVENTS
if (call->event.type && call->class->reg)
- trace_create_file("id", 0444, file->dir, call,
- id);
+ trace_create_file("id", 0444, file->dir,
+ (void *)(long)call->event.type, id);
#endif
/*
@@ -1436,33 +1568,16 @@
return 0;
}
-static void remove_subsystem(struct ftrace_subsystem_dir *dir)
-{
- if (!dir)
- return;
-
- if (!--dir->nr_events) {
- debugfs_remove_recursive(dir->entry);
- list_del(&dir->list);
- __put_system_dir(dir);
- }
-}
-
static void remove_event_from_tracers(struct ftrace_event_call *call)
{
struct ftrace_event_file *file;
struct trace_array *tr;
do_for_each_event_file_safe(tr, file) {
-
if (file->event_call != call)
continue;
- list_del(&file->list);
- debugfs_remove_recursive(file->dir);
- remove_subsystem(file->system);
- kmem_cache_free(file_cachep, file);
-
+ remove_event_file_dir(file);
/*
* The do_for_each_event_file_safe() is
* a double loop. After finding the call for this
@@ -1591,6 +1706,7 @@
int trace_add_event_call(struct ftrace_event_call *call)
{
int ret;
+ mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
ret = __register_event(call, NULL);
@@ -1598,11 +1714,13 @@
__add_event_to_tracers(call, NULL);
mutex_unlock(&event_mutex);
+ mutex_unlock(&trace_types_lock);
return ret;
}
/*
- * Must be called under locking both of event_mutex and trace_event_sem.
+ * Must be called under locking of trace_types_lock, event_mutex and
+ * trace_event_sem.
*/
static void __trace_remove_event_call(struct ftrace_event_call *call)
{
@@ -1611,14 +1729,47 @@
destroy_preds(call);
}
-/* Remove an event_call */
-void trace_remove_event_call(struct ftrace_event_call *call)
+static int probe_remove_event_call(struct ftrace_event_call *call)
{
+ struct trace_array *tr;
+ struct ftrace_event_file *file;
+
+#ifdef CONFIG_PERF_EVENTS
+ if (call->perf_refcount)
+ return -EBUSY;
+#endif
+ do_for_each_event_file(tr, file) {
+ if (file->event_call != call)
+ continue;
+ /*
+ * We can't rely on ftrace_event_enable_disable(enable => 0)
+ * we are going to do, FTRACE_EVENT_FL_SOFT_MODE can suppress
+ * TRACE_REG_UNREGISTER.
+ */
+ if (file->flags & FTRACE_EVENT_FL_ENABLED)
+ return -EBUSY;
+ break;
+ } while_for_each_event_file();
+
+ __trace_remove_event_call(call);
+
+ return 0;
+}
+
+/* Remove an event_call */
+int trace_remove_event_call(struct ftrace_event_call *call)
+{
+ int ret;
+
+ mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
down_write(&trace_event_sem);
- __trace_remove_event_call(call);
+ ret = probe_remove_event_call(call);
up_write(&trace_event_sem);
mutex_unlock(&event_mutex);
+ mutex_unlock(&trace_types_lock);
+
+ return ret;
}
#define for_each_event(event, start, end) \
@@ -1703,6 +1854,16 @@
struct ftrace_module_file_ops *file_ops = NULL;
struct ftrace_event_call **call, **start, **end;
+ if (!mod->num_trace_events)
+ return;
+
+ /* Don't add infrastructure for mods without tracepoints */
+ if (trace_module_has_bad_taint(mod)) {
+ pr_err("%s: module has bad taint, not creating trace events\n",
+ mod->name);
+ return;
+ }
+
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
@@ -1762,6 +1923,7 @@
{
struct module *mod = data;
+ mutex_lock(&trace_types_lock);
mutex_lock(&event_mutex);
switch (val) {
case MODULE_STATE_COMING:
@@ -1772,6 +1934,7 @@
break;
}
mutex_unlock(&event_mutex);
+ mutex_unlock(&trace_types_lock);
return 0;
}
@@ -2188,12 +2351,8 @@
{
struct ftrace_event_file *file, *next;
- list_for_each_entry_safe(file, next, &tr->events, list) {
- list_del(&file->list);
- debugfs_remove_recursive(file->dir);
- remove_subsystem(file->system);
- kmem_cache_free(file_cachep, file);
- }
+ list_for_each_entry_safe(file, next, &tr->events, list)
+ remove_event_file_dir(file);
}
static void
@@ -2329,11 +2488,11 @@
int event_trace_del_tracer(struct trace_array *tr)
{
- /* Disable any running events */
- __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
-
mutex_lock(&event_mutex);
+ /* Disable any running events */
+ __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);
+
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
debugfs_remove_recursive(tr->event_dir);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e1b653f..0a1edc6 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -631,17 +631,15 @@
free_page((unsigned long) buf);
}
+/* caller must hold event_mutex */
void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s)
{
- struct event_filter *filter;
+ struct event_filter *filter = call->filter;
- mutex_lock(&event_mutex);
- filter = call->filter;
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
trace_seq_printf(s, "none\n");
- mutex_unlock(&event_mutex);
}
void print_subsystem_event_filter(struct event_subsystem *system,
@@ -1835,23 +1833,22 @@
return err;
}
+/* caller must hold event_mutex */
int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
{
struct event_filter *filter;
- int err = 0;
-
- mutex_lock(&event_mutex);
+ int err;
if (!strcmp(strstrip(filter_string), "0")) {
filter_disable(call);
filter = call->filter;
if (!filter)
- goto out_unlock;
+ return 0;
RCU_INIT_POINTER(call->filter, NULL);
/* Make sure the filter is not being used */
synchronize_sched();
__free_filter(filter);
- goto out_unlock;
+ return 0;
}
err = create_filter(call, filter_string, true, &filter);
@@ -1878,8 +1875,6 @@
__free_filter(tmp);
}
}
-out_unlock:
- mutex_unlock(&event_mutex);
return err;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d21a746..d7d0b50 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@
#undef __array
#define __array(type, item, len) \
do { \
+ char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- mutex_lock(&event_storage_mutex); \
- snprintf(event_storage, sizeof(event_storage), \
- "%s[%d]", #type, len); \
- ret = trace_define_field(event_call, event_storage, #item, \
+ ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), filter_type); \
- mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
} while (0);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b19d065..2aefbee 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -373,7 +373,7 @@
struct trace_array_cpu *data;
unsigned long flags;
- if (likely(!tracer_enabled))
+ if (!tracer_enabled || !tracing_is_enabled())
return;
cpu = raw_smp_processor_id();
@@ -416,7 +416,7 @@
else
return;
- if (!tracer_enabled)
+ if (!tracer_enabled || !tracing_is_enabled())
return;
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9f46e98..64abc8c 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -90,7 +90,7 @@
}
static int register_probe_event(struct trace_probe *tp);
-static void unregister_probe_event(struct trace_probe *tp);
+static int unregister_probe_event(struct trace_probe *tp);
static DEFINE_MUTEX(probe_lock);
static LIST_HEAD(probe_list);
@@ -281,6 +281,8 @@
static int
disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file)
{
+ struct ftrace_event_file **old = NULL;
+ int wait = 0;
int ret = 0;
mutex_lock(&probe_enable_lock);
@@ -314,10 +316,7 @@
}
rcu_assign_pointer(tp->files, new);
-
- /* Make sure the probe is done with old files */
- synchronize_sched();
- kfree(old);
+ wait = 1;
} else
tp->flags &= ~TP_FLAG_PROFILE;
@@ -326,11 +325,25 @@
disable_kretprobe(&tp->rp);
else
disable_kprobe(&tp->rp.kp);
+ wait = 1;
}
out_unlock:
mutex_unlock(&probe_enable_lock);
+ if (wait) {
+ /*
+ * Synchronize with kprobe_trace_func/kretprobe_trace_func
+ * to ensure disabled (all running handlers are finished).
+ * This is not only for kfree(), but also the caller,
+ * trace_remove_event_call() supposes it for releasing
+ * event_call related objects, which will be accessed in
+ * the kprobe_trace_func/kretprobe_trace_func.
+ */
+ synchronize_sched();
+ kfree(old); /* Ignored if link == NULL */
+ }
+
return ret;
}
@@ -398,9 +411,12 @@
if (trace_probe_is_enabled(tp))
return -EBUSY;
+ /* Will fail if probe is being used by ftrace or perf */
+ if (unregister_probe_event(tp))
+ return -EBUSY;
+
__unregister_trace_probe(tp);
list_del(&tp->list);
- unregister_probe_event(tp);
return 0;
}
@@ -679,7 +695,9 @@
/* TODO: Use batch unregistration */
while (!list_empty(&probe_list)) {
tp = list_entry(probe_list.next, struct trace_probe, list);
- unregister_trace_probe(tp);
+ ret = unregister_trace_probe(tp);
+ if (ret)
+ goto end;
free_trace_probe(tp);
}
@@ -1312,11 +1330,15 @@
return ret;
}
-static void unregister_probe_event(struct trace_probe *tp)
+static int unregister_probe_event(struct trace_probe *tp)
{
+ int ret;
+
/* tp->event is unregistered in trace_remove_event_call() */
- trace_remove_event_call(&tp->call);
- kfree(tp->call.print_fmt);
+ ret = trace_remove_event_call(&tp->call);
+ if (!ret)
+ kfree(tp->call.print_fmt);
+ return ret;
}
/* Make a debugfs interface for controlling probe points */
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 8f2ac73..bdb9ee0 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -306,11 +306,13 @@
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
+ unsigned long irq_flags;
+ int pc;
int syscall_nr;
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, tr->enabled_enter_syscalls))
return;
@@ -321,9 +323,12 @@
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer,
- sys_data->enter_event->event.type, size, 0, 0);
+ sys_data->enter_event->event.type, size, irq_flags, pc);
if (!event)
return;
@@ -333,7 +338,8 @@
if (!filter_current_check_discard(buffer, sys_data->enter_event,
entry, event))
- trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+ trace_current_buffer_unlock_commit(buffer, event,
+ irq_flags, pc);
}
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -343,10 +349,12 @@
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
struct ring_buffer *buffer;
+ unsigned long irq_flags;
+ int pc;
int syscall_nr;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, tr->enabled_exit_syscalls))
return;
@@ -355,9 +363,13 @@
if (!sys_data)
return;
+ local_save_flags(irq_flags);
+ pc = preempt_count();
+
buffer = tr->trace_buffer.buffer;
event = trace_buffer_lock_reserve(buffer,
- sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
+ sys_data->exit_event->event.type, sizeof(*entry),
+ irq_flags, pc);
if (!event)
return;
@@ -367,7 +379,8 @@
if (!filter_current_check_discard(buffer, sys_data->exit_event,
entry, event))
- trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+ trace_current_buffer_unlock_commit(buffer, event,
+ irq_flags, pc);
}
static int reg_event_syscall_enter(struct ftrace_event_file *file,
@@ -544,7 +557,7 @@
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
@@ -620,7 +633,7 @@
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 32494fb0..6fd72b7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -70,7 +70,7 @@
(sizeof(struct probe_arg) * (n)))
static int register_uprobe_event(struct trace_uprobe *tu);
-static void unregister_uprobe_event(struct trace_uprobe *tu);
+static int unregister_uprobe_event(struct trace_uprobe *tu);
static DEFINE_MUTEX(uprobe_lock);
static LIST_HEAD(uprobe_list);
@@ -164,11 +164,17 @@
}
/* Unregister a trace_uprobe and probe_event: call with locking uprobe_lock */
-static void unregister_trace_uprobe(struct trace_uprobe *tu)
+static int unregister_trace_uprobe(struct trace_uprobe *tu)
{
+ int ret;
+
+ ret = unregister_uprobe_event(tu);
+ if (ret)
+ return ret;
+
list_del(&tu->list);
- unregister_uprobe_event(tu);
free_trace_uprobe(tu);
+ return 0;
}
/* Register a trace_uprobe and probe_event */
@@ -181,9 +187,12 @@
/* register as an event */
old_tp = find_probe_event(tu->call.name, tu->call.class->system);
- if (old_tp)
+ if (old_tp) {
/* delete old event */
- unregister_trace_uprobe(old_tp);
+ ret = unregister_trace_uprobe(old_tp);
+ if (ret)
+ goto end;
+ }
ret = register_uprobe_event(tu);
if (ret) {
@@ -256,6 +265,8 @@
group = UPROBE_EVENT_SYSTEM;
if (is_delete) {
+ int ret;
+
if (!event) {
pr_info("Delete command needs an event name.\n");
return -EINVAL;
@@ -269,9 +280,9 @@
return -ENOENT;
}
/* delete an event */
- unregister_trace_uprobe(tu);
+ ret = unregister_trace_uprobe(tu);
mutex_unlock(&uprobe_lock);
- return 0;
+ return ret;
}
if (argc < 2) {
@@ -283,8 +294,10 @@
return -EINVAL;
}
arg = strchr(argv[1], ':');
- if (!arg)
+ if (!arg) {
+ ret = -EINVAL;
goto fail_address_parse;
+ }
*arg++ = '\0';
filename = argv[1];
@@ -406,16 +419,20 @@
return ret;
}
-static void cleanup_all_probes(void)
+static int cleanup_all_probes(void)
{
struct trace_uprobe *tu;
+ int ret = 0;
mutex_lock(&uprobe_lock);
while (!list_empty(&uprobe_list)) {
tu = list_entry(uprobe_list.next, struct trace_uprobe, list);
- unregister_trace_uprobe(tu);
+ ret = unregister_trace_uprobe(tu);
+ if (ret)
+ break;
}
mutex_unlock(&uprobe_lock);
+ return ret;
}
/* Probes listing interfaces */
@@ -460,8 +477,13 @@
static int probes_open(struct inode *inode, struct file *file)
{
- if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
- cleanup_all_probes();
+ int ret;
+
+ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+ ret = cleanup_all_probes();
+ if (ret)
+ return ret;
+ }
return seq_open(file, &probes_seq_op);
}
@@ -968,12 +990,17 @@
return ret;
}
-static void unregister_uprobe_event(struct trace_uprobe *tu)
+static int unregister_uprobe_event(struct trace_uprobe *tu)
{
+ int ret;
+
/* tu->event is unregistered in trace_remove_event_call() */
- trace_remove_event_call(&tu->call);
+ ret = trace_remove_event_call(&tu->call);
+ if (ret)
+ return ret;
kfree(tu->call.print_fmt);
tu->call.print_fmt = NULL;
+ return 0;
}
/* Make a trace interface for controling probe points */
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 29f2654..63630ae 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -631,17 +631,25 @@
EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
#ifdef CONFIG_MODULES
+bool trace_module_has_bad_taint(struct module *mod)
+{
+ return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+}
+
static int tracepoint_module_coming(struct module *mod)
{
struct tp_module *tp_mod, *iter;
int ret = 0;
+ if (!mod->num_tracepoints)
+ return 0;
+
/*
* We skip modules that taint the kernel, especially those with different
* module headers (for forced load), to make sure we don't cause a crash.
* Staging and out-of-tree GPL modules are fine.
*/
- if (mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP)))
+ if (trace_module_has_bad_taint(mod))
return 0;
mutex_lock(&tracepoints_mutex);
tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
@@ -679,6 +687,9 @@
{
struct tp_module *pos;
+ if (!mod->num_tracepoints)
+ return 0;
+
mutex_lock(&tracepoints_mutex);
tracepoint_update_probe_range(mod->tracepoints_ptrs,
mod->tracepoints_ptrs + mod->num_tracepoints);
diff --git a/kernel/uid16.c b/kernel/uid16.c
index f6c83d7..d58cc4d 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -176,7 +176,7 @@
struct group_info *group_info;
int retval;
- if (!nsown_capable(CAP_SETGID))
+ if (!may_setgroups())
return -EPERM;
if ((unsigned)gidsetsize > NGROUPS_MAX)
return -EINVAL;
diff --git a/kernel/user.c b/kernel/user.c
index 69b4c3d..6bbef56 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,7 @@
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
.proc_inum = PROC_USER_INIT_INO,
+ .flags = USERNS_INIT_FLAGS,
.may_mount_sysfs = true,
.may_mount_proc = true,
};
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index d8c30db..3f2fb33 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -24,6 +24,7 @@
#include <linux/fs_struct.h>
static struct kmem_cache *user_ns_cachep __read_mostly;
+static DEFINE_MUTEX(userns_state_mutex);
static bool new_idmap_permitted(const struct file *file,
struct user_namespace *ns, int cap_setid,
@@ -62,6 +63,9 @@
kgid_t group = new->egid;
int ret;
+ if (parent_ns->level > 32)
+ return -EUSERS;
+
/*
* Verify that we can not violate the policy of which files
* may be accessed that is specified by the root directory,
@@ -92,9 +96,15 @@
atomic_set(&ns->count, 1);
/* Leave the new->user_ns reference with the new user namespace. */
ns->parent = parent_ns;
+ ns->level = parent_ns->level + 1;
ns->owner = owner;
ns->group = group;
+ /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */
+ mutex_lock(&userns_state_mutex);
+ ns->flags = parent_ns->flags;
+ mutex_unlock(&userns_state_mutex);
+
set_cred_user_ns(new, ns);
update_mnt_policy(ns);
@@ -105,16 +115,21 @@
int unshare_userns(unsigned long unshare_flags, struct cred **new_cred)
{
struct cred *cred;
+ int err = -ENOMEM;
if (!(unshare_flags & CLONE_NEWUSER))
return 0;
cred = prepare_creds();
- if (!cred)
- return -ENOMEM;
+ if (cred) {
+ err = create_user_ns(cred);
+ if (err)
+ put_cred(cred);
+ else
+ *new_cred = cred;
+ }
- *new_cred = cred;
- return create_user_ns(cred);
+ return err;
}
void free_user_ns(struct user_namespace *ns)
@@ -139,7 +154,7 @@
/* Find the matching extent */
extents = map->nr_extents;
- smp_read_barrier_depends();
+ smp_rmb();
for (idx = 0; idx < extents; idx++) {
first = map->extent[idx].first;
last = first + map->extent[idx].count - 1;
@@ -163,7 +178,7 @@
/* Find the matching extent */
extents = map->nr_extents;
- smp_read_barrier_depends();
+ smp_rmb();
for (idx = 0; idx < extents; idx++) {
first = map->extent[idx].first;
last = first + map->extent[idx].count - 1;
@@ -186,7 +201,7 @@
/* Find the matching extent */
extents = map->nr_extents;
- smp_read_barrier_depends();
+ smp_rmb();
for (idx = 0; idx < extents; idx++) {
first = map->extent[idx].lower_first;
last = first + map->extent[idx].count - 1;
@@ -568,9 +583,6 @@
return false;
}
-
-static DEFINE_MUTEX(id_map_mutex);
-
static ssize_t map_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos,
int cap_setid,
@@ -587,7 +599,7 @@
ssize_t ret = -EINVAL;
/*
- * The id_map_mutex serializes all writes to any given map.
+ * The userns_state_mutex serializes all writes to any given map.
*
* Any map is only ever written once.
*
@@ -602,11 +614,10 @@
* were written before the count of the extents.
*
* To achieve this smp_wmb() is used on guarantee the write
- * order and smp_read_barrier_depends() is guaranteed that we
- * don't have crazy architectures returning stale data.
- *
+ * order and smp_rmb() is guaranteed that we don't have crazy
+ * architectures returning stale data.
*/
- mutex_lock(&id_map_mutex);
+ mutex_lock(&userns_state_mutex);
ret = -EPERM;
/* Only allow one successful write to the map */
@@ -733,7 +744,7 @@
*ppos = count;
ret = count;
out:
- mutex_unlock(&id_map_mutex);
+ mutex_unlock(&userns_state_mutex);
if (page)
free_page(page);
return ret;
@@ -792,17 +803,21 @@
struct user_namespace *ns, int cap_setid,
struct uid_gid_map *new_map)
{
- /* Allow mapping to your own filesystem ids */
- if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1)) {
+ const struct cred *cred = file->f_cred;
+ /* Don't allow mappings that would allow anything that wouldn't
+ * be allowed without the establishment of unprivileged mappings.
+ */
+ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) &&
+ uid_eq(ns->owner, cred->euid)) {
u32 id = new_map->extent[0].lower_first;
if (cap_setid == CAP_SETUID) {
kuid_t uid = make_kuid(ns->parent, id);
- if (uid_eq(uid, file->f_cred->fsuid))
+ if (uid_eq(uid, cred->euid))
return true;
- }
- else if (cap_setid == CAP_SETGID) {
+ } else if (cap_setid == CAP_SETGID) {
kgid_t gid = make_kgid(ns->parent, id);
- if (gid_eq(gid, file->f_cred->fsgid))
+ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) &&
+ gid_eq(gid, cred->egid))
return true;
}
}
@@ -822,6 +837,100 @@
return false;
}
+int proc_setgroups_show(struct seq_file *seq, void *v)
+{
+ struct user_namespace *ns = seq->private;
+ unsigned long userns_flags = ACCESS_ONCE(ns->flags);
+
+ seq_printf(seq, "%s\n",
+ (userns_flags & USERNS_SETGROUPS_ALLOWED) ?
+ "allow" : "deny");
+ return 0;
+}
+
+ssize_t proc_setgroups_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct seq_file *seq = file->private_data;
+ struct user_namespace *ns = seq->private;
+ char kbuf[8], *pos;
+ bool setgroups_allowed;
+ ssize_t ret;
+
+ /* Only allow a very narrow range of strings to be written */
+ ret = -EINVAL;
+ if ((*ppos != 0) || (count >= sizeof(kbuf)))
+ goto out;
+
+ /* What was written? */
+ ret = -EFAULT;
+ if (copy_from_user(kbuf, buf, count))
+ goto out;
+ kbuf[count] = '\0';
+ pos = kbuf;
+
+ /* What is being requested? */
+ ret = -EINVAL;
+ if (strncmp(pos, "allow", 5) == 0) {
+ pos += 5;
+ setgroups_allowed = true;
+ }
+ else if (strncmp(pos, "deny", 4) == 0) {
+ pos += 4;
+ setgroups_allowed = false;
+ }
+ else
+ goto out;
+
+ /* Verify there is not trailing junk on the line */
+ pos = skip_spaces(pos);
+ if (*pos != '\0')
+ goto out;
+
+ ret = -EPERM;
+ mutex_lock(&userns_state_mutex);
+ if (setgroups_allowed) {
+ /* Enabling setgroups after setgroups has been disabled
+ * is not allowed.
+ */
+ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED))
+ goto out_unlock;
+ } else {
+ /* Permanently disabling setgroups after setgroups has
+ * been enabled by writing the gid_map is not allowed.
+ */
+ if (ns->gid_map.nr_extents != 0)
+ goto out_unlock;
+ ns->flags &= ~USERNS_SETGROUPS_ALLOWED;
+ }
+ mutex_unlock(&userns_state_mutex);
+
+ /* Report a successful write */
+ *ppos = count;
+ ret = count;
+out:
+ return ret;
+out_unlock:
+ mutex_unlock(&userns_state_mutex);
+ goto out;
+}
+
+bool userns_may_setgroups(const struct user_namespace *ns)
+{
+ bool allowed;
+
+ mutex_lock(&userns_state_mutex);
+ /* It is not safe to use setgroups until a gid mapping in
+ * the user namespace has been established.
+ */
+ allowed = ns->gid_map.nr_extents != 0;
+ /* Is setgroups allowed? */
+ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED);
+ mutex_unlock(&userns_state_mutex);
+
+ return allowed;
+}
+
static void *userns_get(struct task_struct *task)
{
struct user_namespace *user_ns;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ee8e29a..61bcf37 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -272,6 +272,15 @@
static bool wq_disable_numa;
module_param_named(disable_numa, wq_disable_numa, bool, 0444);
+/* see the comment above the definition of WQ_POWER_EFFICIENT */
+#ifdef CONFIG_WQ_POWER_EFFICIENT_DEFAULT
+static bool wq_power_efficient = true;
+#else
+static bool wq_power_efficient;
+#endif
+
+module_param_named(power_efficient, wq_power_efficient, bool, 0444);
+
static bool wq_numa_enabled; /* unbound NUMA affinity enabled */
/* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */
@@ -295,6 +304,9 @@
/* I: attributes used when instantiating standard unbound pools on demand */
static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS];
+/* I: attributes used when instantiating ordered pools on demand */
+static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS];
+
struct workqueue_struct *system_wq __read_mostly;
EXPORT_SYMBOL(system_wq);
struct workqueue_struct *system_highpri_wq __read_mostly;
@@ -305,6 +317,10 @@
EXPORT_SYMBOL_GPL(system_unbound_wq);
struct workqueue_struct *system_freezable_wq __read_mostly;
EXPORT_SYMBOL_GPL(system_freezable_wq);
+struct workqueue_struct *system_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_power_efficient_wq);
+struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly;
+EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq);
static int worker_thread(void *__worker);
static void copy_workqueue_attrs(struct workqueue_attrs *to,
@@ -1820,6 +1836,12 @@
if (worker->flags & WORKER_IDLE)
pool->nr_idle--;
+ /*
+ * Once WORKER_DIE is set, the kworker may destroy itself at any
+ * point. Pin to ensure the task stays until we're done with it.
+ */
+ get_task_struct(worker->task);
+
list_del_init(&worker->entry);
worker->flags |= WORKER_DIE;
@@ -1828,6 +1850,7 @@
spin_unlock_irq(&pool->lock);
kthread_stop(worker->task);
+ put_task_struct(worker->task);
kfree(worker);
spin_lock_irq(&pool->lock);
@@ -1871,6 +1894,12 @@
/* mayday mayday mayday */
if (list_empty(&pwq->mayday_node)) {
+ /*
+ * If @pwq is for an unbound wq, its base ref may be put at
+ * any time due to an attribute change. Pin @pwq until the
+ * rescuer is done with it.
+ */
+ get_pwq(pwq);
list_add_tail(&pwq->mayday_node, &wq->maydays);
wake_up_process(wq->rescuer->task);
}
@@ -1918,17 +1947,13 @@
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
- *
- * RETURNS:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
*/
-static bool maybe_create_worker(struct worker_pool *pool)
+static void maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
if (!need_to_create_worker(pool))
- return false;
+ return;
restart:
spin_unlock_irq(&pool->lock);
@@ -1945,7 +1970,7 @@
start_worker(worker);
if (WARN_ON_ONCE(need_to_create_worker(pool)))
goto restart;
- return true;
+ return;
}
if (!need_to_create_worker(pool))
@@ -1962,7 +1987,7 @@
spin_lock_irq(&pool->lock);
if (need_to_create_worker(pool))
goto restart;
- return true;
+ return;
}
/**
@@ -1975,15 +2000,9 @@
* LOCKING:
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Called only from manager.
- *
- * RETURNS:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
*/
-static bool maybe_destroy_workers(struct worker_pool *pool)
+static void maybe_destroy_workers(struct worker_pool *pool)
{
- bool ret = false;
-
while (too_many_workers(pool)) {
struct worker *worker;
unsigned long expires;
@@ -1997,10 +2016,7 @@
}
destroy_worker(worker);
- ret = true;
}
-
- return ret;
}
/**
@@ -2020,13 +2036,14 @@
* multiple times. Does GFP_KERNEL allocations.
*
* RETURNS:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
- * multiple times. Does GFP_KERNEL allocations.
+ * %false if the pool doesn't need management and the caller can safely
+ * start processing works, %true if management function was performed and
+ * the conditions that the caller verified before calling the function may
+ * no longer be true.
*/
static bool manage_workers(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
- bool ret = false;
/*
* Managership is governed by two mutexes - manager_arb and
@@ -2050,7 +2067,7 @@
* manager_mutex.
*/
if (!mutex_trylock(&pool->manager_arb))
- return ret;
+ return false;
/*
* With manager arbitration won, manager_mutex would be free in
@@ -2060,7 +2077,6 @@
spin_unlock_irq(&pool->lock);
mutex_lock(&pool->manager_mutex);
spin_lock_irq(&pool->lock);
- ret = true;
}
pool->flags &= ~POOL_MANAGE_WORKERS;
@@ -2069,12 +2085,12 @@
* Destroy and then create so that may_start_working() is true
* on return.
*/
- ret |= maybe_destroy_workers(pool);
- ret |= maybe_create_worker(pool);
+ maybe_destroy_workers(pool);
+ maybe_create_worker(pool);
mutex_unlock(&pool->manager_mutex);
mutex_unlock(&pool->manager_arb);
- return ret;
+ return true;
}
/**
@@ -2188,6 +2204,15 @@
dump_stack();
}
+ /*
+ * The following prevents a kworker from hogging CPU on !PREEMPT
+ * kernels, where a requeueing work item waiting for something to
+ * happen could deadlock with stop_machine as such work item could
+ * indefinitely requeue itself while all other CPUs are trapped in
+ * stop_machine.
+ */
+ cond_resched();
+
spin_lock_irq(&pool->lock);
/* clear cpu intensive status */
@@ -2337,6 +2362,7 @@
struct worker *rescuer = __rescuer;
struct workqueue_struct *wq = rescuer->rescue_wq;
struct list_head *scheduled = &rescuer->scheduled;
+ bool should_stop;
set_user_nice(current, RESCUER_NICE_LEVEL);
@@ -2348,11 +2374,15 @@
repeat:
set_current_state(TASK_INTERRUPTIBLE);
- if (kthread_should_stop()) {
- __set_current_state(TASK_RUNNING);
- rescuer->task->flags &= ~PF_WQ_WORKER;
- return 0;
- }
+ /*
+ * By the time the rescuer is requested to stop, the workqueue
+ * shouldn't have any work pending, but @wq->maydays may still have
+ * pwq(s) queued. This can happen by non-rescuer workers consuming
+ * all the work items before the rescuer got to them. Go through
+ * @wq->maydays processing before acting on should_stop so that the
+ * list is always empty on exit.
+ */
+ should_stop = kthread_should_stop();
/* see whether any pwq is asking for help */
spin_lock_irq(&wq_mayday_lock);
@@ -2384,6 +2414,12 @@
process_scheduled_works(rescuer);
/*
+ * Put the reference grabbed by send_mayday(). @pool won't
+ * go away while we're holding its lock.
+ */
+ put_pwq(pwq);
+
+ /*
* Leave this pool. If keep_working() is %true, notify a
* regular worker; otherwise, we end up with 0 concurrency
* and stalling the execution.
@@ -2398,6 +2434,12 @@
spin_unlock_irq(&wq_mayday_lock);
+ if (should_stop) {
+ __set_current_state(TASK_RUNNING);
+ rescuer->task->flags &= ~PF_WQ_WORKER;
+ return 0;
+ }
+
/* rescuers should never participate in concurrency management */
WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
schedule();
@@ -2832,19 +2874,57 @@
}
EXPORT_SYMBOL_GPL(flush_work);
+struct cwt_wait {
+ wait_queue_t wait;
+ struct work_struct *work;
+};
+
+static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+ struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);
+
+ if (cwait->work != key)
+ return 0;
+ return autoremove_wake_function(wait, mode, sync, key);
+}
+
static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
{
+ static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq);
unsigned long flags;
int ret;
do {
ret = try_to_grab_pending(work, is_dwork, &flags);
/*
- * If someone else is canceling, wait for the same event it
- * would be waiting for before retrying.
+ * If someone else is already canceling, wait for it to
+ * finish. flush_work() doesn't work for PREEMPT_NONE
+ * because we may get scheduled between @work's completion
+ * and the other canceling task resuming and clearing
+ * CANCELING - flush_work() will return false immediately
+ * as @work is no longer busy, try_to_grab_pending() will
+ * return -ENOENT as @work is still being canceled and the
+ * other canceling task won't be able to clear CANCELING as
+ * we're hogging the CPU.
+ *
+ * Let's wait for completion using a waitqueue. As this
+ * may lead to the thundering herd problem, use a custom
+ * wake function which matches @work along with exclusive
+ * wait and wakeup.
*/
- if (unlikely(ret == -ENOENT))
- flush_work(work);
+ if (unlikely(ret == -ENOENT)) {
+ struct cwt_wait cwait;
+
+ init_wait(&cwait.wait);
+ cwait.wait.func = cwt_wakefn;
+ cwait.work = work;
+
+ prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait,
+ TASK_UNINTERRUPTIBLE);
+ if (work_is_canceling(work))
+ schedule();
+ finish_wait(&cancel_waitq, &cwait.wait);
+ }
} while (unlikely(ret < 0));
/* tell other tasks trying to grab @work to back off */
@@ -2853,6 +2933,16 @@
flush_work(work);
clear_work_data(work);
+
+ /*
+ * Paired with prepare_to_wait() above so that either
+ * waitqueue_active() is visible here or !work_is_canceling() is
+ * visible there.
+ */
+ smp_mb();
+ if (waitqueue_active(&cancel_waitq))
+ __wake_up(&cancel_waitq, TASK_NORMAL, 1, work);
+
return ret;
}
@@ -3331,6 +3421,7 @@
}
}
+ dev_set_uevent_suppress(&wq_dev->dev, false);
kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
return 0;
}
@@ -3398,6 +3489,12 @@
{
to->nice = from->nice;
cpumask_copy(to->cpumask, from->cpumask);
+ /*
+ * Unlike hash and equality test, this function doesn't ignore
+ * ->no_numa as it is used for both pool and wq attrs. Instead,
+ * get_unbound_pool() explicitly clears ->no_numa after copying.
+ */
+ to->no_numa = from->no_numa;
}
/* hash value of the content of @attr */
@@ -3565,6 +3662,12 @@
lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */
copy_workqueue_attrs(pool->attrs, attrs);
+ /*
+ * no_numa isn't a worker_pool attribute, always clear it. See
+ * 'struct workqueue_attrs' comments for detail.
+ */
+ pool->attrs->no_numa = false;
+
/* if cpumask is contained inside a NUMA node, we belong to that node */
if (wq_numa_enabled) {
for_each_node(node) {
@@ -4012,7 +4115,8 @@
if (!pwq) {
pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
wq->name);
- goto out_unlock;
+ mutex_lock(&wq->mutex);
+ goto use_dfl_pwq;
}
/*
@@ -4038,7 +4142,7 @@
static int alloc_and_link_pwqs(struct workqueue_struct *wq)
{
bool highpri = wq->flags & WQ_HIGHPRI;
- int cpu;
+ int cpu, ret;
if (!(wq->flags & WQ_UNBOUND)) {
wq->cpu_pwqs = alloc_percpu(struct pool_workqueue);
@@ -4058,6 +4162,13 @@
mutex_unlock(&wq->mutex);
}
return 0;
+ } else if (wq->flags & __WQ_ORDERED) {
+ ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]);
+ /* there should only be single pwq for ordering guarantee */
+ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node ||
+ wq->pwqs.prev != &wq->dfl_pwq->pwqs_node),
+ "ordering guarantee broken for workqueue %s\n", wq->name);
+ return ret;
} else {
return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]);
}
@@ -4086,6 +4197,10 @@
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
+ /* see the comment above the definition of WQ_POWER_EFFICIENT */
+ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
+ flags |= WQ_UNBOUND;
+
/* allocate wq and format name */
if (flags & WQ_UNBOUND)
tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]);
@@ -4905,7 +5020,7 @@
BUG_ON(!tbl);
for_each_node(node)
- BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+ BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
node_online(node) ? node : NUMA_NO_NODE));
for_each_possible_cpu(cpu) {
@@ -4969,13 +5084,23 @@
}
}
- /* create default unbound wq attrs */
+ /* create default unbound and ordered wq attrs */
for (i = 0; i < NR_STD_WORKER_POOLS; i++) {
struct workqueue_attrs *attrs;
BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
attrs->nice = std_nice[i];
unbound_std_wq_attrs[i] = attrs;
+
+ /*
+ * An ordered wq should have only one pwq as ordering is
+ * guaranteed by max_active which is enforced by pwqs.
+ * Turn off NUMA so that dfl_pwq is used for all nodes.
+ */
+ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL)));
+ attrs->nice = std_nice[i];
+ attrs->no_numa = true;
+ ordered_wq_attrs[i] = attrs;
}
system_wq = alloc_workqueue("events", 0, 0);
@@ -4985,8 +5110,15 @@
WQ_UNBOUND_MAX_ACTIVE);
system_freezable_wq = alloc_workqueue("events_freezable",
WQ_FREEZABLE, 0);
+ system_power_efficient_wq = alloc_workqueue("events_power_efficient",
+ WQ_POWER_EFFICIENT, 0);
+ system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient",
+ WQ_FREEZABLE | WQ_POWER_EFFICIENT,
+ 0);
BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
- !system_unbound_wq || !system_freezable_wq);
+ !system_unbound_wq || !system_freezable_wq ||
+ !system_power_efficient_wq ||
+ !system_freezable_power_efficient_wq);
return 0;
}
early_initcall(init_workqueues);
diff --git a/lib/Kconfig b/lib/Kconfig
index fe01d41..06d94d8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -189,6 +189,15 @@
config LZO_DECOMPRESS
tristate
+config LZ4_COMPRESS
+ tristate
+
+config LZ4HC_COMPRESS
+ tristate
+
+config LZ4_DECOMPRESS
+ tristate
+
source "lib/xz/Kconfig"
#
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 566cf2b..74fdc5c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1272,7 +1272,7 @@
depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
depends on !X86_64
select STACKTRACE
- select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
+ select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
help
Provide stacktrace filter for fault-injection capabilities
diff --git a/lib/Makefile b/lib/Makefile
index c55a037..438665a8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,6 +45,7 @@
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
+GCOV_PROFILE_hweight.o := n
CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
@@ -75,6 +76,9 @@
obj-$(CONFIG_BCH) += bch.o
obj-$(CONFIG_LZO_COMPRESS) += lzo/
obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_LZ4_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
obj-$(CONFIG_XZ_DEC) += xz/
obj-$(CONFIG_RAID6_PQ) += raid6/
@@ -139,7 +143,8 @@
obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
-libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o
+libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \
+ fdt_empty_tree.o
$(foreach file, $(libfdt_files), \
$(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt))
lib-$(CONFIG_LIBFDT) += $(libfdt_files)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06f7e4f..e5c4ebe 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -131,7 +131,9 @@
lower = src[off + k];
if (left && off + k == lim - 1)
lower &= mask;
- dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
+ dst[k] = lower >> rem;
+ if (rem)
+ dst[k] |= upper << (BITS_PER_LONG - rem);
if (left && k == lim - 1)
dst[k] &= mask;
}
@@ -172,7 +174,9 @@
upper = src[k];
if (left && k == lim - 1)
upper &= (1UL << left) - 1;
- dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem;
+ dst[k + off] = upper << rem;
+ if (rem)
+ dst[k + off] |= lower >> (BITS_PER_LONG - rem);
if (left && k + off == lim - 1)
dst[k + off] &= (1UL << left) - 1;
}
diff --git a/lib/btree.c b/lib/btree.c
index f9a4846..4264871 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -198,6 +198,7 @@
void btree_destroy(struct btree_head *head)
{
+ mempool_free(head->node, head->mempool);
mempool_destroy(head->mempool);
head->mempool = NULL;
}
diff --git a/lib/checksum.c b/lib/checksum.c
index 129775e..8b39e86 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -181,6 +181,15 @@
EXPORT_SYMBOL(csum_partial_copy);
#ifndef csum_tcpudp_nofold
+static inline u32 from64to32(u64 x)
+{
+ /* add up 32-bit and 32-bit for 32+c bit */
+ x = (x & 0xffffffff) + (x >> 32);
+ /* add up carry.. */
+ x = (x & 0xffffffff) + (x >> 32);
+ return (u32)x;
+}
+
__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
unsigned short len,
unsigned short proto,
@@ -195,8 +204,7 @@
#else
s += (proto + len) << 8;
#endif
- s += (s >> 32);
- return (__force __wsum)s;
+ return (__force __wsum)from64to32(s);
}
EXPORT_SYMBOL(csum_tcpudp_nofold);
#endif
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 31c5f76..f504027 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -184,7 +184,7 @@
if (get_bits(bd, 1))
return RETVAL_OBSOLETE_INPUT;
origPtr = get_bits(bd, 24);
- if (origPtr > dbufSize)
+ if (origPtr >= dbufSize)
return RETVAL_DATA_ERROR;
/* mapping table: if some byte values are never used (encoding things
like ascii text), the compression code removes the gaps to have fewer
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 19ff89e..d619b28 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -48,7 +48,7 @@
out_len = 0x8000; /* 32 K */
out_buf = malloc(out_len);
} else {
- out_len = 0x7fffffff; /* no limit */
+ out_len = ((size_t)~0) - (size_t)out_buf; /* no limit */
}
if (!out_buf) {
error("Out of memory while allocating output buffer");
diff --git a/lib/fdt_empty_tree.c b/lib/fdt_empty_tree.c
new file mode 100644
index 0000000..5d30c58
--- /dev/null
+++ b/lib/fdt_empty_tree.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_empty_tree.c"
diff --git a/lib/genalloc.c b/lib/genalloc.c
index b35cfa9..9e9c46c 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -37,6 +37,11 @@
#include <linux/of_address.h>
#include <linux/of_device.h>
+static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
+{
+ return chunk->end_addr - chunk->start_addr + 1;
+}
+
static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
{
unsigned long val, nval;
@@ -188,7 +193,7 @@
chunk->phys_addr = phys;
chunk->start_addr = virt;
- chunk->end_addr = virt + size;
+ chunk->end_addr = virt + size - 1;
atomic_set(&chunk->avail, size);
spin_lock(&pool->lock);
@@ -213,7 +218,7 @@
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
- if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+ if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
paddr = chunk->phys_addr + (addr - chunk->start_addr);
break;
}
@@ -242,7 +247,7 @@
chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
list_del(&chunk->next_chunk);
- end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+ end_bit = chunk_size(chunk) >> order;
bit = find_next_bit(chunk->bits, end_bit, 0);
BUG_ON(bit < end_bit);
@@ -283,7 +288,7 @@
if (size > atomic_read(&chunk->avail))
continue;
- end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+ end_bit = chunk_size(chunk) >> order;
retry:
start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
pool->data);
@@ -330,8 +335,8 @@
nbits = (size + (1UL << order) - 1) >> order;
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
- if (addr >= chunk->start_addr && addr < chunk->end_addr) {
- BUG_ON(addr + size > chunk->end_addr);
+ if (addr >= chunk->start_addr && addr <= chunk->end_addr) {
+ BUG_ON(addr + size - 1 > chunk->end_addr);
start_bit = (addr - chunk->start_addr) >> order;
remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
BUG_ON(remain);
@@ -369,6 +374,35 @@
EXPORT_SYMBOL(gen_pool_for_each_chunk);
/**
+ * addr_in_gen_pool - checks if an address falls within the range of a pool
+ * @pool: the generic memory pool
+ * @start: start address
+ * @size: size of the region
+ *
+ * Check if the range of addresses falls within the specified pool. Returns
+ * true if the entire range is contained in the pool and false otherwise.
+ */
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+ size_t size)
+{
+ bool found = false;
+ unsigned long end = start + size;
+ struct gen_pool_chunk *chunk;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) {
+ if (start >= chunk->start_addr && start <= chunk->end_addr) {
+ if (end <= chunk->end_addr) {
+ found = true;
+ break;
+ }
+ }
+ }
+ rcu_read_unlock();
+ return found;
+}
+
+/**
* gen_pool_avail - get available free space of the pool
* @pool: pool to get available free space
*
@@ -400,7 +434,7 @@
rcu_read_lock();
list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
- size += chunk->end_addr - chunk->start_addr;
+ size += chunk_size(chunk);
rcu_read_unlock();
return size;
}
@@ -447,6 +481,26 @@
EXPORT_SYMBOL(gen_pool_first_fit);
/**
+ * gen_pool_first_fit_order_align - find the first available region
+ * of memory matching the size requirement. The region will be aligned
+ * to the order of the size specified.
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+ unsigned long size, unsigned long start,
+ unsigned int nr, void *data)
+{
+ unsigned long align_mask = roundup_pow_of_two(nr) - 1;
+
+ return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+}
+EXPORT_SYMBOL(gen_pool_first_fit_order_align);
+
+/**
* gen_pool_best_fit - find the best fitting region of memory
* macthing the size requirement (no alignment constraint)
* @map: The address to base the search on
diff --git a/lib/idr.c b/lib/idr.c
index cca4b93..a3bfde8 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -250,7 +250,7 @@
id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
/* if already at the top layer, we need to grow */
- if (id >= 1 << (idp->layers * IDR_BITS)) {
+ if (id > idr_max(idp->layers)) {
*starting_id = id;
return -EAGAIN;
}
@@ -829,12 +829,10 @@
if (!p)
return ERR_PTR(-EINVAL);
- n = (p->layer+1) * IDR_BITS;
-
- if (id >= (1 << n))
+ if (id > idr_max(p->layer + 1))
return ERR_PTR(-EINVAL);
- n -= IDR_BITS;
+ n = p->layer * IDR_BITS;
while ((n > 0) && p) {
p = p->ary[(id >> n) & IDR_MASK];
n -= IDR_BITS;
diff --git a/lib/lz4/Makefile b/lib/lz4/Makefile
new file mode 100644
index 0000000..8085d04
--- /dev/null
+++ b/lib/lz4/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_LZ4_COMPRESS) += lz4_compress.o
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4hc_compress.o
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4_decompress.o
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
new file mode 100644
index 0000000..fd94058
--- /dev/null
+++ b/lib/lz4/lz4_compress.c
@@ -0,0 +1,443 @@
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+/*
+ * LZ4_compressCtx :
+ * -----------------
+ * Compress 'isize' bytes from 'source' into an output buffer 'dest' of
+ * maximum size 'maxOutputSize'. * If it cannot achieve it, compression
+ * will stop, and result of the function will be zero.
+ * return : the number of bytes written in buffer 'dest', or 0 if the
+ * compression fails
+ */
+static inline int lz4_compressctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ HTYPE *hashtable = (HTYPE *)ctx;
+ const u8 *ip = (u8 *)source;
+#if LZ4_ARCH64
+ const BYTE * const base = ip;
+#else
+ const int base = 0;
+#endif
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (unlikely(forwardip > mflimit))
+ goto _last_literals;
+
+ forwardh = LZ4_HASH_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = ip - base;
+ } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source) &&
+ unlikely(ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS) +
+ (length >> 8) > oend))
+ return 0;
+
+ if (length >= (int)RUN_MASK) {
+ int len;
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+ while (likely(ip < MATCHLIMIT - (STEPSIZE - 1))) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+ /* Encode MatchLength */
+ length = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)ML_MASK) {
+ *token += ML_MASK;
+ length -= ML_MASK;
+ for (; length > 509 ; length -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (length > 254) {
+ length -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)length;
+ } else
+ *token += length;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH_VALUE(ip)];
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (((char *)op - dest) + lastrun + 1
+ + ((lastrun + 255 - RUN_MASK) / 255) > (u32)maxoutputsize)
+ return 0;
+
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+static inline int lz4_compress64kctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ u16 *hashtable = (u16 *)ctx;
+ const u8 *ip = (u8 *) source;
+ const u8 *anchor = ip;
+ const u8 *const base = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int len, length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (forwardip > mflimit)
+ goto _last_literals;
+
+ forwardh = LZ4_HASH64K_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = (u16)(ip - base);
+ } while (A32(ref) != A32(ip));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source)
+ && (ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* Check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS)
+ + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+
+ while (ip < MATCHLIMIT - (STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+
+ /* Encode MatchLength */
+ len = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (len >> 8) > oend))
+ return 0;
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH64K_VALUE(ip-2)] = (u16)(ip - 2 - base);
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH64K_VALUE(ip)];
+ hashtable[LZ4_HASH64K_VALUE(ip)] = (u16)(ip - base);
+ if (A32(ref) == A32(ip)) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (op + lastrun + 1 + (lastrun - RUN_MASK + 255) / 255 > oend)
+ return 0;
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ if (src_len < LZ4_64KLIMIT)
+ out_len = lz4_compress64kctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+ else
+ out_len = lz4_compressctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+
+ return 0;
+exit:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(lz4_compress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 compressor");
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
new file mode 100644
index 0000000..677d1ea
--- /dev/null
+++ b/lib/lz4/lz4_decompress.c
@@ -0,0 +1,326 @@
+/*
+ * LZ4 Decompressor for Linux kernel
+ *
+ * Copyright (C) 2013 LG Electronics Co., Ltd. (http://www.lge.com/)
+ *
+ * Based on LZ4 implementation by Yann Collet.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ */
+
+#ifndef STATIC
+#include <linux/module.h>
+#include <linux/kernel.h>
+#endif
+#include <linux/lz4.h>
+
+#include <asm/unaligned.h>
+
+#include "lz4defs.h"
+
+static int lz4_uncompress(const char *source, char *dest, int osize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *ref;
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + osize;
+ BYTE *cpy;
+ unsigned token;
+ size_t length;
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ while (1) {
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ size_t len;
+
+ len = *ip++;
+ for (; len == 255; length += 255)
+ len = *ip++;
+ length += len;
+ }
+
+ /* copy literals */
+ cpy = op + length;
+ if (unlikely(cpy > oend - COPYLENGTH)) {
+ /*
+ * Error: not enough place for another match
+ * (min 4) + 5 literals
+ */
+ if (cpy != oend)
+ goto _output_error;
+
+ memcpy(op, ip, length);
+ ip += length;
+ break; /* EOF */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+
+ /* Error: offset create reference outside destination buffer */
+ if (unlikely(ref < (BYTE *const) dest))
+ goto _output_error;
+
+ /* get matchlength */
+ length = token & ML_MASK;
+ if (length == ML_MASK) {
+ for (; *ip == 255; length += 255)
+ ip++;
+ length += *ip++;
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op-ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE - 4);
+ if (cpy > (oend - COPYLENGTH)) {
+
+ /* Error: request to write beyond destination buffer */
+ if (cpy > oend)
+ goto _output_error;
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *)ip) - source);
+
+ /* write overflow error detected */
+_output_error:
+ return (int) (-(((char *)ip) - source));
+}
+
+static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
+ int isize, size_t maxoutputsize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *const iend = ip + isize;
+ const BYTE *ref;
+
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + maxoutputsize;
+ BYTE *cpy;
+
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ /* Main Loop */
+ while (ip < iend) {
+
+ unsigned token;
+ size_t length;
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ int s = 255;
+ while ((ip < iend) && (s == 255)) {
+ s = *ip++;
+ length += s;
+ }
+ }
+ /* copy literals */
+ cpy = op + length;
+ if ((cpy > oend - COPYLENGTH) ||
+ (ip + length > iend - COPYLENGTH)) {
+
+ if (cpy > oend)
+ goto _output_error;/* writes beyond buffer */
+
+ if (ip + length != iend)
+ goto _output_error;/*
+ * Error: LZ4 format requires
+ * to consume all input
+ * at this stage
+ */
+ memcpy(op, ip, length);
+ op += length;
+ break;/* Necessarily EOF, due to parsing restrictions */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+ if (ref < (BYTE * const) dest)
+ goto _output_error;
+ /*
+ * Error : offset creates reference
+ * outside of destination buffer
+ */
+
+ /* get matchlength */
+ length = (token & ML_MASK);
+ if (length == ML_MASK) {
+ while (ip < iend) {
+ int s = *ip++;
+ length += s;
+ if (s == 255)
+ continue;
+ break;
+ }
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op - ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE-4);
+ if (cpy > oend - COPYLENGTH) {
+ if (cpy > oend)
+ goto _output_error; /* write outside of buf */
+
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *) op) - dest);
+
+ /* write overflow error detected */
+_output_error:
+ return (int) (-(((char *) ip) - source));
+}
+
+int lz4_decompress(const unsigned char *src, size_t *src_len,
+ unsigned char *dest, size_t actual_dest_len)
+{
+ int ret = -1;
+ int input_len = 0;
+
+ input_len = lz4_uncompress(src, dest, actual_dest_len);
+ if (input_len < 0)
+ goto exit_0;
+ *src_len = input_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL_GPL(lz4_decompress);
+#endif
+
+int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
+ unsigned char *dest, size_t *dest_len)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len,
+ *dest_len);
+ if (out_len < 0)
+ goto exit_0;
+ *dest_len = out_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL_GPL(lz4_decompress_unknownoutputsize);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 Decompressor");
+#endif
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
new file mode 100644
index 0000000..abcecdc
--- /dev/null
+++ b/lib/lz4/lz4defs.h
@@ -0,0 +1,156 @@
+/*
+ * lz4defs.h -- architecture specific defines
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Detects 64 bits mode
+ */
+#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \
+ || defined(__ppc64__) || defined(__LP64__))
+#define LZ4_ARCH64 1
+#else
+#define LZ4_ARCH64 0
+#endif
+
+/*
+ * Architecture-specific macros
+ */
+#define BYTE u8
+typedef struct _U16_S { u16 v; } U16_S;
+typedef struct _U32_S { u32 v; } U32_S;
+typedef struct _U64_S { u64 v; } U64_S;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \
+ || defined(CONFIG_ARM) && __LINUX_ARM_ARCH__ >= 6 \
+ && defined(ARM_EFFICIENT_UNALIGNED_ACCESS)
+
+#define A16(x) (((U16_S *)(x))->v)
+#define A32(x) (((U32_S *)(x))->v)
+#define A64(x) (((U64_S *)(x))->v)
+
+#define PUT4(s, d) (A32(d) = A32(s))
+#define PUT8(s, d) (A64(d) = A64(s))
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ A16(p) = v; \
+ p += 2; \
+ } while (0)
+#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
+
+#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v))
+#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v))
+#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v))
+
+#define PUT4(s, d) \
+ put_unaligned(get_unaligned((const u32 *) s), (u32 *) d)
+#define PUT8(s, d) \
+ put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
+
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ put_unaligned(v, (u16 *)(p)); \
+ p += 2; \
+ } while (0)
+#endif
+
+#define COPYLENGTH 8
+#define ML_BITS 4
+#define ML_MASK ((1U << ML_BITS) - 1)
+#define RUN_BITS (8 - ML_BITS)
+#define RUN_MASK ((1U << RUN_BITS) - 1)
+#define MEMORY_USAGE 14
+#define MINMATCH 4
+#define SKIPSTRENGTH 6
+#define LASTLITERALS 5
+#define MFLIMIT (COPYLENGTH + MINMATCH)
+#define MINLENGTH (MFLIMIT + 1)
+#define MAXD_LOG 16
+#define MAXD (1 << MAXD_LOG)
+#define MAXD_MASK (u32)(MAXD - 1)
+#define MAX_DISTANCE (MAXD - 1)
+#define HASH_LOG (MAXD_LOG - 1)
+#define HASHTABLESIZE (1 << HASH_LOG)
+#define MAX_NB_ATTEMPTS 256
+#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
+#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT - 1))
+#define HASHLOG64K ((MEMORY_USAGE - 2) + 1)
+#define HASH64KTABLESIZE (1U << HASHLOG64K)
+#define LZ4_HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - (MEMORY_USAGE-2)))
+#define LZ4_HASH64K_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASHLOG64K))
+#define HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASH_LOG))
+
+#if LZ4_ARCH64/* 64-bit */
+#define STEPSIZE 8
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT8(s, d); \
+ d += 8; \
+ s += 8; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) LZ4_COPYSTEP(s, d)
+
+#define LZ4_SECURECOPY(s, d, e) \
+ do { \
+ if (d < e) { \
+ LZ4_WILDCOPY(s, d, e); \
+ } \
+ } while (0)
+#define HTYPE u32
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3)
+#endif
+
+#else /* 32-bit */
+#define STEPSIZE 4
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT4(s, d); \
+ d += 4; \
+ s += 4; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) \
+ do { \
+ LZ4_COPYSTEP(s, d); \
+ LZ4_COPYSTEP(s, d); \
+ } while (0)
+
+#define LZ4_SECURECOPY LZ4_WILDCOPY
+#define HTYPE const u8*
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3)
+#endif
+
+#endif
+
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
+ (d = s - get_unaligned_le16(p))
+
+#define LZ4_WILDCOPY(s, d, e) \
+ do { \
+ LZ4_COPYPACKET(s, d); \
+ } while (d < e)
+
+#define LZ4_BLINDCOPY(s, d, l) \
+ do { \
+ u8 *e = (d) + l; \
+ LZ4_WILDCOPY(s, d, e); \
+ d = e; \
+ } while (0)
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
new file mode 100644
index 0000000..eb1a74f
--- /dev/null
+++ b/lib/lz4/lz4hc_compress.c
@@ -0,0 +1,539 @@
+/*
+ * LZ4 HC - High Compression Mode of LZ4
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+struct lz4hc_data {
+ const u8 *base;
+ HTYPE hashtable[HASHTABLESIZE];
+ u16 chaintable[MAXD];
+ const u8 *nexttoupdate;
+} __attribute__((__packed__));
+
+static inline int lz4hc_init(struct lz4hc_data *hc4, const u8 *base)
+{
+ memset((void *)hc4->hashtable, 0, sizeof(hc4->hashtable));
+ memset(hc4->chaintable, 0xFF, sizeof(hc4->chaintable));
+
+#if LZ4_ARCH64
+ hc4->nexttoupdate = base + 1;
+#else
+ hc4->nexttoupdate = base;
+#endif
+ hc4->base = base;
+ return 1;
+}
+
+/* Update chains up to ip (excluded) */
+static inline void lz4hc_insert(struct lz4hc_data *hc4, const u8 *ip)
+{
+ u16 *chaintable = hc4->chaintable;
+ HTYPE *hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+
+ while (hc4->nexttoupdate < ip) {
+ const u8 *p = hc4->nexttoupdate;
+ size_t delta = p - (hashtable[HASH_VALUE(p)] + base);
+ if (delta > MAX_DISTANCE)
+ delta = MAX_DISTANCE;
+ chaintable[(size_t)(p) & MAXD_MASK] = (u16)delta;
+ hashtable[HASH_VALUE(p)] = (p) - base;
+ hc4->nexttoupdate++;
+ }
+}
+
+static inline size_t lz4hc_commonlength(const u8 *p1, const u8 *p2,
+ const u8 *const matchlimit)
+{
+ const u8 *p1t = p1;
+
+ while (p1t < matchlimit - (STEPSIZE - 1)) {
+#if LZ4_ARCH64
+ u64 diff = A64(p2) ^ A64(p1t);
+#else
+ u32 diff = A32(p2) ^ A32(p1t);
+#endif
+ if (!diff) {
+ p1t += STEPSIZE;
+ p2 += STEPSIZE;
+ continue;
+ }
+ p1t += LZ4_NBCOMMONBYTES(diff);
+ return p1t - p1;
+ }
+#if LZ4_ARCH64
+ if ((p1t < (matchlimit-3)) && (A32(p2) == A32(p1t))) {
+ p1t += 4;
+ p2 += 4;
+ }
+#endif
+
+ if ((p1t < (matchlimit - 1)) && (A16(p2) == A16(p1t))) {
+ p1t += 2;
+ p2 += 2;
+ }
+ if ((p1t < matchlimit) && (*p2 == *p1t))
+ p1t++;
+ return p1t - p1;
+}
+
+static inline int lz4hc_insertandfindbestmatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *const matchlimit, const u8 **matchpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+ const u8 *ref;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ int nbattempts = MAX_NB_ATTEMPTS;
+ size_t repl = 0, ml = 0;
+ u16 delta;
+
+ /* HC4 match finder */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ /* potential repetition */
+ if (ref >= ip-4) {
+ /* confirmed */
+ if (A32(ref) == A32(ip)) {
+ delta = (u16)(ip-ref);
+ repl = ml = lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ *matchpos = ref;
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ while ((ref >= ip - MAX_DISTANCE) && nbattempts) {
+ nbattempts--;
+ if (*(ref + ml) == *(ip + ml)) {
+ if (A32(ref) == A32(ip)) {
+ size_t mlt =
+ lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ if (mlt > ml) {
+ ml = mlt;
+ *matchpos = ref;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ /* Complete table */
+ if (repl) {
+ const BYTE *ptr = ip;
+ const BYTE *end;
+ end = ip + repl - (MINMATCH-1);
+ /* Pre-Load */
+ while (ptr < end - delta) {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ ptr++;
+ }
+ do {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ /* Head of chain */
+ hashtable[HASH_VALUE(ptr)] = (ptr) - base;
+ ptr++;
+ } while (ptr < end);
+ hc4->nexttoupdate = end;
+ }
+
+ return (int)ml;
+}
+
+static inline int lz4hc_insertandgetwidermatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *startlimit, const u8 *matchlimit, int longest,
+ const u8 **matchpos, const u8 **startpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ const u8 *ref;
+ int nbattempts = MAX_NB_ATTEMPTS;
+ int delta = (int)(ip - startlimit);
+
+ /* First Match */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ while ((ref >= ip - MAX_DISTANCE) && (ref >= hc4->base)
+ && (nbattempts)) {
+ nbattempts--;
+ if (*(startlimit + longest) == *(ref - delta + longest)) {
+ if (A32(ref) == A32(ip)) {
+ const u8 *reft = ref + MINMATCH;
+ const u8 *ipt = ip + MINMATCH;
+ const u8 *startt = ip;
+
+ while (ipt < matchlimit-(STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(reft) ^ A64(ipt);
+ #else
+ u32 diff = A32(reft) ^ A32(ipt);
+ #endif
+
+ if (!diff) {
+ ipt += STEPSIZE;
+ reft += STEPSIZE;
+ continue;
+ }
+ ipt += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ipt < (matchlimit - 3))
+ && (A32(reft) == A32(ipt))) {
+ ipt += 4;
+ reft += 4;
+ }
+ ipt += 2;
+ #endif
+ if ((ipt < (matchlimit - 1))
+ && (A16(reft) == A16(ipt))) {
+ reft += 2;
+ }
+ if ((ipt < matchlimit) && (*reft == *ipt))
+ ipt++;
+_endcount:
+ reft = ref;
+
+ while ((startt > startlimit)
+ && (reft > hc4->base)
+ && (startt[-1] == reft[-1])) {
+ startt--;
+ reft--;
+ }
+
+ if ((ipt - startt) > longest) {
+ longest = (int)(ipt - startt);
+ *matchpos = reft;
+ *startpos = startt;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+ return longest;
+}
+
+static inline int lz4_encodesequence(const u8 **ip, u8 **op, const u8 **anchor,
+ int ml, const u8 *ref)
+{
+ int length, len;
+ u8 *token;
+
+ /* Encode Literal length */
+ length = (int)(*ip - *anchor);
+ token = (*op)++;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *(*op)++ = 255;
+ *(*op)++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(*anchor, *op, length);
+
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(*op, (u16)(*ip - ref));
+
+ /* Encode MatchLength */
+ len = (int)(ml - MINMATCH);
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *(*op)++ = 255;
+ *(*op)++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *(*op)++ = 255;
+ }
+ *(*op)++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Prepare next loop */
+ *ip += ml;
+ *anchor = *ip;
+
+ return 0;
+}
+
+static int lz4_compresshcctx(struct lz4hc_data *ctx,
+ const char *source,
+ char *dest,
+ int isize)
+{
+ const u8 *ip = (const u8 *)source;
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ const u8 *const matchlimit = (iend - LASTLITERALS);
+
+ u8 *op = (u8 *)dest;
+
+ int ml, ml2, ml3, ml0;
+ const u8 *ref = NULL;
+ const u8 *start2 = NULL;
+ const u8 *ref2 = NULL;
+ const u8 *start3 = NULL;
+ const u8 *ref3 = NULL;
+ const u8 *start0;
+ const u8 *ref0;
+ int lastrun;
+
+ ip++;
+
+ /* Main Loop */
+ while (ip < mflimit) {
+ ml = lz4hc_insertandfindbestmatch(ctx, ip, matchlimit, (&ref));
+ if (!ml) {
+ ip++;
+ continue;
+ }
+
+ /* saved, in case we would skip too much */
+ start0 = ip;
+ ref0 = ref;
+ ml0 = ml;
+_search2:
+ if (ip+ml < mflimit)
+ ml2 = lz4hc_insertandgetwidermatch(ctx, ip + ml - 2,
+ ip + 1, matchlimit, ml, &ref2, &start2);
+ else
+ ml2 = ml;
+ /* No better match */
+ if (ml2 == ml) {
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ continue;
+ }
+
+ if (start0 < ip) {
+ /* empirical */
+ if (start2 < ip + ml0) {
+ ip = start0;
+ ref = ref0;
+ ml = ml0;
+ }
+ }
+ /*
+ * Here, start0==ip
+ * First Match too small : removed
+ */
+ if ((start2 - ip) < 3) {
+ ml = ml2;
+ ip = start2;
+ ref = ref2;
+ goto _search2;
+ }
+
+_search3:
+ /*
+ * Currently we have :
+ * ml2 > ml1, and
+ * ip1+3 <= ip2 (usually < ip1+ml1)
+ */
+ if ((start2 - ip) < OPTIMAL_ML) {
+ int correction;
+ int new_ml = ml;
+ if (new_ml > OPTIMAL_ML)
+ new_ml = OPTIMAL_ML;
+ if (ip + new_ml > start2 + ml2 - MINMATCH)
+ new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
+ correction = new_ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ }
+ /*
+ * Now, we have start2 = ip+new_ml,
+ * with new_ml=min(ml, OPTIMAL_ML=18)
+ */
+ if (start2 + ml2 < mflimit)
+ ml3 = lz4hc_insertandgetwidermatch(ctx,
+ start2 + ml2 - 3, start2, matchlimit,
+ ml2, &ref3, &start3);
+ else
+ ml3 = ml2;
+
+ /* No better match : 2 sequences to encode */
+ if (ml3 == ml2) {
+ /* ip & ref are known; Now for ml */
+ if (start2 < ip+ml)
+ ml = (int)(start2 - ip);
+
+ /* Now, encode 2 sequences */
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start2;
+ lz4_encodesequence(&ip, &op, &anchor, ml2, ref2);
+ continue;
+ }
+
+ /* Not enough space for match 2 : remove it */
+ if (start3 < ip + ml + 3) {
+ /*
+ * can write Seq1 immediately ==> Seq2 is removed,
+ * so Seq3 becomes Seq1
+ */
+ if (start3 >= (ip + ml)) {
+ if (start2 < ip + ml) {
+ int correction =
+ (int)(ip + ml - start2);
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ if (ml2 < MINMATCH) {
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ }
+ }
+
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start3;
+ ref = ref3;
+ ml = ml3;
+
+ start0 = start2;
+ ref0 = ref2;
+ ml0 = ml2;
+ goto _search2;
+ }
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ goto _search3;
+ }
+
+ /*
+ * OK, now we have 3 ascending matches; let's write at least
+ * the first one ip & ref are known; Now for ml
+ */
+ if (start2 < ip + ml) {
+ if ((start2 - ip) < (int)ML_MASK) {
+ int correction;
+ if (ml > OPTIMAL_ML)
+ ml = OPTIMAL_ML;
+ if (ip + ml > start2 + ml2 - MINMATCH)
+ ml = (int)(start2 - ip) + ml2
+ - MINMATCH;
+ correction = ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ } else
+ ml = (int)(start2 - ip);
+ }
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+
+ ip = start2;
+ ref = ref2;
+ ml = ml2;
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+
+ goto _search3;
+ }
+
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8) lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int) (((char *)op) - dest);
+}
+
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ struct lz4hc_data *hc4 = (struct lz4hc_data *)wrkmem;
+ lz4hc_init(hc4, (const u8 *)src);
+ out_len = lz4_compresshcctx((struct lz4hc_data *)hc4, (const u8 *)src,
+ (char *)dst, (int)src_len);
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+ return 0;
+
+exit:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(lz4hc_compress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4HC compressor");
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d..a1c387f 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -25,6 +25,16 @@
#define NEED_OP(x) if (!HAVE_OP(x)) goto output_overrun
#define TEST_LB(m_pos) if ((m_pos) < out) goto lookbehind_overrun
+/* This MAX_255_COUNT is the maximum number of times we can add 255 to a base
+ * count without overflowing an integer. The multiply will overflow when
+ * multiplying 255 by more than MAXINT/255. The sum will overflow earlier
+ * depending on the base count. Since the base count is taken from a u8
+ * and a few bits, it is safe to assume that it will always be lower than
+ * or equal to 2*255, thus we can always prevent any overflow by accepting
+ * two less 255 steps. See Documentation/lzo.txt for more information.
+ */
+#define MAX_255_COUNT ((((size_t)~0) / 255) - 2)
+
int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
unsigned char *out, size_t *out_len)
{
@@ -55,12 +65,19 @@
if (t < 16) {
if (likely(state == 0)) {
if (unlikely(t == 0)) {
+ size_t offset;
+ const unsigned char *ip_last = ip;
+
while (unlikely(*ip == 0)) {
- t += 255;
ip++;
NEED_IP(1);
}
- t += 15 + *ip++;
+ offset = ip - ip_last;
+ if (unlikely(offset > MAX_255_COUNT))
+ return LZO_E_ERROR;
+
+ offset = (offset << 8) - offset;
+ t += offset + 15 + *ip++;
}
t += 3;
copy_literal_run:
@@ -116,12 +133,19 @@
} else if (t >= 32) {
t = (t & 31) + (3 - 1);
if (unlikely(t == 2)) {
+ size_t offset;
+ const unsigned char *ip_last = ip;
+
while (unlikely(*ip == 0)) {
- t += 255;
ip++;
NEED_IP(1);
}
- t += 31 + *ip++;
+ offset = ip - ip_last;
+ if (unlikely(offset > MAX_255_COUNT))
+ return LZO_E_ERROR;
+
+ offset = (offset << 8) - offset;
+ t += offset + 31 + *ip++;
NEED_IP(2);
}
m_pos = op - 1;
@@ -134,12 +158,19 @@
m_pos -= (t & 8) << 11;
t = (t & 7) + (3 - 1);
if (unlikely(t == 2)) {
+ size_t offset;
+ const unsigned char *ip_last = ip;
+
while (unlikely(*ip == 0)) {
- t += 255;
ip++;
NEED_IP(1);
}
- t += 7 + *ip++;
+ offset = ip - ip_last;
+ if (unlikely(offset > MAX_255_COUNT))
+ return LZO_E_ERROR;
+
+ offset = (offset << 8) - offset;
+ t += offset + 7 + *ip++;
NEED_IP(2);
}
next = get_unaligned_le16(ip);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 18eca78..10ad042d 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -201,8 +201,8 @@
}
if (unlikely(rem > 0))
- printk(KERN_WARNING "netlink: %d bytes leftover after parsing "
- "attributes.\n", rem);
+ pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+ rem, current->comm);
err = 0;
errout:
@@ -303,9 +303,15 @@
*/
int nla_strcmp(const struct nlattr *nla, const char *str)
{
- int len = strlen(str) + 1;
- int d = nla_len(nla) - len;
+ int len = strlen(str);
+ char *buf = nla_data(nla);
+ int attrlen = nla_len(nla);
+ int d;
+ if (attrlen > 0 && buf[attrlen - 1] == '\0')
+ attrlen--;
+
+ d = attrlen - len;
if (d == 0)
d = memcmp(nla_data(nla), str, len);
diff --git a/lib/random32.c b/lib/random32.c
index 52280d5..01e8890 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -141,7 +141,7 @@
*/
for_each_possible_cpu (i) {
struct rnd_state *state = &per_cpu(net_rand_state, i);
- state->s1 = __seed(state->s1 ^ entropy, 1);
+ state->s1 = __seed(state->s1 ^ entropy, 2);
}
}
EXPORT_SYMBOL(prandom_seed);
@@ -158,9 +158,9 @@
struct rnd_state *state = &per_cpu(net_rand_state,i);
#define LCG(x) ((x) * 69069) /* super-duper LCG */
- state->s1 = __seed(LCG(i + jiffies), 1);
- state->s2 = __seed(LCG(state->s1), 7);
- state->s3 = __seed(LCG(state->s2), 15);
+ state->s1 = __seed(LCG(i + jiffies), 2);
+ state->s2 = __seed(LCG(state->s1), 8);
+ state->s3 = __seed(LCG(state->s2), 16);
/* "warm it up" */
prandom_u32_state(state);
@@ -187,9 +187,9 @@
u32 seeds[3];
get_random_bytes(&seeds, sizeof(seeds));
- state->s1 = __seed(seeds[0], 1);
- state->s2 = __seed(seeds[1], 7);
- state->s3 = __seed(seeds[2], 15);
+ state->s1 = __seed(seeds[0], 2);
+ state->s2 = __seed(seeds[1], 8);
+ state->s3 = __seed(seeds[2], 16);
/* mix it in */
prandom_u32_state(state);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index a1cf8ca..3e7df38 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -529,7 +529,8 @@
miter->__offset += miter->consumed;
miter->__remaining -= miter->consumed;
- if (miter->__flags & SG_MITER_TO_SG)
+ if ((miter->__flags & SG_MITER_TO_SG) &&
+ !PageSlab(miter->page))
flush_kernel_dcache_page(miter->page);
if (miter->__flags & SG_MITER_ATOMIC) {
diff --git a/lib/string.c b/lib/string.c
index e5878de..cb9ea21 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -586,6 +586,22 @@
EXPORT_SYMBOL(memset);
#endif
+/**
+ * memzero_explicit - Fill a region of memory (e.g. sensitive
+ * keying data) with 0s.
+ * @s: Pointer to the start of the area.
+ * @count: The size of the area.
+ *
+ * memzero_explicit() doesn't need an arch-specific version as
+ * it just invokes the one of memset() implicitly.
+ */
+void memzero_explicit(void *s, size_t count)
+{
+ memset(s, 0, count);
+ barrier();
+}
+EXPORT_SYMBOL(memzero_explicit);
+
#ifndef __HAVE_ARCH_MEMCPY
/**
* memcpy - Copy one area of memory to another
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index e149c64..620fae4 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -26,6 +26,7 @@
#include <linux/math64.h>
#include <linux/uaccess.h>
#include <linux/ioport.h>
+#include <linux/cred.h>
#include <net/addrconf.h>
#include <asm/page.h> /* for PAGE_SIZE */
@@ -1118,11 +1119,37 @@
spec.field_width = default_width;
return string(buf, end, "pK-error", spec);
}
- if (!((kptr_restrict == 0) ||
- (kptr_restrict == 1 &&
- has_capability_noaudit(current, CAP_SYSLOG))))
+
+ switch (kptr_restrict) {
+ case 0:
+ /* Always print %pK values */
+ break;
+ case 1: {
+ /*
+ * Only print the real pointer value if the current
+ * process has CAP_SYSLOG and is running with the
+ * same credentials it started with. This is because
+ * access to files is checked at open() time, but %pK
+ * checks permission at read() time. We don't want to
+ * leak pointer values if a binary opens a file using
+ * %pK and then elevates privileges before reading it.
+ */
+ const struct cred *cred = current_cred();
+
+ if (!has_capability_noaudit(current, CAP_SYSLOG) ||
+ !uid_eq(cred->euid, cred->uid) ||
+ !gid_eq(cred->egid, cred->gid))
+ ptr = NULL;
+ break;
+ }
+ case 2:
+ default:
+ /* Always print 0's for %pK */
ptr = NULL;
+ break;
+ }
break;
+
case 'N':
switch (fmt[1]) {
case 'F':
diff --git a/linaro/configs/android.conf b/linaro/configs/android.conf
new file mode 100644
index 0000000..e4fd1ad
--- /dev/null
+++ b/linaro/configs/android.conf
@@ -0,0 +1,42 @@
+CONFIG_IPV6=y
+# CONFIG_IPV6_SIT is not set
+CONFIG_PANIC_TIMEOUT=0
+CONFIG_HAS_WAKELOCK=y
+CONFIG_WAKELOCK=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DM_CRYPT=y
+CONFIG_POWER_SUPPLY=y
+CONFIG_ANDROID_PARANOID_NETWORK=y
+CONFIG_NET_ACTIVITY_STATS=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_INPUT_GPIO=y
+CONFIG_USB_G_ANDROID=y
+CONFIG_SWITCH=y
+CONFIG_STAGING=y
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ASHMEM=y
+CONFIG_ANDROID_LOGGER=y
+CONFIG_ANDROID_TIMED_OUTPUT=y
+CONFIG_ANDROID_TIMED_GPIO=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ANDROID_INTF_ALARM_DEV=y
+CONFIG_CRYPTO_TWOFISH=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_FUSE_FS=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE=y
+CONFIG_ION=y
+CONFIG_SYNC=y
+CONFIG_SW_SYNC=y
+CONFIG_SW_SYNC_USER=y
+CONFIG_ION_TEST=y
+CONFIG_ION_DUMMY=y
+CONFIG_ADF=y
+CONFIG_ADF_FBDEV=y
+CONFIG_ADF_MEMBLOCK=y
+CONFIG_DMA_SHARED_BUFFER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/arndale.conf b/linaro/configs/arndale.conf
new file mode 100644
index 0000000..109052f
--- /dev/null
+++ b/linaro/configs/arndale.conf
@@ -0,0 +1,66 @@
+CONFIG_KALLSYMS_ALL=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_ARCH_EXYNOS=y
+CONFIG_S3C_LOWLEVEL_UART_PORT=2
+CONFIG_ARCH_EXYNOS5=y
+# CONFIG_EXYNOS_ATAGS is not set
+CONFIG_MACH_EXYNOS4_DT=y
+CONFIG_VMSPLIT_2G=y
+CONFIG_NR_CPUS=2
+CONFIG_HIGHMEM=y
+# CONFIG_COMPACTION is not set
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
+CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init= mem=256M"
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_EXYNOS=y
+CONFIG_AX88796=y
+CONFIG_AX88796_93CX6=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_SAMSUNG=y
+CONFIG_SERIAL_SAMSUNG_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C=y
+CONFIG_I2C_S3C2410=y
+CONFIG_THERMAL=y
+CONFIG_CPU_THERMAL=y
+CONFIG_EXYNOS_THERMAL=y
+CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_S5M8767=y
+CONFIG_DRM=y
+CONFIG_DRM_LOAD_EDID_FIRMWARE=y
+CONFIG_DRM_EXYNOS=y
+CONFIG_DRM_EXYNOS_DMABUF=y
+CONFIG_DRM_EXYNOS_HDMI=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_MMC_DW=y
+CONFIG_MMC_DW_IDMAC=y
+CONFIG_MMC_DW_EXYNOS=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_S3C=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_INFO=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_DEBUG_USER=y
+CONFIG_TUN=y
diff --git a/linaro/configs/big-LITTLE-IKS.conf b/linaro/configs/big-LITTLE-IKS.conf
new file mode 100644
index 0000000..b067fde
--- /dev/null
+++ b/linaro/configs/big-LITTLE-IKS.conf
@@ -0,0 +1,5 @@
+CONFIG_BIG_LITTLE=y
+CONFIG_BL_SWITCHER=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
diff --git a/linaro/configs/big-LITTLE-MP.conf b/linaro/configs/big-LITTLE-MP.conf
new file mode 100644
index 0000000..ced3cf9
--- /dev/null
+++ b/linaro/configs/big-LITTLE-MP.conf
@@ -0,0 +1,12 @@
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+CONFIG_NO_HZ=y
+CONFIG_SCHED_MC=y
+CONFIG_DISABLE_CPU_SCHED_DOMAIN_BALANCE=y
+CONFIG_SCHED_HMP=y
+CONFIG_HMP_FAST_CPU_MASK=""
+CONFIG_HMP_SLOW_CPU_MASK=""
+CONFIG_HMP_VARIABLE_SCALE=y
+CONFIG_HMP_FREQUENCY_INVARIANT_SCALE=y
+CONFIG_SCHED_HMP_LITTLE_PACKING=y
diff --git a/linaro/configs/bigendian.conf b/linaro/configs/bigendian.conf
new file mode 100644
index 0000000..6a10202
--- /dev/null
+++ b/linaro/configs/bigendian.conf
@@ -0,0 +1,4 @@
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_CPU_ENDIAN_BE8=y
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_MMC_DW_IDMAC is not set
diff --git a/linaro/configs/booting-test.conf b/linaro/configs/booting-test.conf
new file mode 100644
index 0000000..7592b21
--- /dev/null
+++ b/linaro/configs/booting-test.conf
@@ -0,0 +1,66 @@
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_HEADERS_CHECK=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_SELFTEST=y
+CONFIG_DEBUG_OBJECTS_TIMERS=y
+CONFIG_DEBUG_OBJECTS_WORK=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
+CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1
+CONFIG_DEBUG_KMEMLEAK=y
+CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=400
+CONFIG_DEBUG_KMEMLEAK_TEST=m
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_PI_LIST=y
+CONFIG_RT_MUTEX_TESTER=y
+CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_DEBUG_KOBJECT=y
+CONFIG_DEBUG_HIGHMEM=y
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DEBUG_VM=y
+CONFIG_DEBUG_VM_RB=y
+CONFIG_DEBUG_WRITECOUNT=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_LIST=y
+CONFIG_TEST_LIST_SORT=y
+CONFIG_DEBUG_SG=y
+CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_DEBUG_CREDENTIALS=y
+CONFIG_DEBUG_BLOCK_EXT_DEVT=y
+CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
+CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_TRACER_MAX_TRACE=y
+CONFIG_GENERIC_TRACER=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FUNCTION_GRAPH_TRACER=y
+CONFIG_IRQSOFF_TRACER=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_FTRACE_MCOUNT_RECORD=y
+CONFIG_FTRACE_SELFTEST=y
+CONFIG_FTRACE_STARTUP_TEST=y
+CONFIG_EVENT_TRACE_TEST_SYSCALLS=y
+CONFIG_RING_BUFFER_BENCHMARK=y
+CONFIG_RING_BUFFER_STARTUP_TEST=y
+CONFIG_DYNAMIC_DEBUG=y
+CONFIG_DMA_API_DEBUG=y
+CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_STRING_HELPERS=y
+CONFIG_TEST_KSTRTOX=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_OLD_MCOUNT=y
+CONFIG_DEBUG_USER=y
+
diff --git a/linaro/configs/debug.conf b/linaro/configs/debug.conf
new file mode 100644
index 0000000..3698056
--- /dev/null
+++ b/linaro/configs/debug.conf
@@ -0,0 +1 @@
+CONFIG_PROVE_LOCKING=y
diff --git a/linaro/configs/distribution.conf b/linaro/configs/distribution.conf
new file mode 100644
index 0000000..729b9b8
--- /dev/null
+++ b/linaro/configs/distribution.conf
@@ -0,0 +1,49 @@
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_CGROUPS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=32768
+CONFIG_SECCOMP=y
+CONFIG_CC_STACKPROTECTOR=y
+CONFIG_SYN_COOKIES=y
+CONFIG_IPV6=y
+CONFIG_NETLABEL=y
+CONFIG_BRIDGE_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NETFILTER_XT_CONNMARK=m
+CONFIG_NETFILTER_XT_MARK=m
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_NAT_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_NAT_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_MARK_T=m
+CONFIG_BRIDGE=m
+CONFIG_TUN=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=65536
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
+# CONFIG_DEVKMEM is not set
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_SECURITY=y
+CONFIG_LSM_MMAP_MIN_ADDR=0
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SMACK=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_DEFAULT_SECURITY_APPARMOR=y
+CONFIG_HUGETLBFS=y
+CONFIG_HUGETLB_PAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y
diff --git a/linaro/configs/highbank.conf b/linaro/configs/highbank.conf
new file mode 100644
index 0000000..bf0f3c1
--- /dev/null
+++ b/linaro/configs/highbank.conf
@@ -0,0 +1,40 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_ARCH_HIGHBANK=y
+CONFIG_ARM_ERRATA_754322=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_AEABI=y
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_CPU_IDLE=y
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_NET=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_SATA_HIGHBANK=y
+CONFIG_NETDEVICES=y
+CONFIG_NET_CALXEDA_XGMAC=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_IPMI_HANDLER=y
+CONFIG_IPMI_SI=y
+CONFIG_I2C=y
+CONFIG_I2C_DESIGNWARE_PLATFORM=y
+CONFIG_SPI=y
+CONFIG_SPI_PL022=y
+CONFIG_GPIO_PL061=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_HIGHBANK_MC=y
+CONFIG_EDAC_HIGHBANK_L2=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_DMADEVICES=y
+CONFIG_PL330_DMA=y
diff --git a/linaro/configs/kvm-guest.conf b/linaro/configs/kvm-guest.conf
new file mode 100644
index 0000000..00e84a3
--- /dev/null
+++ b/linaro/configs/kvm-guest.conf
@@ -0,0 +1,11 @@
+CONFIG_BALLOON_COMPACTION=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_NET=y
+CONFIG_HVC_DRIVER=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_VIRTUALIZATION=y
+# CONFIG_THUMB2_KERNEL is not set
diff --git a/linaro/configs/kvm-host.conf b/linaro/configs/kvm-host.conf
new file mode 100644
index 0000000..21a40e0
--- /dev/null
+++ b/linaro/configs/kvm-host.conf
@@ -0,0 +1,11 @@
+CONFIG_VIRTUALIZATION=y
+CONFIG_ARM_LPAE=y
+CONFIG_ARM_VIRT_EXT=y
+CONFIG_HAVE_KVM_IRQCHIP=y
+CONFIG_KVM_ARM_HOST=y
+CONFIG_KVM_ARM_MAX_VCPUS=4
+CONFIG_KVM_ARM_TIMER=y
+CONFIG_KVM_ARM_VGIC=y
+CONFIG_KVM_MMIO=y
+CONFIG_KVM=y
+CONFIG_BLK_DEV_NBD=m
diff --git a/linaro/configs/linaro-base.conf b/linaro/configs/linaro-base.conf
new file mode 100644
index 0000000..c2a5143
--- /dev/null
+++ b/linaro/configs/linaro-base.conf
@@ -0,0 +1,119 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EMBEDDED=y
+CONFIG_HOTPLUG=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_SMP=y
+CONFIG_SCHED_MC=y
+CONFIG_SCHED_SMT=y
+CONFIG_THUMB2_KERNEL=y
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
+CONFIG_CPU_IDLE=y
+CONFIG_BINFMT_MISC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+# CONFIG_INET_LRO is not set
+CONFIG_NETFILTER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_OOPS=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_NAND=y
+CONFIG_NETDEVICES=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
+CONFIG_BTRFS_FS=y
+CONFIG_QUOTA=y
+CONFIG_QFMT_V2=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_ECRYPT_FS=y
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_SUMMARY=y
+CONFIG_JFFS2_FS_XATTR=y
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+CONFIG_JFFS2_LZO=y
+CONFIG_JFFS2_RUBIN=y
+CONFIG_CRAMFS=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V2 is not set
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_PRINTK_TIME=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_KEYS=y
+CONFIG_CRYPTO_MICHAEL_MIC=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC_T10DIF=y
+CONFIG_CRC_ITU_T=y
+CONFIG_CRC7=y
+CONFIG_HW_PERF_EVENTS=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_JUMP_LABEL=y
+CONFIG_STRICT_DEVMEM=y
+CONFIG_KGDB=y
+CONFIG_KGDB_TESTS=y
+CONFIG_OF_IDLE_STATES=y
+CONFIG_FTRACE=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_MAILBOX=y
+CONFIG_AUDIT=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_LSM_MMAP_MIN_ADDR=4096
+CONFIG_SECURITY_SELINUX=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_DEBUG_INFO=y
+CONFIG_FANOTIFY=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_TORTURE_TEST_RUNNABLE=n
diff --git a/linaro/configs/omap4.conf b/linaro/configs/omap4.conf
new file mode 100644
index 0000000..50fb9d9
--- /dev/null
+++ b/linaro/configs/omap4.conf
@@ -0,0 +1,194 @@
+CONFIG_EXPERT=y
+CONFIG_KPROBES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_MODULE_SRCVERSION_ALL=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_GPIO_PCA953X=y
+CONFIG_OMAP_RESET_CLOCKS=y
+CONFIG_OMAP_MUX_DEBUG=y
+CONFIG_ARCH_OMAP2PLUS=y
+CONFIG_SOC_OMAP5=y
+# CONFIG_ARCH_OMAP2 is not set
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_ARM_THUMBEE=y
+CONFIG_ARM_ERRATA_411920=y
+CONFIG_NR_CPUS=2
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE="root=/dev/mmcblk0p2 rootwait console=ttyO2,115200"
+CONFIG_KEXEC=y
+CONFIG_PM_DEBUG=y
+CONFIG_CAN=m
+CONFIG_CAN_C_CAN=m
+CONFIG_CAN_C_CAN_PLATFORM=m
+CONFIG_BT=m
+CONFIG_BT_HCIUART=m
+CONFIG_BT_HCIUART_H4=y
+CONFIG_BT_HCIUART_BCSP=y
+CONFIG_BT_HCIUART_LL=y
+CONFIG_BT_HCIBCM203X=m
+CONFIG_BT_HCIBPA10X=m
+CONFIG_CFG80211=m
+CONFIG_MAC80211=m
+CONFIG_MAC80211_RC_PID=y
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+CONFIG_CMA=y
+CONFIG_MTD_NAND_OMAP2=y
+CONFIG_MTD_ONENAND=y
+CONFIG_MTD_ONENAND_VERIFY_WRITE=y
+CONFIG_MTD_ONENAND_OMAP2=y
+CONFIG_MTD_UBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM_SIZE=16384
+CONFIG_SENSORS_TSL2550=m
+CONFIG_SENSORS_LIS3_I2C=m
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_SCAN_ASYNC=y
+CONFIG_KS8851=y
+CONFIG_KS8851_MLL=y
+CONFIG_SMC91X=y
+CONFIG_SMSC911X=y
+CONFIG_TI_CPSW=y
+CONFIG_SMSC_PHY=y
+CONFIG_USB_USBNET=y
+CONFIG_USB_NET_SMSC95XX=y
+CONFIG_USB_ALI_M5632=y
+CONFIG_USB_AN2720=y
+CONFIG_USB_EPSON2888=y
+CONFIG_USB_KC2190=y
+CONFIG_LIBERTAS=m
+CONFIG_LIBERTAS_USB=m
+CONFIG_LIBERTAS_SDIO=m
+CONFIG_LIBERTAS_DEBUG=y
+CONFIG_INPUT_JOYDEV=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_GPIO=y
+CONFIG_KEYBOARD_MATRIX=m
+CONFIG_KEYBOARD_TWL4030=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
+CONFIG_INPUT_TWL4030_PWRBUTTON=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_OMAP=y
+CONFIG_SERIAL_OMAP_CONSOLE=y
+CONFIG_HW_RANDOM=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_SPI=y
+CONFIG_SPI_OMAP24XX=y
+CONFIG_PINCTRL_SINGLE=y
+CONFIG_DEBUG_GPIO=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_TWL4030=y
+CONFIG_W1=y
+CONFIG_SENSORS_LM75=m
+CONFIG_WATCHDOG=y
+CONFIG_OMAP_WATCHDOG=y
+CONFIG_TWL4030_WATCHDOG=y
+CONFIG_MFD_TPS65217=y
+CONFIG_MFD_TPS65910=y
+CONFIG_TWL6040_CORE=y
+CONFIG_REGULATOR_TPS65023=y
+CONFIG_REGULATOR_TPS6507X=y
+CONFIG_REGULATOR_TPS65217=y
+CONFIG_REGULATOR_TPS65910=y
+CONFIG_REGULATOR_TWL4030=y
+CONFIG_FB=y
+CONFIG_FIRMWARE_EDID=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_OMAP2_DSS=m
+CONFIG_OMAP2_DSS_RFBI=y
+CONFIG_OMAP2_DSS_SDI=y
+CONFIG_OMAP2_DSS_DSI=y
+CONFIG_FB_OMAP2=m
+CONFIG_PANEL_GENERIC_DPI=m
+CONFIG_PANEL_TFP410=m
+CONFIG_PANEL_SHARP_LS037V7DW01=m
+CONFIG_PANEL_NEC_NL8048HL11_01B=m
+CONFIG_PANEL_TAAL=m
+CONFIG_PANEL_TPO_TD043MTEA1=m
+CONFIG_PANEL_ACX565AKM=m
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+CONFIG_LCD_PLATFORM=y
+CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
+CONFIG_FONTS=y
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+CONFIG_SOUND=m
+CONFIG_SND=m
+CONFIG_SND_VERBOSE_PRINTK=y
+CONFIG_SND_DEBUG=y
+CONFIG_SND_USB_AUDIO=m
+CONFIG_SND_SOC=m
+CONFIG_SND_OMAP_SOC=m
+CONFIG_SND_OMAP_SOC_OMAP_TWL4030=m
+CONFIG_SND_OMAP_SOC_OMAP_ABE_TWL6040=m
+CONFIG_SND_OMAP_SOC_OMAP3_PANDORA=m
+CONFIG_USB=y
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_WDM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_TEST=y
+CONFIG_USB_PHY=y
+CONFIG_NOP_USB_XCEIV=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_GADGET_DEBUG=y
+CONFIG_USB_GADGET_DEBUG_FILES=y
+CONFIG_USB_GADGET_DEBUG_FS=y
+CONFIG_USB_ZERO=m
+CONFIG_MMC=y
+CONFIG_MMC_UNSAFE_RESUME=y
+CONFIG_SDIO_UART=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_MMC_OMAP=y
+CONFIG_MMC_OMAP_HS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=y
+CONFIG_LEDS_TRIGGER_ONESHOT=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_BACKLIGHT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_LEDS_TRIGGER_GPIO=y
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_TWL92330=y
+CONFIG_RTC_DRV_TWL4030=y
+CONFIG_RTC_DRV_OMAP=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_OMAP=y
+# CONFIG_EXT3_FS_XATTR is not set
+CONFIG_UBIFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
+CONFIG_DEBUG_INFO=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_LIBCRC32C=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/preempt-rt.conf b/linaro/configs/preempt-rt.conf
new file mode 100644
index 0000000..98e036d
--- /dev/null
+++ b/linaro/configs/preempt-rt.conf
@@ -0,0 +1,4 @@
+CONFIG_PREEMPT=y
+CONFIG_PREEMPT_RT_FULL=y
+CONFIG_SLUB=y
+# CONFIG_CPU_FREQ is not set
diff --git a/linaro/configs/ubuntu-minimal.conf b/linaro/configs/ubuntu-minimal.conf
new file mode 120000
index 0000000..794e82f
--- /dev/null
+++ b/linaro/configs/ubuntu-minimal.conf
@@ -0,0 +1 @@
+distribution.conf
\ No newline at end of file
diff --git a/linaro/configs/vexpress-tuning.conf b/linaro/configs/vexpress-tuning.conf
new file mode 100644
index 0000000..adea6cc
--- /dev/null
+++ b/linaro/configs/vexpress-tuning.conf
@@ -0,0 +1 @@
+# CONFIG_PROVE_LOCKING is not set
diff --git a/linaro/configs/vexpress.conf b/linaro/configs/vexpress.conf
new file mode 100644
index 0000000..73cae2b
--- /dev/null
+++ b/linaro/configs/vexpress.conf
@@ -0,0 +1,63 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_ARCH_VEXPRESS_CA9X4=y
+CONFIG_BIG_LITTLE=y
+CONFIG_ARCH_VEXPRESS_TC2=y
+CONFIG_ARCH_VEXPRESS_DCSCB=y
+CONFIG_ARM_VEXPRESS_BL_CPUFREQ=y
+CONFIG_PM_OPP=y
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_INTERACTIVE=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_ARM_PSCI=y
+CONFIG_HAVE_ARM_ARCH_TIMER=y
+CONFIG_NR_CPUS=8
+CONFIG_HIGHMEM=y
+CONFIG_HIGHPTE=y
+CONFIG_CMDLINE="console=ttyAMA0,38400n8 root=/dev/mmcblk0p2 rootwait mmci.fmax=4000000"
+CONFIG_VFP=y
+CONFIG_NEON=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_SMSC911X=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FB_ARMHDLCD=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_ARMAACI=y
+CONFIG_USB=y
+CONFIG_USB_ISP1760_HCD=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VEXPRESS_CONFIG=y
+CONFIG_SENSORS_VEXPRESS=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_VEXPRESS=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
+CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=y
+CONFIG_LEDS_TRIGGER_CPU=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
diff --git a/linaro/configs/vexpress64.conf b/linaro/configs/vexpress64.conf
new file mode 100644
index 0000000..c9b66a1
--- /dev/null
+++ b/linaro/configs/vexpress64.conf
@@ -0,0 +1,55 @@
+CONFIG_ARCH_VEXPRESS=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_CMDLINE="console=ttyAMA0"
+CONFIG_COMPAT=y
+CONFIG_SMC91X=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_SERIO_AMBAKMI=y
+CONFIG_SERIAL_AMBA_PL011=y
+CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+# CONFIG_SERIO_I8042 is not set
+CONFIG_FB=y
+CONFIG_FB_ARMCLCD=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_MMC=y
+CONFIG_MMC_ARMMMCI=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_PL031=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_CMA=y
+CONFIG_DMA_CMA=y
+CONFIG_COMMON_CLK_SCPI=y
+CONFIG_SMSC911X=y
+CONFIG_I2C=y
+CONFIG_ARM_MHU_MBOX=y
+CONFIG_ARM_SCPI_PROTOCOL=y
+CONFIG_USB_HIDDEV=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB=y
+CONFIG_USB_ULPI=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_SYNOPSYS=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_PHY=y
+CONFIG_PM_OPP=y
+CONFIG_GENERIC_CPUFREQ_CPU0=y
+CONFIG_ARM_BIG_LITTLE_CPUFREQ=y
+CONFIG_ARM_DT_BL_CPUFREQ=y
+CONFIG_ARM64_CPUIDLE=y
+CONFIG_ARM64_CRYPTO=y
diff --git a/linaro/configs/xen.conf b/linaro/configs/xen.conf
new file mode 100644
index 0000000..d24fabb
--- /dev/null
+++ b/linaro/configs/xen.conf
@@ -0,0 +1,7 @@
+CONFIG_XEN=y
+CONFIG_XEN_NETDEV_FRONTEND=y
+CONFIG_XEN_NETDEV_BACKEND=y
+CONFIG_XEN_BLKDEV_FRONTEND=y
+CONFIG_XEN_BLKDEV_BACKEND=y
+CONFIG_XENFS=y
+CONFIG_XEN_COMPAT_XENFS=y
diff --git a/mm/Kconfig b/mm/Kconfig
index e742d06..7c13c13 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -477,3 +477,62 @@
and swap data is stored as normal on the matching swap device.
If unsure, say Y to enable frontswap.
+
+config GENERIC_EARLY_IOREMAP
+ bool
+
+config CMA
+ bool "Contiguous Memory Allocator"
+ depends on HAVE_MEMBLOCK
+ select MIGRATION
+ select MEMORY_ISOLATION
+ help
+ This enables the Contiguous Memory Allocator which allows other
+ subsystems to allocate big physically-contiguous blocks of memory.
+ CMA reserves a region of memory and allows only movable pages to
+ be allocated from it. This way, the kernel can use the memory for
+ pagecache and when a subsystem requests for contiguous area, the
+ allocated pages are migrated away to serve the contiguous request.
+
+ If unsure, say "n".
+
+config CMA_DEBUG
+ bool "CMA debug messages (DEVELOPMENT)"
+ depends on DEBUG_KERNEL && CMA
+ help
+ Turns on debug messages in CMA. This produces KERN_DEBUG
+ messages for every CMA call as well as various messages while
+ processing calls such as dma_alloc_from_contiguous().
+ This option does not affect warning and error messages.
+
+config ZPOOL
+ tristate "Common API for compressed memory storage"
+ default n
+ help
+ Compressed memory storage API. This allows using either zbud or
+ zsmalloc.
+
+config ZSMALLOC
+ bool "Memory allocator for compressed pages"
+ depends on MMU
+ default n
+ help
+ zsmalloc is a slab-based memory allocator designed to store
+ compressed RAM pages. zsmalloc uses virtual memory mapping
+ in order to reduce fragmentation. However, this results in a
+ non-standard allocator interface where a handle, not a pointer, is
+ returned by an alloc(). This handle must be mapped in order to
+ access the allocated space.
+
+config PGTABLE_MAPPING
+ bool "Use page table mapping to access object in zsmalloc"
+ depends on ZSMALLOC
+ help
+ By default, zsmalloc uses a copy-based object mapping method to
+ access allocations that span two pages. However, if a particular
+ architecture (ex, ARM) performs VM mapping faster than copying,
+ then you should select this. This causes zsmalloc to use page table
+ mapping rather than copying for object mapping.
+
+ You can check speed with zsmalloc benchmark[1].
+ [1] https://github.com/spartacus06/zsmalloc
diff --git a/mm/Makefile b/mm/Makefile
index 72c5acb..0fa6442 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -58,3 +58,6 @@
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
obj-$(CONFIG_CLEANCACHE) += cleancache.o
obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
+obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o
+obj-$(CONFIG_ZPOOL) += zpool.o
+obj-$(CONFIG_ZSMALLOC) += zsmalloc.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 5025174..2e53312 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -232,8 +232,6 @@
bdi_cap_stable_pages_required(bdi) ? 1 : 0);
}
-#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
-
static struct device_attribute bdi_dev_attrs[] = {
__ATTR_RW(read_ahead_kb),
__ATTR_RW(min_ratio),
@@ -287,13 +285,19 @@
* Note, we wouldn't bother setting up the timer, but this function is on the
* fast-path (used by '__mark_inode_dirty()'), so we save few context switches
* by delaying the wake-up.
+ *
+ * We have to be careful not to postpone flush work if it is scheduled for
+ * earlier. Thus we use queue_delayed_work().
*/
void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
{
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
- mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+ spin_lock_bh(&bdi->wb_lock);
+ if (test_bit(BDI_registered, &bdi->state))
+ queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+ spin_unlock_bh(&bdi->wb_lock);
}
/*
@@ -306,9 +310,6 @@
spin_unlock_bh(&bdi_lock);
synchronize_rcu_expedited();
-
- /* bdi_list is now unused, clear it to mark @bdi dying */
- INIT_LIST_HEAD(&bdi->bdi_list);
}
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -359,6 +360,11 @@
*/
bdi_remove_from_list(bdi);
+ /* Make sure nobody queues further work */
+ spin_lock_bh(&bdi->wb_lock);
+ clear_bit(BDI_registered, &bdi->state);
+ spin_unlock_bh(&bdi->wb_lock);
+
/*
* Drain work list and shutdown the delayed_work. At this point,
* @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
diff --git a/mm/bounce.c b/mm/bounce.c
index c9f0a43..5a7d58f 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -204,6 +204,8 @@
struct bio_vec *to, *from;
unsigned i;
+ if (force)
+ goto bounce;
bio_for_each_segment(from, *bio_orig, i)
if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
goto bounce;
diff --git a/mm/compaction.c b/mm/compaction.c
index 05ccb4c..eeaaa92 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@
bool migrate_scanner)
{
struct zone *zone = cc->zone;
+
+ if (cc->ignore_skip_hint)
+ return;
+
if (!page)
return;
@@ -248,7 +252,6 @@
{
int nr_scanned = 0, total_isolated = 0;
struct page *cursor, *valid_page = NULL;
- unsigned long nr_strict_required = end_pfn - blockpfn;
unsigned long flags;
bool locked = false;
@@ -261,11 +264,12 @@
nr_scanned++;
if (!pfn_valid_within(blockpfn))
- continue;
+ goto isolate_fail;
+
if (!valid_page)
valid_page = page;
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/*
* The zone lock must be held to isolate freepages.
@@ -286,12 +290,10 @@
/* Recheck this is a buddy page under lock */
if (!PageBuddy(page))
- continue;
+ goto isolate_fail;
/* Found a free page, break it into order-0 pages */
isolated = split_free_page(page);
- if (!isolated && strict)
- break;
total_isolated += isolated;
for (i = 0; i < isolated; i++) {
list_add(&page->lru, freelist);
@@ -302,7 +304,15 @@
if (isolated) {
blockpfn += isolated - 1;
cursor += isolated - 1;
+ continue;
}
+
+isolate_fail:
+ if (strict)
+ break;
+ else
+ continue;
+
}
trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
@@ -312,7 +322,7 @@
* pages requested were isolated. If there were any failures, 0 is
* returned and CMA will fail.
*/
- if (strict && nr_strict_required > total_isolated)
+ if (strict && blockpfn < end_pfn)
total_isolated = 0;
if (locked)
@@ -647,17 +657,21 @@
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn, end_pfn;
+ unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
/*
* Initialise the free scanner. The starting point is where we last
- * scanned from (or the end of the zone if starting). The low point
- * is the end of the pageblock the migration scanner is using.
+ * successfully isolated from, zone-cached value, or the end of the
+ * zone when isolating for the first time. We need this aligned to
+ * the pageblock boundary, because we do pfn -= pageblock_nr_pages
+ * in the for loop.
+ * The low boundary is the end of the pageblock the migration scanner
+ * is using.
*/
- pfn = cc->free_pfn;
- low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+ pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+ low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
* Take care that if the migration scanner is at the end of the zone
@@ -673,9 +687,10 @@
* pages on cc->migratepages. We stop searching if the migrate
* and free page scanners meet or enough free pages are isolated.
*/
- for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
+ for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
+ unsigned long end_pfn;
if (!pfn_valid(pfn))
continue;
@@ -703,13 +718,10 @@
isolated = 0;
/*
- * As pfn may not start aligned, pfn+pageblock_nr_page
- * may cross a MAX_ORDER_NR_PAGES boundary and miss
- * a pfn_valid check. Ensure isolate_freepages_block()
- * only scans within a pageblock
+ * Take care when isolating in last pageblock of a zone which
+ * ends in the middle of a pageblock.
*/
- end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
- end_pfn = min(end_pfn, z_end_pfn);
+ end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
isolated = isolate_freepages_block(cc, pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
@@ -728,7 +740,14 @@
/* split_free_page does not map the pages */
map_pages(freelist);
- cc->free_pfn = high_pfn;
+ /*
+ * If we crossed the migrate scanner, we want to keep it that way
+ * so that compact_finished() may detect this
+ */
+ if (pfn < low_pfn)
+ cc->free_pfn = max(pfn, zone->zone_start_pfn);
+ else
+ cc->free_pfn = high_pfn;
cc->nr_freepages = nr_freepages;
}
@@ -862,7 +881,7 @@
return COMPACT_PARTIAL;
/* Job done if allocation would set block type */
- if (cc->order >= pageblock_order && area->nr_free)
+ if (order >= pageblock_order && area->nr_free)
return COMPACT_PARTIAL;
}
@@ -937,6 +956,14 @@
}
/*
+ * Clear pageblock skip if there were failures recently and compaction
+ * is about to be retried after being deferred. kswapd does not do
+ * this reset as it'll reset the cached information when going to sleep.
+ */
+ if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
+ __reset_isolation_suitable(zone);
+
+ /*
* Setup to move all movable pages to the end of the zone. Used cached
* information on where the scanners should start but check that it
* is initialised by ensuring the values are within zone boundaries.
@@ -952,14 +979,6 @@
zone->compact_cached_migrate_pfn = cc->migrate_pfn;
}
- /*
- * Clear pageblock skip if there were failures recently and compaction
- * is about to be retried after being deferred. kswapd does not do
- * this reset as it'll reset the cached information when going to sleep.
- */
- if (compaction_restarting(zone, cc->order) && !current_is_kswapd())
- __reset_isolation_suitable(zone);
-
migrate_prep_local();
while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
@@ -993,7 +1012,11 @@
if (err) {
putback_movable_pages(&cc->migratepages);
cc->nr_migratepages = 0;
- if (err == -ENOMEM) {
+ /*
+ * migrate_pages() may return -ENOMEM when scanners meet
+ * and we want compact_finished() to detect it
+ */
+ if (err == -ENOMEM && cc->free_pfn > cc->migrate_pfn) {
ret = COMPACT_PARTIAL;
goto out;
}
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
new file mode 100644
index 0000000..e10ccd2
--- /dev/null
+++ b/mm/early_ioremap.c
@@ -0,0 +1,245 @@
+/*
+ * Provide common bits of early_ioremap() support for architectures needing
+ * temporary mappings during boot before ioremap() is available.
+ *
+ * This is mostly a direct copy of the x86 early_ioremap implementation.
+ *
+ * (C) Copyright 1995 1996, 2014 Linus Torvalds
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <asm/fixmap.h>
+
+#ifdef CONFIG_MMU
+static int early_ioremap_debug __initdata;
+
+static int __init early_ioremap_debug_setup(char *str)
+{
+ early_ioremap_debug = 1;
+
+ return 0;
+}
+early_param("early_ioremap_debug", early_ioremap_debug_setup);
+
+static int after_paging_init __initdata;
+
+void __init __weak early_ioremap_shutdown(void)
+{
+}
+
+void __init early_ioremap_reset(void)
+{
+ early_ioremap_shutdown();
+ after_paging_init = 1;
+}
+
+/*
+ * Generally, ioremap() is available after paging_init() has been called.
+ * Architectures wanting to allow early_ioremap after paging_init() can
+ * define __late_set_fixmap and __late_clear_fixmap to do the right thing.
+ */
+#ifndef __late_set_fixmap
+static inline void __init __late_set_fixmap(enum fixed_addresses idx,
+ phys_addr_t phys, pgprot_t prot)
+{
+ BUG();
+}
+#endif
+
+#ifndef __late_clear_fixmap
+static inline void __init __late_clear_fixmap(enum fixed_addresses idx)
+{
+ BUG();
+}
+#endif
+
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
+static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata;
+
+void __init early_ioremap_setup(void)
+{
+ int i;
+
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+ if (WARN_ON(prev_map[i]))
+ break;
+
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+ slot_virt[i] = __fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i);
+}
+
+static int __init check_early_ioremap_leak(void)
+{
+ int count = 0;
+ int i;
+
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++)
+ if (prev_map[i])
+ count++;
+
+ if (WARN(count, KERN_WARNING
+ "Debug warning: early ioremap leak of %d areas detected.\n"
+ "please boot with early_ioremap_debug and report the dmesg.\n",
+ count))
+ return 1;
+ return 0;
+}
+late_initcall(check_early_ioremap_leak);
+
+static void __init __iomem *
+__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
+{
+ unsigned long offset;
+ resource_size_t last_addr;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+ int i, slot;
+
+ WARN_ON(system_state != SYSTEM_BOOTING);
+
+ slot = -1;
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+ if (!prev_map[i]) {
+ slot = i;
+ break;
+ }
+ }
+
+ if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
+ __func__, (u64)phys_addr, size))
+ return NULL;
+
+ /* Don't allow wraparound or zero size */
+ last_addr = phys_addr + size - 1;
+ if (WARN_ON(!size || last_addr < phys_addr))
+ return NULL;
+
+ prev_size[slot] = size;
+ /*
+ * Mappings have to be page-aligned
+ */
+ offset = phys_addr & ~PAGE_MASK;
+ phys_addr &= PAGE_MASK;
+ size = PAGE_ALIGN(last_addr + 1) - phys_addr;
+
+ /*
+ * Mappings have to fit in the FIX_BTMAP area.
+ */
+ nrpages = size >> PAGE_SHIFT;
+ if (WARN_ON(nrpages > NR_FIX_BTMAPS))
+ return NULL;
+
+ /*
+ * Ok, go for it..
+ */
+ idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+ while (nrpages > 0) {
+ if (after_paging_init)
+ __late_set_fixmap(idx, phys_addr, prot);
+ else
+ __early_set_fixmap(idx, phys_addr, prot);
+ phys_addr += PAGE_SIZE;
+ --idx;
+ --nrpages;
+ }
+ WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
+ __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+
+ prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
+ return prev_map[slot];
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+ unsigned long virt_addr;
+ unsigned long offset;
+ unsigned int nrpages;
+ enum fixed_addresses idx;
+ int i, slot;
+
+ slot = -1;
+ for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+ if (prev_map[i] == addr) {
+ slot = i;
+ break;
+ }
+ }
+
+ if (WARN(slot < 0, "early_iounmap(%p, %08lx) not found slot\n",
+ addr, size))
+ return;
+
+ if (WARN(prev_size[slot] != size,
+ "early_iounmap(%p, %08lx) [%d] size not consistent %08lx\n",
+ addr, size, slot, prev_size[slot]))
+ return;
+
+ WARN(early_ioremap_debug, "early_iounmap(%p, %08lx) [%d]\n",
+ addr, size, slot);
+
+ virt_addr = (unsigned long)addr;
+ if (WARN_ON(virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)))
+ return;
+
+ offset = virt_addr & ~PAGE_MASK;
+ nrpages = PAGE_ALIGN(offset + size) >> PAGE_SHIFT;
+
+ idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
+ while (nrpages > 0) {
+ if (after_paging_init)
+ __late_clear_fixmap(idx);
+ else
+ __early_set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR);
+ --idx;
+ --nrpages;
+ }
+ prev_map[slot] = NULL;
+}
+
+/* Remap an IO device */
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+ return __early_ioremap(phys_addr, size, FIXMAP_PAGE_IO);
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+ return (__force void *)__early_ioremap(phys_addr, size,
+ FIXMAP_PAGE_NORMAL);
+}
+#else /* CONFIG_MMU */
+
+void __init __iomem *
+early_ioremap(resource_size_t phys_addr, unsigned long size)
+{
+ return (__force void __iomem *)phys_addr;
+}
+
+/* Remap memory */
+void __init *
+early_memremap(resource_size_t phys_addr, unsigned long size)
+{
+ return (void *)phys_addr;
+}
+
+void __init early_iounmap(void __iomem *addr, unsigned long size)
+{
+}
+
+#endif /* CONFIG_MMU */
+
+
+void __init early_memunmap(void *addr, unsigned long size)
+{
+ early_iounmap((__force void __iomem *)addr, size);
+}
diff --git a/mm/fremap.c b/mm/fremap.c
index 87da359..1fb6bfe 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -203,9 +203,10 @@
if (mapping_cap_account_dirty(mapping)) {
unsigned long addr;
struct file *file = get_file(vma->vm_file);
+ /* mmap_region may free vma; grab the info now */
+ vm_flags = vma->vm_flags;
- addr = mmap_region(file, start, size,
- vma->vm_flags, pgoff);
+ addr = mmap_region(file, start, size, vm_flags, pgoff);
fput(file);
if (IS_ERR_VALUE(addr)) {
err = addr;
@@ -213,7 +214,7 @@
BUG_ON(addr != start);
err = 0;
}
- goto out;
+ goto out_freed;
}
mutex_lock(&mapping->i_mmap_mutex);
flush_dcache_mmap_lock(mapping);
@@ -248,6 +249,7 @@
out:
if (vma)
vm_flags = vma->vm_flags;
+out_freed:
if (likely(!has_write_lock))
up_read(&mm->mmap_sem);
else
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 1b24bdc..a55036a 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -244,8 +244,10 @@
the (older) page from frontswap
*/
inc_frontswap_failed_stores();
- if (dup)
+ if (dup) {
__frontswap_clear(sis, offset);
+ frontswap_ops->invalidate_page(type, offset);
+ }
}
if (frontswap_writethrough_enabled)
/* report failure so swap also writes to swap device */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 362c329..d21c9ef 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1166,7 +1166,7 @@
if (unlikely(!new_page)) {
count_vm_event(THP_FAULT_FALLBACK);
- if (is_huge_zero_pmd(orig_pmd)) {
+ if (!page) {
ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
address, pmd, orig_pmd, haddr);
} else {
@@ -1190,7 +1190,7 @@
goto out;
}
- if (is_huge_zero_pmd(orig_pmd))
+ if (!page)
clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
else
copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1215,7 +1215,7 @@
page_add_new_anon_rmap(new_page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
update_mmu_cache_pmd(vma, address, pmd);
- if (is_huge_zero_pmd(orig_pmd)) {
+ if (!page) {
add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
put_huge_zero_page();
} else {
@@ -1288,64 +1288,104 @@
int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp)
{
+ struct anon_vma *anon_vma = NULL;
struct page *page;
unsigned long haddr = addr & HPAGE_PMD_MASK;
+ int page_nid = -1, this_nid = numa_node_id();
int target_nid;
- int current_nid = -1;
- bool migrated;
+ bool page_locked;
+ bool migrated = false;
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
page = pmd_page(pmd);
- get_page(page);
- current_nid = page_to_nid(page);
+ page_nid = page_to_nid(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
- if (current_nid == numa_node_id())
+ if (page_nid == this_nid)
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
+ /*
+ * Acquire the page lock to serialise THP migrations but avoid dropping
+ * page_table_lock if at all possible
+ */
+ page_locked = trylock_page(page);
target_nid = mpol_misplaced(page, vma, haddr);
if (target_nid == -1) {
- put_page(page);
- goto clear_pmdnuma;
+ /* If the page was locked, there are no parallel migrations */
+ if (page_locked)
+ goto clear_pmdnuma;
+
+ /*
+ * Otherwise wait for potential migrations and retry. We do
+ * relock and check_same as the page may no longer be mapped.
+ * As the fault is being retried, do not account for it.
+ */
+ spin_unlock(&mm->page_table_lock);
+ wait_on_page_locked(page);
+ page_nid = -1;
+ goto out;
}
- /* Acquire the page lock to serialise THP migrations */
+ /* Page is misplaced, serialise migrations and parallel THP splits */
+ get_page(page);
spin_unlock(&mm->page_table_lock);
- lock_page(page);
+ if (!page_locked)
+ lock_page(page);
+ anon_vma = page_lock_anon_vma_read(page);
/* Confirm the PTE did not while locked */
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp))) {
unlock_page(page);
put_page(page);
+ page_nid = -1;
goto out_unlock;
}
- spin_unlock(&mm->page_table_lock);
- /* Migrate the THP to the requested node */
+ /* Bail if we fail to protect against THP splits for any reason */
+ if (unlikely(!anon_vma)) {
+ put_page(page);
+ page_nid = -1;
+ goto clear_pmdnuma;
+ }
+
+ /*
+ * The page_table_lock above provides a memory barrier
+ * with change_protection_range.
+ */
+ if (mm_tlb_flush_pending(mm))
+ flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+
+ /*
+ * Migrate the THP to the requested node, returns with page unlocked
+ * and pmd_numa cleared.
+ */
+ spin_unlock(&mm->page_table_lock);
migrated = migrate_misplaced_transhuge_page(mm, vma,
pmdp, pmd, addr, page, target_nid);
- if (!migrated)
- goto check_same;
+ if (migrated)
+ page_nid = target_nid;
- task_numa_fault(target_nid, HPAGE_PMD_NR, true);
- return 0;
-
-check_same:
- spin_lock(&mm->page_table_lock);
- if (unlikely(!pmd_same(pmd, *pmdp)))
- goto out_unlock;
+ goto out;
clear_pmdnuma:
+ BUG_ON(!PageLocked(page));
pmd = pmd_mknonnuma(pmd);
set_pmd_at(mm, haddr, pmdp, pmd);
VM_BUG_ON(pmd_numa(*pmdp));
update_mmu_cache_pmd(vma, addr, pmdp);
+ unlock_page(page);
out_unlock:
spin_unlock(&mm->page_table_lock);
- if (current_nid != -1)
- task_numa_fault(current_nid, HPAGE_PMD_NR, false);
+
+out:
+ if (anon_vma)
+ page_unlock_anon_vma_read(anon_vma);
+
+ if (page_nid != -1)
+ task_numa_fault(page_nid, HPAGE_PMD_NR, migrated);
+
return 0;
}
@@ -1693,21 +1733,24 @@
if (pmd) {
pgtable = pgtable_trans_huge_withdraw(mm);
pmd_populate(mm, &_pmd, pgtable);
+ if (pmd_write(*pmd))
+ BUG_ON(page_mapcount(page) != 1);
haddr = address;
for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
pte_t *pte, entry;
BUG_ON(PageCompound(page+i));
+ /*
+ * Note that pmd_numa is not transferred deliberately
+ * to avoid any possibility that pte_numa leaks to
+ * a PROT_NONE VMA by accident.
+ */
entry = mk_pte(page + i, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (!pmd_write(*pmd))
entry = pte_wrprotect(entry);
- else
- BUG_ON(page_mapcount(page) != 1);
if (!pmd_young(*pmd))
entry = pte_mkold(entry);
- if (pmd_numa(*pmd))
- entry = pte_mknuma(entry);
pte = pte_offset_map(&_pmd, haddr);
BUG_ON(!pte_none(*pte));
set_pte_at(mm, haddr, pte, entry);
@@ -2286,6 +2329,8 @@
goto out;
vma = find_vma(mm, address);
+ if (!vma)
+ goto out;
hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
hend = vma->vm_end & HPAGE_PMD_MASK;
if (address < hstart || address + HPAGE_PMD_SIZE > hend)
@@ -2697,6 +2742,7 @@
mmun_start = haddr;
mmun_end = haddr + HPAGE_PMD_SIZE;
+again:
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2719,7 +2765,14 @@
split_huge_page(page);
put_page(page);
- BUG_ON(pmd_trans_huge(*pmd));
+
+ /*
+ * We don't always have down_write of mmap_sem here: a racing
+ * do_huge_pmd_wp_page() might have copied-on-write to another
+ * huge page before our split_huge_page() got the anon_vma lock.
+ */
+ if (unlikely(pmd_trans_huge(*pmd)))
+ goto again;
}
void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e2bfbf7..4642000 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -21,6 +21,7 @@
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/page-isolation.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -434,25 +435,6 @@
return (get_vma_private_data(vma) & flag) != 0;
}
-/* Decrement the reserved pages in the hugepage pool by one */
-static void decrement_hugepage_resv_vma(struct hstate *h,
- struct vm_area_struct *vma)
-{
- if (vma->vm_flags & VM_NORESERVE)
- return;
-
- if (vma->vm_flags & VM_MAYSHARE) {
- /* Shared mappings always use reserves */
- h->resv_huge_pages--;
- } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
- /*
- * Only the process that called mmap() has reserves for
- * private mappings.
- */
- h->resv_huge_pages--;
- }
-}
-
/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
@@ -462,12 +444,35 @@
}
/* Returns true if the VMA has associated reserve pages */
-static int vma_has_reserves(struct vm_area_struct *vma)
+static int vma_has_reserves(struct vm_area_struct *vma, long chg)
{
+ if (vma->vm_flags & VM_NORESERVE) {
+ /*
+ * This address is already reserved by other process(chg == 0),
+ * so, we should decrement reserved count. Without decrementing,
+ * reserve count remains after releasing inode, because this
+ * allocated page will go into page cache and is regarded as
+ * coming from reserved pool in releasing step. Currently, we
+ * don't have any other solution to deal with this situation
+ * properly, so add work-around here.
+ */
+ if (vma->vm_flags & VM_MAYSHARE && chg == 0)
+ return 1;
+ else
+ return 0;
+ }
+
+ /* Shared mappings always use reserves */
if (vma->vm_flags & VM_MAYSHARE)
return 1;
+
+ /*
+ * Only the process that called mmap() has reserves for
+ * private mappings.
+ */
if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
return 1;
+
return 0;
}
@@ -517,9 +522,15 @@
{
struct page *page;
- if (list_empty(&h->hugepage_freelists[nid]))
+ list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+ if (!is_migrate_isolate_page(page))
+ break;
+ /*
+ * if 'non-isolated free hugepage' not found on the list,
+ * the allocation fails.
+ */
+ if (&h->hugepage_freelists[nid] == &page->lru)
return NULL;
- page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
h->free_huge_pages--;
@@ -529,7 +540,8 @@
static struct page *dequeue_huge_page_vma(struct hstate *h,
struct vm_area_struct *vma,
- unsigned long address, int avoid_reserve)
+ unsigned long address, int avoid_reserve,
+ long chg)
{
struct page *page = NULL;
struct mempolicy *mpol;
@@ -548,7 +560,7 @@
* have no page reserves. This check ensures that reservations are
* not "stolen". The child may still get SIGKILLed
*/
- if (!vma_has_reserves(vma) &&
+ if (!vma_has_reserves(vma, chg) &&
h->free_huge_pages - h->resv_huge_pages == 0)
goto err;
@@ -561,8 +573,13 @@
if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
page = dequeue_huge_page_node(h, zone_to_nid(zone));
if (page) {
- if (!avoid_reserve)
- decrement_hugepage_resv_vma(h, vma);
+ if (avoid_reserve)
+ break;
+ if (!vma_has_reserves(vma, chg))
+ break;
+
+ SetPagePrivate(page);
+ h->resv_huge_pages--;
break;
}
}
@@ -620,15 +637,20 @@
int nid = page_to_nid(page);
struct hugepage_subpool *spool =
(struct hugepage_subpool *)page_private(page);
+ bool restore_reserve;
set_page_private(page, 0);
page->mapping = NULL;
BUG_ON(page_count(page));
BUG_ON(page_mapcount(page));
+ restore_reserve = PagePrivate(page);
spin_lock(&hugetlb_lock);
hugetlb_cgroup_uncharge_page(hstate_index(h),
pages_per_huge_page(h), page);
+ if (restore_reserve)
+ h->resv_huge_pages++;
+
if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
/* remove the page from active list */
list_del(&page->lru);
@@ -690,6 +712,40 @@
}
EXPORT_SYMBOL_GPL(PageHuge);
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageHead(page_head))
+ return 0;
+
+ dtor = get_compound_page_dtor(page_head);
+
+ return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
+pgoff_t __basepage_index(struct page *page)
+{
+ struct page *page_head = compound_head(page);
+ pgoff_t index = page_index(page_head);
+ unsigned long compound_idx;
+
+ if (!PageHuge(page_head))
+ return page_index(page);
+
+ if (compound_order(page_head) >= MAX_ORDER)
+ compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
+ else
+ compound_idx = page - page_head;
+
+ return (index << compound_order(page_head)) + compound_idx;
+}
+
static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
{
struct page *page;
@@ -755,33 +811,6 @@
return nid;
}
-static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
-{
- struct page *page;
- int start_nid;
- int next_nid;
- int ret = 0;
-
- start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
- page = alloc_fresh_huge_page_node(h, next_nid);
- if (page) {
- ret = 1;
- break;
- }
- next_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- } while (next_nid != start_nid);
-
- if (ret)
- count_vm_event(HTLB_BUDDY_PGALLOC);
- else
- count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
-
- return ret;
-}
-
/*
* helper for free_pool_huge_page() - return the previously saved
* node ["this node"] from which to free a huge page. Advance the
@@ -800,6 +829,40 @@
return nid;
}
+#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \
+ nr_nodes--)
+
+#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_free(hs, mask)) || 1); \
+ nr_nodes--)
+
+static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
+{
+ struct page *page;
+ int nr_nodes, node;
+ int ret = 0;
+
+ for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+ page = alloc_fresh_huge_page_node(h, node);
+ if (page) {
+ ret = 1;
+ break;
+ }
+ }
+
+ if (ret)
+ count_vm_event(HTLB_BUDDY_PGALLOC);
+ else
+ count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
+ return ret;
+}
+
/*
* Free huge page from pool from next node to free.
* Attempt to keep persistent huge pages more or less
@@ -809,36 +872,31 @@
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
bool acct_surplus)
{
- int start_nid;
- int next_nid;
+ int nr_nodes, node;
int ret = 0;
- start_nid = hstate_next_node_to_free(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
+ for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
/*
* If we're returning unused surplus pages, only examine
* nodes with surplus pages.
*/
- if ((!acct_surplus || h->surplus_huge_pages_node[next_nid]) &&
- !list_empty(&h->hugepage_freelists[next_nid])) {
+ if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
+ !list_empty(&h->hugepage_freelists[node])) {
struct page *page =
- list_entry(h->hugepage_freelists[next_nid].next,
+ list_entry(h->hugepage_freelists[node].next,
struct page, lru);
list_del(&page->lru);
h->free_huge_pages--;
- h->free_huge_pages_node[next_nid]--;
+ h->free_huge_pages_node[node]--;
if (acct_surplus) {
h->surplus_huge_pages--;
- h->surplus_huge_pages_node[next_nid]--;
+ h->surplus_huge_pages_node[node]--;
}
update_and_free_page(h, page);
ret = 1;
break;
}
- next_nid = hstate_next_node_to_free(h, nodes_allowed);
- } while (next_nid != start_nid);
+ }
return ret;
}
@@ -927,10 +985,11 @@
*/
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
- struct page *page;
+ struct page *page = NULL;
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page_node(h, nid);
+ if (h->free_huge_pages - h->resv_huge_pages > 0)
+ page = dequeue_huge_page_node(h, nid);
spin_unlock(&hugetlb_lock);
if (!page)
@@ -1018,11 +1077,8 @@
spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
- if (!list_empty(&surplus_list)) {
- list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
- put_page(page);
- }
- }
+ list_for_each_entry_safe(page, tmp, &surplus_list, lru)
+ put_page(page);
spin_lock(&hugetlb_lock);
return ret;
@@ -1059,6 +1115,7 @@
while (nr_pages--) {
if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
break;
+ cond_resched_lock(&hugetlb_lock);
}
}
@@ -1089,9 +1146,9 @@
} else {
long err;
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
- err = region_chg(&reservations->regions, idx, idx + 1);
+ err = region_chg(&resv->regions, idx, idx + 1);
if (err < 0)
return err;
return 0;
@@ -1109,10 +1166,10 @@
} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
pgoff_t idx = vma_hugecache_offset(h, vma, addr);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
/* Mark this page used in the map. */
- region_add(&reservations->regions, idx, idx + 1);
+ region_add(&resv->regions, idx, idx + 1);
}
}
@@ -1138,38 +1195,35 @@
chg = vma_needs_reservation(h, vma, addr);
if (chg < 0)
return ERR_PTR(-ENOMEM);
- if (chg)
- if (hugepage_subpool_get_pages(spool, chg))
+ if (chg || avoid_reserve)
+ if (hugepage_subpool_get_pages(spool, 1))
return ERR_PTR(-ENOSPC);
ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
if (ret) {
- hugepage_subpool_put_pages(spool, chg);
+ if (chg || avoid_reserve)
+ hugepage_subpool_put_pages(spool, 1);
return ERR_PTR(-ENOSPC);
}
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
- if (page) {
- /* update page cgroup details */
- hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
- h_cg, page);
- spin_unlock(&hugetlb_lock);
- } else {
+ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
+ if (!page) {
spin_unlock(&hugetlb_lock);
page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
hugetlb_cgroup_uncharge_cgroup(idx,
pages_per_huge_page(h),
h_cg);
- hugepage_subpool_put_pages(spool, chg);
+ if (chg || avoid_reserve)
+ hugepage_subpool_put_pages(spool, 1);
return ERR_PTR(-ENOSPC);
}
spin_lock(&hugetlb_lock);
- hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h),
- h_cg, page);
list_move(&page->lru, &h->hugepage_activelist);
- spin_unlock(&hugetlb_lock);
+ /* Fall through */
}
+ hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
+ spin_unlock(&hugetlb_lock);
set_page_private(page, (unsigned long)spool);
@@ -1180,14 +1234,12 @@
int __weak alloc_bootmem_huge_page(struct hstate *h)
{
struct huge_bootmem_page *m;
- int nr_nodes = nodes_weight(node_states[N_MEMORY]);
+ int nr_nodes, node;
- while (nr_nodes) {
+ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
void *addr;
- addr = __alloc_bootmem_node_nopanic(
- NODE_DATA(hstate_next_node_to_alloc(h,
- &node_states[N_MEMORY])),
+ addr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
huge_page_size(h), huge_page_size(h), 0);
if (addr) {
@@ -1199,7 +1251,6 @@
m = addr;
goto found;
}
- nr_nodes--;
}
return 0;
@@ -1338,48 +1389,28 @@
static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
int delta)
{
- int start_nid, next_nid;
- int ret = 0;
+ int nr_nodes, node;
VM_BUG_ON(delta != -1 && delta != 1);
- if (delta < 0)
- start_nid = hstate_next_node_to_alloc(h, nodes_allowed);
- else
- start_nid = hstate_next_node_to_free(h, nodes_allowed);
- next_nid = start_nid;
-
- do {
- int nid = next_nid;
- if (delta < 0) {
- /*
- * To shrink on this node, there must be a surplus page
- */
- if (!h->surplus_huge_pages_node[nid]) {
- next_nid = hstate_next_node_to_alloc(h,
- nodes_allowed);
- continue;
- }
+ if (delta < 0) {
+ for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+ if (h->surplus_huge_pages_node[node])
+ goto found;
}
- if (delta > 0) {
- /*
- * Surplus cannot exceed the total number of pages
- */
- if (h->surplus_huge_pages_node[nid] >=
- h->nr_huge_pages_node[nid]) {
- next_nid = hstate_next_node_to_free(h,
- nodes_allowed);
- continue;
- }
+ } else {
+ for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+ if (h->surplus_huge_pages_node[node] <
+ h->nr_huge_pages_node[node])
+ goto found;
}
+ }
+ return 0;
- h->surplus_huge_pages += delta;
- h->surplus_huge_pages_node[nid] += delta;
- ret = 1;
- break;
- } while (next_nid != start_nid);
-
- return ret;
+found:
+ h->surplus_huge_pages += delta;
+ h->surplus_huge_pages_node[node] += delta;
+ return 1;
}
#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
@@ -1446,6 +1477,7 @@
while (min_count < persistent_huge_pages(h)) {
if (!free_pool_huge_page(h, nodes_allowed, 0))
break;
+ cond_resched_lock(&hugetlb_lock);
}
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
@@ -2190,7 +2222,7 @@
static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
/*
* This new VMA should share its siblings reservation map if present.
@@ -2200,34 +2232,34 @@
* after this open call completes. It is therefore safe to take a
* new reference here without additional locking.
*/
- if (reservations)
- kref_get(&reservations->refs);
+ if (resv)
+ kref_get(&resv->refs);
}
static void resv_map_put(struct vm_area_struct *vma)
{
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
- if (!reservations)
+ if (!resv)
return;
- kref_put(&reservations->refs, resv_map_release);
+ kref_put(&resv->refs, resv_map_release);
}
static void hugetlb_vm_op_close(struct vm_area_struct *vma)
{
struct hstate *h = hstate_vma(vma);
- struct resv_map *reservations = vma_resv_map(vma);
+ struct resv_map *resv = vma_resv_map(vma);
struct hugepage_subpool *spool = subpool_vma(vma);
unsigned long reserve;
unsigned long start;
unsigned long end;
- if (reservations) {
+ if (resv) {
start = vma_hugecache_offset(h, vma, vma->vm_start);
end = vma_hugecache_offset(h, vma, vma->vm_end);
reserve = (end - start) -
- region_count(&reservations->regions, start, end);
+ region_count(&resv->regions, start, end);
resv_map_put(vma);
@@ -2285,51 +2317,6 @@
update_mmu_cache(vma, address, ptep);
}
-
-int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma)
-{
- pte_t *src_pte, *dst_pte, entry;
- struct page *ptepage;
- unsigned long addr;
- int cow;
- struct hstate *h = hstate_vma(vma);
- unsigned long sz = huge_page_size(h);
-
- cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
- for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
- src_pte = huge_pte_offset(src, addr);
- if (!src_pte)
- continue;
- dst_pte = huge_pte_alloc(dst, addr, sz);
- if (!dst_pte)
- goto nomem;
-
- /* If the pagetables are shared don't copy or take references */
- if (dst_pte == src_pte)
- continue;
-
- spin_lock(&dst->page_table_lock);
- spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
- if (!huge_pte_none(huge_ptep_get(src_pte))) {
- if (cow)
- huge_ptep_set_wrprotect(src, addr, src_pte);
- entry = huge_ptep_get(src_pte);
- ptepage = pte_page(entry);
- get_page(ptepage);
- page_dup_rmap(ptepage);
- set_huge_pte_at(dst, addr, dst_pte, entry);
- }
- spin_unlock(&src->page_table_lock);
- spin_unlock(&dst->page_table_lock);
- }
- return 0;
-
-nomem:
- return -ENOMEM;
-}
-
static int is_hugetlb_entry_migration(pte_t pte)
{
swp_entry_t swp;
@@ -2356,6 +2343,78 @@
return 0;
}
+int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
+ struct vm_area_struct *vma)
+{
+ pte_t *src_pte, *dst_pte, entry;
+ struct page *ptepage;
+ unsigned long addr;
+ int cow;
+ struct hstate *h = hstate_vma(vma);
+ unsigned long sz = huge_page_size(h);
+ unsigned long mmun_start; /* For mmu_notifiers */
+ unsigned long mmun_end; /* For mmu_notifiers */
+ int ret = 0;
+
+ cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+
+ mmun_start = vma->vm_start;
+ mmun_end = vma->vm_end;
+ if (cow)
+ mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end);
+
+ for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+ src_pte = huge_pte_offset(src, addr);
+ if (!src_pte)
+ continue;
+ dst_pte = huge_pte_alloc(dst, addr, sz);
+ if (!dst_pte) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ /* If the pagetables are shared don't copy or take references */
+ if (dst_pte == src_pte)
+ continue;
+
+ spin_lock(&dst->page_table_lock);
+ spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
+ entry = huge_ptep_get(src_pte);
+ if (huge_pte_none(entry)) { /* skip none entry */
+ ;
+ } else if (unlikely(is_hugetlb_entry_migration(entry) ||
+ is_hugetlb_entry_hwpoisoned(entry))) {
+ swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+ if (is_write_migration_entry(swp_entry) && cow) {
+ /*
+ * COW mappings require pages in both
+ * parent and child to be set to read.
+ */
+ make_migration_entry_read(&swp_entry);
+ entry = swp_entry_to_pte(swp_entry);
+ set_huge_pte_at(src, addr, src_pte, entry);
+ }
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ } else {
+ if (cow)
+ huge_ptep_set_wrprotect(src, addr, src_pte);
+ entry = huge_ptep_get(src_pte);
+ ptepage = pte_page(entry);
+ get_page(ptepage);
+ page_dup_rmap(ptepage);
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ }
+ spin_unlock(&src->page_table_lock);
+ spin_unlock(&dst->page_table_lock);
+ }
+
+ if (cow)
+ mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end);
+
+ return ret;
+}
+
void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page)
@@ -2392,9 +2451,10 @@
continue;
/*
- * HWPoisoned hugepage is already unmapped and dropped reference
+ * Migrating hugepage or HWPoisoned hugepage is already
+ * unmapped and its refcount is dropped, so just clear pte here.
*/
- if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
+ if (unlikely(!pte_present(pte))) {
huge_pte_clear(mm, address, ptep);
continue;
}
@@ -2473,7 +2533,7 @@
mm = vma->vm_mm;
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
tlb_finish_mmu(&tlb, start, end);
}
@@ -2540,7 +2600,6 @@
{
struct hstate *h = hstate_vma(vma);
struct page *old_page, *new_page;
- int avoidcopy;
int outside_reserve = 0;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
@@ -2550,10 +2609,8 @@
retry_avoidcopy:
/* If no-one else is actually using this page, avoid the copy
* and just make the page writable */
- avoidcopy = (page_mapcount(old_page) == 1);
- if (avoidcopy) {
- if (PageAnon(old_page))
- page_move_anon_rmap(old_page, vma, address);
+ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
+ page_move_anon_rmap(old_page, vma, address);
set_huge_ptep_writable(vma, address, ptep);
return 0;
}
@@ -2567,8 +2624,7 @@
* at the time of fork() could consume its reserves on COW instead
* of the full address range.
*/
- if (!(vma->vm_flags & VM_MAYSHARE) &&
- is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
+ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
old_page != pagecache_page)
outside_reserve = 1;
@@ -2640,6 +2696,8 @@
spin_lock(&mm->page_table_lock);
ptep = huge_pte_offset(mm, address & huge_page_mask(h));
if (likely(pte_same(huge_ptep_get(ptep), pte))) {
+ ClearPagePrivate(new_page);
+
/* Break COW */
huge_ptep_clear_flush(vma, address, ptep);
set_huge_pte_at(mm, address, ptep,
@@ -2651,10 +2709,11 @@
}
spin_unlock(&mm->page_table_lock);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
- /* Caller expects lock to be held */
- spin_lock(&mm->page_table_lock);
page_cache_release(new_page);
page_cache_release(old_page);
+
+ /* Caller expects lock to be held */
+ spin_lock(&mm->page_table_lock);
return 0;
}
@@ -2750,6 +2809,7 @@
goto retry;
goto out;
}
+ ClearPagePrivate(page);
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
@@ -2796,8 +2856,10 @@
if (!huge_pte_none(huge_ptep_get(ptep)))
goto backout;
- if (anon_rmap)
+ if (anon_rmap) {
+ ClearPagePrivate(page);
hugepage_add_new_anon_rmap(page, vma, address);
+ }
else
page_dup_rmap(page);
new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
@@ -2931,15 +2993,6 @@
return ret;
}
-/* Can be overriden by architectures */
-__attribute__((weak)) struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
- pud_t *pud, int write)
-{
- BUG();
- return NULL;
-}
-
long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, unsigned long *nr_pages,
@@ -3169,6 +3222,216 @@
hugetlb_acct_memory(h, -(chg - freed));
}
+#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+static unsigned long page_table_shareable(struct vm_area_struct *svma,
+ struct vm_area_struct *vma,
+ unsigned long addr, pgoff_t idx)
+{
+ unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
+ svma->vm_start;
+ unsigned long sbase = saddr & PUD_MASK;
+ unsigned long s_end = sbase + PUD_SIZE;
+
+ /* Allow segments to share if only one is marked locked */
+ unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
+ unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+
+ /*
+ * match the virtual addresses, permission and the alignment of the
+ * page table page.
+ */
+ if (pmd_index(addr) != pmd_index(saddr) ||
+ vm_flags != svm_flags ||
+ sbase < svma->vm_start || svma->vm_end < s_end)
+ return 0;
+
+ return saddr;
+}
+
+static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
+{
+ unsigned long base = addr & PUD_MASK;
+ unsigned long end = base + PUD_SIZE;
+
+ /*
+ * check on proper vm_flags and page table alignment
+ */
+ if (vma->vm_flags & VM_MAYSHARE &&
+ vma->vm_start <= base && end <= vma->vm_end)
+ return 1;
+ return 0;
+}
+
+/*
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
+ */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+ struct vm_area_struct *vma = find_vma(mm, addr);
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+ vma->vm_pgoff;
+ struct vm_area_struct *svma;
+ unsigned long saddr;
+ pte_t *spte = NULL;
+ pte_t *pte;
+
+ if (!vma_shareable(vma, addr))
+ return (pte_t *)pmd_alloc(mm, pud, addr);
+
+ mutex_lock(&mapping->i_mmap_mutex);
+ vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
+ if (svma == vma)
+ continue;
+
+ saddr = page_table_shareable(svma, vma, addr, idx);
+ if (saddr) {
+ spte = huge_pte_offset(svma->vm_mm, saddr);
+ if (spte) {
+ get_page(virt_to_page(spte));
+ break;
+ }
+ }
+ }
+
+ if (!spte)
+ goto out;
+
+ spin_lock(&mm->page_table_lock);
+ if (pud_none(*pud))
+ pud_populate(mm, pud,
+ (pmd_t *)((unsigned long)spte & PAGE_MASK));
+ else
+ put_page(virt_to_page(spte));
+ spin_unlock(&mm->page_table_lock);
+out:
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+ mutex_unlock(&mapping->i_mmap_mutex);
+ return pte;
+}
+
+/*
+ * unmap huge page backed by shared pte.
+ *
+ * Hugetlb pte page is ref counted at the time of mapping. If pte is shared
+ * indicated by page_count > 1, unmap is achieved by clearing pud and
+ * decrementing the ref count. If count == 1, the pte page is not shared.
+ *
+ * called with vma->vm_mm->page_table_lock held.
+ *
+ * returns: 1 successfully unmapped a shared pte page
+ * 0 the underlying pte page is not shared, or it is the last user
+ */
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+ pgd_t *pgd = pgd_offset(mm, *addr);
+ pud_t *pud = pud_offset(pgd, *addr);
+
+ BUG_ON(page_count(virt_to_page(ptep)) == 0);
+ if (page_count(virt_to_page(ptep)) == 1)
+ return 0;
+
+ pud_clear(pud);
+ put_page(virt_to_page(ptep));
+ *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
+ return 1;
+}
+#define want_pmd_share() (1)
+#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+ return NULL;
+}
+#define want_pmd_share() (0)
+#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
+
+#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pte_t *pte = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ pud = pud_alloc(mm, pgd, addr);
+ if (pud) {
+ if (sz == PUD_SIZE) {
+ pte = (pte_t *)pud;
+ } else {
+ BUG_ON(sz != PMD_SIZE);
+ if (want_pmd_share() && pud_none(*pud))
+ pte = huge_pmd_share(mm, addr, pud);
+ else
+ pte = (pte_t *)pmd_alloc(mm, pud, addr);
+ }
+ }
+ BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+
+ return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd = NULL;
+
+ pgd = pgd_offset(mm, addr);
+ if (pgd_present(*pgd)) {
+ pud = pud_offset(pgd, addr);
+ if (pud_present(*pud)) {
+ if (pud_huge(*pud))
+ return (pte_t *)pud;
+ pmd = pmd_offset(pud, addr);
+ }
+ }
+ return (pte_t *) pmd;
+}
+
+struct page *
+follow_huge_pmd(struct mm_struct *mm, unsigned long address,
+ pmd_t *pmd, int write)
+{
+ struct page *page;
+
+ page = pte_page(*(pte_t *)pmd);
+ if (page)
+ page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+ return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+ pud_t *pud, int write)
+{
+ struct page *page;
+
+ page = pte_page(*(pte_t *)pud);
+ if (page)
+ page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+ return page;
+}
+
+#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+ pud_t *pud, int write)
+{
+ BUG();
+ return NULL;
+}
+
+#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */
+
#ifdef CONFIG_MEMORY_FAILURE
/* Should be called in hugetlb_lock */
diff --git a/mm/ksm.c b/mm/ksm.c
index b6afe0c..7bf748f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -376,7 +376,7 @@
else
ret = VM_FAULT_WRITE;
put_page(page);
- } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+ } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
/*
* We must loop because handle_mm_fault() may back out if there's
* any difficulty e.g. if pte accessed bit gets updated concurrently.
@@ -444,7 +444,7 @@
static struct page *page_trans_compound_anon(struct page *page)
{
if (PageTransCompound(page)) {
- struct page *head = compound_trans_head(page);
+ struct page *head = compound_head(page);
/*
* head may actually be splitted and freed from under
* us but it's ok here.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1947218..eaa3acc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -302,6 +302,7 @@
bool oom_lock;
atomic_t under_oom;
+ atomic_t oom_wakeups;
atomic_t refcnt;
@@ -379,7 +380,7 @@
static size_t memcg_size(void)
{
return sizeof(struct mem_cgroup) +
- nr_node_ids * sizeof(struct mem_cgroup_per_node);
+ nr_node_ids * sizeof(struct mem_cgroup_per_node *);
}
/* internal only representation about the status of kmem accounting. */
@@ -1220,7 +1221,7 @@
if (dead_count == iter->last_dead_count) {
smp_rmb();
last_visited = iter->last_visited;
- if (last_visited &&
+ if (last_visited && last_visited != root &&
!css_tryget(&last_visited->css))
last_visited = NULL;
}
@@ -1229,7 +1230,7 @@
memcg = __mem_cgroup_iter_next(root, last_visited);
if (reclaim) {
- if (last_visited)
+ if (last_visited && last_visited != root)
css_put(&last_visited->css);
iter->last_visited = memcg;
@@ -2075,15 +2076,18 @@
return total;
}
+static DEFINE_SPINLOCK(memcg_oom_lock);
+
/*
* Check OOM-Killer is already running under our hierarchy.
* If someone is running, return false.
- * Has to be called with memcg_oom_lock
*/
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter, *failed = NULL;
+ spin_lock(&memcg_oom_lock);
+
for_each_mem_cgroup_tree(iter, memcg) {
if (iter->oom_lock) {
/*
@@ -2097,33 +2101,33 @@
iter->oom_lock = true;
}
- if (!failed)
- return true;
-
- /*
- * OK, we failed to lock the whole subtree so we have to clean up
- * what we set up to the failing subtree
- */
- for_each_mem_cgroup_tree(iter, memcg) {
- if (iter == failed) {
- mem_cgroup_iter_break(memcg, iter);
- break;
+ if (failed) {
+ /*
+ * OK, we failed to lock the whole subtree so we have
+ * to clean up what we set up to the failing subtree
+ */
+ for_each_mem_cgroup_tree(iter, memcg) {
+ if (iter == failed) {
+ mem_cgroup_iter_break(memcg, iter);
+ break;
+ }
+ iter->oom_lock = false;
}
- iter->oom_lock = false;
}
- return false;
+
+ spin_unlock(&memcg_oom_lock);
+
+ return !failed;
}
-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
{
struct mem_cgroup *iter;
+ spin_lock(&memcg_oom_lock);
for_each_mem_cgroup_tree(iter, memcg)
iter->oom_lock = false;
- return 0;
+ spin_unlock(&memcg_oom_lock);
}
static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
@@ -2147,7 +2151,6 @@
atomic_add_unless(&iter->under_oom, -1, 0);
}
-static DEFINE_SPINLOCK(memcg_oom_lock);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
struct oom_wait_info {
@@ -2177,6 +2180,7 @@
static void memcg_wakeup_oom(struct mem_cgroup *memcg)
{
+ atomic_inc(&memcg->oom_wakeups);
/* for filtering, pass "memcg" as argument. */
__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
}
@@ -2187,57 +2191,97 @@
memcg_wakeup_oom(memcg);
}
-/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
- */
-static bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask,
- int order)
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
{
+ if (!current->memcg_oom.may_oom)
+ return;
+ /*
+ * We are in the middle of the charge context here, so we
+ * don't want to block when potentially sitting on a callstack
+ * that holds all kinds of filesystem and mm locks.
+ *
+ * Also, the caller may handle a failed allocation gracefully
+ * (like optional page cache readahead) and so an OOM killer
+ * invocation might not even be necessary.
+ *
+ * That's why we don't do anything here except remember the
+ * OOM context and then deal with it at the end of the page
+ * fault when the stack is unwound, the locks are released,
+ * and when we know whether the fault was overall successful.
+ */
+ css_get(&memcg->css);
+ current->memcg_oom.memcg = memcg;
+ current->memcg_oom.gfp_mask = mask;
+ current->memcg_oom.order = order;
+}
+
+/**
+ * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ * @handle: actually kill/wait or just clean up the OOM state
+ *
+ * This has to be called at the end of a page fault if the memcg OOM
+ * handler was enabled.
+ *
+ * Memcg supports userspace OOM handling where failed allocations must
+ * sleep on a waitqueue until the userspace task resolves the
+ * situation. Sleeping directly in the charge context with all kinds
+ * of locks held is not a good idea, instead we remember an OOM state
+ * in the task and mem_cgroup_oom_synchronize() has to be called at
+ * the end of the page fault to complete the OOM handling.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * completed, %false otherwise.
+ */
+bool mem_cgroup_oom_synchronize(bool handle)
+{
+ struct mem_cgroup *memcg = current->memcg_oom.memcg;
struct oom_wait_info owait;
- bool locked, need_to_kill;
+ bool locked;
+
+ /* OOM is global, do not handle */
+ if (!memcg)
+ return false;
+
+ if (!handle)
+ goto cleanup;
owait.memcg = memcg;
owait.wait.flags = 0;
owait.wait.func = memcg_oom_wake_function;
owait.wait.private = current;
INIT_LIST_HEAD(&owait.wait.task_list);
- need_to_kill = true;
+
+ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
mem_cgroup_mark_under_oom(memcg);
- /* At first, try to OOM lock hierarchy under memcg.*/
- spin_lock(&memcg_oom_lock);
- locked = mem_cgroup_oom_lock(memcg);
- /*
- * Even if signal_pending(), we can't quit charge() loop without
- * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
- * under OOM is always welcomed, use TASK_KILLABLE here.
- */
- prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
- if (!locked || memcg->oom_kill_disable)
- need_to_kill = false;
+ locked = mem_cgroup_oom_trylock(memcg);
+
if (locked)
mem_cgroup_oom_notify(memcg);
- spin_unlock(&memcg_oom_lock);
- if (need_to_kill) {
+ if (locked && !memcg->oom_kill_disable) {
+ mem_cgroup_unmark_under_oom(memcg);
finish_wait(&memcg_oom_waitq, &owait.wait);
- mem_cgroup_out_of_memory(memcg, mask, order);
+ mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+ current->memcg_oom.order);
} else {
schedule();
+ mem_cgroup_unmark_under_oom(memcg);
finish_wait(&memcg_oom_waitq, &owait.wait);
}
- spin_lock(&memcg_oom_lock);
- if (locked)
+
+ if (locked) {
mem_cgroup_oom_unlock(memcg);
- memcg_wakeup_oom(memcg);
- spin_unlock(&memcg_oom_lock);
-
- mem_cgroup_unmark_under_oom(memcg);
-
- if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
- return false;
- /* Give chance to dying process */
- schedule_timeout_uninterruptible(1);
+ /*
+ * There is no guarantee that an OOM-lock contender
+ * sees the wakeups triggered by the OOM kill
+ * uncharges. Wake any sleepers explicitely.
+ */
+ memcg_oom_recover(memcg);
+ }
+cleanup:
+ current->memcg_oom.memcg = NULL;
+ css_put(&memcg->css);
return true;
}
@@ -2550,12 +2594,11 @@
CHARGE_RETRY, /* need to retry but retry is not bad */
CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
- CHARGE_OOM_DIE, /* the current is killed because of OOM */
};
static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
unsigned int nr_pages, unsigned int min_pages,
- bool oom_check)
+ bool invoke_oom)
{
unsigned long csize = nr_pages * PAGE_SIZE;
struct mem_cgroup *mem_over_limit;
@@ -2612,14 +2655,10 @@
if (mem_cgroup_wait_acct_move(mem_over_limit))
return CHARGE_RETRY;
- /* If we don't need to call oom-killer at el, return immediately */
- if (!oom_check)
- return CHARGE_NOMEM;
- /* check OOM */
- if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
- return CHARGE_OOM_DIE;
+ if (invoke_oom)
+ mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
- return CHARGE_RETRY;
+ return CHARGE_NOMEM;
}
/*
@@ -2663,6 +2702,9 @@
|| fatal_signal_pending(current)))
goto bypass;
+ if (unlikely(task_in_memcg_oom(current)))
+ goto bypass;
+
/*
* We always charge the cgroup the mm_struct belongs to.
* The mm_struct's mem_cgroup changes on task migration if the
@@ -2722,7 +2764,7 @@
}
do {
- bool oom_check;
+ bool invoke_oom = oom && !nr_oom_retries;
/* If killed, bypass charge */
if (fatal_signal_pending(current)) {
@@ -2730,14 +2772,8 @@
goto bypass;
}
- oom_check = false;
- if (oom && !nr_oom_retries) {
- oom_check = true;
- nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- }
-
- ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
- oom_check);
+ ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+ nr_pages, invoke_oom);
switch (ret) {
case CHARGE_OK:
break;
@@ -2750,16 +2786,12 @@
css_put(&memcg->css);
goto nomem;
case CHARGE_NOMEM: /* OOM routine works */
- if (!oom) {
+ if (!oom || invoke_oom) {
css_put(&memcg->css);
goto nomem;
}
- /* If oom, we never return -ENOMEM */
nr_oom_retries--;
break;
- case CHARGE_OOM_DIE: /* Killed by OOM Killer */
- css_put(&memcg->css);
- goto bypass;
}
} while (ret != CHARGE_OK);
@@ -3186,11 +3218,11 @@
if (!s->memcg_params)
return -ENOMEM;
- INIT_WORK(&s->memcg_params->destroy,
- kmem_cache_destroy_work_func);
if (memcg) {
s->memcg_params->memcg = memcg;
s->memcg_params->root_cache = root_cache;
+ INIT_WORK(&s->memcg_params->destroy,
+ kmem_cache_destroy_work_func);
} else
s->memcg_params->is_root_cache = true;
@@ -5584,7 +5616,13 @@
const struct mem_cgroup_threshold *_a = a;
const struct mem_cgroup_threshold *_b = b;
- return _a->threshold - _b->threshold;
+ if (_a->threshold > _b->threshold)
+ return 1;
+
+ if (_a->threshold < _b->threshold)
+ return -1;
+
+ return 0;
}
static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
@@ -6296,16 +6334,6 @@
error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
mutex_unlock(&memcg_create_mutex);
- if (error) {
- /*
- * We call put now because our (and parent's) refcnts
- * are already in place. mem_cgroup_put() will internally
- * call __mem_cgroup_free, so return directly
- */
- mem_cgroup_put(memcg);
- if (parent->use_hierarchy)
- mem_cgroup_put(parent);
- }
return error;
}
@@ -6330,9 +6358,23 @@
static void mem_cgroup_css_offline(struct cgroup *cont)
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ struct cgroup *iter;
mem_cgroup_invalidate_reclaim_iterators(memcg);
+
+ /*
+ * This requires that offlining is serialized. Right now that is
+ * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+ */
+ rcu_read_lock();
+ cgroup_for_each_descendant_post(iter, cont) {
+ rcu_read_unlock();
+ mem_cgroup_reparent_charges(mem_cgroup_from_cont(iter));
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
mem_cgroup_reparent_charges(memcg);
+
mem_cgroup_destroy_all_caches(memcg);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index ceb0c7f..603f1fa 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -208,9 +208,9 @@
#endif
si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
- if ((flags & MF_ACTION_REQUIRED) && t == current) {
+ if ((flags & MF_ACTION_REQUIRED) && t->mm == current->mm) {
si.si_code = BUS_MCEERR_AR;
- ret = force_sig_info(SIGBUS, &si, t);
+ ret = force_sig_info(SIGBUS, &si, current);
} else {
/*
* Don't use force here, it's convenient if the signal
@@ -382,10 +382,12 @@
}
}
-static int task_early_kill(struct task_struct *tsk)
+static int task_early_kill(struct task_struct *tsk, int force_early)
{
if (!tsk->mm)
return 0;
+ if (force_early)
+ return 1;
if (tsk->flags & PF_MCE_PROCESS)
return !!(tsk->flags & PF_MCE_EARLY);
return sysctl_memory_failure_early_kill;
@@ -395,7 +397,7 @@
* Collect processes when the error hit an anonymous page.
*/
static void collect_procs_anon(struct page *page, struct list_head *to_kill,
- struct to_kill **tkc)
+ struct to_kill **tkc, int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -411,7 +413,7 @@
for_each_process (tsk) {
struct anon_vma_chain *vmac;
- if (!task_early_kill(tsk))
+ if (!task_early_kill(tsk, force_early))
continue;
anon_vma_interval_tree_foreach(vmac, &av->rb_root,
pgoff, pgoff) {
@@ -430,7 +432,7 @@
* Collect processes when the error hit a file mapped page.
*/
static void collect_procs_file(struct page *page, struct list_head *to_kill,
- struct to_kill **tkc)
+ struct to_kill **tkc, int force_early)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -441,7 +443,7 @@
for_each_process(tsk) {
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
- if (!task_early_kill(tsk))
+ if (!task_early_kill(tsk, force_early))
continue;
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
@@ -467,7 +469,8 @@
* First preallocate one tokill structure outside the spin locks,
* so that we can kill at least one process reasonably reliable.
*/
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+ int force_early)
{
struct to_kill *tk;
@@ -478,9 +481,9 @@
if (!tk)
return;
if (PageAnon(page))
- collect_procs_anon(page, tokill, &tk);
+ collect_procs_anon(page, tokill, &tk, force_early);
else
- collect_procs_file(page, tokill, &tk);
+ collect_procs_file(page, tokill, &tk, force_early);
kfree(tk);
}
@@ -854,14 +857,14 @@
* the pages and send SIGBUS to the processes if the data was dirty.
*/
static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
- int trapno, int flags)
+ int trapno, int flags, struct page **hpagep)
{
enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
struct address_space *mapping;
LIST_HEAD(tokill);
int ret;
int kill = 1, forcekill;
- struct page *hpage = compound_head(p);
+ struct page *hpage = *hpagep;
struct page *ppage;
if (PageReserved(p) || PageSlab(p))
@@ -936,6 +939,21 @@
BUG_ON(!PageHWPoison(p));
return SWAP_FAIL;
}
+ /*
+ * We pinned the head page for hwpoison handling,
+ * now we split the thp and we are interested in
+ * the hwpoisoned raw page, so move the refcount
+ * to it. Similarly, page lock is shifted.
+ */
+ if (hpage != p) {
+ if (!(flags & MF_COUNT_INCREASED)) {
+ put_page(hpage);
+ get_page(p);
+ }
+ lock_page(p);
+ unlock_page(hpage);
+ *hpagep = p;
+ }
/* THP is split, so ppage should be the real poisoned page. */
ppage = p;
}
@@ -950,19 +968,13 @@
* there's nothing that can be done.
*/
if (kill)
- collect_procs(ppage, &tokill);
-
- if (hpage != ppage)
- lock_page(ppage);
+ collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);
ret = try_to_unmap(ppage, ttu);
if (ret != SWAP_SUCCESS)
printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
pfn, page_mapcount(ppage));
- if (hpage != ppage)
- unlock_page(ppage);
-
/*
* Now that the dirty bit has been propagated to the
* struct page and all unmaps done we can decide if
@@ -1074,15 +1086,16 @@
return 0;
} else if (PageHuge(hpage)) {
/*
- * Check "just unpoisoned", "filter hit", and
- * "race with other subpage."
+ * Check "filter hit" and "race with other subpage."
*/
lock_page(hpage);
- if (!PageHWPoison(hpage)
- || (hwpoison_filter(p) && TestClearPageHWPoison(p))
- || (p != hpage && TestSetPageHWPoison(hpage))) {
- atomic_long_sub(nr_pages, &num_poisoned_pages);
- return 0;
+ if (PageHWPoison(hpage)) {
+ if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+ || (p != hpage && TestSetPageHWPoison(hpage))) {
+ atomic_long_sub(nr_pages, &num_poisoned_pages);
+ unlock_page(hpage);
+ return 0;
+ }
}
set_page_hwpoison_huge_page(hpage);
res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1143,6 +1156,8 @@
*/
if (!PageHWPoison(p)) {
printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+ atomic_long_sub(nr_pages, &num_poisoned_pages);
+ put_page(hpage);
res = 0;
goto out;
}
@@ -1179,8 +1194,12 @@
/*
* Now take care of user space mappings.
* Abort on fail: __delete_from_page_cache() assumes unmapped page.
+ *
+ * When the raw error page is thp tail page, hpage points to the raw
+ * page after thp split.
*/
- if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) {
+ if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
+ != SWAP_SUCCESS) {
printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
res = -EBUSY;
goto out;
@@ -1410,7 +1429,8 @@
/*
* Isolate the page, so that it doesn't get reallocated if it
- * was free.
+ * was free. This flag should be kept set until the source page
+ * is freed and PG_hwpoison on it is set.
*/
set_migratetype_isolate(p, true);
/*
@@ -1433,7 +1453,6 @@
/* Not a free page */
ret = 1;
}
- unset_migratetype_isolate(p, MIGRATE_MOVABLE);
unlock_memory_hotplug();
return ret;
}
@@ -1489,12 +1508,17 @@
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
pfn, ret, page->flags);
} else {
- set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
- atomic_long_add(1 << compound_trans_order(hpage),
- &num_poisoned_pages);
+ /* overcommit hugetlb page will be freed to buddy */
+ if (PageHuge(page)) {
+ set_page_hwpoison_huge_page(hpage);
+ dequeue_hwpoisoned_huge_page(hpage);
+ atomic_long_add(1 << compound_order(hpage),
+ &num_poisoned_pages);
+ } else {
+ SetPageHWPoison(page);
+ atomic_long_inc(&num_poisoned_pages);
+ }
}
- /* keep elevated page count for bad page */
return ret;
}
@@ -1526,7 +1550,7 @@
{
int ret;
unsigned long pfn = page_to_pfn(page);
- struct page *hpage = compound_trans_head(page);
+ struct page *hpage = compound_head(page);
if (PageHWPoison(page)) {
pr_info("soft offline: %#lx page already poisoned\n", pfn);
@@ -1559,7 +1583,7 @@
atomic_long_inc(&num_poisoned_pages);
}
}
- /* keep elevated page count for bad page */
+ unset_migratetype_isolate(page, MIGRATE_MOVABLE);
return ret;
}
@@ -1625,7 +1649,22 @@
if (ret > 0)
ret = -EIO;
} else {
+ /*
+ * After page migration succeeds, the source page can
+ * be trapped in pagevec and actual freeing is delayed.
+ * Freeing code works differently based on PG_hwpoison,
+ * so there's a race. We need to make sure that the
+ * source page should be freed back to buddy before
+ * setting PG_hwpoison.
+ */
+ if (!is_free_buddy_page(page))
+ lru_add_drain_all();
+ if (!is_free_buddy_page(page))
+ drain_all_pages();
SetPageHWPoison(page);
+ if (!is_free_buddy_page(page))
+ pr_info("soft offline: %#lx: page leaked\n",
+ pfn);
atomic_long_inc(&num_poisoned_pages);
}
} else {
diff --git a/mm/memory.c b/mm/memory.c
index 61a262b..7c86434 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,8 @@
unsigned long zero_pfn __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;
+EXPORT_SYMBOL(zero_pfn);
+
/*
* CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
*/
@@ -211,14 +213,15 @@
* tear-down from @mm. The @fullmm argument is used when @mm is without
* users and we're going to destroy the full address space (exit/execve).
*/
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
{
tlb->mm = mm;
- tlb->fullmm = fullmm;
+ /* Is it from 0 to ~0? */
+ tlb->fullmm = !(start | (end+1));
tlb->need_flush_all = 0;
- tlb->start = -1UL;
- tlb->end = 0;
+ tlb->start = start;
+ tlb->end = end;
tlb->need_flush = 0;
tlb->local.next = NULL;
tlb->local.nr = 0;
@@ -258,8 +261,6 @@
{
struct mmu_gather_batch *batch, *next;
- tlb->start = start;
- tlb->end = end;
tlb_flush_mmu(tlb);
/* keep the page table cache within bounds */
@@ -835,20 +836,20 @@
if (!pte_file(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
- if (swap_duplicate(entry) < 0)
- return entry.val;
+ if (likely(!non_swap_entry(entry))) {
+ if (swap_duplicate(entry) < 0)
+ return entry.val;
- /* make sure dst_mm is on swapoff's mmlist. */
- if (unlikely(list_empty(&dst_mm->mmlist))) {
- spin_lock(&mmlist_lock);
- if (list_empty(&dst_mm->mmlist))
- list_add(&dst_mm->mmlist,
- &src_mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- if (likely(!non_swap_entry(entry)))
+ /* make sure dst_mm is on swapoff's mmlist. */
+ if (unlikely(list_empty(&dst_mm->mmlist))) {
+ spin_lock(&mmlist_lock);
+ if (list_empty(&dst_mm->mmlist))
+ list_add(&dst_mm->mmlist,
+ &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
rss[MM_SWAPENTS]++;
- else if (is_migration_entry(entry)) {
+ } else if (is_migration_entry(entry)) {
page = migration_entry_to_page(entry);
if (PageAnon(page))
@@ -1203,13 +1204,23 @@
* and page-free while holding it.
*/
if (force_flush) {
+ unsigned long old_end;
+
force_flush = 0;
-#ifdef HAVE_GENERIC_MMU_GATHER
- tlb->start = addr;
- tlb->end = end;
-#endif
+ /*
+ * Flush the TLB just for the previous segment,
+ * then update the range to be the remaining
+ * TLB range.
+ */
+ old_end = tlb->end;
+ tlb->end = addr;
+
tlb_flush_mmu(tlb);
+
+ tlb->start = addr;
+ tlb->end = old_end;
+
if (addr != end)
goto again;
}
@@ -1396,7 +1407,7 @@
unsigned long end = start + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, start, end);
for ( ; vma && vma->vm_start < end; vma = vma->vm_next)
@@ -1422,7 +1433,7 @@
unsigned long end = address + size;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, address, end);
update_hiwater_rss(mm);
mmu_notifier_invalidate_range_start(mm, address, end);
unmap_single_vma(&tlb, vma, address, end, details);
@@ -1835,7 +1846,8 @@
else
return -EFAULT;
}
- if (ret & VM_FAULT_SIGBUS)
+ if (ret & (VM_FAULT_SIGBUS |
+ VM_FAULT_SIGSEGV))
return i ? i : -EFAULT;
BUG();
}
@@ -1928,19 +1940,24 @@
unsigned long address, unsigned int fault_flags)
{
struct vm_area_struct *vma;
+ vm_flags_t vm_flags;
int ret;
vma = find_extend_vma(mm, address);
if (!vma || address < vma->vm_start)
return -EFAULT;
+ vm_flags = (fault_flags & FAULT_FLAG_WRITE) ? VM_WRITE : VM_READ;
+ if (!(vm_flags & vma->vm_flags))
+ return -EFAULT;
+
ret = handle_mm_fault(mm, vma, address, fault_flags);
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
return -ENOMEM;
if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
return -EHWPOISON;
- if (ret & VM_FAULT_SIGBUS)
+ if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
return -EFAULT;
BUG();
}
@@ -3186,7 +3203,7 @@
if (prev && prev->vm_end == address)
return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM;
- expand_downwards(vma, address - PAGE_SIZE);
+ return expand_downwards(vma, address - PAGE_SIZE);
}
if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) {
struct vm_area_struct *next = vma->vm_next;
@@ -3195,7 +3212,7 @@
if (next && next->vm_start == address + PAGE_SIZE)
return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM;
- expand_upwards(vma, address + PAGE_SIZE);
+ return expand_upwards(vma, address + PAGE_SIZE);
}
return 0;
}
@@ -3217,7 +3234,7 @@
/* Check if we need to add a guard page to the stack */
if (check_stack_guard_page(vma, address) < 0)
- return VM_FAULT_SIGBUS;
+ return VM_FAULT_SIGSEGV;
/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE)) {
@@ -3516,12 +3533,12 @@
}
int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
- unsigned long addr, int current_nid)
+ unsigned long addr, int page_nid)
{
get_page(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
- if (current_nid == numa_node_id())
+ if (page_nid == numa_node_id())
count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL);
return mpol_misplaced(page, vma, addr);
@@ -3532,7 +3549,7 @@
{
struct page *page = NULL;
spinlock_t *ptl;
- int current_nid = -1;
+ int page_nid = -1;
int target_nid;
bool migrated = false;
@@ -3562,15 +3579,10 @@
return 0;
}
- current_nid = page_to_nid(page);
- target_nid = numa_migrate_prep(page, vma, addr, current_nid);
+ page_nid = page_to_nid(page);
+ target_nid = numa_migrate_prep(page, vma, addr, page_nid);
pte_unmap_unlock(ptep, ptl);
if (target_nid == -1) {
- /*
- * Account for the fault against the current node if it not
- * being replaced regardless of where the page is located.
- */
- current_nid = numa_node_id();
put_page(page);
goto out;
}
@@ -3578,11 +3590,11 @@
/* Migrate to the requested node */
migrated = migrate_misplaced_page(page, target_nid);
if (migrated)
- current_nid = target_nid;
+ page_nid = target_nid;
out:
- if (current_nid != -1)
- task_numa_fault(current_nid, 1, migrated);
+ if (page_nid != -1)
+ task_numa_fault(page_nid, 1, migrated);
return 0;
}
@@ -3597,7 +3609,6 @@
unsigned long offset;
spinlock_t *ptl;
bool numa = false;
- int local_nid = numa_node_id();
spin_lock(&mm->page_table_lock);
pmd = *pmdp;
@@ -3620,9 +3631,10 @@
for (addr = _addr + offset; addr < _addr + PMD_SIZE; pte++, addr += PAGE_SIZE) {
pte_t pteval = *pte;
struct page *page;
- int curr_nid = local_nid;
+ int page_nid = -1;
int target_nid;
- bool migrated;
+ bool migrated = false;
+
if (!pte_present(pteval))
continue;
if (!pte_numa(pteval))
@@ -3644,25 +3656,19 @@
if (unlikely(page_mapcount(page) != 1))
continue;
- /*
- * Note that the NUMA fault is later accounted to either
- * the node that is currently running or where the page is
- * migrated to.
- */
- curr_nid = local_nid;
- target_nid = numa_migrate_prep(page, vma, addr,
- page_to_nid(page));
- if (target_nid == -1) {
+ page_nid = page_to_nid(page);
+ target_nid = numa_migrate_prep(page, vma, addr, page_nid);
+ pte_unmap_unlock(pte, ptl);
+ if (target_nid != -1) {
+ migrated = migrate_misplaced_page(page, target_nid);
+ if (migrated)
+ page_nid = target_nid;
+ } else {
put_page(page);
- continue;
}
- /* Migrate to the requested node */
- pte_unmap_unlock(pte, ptl);
- migrated = migrate_misplaced_page(page, target_nid);
- if (migrated)
- curr_nid = target_nid;
- task_numa_fault(curr_nid, 1, migrated);
+ if (page_nid != -1)
+ task_numa_fault(page_nid, 1, migrated);
pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
}
@@ -3751,22 +3757,14 @@
/*
* By the time we get here, we already hold the mm semaphore
*/
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, unsigned int flags)
+static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- __set_current_state(TASK_RUNNING);
-
- count_vm_event(PGFAULT);
- mem_cgroup_count_vm_event(mm, PGFAULT);
-
- /* do counter updates before entering really critical section. */
- check_sync_rss_stat(current);
-
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, flags);
@@ -3847,6 +3845,43 @@
return handle_pte_fault(mm, vma, address, pte, pmd, flags);
}
+int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
+{
+ int ret;
+
+ __set_current_state(TASK_RUNNING);
+
+ count_vm_event(PGFAULT);
+ mem_cgroup_count_vm_event(mm, PGFAULT);
+
+ /* do counter updates before entering really critical section. */
+ check_sync_rss_stat(current);
+
+ /*
+ * Enable the memcg OOM handling for faults triggered in user
+ * space. Kernel faults are handled more gracefully.
+ */
+ if (flags & FAULT_FLAG_USER)
+ mem_cgroup_oom_enable();
+
+ ret = __handle_mm_fault(mm, vma, address, flags);
+
+ if (flags & FAULT_FLAG_USER) {
+ mem_cgroup_oom_disable();
+ /*
+ * The task may have entered a memcg OOM situation but
+ * if the allocation error was handled gracefully (no
+ * VM_FAULT_OOM), there is no need to kill anything.
+ * Just clean up the OOM state peacefully.
+ */
+ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+ mem_cgroup_oom_synchronize(false);
+ }
+
+ return ret;
+}
+
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
@@ -4056,7 +4091,7 @@
if (follow_phys(vma, addr, write, &prot, &phys_addr))
return -EINVAL;
- maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+ maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot);
if (write)
memcpy_toio(maddr + offset, buf, len);
else
@@ -4065,6 +4100,7 @@
return len;
}
+EXPORT_SYMBOL_GPL(generic_access_phys);
#endif
/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1ad92b4..2298237 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1039,6 +1039,10 @@
return NULL;
arch_refresh_nodedata(nid, pgdat);
+ } else {
+ /* Reset the nr_zones and classzone_idx to 0 before reuse */
+ pgdat->nr_zones = 0;
+ pgdat->classzone_idx = 0;
}
/* we can use NODE_DATA(nid) from here */
@@ -1802,15 +1806,6 @@
if (is_vmalloc_addr(zone->wait_table))
vfree(zone->wait_table);
}
-
- /*
- * Since there is no way to guarentee the address of pgdat/zone is not
- * on stack of any kernel threads or used by other kernel objects
- * without reference counting or other symchronizing method, do not
- * reset node_data and free pgdat here. Just reset it to 0 and reuse
- * the memory when the node is online again.
- */
- memset(pgdat, 0, sizeof(*pgdat));
}
EXPORT_SYMBOL(try_offline_node);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 7431001..b2061bb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -608,19 +608,18 @@
* If pagelist != NULL then isolate pages from the LRU and
* put them on the pagelist.
*/
-static struct vm_area_struct *
+static int
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
const nodemask_t *nodes, unsigned long flags, void *private)
{
- int err;
- struct vm_area_struct *first, *vma, *prev;
+ int err = 0;
+ struct vm_area_struct *vma, *prev;
-
- first = find_vma(mm, start);
- if (!first)
- return ERR_PTR(-EFAULT);
+ vma = find_vma(mm, start);
+ if (!vma)
+ return -EFAULT;
prev = NULL;
- for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+ for (; vma && vma->vm_start < end; vma = vma->vm_next) {
unsigned long endvma = vma->vm_end;
if (endvma > end)
@@ -630,9 +629,9 @@
if (!(flags & MPOL_MF_DISCONTIG_OK)) {
if (!vma->vm_next && vma->vm_end < end)
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
if (prev && prev->vm_end < vma->vm_start)
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
}
if (is_vm_hugetlb_page(vma))
@@ -649,15 +648,13 @@
err = check_pgd_range(vma, start, endvma, nodes,
flags, private);
- if (err) {
- first = ERR_PTR(err);
+ if (err)
break;
- }
}
next:
prev = vma;
}
- return first;
+ return err;
}
/*
@@ -732,7 +729,10 @@
if (prev) {
vma = prev;
next = vma->vm_next;
- continue;
+ if (mpol_equal(vma_policy(vma), new_pol))
+ continue;
+ /* vma_merge() joined vma && vma->next, case 8 */
+ goto replace;
}
if (vma->vm_start != vmstart) {
err = split_vma(vma->vm_mm, vma, vmstart, 1);
@@ -744,6 +744,7 @@
if (err)
goto out;
}
+ replace:
err = vma_replace_policy(vma, new_pol);
if (err)
goto out;
@@ -1134,16 +1135,17 @@
/*
* Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
* Search forward from there, if not. N.B., this assumes that the
* list of pages handed to migrate_pages()--which is how we get here--
* is in virtual address order.
*/
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
{
- struct vm_area_struct *vma = (struct vm_area_struct *)private;
+ struct vm_area_struct *vma;
unsigned long uninitialized_var(address);
+ vma = find_vma(current->mm, start);
while (vma) {
address = page_address_in_vma(page, vma);
if (address != -EFAULT)
@@ -1169,7 +1171,7 @@
return -ENOSYS;
}
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
{
return NULL;
}
@@ -1179,7 +1181,6 @@
unsigned short mode, unsigned short mode_flags,
nodemask_t *nmask, unsigned long flags)
{
- struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
struct mempolicy *new;
unsigned long end;
@@ -1245,11 +1246,9 @@
if (err)
goto mpol_out;
- vma = check_range(mm, start, end, nmask,
+ err = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
-
- err = PTR_ERR(vma); /* maybe ... */
- if (!IS_ERR(vma))
+ if (!err)
err = mbind_range(mm, start, end, new);
if (!err) {
@@ -1257,9 +1256,8 @@
if (!list_empty(&pagelist)) {
WARN_ON_ONCE(flags & MPOL_MF_LAZY);
- nr_failed = migrate_pages(&pagelist, new_vma_page,
- (unsigned long)vma,
- MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+ nr_failed = migrate_pages(&pagelist, new_page,
+ start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
if (nr_failed)
putback_lru_pages(&pagelist);
}
@@ -2088,7 +2086,6 @@
} else
*new = *old;
- rcu_read_lock();
if (current_cpuset_is_being_rebound()) {
nodemask_t mems = cpuset_mems_allowed(current);
if (new->flags & MPOL_F_REBINDING)
@@ -2096,7 +2093,6 @@
else
mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
}
- rcu_read_unlock();
atomic_set(&new->refcnt, 1);
return new;
}
@@ -2797,7 +2793,7 @@
*/
VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
- if (!pol || pol == &default_policy)
+ if (!pol || pol == &default_policy || (pol->flags & MPOL_F_MORON))
mode = MPOL_DEFAULT;
else
mode = pol->mode;
diff --git a/mm/migrate.c b/mm/migrate.c
index 6f0c244..a88c12f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -103,7 +103,7 @@
list_del(&page->lru);
dec_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
- if (unlikely(balloon_page_movable(page)))
+ if (unlikely(isolated_balloon_page(page)))
balloon_page_putback(page);
else
putback_lru_page(page);
@@ -1710,12 +1710,13 @@
unlock_page(new_page);
put_page(new_page); /* Free it */
- unlock_page(page);
+ /* Retake the callers reference and putback on LRU */
+ get_page(page);
putback_lru_page(page);
+ mod_zone_page_state(page_zone(page),
+ NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
- count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
- isolated = 0;
- goto out;
+ goto out_unlock;
}
/*
@@ -1732,9 +1733,9 @@
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
entry = pmd_mkhuge(entry);
- page_add_new_anon_rmap(new_page, vma, haddr);
-
+ pmdp_clear_flush(vma, haddr, pmd);
set_pmd_at(mm, haddr, pmd, entry);
+ page_add_new_anon_rmap(new_page, vma, haddr);
update_mmu_cache_pmd(vma, address, &entry);
page_remove_rmap(page);
/*
@@ -1753,7 +1754,6 @@
count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
-out:
mod_zone_page_state(page_zone(page),
NR_ISOLATED_ANON + page_lru,
-HPAGE_PMD_NR);
@@ -1762,6 +1762,11 @@
out_fail:
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
out_dropref:
+ entry = pmd_mknonnuma(entry);
+ set_pmd_at(mm, haddr, pmd, entry);
+ update_mmu_cache_pmd(vma, address, &entry);
+
+out_unlock:
unlock_page(page);
put_page(page);
return 0;
diff --git a/mm/mlock.c b/mm/mlock.c
index 79b7cf7..713e462 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -76,6 +76,7 @@
*/
void mlock_vma_page(struct page *page)
{
+ /* Serialize with page migration */
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page)) {
@@ -106,6 +107,7 @@
{
unsigned int page_mask = 0;
+ /* For try_to_munlock() and to serialize with page migration */
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page)) {
diff --git a/mm/mmap.c b/mm/mmap.c
index f681e18..70ff9b4 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -127,7 +127,7 @@
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
- unsigned long free, allowed, reserve;
+ long free, allowed, reserve;
vm_acct_memory(pages);
@@ -193,7 +193,7 @@
*/
if (mm) {
reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
- allowed -= min(mm->total_vm / 32, reserve);
+ allowed -= min_t(long, mm->total_vm / 32, reserve);
}
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
@@ -865,7 +865,7 @@
if (next->anon_vma)
anon_vma_merge(vma, next);
mm->map_count--;
- vma_set_policy(vma, vma_policy(next));
+ mpol_put(vma_policy(next));
kmem_cache_free(vm_area_cachep, next);
/*
* In mprotect's case 6 (see comments on vma_merge),
@@ -1853,7 +1853,7 @@
struct vm_area_struct *vma;
struct vm_unmapped_area_info info;
- if (len > TASK_SIZE)
+ if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
@@ -1862,7 +1862,7 @@
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
+ if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
(!vma || addr + len <= vma->vm_start))
return addr;
}
@@ -1901,7 +1901,7 @@
struct vm_unmapped_area_info info;
/* requested length too big for entire address space */
- if (len > TASK_SIZE)
+ if (len > TASK_SIZE - mmap_min_addr)
return -ENOMEM;
if (flags & MAP_FIXED)
@@ -1911,14 +1911,14 @@
if (addr) {
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
+ if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
(!vma || addr + len <= vma->vm_start))
return addr;
}
info.flags = VM_UNMAPPED_AREA_TOPDOWN;
info.length = len;
- info.low_limit = PAGE_SIZE;
+ info.low_limit = max(PAGE_SIZE, mmap_min_addr);
info.high_limit = mm->mmap_base;
info.align_mask = 0;
addr = vm_unmapped_area(&info);
@@ -2056,14 +2056,17 @@
{
struct mm_struct *mm = vma->vm_mm;
struct rlimit *rlim = current->signal->rlim;
- unsigned long new_start;
+ unsigned long new_start, actual_size;
/* address space limit tests */
if (!may_expand_vm(mm, grow))
return -ENOMEM;
/* Stack limit test */
- if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
+ actual_size = size;
+ if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN)))
+ actual_size -= PAGE_SIZE;
+ if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
return -ENOMEM;
/* mlock limit tests */
@@ -2356,7 +2359,7 @@
struct mmu_gather tlb;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, start, end);
update_hiwater_rss(mm);
unmap_vmas(&tlb, vma, start, end);
free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
@@ -2735,7 +2738,7 @@
lru_add_drain();
flush_cache_mm(mm);
- tlb_gather_mmu(&tlb, mm, 1);
+ tlb_gather_mmu(&tlb, mm, 0, -1);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 94722a4..e9f65aa 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -135,6 +135,7 @@
pmd_t *pmd;
unsigned long next;
unsigned long pages = 0;
+ unsigned long nr_huge_updates = 0;
bool all_same_node;
pmd = pmd_offset(pud, addr);
@@ -146,6 +147,7 @@
else if (change_huge_pmd(vma, pmd, addr, newprot,
prot_numa)) {
pages += HPAGE_PMD_NR;
+ nr_huge_updates++;
continue;
}
/* fall through */
@@ -165,6 +167,9 @@
change_pmd_protnuma(vma->vm_mm, addr, pmd);
} while (pmd++, addr = next, addr != end);
+ if (nr_huge_updates)
+ count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
+
return pages;
}
@@ -201,6 +206,7 @@
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
+ set_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
@@ -212,6 +218,7 @@
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
+ clear_tlb_flush_pending(mm);
return pages;
}
diff --git a/mm/mremap.c b/mm/mremap.c
index 463a257..2201d06 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -175,10 +175,17 @@
break;
if (pmd_trans_huge(*old_pmd)) {
int err = 0;
- if (extent == HPAGE_PMD_SIZE)
+ if (extent == HPAGE_PMD_SIZE) {
+ VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+ /* See comment in move_ptes() */
+ if (need_rmap_locks)
+ anon_vma_lock_write(vma->anon_vma);
err = move_huge_pmd(vma, new_vma, old_addr,
new_addr, old_end,
old_pmd, new_pmd);
+ if (need_rmap_locks)
+ anon_vma_unlock_write(vma->anon_vma);
+ }
if (err > 0) {
need_flush = true;
continue;
diff --git a/mm/nommu.c b/mm/nommu.c
index 298884d..d9d07a5 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1898,7 +1898,7 @@
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
- unsigned long free, allowed, reserve;
+ long free, allowed, reserve;
vm_acct_memory(pages);
@@ -1963,7 +1963,7 @@
*/
if (mm) {
reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
- allowed -= min(mm->total_vm / 32, reserve);
+ allowed -= min_t(long, mm->total_vm / 32, reserve);
}
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 79e451a..4d87d7c 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -47,19 +47,21 @@
#ifdef CONFIG_NUMA
/**
* has_intersects_mems_allowed() - check task eligiblity for kill
- * @tsk: task struct of which task to consider
+ * @start: task struct of which task to consider
* @mask: nodemask passed to page allocator for mempolicy ooms
*
* Task eligibility is determined by whether or not a candidate task, @tsk,
* shares the same mempolicy nodes as current if it is bound by such a policy
* and whether or not it has the same set of allowed cpuset nodes.
*/
-static bool has_intersects_mems_allowed(struct task_struct *tsk,
+static bool has_intersects_mems_allowed(struct task_struct *start,
const nodemask_t *mask)
{
- struct task_struct *start = tsk;
+ struct task_struct *tsk;
+ bool ret = false;
- do {
+ rcu_read_lock();
+ for_each_thread(start, tsk) {
if (mask) {
/*
* If this is a mempolicy constrained oom, tsk's
@@ -67,19 +69,20 @@
* mempolicy intersects current, otherwise it may be
* needlessly killed.
*/
- if (mempolicy_nodemask_intersects(tsk, mask))
- return true;
+ ret = mempolicy_nodemask_intersects(tsk, mask);
} else {
/*
* This is not a mempolicy constrained oom, so only
* check the mems of tsk's cpuset.
*/
- if (cpuset_mems_allowed_intersects(current, tsk))
- return true;
+ ret = cpuset_mems_allowed_intersects(current, tsk);
}
- } while_each_thread(start, tsk);
+ if (ret)
+ break;
+ }
+ rcu_read_unlock();
- return false;
+ return ret;
}
#else
static bool has_intersects_mems_allowed(struct task_struct *tsk,
@@ -97,16 +100,21 @@
*/
struct task_struct *find_lock_task_mm(struct task_struct *p)
{
- struct task_struct *t = p;
+ struct task_struct *t;
- do {
+ rcu_read_lock();
+
+ for_each_thread(p, t) {
task_lock(t);
if (likely(t->mm))
- return t;
+ goto found;
task_unlock(t);
- } while_each_thread(p, t);
+ }
+ t = NULL;
+found:
+ rcu_read_unlock();
- return NULL;
+ return t;
}
/* return true if the task is not adequate as candidate victim task. */
@@ -170,7 +178,7 @@
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
- adj -= 30;
+ points -= (points * 3) / 100;
/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;
@@ -301,7 +309,7 @@
unsigned long chosen_points = 0;
rcu_read_lock();
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
unsigned int points;
switch (oom_scan_process_thread(p, totalpages, nodemask,
@@ -323,7 +331,7 @@
chosen = p;
chosen_points = points;
}
- } while_each_thread(g, p);
+ }
if (chosen)
get_task_struct(chosen);
rcu_read_unlock();
@@ -394,6 +402,23 @@
dump_tasks(memcg, nodemask);
}
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+ return atomic_read(&oom_kills);
+}
+
+void note_oom_kill(void)
+{
+ atomic_inc(&oom_kills);
+}
+
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* Must be called while holding a reference to p, which will be released upon
@@ -406,7 +431,7 @@
{
struct task_struct *victim = p;
struct task_struct *child;
- struct task_struct *t = p;
+ struct task_struct *t;
struct mm_struct *mm;
unsigned int victim_points = 0;
static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
@@ -437,7 +462,7 @@
* still freeing memory.
*/
read_lock(&tasklist_lock);
- do {
+ for_each_thread(p, t) {
list_for_each_entry(child, &t->children, sibling) {
unsigned int child_points;
@@ -455,13 +480,11 @@
get_task_struct(victim);
}
}
- } while_each_thread(p, t);
+ }
read_unlock(&tasklist_lock);
- rcu_read_lock();
p = find_lock_task_mm(victim);
if (!p) {
- rcu_read_unlock();
put_task_struct(victim);
return;
} else if (victim != p) {
@@ -487,6 +510,7 @@
* That thread will now get access to memory reserves since it has a
* pending fatal signal.
*/
+ rcu_read_lock();
for_each_process(p)
if (p->mm == mm && !same_thread_group(p, victim) &&
!(p->flags & PF_KTHREAD)) {
@@ -678,9 +702,12 @@
*/
void pagefault_out_of_memory(void)
{
- struct zonelist *zonelist = node_zonelist(first_online_node,
- GFP_KERNEL);
+ struct zonelist *zonelist;
+ if (mem_cgroup_oom_synchronize(true))
+ return;
+
+ zonelist = node_zonelist(first_online_node, GFP_KERNEL);
if (try_set_zonelist_oom(zonelist, GFP_KERNEL)) {
out_of_memory(NULL, 0, 0, NULL, false);
clear_zonelist_oom(zonelist, GFP_KERNEL);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4514ad7..b034f79 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -188,6 +188,26 @@
* global dirtyable memory first.
*/
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache. This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+ unsigned long nr_pages;
+
+ nr_pages = zone_page_state(zone, NR_FREE_PAGES);
+ nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+
+ nr_pages += zone_page_state(zone, NR_INACTIVE_FILE);
+ nr_pages += zone_page_state(zone, NR_ACTIVE_FILE);
+
+ return nr_pages;
+}
+
static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
@@ -195,11 +215,9 @@
unsigned long x = 0;
for_each_node_state(node, N_HIGH_MEMORY) {
- struct zone *z =
- &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+ struct zone *z = &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
- x += zone_page_state(z, NR_FREE_PAGES) +
- zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+ x += zone_dirtyable_memory(z);
}
/*
* Unreclaimable memory (kernel memory or anonymous memory
@@ -235,9 +253,12 @@
{
unsigned long x;
- x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+ x = global_page_state(NR_FREE_PAGES);
x -= min(x, dirty_balance_reserve);
+ x += global_page_state(NR_INACTIVE_FILE);
+ x += global_page_state(NR_ACTIVE_FILE);
+
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
@@ -289,32 +310,6 @@
}
/**
- * zone_dirtyable_memory - number of dirtyable pages in a zone
- * @zone: the zone
- *
- * Returns the zone's number of pages potentially available for dirty
- * page cache. This is the base value for the per-zone dirty limits.
- */
-static unsigned long zone_dirtyable_memory(struct zone *zone)
-{
- /*
- * The effective global number of dirtyable pages may exclude
- * highmem as a big-picture measure to keep the ratio between
- * dirty memory and lowmem reasonable.
- *
- * But this function is purely about the individual zone and a
- * highmem zone can hold its share of dirty pages, so we don't
- * care about vm_highmem_is_dirtyable here.
- */
- unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
- zone_reclaimable_pages(zone);
-
- /* don't allow this to underflow */
- nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
- return nr_pages;
-}
-
-/**
* zone_dirty_limit - maximum number of dirty pages allowed in a zone
* @zone: the zone
*
@@ -798,8 +793,11 @@
* bw * elapsed + write_bandwidth * (period - elapsed)
* write_bandwidth = ---------------------------------------------------
* period
+ *
+ * @written may have decreased due to account_page_redirty().
+ * Avoid underflowing @bw calculation.
*/
- bw = written - bdi->written_stamp;
+ bw = written - min(written, bdi->written_stamp);
bw *= HZ;
if (unlikely(elapsed > period)) {
do_div(bw, elapsed);
@@ -863,7 +861,7 @@
unsigned long now)
{
static DEFINE_SPINLOCK(dirty_lock);
- static unsigned long update_time;
+ static unsigned long update_time = INITIAL_JIFFIES;
/*
* check locklessly first to optimize away locking for the most time
@@ -1104,11 +1102,11 @@
return 1;
}
-static long bdi_max_pause(struct backing_dev_info *bdi,
- unsigned long bdi_dirty)
+static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
+ unsigned long bdi_dirty)
{
- long bw = bdi->avg_write_bandwidth;
- long t;
+ unsigned long bw = bdi->avg_write_bandwidth;
+ unsigned long t;
/*
* Limit pause time for small memory systems. If sleeping for too long
@@ -1120,7 +1118,7 @@
t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
t++;
- return min_t(long, t, MAX_PAUSE);
+ return min_t(unsigned long, t, MAX_PAUSE);
}
static long bdi_min_pause(struct backing_dev_info *bdi,
@@ -2031,11 +2029,12 @@
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
+ unsigned long flags;
if (!mapping)
return 1;
- spin_lock_irq(&mapping->tree_lock);
+ spin_lock_irqsave(&mapping->tree_lock, flags);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
@@ -2044,7 +2043,7 @@
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
- spin_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c3edb62..494a081 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -360,9 +360,11 @@
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
- __SetPageTail(p);
set_page_count(p, 0);
p->first_page = page;
+ /* Make sure p->first_page is always valid for PageTail() */
+ smp_wmb();
+ __SetPageTail(p);
}
}
@@ -2118,6 +2120,14 @@
}
/*
+ * PM-freezer should be notified that there might be an OOM killer on
+ * its way to kill and wake somebody up. This is too early and we might
+ * end up not killing anything but false positives are acceptable.
+ * See freeze_processes.
+ */
+ note_oom_kill();
+
+ /*
* Go through the zonelist yet one more time, keep very high watermark
* here, this is only to catch a parallel oom killing, we must fail if
* we're still under heavy pressure.
@@ -2337,7 +2347,7 @@
gfp_to_alloc_flags(gfp_t gfp_mask)
{
int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- const gfp_t wait = gfp_mask & __GFP_WAIT;
+ const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2346,20 +2356,20 @@
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
- * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+ * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
- if (!wait) {
+ if (atomic) {
/*
- * Not worth trying to allocate harder for
- * __GFP_NOMEMALLOC even if it can't schedule.
+ * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+ * if it can't schedule.
*/
- if (!(gfp_mask & __GFP_NOMEMALLOC))
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
alloc_flags |= ALLOC_HARDER;
/*
- * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+ * comment for __cpuset_node_allowed_softwall().
*/
alloc_flags &= ~ALLOC_CPUSET;
} else if (unlikely(rt_task(current)) && !in_interrupt())
@@ -6142,6 +6152,10 @@
list_del(&page->lru);
rmv_page_order(page);
zone->free_area[order].nr_free--;
+#ifdef CONFIG_HIGHMEM
+ if (PageHighMem(page))
+ totalhigh_pages -= 1 << order;
+#endif
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 6d757e3a..e007236 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -170,6 +170,7 @@
sizeof(struct page_cgroup) * PAGES_PER_SECTION;
BUG_ON(PageReserved(page));
+ kmemleak_free(addr);
free_pages_exact(addr, table_size);
}
}
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5da2cbc..9056d22 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -199,7 +199,10 @@
*/
if ((vma->vm_start <= addr) &&
(vma->vm_flags & VM_PFNMAP)) {
- next = vma->vm_end;
+ if (walk->pte_hole)
+ err = walk->pte_hole(addr, next, walk);
+ if (err)
+ break;
pgd = pgd_offset(walk->mm, next);
continue;
}
@@ -242,7 +245,7 @@
if (err)
break;
pgd++;
- } while (addr = next, addr != end);
+ } while (addr = next, addr < end);
return err;
}
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 3707c71..5110816 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -108,7 +108,7 @@
int page_start, int page_end)
{
const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
- unsigned int cpu;
+ unsigned int cpu, tcpu;
int i;
for_each_possible_cpu(cpu) {
@@ -116,14 +116,23 @@
struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
- if (!*pagep) {
- pcpu_free_pages(chunk, pages, populated,
- page_start, page_end);
- return -ENOMEM;
- }
+ if (!*pagep)
+ goto err;
}
}
return 0;
+
+err:
+ while (--i >= page_start)
+ __free_page(pages[pcpu_page_idx(cpu, i)]);
+
+ for_each_possible_cpu(tcpu) {
+ if (tcpu == cpu)
+ break;
+ for (i = page_start; i < page_end; i++)
+ __free_page(pages[pcpu_page_idx(tcpu, i)]);
+ }
+ return -ENOMEM;
}
/**
@@ -263,6 +272,7 @@
__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
page_end - page_start);
}
+ pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
return err;
}
diff --git a/mm/percpu.c b/mm/percpu.c
index 8c8e08f..25e2ea5 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -612,7 +612,7 @@
chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
sizeof(chunk->map[0]));
if (!chunk->map) {
- kfree(chunk);
+ pcpu_mem_free(chunk, pcpu_chunk_struct_size);
return NULL;
}
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 0c8323f..4b62a16 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -86,9 +86,10 @@
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
pte_t *ptep)
{
+ struct mm_struct *mm = (vma)->vm_mm;
pte_t pte;
- pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
- if (pte_accessible(pte))
+ pte = ptep_get_and_clear(mm, address, ptep);
+ if (pte_accessible(mm, pte))
flush_tlb_page(vma, address);
return pte;
}
@@ -166,6 +167,9 @@
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
+ pmd_t entry = *pmdp;
+ if (pmd_numa(entry))
+ entry = pmd_mknonnuma(entry);
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 6280da8..705bfc8 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -103,6 +103,7 @@
* LOCK should suffice since the actual taking of the lock must
* happen _before_ what follows.
*/
+ might_sleep();
if (rwsem_is_locked(&anon_vma->root->rwsem)) {
anon_vma_lock_write(anon_vma);
anon_vma_unlock_write(anon_vma);
@@ -426,8 +427,9 @@
* above cannot corrupt).
*/
if (!page_mapped(page)) {
+ rcu_read_unlock();
put_anon_vma(anon_vma);
- anon_vma = NULL;
+ return NULL;
}
out:
rcu_read_unlock();
@@ -477,9 +479,9 @@
}
if (!page_mapped(page)) {
+ rcu_read_unlock();
put_anon_vma(anon_vma);
- anon_vma = NULL;
- goto out;
+ return NULL;
}
/* we pinned the anon_vma, its safe to sleep */
@@ -600,7 +602,11 @@
spinlock_t *ptl;
if (unlikely(PageHuge(page))) {
+ /* when pud is not present, pte will be NULL */
pte = huge_pte_offset(mm, address);
+ if (!pte)
+ return NULL;
+
ptl = &mm->page_table_lock;
goto check;
}
@@ -1386,9 +1392,19 @@
BUG_ON(!page || PageAnon(page));
if (locked_vma) {
- mlock_vma_page(page); /* no-op if already mlocked */
- if (page == check_page)
+ if (page == check_page) {
+ /* we know we have check_page locked */
+ mlock_vma_page(page);
ret = SWAP_MLOCK;
+ } else if (trylock_page(page)) {
+ /*
+ * If we can lock the page, perform mlock.
+ * Otherwise leave the page alone, it will be
+ * eventually encountered again later.
+ */
+ mlock_vma_page(page);
+ unlock_page(page);
+ }
continue; /* don't unmap */
}
@@ -1661,10 +1677,9 @@
{
struct anon_vma *root = anon_vma->root;
+ anon_vma_free(anon_vma);
if (root != anon_vma && atomic_dec_and_test(&root->refcount))
anon_vma_free(root);
-
- anon_vma_free(anon_vma);
}
#ifdef CONFIG_MIGRATION
diff --git a/mm/shmem.c b/mm/shmem.c
index 5e6a842..4e4a734 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -80,11 +80,12 @@
#define SHORT_SYMLINK_LEN 128
/*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
+ wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
pgoff_t start; /* start of range currently being fallocated */
pgoff_t next; /* the next page offset to be fallocated */
pgoff_t nr_falloced; /* how many new pages have been fallocated */
@@ -533,22 +534,19 @@
return;
index = start;
- for ( ; ; ) {
+ while (index < end) {
cond_resched();
pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
- if (index == start || unfalloc)
+ /* If all gone or hole-punch or unfalloc, we're done */
+ if (index == start || end != -1)
break;
+ /* But if truncating, restart to make sure all gone */
index = start;
continue;
}
- if ((index == start || unfalloc) && indices[0] >= end) {
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- break;
- }
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
@@ -560,8 +558,12 @@
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
- nr_swaps_freed += !shmem_free_swap(mapping,
- index, page);
+ if (shmem_free_swap(mapping, index, page)) {
+ /* Swap was replaced by page: retry */
+ index--;
+ break;
+ }
+ nr_swaps_freed++;
continue;
}
@@ -570,6 +572,11 @@
if (page->mapping == mapping) {
VM_BUG_ON(PageWriteback(page));
truncate_inode_page(mapping, page);
+ } else {
+ /* Page was replaced by swap: retry */
+ unlock_page(page);
+ index--;
+ break;
}
}
unlock_page(page);
@@ -826,6 +833,7 @@
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
+ !shmem_falloc->waitq &&
index >= shmem_falloc->start &&
index < shmem_falloc->next)
shmem_falloc->nr_unswapped++;
@@ -1300,6 +1308,64 @@
int error;
int ret = VM_FAULT_LOCKED;
+ /*
+ * Trinity finds that probing a hole which tmpfs is punching can
+ * prevent the hole-punch from ever completing: which in turn
+ * locks writers out with its hold on i_mutex. So refrain from
+ * faulting pages into the hole while it's being punched. Although
+ * shmem_undo_range() does remove the additions, it may be unable to
+ * keep up, as each new page needs its own unmap_mapping_range() call,
+ * and the i_mmap tree grows ever slower to scan if new vmas are added.
+ *
+ * It does not matter if we sometimes reach this check just before the
+ * hole-punch begins, so that one fault then races with the punch:
+ * we just need to make racing faults a rare case.
+ *
+ * The implementation below would be much simpler if we just used a
+ * standard mutex or completion: but we cannot take i_mutex in fault,
+ * and bloating every shmem inode for this unlikely case would be sad.
+ */
+ if (unlikely(inode->i_private)) {
+ struct shmem_falloc *shmem_falloc;
+
+ spin_lock(&inode->i_lock);
+ shmem_falloc = inode->i_private;
+ if (shmem_falloc &&
+ shmem_falloc->waitq &&
+ vmf->pgoff >= shmem_falloc->start &&
+ vmf->pgoff < shmem_falloc->next) {
+ wait_queue_head_t *shmem_falloc_waitq;
+ DEFINE_WAIT(shmem_fault_wait);
+
+ ret = VM_FAULT_NOPAGE;
+ if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+ !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ /* It's polite to up mmap_sem if we can */
+ up_read(&vma->vm_mm->mmap_sem);
+ ret = VM_FAULT_RETRY;
+ }
+
+ shmem_falloc_waitq = shmem_falloc->waitq;
+ prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ schedule();
+
+ /*
+ * shmem_falloc_waitq points into the shmem_fallocate()
+ * stack of the hole-punching task: shmem_falloc_waitq
+ * is usually invalid by the time we reach here, but
+ * finish_wait() does not dereference it in that case;
+ * though i_lock needed lest racing with wake_up_all().
+ */
+ spin_lock(&inode->i_lock);
+ finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+ spin_unlock(&inode->i_lock);
+ return ret;
+ }
+ spin_unlock(&inode->i_lock);
+ }
+
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
@@ -1821,12 +1887,25 @@
struct address_space *mapping = file->f_mapping;
loff_t unmap_start = round_up(offset, PAGE_SIZE);
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+ shmem_falloc.waitq = &shmem_falloc_waitq;
+ shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+ shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+ spin_lock(&inode->i_lock);
+ inode->i_private = &shmem_falloc;
+ spin_unlock(&inode->i_lock);
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
shmem_truncate_range(inode, offset, offset + len - 1);
/* No need to unmap again: hole-punching leaves COWed pages */
+
+ spin_lock(&inode->i_lock);
+ inode->i_private = NULL;
+ wake_up_all(&shmem_falloc_waitq);
+ spin_unlock(&inode->i_lock);
error = 0;
goto out;
}
@@ -1844,6 +1923,7 @@
goto out;
}
+ shmem_falloc.waitq = NULL;
shmem_falloc.start = start;
shmem_falloc.next = start;
shmem_falloc.nr_falloced = 0;
@@ -2048,8 +2128,10 @@
if (new_dentry->d_inode) {
(void) shmem_unlink(new_dir, new_dentry);
- if (they_are_dirs)
+ if (they_are_dirs) {
+ drop_nlink(new_dentry->d_inode);
drop_nlink(old_dir);
+ }
} else if (they_are_dirs) {
drop_nlink(old_dir);
inc_nlink(new_dir);
@@ -2879,14 +2961,8 @@
/* common code */
-static char *shmem_dname(struct dentry *dentry, char *buffer, int buflen)
-{
- return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
- dentry->d_name.name);
-}
-
static struct dentry_operations anon_ops = {
- .d_dname = shmem_dname
+ .d_dname = simple_dname
};
/**
diff --git a/mm/slab.c b/mm/slab.c
index 8ccd296..bd88411 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -565,7 +565,7 @@
if (slab_state < UP)
return;
- for (i = 1; i < PAGE_SHIFT + MAX_ORDER; i++) {
+ for (i = 1; i <= KMALLOC_SHIFT_HIGH; i++) {
struct kmem_cache_node *n;
struct kmem_cache *cache = kmalloc_caches[i];
diff --git a/mm/slab.h b/mm/slab.h
index f96b49e..4d6d836 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -162,6 +162,8 @@
static inline struct kmem_cache *cache_from_memcg(struct kmem_cache *s, int idx)
{
+ if (!s->memcg_params)
+ return NULL;
return s->memcg_params->memcg_caches[idx];
}
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2d41450..7d21d3f 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -55,6 +55,7 @@
continue;
}
+#if !defined(CONFIG_SLUB)
/*
* For simplicity, we won't check this in the list of memcg
* caches. We have control over memcg naming, and if there
@@ -68,6 +69,7 @@
s = NULL;
return -EINVAL;
}
+#endif
}
WARN_ON(strchr(name, ' ')); /* It confuses parsers */
diff --git a/mm/slub.c b/mm/slub.c
index 57707f0..deaed7b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1201,8 +1201,8 @@
/*
* Enable debugging if selected on the kernel commandline.
*/
- if (slub_debug && (!slub_debug_slabs ||
- !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+ if (slub_debug && (!slub_debug_slabs || (name &&
+ !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
flags |= slub_debug;
return flags;
@@ -4285,7 +4285,13 @@
page = ACCESS_ONCE(c->partial);
if (page) {
- x = page->pobjects;
+ node = page_to_nid(page);
+ if (flags & SO_TOTAL)
+ WARN_ON_ONCE(1);
+ else if (flags & SO_OBJECTS)
+ WARN_ON_ONCE(1);
+ else
+ x = page->pages;
total += x;
nodes[node] += x;
}
diff --git a/mm/swap.c b/mm/swap.c
index dfd7d71..4e35f3f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -31,6 +31,7 @@
#include <linux/memcontrol.h>
#include <linux/gfp.h>
#include <linux/uio.h>
+#include <linux/hugetlb.h>
#include "internal.h"
@@ -80,7 +81,7 @@
{
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
- struct page *page_head = compound_trans_head(page);
+ struct page *page_head = compound_head(page);
if (likely(page != page_head &&
get_page_unless_zero(page_head))) {
@@ -94,14 +95,31 @@
* still hot on arches that do not support
* this_cpu_cmpxchg_double().
*/
- if (PageSlab(page_head)) {
- if (PageTail(page)) {
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+ if (likely(PageTail(page))) {
+ /*
+ * __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
+ atomic_dec(&page->_mapcount);
if (put_page_testzero(page_head))
VM_BUG_ON(1);
-
- atomic_dec(&page->_mapcount);
- goto skip_lock_tail;
+ if (put_page_testzero(page_head))
+ __put_compound_page(page_head);
+ return;
} else
+ /*
+ * __split_huge_page_refcount
+ * run before us, "page" was a
+ * THP tail. The split
+ * page_head has been freed
+ * and reallocated as slab or
+ * hugetlbfs page of smaller
+ * order (only possible if
+ * reallocated as slab on
+ * x86).
+ */
goto skip_lock;
}
/*
@@ -115,8 +133,27 @@
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
skip_lock:
- if (put_page_testzero(page_head))
- __put_single_page(page_head);
+ if (put_page_testzero(page_head)) {
+ /*
+ * The head page may have been
+ * freed and reallocated as a
+ * compound page of smaller
+ * order and then freed again.
+ * All we know is that it
+ * cannot have become: a THP
+ * page, a compound page of
+ * higher order, a tail page.
+ * That is because we still
+ * hold the refcount of the
+ * split THP tail and
+ * page_head was the THP head
+ * before the split.
+ */
+ if (PageHead(page_head))
+ __put_compound_page(page_head);
+ else
+ __put_single_page(page_head);
+ }
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
@@ -138,7 +175,6 @@
VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
-skip_lock_tail:
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
@@ -183,16 +219,30 @@
*/
unsigned long flags;
bool got = false;
- struct page *page_head = compound_trans_head(page);
+ struct page *page_head = compound_head(page);
if (likely(page != page_head && get_page_unless_zero(page_head))) {
-
/* Ref to put_compound_page() comment. */
- if (PageSlab(page_head)) {
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
if (likely(PageTail(page))) {
+ /*
+ * This is a hugetlbfs page or a slab
+ * page. __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
__get_page_tail_foll(page, false);
return true;
} else {
+ /*
+ * __split_huge_page_refcount run
+ * before us, "page" was a THP
+ * tail. The split page_head has been
+ * freed and reallocated as slab or
+ * hugetlbfs page of smaller order
+ * (only possible if reallocated as
+ * slab on x86).
+ */
put_page(page_head);
return false;
}
diff --git a/mm/truncate.c b/mm/truncate.c
index c75b736..2d6151f 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -20,6 +20,7 @@
#include <linux/buffer_head.h> /* grr. try_to_release_page,
do_invalidatepage */
#include <linux/cleancache.h>
+#include <linux/rmap.h>
#include "internal.h"
@@ -567,16 +568,67 @@
*/
void truncate_setsize(struct inode *inode, loff_t newsize)
{
- loff_t oldsize;
+ loff_t oldsize = inode->i_size;
- oldsize = inode->i_size;
i_size_write(inode, newsize);
-
+ if (newsize > oldsize)
+ pagecache_isize_extended(inode, oldsize, newsize);
truncate_pagecache(inode, oldsize, newsize);
}
EXPORT_SYMBOL(truncate_setsize);
/**
+ * pagecache_isize_extended - update pagecache after extension of i_size
+ * @inode: inode for which i_size was extended
+ * @from: original inode size
+ * @to: new inode size
+ *
+ * Handle extension of inode size either caused by extending truncate or by
+ * write starting after current i_size. We mark the page straddling current
+ * i_size RO so that page_mkwrite() is called on the nearest write access to
+ * the page. This way filesystem can be sure that page_mkwrite() is called on
+ * the page before user writes to the page via mmap after the i_size has been
+ * changed.
+ *
+ * The function must be called after i_size is updated so that page fault
+ * coming after we unlock the page will already see the new i_size.
+ * The function must be called while we still hold i_mutex - this not only
+ * makes sure i_size is stable but also that userspace cannot observe new
+ * i_size value before we are prepared to store mmap writes at new inode size.
+ */
+void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
+{
+ int bsize = 1 << inode->i_blkbits;
+ loff_t rounded_from;
+ struct page *page;
+ pgoff_t index;
+
+ WARN_ON(to > inode->i_size);
+
+ if (from >= to || bsize == PAGE_CACHE_SIZE)
+ return;
+ /* Page straddling @from will not have any hole block created? */
+ rounded_from = round_up(from, bsize);
+ if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
+ return;
+
+ index = from >> PAGE_CACHE_SHIFT;
+ page = find_lock_page(inode->i_mapping, index);
+ /* Page not cached? Nothing to do */
+ if (!page)
+ return;
+ /*
+ * See clear_page_dirty_for_io() for details why set_page_dirty()
+ * is needed.
+ */
+ if (page_mkclean(page))
+ set_page_dirty(page);
+ unlock_page(page);
+ page_cache_release(page);
+}
+EXPORT_SYMBOL(pagecache_isize_extended);
+
+/**
* truncate_pagecache_range - unmap and remove pagecache that is hole-punched
* @inode: inode
* @lstart: offset of beginning of hole
diff --git a/mm/util.c b/mm/util.c
index ab1424d..0b17252 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -272,17 +272,14 @@
if (in_group) {
struct task_struct *t;
- rcu_read_lock();
- if (!pid_alive(task))
- goto done;
- t = task;
- do {
+ rcu_read_lock();
+ for_each_thread(task, t) {
if (vm_is_stack_for_task(t, vma)) {
ret = t->pid;
goto done;
}
- } while_each_thread(task, t);
+ }
done:
rcu_read_unlock();
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d365724..d456560 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -388,12 +388,12 @@
addr = ALIGN(first->va_end, align);
if (addr < vstart)
goto nocache;
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
} else {
addr = ALIGN(vstart, align);
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
n = vmap_area_root.rb_node;
@@ -420,7 +420,7 @@
if (addr + cached_hole_size < first->va_start)
cached_hole_size = first->va_start - addr;
addr = ALIGN(first->va_end, align);
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
if (list_is_last(&first->list, &vmap_area_list))
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fa6a853..a2fd7e75 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,7 @@
#include <asm/div64.h>
#include <linux/swapops.h>
+#include <linux/balloon_compaction.h>
#include "internal.h"
@@ -978,7 +979,8 @@
LIST_HEAD(clean_pages);
list_for_each_entry_safe(page, next, page_list, lru) {
- if (page_is_file_cache(page) && !PageDirty(page)) {
+ if (page_is_file_cache(page) && !PageDirty(page) &&
+ !isolated_balloon_page(page)) {
ClearPageActive(page);
list_move(&page->lru, &clean_pages);
}
@@ -2115,6 +2117,20 @@
return aborted_reclaim;
}
+static unsigned long zone_reclaimable_pages(struct zone *zone)
+{
+ int nr;
+
+ nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+ zone_page_state(zone, NR_INACTIVE_FILE);
+
+ if (get_nr_swap_pages() > 0)
+ nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+ zone_page_state(zone, NR_INACTIVE_ANON);
+
+ return nr;
+}
+
static bool zone_reclaimable(struct zone *zone)
{
return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
@@ -2270,10 +2286,17 @@
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
+ if (!populated_zone(zone))
+ continue;
+
pfmemalloc_reserve += min_wmark_pages(zone);
free_pages += zone_page_state(zone, NR_FREE_PAGES);
}
+ /* If there are no reserves (unexpected config) then do not throttle */
+ if (!pfmemalloc_reserve)
+ return true;
+
wmark_ok = free_pages > pfmemalloc_reserve / 2;
/* kswapd must be awake if processes are being throttled */
@@ -2298,9 +2321,9 @@
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
nodemask_t *nodemask)
{
+ struct zoneref *z;
struct zone *zone;
- int high_zoneidx = gfp_zone(gfp_mask);
- pg_data_t *pgdat;
+ pg_data_t *pgdat = NULL;
/*
* Kernel threads should not be throttled as they may be indirectly
@@ -2319,10 +2342,34 @@
if (fatal_signal_pending(current))
goto out;
- /* Check if the pfmemalloc reserves are ok */
- first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
- pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ /*
+ * Check if the pfmemalloc reserves are ok by finding the first node
+ * with a usable ZONE_NORMAL or lower zone. The expectation is that
+ * GFP_KERNEL will be required for allocating network buffers when
+ * swapping over the network so ZONE_HIGHMEM is unusable.
+ *
+ * Throttling is based on the first usable node and throttled processes
+ * wait on a queue until kswapd makes progress and wakes them. There
+ * is an affinity then between processes waking up and where reclaim
+ * progress has been made assuming the process wakes on the same node.
+ * More importantly, processes running on remote nodes will not compete
+ * for remote pfmemalloc reserves and processes on different nodes
+ * should make reasonable progress.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_mask, nodemask) {
+ if (zone_idx(zone) > ZONE_NORMAL)
+ continue;
+
+ /* Throttle based on the first usable node */
+ pgdat = zone->zone_pgdat;
+ if (pfmemalloc_watermark_ok(pgdat))
+ goto out;
+ break;
+ }
+
+ /* If no zone was usable by the allocation flags then do not throttle */
+ if (!pgdat)
goto out;
/* Account for the throttling */
@@ -2584,18 +2631,20 @@
return false;
/*
- * There is a potential race between when kswapd checks its watermarks
- * and a process gets throttled. There is also a potential race if
- * processes get throttled, kswapd wakes, a large process exits therby
- * balancing the zones that causes kswapd to miss a wakeup. If kswapd
- * is going to sleep, no process should be sleeping on pfmemalloc_wait
- * so wake them now if necessary. If necessary, processes will wake
- * kswapd and get throttled again
+ * The throttled processes are normally woken up in balance_pgdat() as
+ * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+ * race between when kswapd checks the watermarks and a process gets
+ * throttled. There is also a potential race if processes get
+ * throttled, kswapd wakes, a large process exits thereby balancing the
+ * zones, which causes kswapd to exit balance_pgdat() before reaching
+ * the wake up checks. If kswapd is going to sleep, no process should
+ * be sleeping on pfmemalloc_wait, so wake them now if necessary. If
+ * the wake up is premature, processes will wake kswapd and get
+ * throttled again. The difference from wake ups in balance_pgdat() is
+ * that here we are under prepare_to_wait().
*/
- if (waitqueue_active(&pgdat->pfmemalloc_wait)) {
- wake_up(&pgdat->pfmemalloc_wait);
- return false;
- }
+ if (waitqueue_active(&pgdat->pfmemalloc_wait))
+ wake_up_all(&pgdat->pfmemalloc_wait);
return pgdat_balanced(pgdat, order, classzone_idx);
}
@@ -3043,7 +3092,10 @@
}
}
+ tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
current->reclaim_state = NULL;
+ lockdep_clear_current_reclaim_state();
+
return 0;
}
@@ -3073,41 +3125,6 @@
wake_up_interruptible(&pgdat->kswapd_wait);
}
-/*
- * The reclaimable count would be mostly accurate.
- * The less reclaimable pages may be
- * - mlocked pages, which will be moved to unevictable list when encountered
- * - mapped pages, which may require several travels to be reclaimed
- * - dirty pages, which is not "instantly" reclaimable
- */
-unsigned long global_reclaimable_pages(void)
-{
- int nr;
-
- nr = global_page_state(NR_ACTIVE_FILE) +
- global_page_state(NR_INACTIVE_FILE);
-
- if (get_nr_swap_pages() > 0)
- nr += global_page_state(NR_ACTIVE_ANON) +
- global_page_state(NR_INACTIVE_ANON);
-
- return nr;
-}
-
-unsigned long zone_reclaimable_pages(struct zone *zone)
-{
- int nr;
-
- nr = zone_page_state(zone, NR_ACTIVE_FILE) +
- zone_page_state(zone, NR_INACTIVE_FILE);
-
- if (get_nr_swap_pages() > 0)
- nr += zone_page_state(zone, NR_ACTIVE_ANON) +
- zone_page_state(zone, NR_INACTIVE_ANON);
-
- return nr;
-}
-
#ifdef CONFIG_HIBERNATION
/*
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f42745e..6d9bace 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -14,6 +14,7 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/cpumask.h>
#include <linux/vmstat.h>
#include <linux/sched.h>
#include <linux/math64.h>
@@ -432,11 +433,12 @@
* with the global counters. These could cause remote node cache line
* bouncing and will have to be only done when necessary.
*/
-void refresh_cpu_vm_stats(int cpu)
+bool refresh_cpu_vm_stats(int cpu)
{
struct zone *zone;
int i;
int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
+ bool vm_activity = false;
for_each_populated_zone(zone) {
struct per_cpu_pageset *p;
@@ -483,14 +485,21 @@
if (p->expire)
continue;
- if (p->pcp.count)
+ if (p->pcp.count) {
+ vm_activity = true;
drain_zone_pages(zone, &p->pcp);
+ }
#endif
}
for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
- if (global_diff[i])
+ if (global_diff[i]) {
atomic_long_add(global_diff[i], &vm_stat[i]);
+ vm_activity = true;
+ }
+
+ return vm_activity;
+
}
/*
@@ -779,6 +788,7 @@
#ifdef CONFIG_NUMA_BALANCING
"numa_pte_updates",
+ "numa_huge_pte_updates",
"numa_hint_faults",
"numa_hint_faults_local",
"numa_pages_migrated",
@@ -1174,20 +1184,70 @@
#ifdef CONFIG_SMP
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
+static struct cpumask vmstat_off_cpus;
+struct delayed_work vmstat_monitor_work;
-static void vmstat_update(struct work_struct *w)
+static inline bool need_vmstat(int cpu)
{
- refresh_cpu_vm_stats(smp_processor_id());
- schedule_delayed_work(&__get_cpu_var(vmstat_work),
- round_jiffies_relative(sysctl_stat_interval));
+ struct zone *zone;
+ int i;
+
+ for_each_populated_zone(zone) {
+ struct per_cpu_pageset *p;
+
+ p = per_cpu_ptr(zone->pageset, cpu);
+
+ for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
+ if (p->vm_stat_diff[i])
+ return true;
+
+ if (zone_to_nid(zone) != numa_node_id() && p->pcp.count)
+ return true;
+ }
+
+ return false;
}
-static void __cpuinit start_cpu_timer(int cpu)
+static void vmstat_update(struct work_struct *w);
+
+static void start_cpu_timer(int cpu)
+{
+ struct delayed_work *work = &per_cpu(vmstat_work, cpu);
+
+ cpumask_clear_cpu(cpu, &vmstat_off_cpus);
+ schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
+}
+
+static void __cpuinit setup_cpu_timer(int cpu)
{
struct delayed_work *work = &per_cpu(vmstat_work, cpu);
INIT_DEFERRABLE_WORK(work, vmstat_update);
- schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
+ start_cpu_timer(cpu);
+}
+
+static void vmstat_update_monitor(struct work_struct *w)
+{
+ int cpu;
+
+ for_each_cpu_and(cpu, &vmstat_off_cpus, cpu_online_mask)
+ if (need_vmstat(cpu))
+ start_cpu_timer(cpu);
+
+ queue_delayed_work(system_unbound_wq, &vmstat_monitor_work,
+ round_jiffies_relative(sysctl_stat_interval));
+}
+
+
+static void vmstat_update(struct work_struct *w)
+{
+ int cpu = smp_processor_id();
+
+ if (likely(refresh_cpu_vm_stats(cpu)))
+ schedule_delayed_work(&__get_cpu_var(vmstat_work),
+ round_jiffies_relative(sysctl_stat_interval));
+ else
+ cpumask_set_cpu(cpu, &vmstat_off_cpus);
}
/*
@@ -1204,17 +1264,19 @@
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
refresh_zone_stat_thresholds();
- start_cpu_timer(cpu);
+ setup_cpu_timer(cpu);
node_set_state(cpu_to_node(cpu), N_CPU);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
- cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
- per_cpu(vmstat_work, cpu).work.func = NULL;
+ if (!cpumask_test_cpu(cpu, &vmstat_off_cpus)) {
+ cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
+ per_cpu(vmstat_work, cpu).work.func = NULL;
+ }
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- start_cpu_timer(cpu);
+ setup_cpu_timer(cpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
@@ -1237,8 +1299,14 @@
register_cpu_notifier(&vmstat_notifier);
+ INIT_DEFERRABLE_WORK(&vmstat_monitor_work,
+ vmstat_update_monitor);
+ queue_delayed_work(system_unbound_wq,
+ &vmstat_monitor_work,
+ round_jiffies_relative(HZ));
+
for_each_online_cpu(cpu)
- start_cpu_timer(cpu);
+ setup_cpu_timer(cpu);
#endif
#ifdef CONFIG_PROC_FS
proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
diff --git a/mm/zpool.c b/mm/zpool.c
new file mode 100644
index 0000000..739cdf0
--- /dev/null
+++ b/mm/zpool.c
@@ -0,0 +1,364 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for memory storage pool implementations.
+ * Typically, this is used to store compressed memory.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/zpool.h>
+
+struct zpool {
+ char *type;
+
+ struct zpool_driver *driver;
+ void *pool;
+ struct zpool_ops *ops;
+
+ struct list_head list;
+};
+
+static LIST_HEAD(drivers_head);
+static DEFINE_SPINLOCK(drivers_lock);
+
+static LIST_HEAD(pools_head);
+static DEFINE_SPINLOCK(pools_lock);
+
+/**
+ * zpool_register_driver() - register a zpool implementation.
+ * @driver: driver to register
+ */
+void zpool_register_driver(struct zpool_driver *driver)
+{
+ spin_lock(&drivers_lock);
+ atomic_set(&driver->refcount, 0);
+ list_add(&driver->list, &drivers_head);
+ spin_unlock(&drivers_lock);
+}
+EXPORT_SYMBOL(zpool_register_driver);
+
+/**
+ * zpool_unregister_driver() - unregister a zpool implementation.
+ * @driver: driver to unregister.
+ *
+ * Module usage counting is used to prevent using a driver
+ * while/after unloading, so if this is called from module
+ * exit function, this should never fail; if called from
+ * other than the module exit function, and this returns
+ * failure, the driver is in use and must remain available.
+ */
+int zpool_unregister_driver(struct zpool_driver *driver)
+{
+ int ret = 0, refcount;
+
+ spin_lock(&drivers_lock);
+ refcount = atomic_read(&driver->refcount);
+ WARN_ON(refcount < 0);
+ if (refcount > 0)
+ ret = -EBUSY;
+ else
+ list_del(&driver->list);
+ spin_unlock(&drivers_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL(zpool_unregister_driver);
+
+/**
+ * zpool_evict() - evict callback from a zpool implementation.
+ * @pool: pool to evict from.
+ * @handle: handle to evict.
+ *
+ * This can be used by zpool implementations to call the
+ * user's evict zpool_ops struct evict callback.
+ */
+int zpool_evict(void *pool, unsigned long handle)
+{
+ struct zpool *zpool;
+
+ spin_lock(&pools_lock);
+ list_for_each_entry(zpool, &pools_head, list) {
+ if (zpool->pool == pool) {
+ spin_unlock(&pools_lock);
+ if (!zpool->ops || !zpool->ops->evict)
+ return -EINVAL;
+ return zpool->ops->evict(zpool, handle);
+ }
+ }
+ spin_unlock(&pools_lock);
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL(zpool_evict);
+
+static struct zpool_driver *zpool_get_driver(char *type)
+{
+ struct zpool_driver *driver;
+
+ spin_lock(&drivers_lock);
+ list_for_each_entry(driver, &drivers_head, list) {
+ if (!strcmp(driver->type, type)) {
+ bool got = try_module_get(driver->owner);
+
+ if (got)
+ atomic_inc(&driver->refcount);
+ spin_unlock(&drivers_lock);
+ return got ? driver : NULL;
+ }
+ }
+
+ spin_unlock(&drivers_lock);
+ return NULL;
+}
+
+static void zpool_put_driver(struct zpool_driver *driver)
+{
+ atomic_dec(&driver->refcount);
+ module_put(driver->owner);
+}
+
+/**
+ * zpool_create_pool() - Create a new zpool
+ * @type The type of the zpool to create (e.g. zbud, zsmalloc)
+ * @gfp The GFP flags to use when allocating the pool.
+ * @ops The optional ops callback.
+ *
+ * This creates a new zpool of the specified type. The gfp flags will be
+ * used when allocating memory, if the implementation supports it. If the
+ * ops param is NULL, then the created zpool will not be shrinkable.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: New zpool on success, NULL on failure.
+ */
+struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
+{
+ struct zpool_driver *driver;
+ struct zpool *zpool;
+
+ pr_info("creating pool type %s\n", type);
+
+ driver = zpool_get_driver(type);
+
+ if (!driver) {
+ request_module("zpool-%s", type);
+ driver = zpool_get_driver(type);
+ }
+
+ if (!driver) {
+ pr_err("no driver for type %s\n", type);
+ return NULL;
+ }
+
+ zpool = kmalloc(sizeof(*zpool), gfp);
+ if (!zpool) {
+ pr_err("couldn't create zpool - out of memory\n");
+ zpool_put_driver(driver);
+ return NULL;
+ }
+
+ zpool->type = driver->type;
+ zpool->driver = driver;
+ zpool->pool = driver->create(gfp, ops);
+ zpool->ops = ops;
+
+ if (!zpool->pool) {
+ pr_err("couldn't create %s pool\n", type);
+ zpool_put_driver(driver);
+ kfree(zpool);
+ return NULL;
+ }
+
+ pr_info("created %s pool\n", type);
+
+ spin_lock(&pools_lock);
+ list_add(&zpool->list, &pools_head);
+ spin_unlock(&pools_lock);
+
+ return zpool;
+}
+
+/**
+ * zpool_destroy_pool() - Destroy a zpool
+ * @pool The zpool to destroy.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when destroying different pools. The same
+ * pool should only be destroyed once, and should not be used
+ * after it is destroyed.
+ *
+ * This destroys an existing zpool. The zpool should not be in use.
+ */
+void zpool_destroy_pool(struct zpool *zpool)
+{
+ pr_info("destroying pool type %s\n", zpool->type);
+
+ spin_lock(&pools_lock);
+ list_del(&zpool->list);
+ spin_unlock(&pools_lock);
+ zpool->driver->destroy(zpool->pool);
+ zpool_put_driver(zpool->driver);
+ kfree(zpool);
+}
+
+/**
+ * zpool_get_type() - Get the type of the zpool
+ * @pool The zpool to check
+ *
+ * This returns the type of the pool.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: The type of zpool.
+ */
+char *zpool_get_type(struct zpool *zpool)
+{
+ return zpool->type;
+}
+
+/**
+ * zpool_malloc() - Allocate memory
+ * @pool The zpool to allocate from.
+ * @size The amount of memory to allocate.
+ * @gfp The GFP flags to use when allocating memory.
+ * @handle Pointer to the handle to set
+ *
+ * This allocates the requested amount of memory from the pool.
+ * The gfp flags will be used when allocating memory, if the
+ * implementation supports it. The provided @handle will be
+ * set to the allocated object handle.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error.
+ */
+int zpool_malloc(struct zpool *zpool, size_t size, gfp_t gfp,
+ unsigned long *handle)
+{
+ return zpool->driver->malloc(zpool->pool, size, gfp, handle);
+}
+
+/**
+ * zpool_free() - Free previously allocated memory
+ * @pool The zpool that allocated the memory.
+ * @handle The handle to the memory to free.
+ *
+ * This frees previously allocated memory. This does not guarantee
+ * that the pool will actually free memory, only that the memory
+ * in the pool will become available for use by the pool.
+ *
+ * Implementations must guarantee this to be thread-safe,
+ * however only when freeing different handles. The same
+ * handle should only be freed once, and should not be used
+ * after freeing.
+ */
+void zpool_free(struct zpool *zpool, unsigned long handle)
+{
+ zpool->driver->free(zpool->pool, handle);
+}
+
+/**
+ * zpool_shrink() - Shrink the pool size
+ * @pool The zpool to shrink.
+ * @pages The number of pages to shrink the pool.
+ * @reclaimed The number of pages successfully evicted.
+ *
+ * This attempts to shrink the actual memory size of the pool
+ * by evicting currently used handle(s). If the pool was
+ * created with no zpool_ops, or the evict call fails for any
+ * of the handles, this will fail. If non-NULL, the @reclaimed
+ * parameter will be set to the number of pages reclaimed,
+ * which may be more than the number of pages requested.
+ *
+ * Implementations must guarantee this to be thread-safe.
+ *
+ * Returns: 0 on success, negative value on error/failure.
+ */
+int zpool_shrink(struct zpool *zpool, unsigned int pages,
+ unsigned int *reclaimed)
+{
+ return zpool->driver->shrink(zpool->pool, pages, reclaimed);
+}
+
+/**
+ * zpool_map_handle() - Map a previously allocated handle into memory
+ * @pool The zpool that the handle was allocated from
+ * @handle The handle to map
+ * @mm How the memory should be mapped
+ *
+ * This maps a previously allocated handle into memory. The @mm
+ * param indicates to the implementation how the memory will be
+ * used, i.e. read-only, write-only, read-write. If the
+ * implementation does not support it, the memory will be treated
+ * as read-write.
+ *
+ * This may hold locks, disable interrupts, and/or preemption,
+ * and the zpool_unmap_handle() must be called to undo those
+ * actions. The code that uses the mapped handle should complete
+ * its operatons on the mapped handle memory quickly and unmap
+ * as soon as possible. As the implementation may use per-cpu
+ * data, multiple handles should not be mapped concurrently on
+ * any cpu.
+ *
+ * Returns: A pointer to the handle's mapped memory area.
+ */
+void *zpool_map_handle(struct zpool *zpool, unsigned long handle,
+ enum zpool_mapmode mapmode)
+{
+ return zpool->driver->map(zpool->pool, handle, mapmode);
+}
+
+/**
+ * zpool_unmap_handle() - Unmap a previously mapped handle
+ * @pool The zpool that the handle was allocated from
+ * @handle The handle to unmap
+ *
+ * This unmaps a previously mapped handle. Any locks or other
+ * actions that the implementation took in zpool_map_handle()
+ * will be undone here. The memory area returned from
+ * zpool_map_handle() should no longer be used after this.
+ */
+void zpool_unmap_handle(struct zpool *zpool, unsigned long handle)
+{
+ zpool->driver->unmap(zpool->pool, handle);
+}
+
+/**
+ * zpool_get_total_size() - The total size of the pool
+ * @pool The zpool to check
+ *
+ * This returns the total size in bytes of the pool.
+ *
+ * Returns: Total size of the zpool in bytes.
+ */
+u64 zpool_get_total_size(struct zpool *zpool)
+{
+ return zpool->driver->total_size(zpool->pool);
+}
+
+static int __init init_zpool(void)
+{
+ pr_info("loaded\n");
+ return 0;
+}
+
+static void __exit exit_zpool(void)
+{
+ pr_info("unloaded\n");
+}
+
+module_init(init_zpool);
+module_exit(exit_zpool);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
+MODULE_DESCRIPTION("Common API for compressed memory storage");
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
new file mode 100644
index 0000000..7031e12f
--- /dev/null
+++ b/mm/zsmalloc.c
@@ -0,0 +1,1221 @@
+/*
+ * zsmalloc memory allocator
+ *
+ * Copyright (C) 2011 Nitin Gupta
+ * Copyright (C) 2012, 2013 Minchan Kim
+ *
+ * This code is released using a dual license strategy: BSD/GPL
+ * You can choose the license that better fits your requirements.
+ *
+ * Released under the terms of 3-clause BSD License
+ * Released under the terms of GNU General Public License Version 2.0
+ */
+
+
+/*
+ * This allocator is designed for use with zcache and zram. Thus, the
+ * allocator is supposed to work well under low memory conditions. In
+ * particular, it never attempts higher order page allocation which is
+ * very likely to fail under memory pressure. On the other hand, if we
+ * just use single (0-order) pages, it would suffer from very high
+ * fragmentation -- any object of size PAGE_SIZE/2 or larger would occupy
+ * an entire page. This was one of the major issues with its predecessor
+ * (xvmalloc).
+ *
+ * To overcome these issues, zsmalloc allocates a bunch of 0-order pages
+ * and links them together using various 'struct page' fields. These linked
+ * pages act as a single higher-order page i.e. an object can span 0-order
+ * page boundaries. The code refers to these linked pages as a single entity
+ * called zspage.
+ *
+ * Following is how we use various fields and flags of underlying
+ * struct page(s) to form a zspage.
+ *
+ * Usage of struct page fields:
+ * page->first_page: points to the first component (0-order) page
+ * page->index (union with page->freelist): offset of the first object
+ * starting in this page. For the first page, this is
+ * always 0, so we use this field (aka freelist) to point
+ * to the first free object in zspage.
+ * page->lru: links together all component pages (except the first page)
+ * of a zspage
+ *
+ * For _first_ page only:
+ *
+ * page->private (union with page->first_page): refers to the
+ * component page after the first page
+ * page->freelist: points to the first free object in zspage.
+ * Free objects are linked together using in-place
+ * metadata.
+ * page->objects: maximum number of objects we can store in this
+ * zspage (class->zspage_order * PAGE_SIZE / class->size)
+ * page->lru: links together first pages of various zspages.
+ * Basically forming list of zspages in a fullness group.
+ * page->mapping: class index and fullness group of the zspage
+ *
+ * Usage of struct page flags:
+ * PG_private: identifies the first component page
+ * PG_private2: identifies the last component page
+ *
+ */
+
+#ifdef CONFIG_ZSMALLOC_DEBUG
+#define DEBUG
+#endif
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+#include <linux/cpumask.h>
+#include <linux/cpu.h>
+#include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/zsmalloc.h>
+#include <linux/zpool.h>
+
+/*
+ * This must be power of 2 and greater than of equal to sizeof(link_free).
+ * These two conditions ensure that any 'struct link_free' itself doesn't
+ * span more than 1 page which avoids complex case of mapping 2 pages simply
+ * to restore link_free pointer values.
+ */
+#define ZS_ALIGN 8
+
+/*
+ * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
+ * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
+ */
+#define ZS_MAX_ZSPAGE_ORDER 2
+#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
+
+/*
+ * Object location (<PFN>, <obj_idx>) is encoded as
+ * as single (void *) handle value.
+ *
+ * Note that object index <obj_idx> is relative to system
+ * page <PFN> it is stored in, so for each sub-page belonging
+ * to a zspage, obj_idx starts with 0.
+ *
+ * This is made more complicated by various memory models and PAE.
+ */
+
+#ifndef MAX_PHYSMEM_BITS
+#ifdef CONFIG_HIGHMEM64G
+#define MAX_PHYSMEM_BITS 36
+#else /* !CONFIG_HIGHMEM64G */
+/*
+ * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
+ * be PAGE_SHIFT
+ */
+#define MAX_PHYSMEM_BITS BITS_PER_LONG
+#endif
+#endif
+#define _PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT)
+#define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS)
+#define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
+
+#define MAX(a, b) ((a) >= (b) ? (a) : (b))
+/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
+#define ZS_MIN_ALLOC_SIZE \
+ MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
+#define ZS_MAX_ALLOC_SIZE PAGE_SIZE
+
+/*
+ * On systems with 4K page size, this gives 255 size classes! There is a
+ * trader-off here:
+ * - Large number of size classes is potentially wasteful as free page are
+ * spread across these classes
+ * - Small number of size classes causes large internal fragmentation
+ * - Probably its better to use specific size classes (empirically
+ * determined). NOTE: all those class sizes must be set as multiple of
+ * ZS_ALIGN to make sure link_free itself never has to span 2 pages.
+ *
+ * ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
+ * (reason above)
+ */
+#define ZS_SIZE_CLASS_DELTA (PAGE_SIZE >> 8)
+#define ZS_SIZE_CLASSES ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
+ ZS_SIZE_CLASS_DELTA + 1)
+
+/*
+ * We do not maintain any list for completely empty or full pages
+ */
+enum fullness_group {
+ ZS_ALMOST_FULL,
+ ZS_ALMOST_EMPTY,
+ _ZS_NR_FULLNESS_GROUPS,
+
+ ZS_EMPTY,
+ ZS_FULL
+};
+
+/*
+ * We assign a page to ZS_ALMOST_EMPTY fullness group when:
+ * n <= N / f, where
+ * n = number of allocated objects
+ * N = total number of objects zspage can store
+ * f = fullness_threshold_frac
+ *
+ * Similarly, we assign zspage to:
+ * ZS_ALMOST_FULL when n > N / f
+ * ZS_EMPTY when n == 0
+ * ZS_FULL when n == N
+ *
+ * (see: fix_fullness_group())
+ */
+static const int fullness_threshold_frac = 4;
+
+struct size_class {
+ /*
+ * Size of objects stored in this class. Must be multiple
+ * of ZS_ALIGN.
+ */
+ int size;
+ unsigned int index;
+
+ /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
+ int pages_per_zspage;
+
+ spinlock_t lock;
+
+ struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
+};
+
+/*
+ * Placed within free objects to form a singly linked list.
+ * For every zspage, first_page->freelist gives head of this list.
+ *
+ * This must be power of 2 and less than or equal to ZS_ALIGN
+ */
+struct link_free {
+ /* Handle of next free chunk (encodes <PFN, obj_idx>) */
+ void *next;
+};
+
+struct zs_pool {
+ struct size_class *size_class[ZS_SIZE_CLASSES];
+
+ gfp_t flags; /* allocation flags used when growing pool */
+ atomic_long_t pages_allocated;
+};
+
+/*
+ * A zspage's class index and fullness group
+ * are encoded in its (first)page->mapping
+ */
+#define CLASS_IDX_BITS 28
+#define FULLNESS_BITS 4
+#define CLASS_IDX_MASK ((1 << CLASS_IDX_BITS) - 1)
+#define FULLNESS_MASK ((1 << FULLNESS_BITS) - 1)
+
+/*
+ * By default, zsmalloc uses a copy-based object mapping method to access
+ * allocations that span two pages. However, if a particular architecture
+ * performs VM mapping faster than copying, then it should be added here
+ * so that USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use
+ * page table mapping rather than copying for object mapping.
+*/
+#if defined(CONFIG_ARM) && !defined(MODULE)
+#define USE_PGTABLE_MAPPING
+#endif
+
+struct mapping_area {
+#ifdef USE_PGTABLE_MAPPING
+ struct vm_struct *vm; /* vm area for mapping object that span pages */
+#else
+ char *vm_buf; /* copy buffer for objects that span pages */
+#endif
+ char *vm_addr; /* address of kmap_atomic()'ed pages */
+ enum zs_mapmode vm_mm; /* mapping mode */
+};
+
+/* zpool driver */
+
+#ifdef CONFIG_ZPOOL
+
+static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
+{
+ return zs_create_pool(gfp);
+}
+
+static void zs_zpool_destroy(void *pool)
+{
+ zs_destroy_pool(pool);
+}
+
+static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
+ unsigned long *handle)
+{
+ *handle = zs_malloc(pool, size);
+ return *handle ? 0 : -1;
+}
+static void zs_zpool_free(void *pool, unsigned long handle)
+{
+ zs_free(pool, handle);
+}
+
+static int zs_zpool_shrink(void *pool, unsigned int pages,
+ unsigned int *reclaimed)
+{
+ return -EINVAL;
+}
+
+static void *zs_zpool_map(void *pool, unsigned long handle,
+ enum zpool_mapmode mm)
+{
+ enum zs_mapmode zs_mm;
+
+ switch (mm) {
+ case ZPOOL_MM_RO:
+ zs_mm = ZS_MM_RO;
+ break;
+ case ZPOOL_MM_WO:
+ zs_mm = ZS_MM_WO;
+ break;
+ case ZPOOL_MM_RW: /* fallthru */
+ default:
+ zs_mm = ZS_MM_RW;
+ break;
+ }
+
+ return zs_map_object(pool, handle, zs_mm);
+}
+static void zs_zpool_unmap(void *pool, unsigned long handle)
+{
+ zs_unmap_object(pool, handle);
+}
+
+static u64 zs_zpool_total_size(void *pool)
+{
+ return zs_get_total_pages(pool) << PAGE_SHIFT;
+}
+
+static struct zpool_driver zs_zpool_driver = {
+ .type = "zsmalloc",
+ .owner = THIS_MODULE,
+ .create = zs_zpool_create,
+ .destroy = zs_zpool_destroy,
+ .malloc = zs_zpool_malloc,
+ .free = zs_zpool_free,
+ .shrink = zs_zpool_shrink,
+ .map = zs_zpool_map,
+ .unmap = zs_zpool_unmap,
+ .total_size = zs_zpool_total_size,
+};
+
+MODULE_ALIAS("zpool-zsmalloc");
+#endif /* CONFIG_ZPOOL */
+
+/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
+static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
+
+static int is_first_page(struct page *page)
+{
+ return PagePrivate(page);
+}
+
+static int is_last_page(struct page *page)
+{
+ return PagePrivate2(page);
+}
+
+static void get_zspage_mapping(struct page *page, unsigned int *class_idx,
+ enum fullness_group *fullness)
+{
+ unsigned long m;
+ BUG_ON(!is_first_page(page));
+
+ m = (unsigned long)page->mapping;
+ *fullness = m & FULLNESS_MASK;
+ *class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
+}
+
+static void set_zspage_mapping(struct page *page, unsigned int class_idx,
+ enum fullness_group fullness)
+{
+ unsigned long m;
+ BUG_ON(!is_first_page(page));
+
+ m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
+ (fullness & FULLNESS_MASK);
+ page->mapping = (struct address_space *)m;
+}
+
+static int get_size_class_index(int size)
+{
+ int idx = 0;
+
+ if (likely(size > ZS_MIN_ALLOC_SIZE))
+ idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
+ ZS_SIZE_CLASS_DELTA);
+
+ return idx;
+}
+
+static enum fullness_group get_fullness_group(struct page *page)
+{
+ int inuse, max_objects;
+ enum fullness_group fg;
+ BUG_ON(!is_first_page(page));
+
+ inuse = page->inuse;
+ max_objects = page->objects;
+
+ if (inuse == 0)
+ fg = ZS_EMPTY;
+ else if (inuse == max_objects)
+ fg = ZS_FULL;
+ else if (inuse <= max_objects / fullness_threshold_frac)
+ fg = ZS_ALMOST_EMPTY;
+ else
+ fg = ZS_ALMOST_FULL;
+
+ return fg;
+}
+
+static void insert_zspage(struct page *page, struct size_class *class,
+ enum fullness_group fullness)
+{
+ struct page **head;
+
+ BUG_ON(!is_first_page(page));
+
+ if (fullness >= _ZS_NR_FULLNESS_GROUPS)
+ return;
+
+ head = &class->fullness_list[fullness];
+ if (*head)
+ list_add_tail(&page->lru, &(*head)->lru);
+
+ *head = page;
+}
+
+static void remove_zspage(struct page *page, struct size_class *class,
+ enum fullness_group fullness)
+{
+ struct page **head;
+
+ BUG_ON(!is_first_page(page));
+
+ if (fullness >= _ZS_NR_FULLNESS_GROUPS)
+ return;
+
+ head = &class->fullness_list[fullness];
+ BUG_ON(!*head);
+ if (list_empty(&(*head)->lru))
+ *head = NULL;
+ else if (*head == page)
+ *head = (struct page *)list_entry((*head)->lru.next,
+ struct page, lru);
+
+ list_del_init(&page->lru);
+}
+
+static enum fullness_group fix_fullness_group(struct zs_pool *pool,
+ struct page *page)
+{
+ int class_idx;
+ struct size_class *class;
+ enum fullness_group currfg, newfg;
+
+ BUG_ON(!is_first_page(page));
+
+ get_zspage_mapping(page, &class_idx, &currfg);
+ newfg = get_fullness_group(page);
+ if (newfg == currfg)
+ goto out;
+
+ class = pool->size_class[class_idx];
+ remove_zspage(page, class, currfg);
+ insert_zspage(page, class, newfg);
+ set_zspage_mapping(page, class_idx, newfg);
+
+out:
+ return newfg;
+}
+
+/*
+ * We have to decide on how many pages to link together
+ * to form a zspage for each size class. This is important
+ * to reduce wastage due to unusable space left at end of
+ * each zspage which is given as:
+ * wastage = Zp - Zp % size_class
+ * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
+ *
+ * For example, for size class of 3/8 * PAGE_SIZE, we should
+ * link together 3 PAGE_SIZE sized pages to form a zspage
+ * since then we can perfectly fit in 8 such objects.
+ */
+static int get_pages_per_zspage(int class_size)
+{
+ int i, max_usedpc = 0;
+ /* zspage order which gives maximum used size per KB */
+ int max_usedpc_order = 1;
+
+ for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
+ int zspage_size;
+ int waste, usedpc;
+
+ zspage_size = i * PAGE_SIZE;
+ waste = zspage_size % class_size;
+ usedpc = (zspage_size - waste) * 100 / zspage_size;
+
+ if (usedpc > max_usedpc) {
+ max_usedpc = usedpc;
+ max_usedpc_order = i;
+ }
+ }
+
+ return max_usedpc_order;
+}
+
+/*
+ * A single 'zspage' is composed of many system pages which are
+ * linked together using fields in struct page. This function finds
+ * the first/head page, given any component page of a zspage.
+ */
+static struct page *get_first_page(struct page *page)
+{
+ if (is_first_page(page))
+ return page;
+ else
+ return page->first_page;
+}
+
+static struct page *get_next_page(struct page *page)
+{
+ struct page *next;
+
+ if (is_last_page(page))
+ next = NULL;
+ else if (is_first_page(page))
+ next = (struct page *)page->private;
+ else
+ next = list_entry(page->lru.next, struct page, lru);
+
+ return next;
+}
+
+/*
+ * Encode <page, obj_idx> as a single handle value.
+ * On hardware platforms with physical memory starting at 0x0 the pfn
+ * could be 0 so we ensure that the handle will never be 0 by adjusting the
+ * encoded obj_idx value before encoding.
+ */
+static void *obj_location_to_handle(struct page *page, unsigned long obj_idx)
+{
+ unsigned long handle;
+
+ if (!page) {
+ BUG_ON(obj_idx);
+ return NULL;
+ }
+
+ handle = page_to_pfn(page) << OBJ_INDEX_BITS;
+ handle |= ((obj_idx + 1) & OBJ_INDEX_MASK);
+
+ return (void *)handle;
+}
+
+/*
+ * Decode <page, obj_idx> pair from the given object handle. We adjust the
+ * decoded obj_idx back to its original value since it was adjusted in
+ * obj_location_to_handle().
+ */
+static void obj_handle_to_location(unsigned long handle, struct page **page,
+ unsigned long *obj_idx)
+{
+ *page = pfn_to_page(handle >> OBJ_INDEX_BITS);
+ *obj_idx = (handle & OBJ_INDEX_MASK) - 1;
+}
+
+static unsigned long obj_idx_to_offset(struct page *page,
+ unsigned long obj_idx, int class_size)
+{
+ unsigned long off = 0;
+
+ if (!is_first_page(page))
+ off = page->index;
+
+ return off + obj_idx * class_size;
+}
+
+static void reset_page(struct page *page)
+{
+ clear_bit(PG_private, &page->flags);
+ clear_bit(PG_private_2, &page->flags);
+ set_page_private(page, 0);
+ page->mapping = NULL;
+ page->freelist = NULL;
+ page_mapcount_reset(page);
+}
+
+static void free_zspage(struct page *first_page)
+{
+ struct page *nextp, *tmp, *head_extra;
+
+ BUG_ON(!is_first_page(first_page));
+ BUG_ON(first_page->inuse);
+
+ head_extra = (struct page *)page_private(first_page);
+
+ reset_page(first_page);
+ __free_page(first_page);
+
+ /* zspage with only 1 system page */
+ if (!head_extra)
+ return;
+
+ list_for_each_entry_safe(nextp, tmp, &head_extra->lru, lru) {
+ list_del(&nextp->lru);
+ reset_page(nextp);
+ __free_page(nextp);
+ }
+ reset_page(head_extra);
+ __free_page(head_extra);
+}
+
+/* Initialize a newly allocated zspage */
+static void init_zspage(struct page *first_page, struct size_class *class)
+{
+ unsigned long off = 0;
+ struct page *page = first_page;
+
+ BUG_ON(!is_first_page(first_page));
+ while (page) {
+ struct page *next_page;
+ struct link_free *link;
+ unsigned int i = 1;
+ void *vaddr;
+
+ /*
+ * page->index stores offset of first object starting
+ * in the page. For the first page, this is always 0,
+ * so we use first_page->index (aka ->freelist) to store
+ * head of corresponding zspage's freelist.
+ */
+ if (page != first_page)
+ page->index = off;
+
+ vaddr = kmap_atomic(page);
+ link = (struct link_free *)vaddr + off / sizeof(*link);
+
+ while ((off += class->size) < PAGE_SIZE) {
+ link->next = obj_location_to_handle(page, i++);
+ link += class->size / sizeof(*link);
+ }
+
+ /*
+ * We now come to the last (full or partial) object on this
+ * page, which must point to the first object on the next
+ * page (if present)
+ */
+ next_page = get_next_page(page);
+ link->next = obj_location_to_handle(next_page, 0);
+ kunmap_atomic(vaddr);
+ page = next_page;
+ off %= PAGE_SIZE;
+ }
+}
+
+/*
+ * Allocate a zspage for the given size class
+ */
+static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
+{
+ int i, error;
+ struct page *first_page = NULL, *uninitialized_var(prev_page);
+
+ /*
+ * Allocate individual pages and link them together as:
+ * 1. first page->private = first sub-page
+ * 2. all sub-pages are linked together using page->lru
+ * 3. each sub-page is linked to the first page using page->first_page
+ *
+ * For each size class, First/Head pages are linked together using
+ * page->lru. Also, we set PG_private to identify the first page
+ * (i.e. no other sub-page has this flag set) and PG_private_2 to
+ * identify the last page.
+ */
+ error = -ENOMEM;
+ for (i = 0; i < class->pages_per_zspage; i++) {
+ struct page *page;
+
+ page = alloc_page(flags);
+ if (!page)
+ goto cleanup;
+
+ INIT_LIST_HEAD(&page->lru);
+ if (i == 0) { /* first page */
+ SetPagePrivate(page);
+ set_page_private(page, 0);
+ first_page = page;
+ first_page->inuse = 0;
+ }
+ if (i == 1)
+ first_page->private = (unsigned long)page;
+ if (i >= 1)
+ page->first_page = first_page;
+ if (i >= 2)
+ list_add(&page->lru, &prev_page->lru);
+ if (i == class->pages_per_zspage - 1) /* last page */
+ SetPagePrivate2(page);
+ prev_page = page;
+ }
+
+ init_zspage(first_page, class);
+
+ first_page->freelist = obj_location_to_handle(first_page, 0);
+ /* Maximum number of objects we can store in this zspage */
+ first_page->objects = class->pages_per_zspage * PAGE_SIZE / class->size;
+
+ error = 0; /* Success */
+
+cleanup:
+ if (unlikely(error) && first_page) {
+ free_zspage(first_page);
+ first_page = NULL;
+ }
+
+ return first_page;
+}
+
+static struct page *find_get_zspage(struct size_class *class)
+{
+ int i;
+ struct page *page;
+
+ for (i = 0; i < _ZS_NR_FULLNESS_GROUPS; i++) {
+ page = class->fullness_list[i];
+ if (page)
+ break;
+ }
+
+ return page;
+}
+
+#ifdef USE_PGTABLE_MAPPING
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+ /*
+ * Make sure we don't leak memory if a cpu UP notification
+ * and zs_init() race and both call zs_cpu_up() on the same cpu
+ */
+ if (area->vm)
+ return 0;
+ area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
+ if (!area->vm)
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+ if (area->vm)
+ free_vm_area(area->vm);
+ area->vm = NULL;
+}
+
+static inline void *__zs_map_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
+ area->vm_addr = area->vm->addr;
+ return area->vm_addr + off;
+}
+
+static inline void __zs_unmap_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ unsigned long addr = (unsigned long)area->vm_addr;
+
+ unmap_kernel_range(addr, PAGE_SIZE * 2);
+}
+
+#else /* USE_PGTABLE_MAPPING */
+
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+ /*
+ * Make sure we don't leak memory if a cpu UP notification
+ * and zs_init() race and both call zs_cpu_up() on the same cpu
+ */
+ if (area->vm_buf)
+ return 0;
+ area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
+ if (!area->vm_buf)
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+ if (area->vm_buf)
+ free_page((unsigned long)area->vm_buf);
+ area->vm_buf = NULL;
+}
+
+static void *__zs_map_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ int sizes[2];
+ void *addr;
+ char *buf = area->vm_buf;
+
+ /* disable page faults to match kmap_atomic() return conditions */
+ pagefault_disable();
+
+ /* no read fastpath */
+ if (area->vm_mm == ZS_MM_WO)
+ goto out;
+
+ sizes[0] = PAGE_SIZE - off;
+ sizes[1] = size - sizes[0];
+
+ /* copy object to per-cpu buffer */
+ addr = kmap_atomic(pages[0]);
+ memcpy(buf, addr + off, sizes[0]);
+ kunmap_atomic(addr);
+ addr = kmap_atomic(pages[1]);
+ memcpy(buf + sizes[0], addr, sizes[1]);
+ kunmap_atomic(addr);
+out:
+ return area->vm_buf;
+}
+
+static void __zs_unmap_object(struct mapping_area *area,
+ struct page *pages[2], int off, int size)
+{
+ int sizes[2];
+ void *addr;
+ char *buf = area->vm_buf;
+
+ /* no write fastpath */
+ if (area->vm_mm == ZS_MM_RO)
+ goto out;
+
+ sizes[0] = PAGE_SIZE - off;
+ sizes[1] = size - sizes[0];
+
+ /* copy per-cpu buffer to object */
+ addr = kmap_atomic(pages[0]);
+ memcpy(addr + off, buf, sizes[0]);
+ kunmap_atomic(addr);
+ addr = kmap_atomic(pages[1]);
+ memcpy(addr, buf + sizes[0], sizes[1]);
+ kunmap_atomic(addr);
+
+out:
+ /* enable page faults to match kunmap_atomic() return conditions */
+ pagefault_enable();
+}
+
+#endif /* USE_PGTABLE_MAPPING */
+
+static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
+ void *pcpu)
+{
+ int ret, cpu = (long)pcpu;
+ struct mapping_area *area;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ area = &per_cpu(zs_map_area, cpu);
+ ret = __zs_cpu_up(area);
+ if (ret)
+ return notifier_from_errno(ret);
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ area = &per_cpu(zs_map_area, cpu);
+ __zs_cpu_down(area);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block zs_cpu_nb = {
+ .notifier_call = zs_cpu_notifier
+};
+
+static void zs_unregister_cpu_notifier(void)
+{
+ int cpu;
+
+ cpu_notifier_register_begin();
+
+ for_each_online_cpu(cpu)
+ zs_cpu_notifier(NULL, CPU_DEAD, (void *)(long)cpu);
+ __unregister_cpu_notifier(&zs_cpu_nb);
+
+ cpu_notifier_register_done();
+}
+
+static int zs_register_cpu_notifier(void)
+{
+ int cpu, uninitialized_var(ret);
+
+ cpu_notifier_register_begin();
+
+ __register_cpu_notifier(&zs_cpu_nb);
+ for_each_online_cpu(cpu) {
+ ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
+ if (notifier_to_errno(ret))
+ break;
+ }
+
+ cpu_notifier_register_done();
+ return notifier_to_errno(ret);
+}
+
+static void __exit zs_exit(void)
+{
+#ifdef CONFIG_ZPOOL
+ zpool_unregister_driver(&zs_zpool_driver);
+#endif
+ zs_unregister_cpu_notifier();
+}
+
+static int __init zs_init(void)
+{
+ int ret = zs_register_cpu_notifier();
+
+ if (ret) {
+ zs_unregister_cpu_notifier();
+ return ret;
+ }
+
+#ifdef CONFIG_ZPOOL
+ zpool_register_driver(&zs_zpool_driver);
+#endif
+ return 0;
+}
+
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+ return pages_per_zspage * PAGE_SIZE / size;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+ if (prev->pages_per_zspage != pages_per_zspage)
+ return false;
+
+ if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+ != get_maxobj_per_zspage(size, pages_per_zspage))
+ return false;
+
+ return true;
+}
+
+/**
+ * zs_create_pool - Creates an allocation pool to work from.
+ * @flags: allocation flags used to allocate pool metadata
+ *
+ * This function must be called before anything when using
+ * the zsmalloc allocator.
+ *
+ * On success, a pointer to the newly created pool is returned,
+ * otherwise NULL.
+ */
+struct zs_pool *zs_create_pool(gfp_t flags)
+{
+ int i, ovhd_size;
+ struct zs_pool *pool;
+
+ ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
+ pool = kzalloc(ovhd_size, GFP_KERNEL);
+ if (!pool)
+ return NULL;
+
+ /*
+ * Iterate reversly, because, size of size_class that we want to use
+ * for merging should be larger or equal to current size.
+ */
+ for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
+ int size;
+ int pages_per_zspage;
+ struct size_class *class;
+ struct size_class *prev_class;
+
+ size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
+ if (size > ZS_MAX_ALLOC_SIZE)
+ size = ZS_MAX_ALLOC_SIZE;
+ pages_per_zspage = get_pages_per_zspage(size);
+
+ /*
+ * size_class is used for normal zsmalloc operation such
+ * as alloc/free for that size. Although it is natural that we
+ * have one size_class for each size, there is a chance that we
+ * can get more memory utilization if we use one size_class for
+ * many different sizes whose size_class have same
+ * characteristics. So, we makes size_class point to
+ * previous size_class if possible.
+ */
+ if (i < ZS_SIZE_CLASSES - 1) {
+ prev_class = pool->size_class[i + 1];
+ if (can_merge(prev_class, size, pages_per_zspage)) {
+ pool->size_class[i] = prev_class;
+ continue;
+ }
+ }
+
+ class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+ if (!class)
+ goto err;
+
+ class->size = size;
+ class->index = i;
+ class->pages_per_zspage = pages_per_zspage;
+ spin_lock_init(&class->lock);
+ pool->size_class[i] = class;
+ }
+
+ pool->flags = flags;
+
+ return pool;
+
+err:
+ zs_destroy_pool(pool);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(zs_create_pool);
+
+void zs_destroy_pool(struct zs_pool *pool)
+{
+ int i;
+
+ for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+ int fg;
+ struct size_class *class = pool->size_class[i];
+
+ if (!class)
+ continue;
+
+ if (class->index != i)
+ continue;
+
+ for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
+ if (class->fullness_list[fg]) {
+ pr_info("Freeing non-empty class with size "
+ "%db, fullness group %d\n",
+ class->size, fg);
+ }
+ }
+ kfree(class);
+ }
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(zs_destroy_pool);
+
+/**
+ * zs_malloc - Allocate block of given size from pool.
+ * @pool: pool to allocate from
+ * @size: size of block to allocate
+ *
+ * On success, handle to the allocated object is returned,
+ * otherwise 0.
+ * Allocation requests with size > ZS_MAX_ALLOC_SIZE will fail.
+ */
+unsigned long zs_malloc(struct zs_pool *pool, size_t size)
+{
+ unsigned long obj;
+ struct link_free *link;
+ struct size_class *class;
+ void *vaddr;
+
+ struct page *first_page, *m_page;
+ unsigned long m_objidx, m_offset;
+
+ if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
+ return 0;
+
+ class = pool->size_class[get_size_class_index(size)];
+
+ spin_lock(&class->lock);
+ first_page = find_get_zspage(class);
+
+ if (!first_page) {
+ spin_unlock(&class->lock);
+ first_page = alloc_zspage(class, pool->flags);
+ if (unlikely(!first_page))
+ return 0;
+
+ set_zspage_mapping(first_page, class->index, ZS_EMPTY);
+ atomic_long_add(class->pages_per_zspage,
+ &pool->pages_allocated);
+ spin_lock(&class->lock);
+ }
+
+ obj = (unsigned long)first_page->freelist;
+ obj_handle_to_location(obj, &m_page, &m_objidx);
+ m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
+
+ vaddr = kmap_atomic(m_page);
+ link = (struct link_free *)vaddr + m_offset / sizeof(*link);
+ first_page->freelist = link->next;
+ memset(link, POISON_INUSE, sizeof(*link));
+ kunmap_atomic(vaddr);
+
+ first_page->inuse++;
+ /* Now move the zspage to another fullness group, if required */
+ fix_fullness_group(pool, first_page);
+ spin_unlock(&class->lock);
+
+ return obj;
+}
+EXPORT_SYMBOL_GPL(zs_malloc);
+
+void zs_free(struct zs_pool *pool, unsigned long obj)
+{
+ struct link_free *link;
+ struct page *first_page, *f_page;
+ unsigned long f_objidx, f_offset;
+ void *vaddr;
+
+ int class_idx;
+ struct size_class *class;
+ enum fullness_group fullness;
+
+ if (unlikely(!obj))
+ return;
+
+ obj_handle_to_location(obj, &f_page, &f_objidx);
+ first_page = get_first_page(f_page);
+
+ get_zspage_mapping(first_page, &class_idx, &fullness);
+ class = pool->size_class[class_idx];
+ f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
+
+ spin_lock(&class->lock);
+
+ /* Insert this object in containing zspage's freelist */
+ vaddr = kmap_atomic(f_page);
+ link = (struct link_free *)(vaddr + f_offset);
+ link->next = first_page->freelist;
+ kunmap_atomic(vaddr);
+ first_page->freelist = (void *)obj;
+
+ first_page->inuse--;
+ fullness = fix_fullness_group(pool, first_page);
+ spin_unlock(&class->lock);
+
+ if (fullness == ZS_EMPTY) {
+ atomic_long_sub(class->pages_per_zspage,
+ &pool->pages_allocated);
+ free_zspage(first_page);
+ }
+}
+EXPORT_SYMBOL_GPL(zs_free);
+
+/**
+ * zs_map_object - get address of allocated object from handle.
+ * @pool: pool from which the object was allocated
+ * @handle: handle returned from zs_malloc
+ *
+ * Before using an object allocated from zs_malloc, it must be mapped using
+ * this function. When done with the object, it must be unmapped using
+ * zs_unmap_object.
+ *
+ * Only one object can be mapped per cpu at a time. There is no protection
+ * against nested mappings.
+ *
+ * This function returns with preemption and page faults disabled.
+*/
+void *zs_map_object(struct zs_pool *pool, unsigned long handle,
+ enum zs_mapmode mm)
+{
+ struct page *page;
+ unsigned long obj_idx, off;
+
+ unsigned int class_idx;
+ enum fullness_group fg;
+ struct size_class *class;
+ struct mapping_area *area;
+ struct page *pages[2];
+
+ BUG_ON(!handle);
+
+ /*
+ * Because we use per-cpu mapping areas shared among the
+ * pools/users, we can't allow mapping in interrupt context
+ * because it can corrupt another users mappings.
+ */
+ BUG_ON(in_interrupt());
+
+ obj_handle_to_location(handle, &page, &obj_idx);
+ get_zspage_mapping(get_first_page(page), &class_idx, &fg);
+ class = pool->size_class[class_idx];
+ off = obj_idx_to_offset(page, obj_idx, class->size);
+
+ area = &get_cpu_var(zs_map_area);
+ area->vm_mm = mm;
+ if (off + class->size <= PAGE_SIZE) {
+ /* this object is contained entirely within a page */
+ area->vm_addr = kmap_atomic(page);
+ return area->vm_addr + off;
+ }
+
+ /* this object spans two pages */
+ pages[0] = page;
+ pages[1] = get_next_page(page);
+ BUG_ON(!pages[1]);
+
+ return __zs_map_object(area, pages, off, class->size);
+}
+EXPORT_SYMBOL_GPL(zs_map_object);
+
+void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
+{
+ struct page *page;
+ unsigned long obj_idx, off;
+
+ unsigned int class_idx;
+ enum fullness_group fg;
+ struct size_class *class;
+ struct mapping_area *area;
+
+ BUG_ON(!handle);
+
+ obj_handle_to_location(handle, &page, &obj_idx);
+ get_zspage_mapping(get_first_page(page), &class_idx, &fg);
+ class = pool->size_class[class_idx];
+ off = obj_idx_to_offset(page, obj_idx, class->size);
+
+ area = &__get_cpu_var(zs_map_area);
+ if (off + class->size <= PAGE_SIZE)
+ kunmap_atomic(area->vm_addr);
+ else {
+ struct page *pages[2];
+
+ pages[0] = page;
+ pages[1] = get_next_page(page);
+ BUG_ON(!pages[1]);
+
+ __zs_unmap_object(area, pages, off, class->size);
+ }
+ put_cpu_var(zs_map_area);
+}
+EXPORT_SYMBOL_GPL(zs_unmap_object);
+
+unsigned long zs_get_total_pages(struct zs_pool *pool)
+{
+ return atomic_long_read(&pool->pages_allocated);
+}
+EXPORT_SYMBOL_GPL(zs_get_total_pages);
+
+module_init(zs_init);
+module_exit(zs_exit);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Nitin Gupta <ngupta@vflare.org>");
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9424f37..86abb2e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -305,9 +305,11 @@
static void vlan_transfer_features(struct net_device *dev,
struct net_device *vlandev)
{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
+
vlandev->gso_max_size = dev->gso_max_size;
- if (dev->features & NETIF_F_HW_VLAN_CTAG_TX)
+ if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
vlandev->hard_header_len = dev->hard_header_len;
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 8a15eaa..42ef36a 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -9,7 +9,7 @@
{
struct sk_buff *skb = *skbp;
__be16 vlan_proto = skb->vlan_proto;
- u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
+ u16 vlan_id = vlan_tx_tag_get_id(skb);
struct net_device *vlan_dev;
struct vlan_pcpu_stats *rx_stats;
@@ -103,8 +103,11 @@
static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
{
- if (skb_cow(skb, skb_headroom(skb)) < 0)
+ if (skb_cow(skb, skb_headroom(skb)) < 0) {
+ kfree_skb(skb);
return NULL;
+ }
+
memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
skb->mac_header += VLAN_HLEN;
return skb;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 3a8c8fd..698e922 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -73,6 +73,8 @@
{
struct vlan_priority_tci_mapping *mp;
+ smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */
+
mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)];
while (mp) {
if (mp->priority == skb->priority) {
@@ -249,6 +251,11 @@
np->next = mp;
np->priority = skb_prio;
np->vlan_qos = vlan_qos;
+ /* Before inserting this element in hash table, make sure all its fields
+ * are committed to memory.
+ * coupled with smp_rmb() in vlan_dev_get_egress_qos_mask()
+ */
+ smp_wmb();
vlan->egress_priority_map[skb_prio & 0xF] = np;
if (vlan_qos)
vlan->nr_egress_mappings++;
@@ -505,10 +512,48 @@
}
}
+static int vlan_calculate_locking_subclass(struct net_device *real_dev)
+{
+ int subclass = 0;
+
+ while (is_vlan_dev(real_dev)) {
+ subclass++;
+ real_dev = vlan_dev_priv(real_dev)->real_dev;
+ }
+
+ return subclass;
+}
+
+static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
+{
+ int err = 0, subclass;
+
+ subclass = vlan_calculate_locking_subclass(to);
+
+ spin_lock_nested(&to->addr_list_lock, subclass);
+ err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
+ if (!err)
+ __dev_set_rx_mode(to);
+ spin_unlock(&to->addr_list_lock);
+}
+
+static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
+{
+ int err = 0, subclass;
+
+ subclass = vlan_calculate_locking_subclass(to);
+
+ spin_lock_nested(&to->addr_list_lock, subclass);
+ err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
+ if (!err)
+ __dev_set_rx_mode(to);
+ spin_unlock(&to->addr_list_lock);
+}
+
static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
{
- dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
- dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+ vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+ vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
}
/*
@@ -542,6 +587,26 @@
.parse = eth_header_parse,
};
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+ unsigned short type,
+ const void *daddr, const void *saddr,
+ unsigned int len)
+{
+ struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+ struct net_device *real_dev = vlan->real_dev;
+
+ if (saddr == NULL)
+ saddr = dev->dev_addr;
+
+ return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
+
+static const struct header_ops vlan_passthru_header_ops = {
+ .create = vlan_passthru_hard_header,
+ .rebuild = dev_rebuild_header,
+ .parse = eth_header_parse,
+};
+
static struct device_type vlan_type = {
.name = "vlan",
};
@@ -584,8 +649,9 @@
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
- dev->header_ops = real_dev->header_ops;
+ if (vlan_hw_offload_capable(real_dev->features,
+ vlan_dev_priv(dev)->vlan_proto)) {
+ dev->header_ops = &vlan_passthru_header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
dev->header_ops = &vlan_header_ops;
@@ -596,9 +662,7 @@
SET_NETDEV_DEVTYPE(dev, &vlan_type);
- if (is_vlan_dev(real_dev))
- subclass = 1;
-
+ subclass = vlan_calculate_locking_subclass(dev);
vlan_dev_set_lockdep_class(dev, subclass);
vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 3091297..c7e634a 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -171,7 +171,7 @@
return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */
nla_total_size(2) + /* IFLA_VLAN_ID */
- sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
+ nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */
vlan_qos_map_size(vlan->nr_ingress_mappings) +
vlan_qos_map_size(vlan->nr_egress_mappings);
}
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index de8df95..2ee3879 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -24,11 +24,11 @@
*/
void p9_release_pages(struct page **pages, int nr_pages)
{
- int i = 0;
- while (pages[i] && nr_pages--) {
- put_page(pages[i]);
- i++;
- }
+ int i;
+
+ for (i = 0; i < nr_pages; i++)
+ if (pages[i])
+ put_page(pages[i]);
}
EXPORT_SYMBOL(p9_release_pages);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index e1c26b1..c76a438 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -340,7 +340,10 @@
int count = nr_pages;
while (nr_pages) {
s = rest_of_page(data);
- pages[index++] = kmap_to_page(data);
+ if (is_vmalloc_addr(data))
+ pages[index++] = vmalloc_to_page(data);
+ else
+ pages[index++] = kmap_to_page(data);
data += s;
nr_pages--;
}
@@ -577,6 +580,10 @@
mutex_lock(&virtio_9p_lock);
list_add_tail(&chan->chan_list, &virtio_chan_list);
mutex_unlock(&virtio_9p_lock);
+
+ /* Let udev rules use the new mount_tag attribute. */
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
+
return 0;
out_free_tag:
@@ -654,6 +661,7 @@
list_del(&chan->chan_list);
mutex_unlock(&virtio_9p_lock);
sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
+ kobject_uevent(&(vdev->dev.kobj), KOBJ_CHANGE);
kfree(chan->tag);
kfree(chan->vc_wq);
kfree(chan);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index ef12839..8799e17 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1489,8 +1489,6 @@
goto drop;
/* Queue packet (standard) */
- skb->sk = sock;
-
if (sock_queue_rcv_skb(sock, skb) < 0)
goto drop;
@@ -1644,7 +1642,6 @@
if (!skb)
goto out;
- skb->sk = sk;
skb_reserve(skb, ddp_dl->header_length);
skb_reserve(skb, dev->hard_header_len);
skb->dev = dev;
@@ -1735,7 +1732,6 @@
size_t size, int flags)
{
struct sock *sk = sock->sk;
- struct sockaddr_at *sat = (struct sockaddr_at *)msg->msg_name;
struct ddpehdr *ddp;
int copied = 0;
int offset = 0;
@@ -1764,14 +1760,13 @@
}
err = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copied);
- if (!err) {
- if (sat) {
- sat->sat_family = AF_APPLETALK;
- sat->sat_port = ddp->deh_sport;
- sat->sat_addr.s_node = ddp->deh_snode;
- sat->sat_addr.s_net = ddp->deh_snet;
- }
- msg->msg_namelen = sizeof(*sat);
+ if (!err && msg->msg_name) {
+ struct sockaddr_at *sat = msg->msg_name;
+ sat->sat_family = AF_APPLETALK;
+ sat->sat_port = ddp->deh_sport;
+ sat->sat_addr.s_node = ddp->deh_snode;
+ sat->sat_addr.s_net = ddp->deh_snet;
+ msg->msg_namelen = sizeof(*sat);
}
skb_free_datagram(sk, skb); /* Free the datagram. */
diff --git a/net/atm/common.c b/net/atm/common.c
index 737bef5..7b49100 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -531,8 +531,6 @@
struct sk_buff *skb;
int copied, error = -EINVAL;
- msg->msg_namelen = 0;
-
if (sock->state != SS_CONNECTED)
return -ENOTCONN;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e277e38..ba6db78 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1636,11 +1636,11 @@
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (msg->msg_namelen != 0) {
- struct sockaddr_ax25 *sax = (struct sockaddr_ax25 *)msg->msg_name;
+ if (msg->msg_name) {
ax25_digi digi;
ax25_address src;
const unsigned char *mac = skb_mac_header(skb);
+ struct sockaddr_ax25 *sax = msg->msg_name;
memset(sax, 0, sizeof(struct full_sockaddr_ax25));
ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL,
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 51aafd6..f1cb1f5 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -61,6 +61,7 @@
batadv_recv_handler_init();
batadv_iv_init();
+ batadv_nc_init();
batadv_event_workqueue = create_singlethread_workqueue("bat_events");
@@ -138,7 +139,7 @@
if (ret < 0)
goto err;
- ret = batadv_nc_init(bat_priv);
+ ret = batadv_nc_mesh_init(bat_priv);
if (ret < 0)
goto err;
@@ -163,7 +164,7 @@
batadv_vis_quit(bat_priv);
batadv_gw_node_purge(bat_priv);
- batadv_nc_free(bat_priv);
+ batadv_nc_mesh_free(bat_priv);
batadv_dat_free(bat_priv);
batadv_bla_free(bat_priv);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index e84629e..f97aeee 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -35,6 +35,20 @@
struct batadv_hard_iface *recv_if);
/**
+ * batadv_nc_init - one-time initialization for network coding
+ */
+int __init batadv_nc_init(void)
+{
+ int ret;
+
+ /* Register our packet type */
+ ret = batadv_recv_handler_register(BATADV_CODED,
+ batadv_nc_recv_coded_packet);
+
+ return ret;
+}
+
+/**
* batadv_nc_start_timer - initialise the nc periodic worker
* @bat_priv: the bat priv with all the soft interface information
*/
@@ -45,10 +59,10 @@
}
/**
- * batadv_nc_init - initialise coding hash table and start house keeping
+ * batadv_nc_mesh_init - initialise coding hash table and start house keeping
* @bat_priv: the bat priv with all the soft interface information
*/
-int batadv_nc_init(struct batadv_priv *bat_priv)
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
{
bat_priv->nc.timestamp_fwd_flush = jiffies;
bat_priv->nc.timestamp_sniffed_purge = jiffies;
@@ -70,11 +84,6 @@
batadv_hash_set_lock_class(bat_priv->nc.coding_hash,
&batadv_nc_decoding_hash_lock_class_key);
- /* Register our packet type */
- if (batadv_recv_handler_register(BATADV_CODED,
- batadv_nc_recv_coded_packet) < 0)
- goto err;
-
INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker);
batadv_nc_start_timer(bat_priv);
@@ -1722,12 +1731,11 @@
}
/**
- * batadv_nc_free - clean up network coding memory
+ * batadv_nc_mesh_free - clean up network coding memory
* @bat_priv: the bat priv with all the soft interface information
*/
-void batadv_nc_free(struct batadv_priv *bat_priv)
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
{
- batadv_recv_handler_unregister(BATADV_CODED);
cancel_delayed_work_sync(&bat_priv->nc.work);
batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL);
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 4fa6d0c..bd4295f 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -22,8 +22,9 @@
#ifdef CONFIG_BATMAN_ADV_NC
-int batadv_nc_init(struct batadv_priv *bat_priv);
-void batadv_nc_free(struct batadv_priv *bat_priv);
+int batadv_nc_init(void);
+int batadv_nc_mesh_init(struct batadv_priv *bat_priv);
+void batadv_nc_mesh_free(struct batadv_priv *bat_priv);
void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
struct batadv_orig_node *orig_neigh_node,
@@ -47,12 +48,17 @@
#else /* ifdef CONFIG_BATMAN_ADV_NC */
-static inline int batadv_nc_init(struct batadv_priv *bat_priv)
+static inline int batadv_nc_init(void)
{
return 0;
}
-static inline void batadv_nc_free(struct batadv_priv *bat_priv)
+static inline int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
+{
+ return 0;
+}
+
+static inline void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
{
return;
}
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9096137..6629cdc 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -221,8 +221,6 @@
if (flags & (MSG_OOB))
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb) {
if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -287,8 +285,6 @@
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
BT_DBG("sk %p size %zu", sk, size);
lock_sock(sk);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 6c7f363..8e7290a 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -652,14 +652,17 @@
if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
struct hci_cp_auth_requested cp;
- /* encrypt must be pending if auth is also pending */
- set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
-
cp.handle = cpu_to_le16(conn->handle);
hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED,
sizeof(cp), &cp);
- if (conn->key_type != 0xff)
+
+ /* If we're already encrypted set the REAUTH_PEND flag,
+ * otherwise set the ENCRYPT_PEND.
+ */
+ if (conn->link_mode & HCI_LM_ENCRYPT)
set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
+ else
+ set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
}
return 0;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ace5e55..7c88f5f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1123,7 +1123,11 @@
goto done;
}
- if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) {
+ /* Check for rfkill but allow the HCI setup stage to proceed
+ * (which in itself doesn't cause any RF activity).
+ */
+ if (test_bit(HCI_RFKILLED, &hdev->dev_flags) &&
+ !test_bit(HCI_SETUP, &hdev->dev_flags)) {
ret = -ERFKILL;
goto done;
}
@@ -1545,10 +1549,13 @@
BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked);
- if (!blocked)
- return 0;
-
- hci_dev_do_close(hdev);
+ if (blocked) {
+ set_bit(HCI_RFKILLED, &hdev->dev_flags);
+ if (!test_bit(HCI_SETUP, &hdev->dev_flags))
+ hci_dev_do_close(hdev);
+ } else {
+ clear_bit(HCI_RFKILLED, &hdev->dev_flags);
+}
return 0;
}
@@ -1570,9 +1577,13 @@
return;
}
- if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
+ if (test_bit(HCI_RFKILLED, &hdev->dev_flags)) {
+ clear_bit(HCI_AUTO_OFF, &hdev->dev_flags);
+ hci_dev_do_close(hdev);
+ } else if (test_bit(HCI_AUTO_OFF, &hdev->dev_flags)) {
queue_delayed_work(hdev->req_workqueue, &hdev->power_off,
HCI_AUTO_OFF_TIMEOUT);
+ }
if (test_and_clear_bit(HCI_SETUP, &hdev->dev_flags))
mgmt_index_added(hdev);
@@ -2241,6 +2252,9 @@
}
}
+ if (hdev->rfkill && rfkill_blocked(hdev->rfkill))
+ set_bit(HCI_RFKILLED, &hdev->dev_flags);
+
set_bit(HCI_SETUP, &hdev->dev_flags);
if (hdev->dev_type != HCI_AMP)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index b93cd2e..5daf7ab 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3051,6 +3051,12 @@
if (!conn)
goto unlock;
+ /* For BR/EDR the necessary steps are taken through the
+ * auth_complete event.
+ */
+ if (conn->type != LE_LINK)
+ goto unlock;
+
if (!ev->status)
conn->sec_level = conn->pending_sec_level;
@@ -3212,8 +3218,11 @@
/* If we're not the initiators request authorization to
* proceed from user space (mgmt_user_confirm with
- * confirm_hint set to 1). */
- if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+ * confirm_hint set to 1). The exception is if neither
+ * side had MITM in which case we do auto-accept.
+ */
+ if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+ (loc_mitm || rem_mitm)) {
BT_DBG("Confirming auto-accept as acceptor");
confirm_hint = 1;
goto confirm;
@@ -3611,11 +3620,21 @@
cp.handle = cpu_to_le16(conn->handle);
if (ltk->authenticated)
- conn->sec_level = BT_SECURITY_HIGH;
+ conn->pending_sec_level = BT_SECURITY_HIGH;
+ else
+ conn->pending_sec_level = BT_SECURITY_MEDIUM;
+
+ conn->enc_key_size = ltk->enc_size;
hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
- if (ltk->type & HCI_SMP_STK) {
+ /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
+ * temporary key used to encrypt a connection following
+ * pairing. It is used during the Encrypted Session Setup to
+ * distribute the keys. Later, security can be re-established
+ * using a distributed LTK.
+ */
+ if (ltk->type == HCI_SMP_STK_SLAVE) {
list_del(<k->list);
kfree(ltk);
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 9bd7d95..fa4bf66 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -752,8 +752,6 @@
if (!skb)
return err;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 940f5ac..de030f5 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -231,17 +231,22 @@
static int hidp_send_report(struct hidp_session *session, struct hid_report *report)
{
- unsigned char buf[32], hdr;
- int rsize;
+ unsigned char hdr;
+ u8 *buf;
+ int rsize, ret;
- rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0);
- if (rsize > sizeof(buf))
+ buf = hid_alloc_report_buf(report, GFP_ATOMIC);
+ if (!buf)
return -EIO;
hid_output_report(report, buf);
hdr = HIDP_TRANS_DATA | HIDP_DATA_RTYPE_OUPUT;
- return hidp_send_intr_message(session, hdr, buf, rsize);
+ rsize = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+ ret = hidp_send_intr_message(session, hdr, buf, rsize);
+
+ kfree(buf);
+ return ret;
}
static int hidp_get_raw_report(struct hid_device *hid,
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 36fed40..5f36f70 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -887,7 +887,8 @@
l2cap_chan_close(chan, 0);
lock_sock(sk);
- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED,
sk->sk_lingertime);
}
@@ -949,13 +950,16 @@
/* Check for backlog size */
if (sk_acceptq_is_full(parent)) {
BT_DBG("backlog full %d", parent->sk_ack_backlog);
+ release_sock(parent);
return NULL;
}
sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
GFP_ATOMIC);
- if (!sk)
+ if (!sk) {
+ release_sock(parent);
return NULL;
+ }
bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f8ecbc7..8208a13 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2333,8 +2333,13 @@
}
if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
- /* Continue with pairing via SMP */
+ /* Continue with pairing via SMP. The hdev lock must be
+ * released as SMP may try to recquire it for crypto
+ * purposes.
+ */
+ hci_dev_unlock(hdev);
err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+ hci_dev_lock(hdev);
if (!err)
err = cmd_complete(sk, hdev->id, mgmt_op,
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index ca957d3..19ba192 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -1857,10 +1857,13 @@
/* Get data directly from socket receive queue without copying it. */
while ((skb = skb_dequeue(&sk->sk_receive_queue))) {
skb_orphan(skb);
- if (!skb_linearize(skb))
+ if (!skb_linearize(skb)) {
s = rfcomm_recv_frame(s, skb);
- else
+ if (!s)
+ break;
+ } else {
kfree_skb(skb);
+ }
}
if (s && (sk->sk_state == BT_CLOSED))
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 30b3721..7ca014d 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -608,7 +608,6 @@
if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) {
rfcomm_dlc_accept(d);
- msg->msg_namelen = 0;
return 0;
}
@@ -888,7 +887,8 @@
sk->sk_shutdown = SHUTDOWN_MASK;
__rfcomm_sock_close(sk);
- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
}
release_sock(sk);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e7bd4ee..c9ae6b7 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -700,7 +700,6 @@
test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
sco_conn_defer_accept(pi->conn->hcon, 0);
sk->sk_state = BT_CONFIG;
- msg->msg_namelen = 0;
release_sock(sk);
return 0;
@@ -859,7 +858,8 @@
sco_sock_clear_timer(sk);
__sco_sock_close(sk);
- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime)
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING))
err = bt_sock_wait_state(sk, BT_CLOSED,
sk->sk_lingertime);
}
@@ -879,7 +879,8 @@
sco_sock_close(sk);
- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) {
+ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime &&
+ !(current->flags & PF_EXITING)) {
lock_sock(sk);
err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime);
release_sock(sk);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index ebfa444..84dd783 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -161,7 +161,7 @@
if (!pv)
return;
- for_each_set_bit_from(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) {
f = __br_fdb_get(br, br->dev->dev_addr, vid);
if (f && f->is_local && !f->dst)
fdb_delete(br, f);
@@ -725,7 +725,7 @@
/* VID was specified, so use it. */
err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
} else {
- if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) {
+ if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
goto out;
}
@@ -734,7 +734,7 @@
* specify a VLAN. To be nice, add/update entry for every
* vlan on this port.
*/
- for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
if (err)
goto out;
@@ -812,7 +812,7 @@
err = __br_fdb_delete(p, addr, vid);
} else {
- if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) {
+ if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) {
err = __br_fdb_delete(p, addr, 0);
goto out;
}
@@ -822,7 +822,7 @@
* vlan on this port.
*/
err = -ENOENT;
- for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
err &= __br_fdb_delete(p, addr, vid);
}
}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 4cdba60..32bd1e8 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -172,6 +172,8 @@
del_nbp(p);
}
+ br_fdb_delete_by_port(br, NULL, 1);
+
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 828e2bc..0a3bc82 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -71,7 +71,7 @@
goto drop;
if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid))
- goto drop;
+ goto out;
/* insert into forwarding database after filtering to avoid spoofing */
br = p->br;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index d6448e3..81de010 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1176,6 +1176,12 @@
br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
+ /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */
+ if (!(ipv6_addr_type(&ip6h->saddr) & IPV6_ADDR_LINKLOCAL)) {
+ err = -EINVAL;
+ goto out;
+ }
+
if (skb->len == sizeof(*mld)) {
if (!pskb_may_pull(skb, sizeof(*mld))) {
err = -EINVAL;
@@ -1185,7 +1191,7 @@
max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay));
if (max_delay)
group = &mld->mld_mca;
- } else if (skb->len >= sizeof(*mld2q)) {
+ } else {
if (!pskb_may_pull(skb, sizeof(*mld2q))) {
err = -EINVAL;
goto out;
@@ -1193,7 +1199,8 @@
mld2q = (struct mld2_query *)icmp6_hdr(skb);
if (!mld2q->mld2q_nsrcs)
group = &mld2q->mld2q_mca;
- max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(ntohs(mld2q->mld2q_mrc)) : 1;
+
+ max_delay = max(msecs_to_jiffies(MLDV2_MRC(ntohs(mld2q->mld2q_mrc))), 1UL);
}
if (!group)
@@ -1838,7 +1845,7 @@
u32 old;
struct net_bridge_mdb_htable *mdb;
- spin_lock(&br->multicast_lock);
+ spin_lock_bh(&br->multicast_lock);
if (!netif_running(br->dev))
goto unlock;
@@ -1870,7 +1877,7 @@
}
unlock:
- spin_unlock(&br->multicast_lock);
+ spin_unlock_bh(&br->multicast_lock);
return err;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 8e3abf5..f16e9e4 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -128,7 +128,7 @@
else
pv = br_get_vlan_info(br);
- if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN))
+ if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID))
goto done;
af = nla_nest_start(skb, IFLA_AF_SPEC);
@@ -136,7 +136,7 @@
goto nla_put_failure;
pvid = br_get_pvid(pv);
- for_each_set_bit(vid, pv->vlan_bitmap, BR_VLAN_BITMAP_LEN) {
+ for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
vinfo.vid = vid;
vinfo.flags = 0;
if (vid == pvid)
@@ -203,7 +203,7 @@
struct net_device *dev, u32 filter_mask)
{
int err = 0;
- struct net_bridge_port *port = br_port_get_rcu(dev);
+ struct net_bridge_port *port = br_port_get_rtnl(dev);
/* not a bridge port and */
if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN))
@@ -438,12 +438,26 @@
return 0;
}
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ if (tb[IFLA_ADDRESS]) {
+ spin_lock_bh(&br->lock);
+ br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+ spin_unlock_bh(&br->lock);
+ }
+
+ return register_netdevice(dev);
+}
+
static size_t br_get_link_af_size(const struct net_device *dev)
{
struct net_port_vlans *pv;
if (br_port_exists(dev))
- pv = nbp_get_vlan_info(br_port_get_rcu(dev));
+ pv = nbp_get_vlan_info(br_port_get_rtnl(dev));
else if (dev->priv_flags & IFF_EBRIDGE)
pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev));
else
@@ -466,6 +480,7 @@
.priv_size = sizeof(struct net_bridge),
.setup = br_dev_setup,
.validate = br_validate,
+ .newlink = br_dev_newlink,
.dellink = br_dev_delete,
};
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d2c043a..11ab662 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -183,13 +183,10 @@
static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
{
- struct net_bridge_port *port =
- rcu_dereference_rtnl(dev->rx_handler_data);
-
- return br_port_exists(dev) ? port : NULL;
+ return rcu_dereference(dev->rx_handler_data);
}
-static inline struct net_bridge_port *br_port_get_rtnl(struct net_device *dev)
+static inline struct net_bridge_port *br_port_get_rtnl(const struct net_device *dev)
{
return br_port_exists(dev) ?
rtnl_dereference(dev->rx_handler_data) : NULL;
@@ -432,6 +429,16 @@
extern int br_handle_frame_finish(struct sk_buff *skb);
extern rx_handler_result_t br_handle_frame(struct sk_buff **pskb);
+static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
+{
+ return rcu_dereference(dev->rx_handler) == br_handle_frame;
+}
+
+static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev)
+{
+ return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL;
+}
+
/* br_ioctl.c */
extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg);
@@ -714,6 +721,7 @@
extern void br_init_port(struct net_bridge_port *p);
extern void br_become_designated_port(struct net_bridge_port *p);
+extern void __br_set_forward_delay(struct net_bridge *br, unsigned long t);
extern int br_set_forward_delay(struct net_bridge *br, unsigned long x);
extern int br_set_hello_time(struct net_bridge *br, unsigned long x);
extern int br_set_max_age(struct net_bridge *br, unsigned long x);
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index 1c0a50f..3c86f05 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -209,7 +209,7 @@
p->designated_age = jiffies - bpdu->message_age;
mod_timer(&p->message_age_timer, jiffies
- + (p->br->max_age - bpdu->message_age));
+ + (bpdu->max_age - bpdu->message_age));
}
/* called under bridge lock */
@@ -544,18 +544,27 @@
}
-int br_set_forward_delay(struct net_bridge *br, unsigned long val)
+void __br_set_forward_delay(struct net_bridge *br, unsigned long t)
{
- unsigned long t = clock_t_to_jiffies(val);
-
- if (br->stp_enabled != BR_NO_STP &&
- (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY))
- return -ERANGE;
-
- spin_lock_bh(&br->lock);
br->bridge_forward_delay = t;
if (br_is_root_bridge(br))
br->forward_delay = br->bridge_forward_delay;
+}
+
+int br_set_forward_delay(struct net_bridge *br, unsigned long val)
+{
+ unsigned long t = clock_t_to_jiffies(val);
+ int err = -ERANGE;
+
+ spin_lock_bh(&br->lock);
+ if (br->stp_enabled != BR_NO_STP &&
+ (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY))
+ goto unlock;
+
+ __br_set_forward_delay(br, t);
+ err = 0;
+
+unlock:
spin_unlock_bh(&br->lock);
- return 0;
+ return err;
}
diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 8660ea3..bdb459d 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -153,7 +153,7 @@
if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0)
goto err;
- p = br_port_get_rcu(dev);
+ p = br_port_get_check_rcu(dev);
if (!p)
goto err;
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index d45e760..656a6f3 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -129,6 +129,14 @@
char *envp[] = { NULL };
r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
+
+ spin_lock_bh(&br->lock);
+
+ if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY)
+ __br_set_forward_delay(br, BR_MIN_FORWARD_DELAY);
+ else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
+ __br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
+
if (r == 0) {
br->stp_enabled = BR_USER_STP;
br_debug(br, "userspace STP started\n");
@@ -137,10 +145,10 @@
br_debug(br, "using kernel STP\n");
/* To start timers on any ports left in blocking */
- spin_lock_bh(&br->lock);
br_port_state_selection(br);
- spin_unlock_bh(&br->lock);
}
+
+ spin_unlock_bh(&br->lock);
}
static void br_stp_stop(struct net_bridge *br)
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index bd58b45..d8deb8b 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -108,7 +108,7 @@
clear_bit(vid, v->vlan_bitmap);
v->num_vlans--;
- if (bitmap_empty(v->vlan_bitmap, BR_VLAN_BITMAP_LEN)) {
+ if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) {
if (v->port_idx)
rcu_assign_pointer(v->parent.port->vlan_info, NULL);
else
@@ -122,7 +122,7 @@
{
smp_wmb();
v->pvid = 0;
- bitmap_zero(v->vlan_bitmap, BR_VLAN_BITMAP_LEN);
+ bitmap_zero(v->vlan_bitmap, VLAN_N_VID);
if (v->port_idx)
rcu_assign_pointer(v->parent.port->vlan_info, NULL);
else
@@ -202,7 +202,7 @@
* rejected.
*/
if (!v)
- return false;
+ goto drop;
if (br_vlan_get_tag(skb, vid)) {
u16 pvid = br_get_pvid(v);
@@ -212,7 +212,7 @@
* traffic belongs to.
*/
if (pvid == VLAN_N_VID)
- return false;
+ goto drop;
/* PVID is set on this port. Any untagged ingress
* frame is considered to belong to this vlan.
@@ -224,7 +224,8 @@
/* Frame had a valid vlan tag. See if vlan is allowed */
if (test_bit(*vid, v->vlan_bitmap))
return true;
-
+drop:
+ kfree_skb(skb);
return false;
}
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 3d110c4..6651a77 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1044,10 +1044,9 @@
if (repl->num_counters &&
copy_to_user(repl->counters, counterstmp,
repl->num_counters * sizeof(struct ebt_counter))) {
- ret = -EFAULT;
+ /* Silent error, can't fail, new table is already in place */
+ net_warn_ratelimited("ebtables: counters copy to user failed while replacing table\n");
}
- else
- ret = 0;
/* decrease module count and free resources */
EBT_ENTRY_ITERATE(table->entries, table->entries_size,
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 05a41c7..526bf56 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -283,11 +283,9 @@
int copylen;
ret = -EOPNOTSUPP;
- if (m->msg_flags&MSG_OOB)
+ if (flags & MSG_OOB)
goto read_error;
- m->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags, 0 , &ret);
if (!skb)
goto read_error;
@@ -361,8 +359,6 @@
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
/*
* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c
index 2bd4b58..0f45522 100644
--- a/net/caif/cfctrl.c
+++ b/net/caif/cfctrl.c
@@ -293,9 +293,10 @@
count = cfctrl_cancel_req(&cfctrl->serv.layer,
user_layer);
- if (count != 1)
+ if (count != 1) {
pr_err("Could not remove request (%d)", count);
return -ENODEV;
+ }
}
return 0;
}
diff --git a/net/can/af_can.c b/net/can/af_can.c
index c4e5085..d3668c5 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -57,6 +57,7 @@
#include <linux/skbuff.h>
#include <linux/can.h>
#include <linux/can/core.h>
+#include <linux/can/skb.h>
#include <linux/ratelimit.h>
#include <net/net_namespace.h>
#include <net/sock.h>
@@ -261,6 +262,9 @@
goto inval_skb;
}
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
@@ -290,7 +294,7 @@
return -ENOMEM;
}
- newskb->sk = skb->sk;
+ can_skb_set_owner(newskb, skb->sk);
newskb->ip_summed = CHECKSUM_UNNECESSARY;
newskb->pkt_type = PACKET_BROADCAST;
}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 8f113e6..35cf02d 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -268,7 +268,7 @@
/* send with loopback */
skb->dev = dev;
- skb->sk = op->sk;
+ can_skb_set_owner(skb, op->sk);
can_send(skb, 1);
/* update statistics */
@@ -1223,7 +1223,7 @@
can_skb_prv(skb)->ifindex = dev->ifindex;
skb->dev = dev;
- skb->sk = sk;
+ can_skb_set_owner(skb, sk);
err = can_send(skb, 1); /* send with loopback */
dev_put(dev);
diff --git a/net/can/gw.c b/net/can/gw.c
index 3ee690e..de25455 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -784,7 +784,7 @@
struct cgw_job *gwj;
int err = 0;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (nlmsg_len(nlh) < sizeof(*r))
@@ -876,7 +876,7 @@
struct can_can_gw ccgw;
int err = 0;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (nlmsg_len(nlh) < sizeof(*r))
diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c
index 925ca58..8c93fa8 100644
--- a/net/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -39,6 +39,11 @@
return xi->starting;
}
+static int build_request(struct ceph_auth_client *ac, void *buf, void *end)
+{
+ return 0;
+}
+
/*
* the generic auth code decode the global_id, and we carry no actual
* authenticate state, so nothing happens here.
@@ -106,6 +111,7 @@
.destroy = destroy,
.is_authenticated = is_authenticated,
.should_authenticate = should_authenticate,
+ .build_request = build_request,
.handle_reply = handle_reply,
.create_authorizer = ceph_auth_none_create_authorizer,
.destroy_authorizer = ceph_auth_none_destroy_authorizer,
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index 96238ba..de6662b 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -13,8 +13,6 @@
#include "auth_x.h"
#include "auth_x_protocol.h"
-#define TEMP_TICKET_BUF_LEN 256
-
static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
static int ceph_x_is_authenticated(struct ceph_auth_client *ac)
@@ -64,7 +62,7 @@
}
static int ceph_x_decrypt(struct ceph_crypto_key *secret,
- void **p, void *end, void *obuf, size_t olen)
+ void **p, void *end, void **obuf, size_t olen)
{
struct ceph_x_encrypt_header head;
size_t head_len = sizeof(head);
@@ -75,8 +73,14 @@
return -EINVAL;
dout("ceph_x_decrypt len %d\n", len);
- ret = ceph_decrypt2(secret, &head, &head_len, obuf, &olen,
- *p, len);
+ if (*obuf == NULL) {
+ *obuf = kmalloc(len, GFP_NOFS);
+ if (!*obuf)
+ return -ENOMEM;
+ olen = len;
+ }
+
+ ret = ceph_decrypt2(secret, &head, &head_len, *obuf, &olen, *p, len);
if (ret)
return ret;
if (head.struct_v != 1 || le64_to_cpu(head.magic) != CEPHX_ENC_MAGIC)
@@ -129,139 +133,120 @@
kfree(th);
}
-static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
- struct ceph_crypto_key *secret,
- void *buf, void *end)
+static int process_one_ticket(struct ceph_auth_client *ac,
+ struct ceph_crypto_key *secret,
+ void **p, void *end)
{
struct ceph_x_info *xi = ac->private;
- int num;
- void *p = buf;
+ int type;
+ u8 tkt_struct_v, blob_struct_v;
+ struct ceph_x_ticket_handler *th;
+ void *dbuf = NULL;
+ void *dp, *dend;
+ int dlen;
+ char is_enc;
+ struct timespec validity;
+ struct ceph_crypto_key old_key;
+ void *ticket_buf = NULL;
+ void *tp, *tpend;
+ struct ceph_timespec new_validity;
+ struct ceph_crypto_key new_session_key;
+ struct ceph_buffer *new_ticket_blob;
+ unsigned long new_expires, new_renew_after;
+ u64 new_secret_id;
int ret;
- char *dbuf;
- char *ticket_buf;
- u8 reply_struct_v;
- dbuf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
- if (!dbuf)
- return -ENOMEM;
+ ceph_decode_need(p, end, sizeof(u32) + 1, bad);
- ret = -ENOMEM;
- ticket_buf = kmalloc(TEMP_TICKET_BUF_LEN, GFP_NOFS);
- if (!ticket_buf)
- goto out_dbuf;
+ type = ceph_decode_32(p);
+ dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
- ceph_decode_need(&p, end, 1 + sizeof(u32), bad);
- reply_struct_v = ceph_decode_8(&p);
- if (reply_struct_v != 1)
+ tkt_struct_v = ceph_decode_8(p);
+ if (tkt_struct_v != 1)
goto bad;
- num = ceph_decode_32(&p);
- dout("%d tickets\n", num);
- while (num--) {
- int type;
- u8 tkt_struct_v, blob_struct_v;
- struct ceph_x_ticket_handler *th;
- void *dp, *dend;
- int dlen;
- char is_enc;
- struct timespec validity;
- struct ceph_crypto_key old_key;
- void *tp, *tpend;
- struct ceph_timespec new_validity;
- struct ceph_crypto_key new_session_key;
- struct ceph_buffer *new_ticket_blob;
- unsigned long new_expires, new_renew_after;
- u64 new_secret_id;
- ceph_decode_need(&p, end, sizeof(u32) + 1, bad);
+ th = get_ticket_handler(ac, type);
+ if (IS_ERR(th)) {
+ ret = PTR_ERR(th);
+ goto out;
+ }
- type = ceph_decode_32(&p);
- dout(" ticket type %d %s\n", type, ceph_entity_type_name(type));
+ /* blob for me */
+ dlen = ceph_x_decrypt(secret, p, end, &dbuf, 0);
+ if (dlen <= 0) {
+ ret = dlen;
+ goto out;
+ }
+ dout(" decrypted %d bytes\n", dlen);
+ dp = dbuf;
+ dend = dp + dlen;
- tkt_struct_v = ceph_decode_8(&p);
- if (tkt_struct_v != 1)
- goto bad;
+ tkt_struct_v = ceph_decode_8(&dp);
+ if (tkt_struct_v != 1)
+ goto bad;
- th = get_ticket_handler(ac, type);
- if (IS_ERR(th)) {
- ret = PTR_ERR(th);
- goto out;
- }
+ memcpy(&old_key, &th->session_key, sizeof(old_key));
+ ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
+ if (ret)
+ goto out;
- /* blob for me */
- dlen = ceph_x_decrypt(secret, &p, end, dbuf,
- TEMP_TICKET_BUF_LEN);
- if (dlen <= 0) {
+ ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
+ ceph_decode_timespec(&validity, &new_validity);
+ new_expires = get_seconds() + validity.tv_sec;
+ new_renew_after = new_expires - (validity.tv_sec / 4);
+ dout(" expires=%lu renew_after=%lu\n", new_expires,
+ new_renew_after);
+
+ /* ticket blob for service */
+ ceph_decode_8_safe(p, end, is_enc, bad);
+ if (is_enc) {
+ /* encrypted */
+ dout(" encrypted ticket\n");
+ dlen = ceph_x_decrypt(&old_key, p, end, &ticket_buf, 0);
+ if (dlen < 0) {
ret = dlen;
goto out;
}
- dout(" decrypted %d bytes\n", dlen);
- dend = dbuf + dlen;
- dp = dbuf;
-
- tkt_struct_v = ceph_decode_8(&dp);
- if (tkt_struct_v != 1)
- goto bad;
-
- memcpy(&old_key, &th->session_key, sizeof(old_key));
- ret = ceph_crypto_key_decode(&new_session_key, &dp, dend);
- if (ret)
- goto out;
-
- ceph_decode_copy(&dp, &new_validity, sizeof(new_validity));
- ceph_decode_timespec(&validity, &new_validity);
- new_expires = get_seconds() + validity.tv_sec;
- new_renew_after = new_expires - (validity.tv_sec / 4);
- dout(" expires=%lu renew_after=%lu\n", new_expires,
- new_renew_after);
-
- /* ticket blob for service */
- ceph_decode_8_safe(&p, end, is_enc, bad);
tp = ticket_buf;
- if (is_enc) {
- /* encrypted */
- dout(" encrypted ticket\n");
- dlen = ceph_x_decrypt(&old_key, &p, end, ticket_buf,
- TEMP_TICKET_BUF_LEN);
- if (dlen < 0) {
- ret = dlen;
- goto out;
- }
- dlen = ceph_decode_32(&tp);
- } else {
- /* unencrypted */
- ceph_decode_32_safe(&p, end, dlen, bad);
- ceph_decode_need(&p, end, dlen, bad);
- ceph_decode_copy(&p, ticket_buf, dlen);
- }
- tpend = tp + dlen;
- dout(" ticket blob is %d bytes\n", dlen);
- ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
- blob_struct_v = ceph_decode_8(&tp);
- new_secret_id = ceph_decode_64(&tp);
- ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
- if (ret)
+ dlen = ceph_decode_32(&tp);
+ } else {
+ /* unencrypted */
+ ceph_decode_32_safe(p, end, dlen, bad);
+ ticket_buf = kmalloc(dlen, GFP_NOFS);
+ if (!ticket_buf) {
+ ret = -ENOMEM;
goto out;
-
- /* all is well, update our ticket */
- ceph_crypto_key_destroy(&th->session_key);
- if (th->ticket_blob)
- ceph_buffer_put(th->ticket_blob);
- th->session_key = new_session_key;
- th->ticket_blob = new_ticket_blob;
- th->validity = new_validity;
- th->secret_id = new_secret_id;
- th->expires = new_expires;
- th->renew_after = new_renew_after;
- dout(" got ticket service %d (%s) secret_id %lld len %d\n",
- type, ceph_entity_type_name(type), th->secret_id,
- (int)th->ticket_blob->vec.iov_len);
- xi->have_keys |= th->service;
+ }
+ tp = ticket_buf;
+ ceph_decode_need(p, end, dlen, bad);
+ ceph_decode_copy(p, ticket_buf, dlen);
}
+ tpend = tp + dlen;
+ dout(" ticket blob is %d bytes\n", dlen);
+ ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad);
+ blob_struct_v = ceph_decode_8(&tp);
+ new_secret_id = ceph_decode_64(&tp);
+ ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend);
+ if (ret)
+ goto out;
- ret = 0;
+ /* all is well, update our ticket */
+ ceph_crypto_key_destroy(&th->session_key);
+ if (th->ticket_blob)
+ ceph_buffer_put(th->ticket_blob);
+ th->session_key = new_session_key;
+ th->ticket_blob = new_ticket_blob;
+ th->validity = new_validity;
+ th->secret_id = new_secret_id;
+ th->expires = new_expires;
+ th->renew_after = new_renew_after;
+ dout(" got ticket service %d (%s) secret_id %lld len %d\n",
+ type, ceph_entity_type_name(type), th->secret_id,
+ (int)th->ticket_blob->vec.iov_len);
+ xi->have_keys |= th->service;
+
out:
kfree(ticket_buf);
-out_dbuf:
kfree(dbuf);
return ret;
@@ -270,6 +255,34 @@
goto out;
}
+static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
+ struct ceph_crypto_key *secret,
+ void *buf, void *end)
+{
+ void *p = buf;
+ u8 reply_struct_v;
+ u32 num;
+ int ret;
+
+ ceph_decode_8_safe(&p, end, reply_struct_v, bad);
+ if (reply_struct_v != 1)
+ return -EINVAL;
+
+ ceph_decode_32_safe(&p, end, num, bad);
+ dout("%d tickets\n", num);
+
+ while (num--) {
+ ret = process_one_ticket(ac, secret, &p, end);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+
+bad:
+ return -EINVAL;
+}
+
static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
struct ceph_x_ticket_handler *th,
struct ceph_x_authorizer *au)
@@ -583,13 +596,14 @@
struct ceph_x_ticket_handler *th;
int ret = 0;
struct ceph_x_authorize_reply reply;
+ void *preply = &reply;
void *p = au->reply_buf;
void *end = p + sizeof(au->reply_buf);
th = get_ticket_handler(ac, au->service);
if (IS_ERR(th))
return PTR_ERR(th);
- ret = ceph_x_decrypt(&th->session_key, &p, end, &reply, sizeof(reply));
+ ret = ceph_x_decrypt(&th->session_key, &p, end, &preply, sizeof(reply));
if (ret < 0)
return ret;
if (ret != sizeof(reply))
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 6e7a236..06f19b9 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -89,11 +89,82 @@
static const u8 *aes_iv = (u8 *)CEPH_AES_IV;
+/*
+ * Should be used for buffers allocated with ceph_kvmalloc().
+ * Currently these are encrypt out-buffer (ceph_buffer) and decrypt
+ * in-buffer (msg front).
+ *
+ * Dispose of @sgt with teardown_sgtable().
+ *
+ * @prealloc_sg is to avoid memory allocation inside sg_alloc_table()
+ * in cases where a single sg is sufficient. No attempt to reduce the
+ * number of sgs by squeezing physically contiguous pages together is
+ * made though, for simplicity.
+ */
+static int setup_sgtable(struct sg_table *sgt, struct scatterlist *prealloc_sg,
+ const void *buf, unsigned int buf_len)
+{
+ struct scatterlist *sg;
+ const bool is_vmalloc = is_vmalloc_addr(buf);
+ unsigned int off = offset_in_page(buf);
+ unsigned int chunk_cnt = 1;
+ unsigned int chunk_len = PAGE_ALIGN(off + buf_len);
+ int i;
+ int ret;
+
+ if (buf_len == 0) {
+ memset(sgt, 0, sizeof(*sgt));
+ return -EINVAL;
+ }
+
+ if (is_vmalloc) {
+ chunk_cnt = chunk_len >> PAGE_SHIFT;
+ chunk_len = PAGE_SIZE;
+ }
+
+ if (chunk_cnt > 1) {
+ ret = sg_alloc_table(sgt, chunk_cnt, GFP_NOFS);
+ if (ret)
+ return ret;
+ } else {
+ WARN_ON(chunk_cnt != 1);
+ sg_init_table(prealloc_sg, 1);
+ sgt->sgl = prealloc_sg;
+ sgt->nents = sgt->orig_nents = 1;
+ }
+
+ for_each_sg(sgt->sgl, sg, sgt->orig_nents, i) {
+ struct page *page;
+ unsigned int len = min(chunk_len - off, buf_len);
+
+ if (is_vmalloc)
+ page = vmalloc_to_page(buf);
+ else
+ page = virt_to_page(buf);
+
+ sg_set_page(sg, page, len, off);
+
+ off = 0;
+ buf += len;
+ buf_len -= len;
+ }
+ WARN_ON(buf_len != 0);
+
+ return 0;
+}
+
+static void teardown_sgtable(struct sg_table *sgt)
+{
+ if (sgt->orig_nents > 1)
+ sg_free_table(sgt);
+}
+
static int ceph_aes_encrypt(const void *key, int key_len,
void *dst, size_t *dst_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[2], sg_out[1];
+ struct scatterlist sg_in[2], prealloc_sg;
+ struct sg_table sg_out;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
int ret;
@@ -109,16 +180,18 @@
*dst_len = src_len + zero_padding;
- crypto_blkcipher_setkey((void *)tfm, key, key_len);
sg_init_table(sg_in, 2);
sg_set_buf(&sg_in[0], src, src_len);
sg_set_buf(&sg_in[1], pad, zero_padding);
- sg_init_table(sg_out, 1);
- sg_set_buf(sg_out, dst, *dst_len);
+ ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+ if (ret)
+ goto out_tfm;
+
+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
+
/*
print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
key, key_len, 1);
@@ -127,16 +200,22 @@
print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
pad, zero_padding, 1);
*/
- ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+ ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
src_len + zero_padding);
- crypto_free_blkcipher(tfm);
- if (ret < 0)
+ if (ret < 0) {
pr_err("ceph_aes_crypt failed %d\n", ret);
+ goto out_sg;
+ }
/*
print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_out);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}
static int ceph_aes_encrypt2(const void *key, int key_len, void *dst,
@@ -144,7 +223,8 @@
const void *src1, size_t src1_len,
const void *src2, size_t src2_len)
{
- struct scatterlist sg_in[3], sg_out[1];
+ struct scatterlist sg_in[3], prealloc_sg;
+ struct sg_table sg_out;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm, .flags = 0 };
int ret;
@@ -160,17 +240,19 @@
*dst_len = src1_len + src2_len + zero_padding;
- crypto_blkcipher_setkey((void *)tfm, key, key_len);
sg_init_table(sg_in, 3);
sg_set_buf(&sg_in[0], src1, src1_len);
sg_set_buf(&sg_in[1], src2, src2_len);
sg_set_buf(&sg_in[2], pad, zero_padding);
- sg_init_table(sg_out, 1);
- sg_set_buf(sg_out, dst, *dst_len);
+ ret = setup_sgtable(&sg_out, &prealloc_sg, dst, *dst_len);
+ if (ret)
+ goto out_tfm;
+
+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
+
/*
print_hex_dump(KERN_ERR, "enc key: ", DUMP_PREFIX_NONE, 16, 1,
key, key_len, 1);
@@ -181,23 +263,30 @@
print_hex_dump(KERN_ERR, "enc pad: ", DUMP_PREFIX_NONE, 16, 1,
pad, zero_padding, 1);
*/
- ret = crypto_blkcipher_encrypt(&desc, sg_out, sg_in,
+ ret = crypto_blkcipher_encrypt(&desc, sg_out.sgl, sg_in,
src1_len + src2_len + zero_padding);
- crypto_free_blkcipher(tfm);
- if (ret < 0)
+ if (ret < 0) {
pr_err("ceph_aes_crypt2 failed %d\n", ret);
+ goto out_sg;
+ }
/*
print_hex_dump(KERN_ERR, "enc out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_out);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}
static int ceph_aes_decrypt(const void *key, int key_len,
void *dst, size_t *dst_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[1], sg_out[2];
+ struct sg_table sg_in;
+ struct scatterlist sg_out[2], prealloc_sg;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm };
char pad[16];
@@ -209,16 +298,16 @@
if (IS_ERR(tfm))
return PTR_ERR(tfm);
- crypto_blkcipher_setkey((void *)tfm, key, key_len);
- sg_init_table(sg_in, 1);
sg_init_table(sg_out, 2);
- sg_set_buf(sg_in, src, src_len);
sg_set_buf(&sg_out[0], dst, *dst_len);
sg_set_buf(&sg_out[1], pad, sizeof(pad));
+ ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+ if (ret)
+ goto out_tfm;
+ crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
/*
@@ -227,12 +316,10 @@
print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
src, src_len, 1);
*/
-
- ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
- crypto_free_blkcipher(tfm);
+ ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
if (ret < 0) {
pr_err("ceph_aes_decrypt failed %d\n", ret);
- return ret;
+ goto out_sg;
}
if (src_len <= *dst_len)
@@ -250,7 +337,12 @@
print_hex_dump(KERN_ERR, "dec out: ", DUMP_PREFIX_NONE, 16, 1,
dst, *dst_len, 1);
*/
- return 0;
+
+out_sg:
+ teardown_sgtable(&sg_in);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}
static int ceph_aes_decrypt2(const void *key, int key_len,
@@ -258,7 +350,8 @@
void *dst2, size_t *dst2_len,
const void *src, size_t src_len)
{
- struct scatterlist sg_in[1], sg_out[3];
+ struct sg_table sg_in;
+ struct scatterlist sg_out[3], prealloc_sg;
struct crypto_blkcipher *tfm = ceph_crypto_alloc_cipher();
struct blkcipher_desc desc = { .tfm = tfm };
char pad[16];
@@ -270,17 +363,17 @@
if (IS_ERR(tfm))
return PTR_ERR(tfm);
- sg_init_table(sg_in, 1);
- sg_set_buf(sg_in, src, src_len);
sg_init_table(sg_out, 3);
sg_set_buf(&sg_out[0], dst1, *dst1_len);
sg_set_buf(&sg_out[1], dst2, *dst2_len);
sg_set_buf(&sg_out[2], pad, sizeof(pad));
+ ret = setup_sgtable(&sg_in, &prealloc_sg, src, src_len);
+ if (ret)
+ goto out_tfm;
crypto_blkcipher_setkey((void *)tfm, key, key_len);
iv = crypto_blkcipher_crt(tfm)->iv;
ivsize = crypto_blkcipher_ivsize(tfm);
-
memcpy(iv, aes_iv, ivsize);
/*
@@ -289,12 +382,10 @@
print_hex_dump(KERN_ERR, "dec in: ", DUMP_PREFIX_NONE, 16, 1,
src, src_len, 1);
*/
-
- ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in, src_len);
- crypto_free_blkcipher(tfm);
+ ret = crypto_blkcipher_decrypt(&desc, sg_out, sg_in.sgl, src_len);
if (ret < 0) {
pr_err("ceph_aes_decrypt failed %d\n", ret);
- return ret;
+ goto out_sg;
}
if (src_len <= *dst1_len)
@@ -324,7 +415,11 @@
dst2, *dst2_len, 1);
*/
- return 0;
+out_sg:
+ teardown_sgtable(&sg_in);
+out_tfm:
+ crypto_free_blkcipher(tfm);
+ return ret;
}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index eb0a46a..e3bea2e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -290,7 +290,8 @@
if (ceph_msgr_slab_init())
return -ENOMEM;
- ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_NON_REENTRANT, 0);
+ ceph_msgr_wq = alloc_workqueue("ceph-msgr",
+ WQ_NON_REENTRANT | WQ_MEM_RECLAIM, 0);
if (ceph_msgr_wq)
return 0;
@@ -556,7 +557,7 @@
return r;
}
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
int offset, size_t size, bool more)
{
int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -569,6 +570,24 @@
return ret;
}
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+ int offset, size_t size, bool more)
+{
+ int ret;
+ struct kvec iov;
+
+ /* sendpage cannot properly handle pages with page_count == 0,
+ * we need to fallback to sendmsg if that's the case */
+ if (page_count(page) >= 1)
+ return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+ iov.iov_base = kmap(page) + offset;
+ iov.iov_len = size;
+ ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+ kunmap(page);
+
+ return ret;
+}
/*
* Shutdown/close the socket for the given connection.
@@ -886,7 +905,7 @@
BUG_ON(page_count > (int)USHRT_MAX);
cursor->page_count = (unsigned short)page_count;
BUG_ON(length > SIZE_MAX - cursor->page_offset);
- cursor->last_piece = (size_t)cursor->page_offset + length <= PAGE_SIZE;
+ cursor->last_piece = cursor->page_offset + cursor->resid <= PAGE_SIZE;
}
static struct page *
@@ -3126,7 +3145,7 @@
INIT_LIST_HEAD(&m->data);
/* front */
- m->front_max = front_len;
+ m->front_alloc_len = front_len;
if (front_len) {
if (front_len > PAGE_CACHE_SIZE) {
m->front.iov_base = __vmalloc(front_len, flags,
@@ -3301,8 +3320,8 @@
void ceph_msg_dump(struct ceph_msg *msg)
{
- pr_debug("msg_dump %p (front_max %d length %zd)\n", msg,
- msg->front_max, msg->data_length);
+ pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg,
+ msg->front_alloc_len, msg->data_length);
print_hex_dump(KERN_DEBUG, "header: ",
DUMP_PREFIX_OFFSET, 16, 1,
&msg->hdr, sizeof(msg->hdr), true);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 1fe25cd..dbcbf5a 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -152,7 +152,7 @@
/* initiatiate authentication handshake */
ret = ceph_auth_build_hello(monc->auth,
monc->m_auth->front.iov_base,
- monc->m_auth->front_max);
+ monc->m_auth->front_alloc_len);
__send_prepared_auth_request(monc, ret);
} else {
dout("open_session mon%d already open\n", monc->cur_mon);
@@ -196,7 +196,7 @@
int num;
p = msg->front.iov_base;
- end = p + msg->front_max;
+ end = p + msg->front_alloc_len;
num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
ceph_encode_32(&p, num);
@@ -897,7 +897,7 @@
ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
msg->front.iov_len,
monc->m_auth->front.iov_base,
- monc->m_auth->front_max);
+ monc->m_auth->front_alloc_len);
if (ret < 0) {
monc->client->auth_err = ret;
wake_up_all(&monc->client->auth_wq);
@@ -939,7 +939,7 @@
return 0;
ret = ceph_build_auth(monc->auth, monc->m_auth->front.iov_base,
- monc->m_auth->front_max);
+ monc->m_auth->front_alloc_len);
if (ret <= 0)
return ret; /* either an error, or no need to authenticate */
__send_prepared_auth_request(monc, ret);
@@ -1041,7 +1041,15 @@
if (!m) {
pr_info("alloc_msg unknown type %d\n", type);
*skip = 1;
+ } else if (front_len > m->front_alloc_len) {
+ pr_warning("mon_alloc_msg front %d > prealloc %d (%u#%llu)\n",
+ front_len, m->front_alloc_len,
+ (unsigned int)con->peer_name.type,
+ le64_to_cpu(con->peer_name.num));
+ ceph_msg_put(m);
+ m = ceph_msg_new(type, front_len, GFP_NOFS, false);
}
+
return m;
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3a246a6..1b51d92 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -733,12 +733,14 @@
object_size = le32_to_cpu(layout->fl_object_size);
object_base = off - objoff;
- if (truncate_size <= object_base) {
- truncate_size = 0;
- } else {
- truncate_size -= object_base;
- if (truncate_size > object_size)
- truncate_size = object_size;
+ if (!(truncate_seq == 1 && truncate_size == -1ULL)) {
+ if (truncate_size <= object_base) {
+ truncate_size = 0;
+ } else {
+ truncate_size -= object_base;
+ if (truncate_size > object_size)
+ truncate_size = object_size;
+ }
}
osd_req_op_extent_init(req, 0, opcode, objoff, objlen,
@@ -965,12 +967,24 @@
*/
static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
{
- dout("__remove_osd %p\n", osd);
- BUG_ON(!list_empty(&osd->o_requests));
- rb_erase(&osd->o_node, &osdc->osds);
+ dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+ WARN_ON(!list_empty(&osd->o_requests));
+ WARN_ON(!list_empty(&osd->o_linger_requests));
+
list_del_init(&osd->o_osd_lru);
- ceph_con_close(&osd->o_con);
- put_osd(osd);
+ rb_erase(&osd->o_node, &osdc->osds);
+ RB_CLEAR_NODE(&osd->o_node);
+}
+
+static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+ dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+
+ if (!RB_EMPTY_NODE(&osd->o_node)) {
+ ceph_con_close(&osd->o_con);
+ __remove_osd(osdc, osd);
+ put_osd(osd);
+ }
}
static void remove_all_osds(struct ceph_osd_client *osdc)
@@ -980,7 +994,7 @@
while (!RB_EMPTY_ROOT(&osdc->osds)) {
struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
struct ceph_osd, o_node);
- __remove_osd(osdc, osd);
+ remove_osd(osdc, osd);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1010,7 +1024,7 @@
list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
if (time_before(jiffies, osd->lru_ttl))
break;
- __remove_osd(osdc, osd);
+ remove_osd(osdc, osd);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1025,8 +1039,7 @@
dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
if (list_empty(&osd->o_requests) &&
list_empty(&osd->o_linger_requests)) {
- __remove_osd(osdc, osd);
-
+ remove_osd(osdc, osd);
return -ENODEV;
}
@@ -1174,6 +1187,7 @@
struct ceph_osd_request *req)
{
dout("__register_linger_request %p\n", req);
+ ceph_osdc_get_request(req);
list_add_tail(&req->r_linger_item, &osdc->req_linger);
if (req->r_osd)
list_add_tail(&req->r_linger_osd,
@@ -1196,6 +1210,7 @@
if (list_empty(&req->r_osd_item))
req->r_osd = NULL;
}
+ ceph_osdc_put_request(req);
}
void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,
@@ -1203,9 +1218,8 @@
{
mutex_lock(&osdc->request_mutex);
if (req->r_linger) {
- __unregister_linger_request(osdc, req);
req->r_linger = 0;
- ceph_osdc_put_request(req);
+ __unregister_linger_request(osdc, req);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1217,16 +1231,27 @@
if (!req->r_linger) {
dout("set_request_linger %p\n", req);
req->r_linger = 1;
- /*
- * caller is now responsible for calling
- * unregister_linger_request
- */
- ceph_osdc_get_request(req);
}
}
EXPORT_SYMBOL(ceph_osdc_set_request_linger);
/*
+ * Returns whether a request should be blocked from being sent
+ * based on the current osdmap and osd_client settings.
+ *
+ * Caller should hold map_sem for read.
+ */
+static bool __req_should_be_paused(struct ceph_osd_client *osdc,
+ struct ceph_osd_request *req)
+{
+ bool pauserd = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD);
+ bool pausewr = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR) ||
+ ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+ return (req->r_flags & CEPH_OSD_FLAG_READ && pauserd) ||
+ (req->r_flags & CEPH_OSD_FLAG_WRITE && pausewr);
+}
+
+/*
* Pick an osd (the first 'up' osd in the pg), allocate the osd struct
* (as needed), and set the request r_osd appropriately. If there is
* no up osd, set r_osd to NULL. Move the request to the appropriate list
@@ -1243,6 +1268,7 @@
int acting[CEPH_PG_MAX_SIZE];
int o = -1, num = 0;
int err;
+ bool was_paused;
dout("map_request %p tid %lld\n", req, req->r_tid);
err = ceph_calc_ceph_pg(&pgid, req->r_oid, osdc->osdmap,
@@ -1259,12 +1285,18 @@
num = err;
}
+ was_paused = req->r_paused;
+ req->r_paused = __req_should_be_paused(osdc, req);
+ if (was_paused && !req->r_paused)
+ force_resend = 1;
+
if ((!force_resend &&
req->r_osd && req->r_osd->o_osd == o &&
req->r_sent >= req->r_osd->o_incarnation &&
req->r_num_pg_osds == num &&
memcmp(req->r_pg_osds, acting, sizeof(acting[0])*num) == 0) ||
- (req->r_osd == NULL && o == -1))
+ (req->r_osd == NULL && o == -1) ||
+ req->r_paused)
return 0; /* no change */
dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n",
@@ -1339,10 +1371,6 @@
ceph_msg_get(req->r_request); /* send consumes a ref */
- /* Mark the request unsafe if this is the first timet's being sent. */
-
- if (!req->r_sent && req->r_unsafe_callback)
- req->r_unsafe_callback(req, true);
req->r_sent = req->r_osd->o_incarnation;
ceph_con_send(&req->r_osd->o_con, req->r_request);
@@ -1433,8 +1461,6 @@
static void complete_request(struct ceph_osd_request *req)
{
- if (req->r_unsafe_callback)
- req->r_unsafe_callback(req, false);
complete_all(&req->r_safe_completion); /* fsync waiter */
}
@@ -1496,14 +1522,14 @@
dout("handle_reply %p tid %llu req %p result %d\n", msg, tid,
req, result);
- ceph_decode_need(&p, end, 4, bad);
+ ceph_decode_need(&p, end, 4, bad_put);
numops = ceph_decode_32(&p);
if (numops > CEPH_OSD_MAX_OP)
goto bad_put;
if (numops != req->r_num_ops)
goto bad_put;
payload_len = 0;
- ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad);
+ ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad_put);
for (i = 0; i < numops; i++) {
struct ceph_osd_op *op = p;
int len;
@@ -1521,11 +1547,13 @@
goto bad_put;
}
- ceph_decode_need(&p, end, 4 + numops * 4, bad);
+ ceph_decode_need(&p, end, 4 + numops * 4, bad_put);
retry_attempt = ceph_decode_32(&p);
for (i = 0; i < numops; i++)
req->r_reply_op_result[i] = ceph_decode_32(&p);
+ already_completed = req->r_got_reply;
+
if (!req->r_got_reply) {
req->r_result = result;
@@ -1556,19 +1584,23 @@
((flags & CEPH_OSD_FLAG_WRITE) == 0))
__unregister_request(osdc, req);
- already_completed = req->r_completed;
- req->r_completed = 1;
mutex_unlock(&osdc->request_mutex);
- if (already_completed)
- goto done;
- if (req->r_callback)
- req->r_callback(req, msg);
- else
- complete_all(&req->r_completion);
+ if (!already_completed) {
+ if (req->r_unsafe_callback &&
+ result >= 0 && !(flags & CEPH_OSD_FLAG_ONDISK))
+ req->r_unsafe_callback(req, true);
+ if (req->r_callback)
+ req->r_callback(req, msg);
+ else
+ complete_all(&req->r_completion);
+ }
- if (flags & CEPH_OSD_FLAG_ONDISK)
+ if (flags & CEPH_OSD_FLAG_ONDISK) {
+ if (req->r_unsafe_callback && already_completed)
+ req->r_unsafe_callback(req, false);
complete_request(req);
+ }
done:
dout("req=%p req->r_linger=%d\n", req, req->r_linger);
@@ -1589,6 +1621,7 @@
{
struct rb_node *p, *n;
+ dout("%s %p\n", __func__, osdc);
for (p = rb_first(&osdc->osds); p; p = n) {
struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);
@@ -1608,14 +1641,17 @@
*
* Caller should hold map_sem for read.
*/
-static void kick_requests(struct ceph_osd_client *osdc, int force_resend)
+static void kick_requests(struct ceph_osd_client *osdc, bool force_resend,
+ bool force_resend_writes)
{
struct ceph_osd_request *req, *nreq;
struct rb_node *p;
int needmap = 0;
int err;
+ bool force_resend_req;
- dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
+ dout("kick_requests %s %s\n", force_resend ? " (force resend)" : "",
+ force_resend_writes ? " (force resend writes)" : "");
mutex_lock(&osdc->request_mutex);
for (p = rb_first(&osdc->requests); p; ) {
req = rb_entry(p, struct ceph_osd_request, r_node);
@@ -1633,12 +1669,17 @@
dout("%p tid %llu restart on osd%d\n",
req, req->r_tid,
req->r_osd ? req->r_osd->o_osd : -1);
+ ceph_osdc_get_request(req);
__unregister_request(osdc, req);
__register_linger_request(osdc, req);
+ ceph_osdc_put_request(req);
continue;
}
- err = __map_request(osdc, req, force_resend);
+ force_resend_req = force_resend ||
+ (force_resend_writes &&
+ req->r_flags & CEPH_OSD_FLAG_WRITE);
+ err = __map_request(osdc, req, force_resend_req);
if (err < 0)
continue; /* error */
if (req->r_osd == NULL) {
@@ -1658,7 +1699,8 @@
r_linger_item) {
dout("linger req=%p req->r_osd=%p\n", req, req->r_osd);
- err = __map_request(osdc, req, force_resend);
+ err = __map_request(osdc, req,
+ force_resend || force_resend_writes);
dout("__map_request returned %d\n", err);
if (err == 0)
continue; /* no change and no osd was specified */
@@ -1700,6 +1742,7 @@
struct ceph_osdmap *newmap = NULL, *oldmap;
int err;
struct ceph_fsid fsid;
+ bool was_full;
dout("handle_map have %u\n", osdc->osdmap ? osdc->osdmap->epoch : 0);
p = msg->front.iov_base;
@@ -1713,6 +1756,8 @@
down_write(&osdc->map_sem);
+ was_full = ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL);
+
/* incremental maps */
ceph_decode_32_safe(&p, end, nr_maps, bad);
dout(" %d inc maps\n", nr_maps);
@@ -1737,7 +1782,10 @@
ceph_osdmap_destroy(osdc->osdmap);
osdc->osdmap = newmap;
}
- kick_requests(osdc, 0);
+ was_full = was_full ||
+ ceph_osdmap_flag(osdc->osdmap,
+ CEPH_OSDMAP_FULL);
+ kick_requests(osdc, 0, was_full);
} else {
dout("ignoring incremental map %u len %d\n",
epoch, maplen);
@@ -1780,12 +1828,17 @@
skipped_map = 1;
ceph_osdmap_destroy(oldmap);
}
- kick_requests(osdc, skipped_map);
+ was_full = was_full ||
+ ceph_osdmap_flag(osdc->osdmap,
+ CEPH_OSDMAP_FULL);
+ kick_requests(osdc, skipped_map, was_full);
}
p += maplen;
nr_maps--;
}
+ if (!osdc->osdmap)
+ goto bad;
done:
downgrade_write(&osdc->map_sem);
ceph_monc_got_osdmap(&osdc->client->monc, osdc->osdmap->epoch);
@@ -1795,7 +1848,9 @@
* we find out when we are no longer full and stop returning
* ENOSPC.
*/
- if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL))
+ if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL) ||
+ ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSERD) ||
+ ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_PAUSEWR))
ceph_monc_request_next_osdmap(&osdc->client->monc);
mutex_lock(&osdc->request_mutex);
@@ -2123,13 +2178,14 @@
__register_request(osdc, req);
req->r_sent = 0;
req->r_got_reply = 0;
- req->r_completed = 0;
rc = __map_request(osdc, req, 0);
if (rc < 0) {
if (nofail) {
dout("osdc_start_request failed map, "
" will retry %lld\n", req->r_tid);
rc = 0;
+ } else {
+ __unregister_request(osdc, req);
}
goto out_unlock;
}
@@ -2206,6 +2262,17 @@
EXPORT_SYMBOL(ceph_osdc_sync);
/*
+ * Call all pending notify callbacks - for use after a watch is
+ * unregistered, to make sure no more callbacks for it will be invoked
+ */
+extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
+{
+ flush_workqueue(osdc->notify_wq);
+}
+EXPORT_SYMBOL(ceph_osdc_flush_notifies);
+
+
+/*
* init, shutdown
*/
int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
@@ -2254,12 +2321,10 @@
if (err < 0)
goto out_msgpool;
+ err = -ENOMEM;
osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify");
- if (IS_ERR(osdc->notify_wq)) {
- err = PTR_ERR(osdc->notify_wq);
- osdc->notify_wq = NULL;
+ if (!osdc->notify_wq)
goto out_msgpool;
- }
return 0;
out_msgpool:
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 603ddd9..dbd9a47 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1129,7 +1129,7 @@
/* pg_temp? */
pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num,
- pool->pgp_num_mask);
+ pool->pg_num_mask);
pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
if (pg) {
*num = pg->len;
diff --git a/net/compat.c b/net/compat.c
index f0a1ba6..d125290 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -71,6 +71,15 @@
__get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
__get_user(kmsg->msg_flags, &umsg->msg_flags))
return -EFAULT;
+
+ if (!tmp1)
+ kmsg->msg_namelen = 0;
+
+ if (kmsg->msg_namelen < 0)
+ return -EINVAL;
+
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ kmsg->msg_namelen = sizeof(struct sockaddr_storage);
kmsg->msg_name = compat_ptr(tmp1);
kmsg->msg_iov = compat_ptr(tmp2);
kmsg->msg_control = compat_ptr(tmp3);
@@ -83,7 +92,7 @@
{
int tot_len;
- if (kern_msg->msg_namelen) {
+ if (kern_msg->msg_name && kern_msg->msg_namelen) {
if (mode == VERIFY_READ) {
int err = move_addr_to_kernel(kern_msg->msg_name,
kern_msg->msg_namelen,
@@ -92,8 +101,10 @@
return err;
}
kern_msg->msg_name = kern_address;
- } else
+ } else {
kern_msg->msg_name = NULL;
+ kern_msg->msg_namelen = 0;
+ }
tot_len = iov_from_user_compat_to_kern(kern_iov,
(struct compat_iovec __user *)kern_msg->msg_iov,
@@ -734,24 +745,18 @@
asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
return __sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
}
asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg,
unsigned int vlen, unsigned int flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
return __sys_sendmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
flags | MSG_CMSG_COMPAT);
}
asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags)
{
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
return __sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT);
}
@@ -774,24 +779,16 @@
int datagrams;
struct timespec ktspec;
- if (flags & MSG_CMSG_COMPAT)
- return -EINVAL;
-
- if (COMPAT_USE_64BIT_TIME)
- return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
- flags | MSG_CMSG_COMPAT,
- (struct timespec *) timeout);
-
if (timeout == NULL)
return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
flags | MSG_CMSG_COMPAT, NULL);
- if (get_compat_timespec(&ktspec, timeout))
+ if (compat_get_timespec(&ktspec, timeout))
return -EFAULT;
datagrams = __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
flags | MSG_CMSG_COMPAT, &ktspec);
- if (datagrams > 0 && put_compat_timespec(&ktspec, timeout))
+ if (datagrams > 0 && compat_put_timespec(&ktspec, timeout))
datagrams = -EFAULT;
return datagrams;
diff --git a/net/core/dev.c b/net/core/dev.c
index faebb39..aeca8dd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -927,7 +927,7 @@
return false;
while (*name) {
- if (*name == '/' || isspace(*name))
+ if (*name == '/' || *name == ':' || isspace(*name))
return false;
name++;
}
@@ -2374,7 +2374,7 @@
* 2. No high memory really exists on this machine.
*/
-static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
@@ -2454,46 +2454,51 @@
}
static netdev_features_t harmonize_features(struct sk_buff *skb,
- __be16 protocol, netdev_features_t features)
+ __be16 protocol,
+ const struct net_device *dev,
+ netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
- } else if (illegal_highdma(skb->dev, skb)) {
+ } else if (illegal_highdma(dev, skb)) {
features &= ~NETIF_F_SG;
}
return features;
}
-netdev_features_t netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
+ const struct net_device *dev)
{
__be16 protocol = skb->protocol;
- netdev_features_t features = skb->dev->features;
+ netdev_features_t features = dev->features;
- if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
- return harmonize_features(skb, protocol, features);
+ return harmonize_features(skb, protocol, dev, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX);
if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) {
- return harmonize_features(skb, protocol, features);
+ return harmonize_features(skb, protocol, dev, features);
} else {
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
- return harmonize_features(skb, protocol, features);
+ return harmonize_features(skb, protocol, dev, features);
}
+
+ return harmonize_features(skb, protocol, dev, features);
}
-EXPORT_SYMBOL(netif_skb_features);
+EXPORT_SYMBOL(netif_skb_dev_features);
/*
* Returns true if either:
@@ -3513,8 +3518,15 @@
}
}
- if (vlan_tx_nonzero_tag_present(skb))
- skb->pkt_type = PACKET_OTHERHOST;
+ if (unlikely(vlan_tx_tag_present(skb))) {
+ if (vlan_tx_tag_get_id(skb))
+ skb->pkt_type = PACKET_OTHERHOST;
+ /* Note: we might in the future use prio bits
+ * and set skb->priority like in vlan_do_receive()
+ * For the time being, just ignore Priority Code Point
+ */
+ skb->vlan_tci = 0;
+ }
/* deliver only exact match when indicated */
null_or_dev = deliver_exact ? skb->dev : NULL;
@@ -3886,6 +3898,7 @@
skb->vlan_tci = 0;
skb->dev = napi->dev;
skb->skb_iif = 0;
+ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
napi->skb = skb;
}
@@ -4471,7 +4484,7 @@
{
const struct net_device_ops *ops = dev->netdev_ops;
- if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
@@ -4622,6 +4635,7 @@
if (ops->ndo_set_rx_mode)
ops->ndo_set_rx_mode(dev);
}
+EXPORT_SYMBOL(__dev_set_rx_mode);
void dev_set_rx_mode(struct net_device *dev)
{
@@ -5813,6 +5827,9 @@
/**
* unregister_netdevice_many - unregister many devices
* @head: list of devices
+ *
+ * Note: As most callers use a stack allocated list_head,
+ * we force a list_del() to make sure stack wont be corrupted later.
*/
void unregister_netdevice_many(struct list_head *head)
{
@@ -5822,6 +5839,7 @@
rollback_registered_many(head);
list_for_each_entry(dev, head, unreg_list)
net_set_todo(dev);
+ list_del(head);
}
}
EXPORT_SYMBOL(unregister_netdevice_many);
@@ -5997,10 +6015,20 @@
oldsd->output_queue = NULL;
oldsd->output_queue_tailp = &oldsd->output_queue;
}
- /* Append NAPI poll list from offline CPU. */
- if (!list_empty(&oldsd->poll_list)) {
- list_splice_init(&oldsd->poll_list, &sd->poll_list);
- raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ /* Append NAPI poll list from offline CPU, with one exception :
+ * process_backlog() must be called by cpu owning percpu backlog.
+ * We properly handle process_queue & input_pkt_queue later.
+ */
+ while (!list_empty(&oldsd->poll_list)) {
+ struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+ struct napi_struct,
+ poll_list);
+
+ list_del_init(&napi->poll_list);
+ if (napi->poll == process_backlog)
+ napi->state = 0;
+ else
+ ____napi_schedule(sd, napi);
}
raise_softirq_irqoff(NET_TX_SOFTIRQ);
@@ -6011,7 +6039,7 @@
netif_rx(skb);
input_queue_head_incr(oldsd);
}
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
input_queue_head_incr(oldsd);
}
@@ -6238,7 +6266,6 @@
}
}
unregister_netdevice_many(&dev_kill_list);
- list_del(&dev_kill_list);
rtnl_unlock();
}
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index d23b668..a974dfe 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -64,7 +64,6 @@
.hdrsize = 0,
.name = "NET_DM",
.version = 2,
- .maxattr = NET_DM_CMD_MAX,
};
static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
diff --git a/net/core/dst.c b/net/core/dst.c
index df9cc81..c0e0218 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -267,6 +267,15 @@
}
EXPORT_SYMBOL(dst_destroy);
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+ struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+ dst = dst_destroy(dst);
+ if (dst)
+ __dst_free(dst);
+}
+
void dst_release(struct dst_entry *dst)
{
if (dst) {
@@ -274,11 +283,8 @@
newrefcnt = atomic_dec_return(&dst->__refcnt);
WARN_ON(newrefcnt < 0);
- if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
- dst = dst_destroy(dst);
- if (dst)
- __dst_free(dst);
- }
+ if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+ call_rcu(&dst->rcu_head, dst_destroy_rcu);
}
}
EXPORT_SYMBOL(dst_release);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d5a9f8e..55e08e2 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -445,7 +445,8 @@
if (frh->action && (frh->action != rule->action))
continue;
- if (frh->table && (frh_get_table(frh, tb) != rule->table))
+ if (frh_get_table(frh, tb) &&
+ (frh_get_table(frh, tb) != rule->table))
continue;
if (tb[FRA_PRIORITY] &&
@@ -719,6 +720,13 @@
attach_rules(&ops->rules_list, dev);
break;
+ case NETDEV_CHANGENAME:
+ list_for_each_entry(ops, &net->rules_ops, list) {
+ detach_rules(&ops->rules_list, dev);
+ attach_rules(&ops->rules_list, dev);
+ }
+ break;
+
case NETDEV_UNREGISTER:
list_for_each_entry(ops, &net->rules_ops, list)
detach_rules(&ops->rules_list, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index 6438f29..c6c18d8 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -36,7 +36,6 @@
#include <asm/uaccess.h>
#include <asm/unaligned.h>
#include <linux/filter.h>
-#include <linux/reciprocal_div.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
@@ -166,7 +165,7 @@
A /= X;
continue;
case BPF_S_ALU_DIV_K:
- A = reciprocal_divide(A, K);
+ A /= K;
continue;
case BPF_S_ALU_MOD_X:
if (X == 0)
@@ -356,6 +355,8 @@
if (skb_is_nonlinear(skb))
return 0;
+ if (skb->len < sizeof(struct nlattr))
+ return 0;
if (A > skb->len - sizeof(struct nlattr))
return 0;
@@ -372,11 +373,13 @@
if (skb_is_nonlinear(skb))
return 0;
+ if (skb->len < sizeof(struct nlattr))
+ return 0;
if (A > skb->len - sizeof(struct nlattr))
return 0;
nla = (struct nlattr *)&skb->data[A];
- if (nla->nla_len > A - skb->len)
+ if (nla->nla_len > skb->len - A)
return 0;
nla = nla_find_nested(nla, X);
@@ -553,11 +556,6 @@
/* Some instructions need special checks */
switch (code) {
case BPF_S_ALU_DIV_K:
- /* check for division by zero */
- if (ftest->k == 0)
- return -EINVAL;
- ftest->k = reciprocal_value(ftest->k);
- break;
case BPF_S_ALU_MOD_K:
/* check for division by zero */
if (ftest->k == 0)
@@ -853,27 +851,7 @@
to->code = decodes[code];
to->jt = filt->jt;
to->jf = filt->jf;
-
- if (code == BPF_S_ALU_DIV_K) {
- /*
- * When loaded this rule user gave us X, which was
- * translated into R = r(X). Now we calculate the
- * RR = r(R) and report it back. If next time this
- * value is loaded and RRR = r(RR) is calculated
- * then the R == RRR will be true.
- *
- * One exception. X == 1 translates into R == 0 and
- * we can't calculate RR out of it with r().
- */
-
- if (filt->k == 0)
- to->k = 1;
- else
- to->k = reciprocal_value(filt->k);
-
- BUG_ON(reciprocal_value(to->k) != filt->k);
- } else
- to->k = filt->k;
+ to->k = filt->k;
}
int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 00ee068..f97101b 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -40,7 +40,7 @@
struct iphdr _iph;
ip:
iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
+ if (!iph || iph->ihl < 5)
return false;
if (ip_is_fragment(iph))
@@ -149,8 +149,8 @@
if (poff >= 0) {
__be32 *ports, _ports;
- nhoff += poff;
- ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
+ ports = skb_header_pointer(skb, nhoff + poff,
+ sizeof(_ports), &_ports);
if (ports)
flow->ports = *ports;
}
@@ -345,14 +345,9 @@
if (new_index < 0)
new_index = skb_tx_hash(dev, skb);
- if (queue_index != new_index && sk) {
- struct dst_entry *dst =
- rcu_dereference_check(sk->sk_dst_cache, 1);
-
- if (dst && skb_dst(skb) == dst)
- sk_tx_queue_set(sk, queue_index);
-
- }
+ if (queue_index != new_index && sk &&
+ rcu_access_pointer(sk->sk_dst_cache))
+ sk_tx_queue_set(sk, new_index);
queue_index = new_index;
}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index ddedf21..b96437b 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -32,6 +32,9 @@
return 0;
nla_put_failure:
+ kfree(d->xstats);
+ d->xstats = NULL;
+ d->xstats_len = 0;
spin_unlock_bh(d->lock);
return -1;
}
@@ -205,7 +208,9 @@
gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
{
if (d->compat_xstats) {
- d->xstats = st;
+ d->xstats = kmemdup(st, len, GFP_ATOMIC);
+ if (!d->xstats)
+ goto err_out;
d->xstats_len = len;
}
@@ -213,6 +218,11 @@
return gnet_stats_copy(d, TCA_STATS_APP, st, len);
return 0;
+
+err_out:
+ d->xstats_len = 0;
+ spin_unlock_bh(d->lock);
+ return -1;
}
EXPORT_SYMBOL(gnet_stats_copy_app);
@@ -245,6 +255,9 @@
return -1;
}
+ kfree(d->xstats);
+ d->xstats = NULL;
+ d->xstats_len = 0;
spin_unlock_bh(d->lock);
return 0;
}
diff --git a/net/core/iovec.c b/net/core/iovec.c
index de178e4..1117a26 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@
{
int size, ct, err;
- if (m->msg_namelen) {
+ if (m->msg_name && m->msg_namelen) {
if (mode == VERIFY_READ) {
void __user *namep;
namep = (void __user __force *) m->msg_name;
@@ -51,6 +51,7 @@
m->msg_name = address;
} else {
m->msg_name = NULL;
+ m->msg_namelen = 0;
}
size = m->msg_iovlen * sizeof(struct iovec);
@@ -106,6 +107,10 @@
int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
int offset, int len)
{
+ /* No data? Done! */
+ if (len == 0)
+ return 0;
+
/* Skip over the finished iovecs */
while (offset >= iov->iov_len) {
offset -= iov->iov_len;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 5c56b21..b49e8ba 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -231,7 +231,7 @@
we must kill timers etc. and move
it to safe state.
*/
- skb_queue_purge(&n->arp_queue);
+ __skb_queue_purge(&n->arp_queue);
n->arp_queue_len_bytes = 0;
n->output = neigh_blackhole;
if (n->nud_state & NUD_VALID)
@@ -286,7 +286,7 @@
if (!n)
goto out_entries;
- skb_queue_head_init(&n->arp_queue);
+ __skb_queue_head_init(&n->arp_queue);
rwlock_init(&n->lock);
seqlock_init(&n->ha_lock);
n->updated = n->used = now;
@@ -708,7 +708,9 @@
if (neigh_del_timer(neigh))
pr_warn("Impossible event\n");
- skb_queue_purge(&neigh->arp_queue);
+ write_lock_bh(&neigh->lock);
+ __skb_queue_purge(&neigh->arp_queue);
+ write_unlock_bh(&neigh->lock);
neigh->arp_queue_len_bytes = 0;
if (dev->netdev_ops->ndo_neigh_destroy)
@@ -762,9 +764,6 @@
nht = rcu_dereference_protected(tbl->nht,
lockdep_is_held(&tbl->lock));
- if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
- goto out;
-
/*
* periodically recompute ReachableTime from random function
*/
@@ -777,6 +776,9 @@
neigh_rand_reach_time(p->base_reachable_time);
}
+ if (atomic_read(&tbl->entries) < tbl->gc_thresh1)
+ goto out;
+
for (i = 0 ; i < (1 << nht->hash_shift); i++) {
np = &nht->hash_buckets[i];
@@ -858,7 +860,7 @@
neigh->ops->error_report(neigh, skb);
write_lock(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
@@ -1210,7 +1212,7 @@
write_lock_bh(&neigh->lock);
}
- skb_queue_purge(&neigh->arp_queue);
+ __skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
}
out:
@@ -1272,7 +1274,7 @@
if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
skb->len) < 0 &&
- dev->header_ops->rebuild(skb))
+ dev_rebuild_header(skb))
return 0;
return dev_queue_xmit(skb);
@@ -1443,16 +1445,18 @@
atomic_set(&p->refcnt, 1);
p->reachable_time =
neigh_rand_reach_time(p->base_reachable_time);
-
- if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
- kfree(p);
- return NULL;
- }
-
dev_hold(dev);
p->dev = dev;
write_pnet(&p->net, hold_net(net));
p->sysctl_table = NULL;
+
+ if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) {
+ release_net(net);
+ dev_put(dev);
+ kfree(p);
+ return NULL;
+ }
+
write_lock_bh(&tbl->lock);
p->next = tbl->parms.next;
tbl->parms.next = p;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index cec074b..e861438 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -386,8 +386,14 @@
!vlan_hw_offload_capable(netif_skb_features(skb),
skb->vlan_proto)) {
skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
- if (unlikely(!skb))
- break;
+ if (unlikely(!skb)) {
+ /* This is actually a packet drop, but we
+ * don't want the code at the end of this
+ * function to try and re-queue a NULL skb.
+ */
+ status = NETDEV_TX_OK;
+ goto unlock_txq;
+ }
skb->vlan_tci = 0;
}
@@ -395,6 +401,7 @@
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
}
+ unlock_txq:
__netif_tx_unlock(txq);
if (status == NETDEV_TX_OK)
@@ -550,7 +557,7 @@
return;
proto = ntohs(eth_hdr(skb)->h_proto);
- if (proto == ETH_P_IP) {
+ if (proto == ETH_P_ARP) {
struct arphdr *arp;
unsigned char *arp_ptr;
/* No arp on this interface */
@@ -738,7 +745,7 @@
struct nd_msg *msg;
struct ipv6hdr *hdr;
- if (skb->protocol != htons(ETH_P_ARP))
+ if (skb->protocol != htons(ETH_P_IPV6))
return false;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
return false;
@@ -941,6 +948,7 @@
{
char *cur=opt, *delim;
int ipv6;
+ bool ipversion_set = false;
if (*cur != '@') {
if ((delim = strchr(cur, '@')) == NULL)
@@ -953,6 +961,7 @@
cur++;
if (*cur != '/') {
+ ipversion_set = true;
if ((delim = strchr(cur, '/')) == NULL)
goto parse_failed;
*delim = 0;
@@ -995,7 +1004,7 @@
ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
if (ipv6 < 0)
goto parse_failed;
- else if (np->ipv6 != (bool)ipv6)
+ else if (ipversion_set && np->ipv6 != (bool)ipv6)
goto parse_failed;
else
np->ipv6 = (bool)ipv6;
@@ -1289,15 +1298,14 @@
void netpoll_cleanup(struct netpoll *np)
{
- if (!np->dev)
- return;
-
rtnl_lock();
+ if (!np->dev)
+ goto out;
__netpoll_cleanup(np);
- rtnl_unlock();
-
dev_put(np->dev);
np->dev = NULL;
+out:
+ rtnl_unlock();
}
EXPORT_SYMBOL(netpoll_cleanup);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 11f2704..ebbea53 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2515,6 +2515,8 @@
if (x) {
int ret;
__u8 *eth;
+ struct iphdr *iph;
+
nhead = x->props.header_len - skb_headroom(skb);
if (nhead > 0) {
ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
@@ -2536,6 +2538,11 @@
eth = (__u8 *) skb_push(skb, ETH_HLEN);
memcpy(eth, pkt_dev->hh, 12);
*(u16 *) ð[12] = protocol;
+
+ /* Update IPv4 header len as well as checksum value */
+ iph = ip_hdr(skb);
+ iph->tot_len = htons(skb->len - ETH_HLEN);
+ ip_send_check(iph);
}
}
return 1;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a08bd2b..a67310e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -714,7 +714,8 @@
return 0;
}
-static size_t rtnl_port_size(const struct net_device *dev)
+static size_t rtnl_port_size(const struct net_device *dev,
+ u32 ext_filter_mask)
{
size_t port_size = nla_total_size(4) /* PORT_VF */
+ nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */
@@ -730,7 +731,8 @@
size_t port_self_size = nla_total_size(sizeof(struct nlattr))
+ port_size;
- if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+ if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+ !(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
if (dev_num_vf(dev->dev.parent))
return port_self_size + vf_ports_size +
@@ -765,7 +767,7 @@
+ nla_total_size(ext_filter_mask
& RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
- + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
+ rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */
}
@@ -826,11 +828,13 @@
return 0;
}
-static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
+static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev,
+ u32 ext_filter_mask)
{
int err;
- if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent)
+ if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent ||
+ !(ext_filter_mask & RTEXT_FILTER_VF))
return 0;
err = rtnl_port_self_fill(skb, dev);
@@ -985,7 +989,7 @@
nla_nest_end(skb, vfinfo);
}
- if (rtnl_port_fill(skb, dev))
+ if (rtnl_port_fill(skb, dev, ext_filter_mask))
goto nla_put_failure;
if (dev->rtnl_link_ops) {
@@ -1039,6 +1043,8 @@
struct hlist_head *head;
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
+ int err;
+ int hdrlen;
s_h = cb->args[0];
s_idx = cb->args[1];
@@ -1046,8 +1052,17 @@
rcu_read_lock();
cb->seq = net->dev_base_seq;
- if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
- ifla_policy) >= 0) {
+ /* A hack to preserve kernel<->userspace interface.
+ * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+ * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+ * what iproute2 < v3.9.0 used.
+ * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+ * attribute, its netlink message is shorter than struct ifinfomsg.
+ */
+ hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+ sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+ if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1059,11 +1074,17 @@
hlist_for_each_entry_rcu(dev, head, index_hlist) {
if (idx < s_idx)
goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, 0,
- NLM_F_MULTI,
- ext_filter_mask) <= 0)
+ err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI,
+ ext_filter_mask);
+ /* If we ran out of room on the first message,
+ * we're in trouble
+ */
+ WARN_ON((err == -EMSGSIZE) && (skb->len == 0));
+
+ if (err <= 0)
goto out;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -1117,14 +1138,10 @@
};
static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
- [IFLA_VF_MAC] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_mac) },
- [IFLA_VF_VLAN] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_vlan) },
- [IFLA_VF_TX_RATE] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_tx_rate) },
- [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY,
- .len = sizeof(struct ifla_vf_spoofchk) },
+ [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) },
+ [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) },
+ [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) },
+ [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) },
};
static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1283,7 +1300,8 @@
return 0;
}
-static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
+static int do_setlink(const struct sk_buff *skb,
+ struct net_device *dev, struct ifinfomsg *ifm,
struct nlattr **tb, char *ifname, int modified)
{
const struct net_device_ops *ops = dev->netdev_ops;
@@ -1295,7 +1313,8 @@
err = PTR_ERR(net);
goto errout;
}
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) {
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ put_net(net);
err = -EPERM;
goto errout;
}
@@ -1549,7 +1568,7 @@
if (err < 0)
goto errout;
- err = do_setlink(dev, ifm, tb, ifname, 0);
+ err = do_setlink(skb, dev, ifm, tb, ifname, 0);
errout:
return err;
}
@@ -1589,7 +1608,6 @@
ops->dellink(dev, &list_kill);
unregister_netdevice_many(&list_kill);
- list_del(&list_kill);
return 0;
}
@@ -1667,7 +1685,8 @@
}
EXPORT_SYMBOL(rtnl_create_link);
-static int rtnl_group_changelink(struct net *net, int group,
+static int rtnl_group_changelink(const struct sk_buff *skb,
+ struct net *net, int group,
struct ifinfomsg *ifm,
struct nlattr **tb)
{
@@ -1676,7 +1695,7 @@
for_each_netdev(net, dev) {
if (dev->group == group) {
- err = do_setlink(dev, ifm, tb, NULL, 0);
+ err = do_setlink(skb, dev, ifm, tb, NULL, 0);
if (err < 0)
return err;
}
@@ -1778,12 +1797,12 @@
modified = 1;
}
- return do_setlink(dev, ifm, tb, ifname, modified);
+ return do_setlink(skb, dev, ifm, tb, ifname, modified);
}
if (!(nlh->nlmsg_flags & NLM_F_CREATE)) {
if (ifm->ifi_index == 0 && tb[IFLA_GROUP])
- return rtnl_group_changelink(net,
+ return rtnl_group_changelink(skb, net,
nla_get_u32(tb[IFLA_GROUP]),
ifm, tb);
return -ENODEV;
@@ -1832,8 +1851,16 @@
goto out;
err = rtnl_configure_link(dev, ifm);
- if (err < 0)
- unregister_netdevice(dev);
+ if (err < 0) {
+ if (ops->newlink) {
+ LIST_HEAD(list_kill);
+
+ ops->dellink(dev, &list_kill);
+ unregister_netdevice_many(&list_kill);
+ } else {
+ unregister_netdevice(dev);
+ }
+ }
out:
put_net(dest_net);
return err;
@@ -1895,9 +1922,13 @@
struct nlattr *tb[IFLA_MAX+1];
u32 ext_filter_mask = 0;
u16 min_ifinfo_dump_size = 0;
+ int hdrlen;
- if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
- ifla_policy) >= 0) {
+ /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+ hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+ sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+ if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
}
@@ -1973,12 +2004,13 @@
static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
struct net_device *dev,
u8 *addr, u32 pid, u32 seq,
- int type, unsigned int flags)
+ int type, unsigned int flags,
+ int nlflags)
{
struct nlmsghdr *nlh;
struct ndmsg *ndm;
- nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags);
if (!nlh)
return -EMSGSIZE;
@@ -2016,7 +2048,7 @@
if (!skb)
goto errout;
- err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+ err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0);
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -2142,7 +2174,7 @@
/* If aging addresses are supported device will need to
* implement its own handler for this.
*/
- if (ndm->ndm_state & NUD_PERMANENT) {
+ if (!(ndm->ndm_state & NUD_PERMANENT)) {
pr_info("%s: FDB only supports static addresses\n", dev->name);
return -EINVAL;
}
@@ -2167,7 +2199,7 @@
int err = -EINVAL;
__u8 *addr;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
@@ -2249,7 +2281,8 @@
err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
portid, seq,
- RTM_NEWNEIGH, NTF_SELF);
+ RTM_NEWNEIGH, NTF_SELF,
+ NLM_F_MULTI);
if (err < 0)
return err;
skip:
@@ -2374,7 +2407,7 @@
struct nlattr *extfilt;
u32 filter_mask = 0;
- extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg),
+ extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
IFLA_EXT_MASK);
if (extfilt)
filter_mask = nla_get_u32(extfilt);
@@ -2448,12 +2481,16 @@
goto errout;
}
+ if (!skb->len)
+ goto errout;
+
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
return 0;
errout:
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
- rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+ if (err)
+ rtnl_set_sk_err(net, RTNLGRP_LINK, err);
return err;
}
@@ -2622,7 +2659,7 @@
sz_idx = type>>2;
kind = type&3;
- if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN))
+ if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
diff --git a/net/core/scm.c b/net/core/scm.c
index 03795d0..b4da80b 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -54,7 +54,7 @@
return -EINVAL;
if ((creds->pid == task_tgid_vnr(current) ||
- ns_capable(current->nsproxy->pid_ns->user_ns, CAP_SYS_ADMIN)) &&
+ ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) &&
((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) ||
uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) &&
((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) ||
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 6a2f13c..d0afc32 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -10,12 +10,27 @@
#include <net/secure_seq.h>
-static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
-void net_secret_init(void)
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static void net_secret_init(void)
{
- get_random_bytes(net_secret, sizeof(net_secret));
+ u32 tmp;
+ int i;
+
+ if (likely(net_secret[0]))
+ return;
+
+ for (i = NET_SECRET_SIZE; i > 0;) {
+ do {
+ get_random_bytes(&tmp, sizeof(tmp));
+ } while (!tmp);
+ cmpxchg(&net_secret[--i], 0, tmp);
+ }
}
+#endif
#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
@@ -42,6 +57,7 @@
u32 hash[MD5_DIGEST_WORDS];
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + (__force u32)daddr[i];
@@ -63,6 +79,7 @@
u32 hash[MD5_DIGEST_WORDS];
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + (__force u32) daddr[i];
@@ -78,35 +95,13 @@
#endif
#ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
- u32 hash[MD5_DIGEST_WORDS];
-
- hash[0] = (__force __u32) daddr;
- hash[1] = net_secret[13];
- hash[2] = net_secret[14];
- hash[3] = net_secret[15];
-
- md5_transform(hash, net_secret);
-
- return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
- __u32 hash[4];
-
- memcpy(hash, daddr, 16);
- md5_transform(hash, net_secret);
-
- return hash[0];
-}
__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport)
{
u32 hash[MD5_DIGEST_WORDS];
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -121,6 +116,7 @@
{
u32 hash[MD5_DIGEST_WORDS];
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = (__force u32)dport ^ net_secret[14];
@@ -140,6 +136,7 @@
u32 hash[MD5_DIGEST_WORDS];
u64 seq;
+ net_secret_init();
hash[0] = (__force u32)saddr;
hash[1] = (__force u32)daddr;
hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
@@ -164,6 +161,7 @@
u64 seq;
u32 i;
+ net_secret_init();
memcpy(hash, saddr, 16);
for (i = 0; i < 4; i++)
secret[i] = net_secret[i] + daddr[i];
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1c1738c..6148716 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -47,6 +47,8 @@
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <linux/netdevice.h>
#ifdef CONFIG_NET_CLS_ACT
#include <net/pkt_sched.h>
@@ -74,36 +76,6 @@
struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
-static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- put_page(buf->page);
-}
-
-static void sock_pipe_buf_get(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- get_page(buf->page);
-}
-
-static int sock_pipe_buf_steal(struct pipe_inode_info *pipe,
- struct pipe_buffer *buf)
-{
- return 1;
-}
-
-
-/* Pipe buffer operations for a socket. */
-static const struct pipe_buf_operations sock_pipe_buf_ops = {
- .can_merge = 0,
- .map = generic_pipe_buf_map,
- .unmap = generic_pipe_buf_unmap,
- .confirm = generic_pipe_buf_confirm,
- .release = sock_pipe_buf_release,
- .steal = sock_pipe_buf_steal,
- .get = sock_pipe_buf_get,
-};
-
/**
* skb_panic - private function for out-of-line support
* @skb: buffer
@@ -585,9 +557,6 @@
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
nf_conntrack_put(skb->nfct);
#endif
-#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
- nf_conntrack_put_reasm(skb->nfct_reasm);
-#endif
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(skb->nf_bridge);
#endif
@@ -1814,7 +1783,7 @@
.partial = partial,
.nr_pages_max = MAX_SKB_FRAGS,
.flags = flags,
- .ops = &sock_pipe_buf_ops,
+ .ops = &nosteal_pipe_buf_ops,
.spd_release = sock_spd_release,
};
struct sk_buff *frag_iter;
@@ -2841,7 +2810,6 @@
tail = nskb;
__copy_skb_header(nskb, skb);
- nskb->mac_len = skb->mac_len;
/* nskb and skb might have different headroom */
if (nskb->ip_summed == CHECKSUM_PARTIAL)
@@ -2851,13 +2819,14 @@
skb_set_network_header(nskb, skb->mac_len);
nskb->transport_header = (nskb->network_header +
skb_network_header_len(skb));
+ skb_reset_mac_len(nskb);
skb_copy_from_linear_data_offset(skb, -tnl_hlen,
nskb->data - tnl_hlen,
doffset + tnl_hlen);
if (fskb != skb_shinfo(skb)->frag_list)
- continue;
+ goto perform_csum_check;
if (!sg) {
nskb->ip_summed = CHECKSUM_NONE;
@@ -2875,6 +2844,8 @@
skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG;
while (pos < offset + len && i < nfrags) {
+ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+ goto err;
*frag = skb_shinfo(skb)->frags[i];
__skb_frag_ref(frag);
size = skb_frag_size(frag);
@@ -2921,6 +2892,7 @@
nskb->len += nskb->data_len;
nskb->truesize += nskb->data_len;
+perform_csum_check:
if (!csum) {
nskb->csum = skb_checksum(nskb, doffset,
nskb->len - doffset, 0);
@@ -3503,3 +3475,28 @@
return true;
}
EXPORT_SYMBOL(skb_try_coalesce);
+
+/**
+ * skb_gso_transport_seglen - Return length of individual segments of a gso packet
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_transport_seglen is used to determine the real size of the
+ * individual segments, including Layer4 headers (TCP/UDP).
+ *
+ * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
+ */
+unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
+{
+ const struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+ return tcp_hdrlen(skb) + shinfo->gso_size;
+
+ /* UFO sets gso_size to the size of the fragmentation
+ * payload, i.e. the size of the L4 (UDP) header is already
+ * accounted for.
+ */
+ return shinfo->gso_size;
+}
+EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
diff --git a/net/core/sock.c b/net/core/sock.c
index d6d024c..af65d17 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,6 +142,55 @@
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
+/**
+ * sk_ns_capable - General socket capability test
+ * @sk: Socket to use a capability on or through
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in the user
+ * namespace @user_ns.
+ */
+bool sk_ns_capable(const struct sock *sk,
+ struct user_namespace *user_ns, int cap)
+{
+ return file_ns_capable(sk->sk_socket->file, user_ns, cap) &&
+ ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(sk_ns_capable);
+
+/**
+ * sk_capable - Socket global capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The global capbility to use
+ *
+ * Test to see if the opener of the socket had when the socket was
+ * created and the current process has the capability @cap in all user
+ * namespaces.
+ */
+bool sk_capable(const struct sock *sk, int cap)
+{
+ return sk_ns_capable(sk, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(sk_capable);
+
+/**
+ * sk_net_capable - Network namespace socket capability test
+ * @sk: Socket to use a capability on or through
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket had when the socke was created
+ * and the current process has the capability @cap over the network namespace
+ * the socket is a member of.
+ */
+bool sk_net_capable(const struct sock *sk, int cap)
+{
+ return sk_ns_capable(sk, sock_net(sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(sk_net_capable);
+
+
#ifdef CONFIG_MEMCG_KMEM
int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
{
@@ -885,7 +934,7 @@
case SO_PEEK_OFF:
if (sock->ops->set_peek_off)
- sock->ops->set_peek_off(sk, val);
+ ret = sock->ops->set_peek_off(sk, val);
else
ret = -EOPNOTSUPP;
break;
@@ -1814,7 +1863,7 @@
gfp_t gfp = sk->sk_allocation;
if (order)
- gfp |= __GFP_COMP | __GFP_NOWARN;
+ gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
pfrag->page = alloc_pages(gfp, order);
if (likely(pfrag->page)) {
pfrag->offset = 0;
@@ -2271,6 +2320,7 @@
sk->sk_stamp = ktime_set(-1L, 0);
+ sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -2308,10 +2358,13 @@
if (sk->sk_backlog.tail)
__release_sock(sk);
+ /* Warning : release_cb() might need to release sk ownership,
+ * ie call sock_release_ownership(sk) before us.
+ */
if (sk->sk_prot->release_cb)
sk->sk_prot->release_cb(sk);
- sk->sk_lock.owned = 0;
+ sock_release_ownership(sk);
if (waitqueue_active(&sk->sk_lock.wq))
wake_up(&sk->sk_lock.wq);
spin_unlock_bh(&sk->sk_lock.slock);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6..c38e7a2 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -49,7 +49,7 @@
}
EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
-int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
struct sk_buff *skb, int attrtype)
{
struct nlattr *attr;
@@ -57,7 +57,7 @@
unsigned int len;
int err = 0;
- if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
+ if (!may_report_filterinfo) {
nla_reserve(skb, attrtype, 0);
return 0;
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cfdb46a..0a327b6 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -20,7 +20,11 @@
#include <net/sock.h>
#include <net/net_ratelimit.h>
+static int zero = 0;
static int one = 1;
+static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
#ifdef CONFIG_RPS
static int rps_sock_flow_sysctl(ctl_table *table, int write,
@@ -95,7 +99,7 @@
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_sndbuf,
},
{
.procname = "rmem_max",
@@ -103,7 +107,7 @@
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_rcvbuf,
},
{
.procname = "wmem_default",
@@ -111,7 +115,7 @@
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_sndbuf,
},
{
.procname = "rmem_default",
@@ -119,7 +123,7 @@
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &one,
+ .extra1 = &min_rcvbuf,
},
{
.procname = "dev_weight",
@@ -204,7 +208,9 @@
.data = &init_net.core.sysctl_somaxconn,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .extra1 = &zero,
+ .extra2 = &ushort_max,
+ .proc_handler = proc_dointvec_minmax
},
{ }
};
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 40d5829..1074ffb 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1670,7 +1670,7 @@
struct nlmsghdr *reply_nlh = NULL;
const struct reply_func *fn;
- if ((nlh->nlmsg_type == RTM_SETDCB) && !capable(CAP_NET_ADMIN))
+ if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9c61f9c..6cf9f77 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -135,6 +135,7 @@
if (dst)
dst->ops->redirect(dst, sk, skb);
+ goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 7d91970..b5e5210 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -573,7 +573,7 @@
struct dn_ifaddr __rcu **ifap;
int err = -EINVAL;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
@@ -617,7 +617,7 @@
struct dn_ifaddr *ifa;
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 57dc159..d332aef 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -505,7 +505,7 @@
struct nlattr *attrs[RTA_MAX+1];
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
@@ -530,7 +530,7 @@
struct nlattr *attrs[RTA_MAX+1];
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (!net_eq(net, &init_net))
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index 2a7efe3..f3dc69a 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -107,7 +107,7 @@
if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
return;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
/* Eventually we might send routing messages too */
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index c32be29..2022b46 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -150,7 +150,9 @@
if (!*_result)
goto put;
- memcpy(*_result, upayload->data, len + 1);
+ memcpy(*_result, upayload->data, len);
+ (*_result)[len] = '\0';
+
if (_expiry)
*_expiry = rkey->expiry;
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 55e1fd5..ca118e8 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -862,7 +862,7 @@
* Traffic class carried in-line
* ECN + DSCP (1 byte), Flow Label is elided
*/
- case 1: /* 10b */
+ case 2: /* 10b */
if (lowpan_fetch_skb_u8(skb, &tmp))
goto drop;
@@ -875,7 +875,7 @@
* Flow Label carried in-line
* ECN + 2-bit Pad + Flow Label (3 bytes), DSCP is elided
*/
- case 2: /* 01b */
+ case 1: /* 01b */
if (lowpan_fetch_skb_u8(skb, &tmp))
goto drop;
@@ -1173,7 +1173,27 @@
.create = lowpan_header_create,
};
+static struct lock_class_key lowpan_tx_busylock;
+static struct lock_class_key lowpan_netdev_xmit_lock_key;
+
+static void lowpan_set_lockdep_class_one(struct net_device *dev,
+ struct netdev_queue *txq,
+ void *_unused)
+{
+ lockdep_set_class(&txq->_xmit_lock,
+ &lowpan_netdev_xmit_lock_key);
+}
+
+
+static int lowpan_dev_init(struct net_device *dev)
+{
+ netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL);
+ dev->qdisc_tx_busylock = &lowpan_tx_busylock;
+ return 0;
+}
+
static const struct net_device_ops lowpan_netdev_ops = {
+ .ndo_init = lowpan_dev_init,
.ndo_start_xmit = lowpan_xmit,
.ndo_set_mac_address = lowpan_set_address,
};
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 581a595..1865fdf 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -315,9 +315,8 @@
if (saddr) {
saddr->family = AF_IEEE802154;
saddr->addr = mac_cb(skb)->sa;
- }
- if (addr_len)
*addr_len = sizeof(*saddr);
+ }
if (flags & MSG_TRUNC)
copied = skb->len;
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 22b1a70..4efd237 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -224,8 +224,10 @@
if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) {
type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]);
- if (type >= __IEEE802154_DEV_MAX)
- return -EINVAL;
+ if (type >= __IEEE802154_DEV_MAX) {
+ rc = -EINVAL;
+ goto nla_put_failure;
+ }
}
dev = phy->add_iface(phy, devname, type);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d01be2a..c4adc31 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,10 +263,8 @@
get_random_bytes(&rnd, sizeof(rnd));
} while (rnd == 0);
- if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) {
+ if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
- net_secret_init();
- }
}
EXPORT_SYMBOL(build_ehash_secret);
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index b28e863..5f3dc1d 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -57,7 +57,7 @@
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -86,18 +86,26 @@
}
EXPORT_SYMBOL(ip4_datagram_connect);
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
void ip4_datagram_release_cb(struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
+ struct dst_entry *dst;
struct flowi4 fl4;
struct rtable *rt;
- if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
- return;
-
rcu_read_lock();
+
+ dst = __sk_dst_get(sk);
+ if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+ rcu_read_unlock();
+ return;
+ }
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
@@ -105,8 +113,10 @@
inet->inet_saddr, inet->inet_dport,
inet->inet_sport, sk->sk_protocol,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
- if (!IS_ERR(rt))
- __sk_dst_set(sk, &rt->dst);
+
+ dst = !IS_ERR(rt) ? &rt->dst : NULL;
+ sk_dst_set(sk, dst);
+
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index dfc39d4..e40eef4 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -771,7 +771,7 @@
ci = nla_data(tb[IFA_CACHEINFO]);
if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
err = -EINVAL;
- goto errout;
+ goto errout_free;
}
*pvalid_lft = ci->ifa_valid;
*pprefered_lft = ci->ifa_prefered;
@@ -779,6 +779,8 @@
return ifa;
+errout_free:
+ inet_free_ifa(ifa);
errout:
return ERR_PTR(err);
}
@@ -1431,7 +1433,8 @@
+ nla_total_size(4) /* IFA_ADDRESS */
+ nla_total_size(4) /* IFA_LOCAL */
+ nla_total_size(4) /* IFA_BROADCAST */
- + nla_total_size(IFNAMSIZ); /* IFA_LABEL */
+ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
}
static inline u32 cstamp_delta(unsigned long cstamp)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a2..4556cd2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1049,6 +1049,8 @@
}
in_dev = __in_dev_get_rtnl(dev);
+ if (!in_dev)
+ return NOTIFY_DONE;
switch (event) {
case NETDEV_UP:
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 26aa65d..c5c8b24 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -62,6 +62,10 @@
else
res->tclassid = 0;
#endif
+
+ if (err == -ESRCH)
+ err = -ENETUNREACH;
+
return err;
}
EXPORT_SYMBOL_GPL(__fib_lookup);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8f6cb7a..bc773a1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -533,7 +533,7 @@
return 1;
attrlen = rtnh_attrlen(rtnh);
- if (attrlen < 0) {
+ if (attrlen > 0) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
nla = nla_find(attrs, attrlen, RTA_GATEWAY);
@@ -818,13 +818,13 @@
fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
if (fi == NULL)
goto failure;
+ fib_info_cnt++;
if (cfg->fc_mx) {
fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
if (!fi->fib_metrics)
goto failure;
} else
fi->fib_metrics = (u32 *) dst_default_metrics;
- fib_info_cnt++;
fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 49616fe..6e8a13d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -71,7 +71,6 @@
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>
-#include <linux/prefetch.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/ip.h>
@@ -1761,10 +1760,8 @@
if (!c)
continue;
- if (IS_LEAF(c)) {
- prefetch(rcu_dereference_rtnl(p->child[idx]));
+ if (IS_LEAF(c))
return (struct leaf *) c;
- }
/* Rescan start scanning in new node */
p = (struct tnode *) c;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 76e10b4..ea78ef5 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -697,8 +697,6 @@
&iph->daddr);
} else {
info = ntohs(icmph->un.frag.mtu);
- if (!info)
- goto out;
}
break;
case ICMP_SR_FAILED:
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index d8c2327..155adf8 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -343,7 +343,7 @@
pip->saddr = fl4.saddr;
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
- ip_select_ident(pip, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
((u8 *)&pip[1])[0] = IPOPT_RA;
((u8 *)&pip[1])[1] = 4;
((u8 *)&pip[1])[2] = 0;
@@ -687,7 +687,7 @@
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->protocol = IPPROTO_IGMP;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
((u8 *)&iph[1])[0] = IPOPT_RA;
((u8 *)&iph[1])[1] = 4;
((u8 *)&iph[1])[2] = 0;
@@ -709,7 +709,7 @@
in_dev->mr_gq_running = 0;
igmpv3_send_report(in_dev, NULL);
- __in_dev_put(in_dev);
+ in_dev_put(in_dev);
}
static void igmp_ifc_timer_expire(unsigned long data)
@@ -721,7 +721,7 @@
in_dev->mr_ifc_count--;
igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval);
}
- __in_dev_put(in_dev);
+ in_dev_put(in_dev);
}
static void igmp_ifc_event(struct in_device *in_dev)
@@ -1874,6 +1874,10 @@
rtnl_lock();
in_dev = ip_mc_find_dev(net, imr);
+ if (!in_dev) {
+ ret = -ENODEV;
+ goto out;
+ }
ifindex = imr->imr_ifindex;
for (imlp = &inet->mc_list;
(iml = rtnl_dereference(*imlp)) != NULL;
@@ -1891,16 +1895,14 @@
*imlp = iml->next_rcu;
- if (in_dev)
- ip_mc_dec_group(in_dev, group);
+ ip_mc_dec_group(in_dev, group);
rtnl_unlock();
/* decrease mem now to avoid the memleak warning */
atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
kfree_rcu(iml, rcu);
return 0;
}
- if (!in_dev)
- ret = -ENODEV;
+out:
rtnl_unlock();
return ret;
}
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 5f64875..14a1ed6 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -71,6 +71,20 @@
mutex_unlock(&inet_diag_table_mutex);
}
+static size_t inet_sk_attr_size(void)
+{
+ return nla_total_size(sizeof(struct tcp_info))
+ + nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+ + nla_total_size(1) /* INET_DIAG_TOS */
+ + nla_total_size(1) /* INET_DIAG_TCLASS */
+ + nla_total_size(sizeof(struct inet_diag_meminfo))
+ + nla_total_size(sizeof(struct inet_diag_msg))
+ + nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
+ + nla_total_size(TCP_CA_NAME_MAX)
+ + nla_total_size(sizeof(struct tcpvegas_info))
+ + 64;
+}
+
int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
@@ -106,6 +120,10 @@
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = inet->inet_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = inet->inet_rcv_saddr;
r->id.idiag_dst[0] = inet->inet_daddr;
@@ -240,12 +258,19 @@
r->idiag_family = tw->tw_family;
r->idiag_retrans = 0;
+
r->id.idiag_if = tw->tw_bound_dev_if;
sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
r->id.idiag_sport = tw->tw_sport;
r->id.idiag_dport = tw->tw_dport;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = tw->tw_rcv_saddr;
r->id.idiag_dst[0] = tw->tw_daddr;
+
r->idiag_state = tw->tw_substate;
r->idiag_timer = 3;
r->idiag_expires = DIV_ROUND_UP(tmo * 1000, HZ);
@@ -315,9 +340,7 @@
if (err)
goto out;
- rep = nlmsg_new(sizeof(struct inet_diag_msg) +
- sizeof(struct inet_diag_meminfo) +
- sizeof(struct tcp_info) + 64, GFP_KERNEL);
+ rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
err = -ENOMEM;
goto out;
@@ -732,8 +755,13 @@
r->id.idiag_sport = inet->inet_sport;
r->id.idiag_dport = ireq->rmt_port;
+
+ memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+ memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
r->id.idiag_src[0] = ireq->loc_addr;
r->id.idiag_dst[0] = ireq->rmt_addr;
+
r->idiag_expires = jiffies_to_msecs(tmo);
r->idiag_rqueue = 0;
r->idiag_wqueue = 0;
@@ -945,7 +973,7 @@
++num;
}
- if (r->idiag_states & TCPF_TIME_WAIT) {
+ if (r->idiag_states & (TCPF_TIME_WAIT | TCPF_FIN_WAIT2)) {
struct inet_timewait_sock *tw;
inet_twsk_for_each(tw, node,
@@ -955,6 +983,8 @@
if (num < s_num)
goto next_dying;
+ if (!(r->idiag_states & (1 << tw->tw_substate)))
+ goto next_dying;
if (r->sdiag_family != AF_UNSPEC &&
tw->tw_family != r->sdiag_family)
goto next_dying;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 7e06641..af02a39 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -211,7 +211,7 @@
}
work = frag_mem_limit(nf) - nf->low_thresh;
- while (work > 0) {
+ while (work > 0 || force) {
spin_lock(&nf->lru_lock);
if (list_empty(&nf->lru_list)) {
@@ -283,9 +283,10 @@
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &hb->chain);
+ inet_frag_lru_add(nf, qp);
spin_unlock(&hb->chain_lock);
read_unlock(&f->lock);
- inet_frag_lru_add(nf, qp);
+
return qp;
}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6af375a..c95848d 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -287,7 +287,7 @@
if (unlikely(!INET_TW_MATCH(sk, net, acookie,
saddr, daddr, ports,
dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 000e3d2..67140ef 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
* Theory of operations.
* We keep one entry for each peer IP address. The nodes contains long-living
* information about the peer which doesn't depend on routes.
- * At this moment this information consists only of ID field for the next
- * outgoing IP packet. This field is incremented with each packet as encoded
- * in inet_getid() function (include/net/inetpeer.h).
- * At the moment of writing this notes identifier of IP packets is generated
- * to be unpredictable using this code only for packets subjected
- * (actually or potentially) to defragmentation. I.e. DF packets less than
- * PMTU in size uses a constant ID and do not use this code (see
- * ip_select_ident() in include/net/ip.h).
*
- * Route cache entries hold references to our nodes.
- * New cache entries get references via lookup by destination IP address in
- * the avl tree. The reference is grabbed only when it's needed i.e. only
- * when we try to output IP packet which needs an unpredictable ID (see
- * __ip_select_ident() in net/ipv4/route.c).
* Nodes are removed only when reference counter goes to 0.
* When it's happened the node may be removed when a sufficient amount of
* time has been passed since its last use. The less-recently-used entry can
@@ -62,7 +49,6 @@
* refcnt: atomically against modifications on other CPU;
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
- * ip_id_count: atomic value (no lock needed)
*/
static struct kmem_cache *peer_cachep __read_mostly;
@@ -504,10 +490,6 @@
p->daddr = *daddr;
atomic_set(&p->refcnt, 1);
atomic_set(&p->rid, 0);
- atomic_set(&p->ip_id_count,
- (daddr->family == AF_INET) ?
- secure_ip_id(daddr->addr.a4) :
- secure_ipv6_id(daddr->addr.a6));
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
p->rate_tokens = 0;
/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 694de3b..479e8a6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -39,6 +39,71 @@
#include <net/route.h>
#include <net/xfrm.h>
+static bool ip_may_fragment(const struct sk_buff *skb)
+{
+ return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
+ skb->local_df;
+}
+
+static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
+static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
+{
+ unsigned int mtu;
+
+ if (skb->local_df || !skb_is_gso(skb))
+ return false;
+
+ mtu = dst_mtu(skb_dst(skb));
+
+ /* if seglen > mtu, do software segmentation for IP fragmentation on
+ * output. DF bit cannot be set since ip_forward would have sent
+ * icmp error.
+ */
+ return skb_gso_network_seglen(skb) > mtu;
+}
+
+/* called if GSO skb needs to be fragmented on forward */
+static int ip_forward_finish_gso(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ netdev_features_t features;
+ struct sk_buff *segs;
+ int ret = 0;
+
+ features = netif_skb_dev_features(skb, dst->dev);
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR(segs)) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ consume_skb(skb);
+
+ do {
+ struct sk_buff *nskb = segs->next;
+ int err;
+
+ segs->next = NULL;
+ err = dst_output(segs);
+
+ if (err && ret == 0)
+ ret = err;
+ segs = nskb;
+ } while (segs);
+
+ return ret;
+}
+
static int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
@@ -49,6 +114,9 @@
if (unlikely(opt->optlen))
ip_forward_options(skb);
+ if (ip_gso_exceeds_dst_mtu(skb))
+ return ip_forward_finish_gso(skb);
+
return dst_output(skb);
}
@@ -58,6 +126,9 @@
struct rtable *rt; /* Route we use */
struct ip_options *opt = &(IPCB(skb)->opt);
+ if (unlikely(skb->sk))
+ goto drop;
+
if (skb_warn_if_lro(skb))
goto drop;
@@ -88,8 +159,7 @@
if (opt->is_strictroute && rt->rt_uses_gateway)
goto sr_failed;
- if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
- (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
+ if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, dst_mtu(&rt->dst))) {
IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->dst)));
@@ -108,7 +178,8 @@
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
- if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+ if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+ !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b66910a..4c1884f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -678,27 +678,30 @@
struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user)
{
struct iphdr iph;
+ int netoff;
u32 len;
if (skb->protocol != htons(ETH_P_IP))
return skb;
- if (!skb_copy_bits(skb, 0, &iph, sizeof(iph)))
+ netoff = skb_network_offset(skb);
+
+ if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0)
return skb;
if (iph.ihl < 5 || iph.version != 4)
return skb;
len = ntohs(iph.tot_len);
- if (skb->len < len || len < (iph.ihl * 4))
+ if (skb->len < netoff + len || len < (iph.ihl * 4))
return skb;
if (ip_is_fragment(&iph)) {
skb = skb_share_check(skb, GFP_ATOMIC);
if (skb) {
- if (!pskb_may_pull(skb, iph.ihl*4))
+ if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
return skb;
- if (pskb_trim_rcsum(skb, len))
+ if (pskb_trim_rcsum(skb, netoff + len))
return skb;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
if (ip_defrag(skb, user))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2a83591..fae5a84 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -335,7 +335,8 @@
iph->saddr, iph->daddr, tpi.key);
if (tunnel) {
- ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ skb_pop_mac_header(skb);
+ ip_tunnel_rcv(tunnel, skb, &tpi, hdr_len, log_ecn_error);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
@@ -503,10 +504,11 @@
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
- ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING))) {
- return -EINVAL;
+ if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
+ ((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
+ return -EINVAL;
}
p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
@@ -571,7 +573,7 @@
if (daddr)
memcpy(&iph->daddr, daddr, 4);
if (iph->daddr)
- return t->hlen;
+ return t->hlen + sizeof(*iph);
return -(t->hlen + sizeof(*iph));
}
@@ -650,6 +652,7 @@
static void ipgre_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipgre_netdev_ops;
+ dev->type = ARPHRD_IPGRE;
ip_tunnel_setup(dev, ipgre_net_id);
}
@@ -688,7 +691,6 @@
memcpy(dev->dev_addr, &iph->saddr, 4);
memcpy(dev->broadcast, &iph->daddr, 4);
- dev->type = ARPHRD_IPGRE;
dev->flags = IFF_NOARP;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->addr_len = 4;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 3da817b..0a22bb0 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -190,10 +190,7 @@
{
struct net *net = dev_net(skb->dev);
- __skb_pull(skb, ip_hdrlen(skb));
-
- /* Point into the IP datagram, just past the header. */
- skb_reset_transport_header(skb);
+ __skb_pull(skb, skb_network_header_len(skb));
rcu_read_lock();
{
@@ -316,7 +313,7 @@
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
- if (sysctl_ip_early_demux && !skb_dst(skb)) {
+ if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
const struct net_protocol *ipprot;
int protocol = iph->protocol;
@@ -437,6 +434,8 @@
goto drop;
}
+ skb->transport_header = skb->network_header + iph->ihl*4;
+
/* Remove any debris in the socket control block */
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec72645..089ed81 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -288,6 +288,10 @@
optptr++;
continue;
}
+ if (unlikely(l < 2)) {
+ pp_ptr = optptr;
+ goto error;
+ }
optlen = optptr[1];
if (optlen<2 || optlen>l) {
pp_ptr = optptr;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 4bcabf3..57e7450 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@
iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
iph->saddr = saddr;
iph->protocol = sk->sk_protocol;
- ip_select_ident(iph, &rt->dst, sk);
+ ip_select_ident(skb, sk);
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
@@ -394,8 +394,7 @@
ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
}
- ip_select_ident_more(iph, &rt->dst, sk,
- (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+ ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
@@ -844,9 +843,10 @@
csummode = CHECKSUM_PARTIAL;
cork->length += length;
- if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+ if (((length > mtu) || (skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
- (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
+ (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+ (sk->sk_type == SOCK_DGRAM)) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, transhdrlen,
maxfraglen, flags);
@@ -1324,7 +1324,7 @@
else
ttl = ip_select_ttl(inet, &rt->dst);
- iph = (struct iphdr *)skb->data;
+ iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = 5;
iph->tos = inet->tos;
@@ -1332,7 +1332,7 @@
iph->ttl = ttl;
iph->protocol = sk->sk_protocol;
ip_copy_addrs(iph, fl4);
- ip_select_ident(iph, &rt->dst, sk);
+ ip_select_ident(skb, sk);
if (opt) {
iph->ihl += opt->optlen>>2;
@@ -1455,23 +1455,8 @@
/*
* Generic function to send a packet as reply to another packet.
* Used to send some TCP resets/acks so far.
- *
- * Use a fake percpu inet socket to avoid false sharing and contention.
*/
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
- .sk = {
- .__sk_common = {
- .skc_refcnt = ATOMIC_INIT(1),
- },
- .sk_wmem_alloc = ATOMIC_INIT(1),
- .sk_allocation = GFP_ATOMIC,
- .sk_flags = (1UL << SOCK_USE_WRITE_QUEUE),
- },
- .pmtudisc = IP_PMTUDISC_WANT,
- .uc_ttl = -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, __be32 daddr,
__be32 saddr, const struct ip_reply_arg *arg,
unsigned int len)
{
@@ -1479,9 +1464,9 @@
struct ipcm_cookie ipc;
struct flowi4 fl4;
struct rtable *rt = skb_rtable(skb);
+ struct net *net = sock_net(sk);
struct sk_buff *nskb;
- struct sock *sk;
- struct inet_sock *inet;
+ int err;
if (ip_options_echo(&replyopts.opt.opt, skb))
return;
@@ -1508,18 +1493,19 @@
if (IS_ERR(rt))
return;
- inet = &get_cpu_var(unicast_sock);
+ inet_sk(sk)->tos = arg->tos;
- inet->tos = arg->tos;
- sk = &inet->sk;
sk->sk_priority = skb->priority;
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
- sock_net_set(sk, net);
- __skb_queue_head_init(&sk->sk_write_queue);
sk->sk_sndbuf = sysctl_wmem_default;
- ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0,
- &ipc, &rt, MSG_DONTWAIT);
+ err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
+ len, 0, &ipc, &rt, MSG_DONTWAIT);
+ if (unlikely(err)) {
+ ip_flush_pending_frames(sk);
+ goto out;
+ }
+
nskb = skb_peek(&sk->sk_write_queue);
if (nskb) {
if (arg->csumoffset >= 0)
@@ -1527,13 +1513,10 @@
arg->csumoffset) = csum_fold(csum_add(nskb->csum,
arg->csum));
nskb->ip_summed = CHECKSUM_NONE;
- skb_orphan(nskb);
skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
ip_push_pending_frames(sk, &fl4);
}
-
- put_cpu_var(unicast_sock);
-
+out:
ip_rt_put(rt);
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d9c4f11..f660314 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -368,7 +368,7 @@
/*
* Handle MSG_ERRQUEUE
*/
-int ip_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct sock_exterr_skb *serr;
struct sk_buff *skb, *skb2;
@@ -405,19 +405,16 @@
serr->addr_offset);
sin->sin_port = serr->port;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
- sin->sin_family = AF_UNSPEC;
+ memset(sin, 0, sizeof(*sin));
if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP) {
- struct inet_sock *inet = inet_sk(sk);
-
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
- sin->sin_port = 0;
- memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
- if (inet->cmsg_flags)
+ if (inet_sk(sk)->cmsg_flags)
ip_cmsg_recv(msg, skb);
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 7fa8f08..84aa69c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -166,6 +166,7 @@
hlist_for_each_entry_rcu(t, head, hash_node) {
if (remote != t->parms.iph.daddr ||
+ t->parms.iph.saddr != 0 ||
!(t->dev->flags & IFF_UP))
continue;
@@ -182,10 +183,11 @@
head = &itn->tunnels[hash];
hlist_for_each_entry_rcu(t, head, hash_node) {
- if ((local != t->parms.iph.saddr &&
- (local != t->parms.iph.daddr ||
- !ipv4_is_multicast(local))) ||
- !(t->dev->flags & IFF_UP))
+ if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+ (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+ continue;
+
+ if (!(t->dev->flags & IFF_UP))
continue;
if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -202,6 +204,8 @@
hlist_for_each_entry_rcu(t, head, hash_node) {
if (t->parms.i_key != key ||
+ t->parms.iph.saddr != 0 ||
+ t->parms.iph.daddr != 0 ||
!(t->dev->flags & IFF_UP))
continue;
@@ -402,7 +406,7 @@
}
int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
- const struct tnl_ptk_info *tpi, bool log_ecn_error)
+ const struct tnl_ptk_info *tpi, int hdr_len, bool log_ecn_error)
{
struct pcpu_tstats *tstats;
const struct iphdr *iph = ip_hdr(skb);
@@ -413,7 +417,7 @@
skb->protocol = tpi->proto;
skb->mac_header = skb->network_header;
- __pskb_pull(skb, tunnel->hlen);
+ __pskb_pull(skb, hdr_len);
skb_postpull_rcsum(skb, skb_transport_header(skb), tunnel->hlen);
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
@@ -486,6 +490,53 @@
}
EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
+static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
+ struct rtable *rt, __be16 df)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
+ int mtu;
+
+ if (df)
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len
+ - sizeof(struct iphdr) - tunnel->hlen;
+ else
+ mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ if (!skb_is_gso(skb) &&
+ (df & htons(IP_DF)) && mtu < pkt_size) {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ return -E2BIG;
+ }
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
+
+ if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
+ mtu >= IPV6_MIN_MTU) {
+ if ((tunnel->parms.iph.daddr &&
+ !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
+ rt6->rt6i_dst.plen == 128) {
+ rt6->rt6i_flags |= RTF_MODIFIED;
+ dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
+ }
+ }
+
+ if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
+ mtu < pkt_size) {
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ return -E2BIG;
+ }
+ }
+#endif
+ return 0;
+}
+
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params)
{
@@ -499,7 +550,6 @@
struct net_device *tdev; /* Device to other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
- int mtu;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
@@ -579,56 +629,18 @@
goto tx_error;
}
- df = tnl_params->frag_off;
- if (df)
- mtu = dst_mtu(&rt->dst) - dev->hard_header_len
- - sizeof(struct iphdr);
- else
- mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
-
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- if (skb->protocol == htons(ETH_P_IP)) {
- df |= (inner_iph->frag_off&htons(IP_DF));
-
- if (!skb_is_gso(skb) &&
- (inner_iph->frag_off&htons(IP_DF)) &&
- mtu < ntohs(inner_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
+ if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+ ip_rt_put(rt);
+ goto tx_error;
}
-#if IS_ENABLED(CONFIG_IPV6)
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
-
- if (rt6 && mtu < dst_mtu(skb_dst(skb)) &&
- mtu >= IPV6_MIN_MTU) {
- if ((tunnel->parms.iph.daddr &&
- !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
- rt6->rt6i_dst.plen == 128) {
- rt6->rt6i_flags |= RTF_MODIFIED;
- dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
- }
- }
-
- if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
- mtu < skb->len) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#endif
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
dst_link_failure(skb);
} else
tunnel->err_count = 0;
@@ -646,15 +658,19 @@
ttl = ip4_dst_hoplimit(&rt->dst);
}
+ df = tnl_params->frag_off;
+ if (skb->protocol == htons(ETH_P_IP))
+ df |= (inner_iph->frag_off&htons(IP_DF));
+
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr)
+ rt->dst.header_len;
- if (max_headroom > dev->needed_headroom) {
+ if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
- if (skb_cow_head(skb, dev->needed_headroom)) {
- dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
- return;
- }
+
+ if (skb_cow_head(skb, dev->needed_headroom)) {
+ dev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return;
}
skb_dst_drop(skb);
@@ -675,7 +691,7 @@
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
iph->ttl = ttl;
- tunnel_ip_select_ident(skb, inner_iph, &rt->dst);
+ __ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
iptunnel_xmit(skb, dev);
return;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c118f6b..4ec3427 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -285,8 +285,17 @@
tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ u32 oldmark = skb->mark;
+ int ret;
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+ /* temporarily mark the skb with the tunnel o_key, to
+ * only match policies with this mark.
+ */
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+ ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+ skb->mark = oldmark;
+ if (!ret)
return -1;
tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -295,7 +304,6 @@
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- skb->mark = 0;
secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
@@ -327,7 +335,7 @@
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
@@ -342,6 +350,7 @@
if (!rt->dst.xfrm ||
rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) {
dev->stats.tx_carrier_errors++;
+ ip_rt_put(rt);
goto tx_error_icmp;
}
tdev = rt->dst.dev;
@@ -570,9 +579,9 @@
static void vti_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &vti_netdev_ops;
+ dev->type = ARPHRD_TUNNEL;
dev->destructor = vti_dev_free;
- dev->type = ARPHRD_TUNNEL;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
dev->mtu = ETH_DATA_LEN;
dev->flags = IFF_NOARP;
@@ -606,17 +615,10 @@
struct iphdr *iph = &tunnel->parms.iph;
struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id);
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
-
iph->version = 4;
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
- if (!dev->tstats)
- return -ENOMEM;
-
dev_hold(dev);
rcu_assign_pointer(ipn->tunnels_wc[0], tunnel);
return 0;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 77bfcce..897b784 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -149,13 +149,13 @@
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+ t->parms.link, 0, IPPROTO_IPIP, 0);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+ ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
IPPROTO_IPIP, 0);
err = 0;
goto out;
@@ -195,7 +195,7 @@
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
- return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
+ return ip_tunnel_rcv(tunnel, skb, &tpi, 0, log_ecn_error);
}
return -1;
@@ -240,11 +240,13 @@
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
return -EFAULT;
- if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
- p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
- return -EINVAL;
- if (p.i_key || p.o_key || p.i_flags || p.o_flags)
- return -EINVAL;
+ if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
+ if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
+ p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
+ return -EINVAL;
+ }
+
+ p.i_key = p.o_key = p.i_flags = p.o_flags = 0;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
@@ -481,4 +483,5 @@
module_init(ipip_init);
module_exit(ipip_fini);
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d9610a..56d079b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@
static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
struct mr_table **mrt)
{
- struct ipmr_result res;
- struct fib_lookup_arg arg = { .result = &res, };
int err;
+ struct ipmr_result res;
+ struct fib_lookup_arg arg = {
+ .result = &res,
+ .flags = FIB_LOOKUP_NOREF,
+ };
err = fib_rules_lookup(net->ipv4.mr_rules_ops,
flowi4_to_flowi(flp4), 0, &arg);
@@ -1658,7 +1661,7 @@
iph->protocol = IPPROTO_IPIP;
iph->ihl = 5;
iph->tot_len = htons(skb->len);
- ip_select_ident(iph, skb_dst(skb), NULL);
+ ip_select_ident(skb, NULL);
ip_send_check(iph);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -2252,13 +2255,14 @@
}
static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc_cache *c, int cmd)
+ u32 portid, u32 seq, struct mfc_cache *c, int cmd,
+ int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2326,7 +2330,7 @@
if (skb == NULL)
goto errout;
- err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2365,7 +2369,8 @@
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0)
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
@@ -2379,7 +2384,8 @@
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0) {
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 85a4f21..c8abe31 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1039,8 +1039,10 @@
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
- sizeof(struct xt_counters) * num_counters) != 0)
- ret = -EFAULT;
+ sizeof(struct xt_counters) * num_counters) != 0) {
+ /* Silent error, can't fail, new table is already in place */
+ net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n");
+ }
vfree(counters);
xt_table_unlock(t);
return ret;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index d23118d..651c107 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1226,8 +1226,10 @@
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
- sizeof(struct xt_counters) * num_counters) != 0)
- ret = -EFAULT;
+ sizeof(struct xt_counters) * num_counters) != 0) {
+ /* Silent error, can't fail, new table is already in place */
+ net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n");
+ }
vfree(counters);
xt_table_unlock(t);
return ret;
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 32b0e97..f8629c0 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -220,6 +220,7 @@
ub->qlen++;
pm = nlmsg_data(nlh);
+ memset(pm, 0, sizeof(*pm));
/* We might not have a timestamp, get one */
if (skb->tstamp.tv64 == 0)
@@ -238,8 +239,6 @@
}
else if (loginfo->prefix[0] != '\0')
strncpy(pm->prefix, loginfo->prefix, sizeof(pm->prefix));
- else
- *(pm->prefix) = '\0';
if (in && in->hard_header_len > 0 &&
skb->mac_header != skb->network_header &&
@@ -251,13 +250,9 @@
if (in)
strncpy(pm->indev_name, in->name, sizeof(pm->indev_name));
- else
- pm->indev_name[0] = '\0';
if (out)
strncpy(pm->outdev_name, out->name, sizeof(pm->outdev_name));
- else
- pm->outdev_name[0] = '\0';
/* copy_len <= skb->len, so can't fail. */
if (skb_copy_bits(skb, 0, pm->payload, copy_len) < 0)
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 7428155..4cfb3bd 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
#endif
#include <net/netfilter/nf_conntrack_zones.h>
-/* Returns new sk_buff, or NULL */
static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
{
int err;
@@ -33,8 +32,10 @@
err = ip_defrag(skb, user);
local_bh_enable();
- if (!err)
+ if (!err) {
ip_send_check(ip_hdr(skb));
+ skb->local_df = 1;
+ }
return err;
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7d93d62..698f3a2 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -204,26 +204,33 @@
{
struct net *net = sock_net(sk);
kgid_t group = current_egid();
- struct group_info *group_info = get_current_groups();
- int i, j, count = group_info->ngroups;
+ struct group_info *group_info;
+ int i, j, count;
kgid_t low, high;
+ int ret = 0;
inet_get_ping_group_range_net(net, &low, &high);
if (gid_lte(low, group) && gid_lte(group, high))
return 0;
+ group_info = get_current_groups();
+ count = group_info->ngroups;
for (i = 0; i < group_info->nblocks; i++) {
int cp_count = min_t(int, NGROUPS_PER_BLOCK, count);
for (j = 0; j < cp_count; j++) {
kgid_t gid = group_info->blocks[i][j];
if (gid_lte(low, gid) && gid_lte(gid, high))
- return 0;
+ goto out_release_group;
}
count -= cp_count;
}
- return -EACCES;
+ ret = -EACCES;
+
+out_release_group:
+ put_group_info(group_info);
+ return ret;
}
static void ping_close(struct sock *sk, long timeout)
@@ -570,7 +577,7 @@
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -626,7 +633,6 @@
size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *isk = inet_sk(sk);
- struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
struct sk_buff *skb;
int copied, err;
@@ -636,11 +642,8 @@
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -660,11 +663,14 @@
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
- if (sin) {
+ if (msg->msg_name) {
+ struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+
sin->sin_family = AF_INET;
sin->sin_port = 0 /* skb->h.uh->source */;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (isk->cmsg_flags)
ip_cmsg_recv(msg, skb);
@@ -714,8 +720,11 @@
sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id),
skb->dev->ifindex);
if (sk != NULL) {
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
+
pr_debug("rcv on socket %p\n", sk);
- ping_queue_rcv_skb(sk, skb_get(skb));
+ if (skb2)
+ ping_queue_rcv_skb(sk, skb2);
sock_put(sk);
return;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dd44e0a..b4a1c42 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -387,7 +387,7 @@
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
@@ -571,7 +571,8 @@
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
- inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP,
+ inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP |
+ (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
if (!inet->hdrincl) {
@@ -691,11 +692,8 @@
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE) {
- err = ip_recv_error(sk, msg, len);
+ err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
@@ -721,6 +719,7 @@
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0..e23c5f6 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
+#include <linux/jhash.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
@@ -464,39 +465,53 @@
return neigh_create(&arp_tbl, pkey, dev);
}
-/*
- * Peer allocation may fail only in serious out-of-memory conditions. However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+ atomic_t id;
+ u32 stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
*/
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
{
- static DEFINE_SPINLOCK(ip_fb_id_lock);
- static u32 ip_fallback_id;
- u32 salt;
+ struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+ u32 old = ACCESS_ONCE(bucket->stamp32);
+ u32 now = (u32)jiffies;
+ u32 delta = 0;
- spin_lock_bh(&ip_fb_id_lock);
- salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
- iph->id = htons(salt & 0xFFFF);
- ip_fallback_id = salt;
- spin_unlock_bh(&ip_fb_id_lock);
-}
+ if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) {
+ u64 x = prandom_u32();
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
-{
- struct net *net = dev_net(dst->dev);
- struct inet_peer *peer;
-
- peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
- if (peer) {
- iph->id = htons(inet_getid(peer, more));
- inet_putpeer(peer);
- return;
+ x *= (now - old);
+ delta = (u32)(x >> 32);
}
- ip_select_fb_ident(iph);
+ return atomic_add_return(segs + delta, &bucket->id) - segs;
+}
+EXPORT_SYMBOL(ip_idents_reserve);
+
+void __ip_select_ident(struct iphdr *iph, int segs)
+{
+ static u32 ip_idents_hashrnd __read_mostly;
+ static bool hashrnd_initialized = false;
+ u32 hash, id;
+
+ if (unlikely(!hashrnd_initialized)) {
+ hashrnd_initialized = true;
+ get_random_bytes(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
+ }
+
+ hash = jhash_3words((__force u32)iph->daddr,
+ (__force u32)iph->saddr,
+ iph->protocol,
+ ip_idents_hashrnd);
+ id = ip_idents_reserve(hash, segs);
+ iph->id = htons(id);
}
EXPORT_SYMBOL(__ip_select_ident);
@@ -985,20 +1000,21 @@
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
- struct dst_entry *dst;
+ struct dst_entry *odst = NULL;
bool new = false;
bh_lock_sock(sk);
- rt = (struct rtable *) __sk_dst_get(sk);
+ odst = sk_dst_get(sk);
- if (sock_owned_by_user(sk) || !rt) {
+ if (sock_owned_by_user(sk) || !odst) {
__ipv4_sk_update_pmtu(skb, sk, mtu);
goto out;
}
__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- if (!__sk_dst_check(sk, 0)) {
+ rt = (struct rtable *)odst;
+ if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
if (IS_ERR(rt))
goto out;
@@ -1008,8 +1024,7 @@
__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
- dst = dst_check(&rt->dst, 0);
- if (!dst) {
+ if (!dst_check(&rt->dst, 0)) {
if (new)
dst_release(&rt->dst);
@@ -1021,10 +1036,11 @@
}
if (new)
- __sk_dst_set(sk, &rt->dst);
+ sk_dst_set(sk, &rt->dst);
out:
bh_unlock_sock(sk);
+ dst_release(odst);
}
EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
@@ -1478,7 +1494,7 @@
struct in_device *out_dev;
unsigned int flags = 0;
bool do_cache;
- u32 itag;
+ u32 itag = 0;
/* get a working reference to the output device */
out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
@@ -1498,11 +1514,10 @@
do_cache = res->fi && !itag;
if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+ skb->protocol == htons(ETH_P_IP) &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
- inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
- flags |= RTCF_DOREDIRECT;
- do_cache = false;
- }
+ inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+ IPCB(skb)->flags |= IPSKB_DOREDIRECT;
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1544,6 +1559,7 @@
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1645,8 +1661,6 @@
if (err != 0)
goto no_route;
- RT_CACHE_STAT_INC(in_slow_tot);
-
if (res.type == RTN_BROADCAST)
goto brd_input;
@@ -1715,13 +1729,18 @@
rth->rt_gateway = 0;
rth->rt_uses_gateway = 0;
INIT_LIST_HEAD(&rth->rt_uncached);
+ RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- if (do_cache)
- rt_cache_route(&FIB_RES_NH(res), rth);
+ if (do_cache) {
+ if (unlikely(!rt_cache_route(&FIB_RES_NH(res), rth))) {
+ rth->dst.flags |= DST_NOCACHE;
+ rt_add_uncached_list(rth);
+ }
+ }
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
@@ -2020,7 +2039,7 @@
RT_SCOPE_LINK);
goto make_route;
}
- if (fl4->saddr) {
+ if (!fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
@@ -2235,6 +2254,8 @@
r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
+ if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+ r->rtm_flags |= RTCF_DOREDIRECT;
if (nla_put_be32(skb, RTA_DST, dst))
goto nla_put_failure;
@@ -2302,7 +2323,7 @@
}
} else
#endif
- if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+ if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
goto nla_put_failure;
}
@@ -2651,6 +2672,12 @@
{
int rc = 0;
+ ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+ if (!ip_idents)
+ panic("IP: failed to allocate ip_idents\n");
+
+ prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
#ifdef CONFIG_IP_ROUTE_CLASSID
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
if (!ip_rt_acct)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index fa2f63f..90b26be 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
static int zero;
static int one = 1;
static int four = 4;
+static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -36,6 +37,8 @@
static int tcp_adv_win_scale_max = 31;
static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
+static int tcp_syn_retries_min = 1;
+static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
@@ -331,7 +334,9 @@
.data = &sysctl_tcp_syn_retries,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &tcp_syn_retries_min,
+ .extra2 = &tcp_syn_retries_max
},
{
.procname = "tcp_synack_retries",
@@ -749,6 +754,15 @@
.extra2 = &four,
},
{
+ .procname = "tcp_min_tso_segs",
+ .data = &sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &gso_max_segs,
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ab450c0..5d4bd6c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,6 +282,8 @@
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -786,14 +788,24 @@
xmit_size_goal = mss_now;
if (large_allowed && sk_can_gso(sk)) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
+ u32 gso_size, hlen;
- /* TSQ : try to have two TSO segments in flight */
- xmit_size_goal = min_t(u32, xmit_size_goal,
- sysctl_tcp_limit_output_bytes >> 1);
+ /* Maybe we should/could use sk->sk_prot->max_header here ? */
+ hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+ inet_csk(sk)->icsk_ext_hdr_len +
+ tp->tcp_header_len;
+
+ /* Goal is to send at least one packet per ms,
+ * not one big TSO packet every 100 ms.
+ * This preserves ACK clocking and is consistent
+ * with tcp_tso_should_defer() heuristic.
+ */
+ gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+ gso_size = max_t(u32, gso_size,
+ sysctl_tcp_min_tso_segs * mss_now);
+
+ xmit_size_goal = min_t(u32, gso_size,
+ sk->sk_gso_max_size - 1 - hlen);
xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
@@ -989,7 +1001,8 @@
}
}
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
+ int *copied, size_t size)
{
struct tcp_sock *tp = tcp_sk(sk);
int err, flags;
@@ -1004,11 +1017,12 @@
if (unlikely(tp->fastopen_req == NULL))
return -ENOBUFS;
tp->fastopen_req->data = msg;
+ tp->fastopen_req->size = size;
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
msg->msg_namelen, flags);
- *size = tp->fastopen_req->copied;
+ *copied = tp->fastopen_req->copied;
tcp_free_fastopen_req(tp);
return err;
}
@@ -1028,7 +1042,7 @@
flags = msg->msg_flags;
if (flags & MSG_FASTOPEN) {
- err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+ err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
if (err == -EINPROGRESS && copied_syn > 0)
goto out;
else if (err)
@@ -1051,7 +1065,7 @@
if (unlikely(tp->repair)) {
if (tp->repair_queue == TCP_RECV_QUEUE) {
copied = tcp_send_rcvq(sk, msg, size);
- goto out;
+ goto out_nopush;
}
err = -EINVAL;
@@ -1118,6 +1132,13 @@
goto wait_for_memory;
/*
+ * All packets are restored as if they have
+ * already been sent.
+ */
+ if (tp->repair)
+ TCP_SKB_CB(skb)->when = tcp_time_stamp;
+
+ /*
* Check whether we can use HW checksum.
*/
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -1217,6 +1238,7 @@
out:
if (copied)
tcp_push(sk, flags, mss_now, tp->nonagle);
+out_nopush:
release_sock(sk);
return copied + copied_syn;
@@ -2440,10 +2462,11 @@
case TCP_THIN_DUPACK:
if (val < 0 || val > 1)
err = -EINVAL;
- else
+ else {
tp->thin_dupack = val;
if (tp->thin_dupack)
tcp_disable_early_retrans(tp);
+ }
break;
case TCP_REPAIR:
@@ -2879,6 +2902,7 @@
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int sum_truesize = 0;
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
@@ -2962,13 +2986,7 @@
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be gso_skb->truesize
- * So we account mss bytes of 'true size' for each segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
+ sum_truesize += skb->truesize;
}
skb = skb->next;
th = tcp_hdr(skb);
@@ -2985,7 +3003,9 @@
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
+ sum_truesize += skb->truesize;
+ atomic_add(sum_truesize - gso_skb->truesize,
+ &skb->sk->sk_wmem_alloc);
}
delta = htonl(oldlen + (skb->tail - skb->transport_header) +
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index a9077f4..894b7ce 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -206,8 +206,8 @@
*/
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
- u64 offs;
- u32 delta, t, bic_target, max_cnt;
+ u32 delta, bic_target, max_cnt;
+ u64 offs, t;
ca->ack_cnt++; /* count the number of ACKs */
@@ -250,9 +250,11 @@
* if the cwnd < 1 million packets !!!
*/
+ t = (s32)(tcp_time_stamp - ca->epoch_start);
+ t += msecs_to_jiffies(ca->delay_min >> 3);
/* change the unit from HZ to bictcp_HZ */
- t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3)
- - ca->epoch_start) << BICTCP_HZ) / HZ;
+ t <<= BICTCP_HZ;
+ do_div(t, HZ);
if (t < ca->bic_K) /* t - K */
offs = ca->bic_K - t;
@@ -406,7 +408,7 @@
ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
ratio += cnt;
- ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT);
+ ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
}
/* Some calls are for duplicates without timetamps */
@@ -414,7 +416,7 @@
return;
/* Discard delay samples right after fast recovery */
- if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+ if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
delay = (rtt_us << 3) / USEC_PER_MSEC;
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 834857f..86183c4 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -23,7 +23,6 @@
#define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */
#define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */
#define ALPHA_BASE ALPHA_SCALE /* 1.0 */
-#define U32_MAX ((u32)~0U)
#define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */
#define BETA_SHIFT 6
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c62257..a8be45e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -699,6 +699,34 @@
}
}
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+ * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+ * We probably need usec resolution in the future.
+ * Note: This also takes care of possible srtt=0 case,
+ * when tcp_rtt_estimator() was not yet called.
+ */
+ if (tp->srtt > 8 + 2)
+ do_div(rate, tp->srtt);
+
+ sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
@@ -1047,7 +1075,7 @@
}
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+ if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
tp->undo_retrans--;
@@ -1102,7 +1130,7 @@
unsigned int new_len = (pkt_len / mss) * mss;
if (!in_sack && new_len < pkt_len) {
new_len += mss;
- if (new_len > skb->len)
+ if (new_len >= skb->len)
return 0;
}
pkt_len = new_len;
@@ -1126,7 +1154,7 @@
/* Account D-SACK for retransmitted packet. */
if (dup_sack && (sacked & TCPCB_RETRANS)) {
- if (tp->undo_marker && tp->undo_retrans &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
after(end_seq, tp->undo_marker))
tp->undo_retrans--;
if (sacked & TCPCB_SACKED_ACKED)
@@ -1264,7 +1292,10 @@
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+ TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ TCP_SKB_CB(prev)->end_seq++;
+
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
@@ -1819,7 +1850,7 @@
tp->lost_out = 0;
tp->undo_marker = 0;
- tp->undo_retrans = 0;
+ tp->undo_retrans = -1;
}
void tcp_clear_retrans(struct tcp_sock *tp)
@@ -2669,7 +2700,7 @@
tp->prior_ssthresh = 0;
tp->undo_marker = tp->snd_una;
- tp->undo_retrans = tp->retrans_out;
+ tp->undo_retrans = tp->retrans_out ? : -1;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
if (!ece_ack)
@@ -2689,13 +2720,12 @@
bool recovered = !before(tp->snd_una, tp->high_seq);
if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
- if (flag & FLAG_ORIG_SACK_ACKED) {
- /* Step 3.b. A timeout is spurious if not all data are
- * lost, i.e., never-retransmitted data are (s)acked.
- */
- tcp_try_undo_loss(sk, true);
+ /* Step 3.b. A timeout is spurious if not all data are
+ * lost, i.e., never-retransmitted data are (s)acked.
+ */
+ if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED))
return;
- }
+
if (after(tp->snd_nxt, tp->high_seq) &&
(flag & FLAG_DATA_SACKED || is_dupack)) {
tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
@@ -3046,10 +3076,11 @@
if (seq_rtt < 0) {
seq_rtt = ca_seq_rtt;
}
- if (!(sacked & TCPCB_SACKED_ACKED))
+ if (!(sacked & TCPCB_SACKED_ACKED)) {
reord = min(pkts_acked, reord);
- if (!after(scb->end_seq, tp->high_seq))
- flag |= FLAG_ORIG_SACK_ACKED;
+ if (!after(scb->end_seq, tp->high_seq))
+ flag |= FLAG_ORIG_SACK_ACKED;
+ }
}
if (sacked & TCPCB_SACKED_ACKED)
@@ -3314,7 +3345,7 @@
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
@@ -3330,7 +3361,7 @@
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight;
+ u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
u32 prior_fackets;
int prior_packets = tp->packets_out;
int prior_sacked = tp->sacked_out;
@@ -3438,6 +3469,8 @@
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
+ if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
@@ -3598,7 +3631,10 @@
++ptr;
tp->rx_opt.rcv_tsval = ntohl(*ptr);
++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ if (*ptr)
+ tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ else
+ tp->rx_opt.rcv_tsecr = 0;
return true;
}
return false;
@@ -3623,7 +3659,7 @@
}
tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
return true;
@@ -5376,7 +5412,7 @@
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
if (th->ack) {
@@ -5733,6 +5769,8 @@
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7999fc5..7c3eec3 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -176,7 +176,7 @@
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return err;
}
@@ -268,7 +268,7 @@
* It can be called through tcp_release_cb() if socket was owned by user
* at the time tcp_v4_err() was called to handle ICMP message.
*/
-static void tcp_v4_mtu_reduced(struct sock *sk)
+void tcp_v4_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
@@ -298,6 +298,7 @@
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
}
+EXPORT_SYMBOL(tcp_v4_mtu_reduced);
static void do_redirect(struct sk_buff *skb, struct sock *sk)
{
@@ -706,7 +707,8 @@
net = dev_net(skb_dst(skb)->dev);
arg.tos = ip_hdr(skb)->tos;
- ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
+ ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ skb, ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
@@ -789,7 +791,8 @@
if (oif)
arg.bound_dev_if = oif;
arg.tos = tos;
- ip_send_unicast_reply(net, skb, ip_hdr(skb)->saddr,
+ ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+ skb, ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
@@ -1898,7 +1901,7 @@
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk->sk_state != TCP_TIME_WAIT) {
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
@@ -2142,6 +2145,7 @@
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
#endif
+ .mtu_reduced = tcp_v4_mtu_reduced,
};
EXPORT_SYMBOL(ipv4_specific);
@@ -2867,7 +2871,6 @@
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v4_do_rcv,
.release_cb = tcp_release_cb,
- .mtu_reduced = tcp_v4_mtu_reduced,
.hash = inet_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
@@ -2897,14 +2900,39 @@
};
EXPORT_SYMBOL(tcp_prot);
-static int __net_init tcp_sk_init(struct net *net)
-{
- net->ipv4.sysctl_tcp_ecn = 2;
- return 0;
-}
-
static void __net_exit tcp_sk_exit(struct net *net)
{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+ free_percpu(net->ipv4.tcp_sk);
+}
+
+static int __net_init tcp_sk_init(struct net *net)
+{
+ int res, cpu;
+
+ net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+ if (!net->ipv4.tcp_sk)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct sock *sk;
+
+ res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+ IPPROTO_TCP, net);
+ if (res)
+ goto fail;
+ *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+ }
+ net->ipv4.sysctl_tcp_ecn = 2;
+ return 0;
+
+fail:
+ tcp_sk_exit(net);
+
+ return res;
}
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index f6a005c..b500d2d 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
int sysctl_tcp_nometrics_save __read_mostly;
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+ struct net *net, unsigned int hash);
+
struct tcp_fastopen_metrics {
u16 mss;
u16 syn_loss:10; /* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@
}
}
+#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+ if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+ tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH 5
+#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL
+
static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
struct inetpeer_addr *addr,
- unsigned int hash,
- bool reclaim)
+ unsigned int hash)
{
struct tcp_metrics_block *tm;
struct net *net;
+ bool reclaim = false;
spin_lock_bh(&tcp_metrics_lock);
net = dev_net(dst->dev);
+
+ /* While waiting for the spin-lock the cache might have been populated
+ * with this entry and so we have to check again.
+ */
+ tm = __tcp_get_metrics(addr, net, hash);
+ if (tm == TCP_METRICS_RECLAIM_PTR) {
+ reclaim = true;
+ tm = NULL;
+ }
+ if (tm) {
+ tcpm_check_stamp(tm, dst);
+ goto out_unlock;
+ }
+
if (unlikely(reclaim)) {
struct tcp_metrics_block *oldest;
@@ -169,17 +197,6 @@
return tm;
}
-#define TCP_METRICS_TIMEOUT (60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
- if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
- tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH 5
-#define TCP_METRICS_RECLAIM_PTR (struct tcp_metrics_block *) 0x1UL
-
static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
{
if (tm)
@@ -280,7 +297,6 @@
struct inetpeer_addr addr;
unsigned int hash;
struct net *net;
- bool reclaim;
addr.family = sk->sk_family;
switch (addr.family) {
@@ -300,13 +316,10 @@
hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
tm = __tcp_get_metrics(&addr, net, hash);
- reclaim = false;
- if (tm == TCP_METRICS_RECLAIM_PTR) {
- reclaim = true;
+ if (tm == TCP_METRICS_RECLAIM_PTR)
tm = NULL;
- }
if (!tm && create)
- tm = tcpm_new(dst, &addr, hash, reclaim);
+ tm = tcpm_new(dst, &addr, hash);
else
tcpm_check_stamp(tm, dst);
@@ -665,10 +678,13 @@
void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
struct tcp_fastopen_cookie *cookie, bool syn_lost)
{
+ struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_metrics_block *tm;
+ if (!dst)
+ return;
rcu_read_lock();
- tm = tcp_get_metrics(sk, __sk_dst_get(sk), true);
+ tm = tcp_get_metrics(sk, dst, true);
if (tm) {
struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ec335fa..76c80b59 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -686,7 +686,8 @@
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
- tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC);
+ tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+ 0, GFP_ATOMIC);
}
/*
* One tasklest per cpu tries to send more skbs.
@@ -754,6 +755,17 @@
if (flags & (1UL << TCP_TSQ_DEFERRED))
tcp_tsq_handler(sk);
+ /* Here begins the tricky part :
+ * We are called from release_sock() with :
+ * 1) BH disabled
+ * 2) sk_lock.slock spinlock held
+ * 3) socket owned by us (sk->sk_lock.owned == 1)
+ *
+ * But following code is meant to be called from BH handlers,
+ * so we should keep BH disabled, but early release socket ownership
+ */
+ sock_release_ownership(sk);
+
if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
tcp_write_timer_handler(sk);
__sock_put(sk);
@@ -763,7 +775,7 @@
__sock_put(sk);
}
if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
- sk->sk_prot->mtu_reduced(sk);
+ inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
__sock_put(sk);
}
}
@@ -887,8 +899,7 @@
skb_orphan(skb);
skb->sk = sk;
- skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
- tcp_wfree : sock_wfree;
+ skb->destructor = tcp_wfree;
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
/* Build TCP header and checksum it. */
@@ -977,6 +988,9 @@
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1058,9 +1072,7 @@
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -1623,7 +1635,7 @@
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
- sk->sk_gso_max_segs * tp->mss_cache))
+ tp->xmit_size_goal_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1844,6 @@
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
-
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
@@ -1851,7 +1862,7 @@
if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
break;
- if (tso_segs == 1) {
+ if (tso_segs == 1 || !sk->sk_gso_max_segs) {
if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
(tcp_skb_is_last(sk, skb) ?
nonagle : TCP_NAGLE_PUSH))))
@@ -1861,15 +1872,34 @@
break;
}
- /* TSQ : sk_wmem_alloc accounts skb truesize,
- * including skb overhead. But thats OK.
+ /* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * This allows for :
+ * - better RTT estimation and ACK scheduling
+ * - faster recovery
+ * - high rates
+ * Alas, some drivers / subsystems require a fair amount
+ * of queued bytes to ensure line rate.
+ * One example is wifi aggregation (802.11 AMPDU)
*/
- if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+ limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+ sk->sk_pacing_rate >> 10);
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
- break;
+ /* It is possible TX completion already happened
+ * before we set TSQ_THROTTLED, so we must
+ * test again the condition.
+ * We abuse smp_mb__after_clear_bit() because
+ * there is no smp_mb__after_set_bit() yet
+ */
+ smp_mb__after_clear_bit();
+ if (atomic_read(&sk->sk_wmem_alloc) > limit)
+ break;
}
+
limit = mss_now;
- if (tso_segs > 1 && !tcp_urg_mode(tp))
+ if (tso_segs > 1 && sk->sk_gso_max_segs && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
min_t(unsigned int,
cwnd_quota,
@@ -2006,9 +2036,7 @@
if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
goto rearm_timer;
- /* Probe with zero data doesn't trigger fast recovery. */
- if (skb->len > 0)
- err = __tcp_retransmit_skb(sk, skb);
+ err = __tcp_retransmit_skb(sk, skb);
/* Record snd_nxt for loss detection. */
if (likely(!err))
@@ -2329,6 +2357,8 @@
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
@@ -2396,13 +2426,15 @@
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
- tp->undo_retrans += tcp_skb_pcount(skb);
-
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
*/
TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
}
+
+ if (tp->undo_retrans < 0)
+ tp->undo_retrans = 0;
+ tp->undo_retrans += tcp_skb_pcount(skb);
return err;
}
@@ -2539,43 +2571,65 @@
}
}
-/* Send a fin. The caller locks the socket for us. This cannot be
- * allowed to fail queueing a FIN frame under any circumstances.
+/* We allow to exceed memory limits for FIN packets to expedite
+ * connection tear down and (memory) recovery.
+ * Otherwise tcp_send_fin() could be tempted to either delay FIN
+ * or even be forced to close flow without any FIN.
+ */
+static void sk_forced_wmem_schedule(struct sock *sk, int size)
+{
+ int amt, status;
+
+ if (size <= sk->sk_forward_alloc)
+ return;
+ amt = sk_mem_pages(size);
+ sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
+ sk_memory_allocated_add(sk, amt, &status);
+}
+
+/* Send a FIN. The caller locks the socket for us.
+ * We should try to send a FIN packet really hard, but eventually give up.
*/
void tcp_send_fin(struct sock *sk)
{
+ struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_write_queue_tail(sk);
- int mss_now;
- /* Optimization, tack on the FIN if we have a queue of
- * unsent frames. But be careful about outgoing SACKS
- * and IP options.
+ /* Optimization, tack on the FIN if we have one skb in write queue and
+ * this skb was not yet sent, or we are under memory pressure.
+ * Note: in the latter case, FIN packet will be sent after a timeout,
+ * as TCP stack thinks it has already been transmitted.
*/
- mss_now = tcp_current_mss(sk);
-
- if (tcp_send_head(sk) != NULL) {
- TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN;
- TCP_SKB_CB(skb)->end_seq++;
+ if (tskb && (tcp_send_head(sk) || sk_under_memory_pressure(sk))) {
+coalesce:
+ TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN;
+ TCP_SKB_CB(tskb)->end_seq++;
tp->write_seq++;
- } else {
- /* Socket is locked, keep trying until memory is available. */
- for (;;) {
- skb = alloc_skb_fclone(MAX_TCP_HEADER,
- sk->sk_allocation);
- if (skb)
- break;
- yield();
+ if (!tcp_send_head(sk)) {
+ /* This means tskb was already sent.
+ * Pretend we included the FIN on previous transmit.
+ * We need to set tp->snd_nxt to the value it would have
+ * if FIN had been sent. This is because retransmit path
+ * does not change tp->snd_nxt.
+ */
+ tp->snd_nxt++;
+ return;
}
-
- /* Reserve space for headers and prepare control bits. */
+ } else {
+ skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+ if (unlikely(!skb)) {
+ if (tskb)
+ goto coalesce;
+ return;
+ }
skb_reserve(skb, MAX_TCP_HEADER);
+ sk_forced_wmem_schedule(sk, skb->truesize);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
@@ -2664,7 +2718,7 @@
int tcp_header_size;
int mss;
- skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC));
+ skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -2744,6 +2798,8 @@
}
#endif
+ /* Do not fool tcpdump (if any), clean our debris */
+ skb->tstamp.tv64 = 0;
return skb;
}
EXPORT_SYMBOL(tcp_make_synack);
@@ -2808,6 +2864,8 @@
if (likely(!tp->repair))
tp->rcv_nxt = 0;
+ else
+ tp->rcv_tstamp = tcp_time_stamp;
tp->rcv_wup = tp->rcv_nxt;
tp->copied_seq = tp->rcv_nxt;
@@ -2841,9 +2899,9 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
- struct sk_buff *syn_data = NULL, *data;
+ int syn_loss = 0, space, err = 0;
unsigned long last_syn_loss = 0;
+ struct sk_buff *syn_data;
tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
@@ -2869,42 +2927,44 @@
space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
- syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
- sk->sk_allocation);
- if (syn_data == NULL)
+ space = min_t(size_t, space, fo->size);
+
+ /* limit to order-0 allocations */
+ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+ syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation);
+ if (!syn_data)
goto fallback;
-
- for (i = 0; i < iovlen && syn_data->len < space; ++i) {
- struct iovec *iov = &fo->data->msg_iov[i];
- unsigned char __user *from = iov->iov_base;
- int len = iov->iov_len;
-
- if (syn_data->len + len > space)
- len = space - syn_data->len;
- else if (i + 1 == iovlen)
- /* No more data pending in inet_wait_for_connect() */
- fo->data = NULL;
-
- if (skb_add_data(syn_data, from, len))
- goto fallback;
+ syn_data->ip_summed = CHECKSUM_PARTIAL;
+ memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
+ skb_shinfo(syn_data)->gso_segs = 1;
+ if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
+ fo->data->msg_iov, 0, space))) {
+ kfree_skb(syn_data);
+ goto fallback;
}
- /* Queue a data-only packet after the regular SYN for retransmission */
- data = pskb_copy(syn_data, sk->sk_allocation);
- if (data == NULL)
- goto fallback;
- TCP_SKB_CB(data)->seq++;
- TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
- TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
- tcp_connect_queue_skb(sk, data);
- fo->copied = data->len;
+ /* No more data pending in inet_wait_for_connect() */
+ if (space == fo->size)
+ fo->data = NULL;
+ fo->copied = space;
- if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+ tcp_connect_queue_skb(sk, syn_data);
+
+ err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation);
+
+ /* Now full SYN+DATA was cloned and sent (or not),
+ * remove the SYN from the original skb (syn_data)
+ * we keep in write queue in case of a retransmit, as we
+ * also have the SYN packet (with no data) in the same queue.
+ */
+ TCP_SKB_CB(syn_data)->seq++;
+ TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH;
+ if (!err) {
tp->syn_data = (fo->copied > 0);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
goto done;
}
- syn_data = NULL;
fallback:
/* Send a regular SYN with Fast Open cookie request option */
@@ -2913,7 +2973,6 @@
err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
if (err)
tp->syn_fastopen = 0;
- kfree_skb(syn_data);
done:
fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */
return err;
@@ -2933,13 +2992,10 @@
return 0;
}
- buff = alloc_skb_fclone(MAX_TCP_HEADER + 15, sk->sk_allocation);
- if (unlikely(buff == NULL))
+ buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
+ if (unlikely(!buff))
return -ENOBUFS;
- /* Reserve space for headers. */
- skb_reserve(buff, MAX_TCP_HEADER);
-
tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
tcp_connect_queue_skb(sk, buff);
@@ -3088,7 +3144,6 @@
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
- tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
tcp_xmit_probe_skb(sk, 0);
}
}
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 80fa2bf..c042e52 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -218,7 +218,8 @@
* This is:
* (actual rate in segments) * baseRTT
*/
- target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt;
+ target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT;
+ do_div(target_cwnd, rtt);
/* Calculate the difference between the window we had,
* and the window we would like to have. This quantity
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index ac43cd7..b4d1858 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -144,7 +144,7 @@
rtt = veno->minrtt;
- target_cwnd = (tp->snd_cwnd * veno->basertt);
+ target_cwnd = (u64)tp->snd_cwnd * veno->basertt;
target_cwnd <<= V_PARAM_SHIFT;
do_div(target_cwnd, rtt);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0bf5d39..c3075b5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -799,7 +799,7 @@
/*
* Push out all pending data as one UDP datagram. Socket is locked.
*/
-static int udp_push_pending_frames(struct sock *sk)
+int udp_push_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
@@ -818,6 +818,7 @@
up->pending = 0;
return err;
}
+EXPORT_SYMBOL(udp_push_pending_frames);
int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len)
@@ -970,7 +971,7 @@
err = PTR_ERR(rt);
rt = NULL;
if (err == -ENETUNREACH)
- IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
goto out;
}
@@ -1069,6 +1070,9 @@
struct udp_sock *up = udp_sk(sk);
int ret;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
if (!up->pending) {
struct msghdr msg = { .msg_flags = flags|MSG_MORE };
@@ -1206,14 +1210,8 @@
int is_udplite = IS_UDPLITE(sk);
bool slow;
- /*
- * Check any passed addresses
- */
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ return ip_recv_error(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1273,6 +1271,7 @@
sin->sin_port = udp_hdr(skb)->source;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 7927db0..4a000f1 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -99,11 +99,13 @@
s_slot = cb->args[0];
num = s_num = cb->args[1];
- for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+ for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) {
struct sock *sk;
struct hlist_nulls_node *node;
struct udp_hslot *hslot = &table->hash[slot];
+ num = 0;
+
if (hlist_nulls_empty(&hslot->head))
continue;
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index eb1dd4d..e3f64831 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -117,12 +117,12 @@
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
- ip_select_ident(top_iph, dst->child, NULL);
top_iph->ttl = ip4_dst_hoplimit(dst->child);
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
+ ip_select_ident(skb, NULL);
return 0;
}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4ab4c38..d0912ac 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1111,8 +1111,11 @@
* Lifetime is greater than REGEN_ADVANCE time units. In particular,
* an implementation must not create a temporary address with a zero
* Preferred Lifetime.
+ * Use age calculation as in addrconf_verify to avoid unnecessary
+ * temporary addresses being generated.
*/
- if (tmp_prefered_lft <= regen_advance) {
+ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
+ if (tmp_prefered_lft <= regen_advance + age) {
in6_ifa_put(ifp);
in6_dev_put(idev);
ret = -1;
@@ -1124,12 +1127,10 @@
if (ifp->flags & IFA_F_OPTIMISTIC)
addr_flags |= IFA_F_OPTIMISTIC;
- ift = !max_addresses ||
- ipv6_count_addresses(idev) < max_addresses ?
- ipv6_add_addr(idev, &addr, tmp_plen,
- ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK,
- addr_flags) : NULL;
- if (IS_ERR_OR_NULL(ift)) {
+ ift = ipv6_add_addr(idev, &addr, tmp_plen,
+ ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK,
+ addr_flags);
+ if (IS_ERR(ift)) {
in6_ifa_put(ifp);
in6_dev_put(idev);
pr_info("%s: retry temporary address regeneration\n", __func__);
@@ -1448,6 +1449,23 @@
}
EXPORT_SYMBOL(ipv6_dev_get_saddr);
+int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr,
+ unsigned char banned_flags)
+{
+ struct inet6_ifaddr *ifp;
+ int err = -EADDRNOTAVAIL;
+
+ list_for_each_entry(ifp, &idev->addr_list, if_list) {
+ if (ifp->scope == IFA_LINK &&
+ !(ifp->flags & banned_flags)) {
+ *addr = ifp->addr;
+ err = 0;
+ break;
+ }
+ }
+ return err;
+}
+
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
unsigned char banned_flags)
{
@@ -1457,17 +1475,8 @@
rcu_read_lock();
idev = __in6_dev_get(dev);
if (idev) {
- struct inet6_ifaddr *ifp;
-
read_lock_bh(&idev->lock);
- list_for_each_entry(ifp, &idev->addr_list, if_list) {
- if (ifp->scope == IFA_LINK &&
- !(ifp->flags & banned_flags)) {
- *addr = ifp->addr;
- err = 0;
- break;
- }
- }
+ err = __ipv6_get_lladdr(idev, addr, banned_flags);
read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
@@ -1527,6 +1536,33 @@
return false;
}
+/* Compares an address/prefix_len with addresses on device @dev.
+ * If one is found it returns true.
+ */
+bool ipv6_chk_custom_prefix(const struct in6_addr *addr,
+ const unsigned int prefix_len, struct net_device *dev)
+{
+ struct inet6_dev *idev;
+ struct inet6_ifaddr *ifa;
+ bool ret = false;
+
+ rcu_read_lock();
+ idev = __in6_dev_get(dev);
+ if (idev) {
+ read_lock_bh(&idev->lock);
+ list_for_each_entry(ifa, &idev->addr_list, if_list) {
+ ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len);
+ if (ret)
+ break;
+ }
+ read_unlock_bh(&idev->lock);
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(ipv6_chk_custom_prefix);
+
int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev)
{
struct inet6_dev *idev;
@@ -2655,8 +2691,18 @@
if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
continue;
- if (sp_ifa->rt)
- continue;
+ if (sp_ifa->rt) {
+ /* This dst has been added to garbage list when
+ * lo device down, release this obsolete dst and
+ * reallocate a new router for ifa.
+ */
+ if (sp_ifa->rt->dst.obsolete > 0) {
+ ip6_rt_put(sp_ifa->rt);
+ sp_ifa->rt = NULL;
+ } else {
+ continue;
+ }
+ }
sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f083a58..b30ad37 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -251,38 +251,36 @@
/* add a label */
static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace)
{
+ struct hlist_node *n;
+ struct ip6addrlbl_entry *last = NULL, *p = NULL;
int ret = 0;
- ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n",
- __func__,
- newp, replace);
+ ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp,
+ replace);
- if (hlist_empty(&ip6addrlbl_table.head)) {
- hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head);
- } else {
- struct hlist_node *n;
- struct ip6addrlbl_entry *p = NULL;
- hlist_for_each_entry_safe(p, n,
- &ip6addrlbl_table.head, list) {
- if (p->prefixlen == newp->prefixlen &&
- net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) &&
- p->ifindex == newp->ifindex &&
- ipv6_addr_equal(&p->prefix, &newp->prefix)) {
- if (!replace) {
- ret = -EEXIST;
- goto out;
- }
- hlist_replace_rcu(&p->list, &newp->list);
- ip6addrlbl_put(p);
- goto out;
- } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) ||
- (p->prefixlen < newp->prefixlen)) {
- hlist_add_before_rcu(&newp->list, &p->list);
+ hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) {
+ if (p->prefixlen == newp->prefixlen &&
+ net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) &&
+ p->ifindex == newp->ifindex &&
+ ipv6_addr_equal(&p->prefix, &newp->prefix)) {
+ if (!replace) {
+ ret = -EEXIST;
goto out;
}
+ hlist_replace_rcu(&p->list, &newp->list);
+ ip6addrlbl_put(p);
+ goto out;
+ } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) ||
+ (p->prefixlen < newp->prefixlen)) {
+ hlist_add_before_rcu(&newp->list, &p->list);
+ goto out;
}
- hlist_add_after_rcu(&p->list, &newp->list);
+ last = p;
}
+ if (last)
+ hlist_add_after_rcu(&last->list, &newp->list);
+ else
+ hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head);
out:
if (!ret)
ip6addrlbl_table.seq++;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 4b56cbb..ce17d3d 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -318,7 +318,7 @@
/*
* Handle MSG_ERRQUEUE
*/
-int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sock_exterr_skb *serr;
@@ -369,14 +369,15 @@
&sin->sin6_addr);
sin->sin6_scope_id = 0;
}
+ *addr_len = sizeof(*sin);
}
memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
sin = &errhdr.offender;
- sin->sin6_family = AF_UNSPEC;
+ memset(sin, 0, sizeof(*sin));
+
if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
sin->sin6_family = AF_INET6;
- sin->sin6_flowinfo = 0;
if (skb->protocol == htons(ETH_P_IPV6)) {
sin->sin6_addr = ipv6_hdr(skb)->saddr;
if (np->rxopt.all)
@@ -385,12 +386,9 @@
ipv6_iface_scope_id(&sin->sin6_addr,
IP6CB(skb)->iif);
} else {
- struct inet_sock *inet = inet_sk(sk);
-
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin->sin6_addr);
- sin->sin6_scope_id = 0;
- if (inet->cmsg_flags)
+ if (inet_sk(sk)->cmsg_flags)
ip_cmsg_recv(msg, skb);
}
}
@@ -423,7 +421,8 @@
/*
* Handle IPV6_RECVPATHMTU
*/
-int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
+ int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
@@ -457,6 +456,7 @@
sin->sin6_port = 0;
sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
+ *addr_len = sizeof(*sin);
}
put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 07a7d65..8d67900 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -162,12 +162,6 @@
off += optlen;
len -= optlen;
}
- /* This case will not be caught by above check since its padding
- * length is smaller than 7:
- * 1 byte NH + 1 byte Length + 6 bytes Padding
- */
- if ((padlen == 6) && ((off - skb_network_header_len(skb)) == 8))
- goto bad;
if (len == 0)
return true;
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index c5e83fa..51af9d0 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -212,7 +212,7 @@
found = (nexthdr == target);
if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) {
- if (target < 0)
+ if (target < 0 || found)
break;
return -ENOENT;
}
diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c
index cf77f3a..447a7fb 100644
--- a/net/ipv6/exthdrs_offload.c
+++ b/net/ipv6/exthdrs_offload.c
@@ -25,11 +25,11 @@
int ret;
ret = inet6_add_offload(&rthdr_offload, IPPROTO_ROUTING);
- if (!ret)
+ if (ret)
goto out;
ret = inet6_add_offload(&dstopt_offload, IPPROTO_DSTOPTS);
- if (!ret)
+ if (ret)
goto out_rt;
out:
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index b4ff0a4..2dee1d9 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -508,7 +508,7 @@
np->tclass, NULL, &fl6, (struct rt6_info *)dst,
MSG_DONTWAIT, np->dontfrag);
if (err) {
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
ip6_flush_pending_frames(sk);
} else {
err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
@@ -931,6 +931,14 @@
.err = ECONNREFUSED,
.fatal = 1,
},
+ { /* POLICY_FAIL */
+ .err = EACCES,
+ .fatal = 1,
+ },
+ { /* REJECT_ROUTE */
+ .err = EACCES,
+ .fatal = 1,
+ },
};
int icmpv6_err_convert(u8 type, u8 code, int *err)
@@ -942,7 +950,7 @@
switch (type) {
case ICMPV6_DEST_UNREACH:
fatal = 1;
- if (code <= ICMPV6_PORT_UNREACH) {
+ if (code < ARRAY_SIZE(tab_unreach)) {
*err = tab_unreach[code].err;
fatal = tab_unreach[code].fatal;
}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 32b4a16..066640e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -116,7 +116,7 @@
}
if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
ports, dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 192dd1a..ceeb945 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -632,6 +632,35 @@
return ln;
}
+static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt)
+{
+ return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
+ RTF_GATEWAY;
+}
+
+static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+ struct net *net)
+{
+ if (atomic_read(&rt->rt6i_ref) != 1) {
+ /* This route is used as dummy address holder in some split
+ * nodes. It is not leaked, but it still holds other resources,
+ * which must be released in time. So, scan ascendant nodes
+ * and replace dummy references to this route with references
+ * to still alive ones.
+ */
+ while (fn) {
+ if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
+ fn->leaf = fib6_find_prefix(net, fn);
+ atomic_inc(&fn->leaf->rt6i_ref);
+ rt6_release(rt);
+ }
+ fn = fn->parent;
+ }
+ /* No more references are possible at this point. */
+ BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
+ }
+}
+
/*
* Insert routing information in a node.
*/
@@ -646,6 +675,7 @@
int add = (!info->nlh ||
(info->nlh->nlmsg_flags & NLM_F_CREATE));
int found = 0;
+ bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
ins = &fn->leaf;
@@ -691,9 +721,8 @@
* To avoid long list, we only had siblings if the
* route have a gateway.
*/
- if (rt->rt6i_flags & RTF_GATEWAY &&
- !(rt->rt6i_flags & RTF_EXPIRES) &&
- !(iter->rt6i_flags & RTF_EXPIRES))
+ if (rt_can_ecmp &&
+ rt6_qualify_for_ecmp(iter))
rt->rt6i_nsiblings++;
}
@@ -715,7 +744,8 @@
/* Find the first route that have the same metric */
sibling = fn->leaf;
while (sibling) {
- if (sibling->rt6i_metric == rt->rt6i_metric) {
+ if (sibling->rt6i_metric == rt->rt6i_metric &&
+ rt6_qualify_for_ecmp(sibling)) {
list_add_tail(&rt->rt6i_siblings,
&sibling->rt6i_siblings);
break;
@@ -768,11 +798,12 @@
rt->dst.rt6_next = iter->dst.rt6_next;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
- rt6_release(iter);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ fib6_purge_rt(iter, fn, info->nl_net);
+ rt6_release(iter);
}
return 0;
@@ -818,9 +849,9 @@
fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst),
allow_create, replace_required);
-
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
+ fn = NULL;
goto out;
}
@@ -986,14 +1017,22 @@
if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) {
#ifdef CONFIG_IPV6_SUBTREES
- if (fn->subtree)
- fn = fib6_lookup_1(fn->subtree, args + 1);
+ if (fn->subtree) {
+ struct fib6_node *sfn;
+ sfn = fib6_lookup_1(fn->subtree,
+ args + 1);
+ if (!sfn)
+ goto backtrack;
+ fn = sfn;
+ }
#endif
- if (!fn || fn->fn_flags & RTN_RTINFO)
+ if (fn->fn_flags & RTN_RTINFO)
return fn;
}
}
-
+#ifdef CONFIG_IPV6_SUBTREES
+backtrack:
+#endif
if (fn->fn_flags & RTN_ROOT)
break;
@@ -1269,24 +1308,7 @@
fn = fib6_repair_tree(net, fn);
}
- if (atomic_read(&rt->rt6i_ref) != 1) {
- /* This route is used as dummy address holder in some split
- * nodes. It is not leaked, but it still holds other resources,
- * which must be released in time. So, scan ascendant nodes
- * and replace dummy references to this route with references
- * to still alive ones.
- */
- while (fn) {
- if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
- fn->leaf = fib6_find_prefix(net, fn);
- atomic_inc(&fn->leaf->rt6i_ref);
- rt6_release(rt);
- }
- fn = fn->parent;
- }
- /* No more references are possible at this point. */
- BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
- }
+ fib6_purge_rt(rt, fn, net);
inet6_rt_notify(RTM_DELROUTE, rt, info);
rt6_release(rt);
@@ -1403,7 +1425,7 @@
if (w->skip) {
w->skip--;
- continue;
+ goto skip;
}
err = w->func(w);
@@ -1413,6 +1435,7 @@
w->count++;
continue;
}
+skip:
w->state = FWS_U;
case FWS_U:
if (fn == w->root)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 46e8843..f0ccdb7 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -453,8 +453,10 @@
if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK)
return 0;
+ rcu_read_lock_bh();
for_each_sk_fl_rcu(np, sfl)
count++;
+ rcu_read_unlock_bh();
if (room <= 0 ||
((count >= FL_MAX_PER_SOCK ||
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ecd6073..65156a7 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -512,11 +512,11 @@
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
- * - Change protocol to IP
+ * - Change protocol to IPv6
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
- skb->protocol = htons(ETH_P_IP);
+ skb->protocol = htons(ETH_P_IPV6);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
@@ -620,7 +620,7 @@
struct ip6_tnl *tunnel = netdev_priv(dev);
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *ipv6h; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
+ unsigned int max_headroom = 0; /* The extra header space needed */
int gre_hlen;
struct ipv6_tel_txoption opt;
int mtu;
@@ -693,7 +693,7 @@
tunnel->err_count = 0;
}
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
+ max_headroom += LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
@@ -787,7 +787,7 @@
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- fl6.flowi6_proto = IPPROTO_IPIP;
+ fl6.flowi6_proto = IPPROTO_GRE;
dsfield = ipv4_get_dsfield(iph);
@@ -837,7 +837,7 @@
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
- fl6.flowi6_proto = IPPROTO_IPV6;
+ fl6.flowi6_proto = IPPROTO_GRE;
dsfield = ipv6_get_dsfield(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
@@ -962,8 +962,6 @@
else
dev->flags &= ~IFF_POINTOPOINT;
- dev->iflink = p->link;
-
/* Precalculate GRE options length */
if (t->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
if (t->parms.o_flags&GRE_CSUM)
@@ -1267,6 +1265,8 @@
if (!dev->tstats)
return -ENOMEM;
+ dev->iflink = tunnel->parms.link;
+
return 0;
}
@@ -1282,7 +1282,6 @@
dev_hold(dev);
}
-
static struct inet6_protocol ip6gre_protocol __read_mostly = {
.handler = ip6gre_rcv,
.err_handler = ip6gre_err,
@@ -1458,6 +1457,8 @@
if (!dev->tstats)
return -ENOMEM;
+ dev->iflink = tunnel->parms.link;
+
return 0;
}
@@ -1549,6 +1550,15 @@
return 0;
}
+static void ip6gre_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+
+ if (dev != ign->fb_tunnel_dev)
+ unregister_netdevice_queue(dev, head);
+}
+
static size_t ip6gre_get_size(const struct net_device *dev)
{
return
@@ -1626,6 +1636,7 @@
.validate = ip6gre_tunnel_validate,
.newlink = ip6gre_newlink,
.changelink = ip6gre_changelink,
+ .dellink = ip6gre_dellink,
.get_size = ip6gre_get_size,
.fill_info = ip6gre_fill_info,
};
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 2bab2aa..774b09c 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -49,7 +49,7 @@
int ip6_rcv_finish(struct sk_buff *skb)
{
- if (sysctl_ip_early_demux && !skb_dst(skb)) {
+ if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
const struct inet6_protocol *ipprot;
ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d5d20cd..1ce7ea1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+ nexthop = rt6_nexthop((struct rt6_info *)dst);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -141,8 +141,8 @@
}
rcu_read_unlock_bh();
- IP6_INC_STATS_BH(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ IP6_INC_STATS(dev_net(dst->dev),
+ ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
@@ -150,7 +150,8 @@
static int ip6_finish_output(struct sk_buff *skb)
{
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
- dst_allfrag(skb_dst(skb)))
+ dst_allfrag(skb_dst(skb)) ||
+ (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
return ip6_fragment(skb, ip6_finish_output2);
else
return ip6_finish_output2(skb);
@@ -344,6 +345,24 @@
return dst_output(skb);
}
+static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
+{
+ if (skb->len <= mtu)
+ return false;
+
+ /* ipv6 conntrack defrag sets max_frag_size + local_df */
+ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
+ return true;
+
+ if (skb->local_df)
+ return false;
+
+ if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+ return false;
+
+ return true;
+}
+
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
@@ -466,8 +485,7 @@
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) ||
- (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) {
+ if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
@@ -522,6 +540,23 @@
skb_copy_secmark(to, from);
}
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+ static u32 ip6_idents_hashrnd __read_mostly;
+ static bool hashrnd_initialized = false;
+ u32 hash, id;
+
+ if (unlikely(!hashrnd_initialized)) {
+ hashrnd_initialized = true;
+ get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+ }
+ hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+ hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+ id = ip_idents_reserve(hash, 1);
+ fhdr->identification = htonl(id);
+}
+
int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct sk_buff *frag;
@@ -898,7 +933,7 @@
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
@@ -1039,6 +1074,8 @@
* udp datagram
*/
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) {
+ struct frag_hdr fhdr;
+
skb = sock_alloc_send_skb(sk,
hh_len + fragheaderlen + transhdrlen + 20,
(flags & MSG_DONTWAIT), &err);
@@ -1059,12 +1096,6 @@
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
- }
-
- err = skb_append_datato_frags(sk,skb, getfrag, from,
- (length - transhdrlen));
- if (!err) {
- struct frag_hdr fhdr;
/* Specify the length of each IPv6 datagram fragment.
* It has to be a multiple of 8.
@@ -1075,15 +1106,10 @@
ipv6_select_ident(&fhdr, rt);
skb_shinfo(skb)->ip6_frag_id = fhdr.identification;
__skb_queue_tail(&sk->sk_write_queue, skb);
-
- return 0;
}
- /* There is not enough support do UPD LSO,
- * so follow normal path
- */
- kfree_skb(skb);
- return err;
+ return skb_append_datato_frags(sk, skb, getfrag, from,
+ (length - transhdrlen));
}
static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
@@ -1098,23 +1124,24 @@
return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
}
-static void ip6_append_data_mtu(int *mtu,
+static void ip6_append_data_mtu(unsigned int *mtu,
int *maxfraglen,
unsigned int fragheaderlen,
struct sk_buff *skb,
- struct rt6_info *rt)
+ struct rt6_info *rt,
+ unsigned int orig_mtu)
{
if (!(rt->dst.flags & DST_XFRM_TUNNEL)) {
if (skb == NULL) {
/* first fragment, reserve header_len */
- *mtu = *mtu - rt->dst.header_len;
+ *mtu = orig_mtu - rt->dst.header_len;
} else {
/*
* this fragment is not first, the headers
* space is regarded as data space.
*/
- *mtu = dst_mtu(rt->dst.path);
+ *mtu = orig_mtu;
}
*maxfraglen = ((*mtu - fragheaderlen) & ~7)
+ fragheaderlen - sizeof(struct frag_hdr);
@@ -1131,11 +1158,10 @@
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
- unsigned int maxfraglen, fragheaderlen;
+ unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
- int mtu;
int copy;
int err;
int offset = 0;
@@ -1214,6 +1240,7 @@
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
+ orig_mtu = mtu;
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1248,27 +1275,28 @@
* --yoshfuji
*/
- cork->length += length;
- if (length > mtu) {
- int proto = sk->sk_protocol;
- if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
- ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
- return -EMSGSIZE;
- }
-
- if (proto == IPPROTO_UDP &&
- (rt->dst.dev->features & NETIF_F_UFO)) {
-
- err = ip6_ufo_append_data(sk, getfrag, from, length,
- hh_len, fragheaderlen,
- transhdrlen, mtu, flags, rt);
- if (err)
- goto error;
- return 0;
- }
+ if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
+ sk->sk_protocol == IPPROTO_RAW)) {
+ ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
+ return -EMSGSIZE;
}
- if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
+ skb = skb_peek_tail(&sk->sk_write_queue);
+ cork->length += length;
+ if (((length > mtu) ||
+ (skb && skb_has_frags(skb))) &&
+ (sk->sk_protocol == IPPROTO_UDP) &&
+ (rt->dst.dev->features & NETIF_F_UFO) &&
+ (sk->sk_type == SOCK_DGRAM)) {
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen,
+ transhdrlen, mtu, flags, rt);
+ if (err)
+ goto error;
+ return 0;
+ }
+
+ if (!skb)
goto alloc_new_skb;
while (length > 0) {
@@ -1292,7 +1320,8 @@
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
- fragheaderlen, skb, rt);
+ fragheaderlen, skb, rt,
+ orig_mtu);
skb_prev = skb;
@@ -1547,8 +1576,8 @@
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
- ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
+ ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
err = ip6_local_out(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e55866..14f46af 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -61,6 +61,7 @@
MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
MODULE_ALIAS_NETDEV("ip6tnl0");
#ifdef IP6_TNL_DEBUG
@@ -264,9 +265,6 @@
int err;
t = netdev_priv(dev);
- err = ip6_tnl_dev_init(dev);
- if (err < 0)
- goto out;
err = register_netdevice(dev);
if (err < 0)
@@ -1432,6 +1430,7 @@
static const struct net_device_ops ip6_tnl_netdev_ops = {
+ .ndo_init = ip6_tnl_dev_init,
.ndo_uninit = ip6_tnl_dev_uninit,
.ndo_start_xmit = ip6_tnl_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
@@ -1513,16 +1512,10 @@
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- int err = ip6_tnl_dev_init_gen(dev);
-
- if (err)
- return err;
t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);
- ip6_tnl_link_config(t);
-
rcu_assign_pointer(ip6n->tnls_wc[0], t);
return 0;
}
@@ -1531,7 +1524,7 @@
{
u8 proto;
- if (!data)
+ if (!data || !data[IFLA_IPTUN_PROTO])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
@@ -1617,6 +1610,15 @@
return ip6_tnl_update(t, &p);
}
+static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+
+ if (dev != ip6n->fb_tnl_dev)
+ unregister_netdevice_queue(dev, head);
+}
+
static size_t ip6_tnl_get_size(const struct net_device *dev)
{
return
@@ -1646,9 +1648,9 @@
if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr),
- &parm->raddr) ||
- nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
&parm->laddr) ||
+ nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
+ &parm->raddr) ||
nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
@@ -1681,6 +1683,7 @@
.validate = ip6_tnl_validate,
.newlink = ip6_tnl_newlink,
.changelink = ip6_tnl_changelink,
+ .dellink = ip6_tnl_dellink,
.get_size = ip6_tnl_get_size,
.fill_info = ip6_tnl_fill_info,
};
@@ -1732,6 +1735,7 @@
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
+ ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 241fb8a..2c84072 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -141,9 +141,12 @@
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr6_table **mrt)
{
- struct ip6mr_result res;
- struct fib_lookup_arg arg = { .result = &res, };
int err;
+ struct ip6mr_result res;
+ struct fib_lookup_arg arg = {
+ .result = &res,
+ .flags = FIB_LOOKUP_NOREF,
+ };
err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
flowi6_to_flowi(flp6), 0, &arg);
@@ -259,10 +262,12 @@
{
struct mr6_table *mrt, *next;
+ rtnl_lock();
list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
list_del(&mrt->list);
ip6mr_free_table(mrt);
}
+ rtnl_unlock();
fib_rules_unregister(net->ipv6.mr6_rules_ops);
}
#else
@@ -289,7 +294,10 @@
static void __net_exit ip6mr_rules_exit(struct net *net)
{
+ rtnl_lock();
ip6mr_free_table(net->ipv6.mrt6);
+ net->ipv6.mrt6 = NULL;
+ rtnl_unlock();
}
#endif
@@ -2343,13 +2351,14 @@
}
static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+ u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
+ int flags)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
if (nlh == NULL)
return -EMSGSIZE;
@@ -2417,7 +2426,7 @@
if (skb == NULL)
goto errout;
- err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2456,7 +2465,8 @@
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0)
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
@@ -2470,7 +2480,8 @@
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
- mfc, RTM_NEWROUTE) < 0) {
+ mfc, RTM_NEWROUTE,
+ NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index bfa6cc3..734aec0 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1343,8 +1343,9 @@
hdr->daddr = *daddr;
}
-static struct sk_buff *mld_newpack(struct net_device *dev, int size)
+static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size)
{
+ struct net_device *dev = idev->dev;
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.igmp_sk;
struct sk_buff *skb;
@@ -1369,7 +1370,7 @@
skb_reserve(skb, hlen);
- if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
+ if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) {
/* <draft-ietf-magma-mld-source-05.txt>:
* use unspecified address as the source address
* when a valid link-local address is not available.
@@ -1438,11 +1439,12 @@
dst_output);
out:
if (!err) {
- ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
- ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
- IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
- } else
- IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
+ ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
+ IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
+ } else {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+ }
rcu_read_unlock();
return;
@@ -1465,7 +1467,7 @@
struct mld2_grec *pgr;
if (!skb)
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(pmc->idev, dev->mtu);
if (!skb)
return NULL;
pgr = (struct mld2_grec *)skb_put(skb, sizeof(struct mld2_grec));
@@ -1485,7 +1487,8 @@
static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
int type, int gdeleted, int sdeleted)
{
- struct net_device *dev = pmc->idev->dev;
+ struct inet6_dev *idev = pmc->idev;
+ struct net_device *dev = idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
@@ -1514,7 +1517,7 @@
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(idev, dev->mtu);
}
}
first = 1;
@@ -1541,7 +1544,7 @@
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(dev, dev->mtu);
+ skb = mld_newpack(idev, dev->mtu);
first = 1;
scount = 0;
}
@@ -1596,8 +1599,8 @@
struct sk_buff *skb = NULL;
int type;
+ read_lock_bh(&idev->lock);
if (!pmc) {
- read_lock_bh(&idev->lock);
for (pmc=idev->mc_list; pmc; pmc=pmc->next) {
if (pmc->mca_flags & MAF_NOREPORT)
continue;
@@ -1609,7 +1612,6 @@
skb = add_grec(skb, pmc, type, 0, 0);
spin_unlock_bh(&pmc->mca_lock);
}
- read_unlock_bh(&idev->lock);
} else {
spin_lock_bh(&pmc->mca_lock);
if (pmc->mca_sfcount[MCAST_EXCLUDE])
@@ -1619,6 +1621,7 @@
skb = add_grec(skb, pmc, type, 0, 0);
spin_unlock_bh(&pmc->mca_lock);
}
+ read_unlock_bh(&idev->lock);
if (skb)
mld_sendpack(skb);
}
@@ -2156,7 +2159,7 @@
idev->mc_gq_running = 0;
mld_send_report(idev, NULL);
- __in6_dev_put(idev);
+ in6_dev_put(idev);
}
static void mld_ifc_timer_expire(unsigned long data)
@@ -2169,7 +2172,7 @@
if (idev->mc_ifc_count)
mld_ifc_start_timer(idev, idev->mc_maxdelay);
}
- __in6_dev_put(idev);
+ in6_dev_put(idev);
}
static void mld_ifc_event(struct inet6_dev *idev)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index ca4ffcc..05f3613 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -372,14 +372,11 @@
int tlen = dev->needed_tailroom;
struct sock *sk = dev_net(dev)->ipv6.ndisc_sk;
struct sk_buff *skb;
- int err;
- skb = sock_alloc_send_skb(sk,
- hlen + sizeof(struct ipv6hdr) + len + tlen,
- 1, &err);
+ skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC);
if (!skb) {
- ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n",
- __func__, err);
+ ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n",
+ __func__);
return NULL;
}
@@ -389,6 +386,11 @@
skb_reserve(skb, hlen + sizeof(struct ipv6hdr));
skb_reset_transport_header(skb);
+ /* Manually assign socket ownership as we avoid calling
+ * sock_alloc_send_pskb() to bypass wmem buffer limits
+ */
+ skb_set_owner_w(skb, sk);
+
return skb;
}
@@ -1191,7 +1193,14 @@
if (rt)
rt6_set_expires(rt, jiffies + (HZ * lifetime));
if (ra_msg->icmph.icmp6_hop_limit) {
- in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ /* Only set hop_limit on the interface if it is higher than
+ * the current hop_limit.
+ */
+ if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) {
+ in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
+ } else {
+ ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n");
+ }
if (rt)
dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1d..d38e6a8 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@
.daddr = iph->daddr,
.saddr = iph->saddr,
};
+ int err;
dst = ip6_route_output(net, skb->sk, &fl6);
- if (dst->error) {
+ err = dst->error;
+ if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
- return dst->error;
+ return err;
}
/* Drop old route. */
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 44400c2..89a4e4d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1236,8 +1236,10 @@
xt_free_table_info(oldinfo);
if (copy_to_user(counters_ptr, counters,
- sizeof(struct xt_counters) * num_counters) != 0)
- ret = -EFAULT;
+ sizeof(struct xt_counters) * num_counters) != 0) {
+ /* Silent error, can't fail, new table is already in place */
+ net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n");
+ }
vfree(counters);
xt_table_unlock(t);
return ret;
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index c9b6a6e..97cd750 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -172,63 +172,13 @@
return nf_conntrack_confirm(skb);
}
-static unsigned int __ipv6_conntrack_in(struct net *net,
- unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct sk_buff *reasm = skb->nfct_reasm;
- const struct nf_conn_help *help;
- struct nf_conn *ct;
- enum ip_conntrack_info ctinfo;
-
- /* This packet is fragmented and has reassembled packet. */
- if (reasm) {
- /* Reassembled packet isn't parsed yet ? */
- if (!reasm->nfct) {
- unsigned int ret;
-
- ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
- if (ret != NF_ACCEPT)
- return ret;
- }
-
- /* Conntrack helpers need the entire reassembled packet in the
- * POST_ROUTING hook. In case of unconfirmed connections NAT
- * might reassign a helper, so the entire packet is also
- * required.
- */
- ct = nf_ct_get(reasm, &ctinfo);
- if (ct != NULL && !nf_ct_is_untracked(ct)) {
- help = nfct_help(ct);
- if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
- nf_conntrack_get_reasm(reasm);
- NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
- (struct net_device *)in,
- (struct net_device *)out,
- okfn, NF_IP6_PRI_CONNTRACK + 1);
- return NF_DROP_ERR(-ECANCELED);
- }
- }
-
- nf_conntrack_get(reasm->nfct);
- skb->nfct = reasm->nfct;
- skb->nfctinfo = reasm->nfctinfo;
- return NF_ACCEPT;
- }
-
- return nf_conntrack_in(net, PF_INET6, hooknum, skb);
-}
-
static unsigned int ipv6_conntrack_in(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+ return nf_conntrack_in(dev_net(in), PF_INET6, hooknum, skb);
}
static unsigned int ipv6_conntrack_local(unsigned int hooknum,
@@ -242,7 +192,7 @@
net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
return NF_ACCEPT;
}
- return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+ return nf_conntrack_in(dev_net(out), PF_INET6, hooknum, skb);
}
static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index dffdc1a..253566a 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -621,31 +621,16 @@
return skb;
}
-void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
- struct net_device *in, struct net_device *out,
- int (*okfn)(struct sk_buff *))
+void nf_ct_frag6_consume_orig(struct sk_buff *skb)
{
struct sk_buff *s, *s2;
- unsigned int ret = 0;
for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
- nf_conntrack_put_reasm(s->nfct_reasm);
- nf_conntrack_get_reasm(skb);
- s->nfct_reasm = skb;
-
s2 = s->next;
s->next = NULL;
-
- if (ret != -ECANCELED)
- ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
- in, out, okfn,
- NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
- else
- kfree_skb(s);
-
+ consume_skb(s);
s = s2;
}
- nf_conntrack_put_reasm(skb);
}
static int nf_ct_net_init(struct net *net)
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index aacd121..581dd9e 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -75,8 +75,11 @@
if (reasm == skb)
return NF_ACCEPT;
- nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
- (struct net_device *)out, okfn);
+ nf_ct_frag6_consume_orig(reasm);
+
+ NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+ (struct net_device *) in, (struct net_device *) out,
+ okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
return NF_STOLEN;
}
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index c2e73e6..a5d4651 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -6,34 +6,6 @@
#include <net/ipv6.h>
#include <net/ip6_fib.h>
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
- static atomic_t ipv6_fragmentation_id;
- int old, new;
-
-#if IS_ENABLED(CONFIG_IPV6)
- if (rt && !(rt->dst.flags & DST_NOPEER)) {
- struct inet_peer *peer;
- struct net *net;
-
- net = dev_net(rt->dst.dev);
- peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
- if (peer) {
- fhdr->identification = htonl(inet_getid(peer, 0));
- inet_putpeer(peer);
- return;
- }
- }
-#endif
- do {
- old = atomic_read(&ipv6_fragmentation_id);
- new = old + 1;
- if (!new)
- new = 1;
- } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old);
- fhdr->identification = htonl(new);
-}
-EXPORT_SYMBOL(ipv6_select_ident);
int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
{
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index eedff8c..464b1c9 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -459,14 +459,11 @@
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- if (addr_len)
- *addr_len=sizeof(*sin6);
-
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
- return ipv6_recv_rxpmtu(sk, msg, len);
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -500,6 +497,7 @@
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
IP6CB(skb)->iif);
+ *addr_len = sizeof(*sin6);
}
sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 790d9f4..1aeb473 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -490,6 +490,7 @@
ipv6_hdr(head)->payload_len = htons(payload_len);
ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
IP6CB(head)->nhoff = nhoff;
+ IP6CB(head)->flags |= IP6SKB_FRAGMENTED;
/* Yes, and fold redundant checksum back. 8) */
if (head->ip_summed == CHECKSUM_COMPLETE)
@@ -524,6 +525,9 @@
struct net *net = dev_net(skb_dst(skb)->dev);
int evicted;
+ if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
+ goto fail_hdr;
+
IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS);
/* Jumbo payload inhibits frag. header */
@@ -544,6 +548,7 @@
ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMOKS);
IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb);
+ IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
return 1;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ad0aa6b..d94d224 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -65,6 +65,12 @@
#include <linux/sysctl.h>
#endif
+enum rt6_nud_state {
+ RT6_NUD_FAIL_HARD = -2,
+ RT6_NUD_FAIL_SOFT = -1,
+ RT6_NUD_SUCCEED = 1
+};
+
static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
const struct in6_addr *dest);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
@@ -78,6 +84,8 @@
static int ip6_pkt_discard(struct sk_buff *skb);
static int ip6_pkt_discard_out(struct sk_buff *skb);
+static int ip6_pkt_prohibit(struct sk_buff *skb);
+static int ip6_pkt_prohibit_out(struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
@@ -101,7 +109,7 @@
u32 *p = NULL;
if (!(rt->dst.flags & DST_HOST))
- return NULL;
+ return dst_cow_metrics_generic(dst, old);
peer = rt6_get_peer_create(rt);
if (peer) {
@@ -227,9 +235,6 @@
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-static int ip6_pkt_prohibit(struct sk_buff *skb);
-static int ip6_pkt_prohibit_out(struct sk_buff *skb);
-
static const struct rt6_info ip6_prohibit_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -467,6 +472,24 @@
}
#ifdef CONFIG_IPV6_ROUTER_PREF
+struct __rt6_probe_work {
+ struct work_struct work;
+ struct in6_addr target;
+ struct net_device *dev;
+};
+
+static void rt6_probe_deferred(struct work_struct *w)
+{
+ struct in6_addr mcaddr;
+ struct __rt6_probe_work *work =
+ container_of(w, struct __rt6_probe_work, work);
+
+ addrconf_addr_solict_mult(&work->target, &mcaddr);
+ ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+ dev_put(work->dev);
+ kfree(w);
+}
+
static void rt6_probe(struct rt6_info *rt)
{
struct neighbour *neigh;
@@ -490,17 +513,23 @@
if (!neigh ||
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
- struct in6_addr mcaddr;
- struct in6_addr *target;
+ struct __rt6_probe_work *work;
- if (neigh) {
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+
+ if (neigh && work)
neigh->updated = jiffies;
- write_unlock(&neigh->lock);
- }
- target = (struct in6_addr *)&rt->rt6i_gateway;
- addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
+ if (neigh)
+ write_unlock(&neigh->lock);
+
+ if (work) {
+ INIT_WORK(&work->work, rt6_probe_deferred);
+ work->target = rt->rt6i_gateway;
+ dev_hold(rt->dst.dev);
+ work->dev = rt->dst.dev;
+ schedule_work(&work->work);
+ }
} else {
out:
write_unlock(&neigh->lock);
@@ -527,26 +556,29 @@
return 0;
}
-static inline bool rt6_check_neigh(struct rt6_info *rt)
+static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
{
struct neighbour *neigh;
- bool ret = false;
+ enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
if (rt->rt6i_flags & RTF_NONEXTHOP ||
!(rt->rt6i_flags & RTF_GATEWAY))
- return true;
+ return RT6_NUD_SUCCEED;
rcu_read_lock_bh();
neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
if (neigh) {
read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
- ret = true;
+ ret = RT6_NUD_SUCCEED;
#ifdef CONFIG_IPV6_ROUTER_PREF
else if (!(neigh->nud_state & NUD_FAILED))
- ret = true;
+ ret = RT6_NUD_SUCCEED;
#endif
read_unlock(&neigh->lock);
+ } else {
+ ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
+ RT6_NUD_SUCCEED : RT6_NUD_FAIL_SOFT;
}
rcu_read_unlock_bh();
@@ -560,43 +592,52 @@
m = rt6_check_dev(rt, oif);
if (!m && (strict & RT6_LOOKUP_F_IFACE))
- return -1;
+ return RT6_NUD_FAIL_HARD;
#ifdef CONFIG_IPV6_ROUTER_PREF
m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
- if (!rt6_check_neigh(rt) && (strict & RT6_LOOKUP_F_REACHABLE))
- return -1;
+ if (strict & RT6_LOOKUP_F_REACHABLE) {
+ int n = rt6_check_neigh(rt);
+ if (n < 0)
+ return n;
+ }
return m;
}
static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
- int *mpri, struct rt6_info *match)
+ int *mpri, struct rt6_info *match,
+ bool *do_rr)
{
int m;
+ bool match_do_rr = false;
if (rt6_check_expired(rt))
goto out;
m = rt6_score_route(rt, oif, strict);
- if (m < 0)
+ if (m == RT6_NUD_FAIL_SOFT && !IS_ENABLED(CONFIG_IPV6_ROUTER_PREF)) {
+ match_do_rr = true;
+ m = 0; /* lowest valid score */
+ } else if (m < 0) {
goto out;
-
- if (m > *mpri) {
- if (strict & RT6_LOOKUP_F_REACHABLE)
- rt6_probe(match);
- *mpri = m;
- match = rt;
- } else if (strict & RT6_LOOKUP_F_REACHABLE) {
- rt6_probe(rt);
}
+ if (strict & RT6_LOOKUP_F_REACHABLE)
+ rt6_probe(rt);
+
+ if (m > *mpri) {
+ *do_rr = match_do_rr;
+ *mpri = m;
+ match = rt;
+ }
out:
return match;
}
static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
struct rt6_info *rr_head,
- u32 metric, int oif, int strict)
+ u32 metric, int oif, int strict,
+ bool *do_rr)
{
struct rt6_info *rt, *match;
int mpri = -1;
@@ -604,10 +645,10 @@
match = NULL;
for (rt = rr_head; rt && rt->rt6i_metric == metric;
rt = rt->dst.rt6_next)
- match = find_match(rt, oif, strict, &mpri, match);
+ match = find_match(rt, oif, strict, &mpri, match, do_rr);
for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
rt = rt->dst.rt6_next)
- match = find_match(rt, oif, strict, &mpri, match);
+ match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
}
@@ -616,15 +657,16 @@
{
struct rt6_info *match, *rt0;
struct net *net;
+ bool do_rr = false;
rt0 = fn->rr_ptr;
if (!rt0)
fn->rr_ptr = rt0 = fn->leaf;
- match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);
+ match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict,
+ &do_rr);
- if (!match &&
- (strict & RT6_LOOKUP_F_REACHABLE)) {
+ if (do_rr) {
struct rt6_info *next = rt0->dst.rt6_next;
/* no entries matched; do round-robin */
@@ -685,8 +727,11 @@
prefix = &prefix_buf;
}
- rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
- dev->ifindex);
+ if (rinfo->prefix_len == 0)
+ rt = rt6_get_dflt_router(gwaddr, dev);
+ else
+ rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
+ gwaddr, dev->ifindex);
if (rt && !lifetime) {
ip6_del_rt(rt);
@@ -829,7 +874,6 @@
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
- rt->rt6i_gateway = *daddr;
}
rt->rt6i_flags |= RTF_CACHE;
@@ -1042,10 +1086,13 @@
if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
return NULL;
- if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
- return dst;
+ if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie))
+ return NULL;
- return NULL;
+ if (rt6_check_expired(rt))
+ return NULL;
+
+ return dst;
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -1074,10 +1121,13 @@
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
- if (rt->rt6i_flags & RTF_CACHE)
- rt6_update_expires(rt, 0);
- else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
+ if (rt->rt6i_flags & RTF_CACHE) {
+ dst_hold(&rt->dst);
+ if (ip6_del_rt(rt))
+ dst_free(&rt->dst);
+ } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) {
rt->rt6i_node->fn_sernum = -1;
+ }
}
}
@@ -1091,12 +1141,9 @@
struct net *net = dev_net(dst->dev);
rt6->rt6i_flags |= RTF_MODIFIED;
- if (mtu < IPV6_MIN_MTU) {
- u32 features = dst_metric(dst, RTAX_FEATURES);
+ if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(dst, RTAX_FEATURES, features);
- }
+
dst_metric_set(dst, RTAX_MTU, mtu);
rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
@@ -1186,7 +1233,7 @@
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
- return mtu;
+ goto out;
mtu = IPV6_MIN_MTU;
@@ -1196,7 +1243,8 @@
mtu = idev->cnf.mtu6;
rcu_read_unlock();
- return mtu;
+out:
+ return min_t(unsigned int, mtu, IP6_MAX_MTU);
}
static struct dst_entry *icmp6_dst_gc_list;
@@ -1223,6 +1271,7 @@
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
atomic_set(&rt->dst.__refcnt, 1);
+ rt->rt6i_gateway = fl6->daddr;
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
rt->rt6i_idev = idev;
@@ -1377,7 +1426,7 @@
if (!table)
goto out;
- rt = ip6_dst_alloc(net, NULL, DST_NOCOUNT, table);
+ rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
if (!rt) {
err = -ENOMEM;
@@ -1446,21 +1495,24 @@
goto out;
}
}
- rt->dst.output = ip6_pkt_discard_out;
- rt->dst.input = ip6_pkt_discard;
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
switch (cfg->fc_type) {
case RTN_BLACKHOLE:
rt->dst.error = -EINVAL;
+ rt->dst.output = dst_discard;
+ rt->dst.input = dst_discard;
break;
case RTN_PROHIBIT:
rt->dst.error = -EACCES;
+ rt->dst.output = ip6_pkt_prohibit_out;
+ rt->dst.input = ip6_pkt_prohibit;
break;
case RTN_THROW:
- rt->dst.error = -EAGAIN;
- break;
default:
- rt->dst.error = -ENETUNREACH;
+ rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
+ : -ENETUNREACH;
+ rt->dst.output = ip6_pkt_discard_out;
+ rt->dst.input = ip6_pkt_discard;
break;
}
goto install_route;
@@ -1779,11 +1831,12 @@
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
+ if (ort->rt6i_flags & RTF_GATEWAY)
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ else
+ rt->rt6i_gateway = *dest;
rt->rt6i_flags = ort->rt6i_flags;
- if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
- (RTF_DEFAULT | RTF_ADDRCONF))
- rt6_set_from(rt, ort);
+ rt6_set_from(rt, ort);
rt->rt6i_metric = 0;
#ifdef CONFIG_IPV6_SUBTREES
@@ -2022,8 +2075,6 @@
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}
-#ifdef CONFIG_IPV6_MULTIPLE_TABLES
-
static int ip6_pkt_prohibit(struct sk_buff *skb)
{
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
@@ -2035,8 +2086,6 @@
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}
-#endif
-
/*
* Allocate a dst for local (unicast / anycast) address.
*/
@@ -2046,12 +2095,10 @@
bool anycast)
{
struct net *net = dev_net(idev->dev);
- struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL);
-
- if (!rt) {
- net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n");
+ struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
+ DST_NOCOUNT, NULL);
+ if (!rt)
return ERR_PTR(-ENOMEM);
- }
in6_dev_hold(idev);
@@ -2066,6 +2113,7 @@
else
rt->rt6i_flags |= RTF_LOCAL;
+ rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3353634..4ddf67c 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -101,19 +101,19 @@
for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) {
if (remote == t->parms.iph.daddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) {
if (local == t->parms.iph.saddr &&
- (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
+ (!dev || !t->parms.link || dev->ifindex == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
@@ -530,12 +530,12 @@
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
- t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+ t->parms.link, 0, IPPROTO_IPV6, 0);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
- ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+ ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
IPPROTO_IPV6, 0);
err = 0;
goto out;
@@ -566,6 +566,70 @@
return false;
}
+/* Checks if an address matches an address on the tunnel interface.
+ * Used to detect the NAT of proto 41 packets and let them pass spoofing test.
+ * Long story:
+ * This function is called after we considered the packet as spoofed
+ * in is_spoofed_6rd.
+ * We may have a router that is doing NAT for proto 41 packets
+ * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb
+ * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd
+ * function will return true, dropping the packet.
+ * But, we can still check if is spoofed against the IP
+ * addresses associated with the interface.
+ */
+static bool only_dnatted(const struct ip_tunnel *tunnel,
+ const struct in6_addr *v6dst)
+{
+ int prefix_len;
+
+#ifdef CONFIG_IPV6_SIT_6RD
+ prefix_len = tunnel->ip6rd.prefixlen + 32
+ - tunnel->ip6rd.relay_prefixlen;
+#else
+ prefix_len = 48;
+#endif
+ return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev);
+}
+
+/* Returns true if a packet is spoofed */
+static bool packet_is_spoofed(struct sk_buff *skb,
+ const struct iphdr *iph,
+ struct ip_tunnel *tunnel)
+{
+ const struct ipv6hdr *ipv6h;
+
+ if (tunnel->dev->priv_flags & IFF_ISATAP) {
+ if (!isatap_chksrc(skb, iph, tunnel))
+ return true;
+
+ return false;
+ }
+
+ if (tunnel->dev->flags & IFF_POINTOPOINT)
+ return false;
+
+ ipv6h = ipv6_hdr(skb);
+
+ if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) {
+ net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+ &iph->saddr, &ipv6h->saddr,
+ &iph->daddr, &ipv6h->daddr);
+ return true;
+ }
+
+ if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr)))
+ return false;
+
+ if (only_dnatted(tunnel, &ipv6h->daddr))
+ return false;
+
+ net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n",
+ &iph->saddr, &ipv6h->saddr,
+ &iph->daddr, &ipv6h->daddr);
+ return true;
+}
+
static int ipip6_rcv(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
@@ -584,19 +648,9 @@
skb->protocol = htons(ETH_P_IPV6);
skb->pkt_type = PACKET_HOST;
- if (tunnel->dev->priv_flags & IFF_ISATAP) {
- if (!isatap_chksrc(skb, iph, tunnel)) {
- tunnel->dev->stats.rx_errors++;
- goto out;
- }
- } else {
- if (is_spoofed_6rd(tunnel, iph->saddr,
- &ipv6_hdr(skb)->saddr) ||
- is_spoofed_6rd(tunnel, iph->daddr,
- &ipv6_hdr(skb)->daddr)) {
- tunnel->dev->stats.rx_errors++;
- goto out;
- }
+ if (packet_is_spoofed(skb, iph, tunnel)) {
+ tunnel->dev->stats.rx_errors++;
+ goto out;
}
__skb_tunnel_rx(skb, tunnel->dev);
@@ -713,7 +767,7 @@
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (neigh == NULL) {
- net_dbg_ratelimited("sit: nexthop == NULL\n");
+ net_dbg_ratelimited("nexthop == NULL\n");
goto tx_error;
}
@@ -742,7 +796,7 @@
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (neigh == NULL) {
- net_dbg_ratelimited("sit: nexthop == NULL\n");
+ net_dbg_ratelimited("nexthop == NULL\n");
goto tx_error;
}
@@ -865,7 +919,7 @@
iph->ttl = iph6->hop_limit;
skb->ip_summed = CHECKSUM_NONE;
- ip_select_ident(iph, skb_dst(skb), NULL);
+ ip_select_ident(skb, NULL);
iptunnel_xmit(skb, dev);
return NETDEV_TX_OK;
@@ -1453,6 +1507,15 @@
#endif
};
+static void ipip6_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct sit_net *sitn = net_generic(net, sit_net_id);
+
+ if (dev != sitn->fb_tunnel_dev)
+ unregister_netdevice_queue(dev, head);
+}
+
static struct rtnl_link_ops sit_link_ops __read_mostly = {
.kind = "sit",
.maxtype = IFLA_IPTUN_MAX,
@@ -1463,6 +1526,7 @@
.changelink = ipip6_changelink,
.get_size = ipip6_get_size,
.fill_info = ipip6_fill_info,
+ .dellink = ipip6_dellink,
};
static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1507,6 +1571,7 @@
goto err_alloc_dev;
}
dev_net_set(sitn->fb_tunnel_dev, net);
+ sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops;
err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
if (err)
@@ -1589,4 +1654,5 @@
module_init(sit_init);
module_exit(sit_cleanup);
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0a17ed9..4659b8a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1426,7 +1426,7 @@
if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
if (np->rxopt.bits.rxtclass)
- np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+ np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb)) {
skb_set_owner_r(opt_skb, sk);
opt_skb = xchg(&np->pktoptions, opt_skb);
@@ -1616,7 +1616,7 @@
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk->sk_state != TCP_TIME_WAIT) {
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst = ACCESS_ONCE(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
@@ -1651,6 +1651,7 @@
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
+ .mtu_reduced = tcp_v6_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -1682,6 +1683,7 @@
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
#endif
+ .mtu_reduced = tcp_v4_mtu_reduced,
};
#ifdef CONFIG_TCP_MD5SIG
@@ -1919,7 +1921,6 @@
.sendpage = tcp_sendpage,
.backlog_rcv = tcp_v6_do_rcv,
.release_cb = tcp_release_cb,
- .mtu_reduced = tcp_v6_mtu_reduced,
.hash = tcp_v6_hash,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 42923b1..6b298dc 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -373,14 +373,11 @@
int is_udp4;
bool slow;
- if (addr_len)
- *addr_len = sizeof(struct sockaddr_in6);
-
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
- return ipv6_recv_rxpmtu(sk, msg, len);
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -461,7 +458,7 @@
ipv6_iface_scope_id(&sin6->sin6_addr,
IP6CB(skb)->iif);
}
-
+ *addr_len = sizeof(*sin6);
}
if (is_udp4) {
if (inet->cmsg_flags)
@@ -955,11 +952,16 @@
struct udphdr *uh;
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
- struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+ struct flowi6 *fl6;
int err = 0;
int is_udplite = IS_UDPLITE(sk);
__wsum csum = 0;
+ if (up->pending == AF_INET)
+ return udp_push_pending_frames(sk);
+
+ fl6 = &inet->cork.fl.u.ip6;
+
/* Grab the skbuff where UDP header space exists. */
if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
goto out;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index d3cfaf9..2f65b02 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -85,7 +85,7 @@
/* Check if there is enough headroom to insert fragment header. */
tnl_hlen = skb_tnl_header_len(skb);
- if (skb_headroom(skb) < (tnl_hlen + frag_hdr_sz)) {
+ if (skb_mac_header(skb) < skb->head + tnl_hlen + frag_hdr_sz) {
if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz))
goto out;
}
@@ -108,7 +108,7 @@
fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
fptr->nexthdr = nexthdr;
fptr->reserved = 0;
- ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb));
+ fptr->identification = skb_shinfo(skb)->ip6_frag_id;
/* Fragment the skb. ipv6 header and the remaining fields of the
* fragment header are updated in ipv6_gso_segment()
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index f547a47..2665bf4 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1778,6 +1778,7 @@
struct ipxhdr *ipx = NULL;
struct sk_buff *skb;
int copied, rc;
+ bool locked = true;
lock_sock(sk);
/* put the autobinding in */
@@ -1804,6 +1805,8 @@
if (sock_flag(sk, SOCK_ZAPPED))
goto out;
+ release_sock(sk);
+ locked = false;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &rc);
if (!skb)
@@ -1823,8 +1826,6 @@
if (skb->tstamp.tv64)
sk->sk_stamp = skb->tstamp;
- msg->msg_namelen = sizeof(*sipx);
-
if (sipx) {
sipx->sipx_family = AF_IPX;
sipx->sipx_port = ipx->ipx_source.sock;
@@ -1832,13 +1833,15 @@
sipx->sipx_network = IPX_SKB_CB(skb)->ipx_source_net;
sipx->sipx_type = ipx->ipx_type;
sipx->sipx_zero = 0;
+ msg->msg_namelen = sizeof(*sipx);
}
rc = copied;
out_free:
skb_free_datagram(sk, skb);
out:
- release_sock(sk);
+ if (locked)
+ release_sock(sk);
return rc;
}
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 0578d4f..a5e62ef5 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1385,8 +1385,6 @@
IRDA_DEBUG(4, "%s()\n", __func__);
- msg->msg_namelen = 0;
-
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
if (!skb)
@@ -1451,8 +1449,6 @@
target = sock_rcvlowat(sk, flags & MSG_WAITALL, size);
timeo = sock_rcvtimeo(sk, noblock);
- msg->msg_namelen = 0;
-
do {
int chunk;
struct sk_buff *skb = skb_dequeue(&sk->sk_receive_queue);
diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c
index 41ac7938..2ee29ed 100644
--- a/net/irda/ircomm/ircomm_tty.c
+++ b/net/irda/ircomm/ircomm_tty.c
@@ -820,7 +820,9 @@
orig_jiffies = jiffies;
/* Set poll time to 200 ms */
- poll_time = IRDA_MIN(timeout, msecs_to_jiffies(200));
+ poll_time = msecs_to_jiffies(200);
+ if (timeout)
+ poll_time = min_t(unsigned long, timeout, poll_time);
spin_lock_irqsave(&self->spinlock, flags);
while (self->tx_skb && self->tx_skb->len) {
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index ae69165..215e9b0 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1324,8 +1324,6 @@
int err = 0;
u32 offset;
- msg->msg_namelen = 0;
-
if ((sk->sk_state == IUCV_DISCONN) &&
skb_queue_empty(&iucv->backlog_skb_q) &&
skb_queue_empty(&sk->sk_receive_queue) &&
@@ -1831,7 +1829,7 @@
spin_lock_irqsave(&list->lock, flags);
while (list_skb != (struct sk_buff *)list) {
- if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+ if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
this = list_skb;
break;
}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 9da8620..66f51c5 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2081,6 +2081,7 @@
pol->sadb_x_policy_type = IPSEC_POLICY_NONE;
}
pol->sadb_x_policy_dir = dir+1;
+ pol->sadb_x_policy_reserved = 0;
pol->sadb_x_policy_id = xp->index;
pol->sadb_x_policy_priority = xp->priority;
@@ -3137,7 +3138,9 @@
pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY;
pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC;
pol->sadb_x_policy_dir = XFRM_POLICY_OUT + 1;
+ pol->sadb_x_policy_reserved = 0;
pol->sadb_x_policy_id = xp->index;
+ pol->sadb_x_policy_priority = xp->priority;
/* Set sadb_comb's. */
if (x->id.proto == IPPROTO_AH)
@@ -3525,6 +3528,7 @@
pol->sadb_x_policy_exttype = SADB_X_EXT_POLICY;
pol->sadb_x_policy_type = IPSEC_POLICY_IPSEC;
pol->sadb_x_policy_dir = dir + 1;
+ pol->sadb_x_policy_reserved = 0;
pol->sadb_x_policy_id = 0;
pol->sadb_x_policy_priority = 0;
@@ -3619,7 +3623,6 @@
if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT))
goto out;
- msg->msg_namelen = 0;
skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto out;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6984c3a..8c27de2 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -115,6 +115,11 @@
static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
+static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
+{
+ return sk->sk_user_data;
+}
+
static inline struct l2tp_net *l2tp_pernet(struct net *net)
{
BUG_ON(!net);
@@ -507,7 +512,7 @@
return 0;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6) {
+ if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
if (!uh->check) {
LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
return 1;
@@ -1071,7 +1076,7 @@
/* Queue the packet to IP for output */
skb->local_df = 1;
#if IS_ENABLED(CONFIG_IPV6)
- if (skb->sk->sk_family == PF_INET6)
+ if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
error = inet6_csk_xmit(skb, NULL);
else
#endif
@@ -1198,7 +1203,7 @@
/* Calculate UDP checksum if configured to do so */
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
l2tp_xmit_ipv6_csum(sk, skb, udp_len);
else
#endif
@@ -1247,10 +1252,9 @@
*/
static void l2tp_tunnel_destruct(struct sock *sk)
{
- struct l2tp_tunnel *tunnel;
+ struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
struct l2tp_net *pn;
- tunnel = sk->sk_user_data;
if (tunnel == NULL)
goto end;
@@ -1618,7 +1622,7 @@
}
/* Check if this socket has already been prepped */
- tunnel = (struct l2tp_tunnel *)sk->sk_user_data;
+ tunnel = l2tp_tunnel(sk);
if (tunnel != NULL) {
/* This socket has already been prepped */
err = -EBUSY;
@@ -1647,6 +1651,24 @@
if (cfg != NULL)
tunnel->debug = cfg->debug;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == PF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (ipv6_addr_v4mapped(&np->saddr) &&
+ ipv6_addr_v4mapped(&np->daddr)) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ tunnel->v4mapped = true;
+ inet->inet_saddr = np->saddr.s6_addr32[3];
+ inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
+ inet->inet_daddr = np->daddr.s6_addr32[3];
+ } else {
+ tunnel->v4mapped = false;
+ }
+ }
+#endif
+
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
tunnel->encap = encap;
if (encap == L2TP_ENCAPTYPE_UDP) {
@@ -1655,7 +1677,7 @@
udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
udpv6_encap_enable();
else
#endif
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 485a490..2f89d43 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -189,6 +189,9 @@
struct sock *sock; /* Parent socket */
int fd; /* Parent fd, if tunnel socket
* was created by userspace */
+#if IS_ENABLED(CONFIG_IPV6)
+ bool v4mapped;
+#endif
struct work_struct del_work;
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 571db8d..da1a1ce 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -518,9 +518,6 @@
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
@@ -543,6 +540,7 @@
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index b8a6039..e6e8408 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -665,7 +665,7 @@
*addr_len = sizeof(*lsa);
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 8dec687..c3ae241 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -197,8 +197,6 @@
if (sk->sk_state & PPPOX_BOUND)
goto end;
- msg->msg_namelen = 0;
-
err = 0;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &err);
@@ -353,7 +351,9 @@
goto error_put_sess_tun;
}
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(ps->tunnel_sock);
sock_put(sk);
@@ -422,7 +422,9 @@
skb->data[0] = ppph[0];
skb->data[1] = ppph[1];
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(sk_tun);
sock_put(sk);
@@ -752,9 +754,10 @@
session->deref = pppol2tp_session_sock_put;
/* If PMTU discovery was enabled, use the MTU that was discovered */
- dst = sk_dst_get(sk);
+ dst = sk_dst_get(tunnel->sock);
if (dst != NULL) {
- u32 pmtu = dst_mtu(__sk_dst_get(sk));
+ u32 pmtu = dst_mtu(dst);
+
if (pmtu != 0)
session->mtu = session->mru = pmtu -
PPPOL2TP_HEADER_OVERHEAD;
@@ -1363,7 +1366,7 @@
int err;
if (level != SOL_PPPOL2TP)
- return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+ return -EINVAL;
if (optlen < sizeof(int))
return -EINVAL;
@@ -1489,7 +1492,7 @@
struct pppol2tp_session *ps;
if (level != SOL_PPPOL2TP)
- return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+ return -EINVAL;
if (get_user(len, optlen))
return -EFAULT;
@@ -1793,7 +1796,8 @@
static const struct pppox_proto pppol2tp_proto = {
.create = pppol2tp_create,
- .ioctl = pppol2tp_ioctl
+ .ioctl = pppol2tp_ioctl,
+ .owner = THIS_MODULE,
};
#ifdef CONFIG_L2TP_V3
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 48aaa89..c3ee805 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -715,13 +715,11 @@
unsigned long cpu_flags;
size_t copied = 0;
u32 peek_seq = 0;
- u32 *seq;
+ u32 *seq, skb_len;
unsigned long used;
int target; /* Read at least this many bytes */
long timeo;
- msg->msg_namelen = 0;
-
lock_sock(sk);
copied = -ENOTCONN;
if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN))
@@ -814,6 +812,7 @@
}
continue;
found_ok_skb:
+ skb_len = skb->len;
/* Ok so how much can we use? */
used = skb->len - offset;
if (len < used)
@@ -846,7 +845,7 @@
}
/* Partial read */
- if (used + offset < skb->len)
+ if (used + offset < skb_len)
continue;
} while (len > 0);
diff --git a/net/llc/sysctl_net_llc.c b/net/llc/sysctl_net_llc.c
index 612a5dd..799bafc 100644
--- a/net/llc/sysctl_net_llc.c
+++ b/net/llc/sysctl_net_llc.c
@@ -18,28 +18,28 @@
{
.procname = "ack",
.data = &sysctl_llc2_ack_timeout,
- .maxlen = sizeof(long),
+ .maxlen = sizeof(sysctl_llc2_ack_timeout),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "busy",
.data = &sysctl_llc2_busy_timeout,
- .maxlen = sizeof(long),
+ .maxlen = sizeof(sysctl_llc2_busy_timeout),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "p",
.data = &sysctl_llc2_p_timeout,
- .maxlen = sizeof(long),
+ .maxlen = sizeof(sysctl_llc2_p_timeout),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "rej",
.data = &sysctl_llc2_rej_timeout,
- .maxlen = sizeof(long),
+ .maxlen = sizeof(sysctl_llc2_rej_timeout),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 4fdb306e..e922bf3 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -652,6 +652,8 @@
if (sta->sdata->dev != dev)
continue;
+ sinfo.filled = 0;
+ sta_set_sinfo(sta, &sinfo);
i = 0;
ADD_STA_STATS(sta);
}
@@ -973,8 +975,10 @@
IEEE80211_P2P_OPPPS_ENABLE_BIT;
err = ieee80211_assign_beacon(sdata, ¶ms->beacon);
- if (err < 0)
+ if (err < 0) {
+ ieee80211_vif_release_channel(sdata);
return err;
+ }
changed |= err;
err = drv_start_ap(sdata->local, sdata);
@@ -983,6 +987,7 @@
if (old)
kfree_rcu(old, rcu_head);
RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
+ ieee80211_vif_release_channel(sdata);
return err;
}
@@ -2354,8 +2359,7 @@
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
- if (sdata->vif.type != NL80211_IFTYPE_STATION &&
- sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
+ if (sdata->vif.type != NL80211_IFTYPE_STATION)
return -EOPNOTSUPP;
if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS))
@@ -2475,6 +2479,24 @@
INIT_DELAYED_WORK(&roc->work, ieee80211_sw_roc_work);
INIT_LIST_HEAD(&roc->dependents);
+ /*
+ * cookie is either the roc cookie (for normal roc)
+ * or the SKB (for mgmt TX)
+ */
+ if (!txskb) {
+ /* local->mtx protects this */
+ local->roc_cookie_counter++;
+ roc->cookie = local->roc_cookie_counter;
+ /* wow, you wrapped 64 bits ... more likely a bug */
+ if (WARN_ON(roc->cookie == 0)) {
+ roc->cookie = 1;
+ local->roc_cookie_counter++;
+ }
+ *cookie = roc->cookie;
+ } else {
+ *cookie = (unsigned long)txskb;
+ }
+
/* if there's one pending or we're scanning, queue this one */
if (!list_empty(&local->roc_list) ||
local->scanning || local->radar_detect_enabled)
@@ -2609,24 +2631,6 @@
if (!queued)
list_add_tail(&roc->list, &local->roc_list);
- /*
- * cookie is either the roc cookie (for normal roc)
- * or the SKB (for mgmt TX)
- */
- if (!txskb) {
- /* local->mtx protects this */
- local->roc_cookie_counter++;
- roc->cookie = local->roc_cookie_counter;
- /* wow, you wrapped 64 bits ... more likely a bug */
- if (WARN_ON(roc->cookie == 0)) {
- roc->cookie = 1;
- local->roc_cookie_counter++;
- }
- *cookie = roc->cookie;
- } else {
- *cookie = (unsigned long)txskb;
- }
-
return 0;
}
@@ -3313,7 +3317,7 @@
return -EINVAL;
}
band = chanctx_conf->def.chan->band;
- sta = sta_info_get(sdata, peer);
+ sta = sta_info_get_bss(sdata, peer);
if (sta) {
qos = test_sta_flag(sta, WLAN_STA_WME);
} else {
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 14abcf4..2d5b4f6 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@
ssize_t ret = -EINVAL;
read_lock(&dev_base_lock);
- if (sdata->dev->reg_state == NETREG_REGISTERED)
- ret = (*format)(sdata, buf, sizeof(buf));
+ ret = (*format)(sdata, buf, sizeof(buf));
read_unlock(&dev_base_lock);
if (ret >= 0)
@@ -62,8 +61,7 @@
ret = -ENODEV;
rtnl_lock();
- if (sdata->dev->reg_state == NETREG_REGISTERED)
- ret = (*write)(sdata, buf, count);
+ ret = (*write)(sdata, buf, count);
rtnl_unlock();
return ret;
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 170f9a7..3052672 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -1166,6 +1166,7 @@
clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state);
ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED |
BSS_CHANGED_IBSS);
+ ieee80211_vif_release_channel(sdata);
synchronize_rcu();
kfree(presp);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9ca8e32..9f0ea9d 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -60,13 +60,24 @@
#define IEEE80211_UNSET_POWER_LEVEL INT_MIN
/*
- * Some APs experience problems when working with U-APSD. Decrease the
- * probability of that happening by using legacy mode for all ACs but VO.
- * The AP that caused us trouble was a Cisco 4410N. It ignores our
- * setting, and always treats non-VO ACs as legacy.
+ * Some APs experience problems when working with U-APSD. Decreasing the
+ * probability of that happening by using legacy mode for all ACs but VO isn't
+ * enough.
+ *
+ * Cisco 4410N originally forced us to enable VO by default only because it
+ * treated non-VO ACs as legacy.
+ *
+ * However some APs (notably Netgear R7000) silently reclassify packets to
+ * different ACs. Since u-APSD ACs require trigger frames for frame retrieval
+ * clients would never see some frames (e.g. ARP responses) or would fetch them
+ * accidentally after a long time.
+ *
+ * It makes little sense to enable u-APSD queues by default because it needs
+ * userspace applications to be aware of it to actually take advantage of the
+ * possible additional powersavings. Implicitly depending on driver autotrigger
+ * frame support doesn't make much sense.
*/
-#define IEEE80211_DEFAULT_UAPSD_QUEUES \
- IEEE80211_WMM_IE_STA_QOSINFO_AC_VO
+#define IEEE80211_DEFAULT_UAPSD_QUEUES 0
#define IEEE80211_DEFAULT_MAX_SP_LEN \
IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL
@@ -311,6 +322,7 @@
bool started, abort, hw_begun, notified;
bool to_be_freed;
+ bool on_channel;
unsigned long hw_start_time;
@@ -842,6 +854,8 @@
* that the scan completed.
* @SCAN_ABORTED: Set for our scan work function when the driver reported
* a scan complete for an aborted scan.
+ * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being
+ * cancelled.
*/
enum {
SCAN_SW_SCANNING,
@@ -849,6 +863,7 @@
SCAN_ONCHANNEL_SCANNING,
SCAN_COMPLETED,
SCAN_ABORTED,
+ SCAN_HW_CANCELLED,
};
/**
@@ -1267,6 +1282,7 @@
void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
__le16 fc, bool acked);
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
/* IBSS code */
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 98d20c0..2c64ab2 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1726,6 +1726,15 @@
if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
dev_close(sdata->dev);
+ /*
+ * Close all AP_VLAN interfaces first, as otherwise they
+ * might be closed while the AP interface they belong to
+ * is closed, causing unregister_netdevice_many() to crash.
+ */
+ list_for_each_entry(sdata, &local->interfaces, list)
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ dev_close(sdata->dev);
+
mutex_lock(&local->iflist_mtx);
list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
list_del(&sdata->list);
@@ -1737,7 +1746,6 @@
}
mutex_unlock(&local->iflist_mtx);
unregister_netdevice_many(&unreg_list);
- list_del(&unreg_list);
list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
list_del(&sdata->list);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 67059b8..635d097 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -607,7 +607,7 @@
int i;
mutex_lock(&local->key_mtx);
- for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
+ for (i = 0; i < ARRAY_SIZE(sta->gtk); i++) {
key = key_mtx_dereference(local, sta->gtk[i]);
if (!key)
continue;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 8a7bfc4..6658c58 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -157,6 +157,8 @@
list_for_each_entry_rcu(sdata, &local->interfaces, list) {
if (!rcu_access_pointer(sdata->vif.chanctx_conf))
continue;
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ continue;
power = min(power, sdata->vif.bss_conf.txpower);
}
rcu_read_unlock();
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 3b7bfc0..ddda201 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -36,6 +36,7 @@
sdata->vif.addr);
nullfunc->frame_control = fc;
nullfunc->duration_id = 0;
+ nullfunc->seq_ctrl = 0;
/* no address resolution for this frame -> set addr 1 immediately */
memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
memset(skb_put(skb, 2), 0, 2); /* append QoS control field */
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 741448b..e606e4a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -31,10 +31,12 @@
#include "led.h"
#define IEEE80211_AUTH_TIMEOUT (HZ / 5)
+#define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10)
#define IEEE80211_AUTH_MAX_TRIES 3
#define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5)
#define IEEE80211_ASSOC_TIMEOUT (HZ / 5)
+#define IEEE80211_ASSOC_TIMEOUT_LONG (HZ / 2)
#define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10)
#define IEEE80211_ASSOC_MAX_TRIES 3
@@ -237,8 +239,9 @@
struct ieee80211_channel *channel,
const struct ieee80211_ht_operation *ht_oper,
const struct ieee80211_vht_operation *vht_oper,
- struct cfg80211_chan_def *chandef, bool verbose)
+ struct cfg80211_chan_def *chandef, bool tracking)
{
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
struct cfg80211_chan_def vht_chandef;
u32 ht_cfreq, ret;
@@ -257,7 +260,7 @@
ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan,
channel->band);
/* check that channel matches the right operating channel */
- if (channel->center_freq != ht_cfreq) {
+ if (!tracking && channel->center_freq != ht_cfreq) {
/*
* It's possible that some APs are confused here;
* Netgear WNDR3700 sometimes reports 4 higher than
@@ -265,11 +268,10 @@
* since we look at probe response/beacon data here
* it should be OK.
*/
- if (verbose)
- sdata_info(sdata,
- "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
- channel->center_freq, ht_cfreq,
- ht_oper->primary_chan, channel->band);
+ sdata_info(sdata,
+ "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n",
+ channel->center_freq, ht_cfreq,
+ ht_oper->primary_chan, channel->band);
ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT;
goto out;
}
@@ -308,6 +310,7 @@
switch (vht_oper->chan_width) {
case IEEE80211_VHT_CHANWIDTH_USE_HT:
vht_chandef.width = chandef->width;
+ vht_chandef.center_freq1 = chandef->center_freq1;
break;
case IEEE80211_VHT_CHANWIDTH_80MHZ:
vht_chandef.width = NL80211_CHAN_WIDTH_80;
@@ -323,7 +326,7 @@
channel->band);
break;
default:
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT operation IE has invalid channel width (%d), disable VHT\n",
vht_oper->chan_width);
@@ -332,7 +335,7 @@
}
if (!cfg80211_chandef_valid(&vht_chandef)) {
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT information is invalid, disable VHT\n");
ret = IEEE80211_STA_DISABLE_VHT;
@@ -345,7 +348,7 @@
}
if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) {
- if (verbose)
+ if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
sdata_info(sdata,
"AP VHT information doesn't match HT, disable VHT\n");
ret = IEEE80211_STA_DISABLE_VHT;
@@ -357,22 +360,53 @@
ret = 0;
out:
+ /*
+ * When tracking the current AP, don't do any further checks if the
+ * new chandef is identical to the one we're currently using for the
+ * connection. This keeps us from playing ping-pong with regulatory,
+ * without it the following can happen (for example):
+ * - connect to an AP with 80 MHz, world regdom allows 80 MHz
+ * - AP advertises regdom US
+ * - CRDA loads regdom US with 80 MHz prohibited (old database)
+ * - the code below detects an unsupported channel, downgrades, and
+ * we disconnect from the AP in the caller
+ * - disconnect causes CRDA to reload world regdomain and the game
+ * starts anew.
+ * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881)
+ *
+ * It seems possible that there are still scenarios with CSA or real
+ * bandwidth changes where a this could happen, but those cases are
+ * less common and wouldn't completely prevent using the AP.
+ */
+ if (tracking &&
+ cfg80211_chandef_identical(chandef, &sdata->vif.bss_conf.chandef))
+ return ret;
+
/* don't print the message below for VHT mismatch if VHT is disabled */
if (ret & IEEE80211_STA_DISABLE_VHT)
vht_chandef = *chandef;
+ /*
+ * Ignore the DISABLED flag when we're already connected and only
+ * tracking the APs beacon for bandwidth changes - otherwise we
+ * might get disconnected here if we connect to an AP, update our
+ * regulatory information based on the AP's country IE and the
+ * information we have is wrong/outdated and disables the channel
+ * that we're actually using for the connection to the AP.
+ */
while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
- IEEE80211_CHAN_DISABLED)) {
+ tracking ? 0 :
+ IEEE80211_CHAN_DISABLED)) {
if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) {
ret = IEEE80211_STA_DISABLE_HT |
IEEE80211_STA_DISABLE_VHT;
- goto out;
+ break;
}
ret |= chandef_downgrade(chandef);
}
- if (chandef->width != vht_chandef.width && verbose)
+ if (chandef->width != vht_chandef.width && !tracking)
sdata_info(sdata,
"capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n");
@@ -412,7 +446,7 @@
/* calculate new channel (type) based on HT/VHT operation IEs */
flags = ieee80211_determine_chantype(sdata, sband, chan, ht_oper,
- vht_oper, &chandef, false);
+ vht_oper, &chandef, true);
/*
* Downgrade the new channel if we associated with restricted
@@ -3461,10 +3495,13 @@
if (tx_flags == 0) {
auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT;
- ifmgd->auth_data->timeout_started = true;
+ auth_data->timeout_started = true;
run_again(ifmgd, auth_data->timeout);
} else {
- auth_data->timeout_started = false;
+ auth_data->timeout =
+ round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG);
+ auth_data->timeout_started = true;
+ run_again(ifmgd, auth_data->timeout);
}
return 0;
@@ -3501,7 +3538,11 @@
assoc_data->timeout_started = true;
run_again(&sdata->u.mgd, assoc_data->timeout);
} else {
- assoc_data->timeout_started = false;
+ assoc_data->timeout =
+ round_jiffies_up(jiffies +
+ IEEE80211_ASSOC_TIMEOUT_LONG);
+ assoc_data->timeout_started = true;
+ run_again(&sdata->u.mgd, assoc_data->timeout);
}
return 0;
@@ -3713,6 +3754,32 @@
}
#ifdef CONFIG_PM
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+ u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+
+ mutex_lock(&ifmgd->mtx);
+
+ if (ifmgd->auth_data) {
+ /*
+ * If we are trying to authenticate while suspending, cfg80211
+ * won't know and won't actually abort those attempts, thus we
+ * need to do that ourselves.
+ */
+ ieee80211_send_deauth_disassoc(sdata,
+ ifmgd->auth_data->bss->bssid,
+ IEEE80211_STYPE_DEAUTH,
+ WLAN_REASON_DEAUTH_LEAVING,
+ false, frame_buf);
+ ieee80211_destroy_auth_data(sdata, false);
+ cfg80211_send_deauth(sdata->dev, frame_buf,
+ IEEE80211_DEAUTH_FRAME_LEN);
+ }
+
+ mutex_unlock(&ifmgd->mtx);
+}
+
void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -3906,7 +3973,7 @@
ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
cbss->channel,
ht_oper, vht_oper,
- &chandef, true);
+ &chandef, false);
sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
local->rx_chains);
@@ -4328,8 +4395,7 @@
rcu_read_unlock();
if (bss->wmm_used && bss->uapsd_supported &&
- (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) &&
- sdata->wmm_acm != 0xff) {
+ (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
assoc_data->uapsd = true;
ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED;
} else {
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index acd1f71..0427a58 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@
container_of(work, struct ieee80211_roc_work, work.work);
struct ieee80211_sub_if_data *sdata = roc->sdata;
struct ieee80211_local *local = sdata->local;
- bool started;
+ bool started, on_channel;
mutex_lock(&local->mtx);
@@ -354,13 +354,24 @@
if (!roc->started) {
struct ieee80211_roc_work *dep;
- /* start this ROC */
+ WARN_ON(local->use_chanctx);
- /* switch channel etc */
+ /* If actually operating on the desired channel (with at least
+ * 20 MHz channel width) don't stop all the operations but still
+ * treat it as though the ROC operation started properly, so
+ * other ROC operations won't interfere with this one.
+ */
+ roc->on_channel = roc->chan == local->_oper_chandef.chan;
+
+ /* start this ROC */
ieee80211_recalc_idle(local);
- local->tmp_channel = roc->chan;
- ieee80211_hw_config(local, 0);
+ if (!roc->on_channel) {
+ ieee80211_offchannel_stop_vifs(local);
+
+ local->tmp_channel = roc->chan;
+ ieee80211_hw_config(local, 0);
+ }
/* tell userspace or send frame */
ieee80211_handle_roc_started(roc);
@@ -379,9 +390,10 @@
finish:
list_del(&roc->list);
started = roc->started;
+ on_channel = roc->on_channel;
ieee80211_roc_notify_destroy(roc, !roc->abort);
- if (started) {
+ if (started && !on_channel) {
ieee80211_flush_queues(local, NULL);
local->tmp_channel = NULL;
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 7fc5d0d..efb510e 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -99,10 +99,21 @@
}
mutex_unlock(&local->sta_mtx);
- /* remove all interfaces */
+ /* remove all interfaces that were created in the driver */
list_for_each_entry(sdata, &local->interfaces, list) {
if (!ieee80211_sdata_running(sdata))
continue;
+ switch (sdata->vif.type) {
+ case NL80211_IFTYPE_AP_VLAN:
+ case NL80211_IFTYPE_MONITOR:
+ continue;
+ case NL80211_IFTYPE_STATION:
+ ieee80211_mgd_quiesce(sdata);
+ break;
+ default:
+ break;
+ }
+
drv_remove_interface(local, sdata);
}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index a02bef3..d68d6cf 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -448,7 +448,7 @@
*/
if (!(rates[0].flags & IEEE80211_TX_RC_MCS)) {
u32 basic_rates = vif->bss_conf.basic_rates;
- s8 baserate = basic_rates ? ffs(basic_rates - 1) : 0;
+ s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0;
rate = &sband->bitrates[rates[0].idx];
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index ac7ef54..e6512e2 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -290,7 +290,7 @@
struct minstrel_rate *msr, *mr;
unsigned int ndx;
bool mrr_capable;
- bool prev_sample = mi->prev_sample;
+ bool prev_sample;
int delta;
int sampling_ratio;
@@ -314,6 +314,7 @@
(mi->sample_count + mi->sample_deferred / 2);
/* delta < 0: no sampling required */
+ prev_sample = mi->prev_sample;
mi->prev_sample = false;
if (delta < 0 || (!mrr_capable && prev_sample))
return;
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index 5b2d301..f3bbea1 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -804,10 +804,18 @@
sample_group = &minstrel_mcs_groups[sample_idx / MCS_GROUP_RATES];
info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
+ rate->count = 1;
+
+ if (sample_idx / MCS_GROUP_RATES == MINSTREL_CCK_GROUP) {
+ int idx = sample_idx % ARRAY_SIZE(mp->cck_rates);
+ rate->idx = mp->cck_rates[idx];
+ rate->flags = 0;
+ return;
+ }
+
rate->idx = sample_idx % MCS_GROUP_RATES +
(sample_group->streams - 1) * MCS_GROUP_RATES;
rate->flags = IEEE80211_TX_RC_MCS | sample_group->flags;
- rate->count = 1;
}
static void
@@ -820,6 +828,9 @@
if (sband->band != IEEE80211_BAND_2GHZ)
return;
+ if (!(mp->hw->flags & IEEE80211_HW_SUPPORTS_HT_CCK_RATES))
+ return;
+
mi->cck_supported = 0;
mi->cck_supported_short = 0;
for (i = 0; i < 4; i++) {
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 8e29526..cd60be8 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -864,7 +864,8 @@
u16 sc;
u8 tid, ack_policy;
- if (!ieee80211_is_data_qos(hdr->frame_control))
+ if (!ieee80211_is_data_qos(hdr->frame_control) ||
+ is_multicast_ether_addr(hdr->addr1))
goto dont_reorder;
/*
@@ -932,8 +933,14 @@
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
- /* Drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.2.9) */
- if (rx->sta && !is_multicast_ether_addr(hdr->addr1)) {
+ /*
+ * Drop duplicate 802.11 retransmissions
+ * (IEEE 802.11-2012: 9.3.2.10 "Duplicate detection and recovery")
+ */
+ if (rx->skb->len >= 24 && rx->sta &&
+ !ieee80211_is_ctl(hdr->frame_control) &&
+ !ieee80211_is_qos_nullfunc(hdr->frame_control) &&
+ !is_multicast_ether_addr(hdr->addr1)) {
if (unlikely(ieee80211_has_retry(hdr->frame_control) &&
rx->sta->last_seq_ctrl[rx->seqno_idx] ==
hdr->seq_ctrl)) {
@@ -1578,11 +1585,14 @@
sc = le16_to_cpu(hdr->seq_ctrl);
frag = sc & IEEE80211_SCTL_FRAG;
- if (likely((!ieee80211_has_morefrags(fc) && frag == 0) ||
- is_multicast_ether_addr(hdr->addr1))) {
- /* not fragmented */
- goto out;
+ if (is_multicast_ether_addr(hdr->addr1)) {
+ rx->local->dot11MulticastReceivedFrameCount++;
+ goto out_no_led;
}
+
+ if (likely(!ieee80211_has_morefrags(fc) && frag == 0))
+ goto out;
+
I802_DEBUG_INC(rx->local->rx_handlers_fragments);
if (skb_linearize(rx->skb))
@@ -1673,12 +1683,10 @@
status->rx_flags |= IEEE80211_RX_FRAGMENTED;
out:
+ ieee80211_led_rx(rx->local);
+ out_no_led:
if (rx->sta)
rx->sta->rx_packets++;
- if (is_multicast_ether_addr(hdr->addr1))
- rx->local->dot11MulticastReceivedFrameCount++;
- else
- ieee80211_led_rx(rx->local);
return RX_CONTINUE;
}
@@ -2015,6 +2023,9 @@
hdr = (struct ieee80211_hdr *) skb->data;
mesh_hdr = (struct ieee80211s_hdr *) (skb->data + hdrlen);
+ if (ieee80211_drop_unencrypted(rx, hdr->frame_control))
+ return RX_DROP_MONITOR;
+
/* frame is in RMC, don't forward */
if (ieee80211_is_data(hdr->frame_control) &&
is_multicast_ether_addr(hdr->addr1) &&
@@ -2996,6 +3007,9 @@
case NL80211_IFTYPE_ADHOC:
if (!bssid)
return 0;
+ if (ether_addr_equal(sdata->vif.addr, hdr->addr2) ||
+ ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2))
+ return 0;
if (ieee80211_is_beacon(hdr->frame_control)) {
return 1;
} else if (!ieee80211_bssid_match(bssid, sdata->u.ibss.bssid)) {
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 99b10392..eb03337 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -202,6 +202,9 @@
enum ieee80211_band band;
int i, ielen, n_chans;
+ if (test_bit(SCAN_HW_CANCELLED, &local->scanning))
+ return false;
+
do {
if (local->hw_scan_band == IEEE80211_NUM_BANDS)
return false;
@@ -878,7 +881,23 @@
if (!local->scan_req)
goto out;
+ /*
+ * We have a scan running and the driver already reported completion,
+ * but the worker hasn't run yet or is stuck on the mutex - mark it as
+ * cancelled.
+ */
+ if (test_bit(SCAN_HW_SCANNING, &local->scanning) &&
+ test_bit(SCAN_COMPLETED, &local->scanning)) {
+ set_bit(SCAN_HW_CANCELLED, &local->scanning);
+ goto out;
+ }
+
if (test_bit(SCAN_HW_SCANNING, &local->scanning)) {
+ /*
+ * Make sure that __ieee80211_scan_completed doesn't trigger a
+ * scan on another band.
+ */
+ set_bit(SCAN_HW_CANCELLED, &local->scanning);
if (local->ops->cancel_hw_scan)
drv_cancel_hw_scan(local,
rcu_dereference_protected(local->scan_sdata,
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 11216bc..557a576 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -270,6 +270,7 @@
sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
+ kfree(rcu_dereference_raw(sta->sta.rates));
kfree(sta);
}
@@ -339,6 +340,7 @@
return NULL;
spin_lock_init(&sta->lock);
+ spin_lock_init(&sta->ps_lock);
INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
mutex_init(&sta->ampdu_mlme.mtx);
@@ -1045,6 +1047,8 @@
skb_queue_head_init(&pending);
+ /* sync with ieee80211_tx_h_unicast_ps_buf */
+ spin_lock(&sta->ps_lock);
/* Send all buffered frames to the station */
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
int count = skb_queue_len(&pending), tmp;
@@ -1064,6 +1068,7 @@
}
ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+ spin_unlock(&sta->ps_lock);
local->total_ps_buffered -= buffered;
@@ -1110,6 +1115,7 @@
memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN);
memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN);
memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN);
+ nullfunc->seq_ctrl = 0;
skb->priority = tid;
skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]);
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index adc3004..3184b2b 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -244,6 +244,7 @@
* @drv_unblock_wk: used for driver PS unblocking
* @listen_interval: listen interval of this station, when we're acting as AP
* @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
* @ps_tx_buf: buffers (per AC) of frames to transmit to this station
* when it leaves power saving state or polls
* @tx_filtered: buffers (per AC) of frames we already tried to
@@ -324,10 +325,8 @@
/* use the accessors defined below */
unsigned long _flags;
- /*
- * STA powersave frame queues, no more than the internal
- * locking required.
- */
+ /* STA powersave lock and frame queues */
+ spinlock_t ps_lock;
struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
unsigned long driver_buffered_tids;
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 4343920..9e78206 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -180,6 +180,9 @@
struct ieee80211_local *local = sta->local;
struct ieee80211_sub_if_data *sdata = sta->sdata;
+ if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
+ sta->last_rx = jiffies;
+
if (ieee80211_is_data_qos(mgmt->frame_control)) {
struct ieee80211_hdr *hdr = (void *) skb->data;
u8 *qc = ieee80211_get_qos_ctl(hdr);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 9972e07..10eea23 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -398,6 +398,9 @@
if (ieee80211_has_order(hdr->frame_control))
return TX_CONTINUE;
+ if (ieee80211_is_probe_req(hdr->frame_control))
+ return TX_CONTINUE;
+
/* no stations in PS mode */
if (!atomic_read(&ps->num_sta_ps))
return TX_CONTINUE;
@@ -471,6 +474,20 @@
sta->sta.addr, sta->sta.aid, ac);
if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
purge_old_ps_buffers(tx->local);
+
+ /* sync with ieee80211_sta_ps_deliver_wakeup */
+ spin_lock(&sta->ps_lock);
+ /*
+ * STA woke up the meantime and all the frames on ps_tx_buf have
+ * been queued to pending queue. No reordering can happen, go
+ * ahead and Tx the packet.
+ */
+ if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+ !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+ spin_unlock(&sta->ps_lock);
+ return TX_CONTINUE;
+ }
+
if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
ps_dbg(tx->sdata,
@@ -484,6 +501,7 @@
info->control.vif = &tx->sdata->vif;
info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+ spin_unlock(&sta->ps_lock);
if (!timer_pending(&local->sta_cleanup))
mod_timer(&local->sta_cleanup,
@@ -511,7 +529,6 @@
{
if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
return TX_CONTINUE;
-
if (tx->flags & IEEE80211_TX_UNICAST)
return ieee80211_tx_h_unicast_ps_buf(tx);
else
@@ -851,7 +868,7 @@
}
/* adjust first fragment's length */
- skb->len = hdrlen + per_fragm;
+ skb_trim(skb, hdrlen + per_fragm);
return 0;
}
@@ -1100,7 +1117,8 @@
tx->sta = rcu_dereference(sdata->u.vlan.sta);
if (!tx->sta && sdata->dev->ieee80211_ptr->use_4addr)
return TX_DROP;
- } else if (info->flags & IEEE80211_TX_CTL_INJECTED ||
+ } else if (info->flags & (IEEE80211_TX_CTL_INJECTED |
+ IEEE80211_TX_INTFL_NL80211_FRAME_TX) ||
tx->sdata->control_port_protocol == tx->skb->protocol) {
tx->sta = sta_info_get_bss(sdata, hdr->addr1);
}
@@ -2692,7 +2710,7 @@
cpu_to_le16(IEEE80211_FCTL_MOREDATA);
}
- if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ if (sdata->vif.type == NL80211_IFTYPE_AP)
sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
if (!ieee80211_tx_prepare(sdata, &tx, skb))
break;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 72e6292..5db8eb5 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2174,6 +2174,10 @@
}
rate = cfg80211_calculate_bitrate(&ri);
+ if (WARN_ONCE(!rate,
+ "Invalid bitrate: flags=0x%x, idx=%d, vht_nss=%d\n",
+ status->flag, status->rate_idx, status->vht_nss))
+ return 0;
/* rewind from end of MPDU */
if (status->flag & RX_FLAG_MACTIME_END)
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index afba19c..a282fdd 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -153,6 +153,11 @@
return IEEE80211_AC_BE;
}
+ if (skb->protocol == sdata->control_port_protocol) {
+ skb->priority = 7;
+ return ieee80211_downgrade_queue(sdata, skb);
+ }
+
/* use the data classifier to determine what 802.1d tag the
* data frame has */
skb->priority = cfg80211_classify8021d(skb);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index f771390..3b04dfd 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1754,6 +1754,12 @@
if (*op < IP_SET_OP_VERSION) {
/* Check the version at the beginning of operations */
struct ip_set_req_version *req_version = data;
+
+ if (*len < sizeof(struct ip_set_req_version)) {
+ ret = -EINVAL;
+ goto done;
+ }
+
if (req_version->version != IPSET_PROTOCOL) {
ret = -EPROTO;
goto done;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 57beb17..707bc52 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -325,18 +325,22 @@
static void
mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length)
{
- u8 i, j;
+ u8 i, j, net_end = nets_length - 1;
- for (i = 0; i < nets_length - 1 && h->nets[i].cidr != cidr; i++)
- ;
- h->nets[i].nets--;
-
- if (h->nets[i].nets != 0)
- return;
-
- for (j = i; j < nets_length - 1 && h->nets[j].nets; j++) {
- h->nets[j].cidr = h->nets[j + 1].cidr;
- h->nets[j].nets = h->nets[j + 1].nets;
+ for (i = 0; i < nets_length; i++) {
+ if (h->nets[i].cidr != cidr)
+ continue;
+ if (h->nets[i].nets > 1 || i == net_end ||
+ h->nets[i + 1].nets == 0) {
+ h->nets[i].nets--;
+ return;
+ }
+ for (j = i; j < net_end && h->nets[j].nets; j++) {
+ h->nets[j].cidr = h->nets[j + 1].cidr;
+ h->nets[j].nets = h->nets[j + 1].nets;
+ }
+ h->nets[j].nets = 0;
+ return;
}
}
#endif
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a083bda..90e756cf 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -797,7 +797,6 @@
ip_vs_control_del(cp);
if (cp->flags & IP_VS_CONN_F_NFCT) {
- ip_vs_conn_drop_conntrack(cp);
/* Do not access conntracks during subsys cleanup
* because nf_conntrack_find_get can not be used after
* conntrack cleanup for the net.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 23b8eb5..1c6a71c 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -650,16 +650,24 @@
return err;
}
-static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
+ unsigned int hooknum)
{
+ if (!sysctl_snat_reroute(skb))
+ return 0;
+ /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
+ if (NF_INET_LOCAL_IN == hooknum)
+ return 0;
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
+ struct dst_entry *dst = skb_dst(skb);
+
+ if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+ ip6_route_me_harder(skb) != 0)
return 1;
} else
#endif
- if ((sysctl_snat_reroute(skb) ||
- skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
ip_route_me_harder(skb, RTN_LOCAL) != 0)
return 1;
@@ -782,7 +790,8 @@
union nf_inet_addr *snet,
__u8 protocol, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp,
- unsigned int offset, unsigned int ihl)
+ unsigned int offset, unsigned int ihl,
+ unsigned int hooknum)
{
unsigned int verdict = NF_DROP;
@@ -812,7 +821,7 @@
#endif
ip_vs_nat_icmp(skb, pp, cp, 1);
- if (ip_vs_route_me_harder(af, skb))
+ if (ip_vs_route_me_harder(af, skb, hooknum))
goto out;
/* do the statistics and put it back */
@@ -907,7 +916,7 @@
snet.ip = iph->saddr;
return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
- pp, ciph.len, ihl);
+ pp, ciph.len, ihl, hooknum);
}
#ifdef CONFIG_IP_VS_IPV6
@@ -972,7 +981,8 @@
snet.in6 = ciph.saddr.in6;
writable = ciph.len;
return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
- pp, writable, sizeof(struct ipv6hdr));
+ pp, writable, sizeof(struct ipv6hdr),
+ hooknum);
}
#endif
@@ -1031,7 +1041,8 @@
*/
static unsigned int
handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
- struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
+ struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
+ unsigned int hooknum)
{
struct ip_vs_protocol *pp = pd->pp;
@@ -1069,7 +1080,7 @@
* if it came from this machine itself. So re-compute
* the routing information.
*/
- if (ip_vs_route_me_harder(af, skb))
+ if (ip_vs_route_me_harder(af, skb, hooknum))
goto drop;
IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
@@ -1131,12 +1142,6 @@
ip_vs_fill_iph_skb(af, skb, &iph);
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1178,7 +1183,7 @@
cp = pp->conn_out_get(af, skb, &iph, 0);
if (likely(cp))
- return handle_response(af, skb, pd, cp, &iph);
+ return handle_response(af, skb, pd, cp, &iph, hooknum);
if (sysctl_nat_icmp_send(net) &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP ||
@@ -1390,15 +1395,19 @@
if (ipip) {
__be32 info = ic->un.gateway;
+ __u8 type = ic->type;
+ __u8 code = ic->code;
/* Update the MTU */
if (ic->type == ICMP_DEST_UNREACH &&
ic->code == ICMP_FRAG_NEEDED) {
struct ip_vs_dest *dest = cp->dest;
u32 mtu = ntohs(ic->un.frag.mtu);
+ __be16 frag_off = cih->frag_off;
/* Strip outer IP and ICMP, go to IPIP header */
- __skb_pull(skb, ihl + sizeof(_icmph));
+ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+ goto ignore_ipip;
offset2 -= ihl + sizeof(_icmph);
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
@@ -1406,7 +1415,7 @@
ipv4_update_pmtu(skb, dev_net(skb->dev),
mtu, 0, 0, 0, 0);
/* Client uses PMTUD? */
- if (!(cih->frag_off & htons(IP_DF)))
+ if (!(frag_off & htons(IP_DF)))
goto ignore_ipip;
/* Prefer the resulting PMTU */
if (dest) {
@@ -1425,12 +1434,13 @@
/* Strip outer IP, ICMP and IPIP, go to IP header of
* original request.
*/
- __skb_pull(skb, offset2);
+ if (pskb_pull(skb, offset2) == NULL)
+ goto ignore_ipip;
skb_reset_network_header(skb);
IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
- ic->type, ic->code, ntohl(info));
- icmp_send(skb, ic->type, ic->code, info);
+ type, code, ntohl(info));
+ icmp_send(skb, type, code, info);
/* ICMP can be shorter but anyways, account it */
ip_vs_out_stats(cp, skb);
@@ -1606,12 +1616,6 @@
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags. */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
@@ -1663,9 +1667,8 @@
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, af, pp, skb, 0,
"ip_vs_in: packet continues traversal as normal");
- if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+ if (iph.fragoffs) {
/* Fragment that couldn't be mapped to a conn entry
- * and don't have any pointer to a reasm skb
* is missing module nf_defrag_ipv6
*/
IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
@@ -1748,38 +1751,6 @@
#ifdef CONFIG_IP_VS_IPV6
/*
- * AF_INET6 fragment handling
- * Copy info from first fragment, to the rest of them.
- */
-static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- struct net *net;
-
- /* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
- * ipvs_property is set when checking first fragment
- * in ip_vs_in() and ip_vs_out().
- */
- if (reasm)
- IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
- if (!reasm || !reasm->ipvs_property)
- return NF_ACCEPT;
-
- net = skb_net(skb);
- if (!net_ipvs(net)->enable)
- return NF_ACCEPT;
-
- /* Copy stored fw mark, saved in ip_vs_{in,out} */
- skb->mark = reasm->mark;
-
- return NF_ACCEPT;
-}
-
-/*
* AF_INET6 handler in NF_INET_LOCAL_IN chain
* Schedule and forward packets from remote clients
*/
@@ -1916,14 +1887,6 @@
.priority = 100,
},
#ifdef CONFIG_IP_VS_IPV6
- /* After mangle & nat fetch 2:nd fragment and following */
- {
- .hook = ip_vs_preroute_frag6,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_PRE_ROUTING,
- .priority = NF_IP6_PRI_NAT_DST + 1,
- },
/* After packet filtering, change source only for VS/NAT */
{
.hook = ip_vs_reply6,
@@ -1946,7 +1909,7 @@
{
.hook = ip_vs_local_reply6,
.owner = THIS_MODULE,
- .pf = NFPROTO_IPV4,
+ .pf = NFPROTO_IPV6,
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP6_PRI_NAT_DST + 1,
},
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 77c1732..4a662f1 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -183,6 +183,8 @@
struct nf_conn *ct;
struct net *net;
+ *diff = 0;
+
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
* so turn this into a no-op for IPv6 packets
@@ -191,8 +193,6 @@
return 1;
#endif
- *diff = 0;
-
/* Only useful for established sessions */
if (cp->state != IP_VS_TCP_S_ESTABLISHED)
return 1;
@@ -321,6 +321,9 @@
struct ip_vs_conn *n_cp;
struct net *net;
+ /* no diff required for incoming packets */
+ *diff = 0;
+
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
* so turn this into a no-op for IPv6 packets
@@ -329,9 +332,6 @@
return 1;
#endif
- /* no diff required for incoming packets */
- *diff = 0;
-
/* Only useful for established sessions */
if (cp->state != IP_VS_TCP_S_ESTABLISHED)
return 1;
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 9ef22bd..bed5f70 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -65,7 +65,6 @@
static int
ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
struct ip_vs_iphdr iph;
unsigned int dataoff, datalen, matchoff, matchlen;
const char *dptr;
@@ -79,15 +78,10 @@
/* todo: IPv6 fragments:
* I think this only should be done for the first fragment. /HS
*/
- if (reasm) {
- skb = reasm;
- dataoff = iph.thoff_reasm + sizeof(struct udphdr);
- } else
- dataoff = iph.len + sizeof(struct udphdr);
+ dataoff = iph.len + sizeof(struct udphdr);
if (dataoff >= skb->len)
return -EINVAL;
- /* todo: Check if this will mess-up the reasm skb !!! /HS */
retc = skb_linearize(skb);
if (retc < 0)
return retc;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index f6046d9..e476cc7 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -878,6 +878,8 @@
IP_VS_DBG(2, "BACKUP, add new conn. failed\n");
return;
}
+ if (!(flags & IP_VS_CONN_F_TEMPLATE))
+ kfree(param->pe_data);
}
if (opt)
@@ -1151,6 +1153,7 @@
(opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL)
);
#endif
+ ip_vs_pe_put(param.pe);
return 0;
/* Error exit */
out:
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b75ff64..1692e75 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -883,7 +883,7 @@
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -967,8 +967,8 @@
iph->nexthdr = IPPROTO_IPV6;
iph->payload_len = old_iph->payload_len;
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
- iph->priority = old_iph->priority;
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
+ ipv6_change_dsfield(iph, 0, ipv6_get_dsfield(old_iph));
iph->daddr = cp->daddr.in6;
iph->saddr = saddr;
iph->hop_limit = old_iph->hop_limit;
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index bdebd03..70866d1 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -778,8 +778,8 @@
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
- if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
- sizeof(rt1->rt6i_gateway)) &&
+ if (ipv6_addr_equal(rt6_nexthop(rt1),
+ rt6_nexthop(rt2)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index a99b6c3..59359be 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -428,7 +428,7 @@
const char *msg;
u_int8_t state;
- dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+ dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
BUG_ON(dh == NULL);
state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
@@ -486,7 +486,7 @@
u_int8_t type, old_state, new_state;
enum ct_dccp_roles role;
- dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+ dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
BUG_ON(dh == NULL);
type = dh->dccph_type;
@@ -577,7 +577,7 @@
unsigned int cscov;
const char *msg;
- dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
+ dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
if (dh == NULL) {
msg = "nf_ct_dccp: short packet ";
goto out_invalid;
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index d25f293..957c1db 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -14,6 +14,30 @@
static unsigned int nf_ct_generic_timeout __read_mostly = 600*HZ;
+static bool nf_generic_should_process(u8 proto)
+{
+ switch (proto) {
+#ifdef CONFIG_NF_CT_PROTO_SCTP_MODULE
+ case IPPROTO_SCTP:
+ return false;
+#endif
+#ifdef CONFIG_NF_CT_PROTO_DCCP_MODULE
+ case IPPROTO_DCCP:
+ return false;
+#endif
+#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE
+ case IPPROTO_GRE:
+ return false;
+#endif
+#ifdef CONFIG_NF_CT_PROTO_UDPLITE_MODULE
+ case IPPROTO_UDPLITE:
+ return false;
+#endif
+ default:
+ return true;
+ }
+}
+
static inline struct nf_generic_net *generic_pernet(struct net *net)
{
return &net->ct.nf_ct_proto.generic;
@@ -67,7 +91,7 @@
static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb,
unsigned int dataoff, unsigned int *timeouts)
{
- return true;
+ return nf_generic_should_process(nf_ct_protonum(ct));
}
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 4d4d8f1..7dcc376 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1043,6 +1043,12 @@
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
+ /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
+ * pickup with loose=1. Avoid large ESTABLISHED timeout.
+ */
+ if (new_state == TCP_CONNTRACK_ESTABLISHED &&
+ timeout > timeouts[TCP_CONNTRACK_UNACK])
+ timeout = timeouts[TCP_CONNTRACK_UNACK];
} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
&& (old_state == TCP_CONNTRACK_SYN_RECV
|| old_state == TCP_CONNTRACK_ESTABLISHED)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 038eee5..2bb801e 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -487,6 +487,39 @@
return i->status & IPS_NAT_MASK ? 1 : 0;
}
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+ struct nf_conn_nat *nat = nfct_nat(ct);
+
+ if (nf_nat_proto_remove(ct, data))
+ return 1;
+
+ if (!nat || !nat->ct)
+ return 0;
+
+ /* This netns is being destroyed, and conntrack has nat null binding.
+ * Remove it from bysource hash, as the table will be freed soon.
+ *
+ * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+ * will delete entry from already-freed table.
+ */
+ if (!del_timer(&ct->timeout))
+ return 1;
+
+ spin_lock_bh(&nf_nat_lock);
+ hlist_del_rcu(&nat->bysource);
+ ct->status &= ~IPS_NAT_DONE_MASK;
+ nat->ct = NULL;
+ spin_unlock_bh(&nf_nat_lock);
+
+ add_timer(&ct->timeout);
+
+ /* don't delete conntrack. Although that would make things a lot
+ * simpler, we'd end up flushing all conntracks on nat rmmod.
+ */
+ return 0;
+}
+
static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
{
struct nf_nat_proto_clean clean = {
@@ -749,7 +782,7 @@
{
struct nf_nat_proto_clean clean = {};
- nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
+ nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean);
synchronize_rcu();
nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
}
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index f02b360..1fb2258 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -34,10 +34,14 @@
struct nf_conntrack_expect *exp)
{
char buffer[sizeof("4294967296 65635")];
+ struct nf_conn *ct = exp->master;
+ union nf_inet_addr newaddr;
u_int16_t port;
unsigned int ret;
/* Reply comes from server. */
+ newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
+
exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
exp->dir = IP_CT_DIR_REPLY;
exp->expectfn = nf_nat_follow_master;
@@ -57,17 +61,35 @@
}
if (port == 0) {
- nf_ct_helper_log(skb, exp->master, "all ports in use");
+ nf_ct_helper_log(skb, ct, "all ports in use");
return NF_DROP;
}
- ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo,
- protoff, matchoff, matchlen, buffer,
- strlen(buffer));
+ /* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27
+ * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28
+ * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26
+ * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26
+ * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27
+ *
+ * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits,
+ * 255.255.255.255==4294967296, 10 digits)
+ * P: bound port (min 1 d, max 5d (65635))
+ * F: filename (min 1 d )
+ * S: size (min 1 d )
+ * 0x01, \n: terminators
+ */
+ /* AAA = "us", ie. where server normally talks to. */
+ snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port);
+ pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
+ buffer, &newaddr.ip, port);
+
+ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+ matchlen, buffer, strlen(buffer));
if (ret != NF_ACCEPT) {
- nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
+ nf_ct_helper_log(skb, ct, "cannot mangle packet");
nf_ct_unexpect_related(exp);
}
+
return ret;
}
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 572d87dc..0a03662 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -147,7 +147,7 @@
const struct nfnetlink_subsystem *ss;
int type, err;
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ if (!netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
/* All the messages must at least contain nfgenmsg */
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 962e979..216261d 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -45,7 +45,8 @@
#define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 100 /* every second */
#define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */
-#define NFULNL_COPY_RANGE_MAX 0xFFFF /* max packet size is limited by 16-bit struct nfattr nfa_len field */
+/* max packet size is limited by 16-bit struct nfattr nfa_len field */
+#define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN)
#define PRINTR(x, args...) do { if (net_ratelimit()) \
printk(x, ## args); } while (0);
@@ -255,6 +256,8 @@
case NFULNL_COPY_PACKET:
inst->copy_mode = mode;
+ if (range == 0)
+ range = NFULNL_COPY_RANGE_MAX;
inst->copy_range = min_t(unsigned int,
range, NFULNL_COPY_RANGE_MAX);
break;
@@ -345,26 +348,25 @@
return skb;
}
-static int
+static void
__nfulnl_send(struct nfulnl_instance *inst)
{
- int status = -1;
-
if (inst->qlen > 1) {
struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0,
NLMSG_DONE,
sizeof(struct nfgenmsg),
0);
- if (!nlh)
+ if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n",
+ inst->skb->len, skb_tailroom(inst->skb))) {
+ kfree_skb(inst->skb);
goto out;
+ }
}
- status = nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
- MSG_DONTWAIT);
-
+ nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid,
+ MSG_DONTWAIT);
+out:
inst->qlen = 0;
inst->skb = NULL;
-out:
- return status;
}
static void
@@ -647,7 +649,8 @@
+ nla_total_size(sizeof(u_int32_t)) /* gid */
+ nla_total_size(plen) /* prefix */
+ nla_total_size(sizeof(struct nfulnl_msg_packet_hw))
- + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp));
+ + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp))
+ + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */
if (in && skb_mac_header_was_set(skb)) {
size += nla_total_size(skb->dev->hard_header_len)
@@ -676,8 +679,7 @@
break;
case NFULNL_COPY_PACKET:
- if (inst->copy_range == 0
- || inst->copy_range > skb->len)
+ if (inst->copy_range > skb->len)
data_len = skb->len;
else
data_len = inst->copy_range;
@@ -690,8 +692,7 @@
goto unlock_and_release;
}
- if (inst->skb &&
- size > skb_tailroom(inst->skb) - sizeof(struct nfgenmsg)) {
+ if (inst->skb && size > skb_tailroom(inst->skb)) {
/* either the queue len is too high or we don't have
* enough room in the skb left. flush to userspace. */
__nfulnl_flush(inst);
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 5352b2d..5497f50 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -227,22 +227,23 @@
spin_unlock_bh(&queue->lock);
}
-static void
-nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+static int
+nfqnl_zcopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen)
{
int i, j = 0;
int plen = 0; /* length of skb->head fragment */
+ int ret;
struct page *page;
unsigned int offset;
/* dont bother with small payloads */
- if (len <= skb_tailroom(to)) {
- skb_copy_bits(from, 0, skb_put(to, len), len);
- return;
- }
+ if (len <= skb_tailroom(to))
+ return skb_copy_bits(from, 0, skb_put(to, len), len);
if (hlen) {
- skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ if (unlikely(ret))
+ return ret;
len -= hlen;
} else {
plen = min_t(int, skb_headlen(from), len);
@@ -260,6 +261,11 @@
to->len += len + plen;
to->data_len += len + plen;
+ if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) {
+ skb_tx_error(from);
+ return -ENOMEM;
+ }
+
for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
if (!len)
break;
@@ -270,6 +276,8 @@
j++;
}
skb_shinfo(to)->nr_frags = j;
+
+ return 0;
}
static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet)
@@ -355,13 +363,16 @@
skb = nfnetlink_alloc_skb(&init_net, size, queue->peer_portid,
GFP_ATOMIC);
- if (!skb)
+ if (!skb) {
+ skb_tx_error(entskb);
return NULL;
+ }
nlh = nlmsg_put(skb, 0, 0,
NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
sizeof(struct nfgenmsg), 0);
if (!nlh) {
+ skb_tx_error(entskb);
kfree_skb(skb);
return NULL;
}
@@ -481,13 +492,15 @@
nla->nla_type = NFQA_PAYLOAD;
nla->nla_len = nla_attr_size(data_len);
- nfqnl_zcopy(skb, entskb, data_len, hlen);
+ if (nfqnl_zcopy(skb, entskb, data_len, hlen))
+ goto nla_put_failure;
}
nlh->nlmsg_len = skb->len;
return skb;
nla_put_failure:
+ skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
return NULL;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 57ee84d..f7ad5c6 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -374,14 +374,14 @@
return err;
}
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr)
+static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
{
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
struct page *p_start, *p_end;
/* First page is flushed through netlink_{get,set}_status */
p_start = pgvec_to_page(hdr + PAGE_SIZE);
- p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + hdr->nm_len - 1);
+ p_end = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
while (p_start <= p_end) {
flush_dcache_page(p_start);
p_start++;
@@ -399,9 +399,9 @@
static void netlink_set_status(struct nl_mmap_hdr *hdr,
enum nl_mmap_status status)
{
+ smp_mb();
hdr->nm_status = status;
flush_dcache_page(pgvec_to_page(hdr));
- smp_wmb();
}
static struct nl_mmap_hdr *
@@ -500,7 +500,7 @@
while (nlk->cb != NULL && netlink_dump_space(nlk)) {
err = netlink_dump(sk);
if (err < 0) {
- sk->sk_err = err;
+ sk->sk_err = -err;
sk->sk_error_report(sk);
break;
}
@@ -563,24 +563,16 @@
struct nl_mmap_hdr *hdr;
struct sk_buff *skb;
unsigned int maxlen;
- bool excl = true;
int err = 0, len = 0;
- /* Netlink messages are validated by the receiver before processing.
- * In order to avoid userspace changing the contents of the message
- * after validation, the socket and the ring may only be used by a
- * single process, otherwise we fall back to copying.
- */
- if (atomic_long_read(&sk->sk_socket->file->f_count) > 2 ||
- atomic_read(&nlk->mapped) > 1)
- excl = false;
-
mutex_lock(&nlk->pg_vec_lock);
ring = &nlk->tx_ring;
maxlen = ring->frame_size - NL_MMAP_HDRLEN;
do {
+ unsigned int nm_len;
+
hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
if (hdr == NULL) {
if (!(msg->msg_flags & MSG_DONTWAIT) &&
@@ -588,35 +580,23 @@
schedule();
continue;
}
- if (hdr->nm_len > maxlen) {
+
+ nm_len = ACCESS_ONCE(hdr->nm_len);
+ if (nm_len > maxlen) {
err = -EINVAL;
goto out;
}
- netlink_frame_flush_dcache(hdr);
+ netlink_frame_flush_dcache(hdr, nm_len);
- if (likely(dst_portid == 0 && dst_group == 0 && excl)) {
- skb = alloc_skb_head(GFP_KERNEL);
- if (skb == NULL) {
- err = -ENOBUFS;
- goto out;
- }
- sock_hold(sk);
- netlink_ring_setup_skb(skb, sk, ring, hdr);
- NETLINK_CB(skb).flags |= NETLINK_SKB_TX;
- __skb_put(skb, hdr->nm_len);
- netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
- atomic_inc(&ring->pending);
- } else {
- skb = alloc_skb(hdr->nm_len, GFP_KERNEL);
- if (skb == NULL) {
- err = -ENOBUFS;
- goto out;
- }
- __skb_put(skb, hdr->nm_len);
- memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, hdr->nm_len);
- netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
+ skb = alloc_skb(nm_len, GFP_KERNEL);
+ if (skb == NULL) {
+ err = -ENOBUFS;
+ goto out;
}
+ __skb_put(skb, nm_len);
+ memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
+ netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
netlink_increment_head(ring);
@@ -662,7 +642,7 @@
hdr->nm_pid = NETLINK_CB(skb).creds.pid;
hdr->nm_uid = from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
hdr->nm_gid = from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
- netlink_frame_flush_dcache(hdr);
+ netlink_frame_flush_dcache(hdr, hdr->nm_len);
netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
@@ -1219,7 +1199,74 @@
return err;
}
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+ struct user_namespace *user_ns, int cap)
+{
+ return ((nsp->flags & NETLINK_SKB_DST) ||
+ file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+ ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+ struct user_namespace *user_ns, int cap)
+{
+ return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+ return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
{
return (nl_table[sock->sk->sk_protocol].flags & flag) ||
ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1287,7 +1334,7 @@
/* Only superuser is allowed to listen multicasts */
if (nladdr->nl_groups) {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
@@ -1349,7 +1396,7 @@
return -EINVAL;
/* Only superuser is allowed to send multicasts */
- if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ if (nladdr->nl_groups && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
return -EPERM;
if (!nlk->portid)
@@ -1921,7 +1968,7 @@
break;
case NETLINK_ADD_MEMBERSHIP:
case NETLINK_DROP_MEMBERSHIP: {
- if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+ if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
return -EPERM;
err = netlink_realloc_groups(sk);
if (err)
@@ -2053,6 +2100,7 @@
struct sk_buff *skb;
int err;
struct scm_cookie scm;
+ u32 netlink_skb_flags = 0;
if (msg->msg_flags&MSG_OOB)
return -EOPNOTSUPP;
@@ -2072,8 +2120,9 @@
dst_group = ffs(addr->nl_groups);
err = -EPERM;
if ((dst_group || dst_portid) &&
- !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+ !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
goto out;
+ netlink_skb_flags |= NETLINK_SKB_DST;
} else {
dst_portid = nlk->dst_portid;
dst_group = nlk->dst_group;
@@ -2103,6 +2152,7 @@
NETLINK_CB(skb).portid = nlk->portid;
NETLINK_CB(skb).dst_group = dst_group;
NETLINK_CB(skb).creds = siocb->scm->creds;
+ NETLINK_CB(skb).flags = netlink_skb_flags;
err = -EFAULT;
if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2168,8 +2218,6 @@
}
#endif
- msg->msg_namelen = 0;
-
copied = data_skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
@@ -2204,7 +2252,7 @@
if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
ret = netlink_dump(sk);
if (ret) {
- sk->sk_err = ret;
+ sk->sk_err = -ret;
sk->sk_error_report(sk);
}
}
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 2fd6dbe..ade434b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -364,7 +364,7 @@
EXPORT_SYMBOL(genl_unregister_ops);
/**
- * genl_register_family - register a generic netlink family
+ * __genl_register_family - register a generic netlink family
* @family: generic netlink family
*
* Registers the specified family after validating it first. Only one
@@ -374,7 +374,7 @@
*
* Return 0 on success or a negative error code.
*/
-int genl_register_family(struct genl_family *family)
+int __genl_register_family(struct genl_family *family)
{
int err = -EINVAL;
@@ -430,10 +430,10 @@
errout:
return err;
}
-EXPORT_SYMBOL(genl_register_family);
+EXPORT_SYMBOL(__genl_register_family);
/**
- * genl_register_family_with_ops - register a generic netlink family
+ * __genl_register_family_with_ops - register a generic netlink family
* @family: generic netlink family
* @ops: operations to be registered
* @n_ops: number of elements to register
@@ -457,12 +457,12 @@
*
* Return 0 on success or a negative error code.
*/
-int genl_register_family_with_ops(struct genl_family *family,
+int __genl_register_family_with_ops(struct genl_family *family,
struct genl_ops *ops, size_t n_ops)
{
int err, i;
- err = genl_register_family(family);
+ err = __genl_register_family(family);
if (err)
return err;
@@ -476,7 +476,7 @@
genl_unregister_family(family);
return err;
}
-EXPORT_SYMBOL(genl_register_family_with_ops);
+EXPORT_SYMBOL(__genl_register_family_with_ops);
/**
* genl_unregister_family - unregister generic netlink family
@@ -544,6 +544,30 @@
}
EXPORT_SYMBOL(genlmsg_put);
+static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct genl_ops *ops = cb->data;
+ int rc;
+
+ genl_lock();
+ rc = ops->dumpit(skb, cb);
+ genl_unlock();
+ return rc;
+}
+
+static int genl_lock_done(struct netlink_callback *cb)
+{
+ struct genl_ops *ops = cb->data;
+ int rc = 0;
+
+ if (ops->done) {
+ genl_lock();
+ rc = ops->done(cb);
+ genl_unlock();
+ }
+ return rc;
+}
+
static int genl_family_rcv_msg(struct genl_family *family,
struct sk_buff *skb,
struct nlmsghdr *nlh)
@@ -568,19 +592,38 @@
return -EOPNOTSUPP;
if ((ops->flags & GENL_ADMIN_PERM) &&
- !capable(CAP_NET_ADMIN))
+ !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
- struct netlink_dump_control c = {
- .dump = ops->dumpit,
- .done = ops->done,
- };
+ int rc;
if (ops->dumpit == NULL)
return -EOPNOTSUPP;
- return netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ if (!family->parallel_ops) {
+ struct netlink_dump_control c = {
+ .module = family->module,
+ .data = ops,
+ .dump = genl_lock_dumpit,
+ .done = genl_lock_done,
+ };
+
+ genl_unlock();
+ rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ genl_lock();
+
+ } else {
+ struct netlink_dump_control c = {
+ .module = family->module,
+ .dump = ops->dumpit,
+ .done = ops->done,
+ };
+
+ rc = __netlink_dump_start(net->genl_sock, skb, nlh, &c);
+ }
+
+ return rc;
}
if (ops->doit == NULL)
@@ -877,8 +920,10 @@
#ifdef CONFIG_MODULES
if (res == NULL) {
genl_unlock();
+ up_read(&cb_lock);
request_module("net-pf-%d-proto-%d-family-%s",
PF_NETLINK, NETLINK_GENERIC, name);
+ down_read(&cb_lock);
genl_lock();
res = genl_family_find_byname(name);
}
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index ec0c80f..13b92982 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1179,10 +1179,9 @@
sax->sax25_family = AF_NETROM;
skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call,
AX25_ADDR_LEN);
+ msg->msg_namelen = sizeof(*sax);
}
- msg->msg_namelen = sizeof(*sax);
-
skb_free_datagram(sk, skb);
release_sock(sk);
diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h
index ff8c434..f924dd2 100644
--- a/net/nfc/llcp.h
+++ b/net/nfc/llcp.h
@@ -19,6 +19,7 @@
enum llcp_state {
LLCP_CONNECTED = 1, /* wait_for_packet() wants that */
+ LLCP_CONNECTING,
LLCP_CLOSED,
LLCP_BOUND,
LLCP_LISTEN,
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 380253e..86470cf5 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -571,7 +571,7 @@
if (sk->sk_shutdown == SHUTDOWN_MASK)
mask |= POLLHUP;
- if (sock_writeable(sk))
+ if (sock_writeable(sk) && sk->sk_state == LLCP_CONNECTED)
mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
else
set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
@@ -722,14 +722,16 @@
if (ret)
goto sock_unlink;
+ sk->sk_state = LLCP_CONNECTING;
+
ret = sock_wait_state(sk, LLCP_CONNECTED,
sock_sndtimeo(sk, flags & O_NONBLOCK));
- if (ret)
+ if (ret && ret != -EINPROGRESS)
goto sock_unlink;
release_sock(sk);
- return 0;
+ return ret;
sock_unlink:
nfc_llcp_put_ssap(local, llcp_sock->ssap);
@@ -798,8 +800,6 @@
pr_debug("%p %zu\n", sk, len);
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state == LLCP_CLOSED &&
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 313bf1b..5d11f4a 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -241,8 +241,6 @@
if (!skb)
return rc;
- msg->msg_namelen = 0;
-
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 894b6cb..c4779ca 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -40,6 +40,9 @@
static int make_writable(struct sk_buff *skb, int write_len)
{
+ if (!pskb_may_pull(skb, write_len))
+ return -ENOMEM;
+
if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
return 0;
@@ -68,6 +71,8 @@
vlan_set_encap_proto(skb, vhdr);
skb->mac_header += VLAN_HLEN;
+ if (skb_network_offset(skb) < ETH_HLEN)
+ skb_set_network_header(skb, ETH_HLEN);
skb_reset_mac_len(skb);
return 0;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 20a1bd0..81b4b81 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -237,6 +237,30 @@
static void __fanout_unlink(struct sock *sk, struct packet_sock *po);
static void __fanout_link(struct sock *sk, struct packet_sock *po);
+static struct net_device *packet_cached_dev_get(struct packet_sock *po)
+{
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = rcu_dereference(po->cached_dev);
+ if (likely(dev))
+ dev_hold(dev);
+ rcu_read_unlock();
+
+ return dev;
+}
+
+static void packet_cached_dev_assign(struct packet_sock *po,
+ struct net_device *dev)
+{
+ rcu_assign_pointer(po->cached_dev, dev);
+}
+
+static void packet_cached_dev_reset(struct packet_sock *po)
+{
+ RCU_INIT_POINTER(po->cached_dev, NULL);
+}
+
/* register_prot_hook must be invoked with the po->bind_lock held,
* or from a context in which asynchronous accesses to the packet
* socket is not possible (packet_create()).
@@ -244,11 +268,13 @@
static void register_prot_hook(struct sock *sk)
{
struct packet_sock *po = pkt_sk(sk);
+
if (!po->running) {
if (po->fanout)
__fanout_link(sk, po);
else
dev_add_pack(&po->prot_hook);
+
sock_hold(sk);
po->running = 1;
}
@@ -266,10 +292,12 @@
struct packet_sock *po = pkt_sk(sk);
po->running = 0;
+
if (po->fanout)
__fanout_unlink(sk, po);
else
__dev_remove_pack(&po->prot_hook);
+
__sock_put(sk);
if (sync) {
@@ -432,9 +460,9 @@
pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
- spin_lock(&rb_queue->lock);
+ spin_lock_bh(&rb_queue->lock);
pkc->delete_blk_timer = 1;
- spin_unlock(&rb_queue->lock);
+ spin_unlock_bh(&rb_queue->lock);
prb_del_retire_blk_timer(pkc);
}
@@ -537,6 +565,7 @@
p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
+ p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv);
prb_init_ft_ops(p1, req_u);
prb_setup_retire_blk_timer(po, tx_ring);
prb_open_block(p1, pbd);
@@ -1775,6 +1804,18 @@
if ((int)snaplen < 0)
snaplen = 0;
}
+ } else if (unlikely(macoff + snaplen >
+ GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) {
+ u32 nval;
+
+ nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff;
+ pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n",
+ snaplen, nval, macoff);
+ snaplen = nval;
+ if (unlikely((int)snaplen < 0)) {
+ snaplen = 0;
+ macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len;
+ }
}
spin_lock(&sk->sk_receive_queue.lock);
h.raw = packet_current_rx_frame(po, skb,
@@ -2046,7 +2087,6 @@
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
int err, reserve = 0;
void *ph;
struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name;
@@ -2058,8 +2098,8 @@
mutex_lock(&po->pg_vec_lock);
- if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ if (likely(saddr == NULL)) {
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
@@ -2073,19 +2113,17 @@
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
-
- reserve = dev->hard_header_len;
-
err = -ENETDOWN;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ reserve = dev->hard_header_len;
+
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
@@ -2162,8 +2200,7 @@
__packet_set_status(po, ph, status);
kfree_skb(skb);
out_put:
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
out:
mutex_unlock(&po->pg_vec_lock);
return err;
@@ -2201,7 +2238,6 @@
struct sk_buff *skb;
struct net_device *dev;
__be16 proto;
- bool need_rls_dev = false;
unsigned char *addr;
int err, reserve = 0;
struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2216,8 +2252,8 @@
* Get and verify the address.
*/
- if (saddr == NULL) {
- dev = po->prot_hook.dev;
+ if (likely(saddr == NULL)) {
+ dev = packet_cached_dev_get(po);
proto = po->num;
addr = NULL;
} else {
@@ -2229,19 +2265,17 @@
proto = saddr->sll_protocol;
addr = saddr->sll_addr;
dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
- need_rls_dev = true;
}
err = -ENXIO;
- if (dev == NULL)
+ if (unlikely(dev == NULL))
goto out_unlock;
+ err = -ENETDOWN;
+ if (unlikely(!(dev->flags & IFF_UP)))
+ goto out_unlock;
+
if (sock->type == SOCK_RAW)
reserve = dev->hard_header_len;
-
- err = -ENETDOWN;
- if (!(dev->flags & IFF_UP))
- goto out_unlock;
-
if (po->has_vnet_hdr) {
vnet_hdr_len = sizeof(vnet_hdr);
@@ -2375,15 +2409,14 @@
if (err > 0 && (err = net_xmit_errno(err)) != 0)
goto out_unlock;
- if (need_rls_dev)
- dev_put(dev);
+ dev_put(dev);
return len;
out_free:
kfree_skb(skb);
out_unlock:
- if (dev && need_rls_dev)
+ if (dev)
dev_put(dev);
out:
return err;
@@ -2428,6 +2461,8 @@
spin_lock(&po->bind_lock);
unregister_prot_hook(sk, false);
+ packet_cached_dev_reset(po);
+
if (po->prot_hook.dev) {
dev_put(po->prot_hook.dev);
po->prot_hook.dev = NULL;
@@ -2483,14 +2518,17 @@
spin_lock(&po->bind_lock);
unregister_prot_hook(sk, true);
+
po->num = protocol;
po->prot_hook.type = protocol;
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);
- po->prot_hook.dev = dev;
+ po->prot_hook.dev = dev;
po->ifindex = dev ? dev->ifindex : 0;
+ packet_cached_dev_assign(po, dev);
+
if (protocol == 0)
goto out_unlock;
@@ -2604,6 +2642,8 @@
sk->sk_family = PF_PACKET;
po->num = proto;
+ packet_cached_dev_reset(po);
+
sk->sk_destruct = packet_sock_destruct;
sk_refcnt_debug_inc(sk);
@@ -2694,7 +2734,6 @@
struct sock *sk = sock->sk;
struct sk_buff *skb;
int copied, err;
- struct sockaddr_ll *sll;
int vnet_hdr_len = 0;
err = -EINVAL;
@@ -2777,22 +2816,10 @@
goto out_free;
}
- /*
- * If the address length field is there to be filled in, we fill
- * it in now.
+ /* You lose any data beyond the buffer you gave. If it worries
+ * a user program they can ask the device for its MTU
+ * anyway.
*/
-
- sll = &PACKET_SKB_CB(skb)->sa.ll;
- if (sock->type == SOCK_PACKET)
- msg->msg_namelen = sizeof(struct sockaddr_pkt);
- else
- msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr);
-
- /*
- * You lose any data beyond the buffer you gave. If it worries a
- * user program they can ask the device for its MTU anyway.
- */
-
copied = skb->len;
if (copied > len) {
copied = len;
@@ -2805,9 +2832,20 @@
sock_recv_ts_and_drops(msg, sk, skb);
- if (msg->msg_name)
+ if (msg->msg_name) {
+ /* If the address length field is there to be filled
+ * in, we fill it in now.
+ */
+ if (sock->type == SOCK_PACKET) {
+ msg->msg_namelen = sizeof(struct sockaddr_pkt);
+ } else {
+ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
+ msg->msg_namelen = sll->sll_halen +
+ offsetof(struct sockaddr_ll, sll_addr);
+ }
memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
msg->msg_namelen);
+ }
if (pkt_sk(sk)->auxdata) {
struct tpacket_auxdata aux;
@@ -3259,9 +3297,11 @@
if (po->tp_version == TPACKET_V3) {
lv = sizeof(struct tpacket_stats_v3);
+ st.stats3.tp_packets += st.stats3.tp_drops;
data = &st.stats3;
} else {
lv = sizeof(struct tpacket_stats);
+ st.stats1.tp_packets += st.stats1.tp_drops;
data = &st.stats1;
}
@@ -3356,6 +3396,7 @@
sk->sk_error_report(sk);
}
if (msg == NETDEV_UNREGISTER) {
+ packet_cached_dev_reset(po);
po->ifindex = -1;
if (po->prot_hook.dev)
dev_put(po->prot_hook.dev);
@@ -3614,6 +3655,10 @@
goto out;
if (unlikely(req->tp_block_size & (PAGE_SIZE - 1)))
goto out;
+ if (po->tp_version >= TPACKET_V3 &&
+ (int)(req->tp_block_size -
+ BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+ goto out;
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
po->tp_reserve))
goto out;
diff --git a/net/packet/diag.c b/net/packet/diag.c
index a9584a2..674b0a6 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -127,6 +127,7 @@
static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
struct packet_diag_req *req,
+ bool may_report_filterinfo,
struct user_namespace *user_ns,
u32 portid, u32 seq, u32 flags, int sk_ino)
{
@@ -171,7 +172,8 @@
goto out_nlmsg_trim;
if ((req->pdiag_show & PACKET_SHOW_FILTER) &&
- sock_diag_put_filterinfo(user_ns, sk, skb, PACKET_DIAG_FILTER))
+ sock_diag_put_filterinfo(may_report_filterinfo, sk, skb,
+ PACKET_DIAG_FILTER))
goto out_nlmsg_trim;
return nlmsg_end(skb, nlh);
@@ -187,9 +189,11 @@
struct packet_diag_req *req;
struct net *net;
struct sock *sk;
+ bool may_report_filterinfo;
net = sock_net(skb->sk);
req = nlmsg_data(cb->nlh);
+ may_report_filterinfo = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
mutex_lock(&net->packet.sklist_lock);
sk_for_each(sk, &net->packet.sklist) {
@@ -199,6 +203,7 @@
goto next;
if (sk_diag_fill(sk, skb, req,
+ may_report_filterinfo,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
diff --git a/net/packet/internal.h b/net/packet/internal.h
index c4e4b45..ca086c0 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -29,6 +29,7 @@
char *pkblk_start;
char *pkblk_end;
int kblk_size;
+ unsigned int max_frame_len;
unsigned int knum_blocks;
uint64_t knxt_seq_num;
char *prev;
@@ -113,6 +114,7 @@
unsigned int tp_loss:1;
unsigned int tp_tx_has_off:1;
unsigned int tp_tstamp;
+ struct net_device __rcu *cached_dev;
struct packet_type prot_hook ____cacheline_aligned_in_smp;
};
diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c
index 12c30f3..38946b2 100644
--- a/net/phonet/datagram.c
+++ b/net/phonet/datagram.c
@@ -139,9 +139,6 @@
MSG_CMSG_COMPAT))
goto out_nofree;
- if (addr_len)
- *addr_len = sizeof(sa);
-
skb = skb_recv_datagram(sk, flags, noblock, &rval);
if (skb == NULL)
goto out_nofree;
@@ -162,8 +159,10 @@
rval = (flags & MSG_TRUNC) ? skb->len : copylen;
- if (msg->msg_name != NULL)
- memcpy(msg->msg_name, &sa, sizeof(struct sockaddr_pn));
+ if (msg->msg_name != NULL) {
+ memcpy(msg->msg_name, &sa, sizeof(sa));
+ *addr_len = sizeof(sa);
+ }
out:
skb_free_datagram(sk, skb);
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index dc15f43..b64151a 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -70,10 +70,10 @@
int err;
u8 pnaddr;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- if (!capable(CAP_SYS_ADMIN))
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
return -EPERM;
ASSERT_RTNL();
@@ -233,10 +233,10 @@
int err;
u8 dst;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
- if (!capable(CAP_SYS_ADMIN))
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
return -EPERM;
ASSERT_RTNL();
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b4c8b00..ba2dffe 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -338,7 +338,8 @@
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
/* due to this, we will claim to support iWARP devices unless we
check node_type. */
- if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA)
+ if (ret || !cm_id->device ||
+ cm_id->device->node_type != RDMA_NODE_IB_CA)
ret = -EADDRNOTAVAIL;
rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 8eb9501..b7ebe23 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -421,8 +421,7 @@
struct rds_ib_refill_cache *cache)
{
unsigned long flags;
- struct list_head *old;
- struct list_head __percpu *chpfirst;
+ struct list_head *old, *chpfirst;
local_irq_save(flags);
@@ -432,7 +431,7 @@
else /* put on front */
list_add_tail(new_item, chpfirst);
- __this_cpu_write(chpfirst, new_item);
+ __this_cpu_write(cache->percpu->first, new_item);
__this_cpu_inc(cache->percpu->count);
if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT)
@@ -452,7 +451,7 @@
} while (old);
- __this_cpu_write(chpfirst, NULL);
+ __this_cpu_write(cache->percpu->first, NULL);
__this_cpu_write(cache->percpu->count, 0);
end:
local_irq_restore(flags);
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index e590949..37be6e2 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -552,9 +552,8 @@
&& rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) {
rds_cong_map_updated(conn->c_fcong, ~(u64) 0);
scat = &rm->data.op_sg[sg];
- ret = sizeof(struct rds_header) + RDS_CONG_MAP_BYTES;
- ret = min_t(int, ret, scat->length - conn->c_xmit_data_off);
- return ret;
+ ret = max_t(int, RDS_CONG_MAP_BYTES, scat->length);
+ return sizeof(struct rds_header) + ret;
}
/* FIXME we may overallocate here */
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 7826d46..5899356 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -239,7 +239,8 @@
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
/* due to this, we will claim to support IB devices unless we
check node_type. */
- if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
+ if (ret || !cm_id->device ||
+ cm_id->device->node_type != RDMA_NODE_RNIC)
ret = -EADDRNOTAVAIL;
rdsdebug("addr %pI4 ret %d node type %d\n",
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index a817705..dba8d08 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -88,7 +88,9 @@
int *unpinned);
static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
-static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
+static int rds_iw_get_device(struct sockaddr_in *src, struct sockaddr_in *dst,
+ struct rds_iw_device **rds_iwdev,
+ struct rdma_cm_id **cm_id)
{
struct rds_iw_device *iwdev;
struct rds_iw_cm_id *i_cm_id;
@@ -112,15 +114,15 @@
src_addr->sin_port,
dst_addr->sin_addr.s_addr,
dst_addr->sin_port,
- rs->rs_bound_addr,
- rs->rs_bound_port,
- rs->rs_conn_addr,
- rs->rs_conn_port);
+ src->sin_addr.s_addr,
+ src->sin_port,
+ dst->sin_addr.s_addr,
+ dst->sin_port);
#ifdef WORKING_TUPLE_DETECTION
- if (src_addr->sin_addr.s_addr == rs->rs_bound_addr &&
- src_addr->sin_port == rs->rs_bound_port &&
- dst_addr->sin_addr.s_addr == rs->rs_conn_addr &&
- dst_addr->sin_port == rs->rs_conn_port) {
+ if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr &&
+ src_addr->sin_port == src->sin_port &&
+ dst_addr->sin_addr.s_addr == dst->sin_addr.s_addr &&
+ dst_addr->sin_port == dst->sin_port) {
#else
/* FIXME - needs to compare the local and remote
* ipaddr/port tuple, but the ipaddr is the only
@@ -128,7 +130,7 @@
* zero'ed. It doesn't appear to be properly populated
* during connection setup...
*/
- if (src_addr->sin_addr.s_addr == rs->rs_bound_addr) {
+ if (src_addr->sin_addr.s_addr == src->sin_addr.s_addr) {
#endif
spin_unlock_irq(&iwdev->spinlock);
*rds_iwdev = iwdev;
@@ -180,19 +182,13 @@
{
struct sockaddr_in *src_addr, *dst_addr;
struct rds_iw_device *rds_iwdev_old;
- struct rds_sock rs;
struct rdma_cm_id *pcm_id;
int rc;
src_addr = (struct sockaddr_in *)&cm_id->route.addr.src_addr;
dst_addr = (struct sockaddr_in *)&cm_id->route.addr.dst_addr;
- rs.rs_bound_addr = src_addr->sin_addr.s_addr;
- rs.rs_bound_port = src_addr->sin_port;
- rs.rs_conn_addr = dst_addr->sin_addr.s_addr;
- rs.rs_conn_port = dst_addr->sin_port;
-
- rc = rds_iw_get_device(&rs, &rds_iwdev_old, &pcm_id);
+ rc = rds_iw_get_device(src_addr, dst_addr, &rds_iwdev_old, &pcm_id);
if (rc)
rds_iw_remove_cm_id(rds_iwdev, cm_id);
@@ -598,9 +594,17 @@
struct rds_iw_device *rds_iwdev;
struct rds_iw_mr *ibmr = NULL;
struct rdma_cm_id *cm_id;
+ struct sockaddr_in src = {
+ .sin_addr.s_addr = rs->rs_bound_addr,
+ .sin_port = rs->rs_bound_port,
+ };
+ struct sockaddr_in dst = {
+ .sin_addr.s_addr = rs->rs_conn_addr,
+ .sin_port = rs->rs_conn_port,
+ };
int ret;
- ret = rds_iw_get_device(rs, &rds_iwdev, &cm_id);
+ ret = rds_iw_get_device(&src, &dst, &rds_iwdev, &cm_id);
if (ret || !cm_id) {
ret = -ENODEV;
goto out;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 9f0f17c..de339b2 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -410,8 +410,6 @@
rdsdebug("size %zu flags 0x%x timeo %ld\n", size, msg_flags, timeo);
- msg->msg_namelen = 0;
-
if (msg_flags & MSG_OOB)
goto out;
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index 907214b..fc6cbe8 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -71,14 +71,14 @@
{
.procname = "max_unacked_packets",
.data = &rds_sysctl_max_unacked_packets,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "max_unacked_bytes",
.data = &rds_sysctl_max_unacked_bytes,
- .maxlen = sizeof(unsigned long),
+ .maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 9c83474..27e6896 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1216,7 +1216,6 @@
{
struct sock *sk = sock->sk;
struct rose_sock *rose = rose_sk(sk);
- struct sockaddr_rose *srose = (struct sockaddr_rose *)msg->msg_name;
size_t copied;
unsigned char *asmptr;
struct sk_buff *skb;
@@ -1252,24 +1251,19 @@
skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- if (srose != NULL) {
- memset(srose, 0, msg->msg_namelen);
+ if (msg->msg_name) {
+ struct sockaddr_rose *srose;
+ struct full_sockaddr_rose *full_srose = msg->msg_name;
+
+ memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
+ srose = msg->msg_name;
srose->srose_family = AF_ROSE;
srose->srose_addr = rose->dest_addr;
srose->srose_call = rose->dest_call;
srose->srose_ndigis = rose->dest_ndigis;
- if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) {
- struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name;
- for (n = 0 ; n < rose->dest_ndigis ; n++)
- full_srose->srose_digis[n] = rose->dest_digis[n];
- msg->msg_namelen = sizeof(struct full_sockaddr_rose);
- } else {
- if (rose->dest_ndigis >= 1) {
- srose->srose_ndigis = 1;
- srose->srose_digi = rose->dest_digis[0];
- }
- msg->msg_namelen = sizeof(struct sockaddr_rose);
- }
+ for (n = 0 ; n < rose->dest_ndigis ; n++)
+ full_srose->srose_digis[n] = rose->dest_digis[n];
+ msg->msg_namelen = sizeof(struct full_sockaddr_rose);
}
skb_free_datagram(sk, skb);
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4b48687..5cc2da5 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -87,7 +87,7 @@
if (!skb) {
/* nothing remains on the queue */
if (copied &&
- (msg->msg_flags & MSG_PEEK || timeo == 0))
+ (flags & MSG_PEEK || timeo == 0))
goto out;
/* wait for a message to turn up */
@@ -143,10 +143,13 @@
/* copy the peer address and timestamp */
if (!continue_call) {
- if (msg->msg_name && msg->msg_namelen > 0)
+ if (msg->msg_name) {
+ size_t len =
+ sizeof(call->conn->trans->peer->srx);
memcpy(msg->msg_name,
- &call->conn->trans->peer->srx,
- sizeof(call->conn->trans->peer->srx));
+ &call->conn->trans->peer->srx, len);
+ msg->msg_namelen = len;
+ }
sock_recv_ts_and_drops(msg, &rx->sk, skb);
}
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index fd70728..15d46b9 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -989,7 +989,7 @@
u32 portid = skb ? NETLINK_CB(skb).portid : 0;
int ret = 0, ovr = 0;
- if ((n->nlmsg_type != RTM_GETACTION) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8e118af..2ea40d1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -138,7 +138,7 @@
int err;
int tp_created = 0;
- if ((n->nlmsg_type != RTM_GETTFILTER) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
replay:
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 3a633de..a2abc44 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -227,6 +227,7 @@
* to replay the request.
*/
module_put(em->ops->owner);
+ em->ops = NULL;
err = -EAGAIN;
}
#endif
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 281c1bd..2d2f079 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -285,6 +285,45 @@
return q;
}
+/* The linklayer setting were not transferred from iproute2, in older
+ * versions, and the rate tables lookup systems have been dropped in
+ * the kernel. To keep backward compatible with older iproute2 tc
+ * utils, we detect the linklayer setting by detecting if the rate
+ * table were modified.
+ *
+ * For linklayer ATM table entries, the rate table will be aligned to
+ * 48 bytes, thus some table entries will contain the same value. The
+ * mpu (min packet unit) is also encoded into the old rate table, thus
+ * starting from the mpu, we find low and high table entries for
+ * mapping this cell. If these entries contain the same value, when
+ * the rate tables have been modified for linklayer ATM.
+ *
+ * This is done by rounding mpu to the nearest 48 bytes cell/entry,
+ * and then roundup to the next cell, calc the table entry one below,
+ * and compare.
+ */
+static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab)
+{
+ int low = roundup(r->mpu, 48);
+ int high = roundup(low+1, 48);
+ int cell_low = low >> r->cell_log;
+ int cell_high = (high >> r->cell_log) - 1;
+
+ /* rtab is too inaccurate at rates > 100Mbit/s */
+ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) {
+ pr_debug("TC linklayer: Giving up ATM detection\n");
+ return TC_LINKLAYER_ETHERNET;
+ }
+
+ if ((cell_high > cell_low) && (cell_high < 256)
+ && (rtab[cell_low] == rtab[cell_high])) {
+ pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n",
+ cell_low, cell_high, rtab[cell_high]);
+ return TC_LINKLAYER_ATM;
+ }
+ return TC_LINKLAYER_ETHERNET;
+}
+
static struct qdisc_rate_table *qdisc_rtab_list;
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab)
@@ -308,6 +347,8 @@
rtab->rate = *r;
rtab->refcnt = 1;
memcpy(rtab->data, nla_data(tab), 1024);
+ if (r->linklayer == TC_LINKLAYER_UNAWARE)
+ r->linklayer = __detect_linklayer(r, rtab->data);
rtab->next = qdisc_rtab_list;
qdisc_rtab_list = rtab;
}
@@ -983,7 +1024,7 @@
struct Qdisc *p = NULL;
int err;
- if ((n->nlmsg_type != RTM_GETQDISC) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1050,7 +1091,7 @@
struct Qdisc *q, *p;
int err;
- if (!capable(CAP_NET_ADMIN))
+ if (!netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
replay:
@@ -1390,7 +1431,7 @@
u32 qid;
int err;
- if ((n->nlmsg_type != RTM_GETTCLASS) && !capable(CAP_NET_ADMIN))
+ if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
return -EPERM;
err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index ca8e0a5..1f9c314 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -605,6 +605,7 @@
struct sockaddr_atmpvc pvc;
int state;
+ memset(&pvc, 0, sizeof(pvc));
pvc.sap_family = AF_ATMPVC;
pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1;
pvc.sap_addr.vpi = flow->vcc->vpi;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 1bc210f..8ec1598 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1465,6 +1465,7 @@
unsigned char *b = skb_tail_pointer(skb);
struct tc_cbq_wrropt opt;
+ memset(&opt, 0, sizeof(opt));
opt.flags = 0;
opt.allot = cl->allot;
opt.priority = cl->priority + 1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2022408..a7f838b 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -908,6 +908,7 @@
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
r->rate_bps = (u64)conf->rate << 3;
+ r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
* Calibrate mult, shift so that token counting is accurate
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index adaedd7..e09b074 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -87,7 +87,7 @@
unsigned int children;
struct htb_class *parent; /* parent class */
- int prio; /* these two are used only by leaves... */
+ u32 prio; /* these two are used only by leaves... */
int quantum; /* but stored for parent-to-leaf return */
union {
@@ -1312,6 +1312,7 @@
struct htb_sched *q = qdisc_priv(sch);
struct htb_class *cl = (struct htb_class *)*arg, *parent;
struct nlattr *opt = tca[TCA_OPTIONS];
+ struct qdisc_rate_table *rtab = NULL, *ctab = NULL;
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_opt *hopt;
@@ -1333,6 +1334,18 @@
if (!hopt->rate.rate || !hopt->ceil.rate)
goto failure;
+ /* Keeping backward compatible with rate_table based iproute2 tc */
+ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) {
+ rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]);
+ if (rtab)
+ qdisc_put_rtab(rtab);
+ }
+ if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) {
+ ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]);
+ if (ctab)
+ qdisc_put_rtab(ctab);
+ }
+
if (!cl) { /* new class */
struct Qdisc *new_q;
int prio;
@@ -1463,7 +1476,7 @@
psched_ratecfg_precompute(&cl->ceil, &hopt->ceil);
cl->buffer = PSCHED_TICKS2NS(hopt->buffer);
- cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer);
+ cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
sch_tree_unlock(sch);
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index d51852b..5792252 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -113,7 +113,6 @@
#define FRAC_BITS 30 /* fixed point arithmetic */
#define ONE_FP (1UL << FRAC_BITS)
-#define IWSUM (ONE_FP/QFQ_MAX_WSUM)
#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */
#define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */
@@ -189,6 +188,7 @@
struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */
u32 num_active_agg; /* Num. of active aggregates */
u32 wsum; /* weight sum */
+ u32 iwsum; /* inverse weight sum */
unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */
struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */
@@ -314,6 +314,7 @@
q->wsum +=
(int) agg->class_weight * (new_num_classes - agg->num_classes);
+ q->iwsum = ONE_FP / q->wsum;
agg->num_classes = new_num_classes;
}
@@ -340,6 +341,10 @@
{
if (!hlist_unhashed(&agg->nonfull_next))
hlist_del_init(&agg->nonfull_next);
+ q->wsum -= agg->class_weight;
+ if (q->wsum != 0)
+ q->iwsum = ONE_FP / q->wsum;
+
if (q->in_serv_agg == agg)
q->in_serv_agg = qfq_choose_next_agg(q);
kfree(agg);
@@ -827,38 +832,60 @@
}
}
-
/*
- * The index of the slot in which the aggregate is to be inserted must
- * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1'
- * because the start time of the group may be moved backward by one
- * slot after the aggregate has been inserted, and this would cause
- * non-empty slots to be right-shifted by one position.
+ * The index of the slot in which the input aggregate agg is to be
+ * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2'
+ * and not a '-1' because the start time of the group may be moved
+ * backward by one slot after the aggregate has been inserted, and
+ * this would cause non-empty slots to be right-shifted by one
+ * position.
*
- * If the weight and lmax (max_pkt_size) of the classes do not change,
- * then QFQ+ does meet the above contraint according to the current
- * values of its parameters. In fact, if the weight and lmax of the
- * classes do not change, then, from the theory, QFQ+ guarantees that
- * the slot index is never higher than
- * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
- * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18
+ * QFQ+ fully satisfies this bound to the slot index if the parameters
+ * of the classes are not changed dynamically, and if QFQ+ never
+ * happens to postpone the service of agg unjustly, i.e., it never
+ * happens that the aggregate becomes backlogged and eligible, or just
+ * eligible, while an aggregate with a higher approximated finish time
+ * is being served. In particular, in this case QFQ+ guarantees that
+ * the timestamps of agg are low enough that the slot index is never
+ * higher than 2. Unfortunately, QFQ+ cannot provide the same
+ * guarantee if it happens to unjustly postpone the service of agg, or
+ * if the parameters of some class are changed.
*
- * When the weight of a class is increased or the lmax of the class is
- * decreased, a new aggregate with smaller slot size than the original
- * parent aggregate of the class may happen to be activated. The
- * activation of this aggregate should be properly delayed to when the
- * service of the class has finished in the ideal system tracked by
- * QFQ+. If the activation of the aggregate is not delayed to this
- * reference time instant, then this aggregate may be unjustly served
- * before other aggregates waiting for service. This may cause the
- * above bound to the slot index to be violated for some of these
- * unlucky aggregates.
+ * As for the first event, i.e., an out-of-order service, the
+ * upper bound to the slot index guaranteed by QFQ+ grows to
+ * 2 +
+ * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) *
+ * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1.
+ *
+ * The following function deals with this problem by backward-shifting
+ * the timestamps of agg, if needed, so as to guarantee that the slot
+ * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may
+ * cause the service of other aggregates to be postponed, yet the
+ * worst-case guarantees of these aggregates are not violated. In
+ * fact, in case of no out-of-order service, the timestamps of agg
+ * would have been even lower than they are after the backward shift,
+ * because QFQ+ would have guaranteed a maximum value equal to 2 for
+ * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose
+ * service is postponed because of the backward-shift would have
+ * however waited for the service of agg before being served.
+ *
+ * The other event that may cause the slot index to be higher than 2
+ * for agg is a recent change of the parameters of some class. If the
+ * weight of a class is increased or the lmax (max_pkt_size) of the
+ * class is decreased, then a new aggregate with smaller slot size
+ * than the original parent aggregate of the class may happen to be
+ * activated. The activation of this aggregate should be properly
+ * delayed to when the service of the class has finished in the ideal
+ * system tracked by QFQ+. If the activation of the aggregate is not
+ * delayed to this reference time instant, then this aggregate may be
+ * unjustly served before other aggregates waiting for service. This
+ * may cause the above bound to the slot index to be violated for some
+ * of these unlucky aggregates.
*
* Instead of delaying the activation of the new aggregate, which is
- * quite complex, the following inaccurate but simple solution is used:
- * if the slot index is higher than QFQ_MAX_SLOTS-2, then the
- * timestamps of the aggregate are shifted backward so as to let the
- * slot index become equal to QFQ_MAX_SLOTS-2.
+ * quite complex, the above-discussed capping of the slot index is
+ * used to handle also the consequences of a change of the parameters
+ * of a class.
*/
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg,
u64 roundedS)
@@ -1077,7 +1104,7 @@
else
in_serv_agg->budget -= len;
- q->V += (u64)len * IWSUM;
+ q->V += (u64)len * q->iwsum;
pr_debug("qfq dequeue: len %u F %lld now %lld\n",
len, (unsigned long long) in_serv_agg->F,
(unsigned long long) q->V);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 91cfd8f..6360a14 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -387,7 +387,7 @@
/* Only real associations count against the endpoint, so
* don't bother for if this is a temporary association.
*/
- if (!asoc->temp) {
+ if (!list_empty(&asoc->asocs)) {
list_del(&asoc->asocs);
/* Decrement the backlog value for a TCP-style listening
@@ -1213,6 +1213,7 @@
asoc->c = new->c;
asoc->peer.rwnd = new->peer.rwnd;
asoc->peer.sack_needed = new->peer.sack_needed;
+ asoc->peer.auth_capable = new->peer.auth_capable;
asoc->peer.i = new->peer.i;
sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
asoc->peer.i.initial_tsn, GFP_ATOMIC);
@@ -1296,7 +1297,6 @@
asoc->peer.peer_hmacs = new->peer.peer_hmacs;
new->peer.peer_hmacs = NULL;
- sctp_auth_key_put(asoc->asoc_shared_key);
sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC);
}
@@ -1658,6 +1658,8 @@
* ack chunk whose serial number matches that of the request.
*/
list_for_each_entry(ack, &asoc->asconf_ack_list, transmitted_list) {
+ if (sctp_chunk_pending(ack))
+ continue;
if (ack->subh.addip_hdr->serial == serial) {
sctp_chunk_hold(ack);
return ack;
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index ba1dfc3..bc2fae7 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -393,14 +393,13 @@
*/
int sctp_auth_asoc_init_active_key(struct sctp_association *asoc, gfp_t gfp)
{
- struct net *net = sock_net(asoc->base.sk);
struct sctp_auth_bytes *secret;
struct sctp_shared_key *ep_key;
/* If we don't support AUTH, or peer is not capable
* we don't need to do anything.
*/
- if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+ if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
return 0;
/* If the key_id is non-zero and we couldn't find an
@@ -447,16 +446,16 @@
*/
int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp)
{
- struct net *net = sock_net(ep->base.sk);
struct crypto_hash *tfm = NULL;
__u16 id;
- /* if the transforms are already allocted, we are done */
- if (!net->sctp.auth_enable) {
+ /* If AUTH extension is disabled, we are done */
+ if (!ep->auth_enable) {
ep->auth_hmacs = NULL;
return 0;
}
+ /* If the transforms are already allocated, we are done */
if (ep->auth_hmacs)
return 0;
@@ -677,12 +676,10 @@
/* Check if peer requested that this chunk is authenticated */
int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
{
- struct net *net;
if (!asoc)
return 0;
- net = sock_net(asoc->base.sk);
- if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
+ if (!asoc->ep->auth_enable || !asoc->peer.auth_capable)
return 0;
return __sctp_auth_cid(chunk, asoc->peer.peer_chunks);
@@ -691,12 +688,10 @@
/* Check if we requested that peer authenticate this chunk. */
int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc)
{
- struct net *net;
if (!asoc)
return 0;
- net = sock_net(asoc->base.sk);
- if (!net->sctp.auth_enable)
+ if (!asoc->ep->auth_enable)
return 0;
return __sctp_auth_cid(chunk,
@@ -879,8 +874,6 @@
list_add(&cur_key->key_list, sh_keys);
cur_key->key = key;
- sctp_auth_key_hold(key);
-
return 0;
nomem:
if (!replace)
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 5fbd7bc..e09f906 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -75,7 +75,8 @@
if (!ep->digest)
return NULL;
- if (net->sctp.auth_enable) {
+ ep->auth_enable = net->sctp.auth_enable;
+ if (ep->auth_enable) {
/* Allocate space for HMACS and CHUNKS authentication
* variables. There are arrays that we encode directly
* into parameters to make the rest of the operations easier.
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 4b2c831..bd4fb45 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -648,8 +648,7 @@
break;
case ICMP_REDIRECT:
sctp_icmp_redirect(sk, transport, skb);
- err = 0;
- break;
+ /* Fall through to out_unlock. */
default:
goto out_unlock;
}
diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c
index 3221d07..49c58ea 100644
--- a/net/sctp/inqueue.c
+++ b/net/sctp/inqueue.c
@@ -147,18 +147,9 @@
} else {
/* Nothing to do. Next chunk in the packet, please. */
ch = (sctp_chunkhdr_t *) chunk->chunk_end;
-
/* Force chunk->skb->data to chunk->chunk_end. */
- skb_pull(chunk->skb,
- chunk->chunk_end - chunk->skb->data);
-
- /* Verify that we have at least chunk headers
- * worth of buffer left.
- */
- if (skb_headlen(chunk->skb) < sizeof(sctp_chunkhdr_t)) {
- sctp_chunk_free(chunk);
- chunk = queue->in_progress = NULL;
- }
+ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data);
+ /* We are guaranteed to pull a SCTP header. */
}
}
@@ -194,24 +185,14 @@
skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
chunk->subh.v = NULL; /* Subheader is no longer valid. */
- if (chunk->chunk_end < skb_tail_pointer(chunk->skb)) {
+ if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) <
+ skb_tail_pointer(chunk->skb)) {
/* This is not a singleton */
chunk->singleton = 0;
} else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) {
- /* RFC 2960, Section 6.10 Bundling
- *
- * Partial chunks MUST NOT be placed in an SCTP packet.
- * If the receiver detects a partial chunk, it MUST drop
- * the chunk.
- *
- * Since the end of the chunk is past the end of our buffer
- * (which contains the whole packet, we can freely discard
- * the whole packet.
- */
- sctp_chunk_free(chunk);
- chunk = queue->in_progress = NULL;
-
- return NULL;
+ /* Discard inside state machine. */
+ chunk->pdiscard = 1;
+ chunk->chunk_end = skb_tail_pointer(chunk->skb);
} else {
/* We are at the end of the packet, so mark the chunk
* in case we need to send a SACK.
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 391a245..422d8bd 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -189,7 +189,7 @@
break;
case NDISC_REDIRECT:
sctp_icmp_redirect(sk, transport, skb);
- break;
+ goto out_unlock;
default:
break;
}
@@ -210,45 +210,24 @@
in6_dev_put(idev);
}
-/* Based on tcp_v6_xmit() in tcp_ipv6.c. */
static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
{
struct sock *sk = skb->sk;
struct ipv6_pinfo *np = inet6_sk(sk);
- struct flowi6 fl6;
-
- memset(&fl6, 0, sizeof(fl6));
-
- fl6.flowi6_proto = sk->sk_protocol;
-
- /* Fill in the dest address from the route entry passed with the skb
- * and the source address from the transport.
- */
- fl6.daddr = transport->ipaddr.v6.sin6_addr;
- fl6.saddr = transport->saddr.v6.sin6_addr;
-
- fl6.flowlabel = np->flow_label;
- IP6_ECN_flow_xmit(sk, fl6.flowlabel);
- if (ipv6_addr_type(&fl6.saddr) & IPV6_ADDR_LINKLOCAL)
- fl6.flowi6_oif = transport->saddr.v6.sin6_scope_id;
- else
- fl6.flowi6_oif = sk->sk_bound_dev_if;
-
- if (np->opt && np->opt->srcrt) {
- struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
- fl6.daddr = *rt0->addr;
- }
+ struct flowi6 *fl6 = &transport->fl.u.ip6;
SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n",
__func__, skb, skb->len,
- &fl6.saddr, &fl6.daddr);
+ &fl6->saddr, &fl6->daddr);
- SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
+ IP6_ECN_flow_xmit(sk, fl6->flowlabel);
if (!(transport->param_flags & SPP_PMTUD_ENABLE))
skb->local_df = 1;
- return ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
+ SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
+
+ return ip6_xmit(sk, skb, fl6, np->opt, np->tclass);
}
/* Returns the dst cache entry for the given source and destination ip
@@ -261,10 +240,12 @@
struct dst_entry *dst = NULL;
struct flowi6 *fl6 = &fl->u.ip6;
struct sctp_bind_addr *bp;
+ struct ipv6_pinfo *np = inet6_sk(sk);
struct sctp_sockaddr_entry *laddr;
union sctp_addr *baddr = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
+ struct in6_addr *final_p, final;
__u8 matchlen = 0;
__u8 bmatchlen;
sctp_scope_t scope;
@@ -287,7 +268,8 @@
SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr);
}
- dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
+ final_p = fl6_update_dst(fl6, np->opt, &final);
+ dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
if (!asoc || saddr)
goto out;
@@ -339,10 +321,12 @@
}
}
rcu_read_unlock();
+
if (baddr) {
fl6->saddr = baddr->v6.sin6_addr;
fl6->fl6_sport = baddr->v6.sin6_port;
- dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
+ final_p = fl6_update_dst(fl6, np->opt, &final);
+ dst = ip6_dst_lookup_flow(sk, fl6, final_p, false);
}
out:
diff --git a/net/sctp/output.c b/net/sctp/output.c
index bbef4a7..73b8ca5 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -413,12 +413,12 @@
sk = chunk->skb->sk;
/* Allocate the new skb. */
- nskb = alloc_skb(packet->size + LL_MAX_HEADER, GFP_ATOMIC);
+ nskb = alloc_skb(packet->size + MAX_HEADER, GFP_ATOMIC);
if (!nskb)
goto nomem;
/* Make sure the outbound skb has enough header room reserved. */
- skb_reserve(nskb, packet->overhead + LL_MAX_HEADER);
+ skb_reserve(nskb, packet->overhead + MAX_HEADER);
/* Set the owning socket so that we know where to get the
* destination IP address.
@@ -547,7 +547,8 @@
* by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
*/
if (!sctp_checksum_disable) {
- if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) {
+ if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
+ (dst_xfrm(dst) != NULL) || packet->ipfragok) {
__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
/* 3) Put the resultant value into the checksum field in the
@@ -617,7 +618,7 @@
return err;
no_route:
kfree_skb(nskb);
- IP_INC_STATS_BH(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
+ IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
/* FIXME: Returning the 'err' will effect all the associations
* associated with a socket, although only one of the paths of the
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index eaee00c..5a3c1c0 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -498,8 +498,13 @@
continue;
if ((laddr->state == SCTP_ADDR_SRC) &&
(AF_INET == laddr->a.sa.sa_family)) {
- fl4->saddr = laddr->a.v4.sin_addr.s_addr;
fl4->fl4_sport = laddr->a.v4.sin_port;
+ flowi4_update_output(fl4,
+ asoc->base.sk->sk_bound_dev_if,
+ RT_CONN_FLAGS(asoc->base.sk),
+ daddr->v4.sin_addr.s_addr,
+ laddr->a.v4.sin_addr.s_addr);
+
rt = ip_route_output_key(sock_net(sk), fl4);
if (!IS_ERR(rt)) {
dst = &rt->dst;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index cf579e7..beedadf 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -199,6 +199,7 @@
gfp_t gfp, int vparam_len)
{
struct net *net = sock_net(asoc->base.sk);
+ struct sctp_endpoint *ep = asoc->ep;
sctp_inithdr_t init;
union sctp_params addrs;
size_t chunksize;
@@ -258,7 +259,7 @@
chunksize += vparam_len;
/* Account for AUTH related parameters */
- if (net->sctp.auth_enable) {
+ if (ep->auth_enable) {
/* Add random parameter length*/
chunksize += sizeof(asoc->c.auth_random);
@@ -343,7 +344,7 @@
}
/* Add SCTP-AUTH chunks to the parameter list */
- if (net->sctp.auth_enable) {
+ if (ep->auth_enable) {
sctp_addto_chunk(retval, sizeof(asoc->c.auth_random),
asoc->c.auth_random);
if (auth_hmacs)
@@ -1403,8 +1404,8 @@
BUG_ON(!list_empty(&chunk->list));
list_del_init(&chunk->transmitted_list);
- /* Free the chunk skb data and the SCTP_chunk stub itself. */
- dev_kfree_skb(chunk->skb);
+ consume_skb(chunk->skb);
+ consume_skb(chunk->auth_chunk);
SCTP_DBG_OBJCNT_DEC(chunk);
kmem_cache_free(sctp_chunk_cachep, chunk);
@@ -1995,7 +1996,7 @@
/* if the peer reports AUTH, assume that he
* supports AUTH.
*/
- if (net->sctp.auth_enable)
+ if (asoc->ep->auth_enable)
asoc->peer.auth_capable = 1;
break;
case SCTP_CID_ASCONF:
@@ -2087,6 +2088,7 @@
* SCTP_IERROR_NO_ERROR - continue with the chunk
*/
static sctp_ierror_t sctp_verify_param(struct net *net,
+ const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
union sctp_params param,
sctp_cid_t cid,
@@ -2137,7 +2139,7 @@
goto fallthrough;
case SCTP_PARAM_RANDOM:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fallthrough;
/* SCTP-AUTH: Secion 6.1
@@ -2154,7 +2156,7 @@
break;
case SCTP_PARAM_CHUNKS:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fallthrough;
/* SCTP-AUTH: Section 3.2
@@ -2170,7 +2172,7 @@
break;
case SCTP_PARAM_HMAC_ALGO:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fallthrough;
hmacs = (struct sctp_hmac_algo_param *)param.p;
@@ -2204,10 +2206,9 @@
}
/* Verify the INIT packet before we process it. */
-int sctp_verify_init(struct net *net, const struct sctp_association *asoc,
- sctp_cid_t cid,
- sctp_init_chunk_t *peer_init,
- struct sctp_chunk *chunk,
+int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc, sctp_cid_t cid,
+ sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk,
struct sctp_chunk **errp)
{
union sctp_params param;
@@ -2250,8 +2251,8 @@
/* Verify all the variable length parameters */
sctp_walk_params(param, peer_init, init_hdr.params) {
-
- result = sctp_verify_param(net, asoc, param, cid, chunk, errp);
+ result = sctp_verify_param(net, ep, asoc, param, cid,
+ chunk, errp);
switch (result) {
case SCTP_IERROR_ABORT:
case SCTP_IERROR_NOMEM:
@@ -2483,6 +2484,7 @@
struct sctp_af *af;
union sctp_addr_param *addr_param;
struct sctp_transport *t;
+ struct sctp_endpoint *ep = asoc->ep;
/* We maintain all INIT parameters in network byte order all the
* time. This allows us to not worry about whether the parameters
@@ -2593,7 +2595,10 @@
addr_param = param.v + sizeof(sctp_addip_param_t);
- af = sctp_get_af_specific(param_type2af(param.p->type));
+ af = sctp_get_af_specific(param_type2af(addr_param->p.type));
+ if (af == NULL)
+ break;
+
af->from_addr_param(&addr, addr_param,
htons(asoc->peer.port), 0);
@@ -2623,7 +2628,7 @@
goto fall_through;
case SCTP_PARAM_RANDOM:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fall_through;
/* Save peer's random parameter */
@@ -2636,7 +2641,7 @@
break;
case SCTP_PARAM_HMAC_ALGO:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fall_through;
/* Save peer's HMAC list */
@@ -2652,7 +2657,7 @@
break;
case SCTP_PARAM_CHUNKS:
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
goto fall_through;
asoc->peer.peer_chunks = kmemdup(param.p,
@@ -3092,50 +3097,63 @@
return SCTP_ERROR_NO_ERROR;
}
-/* Verify the ASCONF packet before we process it. */
-int sctp_verify_asconf(const struct sctp_association *asoc,
- struct sctp_paramhdr *param_hdr, void *chunk_end,
- struct sctp_paramhdr **errp) {
- sctp_addip_param_t *asconf_param;
+/* Verify the ASCONF packet before we process it. */
+bool sctp_verify_asconf(const struct sctp_association *asoc,
+ struct sctp_chunk *chunk, bool addr_param_needed,
+ struct sctp_paramhdr **errp)
+{
+ sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) chunk->chunk_hdr;
union sctp_params param;
- int length, plen;
+ bool addr_param_seen = false;
- param.v = (sctp_paramhdr_t *) param_hdr;
- while (param.v <= chunk_end - sizeof(sctp_paramhdr_t)) {
- length = ntohs(param.p->length);
+ sctp_walk_params(param, addip, addip_hdr.params) {
+ size_t length = ntohs(param.p->length);
+
*errp = param.p;
-
- if (param.v > chunk_end - length ||
- length < sizeof(sctp_paramhdr_t))
- return 0;
-
switch (param.p->type) {
+ case SCTP_PARAM_ERR_CAUSE:
+ break;
+ case SCTP_PARAM_IPV4_ADDRESS:
+ if (length != sizeof(sctp_ipv4addr_param_t))
+ return false;
+ addr_param_seen = true;
+ break;
+ case SCTP_PARAM_IPV6_ADDRESS:
+ if (length != sizeof(sctp_ipv6addr_param_t))
+ return false;
+ addr_param_seen = true;
+ break;
case SCTP_PARAM_ADD_IP:
case SCTP_PARAM_DEL_IP:
case SCTP_PARAM_SET_PRIMARY:
- asconf_param = (sctp_addip_param_t *)param.v;
- plen = ntohs(asconf_param->param_hdr.length);
- if (plen < sizeof(sctp_addip_param_t) +
- sizeof(sctp_paramhdr_t))
- return 0;
+ /* In ASCONF chunks, these need to be first. */
+ if (addr_param_needed && !addr_param_seen)
+ return false;
+ length = ntohs(param.addip->param_hdr.length);
+ if (length < sizeof(sctp_addip_param_t) +
+ sizeof(sctp_paramhdr_t))
+ return false;
break;
case SCTP_PARAM_SUCCESS_REPORT:
case SCTP_PARAM_ADAPTATION_LAYER_IND:
if (length != sizeof(sctp_addip_param_t))
- return 0;
-
+ return false;
break;
default:
- break;
+ /* This is unkown to us, reject! */
+ return false;
}
-
- param.v += WORD_ROUND(length);
}
- if (param.v != chunk_end)
- return 0;
+ /* Remaining sanity checks. */
+ if (addr_param_needed && !addr_param_seen)
+ return false;
+ if (!addr_param_needed && addr_param_seen)
+ return false;
+ if (param.v != chunk->chunk_end)
+ return false;
- return 1;
+ return true;
}
/* Process an incoming ASCONF chunk with the next expected serial no. and
@@ -3144,16 +3162,17 @@
struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc,
struct sctp_chunk *asconf)
{
+ sctp_addip_chunk_t *addip = (sctp_addip_chunk_t *) asconf->chunk_hdr;
+ bool all_param_pass = true;
+ union sctp_params param;
sctp_addiphdr_t *hdr;
union sctp_addr_param *addr_param;
sctp_addip_param_t *asconf_param;
struct sctp_chunk *asconf_ack;
-
__be16 err_code;
int length = 0;
int chunk_len;
__u32 serial;
- int all_param_pass = 1;
chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t);
hdr = (sctp_addiphdr_t *)asconf->skb->data;
@@ -3181,9 +3200,14 @@
goto done;
/* Process the TLVs contained within the ASCONF chunk. */
- while (chunk_len > 0) {
+ sctp_walk_params(param, addip, addip_hdr.params) {
+ /* Skip preceeding address parameters. */
+ if (param.p->type == SCTP_PARAM_IPV4_ADDRESS ||
+ param.p->type == SCTP_PARAM_IPV6_ADDRESS)
+ continue;
+
err_code = sctp_process_asconf_param(asoc, asconf,
- asconf_param);
+ param.addip);
/* ADDIP 4.1 A7)
* If an error response is received for a TLV parameter,
* all TLVs with no response before the failed TLV are
@@ -3191,28 +3215,20 @@
* the failed response are considered unsuccessful unless
* a specific success indication is present for the parameter.
*/
- if (SCTP_ERROR_NO_ERROR != err_code)
- all_param_pass = 0;
-
+ if (err_code != SCTP_ERROR_NO_ERROR)
+ all_param_pass = false;
if (!all_param_pass)
- sctp_add_asconf_response(asconf_ack,
- asconf_param->crr_id, err_code,
- asconf_param);
+ sctp_add_asconf_response(asconf_ack, param.addip->crr_id,
+ err_code, param.addip);
/* ADDIP 4.3 D11) When an endpoint receiving an ASCONF to add
* an IP address sends an 'Out of Resource' in its response, it
* MUST also fail any subsequent add or delete requests bundled
* in the ASCONF.
*/
- if (SCTP_ERROR_RSRC_LOW == err_code)
+ if (err_code == SCTP_ERROR_RSRC_LOW)
goto done;
-
- /* Move to the next ASCONF param. */
- length = ntohs(asconf_param->param_hdr.length);
- asconf_param = (void *)asconf_param + length;
- chunk_len -= length;
}
-
done:
asoc->peer.addip_serial++;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index de1a013..c52763a 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -177,6 +177,9 @@
{
__u16 chunk_length = ntohs(chunk->chunk_hdr->length);
+ /* Previously already marked? */
+ if (unlikely(chunk->pdiscard))
+ return 0;
if (unlikely(chunk_length < required_length))
return 0;
@@ -364,7 +367,7 @@
/* Verify the INIT chunk before processing it. */
err_chunk = NULL;
- if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+ if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
(sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
&err_chunk)) {
/* This chunk contains fatal error. It is to be discarded.
@@ -531,7 +534,7 @@
/* Verify the INIT chunk before processing it. */
err_chunk = NULL;
- if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+ if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
(sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
&err_chunk)) {
@@ -765,6 +768,12 @@
struct sctp_chunk auth;
sctp_ierror_t ret;
+ /* Make sure that we and the peer are AUTH capable */
+ if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
+ sctp_association_free(new_asoc);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ }
+
/* set-up our fake chunk so that we can process it */
auth.skb = chunk->auth_chunk;
auth.asoc = chunk->asoc;
@@ -775,10 +784,6 @@
auth.transport = chunk->transport;
ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
-
- /* We can now safely free the auth_chunk clone */
- kfree_skb(chunk->auth_chunk);
-
if (ret != SCTP_IERROR_NO_ERROR) {
sctp_association_free(new_asoc);
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -1435,7 +1440,7 @@
/* Verify the INIT chunk before processing it. */
err_chunk = NULL;
- if (!sctp_verify_init(net, asoc, chunk->chunk_hdr->type,
+ if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type,
(sctp_init_chunk_t *)chunk->chunk_hdr, chunk,
&err_chunk)) {
/* This chunk contains fatal error. It is to be discarded.
@@ -1780,9 +1785,22 @@
/* Update the content of current association. */
sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev));
- sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
- SCTP_STATE(SCTP_STATE_ESTABLISHED));
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+ if (sctp_state(asoc, SHUTDOWN_PENDING) &&
+ (sctp_sstate(asoc->base.sk, CLOSING) ||
+ sock_flag(asoc->base.sk, SOCK_DEAD))) {
+ /* if were currently in SHUTDOWN_PENDING, but the socket
+ * has been closed by user, don't transition to ESTABLISHED.
+ * Instead trigger SHUTDOWN bundled with COOKIE_ACK.
+ */
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+ return sctp_sf_do_9_2_start_shutdown(net, ep, asoc,
+ SCTP_ST_CHUNK(0), NULL,
+ commands);
+ } else {
+ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
+ SCTP_STATE(SCTP_STATE_ESTABLISHED));
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl));
+ }
return SCTP_DISPOSITION_CONSUME;
nomem_ev:
@@ -3578,9 +3596,7 @@
struct sctp_chunk *asconf_ack = NULL;
struct sctp_paramhdr *err_param = NULL;
sctp_addiphdr_t *hdr;
- union sctp_addr_param *addr_param;
__u32 serial;
- int length;
if (!sctp_vtag_verify(chunk, asoc)) {
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_BAD_TAG,
@@ -3605,17 +3621,8 @@
hdr = (sctp_addiphdr_t *)chunk->skb->data;
serial = ntohl(hdr->serial);
- addr_param = (union sctp_addr_param *)hdr->params;
- length = ntohs(addr_param->p.length);
- if (length < sizeof(sctp_paramhdr_t))
- return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
- (void *)addr_param, commands);
-
/* Verify the ASCONF chunk before processing it. */
- if (!sctp_verify_asconf(asoc,
- (sctp_paramhdr_t *)((void *)addr_param + length),
- (void *)chunk->chunk_end,
- &err_param))
+ if (!sctp_verify_asconf(asoc, chunk, true, &err_param))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)err_param, commands);
@@ -3733,10 +3740,7 @@
rcvd_serial = ntohl(addip_hdr->serial);
/* Verify the ASCONF-ACK chunk before processing it. */
- if (!sctp_verify_asconf(asoc,
- (sctp_paramhdr_t *)addip_hdr->params,
- (void *)asconf_ack->chunk_end,
- &err_param))
+ if (!sctp_verify_asconf(asoc, asconf_ack, false, &err_param))
return sctp_sf_violation_paramlen(net, ep, asoc, type, arg,
(void *)err_param, commands);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6abb1ca..dfb9b13 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -71,6 +71,7 @@
#include <linux/crypto.h>
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/compat.h>
#include <net/ip.h>
#include <net/icmp.h>
@@ -820,6 +821,9 @@
goto skip_mkasconf;
}
+ if (laddr == NULL)
+ return -EINVAL;
+
/* We do not need RCU protection throughout this loop
* because this is done under a socket lock from the
* setsockopt call.
@@ -1381,11 +1385,19 @@
/*
* New (hopefully final) interface for the API.
* We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations. The only defferent part
+ * can avoid any unnecessary allocations. The only different part
* is that we store the actual length of the address buffer into the
- * addrs_num structure member. That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
* code.
*/
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+ sctp_assoc_t assoc_id;
+ s32 addr_num;
+ compat_uptr_t addrs; /* struct sockaddr * */
+};
+#endif
+
SCTP_STATIC int sctp_getsockopt_connectx3(struct sock* sk, int len,
char __user *optval,
int __user *optlen)
@@ -1394,16 +1406,30 @@
sctp_assoc_t assoc_id = 0;
int err = 0;
- if (len < sizeof(param))
- return -EINVAL;
+#ifdef CONFIG_COMPAT
+ if (is_compat_task()) {
+ struct compat_sctp_getaddrs_old param32;
- if (copy_from_user(¶m, optval, sizeof(param)))
- return -EFAULT;
+ if (len < sizeof(param32))
+ return -EINVAL;
+ if (copy_from_user(¶m32, optval, sizeof(param32)))
+ return -EFAULT;
- err = __sctp_setsockopt_connectx(sk,
- (struct sockaddr __user *)param.addrs,
- param.addr_num, &assoc_id);
+ param.assoc_id = param32.assoc_id;
+ param.addr_num = param32.addr_num;
+ param.addrs = compat_ptr(param32.addrs);
+ } else
+#endif
+ {
+ if (len < sizeof(param))
+ return -EINVAL;
+ if (copy_from_user(¶m, optval, sizeof(param)))
+ return -EFAULT;
+ }
+ err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+ param.addrs, param.addr_num,
+ &assoc_id);
if (err == 0 || err == -EINPROGRESS) {
if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
return -EFAULT;
@@ -3292,10 +3318,10 @@
char __user *optval,
unsigned int optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authchunk val;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (optlen != sizeof(struct sctp_authchunk))
@@ -3312,7 +3338,7 @@
}
/* add this chunk id to the endpoint */
- return sctp_auth_ep_add_chunkid(sctp_sk(sk)->ep, val.sauth_chunk);
+ return sctp_auth_ep_add_chunkid(ep, val.sauth_chunk);
}
/*
@@ -3325,12 +3351,12 @@
char __user *optval,
unsigned int optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_hmacalgo *hmacs;
u32 idents;
int err;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (optlen < sizeof(struct sctp_hmacalgo))
@@ -3347,7 +3373,7 @@
goto out;
}
- err = sctp_auth_ep_set_hmacs(sctp_sk(sk)->ep, hmacs);
+ err = sctp_auth_ep_set_hmacs(ep, hmacs);
out:
kfree(hmacs);
return err;
@@ -3363,12 +3389,12 @@
char __user *optval,
unsigned int optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authkey *authkey;
struct sctp_association *asoc;
int ret;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (optlen <= sizeof(struct sctp_authkey))
@@ -3389,7 +3415,7 @@
goto out;
}
- ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey);
+ ret = sctp_auth_set_key(ep, asoc, authkey);
out:
kzfree(authkey);
return ret;
@@ -3405,11 +3431,11 @@
char __user *optval,
unsigned int optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authkeyid val;
struct sctp_association *asoc;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (optlen != sizeof(struct sctp_authkeyid))
@@ -3421,8 +3447,7 @@
if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
return -EINVAL;
- return sctp_auth_set_active_key(sctp_sk(sk)->ep, asoc,
- val.scact_keynumber);
+ return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
}
/*
@@ -3434,11 +3459,11 @@
char __user *optval,
unsigned int optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authkeyid val;
struct sctp_association *asoc;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (optlen != sizeof(struct sctp_authkeyid))
@@ -3450,8 +3475,7 @@
if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP))
return -EINVAL;
- return sctp_auth_del_key_id(sctp_sk(sk)->ep, asoc,
- val.scact_keynumber);
+ return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
}
@@ -5342,16 +5366,16 @@
static int sctp_getsockopt_hmac_ident(struct sock *sk, int len,
char __user *optval, int __user *optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_hmacalgo __user *p = (void __user *)optval;
struct sctp_hmac_algo_param *hmacs;
__u16 data_len = 0;
u32 num_idents;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
- hmacs = sctp_sk(sk)->ep->auth_hmacs_list;
+ hmacs = ep->auth_hmacs_list;
data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t);
if (len < sizeof(struct sctp_hmacalgo) + data_len)
@@ -5372,11 +5396,11 @@
static int sctp_getsockopt_active_key(struct sock *sk, int len,
char __user *optval, int __user *optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authkeyid val;
struct sctp_association *asoc;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (len < sizeof(struct sctp_authkeyid))
@@ -5391,7 +5415,7 @@
if (asoc)
val.scact_keynumber = asoc->active_key_id;
else
- val.scact_keynumber = sctp_sk(sk)->ep->active_key_id;
+ val.scact_keynumber = ep->active_key_id;
len = sizeof(struct sctp_authkeyid);
if (put_user(len, optlen))
@@ -5405,7 +5429,7 @@
static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len,
char __user *optval, int __user *optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authchunks __user *p = (void __user *)optval;
struct sctp_authchunks val;
struct sctp_association *asoc;
@@ -5413,7 +5437,7 @@
u32 num_chunks = 0;
char __user *to;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (len < sizeof(struct sctp_authchunks))
@@ -5449,7 +5473,7 @@
static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len,
char __user *optval, int __user *optlen)
{
- struct net *net = sock_net(sk);
+ struct sctp_endpoint *ep = sctp_sk(sk)->ep;
struct sctp_authchunks __user *p = (void __user *)optval;
struct sctp_authchunks val;
struct sctp_association *asoc;
@@ -5457,7 +5481,7 @@
u32 num_chunks = 0;
char __user *to;
- if (!net->sctp.auth_enable)
+ if (!ep->auth_enable)
return -EACCES;
if (len < sizeof(struct sctp_authchunks))
@@ -5474,7 +5498,7 @@
if (asoc)
ch = (struct sctp_chunks_param*)asoc->c.auth_chunks;
else
- ch = sctp_sk(sk)->ep->auth_chunk_list;
+ ch = ep->auth_chunk_list;
if (!ch)
goto num;
@@ -6193,7 +6217,7 @@
/* Is there any exceptional events? */
if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
mask |= POLLERR |
- sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0;
+ (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
@@ -6556,6 +6580,46 @@
}
}
+static void sctp_wake_up_waiters(struct sock *sk,
+ struct sctp_association *asoc)
+{
+ struct sctp_association *tmp = asoc;
+
+ /* We do accounting for the sndbuf space per association,
+ * so we only need to wake our own association.
+ */
+ if (asoc->ep->sndbuf_policy)
+ return __sctp_write_space(asoc);
+
+ /* If association goes down and is just flushing its
+ * outq, then just normally notify others.
+ */
+ if (asoc->base.dead)
+ return sctp_write_space(sk);
+
+ /* Accounting for the sndbuf space is per socket, so we
+ * need to wake up others, try to be fair and in case of
+ * other associations, let them have a go first instead
+ * of just doing a sctp_write_space() call.
+ *
+ * Note that we reach sctp_wake_up_waiters() only when
+ * associations free up queued chunks, thus we are under
+ * lock and the list of associations on a socket is
+ * guaranteed not to change.
+ */
+ for (tmp = list_next_entry(tmp, asocs); 1;
+ tmp = list_next_entry(tmp, asocs)) {
+ /* Manually skip the head element. */
+ if (&tmp->asocs == &((sctp_sk(sk))->ep->asocs))
+ continue;
+ /* Wake up association. */
+ __sctp_write_space(tmp);
+ /* We've reached the end. */
+ if (tmp == asoc)
+ break;
+ }
+}
+
/* Do accounting for the sndbuf space.
* Decrement the used sndbuf space of the corresponding association by the
* data size which was just transmitted(freed).
@@ -6583,7 +6647,7 @@
sk_mem_uncharge(sk, skb->truesize);
sock_wfree(skb);
- __sctp_write_space(asoc);
+ sctp_wake_up_waiters(sk, asoc);
sctp_association_put(asoc);
}
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index bf3c6e8..29299dc 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -65,8 +65,11 @@
static int proc_sctp_do_hmac_alg(ctl_table *ctl,
int write,
void __user *buffer, size_t *lenp,
-
loff_t *ppos);
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+
static ctl_table sctp_table[] = {
{
.procname = "sctp_mem",
@@ -267,7 +270,7 @@
.data = &init_net.sctp.auth_enable,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_sctp_do_auth,
},
{
.procname = "addr_scope_policy",
@@ -348,6 +351,36 @@
return ret;
}
+static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ struct net *net = current->nsproxy->net_ns;
+ struct ctl_table tbl;
+ int new_value, ret;
+
+ memset(&tbl, 0, sizeof(struct ctl_table));
+ tbl.maxlen = sizeof(unsigned int);
+
+ if (write)
+ tbl.data = &new_value;
+ else
+ tbl.data = &net->sctp.auth_enable;
+
+ ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+ if (write && ret == 0) {
+ struct sock *sk = net->sctp.ctl_sock;
+
+ net->sctp.auth_enable = new_value;
+ /* Update the value in the control socket */
+ lock_sock(sk);
+ sctp_sk(sk)->ep->auth_enable = new_value;
+ release_sock(sk);
+ }
+
+ return ret;
+}
+
int sctp_sysctl_net_register(struct net *net)
{
struct ctl_table *table;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 10c018a..ca907f2 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -373,9 +373,10 @@
* specification [SCTP] and any extensions for a list of possible
* error formats.
*/
-struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
- const struct sctp_association *asoc, struct sctp_chunk *chunk,
- __u16 flags, gfp_t gfp)
+struct sctp_ulpevent *
+sctp_ulpevent_make_remote_error(const struct sctp_association *asoc,
+ struct sctp_chunk *chunk, __u16 flags,
+ gfp_t gfp)
{
struct sctp_ulpevent *event;
struct sctp_remote_error *sre;
@@ -394,8 +395,7 @@
/* Copy the skb to a new skb with room for us to prepend
* notification with.
*/
- skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
- 0, gfp);
+ skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp);
/* Pull off the rest of the cause TLV from the chunk. */
skb_pull(chunk->skb, elen);
@@ -406,62 +406,21 @@
event = sctp_skb2event(skb);
sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
- sre = (struct sctp_remote_error *)
- skb_push(skb, sizeof(struct sctp_remote_error));
+ sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre));
/* Trim the buffer to the right length. */
- skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+ skb_trim(skb, sizeof(*sre) + elen);
- /* Socket Extensions for SCTP
- * 5.3.1.3 SCTP_REMOTE_ERROR
- *
- * sre_type:
- * It should be SCTP_REMOTE_ERROR.
- */
+ /* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */
+ memset(sre, 0, sizeof(*sre));
sre->sre_type = SCTP_REMOTE_ERROR;
-
- /*
- * Socket Extensions for SCTP
- * 5.3.1.3 SCTP_REMOTE_ERROR
- *
- * sre_flags: 16 bits (unsigned integer)
- * Currently unused.
- */
sre->sre_flags = 0;
-
- /* Socket Extensions for SCTP
- * 5.3.1.3 SCTP_REMOTE_ERROR
- *
- * sre_length: sizeof (__u32)
- *
- * This field is the total length of the notification data,
- * including the notification header.
- */
sre->sre_length = skb->len;
-
- /* Socket Extensions for SCTP
- * 5.3.1.3 SCTP_REMOTE_ERROR
- *
- * sre_error: 16 bits (unsigned integer)
- * This value represents one of the Operational Error causes defined in
- * the SCTP specification, in network byte order.
- */
sre->sre_error = cause;
-
- /* Socket Extensions for SCTP
- * 5.3.1.3 SCTP_REMOTE_ERROR
- *
- * sre_assoc_id: sizeof (sctp_assoc_t)
- *
- * The association id field, holds the identifier for the association.
- * All notifications for a given association have the same association
- * identifier. For TCP style socket, this field is ignored.
- */
sctp_ulpevent_set_owner(event, asoc);
sre->sre_assoc_id = sctp_assoc2id(asoc);
return event;
-
fail:
return NULL;
}
@@ -906,7 +865,9 @@
return notification->sn_header.sn_type;
}
-/* Copy out the sndrcvinfo into a msghdr. */
+/* RFC6458, Section 5.3.2. SCTP Header Information Structure
+ * (SCTP_SNDRCV, DEPRECATED)
+ */
void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
struct msghdr *msghdr)
{
@@ -915,74 +876,21 @@
if (sctp_ulpevent_is_notification(event))
return;
- /* Sockets API Extensions for SCTP
- * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
- *
- * sinfo_stream: 16 bits (unsigned integer)
- *
- * For recvmsg() the SCTP stack places the message's stream number in
- * this value.
- */
+ memset(&sinfo, 0, sizeof(sinfo));
sinfo.sinfo_stream = event->stream;
- /* sinfo_ssn: 16 bits (unsigned integer)
- *
- * For recvmsg() this value contains the stream sequence number that
- * the remote endpoint placed in the DATA chunk. For fragmented
- * messages this is the same number for all deliveries of the message
- * (if more than one recvmsg() is needed to read the message).
- */
sinfo.sinfo_ssn = event->ssn;
- /* sinfo_ppid: 32 bits (unsigned integer)
- *
- * In recvmsg() this value is
- * the same information that was passed by the upper layer in the peer
- * application. Please note that byte order issues are NOT accounted
- * for and this information is passed opaquely by the SCTP stack from
- * one end to the other.
- */
sinfo.sinfo_ppid = event->ppid;
- /* sinfo_flags: 16 bits (unsigned integer)
- *
- * This field may contain any of the following flags and is composed of
- * a bitwise OR of these values.
- *
- * recvmsg() flags:
- *
- * SCTP_UNORDERED - This flag is present when the message was sent
- * non-ordered.
- */
sinfo.sinfo_flags = event->flags;
- /* sinfo_tsn: 32 bit (unsigned integer)
- *
- * For the receiving side, this field holds a TSN that was
- * assigned to one of the SCTP Data Chunks.
- */
sinfo.sinfo_tsn = event->tsn;
- /* sinfo_cumtsn: 32 bit (unsigned integer)
- *
- * This field will hold the current cumulative TSN as
- * known by the underlying SCTP layer. Note this field is
- * ignored when sending and only valid for a receive
- * operation when sinfo_flags are set to SCTP_UNORDERED.
- */
sinfo.sinfo_cumtsn = event->cumtsn;
- /* sinfo_assoc_id: sizeof (sctp_assoc_t)
- *
- * The association handle field, sinfo_assoc_id, holds the identifier
- * for the association announced in the COMMUNICATION_UP notification.
- * All notifications for a given association have the same identifier.
- * Ignored for one-to-one style sockets.
- */
sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
-
- /* context value that is set via SCTP_CONTEXT socket option. */
+ /* Context value that is set via SCTP_CONTEXT socket option. */
sinfo.sinfo_context = event->asoc->default_rcv_context;
-
/* These fields are not used while receiving. */
sinfo.sinfo_timetolive = 0;
put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
- sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+ sizeof(sinfo), &sinfo);
}
/* Do accounting for bytes received and hold a reference to the association
diff --git a/net/socket.c b/net/socket.c
index 4ca1526..fc90b4f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -215,12 +215,13 @@
int err;
int len;
+ BUG_ON(klen > sizeof(struct sockaddr_storage));
err = get_user(len, ulen);
if (err)
return err;
if (len > klen)
len = klen;
- if (len < 0 || len > sizeof(struct sockaddr_storage))
+ if (len < 0)
return -EINVAL;
if (len) {
if (audit_sockaddr(klen, kaddr))
@@ -1832,8 +1833,10 @@
msg.msg_iov = &iov;
iov.iov_len = size;
iov.iov_base = ubuf;
- msg.msg_name = (struct sockaddr *)&address;
- msg.msg_namelen = sizeof(address);
+ /* Save some cycles and don't copy the address if not needed */
+ msg.msg_name = addr ? (struct sockaddr *)&address : NULL;
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg.msg_namelen = 0;
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = sock_recvmsg(sock, &msg, size, flags);
@@ -1956,6 +1959,20 @@
unsigned int name_len;
};
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+ struct msghdr __user *umsg)
+{
+ if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+ return -EFAULT;
+
+ if (kmsg->msg_namelen < 0)
+ return -EINVAL;
+
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ kmsg->msg_namelen = sizeof(struct sockaddr_storage);
+ return 0;
+}
+
static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
struct used_address *used_address)
@@ -1974,8 +1991,11 @@
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2183,8 +2203,11 @@
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2197,16 +2220,14 @@
goto out;
}
- /*
- * Save the user-mode address (verify_iovec will change the
- * kernel msghdr to use the kernel address space)
+ /* Save the user-mode address (verify_iovec will change the
+ * kernel msghdr to use the kernel address space)
*/
-
uaddr = (__force void __user *)msg_sys->msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
- if (MSG_CMSG_COMPAT & flags) {
+ if (MSG_CMSG_COMPAT & flags)
err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
- } else
+ else
err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
if (err < 0)
goto out_freeiov;
@@ -2215,6 +2236,9 @@
cmsg_ptr = (unsigned long)msg_sys->msg_control;
msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT);
+ /* We assume all kernel code knows the size of sockaddr_storage */
+ msg_sys->msg_namelen = 0;
+
if (sock->file->f_flags & O_NONBLOCK)
flags |= MSG_DONTWAIT;
err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys,
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index d304f41..f1eb0d1 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -120,7 +120,7 @@
if (IS_ERR(clnt)) {
dprintk("RPC: failed to create AF_LOCAL gssproxy "
"client (errno %ld).\n", PTR_ERR(clnt));
- result = -PTR_ERR(clnt);
+ result = PTR_ERR(clnt);
*_clnt = NULL;
goto out;
}
@@ -213,6 +213,26 @@
return status;
}
+static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
+{
+ int i;
+
+ for (i = 0; i < arg->npages && arg->pages[i]; i++)
+ __free_page(arg->pages[i]);
+}
+
+static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg)
+{
+ arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE);
+ arg->pages = kzalloc(arg->npages * sizeof(struct page *), GFP_KERNEL);
+ /*
+ * XXX: actual pages are allocated by xdr layer in
+ * xdr_partial_copy_from_skb.
+ */
+ if (!arg->pages)
+ return -ENOMEM;
+ return 0;
+}
/*
* Public functions
@@ -261,10 +281,16 @@
arg.context_handle = &ctxh;
res.output_token->len = GSSX_max_output_token_sz;
+ ret = gssp_alloc_receive_pages(&arg);
+ if (ret)
+ return ret;
+
/* use nfs/ for targ_name ? */
ret = gssp_call(net, &msg);
+ gssp_free_receive_pages(&arg);
+
/* we need to fetch all data even in case of error so
* that we can free special strctures is they have been allocated */
data->major_status = res.status.major_status;
@@ -328,7 +354,6 @@
kfree(data->in_handle.data);
kfree(data->out_handle.data);
kfree(data->out_token.data);
- kfree(data->mech_oid.data);
free_svc_cred(&data->creds);
}
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 357f613..f0f78c5 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -166,14 +166,15 @@
return 0;
}
-static int get_s32(void **p, void *max, s32 *res)
+static int get_host_u32(struct xdr_stream *xdr, u32 *res)
{
- void *base = *p;
- void *next = (void *)((char *)base + sizeof(s32));
- if (unlikely(next > max || next < base))
+ __be32 *p;
+
+ p = xdr_inline_decode(xdr, 4);
+ if (!p)
return -EINVAL;
- memcpy(res, base, sizeof(s32));
- *p = next;
+ /* Contents of linux creds are all host-endian: */
+ memcpy(res, p, sizeof(u32));
return 0;
}
@@ -182,9 +183,9 @@
{
u32 length;
__be32 *p;
- void *q, *end;
- s32 tmp;
- int N, i, err;
+ u32 tmp;
+ u32 N;
+ int i, err;
p = xdr_inline_decode(xdr, 4);
if (unlikely(p == NULL))
@@ -192,33 +193,28 @@
length = be32_to_cpup(p);
- /* FIXME: we do not want to use the scratch buffer for this one
- * may need to use functions that allows us to access an io vector
- * directly */
- p = xdr_inline_decode(xdr, length);
- if (unlikely(p == NULL))
+ if (length > (3 + NGROUPS_MAX) * sizeof(u32))
return -ENOSPC;
- q = p;
- end = q + length;
-
/* uid */
- err = get_s32(&q, end, &tmp);
+ err = get_host_u32(xdr, &tmp);
if (err)
return err;
creds->cr_uid = make_kuid(&init_user_ns, tmp);
/* gid */
- err = get_s32(&q, end, &tmp);
+ err = get_host_u32(xdr, &tmp);
if (err)
return err;
creds->cr_gid = make_kgid(&init_user_ns, tmp);
/* number of additional gid's */
- err = get_s32(&q, end, &tmp);
+ err = get_host_u32(xdr, &tmp);
if (err)
return err;
N = tmp;
+ if ((3 + N) * sizeof(u32) != length)
+ return -EINVAL;
creds->cr_group_info = groups_alloc(N);
if (creds->cr_group_info == NULL)
return -ENOMEM;
@@ -226,7 +222,7 @@
/* gid's */
for (i = 0; i < N; i++) {
kgid_t kgid;
- err = get_s32(&q, end, &tmp);
+ err = get_host_u32(xdr, &tmp);
if (err)
goto out_free_groups;
err = -EINVAL;
@@ -430,7 +426,7 @@
static int dummy_dec_nameattr_array(struct xdr_stream *xdr,
struct gssx_name_attr_array *naa)
{
- struct gssx_name_attr dummy;
+ struct gssx_name_attr dummy = { .attr = {.len = 0} };
u32 count, i;
__be32 *p;
@@ -493,12 +489,13 @@
return err;
}
+
static int gssx_dec_name(struct xdr_stream *xdr,
struct gssx_name *name)
{
- struct xdr_netobj dummy_netobj;
- struct gssx_name_attr_array dummy_name_attr_array;
- struct gssx_option_array dummy_option_array;
+ struct xdr_netobj dummy_netobj = { .len = 0 };
+ struct gssx_name_attr_array dummy_name_attr_array = { .count = 0 };
+ struct gssx_option_array dummy_option_array = { .count = 0 };
int err;
/* name->display_name */
@@ -783,6 +780,9 @@
/* arg->options */
err = dummy_enc_opt_array(xdr, &arg->options);
+ xdr_inline_pages(&req->rq_rcv_buf,
+ PAGE_SIZE/2 /* pretty arbitrary */,
+ arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE);
done:
if (err)
dprintk("RPC: gssx_enc_accept_sec_context: %d\n", err);
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.h b/net/sunrpc/auth_gss/gss_rpc_xdr.h
index 1c98b27..685a688 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.h
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.h
@@ -147,6 +147,8 @@
struct gssx_cb *input_cb;
u32 ret_deleg_cred;
struct gssx_option_array options;
+ struct page **pages;
+ unsigned int npages;
};
struct gssx_res_accept_sec_context {
@@ -240,7 +242,8 @@
2 * GSSX_max_princ_sz + \
8 + 8 + 4 + 4 + 4)
#define GSSX_max_output_token_sz 1024
-#define GSSX_max_creds_sz (4 + 4 + 4 + NGROUPS_MAX * 4)
+/* grouplist not included; we allocate separate pages for that: */
+#define GSSX_max_creds_sz (4 + 4 + 4 /* + NGROUPS_MAX*4 */)
#define GSSX_RES_accept_sec_context_sz (GSSX_default_status_sz + \
GSSX_default_ctx_sz + \
GSSX_max_output_token_sz + \
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 80fe5c8..231b719 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -930,7 +930,7 @@
poll_wait(filp, &queue_wait, wait);
/* alway allow write */
- mask = POLL_OUT | POLLWRNORM;
+ mask = POLLOUT | POLLWRNORM;
if (!rp)
return mask;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 5a750b9c3..3524a8b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1402,14 +1402,18 @@
task->tk_action = call_refresh;
switch (status) {
case 0:
- if (rpcauth_uptodatecred(task))
+ if (rpcauth_uptodatecred(task)) {
task->tk_action = call_allocate;
- return;
+ return;
+ }
+ /* Use rate-limiting and a max number of retries if refresh
+ * had status 0 but failed to update the cred.
+ */
case -ETIMEDOUT:
rpc_delay(task, 3*HZ);
- case -EKEYEXPIRED:
case -EAGAIN:
status = -EACCES;
+ case -EKEYEXPIRED:
if (!task->tk_cred_retry)
break;
task->tk_cred_retry--;
@@ -1644,6 +1648,10 @@
task->tk_action = call_connect_status;
if (task->tk_status < 0)
return;
+ if (task->tk_flags & RPC_TASK_NOCONNECT) {
+ rpc_exit(task, -ENOTCONN);
+ return;
+ }
xprt_connect(task);
}
}
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index 74d948f..779742c 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -23,6 +23,7 @@
struct rpc_clnt *rpcb_local_clnt4;
spinlock_t rpcb_clnt_lock;
unsigned int rpcb_users;
+ unsigned int rpcb_is_af_local : 1;
struct mutex gssp_lock;
wait_queue_head_t gssp_wq;
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 3df764d..1891a10 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -204,13 +204,15 @@
}
static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt,
- struct rpc_clnt *clnt4)
+ struct rpc_clnt *clnt4,
+ bool is_af_local)
{
struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
/* Protected by rpcb_create_local_mutex */
sn->rpcb_local_clnt = clnt;
sn->rpcb_local_clnt4 = clnt4;
+ sn->rpcb_is_af_local = is_af_local ? 1 : 0;
smp_wmb();
sn->rpcb_users = 1;
dprintk("RPC: created new rpcb local clients (rpcb_local_clnt: "
@@ -238,6 +240,14 @@
.program = &rpcb_program,
.version = RPCBVERS_2,
.authflavor = RPC_AUTH_NULL,
+ /*
+ * We turn off the idle timeout to prevent the kernel
+ * from automatically disconnecting the socket.
+ * Otherwise, we'd have to cache the mount namespace
+ * of the caller and somehow pass that to the socket
+ * reconnect code.
+ */
+ .flags = RPC_CLNT_CREATE_NO_IDLE_TIMEOUT,
};
struct rpc_clnt *clnt, *clnt4;
int result = 0;
@@ -263,7 +273,7 @@
clnt4 = NULL;
}
- rpcb_set_local(net, clnt, clnt4);
+ rpcb_set_local(net, clnt, clnt4, true);
out:
return result;
@@ -315,7 +325,7 @@
clnt4 = NULL;
}
- rpcb_set_local(net, clnt, clnt4);
+ rpcb_set_local(net, clnt, clnt4, false);
out:
return result;
@@ -376,13 +386,16 @@
return rpc_create(&args);
}
-static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg)
+static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, struct rpc_message *msg, bool is_set)
{
- int result, error = 0;
+ int flags = RPC_TASK_NOCONNECT;
+ int error, result = 0;
+ if (is_set || !sn->rpcb_is_af_local)
+ flags = RPC_TASK_SOFTCONN;
msg->rpc_resp = &result;
- error = rpc_call_sync(clnt, msg, RPC_TASK_SOFTCONN);
+ error = rpc_call_sync(clnt, msg, flags);
if (error < 0) {
dprintk("RPC: failed to contact local rpcbind "
"server (errno %d).\n", -error);
@@ -439,16 +452,19 @@
.rpc_argp = &map,
};
struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+ bool is_set = false;
dprintk("RPC: %sregistering (%u, %u, %d, %u) with local "
"rpcbind\n", (port ? "" : "un"),
prog, vers, prot, port);
msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET];
- if (port)
+ if (port != 0) {
msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET];
+ is_set = true;
+ }
- return rpcb_register_call(sn->rpcb_local_clnt, &msg);
+ return rpcb_register_call(sn, sn->rpcb_local_clnt, &msg, is_set);
}
/*
@@ -461,6 +477,7 @@
const struct sockaddr_in *sin = (const struct sockaddr_in *)sap;
struct rpcbind_args *map = msg->rpc_argp;
unsigned short port = ntohs(sin->sin_port);
+ bool is_set = false;
int result;
map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
@@ -471,10 +488,12 @@
map->r_addr, map->r_netid);
msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
- if (port)
+ if (port != 0) {
msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
+ is_set = true;
+ }
- result = rpcb_register_call(sn->rpcb_local_clnt4, msg);
+ result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set);
kfree(map->r_addr);
return result;
}
@@ -489,6 +508,7 @@
const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap;
struct rpcbind_args *map = msg->rpc_argp;
unsigned short port = ntohs(sin6->sin6_port);
+ bool is_set = false;
int result;
map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
@@ -499,10 +519,12 @@
map->r_addr, map->r_netid);
msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
- if (port)
+ if (port != 0) {
msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
+ is_set = true;
+ }
- result = rpcb_register_call(sn->rpcb_local_clnt4, msg);
+ result = rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, is_set);
kfree(map->r_addr);
return result;
}
@@ -519,7 +541,7 @@
map->r_addr = "";
msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
- return rpcb_register_call(sn->rpcb_local_clnt4, msg);
+ return rpcb_register_call(sn, sn->rpcb_local_clnt4, msg, false);
}
/**
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 80a6640..b9aad47 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -730,6 +730,8 @@
newxpt = xprt->xpt_ops->xpo_accept(xprt);
if (newxpt)
svc_add_new_temp_xprt(serv, newxpt);
+ else
+ module_put(xprt->xpt_class->xcl_owner);
} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
/* XPT_DATA|XPT_DEFERRED case: */
dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index 06bdf5a..1583c8a 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -493,8 +493,6 @@
if (rv)
return -EINVAL;
uid = make_kuid(&init_user_ns, id);
- if (!uid_valid(uid))
- return -EINVAL;
ug.uid = uid;
expiry = get_expiry(&mesg);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 0f679df..5c62c5e 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -683,6 +683,7 @@
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_udp_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
+ .xcl_ident = XPRT_TRANSPORT_UDP,
};
static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
@@ -917,7 +918,10 @@
len = svsk->sk_datalen;
npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < npages; i++) {
- BUG_ON(svsk->sk_pages[i] == NULL);
+ if (svsk->sk_pages[i] == NULL) {
+ WARN_ON_ONCE(1);
+ continue;
+ }
put_page(svsk->sk_pages[i]);
svsk->sk_pages[i] = NULL;
}
@@ -1092,8 +1096,10 @@
goto err_noclose;
}
- if (svc_sock_reclen(svsk) < 8)
+ if (svsk->sk_datalen < 8) {
+ svsk->sk_datalen = 0;
goto err_delete; /* client is nuts. */
+ }
rqstp->rq_arg.len = svsk->sk_datalen;
rqstp->rq_arg.page_base = 0;
@@ -1270,6 +1276,7 @@
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_tcp_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+ .xcl_ident = XPRT_TRANSPORT_TCP,
};
void svc_init_xprt_sock(void)
@@ -1388,6 +1395,22 @@
return svsk;
}
+bool svc_alien_sock(struct net *net, int fd)
+{
+ int err;
+ struct socket *sock = sockfd_lookup(fd, &err);
+ bool ret = false;
+
+ if (!sock)
+ goto out;
+ if (sock_net(sock->sk) != net)
+ ret = true;
+ sockfd_put(sock);
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(svc_alien_sock);
+
/**
* svc_addsock - add a listener socket to an RPC service
* @serv: pointer to RPC service to which to add a new listener
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 75edcfa..1504bb1 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -207,10 +207,13 @@
pgfrom_base -= copy;
vto = kmap_atomic(*pgto);
- vfrom = kmap_atomic(*pgfrom);
- memmove(vto + pgto_base, vfrom + pgfrom_base, copy);
+ if (*pgto != *pgfrom) {
+ vfrom = kmap_atomic(*pgfrom);
+ memcpy(vto + pgto_base, vfrom + pgfrom_base, copy);
+ kunmap_atomic(vfrom);
+ } else
+ memmove(vto + pgto_base, vto + pgfrom_base, copy);
flush_dcache_page(*pgto);
- kunmap_atomic(vfrom);
kunmap_atomic(vto);
} while ((len -= copy) != 0);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 095363e..42ce6bf 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1290,7 +1290,7 @@
}
}
spin_unlock(&xprt_list_lock);
- printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident);
+ dprintk("RPC: transport (%d) not supported\n", args->ident);
return ERR_PTR(-EIO);
found:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 8d2eddd..65b1462 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -98,6 +98,7 @@
*/
static u32 *decode_write_list(u32 *va, u32 *vaend)
{
+ unsigned long start, end;
int nchunks;
struct rpcrdma_write_array *ary =
@@ -113,9 +114,12 @@
return NULL;
}
nchunks = ntohl(ary->wc_nchunks);
- if (((unsigned long)&ary->wc_array[0] +
- (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
- (unsigned long)vaend) {
+
+ start = (unsigned long)&ary->wc_array[0];
+ end = (unsigned long)vaend;
+ if (nchunks < 0 ||
+ nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) ||
+ (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) {
dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
ary, nchunks, vaend);
return NULL;
@@ -129,6 +133,7 @@
static u32 *decode_reply_array(u32 *va, u32 *vaend)
{
+ unsigned long start, end;
int nchunks;
struct rpcrdma_write_array *ary =
(struct rpcrdma_write_array *)va;
@@ -143,9 +148,12 @@
return NULL;
}
nchunks = ntohl(ary->wc_nchunks);
- if (((unsigned long)&ary->wc_array[0] +
- (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
- (unsigned long)vaend) {
+
+ start = (unsigned long)&ary->wc_array[0];
+ end = (unsigned long)vaend;
+ if (nchunks < 0 ||
+ nchunks > (SIZE_MAX - start) / sizeof(struct rpcrdma_write_chunk) ||
+ (start + (sizeof(struct rpcrdma_write_chunk) * nchunks)) > end) {
dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
ary, nchunks, vaend);
return NULL;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 62e4f9b..ed36cb5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -89,6 +89,7 @@
.xcl_owner = THIS_MODULE,
.xcl_ops = &svc_rdma_ops,
.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+ .xcl_ident = XPRT_TRANSPORT_RDMA,
};
struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ffd5034..fc47165 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -391,8 +391,10 @@
return kernel_sendmsg(sock, &msg, NULL, 0, 0);
}
-static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more)
+static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy)
{
+ ssize_t (*do_sendpage)(struct socket *sock, struct page *page,
+ int offset, size_t size, int flags);
struct page **ppage;
unsigned int remainder;
int err, sent = 0;
@@ -401,6 +403,9 @@
base += xdr->page_base;
ppage = xdr->pages + (base >> PAGE_SHIFT);
base &= ~PAGE_MASK;
+ do_sendpage = sock->ops->sendpage;
+ if (!zerocopy)
+ do_sendpage = sock_no_sendpage;
for(;;) {
unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder);
int flags = XS_SENDMSG_FLAGS;
@@ -408,7 +413,7 @@
remainder -= len;
if (remainder != 0 || more)
flags |= MSG_MORE;
- err = sock->ops->sendpage(sock, *ppage, base, len, flags);
+ err = do_sendpage(sock, *ppage, base, len, flags);
if (remainder == 0 || err != len)
break;
sent += err;
@@ -429,9 +434,10 @@
* @addrlen: UDP only -- length of destination address
* @xdr: buffer containing this request
* @base: starting position in the buffer
+ * @zerocopy: true if it is safe to use sendpage()
*
*/
-static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base)
+static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy)
{
unsigned int remainder = xdr->len - base;
int err, sent = 0;
@@ -459,7 +465,7 @@
if (base < xdr->page_len) {
unsigned int len = xdr->page_len - base;
remainder -= len;
- err = xs_send_pagedata(sock, xdr, base, remainder != 0);
+ err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy);
if (remainder == 0 || err != len)
goto out;
sent += err;
@@ -496,6 +502,7 @@
struct rpc_rqst *req = task->tk_rqstp;
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ struct sock *sk = transport->inet;
int ret = -EAGAIN;
dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
@@ -513,7 +520,7 @@
* window size
*/
set_bit(SOCK_NOSPACE, &transport->sock->flags);
- transport->inet->sk_write_pending++;
+ sk->sk_write_pending++;
/* ...and wait for more buffer space */
xprt_wait_for_buffer_space(task, xs_nospace_callback);
}
@@ -523,6 +530,9 @@
}
spin_unlock_bh(&xprt->transport_lock);
+
+ /* Race breaker in case memory is freed before above code is called */
+ sk->sk_write_space(sk);
return ret;
}
@@ -562,7 +572,7 @@
req->rq_svec->iov_base, req->rq_svec->iov_len);
status = xs_sendpages(transport->sock, NULL, 0,
- xdr, req->rq_bytes_sent);
+ xdr, req->rq_bytes_sent, true);
dprintk("RPC: %s(%u) = %d\n",
__func__, xdr->len - req->rq_bytes_sent, status);
if (likely(status >= 0)) {
@@ -618,7 +628,7 @@
status = xs_sendpages(transport->sock,
xs_addr(xprt),
xprt->addrlen, xdr,
- req->rq_bytes_sent);
+ req->rq_bytes_sent, true);
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
@@ -689,6 +699,7 @@
struct rpc_xprt *xprt = req->rq_xprt;
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
struct xdr_buf *xdr = &req->rq_snd_buf;
+ bool zerocopy = true;
int status;
xs_encode_stream_record_marker(&req->rq_snd_buf);
@@ -696,13 +707,20 @@
xs_pktdump("packet data:",
req->rq_svec->iov_base,
req->rq_svec->iov_len);
+ /* Don't use zero copy if this is a resend. If the RPC call
+ * completes while the socket holds a reference to the pages,
+ * then we may end up resending corrupted data.
+ */
+ if (task->tk_flags & RPC_TASK_SENT)
+ zerocopy = false;
/* Continue transmitting the packet/record. We must be careful
* to cope with writespace callbacks arriving _after_ we have
* called sendmsg(). */
while (1) {
status = xs_sendpages(transport->sock,
- NULL, 0, xdr, req->rq_bytes_sent);
+ NULL, 0, xdr, req->rq_bytes_sent,
+ zerocopy);
dprintk("RPC: xs_tcp_send_request(%u) = %d\n",
xdr->len - req->rq_bytes_sent, status);
diff --git a/net/sysctl_net.c b/net/sysctl_net.c
index 9bc6db04..e7000be 100644
--- a/net/sysctl_net.c
+++ b/net/sysctl_net.c
@@ -47,12 +47,12 @@
/* Allow network administrator to have same access as root. */
if (ns_capable(net->user_ns, CAP_NET_ADMIN) ||
- uid_eq(root_uid, current_uid())) {
+ uid_eq(root_uid, current_euid())) {
int mode = (table->mode >> 6) & 7;
return (mode << 6) | (mode << 3) | mode;
}
/* Allow netns root group to have the same access as the root group */
- if (gid_eq(root_gid, current_gid())) {
+ if (in_egroup_p(root_gid)) {
int mode = (table->mode >> 3) & 7;
return (mode << 3) | mode;
}
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index e5f3da5..bf27554 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -531,6 +531,7 @@
buf = node->bclink.deferred_head;
node->bclink.deferred_head = buf->next;
+ buf->next = NULL;
node->bclink.deferred_size--;
goto receive;
}
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 8bcd498..1e6081f 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -47,7 +47,7 @@
int hdr_space = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
u16 cmd;
- if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN)))
+ if ((req_userhdr->cmd & 0xC000) && (!netlink_capable(skb, CAP_NET_ADMIN)))
cmd = TIPC_CMD_NOT_NET_ADMIN;
else
cmd = req_userhdr->cmd;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 515ce38..2b1d7c2 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -905,9 +905,6 @@
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
restart:
@@ -1017,9 +1014,6 @@
goto exit;
}
- /* will be updated in set_orig_addr() if needed */
- m->msg_namelen = 0;
-
target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len);
timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
@@ -1179,7 +1173,7 @@
/* Accept only ACK or NACK message */
if (unlikely(msg_errcode(msg))) {
sock->state = SS_DISCONNECTING;
- sk->sk_err = -ECONNREFUSED;
+ sk->sk_err = ECONNREFUSED;
retval = TIPC_OK;
break;
}
@@ -1190,7 +1184,7 @@
res = auto_connect(sock, msg);
if (res) {
sock->state = SS_DISCONNECTING;
- sk->sk_err = res;
+ sk->sk_err = -res;
retval = TIPC_OK;
break;
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 826e099..75e198d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -160,9 +160,8 @@
static inline unsigned int unix_hash_fold(__wsum n)
{
- unsigned int hash = (__force unsigned int)n;
+ unsigned int hash = (__force unsigned int)csum_fold(n);
- hash ^= hash>>16;
hash ^= hash>>8;
return hash&(UNIX_HASH_SIZE-1);
}
@@ -529,13 +528,17 @@
static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *,
struct msghdr *, size_t, int);
-static void unix_set_peek_off(struct sock *sk, int val)
+static int unix_set_peek_off(struct sock *sk, int val)
{
struct unix_sock *u = unix_sk(sk);
- mutex_lock(&u->readlock);
+ if (mutex_lock_interruptible(&u->readlock))
+ return -EINTR;
+
sk->sk_peek_off = val;
mutex_unlock(&u->readlock);
+
+ return 0;
}
@@ -713,7 +716,9 @@
int err;
unsigned int retries = 0;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ return err;
err = 0;
if (u->addr)
@@ -872,7 +877,9 @@
goto out;
addr_len = err;
- mutex_lock(&u->readlock);
+ err = mutex_lock_interruptible(&u->readlock);
+ if (err)
+ goto out;
err = -EINVAL;
if (u->addr)
@@ -1245,6 +1252,15 @@
return 0;
}
+static void unix_sock_inherit_flags(const struct socket *old,
+ struct socket *new)
+{
+ if (test_bit(SOCK_PASSCRED, &old->flags))
+ set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSSEC, &old->flags))
+ set_bit(SOCK_PASSSEC, &new->flags);
+}
+
static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
struct sock *sk = sock->sk;
@@ -1279,6 +1295,7 @@
/* attach accepted sock to socket */
unix_state_lock(tsk);
newsock->state = SS_CONNECTED;
+ unix_sock_inherit_flags(sock, newsock);
sock_graft(tsk, newsock);
unix_state_unlock(tsk);
return 0;
@@ -1751,7 +1768,6 @@
{
struct unix_sock *u = unix_sk(sk);
- msg->msg_namelen = 0;
if (u->addr) {
msg->msg_namelen = u->addr->len;
memcpy(msg->msg_name, u->addr->name, u->addr->len);
@@ -1775,11 +1791,12 @@
if (flags&MSG_OOB)
goto out;
- msg->msg_namelen = 0;
-
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(sock_rcvtimeo(sk, noblock));
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
@@ -1899,6 +1916,7 @@
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = msg->msg_name;
int copied = 0;
+ int noblock = flags & MSG_DONTWAIT;
int check_creds = 0;
int target;
int err = 0;
@@ -1914,9 +1932,7 @@
goto out;
target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
- timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
-
- msg->msg_namelen = 0;
+ timeo = sock_rcvtimeo(sk, noblock);
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
@@ -1928,8 +1944,11 @@
}
err = mutex_lock_interruptible(&u->readlock);
- if (err) {
- err = sock_intr_errno(timeo);
+ if (unlikely(err)) {
+ /* recvmsg() in non blocking mode is supposed to return -EAGAIN
+ * sk_rcvtimeo is not honored by mutex_lock_interruptible()
+ */
+ err = noblock ? -EAGAIN : -ERESTARTSYS;
goto out;
}
diff --git a/net/unix/diag.c b/net/unix/diag.c
index d591091..86fa0f3 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -124,6 +124,7 @@
rep->udiag_family = AF_UNIX;
rep->udiag_type = sk->sk_type;
rep->udiag_state = sk->sk_state;
+ rep->pad = 0;
rep->udiag_ino = sk_ino;
sock_diag_save_cookie(sk, rep->udiag_cookie);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 3f77f42..9b88693 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1670,8 +1670,6 @@
vsk = vsock_sk(sk);
err = 0;
- msg->msg_namelen = 0;
-
lock_sock(sk);
if (sk->sk_state != SS_CONNECTED) {
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index daff752..62bbf7d 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1746,8 +1746,6 @@
if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
return -EOPNOTSUPP;
- msg->msg_namelen = 0;
-
/* Retrieve the head sk_buff from the socket's receive queue. */
err = 0;
skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err);
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index fd556ac..e69a17d 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -338,7 +338,7 @@
{
struct ieee80211_sta_ht_cap *ht_cap;
struct ieee80211_sta_vht_cap *vht_cap;
- u32 width, control_freq;
+ u32 width, control_freq, cap;
if (WARN_ON(!cfg80211_chandef_valid(chandef)))
return false;
@@ -370,7 +370,8 @@
return false;
break;
case NL80211_CHAN_WIDTH_80P80:
- if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))
+ cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+ if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
return false;
case NL80211_CHAN_WIDTH_80:
if (!vht_cap->vht_supported)
@@ -381,7 +382,9 @@
case NL80211_CHAN_WIDTH_160:
if (!vht_cap->vht_supported)
return false;
- if (!(vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ))
+ cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK;
+ if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ &&
+ cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ)
return false;
prohibited_flags |= IEEE80211_CHAN_NO_160MHZ;
width = 160;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 73405e0..64fcbae 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -876,6 +876,7 @@
cfg80211_leave_mesh(rdev, dev);
break;
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_P2P_GO:
cfg80211_stop_ap(rdev, dev);
break;
default:
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index d80e471..e62c1ad 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -269,6 +269,8 @@
if (chan->flags & IEEE80211_CHAN_DISABLED)
continue;
wdev->wext.ibss.chandef.chan = chan;
+ wdev->wext.ibss.chandef.center_freq1 =
+ chan->center_freq;
break;
}
@@ -353,6 +355,7 @@
if (chan) {
wdev->wext.ibss.chandef.chan = chan;
wdev->wext.ibss.chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
+ wdev->wext.ibss.chandef.center_freq1 = freq;
wdev->wext.ibss.channel_fixed = true;
} else {
/* cfg80211_ibss_wext_join will pick one if needed */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b14b7e3..90a0e55 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -471,10 +471,12 @@
goto out_unlock;
}
*rdev = wiphy_to_dev((*wdev)->wiphy);
- cb->args[0] = (*rdev)->wiphy_idx;
+ /* 0 is the first index - add 1 to parse only once */
+ cb->args[0] = (*rdev)->wiphy_idx + 1;
cb->args[1] = (*wdev)->identifier;
} else {
- struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0]);
+ /* subtract the 1 again here */
+ struct wiphy *wiphy = wiphy_idx_to_wiphy(cb->args[0] - 1);
struct wireless_dev *tmp;
if (!wiphy) {
@@ -2627,6 +2629,9 @@
if (!rdev->ops->get_key)
return -EOPNOTSUPP;
+ if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
+ return -ENOENT;
+
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg)
return -ENOMEM;
@@ -2646,10 +2651,6 @@
nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
goto nla_put_failure;
- if (pairwise && mac_addr &&
- !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
- return -ENOENT;
-
err = rdev_get_key(rdev, dev, key_idx, pairwise, mac_addr, &cookie,
get_key_callback);
@@ -2820,7 +2821,7 @@
wdev_lock(dev->ieee80211_ptr);
err = nl80211_key_allowed(dev->ieee80211_ptr);
- if (key.type == NL80211_KEYTYPE_PAIRWISE && mac_addr &&
+ if (key.type == NL80211_KEYTYPE_GROUP && mac_addr &&
!(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
err = -ENOENT;
@@ -4031,6 +4032,16 @@
if (parse_station_flags(info, dev->ieee80211_ptr->iftype, ¶ms))
return -EINVAL;
+ /* HT/VHT requires QoS, but if we don't have that just ignore HT/VHT
+ * as userspace might just pass through the capabilities from the IEs
+ * directly, rather than enforcing this restriction and returning an
+ * error in this case.
+ */
+ if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
+ params.ht_capa = NULL;
+ params.vht_capa = NULL;
+ }
+
/* When you run into this, adjust the code below for the new flag */
BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7);
@@ -6566,6 +6577,9 @@
void *hdr = ((void **)skb->cb)[1];
struct nlattr *data = ((void **)skb->cb)[2];
+ /* clear CB data for netlink core to own from now on */
+ memset(skb->cb, 0, sizeof(skb->cb));
+
if (WARN_ON(!rdev->testmode_info)) {
kfree_skb(skb);
return -EINVAL;
@@ -6588,12 +6602,17 @@
void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp)
{
+ struct cfg80211_registered_device *rdev = ((void **)skb->cb)[0];
void *hdr = ((void **)skb->cb)[1];
struct nlattr *data = ((void **)skb->cb)[2];
+ /* clear CB data for netlink core to own from now on */
+ memset(skb->cb, 0, sizeof(skb->cb));
+
nla_nest_end(skb, data);
genlmsg_end(skb, hdr);
- genlmsg_multicast(skb, 0, nl80211_testmode_mcgrp.id, gfp);
+ genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), skb, 0,
+ nl80211_testmode_mcgrp.id, gfp);
}
EXPORT_SYMBOL(cfg80211_testmode_event);
#endif
@@ -10028,7 +10047,8 @@
genlmsg_end(msg, hdr);
- genlmsg_multicast(msg, 0, nl80211_mlme_mcgrp.id, gfp);
+ genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0,
+ nl80211_mlme_mcgrp.id, gfp);
return;
nla_put_failure:
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 7d604c0..722da61 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -97,6 +97,10 @@
struct ieee80211_radiotap_header *radiotap_header,
int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns)
{
+ /* check the radiotap header can actually be present */
+ if (max_length < sizeof(struct ieee80211_radiotap_header))
+ return -EINVAL;
+
/* Linux only supports version 0 radiotap format */
if (radiotap_header->it_version)
return -EINVAL;
@@ -120,6 +124,10 @@
/* find payload start allowing for extended bitmap(s) */
if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) {
+ if ((unsigned long)iterator->_arg -
+ (unsigned long)iterator->_rtheader + sizeof(uint32_t) >
+ (unsigned long)iterator->_max_length)
+ return -EINVAL;
while (get_unaligned_le32(iterator->_arg) &
(1 << IEEE80211_RADIOTAP_EXT)) {
iterator->_arg += sizeof(uint32_t);
@@ -131,7 +139,8 @@
*/
if ((unsigned long)iterator->_arg -
- (unsigned long)iterator->_rtheader >
+ (unsigned long)iterator->_rtheader +
+ sizeof(uint32_t) >
(unsigned long)iterator->_max_length)
return -EINVAL;
}
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index fd99ea4..81019ee 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -253,10 +253,10 @@
rdev = container_of(wk, struct cfg80211_registered_device,
sched_scan_results_wk);
- request = rdev->sched_scan_req;
-
mutex_lock(&rdev->sched_scan_mtx);
+ request = rdev->sched_scan_req;
+
/* we don't have sched_scan_req anymore if the scan is stopping */
if (request) {
if (request->flags & NL80211_SCAN_FLAG_FLUSH) {
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5755bc1..bc5a75b 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1972,7 +1972,8 @@
MAC_ASSIGN(addr, addr);
__entry->key_type = key_type;
__entry->key_id = key_id;
- memcpy(__entry->tsc, tsc, 6);
+ if (tsc)
+ memcpy(__entry->tsc, tsc, 6);
),
TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm",
NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 37ca969..f96af3b 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1340,10 +1340,9 @@
if (sx25) {
sx25->sx25_family = AF_X25;
sx25->sx25_addr = x25->dest_addr;
+ msg->msg_namelen = sizeof(*sx25);
}
- msg->msg_namelen = sizeof(struct sockaddr_x25);
-
x25_check_rbuf(sk);
rc = copied;
out_free_dgram:
@@ -1583,11 +1582,11 @@
case SIOCX25CALLACCPTAPPRV: {
rc = -EINVAL;
lock_sock(sk);
- if (sk->sk_state != TCP_CLOSE)
- break;
- clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags);
+ if (sk->sk_state == TCP_CLOSE) {
+ clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags);
+ rc = 0;
+ }
release_sock(sk);
- rc = 0;
break;
}
@@ -1595,14 +1594,15 @@
rc = -EINVAL;
lock_sock(sk);
if (sk->sk_state != TCP_ESTABLISHED)
- break;
+ goto out_sendcallaccpt_release;
/* must call accptapprv above */
if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags))
- break;
+ goto out_sendcallaccpt_release;
x25_write_internal(sk, X25_CALL_ACCEPTED);
x25->state = X25_STATE_3;
- release_sock(sk);
rc = 0;
+out_sendcallaccpt_release:
+ release_sock(sk);
break;
}
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 3f565e4..7a70a5a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2362,7 +2362,7 @@
link = &xfrm_dispatch[type];
/* All operations require privileges, even GET */
- if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+ if (!netlink_net_capable(skb, CAP_NET_ADMIN))
return -EPERM;
if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst
index 182084d..8ccf830 100644
--- a/scripts/Makefile.headersinst
+++ b/scripts/Makefile.headersinst
@@ -47,18 +47,24 @@
all-files := $(header-y) $(genhdr-y) $(wrapper-files)
output-files := $(addprefix $(installdir)/, $(all-files))
-input-files := $(foreach hdr, $(header-y), \
+input-files1 := $(foreach hdr, $(header-y), \
$(if $(wildcard $(srcdir)/$(hdr)), \
- $(wildcard $(srcdir)/$(hdr)), \
+ $(wildcard $(srcdir)/$(hdr))) \
+ )
+input-files1-name := $(notdir $(input-files1))
+input-files2 := $(foreach hdr, $(header-y), \
+ $(if $(wildcard $(srcdir)/$(hdr)),, \
$(if $(wildcard $(oldsrcdir)/$(hdr)), \
$(wildcard $(oldsrcdir)/$(hdr)), \
$(error Missing UAPI file $(srcdir)/$(hdr))) \
- )) \
- $(foreach hdr, $(genhdr-y), \
+ ))
+input-files2-name := $(notdir $(input-files2))
+input-files3 := $(foreach hdr, $(genhdr-y), \
$(if $(wildcard $(gendir)/$(hdr)), \
$(wildcard $(gendir)/$(hdr)), \
$(error Missing generated UAPI file $(gendir)/$(hdr)) \
))
+input-files3-name := $(notdir $(input-files3))
# Work out what needs to be removed
oldheaders := $(patsubst $(installdir)/%,%,$(wildcard $(installdir)/*.h))
@@ -72,7 +78,9 @@
quiet_cmd_install = INSTALL $(printdir) ($(words $(all-files))\
file$(if $(word 2, $(all-files)),s))
cmd_install = \
- $(CONFIG_SHELL) $< $(installdir) $(input-files); \
+ $(CONFIG_SHELL) $< $(installdir) $(srcdir) $(input-files1-name); \
+ $(CONFIG_SHELL) $< $(installdir) $(oldsrcdir) $(input-files2-name); \
+ $(CONFIG_SHELL) $< $(installdir) $(gendir) $(input-files3-name); \
for F in $(wrapper-files); do \
echo "\#include <asm-generic/$$F>" > $(installdir)/$$F; \
done; \
@@ -98,7 +106,7 @@
@:
targets += $(install-file)
-$(install-file): scripts/headers_install.sh $(input-files) FORCE
+$(install-file): scripts/headers_install.sh $(input-files1) $(input-files2) $(input-files3) FORCE
$(if $(unwanted),$(call cmd,remove),)
$(if $(wildcard $(dir $@)),,$(shell mkdir -p $(dir $@)))
$(call if_changed,install)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f97869f..c4b37f6 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -152,6 +152,7 @@
dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \
-I$(srctree)/arch/$(SRCARCH)/boot/dts \
-I$(srctree)/arch/$(SRCARCH)/boot/dts/include \
+ -I$(srctree)/include \
-undef -D__DTS__
# Finds the multi-part object the current object will be linked into
diff --git a/scripts/gcc-goto.sh b/scripts/gcc-goto.sh
index a2af2e8..c9469d3 100644
--- a/scripts/gcc-goto.sh
+++ b/scripts/gcc-goto.sh
@@ -5,7 +5,7 @@
cat << "END" | $@ -x c - -c -o /dev/null >/dev/null 2>&1 && echo "y"
int main(void)
{
-#ifdef __arm__
+#if defined(__arm__) || defined(__aarch64__)
/*
* Not related to asm goto, but used by jump label
* and broken on some ARM GCC versions (see GCC Bug 48637).
diff --git a/scripts/headers_install.sh b/scripts/headers_install.sh
index 643764f..5de5660 100644
--- a/scripts/headers_install.sh
+++ b/scripts/headers_install.sh
@@ -2,7 +2,7 @@
if [ $# -lt 1 ]
then
- echo "Usage: headers_install.sh OUTDIR [FILES...]
+ echo "Usage: headers_install.sh OUTDIR SRCDIR [FILES...]
echo
echo "Prepares kernel header files for use by user space, by removing"
echo "all compiler.h definitions and #includes, removing any"
@@ -10,6 +10,7 @@
echo "asm/inline/volatile keywords."
echo
echo "OUTDIR: directory to write each userspace header FILE to."
+ echo "SRCDIR: source directory where files are picked."
echo "FILES: list of header files to operate on."
exit 1
@@ -19,6 +20,8 @@
OUTDIR="$1"
shift
+SRCDIR="$1"
+shift
# Iterate through files listed on command line
@@ -34,7 +37,7 @@
-e 's/(^|[^a-zA-Z0-9])__packed([^a-zA-Z0-9_]|$)/\1__attribute__((packed))\2/g' \
-e 's/(^|[ \t(])(inline|asm|volatile)([ \t(]|$)/\1__\2__\3/g' \
-e 's@#(ifndef|define|endif[ \t]*/[*])[ \t]*_UAPI@#\1 @' \
- "$i" > "$OUTDIR/$FILE.sed" || exit 1
+ "$SRCDIR/$i" > "$OUTDIR/$FILE.sed" || exit 1
scripts/unifdef -U__KERNEL__ -D__EXPORTED_HEADERS__ "$OUTDIR/$FILE.sed" \
> "$OUTDIR/$FILE"
[ $? -gt 1 ] && exit 1
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 487ac6f..9a11f9f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -55,6 +55,7 @@
static unsigned int table_size, table_cnt;
static int all_symbols = 0;
static char symbol_prefix_char = '\0';
+static unsigned long long kernel_start_addr = 0;
int token_profit[0x10000];
@@ -65,7 +66,10 @@
static void usage(void)
{
- fprintf(stderr, "Usage: kallsyms [--all-symbols] [--symbol-prefix=<prefix char>] < in.map > out.S\n");
+ fprintf(stderr, "Usage: kallsyms [--all-symbols] "
+ "[--symbol-prefix=<prefix char>] "
+ "[--page-offset=<CONFIG_PAGE_OFFSET>] "
+ "< in.map > out.S\n");
exit(1);
}
@@ -194,6 +198,9 @@
int i;
int offset = 1;
+ if (s->addr < kernel_start_addr)
+ return 0;
+
/* skip prefix char */
if (symbol_prefix_char && *(s->sym + 1) == symbol_prefix_char)
offset++;
@@ -646,6 +653,9 @@
if ((*p == '"' && *(p+2) == '"') || (*p == '\'' && *(p+2) == '\''))
p++;
symbol_prefix_char = *p;
+ } else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
+ const char *p = &argv[i][14];
+ kernel_start_addr = strtoull(p, NULL, 16);
} else
usage();
}
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index fd3f018..d908e54 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -525,7 +525,7 @@
{
int i, j;
struct menu *submenu[8], *menu, *location = NULL;
- struct jump_key *jump;
+ struct jump_key *jump = NULL;
str_printf(r, _("Prompt: %s\n"), _(prop->text));
menu = prop->menu->parent;
@@ -563,8 +563,8 @@
str_printf(r, _(" Location:\n"));
for (j = 4; --i >= 0; j += 2) {
menu = submenu[i];
- if (head && location && menu == location)
- jump->offset = r->len - 1;
+ if (jump && menu == location)
+ jump->offset = strlen(r->s);
str_printf(r, "%*c-> %s", j, ' ',
_(menu_get_prompt(menu)));
if (menu->sym) {
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 4305b2f..8c0e07b 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1750,7 +1750,7 @@
# strip kmemcheck_bitfield_{begin,end}.*;
$members =~ s/kmemcheck_bitfield_.*?;//gos;
# strip attributes
- $members =~ s/__aligned\s*\(.+\)//gos;
+ $members =~ s/__aligned\s*\([^;]*\)//gos;
create_parameterlist($members, ';', $file);
check_sections($file, $declaration_name, "struct", $sectcheck, $struct_actual, $nested);
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 0149949..32b10f5 100644
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -82,6 +82,8 @@
kallsymopt="${kallsymopt} --all-symbols"
fi
+ kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET"
+
local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}"
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index e66d4d2..5e74595 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -174,6 +174,9 @@
DEVID_FIELD(x86_cpu_id, model);
DEVID_FIELD(x86_cpu_id, vendor);
+ DEVID(cpu_feature);
+ DEVID_FIELD(cpu_feature, feature);
+
DEVID(mei_cl_device_id);
DEVID_FIELD(mei_cl_device_id, name);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 45f9a33..09632f0 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -208,8 +208,8 @@
range_lo < 0x9 ? "[%X-9" : "[%X",
range_lo);
sprintf(alias + strlen(alias),
- range_hi > 0xA ? "a-%X]" : "%X]",
- range_lo);
+ range_hi > 0xA ? "A-%X]" : "%X]",
+ range_hi);
}
}
if (bcdDevice_initial_digits < (sizeof(bcdDevice_lo) * 2 - 1))
@@ -1133,6 +1133,16 @@
}
ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);
+/* LOOKS like cpu:type:*:feature:*FEAT* */
+static int do_cpu_entry(const char *filename, void *symval, char *alias)
+{
+ DEF_FIELD(symval, cpu_feature, feature);
+
+ sprintf(alias, "cpu:type:*:feature:*%04X*", feature);
+ return 1;
+}
+ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);
+
/* Looks like: mei:S */
static int do_mei_entry(const char *filename, void *symval,
char *alias)
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index a4be8e1..a2c361c 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -573,12 +573,16 @@
if (strncmp(symname, "_restgpr_", sizeof("_restgpr_") - 1) == 0 ||
strncmp(symname, "_savegpr_", sizeof("_savegpr_") - 1) == 0 ||
strncmp(symname, "_rest32gpr_", sizeof("_rest32gpr_") - 1) == 0 ||
- strncmp(symname, "_save32gpr_", sizeof("_save32gpr_") - 1) == 0)
+ strncmp(symname, "_save32gpr_", sizeof("_save32gpr_") - 1) == 0 ||
+ strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
+ strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0)
return 1;
if (info->hdr->e_machine == EM_PPC64)
/* Special register function linked on all modules during final link of .ko */
if (strncmp(symname, "_restgpr0_", sizeof("_restgpr0_") - 1) == 0 ||
- strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0)
+ strncmp(symname, "_savegpr0_", sizeof("_savegpr0_") - 1) == 0 ||
+ strncmp(symname, "_restvr_", sizeof("_restvr_") - 1) == 0 ||
+ strncmp(symname, "_savevr_", sizeof("_savevr_") - 1) == 0)
return 1;
/* Do not ignore this symbol */
return 0;
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index acb8650..3001ec5 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -62,7 +62,7 @@
fi
# Create the package
- dpkg-gencontrol -isp $forcearch -p$pname -P"$pdir"
+ dpkg-gencontrol -isp $forcearch -Vkernel:debarch="${debarch:-$(dpkg --print-architecture)}" -p$pname -P"$pdir"
dpkg --build "$pdir" ..
}
@@ -252,15 +252,14 @@
(cd $objtree; tar -c -f - -T "$objtree/debian/hdrobjfiles") | (cd $destdir; tar -xf -)
ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
-arch=$(dpkg --print-architecture)
cat <<EOF >> debian/control
Package: $kernel_headers_packagename
Provides: linux-headers, linux-headers-2.6
-Architecture: $arch
-Description: Linux kernel headers for $KERNELRELEASE on $arch
- This package provides kernel header files for $KERNELRELEASE on $arch
+Architecture: any
+Description: Linux kernel headers for $KERNELRELEASE on \${kernel:debarch}
+ This package provides kernel header files for $KERNELRELEASE on \${kernel:debarch}
.
This is useful for people who need to build external modules
EOF
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index 9c22317..e11aa4a 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -40,6 +40,11 @@
#define R_METAG_NONE 3
#endif
+#ifndef EM_AARCH64
+#define EM_AARCH64 183
+#define R_AARCH64_ABS64 257
+#endif
+
static int fd_map; /* File descriptor for file being modified. */
static int mmap_failed; /* Boolean flag. */
static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */
@@ -347,6 +352,8 @@
case EM_ARM: reltype = R_ARM_ABS32;
altmcount = "__gnu_mcount_nc";
break;
+ case EM_AARCH64:
+ reltype = R_AARCH64_ABS64; gpfx = '_'; break;
case EM_IA_64: reltype = R_IA64_IMM64; gpfx = '_'; break;
case EM_METAG: reltype = R_METAG_ADDR32;
altmcount = "_mcount_wrapper";
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 9d1421e..49b582a 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -163,11 +163,11 @@
static int MIPS_is_fake_mcount(Elf_Rel const *rp)
{
- static Elf_Addr old_r_offset;
+ static Elf_Addr old_r_offset = ~(Elf_Addr)0;
Elf_Addr current_r_offset = _w(rp->r_offset);
int is_fake;
- is_fake = old_r_offset &&
+ is_fake = (old_r_offset != ~(Elf_Addr)0) &&
(current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET);
old_r_offset = current_r_offset;
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 858966a..aead5de 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -262,7 +262,6 @@
# force flags for this arch
$ld .= " -m shlelf_linux";
$objcopy .= " -O elf32-sh-linux";
- $cc .= " -m32";
} elsif ($arch eq "powerpc") {
$local_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)";
@@ -279,6 +278,11 @@
$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_ARM_(CALL|PC24|THM_CALL)" .
"\\s+(__gnu_mcount_nc|mcount)\$";
+} elsif ($arch eq "arm64") {
+ $alignment = 3;
+ $section_type = '%progbits';
+ $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_AARCH64_CALL26\\s+_mcount\$";
+ $type = ".quad";
} elsif ($arch eq "ia64") {
$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s_mcount\$";
$type = "data8";
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
index 1f10e89..f9ce116 100644
--- a/scripts/sortextable.c
+++ b/scripts/sortextable.c
@@ -31,6 +31,10 @@
#include <tools/be_byteshift.h>
#include <tools/le_byteshift.h>
+#ifndef EM_AARCH64
+#define EM_AARCH64 183
+#endif
+
static int fd_map; /* File descriptor for file being modified. */
static int mmap_failed; /* Boolean flag. */
static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */
@@ -249,6 +253,7 @@
custom_sort = sort_relative_table;
break;
case EM_ARM:
+ case EM_AARCH64:
case EM_MIPS:
break;
} /* end switch */
diff --git a/scripts/sortextable.h b/scripts/sortextable.h
index f5eb43d..3f06479 100644
--- a/scripts/sortextable.h
+++ b/scripts/sortextable.h
@@ -101,7 +101,7 @@
Elf_Sym *sort_needed_sym;
Elf_Shdr *sort_needed_sec;
Elf_Rel *relocs = NULL;
- int relocs_size;
+ int relocs_size = 0;
uint32_t *sort_done_location;
const char *secstrtab;
const char *strtab;
diff --git a/security/commoncap.c b/security/commoncap.c
index c44b6fe..c9219a6 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -421,6 +421,9 @@
cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
}
+ cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+ cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
return 0;
}
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index cdbde17..b980a6c 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -275,12 +275,23 @@
* @xattr_value: pointer to the new extended attribute value
* @xattr_value_len: pointer to the new extended attribute value length
*
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid. As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value. Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
*/
int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
const void *xattr_value, size_t xattr_value_len)
{
+ const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+ if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+ if (!xattr_value_len)
+ return -EINVAL;
+ if (xattr_data->type != EVM_IMA_XATTR_DIGSIG)
+ return -EPERM;
+ }
return evm_protect_xattr(dentry, xattr_name, xattr_value,
xattr_value_len);
}
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index a02e079..9da974c 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -24,6 +24,36 @@
static struct crypto_shash *ima_shash_tfm;
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+ char *addr, unsigned long count)
+{
+ mm_segment_t old_fs;
+ char __user *buf = addr;
+ ssize_t ret;
+
+ if (!(file->f_mode & FMODE_READ))
+ return -EBADF;
+ if (!file->f_op->read && !file->f_op->aio_read)
+ return -EINVAL;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ if (file->f_op->read)
+ ret = file->f_op->read(file, buf, count, &offset);
+ else
+ ret = do_sync_read(file, buf, count, &offset);
+ set_fs(old_fs);
+ return ret;
+}
+
int ima_init_crypto(void)
{
long rc;
@@ -70,7 +100,7 @@
while (offset < i_size) {
int rbuf_len;
- rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+ rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
if (rbuf_len < 0) {
rc = rbuf_len;
break;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 399433a..a9c3d3c 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -73,7 +73,6 @@
{.action = DONT_MEASURE,.fsmagic = SYSFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = DEBUGFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = TMPFS_MAGIC,.flags = IMA_FSMAGIC},
- {.action = DONT_MEASURE,.fsmagic = RAMFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = DEVPTS_SUPER_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = BINFMTFS_MAGIC,.flags = IMA_FSMAGIC},
{.action = DONT_MEASURE,.fsmagic = SECURITYFS_MAGIC,.flags = IMA_FSMAGIC},
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 9e1e005..c4c8df4 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -1018,10 +1018,13 @@
ret = encrypted_shash_alloc();
if (ret < 0)
return ret;
+ ret = aes_get_sizes();
+ if (ret < 0)
+ goto out;
ret = register_key_type(&key_type_encrypted);
if (ret < 0)
goto out;
- return aes_get_sizes();
+ return 0;
out:
encrypted_shash_release();
return ret;
diff --git a/security/keys/gc.c b/security/keys/gc.c
index d67c97b..7978186 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -201,12 +201,12 @@
if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
atomic_dec(&key->user->nikeys);
- key_user_put(key->user);
-
/* now throw away the key memory */
if (key->type->destroy)
key->type->destroy(key);
+ key_user_put(key->user);
+
kfree(key->description);
#ifdef KEY_DEBUGGING
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5c6f2cd..fdd6e4f 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -53,6 +53,7 @@
#include <net/ip.h> /* for local_port_range[] */
#include <net/sock.h>
#include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */
+#include <net/inet_connection_sock.h>
#include <net/net_namespace.h>
#include <net/netlabel.h>
#include <linux/uaccess.h>
@@ -218,6 +219,14 @@
return 0;
}
+static void inode_free_rcu(struct rcu_head *head)
+{
+ struct inode_security_struct *isec;
+
+ isec = container_of(head, struct inode_security_struct, rcu);
+ kmem_cache_free(sel_inode_cache, isec);
+}
+
static void inode_free_security(struct inode *inode)
{
struct inode_security_struct *isec = inode->i_security;
@@ -228,8 +237,16 @@
list_del_init(&isec->list);
spin_unlock(&sbsec->isec_lock);
- inode->i_security = NULL;
- kmem_cache_free(sel_inode_cache, isec);
+ /*
+ * The inode may still be referenced in a path walk and
+ * a call to selinux_inode_permission() can be made
+ * after inode_free_security() is called. Ideally, the VFS
+ * wouldn't do this, but fixing that is a much harder
+ * job. For now, simply free the i_security via RCU, and
+ * leave the current inode->i_security pointer intact.
+ * The inode will be freed after the RCU grace period too.
+ */
+ call_rcu(&isec->rcu, inode_free_rcu);
}
static int file_alloc_security(struct file *file)
@@ -420,6 +437,7 @@
list_entry(sbsec->isec_head.next,
struct inode_security_struct, list);
struct inode *inode = isec->inode;
+ list_del_init(&isec->list);
spin_unlock(&sbsec->isec_lock);
inode = igrab(inode);
if (inode) {
@@ -428,7 +446,6 @@
iput(inode);
}
spin_lock(&sbsec->isec_lock);
- list_del_init(&isec->list);
goto next_inode;
}
spin_unlock(&sbsec->isec_lock);
@@ -1344,15 +1361,33 @@
isec->sid = sbsec->sid;
if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
- if (opt_dentry) {
- isec->sclass = inode_mode_to_security_class(inode->i_mode);
- rc = selinux_proc_get_sid(opt_dentry,
- isec->sclass,
- &sid);
- if (rc)
- goto out_unlock;
- isec->sid = sid;
- }
+ /* We must have a dentry to determine the label on
+ * procfs inodes */
+ if (opt_dentry)
+ /* Called from d_instantiate or
+ * d_splice_alias. */
+ dentry = dget(opt_dentry);
+ else
+ /* Called from selinux_complete_init, try to
+ * find a dentry. */
+ dentry = d_find_alias(inode);
+ /*
+ * This can be hit on boot when a file is accessed
+ * before the policy is loaded. When we load policy we
+ * may find inodes that have no dentry on the
+ * sbsec->isec_head list. No reason to complain as
+ * these will get fixed up the next time we go through
+ * inode_doinit() with a dentry, before these inodes
+ * could be used again by userspace.
+ */
+ if (!dentry)
+ goto out_unlock;
+ isec->sclass = inode_mode_to_security_class(inode->i_mode);
+ rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
+ dput(dentry);
+ if (rc)
+ goto out_unlock;
+ isec->sid = sid;
}
break;
}
@@ -3722,7 +3757,7 @@
u32 nlbl_sid;
u32 nlbl_type;
- selinux_skb_xfrm_sid(skb, &xfrm_sid);
+ selinux_xfrm_skb_sid(skb, &xfrm_sid);
selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
err = security_net_peersid_resolve(nlbl_sid, nlbl_type, xfrm_sid, sid);
@@ -3736,6 +3771,30 @@
return 0;
}
+/**
+ * selinux_conn_sid - Determine the child socket label for a connection
+ * @sk_sid: the parent socket's SID
+ * @skb_sid: the packet's SID
+ * @conn_sid: the resulting connection SID
+ *
+ * If @skb_sid is valid then the user:role:type information from @sk_sid is
+ * combined with the MLS information from @skb_sid in order to create
+ * @conn_sid. If @skb_sid is not valid then then @conn_sid is simply a copy
+ * of @sk_sid. Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid)
+{
+ int err = 0;
+
+ if (skb_sid != SECSID_NULL)
+ err = security_sid_mls_copy(sk_sid, skb_sid, conn_sid);
+ else
+ *conn_sid = sk_sid;
+
+ return err;
+}
+
/* socket security operations */
static int socket_sockcreate_sid(const struct task_security_struct *tsec,
@@ -4203,8 +4262,10 @@
}
err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
PEER__RECV, &ad);
- if (err)
+ if (err) {
selinux_netlbl_err(skb, err, 0);
+ return err;
+ }
}
if (secmark_active) {
@@ -4342,7 +4403,7 @@
struct sk_security_struct *sksec = sk->sk_security;
int err;
u16 family = sk->sk_family;
- u32 newsid;
+ u32 connsid;
u32 peersid;
/* handle mapped IPv4 packets arriving via IPv6 sockets */
@@ -4352,16 +4413,11 @@
err = selinux_skb_peerlbl_sid(skb, family, &peersid);
if (err)
return err;
- if (peersid == SECSID_NULL) {
- req->secid = sksec->sid;
- req->peer_secid = SECSID_NULL;
- } else {
- err = security_sid_mls_copy(sksec->sid, peersid, &newsid);
- if (err)
- return err;
- req->secid = newsid;
- req->peer_secid = peersid;
- }
+ err = selinux_conn_sid(sksec->sid, peersid, &connsid);
+ if (err)
+ return err;
+ req->secid = connsid;
+ req->peer_secid = peersid;
return selinux_netlbl_inet_conn_request(req, family);
}
@@ -4621,6 +4677,7 @@
static unsigned int selinux_ip_output(struct sk_buff *skb,
u16 family)
{
+ struct sock *sk;
u32 sid;
if (!netlbl_enabled())
@@ -4629,8 +4686,27 @@
/* we do this in the LOCAL_OUT path and not the POST_ROUTING path
* because we want to make sure we apply the necessary labeling
* before IPsec is applied so we can leverage AH protection */
- if (skb->sk) {
- struct sk_security_struct *sksec = skb->sk->sk_security;
+ sk = skb->sk;
+ if (sk) {
+ struct sk_security_struct *sksec;
+
+ if (sk->sk_state == TCP_LISTEN)
+ /* if the socket is the listening state then this
+ * packet is a SYN-ACK packet which means it needs to
+ * be labeled based on the connection/request_sock and
+ * not the parent socket. unfortunately, we can't
+ * lookup the request_sock yet as it isn't queued on
+ * the parent socket until after the SYN-ACK is sent.
+ * the "solution" is to simply pass the packet as-is
+ * as any IP option based labeling should be copied
+ * from the initial connection request (in the IP
+ * layer). it is far from ideal, but until we get a
+ * security label in the packet itself this is the
+ * best we can do. */
+ return NF_ACCEPT;
+
+ /* standard practice, label using the parent socket */
+ sksec = sk->sk_security;
sid = sksec->sid;
} else
sid = SECINITSID_KERNEL;
@@ -4700,27 +4776,37 @@
* as fast and as clean as possible. */
if (!selinux_policycap_netpeer)
return selinux_ip_postroute_compat(skb, ifindex, family);
+
+ secmark_active = selinux_secmark_enabled();
+ peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
+ if (!secmark_active && !peerlbl_active)
+ return NF_ACCEPT;
+
+ sk = skb->sk;
+
#ifdef CONFIG_XFRM
/* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec
* packet transformation so allow the packet to pass without any checks
* since we'll have another chance to perform access control checks
* when the packet is on it's final way out.
* NOTE: there appear to be some IPv6 multicast cases where skb->dst
- * is NULL, in this case go ahead and apply access control. */
- if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL)
+ * is NULL, in this case go ahead and apply access control.
+ * is NULL, in this case go ahead and apply access control.
+ * NOTE: if this is a local socket (skb->sk != NULL) that is in the
+ * TCP listening state we cannot wait until the XFRM processing
+ * is done as we will miss out on the SA label if we do;
+ * unfortunately, this means more work, but it is only once per
+ * connection. */
+ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL &&
+ !(sk != NULL && sk->sk_state == TCP_LISTEN))
return NF_ACCEPT;
#endif
- secmark_active = selinux_secmark_enabled();
- peerlbl_active = netlbl_enabled() || selinux_xfrm_enabled();
- if (!secmark_active && !peerlbl_active)
- return NF_ACCEPT;
- /* if the packet is being forwarded then get the peer label from the
- * packet itself; otherwise check to see if it is from a local
- * application or the kernel, if from an application get the peer label
- * from the sending socket, otherwise use the kernel's sid */
- sk = skb->sk;
if (sk == NULL) {
+ /* Without an associated socket the packet is either coming
+ * from the kernel or it is being forwarded; check the packet
+ * to determine which and if the packet is being forwarded
+ * query the packet directly to determine the security label. */
if (skb->skb_iif) {
secmark_perm = PACKET__FORWARD_OUT;
if (selinux_skb_peerlbl_sid(skb, family, &peer_sid))
@@ -4729,7 +4815,45 @@
secmark_perm = PACKET__SEND;
peer_sid = SECINITSID_KERNEL;
}
+ } else if (sk->sk_state == TCP_LISTEN) {
+ /* Locally generated packet but the associated socket is in the
+ * listening state which means this is a SYN-ACK packet. In
+ * this particular case the correct security label is assigned
+ * to the connection/request_sock but unfortunately we can't
+ * query the request_sock as it isn't queued on the parent
+ * socket until after the SYN-ACK packet is sent; the only
+ * viable choice is to regenerate the label like we do in
+ * selinux_inet_conn_request(). See also selinux_ip_output()
+ * for similar problems. */
+ u32 skb_sid;
+ struct sk_security_struct *sksec = sk->sk_security;
+ if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+ return NF_DROP;
+ /* At this point, if the returned skb peerlbl is SECSID_NULL
+ * and the packet has been through at least one XFRM
+ * transformation then we must be dealing with the "final"
+ * form of labeled IPsec packet; since we've already applied
+ * all of our access controls on this packet we can safely
+ * pass the packet. */
+ if (skb_sid == SECSID_NULL) {
+ switch (family) {
+ case PF_INET:
+ if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
+ return NF_ACCEPT;
+ break;
+ case PF_INET6:
+ if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
+ return NF_ACCEPT;
+ default:
+ return NF_DROP_ERR(-ECONNREFUSED);
+ }
+ }
+ if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
+ return NF_DROP;
+ secmark_perm = PACKET__SEND;
} else {
+ /* Locally generated packet, fetch the security label from the
+ * associated socket. */
struct sk_security_struct *sksec = sk->sk_security;
peer_sid = sksec->sid;
secmark_perm = PACKET__SEND;
@@ -5393,11 +5517,11 @@
/* Check for ptracing, and update the task SID if ok.
Otherwise, leave SID unchanged and fail. */
ptsid = 0;
- task_lock(p);
+ rcu_read_lock();
tracer = ptrace_parent(p);
if (tracer)
ptsid = task_sid(tracer);
- task_unlock(p);
+ rcu_read_unlock();
if (tracer) {
error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index aa47bca..6fd9dd2 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -38,7 +38,10 @@
struct inode_security_struct {
struct inode *inode; /* back pointer to inode object */
- struct list_head list; /* list of inode_security_struct */
+ union {
+ struct list_head list; /* list of inode_security_struct */
+ struct rcu_head rcu; /* for freeing the inode_security_struct */
+ };
u32 task_sid; /* SID of creating task */
u32 sid; /* SID of this object */
u16 sclass; /* security class of this object */
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
index 65f67cb..3ffdadc 100644
--- a/security/selinux/include/xfrm.h
+++ b/security/selinux/include/xfrm.h
@@ -47,6 +47,7 @@
int selinux_xfrm_postroute_last(u32 isec_sid, struct sk_buff *skb,
struct common_audit_data *ad, u8 proto);
int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid);
static inline void selinux_xfrm_notify_policyload(void)
{
@@ -80,12 +81,12 @@
static inline void selinux_xfrm_notify_policyload(void)
{
}
-#endif
-static inline void selinux_skb_xfrm_sid(struct sk_buff *skb, u32 *sid)
+static inline int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
{
- int err = selinux_xfrm_decode_session(skb, sid, 0);
- BUG_ON(err);
+ *sid = SECSID_NULL;
+ return 0;
}
+#endif
#endif /* _SELINUX_XFRM_H_ */
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index da4b8b2..6235d05 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -442,8 +442,7 @@
sksec->nlbl_state != NLBL_CONNLABELED)
return 0;
- local_bh_disable();
- bh_lock_sock_nested(sk);
+ lock_sock(sk);
/* connected sockets are allowed to disconnect when the address family
* is set to AF_UNSPEC, if that is what is happening we want to reset
@@ -464,7 +463,6 @@
sksec->nlbl_state = NLBL_CONNLABELED;
socket_connect_return:
- bh_unlock_sock(sk);
- local_bh_enable();
+ release_sock(sk);
return rc;
}
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index ff42773..a96bed4 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -150,7 +150,7 @@
goto out;
/* No partial writes. */
- length = EINVAL;
+ length = -EINVAL;
if (*ppos != 0)
goto out;
@@ -1190,7 +1190,7 @@
spin_lock(&de->d_lock);
node = de->d_subdirs.next;
while (node != &de->d_subdirs) {
- struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
+ struct dentry *d = list_entry(node, struct dentry, d_child);
spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
list_del_init(node);
@@ -1664,12 +1664,12 @@
list_for_each(class_node, &class_dir->d_subdirs) {
struct dentry *class_subdir = list_entry(class_node,
- struct dentry, d_u.d_child);
+ struct dentry, d_child);
struct list_head *class_subdir_node;
list_for_each(class_subdir_node, &class_subdir->d_subdirs) {
struct dentry *d = list_entry(class_subdir_node,
- struct dentry, d_u.d_child);
+ struct dentry, d_child);
if (d->d_inode)
if (d->d_inode->i_mode & S_IFDIR)
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 9cd9b7c..bcdca73 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -1941,7 +1941,19 @@
if (rc)
goto out;
- hashtab_insert(p->filename_trans, ft, otype);
+ rc = hashtab_insert(p->filename_trans, ft, otype);
+ if (rc) {
+ /*
+ * Do not return -EEXIST to the caller, or the system
+ * will not boot.
+ */
+ if (rc != -EEXIST)
+ goto out;
+ /* But free memory to avoid memory leak. */
+ kfree(ft);
+ kfree(name);
+ kfree(otype);
+ }
}
hash_eval(p->filename_trans, "filenametr");
return 0;
@@ -3246,10 +3258,10 @@
if (rc)
return rc;
- buf[0] = ft->stype;
- buf[1] = ft->ttype;
- buf[2] = ft->tclass;
- buf[3] = otype->otype;
+ buf[0] = cpu_to_le32(ft->stype);
+ buf[1] = cpu_to_le32(ft->ttype);
+ buf[2] = cpu_to_le32(ft->tclass);
+ buf[3] = cpu_to_le32(otype->otype);
rc = put_entry(buf, sizeof(u32), 4, fp);
if (rc)
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index b4feecc..18caa16 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1231,6 +1231,10 @@
struct context context;
int rc = 0;
+ /* An empty security context is never valid. */
+ if (!scontext_len)
+ return -EINVAL;
+
if (!ss_initialized) {
int i;
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index d030818..78504a1 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -152,21 +152,13 @@
return rc;
}
-/*
- * LSM hook implementation that checks and/or returns the xfrm sid for the
- * incoming packet.
- */
-
-int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb,
+ u32 *sid, int ckall)
{
- struct sec_path *sp;
+ struct sec_path *sp = skb->sp;
*sid = SECSID_NULL;
- if (skb == NULL)
- return 0;
-
- sp = skb->sp;
if (sp) {
int i, sid_set = 0;
@@ -190,6 +182,45 @@
return 0;
}
+static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct xfrm_state *x;
+
+ if (dst == NULL)
+ return SECSID_NULL;
+ x = dst->xfrm;
+ if (x == NULL || !selinux_authorizable_xfrm(x))
+ return SECSID_NULL;
+
+ return x->security->ctx_sid;
+}
+
+/*
+ * LSM hook implementation that checks and/or returns the xfrm sid for the
+ * incoming packet.
+ */
+
+int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+{
+ if (skb == NULL) {
+ *sid = SECSID_NULL;
+ return 0;
+ }
+ return selinux_xfrm_skb_sid_ingress(skb, sid, ckall);
+}
+
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
+{
+ int rc;
+
+ rc = selinux_xfrm_skb_sid_ingress(skb, sid, 0);
+ if (rc == 0 && *sid == SECSID_NULL)
+ *sid = selinux_xfrm_skb_sid_egress(skb);
+
+ return rc;
+}
+
/*
* Security blob allocation for xfrm_policy and xfrm_state
* CTX does not have a meaningful value on input
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index 76e0d56..823359e 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -166,7 +166,9 @@
} else {
printk(KERN_ERR "%s: DMA error on channel %d (DCSR=%#x)\n",
rtd->params->name, dma_ch, dcsr);
+ snd_pcm_stream_lock(substream);
snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(substream);
}
}
EXPORT_SYMBOL(pxa2xx_pcm_dma_irq);
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 99db892..3fdf998 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -133,7 +133,7 @@
kfree(data);
}
snd_card_unref(compr->card);
- return 0;
+ return ret;
}
static int snd_compr_free(struct inode *inode, struct file *f)
@@ -668,14 +668,48 @@
return -EPERM;
retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
if (!retval) {
- stream->runtime->state = SNDRV_PCM_STATE_SETUP;
- wake_up(&stream->runtime->sleep);
+ snd_compr_drain_notify(stream);
stream->runtime->total_bytes_available = 0;
stream->runtime->total_bytes_transferred = 0;
}
return retval;
}
+static int snd_compress_wait_for_drain(struct snd_compr_stream *stream)
+{
+ int ret;
+
+ /*
+ * We are called with lock held. So drop the lock while we wait for
+ * drain complete notfication from the driver
+ *
+ * It is expected that driver will notify the drain completion and then
+ * stream will be moved to SETUP state, even if draining resulted in an
+ * error. We can trigger next track after this.
+ */
+ stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+ mutex_unlock(&stream->device->lock);
+
+ /* we wait for drain to complete here, drain can return when
+ * interruption occurred, wait returned error or success.
+ * For the first two cases we don't do anything different here and
+ * return after waking up
+ */
+
+ ret = wait_event_interruptible(stream->runtime->sleep,
+ (stream->runtime->state != SNDRV_PCM_STATE_DRAINING));
+ if (ret == -ERESTARTSYS)
+ pr_debug("wait aborted by a signal");
+ else if (ret)
+ pr_debug("wait for drain failed with %d\n", ret);
+
+
+ wake_up(&stream->runtime->sleep);
+ mutex_lock(&stream->device->lock);
+
+ return ret;
+}
+
static int snd_compr_drain(struct snd_compr_stream *stream)
{
int retval;
@@ -683,12 +717,15 @@
if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
stream->runtime->state == SNDRV_PCM_STATE_SETUP)
return -EPERM;
+
retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
- if (!retval) {
- stream->runtime->state = SNDRV_PCM_STATE_DRAINING;
+ if (retval) {
+ pr_debug("SND_COMPR_TRIGGER_DRAIN failed %d\n", retval);
wake_up(&stream->runtime->sleep);
+ return retval;
}
- return retval;
+
+ return snd_compress_wait_for_drain(stream);
}
static int snd_compr_next_track(struct snd_compr_stream *stream)
@@ -724,9 +761,14 @@
return -EPERM;
retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_PARTIAL_DRAIN);
+ if (retval) {
+ pr_debug("Partial drain returned failure\n");
+ wake_up(&stream->runtime->sleep);
+ return retval;
+ }
stream->next_track = false;
- return retval;
+ return snd_compress_wait_for_drain(stream);
}
static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
@@ -743,7 +785,7 @@
mutex_lock(&stream->device->lock);
switch (_IOC_NR(cmd)) {
case _IOC_NR(SNDRV_COMPRESS_IOCTL_VERSION):
- put_user(SNDRV_COMPRESS_VERSION,
+ retval = put_user(SNDRV_COMPRESS_VERSION,
(int __user *)arg) ? -EFAULT : 0;
break;
case _IOC_NR(SNDRV_COMPRESS_GET_CAPS):
@@ -837,7 +879,8 @@
struct snd_compr *compr;
compr = device->device_data;
- snd_unregister_device(compr->direction, compr->card, compr->device);
+ snd_unregister_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card,
+ compr->device);
return 0;
}
diff --git a/sound/core/control.c b/sound/core/control.c
index d8aa206..f2082a3 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -289,6 +289,10 @@
{
struct snd_kcontrol *kctl;
+ /* Make sure that the ids assigned to the control do not wrap around */
+ if (card->last_numid >= UINT_MAX - count)
+ card->last_numid = 0;
+
list_for_each_entry(kctl, &card->controls, list) {
if (kctl->id.numid < card->last_numid + 1 + count &&
kctl->id.numid + kctl->count > card->last_numid + 1) {
@@ -331,6 +335,7 @@
{
struct snd_ctl_elem_id id;
unsigned int idx;
+ unsigned int count;
int err = -EINVAL;
if (! kcontrol)
@@ -338,6 +343,9 @@
if (snd_BUG_ON(!card || !kcontrol->info))
goto error;
id = kcontrol->id;
+ if (id.index > UINT_MAX - kcontrol->count)
+ goto error;
+
down_write(&card->controls_rwsem);
if (snd_ctl_find_id(card, &id)) {
up_write(&card->controls_rwsem);
@@ -359,8 +367,9 @@
card->controls_count += kcontrol->count;
kcontrol->id.numid = card->last_numid + 1;
card->last_numid += kcontrol->count;
+ count = kcontrol->count;
up_write(&card->controls_rwsem);
- for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+ for (idx = 0; idx < count; idx++, id.index++, id.numid++)
snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
return 0;
@@ -389,6 +398,7 @@
bool add_on_replace)
{
struct snd_ctl_elem_id id;
+ unsigned int count;
unsigned int idx;
struct snd_kcontrol *old;
int ret;
@@ -424,8 +434,9 @@
card->controls_count += kcontrol->count;
kcontrol->id.numid = card->last_numid + 1;
card->last_numid += kcontrol->count;
+ count = kcontrol->count;
up_write(&card->controls_rwsem);
- for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+ for (idx = 0; idx < count; idx++, id.index++, id.numid++)
snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
return 0;
@@ -898,9 +909,9 @@
result = kctl->put(kctl, control);
}
if (result > 0) {
+ struct snd_ctl_elem_id id = control->id;
up_read(&card->controls_rwsem);
- snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
- &control->id);
+ snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
return 0;
}
}
@@ -992,6 +1003,7 @@
struct user_element {
struct snd_ctl_elem_info info;
+ struct snd_card *card;
void *elem_data; /* element data */
unsigned long elem_data_size; /* size of element data in bytes */
void *tlv_data; /* TLV data */
@@ -1035,7 +1047,9 @@
{
struct user_element *ue = kcontrol->private_data;
+ mutex_lock(&ue->card->user_ctl_lock);
memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+ mutex_unlock(&ue->card->user_ctl_lock);
return 0;
}
@@ -1044,10 +1058,12 @@
{
int change;
struct user_element *ue = kcontrol->private_data;
-
+
+ mutex_lock(&ue->card->user_ctl_lock);
change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
if (change)
memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+ mutex_unlock(&ue->card->user_ctl_lock);
return change;
}
@@ -1067,19 +1083,32 @@
new_data = memdup_user(tlv, size);
if (IS_ERR(new_data))
return PTR_ERR(new_data);
+ mutex_lock(&ue->card->user_ctl_lock);
change = ue->tlv_data_size != size;
if (!change)
change = memcmp(ue->tlv_data, new_data, size);
kfree(ue->tlv_data);
ue->tlv_data = new_data;
ue->tlv_data_size = size;
+ mutex_unlock(&ue->card->user_ctl_lock);
} else {
- if (! ue->tlv_data_size || ! ue->tlv_data)
- return -ENXIO;
- if (size < ue->tlv_data_size)
- return -ENOSPC;
+ int ret = 0;
+
+ mutex_lock(&ue->card->user_ctl_lock);
+ if (!ue->tlv_data_size || !ue->tlv_data) {
+ ret = -ENXIO;
+ goto err_unlock;
+ }
+ if (size < ue->tlv_data_size) {
+ ret = -ENOSPC;
+ goto err_unlock;
+ }
if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
- return -EFAULT;
+ ret = -EFAULT;
+err_unlock:
+ mutex_unlock(&ue->card->user_ctl_lock);
+ if (ret)
+ return ret;
}
return change;
}
@@ -1137,31 +1166,28 @@
struct user_element *ue;
int idx, err;
- if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
- return -ENOMEM;
if (info->count < 1)
return -EINVAL;
+ if (!*info->id.name)
+ return -EINVAL;
+ if (strnlen(info->id.name, sizeof(info->id.name)) >= sizeof(info->id.name))
+ return -EINVAL;
access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
(info->access & (SNDRV_CTL_ELEM_ACCESS_READWRITE|
SNDRV_CTL_ELEM_ACCESS_INACTIVE|
SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
info->id.numid = 0;
memset(&kctl, 0, sizeof(kctl));
- down_write(&card->controls_rwsem);
- _kctl = snd_ctl_find_id(card, &info->id);
- err = 0;
- if (_kctl) {
- if (replace)
- err = snd_ctl_remove(card, _kctl);
- else
- err = -EBUSY;
- } else {
- if (replace)
- err = -ENOENT;
+
+ if (replace) {
+ err = snd_ctl_remove_user_ctl(file, &info->id);
+ if (err)
+ return err;
}
- up_write(&card->controls_rwsem);
- if (err < 0)
- return err;
+
+ if (card->user_ctl_count >= MAX_USER_CONTROLS)
+ return -ENOMEM;
+
memcpy(&kctl.id, &info->id, sizeof(info->id));
kctl.count = info->owner ? info->owner : 1;
access |= SNDRV_CTL_ELEM_ACCESS_USER;
@@ -1211,6 +1237,7 @@
ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
if (ue == NULL)
return -ENOMEM;
+ ue->card = card;
ue->info = *info;
ue->info.access = 0;
ue->elem_data = (char *)ue + sizeof(*ue);
@@ -1322,8 +1349,9 @@
}
err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
if (err > 0) {
+ struct snd_ctl_elem_id id = kctl->id;
up_read(&card->controls_rwsem);
- snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+ snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
return 0;
}
} else {
diff --git a/sound/core/info.c b/sound/core/info.c
index e79baa1..08070e1 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -679,7 +679,7 @@
* snd_info_get_line - read one line from the procfs buffer
* @buffer: the procfs buffer
* @line: the buffer to store
- * @len: the max. buffer size - 1
+ * @len: the max. buffer size
*
* Reads one line from the buffer and stores the string.
*
@@ -699,7 +699,7 @@
buffer->stop = 1;
if (c == '\n')
break;
- if (len) {
+ if (len > 1) {
len--;
*line++ = c;
}
diff --git a/sound/core/init.c b/sound/core/init.c
index 6ef0640..27791a5 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -208,6 +208,7 @@
INIT_LIST_HEAD(&card->devices);
init_rwsem(&card->controls_rwsem);
rwlock_init(&card->ctl_files_rwlock);
+ mutex_init(&card->user_ctl_lock);
INIT_LIST_HEAD(&card->controls);
INIT_LIST_HEAD(&card->ctl_files);
spin_lock_init(&card->files_lock);
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 17f45e8..e1e9e0c 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -49,6 +49,8 @@
struct snd_pcm *pcm;
list_for_each_entry(pcm, &snd_pcm_devices, list) {
+ if (pcm->internal)
+ continue;
if (pcm->card == card && pcm->device == device)
return pcm;
}
@@ -60,6 +62,8 @@
struct snd_pcm *pcm;
list_for_each_entry(pcm, &snd_pcm_devices, list) {
+ if (pcm->internal)
+ continue;
if (pcm->card == card && pcm->device > device)
return pcm->device;
else if (pcm->card->number > card->number)
diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c
index af49721..c4ac3c1 100644
--- a/sound/core/pcm_compat.c
+++ b/sound/core/pcm_compat.c
@@ -206,6 +206,8 @@
if (err < 0)
return err;
+ if (clear_user(src, sizeof(*src)))
+ return -EFAULT;
if (put_user(status.state, &src->state) ||
compat_put_timespec(&status.trigger_tstamp, &src->trigger_tstamp) ||
compat_put_timespec(&status.tstamp, &src->tstamp) ||
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 41b3dfe..8eddece 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1782,14 +1782,16 @@
{
struct snd_pcm_hw_params *params = arg;
snd_pcm_format_t format;
- int channels, width;
+ int channels;
+ ssize_t frame_size;
params->fifo_size = substream->runtime->hw.fifo_size;
if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_FIFO_IN_FRAMES)) {
format = params_format(params);
channels = params_channels(params);
- width = snd_pcm_format_physical_width(format);
- params->fifo_size /= width * channels;
+ frame_size = snd_pcm_format_size(format, channels);
+ if (frame_size > 0)
+ params->fifo_size /= (unsigned)frame_size;
}
return 0;
}
@@ -1936,6 +1938,8 @@
case SNDRV_PCM_STATE_DISCONNECTED:
err = -EBADFD;
goto _endloop;
+ case SNDRV_PCM_STATE_PAUSED:
+ continue;
}
if (!tout) {
snd_printd("%s write error (DMA or IRQ trouble?)\n",
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f928181..707405c 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1404,6 +1404,8 @@
if (! snd_pcm_playback_empty(substream)) {
snd_pcm_do_start(substream, SNDRV_PCM_STATE_DRAINING);
snd_pcm_post_start(substream, SNDRV_PCM_STATE_DRAINING);
+ } else {
+ runtime->status->state = SNDRV_PCM_STATE_SETUP;
}
break;
case SNDRV_PCM_STATE_RUNNING:
@@ -3197,7 +3199,7 @@
#ifndef ARCH_HAS_DMA_MMAP_COHERENT
/* This should be defined / handled globally! */
-#ifdef CONFIG_ARM
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
#define ARCH_HAS_DMA_MMAP_COHERENT
#endif
#endif
diff --git a/sound/core/seq/oss/seq_oss_init.c b/sound/core/seq/oss/seq_oss_init.c
index e3cb46f..b3f39b5 100644
--- a/sound/core/seq/oss/seq_oss_init.c
+++ b/sound/core/seq/oss/seq_oss_init.c
@@ -31,6 +31,7 @@
#include <linux/export.h>
#include <linux/moduleparam.h>
#include <linux/slab.h>
+#include <linux/workqueue.h>
/*
* common variables
@@ -60,6 +61,14 @@
#define call_ctl(type,rec) snd_seq_kernel_client_ctl(system_client, type, rec)
+/* call snd_seq_oss_midi_lookup_ports() asynchronously */
+static void async_call_lookup_ports(struct work_struct *work)
+{
+ snd_seq_oss_midi_lookup_ports(system_client);
+}
+
+static DECLARE_WORK(async_lookup_work, async_call_lookup_ports);
+
/*
* create sequencer client for OSS sequencer
*/
@@ -85,9 +94,6 @@
system_client = rc;
debug_printk(("new client = %d\n", rc));
- /* look up midi devices */
- snd_seq_oss_midi_lookup_ports(system_client);
-
/* create annoucement receiver port */
memset(port, 0, sizeof(*port));
strcpy(port->name, "Receiver");
@@ -115,6 +121,9 @@
}
rc = 0;
+ /* look up midi devices */
+ schedule_work(&async_lookup_work);
+
__error:
kfree(port);
return rc;
@@ -160,6 +169,7 @@
int
snd_seq_oss_delete_client(void)
{
+ cancel_work_sync(&async_lookup_work);
if (system_client >= 0)
snd_seq_delete_kernel_client(system_client);
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index 677dc84..862d8489 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -72,7 +72,7 @@
* look up the existing ports
* this looks a very exhausting job.
*/
-int __init
+int
snd_seq_oss_midi_lookup_ports(int client)
{
struct snd_seq_client_info *clinfo;
diff --git a/sound/core/seq/seq_dummy.c b/sound/core/seq/seq_dummy.c
index dbc5507..f60d814 100644
--- a/sound/core/seq/seq_dummy.c
+++ b/sound/core/seq/seq_dummy.c
@@ -82,36 +82,6 @@
static int my_client = -1;
/*
- * unuse callback - send ALL_SOUNDS_OFF and RESET_CONTROLLERS events
- * to subscribers.
- * Note: this callback is called only after all subscribers are removed.
- */
-static int
-dummy_unuse(void *private_data, struct snd_seq_port_subscribe *info)
-{
- struct snd_seq_dummy_port *p;
- int i;
- struct snd_seq_event ev;
-
- p = private_data;
- memset(&ev, 0, sizeof(ev));
- if (p->duplex)
- ev.source.port = p->connect;
- else
- ev.source.port = p->port;
- ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
- ev.type = SNDRV_SEQ_EVENT_CONTROLLER;
- for (i = 0; i < 16; i++) {
- ev.data.control.channel = i;
- ev.data.control.param = MIDI_CTL_ALL_SOUNDS_OFF;
- snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
- ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS;
- snd_seq_kernel_client_dispatch(p->client, &ev, 0, 0);
- }
- return 0;
-}
-
-/*
* event input callback - just redirect events to subscribers
*/
static int
@@ -175,7 +145,6 @@
| SNDRV_SEQ_PORT_TYPE_PORT;
memset(&pcb, 0, sizeof(pcb));
pcb.owner = THIS_MODULE;
- pcb.unuse = dummy_unuse;
pcb.event_input = dummy_input;
pcb.private_free = dummy_free;
pcb.private_data = rec;
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index e04e750..7a9149b 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -56,8 +56,7 @@
static void snd_ak4113_free(struct ak4113 *chip)
{
- chip->init = 1; /* don't schedule new work */
- mb();
+ atomic_inc(&chip->wq_processing); /* don't schedule new work */
cancel_delayed_work_sync(&chip->work);
kfree(chip);
}
@@ -89,6 +88,7 @@
chip->write = write;
chip->private_data = private_data;
INIT_DELAYED_WORK(&chip->work, ak4113_stats);
+ atomic_set(&chip->wq_processing, 0);
for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
chip->regmap[reg] = pgm[reg];
@@ -139,13 +139,11 @@
void snd_ak4113_reinit(struct ak4113 *chip)
{
- chip->init = 1;
- mb();
- flush_delayed_work(&chip->work);
+ if (atomic_inc_return(&chip->wq_processing) == 1)
+ cancel_delayed_work_sync(&chip->work);
ak4113_init_regs(chip);
/* bring up statistics / event queing */
- chip->init = 0;
- if (chip->kctls[0])
+ if (atomic_dec_and_test(&chip->wq_processing))
schedule_delayed_work(&chip->work, HZ / 10);
}
EXPORT_SYMBOL_GPL(snd_ak4113_reinit);
@@ -632,8 +630,9 @@
{
struct ak4113 *chip = container_of(work, struct ak4113, work.work);
- if (!chip->init)
+ if (atomic_inc_return(&chip->wq_processing) == 1)
snd_ak4113_check_rate_and_errors(chip, chip->check_flags);
- schedule_delayed_work(&chip->work, HZ / 10);
+ if (atomic_dec_and_test(&chip->wq_processing))
+ schedule_delayed_work(&chip->work, HZ / 10);
}
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index 5bf4fca..84a1ee7 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -66,8 +66,7 @@
static void snd_ak4114_free(struct ak4114 *chip)
{
- chip->init = 1; /* don't schedule new work */
- mb();
+ atomic_inc(&chip->wq_processing); /* don't schedule new work */
cancel_delayed_work_sync(&chip->work);
kfree(chip);
}
@@ -100,6 +99,7 @@
chip->write = write;
chip->private_data = private_data;
INIT_DELAYED_WORK(&chip->work, ak4114_stats);
+ atomic_set(&chip->wq_processing, 0);
for (reg = 0; reg < 7; reg++)
chip->regmap[reg] = pgm[reg];
@@ -152,13 +152,11 @@
void snd_ak4114_reinit(struct ak4114 *chip)
{
- chip->init = 1;
- mb();
- flush_delayed_work(&chip->work);
+ if (atomic_inc_return(&chip->wq_processing) == 1)
+ cancel_delayed_work_sync(&chip->work);
ak4114_init_regs(chip);
/* bring up statistics / event queing */
- chip->init = 0;
- if (chip->kctls[0])
+ if (atomic_dec_and_test(&chip->wq_processing))
schedule_delayed_work(&chip->work, HZ / 10);
}
@@ -612,10 +610,10 @@
{
struct ak4114 *chip = container_of(work, struct ak4114, work.work);
- if (!chip->init)
+ if (atomic_inc_return(&chip->wq_processing) == 1)
snd_ak4114_check_rate_and_errors(chip, chip->check_flags);
-
- schedule_delayed_work(&chip->work, HZ / 10);
+ if (atomic_dec_and_test(&chip->wq_processing))
+ schedule_delayed_work(&chip->work, HZ / 10);
}
EXPORT_SYMBOL(snd_ak4114_create);
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index ddabb40..3a7946eb 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -73,9 +73,11 @@
#ifdef MSND_CLASSIC
# include "msnd_classic.h"
# define LOGNAME "msnd_classic"
+# define DEV_NAME "msnd-classic"
#else
# include "msnd_pinnacle.h"
# define LOGNAME "snd_msnd_pinnacle"
+# define DEV_NAME "msnd-pinnacle"
#endif
static void set_default_audio_parameters(struct snd_msnd *chip)
@@ -1068,8 +1070,6 @@
return 0;
}
-#define DEV_NAME "msnd-pinnacle"
-
static struct isa_driver snd_msnd_driver = {
.match = snd_msnd_isa_match,
.probe = snd_msnd_isa_probe,
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index b41ed86..e427dbf 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -173,11 +173,7 @@
#endif /* CONFIG_PNP */
-#ifdef OPTi93X
-#define DEV_NAME "opti93x"
-#else
-#define DEV_NAME "opti92x"
-#endif
+#define DEV_NAME KBUILD_MODNAME
static char * snd_opti9xx_names[] = {
"unknown",
@@ -1168,7 +1164,7 @@
static struct pnp_card_driver opti9xx_pnpc_driver = {
.flags = PNP_DRIVER_RES_DISABLE,
- .name = "opti9xx",
+ .name = DEV_NAME,
.id_table = snd_opti9xx_pnpids,
.probe = snd_opti9xx_pnp_probe,
.remove = snd_opti9xx_pnp_remove,
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index fe6fa93..3397ddb 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -30,6 +30,7 @@
select SND_PCM
select SND_AC97_CODEC
select SND_OPL3_LIB
+ select ZONE_DMA
help
Say 'Y' or 'M' to include support for Avance Logic ALS300/ALS300+
@@ -54,6 +55,7 @@
tristate "ALi M5451 PCI Audio Controller"
select SND_MPU401_UART
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for the integrated AC97 sound
device on motherboards using the ALi M5451 Audio Controller
@@ -158,6 +160,7 @@
select SND_PCM
select SND_RAWMIDI
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for Aztech AZF3328 (PCI168)
soundcards.
@@ -463,6 +466,7 @@
select SND_HWDEP
select SND_RAWMIDI
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y to include support for Sound Blaster PCI 512, Live!,
Audigy and E-mu APS (partially supported) soundcards.
@@ -478,6 +482,7 @@
tristate "Emu10k1X (Dell OEM Version)"
select SND_AC97_CODEC
select SND_RAWMIDI
+ select ZONE_DMA
help
Say Y here to include support for the Dell OEM version of the
Sound Blaster Live!.
@@ -511,6 +516,7 @@
select SND_OPL3_LIB
select SND_MPU401_UART
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on ESS Solo-1
(ES1938, ES1946, ES1969) chips.
@@ -522,6 +528,7 @@
tristate "ESS ES1968/1978 (Maestro-1/2/2E)"
select SND_MPU401_UART
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on ESS Maestro
1/2/2E chips.
@@ -603,6 +610,7 @@
select SND_MPU401_UART
select SND_AC97_CODEC
select BITREVERSE
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on the
ICE1712 (Envy24) chip.
@@ -690,6 +698,7 @@
config SND_MAESTRO3
tristate "ESS Allegro/Maestro3"
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on ESS Maestro 3
(Allegro) chips.
@@ -786,6 +795,7 @@
tristate "SiS 7019 Audio Accelerator"
depends on X86 && !X86_64
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for the SiS 7019 Audio Accelerator.
@@ -797,6 +807,7 @@
select SND_OPL3_LIB
select SND_MPU401_UART
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on the S3
SonicVibes chip.
@@ -808,6 +819,7 @@
tristate "Trident 4D-Wave DX/NX; SiS 7018"
select SND_MPU401_UART
select SND_AC97_CODEC
+ select ZONE_DMA
help
Say Y here to include support for soundcards based on Trident
4D-Wave DX/NX or SiS 7018 chips.
@@ -844,8 +856,8 @@
select SND_JACK if INPUT=y || INPUT=SND
help
Say Y here to include support for sound cards based on the
- Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS,
- Essence ST (Deluxe), and Essence STX.
+ Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX,
+ Essence ST (Deluxe), and Essence STX (II).
Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental;
for the Xense, missing.
diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index fbc1720..a471d82 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -769,7 +769,10 @@
s->number);
ds->drained_count++;
if (ds->drained_count > 20) {
+ unsigned long flags;
+ snd_pcm_stream_lock_irqsave(s, flags);
snd_pcm_stop(s, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock_irqrestore(s, flags);
continue;
}
} else {
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index 6e78c67..819430a 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -689,7 +689,9 @@
if (! dma->substream || ! dma->running)
return;
snd_printdd("atiixp: XRUN detected (DMA %d)\n", dma->ops->type);
+ snd_pcm_stream_lock(dma->substream);
snd_pcm_stop(dma->substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(dma->substream);
}
/*
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index d0bec7b..57f4182 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -638,7 +638,9 @@
if (! dma->substream || ! dma->running)
return;
snd_printdd("atiixp-modem: XRUN detected (DMA %d)\n", dma->ops->type);
+ snd_pcm_stream_lock(dma->substream);
snd_pcm_stop(dma->substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(dma->substream);
}
/*
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index cae3659..0a34b5f 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -85,6 +85,8 @@
* get more voice for pcm
*
* terminate most inactive voice and give it as a pcm voice.
+ *
+ * voice_lock is already held.
*/
int
snd_emu10k1_synth_get_voice(struct snd_emu10k1 *hw)
@@ -92,12 +94,10 @@
struct snd_emux *emu;
struct snd_emux_voice *vp;
struct best_voice best[V_END];
- unsigned long flags;
int i;
emu = hw->synth;
- spin_lock_irqsave(&emu->voice_lock, flags);
lookup_voices(emu, hw, best, 1); /* no OFF voices */
for (i = 0; i < V_END; i++) {
if (best[i].voice >= 0) {
@@ -113,11 +113,9 @@
vp->emu->num_voices--;
vp->ch = -1;
vp->state = SNDRV_EMUX_ST_OFF;
- spin_unlock_irqrestore(&emu->voice_lock, flags);
return ch;
}
}
- spin_unlock_irqrestore(&emu->voice_lock, flags);
/* not found */
return -ENOMEM;
diff --git a/sound/pci/emu10k1/emuproc.c b/sound/pci/emu10k1/emuproc.c
index 2ca9f2e..53745f4 100644
--- a/sound/pci/emu10k1/emuproc.c
+++ b/sound/pci/emu10k1/emuproc.c
@@ -241,31 +241,22 @@
struct snd_emu10k1 *emu = entry->private_data;
u32 value;
u32 value2;
- unsigned long flags;
u32 rate;
if (emu->card_capabilities->emu_model) {
- spin_lock_irqsave(&emu->emu_lock, flags);
snd_emu1010_fpga_read(emu, 0x38, &value);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
if ((value & 0x1) == 0) {
- spin_lock_irqsave(&emu->emu_lock, flags);
snd_emu1010_fpga_read(emu, 0x2a, &value);
snd_emu1010_fpga_read(emu, 0x2b, &value2);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
rate = 0x1770000 / (((value << 5) | value2)+1);
snd_iprintf(buffer, "ADAT Locked : %u\n", rate);
} else {
snd_iprintf(buffer, "ADAT Unlocked\n");
}
- spin_lock_irqsave(&emu->emu_lock, flags);
snd_emu1010_fpga_read(emu, 0x20, &value);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
if ((value & 0x4) == 0) {
- spin_lock_irqsave(&emu->emu_lock, flags);
snd_emu1010_fpga_read(emu, 0x28, &value);
snd_emu1010_fpga_read(emu, 0x29, &value2);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
rate = 0x1770000 / (((value << 5) | value2)+1);
snd_iprintf(buffer, "SPDIF Locked : %d\n", rate);
} else {
@@ -410,14 +401,11 @@
{
struct snd_emu10k1 *emu = entry->private_data;
u32 value;
- unsigned long flags;
int i;
snd_iprintf(buffer, "EMU1010 Registers:\n\n");
for(i = 0; i < 0x40; i+=1) {
- spin_lock_irqsave(&emu->emu_lock, flags);
snd_emu1010_fpga_read(emu, i, &value);
- spin_unlock_irqrestore(&emu->emu_lock, flags);
snd_iprintf(buffer, "%02X: %08X, %02X\n", i, value, (value >> 8) & 0x7f);
}
}
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index 7c11d46..48a9d00 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -860,7 +860,7 @@
}
}
if (id < 0 && quirk) {
- for (q = quirk; q->subvendor; q++) {
+ for (q = quirk; q->subvendor || q->subdevice; q++) {
unsigned int vendorid =
q->subdevice | (q->subvendor << 16);
unsigned int mask = 0xffff0000 | q->subdevice_mask;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 55108b5..83a0f9b4 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -327,8 +327,10 @@
unsigned int parm;
parm = snd_hda_param_read(codec, nid, AC_PAR_NODE_COUNT);
- if (parm == -1)
+ if (parm == -1) {
+ *start_id = 0;
return 0;
+ }
*start_id = (parm >> 16) & 0x7fff;
return (int)(parm & 0x7fff);
}
@@ -2517,9 +2519,6 @@
cancel_delayed_work_sync(&codec->jackpoll_work);
#ifdef CONFIG_PM
cancel_delayed_work_sync(&codec->power_work);
- codec->power_on = 0;
- codec->power_transition = 0;
- codec->power_jiffies = jiffies;
flush_workqueue(bus->workq);
#endif
snd_hda_ctls_clear(codec);
@@ -3927,6 +3926,10 @@
* in the resume / power-save sequence
*/
hda_keep_power_on(codec);
+ if (codec->pm_down_notified) {
+ codec->pm_down_notified = 0;
+ hda_call_pm_notify(codec->bus, true);
+ }
hda_set_power_state(codec, AC_PWRST_D0);
restore_shutup_pins(codec);
hda_exec_init_verbs(codec);
@@ -4789,8 +4792,8 @@
spin_unlock(&codec->power_lock);
state = hda_call_codec_suspend(codec, true);
- codec->pm_down_notified = 0;
- if (!bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) {
+ if (!codec->pm_down_notified &&
+ !bus->power_keep_link_on && (state & AC_PWRST_CLK_STOP_OK)) {
codec->pm_down_notified = 1;
hda_call_pm_notify(bus, false);
}
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 4b1524a..db67e5b 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -468,6 +468,20 @@
memset(path, 0, sizeof(*path));
}
+/* return a DAC if paired to the given pin by codec driver */
+static hda_nid_t get_preferred_dac(struct hda_codec *codec, hda_nid_t pin)
+{
+ struct hda_gen_spec *spec = codec->spec;
+ const hda_nid_t *list = spec->preferred_dacs;
+
+ if (!list)
+ return 0;
+ for (; *list; list += 2)
+ if (*list == pin)
+ return list[1];
+ return 0;
+}
+
/* look for an empty DAC slot */
static hda_nid_t look_for_dac(struct hda_codec *codec, hda_nid_t pin,
bool is_digital)
@@ -519,7 +533,7 @@
}
#define nid_has_mute(codec, nid, dir) \
- check_amp_caps(codec, nid, dir, AC_AMPCAP_MUTE)
+ check_amp_caps(codec, nid, dir, (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE))
#define nid_has_volume(codec, nid, dir) \
check_amp_caps(codec, nid, dir, AC_AMPCAP_NUM_STEPS)
@@ -621,19 +635,52 @@
if (enable)
val = (caps & AC_AMPCAP_OFFSET) >> AC_AMPCAP_OFFSET_SHIFT;
}
- if (caps & AC_AMPCAP_MUTE) {
+ if (caps & (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE)) {
if (!enable)
val |= HDA_AMP_MUTE;
}
return val;
}
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid, int dir)
+{
+ unsigned int wcaps = get_wcaps(codec, nid);
+ hda_nid_t conn;
+
+ if (wcaps & AC_WCAP_STEREO)
+ return true;
+ if (dir != HDA_INPUT || get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+ return false;
+ if (snd_hda_get_num_conns(codec, nid) != 1)
+ return false;
+ if (snd_hda_get_connections(codec, nid, &conn, 1) < 0)
+ return false;
+ return !!(get_wcaps(codec, conn) & AC_WCAP_STEREO);
+}
+
/* initialize the amp value (only at the first time) */
static void init_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx)
{
unsigned int caps = query_amp_caps(codec, nid, dir);
int val = get_amp_val_to_activate(codec, nid, dir, caps, false);
- snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val);
+
+ if (is_stereo_amps(codec, nid, dir))
+ snd_hda_codec_amp_init_stereo(codec, nid, dir, idx, 0xff, val);
+ else
+ snd_hda_codec_amp_init(codec, nid, 0, dir, idx, 0xff, val);
+}
+
+/* update the amp, doing in stereo or mono depending on NID */
+static int update_amp(struct hda_codec *codec, hda_nid_t nid, int dir, int idx,
+ unsigned int mask, unsigned int val)
+{
+ if (is_stereo_amps(codec, nid, dir))
+ return snd_hda_codec_amp_stereo(codec, nid, dir, idx,
+ mask, val);
+ else
+ return snd_hda_codec_amp_update(codec, nid, 0, dir, idx,
+ mask, val);
}
/* calculate amp value mask we can modify;
@@ -645,7 +692,7 @@
{
unsigned int mask = 0xff;
- if (caps & AC_AMPCAP_MUTE) {
+ if (caps & (AC_AMPCAP_MUTE | AC_AMPCAP_MIN_MUTE)) {
if (is_ctl_associated(codec, nid, dir, idx, NID_PATH_MUTE_CTL))
mask &= ~0x80;
}
@@ -673,7 +720,7 @@
return;
val &= mask;
- snd_hda_codec_amp_stereo(codec, nid, dir, idx, mask, val);
+ update_amp(codec, nid, dir, idx, mask, val);
}
static void activate_amp_out(struct hda_codec *codec, struct nid_path *path,
@@ -786,10 +833,10 @@
if (spec->own_eapd_ctl ||
!(snd_hda_query_pin_caps(codec, pin) & AC_PINCAP_EAPD))
return;
- if (codec->inv_eapd)
- enable = !enable;
if (spec->keep_eapd_on && !enable)
return;
+ if (codec->inv_eapd)
+ enable = !enable;
snd_hda_codec_update_cache(codec, pin, 0,
AC_VERB_SET_EAPD_BTLENABLE,
enable ? 0x02 : 0x00);
@@ -840,7 +887,7 @@
const char *pfx, const char *dir,
const char *sfx, int cidx, unsigned long val)
{
- char name[32];
+ char name[44];
snprintf(name, sizeof(name), "%s %s %s", pfx, dir, sfx);
if (!add_control(spec, type, name, cidx, val))
return -ENOMEM;
@@ -1134,7 +1181,14 @@
continue;
}
- dacs[i] = look_for_dac(codec, pin, false);
+ dacs[i] = get_preferred_dac(codec, pin);
+ if (dacs[i]) {
+ if (is_dac_already_used(codec, dacs[i]))
+ badness += bad->shared_primary;
+ }
+
+ if (!dacs[i])
+ dacs[i] = look_for_dac(codec, pin, false);
if (!dacs[i] && !i) {
/* try to steal the DAC of surrounds for the front */
for (j = 1; j < num_outs; j++) {
@@ -2445,12 +2499,8 @@
for (i = 0; i < num_pins; i++) {
hda_nid_t pin = pins[i];
- if (pin == spec->hp_mic_pin) {
- int ret = create_hp_mic_jack_mode(codec, pin);
- if (ret < 0)
- return ret;
+ if (pin == spec->hp_mic_pin)
continue;
- }
if (get_out_jack_num_items(codec, pin) > 1) {
struct snd_kcontrol_new *knew;
char name[44];
@@ -2703,7 +2753,7 @@
val &= ~(AC_PINCTL_VREFEN | PIN_HP);
val |= get_vref_idx(vref_caps, idx) | PIN_IN;
} else
- val = snd_hda_get_default_vref(codec, nid);
+ val = snd_hda_get_default_vref(codec, nid) | PIN_IN;
}
snd_hda_set_pin_ctl_cache(codec, nid, val);
call_hp_automute(codec, NULL);
@@ -2723,9 +2773,6 @@
struct hda_gen_spec *spec = codec->spec;
struct snd_kcontrol_new *knew;
- if (get_out_jack_num_items(codec, pin) <= 1 &&
- get_in_jack_num_items(codec, pin) <= 1)
- return 0; /* no need */
knew = snd_hda_gen_add_kctl(spec, "Headphone Mic Jack Mode",
&hp_mic_jack_mode_enum);
if (!knew)
@@ -2754,6 +2801,44 @@
return 0;
}
+/* return true if either a volume or a mute amp is found for the given
+ * aamix path; the amp has to be either in the mixer node or its direct leaf
+ */
+static bool look_for_mix_leaf_ctls(struct hda_codec *codec, hda_nid_t mix_nid,
+ hda_nid_t pin, unsigned int *mix_val,
+ unsigned int *mute_val)
+{
+ int idx, num_conns;
+ const hda_nid_t *list;
+ hda_nid_t nid;
+
+ idx = snd_hda_get_conn_index(codec, mix_nid, pin, true);
+ if (idx < 0)
+ return false;
+
+ *mix_val = *mute_val = 0;
+ if (nid_has_volume(codec, mix_nid, HDA_INPUT))
+ *mix_val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
+ if (nid_has_mute(codec, mix_nid, HDA_INPUT))
+ *mute_val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
+ if (*mix_val && *mute_val)
+ return true;
+
+ /* check leaf node */
+ num_conns = snd_hda_get_conn_list(codec, mix_nid, &list);
+ if (num_conns < idx)
+ return false;
+ nid = list[idx];
+ if (!*mix_val && nid_has_volume(codec, nid, HDA_OUTPUT) &&
+ !is_ctl_associated(codec, nid, HDA_OUTPUT, 0, NID_PATH_VOL_CTL))
+ *mix_val = HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_OUTPUT);
+ if (!*mute_val && nid_has_mute(codec, nid, HDA_OUTPUT) &&
+ !is_ctl_associated(codec, nid, HDA_OUTPUT, 0, NID_PATH_MUTE_CTL))
+ *mute_val = HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_OUTPUT);
+
+ return *mix_val || *mute_val;
+}
+
/* create input playback/capture controls for the given pin */
static int new_analog_input(struct hda_codec *codec, int input_idx,
hda_nid_t pin, const char *ctlname, int ctlidx,
@@ -2761,12 +2846,11 @@
{
struct hda_gen_spec *spec = codec->spec;
struct nid_path *path;
- unsigned int val;
+ unsigned int mix_val, mute_val;
int err, idx;
- if (!nid_has_volume(codec, mix_nid, HDA_INPUT) &&
- !nid_has_mute(codec, mix_nid, HDA_INPUT))
- return 0; /* no need for analog loopback */
+ if (!look_for_mix_leaf_ctls(codec, mix_nid, pin, &mix_val, &mute_val))
+ return 0;
path = snd_hda_add_new_path(codec, pin, mix_nid, 0);
if (!path)
@@ -2775,20 +2859,18 @@
spec->loopback_paths[input_idx] = snd_hda_get_path_idx(codec, path);
idx = path->idx[path->depth - 1];
- if (nid_has_volume(codec, mix_nid, HDA_INPUT)) {
- val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
- err = __add_pb_vol_ctrl(spec, HDA_CTL_WIDGET_VOL, ctlname, ctlidx, val);
+ if (mix_val) {
+ err = __add_pb_vol_ctrl(spec, HDA_CTL_WIDGET_VOL, ctlname, ctlidx, mix_val);
if (err < 0)
return err;
- path->ctls[NID_PATH_VOL_CTL] = val;
+ path->ctls[NID_PATH_VOL_CTL] = mix_val;
}
- if (nid_has_mute(codec, mix_nid, HDA_INPUT)) {
- val = HDA_COMPOSE_AMP_VAL(mix_nid, 3, idx, HDA_INPUT);
- err = __add_pb_sw_ctrl(spec, HDA_CTL_WIDGET_MUTE, ctlname, ctlidx, val);
+ if (mute_val) {
+ err = __add_pb_sw_ctrl(spec, HDA_CTL_WIDGET_MUTE, ctlname, ctlidx, mute_val);
if (err < 0)
return err;
- path->ctls[NID_PATH_MUTE_CTL] = val;
+ path->ctls[NID_PATH_MUTE_CTL] = mute_val;
}
path->active = true;
@@ -3474,7 +3556,7 @@
if (!multi)
err = create_single_cap_vol_ctl(codec, n, vol, sw,
inv_dmic);
- else if (!multi_cap_vol)
+ else if (!multi_cap_vol && !inv_dmic)
err = create_bind_cap_vol_ctl(codec, n, vol, sw);
else
err = create_multi_cap_vol_ctl(codec);
@@ -4175,6 +4257,24 @@
return AC_PWRST_D3;
}
+/* mute all aamix inputs initially; parse up to the first leaves */
+static void mute_all_mixer_nid(struct hda_codec *codec, hda_nid_t mix)
+{
+ int i, nums;
+ const hda_nid_t *conn;
+ bool has_amp;
+
+ nums = snd_hda_get_conn_list(codec, mix, &conn);
+ has_amp = nid_has_mute(codec, mix, HDA_INPUT);
+ for (i = 0; i < nums; i++) {
+ if (has_amp)
+ update_amp(codec, mix, HDA_INPUT, i,
+ 0xff, HDA_AMP_MUTE);
+ else if (nid_has_volume(codec, conn[i], HDA_OUTPUT))
+ update_amp(codec, conn[i], HDA_OUTPUT, 0,
+ 0xff, HDA_AMP_MUTE);
+ }
+}
/*
* Parse the given BIOS configuration and set up the hda_gen_spec
@@ -4287,6 +4387,17 @@
if (err < 0)
return err;
+ /* create "Headphone Mic Jack Mode" if no input selection is
+ * available (or user specifies add_jack_modes hint)
+ */
+ if (spec->hp_mic_pin &&
+ (spec->auto_mic || spec->input_mux.num_items == 1 ||
+ spec->add_jack_modes)) {
+ err = create_hp_mic_jack_mode(codec, spec->hp_mic_pin);
+ if (err < 0)
+ return err;
+ }
+
if (spec->add_jack_modes) {
if (cfg->line_out_type != AUTO_PIN_SPEAKER_OUT) {
err = create_out_jack_modes(codec, cfg->line_outs,
@@ -4302,6 +4413,10 @@
}
}
+ /* mute all aamix input initially */
+ if (spec->mixer_nid)
+ mute_all_mixer_nid(codec, spec->mixer_nid);
+
dig_only:
parse_digital(codec);
@@ -4383,9 +4498,11 @@
true, &spec->vmaster_mute.sw_kctl);
if (err < 0)
return err;
- if (spec->vmaster_mute.hook)
+ if (spec->vmaster_mute.hook) {
snd_hda_add_vmaster_hook(codec, &spec->vmaster_mute,
spec->vmaster_mute_enum);
+ snd_hda_sync_vmaster_hook(&spec->vmaster_mute);
+ }
}
free_kctls(spec); /* no longer needed */
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 7620031..a18a100 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -241,6 +241,9 @@
const struct badness_table *main_out_badness;
const struct badness_table *extra_out_badness;
+ /* preferred pin/DAC pairs; an array of paired NIDs */
+ const hda_nid_t *preferred_dacs;
+
/* loopback mixing mode */
bool aamix_mode;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index de18722..1800db6 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -3332,9 +3332,14 @@
* white/black-list for enable_msi
*/
static struct snd_pci_quirk msi_black_list[] = {
+ SND_PCI_QUIRK(0x103c, 0x2191, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x2192, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x21f7, "HP", 0), /* AMD Hudson */
+ SND_PCI_QUIRK(0x103c, 0x21fa, "HP", 0), /* AMD Hudson */
SND_PCI_QUIRK(0x1043, 0x81f2, "ASUS", 0), /* Athlon64 X2 + nvidia */
SND_PCI_QUIRK(0x1043, 0x81f6, "ASUS", 0), /* nvidia */
SND_PCI_QUIRK(0x1043, 0x822d, "ASUS", 0), /* Athlon64 X2 + nvidia MCP55 */
+ SND_PCI_QUIRK(0x1179, 0xfb44, "Toshiba Satellite C870", 0), /* AMD Hudson */
SND_PCI_QUIRK(0x1849, 0x0888, "ASRock", 0), /* Athlon64 X2 + nvidia */
SND_PCI_QUIRK(0xa0a0, 0x0575, "Aopen MZ915-M", 0), /* ICH6 */
{}
@@ -3851,6 +3856,9 @@
/* Lynx Point */
{ PCI_DEVICE(0x8086, 0x8c20),
.driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+ /* 9 Series */
+ { PCI_DEVICE(0x8086, 0x8ca0),
+ .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
/* Wellsburg */
{ PCI_DEVICE(0x8086, 0x8d20),
.driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index e0bf753..2e7493e 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -562,6 +562,14 @@
return chans;
}
+static inline void snd_hda_override_wcaps(struct hda_codec *codec,
+ hda_nid_t nid, u32 val)
+{
+ if (nid >= codec->start_nid &&
+ nid < codec->start_nid + codec->num_nodes)
+ codec->wcaps[nid - codec->start_nid] = val;
+}
+
u32 query_amp_caps(struct hda_codec *codec, hda_nid_t nid, int direction);
int snd_hda_override_amp_caps(struct hda_codec *codec, hda_nid_t nid, int dir,
unsigned int caps);
@@ -667,7 +675,7 @@
if (state & AC_PWRST_ERROR)
return true;
state = (state >> 4) & 0x0f;
- return (state != target_state);
+ return (state == target_state);
}
unsigned int snd_hda_codec_eapd_power_filter(struct hda_codec *codec,
diff --git a/sound/pci/hda/hda_proc.c b/sound/pci/hda/hda_proc.c
index 0fee8fa..eb94e49 100644
--- a/sound/pci/hda/hda_proc.c
+++ b/sound/pci/hda/hda_proc.c
@@ -129,13 +129,38 @@
(caps & AC_AMPCAP_MUTE) >> AC_AMPCAP_MUTE_SHIFT);
}
+/* is this a stereo widget or a stereo-to-mono mix? */
+static bool is_stereo_amps(struct hda_codec *codec, hda_nid_t nid,
+ int dir, unsigned int wcaps, int indices)
+{
+ hda_nid_t conn;
+
+ if (wcaps & AC_WCAP_STEREO)
+ return true;
+ /* check for a stereo-to-mono mix; it must be:
+ * only a single connection, only for input, and only a mixer widget
+ */
+ if (indices != 1 || dir != HDA_INPUT ||
+ get_wcaps_type(wcaps) != AC_WID_AUD_MIX)
+ return false;
+
+ if (snd_hda_get_raw_connections(codec, nid, &conn, 1) < 0)
+ return false;
+ /* the connection source is a stereo? */
+ wcaps = snd_hda_param_read(codec, conn, AC_PAR_AUDIO_WIDGET_CAP);
+ return !!(wcaps & AC_WCAP_STEREO);
+}
+
static void print_amp_vals(struct snd_info_buffer *buffer,
struct hda_codec *codec, hda_nid_t nid,
- int dir, int stereo, int indices)
+ int dir, unsigned int wcaps, int indices)
{
unsigned int val;
+ bool stereo;
int i;
+ stereo = is_stereo_amps(codec, nid, dir, wcaps, indices);
+
dir = dir == HDA_OUTPUT ? AC_AMP_GET_OUTPUT : AC_AMP_GET_INPUT;
for (i = 0; i < indices; i++) {
snd_iprintf(buffer, " [");
@@ -682,12 +707,10 @@
(codec->single_adc_amp &&
wid_type == AC_WID_AUD_IN))
print_amp_vals(buffer, codec, nid, HDA_INPUT,
- wid_caps & AC_WCAP_STEREO,
- 1);
+ wid_caps, 1);
else
print_amp_vals(buffer, codec, nid, HDA_INPUT,
- wid_caps & AC_WCAP_STEREO,
- conn_len);
+ wid_caps, conn_len);
}
if (wid_caps & AC_WCAP_OUT_AMP) {
snd_iprintf(buffer, " Amp-Out caps: ");
@@ -696,11 +719,10 @@
if (wid_type == AC_WID_PIN &&
codec->pin_amp_workaround)
print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
- wid_caps & AC_WCAP_STEREO,
- conn_len);
+ wid_caps, conn_len);
else
print_amp_vals(buffer, codec, nid, HDA_OUTPUT,
- wid_caps & AC_WCAP_STEREO, 1);
+ wid_caps, 1);
}
switch (wid_type) {
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 977b0d8..290e098 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -1197,8 +1197,12 @@
static void ad_fixup_inv_jack_detect(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
- if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ struct ad198x_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
codec->inv_jack_detect = 1;
+ spec->gen.keep_eapd_on = 1;
+ }
}
enum {
@@ -1223,6 +1227,14 @@
{
int err;
struct ad198x_spec *spec;
+ static hda_nid_t preferred_pairs[] = {
+ 0x1a, 0x03,
+ 0x1b, 0x03,
+ 0x1c, 0x04,
+ 0x1d, 0x05,
+ 0x1e, 0x03,
+ 0
+ };
err = alloc_ad_spec(codec);
if (err < 0)
@@ -1243,6 +1255,8 @@
* So, let's disable the shared stream.
*/
spec->gen.multiout.no_share_stream = 1;
+ /* give fixed DAC/pin pairs */
+ spec->gen.preferred_dacs = preferred_pairs;
snd_hda_pick_fixup(codec, NULL, ad1986a_fixup_tbl, ad1986a_fixups);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
@@ -1666,6 +1680,7 @@
return err;
spec = codec->spec;
+ spec->gen.mixer_nid = 0x0e;
spec->gen.beep_nid = 0x10;
set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
err = ad198x_parse_auto_config(codec);
@@ -2112,6 +2127,9 @@
{
struct hda_codec *codec = private_data;
struct ad198x_spec *spec = codec->spec;
+
+ if (!spec->eapd_nid)
+ return;
snd_hda_codec_update_cache(codec, spec->eapd_nid, 0,
AC_VERB_SET_EAPD_BTLENABLE,
enabled ? 0x02 : 0x00);
@@ -3601,13 +3619,16 @@
{
struct ad198x_spec *spec = codec->spec;
- if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook;
+ break;
+ case HDA_FIXUP_ACT_PROBE:
if (spec->gen.autocfg.line_out_type == AUTO_PIN_SPEAKER_OUT)
spec->eapd_nid = spec->gen.autocfg.line_out_pins[0];
else
spec->eapd_nid = spec->gen.autocfg.speaker_pins[0];
- if (spec->eapd_nid)
- spec->gen.vmaster_mute.hook = ad_vmaster_eapd_hook;
+ break;
}
}
@@ -3646,6 +3667,7 @@
spec = codec->spec;
spec->gen.mixer_nid = 0x20;
+ spec->gen.mixer_merge_nid = 0x21;
spec->gen.beep_nid = 0x10;
set_beep_amp(spec, 0x10, 0, HDA_OUTPUT);
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 90ff7a3..4126f3d 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -2662,60 +2662,6 @@
}
/*
- * PCM stuffs
- */
-static void ca0132_setup_stream(struct hda_codec *codec, hda_nid_t nid,
- u32 stream_tag,
- int channel_id, int format)
-{
- unsigned int oldval, newval;
-
- if (!nid)
- return;
-
- snd_printdd(
- "ca0132_setup_stream: NID=0x%x, stream=0x%x, "
- "channel=%d, format=0x%x\n",
- nid, stream_tag, channel_id, format);
-
- /* update the format-id if changed */
- oldval = snd_hda_codec_read(codec, nid, 0,
- AC_VERB_GET_STREAM_FORMAT,
- 0);
- if (oldval != format) {
- msleep(20);
- snd_hda_codec_write(codec, nid, 0,
- AC_VERB_SET_STREAM_FORMAT,
- format);
- }
-
- oldval = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
- newval = (stream_tag << 4) | channel_id;
- if (oldval != newval) {
- snd_hda_codec_write(codec, nid, 0,
- AC_VERB_SET_CHANNEL_STREAMID,
- newval);
- }
-}
-
-static void ca0132_cleanup_stream(struct hda_codec *codec, hda_nid_t nid)
-{
- unsigned int val;
-
- if (!nid)
- return;
-
- snd_printdd(KERN_INFO "ca0132_cleanup_stream: NID=0x%x\n", nid);
-
- val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0);
- if (!val)
- return;
-
- snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_STREAM_FORMAT, 0);
- snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0);
-}
-
-/*
* PCM callbacks
*/
static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
@@ -2726,7 +2672,7 @@
{
struct ca0132_spec *spec = codec->spec;
- ca0132_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
+ snd_hda_codec_setup_stream(codec, spec->dacs[0], stream_tag, 0, format);
return 0;
}
@@ -2745,7 +2691,7 @@
if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID])
msleep(50);
- ca0132_cleanup_stream(codec, spec->dacs[0]);
+ snd_hda_codec_cleanup_stream(codec, spec->dacs[0]);
return 0;
}
@@ -2822,10 +2768,8 @@
unsigned int format,
struct snd_pcm_substream *substream)
{
- struct ca0132_spec *spec = codec->spec;
-
- ca0132_setup_stream(codec, spec->adcs[substream->number],
- stream_tag, 0, format);
+ snd_hda_codec_setup_stream(codec, hinfo->nid,
+ stream_tag, 0, format);
return 0;
}
@@ -2839,7 +2783,7 @@
if (spec->dsp_state == DSP_DOWNLOADING)
return 0;
- ca0132_cleanup_stream(codec, hinfo->nid);
+ snd_hda_codec_cleanup_stream(codec, hinfo->nid);
return 0;
}
@@ -4435,6 +4379,9 @@
return; /* NOP */
#endif
+ if (spec->dsp_state == DSP_DOWNLOAD_FAILED)
+ return; /* don't retry failures */
+
chipio_enable_clocks(codec);
spec->dsp_state = DSP_DOWNLOADING;
if (!ca0132_download_dsp_images(codec))
@@ -4611,7 +4558,8 @@
struct auto_pin_cfg *cfg = &spec->autocfg;
int i;
- spec->dsp_state = DSP_DOWNLOAD_INIT;
+ if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
+ spec->dsp_state = DSP_DOWNLOAD_INIT;
spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
snd_hda_power_up(codec);
@@ -4722,6 +4670,7 @@
codec->spec = spec;
spec->codec = codec;
+ spec->dsp_state = DSP_DOWNLOAD_INIT;
spec->num_mixers = 1;
spec->mixers[0] = ca0132_mixer;
@@ -4742,6 +4691,8 @@
return err;
codec->patch_ops = ca0132_patch_ops;
+ codec->pcm_format_first = 1;
+ codec->no_sticky_stream = 1;
return 0;
}
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index cccaf9c..e2642ba 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -363,6 +363,7 @@
SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81),
SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122),
SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101),
+ SND_PCI_QUIRK(0x106b, 0x5600, "MacBookAir 5,2", CS420X_MBP81),
SND_PCI_QUIRK(0x106b, 0x5b00, "MacBookAir 4,2", CS420X_MBA42),
SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE),
{} /* terminator */
@@ -531,6 +532,7 @@
return -ENOMEM;
spec->gen.automute_hook = cs_automute;
+ codec->single_adc_amp = 1;
snd_hda_pick_fixup(codec, cs420x_models, cs420x_fixup_tbl,
cs420x_fixups);
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index b314d3e..fab9099 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -3223,8 +3223,10 @@
CXT_PINCFG_LENOVO_TP410,
CXT_PINCFG_LEMOTE_A1004,
CXT_PINCFG_LEMOTE_A1205,
+ CXT_PINCFG_COMPAQ_CQ60,
CXT_FIXUP_STEREO_DMIC,
CXT_FIXUP_INC_MIC_BOOST,
+ CXT_FIXUP_GPIO1,
};
static void cxt_fixup_stereo_dmic(struct hda_codec *codec,
@@ -3295,6 +3297,15 @@
.type = HDA_FIXUP_PINS,
.v.pins = cxt_pincfg_lemote,
},
+ [CXT_PINCFG_COMPAQ_CQ60] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ /* 0x17 was falsely set up as a mic, it should 0x1d */
+ { 0x17, 0x400001f0 },
+ { 0x1d, 0x97a70120 },
+ { }
+ }
+ },
[CXT_FIXUP_STEREO_DMIC] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_stereo_dmic,
@@ -3303,15 +3314,26 @@
.type = HDA_FIXUP_FUNC,
.v.func = cxt5066_increase_mic_boost,
},
+ [CXT_FIXUP_GPIO1] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ { 0x01, AC_VERB_SET_GPIO_MASK, 0x01 },
+ { 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01 },
+ { 0x01, AC_VERB_SET_GPIO_DATA, 0x01 },
+ { }
+ },
+ },
};
static const struct snd_pci_quirk cxt5051_fixups[] = {
+ SND_PCI_QUIRK(0x103c, 0x360b, "Compaq CQ60", CXT_PINCFG_COMPAQ_CQ60),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo X200", CXT_PINCFG_LENOVO_X200),
{}
};
static const struct snd_pci_quirk cxt5066_fixups[] = {
SND_PCI_QUIRK(0x1025, 0x0543, "Acer Aspire One 522", CXT_FIXUP_STEREO_DMIC),
+ SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_GPIO1),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
SND_PCI_QUIRK(0x17aa, 0x215e, "Lenovo T410", CXT_PINCFG_LENOVO_TP410),
SND_PCI_QUIRK(0x17aa, 0x215f, "Lenovo T510", CXT_PINCFG_LENOVO_TP410),
@@ -3480,6 +3502,8 @@
.patch = patch_conexant_auto },
{ .id = 0x14f15115, .name = "CX20757",
.patch = patch_conexant_auto },
+ { .id = 0x14f151d7, .name = "CX20952",
+ .patch = patch_conexant_auto },
{} /* terminator */
};
@@ -3506,6 +3530,7 @@
MODULE_ALIAS("snd-hda-codec-id:14f15113");
MODULE_ALIAS("snd-hda-codec-id:14f15114");
MODULE_ALIAS("snd-hda-codec-id:14f15115");
+MODULE_ALIAS("snd-hda-codec-id:14f151d7");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Conexant HD-audio codec");
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index e12f7a0..ba442d2 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -67,6 +67,8 @@
struct delayed_work work;
struct snd_kcontrol *eld_ctl;
int repoll_count;
+ bool setup; /* the stream has been set up by prepare callback */
+ int channels; /* current number of channels */
bool non_pcm;
bool chmap_set; /* channel-map override by ALSA API? */
unsigned char chmap[8]; /* ALSA API channel-map */
@@ -84,6 +86,9 @@
unsigned int channels_max; /* max over all cvts */
struct hdmi_eld temp_eld;
+
+ bool dyn_pin_out;
+
/*
* Non-generic ATI/NVIDIA specific
*/
@@ -448,15 +453,25 @@
static void hdmi_init_pin(struct hda_codec *codec, hda_nid_t pin_nid)
{
+ struct hdmi_spec *spec = codec->spec;
+ int pin_out;
+
/* Unmute */
if (get_wcaps(codec, pin_nid) & AC_WCAP_OUT_AMP)
snd_hda_codec_write(codec, pin_nid, 0,
AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
- /* Enable pin out: some machines with GM965 gets broken output when
- * the pin is disabled or changed while using with HDMI
- */
+
+ if (spec->dyn_pin_out)
+ /* Disable pin out until stream is active */
+ pin_out = 0;
+ else
+ /* Enable pin out: some machines with GM965 gets broken output
+ * when the pin is disabled or changed while using with HDMI
+ */
+ pin_out = PIN_OUT;
+
snd_hda_codec_write(codec, pin_nid, 0,
- AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+ AC_VERB_SET_PIN_WIDGET_CONTROL, pin_out);
}
static int hdmi_get_channel_count(struct hda_codec *codec, hda_nid_t cvt_nid)
@@ -551,6 +566,17 @@
}
}
+ if (!ca) {
+ /* if there was no match, select the regular ALSA channel
+ * allocation with the matching number of channels */
+ for (i = 0; i < ARRAY_SIZE(channel_allocations); i++) {
+ if (channels == channel_allocations[i].channels) {
+ ca = channel_allocations[i].ca_index;
+ break;
+ }
+ }
+ }
+
snd_print_channel_allocation(eld->info.spk_alloc, buf, sizeof(buf));
snd_printdd("HDMI: select CA 0x%x for %d-channel allocation: %s\n",
ca, channels, buf);
@@ -725,9 +751,10 @@
static void hdmi_setup_fake_chmap(unsigned char *map, int ca)
{
int i;
+ int ordered_ca = get_channel_allocation_order(ca);
for (i = 0; i < 8; i++) {
- if (i < channel_allocations[ca].channels)
- map[i] = from_cea_slot((hdmi_channel_mapping[ca][i] >> 4) & 0x0f);
+ if (i < channel_allocations[ordered_ca].channels)
+ map[i] = from_cea_slot(hdmi_channel_mapping[ca][i] & 0x0f);
else
map[i] = 0;
}
@@ -868,18 +895,19 @@
return true;
}
-static void hdmi_setup_audio_infoframe(struct hda_codec *codec, int pin_idx,
- bool non_pcm,
- struct snd_pcm_substream *substream)
+static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
+ struct hdmi_spec_per_pin *per_pin,
+ bool non_pcm)
{
- struct hdmi_spec *spec = codec->spec;
- struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
hda_nid_t pin_nid = per_pin->pin_nid;
- int channels = substream->runtime->channels;
+ int channels = per_pin->channels;
struct hdmi_eld *eld;
int ca;
union audio_infoframe ai;
+ if (!channels)
+ return;
+
eld = &per_pin->sink_eld;
if (!eld->monitor_present)
return;
@@ -916,6 +944,14 @@
}
/*
+ * always configure channel mapping, it may have been changed by the
+ * user in the meantime
+ */
+ hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
+ channels, per_pin->chmap,
+ per_pin->chmap_set);
+
+ /*
* sizeof(ai) is used instead of sizeof(*hdmi_ai) or
* sizeof(*dp_ai) to avoid partial match/update problems when
* the user switches between HDMI/DP monitors.
@@ -926,20 +962,10 @@
"pin=%d channels=%d\n",
pin_nid,
channels);
- hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
- channels, per_pin->chmap,
- per_pin->chmap_set);
hdmi_stop_infoframe_trans(codec, pin_nid);
hdmi_fill_audio_infoframe(codec, pin_nid,
ai.bytes, sizeof(ai));
hdmi_start_infoframe_trans(codec, pin_nid);
- } else {
- /* For non-pcm audio switch, setup new channel mapping
- * accordingly */
- if (per_pin->non_pcm != non_pcm)
- hdmi_setup_channel_mapping(codec, pin_nid, non_pcm, ca,
- channels, per_pin->chmap,
- per_pin->chmap_set);
}
per_pin->non_pcm = non_pcm;
@@ -1146,7 +1172,7 @@
per_cvt->assigned = 1;
hinfo->nid = per_cvt->cvt_nid;
- snd_hda_codec_write(codec, per_pin->pin_nid, 0,
+ snd_hda_codec_write_cache(codec, per_pin->pin_nid, 0,
AC_VERB_SET_CONNECT_SEL,
mux_idx);
snd_hda_spdif_ctls_assign(codec, pin_idx, per_cvt->cvt_nid);
@@ -1263,6 +1289,7 @@
eld_changed = true;
}
if (update_eld) {
+ bool old_eld_valid = pin_eld->eld_valid;
pin_eld->eld_valid = eld->eld_valid;
eld_changed = pin_eld->eld_size != eld->eld_size ||
memcmp(pin_eld->eld_buffer, eld->eld_buffer,
@@ -1272,6 +1299,18 @@
eld->eld_size);
pin_eld->eld_size = eld->eld_size;
pin_eld->info = eld->info;
+
+ /* Haswell-specific workaround: re-setup when the transcoder is
+ * changed during the stream playback
+ */
+ if (codec->vendor_id == 0x80862807 &&
+ eld->eld_valid && !old_eld_valid && per_pin->setup) {
+ snd_hda_codec_write(codec, pin_nid, 0,
+ AC_VERB_SET_AMP_GAIN_MUTE,
+ AMP_OUT_UNMUTE);
+ hdmi_setup_audio_infoframe(codec, per_pin,
+ per_pin->non_pcm);
+ }
}
mutex_unlock(&pin_eld->lock);
@@ -1444,14 +1483,26 @@
hda_nid_t cvt_nid = hinfo->nid;
struct hdmi_spec *spec = codec->spec;
int pin_idx = hinfo_to_pin_index(spec, hinfo);
- hda_nid_t pin_nid = get_pin(spec, pin_idx)->pin_nid;
+ struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+ hda_nid_t pin_nid = per_pin->pin_nid;
bool non_pcm;
+ int pinctl;
non_pcm = check_non_pcm_per_cvt(codec, cvt_nid);
+ per_pin->channels = substream->runtime->channels;
+ per_pin->setup = true;
hdmi_set_channel_count(codec, cvt_nid, substream->runtime->channels);
- hdmi_setup_audio_infoframe(codec, pin_idx, non_pcm, substream);
+ hdmi_setup_audio_infoframe(codec, per_pin, non_pcm);
+
+ if (spec->dyn_pin_out) {
+ pinctl = snd_hda_codec_read(codec, pin_nid, 0,
+ AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+ snd_hda_codec_write(codec, pin_nid, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL,
+ pinctl | PIN_OUT);
+ }
return hdmi_setup_stream(codec, cvt_nid, pin_nid, stream_tag, format);
}
@@ -1472,6 +1523,7 @@
int cvt_idx, pin_idx;
struct hdmi_spec_per_cvt *per_cvt;
struct hdmi_spec_per_pin *per_pin;
+ int pinctl;
if (hinfo->nid) {
cvt_idx = cvt_nid_to_cvt_index(spec, hinfo->nid);
@@ -1488,9 +1540,20 @@
return -EINVAL;
per_pin = get_pin(spec, pin_idx);
+ if (spec->dyn_pin_out) {
+ pinctl = snd_hda_codec_read(codec, per_pin->pin_nid, 0,
+ AC_VERB_GET_PIN_WIDGET_CONTROL, 0);
+ snd_hda_codec_write(codec, per_pin->pin_nid, 0,
+ AC_VERB_SET_PIN_WIDGET_CONTROL,
+ pinctl & ~PIN_OUT);
+ }
+
snd_hda_spdif_ctls_unassign(codec, pin_idx);
per_pin->chmap_set = false;
memset(per_pin->chmap, 0, sizeof(per_pin->chmap));
+
+ per_pin->setup = false;
+ per_pin->channels = 0;
}
return 0;
@@ -1626,8 +1689,7 @@
per_pin->chmap_set = true;
memcpy(per_pin->chmap, chmap, sizeof(chmap));
if (prepared)
- hdmi_setup_audio_infoframe(codec, pin_idx, per_pin->non_pcm,
- substream);
+ hdmi_setup_audio_infoframe(codec, per_pin, per_pin->non_pcm);
return 0;
}
@@ -1715,6 +1777,9 @@
struct snd_pcm_chmap *chmap;
struct snd_kcontrol *kctl;
int i;
+
+ if (!codec->pcm_info[pin_idx].pcm)
+ break;
err = snd_pcm_add_chmap_ctls(codec->pcm_info[pin_idx].pcm,
SNDRV_PCM_STREAM_PLAYBACK,
NULL, 0, pin_idx, &chmap);
@@ -1967,8 +2032,9 @@
int err;
per_cvt = get_cvt(spec, 0);
- err = snd_hda_create_spdif_out_ctls(codec, per_cvt->cvt_nid,
- per_cvt->cvt_nid);
+ err = snd_hda_create_dig_out_ctls(codec, per_cvt->cvt_nid,
+ per_cvt->cvt_nid,
+ HDA_PCM_TYPE_HDMI);
if (err < 0)
return err;
return simple_hdmi_build_jack(codec, 0);
@@ -2441,6 +2507,21 @@
return 0;
}
+static int patch_nvhdmi(struct hda_codec *codec)
+{
+ struct hdmi_spec *spec;
+ int err;
+
+ err = patch_generic_hdmi(codec);
+ if (err)
+ return err;
+
+ spec = codec->spec;
+ spec->dyn_pin_out = true;
+
+ return 0;
+}
+
/*
* ATI-specific implementations
*
@@ -2513,29 +2594,30 @@
{ .id = 0x10de0005, .name = "MCP77/78 HDMI", .patch = patch_nvhdmi_8ch_7x },
{ .id = 0x10de0006, .name = "MCP77/78 HDMI", .patch = patch_nvhdmi_8ch_7x },
{ .id = 0x10de0007, .name = "MCP79/7A HDMI", .patch = patch_nvhdmi_8ch_7x },
-{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de000c, .name = "MCP89 HDMI", .patch = patch_generic_hdmi },
-{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP", .patch = patch_generic_hdmi },
+{ .id = 0x10de000a, .name = "GPU 0a HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de000b, .name = "GPU 0b HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de000c, .name = "MCP89 HDMI", .patch = patch_nvhdmi },
+{ .id = 0x10de000d, .name = "GPU 0d HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0010, .name = "GPU 10 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0011, .name = "GPU 11 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0012, .name = "GPU 12 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0013, .name = "GPU 13 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0014, .name = "GPU 14 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0015, .name = "GPU 15 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0016, .name = "GPU 16 HDMI/DP", .patch = patch_nvhdmi },
/* 17 is known to be absent */
-{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP", .patch = patch_generic_hdmi },
-{ .id = 0x10de0051, .name = "GPU 51 HDMI/DP", .patch = patch_generic_hdmi },
+{ .id = 0x10de0018, .name = "GPU 18 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0019, .name = "GPU 19 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de001a, .name = "GPU 1a HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de001b, .name = "GPU 1b HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de001c, .name = "GPU 1c HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0040, .name = "GPU 40 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0041, .name = "GPU 41 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0042, .name = "GPU 42 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0043, .name = "GPU 43 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0044, .name = "GPU 44 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0051, .name = "GPU 51 HDMI/DP", .patch = patch_nvhdmi },
+{ .id = 0x10de0060, .name = "GPU 60 HDMI/DP", .patch = patch_nvhdmi },
{ .id = 0x10de0067, .name = "MCP67 HDMI", .patch = patch_nvhdmi_2ch },
{ .id = 0x10de8001, .name = "MCP73 HDMI", .patch = patch_nvhdmi_2ch },
{ .id = 0x11069f80, .name = "VX900 HDMI/DP", .patch = patch_via_hdmi },
@@ -2588,6 +2670,7 @@
MODULE_ALIAS("snd-hda-codec-id:10de0043");
MODULE_ALIAS("snd-hda-codec-id:10de0044");
MODULE_ALIAS("snd-hda-codec-id:10de0051");
+MODULE_ALIAS("snd-hda-codec-id:10de0060");
MODULE_ALIAS("snd-hda-codec-id:10de0067");
MODULE_ALIAS("snd-hda-codec-id:10de8001");
MODULE_ALIAS("snd-hda-codec-id:11069f80");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 403010c..a8eb7fe 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -175,6 +175,8 @@
spec->pll_coef_idx);
val = snd_hda_codec_read(codec, spec->pll_nid, 0,
AC_VERB_GET_PROC_COEF, 0);
+ if (val == -1)
+ return;
snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
spec->pll_coef_idx);
snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF,
@@ -264,7 +266,7 @@
{
/* We currently only handle front, HP */
static hda_nid_t pins[] = {
- 0x0f, 0x10, 0x14, 0x15, 0
+ 0x0f, 0x10, 0x14, 0x15, 0x17, 0
};
hda_nid_t *p;
for (p = pins; *p; p++)
@@ -316,6 +318,7 @@
case 0x10ec0885:
case 0x10ec0887:
/*case 0x10ec0889:*/ /* this causes an SPDIF problem */
+ case 0x10ec0900:
alc889_coef_init(codec);
break;
case 0x10ec0888:
@@ -937,6 +940,7 @@
static const struct snd_pci_quirk beep_white_list[] = {
SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
+ SND_PCI_QUIRK(0x1043, 0x115d, "ASUS", 1),
SND_PCI_QUIRK(0x1043, 0x829f, "ASUS", 1),
SND_PCI_QUIRK(0x1043, 0x8376, "EeePC", 1),
SND_PCI_QUIRK(0x1043, 0x83ce, "EeePC", 1),
@@ -1027,6 +1031,7 @@
ALC880_FIXUP_GPIO2,
ALC880_FIXUP_MEDION_RIM,
ALC880_FIXUP_LG,
+ ALC880_FIXUP_LG_LW25,
ALC880_FIXUP_W810,
ALC880_FIXUP_EAPD_COEF,
ALC880_FIXUP_TCL_S700,
@@ -1036,6 +1041,7 @@
ALC880_FIXUP_UNIWILL,
ALC880_FIXUP_UNIWILL_DIG,
ALC880_FIXUP_Z71V,
+ ALC880_FIXUP_ASUS_W5A,
ALC880_FIXUP_3ST_BASE,
ALC880_FIXUP_3ST,
ALC880_FIXUP_3ST_DIG,
@@ -1085,6 +1091,14 @@
{ }
}
},
+ [ALC880_FIXUP_LG_LW25] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1a, 0x0181344f }, /* line-in */
+ { 0x1b, 0x0321403f }, /* headphone */
+ { }
+ }
+ },
[ALC880_FIXUP_W810] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -1198,6 +1212,26 @@
{ }
}
},
+ [ALC880_FIXUP_ASUS_W5A] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ /* set up the whole pins as BIOS is utterly broken */
+ { 0x14, 0x0121411f }, /* HP */
+ { 0x15, 0x411111f0 }, /* N/A */
+ { 0x16, 0x411111f0 }, /* N/A */
+ { 0x17, 0x411111f0 }, /* N/A */
+ { 0x18, 0x90a60160 }, /* mic */
+ { 0x19, 0x411111f0 }, /* N/A */
+ { 0x1a, 0x411111f0 }, /* N/A */
+ { 0x1b, 0x411111f0 }, /* N/A */
+ { 0x1c, 0x411111f0 }, /* N/A */
+ { 0x1d, 0x411111f0 }, /* N/A */
+ { 0x1e, 0xb743111e }, /* SPDIF out */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC880_FIXUP_GPIO1,
+ },
[ALC880_FIXUP_3ST_BASE] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -1319,6 +1353,7 @@
static const struct snd_pci_quirk alc880_fixup_tbl[] = {
SND_PCI_QUIRK(0x1019, 0x0f69, "Coeus G610P", ALC880_FIXUP_W810),
+ SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS W5A", ALC880_FIXUP_ASUS_W5A),
SND_PCI_QUIRK(0x1043, 0x1964, "ASUS Z71V", ALC880_FIXUP_Z71V),
SND_PCI_QUIRK_VENDOR(0x1043, "ASUS", ALC880_FIXUP_GPIO1),
SND_PCI_QUIRK(0x1558, 0x5401, "Clevo GPIO2", ALC880_FIXUP_GPIO2),
@@ -1337,6 +1372,7 @@
SND_PCI_QUIRK(0x1854, 0x003b, "LG", ALC880_FIXUP_LG),
SND_PCI_QUIRK(0x1854, 0x005f, "LG P1 Express", ALC880_FIXUP_LG),
SND_PCI_QUIRK(0x1854, 0x0068, "LG w1", ALC880_FIXUP_LG),
+ SND_PCI_QUIRK(0x1854, 0x0077, "LG LW25", ALC880_FIXUP_LG_LW25),
SND_PCI_QUIRK(0x19db, 0x4188, "TCL S700", ALC880_FIXUP_TCL_S700),
/* Below is the copied entries from alc880_quirks.c.
@@ -1463,6 +1499,7 @@
ALC260_FIXUP_KN1,
ALC260_FIXUP_FSC_S7020,
ALC260_FIXUP_FSC_S7020_JWSE,
+ ALC260_FIXUP_VAIO_PINS,
};
static void alc260_gpio1_automute(struct hda_codec *codec)
@@ -1556,12 +1593,10 @@
[ALC260_FIXUP_COEF] = {
.type = HDA_FIXUP_VERBS,
.v.verbs = (const struct hda_verb[]) {
- { 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
- { 0x20, AC_VERB_SET_PROC_COEF, 0x3040 },
+ { 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+ { 0x1a, AC_VERB_SET_PROC_COEF, 0x3040 },
{ }
},
- .chained = true,
- .chain_id = ALC260_FIXUP_HP_PIN_0F,
},
[ALC260_FIXUP_GPIO1] = {
.type = HDA_FIXUP_VERBS,
@@ -1576,8 +1611,8 @@
[ALC260_FIXUP_REPLACER] = {
.type = HDA_FIXUP_VERBS,
.v.verbs = (const struct hda_verb[]) {
- { 0x20, AC_VERB_SET_COEF_INDEX, 0x07 },
- { 0x20, AC_VERB_SET_PROC_COEF, 0x3050 },
+ { 0x1a, AC_VERB_SET_COEF_INDEX, 0x07 },
+ { 0x1a, AC_VERB_SET_PROC_COEF, 0x3050 },
{ }
},
.chained = true,
@@ -1603,6 +1638,24 @@
.chained = true,
.chain_id = ALC260_FIXUP_FSC_S7020,
},
+ [ALC260_FIXUP_VAIO_PINS] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ /* Pin configs are missing completely on some VAIOs */
+ { 0x0f, 0x01211020 },
+ { 0x10, 0x0001003f },
+ { 0x11, 0x411111f0 },
+ { 0x12, 0x01a15930 },
+ { 0x13, 0x411111f0 },
+ { 0x14, 0x411111f0 },
+ { 0x15, 0x411111f0 },
+ { 0x16, 0x411111f0 },
+ { 0x17, 0x411111f0 },
+ { 0x18, 0x411111f0 },
+ { 0x19, 0x411111f0 },
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc260_fixup_tbl[] = {
@@ -1611,6 +1664,8 @@
SND_PCI_QUIRK(0x1025, 0x008f, "Acer", ALC260_FIXUP_GPIO1),
SND_PCI_QUIRK(0x103c, 0x280a, "HP dc5750", ALC260_FIXUP_HP_DC5750),
SND_PCI_QUIRK(0x103c, 0x30ba, "HP Presario B1900", ALC260_FIXUP_HP_B1900),
+ SND_PCI_QUIRK(0x104d, 0x81bb, "Sony VAIO", ALC260_FIXUP_VAIO_PINS),
+ SND_PCI_QUIRK(0x104d, 0x81e2, "Sony VAIO TX", ALC260_FIXUP_HP_PIN_0F),
SND_PCI_QUIRK(0x10cf, 0x1326, "FSC LifeBook S7020", ALC260_FIXUP_FSC_S7020),
SND_PCI_QUIRK(0x1509, 0x4540, "Favorit 100XS", ALC260_FIXUP_GPIO1),
SND_PCI_QUIRK(0x152d, 0x0729, "Quanta KN1", ALC260_FIXUP_KN1),
@@ -1710,8 +1765,12 @@
ALC889_FIXUP_DAC_ROUTE,
ALC889_FIXUP_MBP_VREF,
ALC889_FIXUP_IMAC91_VREF,
+ ALC889_FIXUP_MBA11_VREF,
+ ALC889_FIXUP_MBA21_VREF,
+ ALC889_FIXUP_MP11_VREF,
ALC882_FIXUP_INV_DMIC,
ALC882_FIXUP_NO_PRIMARY_HP,
+ ALC887_FIXUP_ASUS_BASS,
};
static void alc889_fixup_coef(struct hda_codec *codec,
@@ -1812,17 +1871,13 @@
}
}
-/* Set VREF on speaker pins on imac91 */
-static void alc889_fixup_imac91_vref(struct hda_codec *codec,
- const struct hda_fixup *fix, int action)
+static void alc889_fixup_mac_pins(struct hda_codec *codec,
+ const hda_nid_t *nids, int num_nids)
{
struct alc_spec *spec = codec->spec;
- static hda_nid_t nids[2] = { 0x18, 0x1a };
int i;
- if (action != HDA_FIXUP_ACT_INIT)
- return;
- for (i = 0; i < ARRAY_SIZE(nids); i++) {
+ for (i = 0; i < num_nids; i++) {
unsigned int val;
val = snd_hda_codec_get_pin_target(codec, nids[i]);
val |= AC_PINCTL_VREF_50;
@@ -1831,6 +1886,36 @@
spec->gen.keep_vref_in_automute = 1;
}
+/* Set VREF on speaker pins on imac91 */
+static void alc889_fixup_imac91_vref(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static hda_nid_t nids[2] = { 0x18, 0x1a };
+
+ if (action == HDA_FIXUP_ACT_INIT)
+ alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
+/* Set VREF on speaker pins on mba11 */
+static void alc889_fixup_mba11_vref(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static hda_nid_t nids[1] = { 0x18 };
+
+ if (action == HDA_FIXUP_ACT_INIT)
+ alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
+/* Set VREF on speaker pins on mba21 */
+static void alc889_fixup_mba21_vref(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static hda_nid_t nids[2] = { 0x18, 0x19 };
+
+ if (action == HDA_FIXUP_ACT_INIT)
+ alc889_fixup_mac_pins(codec, nids, ARRAY_SIZE(nids));
+}
+
/* Don't take HP output as primary
* Strangely, the speaker output doesn't work on Vaio Z and some Vaio
* all-in-one desktop PCs (for example VGC-LN51JGB) through DAC 0x05
@@ -2025,6 +2110,24 @@
.chained = true,
.chain_id = ALC882_FIXUP_GPIO1,
},
+ [ALC889_FIXUP_MBA11_VREF] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc889_fixup_mba11_vref,
+ .chained = true,
+ .chain_id = ALC889_FIXUP_MBP_VREF,
+ },
+ [ALC889_FIXUP_MBA21_VREF] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc889_fixup_mba21_vref,
+ .chained = true,
+ .chain_id = ALC889_FIXUP_MBP_VREF,
+ },
+ [ALC889_FIXUP_MP11_VREF] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc889_fixup_mba11_vref,
+ .chained = true,
+ .chain_id = ALC885_FIXUP_MACPRO_GPIO,
+ },
[ALC882_FIXUP_INV_DMIC] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc_fixup_inv_dmic_0x12,
@@ -2033,6 +2136,13 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc882_fixup_no_primary_hp,
},
+ [ALC887_FIXUP_ASUS_BASS] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ {0x16, 0x99130130}, /* bass speaker */
+ {}
+ },
+ },
};
static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -2066,6 +2176,7 @@
SND_PCI_QUIRK(0x1043, 0x1873, "ASUS W90V", ALC882_FIXUP_ASUS_W90V),
SND_PCI_QUIRK(0x1043, 0x1971, "Asus W2JC", ALC882_FIXUP_ASUS_W2JC),
SND_PCI_QUIRK(0x1043, 0x835f, "Asus Eee 1601", ALC888_FIXUP_EEE1601),
+ SND_PCI_QUIRK(0x1043, 0x84bc, "ASUS ET2700", ALC887_FIXUP_ASUS_BASS),
SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT),
SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP),
SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP),
@@ -2074,14 +2185,14 @@
SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x00a1, "Macbook", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x00a4, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
- SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC885_FIXUP_MACPRO_GPIO),
+ SND_PCI_QUIRK(0x106b, 0x0c00, "Mac Pro", ALC889_FIXUP_MP11_VREF),
SND_PCI_QUIRK(0x106b, 0x1000, "iMac 24", ALC885_FIXUP_MACPRO_GPIO),
SND_PCI_QUIRK(0x106b, 0x2800, "AppleTV", ALC885_FIXUP_MACPRO_GPIO),
SND_PCI_QUIRK(0x106b, 0x2c00, "MacbookPro rev3", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x3000, "iMac", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x3200, "iMac 7,1 Aluminum", ALC882_FIXUP_EAPD),
- SND_PCI_QUIRK(0x106b, 0x3400, "MacBookAir 1,1", ALC889_FIXUP_MBP_VREF),
- SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBP_VREF),
+ SND_PCI_QUIRK(0x106b, 0x3400, "MacBookAir 1,1", ALC889_FIXUP_MBA11_VREF),
+ SND_PCI_QUIRK(0x106b, 0x3500, "MacBookAir 2,1", ALC889_FIXUP_MBA21_VREF),
SND_PCI_QUIRK(0x106b, 0x3600, "Macbook 3,1", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x3800, "MacbookPro 4,1", ALC889_FIXUP_MBP_VREF),
SND_PCI_QUIRK(0x106b, 0x3e00, "iMac 24 Aluminum", ALC885_FIXUP_MACPRO_GPIO),
@@ -2142,6 +2253,7 @@
switch (codec->vendor_id) {
case 0x10ec0882:
case 0x10ec0885:
+ case 0x10ec0900:
break;
default:
/* ALC883 and variants */
@@ -2370,6 +2482,7 @@
enum {
ALC268_FIXUP_INV_DMIC,
ALC268_FIXUP_HP_EAPD,
+ ALC268_FIXUP_SPDIF,
};
static const struct hda_fixup alc268_fixups[] = {
@@ -2384,6 +2497,13 @@
{}
}
},
+ [ALC268_FIXUP_SPDIF] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1e, 0x014b1180 }, /* enable SPDIF out */
+ {}
+ }
+ },
};
static const struct hda_model_fixup alc268_fixup_models[] = {
@@ -2393,6 +2513,7 @@
};
static const struct snd_pci_quirk alc268_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1025, 0x0139, "Acer TravelMate 6293", ALC268_FIXUP_SPDIF),
SND_PCI_QUIRK(0x1025, 0x015b, "Acer AOA 150 (ZG5)", ALC268_FIXUP_INV_DMIC),
/* below is codec SSID since multiple Toshiba laptops have the
* same PCI SSID 1179:ff00
@@ -2521,6 +2642,7 @@
ALC269_TYPE_ALC282,
ALC269_TYPE_ALC284,
ALC269_TYPE_ALC286,
+ ALC269_TYPE_ALC255,
};
/*
@@ -2545,6 +2667,7 @@
case ALC269_TYPE_ALC269VD:
case ALC269_TYPE_ALC282:
case ALC269_TYPE_ALC286:
+ case ALC269_TYPE_ALC255:
ssids = alc269_ssids;
break;
default:
@@ -2558,6 +2681,8 @@
static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
{
int val = alc_read_coef_idx(codec, 0x04);
+ if (val == -1)
+ return;
if (power_up)
val |= 1 << 11;
else
@@ -2738,12 +2863,30 @@
if (spec->mute_led_polarity)
enabled = !enabled;
- pinval = AC_PINCTL_IN_EN |
- (enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80);
+ pinval = snd_hda_codec_get_pin_target(codec, spec->mute_led_nid);
+ pinval &= ~AC_PINCTL_VREFEN;
+ pinval |= enabled ? AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_80;
if (spec->mute_led_nid)
snd_hda_set_pin_ctl_cache(codec, spec->mute_led_nid, pinval);
}
+/* Make sure the led works even in runtime suspend */
+static unsigned int led_power_filter(struct hda_codec *codec,
+ hda_nid_t nid,
+ unsigned int power_state)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (power_state != AC_PWRST_D3 || nid != spec->mute_led_nid)
+ return power_state;
+
+ /* Set pin ctl again, it might have just been set to 0 */
+ snd_hda_set_pin_ctl(codec, nid,
+ snd_hda_codec_get_pin_target(codec, nid));
+
+ return AC_PWRST_D0;
+}
+
static void alc269_fixup_hp_mute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -2763,6 +2906,7 @@
spec->mute_led_nid = pin - 0x0a + 0x18;
spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
spec->gen.vmaster_mute_enum = 1;
+ codec->power_filter = led_power_filter;
snd_printd("Detected mute LED for %x:%d\n", spec->mute_led_nid,
spec->mute_led_polarity);
break;
@@ -2778,6 +2922,7 @@
spec->mute_led_nid = 0x18;
spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
spec->gen.vmaster_mute_enum = 1;
+ codec->power_filter = led_power_filter;
}
}
@@ -2790,6 +2935,7 @@
spec->mute_led_nid = 0x19;
spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
spec->gen.vmaster_mute_enum = 1;
+ codec->power_filter = led_power_filter;
}
}
@@ -2948,6 +3094,7 @@
alc_write_coef_idx(codec, 0x18, 0x7388);
break;
case 0x10ec0668:
+ alc_write_coef_idx(codec, 0x11, 0x0001);
alc_write_coef_idx(codec, 0x15, 0x0d60);
alc_write_coef_idx(codec, 0xc3, 0x0000);
break;
@@ -2970,6 +3117,7 @@
alc_write_coef_idx(codec, 0x18, 0x7388);
break;
case 0x10ec0668:
+ alc_write_coef_idx(codec, 0x11, 0x0001);
alc_write_coef_idx(codec, 0x15, 0x0d50);
alc_write_coef_idx(codec, 0xc3, 0x0000);
break;
@@ -3030,8 +3178,10 @@
else
new_headset_mode = ALC_HEADSET_MODE_HEADPHONE;
- if (new_headset_mode == spec->current_headset_mode)
+ if (new_headset_mode == spec->current_headset_mode) {
+ snd_hda_gen_update_outputs(codec);
return;
+ }
switch (new_headset_mode) {
case ALC_HEADSET_MODE_UNPLUGGED:
@@ -3190,6 +3340,15 @@
}
}
+static void alc290_fixup_mono_speakers(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ /* Remove DAC node 0x03, as it seems to be
+ giving mono output */
+ snd_hda_override_wcaps(codec, 0x03, 0);
+}
+
enum {
ALC269_FIXUP_SONY_VAIO,
ALC275_FIXUP_SONY_VAIO_GPIO2,
@@ -3203,6 +3362,8 @@
ALC269_FIXUP_STEREO_DMIC,
ALC269_FIXUP_QUANTA_MUTE,
ALC269_FIXUP_LIFEBOOK,
+ ALC269_FIXUP_LIFEBOOK_EXTMIC,
+ ALC269_FIXUP_LIFEBOOK_HP_PIN,
ALC269_FIXUP_AMIC,
ALC269_FIXUP_DMIC,
ALC269VB_FIXUP_AMIC,
@@ -3213,9 +3374,12 @@
ALC269_FIXUP_HP_GPIO_LED,
ALC269_FIXUP_INV_DMIC,
ALC269_FIXUP_LENOVO_DOCK,
+ ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
+ ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+ ALC290_FIXUP_MONO_SPEAKERS,
ALC269_FIXUP_HEADSET_MODE,
ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
ALC269_FIXUP_ASUS_X101_FUNC,
@@ -3307,6 +3471,20 @@
.chained = true,
.chain_id = ALC269_FIXUP_QUANTA_MUTE
},
+ [ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+ { }
+ },
+ },
+ [ALC269_FIXUP_LIFEBOOK_HP_PIN] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x21, 0x0221102f }, /* HP out */
+ { }
+ },
+ },
[ALC269_FIXUP_AMIC] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
@@ -3402,6 +3580,15 @@
.chained = true,
.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
},
+ [ALC269_FIXUP_DELL3_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1a, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+ },
[ALC269_FIXUP_HEADSET_MODE] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc_fixup_headset_mode,
@@ -3410,6 +3597,13 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc_fixup_headset_mode_no_hp_mic,
},
+ [ALC286_FIXUP_SONY_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x18, 0x01a1913c }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ },
[ALC269_FIXUP_ASUS_X101_FUNC] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc269_fixup_x101_headset_mic,
@@ -3467,9 +3661,16 @@
.type = HDA_FIXUP_FUNC,
.v.func = alc269_fixup_limit_int_mic_boost,
},
+ [ALC290_FIXUP_MONO_SPEAKERS] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc290_fixup_mono_speakers,
+ .chained = true,
+ .chain_id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1025, 0x0283, "Acer TravelMate 8371", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x029b, "Acer 1810TZ", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x0349, "Acer AOD260", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1028, 0x05bd, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -3495,9 +3696,15 @@
SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05f8, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x05f9, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x05fb, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0606, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0608, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0609, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0613, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_MONO_SPEAKERS),
+ SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS),
SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
SND_PCI_QUIRK(0x103c, 0x18e6, "HP", ALC269_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -3516,6 +3723,8 @@
SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x8516, "ASUS X101CH", ALC269_FIXUP_ASUS_X101),
+ SND_PCI_QUIRK(0x104d, 0x90b5, "Sony VAIO Pro 11", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x104d, 0x90b6, "Sony VAIO Pro 13", ALC286_FIXUP_SONY_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x104d, 0x9073, "Sony VAIO", ALC275_FIXUP_SONY_VAIO_GPIO2),
SND_PCI_QUIRK(0x104d, 0x907b, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
SND_PCI_QUIRK(0x104d, 0x9084, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ),
@@ -3526,6 +3735,8 @@
SND_PCI_QUIRK(0x1025, 0x0742, "Acer AO756", ALC271_FIXUP_HP_GATE_MIC_JACK),
SND_PCI_QUIRK_VENDOR(0x1025, "Acer Aspire", ALC271_FIXUP_DMIC),
SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+ SND_PCI_QUIRK(0x10cf, 0x15dc, "Lifebook T731", ALC269_FIXUP_LIFEBOOK_HP_PIN),
+ SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
@@ -3626,27 +3837,30 @@
if ((alc_get_coef0(codec) & 0x00ff) == 0x017) {
val = alc_read_coef_idx(codec, 0x04);
/* Power up output pin */
- alc_write_coef_idx(codec, 0x04, val | (1<<11));
+ if (val != -1)
+ alc_write_coef_idx(codec, 0x04, val | (1<<11));
}
if ((alc_get_coef0(codec) & 0x00ff) == 0x018) {
val = alc_read_coef_idx(codec, 0xd);
- if ((val & 0x0c00) >> 10 != 0x1) {
+ if (val != -1 && (val & 0x0c00) >> 10 != 0x1) {
/* Capless ramp up clock control */
alc_write_coef_idx(codec, 0xd, val | (1<<10));
}
val = alc_read_coef_idx(codec, 0x17);
- if ((val & 0x01c0) >> 6 != 0x4) {
+ if (val != -1 && (val & 0x01c0) >> 6 != 0x4) {
/* Class D power on reset */
alc_write_coef_idx(codec, 0x17, val | (1<<7));
}
}
val = alc_read_coef_idx(codec, 0xd); /* Class D */
- alc_write_coef_idx(codec, 0xd, val | (1<<14));
+ if (val != -1)
+ alc_write_coef_idx(codec, 0xd, val | (1<<14));
val = alc_read_coef_idx(codec, 0x4); /* HP */
- alc_write_coef_idx(codec, 0x4, val | (1<<11));
+ if (val != -1)
+ alc_write_coef_idx(codec, 0x4, val | (1<<11));
}
/*
@@ -3714,8 +3928,12 @@
spec->codec_variant = ALC269_TYPE_ALC284;
break;
case 0x10ec0286:
+ case 0x10ec0288:
spec->codec_variant = ALC269_TYPE_ALC286;
break;
+ case 0x10ec0255:
+ spec->codec_variant = ALC269_TYPE_ALC255;
+ break;
}
/* automatic parse from the BIOS config */
@@ -3758,6 +3976,7 @@
ALC861_FIXUP_AMP_VREF_0F,
ALC861_FIXUP_NO_JACK_DETECT,
ALC861_FIXUP_ASUS_A6RP,
+ ALC660_FIXUP_ASUS_W7J,
};
/* On some laptops, VREF of pin 0x0f is abused for controlling the main amp */
@@ -3807,10 +4026,22 @@
.v.func = alc861_fixup_asus_amp_vref_0f,
.chained = true,
.chain_id = ALC861_FIXUP_NO_JACK_DETECT,
+ },
+ [ALC660_FIXUP_ASUS_W7J] = {
+ .type = HDA_FIXUP_VERBS,
+ .v.verbs = (const struct hda_verb[]) {
+ /* ASUS W7J needs a magic pin setup on unused NID 0x10
+ * for enabling outputs
+ */
+ {0x10, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x24},
+ { }
+ },
}
};
static const struct snd_pci_quirk alc861_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1043, 0x1253, "ASUS W7J", ALC660_FIXUP_ASUS_W7J),
+ SND_PCI_QUIRK(0x1043, 0x1263, "ASUS Z35HL", ALC660_FIXUP_ASUS_W7J),
SND_PCI_QUIRK(0x1043, 0x1393, "ASUS A6Rp", ALC861_FIXUP_ASUS_A6RP),
SND_PCI_QUIRK_VENDOR(0x1043, "ASUS laptop", ALC861_FIXUP_AMP_VREF_0F),
SND_PCI_QUIRK(0x1462, 0x7254, "HP DX2200", ALC861_FIXUP_NO_JACK_DETECT),
@@ -4194,13 +4425,17 @@
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
SND_PCI_QUIRK(0x1019, 0x9087, "ECS", ALC662_FIXUP_ASUS_MODE2),
+ SND_PCI_QUIRK(0x1025, 0x022f, "Acer Aspire One", ALC662_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x0308, "Acer Aspire 8942G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x1025, 0x031c, "Gateway NV79", ALC662_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x1025, 0x0349, "eMachines eM250", ALC662_FIXUP_INV_DMIC),
+ SND_PCI_QUIRK(0x1025, 0x034a, "Gateway LT27", ALC662_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE),
SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800),
+ SND_PCI_QUIRK(0x1043, 0x1477, "ASUS N56VZ", ALC662_FIXUP_ASUS_MODE4),
+ SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_ASUS_MODE4),
SND_PCI_QUIRK(0x1043, 0x8469, "ASUS mobo", ALC662_FIXUP_NO_JACK_DETECT),
SND_PCI_QUIRK(0x105b, 0x0cd6, "Foxconn", ALC662_FIXUP_ASUS_MODE2),
SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
@@ -4361,6 +4596,7 @@
case 0x10ec0272:
case 0x10ec0663:
case 0x10ec0665:
+ case 0x10ec0668:
set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
break;
case 0x10ec0273:
@@ -4418,7 +4654,9 @@
*/
static const struct hda_codec_preset snd_hda_preset_realtek[] = {
{ .id = 0x10ec0221, .name = "ALC221", .patch = patch_alc269 },
+ { .id = 0x10ec0231, .name = "ALC231", .patch = patch_alc269 },
{ .id = 0x10ec0233, .name = "ALC233", .patch = patch_alc269 },
+ { .id = 0x10ec0255, .name = "ALC255", .patch = patch_alc269 },
{ .id = 0x10ec0260, .name = "ALC260", .patch = patch_alc260 },
{ .id = 0x10ec0262, .name = "ALC262", .patch = patch_alc262 },
{ .id = 0x10ec0267, .name = "ALC267", .patch = patch_alc268 },
@@ -4433,6 +4671,7 @@
{ .id = 0x10ec0283, .name = "ALC283", .patch = patch_alc269 },
{ .id = 0x10ec0284, .name = "ALC284", .patch = patch_alc269 },
{ .id = 0x10ec0286, .name = "ALC286", .patch = patch_alc269 },
+ { .id = 0x10ec0288, .name = "ALC288", .patch = patch_alc269 },
{ .id = 0x10ec0290, .name = "ALC290", .patch = patch_alc269 },
{ .id = 0x10ec0292, .name = "ALC292", .patch = patch_alc269 },
{ .id = 0x10ec0861, .rev = 0x100340, .name = "ALC660",
@@ -4452,6 +4691,7 @@
{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+ { .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 1d9d642..44d3fb9 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -83,6 +83,9 @@
STAC_DELL_M6_BOTH,
STAC_DELL_EQ,
STAC_ALIENWARE_M17X,
+ STAC_92HD89XX_HP_FRONT_JACK,
+ STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
+ STAC_92HD73XX_ASUS_MOBO,
STAC_92HD73XX_MODELS
};
@@ -97,6 +100,7 @@
STAC_92HD83XXX_HP_LED,
STAC_92HD83XXX_HP_INV_LED,
STAC_92HD83XXX_HP_MIC_LED,
+ STAC_HP_LED_GPIO10,
STAC_92HD83XXX_HEADSET_JACK,
STAC_92HD83XXX_HP,
STAC_HP_ENVY_BASS,
@@ -417,9 +421,11 @@
val &= ~spec->eapd_mask;
else
val |= spec->eapd_mask;
- if (spec->gpio_data != val)
+ if (spec->gpio_data != val) {
+ spec->gpio_data = val;
stac_gpio_set(codec, spec->gpio_mask, spec->gpio_dir,
val);
+ }
}
}
@@ -534,8 +540,8 @@
if (snd_hda_jack_tbl_get(codec, nid))
continue;
if (def_conf == AC_JACK_PORT_COMPLEX &&
- !(spec->vref_mute_led_nid == nid ||
- is_jack_detectable(codec, nid))) {
+ spec->vref_mute_led_nid != nid &&
+ is_jack_detectable(codec, nid)) {
snd_hda_jack_detect_enable_callback(codec, nid,
STAC_PWR_EVENT,
jack_update_power);
@@ -568,9 +574,9 @@
spec->gpio_mask;
}
if (get_int_hint(codec, "gpio_dir", &spec->gpio_dir))
- spec->gpio_mask &= spec->gpio_mask;
- if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
spec->gpio_dir &= spec->gpio_mask;
+ if (get_int_hint(codec, "gpio_data", &spec->gpio_data))
+ spec->gpio_data &= spec->gpio_mask;
if (get_int_hint(codec, "eapd_mask", &spec->eapd_mask))
spec->eapd_mask &= spec->gpio_mask;
if (get_int_hint(codec, "gpio_mute", &spec->gpio_mute))
@@ -1773,6 +1779,17 @@
{}
};
+static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
+ { 0x0a, 0x02214030 },
+ { 0x0b, 0x02A19010 },
+ {}
+};
+
+static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = {
+ { 0x0e, 0x400000f0 },
+ {}
+};
+
static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -1891,7 +1908,26 @@
[STAC_92HD73XX_NO_JD] = {
.type = HDA_FIXUP_FUNC,
.v.func = stac92hd73xx_fixup_no_jd,
- }
+ },
+ [STAC_92HD89XX_HP_FRONT_JACK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = stac92hd89xx_hp_front_jack_pin_configs,
+ },
+ [STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
+ },
+ [STAC_92HD73XX_ASUS_MOBO] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ /* enable 5.1 and SPDIF out */
+ { 0x0c, 0x01014411 },
+ { 0x0d, 0x01014410 },
+ { 0x0e, 0x01014412 },
+ { 0x22, 0x014b1180 },
+ { }
+ }
+ },
};
static const struct hda_model_fixup stac92hd73xx_models[] = {
@@ -1903,6 +1939,7 @@
{ .id = STAC_DELL_M6_BOTH, .name = "dell-m6" },
{ .id = STAC_DELL_EQ, .name = "dell-eq" },
{ .id = STAC_ALIENWARE_M17X, .name = "alienware" },
+ { .id = STAC_92HD73XX_ASUS_MOBO, .name = "asus-mobo" },
{}
};
@@ -1951,6 +1988,12 @@
"Alienware M17x", STAC_ALIENWARE_M17X),
SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
"Alienware M17x R3", STAC_DELL_EQ),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927,
+ "HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
+ "unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_ASUSTEK, 0x83f8, "ASUS AT4NM10",
+ STAC_92HD73XX_ASUS_MOBO),
{} /* terminator */
};
@@ -2092,6 +2135,17 @@
spec->mic_mute_led_gpio = 0x08; /* GPIO3 */
}
+static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct sigmatel_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->gpio_led = 0x10; /* GPIO4 */
+ spec->default_polarity = 0;
+ }
+}
+
static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -2158,6 +2212,12 @@
.chained = true,
.chain_id = STAC_92HD83XXX_HP,
},
+ [STAC_HP_LED_GPIO10] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = stac92hd83xxx_fixup_hp_led_gpio10,
+ .chained = true,
+ .chain_id = STAC_92HD83XXX_HP,
+ },
[STAC_92HD83XXX_HEADSET_JACK] = {
.type = HDA_FIXUP_FUNC,
.v.func = stac92hd83xxx_fixup_headset_jack,
@@ -2229,6 +2289,8 @@
"HP", STAC_92HD83XXX_HP_cNB11_INTQUAD),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888,
"HP Envy Spectre", STAC_HP_ENVY_BASS),
+ SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899,
+ "HP Folio 13", STAC_HP_LED_GPIO10),
SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df,
"HP Folio", STAC_92HD83XXX_HP_MIC_LED),
SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_HP, 0xff00, 0x1900,
@@ -2813,6 +2875,7 @@
/* codec SSIDs for Intel Mac sharing the same PCI SSID 8384:7680 */
static const struct snd_pci_quirk stac922x_intel_mac_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x0000, 0x0100, "Mac Mini", STAC_INTEL_MAC_V3),
SND_PCI_QUIRK(0x106b, 0x0800, "Mac", STAC_INTEL_MAC_V1),
SND_PCI_QUIRK(0x106b, 0x0600, "Mac", STAC_INTEL_MAC_V2),
SND_PCI_QUIRK(0x106b, 0x0700, "Mac", STAC_INTEL_MAC_V2),
@@ -3227,7 +3290,7 @@
/* configure the analog microphone on some laptops */
{ 0x0c, 0x90a79130 },
/* correct the front output jack as a hp out */
- { 0x0f, 0x0227011f },
+ { 0x0f, 0x0221101f },
/* correct the front input jack as a mic */
{ 0x0e, 0x02a79130 },
{}
@@ -3599,29 +3662,34 @@
return err;
}
- stac_init_power_map(codec);
-
return 0;
}
+static int stac_build_controls(struct hda_codec *codec)
+{
+ int err = snd_hda_gen_build_controls(codec);
+
+ if (err < 0)
+ return err;
+ stac_init_power_map(codec);
+ return 0;
+}
static int stac_init(struct hda_codec *codec)
{
struct sigmatel_spec *spec = codec->spec;
- unsigned int gpio;
int i;
/* override some hints */
stac_store_hints(codec);
/* set up GPIO */
- gpio = spec->gpio_data;
/* turn on EAPD statically when spec->eapd_switch isn't set.
* otherwise, unsol event will turn it on/off dynamically
*/
if (!spec->eapd_switch)
- gpio |= spec->eapd_mask;
- stac_gpio_set(codec, spec->gpio_mask, spec->gpio_dir, gpio);
+ spec->gpio_data |= spec->eapd_mask;
+ stac_gpio_set(codec, spec->gpio_mask, spec->gpio_dir, spec->gpio_data);
snd_hda_gen_init(codec);
@@ -3748,7 +3816,7 @@
#endif /* CONFIG_PM */
static const struct hda_codec_ops stac_patch_ops = {
- .build_controls = snd_hda_gen_build_controls,
+ .build_controls = stac_build_controls,
.build_pcms = snd_hda_gen_build_pcms,
.init = stac_init,
.free = stac_free,
@@ -3921,6 +3989,7 @@
{
struct sigmatel_spec *spec = codec->spec;
+ spec->gpio_mask |= spec->eapd_mask;
if (spec->gpio_led) {
if (!spec->vref_mute_led_nid) {
spec->gpio_mask |= spec->gpio_led;
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index e524554..aed19c3 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -910,6 +910,8 @@
static void override_mic_boost(struct hda_codec *codec, hda_nid_t pin,
int offset, int num_steps, int step_size)
{
+ snd_hda_override_wcaps(codec, pin,
+ get_wcaps(codec, pin) | AC_WCAP_IN_AMP);
snd_hda_override_amp_caps(codec, pin, HDA_INPUT,
(offset << AC_AMPCAP_OFFSET_SHIFT) |
(num_steps << AC_AMPCAP_NUM_STEPS_SHIFT) |
diff --git a/sound/pci/ice1712/ice1712.c b/sound/pci/ice1712/ice1712.c
index 806407a..e6b70e3 100644
--- a/sound/pci/ice1712/ice1712.c
+++ b/sound/pci/ice1712/ice1712.c
@@ -685,9 +685,10 @@
if (!(snd_ice1712_read(ice, ICE1712_IREG_PBK_CTRL) & 1))
return 0;
ptr = runtime->buffer_size - inw(ice->ddma_port + 4);
+ ptr = bytes_to_frames(substream->runtime, ptr);
if (ptr == runtime->buffer_size)
ptr = 0;
- return bytes_to_frames(substream->runtime, ptr);
+ return ptr;
}
static snd_pcm_uframes_t snd_ice1712_playback_ds_pointer(struct snd_pcm_substream *substream)
@@ -704,9 +705,10 @@
addr = ICE1712_DSC_ADDR0;
ptr = snd_ice1712_ds_read(ice, substream->number * 2, addr) -
ice->playback_con_virt_addr[substream->number];
+ ptr = bytes_to_frames(substream->runtime, ptr);
if (ptr == substream->runtime->buffer_size)
ptr = 0;
- return bytes_to_frames(substream->runtime, ptr);
+ return ptr;
}
static snd_pcm_uframes_t snd_ice1712_capture_pointer(struct snd_pcm_substream *substream)
@@ -717,9 +719,10 @@
if (!(snd_ice1712_read(ice, ICE1712_IREG_CAP_CTRL) & 1))
return 0;
ptr = inl(ICEREG(ice, CONCAP_ADDR)) - ice->capture_con_virt_addr;
+ ptr = bytes_to_frames(substream->runtime, ptr);
if (ptr == substream->runtime->buffer_size)
ptr = 0;
- return bytes_to_frames(substream->runtime, ptr);
+ return ptr;
}
static const struct snd_pcm_hardware snd_ice1712_playback = {
@@ -1113,9 +1116,10 @@
if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_PLAYBACK_START))
return 0;
ptr = ice->playback_pro_size - (inw(ICEMT(ice, PLAYBACK_SIZE)) << 2);
+ ptr = bytes_to_frames(substream->runtime, ptr);
if (ptr == substream->runtime->buffer_size)
ptr = 0;
- return bytes_to_frames(substream->runtime, ptr);
+ return ptr;
}
static snd_pcm_uframes_t snd_ice1712_capture_pro_pointer(struct snd_pcm_substream *substream)
@@ -1126,9 +1130,10 @@
if (!(inl(ICEMT(ice, PLAYBACK_CONTROL)) & ICE1712_CAPTURE_START_SHADOW))
return 0;
ptr = ice->capture_pro_size - (inw(ICEMT(ice, CAPTURE_SIZE)) << 2);
+ ptr = bytes_to_frames(substream->runtime, ptr);
if (ptr == substream->runtime->buffer_size)
ptr = 0;
- return bytes_to_frames(substream->runtime, ptr);
+ return ptr;
}
static const struct snd_pcm_hardware snd_ice1712_playback_pro = {
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 64b9fda..dbbbacf 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -53,6 +53,7 @@
{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
+ { OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
{ }
};
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index 77acd79..eb7ad77 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -294,6 +294,16 @@
oxygen_write16_masked(chip, OXYGEN_GPIO_DATA,
data->output_sel == 1 ? GPIO_HP_REAR : 0,
GPIO_HP_REAR);
+ oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING,
+ data->output_sel == 0 ?
+ OXYGEN_PLAY_MUTE01 :
+ OXYGEN_PLAY_MUTE23 |
+ OXYGEN_PLAY_MUTE45 |
+ OXYGEN_PLAY_MUTE67,
+ OXYGEN_PLAY_MUTE01 |
+ OXYGEN_PLAY_MUTE23 |
+ OXYGEN_PLAY_MUTE45 |
+ OXYGEN_PLAY_MUTE67);
}
mutex_unlock(&chip->mutex);
return changed;
@@ -596,7 +606,7 @@
.model_data_size = sizeof(struct dg),
.device_config = PLAYBACK_0_TO_I2S |
PLAYBACK_1_TO_SPDIF |
- CAPTURE_0_FROM_I2S_2 |
+ CAPTURE_0_FROM_I2S_1 |
CAPTURE_1_FROM_SPDIF,
.dac_channels_pcm = 6,
.dac_channels_mixer = 0,
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index c8c7f2c..e026059 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -100,8 +100,8 @@
*/
/*
- * Xonar Essence ST (Deluxe)/STX
- * -----------------------------
+ * Xonar Essence ST (Deluxe)/STX (II)
+ * ----------------------------------
*
* CMI8788:
*
@@ -1138,6 +1138,14 @@
chip->model.resume = xonar_stx_resume;
chip->model.set_dac_params = set_pcm1796_params;
break;
+ case 0x85f4:
+ chip->model = model_xonar_st;
+ /* TODO: daughterboard support */
+ chip->model.shortname = "Xonar STX II";
+ chip->model.init = xonar_stx_init;
+ chip->model.resume = xonar_stx_resume;
+ chip->model.set_dac_params = set_pcm1796_params;
+ break;
default:
return -EINVAL;
}
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 63c1c80..fa66ba3 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -2032,32 +2032,43 @@
{
static int dev;
struct gameport *gameport;
+ int ret;
if (dev >= SNDRV_CARDS)
return -ENODEV;
+
if (!enable[dev]) {
- dev++;
- return -ENOENT;
+ ret = -ENOENT;
+ goto inc_dev;
}
- if (!joystick_port[dev++])
- return 0;
+ if (!joystick_port[dev]) {
+ ret = 0;
+ goto inc_dev;
+ }
gameport = gameport_allocate_port();
- if (!gameport)
- return -ENOMEM;
+ if (!gameport) {
+ ret = -ENOMEM;
+ goto inc_dev;
+ }
if (!request_region(joystick_port[dev], 8, "Riptide gameport")) {
snd_printk(KERN_WARNING
"Riptide: cannot grab gameport 0x%x\n",
joystick_port[dev]);
gameport_free_port(gameport);
- return -EBUSY;
+ ret = -EBUSY;
+ goto inc_dev;
}
gameport->io = joystick_port[dev];
gameport_register_port(gameport);
pci_set_drvdata(pci, gameport);
- return 0;
+
+ ret = 0;
+inc_dev:
+ dev++;
+ return ret;
}
static void snd_riptide_joystick_remove(struct pci_dev *pci)
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 9ea05e9..dd910d2 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -5789,6 +5789,9 @@
snd_pcm_hw_constraint_minmax(runtime,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
64, 8192);
+ snd_pcm_hw_constraint_minmax(runtime,
+ SNDRV_PCM_HW_PARAM_PERIODS,
+ 2, 2);
break;
}
@@ -5863,6 +5866,9 @@
snd_pcm_hw_constraint_minmax(runtime,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
64, 8192);
+ snd_pcm_hw_constraint_minmax(runtime,
+ SNDRV_PCM_HW_PARAM_PERIODS,
+ 2, 2);
break;
}
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 773a67f..431bf68 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -285,7 +285,7 @@
/* ADAT channels are remapped */
1, 3, 5, 7, 9, 11, 13, 15,
/* channels 8 and 9 are S/PDIF */
- 24, 25
+ 24, 25,
/* others don't exist */
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
diff --git a/sound/soc/atmel/atmel-pcm-dma.c b/sound/soc/atmel/atmel-pcm-dma.c
index 1d38fd0..d128265 100644
--- a/sound/soc/atmel/atmel-pcm-dma.c
+++ b/sound/soc/atmel/atmel-pcm-dma.c
@@ -81,7 +81,9 @@
/* stop RX and capture: will be enabled again at restart */
ssc_writex(prtd->ssc->regs, SSC_CR, prtd->mask->ssc_disable);
+ snd_pcm_stream_lock(substream);
snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(substream);
/* now drain RHR and read status to remove xrun condition */
ssc_readx(prtd->ssc->regs, SSC_RHR);
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index f3fdfa0..c5f7959 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -331,7 +331,6 @@
struct atmel_pcm_dma_params *dma_params;
int dir, channels, bits;
u32 tfmr, rfmr, tcmr, rcmr;
- int start_event;
int ret;
/*
@@ -450,19 +449,10 @@
* The SSC transmit clock is obtained from the BCLK signal on
* on the TK line, and the SSC receive clock is
* generated from the transmit clock.
- *
- * For single channel data, one sample is transferred
- * on the falling edge of the LRC clock.
- * For two channel data, one sample is
- * transferred on both edges of the LRC clock.
*/
- start_event = ((channels == 1)
- ? SSC_START_FALLING_RF
- : SSC_START_EDGE_RF);
-
rcmr = SSC_BF(RCMR_PERIOD, 0)
| SSC_BF(RCMR_STTDLY, START_DELAY)
- | SSC_BF(RCMR_START, start_event)
+ | SSC_BF(RCMR_START, SSC_START_FALLING_RF)
| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
| SSC_BF(RCMR_CKS, SSC_CKS_CLOCK);
@@ -470,14 +460,14 @@
rfmr = SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
| SSC_BF(RFMR_FSLEN, 0)
- | SSC_BF(RFMR_DATNB, 0)
+ | SSC_BF(RFMR_DATNB, (channels - 1))
| SSC_BIT(RFMR_MSBF)
| SSC_BF(RFMR_LOOP, 0)
| SSC_BF(RFMR_DATLEN, (bits - 1));
tcmr = SSC_BF(TCMR_PERIOD, 0)
| SSC_BF(TCMR_STTDLY, START_DELAY)
- | SSC_BF(TCMR_START, start_event)
+ | SSC_BF(TCMR_START, SSC_START_FALLING_RF)
| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
| SSC_BF(TCMR_CKS, SSC_CKS_PIN);
@@ -486,7 +476,7 @@
| SSC_BF(TFMR_FSDEN, 0)
| SSC_BF(TFMR_FSOS, SSC_FSOS_NONE)
| SSC_BF(TFMR_FSLEN, 0)
- | SSC_BF(TFMR_DATNB, 0)
+ | SSC_BF(TFMR_DATNB, (channels - 1))
| SSC_BIT(TFMR_MSBF)
| SSC_BF(TFMR_DATDEF, 0)
| SSC_BF(TFMR_DATLEN, (bits - 1));
diff --git a/sound/soc/blackfin/bf5xx-i2s.c b/sound/soc/blackfin/bf5xx-i2s.c
index dd0c2a4..e0869aa 100644
--- a/sound/soc/blackfin/bf5xx-i2s.c
+++ b/sound/soc/blackfin/bf5xx-i2s.c
@@ -111,6 +111,7 @@
bf5xx_i2s->tcr2 |= 7;
bf5xx_i2s->rcr2 |= 7;
sport_handle->wdsize = 1;
+ break;
case SNDRV_PCM_FORMAT_S16_LE:
bf5xx_i2s->tcr2 |= 15;
bf5xx_i2s->rcr2 |= 15;
diff --git a/sound/soc/codecs/88pm860x-codec.c b/sound/soc/codecs/88pm860x-codec.c
index 60159c0..6fd174b 100644
--- a/sound/soc/codecs/88pm860x-codec.c
+++ b/sound/soc/codecs/88pm860x-codec.c
@@ -351,6 +351,9 @@
val = ucontrol->value.integer.value[0];
val2 = ucontrol->value.integer.value[1];
+ if (val >= ARRAY_SIZE(st_table) || val2 >= ARRAY_SIZE(st_table))
+ return -EINVAL;
+
err = snd_soc_update_bits(codec, reg, 0x3f, st_table[val].m);
if (err < 0)
return err;
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index a153b16..bce45c1 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -1225,13 +1225,18 @@
struct ab8500_codec_drvdata *drvdata = dev_get_drvdata(codec->dev);
struct device *dev = codec->dev;
bool apply_fir, apply_iir;
- int req, status;
+ unsigned int req;
+ int status;
dev_dbg(dev, "%s: Enter.\n", __func__);
mutex_lock(&drvdata->anc_lock);
req = ucontrol->value.integer.value[0];
+ if (req >= ARRAY_SIZE(enum_anc_state)) {
+ status = -EINVAL;
+ goto cleanup;
+ }
if (req != ANC_APPLY_FIR_IIR && req != ANC_APPLY_FIR &&
req != ANC_APPLY_IIR) {
dev_err(dev, "%s: ERROR: Unsupported status to set '%s'!\n",
diff --git a/sound/soc/codecs/adau1701.c b/sound/soc/codecs/adau1701.c
index dafdbe8..0c499c6 100644
--- a/sound/soc/codecs/adau1701.c
+++ b/sound/soc/codecs/adau1701.c
@@ -64,7 +64,7 @@
#define ADAU1701_SEROCTL_WORD_LEN_24 0x0000
#define ADAU1701_SEROCTL_WORD_LEN_20 0x0001
-#define ADAU1701_SEROCTL_WORD_LEN_16 0x0010
+#define ADAU1701_SEROCTL_WORD_LEN_16 0x0002
#define ADAU1701_SEROCTL_WORD_LEN_MASK 0x0003
#define ADAU1701_AUXNPOW_VBPD 0x40
diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index 3c839cc..0ef2b2a 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -307,7 +307,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
- unsigned int deemph = ucontrol->value.enumerated.item[0];
+ unsigned int deemph = ucontrol->value.integer.value[0];
if (deemph > 1)
return -EINVAL;
@@ -323,7 +323,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct adav80x *adav80x = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = adav80x->deemph;
+ ucontrol->value.integer.value[0] = adav80x->deemph;
return 0;
};
diff --git a/sound/soc/codecs/ak4641.c b/sound/soc/codecs/ak4641.c
index 5f9af1f..68379c1 100644
--- a/sound/soc/codecs/ak4641.c
+++ b/sound/soc/codecs/ak4641.c
@@ -74,7 +74,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
if (deemph > 1)
return -EINVAL;
@@ -90,7 +90,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct ak4641_priv *ak4641 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = ak4641->deemph;
+ ucontrol->value.integer.value[0] = ak4641->deemph;
return 0;
};
diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 2d03787..687565d 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -257,7 +257,7 @@
* This operation came from example code of
* "ASAHI KASEI AK4642" (japanese) manual p94.
*/
- snd_soc_write(codec, SG_SL1, PMMP | MGAIN0);
+ snd_soc_update_bits(codec, SG_SL1, PMMP | MGAIN0, PMMP | MGAIN0);
snd_soc_write(codec, TIMER, ZTM(0x3) | WTM(0x3));
snd_soc_write(codec, ALC_CTL1, ALC | LMTH0);
snd_soc_update_bits(codec, PW_MGMT1, PMADL, PMADL);
diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c
index 389f232..663a2a7 100644
--- a/sound/soc/codecs/arizona.c
+++ b/sound/soc/codecs/arizona.c
@@ -1455,6 +1455,8 @@
try_wait_for_completion(&fll->ok);
regmap_update_bits(arizona->regmap, fll->base + 1,
+ ARIZONA_FLL1_FREERUN, 0);
+ regmap_update_bits(arizona->regmap, fll->base + 1,
ARIZONA_FLL1_ENA, ARIZONA_FLL1_ENA);
if (fll->ref_src >= 0 && fll->sync_src >= 0 &&
fll->ref_src != fll->sync_src)
@@ -1473,6 +1475,8 @@
struct arizona *arizona = fll->arizona;
bool change;
+ regmap_update_bits(arizona->regmap, fll->base + 1,
+ ARIZONA_FLL1_FREERUN, ARIZONA_FLL1_FREERUN);
regmap_update_bits_check(arizona->regmap, fll->base + 1,
ARIZONA_FLL1_ENA, 0, &change);
regmap_update_bits(arizona->regmap, fll->base + 0x11,
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 03036b3..ffa4a2d 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -267,7 +267,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = cs4271->deemph;
+ ucontrol->value.integer.value[0] = cs4271->deemph;
return 0;
}
@@ -277,7 +277,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct cs4271_private *cs4271 = snd_soc_codec_get_drvdata(codec);
- cs4271->deemph = ucontrol->value.enumerated.item[0];
+ cs4271->deemph = ucontrol->value.integer.value[0];
return cs4271_set_deemph(codec);
}
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 1e0fa3b..e1dfebb 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -124,9 +124,8 @@
static const DECLARE_TLV_DB_SCALE(adc_pcm_tlv, -5150, 50, 0);
static const DECLARE_TLV_DB_SCALE(tone_tlv, -1050, 150, 0);
-/* This is a lie. after -102 db, it stays at -102 */
-/* maybe a range would be better */
-static const DECLARE_TLV_DB_SCALE(aout_tlv, -11550, 50, 0);
+
+static const DECLARE_TLV_DB_SCALE(aout_tlv, -10200, 50, 0);
static const DECLARE_TLV_DB_SCALE(boost_tlv, 1600, 1600, 0);
static const char *chan_mix[] = {
@@ -141,7 +140,7 @@
static const struct snd_kcontrol_new cs42l51_snd_controls[] = {
SOC_DOUBLE_R_SX_TLV("PCM Playback Volume",
CS42L51_PCMA_VOL, CS42L51_PCMB_VOL,
- 6, 0x19, 0x7F, adc_pcm_tlv),
+ 0, 0x19, 0x7F, adc_pcm_tlv),
SOC_DOUBLE_R("PCM Playback Switch",
CS42L51_PCMA_VOL, CS42L51_PCMB_VOL, 7, 1, 1),
SOC_DOUBLE_R_SX_TLV("Analog Playback Volume",
@@ -149,7 +148,7 @@
0, 0x34, 0xE4, aout_tlv),
SOC_DOUBLE_R_SX_TLV("ADC Mixer Volume",
CS42L51_ADCA_VOL, CS42L51_ADCB_VOL,
- 6, 0x19, 0x7F, adc_pcm_tlv),
+ 0, 0x19, 0x7F, adc_pcm_tlv),
SOC_DOUBLE_R("ADC Mixer Switch",
CS42L51_ADCA_VOL, CS42L51_ADCB_VOL, 7, 1, 1),
SOC_SINGLE("Playback Deemphasis Switch", CS42L51_DAC_CTL, 3, 1, 0),
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index 987f728..b99af63 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -350,7 +350,7 @@
static const unsigned int swap_values[] = { 0, 1, 3 };
static const struct soc_enum adca_swap_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 1,
+ SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 2, 3,
ARRAY_SIZE(left_swap_text),
left_swap_text,
swap_values);
@@ -359,7 +359,7 @@
SOC_DAPM_ENUM("Route", adca_swap_enum);
static const struct soc_enum pcma_swap_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 1,
+ SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 6, 3,
ARRAY_SIZE(left_swap_text),
left_swap_text,
swap_values);
@@ -368,7 +368,7 @@
SOC_DAPM_ENUM("Route", pcma_swap_enum);
static const struct soc_enum adcb_swap_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 1,
+ SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 0, 3,
ARRAY_SIZE(right_swap_text),
right_swap_text,
swap_values);
@@ -377,7 +377,7 @@
SOC_DAPM_ENUM("Route", adcb_swap_enum);
static const struct soc_enum pcmb_swap_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 1,
+ SOC_VALUE_ENUM_SINGLE(CS42L52_ADC_PCM_MIXER, 4, 3,
ARRAY_SIZE(right_swap_text),
right_swap_text,
swap_values);
@@ -451,7 +451,7 @@
SOC_ENUM("Beep Pitch", beep_pitch_enum),
SOC_ENUM("Beep on Time", beep_ontime_enum),
SOC_ENUM("Beep off Time", beep_offtime_enum),
- SOC_SINGLE_TLV("Beep Volume", CS42L52_BEEP_VOL, 0, 0x1f, 0x07, hl_tlv),
+ SOC_SINGLE_SX_TLV("Beep Volume", CS42L52_BEEP_VOL, 0, 0x07, 0x1f, hl_tlv),
SOC_SINGLE("Beep Mixer Switch", CS42L52_BEEP_TONE_CTL, 5, 1, 1),
SOC_ENUM("Beep Treble Corner Freq", beep_treble_enum),
SOC_ENUM("Beep Bass Corner Freq", beep_bass_enum),
diff --git a/sound/soc/codecs/cs42l52.h b/sound/soc/codecs/cs42l52.h
index 4277012..a935d73 100644
--- a/sound/soc/codecs/cs42l52.h
+++ b/sound/soc/codecs/cs42l52.h
@@ -179,7 +179,7 @@
#define CS42L52_MICB_CTL 0x11
#define CS42L52_MIC_CTL_MIC_SEL_MASK 0xBF
#define CS42L52_MIC_CTL_MIC_SEL_SHIFT 6
-#define CS42L52_MIC_CTL_TYPE_MASK 0xDF
+#define CS42L52_MIC_CTL_TYPE_MASK 0x20
#define CS42L52_MIC_CTL_TYPE_SHIFT 5
diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c
index 3b20c86..eade6e2 100644
--- a/sound/soc/codecs/cs42l73.c
+++ b/sound/soc/codecs/cs42l73.c
@@ -325,7 +325,7 @@
static const unsigned int cs42l73_mono_mix_values[] = { 0, 1, 2 };
static const struct soc_enum spk_asp_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 1,
+ SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 6, 3,
ARRAY_SIZE(cs42l73_mono_mix_texts),
cs42l73_mono_mix_texts,
cs42l73_mono_mix_values);
@@ -343,7 +343,7 @@
SOC_DAPM_ENUM("Route", spk_xsp_enum);
static const struct soc_enum esl_asp_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 5,
+ SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 2, 3,
ARRAY_SIZE(cs42l73_mono_mix_texts),
cs42l73_mono_mix_texts,
cs42l73_mono_mix_values);
@@ -352,7 +352,7 @@
SOC_DAPM_ENUM("Route", esl_asp_enum);
static const struct soc_enum esl_xsp_enum =
- SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 7,
+ SOC_VALUE_ENUM_SINGLE(CS42L73_MMIXCTL, 0, 3,
ARRAY_SIZE(cs42l73_mono_mix_texts),
cs42l73_mono_mix_texts,
cs42l73_mono_mix_values);
diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c
index dc0284d..76fdf0a 100644
--- a/sound/soc/codecs/da732x.c
+++ b/sound/soc/codecs/da732x.c
@@ -1268,11 +1268,23 @@
},
};
+static bool da732x_volatile(struct device *dev, unsigned int reg)
+{
+ switch (reg) {
+ case DA732X_REG_HPL_DAC_OFF_CNTL:
+ case DA732X_REG_HPR_DAC_OFF_CNTL:
+ return true;
+ default:
+ return false;
+ }
+}
+
static const struct regmap_config da732x_regmap = {
.reg_bits = 8,
.val_bits = 8,
.max_register = DA732X_MAX_REG,
+ .volatile_reg = da732x_volatile,
.reg_defaults = da732x_reg_cache,
.num_reg_defaults = ARRAY_SIZE(da732x_reg_cache),
.cache_type = REGCACHE_RBTREE,
diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c
index 3eeada5..566a367 100644
--- a/sound/soc/codecs/max98088.c
+++ b/sound/soc/codecs/max98088.c
@@ -1612,7 +1612,7 @@
static void max98088_sync_cache(struct snd_soc_codec *codec)
{
- u16 *reg_cache = codec->reg_cache;
+ u8 *reg_cache = codec->reg_cache;
int i;
if (!codec->cache_sync)
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
index 8d14a76..be8de7c 100644
--- a/sound/soc/codecs/max98090.c
+++ b/sound/soc/codecs/max98090.c
@@ -255,6 +255,7 @@
static bool max98090_volatile_register(struct device *dev, unsigned int reg)
{
switch (reg) {
+ case M98090_REG_SOFTWARE_RESET:
case M98090_REG_DEVICE_STATUS:
case M98090_REG_JACK_STATUS:
case M98090_REG_REVISION_ID:
@@ -336,6 +337,7 @@
case M98090_REG_RECORD_TDM_SLOT:
case M98090_REG_SAMPLE_RATE:
case M98090_REG_DMIC34_BIQUAD_BASE ... M98090_REG_DMIC34_BIQUAD_BASE + 0x0E:
+ case M98090_REG_REVISION_ID:
return true;
default:
return false;
@@ -1362,8 +1364,8 @@
{"STENL Mux", "Sidetone Left", "DMICL"},
{"STENR Mux", "Sidetone Right", "ADCR"},
{"STENR Mux", "Sidetone Right", "DMICR"},
- {"DACL", "NULL", "STENL Mux"},
- {"DACR", "NULL", "STENL Mux"},
+ {"DACL", NULL, "STENL Mux"},
+ {"DACR", NULL, "STENL Mux"},
{"AIFINL", NULL, "SHDN"},
{"AIFINR", NULL, "SHDN"},
@@ -1755,16 +1757,6 @@
switch (level) {
case SND_SOC_BIAS_ON:
- if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
- ret = regcache_sync(max98090->regmap);
-
- if (ret != 0) {
- dev_err(codec->dev,
- "Failed to sync cache: %d\n", ret);
- return ret;
- }
- }
-
if (max98090->jack_state == M98090_JACK_STATE_HEADSET) {
/*
* Set to normal bias level.
@@ -1778,6 +1770,16 @@
break;
case SND_SOC_BIAS_STANDBY:
+ if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) {
+ ret = regcache_sync(max98090->regmap);
+ if (ret != 0) {
+ dev_err(codec->dev,
+ "Failed to sync cache: %d\n", ret);
+ return ret;
+ }
+ }
+ break;
+
case SND_SOC_BIAS_OFF:
/* Set internal pull-up to lowest power mode */
snd_soc_update_bits(codec, M98090_REG_JACK_DETECT,
@@ -2232,7 +2234,7 @@
/* Register for interrupts */
dev_dbg(codec->dev, "irq = %d\n", max98090->irq);
- ret = request_threaded_irq(max98090->irq, NULL,
+ ret = devm_request_threaded_irq(codec->dev, max98090->irq, NULL,
max98090_interrupt, IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"max98090_interrupt", codec);
if (ret < 0) {
@@ -2342,6 +2344,8 @@
regcache_cache_only(max98090->regmap, false);
+ max98090_reset(max98090);
+
regcache_sync(max98090->regmap);
return 0;
diff --git a/sound/soc/codecs/max98095.c b/sound/soc/codecs/max98095.c
index 41cdd16..8dbcacd 100644
--- a/sound/soc/codecs/max98095.c
+++ b/sound/soc/codecs/max98095.c
@@ -1863,7 +1863,7 @@
struct max98095_pdata *pdata = max98095->pdata;
int channel = max98095_get_eq_channel(kcontrol->id.name);
struct max98095_cdata *cdata;
- int sel = ucontrol->value.integer.value[0];
+ unsigned int sel = ucontrol->value.integer.value[0];
struct max98095_eq_cfg *coef_set;
int fs, best, best_val, i;
int regmask, regsave;
@@ -2016,7 +2016,7 @@
struct max98095_pdata *pdata = max98095->pdata;
int channel = max98095_get_bq_channel(codec, kcontrol->id.name);
struct max98095_cdata *cdata;
- int sel = ucontrol->value.integer.value[0];
+ unsigned int sel = ucontrol->value.integer.value[0];
struct max98095_biquad_cfg *coef_set;
int fs, best, best_val, i;
int regmask, regsave;
diff --git a/sound/soc/codecs/mc13783.c b/sound/soc/codecs/mc13783.c
index 5402dfb..8a8d936 100644
--- a/sound/soc/codecs/mc13783.c
+++ b/sound/soc/codecs/mc13783.c
@@ -126,6 +126,10 @@
ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
+ /* include errata fix for spi audio problems */
+ if (reg == MC13783_AUDIO_CODEC || reg == MC13783_AUDIO_DAC)
+ ret = mc13xxx_reg_write(priv->mc13xxx, reg, value);
+
mc13xxx_unlock(priv->mc13xxx);
return ret;
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 92bbfec..665e0dd 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -37,7 +37,7 @@
static const u16 sgtl5000_regs[SGTL5000_MAX_REG_OFFSET] = {
[SGTL5000_CHIP_CLK_CTRL] = 0x0008,
[SGTL5000_CHIP_I2S_CTRL] = 0x0010,
- [SGTL5000_CHIP_SSS_CTRL] = 0x0008,
+ [SGTL5000_CHIP_SSS_CTRL] = 0x0010,
[SGTL5000_CHIP_DAC_VOL] = 0x3c3c,
[SGTL5000_CHIP_PAD_STRENGTH] = 0x015f,
[SGTL5000_CHIP_ANA_HP_CTRL] = 0x1818,
@@ -1111,13 +1111,7 @@
/* Enable VDDC charge pump */
ana_pwr |= SGTL5000_VDDC_CHRGPMP_POWERUP;
} else if (vddio >= 3100 && vdda >= 3100) {
- /*
- * if vddio and vddd > 3.1v,
- * charge pump should be clean before set ana_pwr
- */
- snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER,
- SGTL5000_VDDC_CHRGPMP_POWERUP, 0);
-
+ ana_pwr &= ~SGTL5000_VDDC_CHRGPMP_POWERUP;
/* VDDC use VDDIO rail */
lreg_ctrl |= SGTL5000_VDDC_ASSN_OVRD;
lreg_ctrl |= SGTL5000_VDDC_MAN_ASSN_VDDIO <<
@@ -1242,6 +1236,9 @@
/* wait for all power rails bring up */
udelay(10);
+ /* Need 8 clocks before I2C accesses */
+ udelay(1);
+
/* read chip information */
reg = snd_soc_read(codec, SGTL5000_CHIP_ID);
if (((reg & SGTL5000_PARTID_MASK) >> SGTL5000_PARTID_SHIFT) !=
@@ -1317,8 +1314,7 @@
/* enable small pop, introduce 400ms delay in turning off */
snd_soc_update_bits(codec, SGTL5000_CHIP_REF_CTRL,
- SGTL5000_SMALL_POP,
- SGTL5000_SMALL_POP);
+ SGTL5000_SMALL_POP, 1);
/* disable short cut detector */
snd_soc_write(codec, SGTL5000_CHIP_SHORT_CTRL, 0);
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index 8a9f435..0bd6e1c 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -275,7 +275,7 @@
#define SGTL5000_BIAS_CTRL_MASK 0x000e
#define SGTL5000_BIAS_CTRL_SHIFT 1
#define SGTL5000_BIAS_CTRL_WIDTH 3
-#define SGTL5000_SMALL_POP 0x0001
+#define SGTL5000_SMALL_POP 0
/*
* SGTL5000_CHIP_MIC_CTRL
@@ -347,7 +347,7 @@
#define SGTL5000_PLL_INT_DIV_MASK 0xf800
#define SGTL5000_PLL_INT_DIV_SHIFT 11
#define SGTL5000_PLL_INT_DIV_WIDTH 5
-#define SGTL5000_PLL_FRAC_DIV_MASK 0x0700
+#define SGTL5000_PLL_FRAC_DIV_MASK 0x07ff
#define SGTL5000_PLL_FRAC_DIV_SHIFT 0
#define SGTL5000_PLL_FRAC_DIV_WIDTH 11
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index 4068f24..bb3878c 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -176,6 +176,13 @@
goto done;
}
+ if (ssfw_head->version != 1) {
+ dev_err(dev,
+ "Failed to load firmware: Invalid version %d. Supported firmware versions: 1\n",
+ ssfw_head->version);
+ goto done;
+ }
+
crc = crc32(0, fw->data + sizeof(*ssfw_head),
fw->size - sizeof(*ssfw_head));
pr_debug("%s: crc=%x\n", __func__, crc);
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index cfb55fe..8517e70 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -187,42 +187,42 @@
13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0),
};
-static const struct soc_enum sta32x_drc_ac_enum =
- SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
- 2, sta32x_drc_ac);
-static const struct soc_enum sta32x_auto_eq_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
- 3, sta32x_auto_eq_mode);
-static const struct soc_enum sta32x_auto_gc_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
- 4, sta32x_auto_gc_mode);
-static const struct soc_enum sta32x_auto_xo_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
- 16, sta32x_auto_xo_mode);
-static const struct soc_enum sta32x_preset_eq_enum =
- SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
- 32, sta32x_preset_eq_mode);
-static const struct soc_enum sta32x_limiter_ch1_enum =
- SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch2_enum =
- SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter_ch3_enum =
- SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
- 3, sta32x_limiter_select);
-static const struct soc_enum sta32x_limiter1_attack_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT,
- 16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter2_attack_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT,
- 16, sta32x_limiter_attack_rate);
-static const struct soc_enum sta32x_limiter1_release_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT,
- 16, sta32x_limiter_release_rate);
-static const struct soc_enum sta32x_limiter2_release_rate_enum =
- SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT,
- 16, sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum,
+ STA32X_CONFD, STA32X_CONFD_DRC_SHIFT,
+ sta32x_drc_ac);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum,
+ STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT,
+ sta32x_auto_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum,
+ STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT,
+ sta32x_auto_gc_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum,
+ STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT,
+ sta32x_auto_xo_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum,
+ STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT,
+ sta32x_preset_eq_mode);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum,
+ STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum,
+ STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum,
+ STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT,
+ sta32x_limiter_select);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum,
+ STA32X_L1AR, STA32X_LxA_SHIFT,
+ sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum,
+ STA32X_L2AR, STA32X_LxA_SHIFT,
+ sta32x_limiter_attack_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum,
+ STA32X_L1AR, STA32X_LxR_SHIFT,
+ sta32x_limiter_release_rate);
+static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum,
+ STA32X_L2AR, STA32X_LxR_SHIFT,
+ sta32x_limiter_release_rate);
/* byte array controls for setting biquad, mixer, scaling coefficients;
* for biquads all five coefficients need to be set in one go,
@@ -331,7 +331,7 @@
static int sta32x_cache_sync(struct snd_soc_codec *codec)
{
- struct sta32x_priv *sta32x = codec->control_data;
+ struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
unsigned int mute;
int rc;
@@ -432,7 +432,7 @@
SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum),
SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum),
SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
-SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum),
+SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum),
/* depending on mode, the attack/release thresholds have
* two different enum definitions; provide both
diff --git a/sound/soc/codecs/tas5086.c b/sound/soc/codecs/tas5086.c
index d447c4a..675a8fd 100644
--- a/sound/soc/codecs/tas5086.c
+++ b/sound/soc/codecs/tas5086.c
@@ -173,7 +173,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = priv->deemph;
+ ucontrol->value.integer.value[0] = priv->deemph;
return 0;
}
@@ -184,7 +184,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct tas5086_private *priv = snd_soc_codec_get_drvdata(codec);
- priv->deemph = ucontrol->value.enumerated.item[0];
+ priv->deemph = ucontrol->value.integer.value[0];
return tas5086_set_deemph(codec);
}
diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c
index 7fefd76..124fb53 100644
--- a/sound/soc/codecs/wm2000.c
+++ b/sound/soc/codecs/wm2000.c
@@ -605,7 +605,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
- ucontrol->value.enumerated.item[0] = wm2000->anc_active;
+ ucontrol->value.integer.value[0] = wm2000->anc_active;
return 0;
}
@@ -615,7 +615,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
- int anc_active = ucontrol->value.enumerated.item[0];
+ int anc_active = ucontrol->value.integer.value[0];
int ret;
if (anc_active > 1)
@@ -638,7 +638,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
- ucontrol->value.enumerated.item[0] = wm2000->spk_ena;
+ ucontrol->value.integer.value[0] = wm2000->spk_ena;
return 0;
}
@@ -648,7 +648,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm2000_priv *wm2000 = dev_get_drvdata(codec->dev);
- int val = ucontrol->value.enumerated.item[0];
+ int val = ucontrol->value.integer.value[0];
int ret;
if (val > 1)
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 88ad7db..3775394 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -37,6 +37,95 @@
struct arizona_fll fll[2];
};
+static const struct reg_default wm5110_sysclk_revd_patch[] = {
+ { 0x3093, 0x1001 },
+ { 0x30E3, 0x1301 },
+ { 0x3133, 0x1201 },
+ { 0x3183, 0x1501 },
+ { 0x31D3, 0x1401 },
+ { 0x0049, 0x01ea },
+ { 0x004a, 0x01f2 },
+ { 0x0057, 0x01e7 },
+ { 0x0058, 0x01fb },
+ { 0x33ce, 0xc4f5 },
+ { 0x33cf, 0x1361 },
+ { 0x33d0, 0x0402 },
+ { 0x33d1, 0x4700 },
+ { 0x33d2, 0x026d },
+ { 0x33d3, 0xff00 },
+ { 0x33d4, 0x026d },
+ { 0x33d5, 0x0101 },
+ { 0x33d6, 0xc4f5 },
+ { 0x33d7, 0x0361 },
+ { 0x33d8, 0x0402 },
+ { 0x33d9, 0x6701 },
+ { 0x33da, 0xc4f5 },
+ { 0x33db, 0x136f },
+ { 0x33dc, 0xc4f5 },
+ { 0x33dd, 0x134f },
+ { 0x33de, 0xc4f5 },
+ { 0x33df, 0x131f },
+ { 0x33e0, 0x026d },
+ { 0x33e1, 0x4f01 },
+ { 0x33e2, 0x026d },
+ { 0x33e3, 0xf100 },
+ { 0x33e4, 0x026d },
+ { 0x33e5, 0x0001 },
+ { 0x33e6, 0xc4f5 },
+ { 0x33e7, 0x0361 },
+ { 0x33e8, 0x0402 },
+ { 0x33e9, 0x6601 },
+ { 0x33ea, 0xc4f5 },
+ { 0x33eb, 0x136f },
+ { 0x33ec, 0xc4f5 },
+ { 0x33ed, 0x134f },
+ { 0x33ee, 0xc4f5 },
+ { 0x33ef, 0x131f },
+ { 0x33f0, 0x026d },
+ { 0x33f1, 0x4e01 },
+ { 0x33f2, 0x026d },
+ { 0x33f3, 0xf000 },
+ { 0x33f6, 0xc4f5 },
+ { 0x33f7, 0x1361 },
+ { 0x33f8, 0x0402 },
+ { 0x33f9, 0x4600 },
+ { 0x33fa, 0x026d },
+ { 0x33fb, 0xfe00 },
+};
+
+static int wm5110_sysclk_ev(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ struct snd_soc_codec *codec = w->codec;
+ struct arizona *arizona = dev_get_drvdata(codec->dev->parent);
+ struct regmap *regmap = codec->control_data;
+ const struct reg_default *patch = NULL;
+ int i, patch_size;
+
+ switch (arizona->rev) {
+ case 3:
+ patch = wm5110_sysclk_revd_patch;
+ patch_size = ARRAY_SIZE(wm5110_sysclk_revd_patch);
+ break;
+ default:
+ return 0;
+ }
+
+ switch (event) {
+ case SND_SOC_DAPM_POST_PMU:
+ if (patch)
+ for (i = 0; i < patch_size; i++)
+ regmap_write(regmap, patch[i].reg,
+ patch[i].def);
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
static DECLARE_TLV_DB_SCALE(ana_tlv, 0, 100, 0);
static DECLARE_TLV_DB_SCALE(eq_tlv, -1200, 100, 0);
static DECLARE_TLV_DB_SCALE(digital_tlv, -6400, 50, 0);
@@ -386,7 +475,7 @@
static const struct snd_soc_dapm_widget wm5110_dapm_widgets[] = {
SND_SOC_DAPM_SUPPLY("SYSCLK", ARIZONA_SYSTEM_CLOCK_1, ARIZONA_SYSCLK_ENA_SHIFT,
- 0, NULL, 0),
+ 0, wm5110_sysclk_ev, SND_SOC_DAPM_POST_PMU),
SND_SOC_DAPM_SUPPLY("ASYNCCLK", ARIZONA_ASYNC_CLOCK_1,
ARIZONA_ASYNC_CLK_ENA_SHIFT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("OPCLK", ARIZONA_OUTPUT_SYSTEM_CLOCK,
@@ -856,7 +945,7 @@
{ "HPOUT2R", NULL, "OUT2R" },
{ "HPOUT3L", NULL, "OUT3L" },
- { "HPOUT3R", NULL, "OUT3L" },
+ { "HPOUT3R", NULL, "OUT3R" },
{ "SPKOUTLN", NULL, "OUT4L" },
{ "SPKOUTLP", NULL, "OUT4L" },
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 5276062..944b09b 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -121,7 +121,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = wm8731->deemph;
+ ucontrol->value.integer.value[0] = wm8731->deemph;
return 0;
}
@@ -131,7 +131,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8731_priv *wm8731 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
int ret = 0;
if (deemph > 1)
@@ -407,10 +407,10 @@
iface |= 0x0001;
break;
case SND_SOC_DAIFMT_DSP_A:
- iface |= 0x0003;
+ iface |= 0x0013;
break;
case SND_SOC_DAIFMT_DSP_B:
- iface |= 0x0013;
+ iface |= 0x0003;
break;
default:
return -EINVAL;
diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c
index 89a18d8..5bce210 100644
--- a/sound/soc/codecs/wm8770.c
+++ b/sound/soc/codecs/wm8770.c
@@ -196,8 +196,8 @@
"AIN5", "AIN6", "AIN7", "AIN8"
};
-static const struct soc_enum ain_enum =
- SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text);
+static SOC_ENUM_DOUBLE_DECL(ain_enum,
+ WM8770_ADCMUX, 0, 4, ain_text);
static const struct snd_kcontrol_new ain_mux =
SOC_DAPM_ENUM("Capture Mux", ain_enum);
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index 9d88437..79f4a21 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -446,7 +446,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = wm8903->deemph;
+ ucontrol->value.integer.value[0] = wm8903->deemph;
return 0;
}
@@ -456,7 +456,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8903_priv *wm8903 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
int ret = 0;
if (deemph > 1)
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 3ff195c..c68d541 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -523,7 +523,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = wm8904->deemph;
+ ucontrol->value.integer.value[0] = wm8904->deemph;
return 0;
}
@@ -532,7 +532,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
if (deemph > 1)
return -EINVAL;
@@ -1449,7 +1449,7 @@
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
case SND_SOC_DAIFMT_DSP_B:
- aif1 |= WM8904_AIF_LRCLK_INV;
+ aif1 |= 0x3 | WM8904_AIF_LRCLK_INV;
case SND_SOC_DAIFMT_DSP_A:
aif1 |= 0x3;
break;
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index 82c8ba9..1c1fc61 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -393,7 +393,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = wm8955->deemph;
+ ucontrol->value.integer.value[0] = wm8955->deemph;
return 0;
}
@@ -402,7 +402,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
if (deemph > 1)
return -EINVAL;
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index b0710d8..754f88e 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -153,7 +153,7 @@
data32 &= 0xffffff;
- wm8994_bulk_write(codec->control_data,
+ wm8994_bulk_write(wm8994->wm8994,
data32 & 0xffffff,
block_len / 2,
(void *)(data + 8));
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 0a4ffdd..4a8decf 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -181,7 +181,7 @@
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
- ucontrol->value.enumerated.item[0] = wm8960->deemph;
+ ucontrol->value.integer.value[0] = wm8960->deemph;
return 0;
}
@@ -190,7 +190,7 @@
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
- int deemph = ucontrol->value.enumerated.item[0];
+ int deemph = ucontrol->value.integer.value[0];
if (deemph > 1)
return -EINVAL;
@@ -555,7 +555,7 @@
{ 22050, 2 },
{ 24000, 2 },
{ 16000, 3 },
- { 11250, 4 },
+ { 11025, 4 },
{ 12000, 4 },
{ 8000, 5 },
};
@@ -857,9 +857,9 @@
if (pll_div.k) {
reg |= 0x20;
- snd_soc_write(codec, WM8960_PLL2, (pll_div.k >> 18) & 0x3f);
- snd_soc_write(codec, WM8960_PLL3, (pll_div.k >> 9) & 0x1ff);
- snd_soc_write(codec, WM8960_PLL4, pll_div.k & 0x1ff);
+ snd_soc_write(codec, WM8960_PLL2, (pll_div.k >> 16) & 0xff);
+ snd_soc_write(codec, WM8960_PLL3, (pll_div.k >> 8) & 0xff);
+ snd_soc_write(codec, WM8960_PLL4, pll_div.k & 0xff);
}
snd_soc_write(codec, WM8960_PLL1, reg);
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index e971028..1ae1f8b 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -153,6 +153,7 @@
{ 40, 0x0000 }, /* R40 - SPKOUTL volume */
{ 41, 0x0000 }, /* R41 - SPKOUTR volume */
+ { 49, 0x0010 }, /* R49 - Class D Control 1 */
{ 51, 0x0003 }, /* R51 - Class D Control 2 */
{ 56, 0x0506 }, /* R56 - Clocking 4 */
@@ -794,7 +795,6 @@
case WM8962_ALC2:
case WM8962_THERMAL_SHUTDOWN_STATUS:
case WM8962_ADDITIONAL_CONTROL_4:
- case WM8962_CLASS_D_CONTROL_1:
case WM8962_DC_SERVO_6:
case WM8962_INTERRUPT_STATUS_1:
case WM8962_INTERRUPT_STATUS_2:
@@ -1600,7 +1600,6 @@
struct snd_ctl_elem_value *ucontrol)
{
struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
- u16 *reg_cache = codec->reg_cache;
int ret;
/* Apply the update (if any) */
@@ -1609,16 +1608,19 @@
return 0;
/* If the left PGA is enabled hit that VU bit... */
- if (snd_soc_read(codec, WM8962_PWR_MGMT_2) & WM8962_HPOUTL_PGA_ENA)
- return snd_soc_write(codec, WM8962_HPOUTL_VOLUME,
- reg_cache[WM8962_HPOUTL_VOLUME]);
+ ret = snd_soc_read(codec, WM8962_PWR_MGMT_2);
+ if (ret & WM8962_HPOUTL_PGA_ENA) {
+ snd_soc_write(codec, WM8962_HPOUTL_VOLUME,
+ snd_soc_read(codec, WM8962_HPOUTL_VOLUME));
+ return 1;
+ }
/* ...otherwise the right. The VU is stereo. */
- if (snd_soc_read(codec, WM8962_PWR_MGMT_2) & WM8962_HPOUTR_PGA_ENA)
- return snd_soc_write(codec, WM8962_HPOUTR_VOLUME,
- reg_cache[WM8962_HPOUTR_VOLUME]);
+ if (ret & WM8962_HPOUTR_PGA_ENA)
+ snd_soc_write(codec, WM8962_HPOUTR_VOLUME,
+ snd_soc_read(codec, WM8962_HPOUTR_VOLUME));
- return 0;
+ return 1;
}
/* The VU bits for the speakers are in a different register to the mute
@@ -2899,13 +2901,22 @@
static int wm8962_mute(struct snd_soc_dai *dai, int mute)
{
struct snd_soc_codec *codec = dai->codec;
- int val;
+ int val, ret;
if (mute)
- val = WM8962_DAC_MUTE;
+ val = WM8962_DAC_MUTE | WM8962_DAC_MUTE_ALT;
else
val = 0;
+ /**
+ * The DAC mute bit is mirrored in two registers, update both to keep
+ * the register cache consistent.
+ */
+ ret = snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_1,
+ WM8962_DAC_MUTE_ALT, val);
+ if (ret < 0)
+ return ret;
+
return snd_soc_update_bits(codec, WM8962_ADC_DAC_CONTROL_1,
WM8962_DAC_MUTE, val);
}
@@ -3374,7 +3385,6 @@
int ret;
struct wm8962_priv *wm8962 = snd_soc_codec_get_drvdata(codec);
struct wm8962_pdata *pdata = dev_get_platdata(codec->dev);
- u16 *reg_cache = codec->reg_cache;
int i, trigger, irq_pol;
bool dmicclk, dmicdat;
@@ -3432,8 +3442,9 @@
/* Put the speakers into mono mode? */
if (pdata->spk_mono)
- reg_cache[WM8962_CLASS_D_CONTROL_2]
- |= WM8962_SPK_MONO;
+ snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_2,
+ WM8962_SPK_MONO_MASK, WM8962_SPK_MONO);
+
/* Micbias setup, detection enable and detection
* threasholds. */
@@ -3684,6 +3695,8 @@
if (ret < 0)
goto err_enable;
+ regcache_cache_only(wm8962->regmap, true);
+
/* The drivers should power up as needed */
regulator_bulk_disable(ARRAY_SIZE(wm8962->supplies), wm8962->supplies);
diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h
index a1a5d52..910aafd 100644
--- a/sound/soc/codecs/wm8962.h
+++ b/sound/soc/codecs/wm8962.h
@@ -1954,6 +1954,10 @@
#define WM8962_SPKOUTL_ENA_MASK 0x0040 /* SPKOUTL_ENA */
#define WM8962_SPKOUTL_ENA_SHIFT 6 /* SPKOUTL_ENA */
#define WM8962_SPKOUTL_ENA_WIDTH 1 /* SPKOUTL_ENA */
+#define WM8962_DAC_MUTE_ALT 0x0010 /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_MASK 0x0010 /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_SHIFT 4 /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_WIDTH 1 /* DAC_MUTE */
#define WM8962_SPKOUTL_PGA_MUTE 0x0002 /* SPKOUTL_PGA_MUTE */
#define WM8962_SPKOUTL_PGA_MUTE_MASK 0x0002 /* SPKOUTL_PGA_MUTE */
#define WM8962_SPKOUTL_PGA_MUTE_SHIFT 1 /* SPKOUTL_PGA_MUTE */
diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 837978e..ded9ed8 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -1264,6 +1264,8 @@
/* disable POBCTRL, SOFT_ST and BUFDCOPEN */
snd_soc_write(codec, WM8990_ANTIPOP2, 0x0);
+
+ codec->cache_sync = 1;
break;
}
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 3470b64..d785e46 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -964,6 +964,7 @@
file, blocks, pos - firmware->size);
out_fw:
+ regmap_async_complete(regmap);
release_firmware(firmware);
wm_adsp_buf_free(&buf_list);
out:
@@ -1073,13 +1074,17 @@
return ret;
/* Wait for the RAM to start, should be near instantaneous */
- count = 0;
- do {
+ for (count = 0; count < 10; ++count) {
ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1,
&val);
if (ret != 0)
return ret;
- } while (!(val & ADSP2_RAM_RDY) && ++count < 10);
+
+ if (val & ADSP2_RAM_RDY)
+ break;
+
+ msleep(1);
+ }
if (!(val & ADSP2_RAM_RDY)) {
adsp_err(dsp, "Failed to start DSP RAM\n");
@@ -1280,3 +1285,5 @@
return 0;
}
EXPORT_SYMBOL_GPL(wm_adsp2_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index f5d81b9..7a0466e 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -530,6 +530,7 @@
hubs->hp_startup_mode);
break;
}
+ break;
case SND_SOC_DAPM_PRE_PMD:
snd_soc_update_bits(codec, WM8993_CHARGE_PUMP_1,
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 81490fe..ade9d63 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -632,8 +632,17 @@
{
u32 fmt;
u32 tx_rotate = (word_length / 4) & 0x7;
- u32 rx_rotate = (32 - word_length) / 4;
u32 mask = (1ULL << word_length) - 1;
+ /*
+ * For captured data we should not rotate, inversion and masking is
+ * enoguh to get the data to the right position:
+ * Format data from bus after reverse (XRBUF)
+ * S16_LE: |LSB|MSB|xxx|xxx| |xxx|xxx|MSB|LSB|
+ * S24_3LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB|
+ * S24_LE: |LSB|DAT|MSB|xxx| |xxx|MSB|DAT|LSB|
+ * S32_LE: |LSB|DAT|DAT|MSB| |MSB|DAT|DAT|LSB|
+ */
+ u32 rx_rotate = 0;
/*
* if s BCLK-to-LRCLK ratio has been configured via the set_clkdiv()
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index 593a3ea1..489a9abf1 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -263,6 +263,19 @@
snd_soc_dai_set_dma_data(dai, substream, NULL);
}
+static int dw_i2s_prepare(struct snd_pcm_substream *substream,
+ struct snd_soc_dai *dai)
+{
+ struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai);
+
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+ i2s_write_reg(dev->i2s_base, TXFFR, 1);
+ else
+ i2s_write_reg(dev->i2s_base, RXFFR, 1);
+
+ return 0;
+}
+
static int dw_i2s_trigger(struct snd_pcm_substream *substream,
int cmd, struct snd_soc_dai *dai)
{
@@ -294,6 +307,7 @@
.startup = dw_i2s_startup,
.shutdown = dw_i2s_shutdown,
.hw_params = dw_i2s_hw_params,
+ .prepare = dw_i2s_prepare,
.trigger = dw_i2s_trigger,
};
diff --git a/sound/soc/fsl/imx-pcm-fiq.c b/sound/soc/fsl/imx-pcm-fiq.c
index 670b96b..dcfd0fa 100644
--- a/sound/soc/fsl/imx-pcm-fiq.c
+++ b/sound/soc/fsl/imx-pcm-fiq.c
@@ -42,7 +42,8 @@
struct hrtimer hrt;
int poll_time_ns;
struct snd_pcm_substream *substream;
- atomic_t running;
+ atomic_t playing;
+ atomic_t capturing;
};
static enum hrtimer_restart snd_hrtimer_callback(struct hrtimer *hrt)
@@ -54,7 +55,7 @@
struct pt_regs regs;
unsigned long delta;
- if (!atomic_read(&iprtd->running))
+ if (!atomic_read(&iprtd->playing) && !atomic_read(&iprtd->capturing))
return HRTIMER_NORESTART;
get_fiq_regs(®s);
@@ -122,7 +123,6 @@
return 0;
}
-static int fiq_enable;
static int imx_pcm_fiq;
static int snd_imx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
@@ -134,23 +134,27 @@
case SNDRV_PCM_TRIGGER_START:
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- atomic_set(&iprtd->running, 1);
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+ atomic_set(&iprtd->playing, 1);
+ else
+ atomic_set(&iprtd->capturing, 1);
hrtimer_start(&iprtd->hrt, ns_to_ktime(iprtd->poll_time_ns),
HRTIMER_MODE_REL);
- if (++fiq_enable == 1)
- enable_fiq(imx_pcm_fiq);
-
+ enable_fiq(imx_pcm_fiq);
break;
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- atomic_set(&iprtd->running, 0);
-
- if (--fiq_enable == 0)
+ if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+ atomic_set(&iprtd->playing, 0);
+ else
+ atomic_set(&iprtd->capturing, 0);
+ if (!atomic_read(&iprtd->playing) &&
+ !atomic_read(&iprtd->capturing))
disable_fiq(imx_pcm_fiq);
-
break;
+
default:
return -EINVAL;
}
@@ -198,7 +202,8 @@
iprtd->substream = substream;
- atomic_set(&iprtd->running, 0);
+ atomic_set(&iprtd->playing, 0);
+ atomic_set(&iprtd->capturing, 0);
hrtimer_init(&iprtd->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
iprtd->hrt.function = snd_hrtimer_callback;
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 6f4dd75..95a9b07 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -757,9 +757,7 @@
SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_64000 | \
SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000)
-#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
- SNDRV_PCM_FMTBIT_S24_LE | \
- SNDRV_PCM_FMTBIT_S32_LE)
+#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE)
static const struct snd_soc_dai_ops pxa_ssp_dai_ops = {
.startup = pxa_ssp_startup,
diff --git a/sound/soc/s6000/s6000-pcm.c b/sound/soc/s6000/s6000-pcm.c
index 1358c7d..d0740a7 100644
--- a/sound/soc/s6000/s6000-pcm.c
+++ b/sound/soc/s6000/s6000-pcm.c
@@ -128,7 +128,9 @@
substream->runtime &&
snd_pcm_running(substream)) {
dev_dbg(pcm->dev, "xrun\n");
+ snd_pcm_stream_lock(substream);
snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock(substream);
ret = IRQ_HANDLED;
}
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 82ebb1a..5c9b5e4 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -853,11 +853,9 @@
{
struct i2s_dai *i2s = to_info(dai);
- if (dai->active) {
- i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
- i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
- i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
- }
+ i2s->suspend_i2smod = readl(i2s->addr + I2SMOD);
+ i2s->suspend_i2scon = readl(i2s->addr + I2SCON);
+ i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR);
return 0;
}
@@ -866,11 +864,9 @@
{
struct i2s_dai *i2s = to_info(dai);
- if (dai->active) {
- writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
- writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
- writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
- }
+ writel(i2s->suspend_i2scon, i2s->addr + I2SCON);
+ writel(i2s->suspend_i2smod, i2s->addr + I2SMOD);
+ writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR);
return 0;
}
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index 06a8000a..5e9690c 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -24,6 +24,7 @@
#include <sound/compress_driver.h>
#include <sound/soc.h>
#include <sound/initval.h>
+#include <sound/soc-dpcm.h>
static int soc_compr_open(struct snd_compr_stream *cstream)
{
@@ -75,6 +76,98 @@
return ret;
}
+static int soc_compr_open_fe(struct snd_compr_stream *cstream)
+{
+ struct snd_soc_pcm_runtime *fe = cstream->private_data;
+ struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream;
+ struct snd_soc_platform *platform = fe->platform;
+ struct snd_soc_dai *cpu_dai = fe->cpu_dai;
+ struct snd_soc_dai *codec_dai = fe->codec_dai;
+ struct snd_soc_dpcm *dpcm;
+ struct snd_soc_dapm_widget_list *list;
+ int stream;
+ int ret = 0;
+
+ if (cstream->direction == SND_COMPRESS_PLAYBACK)
+ stream = SNDRV_PCM_STREAM_PLAYBACK;
+ else
+ stream = SNDRV_PCM_STREAM_CAPTURE;
+
+ mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+ if (platform->driver->compr_ops && platform->driver->compr_ops->open) {
+ ret = platform->driver->compr_ops->open(cstream);
+ if (ret < 0) {
+ pr_err("compress asoc: can't open platform %s\n", platform->name);
+ goto out;
+ }
+ }
+
+ if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->startup) {
+ ret = fe->dai_link->compr_ops->startup(cstream);
+ if (ret < 0) {
+ pr_err("compress asoc: %s startup failed\n", fe->dai_link->name);
+ goto machine_err;
+ }
+ }
+
+ fe->dpcm[stream].runtime = fe_substream->runtime;
+
+ if (dpcm_path_get(fe, stream, &list) <= 0) {
+ dev_dbg(fe->dev, "ASoC: %s no valid %s route\n",
+ fe->dai_link->name, stream ? "capture" : "playback");
+ }
+
+ /* calculate valid and active FE <-> BE dpcms */
+ dpcm_process_paths(fe, stream, &list, 1);
+
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+ ret = dpcm_be_dai_startup(fe, stream);
+ if (ret < 0) {
+ /* clean up all links */
+ list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+ dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+ dpcm_be_disconnect(fe, stream);
+ fe->dpcm[stream].runtime = NULL;
+ goto fe_err;
+ }
+
+ dpcm_clear_pending_state(fe, stream);
+ dpcm_path_put(&list);
+
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_OPEN;
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+
+ if (cstream->direction == SND_COMPRESS_PLAYBACK) {
+ cpu_dai->playback_active++;
+ codec_dai->playback_active++;
+ } else {
+ cpu_dai->capture_active++;
+ codec_dai->capture_active++;
+ }
+
+ cpu_dai->active++;
+ codec_dai->active++;
+ fe->codec->active++;
+
+ mutex_unlock(&fe->card->mutex);
+
+ return 0;
+
+fe_err:
+ if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
+ fe->dai_link->compr_ops->shutdown(cstream);
+machine_err:
+ if (platform->driver->compr_ops && platform->driver->compr_ops->free)
+ platform->driver->compr_ops->free(cstream);
+out:
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+ mutex_unlock(&fe->card->mutex);
+ return ret;
+}
+
/*
* Power down the audio subsystem pmdown_time msecs after close is called.
* This is to ensure there are no pops or clicks in between any music tracks
@@ -149,8 +242,9 @@
SND_SOC_DAPM_STREAM_STOP);
} else {
rtd->pop_wait = 1;
- schedule_delayed_work(&rtd->delayed_work,
- msecs_to_jiffies(rtd->pmdown_time));
+ queue_delayed_work(system_power_efficient_wq,
+ &rtd->delayed_work,
+ msecs_to_jiffies(rtd->pmdown_time));
}
} else {
/* capture streams can be powered down now */
@@ -163,6 +257,65 @@
return 0;
}
+static int soc_compr_free_fe(struct snd_compr_stream *cstream)
+{
+ struct snd_soc_pcm_runtime *fe = cstream->private_data;
+ struct snd_soc_platform *platform = fe->platform;
+ struct snd_soc_dai *cpu_dai = fe->cpu_dai;
+ struct snd_soc_dai *codec_dai = fe->codec_dai;
+ struct snd_soc_dpcm *dpcm;
+ int stream, ret;
+
+ mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+ if (cstream->direction == SND_COMPRESS_PLAYBACK) {
+ stream = SNDRV_PCM_STREAM_PLAYBACK;
+ cpu_dai->playback_active--;
+ codec_dai->playback_active--;
+ } else {
+ stream = SNDRV_PCM_STREAM_CAPTURE;
+ cpu_dai->capture_active--;
+ codec_dai->capture_active--;
+ }
+
+ cpu_dai->active--;
+ codec_dai->active--;
+ fe->codec->active--;
+
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+ ret = dpcm_be_dai_hw_free(fe, stream);
+ if (ret < 0)
+ dev_err(fe->dev, "compressed hw_free failed %d\n", ret);
+
+ ret = dpcm_be_dai_shutdown(fe, stream);
+
+ /* mark FE's links ready to prune */
+ list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+ dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+ if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
+ else
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_STOP);
+
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_CLOSE;
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+
+ dpcm_be_disconnect(fe, stream);
+
+ fe->dpcm[stream].runtime = NULL;
+
+ if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
+ fe->dai_link->compr_ops->shutdown(cstream);
+
+ if (platform->driver->compr_ops && platform->driver->compr_ops->free)
+ platform->driver->compr_ops->free(cstream);
+
+ mutex_unlock(&fe->card->mutex);
+ return 0;
+}
+
static int soc_compr_trigger(struct snd_compr_stream *cstream, int cmd)
{
@@ -193,6 +346,59 @@
return ret;
}
+static int soc_compr_trigger_fe(struct snd_compr_stream *cstream, int cmd)
+{
+ struct snd_soc_pcm_runtime *fe = cstream->private_data;
+ struct snd_soc_platform *platform = fe->platform;
+ int ret = 0, stream;
+
+ if (cmd == SND_COMPR_TRIGGER_PARTIAL_DRAIN ||
+ cmd == SND_COMPR_TRIGGER_DRAIN) {
+
+ if (platform->driver->compr_ops &&
+ platform->driver->compr_ops->trigger)
+ return platform->driver->compr_ops->trigger(cstream, cmd);
+ }
+
+ if (cstream->direction == SND_COMPRESS_PLAYBACK)
+ stream = SNDRV_PCM_STREAM_PLAYBACK;
+ else
+ stream = SNDRV_PCM_STREAM_CAPTURE;
+
+
+ mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+ if (platform->driver->compr_ops && platform->driver->compr_ops->trigger) {
+ ret = platform->driver->compr_ops->trigger(cstream, cmd);
+ if (ret < 0)
+ goto out;
+ }
+
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+ ret = dpcm_be_dai_trigger(fe, stream, cmd);
+
+ switch (cmd) {
+ case SNDRV_PCM_TRIGGER_START:
+ case SNDRV_PCM_TRIGGER_RESUME:
+ case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_START;
+ break;
+ case SNDRV_PCM_TRIGGER_STOP:
+ case SNDRV_PCM_TRIGGER_SUSPEND:
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
+ break;
+ case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PAUSED;
+ break;
+ }
+
+out:
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+ mutex_unlock(&fe->card->mutex);
+ return ret;
+}
+
static int soc_compr_set_params(struct snd_compr_stream *cstream,
struct snd_compr_params *params)
{
@@ -240,6 +446,64 @@
return ret;
}
+static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
+ struct snd_compr_params *params)
+{
+ struct snd_soc_pcm_runtime *fe = cstream->private_data;
+ struct snd_pcm_substream *fe_substream = fe->pcm->streams[0].substream;
+ struct snd_soc_platform *platform = fe->platform;
+ int ret = 0, stream;
+
+ if (cstream->direction == SND_COMPRESS_PLAYBACK)
+ stream = SNDRV_PCM_STREAM_PLAYBACK;
+ else
+ stream = SNDRV_PCM_STREAM_CAPTURE;
+
+ mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+
+ if (platform->driver->compr_ops && platform->driver->compr_ops->set_params) {
+ ret = platform->driver->compr_ops->set_params(cstream, params);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->set_params) {
+ ret = fe->dai_link->compr_ops->set_params(cstream);
+ if (ret < 0)
+ goto out;
+ }
+
+ /*
+ * Create an empty hw_params for the BE as the machine driver must
+ * fix this up to match DSP decoder and ASRC configuration.
+ * I.e. machine driver fixup for compressed BE is mandatory.
+ */
+ memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
+ sizeof(struct snd_pcm_hw_params));
+
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+ ret = dpcm_be_dai_hw_params(fe, stream);
+ if (ret < 0)
+ goto out;
+
+ ret = dpcm_be_dai_prepare(fe, stream);
+ if (ret < 0)
+ goto out;
+
+ if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
+ else
+ dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
+
+ fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE;
+
+out:
+ fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
+ mutex_unlock(&fe->card->mutex);
+ return ret;
+}
+
static int soc_compr_get_params(struct snd_compr_stream *cstream,
struct snd_codec *params)
{
@@ -334,7 +598,7 @@
return ret;
}
-static int sst_compr_set_metadata(struct snd_compr_stream *cstream,
+static int soc_compr_set_metadata(struct snd_compr_stream *cstream,
struct snd_compr_metadata *metadata)
{
struct snd_soc_pcm_runtime *rtd = cstream->private_data;
@@ -347,7 +611,7 @@
return ret;
}
-static int sst_compr_get_metadata(struct snd_compr_stream *cstream,
+static int soc_compr_get_metadata(struct snd_compr_stream *cstream,
struct snd_compr_metadata *metadata)
{
struct snd_soc_pcm_runtime *rtd = cstream->private_data;
@@ -359,13 +623,14 @@
return ret;
}
+
/* ASoC Compress operations */
static struct snd_compr_ops soc_compr_ops = {
.open = soc_compr_open,
.free = soc_compr_free,
.set_params = soc_compr_set_params,
- .set_metadata = sst_compr_set_metadata,
- .get_metadata = sst_compr_get_metadata,
+ .set_metadata = soc_compr_set_metadata,
+ .get_metadata = soc_compr_get_metadata,
.get_params = soc_compr_get_params,
.trigger = soc_compr_trigger,
.pointer = soc_compr_pointer,
@@ -374,6 +639,21 @@
.get_codec_caps = soc_compr_get_codec_caps
};
+/* ASoC Dynamic Compress operations */
+static struct snd_compr_ops soc_compr_dyn_ops = {
+ .open = soc_compr_open_fe,
+ .free = soc_compr_free_fe,
+ .set_params = soc_compr_set_params_fe,
+ .get_params = soc_compr_get_params,
+ .set_metadata = soc_compr_set_metadata,
+ .get_metadata = soc_compr_get_metadata,
+ .trigger = soc_compr_trigger_fe,
+ .pointer = soc_compr_pointer,
+ .ack = soc_compr_ack,
+ .get_caps = soc_compr_get_caps,
+ .get_codec_caps = soc_compr_get_codec_caps
+};
+
/* create a new compress */
int soc_new_compress(struct snd_soc_pcm_runtime *rtd, int num)
{
@@ -382,6 +662,7 @@
struct snd_soc_dai *codec_dai = rtd->codec_dai;
struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
struct snd_compr *compr;
+ struct snd_pcm *be_pcm;
char new_name[64];
int ret = 0, direction = 0;
@@ -409,7 +690,26 @@
ret = -ENOMEM;
goto compr_err;
}
- memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
+
+ if (rtd->dai_link->dynamic) {
+ snprintf(new_name, sizeof(new_name), "(%s)",
+ rtd->dai_link->stream_name);
+
+ ret = snd_pcm_new_internal(rtd->card->snd_card, new_name, num,
+ 1, 0, &be_pcm);
+ if (ret < 0) {
+ dev_err(rtd->card->dev, "ASoC: can't create compressed for %s\n",
+ rtd->dai_link->name);
+ goto compr_err;
+ }
+
+ rtd->pcm = be_pcm;
+ rtd->fe_compr = 1;
+ be_pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream->private_data = rtd;
+ be_pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream->private_data = rtd;
+ memcpy(compr->ops, &soc_compr_dyn_ops, sizeof(soc_compr_dyn_ops));
+ } else
+ memcpy(compr->ops, &soc_compr_ops, sizeof(soc_compr_ops));
/* Add copy callback for not memory mapped DSPs */
if (platform->driver->compr_ops && platform->driver->compr_ops->copy)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c7051c4..c2ecb4e 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -682,13 +682,14 @@
return -EINVAL;
}
- path = list_first_entry(&w->sources, struct snd_soc_dapm_path,
- list_sink);
- if (!path) {
+ if (list_empty(&w->sources)) {
dev_err(dapm->dev, "ASoC: mux %s has no paths\n", w->name);
return -EINVAL;
}
+ path = list_first_entry(&w->sources, struct snd_soc_dapm_path,
+ list_sink);
+
ret = dapm_create_or_share_mixmux_kcontrol(w, 0, path);
if (ret < 0)
return ret;
@@ -1796,7 +1797,7 @@
w->active ? "active" : "inactive");
list_for_each_entry(p, &w->sources, list_sink) {
- if (p->connected && !p->connected(w, p->sink))
+ if (p->connected && !p->connected(w, p->source))
continue;
if (p->connect)
diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index 0bb5cccd..7aa26b5 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -263,7 +263,7 @@
if (device_may_wakeup(dev))
pm_wakeup_event(dev, gpio->debounce_time + 50);
- schedule_delayed_work(&gpio->work,
+ queue_delayed_work(system_power_efficient_wq, &gpio->work,
msecs_to_jiffies(gpio->debounce_time));
return IRQ_HANDLED;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index ccb6be4..7b4bf0cc1 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -34,7 +34,7 @@
#define DPCM_MAX_BE_USERS 8
/* DPCM stream event, send event to FE and all active BEs. */
-static int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
+int dpcm_dapm_stream_event(struct snd_soc_pcm_runtime *fe, int dir,
int event)
{
struct snd_soc_dpcm *dpcm;
@@ -408,8 +408,9 @@
} else {
/* start delayed pop wq here for playback streams */
rtd->pop_wait = 1;
- schedule_delayed_work(&rtd->delayed_work,
- msecs_to_jiffies(rtd->pmdown_time));
+ queue_delayed_work(system_power_efficient_wq,
+ &rtd->delayed_work,
+ msecs_to_jiffies(rtd->pmdown_time));
}
} else {
/* capture streams can be powered down now */
@@ -757,7 +758,7 @@
}
/* disconnect a BE and FE */
-static void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
+void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm, *d;
@@ -853,7 +854,7 @@
return 0;
}
-static int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
+int dpcm_path_get(struct snd_soc_pcm_runtime *fe,
int stream, struct snd_soc_dapm_widget_list **list_)
{
struct snd_soc_dai *cpu_dai = fe->cpu_dai;
@@ -875,11 +876,6 @@
return paths;
}
-static inline void dpcm_path_put(struct snd_soc_dapm_widget_list **list)
-{
- kfree(*list);
-}
-
static int dpcm_prune_paths(struct snd_soc_pcm_runtime *fe, int stream,
struct snd_soc_dapm_widget_list **list_)
{
@@ -949,7 +945,7 @@
continue;
/* don't connect if FE is not running */
- if (!fe->dpcm[stream].runtime)
+ if (!fe->dpcm[stream].runtime && !fe->fe_compr)
continue;
/* newly connected FE and BE */
@@ -974,7 +970,7 @@
* Find the corresponding BE DAIs that source or sink audio to this
* FE substream.
*/
-static int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
+int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
int stream, struct snd_soc_dapm_widget_list **list, int new)
{
if (new)
@@ -983,7 +979,7 @@
return dpcm_prune_paths(fe, stream, list);
}
-static void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
+void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
@@ -1021,7 +1017,7 @@
}
}
-static int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_startup(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
int err, count = 0;
@@ -1163,7 +1159,7 @@
return ret;
}
-static int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_shutdown(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
@@ -1224,7 +1220,7 @@
return 0;
}
-static int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
@@ -1289,7 +1285,7 @@
return 0;
}
-static int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_hw_params(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
int ret;
@@ -1419,7 +1415,7 @@
return ret;
}
-static int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
+int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
int cmd)
{
struct snd_soc_dpcm *dpcm;
@@ -1587,7 +1583,7 @@
return ret;
}
-static int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
+int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream)
{
struct snd_soc_dpcm *dpcm;
int ret = 0;
@@ -1886,6 +1882,7 @@
dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
}
+ dpcm_path_put(&list);
capture:
/* skip if FE doesn't have capture capability */
if (!fe->cpu_dai->driver->capture.channels_min)
diff --git a/sound/soc/tegra/tegra20_ac97.c b/sound/soc/tegra/tegra20_ac97.c
index 2f70ea7..05676c0 100644
--- a/sound/soc/tegra/tegra20_ac97.c
+++ b/sound/soc/tegra/tegra20_ac97.c
@@ -399,9 +399,9 @@
ac97->capture_dma_data.slave_id = of_dma[1];
ac97->playback_dma_data.addr = mem->start + TEGRA20_AC97_FIFO_TX1;
- ac97->capture_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- ac97->capture_dma_data.maxburst = 4;
- ac97->capture_dma_data.slave_id = of_dma[0];
+ ac97->playback_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+ ac97->playback_dma_data.maxburst = 4;
+ ac97->playback_dma_data.slave_id = of_dma[1];
ret = snd_soc_register_component(&pdev->dev, &tegra20_ac97_component,
&tegra20_ac97_dai, 1);
diff --git a/sound/soc/tegra/tegra20_i2s.c b/sound/soc/tegra/tegra20_i2s.c
index 52af7f6..540832e 100644
--- a/sound/soc/tegra/tegra20_i2s.c
+++ b/sound/soc/tegra/tegra20_i2s.c
@@ -74,7 +74,7 @@
unsigned int fmt)
{
struct tegra20_i2s *i2s = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
case SND_SOC_DAIFMT_NB_NF:
@@ -83,10 +83,10 @@
return -EINVAL;
}
- mask = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+ mask |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
- val = TEGRA20_I2S_CTRL_MASTER_ENABLE;
+ val |= TEGRA20_I2S_CTRL_MASTER_ENABLE;
break;
case SND_SOC_DAIFMT_CBM_CFM:
break;
diff --git a/sound/soc/tegra/tegra20_spdif.c b/sound/soc/tegra/tegra20_spdif.c
index 5eaa12c..2e7d4ac 100644
--- a/sound/soc/tegra/tegra20_spdif.c
+++ b/sound/soc/tegra/tegra20_spdif.c
@@ -67,15 +67,15 @@
{
struct device *dev = dai->dev;
struct tegra20_spdif *spdif = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
int ret, spdifclock;
- mask = TEGRA20_SPDIF_CTRL_PACK |
- TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
+ mask |= TEGRA20_SPDIF_CTRL_PACK |
+ TEGRA20_SPDIF_CTRL_BIT_MODE_MASK;
switch (params_format(params)) {
case SNDRV_PCM_FORMAT_S16_LE:
- val = TEGRA20_SPDIF_CTRL_PACK |
- TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
+ val |= TEGRA20_SPDIF_CTRL_PACK |
+ TEGRA20_SPDIF_CTRL_BIT_MODE_16BIT;
break;
default:
return -EINVAL;
@@ -323,8 +323,8 @@
}
spdif->playback_dma_data.addr = mem->start + TEGRA20_SPDIF_DATA_OUT;
- spdif->capture_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- spdif->capture_dma_data.maxburst = 4;
+ spdif->playback_dma_data.addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+ spdif->playback_dma_data.maxburst = 4;
spdif->playback_dma_data.slave_id = dmareq->start;
pm_runtime_enable(&pdev->dev);
diff --git a/sound/soc/tegra/tegra30_i2s.c b/sound/soc/tegra/tegra30_i2s.c
index 31d092d..5c6520b 100644
--- a/sound/soc/tegra/tegra30_i2s.c
+++ b/sound/soc/tegra/tegra30_i2s.c
@@ -117,7 +117,7 @@
unsigned int fmt)
{
struct tegra30_i2s *i2s = snd_soc_dai_get_drvdata(dai);
- unsigned int mask, val;
+ unsigned int mask = 0, val = 0;
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
case SND_SOC_DAIFMT_NB_NF:
@@ -126,10 +126,10 @@
return -EINVAL;
}
- mask = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+ mask |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
- val = TEGRA30_I2S_CTRL_MASTER_ENABLE;
+ val |= TEGRA30_I2S_CTRL_MASTER_ENABLE;
break;
case SND_SOC_DAIFMT_CBM_CFM:
break;
@@ -228,7 +228,7 @@
reg = TEGRA30_I2S_CIF_RX_CTRL;
} else {
val |= TEGRA30_AUDIOCIF_CTRL_DIRECTION_TX;
- reg = TEGRA30_I2S_CIF_RX_CTRL;
+ reg = TEGRA30_I2S_CIF_TX_CTRL;
}
regmap_write(i2s->regmap, reg, val);
diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c
index 4394ae7..0716ba6 100644
--- a/sound/usb/6fire/chip.c
+++ b/sound/usb/6fire/chip.c
@@ -101,7 +101,7 @@
usb_set_intfdata(intf, chips[i]);
mutex_unlock(®ister_mutex);
return 0;
- } else if (regidx < 0)
+ } else if (!devices[i] && regidx < 0)
regidx = i;
}
if (regidx < 0) {
diff --git a/sound/usb/6fire/comm.c b/sound/usb/6fire/comm.c
index 9e6e3ff..23452ee 100644
--- a/sound/usb/6fire/comm.c
+++ b/sound/usb/6fire/comm.c
@@ -110,19 +110,37 @@
static int usb6fire_comm_write8(struct comm_runtime *rt, u8 request,
u8 reg, u8 value)
{
- u8 buffer[13]; /* 13: maximum length of message */
+ u8 *buffer;
+ int ret;
+
+ /* 13: maximum length of message */
+ buffer = kmalloc(13, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
usb6fire_comm_init_buffer(buffer, 0x00, request, reg, value, 0x00);
- return usb6fire_comm_send_buffer(buffer, rt->chip->dev);
+ ret = usb6fire_comm_send_buffer(buffer, rt->chip->dev);
+
+ kfree(buffer);
+ return ret;
}
static int usb6fire_comm_write16(struct comm_runtime *rt, u8 request,
u8 reg, u8 vl, u8 vh)
{
- u8 buffer[13]; /* 13: maximum length of message */
+ u8 *buffer;
+ int ret;
+
+ /* 13: maximum length of message */
+ buffer = kmalloc(13, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
usb6fire_comm_init_buffer(buffer, 0x00, request, reg, vl, vh);
- return usb6fire_comm_send_buffer(buffer, rt->chip->dev);
+ ret = usb6fire_comm_send_buffer(buffer, rt->chip->dev);
+
+ kfree(buffer);
+ return ret;
}
int usb6fire_comm_init(struct sfire_chip *chip)
@@ -135,6 +153,12 @@
if (!rt)
return -ENOMEM;
+ rt->receiver_buffer = kzalloc(COMM_RECEIVER_BUFSIZE, GFP_KERNEL);
+ if (!rt->receiver_buffer) {
+ kfree(rt);
+ return -ENOMEM;
+ }
+
urb = &rt->receiver;
rt->serial = 1;
rt->chip = chip;
@@ -153,6 +177,7 @@
urb->interval = 1;
ret = usb_submit_urb(urb, GFP_KERNEL);
if (ret < 0) {
+ kfree(rt->receiver_buffer);
kfree(rt);
snd_printk(KERN_ERR PREFIX "cannot create comm data receiver.");
return ret;
@@ -171,6 +196,9 @@
void usb6fire_comm_destroy(struct sfire_chip *chip)
{
- kfree(chip->comm);
+ struct comm_runtime *rt = chip->comm;
+
+ kfree(rt->receiver_buffer);
+ kfree(rt);
chip->comm = NULL;
}
diff --git a/sound/usb/6fire/comm.h b/sound/usb/6fire/comm.h
index 6a0840b..780d5ed 100644
--- a/sound/usb/6fire/comm.h
+++ b/sound/usb/6fire/comm.h
@@ -24,7 +24,7 @@
struct sfire_chip *chip;
struct urb receiver;
- u8 receiver_buffer[COMM_RECEIVER_BUFSIZE];
+ u8 *receiver_buffer;
u8 serial; /* urb serial */
diff --git a/sound/usb/6fire/midi.c b/sound/usb/6fire/midi.c
index 2672242..f3dd726 100644
--- a/sound/usb/6fire/midi.c
+++ b/sound/usb/6fire/midi.c
@@ -19,6 +19,10 @@
#include "chip.h"
#include "comm.h"
+enum {
+ MIDI_BUFSIZE = 64
+};
+
static void usb6fire_midi_out_handler(struct urb *urb)
{
struct midi_runtime *rt = urb->context;
@@ -156,6 +160,12 @@
if (!rt)
return -ENOMEM;
+ rt->out_buffer = kzalloc(MIDI_BUFSIZE, GFP_KERNEL);
+ if (!rt->out_buffer) {
+ kfree(rt);
+ return -ENOMEM;
+ }
+
rt->chip = chip;
rt->in_received = usb6fire_midi_in_received;
rt->out_buffer[0] = 0x80; /* 'send midi' command */
@@ -169,6 +179,7 @@
ret = snd_rawmidi_new(chip->card, "6FireUSB", 0, 1, 1, &rt->instance);
if (ret < 0) {
+ kfree(rt->out_buffer);
kfree(rt);
snd_printk(KERN_ERR PREFIX "unable to create midi.\n");
return ret;
@@ -197,6 +208,9 @@
void usb6fire_midi_destroy(struct sfire_chip *chip)
{
- kfree(chip->midi);
+ struct midi_runtime *rt = chip->midi;
+
+ kfree(rt->out_buffer);
+ kfree(rt);
chip->midi = NULL;
}
diff --git a/sound/usb/6fire/midi.h b/sound/usb/6fire/midi.h
index c321006..84851b9 100644
--- a/sound/usb/6fire/midi.h
+++ b/sound/usb/6fire/midi.h
@@ -16,10 +16,6 @@
#include "common.h"
-enum {
- MIDI_BUFSIZE = 64
-};
-
struct midi_runtime {
struct sfire_chip *chip;
struct snd_rawmidi *instance;
@@ -32,7 +28,7 @@
struct snd_rawmidi_substream *out;
struct urb out_urb;
u8 out_serial; /* serial number of out packet */
- u8 out_buffer[MIDI_BUFSIZE];
+ u8 *out_buffer;
int buffer_offset;
void (*in_received)(struct midi_runtime *rt, u8 *data, int length);
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index 40dd50a..25f9e61 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -543,7 +543,7 @@
snd_pcm_uframes_t ret;
if (rt->panic || !sub)
- return SNDRV_PCM_STATE_XRUN;
+ return SNDRV_PCM_POS_XRUN;
spin_lock_irqsave(&sub->lock, flags);
ret = sub->dma_off;
@@ -580,6 +580,33 @@
urb->instance.number_of_packets = PCM_N_PACKETS_PER_URB;
}
+static int usb6fire_pcm_buffers_init(struct pcm_runtime *rt)
+{
+ int i;
+
+ for (i = 0; i < PCM_N_URBS; i++) {
+ rt->out_urbs[i].buffer = kzalloc(PCM_N_PACKETS_PER_URB
+ * PCM_MAX_PACKET_SIZE, GFP_KERNEL);
+ if (!rt->out_urbs[i].buffer)
+ return -ENOMEM;
+ rt->in_urbs[i].buffer = kzalloc(PCM_N_PACKETS_PER_URB
+ * PCM_MAX_PACKET_SIZE, GFP_KERNEL);
+ if (!rt->in_urbs[i].buffer)
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static void usb6fire_pcm_buffers_destroy(struct pcm_runtime *rt)
+{
+ int i;
+
+ for (i = 0; i < PCM_N_URBS; i++) {
+ kfree(rt->out_urbs[i].buffer);
+ kfree(rt->in_urbs[i].buffer);
+ }
+}
+
int usb6fire_pcm_init(struct sfire_chip *chip)
{
int i;
@@ -591,6 +618,13 @@
if (!rt)
return -ENOMEM;
+ ret = usb6fire_pcm_buffers_init(rt);
+ if (ret) {
+ usb6fire_pcm_buffers_destroy(rt);
+ kfree(rt);
+ return ret;
+ }
+
rt->chip = chip;
rt->stream_state = STREAM_DISABLED;
rt->rate = ARRAY_SIZE(rates);
@@ -612,6 +646,7 @@
ret = snd_pcm_new(chip->card, "DMX6FireUSB", 0, 1, 1, &pcm);
if (ret < 0) {
+ usb6fire_pcm_buffers_destroy(rt);
kfree(rt);
snd_printk(KERN_ERR PREFIX "cannot create pcm instance.\n");
return ret;
@@ -627,6 +662,7 @@
snd_dma_continuous_data(GFP_KERNEL),
MAX_BUFSIZE, MAX_BUFSIZE);
if (ret) {
+ usb6fire_pcm_buffers_destroy(rt);
kfree(rt);
snd_printk(KERN_ERR PREFIX
"error preallocating pcm buffers.\n");
@@ -641,17 +677,25 @@
void usb6fire_pcm_abort(struct sfire_chip *chip)
{
struct pcm_runtime *rt = chip->pcm;
+ unsigned long flags;
int i;
if (rt) {
rt->panic = true;
- if (rt->playback.instance)
+ if (rt->playback.instance) {
+ snd_pcm_stream_lock_irqsave(rt->playback.instance, flags);
snd_pcm_stop(rt->playback.instance,
SNDRV_PCM_STATE_XRUN);
- if (rt->capture.instance)
+ snd_pcm_stream_unlock_irqrestore(rt->playback.instance, flags);
+ }
+
+ if (rt->capture.instance) {
+ snd_pcm_stream_lock_irqsave(rt->capture.instance, flags);
snd_pcm_stop(rt->capture.instance,
SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock_irqrestore(rt->capture.instance, flags);
+ }
for (i = 0; i < PCM_N_URBS; i++) {
usb_poison_urb(&rt->in_urbs[i].instance);
@@ -663,6 +707,9 @@
void usb6fire_pcm_destroy(struct sfire_chip *chip)
{
- kfree(chip->pcm);
+ struct pcm_runtime *rt = chip->pcm;
+
+ usb6fire_pcm_buffers_destroy(rt);
+ kfree(rt);
chip->pcm = NULL;
}
diff --git a/sound/usb/6fire/pcm.h b/sound/usb/6fire/pcm.h
index 9b01133..f5779d6 100644
--- a/sound/usb/6fire/pcm.h
+++ b/sound/usb/6fire/pcm.h
@@ -32,7 +32,7 @@
struct urb instance;
struct usb_iso_packet_descriptor packets[PCM_N_PACKETS_PER_URB];
/* END DO NOT SEPARATE */
- u8 buffer[PCM_N_PACKETS_PER_URB * PCM_MAX_PACKET_SIZE];
+ u8 *buffer;
struct pcm_urb *peer;
};
diff --git a/sound/usb/Kconfig b/sound/usb/Kconfig
index 225dfd7..ba26642 100644
--- a/sound/usb/Kconfig
+++ b/sound/usb/Kconfig
@@ -14,6 +14,7 @@
select SND_HWDEP
select SND_RAWMIDI
select SND_PCM
+ select BITREVERSE
help
Say Y here to include support for USB audio and USB MIDI
devices.
diff --git a/sound/usb/card.h b/sound/usb/card.h
index bf2889a..82c2d80 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -90,6 +90,7 @@
unsigned int curframesize; /* current packet size in frames (for capture) */
unsigned int syncmaxsize; /* sync endpoint packet size */
unsigned int fill_max:1; /* fill max packet size always */
+ unsigned int udh01_fb_quirk:1; /* corrupted feedback data */
unsigned int datainterval; /* log_2 of data packet interval */
unsigned int syncinterval; /* P for adaptive mode, 0 otherwise */
unsigned char silence_value;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 7a444b5..308c02b 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -467,6 +467,10 @@
ep->syncinterval = 3;
ep->syncmaxsize = le16_to_cpu(get_endpoint(alts, 1)->wMaxPacketSize);
+
+ if (chip->usb_id == USB_ID(0x0644, 0x8038) /* TEAC UD-H01 */ &&
+ ep->syncmaxsize == 4)
+ ep->udh01_fb_quirk = 1;
}
list_add_tail(&ep->list, &chip->ep_list);
@@ -591,17 +595,16 @@
ep->stride = frame_bits >> 3;
ep->silence_value = pcm_format == SNDRV_PCM_FORMAT_U8 ? 0x80 : 0;
- /* calculate max. frequency */
- if (ep->maxpacksize) {
+ /* assume max. frequency is 25% higher than nominal */
+ ep->freqmax = ep->freqn + (ep->freqn >> 2);
+ maxsize = ((ep->freqmax + 0xffff) * (frame_bits >> 3))
+ >> (16 - ep->datainterval);
+ /* but wMaxPacketSize might reduce this */
+ if (ep->maxpacksize && ep->maxpacksize < maxsize) {
/* whatever fits into a max. size packet */
maxsize = ep->maxpacksize;
ep->freqmax = (maxsize / (frame_bits >> 3))
<< (16 - ep->datainterval);
- } else {
- /* no max. packet size: just take 25% higher than nominal */
- ep->freqmax = ep->freqn + (ep->freqn >> 2);
- maxsize = ((ep->freqmax + 0xffff) * (frame_bits >> 3))
- >> (16 - ep->datainterval);
}
if (ep->fill_max)
@@ -1076,7 +1079,16 @@
if (f == 0)
return;
- if (unlikely(ep->freqshift == INT_MIN)) {
+ if (unlikely(sender->udh01_fb_quirk)) {
+ /*
+ * The TEAC UD-H01 firmware sometimes changes the feedback value
+ * by +/- 0x1.0000.
+ */
+ if (f < ep->freqn - 0x8000)
+ f += 0x10000;
+ else if (f > ep->freqn + 0x8000)
+ f -= 0x10000;
+ } else if (unlikely(ep->freqshift == INT_MIN)) {
/*
* The first time we see a feedback value, determine its format
* by shifting it left or right until it matches the nominal
diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 8e01fa4..9324913 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -364,6 +364,8 @@
if (in && in->error_resubmit) {
in->error_resubmit = 0;
for (j = 0; j < INPUT_URBS; ++j) {
+ if (atomic_read(&in->urbs[j]->use_count))
+ continue;
in->urbs[j]->dev = umidi->dev;
snd_usbmidi_submit_urb(in->urbs[j], GFP_ATOMIC);
}
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 6ad617b..76d8329 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -613,14 +613,24 @@
static void abort_alsa_capture(struct ua101 *ua)
{
- if (test_bit(ALSA_CAPTURE_RUNNING, &ua->states))
+ unsigned long flags;
+
+ if (test_bit(ALSA_CAPTURE_RUNNING, &ua->states)) {
+ snd_pcm_stream_lock_irqsave(ua->capture.substream, flags);
snd_pcm_stop(ua->capture.substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock_irqrestore(ua->capture.substream, flags);
+ }
}
static void abort_alsa_playback(struct ua101 *ua)
{
- if (test_bit(ALSA_PLAYBACK_RUNNING, &ua->states))
+ unsigned long flags;
+
+ if (test_bit(ALSA_PLAYBACK_RUNNING, &ua->states)) {
+ snd_pcm_stream_lock_irqsave(ua->playback.substream, flags);
snd_pcm_stop(ua->playback.substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock_irqrestore(ua->playback.substream, flags);
+ }
}
static int set_stream_hw(struct ua101 *ua, struct snd_pcm_substream *substream,
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index d543808..061be0e 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -883,11 +883,14 @@
}
break;
+ case USB_ID(0x046d, 0x0807): /* Logitech Webcam C500 */
case USB_ID(0x046d, 0x0808):
case USB_ID(0x046d, 0x0809):
+ case USB_ID(0x046d, 0x0819): /* Logitech Webcam C210 */
case USB_ID(0x046d, 0x081b): /* HD Webcam c310 */
case USB_ID(0x046d, 0x081d): /* HD Webcam c510 */
case USB_ID(0x046d, 0x0825): /* HD Webcam c270 */
+ case USB_ID(0x046d, 0x0826): /* HD Webcam c525 */
case USB_ID(0x046d, 0x0991):
/* Most audio usb devices lie about volume resolution.
* Most Logitech webcams have res = 384.
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index cc2dd1f..4df31b0 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -322,6 +322,14 @@
{ 0 } /* terminator */
};
+/* some (all?) SCMS USB3318 devices are affected by a firmware lock up
+ * when anything attempts to access FU 10 (control)
+ */
+static const struct usbmix_name_map scms_usb3318_map[] = {
+ { 10, NULL },
+ { 0 }
+};
+
/*
* Control map entries
*/
@@ -409,6 +417,16 @@
.id = USB_ID(0x200c, 0x1018),
.map = ebox44_map,
},
+ {
+ /* KEF X300A */
+ .id = USB_ID(0x27ac, 0x1000),
+ .map = scms_usb3318_map,
+ },
+ {
+ /* Arcam rPAC */
+ .id = USB_ID(0x25c4, 0x0003),
+ .map = scms_usb3318_map,
+ },
{ 0 } /* terminator */
};
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index ebe9144..c311681 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -175,6 +175,7 @@
{ USB_ID(0x041e, 0x3040), 2, 2, 6, 6, 2, 0x6e91 }, /* Live! 24-bit */
{ USB_ID(0x041e, 0x3042), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 */
{ USB_ID(0x041e, 0x30df), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */
+ { USB_ID(0x041e, 0x3237), 0, 1, 1, 1, 1, 0x000d }, /* Usb X-Fi S51 Pro */
{ USB_ID(0x041e, 0x3048), 2, 2, 6, 6, 2, 0x6e91 }, /* Toshiba SB0500 */
};
@@ -799,6 +800,11 @@
return changed;
}
+static void kctl_private_value_free(struct snd_kcontrol *kctl)
+{
+ kfree((void *)kctl->private_value);
+}
+
static int snd_ftu_create_effect_switch(struct usb_mixer_interface *mixer,
int validx, int bUnitID)
{
@@ -833,6 +839,7 @@
return -ENOMEM;
}
+ kctl->private_free = kctl_private_value_free;
err = snd_ctl_add(mixer->chip->card, kctl);
if (err < 0)
return err;
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 93b6e32..0d7a872 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1420,7 +1420,8 @@
* on two reads of a counter updated every ms.
*/
if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
- snd_printk(KERN_DEBUG "delay: estimated %d, actual %d\n",
+ dev_dbg_ratelimited(&subs->dev->dev,
+ "delay: estimated %d, actual %d\n",
est_delay, subs->last_delay);
if (!subs->running) {
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 8b75bcf..d5bed1d 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -386,6 +386,36 @@
}
},
{
+ USB_DEVICE(0x0499, 0x1509),
+ .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+ /* .vendor_name = "Yamaha", */
+ /* .product_name = "Steinberg UR22", */
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = (const struct snd_usb_audio_quirk[]) {
+ {
+ .ifnum = 1,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 2,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = 3,
+ .type = QUIRK_MIDI_YAMAHA
+ },
+ {
+ .ifnum = 4,
+ .type = QUIRK_IGNORE_INTERFACE
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
+{
USB_DEVICE(0x0499, 0x150a),
.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
/* .vendor_name = "Yamaha", */
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 3879eae..734c657 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -914,6 +914,20 @@
if ((le16_to_cpu(dev->descriptor.idVendor) == 0x23ba) &&
(requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
mdelay(20);
+
+ /* Marantz/Denon devices with USB DAC functionality need a delay
+ * after each class compliant request
+ */
+ if ((le16_to_cpu(dev->descriptor.idVendor) == 0x154e) &&
+ (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) {
+
+ switch (le16_to_cpu(dev->descriptor.idProduct)) {
+ case 0x3005: /* Marantz HD-DAC1 */
+ case 0x3006: /* Marantz SA-14S1 */
+ mdelay(20);
+ break;
+ }
+ }
}
/*
diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c
index d0323a6..999550b 100644
--- a/sound/usb/usx2y/us122l.c
+++ b/sound/usb/usx2y/us122l.c
@@ -262,7 +262,9 @@
}
area->vm_ops = &usb_stream_hwdep_vm_ops;
- area->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+ area->vm_flags |= VM_DONTDUMP;
+ if (!read)
+ area->vm_flags |= VM_DONTEXPAND;
area->vm_private_data = us122l;
atomic_inc(&us122l->mmap_count);
out:
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index b376532..cd69a80 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -273,7 +273,11 @@
struct snd_usX2Y_substream *subs = usX2Y->subs[s];
if (subs) {
if (atomic_read(&subs->state) >= state_PRERUNNING) {
+ unsigned long flags;
+
+ snd_pcm_stream_lock_irqsave(subs->pcm_substream, flags);
snd_pcm_stop(subs->pcm_substream, SNDRV_PCM_STATE_XRUN);
+ snd_pcm_stream_unlock_irqrestore(subs->pcm_substream, flags);
}
for (u = 0; u < NRURBS; u++) {
struct urb *urb = subs->urb[u];
@@ -295,19 +299,6 @@
usX2Y_clients_stop(usX2Y);
}
-static void usX2Y_error_sequence(struct usX2Ydev *usX2Y,
- struct snd_usX2Y_substream *subs, struct urb *urb)
-{
- snd_printk(KERN_ERR
-"Sequence Error!(hcd_frame=%i ep=%i%s;wait=%i,frame=%i).\n"
-"Most probably some urb of usb-frame %i is still missing.\n"
-"Cause could be too long delays in usb-hcd interrupt handling.\n",
- usb_get_current_frame_number(usX2Y->dev),
- subs->endpoint, usb_pipein(urb->pipe) ? "in" : "out",
- usX2Y->wait_iso_frame, urb->start_frame, usX2Y->wait_iso_frame);
- usX2Y_clients_stop(usX2Y);
-}
-
static void i_usX2Y_urb_complete(struct urb *urb)
{
struct snd_usX2Y_substream *subs = urb->context;
@@ -324,12 +315,9 @@
usX2Y_error_urb_status(usX2Y, subs, urb);
return;
}
- if (likely((urb->start_frame & 0xFFFF) == (usX2Y->wait_iso_frame & 0xFFFF)))
- subs->completed_urb = urb;
- else {
- usX2Y_error_sequence(usX2Y, subs, urb);
- return;
- }
+
+ subs->completed_urb = urb;
+
{
struct snd_usX2Y_substream *capsubs = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE],
*playbacksubs = usX2Y->subs[SNDRV_PCM_STREAM_PLAYBACK];
diff --git a/sound/usb/usx2y/usx2yhwdeppcm.c b/sound/usb/usx2y/usx2yhwdeppcm.c
index f2a1acd..814d0e8 100644
--- a/sound/usb/usx2y/usx2yhwdeppcm.c
+++ b/sound/usb/usx2y/usx2yhwdeppcm.c
@@ -244,13 +244,8 @@
usX2Y_error_urb_status(usX2Y, subs, urb);
return;
}
- if (likely((urb->start_frame & 0xFFFF) == (usX2Y->wait_iso_frame & 0xFFFF)))
- subs->completed_urb = urb;
- else {
- usX2Y_error_sequence(usX2Y, subs, urb);
- return;
- }
+ subs->completed_urb = urb;
capsubs = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE];
capsubs2 = usX2Y->subs[SNDRV_PCM_STREAM_CAPTURE + 2];
playbacksubs = usX2Y->subs[SNDRV_PCM_STREAM_PLAYBACK];
diff --git a/tools/gator/daemon/Android.mk b/tools/gator/daemon/Android.mk
new file mode 100644
index 0000000..c5c8bdc
--- /dev/null
+++ b/tools/gator/daemon/Android.mk
@@ -0,0 +1,82 @@
+LOCAL_PATH := $(call my-dir)
+
+# Don't use this file if GATOR_DAEMON_PATH is set and we're not under that path
+ifneq ($(and $(GATOR_DAEMON_PATH),$(filter $(patsubst %/,%,$(GATOR_DAEMON_PATH))/%,$(LOCAL_PATH)/)),)
+
+include $(CLEAR_VARS)
+
+XML_H := $(shell cd $(LOCAL_PATH) && make events_xml.h defaults_xml.h SrcMd5.cpp)
+
+LOCAL_SRC_FILES := \
+ AnnotateListener.cpp \
+ Buffer.cpp \
+ CCNDriver.cpp \
+ CapturedXML.cpp \
+ Child.cpp \
+ Command.cpp \
+ ConfigurationXML.cpp \
+ DiskIODriver.cpp \
+ Driver.cpp \
+ DriverSource.cpp \
+ DynBuf.cpp \
+ EventsXML.cpp \
+ ExternalSource.cpp \
+ FSDriver.cpp \
+ Fifo.cpp \
+ FtraceDriver.cpp \
+ FtraceSource.cpp \
+ HwmonDriver.cpp \
+ KMod.cpp \
+ LocalCapture.cpp \
+ Logging.cpp \
+ main.cpp \
+ MaliVideoDriver.cpp \
+ MemInfoDriver.cpp\
+ Monitor.cpp \
+ NetDriver.cpp \
+ OlySocket.cpp \
+ OlyUtility.cpp \
+ PerfBuffer.cpp \
+ PerfDriver.cpp \
+ PerfGroup.cpp \
+ PerfSource.cpp \
+ Proc.cpp \
+ Sender.cpp \
+ SessionData.cpp \
+ SessionXML.cpp \
+ Setup.cpp \
+ Source.cpp \
+ SrcMd5.cpp \
+ StreamlineSetup.cpp \
+ UEvent.cpp \
+ UserSpaceSource.cpp \
+ libsensors/access.c \
+ libsensors/conf-lex.c \
+ libsensors/conf-parse.c \
+ libsensors/data.c \
+ libsensors/error.c \
+ libsensors/general.c \
+ libsensors/init.c \
+ libsensors/sysfs.c \
+ mxml/mxml-attr.c \
+ mxml/mxml-entity.c \
+ mxml/mxml-file.c \
+ mxml/mxml-get.c \
+ mxml/mxml-index.c \
+ mxml/mxml-node.c \
+ mxml/mxml-private.c \
+ mxml/mxml-search.c \
+ mxml/mxml-set.c \
+ mxml/mxml-string.c
+
+LOCAL_CFLAGS += -Wall -O3 -fno-exceptions -pthread -DETCDIR=\"/etc\" -Ilibsensors -fPIE
+LOCAL_LDFLAGS += -fPIE -pie
+
+LOCAL_C_INCLUDES := $(LOCAL_PATH)
+
+LOCAL_MODULE := gatord
+LOCAL_MODULE_TAGS := optional
+
+include $(BUILD_EXECUTABLE)
+
+endif
diff --git a/tools/gator/daemon/AnnotateListener.cpp b/tools/gator/daemon/AnnotateListener.cpp
new file mode 100644
index 0000000..5966cbe
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.cpp
@@ -0,0 +1,89 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "AnnotateListener.h"
+
+#include <unistd.h>
+
+#include "OlySocket.h"
+
+static const char STREAMLINE_ANNOTATE_PARENT[] = "\0streamline-annotate-parent";
+
+struct AnnotateClient {
+ AnnotateClient *next;
+ int fd;
+};
+
+AnnotateListener::AnnotateListener() : mClients(NULL), mSock(NULL), mUds(NULL) {
+}
+
+AnnotateListener::~AnnotateListener() {
+ close();
+ delete mUds;
+ delete mSock;
+}
+
+void AnnotateListener::setup() {
+ mSock = new OlyServerSocket(8082);
+ mUds = new OlyServerSocket(STREAMLINE_ANNOTATE_PARENT, sizeof(STREAMLINE_ANNOTATE_PARENT), true);
+}
+
+int AnnotateListener::getSockFd() {
+ return mSock->getFd();
+}
+
+void AnnotateListener::handleSock() {
+ AnnotateClient *const client = new AnnotateClient();
+ client->fd = mSock->acceptConnection();
+ client->next = mClients;
+ mClients = client;
+}
+
+int AnnotateListener::getUdsFd() {
+ return mUds->getFd();
+}
+
+void AnnotateListener::handleUds() {
+ AnnotateClient *const client = new AnnotateClient();
+ client->fd = mUds->acceptConnection();
+ client->next = mClients;
+ mClients = client;
+}
+
+void AnnotateListener::close() {
+ if (mUds != NULL) {
+ mUds->closeServerSocket();
+ }
+ if (mSock != NULL) {
+ mSock->closeServerSocket();
+ }
+ while (mClients != NULL) {
+ ::close(mClients->fd);
+ AnnotateClient *next = mClients->next;
+ delete mClients;
+ mClients = next;
+ }
+}
+
+void AnnotateListener::signal() {
+ const char ch = 0;
+ AnnotateClient **ptr = &mClients;
+ AnnotateClient *client = mClients;
+ while (client != NULL) {
+ if (write(client->fd, &ch, sizeof(ch)) != 1) {
+ ::close(client->fd);
+ AnnotateClient *next = client->next;
+ delete client;
+ *ptr = next;
+ client = next;
+ continue;
+ }
+ ptr = &client->next;
+ client = client->next;
+ }
+}
diff --git a/tools/gator/daemon/AnnotateListener.h b/tools/gator/daemon/AnnotateListener.h
new file mode 100644
index 0000000..6bc747d
--- /dev/null
+++ b/tools/gator/daemon/AnnotateListener.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ANNOTATELISTENER_H
+#define ANNOTATELISTENER_H
+
+struct AnnotateClient;
+class OlyServerSocket;
+
+class AnnotateListener {
+public:
+ AnnotateListener();
+ ~AnnotateListener();
+
+ void setup();
+ int getSockFd();
+ int getUdsFd();
+
+ void handleSock();
+ void handleUds();
+ void close();
+ void signal();
+
+private:
+ AnnotateClient *mClients;
+ OlyServerSocket *mSock;
+ OlyServerSocket *mUds;
+
+ // Intentionally unimplemented
+ AnnotateListener(const AnnotateListener &);
+ AnnotateListener &operator=(const AnnotateListener &);
+};
+
+#endif // ANNOTATELISTENER_H
diff --git a/tools/gator/daemon/Application.mk b/tools/gator/daemon/Application.mk
new file mode 100644
index 0000000..8b0a788
--- /dev/null
+++ b/tools/gator/daemon/Application.mk
@@ -0,0 +1,3 @@
+APP_PLATFORM := android-9
+# Replace armeabi-v7a with arm64-v8a to build an arm64 gatord or with armeabi to build an ARM11 gatord
+APP_ABI := armeabi-v7a
diff --git a/tools/gator/daemon/Buffer.cpp b/tools/gator/daemon/Buffer.cpp
new file mode 100644
index 0000000..c4ced9f
--- /dev/null
+++ b/tools/gator/daemon/Buffer.cpp
@@ -0,0 +1,459 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Buffer.h"
+
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+#define mask (mSize - 1)
+#define FRAME_HEADER_SIZE 3
+
+enum {
+ CODE_PEA = 1,
+ CODE_KEYS = 2,
+ CODE_FORMAT = 3,
+ CODE_MAPS = 4,
+ CODE_COMM = 5,
+ CODE_KEYS_OLD = 6,
+ CODE_ONLINE_CPU = 7,
+ CODE_OFFLINE_CPU = 8,
+ CODE_KALLSYMS = 9,
+ CODE_COUNTERS = 10,
+};
+
+// Summary Frame Messages
+enum {
+ MESSAGE_SUMMARY = 1,
+ MESSAGE_CORE_NAME = 3,
+};
+
+// From gator_marshaling.c
+#define NEWLINE_CANARY \
+ /* Unix */ \
+ "1\n" \
+ /* Windows */ \
+ "2\r\n" \
+ /* Mac OS */ \
+ "3\r" \
+ /* RISC OS */ \
+ "4\n\r" \
+ /* Add another character so the length isn't 0x0a bytes */ \
+ "5"
+
+Buffer::Buffer(const int32_t core, const int32_t buftype, const int size, sem_t *const readerSem) : mBuf(new char[size]), mReaderSem(readerSem), mCommitTime(gSessionData->mLiveRate), mSize(size), mReadPos(0), mWritePos(0), mCommitPos(0), mAvailable(true), mIsDone(false), mCore(core), mBufType(buftype) {
+ if ((mSize & mask) != 0) {
+ logg->logError("Buffer size is not a power of 2");
+ handleException();
+ }
+ sem_init(&mWriterSem, 0, 0);
+ frame();
+}
+
+Buffer::~Buffer() {
+ delete [] mBuf;
+ sem_destroy(&mWriterSem);
+}
+
+void Buffer::write(Sender *const sender) {
+ if (!commitReady()) {
+ return;
+ }
+
+ // commit and read are updated by the writer, only read them once
+ int commitPos = mCommitPos;
+ int readPos = mReadPos;
+
+ // determine the size of two halves
+ int length1 = commitPos - readPos;
+ char *buffer1 = mBuf + readPos;
+ int length2 = 0;
+ char *buffer2 = mBuf;
+ if (length1 < 0) {
+ length1 = mSize - readPos;
+ length2 = commitPos;
+ }
+
+ logg->logMessage("Sending data length1: %i length2: %i", length1, length2);
+
+ // start, middle or end
+ if (length1 > 0) {
+ sender->writeData(buffer1, length1, RESPONSE_APC_DATA);
+ }
+
+ // possible wrap around
+ if (length2 > 0) {
+ sender->writeData(buffer2, length2, RESPONSE_APC_DATA);
+ }
+
+ mReadPos = commitPos;
+
+ // send a notification that space is available
+ sem_post(&mWriterSem);
+}
+
+bool Buffer::commitReady() const {
+ return mCommitPos != mReadPos;
+}
+
+int Buffer::bytesAvailable() const {
+ int filled = mWritePos - mReadPos;
+ if (filled < 0) {
+ filled += mSize;
+ }
+
+ int remaining = mSize - filled;
+
+ if (mAvailable) {
+ // Give some extra room; also allows space to insert the overflow error packet
+ remaining -= 200;
+ } else {
+ // Hysteresis, prevents multiple overflow messages
+ remaining -= 2000;
+ }
+
+ return remaining;
+}
+
+bool Buffer::checkSpace(const int bytes) {
+ const int remaining = bytesAvailable();
+
+ if (remaining < bytes) {
+ mAvailable = false;
+ } else {
+ mAvailable = true;
+ }
+
+ return mAvailable;
+}
+
+int Buffer::contiguousSpaceAvailable() const {
+ int remaining = bytesAvailable();
+ int contiguous = mSize - mWritePos;
+ if (remaining < contiguous) {
+ return remaining;
+ } else {
+ return contiguous;
+ }
+}
+
+void Buffer::commit(const uint64_t time, const bool force) {
+ // post-populate the length, which does not include the response type length nor the length itself, i.e. only the length of the payload
+ const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+ int length = mWritePos - mCommitPos;
+ if (length < 0) {
+ length += mSize;
+ }
+ length = length - typeLength - sizeof(int32_t);
+ if (!force && !mIsDone && length <= FRAME_HEADER_SIZE) {
+ // Nothing to write, only the frame header is present
+ return;
+ }
+ for (size_t byte = 0; byte < sizeof(int32_t); byte++) {
+ mBuf[(mCommitPos + typeLength + byte) & mask] = (length >> byte * 8) & 0xFF;
+ }
+
+ logg->logMessage("Committing data mReadPos: %i mWritePos: %i mCommitPos: %i", mReadPos, mWritePos, mCommitPos);
+ mCommitPos = mWritePos;
+
+ if (gSessionData->mLiveRate > 0) {
+ while (time > mCommitTime) {
+ mCommitTime += gSessionData->mLiveRate;
+ }
+ }
+
+ if (!mIsDone) {
+ frame();
+ }
+
+ // send a notification that data is ready
+ sem_post(mReaderSem);
+}
+
+void Buffer::check(const uint64_t time) {
+ int filled = mWritePos - mCommitPos;
+ if (filled < 0) {
+ filled += mSize;
+ }
+ if (filled >= ((mSize * 3) / 4) || (gSessionData->mLiveRate > 0 && time >= mCommitTime)) {
+ commit(time);
+ }
+}
+
+void Buffer::packInt(char *const buf, const int size, int &writePos, int32_t x) {
+ int packedBytes = 0;
+ int more = true;
+ while (more) {
+ // low order 7 bits of x
+ char b = x & 0x7f;
+ x >>= 7;
+
+ if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+ more = false;
+ } else {
+ b |= 0x80;
+ }
+
+ buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+ packedBytes++;
+ }
+
+ writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt(int32_t x) {
+ packInt(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::packInt64(char *const buf, const int size, int &writePos, int64_t x) {
+ int packedBytes = 0;
+ int more = true;
+ while (more) {
+ // low order 7 bits of x
+ char b = x & 0x7f;
+ x >>= 7;
+
+ if ((x == 0 && (b & 0x40) == 0) || (x == -1 && (b & 0x40) != 0)) {
+ more = false;
+ } else {
+ b |= 0x80;
+ }
+
+ buf[(writePos + packedBytes) & /*mask*/(size - 1)] = b;
+ packedBytes++;
+ }
+
+ writePos = (writePos + packedBytes) & /*mask*/(size - 1);
+}
+
+void Buffer::packInt64(int64_t x) {
+ packInt64(mBuf, mSize, mWritePos, x);
+}
+
+void Buffer::writeBytes(const void *const data, size_t count) {
+ size_t i;
+ for (i = 0; i < count; ++i) {
+ mBuf[(mWritePos + i) & mask] = static_cast<const char *>(data)[i];
+ }
+
+ mWritePos = (mWritePos + i) & mask;
+}
+
+void Buffer::writeString(const char *const str) {
+ const int len = strlen(str);
+ packInt(len);
+ writeBytes(str, len);
+}
+
+void Buffer::frame() {
+ if (!gSessionData->mLocalCapture) {
+ packInt(RESPONSE_APC_DATA);
+ }
+ // Reserve space for the length
+ mWritePos += sizeof(int32_t);
+ packInt(mBufType);
+ if ((mBufType == FRAME_BLOCK_COUNTER) || (mBufType == FRAME_PERF_ATTRS) || (mBufType == FRAME_PERF)) {
+ packInt(mCore);
+ }
+}
+
+void Buffer::summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname) {
+ packInt(MESSAGE_SUMMARY);
+ writeString(NEWLINE_CANARY);
+ packInt64(timestamp);
+ packInt64(uptime);
+ packInt64(monotonicDelta);
+ writeString("uname");
+ writeString(uname);
+ writeString("");
+ check(currTime);
+}
+
+void Buffer::coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name) {
+ if (checkSpace(3 * MAXSIZE_PACK32 + 0x100)) {
+ packInt(MESSAGE_CORE_NAME);
+ packInt(core);
+ packInt(cpuid);
+ writeString(name);
+ }
+ check(currTime);
+}
+
+bool Buffer::eventHeader(const uint64_t curr_time) {
+ bool retval = false;
+ if (checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ // key of zero indicates a timestamp
+ packInt(0);
+ packInt64(curr_time);
+ retval = true;
+ }
+
+ return retval;
+}
+
+bool Buffer::eventTid(const int tid) {
+ bool retval = false;
+ if (checkSpace(2 * MAXSIZE_PACK32)) {
+ // key of 1 indicates a tid
+ packInt(1);
+ packInt(tid);
+ retval = true;
+ }
+
+ return retval;
+}
+
+void Buffer::event(const int key, const int32_t value) {
+ if (checkSpace(2 * MAXSIZE_PACK32)) {
+ packInt(key);
+ packInt(value);
+ }
+}
+
+void Buffer::event64(const int key, const int64_t value) {
+ if (checkSpace(MAXSIZE_PACK64 + MAXSIZE_PACK32)) {
+ packInt(key);
+ packInt64(value);
+ }
+}
+
+void Buffer::marshalPea(const uint64_t currTime, const struct perf_event_attr *const pea, int key) {
+ while (!checkSpace(2 * MAXSIZE_PACK32 + pea->size)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_PEA);
+ writeBytes(pea, pea->size);
+ packInt(key);
+ check(currTime);
+}
+
+void Buffer::marshalKeys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys) {
+ while (!checkSpace(2 * MAXSIZE_PACK32 + count * (MAXSIZE_PACK32 + MAXSIZE_PACK64))) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_KEYS);
+ packInt(count);
+ for (int i = 0; i < count; ++i) {
+ packInt64(ids[i]);
+ packInt(keys[i]);
+ }
+ check(currTime);
+}
+
+void Buffer::marshalKeysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf) {
+ while (!checkSpace((2 + keyCount) * MAXSIZE_PACK32 + bytes)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_KEYS_OLD);
+ packInt(keyCount);
+ for (int i = 0; i < keyCount; ++i) {
+ packInt(keys[i]);
+ }
+ writeBytes(buf, bytes);
+ check(currTime);
+}
+
+void Buffer::marshalFormat(const uint64_t currTime, const int length, const char *const format) {
+ while (!checkSpace(MAXSIZE_PACK32 + length + 1)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_FORMAT);
+ writeBytes(format, length + 1);
+ check(currTime);
+}
+
+void Buffer::marshalMaps(const uint64_t currTime, const int pid, const int tid, const char *const maps) {
+ const int mapsLen = strlen(maps) + 1;
+ while (!checkSpace(3 * MAXSIZE_PACK32 + mapsLen)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_MAPS);
+ packInt(pid);
+ packInt(tid);
+ writeBytes(maps, mapsLen);
+ check(currTime);
+}
+
+void Buffer::marshalComm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm) {
+ const int imageLen = strlen(image) + 1;
+ const int commLen = strlen(comm) + 1;
+ while (!checkSpace(3 * MAXSIZE_PACK32 + imageLen + commLen)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_COMM);
+ packInt(pid);
+ packInt(tid);
+ writeBytes(image, imageLen);
+ writeBytes(comm, commLen);
+ check(currTime);
+}
+
+void Buffer::onlineCPU(const uint64_t currTime, const int cpu) {
+ while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_ONLINE_CPU);
+ packInt64(currTime);
+ packInt(cpu);
+ check(currTime);
+}
+
+void Buffer::offlineCPU(const uint64_t currTime, const int cpu) {
+ while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_OFFLINE_CPU);
+ packInt64(currTime);
+ packInt(cpu);
+ check(currTime);
+}
+
+void Buffer::marshalKallsyms(const uint64_t currTime, const char *const kallsyms) {
+ const int kallsymsLen = strlen(kallsyms) + 1;
+ while (!checkSpace(3 * MAXSIZE_PACK32 + kallsymsLen)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_KALLSYMS);
+ writeBytes(kallsyms, kallsymsLen);
+ check(currTime);
+}
+
+void Buffer::perfCounterHeader(const uint64_t time) {
+ while (!checkSpace(MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(CODE_COUNTERS);
+ packInt64(time);
+}
+
+void Buffer::perfCounter(const int core, const int key, const int64_t value) {
+ while (!checkSpace(2*MAXSIZE_PACK32 + MAXSIZE_PACK64)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(core);
+ packInt(key);
+ packInt64(value);
+}
+
+void Buffer::perfCounterFooter(const uint64_t currTime) {
+ while (!checkSpace(MAXSIZE_PACK32)) {
+ sem_wait(&mWriterSem);
+ }
+ packInt(-1);
+ check(currTime);
+}
+
+void Buffer::setDone() {
+ mIsDone = true;
+ commit(0);
+}
+
+bool Buffer::isDone() const {
+ return mIsDone && mReadPos == mCommitPos && mCommitPos == mWritePos;
+}
diff --git a/tools/gator/daemon/Buffer.h b/tools/gator/daemon/Buffer.h
new file mode 100644
index 0000000..13c44e1
--- /dev/null
+++ b/tools/gator/daemon/Buffer.h
@@ -0,0 +1,109 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef BUFFER_H
+#define BUFFER_H
+
+#include <stdint.h>
+#include <semaphore.h>
+
+#include "k/perf_event.h"
+
+class Sender;
+
+enum {
+ FRAME_SUMMARY = 1,
+ FRAME_BLOCK_COUNTER = 5,
+ FRAME_EXTERNAL = 10,
+ FRAME_PERF_ATTRS = 11,
+ FRAME_PERF = 12,
+};
+
+class Buffer {
+public:
+ static const size_t MAXSIZE_PACK32 = 5;
+ static const size_t MAXSIZE_PACK64 = 10;
+
+ Buffer(int32_t core, int32_t buftype, const int size, sem_t *const readerSem);
+ ~Buffer();
+
+ void write(Sender *sender);
+
+ int bytesAvailable() const;
+ int contiguousSpaceAvailable() const;
+ void commit(const uint64_t time, const bool force = false);
+ void check(const uint64_t time);
+
+ // Summary messages
+ void summary(const uint64_t currTime, const int64_t timestamp, const int64_t uptime, const int64_t monotonicDelta, const char *const uname);
+ void coreName(const uint64_t currTime, const int core, const int cpuid, const char *const name);
+
+ // Block Counter messages
+ bool eventHeader(uint64_t curr_time);
+ bool eventTid(int tid);
+ void event(int key, int32_t value);
+ void event64(int key, int64_t value);
+
+ // Perf Attrs messages
+ void marshalPea(const uint64_t currTime, const struct perf_event_attr *const pea, int key);
+ void marshalKeys(const uint64_t currTime, const int count, const __u64 *const ids, const int *const keys);
+ void marshalKeysOld(const uint64_t currTime, const int keyCount, const int *const keys, const int bytes, const char *const buf);
+ void marshalFormat(const uint64_t currTime, const int length, const char *const format);
+ void marshalMaps(const uint64_t currTime, const int pid, const int tid, const char *const maps);
+ void marshalComm(const uint64_t currTime, const int pid, const int tid, const char *const image, const char *const comm);
+ void onlineCPU(const uint64_t currTime, const int cpu);
+ void offlineCPU(const uint64_t currTime, const int cpu);
+ void marshalKallsyms(const uint64_t currTime, const char *const kallsyms);
+ void perfCounterHeader(const uint64_t time);
+ void perfCounter(const int core, const int key, const int64_t value);
+ void perfCounterFooter(const uint64_t currTime);
+
+ void setDone();
+ bool isDone() const;
+
+ // Prefer a new member to using these functions if possible
+ char *getWritePos() { return mBuf + mWritePos; }
+ void advanceWrite(int bytes) { mWritePos = (mWritePos + bytes) & /*mask*/(mSize - 1); }
+ static void packInt(char *const buf, const int size, int &writePos, int32_t x);
+ void packInt(int32_t x);
+ static void packInt64(char *const buf, const int size, int &writePos, int64_t x);
+ void packInt64(int64_t x);
+ void writeBytes(const void *const data, size_t count);
+ void writeString(const char *const str);
+
+ static void writeLEInt(unsigned char *buf, int v) {
+ buf[0] = (v >> 0) & 0xFF;
+ buf[1] = (v >> 8) & 0xFF;
+ buf[2] = (v >> 16) & 0xFF;
+ buf[3] = (v >> 24) & 0xFF;
+ }
+
+private:
+ void frame();
+ bool commitReady() const;
+ bool checkSpace(int bytes);
+
+ char *const mBuf;
+ sem_t *const mReaderSem;
+ uint64_t mCommitTime;
+ sem_t mWriterSem;
+ const int mSize;
+ int mReadPos;
+ int mWritePos;
+ int mCommitPos;
+ bool mAvailable;
+ bool mIsDone;
+ const int32_t mCore;
+ const int32_t mBufType;
+
+ // Intentionally unimplemented
+ Buffer(const Buffer &);
+ Buffer &operator=(const Buffer &);
+};
+
+#endif // BUFFER_H
diff --git a/tools/gator/daemon/CCNDriver.cpp b/tools/gator/daemon/CCNDriver.cpp
new file mode 100644
index 0000000..d77513a
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.cpp
@@ -0,0 +1,294 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CCNDriver.h"
+
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "k/perf_event.h"
+
+#include "Config.h"
+#include "DriverSource.h"
+#include "Logging.h"
+
+static const char TAG_CATEGORY[] = "category";
+static const char TAG_COUNTER_SET[] = "counter_set";
+static const char TAG_EVENT[] = "event";
+static const char TAG_OPTION[] = "option";
+static const char TAG_OPTION_SET[] = "option_set";
+
+static const char ATTR_AVERAGE_SELECTION[] = "average_selection";
+static const char ATTR_COUNTER[] = "counter";
+static const char ATTR_COUNT[] = "count";
+static const char ATTR_DESCRIPTION[] = "description";
+static const char ATTR_DISPLAY[] = "display";
+static const char ATTR_EVENT[] = "event";
+static const char ATTR_EVENT_DELTA[] = "event_delta";
+static const char ATTR_NAME[] = "name";
+static const char ATTR_OPTION_SET[] = "option_set";
+static const char ATTR_TITLE[] = "title";
+static const char ATTR_UNITS[] = "units";
+
+static const char XP_REGION[] = "XP_Region";
+static const char HNF_REGION[] = "HN-F_Region";
+static const char RNI_REGION[] = "RN-I_Region";
+static const char SBAS_REGION[] = "SBAS_Region";
+static const char CCN_5XX[] = "CCN-5xx";
+#define ARM_CCN_5XX "ARM_CCN_5XX_"
+
+static const char *const VC_TYPES[] = { "REQ", "RSP", "SNP", "DAT" };
+static const char *const XP_EVENT_NAMES[] = { NULL, "H-bit", "S-bit", "P-Cnt", "TknV" };
+static const char *const XP_EVENT_DESCRIPTIONS[] = { NULL, "Set H-bit, signaled when this XP sets the H-bit.", "Set S-bit, signaled when this XP sets the S-bit.", "Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC.", "No TknV, signaled when this XP transmits a valid packet." };
+static const char *const HNF_EVENT_NAMES[] = { NULL, "Cache Miss", "L3 SF Cache Access", "Cache Fill", "POCQ Retry", "POCQ Reqs Recvd", "SF Hit", "SF Evictions", "Snoops Sent", "Snoops Broadcast", "L3 Eviction", "L3 Fill Invalid Way", "MC Retries", "MC Reqs", "QOS HH Retry" };
+static const char *const HNF_EVENT_DESCRIPTIONS[] = { NULL, "Counts the total cache misses. This is the first time lookup result, and is high priority.", "Counts the number of cache accesses. This is the first time access, and is high priority.", "Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache.", "Counts the number of requests that have been retried.", "Counts the number of requests received by HN.", "Counts the number of snoop filter hits.", "Counts the number of snoop filter evictions. Cache invalidations are initiated.", "Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops.", "Counts the number of snoop broadcasts sent.", "Counts the number of L3 evictions.", "Counts the number of L3 fills to an invalid way.", "Counts the number of transactions retried by the memory controller.", "Counts the number of requests to the memory controller.", "Counts the number of times a highest-priority QoS class was retried at the HN-F." };
+static const char *const RNI_EVENT_NAMES[] = { NULL, "S0 RDataBeats", "S1 RDataBeats", "S2 RDataBeats", "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const RNI_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", "S1 RDataBeats.", "S2 RDataBeats.", "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+static const char *const SBAS_EVENT_NAMES[] = { NULL, "S0 RDataBeats", NULL, NULL, "RXDAT Flits received", "TXDAT Flits sent", "Total TXREQ Flits sent", "Retried TXREQ Flits sent", "RRT full", "WRT full", "Replayed TXREQ Flits" };
+static const char *const SBAS_EVENT_DESCRIPTIONS[] = { NULL, "S0 RDataBeats.", NULL, NULL, "RXDAT Flits received.", "TXDAT Flits sent.", "Total TXREQ Flits sent.", "Retried TXREQ Flits sent.", "RRT full.", "WRT full.", "Replayed TXREQ Flits." };
+
+// This class is used only to poll for CCN-5xx configuration and emit events XML for it. All other operations are handled by PerfDriver
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+ return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+}
+
+static unsigned int getConfig(unsigned int node, unsigned int type, unsigned int event, unsigned int port, unsigned int vc) {
+ return
+ ((node & 0xff) << 0) |
+ ((type & 0xff) << 8) |
+ ((event & 0xff) << 16) |
+ ((port & 0x03) << 24) |
+ ((vc & 0x07) << 26) |
+ 0;
+}
+
+static bool perfPoll(struct perf_event_attr *const pea) {
+ int fd = sys_perf_event_open(pea, -1, 0, -1, 0);
+ if (fd < 0) {
+ return false;
+ }
+ close(fd);
+ return true;
+}
+
+CCNDriver::CCNDriver() : mNodeTypes(NULL), mXpCount(0) {
+}
+
+CCNDriver::~CCNDriver() {
+ delete mNodeTypes;
+}
+
+bool CCNDriver::claimCounter(const Counter &) const {
+ // Handled by PerfDriver
+ return false;
+}
+
+void CCNDriver::resetCounters() {
+ // Handled by PerfDriver
+}
+
+void CCNDriver::setupCounter(Counter &) {
+ // Handled by PerfDriver
+}
+
+void CCNDriver::readEvents(mxml_node_t *const) {
+ struct stat st;
+ if (stat("/sys/bus/event_source/devices/ccn", &st) != 0) {
+ // Not found
+ return;
+ }
+
+ int type;
+ if (DriverSource::readIntDriver("/sys/bus/event_source/devices/ccn/type", &type) != 0) {
+ logg->logError("Unable to read CCN-5xx type");
+ handleException();
+ }
+
+ // Detect number of xps
+ struct perf_event_attr pea;
+ memset(&pea, 0, sizeof(pea));
+ pea.type = type;
+ pea.size = sizeof(pea);
+
+ mXpCount = 1;
+ while (true) {
+ pea.config = getConfig(0, 0x08, 1, 0, 1) | mXpCount;
+ if (!perfPoll(&pea)) {
+ break;
+ }
+ mXpCount *= 2;
+ };
+ {
+ int lower = mXpCount/2 + 1;
+ while (lower < mXpCount) {
+ int mid = (lower + mXpCount)/2;
+ pea.config = getConfig(0, 0x08, 1, 0, 1) | mid;
+ if (perfPoll(&pea)) {
+ lower = mid + 1;
+ } else {
+ mXpCount = mid;
+ }
+ }
+ }
+
+ mNodeTypes = new NodeType[2*mXpCount];
+
+ // Detect node types
+ for (int i = 0; i < 2*mXpCount; ++i) {
+ pea.config = getConfig(0, 0x04, 1, 0, 0) | i;
+ if (perfPoll(&pea)) {
+ mNodeTypes[i] = NT_HNF;
+ continue;
+ }
+
+ pea.config = getConfig(0, 0x16, 1, 0, 0) | i;
+ if (perfPoll(&pea)) {
+ mNodeTypes[i] = NT_RNI;
+ continue;
+ }
+
+ pea.config = getConfig(0, 0x10, 1, 0, 0) | i;
+ if (perfPoll(&pea)) {
+ mNodeTypes[i] = NT_SBAS;
+ continue;
+ }
+
+ mNodeTypes[i] = NT_UNKNOWN;
+ }
+}
+
+int CCNDriver::writeCounters(mxml_node_t *const) const {
+ // Handled by PerfDriver
+ return 0;
+}
+
+void CCNDriver::writeEvents(mxml_node_t *const root) const {
+ mxml_node_t *const counter_set = mxmlNewElement(root, TAG_COUNTER_SET);
+ mxmlElementSetAttr(counter_set, ATTR_NAME, ARM_CCN_5XX "cnt");
+ mxmlElementSetAttr(counter_set, ATTR_COUNT, "8");
+
+ mxml_node_t *const category = mxmlNewElement(root, TAG_CATEGORY);
+ mxmlElementSetAttr(category, ATTR_NAME, CCN_5XX);
+ mxmlElementSetAttr(category, TAG_COUNTER_SET, ARM_CCN_5XX "cnt");
+
+ mxml_node_t *const clock_event = mxmlNewElement(category, TAG_EVENT);
+ mxmlElementSetAttr(clock_event, ATTR_COUNTER, ARM_CCN_5XX "ccnt");
+ mxmlElementSetAttr(clock_event, ATTR_EVENT, "0xff00");
+ mxmlElementSetAttr(clock_event, ATTR_TITLE, "CCN-5xx Clock");
+ mxmlElementSetAttr(clock_event, ATTR_NAME, "Cycles");
+ mxmlElementSetAttr(clock_event, ATTR_DISPLAY, "hertz");
+ mxmlElementSetAttr(clock_event, ATTR_UNITS, "Hz");
+ mxmlElementSetAttr(clock_event, ATTR_AVERAGE_SELECTION, "yes");
+ mxmlElementSetAttr(clock_event, ATTR_DESCRIPTION, "The number of core clock cycles");
+
+ mxml_node_t *const xp_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+ mxmlElementSetAttr(xp_option_set, ATTR_NAME, XP_REGION);
+
+ for (int i = 0; i < mXpCount; ++i) {
+ mxml_node_t *const option = mxmlNewElement(xp_option_set, TAG_OPTION);
+ mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+ mxmlElementSetAttrf(option, ATTR_NAME, "XP %i", i);
+ mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Crosspoint %i", i);
+ }
+
+ for (int vc = 0; vc < ARRAY_LENGTH(VC_TYPES); ++vc) {
+ if (VC_TYPES[vc] == NULL) {
+ continue;
+ }
+ for (int bus = 0; bus < 2; ++bus) {
+ for (int eventId = 0; eventId < ARRAY_LENGTH(XP_EVENT_NAMES); ++eventId) {
+ if (XP_EVENT_NAMES[eventId] == NULL) {
+ continue;
+ }
+ mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+ mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x08, eventId, bus, vc));
+ mxmlElementSetAttr(event, ATTR_OPTION_SET, XP_REGION);
+ mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+ mxmlElementSetAttrf(event, ATTR_NAME, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_NAMES[eventId]);
+ mxmlElementSetAttrf(event, ATTR_DESCRIPTION, "Bus %i: %s: %s", bus, VC_TYPES[vc], XP_EVENT_DESCRIPTIONS[eventId]);
+ }
+ }
+ }
+
+ mxml_node_t *const hnf_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+ mxmlElementSetAttr(hnf_option_set, ATTR_NAME, HNF_REGION);
+
+ for (int eventId = 0; eventId < ARRAY_LENGTH(HNF_EVENT_NAMES); ++eventId) {
+ if (HNF_EVENT_NAMES[eventId] == NULL) {
+ continue;
+ }
+ mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+ mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x04, eventId, 0, 0));
+ mxmlElementSetAttr(event, ATTR_OPTION_SET, HNF_REGION);
+ mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+ mxmlElementSetAttr(event, ATTR_NAME, HNF_EVENT_NAMES[eventId]);
+ mxmlElementSetAttr(event, ATTR_DESCRIPTION, HNF_EVENT_DESCRIPTIONS[eventId]);
+ }
+
+ mxml_node_t *const rni_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+ mxmlElementSetAttr(rni_option_set, ATTR_NAME, RNI_REGION);
+
+ for (int eventId = 0; eventId < ARRAY_LENGTH(RNI_EVENT_NAMES); ++eventId) {
+ if (RNI_EVENT_NAMES[eventId] == NULL) {
+ continue;
+ }
+ mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+ mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x16, eventId, 0, 0));
+ mxmlElementSetAttr(event, ATTR_OPTION_SET, RNI_REGION);
+ mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+ mxmlElementSetAttr(event, ATTR_NAME, RNI_EVENT_NAMES[eventId]);
+ mxmlElementSetAttr(event, ATTR_DESCRIPTION, RNI_EVENT_DESCRIPTIONS[eventId]);
+ }
+
+ mxml_node_t *const sbas_option_set = mxmlNewElement(category, TAG_OPTION_SET);
+ mxmlElementSetAttr(sbas_option_set, ATTR_NAME, SBAS_REGION);
+
+ for (int eventId = 0; eventId < ARRAY_LENGTH(SBAS_EVENT_NAMES); ++eventId) {
+ if (SBAS_EVENT_NAMES[eventId] == NULL) {
+ continue;
+ }
+ mxml_node_t *const event = mxmlNewElement(category, TAG_EVENT);
+ mxmlElementSetAttrf(event, ATTR_EVENT, "0x%x", getConfig(0, 0x10, eventId, 0, 0));
+ mxmlElementSetAttr(event, ATTR_OPTION_SET, SBAS_REGION);
+ mxmlElementSetAttr(event, ATTR_TITLE, CCN_5XX);
+ mxmlElementSetAttr(event, ATTR_NAME, SBAS_EVENT_NAMES[eventId]);
+ mxmlElementSetAttr(event, ATTR_DESCRIPTION, SBAS_EVENT_DESCRIPTIONS[eventId]);
+ }
+
+ for (int i = 0; i < 2*mXpCount; ++i) {
+ switch (mNodeTypes[i]) {
+ case NT_HNF: {
+ mxml_node_t *const option = mxmlNewElement(hnf_option_set, TAG_OPTION);
+ mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+ mxmlElementSetAttrf(option, ATTR_NAME, "HN-F %i", i);
+ mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "Fully-coherent Home Node %i", i);
+ break;
+ }
+ case NT_RNI: {
+ mxml_node_t *const option = mxmlNewElement(rni_option_set, TAG_OPTION);
+ mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+ mxmlElementSetAttrf(option, ATTR_NAME, "RN-I %i", i);
+ mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "I/O-coherent Requesting Node %i", i);
+ break;
+ }
+ case NT_SBAS: {
+ mxml_node_t *const option = mxmlNewElement(sbas_option_set, TAG_OPTION);
+ mxmlElementSetAttrf(option, ATTR_EVENT_DELTA, "0x%x", getConfig(i, 0, 0, 0, 0));
+ mxmlElementSetAttrf(option, ATTR_NAME, "SBAS %i", i);
+ mxmlElementSetAttrf(option, ATTR_DESCRIPTION, "ACE master to CHI protocol bridge %i", i);
+ break;
+ }
+ default:
+ continue;
+ }
+ }
+}
diff --git a/tools/gator/daemon/CCNDriver.h b/tools/gator/daemon/CCNDriver.h
new file mode 100644
index 0000000..06ac33f
--- /dev/null
+++ b/tools/gator/daemon/CCNDriver.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CCNDRIVER_H
+#define CCNDRIVER_H
+
+#include "Driver.h"
+
+class CCNDriver : public Driver {
+public:
+ CCNDriver();
+ ~CCNDriver();
+
+ bool claimCounter(const Counter &counter) const;
+ void resetCounters();
+ void setupCounter(Counter &counter);
+
+ void readEvents(mxml_node_t *const);
+ int writeCounters(mxml_node_t *const root) const;
+ void writeEvents(mxml_node_t *const) const;
+
+private:
+ enum NodeType {
+ NT_UNKNOWN,
+ NT_HNF,
+ NT_RNI,
+ NT_SBAS,
+ };
+
+ NodeType *mNodeTypes;
+ int mXpCount;
+
+ // Intentionally unimplemented
+ CCNDriver(const CCNDriver &);
+ CCNDriver &operator=(const CCNDriver &);
+};
+
+#endif // CCNDRIVER_H
diff --git a/tools/gator/daemon/COPYING b/tools/gator/daemon/COPYING
new file mode 100644
index 0000000..d159169
--- /dev/null
+++ b/tools/gator/daemon/COPYING
@@ -0,0 +1,339 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License along
+ with this program; if not, write to the Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.
diff --git a/tools/gator/daemon/CapturedXML.cpp b/tools/gator/daemon/CapturedXML.cpp
new file mode 100644
index 0000000..1854c77
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.cpp
@@ -0,0 +1,144 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "CapturedXML.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <dirent.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+
+CapturedXML::CapturedXML() {
+}
+
+CapturedXML::~CapturedXML() {
+}
+
+mxml_node_t* CapturedXML::getTree(bool includeTime) {
+ mxml_node_t *xml;
+ mxml_node_t *captured;
+ mxml_node_t *target;
+ int x;
+
+ xml = mxmlNewXML("1.0");
+
+ captured = mxmlNewElement(xml, "captured");
+ mxmlElementSetAttr(captured, "version", "1");
+ if (gSessionData->perf.isSetup()) {
+ mxmlElementSetAttr(captured, "type", "Perf");
+ }
+ mxmlElementSetAttrf(captured, "protocol", "%d", PROTOCOL_VERSION);
+ if (includeTime) { // Send the following only after the capture is complete
+ if (time(NULL) > 1267000000) { // If the time is reasonable (after Feb 23, 2010)
+ mxmlElementSetAttrf(captured, "created", "%lu", time(NULL)); // Valid until the year 2038
+ }
+ }
+
+ target = mxmlNewElement(captured, "target");
+ mxmlElementSetAttr(target, "name", gSessionData->mCoreName);
+ mxmlElementSetAttrf(target, "sample_rate", "%d", gSessionData->mSampleRate);
+ mxmlElementSetAttrf(target, "cores", "%d", gSessionData->mCores);
+ mxmlElementSetAttrf(target, "cpuid", "0x%x", gSessionData->mMaxCpuId);
+
+ if (!gSessionData->mOneShot && (gSessionData->mSampleRate > 0)) {
+ mxmlElementSetAttr(target, "supports_live", "yes");
+ }
+
+ if (gSessionData->mLocalCapture) {
+ mxmlElementSetAttr(target, "local_capture", "yes");
+ }
+
+ mxml_node_t *counters = NULL;
+ for (x = 0; x < MAX_PERFORMANCE_COUNTERS; x++) {
+ const Counter & counter = gSessionData->mCounters[x];
+ if (counter.isEnabled()) {
+ if (counters == NULL) {
+ counters = mxmlNewElement(captured, "counters");
+ }
+ mxml_node_t *const node = mxmlNewElement(counters, "counter");
+ mxmlElementSetAttrf(node, "key", "0x%x", counter.getKey());
+ mxmlElementSetAttr(node, "type", counter.getType());
+ if (counter.getEvent() != -1) {
+ mxmlElementSetAttrf(node, "event", "0x%x", counter.getEvent());
+ }
+ if (counter.getCount() > 0) {
+ mxmlElementSetAttrf(node, "count", "%d", counter.getCount());
+ }
+ if (counter.getCores() > 0) {
+ mxmlElementSetAttrf(node, "cores", "%d", counter.getCores());
+ }
+ }
+ }
+
+ return xml;
+}
+
+char* CapturedXML::getXML(bool includeTime) {
+ char* xml_string;
+ mxml_node_t *xml = getTree(includeTime);
+ xml_string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+ mxmlDelete(xml);
+ return xml_string;
+}
+
+void CapturedXML::write(char* path) {
+ char file[PATH_MAX];
+
+ // Set full path
+ snprintf(file, PATH_MAX, "%s/captured.xml", path);
+
+ char* xml = getXML(true);
+ if (util->writeToDisk(file, xml) < 0) {
+ logg->logError("Error writing %s\nPlease verify the path.", file);
+ handleException();
+ }
+
+ free(xml);
+}
+
+// whitespace callback utility function used with mini-xml
+const char * mxmlWhitespaceCB(mxml_node_t *node, int loc) {
+ const char *name;
+
+ name = mxmlGetElement(node);
+
+ if (loc == MXML_WS_BEFORE_OPEN) {
+ // Single indentation
+ if (!strcmp(name, "target") || !strcmp(name, "counters"))
+ return "\n ";
+
+ // Double indentation
+ if (!strcmp(name, "counter"))
+ return "\n ";
+
+ // Avoid a carriage return on the first line of the xml file
+ if (!strncmp(name, "?xml", 4))
+ return NULL;
+
+ // Default - no indentation
+ return "\n";
+ }
+
+ if (loc == MXML_WS_BEFORE_CLOSE) {
+ // No indentation
+ if (!strcmp(name, "captured"))
+ return "\n";
+
+ // Single indentation
+ if (!strcmp(name, "counters"))
+ return "\n ";
+
+ // Default - no carriage return
+ return NULL;
+ }
+
+ return NULL;
+}
diff --git a/tools/gator/daemon/CapturedXML.h b/tools/gator/daemon/CapturedXML.h
new file mode 100644
index 0000000..69d80c0
--- /dev/null
+++ b/tools/gator/daemon/CapturedXML.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CAPTURED_XML_H__
+#define __CAPTURED_XML_H__
+
+#include "mxml/mxml.h"
+
+class CapturedXML {
+public:
+ CapturedXML();
+ ~CapturedXML();
+ char* getXML(bool includeTime); // the string should be freed by the caller
+ void write(char* path);
+private:
+ mxml_node_t* getTree(bool includeTime);
+};
+
+const char * mxmlWhitespaceCB(mxml_node_t *node, int where);
+
+#endif //__CAPTURED_XML_H__
diff --git a/tools/gator/daemon/Child.cpp b/tools/gator/daemon/Child.cpp
new file mode 100644
index 0000000..a19e9cf
--- /dev/null
+++ b/tools/gator/daemon/Child.cpp
@@ -0,0 +1,393 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Child.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <sys/prctl.h>
+
+#include "CapturedXML.h"
+#include "Command.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "DriverSource.h"
+#include "ExternalSource.h"
+#include "FtraceSource.h"
+#include "LocalCapture.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "PerfSource.h"
+#include "Sender.h"
+#include "SessionData.h"
+#include "StreamlineSetup.h"
+#include "UserSpaceSource.h"
+
+static sem_t haltPipeline, senderThreadStarted, startProfile, senderSem; // Shared by Child and spawned threads
+static Source *primarySource = NULL;
+static Source *externalSource = NULL;
+static Source *userSpaceSource = NULL;
+static Source *ftraceSource = NULL;
+static Sender* sender = NULL; // Shared by Child.cpp and spawned threads
+Child* child = NULL; // shared by Child.cpp and main.cpp
+
+extern void cleanUp();
+void handleException() {
+ if (child && child->numExceptions++ > 0) {
+ // it is possible one of the below functions itself can cause an exception, thus allow only one exception
+ logg->logMessage("Received multiple exceptions, terminating the child");
+ exit(1);
+ }
+ fprintf(stderr, "%s", logg->getLastError());
+
+ if (child && child->socket) {
+ if (sender) {
+ // send the error, regardless of the command sent by Streamline
+ sender->writeData(logg->getLastError(), strlen(logg->getLastError()), RESPONSE_ERROR);
+
+ // cannot close the socket before Streamline issues the command, so wait for the command before exiting
+ if (gSessionData->mWaitingOnCommand) {
+ char discard;
+ child->socket->receiveNBytes(&discard, 1);
+ }
+
+ // Ensure all data is flushed
+ child->socket->shutdownConnection();
+
+ // this indirectly calls close socket which will ensure the data has been sent
+ delete sender;
+ }
+ }
+
+ if (gSessionData->mLocalCapture)
+ cleanUp();
+
+ exit(1);
+}
+
+// CTRL C Signal Handler for child process
+static void child_handler(int signum) {
+ static bool beenHere = false;
+ if (beenHere == true) {
+ logg->logMessage("Gator is being forced to shut down.");
+ exit(1);
+ }
+ beenHere = true;
+ logg->logMessage("Gator is shutting down.");
+ if (signum == SIGALRM || !primarySource) {
+ exit(1);
+ } else {
+ child->endSession();
+ alarm(5); // Safety net in case endSession does not complete within 5 seconds
+ }
+}
+
+static void *durationThread(void *) {
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-duration", 0, 0, 0);
+ sem_wait(&startProfile);
+ if (gSessionData->mSessionIsActive) {
+ // Time out after duration seconds
+ // Add a second for host-side filtering
+ sleep(gSessionData->mDuration + 1);
+ if (gSessionData->mSessionIsActive) {
+ logg->logMessage("Duration expired.");
+ child->endSession();
+ }
+ }
+ logg->logMessage("Exit duration thread");
+ return 0;
+}
+
+static void *stopThread(void *) {
+ OlySocket* socket = child->socket;
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-stopper", 0, 0, 0);
+ while (gSessionData->mSessionIsActive) {
+ // This thread will stall until the APC_STOP or PING command is received over the socket or the socket is disconnected
+ unsigned char header[5];
+ const int result = socket->receiveNBytes((char*)&header, sizeof(header));
+ const char type = header[0];
+ const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+ if (result == -1) {
+ child->endSession();
+ } else if (result > 0) {
+ if ((type != COMMAND_APC_STOP) && (type != COMMAND_PING)) {
+ logg->logMessage("INVESTIGATE: Received unknown command type %d", type);
+ } else {
+ // verify a length of zero
+ if (length == 0) {
+ if (type == COMMAND_APC_STOP) {
+ logg->logMessage("Stop command received.");
+ child->endSession();
+ } else {
+ // Ping is used to make sure gator is alive and requires an ACK as the response
+ logg->logMessage("Ping command received.");
+ sender->writeData(NULL, 0, RESPONSE_ACK);
+ }
+ } else {
+ logg->logMessage("INVESTIGATE: Received stop command but with length = %d", length);
+ }
+ }
+ }
+ }
+
+ logg->logMessage("Exit stop thread");
+ return 0;
+}
+
+static void *senderThread(void *) {
+ char end_sequence[] = {RESPONSE_APC_DATA, 0, 0, 0, 0};
+
+ sem_post(&senderThreadStarted);
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-sender", 0, 0, 0);
+ sem_wait(&haltPipeline);
+
+ while (!externalSource->isDone() ||
+ (userSpaceSource != NULL && !userSpaceSource->isDone()) ||
+ (ftraceSource != NULL && !ftraceSource->isDone()) ||
+ !primarySource->isDone()) {
+ sem_wait(&senderSem);
+
+ externalSource->write(sender);
+ if (userSpaceSource != NULL) {
+ userSpaceSource->write(sender);
+ }
+ if (ftraceSource != NULL) {
+ ftraceSource->write(sender);
+ }
+ primarySource->write(sender);
+ }
+
+ // write end-of-capture sequence
+ if (!gSessionData->mLocalCapture) {
+ sender->writeData(end_sequence, sizeof(end_sequence), RESPONSE_APC_DATA);
+ }
+
+ logg->logMessage("Exit sender thread");
+ return 0;
+}
+
+Child::Child() {
+ initialization();
+ gSessionData->mLocalCapture = true;
+}
+
+Child::Child(OlySocket* sock, int conn) {
+ initialization();
+ socket = sock;
+ mNumConnections = conn;
+}
+
+Child::~Child() {
+}
+
+void Child::initialization() {
+ // Set up different handlers for signals
+ gSessionData->mSessionIsActive = true;
+ signal(SIGINT, child_handler);
+ signal(SIGTERM, child_handler);
+ signal(SIGABRT, child_handler);
+ signal(SIGALRM, child_handler);
+ socket = NULL;
+ numExceptions = 0;
+ mNumConnections = 0;
+
+ // Initialize semaphores
+ sem_init(&senderThreadStarted, 0, 0);
+ sem_init(&startProfile, 0, 0);
+ sem_init(&senderSem, 0, 0);
+}
+
+void Child::endSession() {
+ gSessionData->mSessionIsActive = false;
+ primarySource->interrupt();
+ externalSource->interrupt();
+ if (userSpaceSource != NULL) {
+ userSpaceSource->interrupt();
+ }
+ if (ftraceSource != NULL) {
+ ftraceSource->interrupt();
+ }
+ sem_post(&haltPipeline);
+}
+
+void Child::run() {
+ LocalCapture* localCapture = NULL;
+ pthread_t durationThreadID, stopThreadID, senderThreadID;
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-child", 0, 0, 0);
+
+ // Disable line wrapping when generating xml files; carriage returns and indentation to be added manually
+ mxmlSetWrapMargin(0);
+
+ // Instantiate the Sender - must be done first, after which error messages can be sent
+ sender = new Sender(socket);
+
+ if (mNumConnections > 1) {
+ logg->logError("Session already in progress");
+ handleException();
+ }
+
+ // Populate gSessionData with the configuration
+ { ConfigurationXML configuration; }
+
+ // Set up the driver; must be done after gSessionData->mPerfCounterType[] is populated
+ if (!gSessionData->perf.isSetup()) {
+ primarySource = new DriverSource(&senderSem, &startProfile);
+ } else {
+ primarySource = new PerfSource(&senderSem, &startProfile);
+ }
+
+ // Initialize all drivers
+ for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+ driver->resetCounters();
+ }
+
+ // Set up counters using the associated driver's setup function
+ for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+ Counter & counter = gSessionData->mCounters[i];
+ if (counter.isEnabled()) {
+ counter.getDriver()->setupCounter(counter);
+ }
+ }
+
+ // Start up and parse session xml
+ if (socket) {
+ // Respond to Streamline requests
+ StreamlineSetup ss(socket);
+ } else {
+ char* xmlString;
+ xmlString = util->readFromDisk(gSessionData->mSessionXMLPath);
+ if (xmlString == 0) {
+ logg->logError("Unable to read session xml file: %s", gSessionData->mSessionXMLPath);
+ handleException();
+ }
+ gSessionData->parseSessionXML(xmlString);
+ localCapture = new LocalCapture();
+ localCapture->createAPCDirectory(gSessionData->mTargetPath);
+ localCapture->copyImages(gSessionData->mImages);
+ localCapture->write(xmlString);
+ sender->createDataFile(gSessionData->mAPCDir);
+ free(xmlString);
+ }
+
+ if (gSessionData->kmod.isMaliCapture() && (gSessionData->mSampleRate == 0)) {
+ logg->logError("Mali counters are not supported with Sample Rate: None.");
+ handleException();
+ }
+
+ // Initialize ftrace source before child as it's slow and dependens on nothing else
+ // If initialized later, us gator with ftrace has time sync issues
+ if (gSessionData->ftraceDriver.countersEnabled()) {
+ ftraceSource = new FtraceSource(&senderSem);
+ if (!ftraceSource->prepare()) {
+ logg->logError("Unable to prepare userspace source for capture");
+ handleException();
+ }
+ ftraceSource->start();
+ }
+
+ // Must be after session XML is parsed
+ if (!primarySource->prepare()) {
+ if (gSessionData->perf.isSetup()) {
+ logg->logError("Unable to communicate with the perf API, please ensure that CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER are enabled. Please refer to README_Streamline.txt for more information.");
+ } else {
+ logg->logError("Unable to prepare gator driver for capture");
+ }
+ handleException();
+ }
+
+ // Sender thread shall be halted until it is signaled for one shot mode
+ sem_init(&haltPipeline, 0, gSessionData->mOneShot ? 0 : 2);
+
+ // Must be initialized before senderThread is started as senderThread checks externalSource
+ externalSource = new ExternalSource(&senderSem);
+ if (!externalSource->prepare()) {
+ logg->logError("Unable to prepare external source for capture");
+ handleException();
+ }
+ externalSource->start();
+
+ // Create the duration, stop, and sender threads
+ bool thread_creation_success = true;
+ if (gSessionData->mDuration > 0 && pthread_create(&durationThreadID, NULL, durationThread, NULL)) {
+ thread_creation_success = false;
+ } else if (socket && pthread_create(&stopThreadID, NULL, stopThread, NULL)) {
+ thread_creation_success = false;
+ } else if (pthread_create(&senderThreadID, NULL, senderThread, NULL)) {
+ thread_creation_success = false;
+ }
+
+ bool startUSSource = false;
+ for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+ if (gSessionData->usDrivers[i]->countersEnabled()) {
+ startUSSource = true;
+ }
+ }
+ if (startUSSource) {
+ userSpaceSource = new UserSpaceSource(&senderSem);
+ if (!userSpaceSource->prepare()) {
+ logg->logError("Unable to prepare userspace source for capture");
+ handleException();
+ }
+ userSpaceSource->start();
+ }
+
+ if (gSessionData->mAllowCommands && (gSessionData->mCaptureCommand != NULL)) {
+ pthread_t thread;
+ if (pthread_create(&thread, NULL, commandThread, NULL)) {
+ thread_creation_success = false;
+ }
+ }
+
+ if (!thread_creation_success) {
+ logg->logError("Failed to create gator threads");
+ handleException();
+ }
+
+ // Wait until thread has started
+ sem_wait(&senderThreadStarted);
+
+ // Start profiling
+ primarySource->run();
+
+ // Wait for the other threads to exit
+ if (ftraceSource != NULL) {
+ ftraceSource->join();
+ }
+ if (userSpaceSource != NULL) {
+ userSpaceSource->join();
+ }
+ externalSource->join();
+ pthread_join(senderThreadID, NULL);
+
+ // Shutting down the connection should break the stop thread which is stalling on the socket recv() function
+ if (socket) {
+ logg->logMessage("Waiting on stop thread");
+ socket->shutdownConnection();
+ pthread_join(stopThreadID, NULL);
+ }
+
+ // Write the captured xml file
+ if (gSessionData->mLocalCapture) {
+ CapturedXML capturedXML;
+ capturedXML.write(gSessionData->mAPCDir);
+ }
+
+ logg->logMessage("Profiling ended.");
+
+ delete ftraceSource;
+ delete userSpaceSource;
+ delete externalSource;
+ delete primarySource;
+ delete sender;
+ delete localCapture;
+}
diff --git a/tools/gator/daemon/Child.h b/tools/gator/daemon/Child.h
new file mode 100644
index 0000000..a6c54db
--- /dev/null
+++ b/tools/gator/daemon/Child.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __CHILD_H__
+#define __CHILD_H__
+
+class OlySocket;
+
+class Child {
+public:
+ Child();
+ Child(OlySocket* sock, int numConnections);
+ ~Child();
+ void run();
+ OlySocket *socket;
+ void endSession();
+ int numExceptions;
+private:
+ int mNumConnections;
+
+ void initialization();
+
+ // Intentionally unimplemented
+ Child(const Child &);
+ Child &operator=(const Child &);
+};
+
+#endif //__CHILD_H__
diff --git a/tools/gator/daemon/Command.cpp b/tools/gator/daemon/Command.cpp
new file mode 100644
index 0000000..0a6e3b9
--- /dev/null
+++ b/tools/gator/daemon/Command.cpp
@@ -0,0 +1,172 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Command.h"
+
+#include <fcntl.h>
+#include <pwd.h>
+#include <stdio.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+static int getUid(const char *const name, char *const shPath, const char *const tmpDir) {
+ // Lookups may fail when using a different libc or a statically compiled executable
+ char gatorTemp[32];
+ snprintf(gatorTemp, sizeof(gatorTemp), "%s/gator_temp", tmpDir);
+
+ const int fd = open(gatorTemp, 600, O_CREAT | O_CLOEXEC);
+ if (fd < 0) {
+ return -1;
+ }
+ close(fd);
+
+ char cmd[128];
+ snprintf(cmd, sizeof(cmd), "chown %s %s || rm %s", name, gatorTemp, gatorTemp);
+
+ const int pid = fork();
+ if (pid < 0) {
+ logg->logError("fork failed");
+ handleException();
+ }
+ if (pid == 0) {
+ char cargv1[] = "-c";
+ char *cargv[] = {
+ shPath,
+ cargv1,
+ cmd,
+ NULL,
+ };
+
+ execv(cargv[0], cargv);
+ exit(-1);
+ }
+ while ((waitpid(pid, NULL, 0) < 0) && (errno == EINTR));
+
+ struct stat st;
+ int result = -1;
+ if (stat(gatorTemp, &st) == 0) {
+ result = st.st_uid;
+ }
+ unlink(gatorTemp);
+ return result;
+}
+
+static int getUid(const char *const name) {
+ // Look up the username
+ struct passwd *const user = getpwnam(name);
+ if (user != NULL) {
+ return user->pw_uid;
+ }
+
+
+ // Are we on Linux
+ char cargv0l[] = "/bin/sh";
+ if ((access(cargv0l, X_OK) == 0) && (access("/tmp", W_OK) == 0)) {
+ return getUid(name, cargv0l, "/tmp");
+ }
+
+ // Are we on android
+ char cargv0a[] = "/system/bin/sh";
+ if ((access(cargv0a, X_OK) == 0) && (access("/data", W_OK) == 0)) {
+ return getUid(name, cargv0a, "/data");
+ }
+
+ return -1;
+}
+
+void *commandThread(void *) {
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-command", 0, 0, 0);
+
+ const char *const name = gSessionData->mCaptureUser == NULL ? "nobody" : gSessionData->mCaptureUser;
+ const int uid = getUid(name);
+ if (uid < 0) {
+ logg->logError("Unable to look up the user %s, please double check that the user exists", name);
+ handleException();
+ }
+
+ sleep(3);
+
+ char buf[128];
+ int pipefd[2];
+ if (pipe_cloexec(pipefd) != 0) {
+ logg->logError("pipe failed");
+ handleException();
+ }
+
+ const int pid = fork();
+ if (pid < 0) {
+ logg->logError("fork failed");
+ handleException();
+ }
+ if (pid == 0) {
+ char cargv0l[] = "/bin/sh";
+ char cargv0a[] = "/system/bin/sh";
+ char cargv1[] = "-c";
+ char *cargv[] = {
+ cargv0l,
+ cargv1,
+ gSessionData->mCaptureCommand,
+ NULL,
+ };
+
+ buf[0] = '\0';
+ close(pipefd[0]);
+
+ // Gator runs at a high priority, reset the priority to the default
+ if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+ snprintf(buf, sizeof(buf), "setpriority failed");
+ goto fail_exit;
+ }
+
+ if (setuid(uid) != 0) {
+ snprintf(buf, sizeof(buf), "setuid failed");
+ goto fail_exit;
+ }
+
+ {
+ const char *const path = gSessionData->mCaptureWorkingDir == NULL ? "/" : gSessionData->mCaptureWorkingDir;
+ if (chdir(path) != 0) {
+ snprintf(buf, sizeof(buf), "Unable to cd to %s, please verify the directory exists and is accessable to %s", path, name);
+ goto fail_exit;
+ }
+ }
+
+ execv(cargv[0], cargv);
+ cargv[0] = cargv0a;
+ execv(cargv[0], cargv);
+ snprintf(buf, sizeof(buf), "execv failed");
+
+ fail_exit:
+ if (buf[0] != '\0') {
+ const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+ // Can't do anything if this fails
+ (void)bytes;
+ }
+
+ exit(-1);
+ }
+
+ close(pipefd[1]);
+ const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+ if (bytes > 0) {
+ logg->logError("%s", buf);
+ handleException();
+ }
+ close(pipefd[0]);
+
+ return NULL;
+}
diff --git a/tools/gator/daemon/Command.h b/tools/gator/daemon/Command.h
new file mode 100644
index 0000000..2838adc
--- /dev/null
+++ b/tools/gator/daemon/Command.h
@@ -0,0 +1,14 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COMMAND_H
+#define COMMAND_H
+
+void *commandThread(void *);
+
+#endif // COMMAND_H
diff --git a/tools/gator/daemon/Config.h b/tools/gator/daemon/Config.h
new file mode 100644
index 0000000..eb31556
--- /dev/null
+++ b/tools/gator/daemon/Config.h
@@ -0,0 +1,28 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef CONFIG_H
+#define CONFIG_H
+
+#define ARRAY_LENGTH(A) static_cast<int>(sizeof(A)/sizeof((A)[0]))
+#define ACCESS_ONCE(x) (*(volatile typeof(x)*)&(x))
+
+#define MAX_PERFORMANCE_COUNTERS 50
+#define NR_CPUS 32
+
+template<typename T>
+static inline T min(const T a, const T b) {
+ return (a < b ? a : b);
+}
+
+template<typename T>
+static inline T max(const T a, const T b) {
+ return (a > b ? a : b);
+}
+
+#endif // CONFIG_H
diff --git a/tools/gator/daemon/ConfigurationXML.cpp b/tools/gator/daemon/ConfigurationXML.cpp
new file mode 100644
index 0000000..be224a4
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.cpp
@@ -0,0 +1,217 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ConfigurationXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <dirent.h>
+
+#include "Driver.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char* ATTR_COUNTER = "counter";
+static const char* ATTR_REVISION = "revision";
+static const char* ATTR_EVENT = "event";
+static const char* ATTR_COUNT = "count";
+static const char* ATTR_CORES = "cores";
+
+ConfigurationXML::ConfigurationXML() {
+ const char * configuration_xml;
+ unsigned int configuration_xml_len;
+ getDefaultConfigurationXml(configuration_xml, configuration_xml_len);
+
+ char path[PATH_MAX];
+
+ getPath(path);
+ mConfigurationXML = util->readFromDisk(path);
+
+ for (int retryCount = 0; retryCount < 2; ++retryCount) {
+ if (mConfigurationXML == NULL) {
+ logg->logMessage("Unable to locate configuration.xml, using default in binary");
+ // null-terminate configuration_xml
+ mConfigurationXML = (char*)malloc(configuration_xml_len + 1);
+ memcpy(mConfigurationXML, (const void*)configuration_xml, configuration_xml_len);
+ mConfigurationXML[configuration_xml_len] = 0;
+ }
+
+ int ret = parse(mConfigurationXML);
+ if (ret == 1) {
+ remove();
+
+ // Free the current configuration and reload
+ free((void*)mConfigurationXML);
+ mConfigurationXML = NULL;
+ continue;
+ }
+
+ break;
+ }
+
+ validate();
+}
+
+ConfigurationXML::~ConfigurationXML() {
+ if (mConfigurationXML) {
+ free((void*)mConfigurationXML);
+ }
+}
+
+int ConfigurationXML::parse(const char* configurationXML) {
+ mxml_node_t *tree, *node;
+ int ret;
+
+ // clear counter overflow
+ gSessionData->mCounterOverflow = 0;
+ gSessionData->mIsEBS = false;
+ mIndex = 0;
+
+ // disable all counters prior to parsing the configuration xml
+ for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+ gSessionData->mCounters[i].setEnabled(false);
+ }
+
+ tree = mxmlLoadString(NULL, configurationXML, MXML_NO_CALLBACK);
+
+ node = mxmlGetFirstChild(tree);
+ while (node && mxmlGetType(node) != MXML_ELEMENT)
+ node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+
+ ret = configurationsTag(node);
+
+ node = mxmlGetFirstChild(node);
+ while (node) {
+ if (mxmlGetType(node) != MXML_ELEMENT) {
+ node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+ continue;
+ }
+ configurationTag(node);
+ node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+ }
+
+ mxmlDelete(tree);
+
+ return ret;
+}
+
+void ConfigurationXML::validate(void) {
+ for (int i = 0; i < MAX_PERFORMANCE_COUNTERS; i++) {
+ const Counter & counter = gSessionData->mCounters[i];
+ if (counter.isEnabled()) {
+ if (strcmp(counter.getType(), "") == 0) {
+ logg->logError("Invalid required attribute in configuration.xml:\n counter=\"%s\"\n event=%d\n", counter.getType(), counter.getEvent());
+ handleException();
+ }
+
+ // iterate through the remaining enabled performance counters
+ for (int j = i + 1; j < MAX_PERFORMANCE_COUNTERS; j++) {
+ const Counter & counter2 = gSessionData->mCounters[j];
+ if (counter2.isEnabled()) {
+ // check if the types are the same
+ if (strcmp(counter.getType(), counter2.getType()) == 0) {
+ logg->logError("Duplicate performance counter type in configuration.xml: %s", counter.getType());
+ handleException();
+ }
+ }
+ }
+ }
+ }
+}
+
+#define CONFIGURATION_REVISION 3
+int ConfigurationXML::configurationsTag(mxml_node_t *node) {
+ const char* revision_string;
+
+ revision_string = mxmlElementGetAttr(node, ATTR_REVISION);
+ if (!revision_string) {
+ return 1; //revision issue;
+ }
+
+ int revision = strtol(revision_string, NULL, 10);
+ if (revision < CONFIGURATION_REVISION) {
+ return 1; // revision issue
+ }
+
+ // A revision >= CONFIGURATION_REVISION is okay
+ // Greater than can occur when Streamline is newer than gator
+
+ return 0;
+}
+
+void ConfigurationXML::configurationTag(mxml_node_t *node) {
+ // handle all other performance counters
+ if (mIndex >= MAX_PERFORMANCE_COUNTERS) {
+ mIndex++;
+ gSessionData->mCounterOverflow = mIndex;
+ return;
+ }
+
+ // read attributes
+ Counter & counter = gSessionData->mCounters[mIndex];
+ counter.clear();
+ if (mxmlElementGetAttr(node, ATTR_COUNTER)) counter.setType(mxmlElementGetAttr(node, ATTR_COUNTER));
+ if (mxmlElementGetAttr(node, ATTR_EVENT)) counter.setEvent(strtol(mxmlElementGetAttr(node, ATTR_EVENT), NULL, 16));
+ if (mxmlElementGetAttr(node, ATTR_COUNT)) counter.setCount(strtol(mxmlElementGetAttr(node, ATTR_COUNT), NULL, 10));
+ if (mxmlElementGetAttr(node, ATTR_CORES)) counter.setCores(strtol(mxmlElementGetAttr(node, ATTR_CORES), NULL, 10));
+ if (counter.getCount() > 0) {
+ gSessionData->mIsEBS = true;
+ }
+ counter.setEnabled(true);
+
+ // Associate a driver with each counter
+ for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+ if (driver->claimCounter(counter)) {
+ if (counter.getDriver() != NULL) {
+ logg->logError("More than one driver has claimed %s:%i", counter.getType(), counter.getEvent());
+ handleException();
+ }
+ counter.setDriver(driver);
+ }
+ }
+
+ // If no driver is associated with the counter, disable it
+ if (counter.getDriver() == NULL) {
+ logg->logMessage("No driver has claimed %s:%i", counter.getType(), counter.getEvent());
+ counter.setEnabled(false);
+ }
+
+ if (counter.isEnabled()) {
+ // update counter index
+ mIndex++;
+ }
+}
+
+void ConfigurationXML::getDefaultConfigurationXml(const char * & xml, unsigned int & len) {
+#include "defaults_xml.h" // defines and initializes char defaults_xml[] and int defaults_xml_len
+ xml = (const char *)defaults_xml;
+ len = defaults_xml_len;
+}
+
+void ConfigurationXML::getPath(char* path) {
+ if (gSessionData->mConfigurationXMLPath) {
+ strncpy(path, gSessionData->mConfigurationXMLPath, PATH_MAX);
+ } else {
+ if (util->getApplicationFullPath(path, PATH_MAX) != 0) {
+ logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+ }
+ strncat(path, "configuration.xml", PATH_MAX - strlen(path) - 1);
+ }
+}
+
+void ConfigurationXML::remove() {
+ char path[PATH_MAX];
+ getPath(path);
+
+ if (::remove(path) != 0) {
+ logg->logError("Invalid configuration.xml file detected and unable to delete it. To resolve, delete configuration.xml on disk");
+ handleException();
+ }
+ logg->logMessage("Invalid configuration.xml file detected and removed");
+}
diff --git a/tools/gator/daemon/ConfigurationXML.h b/tools/gator/daemon/ConfigurationXML.h
new file mode 100644
index 0000000..a986ce99
--- /dev/null
+++ b/tools/gator/daemon/ConfigurationXML.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTERS_H
+#define COUNTERS_H
+
+#include "mxml/mxml.h"
+
+class ConfigurationXML {
+public:
+ static void getDefaultConfigurationXml(const char * & xml, unsigned int & len);
+ static void getPath(char* path);
+ static void remove();
+
+ ConfigurationXML();
+ ~ConfigurationXML();
+ const char* getConfigurationXML() {return mConfigurationXML;}
+ void validate(void);
+
+private:
+ char* mConfigurationXML;
+ int mIndex;
+
+ int parse(const char* xmlFile);
+ int configurationsTag(mxml_node_t *node);
+ void configurationTag(mxml_node_t *node);
+
+ // Intentionally unimplemented
+ ConfigurationXML(const ConfigurationXML &);
+ ConfigurationXML &operator=(const ConfigurationXML &);
+};
+
+#endif // COUNTERS_H
diff --git a/tools/gator/daemon/Counter.h b/tools/gator/daemon/Counter.h
new file mode 100644
index 0000000..a4c22f5
--- /dev/null
+++ b/tools/gator/daemon/Counter.h
@@ -0,0 +1,65 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef COUNTER_H
+#define COUNTER_H
+
+#include <string.h>
+
+class Driver;
+
+class Counter {
+public:
+ static const size_t MAX_STRING_LEN = 80;
+ static const size_t MAX_DESCRIPTION_LEN = 400;
+
+ Counter () {
+ clear();
+ }
+
+ void clear () {
+ mType[0] = '\0';
+ mEnabled = false;
+ mEvent = -1;
+ mCount = 0;
+ mCores = -1;
+ mKey = 0;
+ mDriver = NULL;
+ }
+
+ void setType(const char *const type) { strncpy(mType, type, sizeof(mType)); mType[sizeof(mType) - 1] = '\0'; }
+ void setEnabled(const bool enabled) { mEnabled = enabled; }
+ void setEvent(const int event) { mEvent = event; }
+ void setCount(const int count) { mCount = count; }
+ void setCores(const int cores) { mCores = cores; }
+ void setKey(const int key) { mKey = key; }
+ void setDriver(Driver *const driver) { mDriver = driver; }
+
+ const char *getType() const { return mType;}
+ bool isEnabled() const { return mEnabled; }
+ int getEvent() const { return mEvent; }
+ int getCount() const { return mCount; }
+ int getCores() const { return mCores; }
+ int getKey() const { return mKey; }
+ Driver *getDriver() const { return mDriver; }
+
+private:
+ // Intentionally unimplemented
+ Counter(const Counter &);
+ Counter & operator=(const Counter &);
+
+ char mType[MAX_STRING_LEN];
+ bool mEnabled;
+ int mEvent;
+ int mCount;
+ int mCores;
+ int mKey;
+ Driver *mDriver;
+};
+
+#endif // COUNTER_H
diff --git a/tools/gator/daemon/DiskIODriver.cpp b/tools/gator/daemon/DiskIODriver.cpp
new file mode 100644
index 0000000..af62bb9
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.cpp
@@ -0,0 +1,125 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DiskIODriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class DiskIOCounter : public DriverCounter {
+public:
+ DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value);
+ ~DiskIOCounter();
+
+ int64_t read();
+
+private:
+ int64_t *const mValue;
+ int64_t mPrev;
+
+ // Intentionally unimplemented
+ DiskIOCounter(const DiskIOCounter &);
+ DiskIOCounter &operator=(const DiskIOCounter &);
+};
+
+DiskIOCounter::DiskIOCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+DiskIOCounter::~DiskIOCounter() {
+}
+
+int64_t DiskIOCounter::read() {
+ int64_t result = *mValue - mPrev;
+ mPrev = *mValue;
+ // Kernel assumes a sector is 512 bytes
+ return result << 9;
+}
+
+DiskIODriver::DiskIODriver() : mBuf(), mReadBytes(0), mWriteBytes(0) {
+}
+
+DiskIODriver::~DiskIODriver() {
+}
+
+void DiskIODriver::readEvents(mxml_node_t *const) {
+ // Only for use with perf
+ if (!gSessionData->perf.isSetup()) {
+ return;
+ }
+
+ setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_rd"), &mReadBytes));
+ setCounters(new DiskIOCounter(getCounters(), strdup("Linux_block_rq_wr"), &mWriteBytes));
+}
+
+void DiskIODriver::doRead() {
+ if (!countersEnabled()) {
+ return;
+ }
+
+ if (!mBuf.read("/proc/diskstats")) {
+ logg->logError("Unable to read /proc/diskstats");
+ handleException();
+ }
+
+ mReadBytes = 0;
+ mWriteBytes = 0;
+
+ char *lastName = NULL;
+ int lastNameLen = -1;
+ char *line = mBuf.getBuf();
+ while (*line != '\0') {
+ char *end = strchr(line, '\n');
+ if (end != NULL) {
+ *end = '\0';
+ }
+
+ int nameStart = -1;
+ int nameEnd = -1;
+ int64_t readBytes = -1;
+ int64_t writeBytes = -1;
+ const int count = sscanf(line, "%*d %*d %n%*s%n %*u %*u %" SCNu64 " %*u %*u %*u %" SCNu64, &nameStart, &nameEnd, &readBytes, &writeBytes);
+ if (count != 2) {
+ logg->logError("Unable to parse /proc/diskstats");
+ handleException();
+ }
+
+ // Skip partitions which are identified if the name is a substring of the last non-partition
+ if ((lastName == NULL) || (strncmp(lastName, line + nameStart, lastNameLen) != 0)) {
+ lastName = line + nameStart;
+ lastNameLen = nameEnd - nameStart;
+ mReadBytes += readBytes;
+ mWriteBytes += writeBytes;
+ }
+
+ if (end == NULL) {
+ break;
+ }
+ line = end + 1;
+ }
+}
+
+void DiskIODriver::start() {
+ doRead();
+ // Initialize previous values
+ for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->read();
+ }
+}
+
+void DiskIODriver::read(Buffer *const buffer) {
+ doRead();
+ super::read(buffer);
+}
diff --git a/tools/gator/daemon/DiskIODriver.h b/tools/gator/daemon/DiskIODriver.h
new file mode 100644
index 0000000..6ecda5a
--- /dev/null
+++ b/tools/gator/daemon/DiskIODriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DISKIODRIVER_H
+#define DISKIODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class DiskIODriver : public PolledDriver {
+private:
+ typedef PolledDriver super;
+
+public:
+ DiskIODriver();
+ ~DiskIODriver();
+
+ void readEvents(mxml_node_t *const root);
+ void start();
+ void read(Buffer *const buffer);
+
+private:
+ void doRead();
+
+ DynBuf mBuf;
+ int64_t mReadBytes;
+ int64_t mWriteBytes;
+
+ // Intentionally unimplemented
+ DiskIODriver(const DiskIODriver &);
+ DiskIODriver &operator=(const DiskIODriver &);
+};
+
+#endif // DISKIODRIVER_H
diff --git a/tools/gator/daemon/Driver.cpp b/tools/gator/daemon/Driver.cpp
new file mode 100644
index 0000000..72c7314
--- /dev/null
+++ b/tools/gator/daemon/Driver.cpp
@@ -0,0 +1,96 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Driver.h"
+
+#include "Buffer.h"
+#include "SessionData.h"
+
+DriverCounter::DriverCounter(DriverCounter *const next, const char *const name) : mNext(next), mName(name), mKey(getEventKey()), mEnabled(false) {
+}
+
+DriverCounter::~DriverCounter() {
+ delete mName;
+}
+
+Driver *Driver::head = NULL;
+
+Driver::Driver() : next(head) {
+ head = this;
+}
+
+SimpleDriver::~SimpleDriver() {
+ DriverCounter *counters = mCounters;
+ while (counters != NULL) {
+ DriverCounter *counter = counters;
+ counters = counter->getNext();
+ delete counter;
+ }
+}
+
+DriverCounter *SimpleDriver::findCounter(const Counter &counter) const {
+ for (DriverCounter *driverCounter = mCounters; driverCounter != NULL; driverCounter = driverCounter->getNext()) {
+ if (strcmp(driverCounter->getName(), counter.getType()) == 0) {
+ return driverCounter;
+ }
+ }
+
+ return NULL;
+}
+
+bool SimpleDriver::claimCounter(const Counter &counter) const {
+ return findCounter(counter) != NULL;
+}
+
+bool SimpleDriver::countersEnabled() const {
+ for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+ if (counter->isEnabled()) {
+ return true;
+ }
+ }
+ return false;
+}
+
+void SimpleDriver::resetCounters() {
+ for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+ counter->setEnabled(false);
+ }
+}
+
+void SimpleDriver::setupCounter(Counter &counter) {
+ DriverCounter *const driverCounter = findCounter(counter);
+ if (driverCounter == NULL) {
+ counter.setEnabled(false);
+ return;
+ }
+ driverCounter->setEnabled(true);
+ counter.setKey(driverCounter->getKey());
+}
+
+int SimpleDriver::writeCounters(mxml_node_t *root) const {
+ int count = 0;
+ for (DriverCounter *counter = mCounters; counter != NULL; counter = counter->getNext()) {
+ mxml_node_t *node = mxmlNewElement(root, "counter");
+ mxmlElementSetAttr(node, "name", counter->getName());
+ ++count;
+ }
+
+ return count;
+}
+
+PolledDriver::~PolledDriver() {
+}
+
+void PolledDriver::read(Buffer *const buffer) {
+ for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ buffer->event64(counter->getKey(), counter->read());
+ }
+}
diff --git a/tools/gator/daemon/Driver.h b/tools/gator/daemon/Driver.h
new file mode 100644
index 0000000..19ec127
--- /dev/null
+++ b/tools/gator/daemon/Driver.h
@@ -0,0 +1,118 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVER_H
+#define DRIVER_H
+
+#include <stdint.h>
+
+#include "mxml/mxml.h"
+
+class Buffer;
+class Counter;
+
+class DriverCounter {
+public:
+ DriverCounter(DriverCounter *const next, const char *const name);
+ virtual ~DriverCounter();
+
+ DriverCounter *getNext() const { return mNext; }
+ const char *getName() const { return mName; }
+ int getKey() const { return mKey; }
+ bool isEnabled() const { return mEnabled; }
+ void setEnabled(const bool enabled) { mEnabled = enabled; }
+ virtual int64_t read() { return -1; }
+
+private:
+ DriverCounter *const mNext;
+ const char *const mName;
+ const int mKey;
+ bool mEnabled;
+
+ // Intentionally unimplemented
+ DriverCounter(const DriverCounter &);
+ DriverCounter &operator=(const DriverCounter &);
+};
+
+class Driver {
+public:
+ static Driver *getHead() { return head; }
+
+ virtual ~Driver() {}
+
+ // Returns true if this driver can manage the counter
+ virtual bool claimCounter(const Counter &counter) const = 0;
+ // Clears and disables all counters
+ virtual void resetCounters() = 0;
+ // Enables and prepares the counter for capture
+ virtual void setupCounter(Counter &counter) = 0;
+
+ // Performs any actions needed for setup or based on eventsXML
+ virtual void readEvents(mxml_node_t *const) {}
+ // Emits available counters
+ virtual int writeCounters(mxml_node_t *const root) const = 0;
+ // Emits possible dynamically generated events/counters
+ virtual void writeEvents(mxml_node_t *const) const {}
+
+ Driver *getNext() const { return next; }
+
+protected:
+ Driver();
+
+private:
+ static Driver *head;
+ Driver *next;
+
+ // Intentionally unimplemented
+ Driver(const Driver &);
+ Driver &operator=(const Driver &);
+};
+
+class SimpleDriver : public Driver {
+public:
+ virtual ~SimpleDriver();
+
+ bool claimCounter(const Counter &counter) const;
+ bool countersEnabled() const;
+ void resetCounters();
+ void setupCounter(Counter &counter);
+ int writeCounters(mxml_node_t *root) const;
+
+protected:
+ SimpleDriver() : mCounters(NULL) {}
+
+ DriverCounter *getCounters() const { return mCounters; }
+ void setCounters(DriverCounter *const counter) { mCounters = counter; }
+
+ DriverCounter *findCounter(const Counter &counter) const;
+
+private:
+ DriverCounter *mCounters;
+
+ // Intentionally unimplemented
+ SimpleDriver(const SimpleDriver &);
+ SimpleDriver &operator=(const SimpleDriver &);
+};
+
+class PolledDriver : public SimpleDriver {
+public:
+ virtual ~PolledDriver();
+
+ virtual void start() {}
+ virtual void read(Buffer *const buffer);
+
+protected:
+ PolledDriver() {}
+
+private:
+ // Intentionally unimplemented
+ PolledDriver(const PolledDriver &);
+ PolledDriver &operator=(const PolledDriver &);
+};
+
+#endif // DRIVER_H
diff --git a/tools/gator/daemon/DriverSource.cpp b/tools/gator/daemon/DriverSource.cpp
new file mode 100644
index 0000000..34920ce
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.cpp
@@ -0,0 +1,323 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "DriverSource.h"
+
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Child.h"
+#include "DynBuf.h"
+#include "Fifo.h"
+#include "Logging.h"
+#include "Proc.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+DriverSource::DriverSource(sem_t *senderSem, sem_t *startProfile) : mBuffer(NULL), mFifo(NULL), mSenderSem(senderSem), mStartProfile(startProfile), mBufferSize(0), mBufferFD(0), mLength(1) {
+ int driver_version = 0;
+
+ mBuffer = new Buffer(0, FRAME_PERF_ATTRS, 4*1024*1024, senderSem);
+ if (readIntDriver("/dev/gator/version", &driver_version) == -1) {
+ logg->logError("Error reading gator driver version");
+ handleException();
+ }
+
+ // Verify the driver version matches the daemon version
+ if (driver_version != PROTOCOL_VERSION) {
+ if ((driver_version > PROTOCOL_DEV) || (PROTOCOL_VERSION > PROTOCOL_DEV)) {
+ // One of the mismatched versions is development version
+ logg->logError(
+ "DEVELOPMENT BUILD MISMATCH: gator driver version \"%d\" is not in sync with gator daemon version \"%d\".\n"
+ ">> The following must be synchronized from engineering repository:\n"
+ ">> * gator driver\n"
+ ">> * gator daemon\n"
+ ">> * Streamline", driver_version, PROTOCOL_VERSION);
+ handleException();
+ } else {
+ // Release version mismatch
+ logg->logError(
+ "gator driver version \"%d\" is different than gator daemon version \"%d\".\n"
+ ">> Please upgrade the driver and daemon to the latest versions.", driver_version, PROTOCOL_VERSION);
+ handleException();
+ }
+ }
+
+ int enable = -1;
+ if (readIntDriver("/dev/gator/enable", &enable) != 0 || enable != 0) {
+ logg->logError("Driver already enabled, possibly a session is already in progress.");
+ handleException();
+ }
+
+ readIntDriver("/dev/gator/cpu_cores", &gSessionData->mCores);
+ if (gSessionData->mCores == 0) {
+ gSessionData->mCores = 1;
+ }
+
+ if (readIntDriver("/dev/gator/buffer_size", &mBufferSize) || mBufferSize <= 0) {
+ logg->logError("Unable to read the driver buffer size");
+ handleException();
+ }
+}
+
+DriverSource::~DriverSource() {
+ delete mFifo;
+
+ // Write zero for safety, as a zero should have already been written
+ writeDriver("/dev/gator/enable", "0");
+
+ // Calls event_buffer_release in the driver
+ if (mBufferFD) {
+ close(mBufferFD);
+ }
+}
+
+bool DriverSource::prepare() {
+ // Create user-space buffers, add 5 to the size to account for the 1-byte type and 4-byte length
+ logg->logMessage("Created %d MB collector buffer with a %d-byte ragged end", gSessionData->mTotalBufferSize, mBufferSize);
+ mFifo = new Fifo(mBufferSize + 5, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+ return true;
+}
+
+void DriverSource::bootstrapThread() {
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+ DynBuf printb;
+ DynBuf b1;
+ DynBuf b2;
+ // MonotonicStarted may not be not assigned yet
+ const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+ if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+ logg->logError("readProcComms failed");
+ handleException();
+ }
+
+ mBuffer->commit(currTime);
+ mBuffer->setDone();
+}
+
+void *DriverSource::bootstrapThreadStatic(void *arg) {
+ static_cast<DriverSource *>(arg)->bootstrapThread();
+ return NULL;
+}
+
+void DriverSource::run() {
+ // Get the initial pointer to the collect buffer
+ char *collectBuffer = mFifo->start();
+ int bytesCollected = 0;
+
+ logg->logMessage("********** Profiling started **********");
+
+ // Set the maximum backtrace depth
+ if (writeReadDriver("/dev/gator/backtrace_depth", &gSessionData->mBacktraceDepth)) {
+ logg->logError("Unable to set the driver backtrace depth");
+ handleException();
+ }
+
+ // open the buffer which calls userspace_buffer_open() in the driver
+ mBufferFD = open("/dev/gator/buffer", O_RDONLY | O_CLOEXEC);
+ if (mBufferFD < 0) {
+ logg->logError("The gator driver did not set up properly. Please view the linux console or dmesg log for more information on the failure.");
+ handleException();
+ }
+
+ // set the tick rate of the profiling timer
+ if (writeReadDriver("/dev/gator/tick", &gSessionData->mSampleRate) != 0) {
+ logg->logError("Unable to set the driver tick");
+ handleException();
+ }
+
+ // notify the kernel of the response type
+ int response_type = gSessionData->mLocalCapture ? 0 : RESPONSE_APC_DATA;
+ if (writeDriver("/dev/gator/response_type", response_type)) {
+ logg->logError("Unable to write the response type");
+ handleException();
+ }
+
+ // Set the live rate
+ if (writeReadDriver("/dev/gator/live_rate", &gSessionData->mLiveRate)) {
+ logg->logError("Unable to set the driver live rate");
+ handleException();
+ }
+
+ logg->logMessage("Start the driver");
+
+ // This command makes the driver start profiling by calling gator_op_start() in the driver
+ if (writeDriver("/dev/gator/enable", "1") != 0) {
+ logg->logError("The gator driver did not start properly. Please view the linux console or dmesg log for more information on the failure.");
+ handleException();
+ }
+
+ lseek(mBufferFD, 0, SEEK_SET);
+
+ sem_post(mStartProfile);
+
+ pthread_t bootstrapThreadID;
+ if (pthread_create(&bootstrapThreadID, NULL, bootstrapThreadStatic, this) != 0) {
+ logg->logError("Unable to start the gator_bootstrap thread");
+ handleException();
+ }
+
+ // Collect Data
+ do {
+ // This command will stall until data is received from the driver
+ // Calls event_buffer_read in the driver
+ errno = 0;
+ bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+
+ // If read() returned due to an interrupt signal, re-read to obtain the last bit of collected data
+ if (bytesCollected == -1 && errno == EINTR) {
+ bytesCollected = read(mBufferFD, collectBuffer, mBufferSize);
+ }
+
+ // return the total bytes written
+ logg->logMessage("Driver read of %d bytes", bytesCollected);
+
+ // In one shot mode, stop collection once all the buffers are filled
+ if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+ if (bytesCollected == -1 || mFifo->willFill(bytesCollected)) {
+ logg->logMessage("One shot (gator.ko)");
+ child->endSession();
+ }
+ }
+ collectBuffer = mFifo->write(bytesCollected);
+ } while (bytesCollected > 0);
+
+ logg->logMessage("Exit collect data loop");
+
+ pthread_join(bootstrapThreadID, NULL);
+}
+
+void DriverSource::interrupt() {
+ // This command should cause the read() function in collect() to return and stop the driver from profiling
+ if (writeDriver("/dev/gator/enable", "0") != 0) {
+ logg->logMessage("Stopping kernel failed");
+ }
+}
+
+bool DriverSource::isDone() {
+ return mLength <= 0 && (mBuffer == NULL || mBuffer->isDone());
+}
+
+void DriverSource::write(Sender *sender) {
+ char *data = mFifo->read(&mLength);
+ if (data != NULL) {
+ sender->writeData(data, mLength, RESPONSE_APC_DATA);
+ mFifo->release();
+ // Assume the summary packet is in the first block received from the driver
+ gSessionData->mSentSummary = true;
+ }
+ if (mBuffer != NULL && !mBuffer->isDone()) {
+ mBuffer->write(sender);
+ if (mBuffer->isDone()) {
+ Buffer *buf = mBuffer;
+ mBuffer = NULL;
+ delete buf;
+ }
+ }
+}
+
+int DriverSource::readIntDriver(const char *fullpath, int *value) {
+ char data[40]; // Sufficiently large to hold any integer
+ const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ return -1;
+ }
+
+ const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+ close(fd);
+ if (bytes < 0) {
+ return -1;
+ }
+ data[bytes] = '\0';
+
+ char *endptr;
+ errno = 0;
+ *value = strtol(data, &endptr, 10);
+ if (errno != 0 || *endptr != '\n') {
+ logg->logMessage("Invalid value in file %s", fullpath);
+ return -1;
+ }
+
+ return 0;
+}
+
+int DriverSource::readInt64Driver(const char *fullpath, int64_t *value) {
+ char data[40]; // Sufficiently large to hold any integer
+ const int fd = open(fullpath, O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ return -1;
+ }
+
+ const ssize_t bytes = read(fd, data, sizeof(data) - 1);
+ close(fd);
+ if (bytes < 0) {
+ return -1;
+ }
+ data[bytes] = '\0';
+
+ char *endptr;
+ errno = 0;
+ *value = strtoll(data, &endptr, 10);
+ if (errno != 0 || (*endptr != '\n' && *endptr != '\0')) {
+ logg->logMessage("Invalid value in file %s", fullpath);
+ return -1;
+ }
+
+ return 0;
+}
+
+int DriverSource::writeDriver(const char *fullpath, const char *data) {
+ int fd = open(fullpath, O_WRONLY | O_CLOEXEC);
+ if (fd < 0) {
+ return -1;
+ }
+ if (::write(fd, data, strlen(data)) < 0) {
+ close(fd);
+ logg->logMessage("Opened but could not write to %s", fullpath);
+ return -1;
+ }
+ close(fd);
+ return 0;
+}
+
+int DriverSource::writeDriver(const char *path, int value) {
+ char data[40]; // Sufficiently large to hold any integer
+ snprintf(data, sizeof(data), "%d", value);
+ return writeDriver(path, data);
+}
+
+int DriverSource::writeDriver(const char *path, int64_t value) {
+ char data[40]; // Sufficiently large to hold any integer
+ snprintf(data, sizeof(data), "%" PRIi64, value);
+ return writeDriver(path, data);
+}
+
+int DriverSource::writeReadDriver(const char *path, int *value) {
+ if (writeDriver(path, *value) || readIntDriver(path, value)) {
+ return -1;
+ }
+ return 0;
+}
+
+int DriverSource::writeReadDriver(const char *path, int64_t *value) {
+ if (writeDriver(path, *value) || readInt64Driver(path, value)) {
+ return -1;
+ }
+ return 0;
+}
diff --git a/tools/gator/daemon/DriverSource.h b/tools/gator/daemon/DriverSource.h
new file mode 100644
index 0000000..32d983d
--- /dev/null
+++ b/tools/gator/daemon/DriverSource.h
@@ -0,0 +1,57 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DRIVERSOURCE_H
+#define DRIVERSOURCE_H
+
+#include <semaphore.h>
+#include <stdint.h>
+
+#include "Source.h"
+
+class Buffer;
+class Fifo;
+
+class DriverSource : public Source {
+public:
+ DriverSource(sem_t *senderSem, sem_t *startProfile);
+ ~DriverSource();
+
+ bool prepare();
+ void run();
+ void interrupt();
+
+ bool isDone();
+ void write(Sender *sender);
+
+ static int readIntDriver(const char *fullpath, int *value);
+ static int readInt64Driver(const char *fullpath, int64_t *value);
+ static int writeDriver(const char *fullpath, const char *data);
+ static int writeDriver(const char *path, int value);
+ static int writeDriver(const char *path, int64_t value);
+ static int writeReadDriver(const char *path, int *value);
+ static int writeReadDriver(const char *path, int64_t *value);
+
+private:
+ static void *bootstrapThreadStatic(void *arg);
+ void bootstrapThread();
+
+ Buffer *mBuffer;
+ Fifo *mFifo;
+ sem_t *const mSenderSem;
+ sem_t *const mStartProfile;
+ int mBufferSize;
+ int mBufferFD;
+ int mLength;
+
+ // Intentionally unimplemented
+ DriverSource(const DriverSource &);
+ DriverSource &operator=(const DriverSource &);
+};
+
+#endif // DRIVERSOURCE_H
diff --git a/tools/gator/daemon/DynBuf.cpp b/tools/gator/daemon/DynBuf.cpp
new file mode 100644
index 0000000..690cbcb
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.cpp
@@ -0,0 +1,139 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "DynBuf.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+// Pick an aggressive size as buffer is primarily used for disk IO
+#define MIN_BUFFER_FREE (1 << 12)
+
+int DynBuf::resize(const size_t minCapacity) {
+ size_t scaledCapacity = 2 * capacity;
+ if (scaledCapacity < minCapacity) {
+ scaledCapacity = minCapacity;
+ }
+ if (scaledCapacity < 2 * MIN_BUFFER_FREE) {
+ scaledCapacity = 2 * MIN_BUFFER_FREE;
+ }
+ capacity = scaledCapacity;
+
+ buf = static_cast<char *>(realloc(buf, capacity));
+ if (buf == NULL) {
+ return -errno;
+ }
+
+ return 0;
+}
+
+bool DynBuf::read(const char *const path) {
+ int result = false;
+
+ const int fd = open(path, O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ logg->logMessage("open failed");
+ return false;
+ }
+
+ length = 0;
+
+ for (;;) {
+ const size_t minCapacity = length + MIN_BUFFER_FREE + 1;
+ if (capacity < minCapacity) {
+ if (resize(minCapacity) != 0) {
+ logg->logMessage("DynBuf::resize failed");
+ goto fail;
+ }
+ }
+
+ const ssize_t bytes = ::read(fd, buf + length, capacity - length - 1);
+ if (bytes < 0) {
+ logg->logMessage("read failed");
+ goto fail;
+ } else if (bytes == 0) {
+ break;
+ }
+ length += bytes;
+ }
+
+ buf[length] = '\0';
+ result = true;
+
+ fail:
+ close(fd);
+
+ return result;
+}
+
+int DynBuf::readlink(const char *const path) {
+ ssize_t bytes = MIN_BUFFER_FREE;
+
+ for (;;) {
+ if (static_cast<size_t>(bytes) >= capacity) {
+ const int err = resize(2 * bytes);
+ if (err != 0) {
+ return err;
+ }
+ }
+ bytes = ::readlink(path, buf, capacity);
+ if (bytes < 0) {
+ return -errno;
+ } else if (static_cast<size_t>(bytes) < capacity) {
+ break;
+ }
+ }
+
+ length = bytes;
+ buf[bytes] = '\0';
+
+ return 0;
+}
+
+bool DynBuf::printf(const char *format, ...) {
+ va_list ap;
+
+ if (capacity <= 0) {
+ if (resize(2 * MIN_BUFFER_FREE) != 0) {
+ logg->logMessage("DynBuf::resize failed");
+ return false;
+ }
+ }
+
+ va_start(ap, format);
+ int bytes = vsnprintf(buf, capacity, format, ap);
+ va_end(ap);
+ if (bytes < 0) {
+ logg->logMessage("fsnprintf failed");
+ return false;
+ }
+
+ if (static_cast<size_t>(bytes) > capacity) {
+ if (resize(bytes + 1) != 0) {
+ logg->logMessage("DynBuf::resize failed");
+ return false;
+ }
+
+ va_start(ap, format);
+ bytes = vsnprintf(buf, capacity, format, ap);
+ va_end(ap);
+ if (bytes < 0) {
+ logg->logMessage("fsnprintf failed");
+ return false;
+ }
+ }
+
+ length = bytes;
+
+ return true;
+}
diff --git a/tools/gator/daemon/DynBuf.h b/tools/gator/daemon/DynBuf.h
new file mode 100644
index 0000000..da83cd6
--- /dev/null
+++ b/tools/gator/daemon/DynBuf.h
@@ -0,0 +1,52 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DYNBUF_H
+#define DYNBUF_H
+
+#include <stdlib.h>
+
+class DynBuf {
+public:
+ DynBuf() : capacity(0), length(0), buf(NULL) {}
+ ~DynBuf() {
+ reset();
+ }
+
+ inline void reset() {
+ capacity = 0;
+ length = 0;
+ if (buf != NULL) {
+ free(buf);
+ buf = NULL;
+ }
+ }
+
+ bool read(const char *const path);
+ // On error instead of printing the error and returning false, this returns -errno
+ int readlink(const char *const path);
+ __attribute__ ((format(printf, 2, 3)))
+ bool printf(const char *format, ...);
+
+ size_t getLength() const { return length; }
+ const char *getBuf() const { return buf; }
+ char *getBuf() { return buf; }
+
+private:
+ int resize(const size_t minCapacity);
+
+ size_t capacity;
+ size_t length;
+ char *buf;
+
+ // Intentionally undefined
+ DynBuf(const DynBuf &);
+ DynBuf &operator=(const DynBuf &);
+};
+
+#endif // DYNBUF_H
diff --git a/tools/gator/daemon/EventsXML.cpp b/tools/gator/daemon/EventsXML.cpp
new file mode 100644
index 0000000..cec08d5
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.cpp
@@ -0,0 +1,231 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "EventsXML.h"
+
+#include "CapturedXML.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+class XMLList {
+public:
+ XMLList(XMLList *const prev, mxml_node_t *const node) : mPrev(prev), mNode(node) {}
+
+ XMLList *getPrev() { return mPrev; }
+ mxml_node_t *getNode() const { return mNode; }
+ void setNode(mxml_node_t *const node) { mNode = node; }
+
+ static void free(XMLList *list) {
+ while (list != NULL) {
+ XMLList *prev = list->getPrev();
+ delete list;
+ list = prev;
+ }
+ }
+
+private:
+ XMLList *const mPrev;
+ mxml_node_t *mNode;
+
+ // Intentionally unimplemented
+ XMLList(const XMLList &);
+ XMLList &operator=(const XMLList &);
+};
+
+mxml_node_t *EventsXML::getTree() {
+#include "events_xml.h" // defines and initializes char events_xml[] and int events_xml_len
+ char path[PATH_MAX];
+ mxml_node_t *xml = NULL;
+ FILE *fl;
+
+ // Avoid unused variable warning
+ (void)events_xml_len;
+
+ // Load the provided or default events xml
+ if (gSessionData->mEventsXMLPath) {
+ strncpy(path, gSessionData->mEventsXMLPath, PATH_MAX);
+ fl = fopen(path, "r");
+ if (fl) {
+ xml = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+ fclose(fl);
+ }
+ }
+ if (xml == NULL) {
+ logg->logMessage("Unable to locate events.xml, using default");
+ xml = mxmlLoadString(NULL, (const char *)events_xml, MXML_NO_CALLBACK);
+ }
+
+ // Append additional events XML
+ if (gSessionData->mEventsXMLAppend) {
+ fl = fopen(gSessionData->mEventsXMLAppend, "r");
+ if (fl == NULL) {
+ logg->logError("Unable to open additional events XML %s", gSessionData->mEventsXMLAppend);
+ handleException();
+ }
+ mxml_node_t *append = mxmlLoadFile(NULL, fl, MXML_NO_CALLBACK);
+ fclose(fl);
+
+ mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+ if (!events) {
+ logg->logError("Unable to find <events> node in the events.xml, please ensure the first two lines of events XML starts with:\n"
+ "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+ "<events>");
+ handleException();
+ }
+
+ XMLList *categoryList = NULL;
+ XMLList *eventList = NULL;
+ {
+ // Make list of all categories in xml
+ mxml_node_t *node = xml;
+ while (true) {
+ node = mxmlFindElement(node, xml, "category", NULL, NULL, MXML_DESCEND);
+ if (node == NULL) {
+ break;
+ }
+ categoryList = new XMLList(categoryList, node);
+ }
+
+ // Make list of all events in xml
+ node = xml;
+ while (true) {
+ node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+ if (node == NULL) {
+ break;
+ }
+ eventList = new XMLList(eventList, node);
+ }
+ }
+
+ // Handle events
+ for (mxml_node_t *node = mxmlFindElement(append, append, "event", NULL, NULL, MXML_DESCEND),
+ *next = mxmlFindElement(node, append, "event", NULL, NULL, MXML_DESCEND);
+ node != NULL;
+ node = next, next = mxmlFindElement(node, append, "event", NULL, NULL, MXML_DESCEND)) {
+ const char *const category = mxmlElementGetAttr(mxmlGetParent(node), "name");
+ const char *const title = mxmlElementGetAttr(node, "title");
+ const char *const name = mxmlElementGetAttr(node, "name");
+ if (category == NULL || title == NULL || name == NULL) {
+ logg->logError("Not all event XML nodes have the required title and name and parent name attributes");
+ handleException();
+ }
+
+ // Replace any duplicate events
+ for (XMLList *event = eventList; event != NULL; event = event->getPrev()) {
+ const char *const category2 = mxmlElementGetAttr(mxmlGetParent(event->getNode()), "name");
+ const char *const title2 = mxmlElementGetAttr(event->getNode(), "title");
+ const char *const name2 = mxmlElementGetAttr(event->getNode(), "name");
+ if (category2 == NULL || title2 == NULL || name2 == NULL) {
+ logg->logError("Not all event XML nodes have the required title and name and parent name attributes");
+ handleException();
+ }
+
+ if (strcmp(category, category2) == 0 && strcmp(title, title2) == 0 && strcmp(name, name2) == 0) {
+ logg->logMessage("Replacing counter %s %s: %s", category, title, name);
+ mxml_node_t *parent = mxmlGetParent(event->getNode());
+ mxmlDelete(event->getNode());
+ mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+ event->setNode(node);
+ break;
+ }
+ }
+ }
+
+ // Handle categories
+ for (mxml_node_t *node = strcmp(mxmlGetElement(append), "category") == 0 ? append : mxmlFindElement(append, append, "category", NULL, NULL, MXML_DESCEND),
+ *next = mxmlFindElement(node, append, "category", NULL, NULL, MXML_DESCEND);
+ node != NULL;
+ node = next, next = mxmlFindElement(node, append, "category", NULL, NULL, MXML_DESCEND)) {
+ // After replacing duplicate events, a category may be empty
+ if (mxmlGetFirstChild(node) == NULL) {
+ continue;
+ }
+
+ const char *const name = mxmlElementGetAttr(node, "name");
+ if (name == NULL) {
+ logg->logError("Not all event XML categories have the required name attribute");
+ handleException();
+ }
+
+ // Merge identically named categories
+ bool merged = false;
+ for (XMLList *category = categoryList; category != NULL; category = category->getPrev()) {
+ const char *const name2 = mxmlElementGetAttr(category->getNode(), "name");
+ if (name2 == NULL) {
+ logg->logError("Not all event XML categories have the required name attribute");
+ handleException();
+ }
+
+ if (strcmp(name, name2) == 0) {
+ logg->logMessage("Merging category %s", name);
+ while (true) {
+ mxml_node_t *child = mxmlGetFirstChild(node);
+ if (child == NULL) {
+ break;
+ }
+ mxmlAdd(category->getNode(), MXML_ADD_AFTER, mxmlGetLastChild(category->getNode()), child);
+ }
+ merged = true;
+ break;
+ }
+ }
+
+ if (merged) {
+ continue;
+ }
+
+ // Add new categories
+ logg->logMessage("Appending category %s", name);
+ mxmlAdd(events, MXML_ADD_AFTER, mxmlGetLastChild(events), node);
+ }
+
+ XMLList::free(eventList);
+ XMLList::free(categoryList);
+
+ mxmlDelete(append);
+ }
+
+ return xml;
+}
+
+char *EventsXML::getXML() {
+ mxml_node_t *xml = getTree();
+
+ // Add dynamic events from the drivers
+ mxml_node_t *events = mxmlFindElement(xml, xml, "events", NULL, NULL, MXML_DESCEND);
+ if (!events) {
+ logg->logError("Unable to find <events> node in the events.xml, please ensure the first two lines of events XML are:\n"
+ "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+ "<events>");
+ handleException();
+ }
+ for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+ driver->writeEvents(events);
+ }
+
+ char *string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+ mxmlDelete(xml);
+
+ return string;
+}
+
+void EventsXML::write(const char *path) {
+ char file[PATH_MAX];
+
+ // Set full path
+ snprintf(file, PATH_MAX, "%s/events.xml", path);
+
+ char *buf = getXML();
+ if (util->writeToDisk(file, buf) < 0) {
+ logg->logError("Error writing %s\nPlease verify the path.", file);
+ handleException();
+ }
+
+ free(buf);
+}
diff --git a/tools/gator/daemon/EventsXML.h b/tools/gator/daemon/EventsXML.h
new file mode 100644
index 0000000..2b38fa4
--- /dev/null
+++ b/tools/gator/daemon/EventsXML.h
@@ -0,0 +1,28 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EVENTS_XML
+#define EVENTS_XML
+
+#include "mxml/mxml.h"
+
+class EventsXML {
+public:
+ EventsXML() {}
+
+ mxml_node_t *getTree();
+ char *getXML();
+ void write(const char* path);
+
+private:
+ // Intentionally unimplemented
+ EventsXML(const EventsXML &);
+ EventsXML &operator=(const EventsXML &);
+};
+
+#endif // EVENTS_XML
diff --git a/tools/gator/daemon/ExternalSource.cpp b/tools/gator/daemon/ExternalSource.cpp
new file mode 100644
index 0000000..8d71b6d
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.cpp
@@ -0,0 +1,279 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ExternalSource.h"
+
+#include <fcntl.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+static const char STREAMLINE_ANNOTATE[] = "\0streamline-annotate";
+static const char MALI_VIDEO[] = "\0mali-video";
+static const char MALI_VIDEO_STARTUP[] = "\0mali-video-startup";
+static const char MALI_VIDEO_V1[] = "MALI_VIDEO 1\n";
+static const char MALI_GRAPHICS[] = "\0mali_thirdparty_server";
+static const char MALI_GRAPHICS_STARTUP[] = "\0mali_thirdparty_client";
+static const char MALI_GRAPHICS_V1[] = "MALI_GRAPHICS 1\n";
+
+static bool setNonblock(const int fd) {
+ int flags;
+
+ flags = fcntl(fd, F_GETFL);
+ if (flags < 0) {
+ logg->logMessage("fcntl getfl failed");
+ return false;
+ }
+
+ if (fcntl(fd, F_SETFL, flags | O_NONBLOCK) != 0) {
+ logg->logMessage("fcntl setfl failed");
+ return false;
+ }
+
+ return true;
+}
+
+ExternalSource::ExternalSource(sem_t *senderSem) : mBuffer(0, FRAME_EXTERNAL, 128*1024, senderSem), mMonitor(), mMveStartupUds(MALI_VIDEO_STARTUP, sizeof(MALI_VIDEO_STARTUP)), mMaliStartupUds(MALI_GRAPHICS_STARTUP, sizeof(MALI_GRAPHICS_STARTUP)), mAnnotate(8083), mAnnotateUds(STREAMLINE_ANNOTATE, sizeof(STREAMLINE_ANNOTATE), true), mInterruptFd(-1), mMaliUds(-1), mMveUds(-1) {
+ sem_init(&mBufferSem, 0, 0);
+}
+
+ExternalSource::~ExternalSource() {
+}
+
+void ExternalSource::waitFor(const int bytes) {
+ while (mBuffer.bytesAvailable() <= bytes) {
+ if (gSessionData->mOneShot && gSessionData->mSessionIsActive) {
+ logg->logMessage("One shot (external)");
+ child->endSession();
+ }
+ sem_wait(&mBufferSem);
+ }
+}
+
+void ExternalSource::configureConnection(const int fd, const char *const handshake, size_t size) {
+ if (!setNonblock(fd)) {
+ logg->logError("Unable to set nonblock on fh");
+ handleException();
+ }
+
+ if (!mMonitor.add(fd)) {
+ logg->logError("Unable to add fh to monitor");
+ handleException();
+ }
+
+ // Write the handshake to the circular buffer
+ waitFor(Buffer::MAXSIZE_PACK32 + size - 1);
+ mBuffer.packInt(fd);
+ mBuffer.writeBytes(handshake, size - 1);
+ mBuffer.commit(1, true);
+}
+
+bool ExternalSource::connectMali() {
+ mMaliUds = OlySocket::connect(MALI_GRAPHICS, sizeof(MALI_GRAPHICS));
+ if (mMaliUds < 0) {
+ return false;
+ }
+
+ configureConnection(mMaliUds, MALI_GRAPHICS_V1, sizeof(MALI_GRAPHICS_V1));
+
+ return true;
+}
+
+bool ExternalSource::connectMve() {
+ if (!gSessionData->maliVideo.countersEnabled()) {
+ return true;
+ }
+
+ mMveUds = OlySocket::connect(MALI_VIDEO, sizeof(MALI_VIDEO));
+ if (mMveUds < 0) {
+ return false;
+ }
+
+ if (!gSessionData->maliVideo.start(mMveUds)) {
+ return false;
+ }
+
+ configureConnection(mMveUds, MALI_VIDEO_V1, sizeof(MALI_VIDEO_V1));
+
+ return true;
+}
+
+bool ExternalSource::prepare() {
+ if (!mMonitor.init() ||
+ !setNonblock(mMveStartupUds.getFd()) || !mMonitor.add(mMveStartupUds.getFd()) ||
+ !setNonblock(mMaliStartupUds.getFd()) || !mMonitor.add(mMaliStartupUds.getFd()) ||
+ !setNonblock(mAnnotate.getFd()) || !mMonitor.add(mAnnotate.getFd()) ||
+ !setNonblock(mAnnotateUds.getFd()) || !mMonitor.add(mAnnotateUds.getFd()) ||
+ false) {
+ return false;
+ }
+
+ connectMali();
+ connectMve();
+
+ return true;
+}
+
+void ExternalSource::run() {
+ int pipefd[2];
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-external", 0, 0, 0);
+
+ if (pipe_cloexec(pipefd) != 0) {
+ logg->logError("pipe failed");
+ handleException();
+ }
+ mInterruptFd = pipefd[1];
+
+ if (!mMonitor.add(pipefd[0])) {
+ logg->logError("Monitor::add failed");
+ handleException();
+ }
+
+ // Notify annotate clients to retry connecting to gatord
+ uint64_t val = 1;
+ if (::write(gSessionData->mAnnotateStart, &val, sizeof(val)) != sizeof(val)) {
+ logg->logMessage("Writing to annotate pipe failed");
+ }
+
+ while (gSessionData->mSessionIsActive) {
+ struct epoll_event events[16];
+ // Clear any pending sem posts
+ while (sem_trywait(&mBufferSem) == 0);
+ int ready = mMonitor.wait(events, ARRAY_LENGTH(events), -1);
+ if (ready < 0) {
+ logg->logError("Monitor::wait failed");
+ handleException();
+ }
+
+ const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+ for (int i = 0; i < ready; ++i) {
+ const int fd = events[i].data.fd;
+ if (fd == mMveStartupUds.getFd()) {
+ // Mali Video Engine says it's alive
+ int client = mMveStartupUds.acceptConnection();
+ // Don't read from this connection, establish a new connection to Mali-V500
+ close(client);
+ if (!connectMve()) {
+ logg->logError("Unable to configure incoming Mali video connection");
+ handleException();
+ }
+ } else if (fd == mMaliStartupUds.getFd()) {
+ // Mali Graphics says it's alive
+ int client = mMaliStartupUds.acceptConnection();
+ // Don't read from this connection, establish a new connection to Mali Graphics
+ close(client);
+ if (!connectMali()) {
+ logg->logError("Unable to configure incoming Mali graphics connection");
+ handleException();
+ }
+ } else if (fd == mAnnotate.getFd()) {
+ int client = mAnnotate.acceptConnection();
+ if (!setNonblock(client) || !mMonitor.add(client)) {
+ logg->logError("Unable to set socket options on incoming annotation connection");
+ handleException();
+ }
+ } else if (fd == mAnnotateUds.getFd()) {
+ int client = mAnnotateUds.acceptConnection();
+ if (!setNonblock(client) || !mMonitor.add(client)) {
+ logg->logError("Unable to set socket options on incoming annotation connection");
+ handleException();
+ }
+ } else if (fd == pipefd[0]) {
+ // Means interrupt has been called and mSessionIsActive should be reread
+ } else {
+ /* This can result in some starvation if there are multiple
+ * threads which are annotating heavily, but it is not
+ * recommended that threads annotate that much as it can also
+ * starve out the gator data.
+ */
+ while (gSessionData->mSessionIsActive) {
+ // Wait until there is enough room for the fd, two headers and two ints
+ waitFor(7*Buffer::MAXSIZE_PACK32 + 2*sizeof(uint32_t));
+ mBuffer.packInt(fd);
+ const int contiguous = mBuffer.contiguousSpaceAvailable();
+ const int bytes = read(fd, mBuffer.getWritePos(), contiguous);
+ if (bytes < 0) {
+ if (errno == EAGAIN) {
+ // Nothing left to read
+ mBuffer.commit(currTime, true);
+ break;
+ }
+ // Something else failed, close the socket
+ mBuffer.commit(currTime, true);
+ mBuffer.packInt(-1);
+ mBuffer.packInt(fd);
+ // Here and other commits, always force-flush the buffer as this frame don't work like others
+ mBuffer.commit(currTime, true);
+ close(fd);
+ break;
+ } else if (bytes == 0) {
+ // The other side is closed
+ mBuffer.commit(currTime, true);
+ mBuffer.packInt(-1);
+ mBuffer.packInt(fd);
+ mBuffer.commit(currTime, true);
+ close(fd);
+ break;
+ }
+
+ mBuffer.advanceWrite(bytes);
+ mBuffer.commit(currTime, true);
+
+ // Short reads also mean nothing is left to read
+ if (bytes < contiguous) {
+ break;
+ }
+ }
+ }
+ }
+ }
+
+ mBuffer.setDone();
+
+ if (mMveUds >= 0) {
+ gSessionData->maliVideo.stop(mMveUds);
+ }
+
+ mInterruptFd = -1;
+ close(pipefd[0]);
+ close(pipefd[1]);
+}
+
+void ExternalSource::interrupt() {
+ if (mInterruptFd >= 0) {
+ int8_t c = 0;
+ // Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+ if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+ logg->logError("write failed");
+ handleException();
+ }
+ }
+}
+
+bool ExternalSource::isDone() {
+ return mBuffer.isDone();
+}
+
+void ExternalSource::write(Sender *sender) {
+ // Don't send external data until the summary packet is sent so that monotonic delta is available
+ if (!gSessionData->mSentSummary) {
+ return;
+ }
+ if (!mBuffer.isDone()) {
+ mBuffer.write(sender);
+ sem_post(&mBufferSem);
+ }
+}
diff --git a/tools/gator/daemon/ExternalSource.h b/tools/gator/daemon/ExternalSource.h
new file mode 100644
index 0000000..25ae7cd4
--- /dev/null
+++ b/tools/gator/daemon/ExternalSource.h
@@ -0,0 +1,54 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef EXTERNALSOURCE_H
+#define EXTERNALSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "Source.h"
+
+// Counters from external sources like graphics drivers and annotations
+class ExternalSource : public Source {
+public:
+ ExternalSource(sem_t *senderSem);
+ ~ExternalSource();
+
+ bool prepare();
+ void run();
+ void interrupt();
+
+ bool isDone();
+ void write(Sender *sender);
+
+private:
+ void waitFor(const int bytes);
+ void configureConnection(const int fd, const char *const handshake, size_t size);
+ bool connectMali();
+ bool connectMve();
+
+ sem_t mBufferSem;
+ Buffer mBuffer;
+ Monitor mMonitor;
+ OlyServerSocket mMveStartupUds;
+ OlyServerSocket mMaliStartupUds;
+ OlyServerSocket mAnnotate;
+ OlyServerSocket mAnnotateUds;
+ int mInterruptFd;
+ int mMaliUds;
+ int mMveUds;
+
+ // Intentionally unimplemented
+ ExternalSource(const ExternalSource &);
+ ExternalSource &operator=(const ExternalSource &);
+};
+
+#endif // EXTERNALSOURCE_H
diff --git a/tools/gator/daemon/FSDriver.cpp b/tools/gator/daemon/FSDriver.cpp
new file mode 100644
index 0000000..afac9df
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.cpp
@@ -0,0 +1,156 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FSDriver.h"
+
+#include <fcntl.h>
+#include <regex.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+
+class FSCounter : public DriverCounter {
+public:
+ FSCounter(DriverCounter *next, char *name, char *path, const char *regex);
+ ~FSCounter();
+
+ const char *getPath() const { return mPath; }
+
+ int64_t read();
+
+private:
+ char *const mPath;
+ regex_t mReg;
+ bool mUseRegex;
+
+ // Intentionally unimplemented
+ FSCounter(const FSCounter &);
+ FSCounter &operator=(const FSCounter &);
+};
+
+FSCounter::FSCounter(DriverCounter *next, char *name, char *path, const char *regex) : DriverCounter(next, name), mPath(path), mUseRegex(regex != NULL) {
+ if (mUseRegex) {
+ int result = regcomp(&mReg, regex, REG_EXTENDED);
+ if (result != 0) {
+ char buf[128];
+ regerror(result, &mReg, buf, sizeof(buf));
+ logg->logError("Invalid regex '%s': %s", regex, buf);
+ handleException();
+ }
+ }
+}
+
+FSCounter::~FSCounter() {
+ free(mPath);
+ if (mUseRegex) {
+ regfree(&mReg);
+ }
+}
+
+int64_t FSCounter::read() {
+ int64_t value;
+ if (mUseRegex) {
+ char buf[4096];
+ size_t pos = 0;
+ const int fd = open(mPath, O_RDONLY | O_CLOEXEC);
+ if (fd < 0) {
+ goto fail;
+ }
+ while (pos < sizeof(buf) - 1) {
+ const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+ if (bytes < 0) {
+ goto fail;
+ } else if (bytes == 0) {
+ break;
+ }
+ pos += bytes;
+ }
+ close(fd);
+ buf[pos] = '\0';
+
+ regmatch_t match[2];
+ int result = regexec(&mReg, buf, 2, match, 0);
+ if (result != 0) {
+ // No match
+ return 0;
+ }
+
+ if (match[1].rm_so < 0) {
+ value = 1;
+ } else {
+ errno = 0;
+ value = strtoll(buf + match[1].rm_so, NULL, 0);
+ if (errno != 0) {
+ logg->logError("Parsing %s failed: %s", mPath, strerror(errno));
+ handleException();
+ }
+ }
+ } else {
+ if (DriverSource::readInt64Driver(mPath, &value) != 0) {
+ goto fail;
+ }
+ }
+ return value;
+
+ fail:
+ logg->logError("Unable to read %s", mPath);
+ handleException();
+}
+
+FSDriver::FSDriver() {
+}
+
+FSDriver::~FSDriver() {
+}
+
+void FSDriver::readEvents(mxml_node_t *const xml) {
+ mxml_node_t *node = xml;
+ while (true) {
+ node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+ if (node == NULL) {
+ break;
+ }
+ const char *counter = mxmlElementGetAttr(node, "counter");
+ if (counter == NULL) {
+ continue;
+ }
+
+ if (counter[0] == '/') {
+ logg->logError("Old style filesystem counter (%s) detected, please create a new unique counter value and move the filename into the path attribute, see events-Filesystem.xml for examples", counter);
+ handleException();
+ }
+
+ if (strncmp(counter, "filesystem_", 11) != 0) {
+ continue;
+ }
+
+ const char *path = mxmlElementGetAttr(node, "path");
+ if (path == NULL) {
+ logg->logError("The filesystem counter %s is missing the required path attribute", counter);
+ handleException();
+ }
+ const char *regex = mxmlElementGetAttr(node, "regex");
+ setCounters(new FSCounter(getCounters(), strdup(counter), strdup(path), regex));
+ }
+}
+
+int FSDriver::writeCounters(mxml_node_t *root) const {
+ int count = 0;
+ for (FSCounter *counter = static_cast<FSCounter *>(getCounters()); counter != NULL; counter = static_cast<FSCounter *>(counter->getNext())) {
+ if (access(counter->getPath(), R_OK) == 0) {
+ mxml_node_t *node = mxmlNewElement(root, "counter");
+ mxmlElementSetAttr(node, "name", counter->getName());
+ ++count;
+ }
+ }
+
+ return count;
+}
diff --git a/tools/gator/daemon/FSDriver.h b/tools/gator/daemon/FSDriver.h
new file mode 100644
index 0000000..63a4e90
--- /dev/null
+++ b/tools/gator/daemon/FSDriver.h
@@ -0,0 +1,29 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FSDRIVER_H
+#define FSDRIVER_H
+
+#include "Driver.h"
+
+class FSDriver : public PolledDriver {
+public:
+ FSDriver();
+ ~FSDriver();
+
+ void readEvents(mxml_node_t *const xml);
+
+ int writeCounters(mxml_node_t *root) const;
+
+private:
+ // Intentionally unimplemented
+ FSDriver(const FSDriver &);
+ FSDriver &operator=(const FSDriver &);
+};
+
+#endif // FSDRIVER_H
diff --git a/tools/gator/daemon/Fifo.cpp b/tools/gator/daemon/Fifo.cpp
new file mode 100644
index 0000000..8d3b9ff
--- /dev/null
+++ b/tools/gator/daemon/Fifo.cpp
@@ -0,0 +1,127 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Fifo.h"
+
+#include <stdlib.h>
+
+#include "Logging.h"
+
+// bufferSize is the amount of data to be filled
+// singleBufferSize is the maximum size that may be filled during a single write
+// (bufferSize + singleBufferSize) will be allocated
+Fifo::Fifo(int singleBufferSize, int bufferSize, sem_t* readerSem) {
+ mWrite = mRead = mReadCommit = mRaggedEnd = 0;
+ mWrapThreshold = bufferSize;
+ mSingleBufferSize = singleBufferSize;
+ mReaderSem = readerSem;
+ mBuffer = (char*)malloc(bufferSize + singleBufferSize);
+ mEnd = false;
+
+ if (mBuffer == NULL) {
+ logg->logError("failed to allocate %d bytes", bufferSize + singleBufferSize);
+ handleException();
+ }
+
+ if (sem_init(&mWaitForSpaceSem, 0, 0)) {
+ logg->logError("sem_init() failed");
+ handleException();
+ }
+}
+
+Fifo::~Fifo() {
+ free(mBuffer);
+ sem_destroy(&mWaitForSpaceSem);
+}
+
+int Fifo::numBytesFilled() const {
+ return mWrite - mRead + mRaggedEnd;
+}
+
+char* Fifo::start() const {
+ return mBuffer;
+}
+
+bool Fifo::isEmpty() const {
+ return mRead == mWrite && mRaggedEnd == 0;
+}
+
+bool Fifo::isFull() const {
+ return willFill(0);
+}
+
+// Determines if the buffer will fill assuming 'additional' bytes will be added to the buffer
+// 'full' means there is less than singleBufferSize bytes available contiguously; it does not mean there are zero bytes available
+bool Fifo::willFill(int additional) const {
+ if (mWrite > mRead) {
+ if (numBytesFilled() + additional < mWrapThreshold) {
+ return false;
+ }
+ } else {
+ if (numBytesFilled() + additional < mWrapThreshold - mSingleBufferSize) {
+ return false;
+ }
+ }
+ return true;
+}
+
+// This function will stall until contiguous singleBufferSize bytes are available
+char* Fifo::write(int length) {
+ if (length <= 0) {
+ length = 0;
+ mEnd = true;
+ }
+
+ // update the write pointer
+ mWrite += length;
+
+ // handle the wrap-around
+ if (mWrite >= mWrapThreshold) {
+ mRaggedEnd = mWrite;
+ mWrite = 0;
+ }
+
+ // send a notification that data is ready
+ sem_post(mReaderSem);
+
+ // wait for space
+ while (isFull()) {
+ sem_wait(&mWaitForSpaceSem);
+ }
+
+ return &mBuffer[mWrite];
+}
+
+void Fifo::release() {
+ // update the read pointer now that the data has been handled
+ mRead = mReadCommit;
+
+ // handle the wrap-around
+ if (mRead >= mWrapThreshold) {
+ mRaggedEnd = mRead = mReadCommit = 0;
+ }
+
+ // send a notification that data is free (space is available)
+ sem_post(&mWaitForSpaceSem);
+}
+
+// This function will return null if no data is available
+char* Fifo::read(int *const length) {
+ // wait for data
+ if (isEmpty() && !mEnd) {
+ return NULL;
+ }
+
+ // obtain the length
+ do {
+ mReadCommit = mRaggedEnd ? mRaggedEnd : mWrite;
+ *length = mReadCommit - mRead;
+ } while (*length < 0); // plugs race condition without using semaphores
+
+ return &mBuffer[mRead];
+}
diff --git a/tools/gator/daemon/Fifo.h b/tools/gator/daemon/Fifo.h
new file mode 100644
index 0000000..01fa11b
--- /dev/null
+++ b/tools/gator/daemon/Fifo.h
@@ -0,0 +1,48 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __FIFO_H__
+#define __FIFO_H__
+
+#ifdef WIN32
+#include <windows.h>
+#define sem_t HANDLE
+#define sem_init(sem, pshared, value) ((*(sem) = CreateSemaphore(NULL, value, LONG_MAX, NULL)) == NULL)
+#define sem_wait(sem) WaitForSingleObject(*(sem), INFINITE)
+#define sem_post(sem) ReleaseSemaphore(*(sem), 1, NULL)
+#define sem_destroy(sem) CloseHandle(*(sem))
+#else
+#include <semaphore.h>
+#endif
+
+class Fifo {
+public:
+ Fifo(int singleBufferSize, int totalBufferSize, sem_t* readerSem);
+ ~Fifo();
+ int numBytesFilled() const;
+ bool isEmpty() const;
+ bool isFull() const;
+ bool willFill(int additional) const;
+ char* start() const;
+ char* write(int length);
+ void release();
+ char* read(int *const length);
+
+private:
+ int mSingleBufferSize, mWrite, mRead, mReadCommit, mRaggedEnd, mWrapThreshold;
+ sem_t mWaitForSpaceSem;
+ sem_t* mReaderSem;
+ char* mBuffer;
+ bool mEnd;
+
+ // Intentionally unimplemented
+ Fifo(const Fifo &);
+ Fifo &operator=(const Fifo &);
+};
+
+#endif //__FIFO_H__
diff --git a/tools/gator/daemon/FtraceDriver.cpp b/tools/gator/daemon/FtraceDriver.cpp
new file mode 100644
index 0000000..98bd0a5
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.cpp
@@ -0,0 +1,195 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceDriver.h"
+
+#include <regex.h>
+#include <unistd.h>
+
+#include "DriverSource.h"
+#include "Logging.h"
+#include "Setup.h"
+
+class FtraceCounter : public DriverCounter {
+public:
+ FtraceCounter(DriverCounter *next, char *name, const char *regex, const char *enable);
+ ~FtraceCounter();
+
+ void prepare();
+ int read(const char *const line, int64_t *values);
+ void stop();
+
+private:
+ regex_t mReg;
+ char *const mEnable;
+ int mWasEnabled;
+
+ // Intentionally unimplemented
+ FtraceCounter(const FtraceCounter &);
+ FtraceCounter &operator=(const FtraceCounter &);
+};
+
+FtraceCounter::FtraceCounter(DriverCounter *next, char *name, const char *regex, const char *enable) : DriverCounter(next, name), mEnable(enable == NULL ? NULL : strdup(enable)) {
+ int result = regcomp(&mReg, regex, REG_EXTENDED);
+ if (result != 0) {
+ char buf[128];
+ regerror(result, &mReg, buf, sizeof(buf));
+ logg->logError("Invalid regex '%s': %s", regex, buf);
+ handleException();
+ }
+}
+
+FtraceCounter::~FtraceCounter() {
+ regfree(&mReg);
+ if (mEnable != NULL) {
+ free(mEnable);
+ }
+}
+
+void FtraceCounter::prepare() {
+ if (mEnable == NULL) {
+ return;
+ }
+
+ char buf[1<<10];
+ snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%s/enable", mEnable);
+ if ((DriverSource::readIntDriver(buf, &mWasEnabled) != 0) ||
+ (DriverSource::writeDriver(buf, 1) != 0)) {
+ logg->logError("Unable to read or write to %s", buf);
+ handleException();
+ }
+}
+
+int FtraceCounter::read(const char *const line, int64_t *values) {
+ regmatch_t match[2];
+ int result = regexec(&mReg, line, 2, match, 0);
+ if (result != 0) {
+ // No match
+ return 0;
+ }
+
+ int64_t value;
+ if (match[1].rm_so < 0) {
+ value = 1;
+ } else {
+ errno = 0;
+ value = strtoll(line + match[1].rm_so, NULL, 0);
+ if (errno != 0) {
+ logg->logError("Parsing %s failed: %s", getName(), strerror(errno));
+ handleException();
+ }
+ }
+
+ values[0] = getKey();
+ values[1] = value;
+
+ return 1;
+}
+
+void FtraceCounter::stop() {
+ if (mEnable == NULL) {
+ return;
+ }
+
+ char buf[1<<10];
+ snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%s/enable", mEnable);
+ DriverSource::writeDriver(buf, mWasEnabled);
+}
+
+FtraceDriver::FtraceDriver() : mValues(NULL) {
+}
+
+FtraceDriver::~FtraceDriver() {
+ delete [] mValues;
+}
+
+void FtraceDriver::readEvents(mxml_node_t *const xml) {
+ // Check the kernel version
+ int release[3];
+ if (!getLinuxVersion(release)) {
+ logg->logError("getLinuxVersion failed");
+ handleException();
+ }
+
+ // The perf clock was added in 3.10
+ if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 10, 0)) {
+ logg->logMessage("Unsupported kernel version, to use ftrace please upgrade to Linux 3.10 or later");
+ return;
+ }
+
+ mxml_node_t *node = xml;
+ int count = 0;
+ while (true) {
+ node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+ if (node == NULL) {
+ break;
+ }
+ const char *counter = mxmlElementGetAttr(node, "counter");
+ if (counter == NULL) {
+ continue;
+ }
+
+ if (strncmp(counter, "ftrace_", 7) != 0) {
+ continue;
+ }
+
+ const char *regex = mxmlElementGetAttr(node, "regex");
+ if (regex == NULL) {
+ logg->logError("The regex counter %s is missing the required regex attribute", counter);
+ handleException();
+ }
+ bool addCounter = true;
+ const char *enable = mxmlElementGetAttr(node, "enable");
+ if (enable != NULL) {
+ char buf[1<<10];
+ snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/events/%s/enable", enable);
+ if (access(buf, W_OK) != 0) {
+ logg->logMessage("Disabling counter %s, %s not found", counter, buf);
+ addCounter = false;
+ }
+ }
+ if (addCounter) {
+ setCounters(new FtraceCounter(getCounters(), strdup(counter), regex, enable));
+ ++count;
+ }
+ }
+
+ mValues = new int64_t[2*count];
+}
+
+void FtraceDriver::prepare() {
+ for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->prepare();
+ }
+}
+
+int FtraceDriver::read(const char *line, int64_t **buf) {
+ int count = 0;
+
+ for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ count += counter->read(line, mValues + 2*count);
+ }
+
+ *buf = mValues;
+ return count;
+}
+
+void FtraceDriver::stop() {
+ for (FtraceCounter *counter = static_cast<FtraceCounter *>(getCounters()); counter != NULL; counter = static_cast<FtraceCounter *>(counter->getNext())) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->stop();
+ }
+}
diff --git a/tools/gator/daemon/FtraceDriver.h b/tools/gator/daemon/FtraceDriver.h
new file mode 100644
index 0000000..b79dc91
--- /dev/null
+++ b/tools/gator/daemon/FtraceDriver.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACEDRIVER_H
+#define FTRACEDRIVER_H
+
+#include "Driver.h"
+
+class FtraceDriver : public SimpleDriver {
+public:
+ FtraceDriver();
+ ~FtraceDriver();
+
+ void readEvents(mxml_node_t *const xml);
+
+ void prepare();
+ int read(const char *line, int64_t **buf);
+ void stop();
+
+private:
+ int64_t *mValues;
+
+ // Intentionally unimplemented
+ FtraceDriver(const FtraceDriver &);
+ FtraceDriver &operator=(const FtraceDriver &);
+};
+
+#endif // FTRACEDRIVER_H
diff --git a/tools/gator/daemon/FtraceSource.cpp b/tools/gator/daemon/FtraceSource.cpp
new file mode 100644
index 0000000..14a48b3
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.cpp
@@ -0,0 +1,188 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "FtraceSource.h"
+
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+static void handler(int signum)
+{
+ (void)signum;
+};
+
+FtraceSource::FtraceSource(sem_t *senderSem) : mFtraceFh(NULL), mBuffer(0, FRAME_BLOCK_COUNTER, 128*1024, senderSem), mTid(-1), mTracingOn(0) {
+}
+
+FtraceSource::~FtraceSource() {
+}
+
+bool FtraceSource::prepare() {
+ {
+ struct sigaction act;
+ act.sa_handler = handler;
+ act.sa_flags = (int)SA_RESETHAND;
+ if (sigaction(SIGUSR1, &act, NULL) != 0) {
+ logg->logError("sigaction failed: %s\n", strerror(errno));
+ handleException();
+ }
+ }
+
+ gSessionData->ftraceDriver.prepare();
+
+ if (DriverSource::readIntDriver("/sys/kernel/debug/tracing/tracing_on", &mTracingOn)) {
+ logg->logError("Unable to read if ftrace is enabled");
+ handleException();
+ }
+
+ if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "0") != 0) {
+ logg->logError("Unable to turn ftrace off before truncating the buffer");
+ handleException();
+ }
+
+ {
+ int fd;
+ fd = open("/sys/kernel/debug/tracing/trace", O_WRONLY | O_TRUNC | O_CLOEXEC, 0666);
+ if (fd < 0) {
+ logg->logError("Unable truncate ftrace buffer: %s", strerror(errno));
+ handleException();
+ }
+ close(fd);
+ }
+
+ if (DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "perf") != 0) {
+ logg->logError("Unable to switch ftrace to the perf clock, please ensure you are running Linux 3.10 or later");
+ handleException();
+ }
+
+ mFtraceFh = fopen_cloexec("/sys/kernel/debug/tracing/trace_pipe", "rb");
+ if (mFtraceFh == NULL) {
+ logg->logError("Unable to open trace_pipe");
+ handleException();
+ }
+
+ return true;
+}
+
+void FtraceSource::run() {
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-ftrace", 0, 0, 0);
+ mTid = syscall(__NR_gettid);
+
+ if (DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", "1") != 0) {
+ logg->logError("Unable to turn ftrace on");
+ handleException();
+ }
+
+ // Wait until monotonicStarted is set before sending data
+ int64_t monotonicStarted = 0;
+ while (monotonicStarted <= 0 && gSessionData->mSessionIsActive) {
+ usleep(10);
+
+ if (gSessionData->perf.isSetup()) {
+ monotonicStarted = gSessionData->mMonotonicStarted;
+ } else {
+ if (DriverSource::readInt64Driver("/dev/gator/started", &monotonicStarted) == -1) {
+ logg->logError("Error reading gator driver start time");
+ handleException();
+ }
+ }
+ }
+
+ while (gSessionData->mSessionIsActive) {
+ char buf[1<<12];
+
+ if (fgets(buf, sizeof(buf), mFtraceFh) == NULL) {
+ if (errno == EINTR) {
+ // Interrupted by interrupt - likely user request to terminate
+ break;
+ }
+ logg->logError("Unable read trace data: %s", strerror(errno));
+ handleException();
+ }
+
+ const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+ char *const colon = strstr(buf, ": ");
+ if (colon == NULL) {
+ if (strstr(buf, " [LOST ") != NULL) {
+ logg->logError("Ftrace events lost, aborting the capture. It is recommended to discard this report and collect a new capture. If this error occurs often, please reduce the number of ftrace counters selected or the amount of ftrace events generated.");
+ } else {
+ logg->logError("Unable to find colon: %s", buf);
+ }
+ handleException();
+ }
+ *colon = '\0';
+
+ char *const space = strrchr(buf, ' ');
+ if (space == NULL) {
+ logg->logError("Unable to find space: %s", buf);
+ handleException();
+ }
+ *colon = ':';
+
+ int64_t *data = NULL;
+ int count = gSessionData->ftraceDriver.read(colon + 2, &data);
+ if (count > 0) {
+ errno = 0;
+ const long long time = strtod(space, NULL) * 1000000000;
+ if (errno != 0) {
+ logg->logError("Unable to parse time: %s", strerror(errno));
+ handleException();
+ }
+ mBuffer.event64(-1, time);
+
+ for (int i = 0; i < count; ++i) {
+ mBuffer.event64(data[2*i + 0], data[2*i + 1]);
+ }
+
+ mBuffer.check(currTime);
+
+ if (gSessionData->mOneShot && gSessionData->mSessionIsActive && (mBuffer.bytesAvailable() <= 0)) {
+ logg->logMessage("One shot (ftrace)");
+ child->endSession();
+ }
+ }
+
+ }
+
+ mBuffer.setDone();
+
+ DriverSource::writeDriver("/sys/kernel/debug/tracing/tracing_on", mTracingOn);
+ fclose(mFtraceFh);
+ DriverSource::writeDriver("/sys/kernel/debug/tracing/trace_clock", "local");
+ gSessionData->ftraceDriver.stop();
+}
+
+void FtraceSource::interrupt() {
+ // Closing the underlying file handle does not result in the read on the ftrace file handle to return, so send a signal to the thread
+ syscall(__NR_tgkill, getpid(), mTid, SIGUSR1);
+}
+
+bool FtraceSource::isDone() {
+ return mBuffer.isDone();
+}
+
+void FtraceSource::write(Sender *sender) {
+ // Don't send ftrace data until the summary packet is sent so that monotonic delta is available
+ if (!gSessionData->mSentSummary) {
+ return;
+ }
+ if (!mBuffer.isDone()) {
+ mBuffer.write(sender);
+ }
+}
diff --git a/tools/gator/daemon/FtraceSource.h b/tools/gator/daemon/FtraceSource.h
new file mode 100644
index 0000000..bc068d2
--- /dev/null
+++ b/tools/gator/daemon/FtraceSource.h
@@ -0,0 +1,43 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef FTRACESOURCE_H
+#define FTRACESOURCE_H
+
+#include <semaphore.h>
+#include <stdio.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+class FtraceSource : public Source {
+public:
+ FtraceSource(sem_t *senderSem);
+ ~FtraceSource();
+
+ bool prepare();
+ void run();
+ void interrupt();
+
+ bool isDone();
+ void write(Sender *sender);
+
+private:
+ void waitFor(const int bytes);
+
+ FILE *mFtraceFh;
+ Buffer mBuffer;
+ int mTid;
+ int mTracingOn;
+
+ // Intentionally unimplemented
+ FtraceSource(const FtraceSource &);
+ FtraceSource &operator=(const FtraceSource &);
+};
+
+#endif // FTRACESOURCE_H
diff --git a/tools/gator/daemon/HwmonDriver.cpp b/tools/gator/daemon/HwmonDriver.cpp
new file mode 100644
index 0000000..d8353b0
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.cpp
@@ -0,0 +1,245 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "HwmonDriver.h"
+
+#include "libsensors/sensors.h"
+
+#include "Logging.h"
+
+// feature->type to input map
+static sensors_subfeature_type getInput(const sensors_feature_type type) {
+ switch (type) {
+ case SENSORS_FEATURE_IN: return SENSORS_SUBFEATURE_IN_INPUT;
+ case SENSORS_FEATURE_FAN: return SENSORS_SUBFEATURE_FAN_INPUT;
+ case SENSORS_FEATURE_TEMP: return SENSORS_SUBFEATURE_TEMP_INPUT;
+ case SENSORS_FEATURE_POWER: return SENSORS_SUBFEATURE_POWER_INPUT;
+ case SENSORS_FEATURE_ENERGY: return SENSORS_SUBFEATURE_ENERGY_INPUT;
+ case SENSORS_FEATURE_CURR: return SENSORS_SUBFEATURE_CURR_INPUT;
+ case SENSORS_FEATURE_HUMIDITY: return SENSORS_SUBFEATURE_HUMIDITY_INPUT;
+ default:
+ logg->logError("Unsupported hwmon feature %i", type);
+ handleException();
+ }
+};
+
+class HwmonCounter : public DriverCounter {
+public:
+ HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *chip, const sensors_feature *feature);
+ ~HwmonCounter();
+
+ const char *getLabel() const { return mLabel; }
+ const char *getTitle() const { return mTitle; }
+ bool isDuplicate() const { return mDuplicate; }
+ const char *getDisplay() const { return mDisplay; }
+ const char *getCounterClass() const { return mCounterClass; }
+ const char *getUnit() const { return mUnit; }
+ double getMultiplier() const { return mMultiplier; }
+
+ int64_t read();
+
+private:
+ void init(const sensors_chip_name *chip, const sensors_feature *feature);
+
+ const sensors_chip_name *mChip;
+ const sensors_feature *mFeature;
+ char *mLabel;
+ const char *mTitle;
+ const char *mDisplay;
+ const char *mCounterClass;
+ const char *mUnit;
+ double mPreviousValue;
+ double mMultiplier;
+ int mMonotonic: 1,
+ mDuplicate : 1;
+
+ // Intentionally unimplemented
+ HwmonCounter(const HwmonCounter &);
+ HwmonCounter &operator=(const HwmonCounter &);
+};
+
+HwmonCounter::HwmonCounter(DriverCounter *next, char *const name, const sensors_chip_name *const chip, const sensors_feature *feature) : DriverCounter(next, name), mChip(chip), mFeature(feature), mDuplicate(false) {
+ mLabel = sensors_get_label(mChip, mFeature);
+
+ switch (mFeature->type) {
+ case SENSORS_FEATURE_IN:
+ mTitle = "Voltage";
+ mDisplay = "maximum";
+ mCounterClass = "absolute";
+ mUnit = "V";
+ mMultiplier = 0.001;
+ mMonotonic = false;
+ break;
+ case SENSORS_FEATURE_FAN:
+ mTitle = "Fan";
+ mDisplay = "average";
+ mCounterClass = "absolute";
+ mUnit = "RPM";
+ mMultiplier = 1.0;
+ mMonotonic = false;
+ break;
+ case SENSORS_FEATURE_TEMP:
+ mTitle = "Temperature";
+ mDisplay = "maximum";
+ mCounterClass = "absolute";
+ mUnit = "°C";
+ mMultiplier = 0.001;
+ mMonotonic = false;
+ break;
+ case SENSORS_FEATURE_POWER:
+ mTitle = "Power";
+ mDisplay = "maximum";
+ mCounterClass = "absolute";
+ mUnit = "W";
+ mMultiplier = 0.000001;
+ mMonotonic = false;
+ break;
+ case SENSORS_FEATURE_ENERGY:
+ mTitle = "Energy";
+ mDisplay = "accumulate";
+ mCounterClass = "delta";
+ mUnit = "J";
+ mMultiplier = 0.000001;
+ mMonotonic = true;
+ break;
+ case SENSORS_FEATURE_CURR:
+ mTitle = "Current";
+ mDisplay = "maximum";
+ mCounterClass = "absolute";
+ mUnit = "A";
+ mMultiplier = 0.001;
+ mMonotonic = false;
+ break;
+ case SENSORS_FEATURE_HUMIDITY:
+ mTitle = "Humidity";
+ mDisplay = "average";
+ mCounterClass = "absolute";
+ mUnit = "%";
+ mMultiplier = 0.001;
+ mMonotonic = false;
+ break;
+ default:
+ logg->logError("Unsupported hwmon feature %i", mFeature->type);
+ handleException();
+ }
+
+ for (HwmonCounter * counter = static_cast<HwmonCounter *>(next); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+ if (strcmp(mLabel, counter->getLabel()) == 0 && strcmp(mTitle, counter->getTitle()) == 0) {
+ mDuplicate = true;
+ counter->mDuplicate = true;
+ break;
+ }
+ }
+}
+
+HwmonCounter::~HwmonCounter() {
+ free((void *)mLabel);
+}
+
+int64_t HwmonCounter::read() {
+ double value;
+ double result;
+ const sensors_subfeature *subfeature;
+
+ // Keep in sync with the read check in HwmonDriver::readEvents
+ subfeature = sensors_get_subfeature(mChip, mFeature, getInput(mFeature->type));
+ if (!subfeature) {
+ logg->logError("No input value for hwmon sensor %s", mLabel);
+ handleException();
+ }
+
+ if (sensors_get_value(mChip, subfeature->number, &value) != 0) {
+ logg->logError("Can't get input value for hwmon sensor %s", mLabel);
+ handleException();
+ }
+
+ result = (mMonotonic ? value - mPreviousValue : value);
+ mPreviousValue = value;
+
+ return result;
+}
+
+HwmonDriver::HwmonDriver() {
+}
+
+HwmonDriver::~HwmonDriver() {
+ sensors_cleanup();
+}
+
+void HwmonDriver::readEvents(mxml_node_t *const) {
+ int err = sensors_init(NULL);
+ if (err) {
+ logg->logMessage("Failed to initialize libsensors! (%d)", err);
+ return;
+ }
+ sensors_sysfs_no_scaling = 1;
+
+ int chip_nr = 0;
+ const sensors_chip_name *chip;
+ while ((chip = sensors_get_detected_chips(NULL, &chip_nr))) {
+ int feature_nr = 0;
+ const sensors_feature *feature;
+ while ((feature = sensors_get_features(chip, &feature_nr))) {
+ // Keep in sync with HwmonCounter::read
+ // Can this counter be read?
+ double value;
+ const sensors_subfeature *const subfeature = sensors_get_subfeature(chip, feature, getInput(feature->type));
+ if ((subfeature == NULL) || (sensors_get_value(chip, subfeature->number, &value) != 0)) {
+ continue;
+ }
+
+ // Get the name of the counter
+ int len = sensors_snprintf_chip_name(NULL, 0, chip) + 1;
+ char *chip_name = new char[len];
+ sensors_snprintf_chip_name(chip_name, len, chip);
+ len = snprintf(NULL, 0, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number) + 1;
+ char *const name = new char[len];
+ snprintf(name, len, "hwmon_%s_%d_%d", chip_name, chip_nr, feature->number);
+ delete [] chip_name;
+
+ setCounters(new HwmonCounter(getCounters(), name, chip, feature));
+ }
+ }
+}
+
+void HwmonDriver::writeEvents(mxml_node_t *root) const {
+ root = mxmlNewElement(root, "category");
+ mxmlElementSetAttr(root, "name", "Hardware Monitor");
+
+ char buf[1024];
+ for (HwmonCounter *counter = static_cast<HwmonCounter *>(getCounters()); counter != NULL; counter = static_cast<HwmonCounter *>(counter->getNext())) {
+ mxml_node_t *node = mxmlNewElement(root, "event");
+ mxmlElementSetAttr(node, "counter", counter->getName());
+ mxmlElementSetAttr(node, "title", counter->getTitle());
+ if (counter->isDuplicate()) {
+ mxmlElementSetAttrf(node, "name", "%s (0x%x)", counter->getLabel(), counter->getKey());
+ } else {
+ mxmlElementSetAttr(node, "name", counter->getLabel());
+ }
+ mxmlElementSetAttr(node, "display", counter->getDisplay());
+ mxmlElementSetAttr(node, "class", counter->getCounterClass());
+ mxmlElementSetAttr(node, "units", counter->getUnit());
+ if (counter->getMultiplier() != 1.0) {
+ mxmlElementSetAttrf(node, "multiplier", "%lf", counter->getMultiplier());
+ }
+ if (strcmp(counter->getDisplay(), "average") == 0 || strcmp(counter->getDisplay(), "maximum") == 0) {
+ mxmlElementSetAttr(node, "average_selection", "yes");
+ }
+ snprintf(buf, sizeof(buf), "libsensors %s sensor %s (%s)", counter->getTitle(), counter->getLabel(), counter->getName());
+ mxmlElementSetAttr(node, "description", buf);
+ }
+}
+
+void HwmonDriver::start() {
+ for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->read();
+ }
+}
diff --git a/tools/gator/daemon/HwmonDriver.h b/tools/gator/daemon/HwmonDriver.h
new file mode 100644
index 0000000..f15d557
--- /dev/null
+++ b/tools/gator/daemon/HwmonDriver.h
@@ -0,0 +1,31 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef HWMONDRIVER_H
+#define HWMONDRIVER_H
+
+#include "Driver.h"
+
+class HwmonDriver : public PolledDriver {
+public:
+ HwmonDriver();
+ ~HwmonDriver();
+
+ void readEvents(mxml_node_t *const root);
+
+ void writeEvents(mxml_node_t *root) const;
+
+ void start();
+
+private:
+ // Intentionally unimplemented
+ HwmonDriver(const HwmonDriver &);
+ HwmonDriver &operator=(const HwmonDriver &);
+};
+
+#endif // HWMONDRIVER_H
diff --git a/tools/gator/daemon/KMod.cpp b/tools/gator/daemon/KMod.cpp
new file mode 100644
index 0000000..e33b499
--- /dev/null
+++ b/tools/gator/daemon/KMod.cpp
@@ -0,0 +1,119 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "KMod.h"
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <unistd.h>
+
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// Claim all the counters in /dev/gator/events
+bool KMod::claimCounter(const Counter &counter) const {
+ char text[128];
+ snprintf(text, sizeof(text), "/dev/gator/events/%s", counter.getType());
+ return access(text, F_OK) == 0;
+}
+
+void KMod::resetCounters() {
+ char base[128];
+ char text[128];
+
+ // Initialize all perf counters in the driver, i.e. set enabled to zero
+ struct dirent *ent;
+ DIR* dir = opendir("/dev/gator/events");
+ if (dir) {
+ while ((ent = readdir(dir)) != NULL) {
+ // skip hidden files, current dir, and parent dir
+ if (ent->d_name[0] == '.')
+ continue;
+ snprintf(base, sizeof(base), "/dev/gator/events/%s", ent->d_name);
+ snprintf(text, sizeof(text), "%s/enabled", base);
+ DriverSource::writeDriver(text, 0);
+ snprintf(text, sizeof(text), "%s/count", base);
+ DriverSource::writeDriver(text, 0);
+ }
+ closedir(dir);
+ }
+}
+
+static const char ARM_MALI_MIDGARD[] = "ARM_Mali-Midgard_";
+static const char ARM_MALI_T[] = "ARM_Mali-T";
+
+void KMod::setupCounter(Counter &counter) {
+ char base[128];
+ char text[128];
+ snprintf(base, sizeof(base), "/dev/gator/events/%s", counter.getType());
+
+ if ((strncmp(counter.getType(), ARM_MALI_MIDGARD, sizeof(ARM_MALI_MIDGARD) - 1) == 0 ||
+ strncmp(counter.getType(), ARM_MALI_T, sizeof(ARM_MALI_T) - 1) == 0)) {
+ mIsMaliCapture = true;
+ }
+
+ snprintf(text, sizeof(text), "%s/enabled", base);
+ int enabled = true;
+ if (DriverSource::writeReadDriver(text, &enabled) || !enabled) {
+ counter.setEnabled(false);
+ return;
+ }
+
+ int value = 0;
+ snprintf(text, sizeof(text), "%s/key", base);
+ DriverSource::readIntDriver(text, &value);
+ counter.setKey(value);
+
+ snprintf(text, sizeof(text), "%s/cores", base);
+ if (DriverSource::readIntDriver(text, &value) == 0) {
+ counter.setCores(value);
+ }
+
+ snprintf(text, sizeof(text), "%s/event", base);
+ DriverSource::writeDriver(text, counter.getEvent());
+ snprintf(text, sizeof(text), "%s/count", base);
+ if (access(text, F_OK) == 0) {
+ int count = counter.getCount();
+ if (DriverSource::writeReadDriver(text, &count) && counter.getCount() > 0) {
+ logg->logError("Cannot enable EBS for %s:%i with a count of %d\n", counter.getType(), counter.getEvent(), counter.getCount());
+ handleException();
+ }
+ counter.setCount(count);
+ } else if (counter.getCount() > 0) {
+ ConfigurationXML::remove();
+ logg->logError("Event Based Sampling is only supported with kernel versions 3.0.0 and higher with CONFIG_PERF_EVENTS=y, and CONFIG_HW_PERF_EVENTS=y. The invalid configuration.xml has been removed.\n");
+ handleException();
+ }
+}
+
+int KMod::writeCounters(mxml_node_t *root) const {
+ struct dirent *ent;
+ mxml_node_t *counter;
+
+ // counters.xml is simply a file listing of /dev/gator/events
+ DIR* dir = opendir("/dev/gator/events");
+ if (dir == NULL) {
+ return 0;
+ }
+
+ int count = 0;
+ while ((ent = readdir(dir)) != NULL) {
+ // skip hidden files, current dir, and parent dir
+ if (ent->d_name[0] == '.')
+ continue;
+ counter = mxmlNewElement(root, "counter");
+ mxmlElementSetAttr(counter, "name", ent->d_name);
+ ++count;
+ }
+ closedir(dir);
+
+ return count;
+}
diff --git a/tools/gator/daemon/KMod.h b/tools/gator/daemon/KMod.h
new file mode 100644
index 0000000..7f06b4b
--- /dev/null
+++ b/tools/gator/daemon/KMod.h
@@ -0,0 +1,32 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KMOD_H
+#define KMOD_H
+
+#include "Driver.h"
+
+// Driver for the gator kernel module
+class KMod : public Driver {
+public:
+ KMod() : mIsMaliCapture(false) {}
+ ~KMod() {}
+
+ bool claimCounter(const Counter &counter) const;
+ void resetCounters();
+ void setupCounter(Counter &counter);
+
+ int writeCounters(mxml_node_t *root) const;
+
+ bool isMaliCapture() const { return mIsMaliCapture; }
+
+private:
+ bool mIsMaliCapture;
+};
+
+#endif // KMOD_H
diff --git a/tools/gator/daemon/LocalCapture.cpp b/tools/gator/daemon/LocalCapture.cpp
new file mode 100644
index 0000000..5689987
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.cpp
@@ -0,0 +1,131 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "LocalCapture.h"
+
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "SessionData.h"
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "EventsXML.h"
+
+LocalCapture::LocalCapture() {}
+
+LocalCapture::~LocalCapture() {}
+
+void LocalCapture::createAPCDirectory(char* target_path) {
+ gSessionData->mAPCDir = createUniqueDirectory(target_path, ".apc");
+ if ((removeDirAndAllContents(gSessionData->mAPCDir) != 0 || mkdir(gSessionData->mAPCDir, S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH) != 0)) {
+ logg->logError("Unable to create directory %s", gSessionData->mAPCDir);
+ handleException();
+ }
+}
+
+void LocalCapture::write(char* string) {
+ char file[PATH_MAX];
+
+ // Set full path
+ snprintf(file, PATH_MAX, "%s/session.xml", gSessionData->mAPCDir);
+
+ // Write the file
+ if (util->writeToDisk(file, string) < 0) {
+ logg->logError("Error writing %s\nPlease verify the path.", file);
+ handleException();
+ }
+
+ // Write events XML
+ EventsXML eventsXML;
+ eventsXML.write(gSessionData->mAPCDir);
+}
+
+char* LocalCapture::createUniqueDirectory(const char* initialPath, const char* ending) {
+ char* output;
+ char path[PATH_MAX];
+
+ // Ensure the path is an absolute path, i.e. starts with a slash
+ if (initialPath == 0 || strlen(initialPath) == 0) {
+ logg->logError("Missing -o command line option required for a local capture.");
+ handleException();
+ } else if (initialPath[0] != '/') {
+ if (getcwd(path, PATH_MAX) == 0) {
+ logg->logMessage("Unable to retrieve the current working directory");
+ }
+ strncat(path, "/", PATH_MAX - strlen(path) - 1);
+ strncat(path, initialPath, PATH_MAX - strlen(path) - 1);
+ } else {
+ strncpy(path, initialPath, PATH_MAX);
+ path[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+ }
+
+ // Add ending if it is not already there
+ if (strcmp(&path[strlen(path) - strlen(ending)], ending) != 0) {
+ strncat(path, ending, PATH_MAX - strlen(path) - 1);
+ }
+
+ output = strdup(path);
+
+ return output;
+}
+
+int LocalCapture::removeDirAndAllContents(char* path) {
+ int error = 0;
+ struct stat mFileInfo;
+ // Does the path exist?
+ if (stat(path, &mFileInfo) == 0) {
+ // Is it a directory?
+ if (mFileInfo.st_mode & S_IFDIR) {
+ DIR * dir = opendir(path);
+ dirent* entry = readdir(dir);
+ while (entry) {
+ if (strcmp(entry->d_name, ".") != 0 && strcmp(entry->d_name, "..") != 0) {
+ char* newpath = (char*)malloc(strlen(path) + strlen(entry->d_name) + 2);
+ sprintf(newpath, "%s/%s", path, entry->d_name);
+ error = removeDirAndAllContents(newpath);
+ free(newpath);
+ if (error) {
+ break;
+ }
+ }
+ entry = readdir(dir);
+ }
+ closedir(dir);
+ if (error == 0) {
+ error = rmdir(path);
+ }
+ } else {
+ error = remove(path);
+ }
+ }
+ return error;
+}
+
+void LocalCapture::copyImages(ImageLinkList* ptr) {
+ char dstfilename[PATH_MAX];
+
+ while (ptr) {
+ strncpy(dstfilename, gSessionData->mAPCDir, PATH_MAX);
+ dstfilename[PATH_MAX - 1] = 0; // strncpy does not guarantee a null-terminated string
+ if (gSessionData->mAPCDir[strlen(gSessionData->mAPCDir) - 1] != '/') {
+ strncat(dstfilename, "/", PATH_MAX - strlen(dstfilename) - 1);
+ }
+ strncat(dstfilename, util->getFilePart(ptr->path), PATH_MAX - strlen(dstfilename) - 1);
+ if (util->copyFile(ptr->path, dstfilename)) {
+ logg->logMessage("copied file %s to %s", ptr->path, dstfilename);
+ } else {
+ logg->logMessage("copy of file %s to %s failed", ptr->path, dstfilename);
+ }
+
+ ptr = ptr->next;
+ }
+}
diff --git a/tools/gator/daemon/LocalCapture.h b/tools/gator/daemon/LocalCapture.h
new file mode 100644
index 0000000..807f49d
--- /dev/null
+++ b/tools/gator/daemon/LocalCapture.h
@@ -0,0 +1,26 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOCAL_CAPTURE_H__
+#define __LOCAL_CAPTURE_H__
+
+struct ImageLinkList;
+
+class LocalCapture {
+public:
+ LocalCapture();
+ ~LocalCapture();
+ void write(char* string);
+ void copyImages(ImageLinkList* ptr);
+ void createAPCDirectory(char* target_path);
+private:
+ char* createUniqueDirectory(const char* path, const char* ending);
+ int removeDirAndAllContents(char* path);
+};
+
+#endif //__LOCAL_CAPTURE_H__
diff --git a/tools/gator/daemon/Logging.cpp b/tools/gator/daemon/Logging.cpp
new file mode 100644
index 0000000..8846622
--- /dev/null
+++ b/tools/gator/daemon/Logging.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Logging.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+
+#ifdef WIN32
+#define MUTEX_INIT() mLoggingMutex = CreateMutex(NULL, false, NULL);
+#define MUTEX_LOCK() WaitForSingleObject(mLoggingMutex, 0xFFFFFFFF);
+#define MUTEX_UNLOCK() ReleaseMutex(mLoggingMutex);
+#define snprintf _snprintf
+#else
+#include <pthread.h>
+#define MUTEX_INIT() pthread_mutex_init(&mLoggingMutex, NULL)
+#define MUTEX_LOCK() pthread_mutex_lock(&mLoggingMutex)
+#define MUTEX_UNLOCK() pthread_mutex_unlock(&mLoggingMutex)
+#endif
+
+// Global thread-safe logging
+Logging* logg = NULL;
+
+Logging::Logging(bool debug) {
+ mDebug = debug;
+ MUTEX_INIT();
+
+ strcpy(mErrBuf, "Unknown Error");
+ strcpy(mLogBuf, "Unknown Message");
+}
+
+Logging::~Logging() {
+}
+
+void Logging::_logError(const char *function, const char *file, int line, const char *fmt, ...) {
+ va_list args;
+
+ MUTEX_LOCK();
+ if (mDebug) {
+ snprintf(mErrBuf, sizeof(mErrBuf), "ERROR: %s(%s:%i): ", function, file, line);
+ } else {
+ mErrBuf[0] = 0;
+ }
+
+ va_start(args, fmt);
+ vsnprintf(mErrBuf + strlen(mErrBuf), sizeof(mErrBuf) - 2 - strlen(mErrBuf), fmt, args); // subtract 2 for \n and \0
+ va_end(args);
+
+ if (strlen(mErrBuf) > 0) {
+ strcat(mErrBuf, "\n");
+ }
+ MUTEX_UNLOCK();
+}
+
+void Logging::_logMessage(const char *function, const char *file, int line, const char *fmt, ...) {
+ if (mDebug) {
+ va_list args;
+
+ MUTEX_LOCK();
+ snprintf(mLogBuf, sizeof(mLogBuf), "INFO: %s(%s:%i): ", function, file, line);
+
+ va_start(args, fmt);
+ vsnprintf(mLogBuf + strlen(mLogBuf), sizeof(mLogBuf) - 2 - strlen(mLogBuf), fmt, args); // subtract 2 for \n and \0
+ va_end(args);
+ strcat(mLogBuf, "\n");
+
+ fprintf(stdout, "%s", mLogBuf);
+ fflush(stdout);
+ MUTEX_UNLOCK();
+ }
+}
diff --git a/tools/gator/daemon/Logging.h b/tools/gator/daemon/Logging.h
new file mode 100644
index 0000000..a7b4523
--- /dev/null
+++ b/tools/gator/daemon/Logging.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LOGGING_H__
+#define __LOGGING_H__
+
+#include <pthread.h>
+
+#define DRIVER_ERROR "\n Driver issue:\n >> gator.ko must be built against the current kernel version & configuration\n >> gator.ko should be co-located with gatord in the same directory\n >> OR insmod gator.ko prior to launching gatord"
+
+class Logging {
+public:
+ Logging(bool debug);
+ ~Logging();
+#define logError(...) _logError(__func__, __FILE__, __LINE__, __VA_ARGS__)
+ __attribute__ ((format (printf, 5, 6)))
+ void _logError(const char *function, const char *file, int line, const char *fmt, ...);
+#define logMessage(...) _logMessage(__func__, __FILE__, __LINE__, __VA_ARGS__)
+ __attribute__ ((format (printf, 5, 6)))
+ void _logMessage(const char *function, const char *file, int line, const char *fmt, ...);
+ char *getLastError() {return mErrBuf;}
+ char *getLastMessage() {return mLogBuf;}
+
+private:
+ char mErrBuf[4096]; // Arbitrarily large buffer to hold a string
+ char mLogBuf[4096]; // Arbitrarily large buffer to hold a string
+ bool mDebug;
+ pthread_mutex_t mLoggingMutex;
+};
+
+extern Logging *logg;
+
+extern void handleException() __attribute__ ((noreturn));
+
+#endif //__LOGGING_H__
diff --git a/tools/gator/daemon/Makefile b/tools/gator/daemon/Makefile
new file mode 100644
index 0000000..27531b4
--- /dev/null
+++ b/tools/gator/daemon/Makefile
@@ -0,0 +1,22 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/arm-linux-gnueabihf-
+# NOTE: This toolchain uses the hardfloat abi by default. For non-hardfloat
+# targets run 'make SOFTFLOAT=1 SYSROOT=/path/to/sysroot', see
+# README_Streamline.txt for more details
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+ifeq ($(SOFTFLOAT),1)
+ CPPFLAGS += -marm -mthumb-interwork -march=armv4t -mfloat-abi=soft
+ LDFLAGS += -marm -march=armv4t -mfloat-abi=soft
+endif
+ifneq ($(SYSROOT),)
+ LDFLAGS += --sysroot=$(SYSROOT)
+endif
+
+include common.mk
diff --git a/tools/gator/daemon/Makefile_aarch64 b/tools/gator/daemon/Makefile_aarch64
new file mode 100644
index 0000000..efd1fa0
--- /dev/null
+++ b/tools/gator/daemon/Makefile_aarch64
@@ -0,0 +1,12 @@
+#
+# Makefile for ARM Streamline - Gator Daemon
+# make -f Makefile_aarch64
+#
+
+# Uncomment and define CROSS_COMPILE if it is not already defined
+# CROSS_COMPILE=/path/to/cross-compiler/aarch64-linux-gnu-
+
+CC = $(CROSS_COMPILE)gcc
+CXX = $(CROSS_COMPILE)g++
+
+include common.mk
diff --git a/tools/gator/daemon/MaliVideoDriver.cpp b/tools/gator/daemon/MaliVideoDriver.cpp
new file mode 100644
index 0000000..2db332d
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.cpp
@@ -0,0 +1,191 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MaliVideoDriver.h"
+
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Counter.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+// From instr/src/mve_instr_comm_protocol.h
+typedef enum mve_instr_configuration_type {
+ MVE_INSTR_RAW = 1 << 0,
+ MVE_INSTR_COUNTERS = 1 << 1,
+ MVE_INSTR_EVENTS = 1 << 2,
+ MVE_INSTR_ACTIVITIES = 1 << 3,
+
+ // Raw always pushed regardless
+ MVE_INSTR_PULL = 1 << 12,
+ // Raw always unpacked regardless
+ MVE_INSTR_PACKED_COMM = 1 << 13,
+ // Don’t send ACKt response
+ MVE_INSTR_NO_AUTO_ACK = 1 << 14,
+} mve_instr_configuration_type_t;
+
+static const char COUNTER[] = "ARM_Mali-V500_cnt";
+static const char EVENT[] = "ARM_Mali-V500_evn";
+static const char ACTIVITY[] = "ARM_Mali-V500_act";
+
+class MaliVideoCounter : public DriverCounter {
+public:
+ MaliVideoCounter(DriverCounter *next, const char *name, const MaliVideoCounterType type, const int id) : DriverCounter(next, name), mType(type), mId(id) {
+ }
+
+ ~MaliVideoCounter() {
+ }
+
+ MaliVideoCounterType getType() const { return mType; }
+ int getId() const { return mId; }
+
+private:
+ const MaliVideoCounterType mType;
+ // Mali Video id
+ const int mId;
+};
+
+MaliVideoDriver::MaliVideoDriver() {
+}
+
+MaliVideoDriver::~MaliVideoDriver() {
+}
+
+void MaliVideoDriver::readEvents(mxml_node_t *const xml) {
+ mxml_node_t *node = xml;
+ while (true) {
+ node = mxmlFindElement(node, xml, "event", NULL, NULL, MXML_DESCEND);
+ if (node == NULL) {
+ break;
+ }
+ const char *counter = mxmlElementGetAttr(node, "counter");
+ if (counter == NULL) {
+ // Ignore
+ } else if (strncmp(counter, COUNTER, sizeof(COUNTER) - 1) == 0) {
+ const int i = strtol(counter + sizeof(COUNTER) - 1, NULL, 10);
+ setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_COUNTER, i));
+ } else if (strncmp(counter, EVENT, sizeof(EVENT) - 1) == 0) {
+ const int i = strtol(counter + sizeof(EVENT) - 1, NULL, 10);
+ setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_EVENT, i));
+ } else if (strncmp(counter, ACTIVITY, sizeof(ACTIVITY) - 1) == 0) {
+ const int i = strtol(counter + sizeof(ACTIVITY) - 1, NULL, 10);
+ setCounters(new MaliVideoCounter(getCounters(), strdup(counter), MVCT_ACTIVITY, i));
+ }
+ }
+}
+
+int MaliVideoDriver::writeCounters(mxml_node_t *root) const {
+ if (access("/dev/mv500", F_OK) != 0) {
+ return 0;
+ }
+
+ return super::writeCounters(root);
+}
+
+void MaliVideoDriver::marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos) {
+ // size
+ int numEnabled = 0;
+ for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+ if (counter->isEnabled() && (counter->getType() == type)) {
+ ++numEnabled;
+ }
+ }
+ Buffer::packInt(buf, bufsize, pos, numEnabled*sizeof(uint32_t));
+ for (MaliVideoCounter *counter = static_cast<MaliVideoCounter *>(getCounters()); counter != NULL; counter = static_cast<MaliVideoCounter *>(counter->getNext())) {
+ if (counter->isEnabled() && (counter->getType() == type)) {
+ Buffer::packInt(buf, bufsize, pos, counter->getId());
+ }
+ }
+}
+
+static bool writeAll(const int mveUds, const char *const buf, const int pos) {
+ int written = 0;
+ while (written < pos) {
+ size_t bytes = ::write(mveUds, buf + written, pos - written);
+ if (bytes <= 0) {
+ logg->logMessage("write failed");
+ return false;
+ }
+ written += bytes;
+ }
+
+ return true;
+}
+
+bool MaliVideoDriver::start(const int mveUds) {
+ char buf[256];
+ int pos = 0;
+
+ // code - MVE_INSTR_STARTUP
+ buf[pos++] = 'C';
+ buf[pos++] = 'L';
+ buf[pos++] = 'N';
+ buf[pos++] = 'T';
+ // size
+ Buffer::packInt(buf, sizeof(buf), pos, sizeof(uint32_t));
+ // client_version_number
+ Buffer::packInt(buf, sizeof(buf), pos, 1);
+
+ // code - MVE_INSTR_CONFIGURE
+ buf[pos++] = 'C';
+ buf[pos++] = 'N';
+ buf[pos++] = 'F';
+ buf[pos++] = 'G';
+ // size
+ Buffer::packInt(buf, sizeof(buf), pos, 5*sizeof(uint32_t));
+ // configuration
+ Buffer::packInt(buf, sizeof(buf), pos, MVE_INSTR_COUNTERS | MVE_INSTR_EVENTS | MVE_INSTR_ACTIVITIES | MVE_INSTR_PACKED_COMM);
+ // communication_protocol_version
+ Buffer::packInt(buf, sizeof(buf), pos, 1);
+ // data_protocol_version
+ Buffer::packInt(buf, sizeof(buf), pos, 1);
+ // sample_rate - convert samples/second to ms/sample
+ Buffer::packInt(buf, sizeof(buf), pos, 1000/gSessionData->mSampleRate);
+ // live_rate - convert ns/flush to ms/flush
+ Buffer::packInt(buf, sizeof(buf), pos, gSessionData->mLiveRate/1000000);
+
+ // code - MVE_INSTR_ENABLE_COUNTERS
+ buf[pos++] = 'C';
+ buf[pos++] = 'F';
+ buf[pos++] = 'G';
+ buf[pos++] = 'c';
+ marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+ // code - MVE_INSTR_ENABLE_EVENTS
+ buf[pos++] = 'C';
+ buf[pos++] = 'F';
+ buf[pos++] = 'G';
+ buf[pos++] = 'e';
+ marshalEnable(MVCT_EVENT, buf, sizeof(buf), pos);
+
+ // code - MVE_INSTR_ENABLE_ACTIVITIES
+ buf[pos++] = 'C';
+ buf[pos++] = 'F';
+ buf[pos++] = 'G';
+ buf[pos++] = 'a';
+ marshalEnable(MVCT_ACTIVITY, buf, sizeof(buf), pos);
+
+ return writeAll(mveUds, buf, pos);
+}
+
+void MaliVideoDriver::stop(const int mveUds) {
+ char buf[8];
+ int pos = 0;
+
+ // code - MVE_INSTR_STOP
+ buf[pos++] = 'S';
+ buf[pos++] = 'T';
+ buf[pos++] = 'O';
+ buf[pos++] = 'P';
+ marshalEnable(MVCT_COUNTER, buf, sizeof(buf), pos);
+
+ writeAll(mveUds, buf, pos);
+
+ close(mveUds);
+}
diff --git a/tools/gator/daemon/MaliVideoDriver.h b/tools/gator/daemon/MaliVideoDriver.h
new file mode 100644
index 0000000..35b0558
--- /dev/null
+++ b/tools/gator/daemon/MaliVideoDriver.h
@@ -0,0 +1,45 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MALIVIDEODRIVER_H
+#define MALIVIDEODRIVER_H
+
+#include "Driver.h"
+
+class MaliVideoCounter;
+
+enum MaliVideoCounterType {
+ MVCT_COUNTER,
+ MVCT_EVENT,
+ MVCT_ACTIVITY,
+};
+
+class MaliVideoDriver : public SimpleDriver {
+private:
+ typedef SimpleDriver super;
+
+public:
+ MaliVideoDriver();
+ ~MaliVideoDriver();
+
+ void readEvents(mxml_node_t *const root);
+
+ int writeCounters(mxml_node_t *root) const;
+
+ bool start(const int mveUds);
+ void stop(const int mveUds);
+
+private:
+ void marshalEnable(const MaliVideoCounterType type, char *const buf, const size_t bufsize, int &pos);
+
+ // Intentionally unimplemented
+ MaliVideoDriver(const MaliVideoDriver &);
+ MaliVideoDriver &operator=(const MaliVideoDriver &);
+};
+
+#endif // MALIVIDEODRIVER_H
diff --git a/tools/gator/daemon/MemInfoDriver.cpp b/tools/gator/daemon/MemInfoDriver.cpp
new file mode 100644
index 0000000..6818b97
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.cpp
@@ -0,0 +1,93 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "MemInfoDriver.h"
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class MemInfoCounter : public DriverCounter {
+public:
+ MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value);
+ ~MemInfoCounter();
+
+ int64_t read();
+
+private:
+ int64_t *const mValue;
+
+ // Intentionally unimplemented
+ MemInfoCounter(const MemInfoCounter &);
+ MemInfoCounter &operator=(const MemInfoCounter &);
+};
+
+MemInfoCounter::MemInfoCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value) {
+}
+
+MemInfoCounter::~MemInfoCounter() {
+}
+
+int64_t MemInfoCounter::read() {
+ return *mValue;
+}
+
+MemInfoDriver::MemInfoDriver() : mBuf(), mMemUsed(0), mMemFree(0), mBuffers(0) {
+}
+
+MemInfoDriver::~MemInfoDriver() {
+}
+
+void MemInfoDriver::readEvents(mxml_node_t *const) {
+ // Only for use with perf
+ if (!gSessionData->perf.isSetup()) {
+ return;
+ }
+
+ setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memused2"), &mMemUsed));
+ setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_memfree"), &mMemFree));
+ setCounters(new MemInfoCounter(getCounters(), strdup("Linux_meminfo_bufferram"), &mBuffers));
+}
+
+void MemInfoDriver::read(Buffer *const buffer) {
+ if (!countersEnabled()) {
+ return;
+ }
+
+ if (!mBuf.read("/proc/meminfo")) {
+ logg->logError("Failed to read /proc/meminfo");
+ handleException();
+ }
+
+ char *key = mBuf.getBuf();
+ char *colon;
+ int64_t memTotal = 0;
+ while ((colon = strchr(key, ':')) != NULL) {
+ char *end = strchr(colon + 1, '\n');
+ if (end != NULL) {
+ *end = '\0';
+ }
+ *colon = '\0';
+
+ if (strcmp(key, "MemTotal") == 0) {
+ memTotal = strtoll(colon + 1, NULL, 10) << 10;
+ } else if (strcmp(key, "MemFree") == 0) {
+ mMemFree = strtoll(colon + 1, NULL, 10) << 10;
+ } else if (strcmp(key, "Buffers") == 0) {
+ mBuffers = strtoll(colon + 1, NULL, 10) << 10;
+ }
+
+ if (end == NULL) {
+ break;
+ }
+ key = end + 1;
+ }
+
+ mMemUsed = memTotal - mMemFree;
+
+ super::read(buffer);
+}
diff --git a/tools/gator/daemon/MemInfoDriver.h b/tools/gator/daemon/MemInfoDriver.h
new file mode 100644
index 0000000..ffeaf30
--- /dev/null
+++ b/tools/gator/daemon/MemInfoDriver.h
@@ -0,0 +1,37 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MEMINFODRIVER_H
+#define MEMINFODRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class MemInfoDriver : public PolledDriver {
+private:
+ typedef PolledDriver super;
+
+public:
+ MemInfoDriver();
+ ~MemInfoDriver();
+
+ void readEvents(mxml_node_t *const root);
+ void read(Buffer *const buffer);
+
+private:
+ DynBuf mBuf;
+ int64_t mMemUsed;
+ int64_t mMemFree;
+ int64_t mBuffers;
+
+ // Intentionally unimplemented
+ MemInfoDriver(const MemInfoDriver &);
+ MemInfoDriver &operator=(const MemInfoDriver &);
+};
+
+#endif // MEMINFODRIVER_H
diff --git a/tools/gator/daemon/Monitor.cpp b/tools/gator/daemon/Monitor.cpp
new file mode 100644
index 0000000..0428887
--- /dev/null
+++ b/tools/gator/daemon/Monitor.cpp
@@ -0,0 +1,82 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Monitor.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Logging.h"
+
+Monitor::Monitor() : mFd(-1) {
+}
+
+Monitor::~Monitor() {
+ if (mFd >= 0) {
+ ::close(mFd);
+ }
+}
+
+void Monitor::close() {
+ if (mFd >= 0) {
+ ::close(mFd);
+ mFd = -1;
+ }
+}
+
+bool Monitor::init() {
+#ifdef EPOLL_CLOEXEC
+ mFd = epoll_create1(EPOLL_CLOEXEC);
+#else
+ mFd = epoll_create(16);
+#endif
+ if (mFd < 0) {
+ logg->logMessage("epoll_create1 failed");
+ return false;
+ }
+
+#ifndef EPOLL_CLOEXEC
+ int fdf = fcntl(mFd, F_GETFD);
+ if ((fdf == -1) || (fcntl(mFd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ logg->logMessage("fcntl failed");
+ ::close(mFd);
+ return -1;
+ }
+#endif
+
+ return true;
+}
+
+bool Monitor::add(const int fd) {
+ struct epoll_event event;
+ memset(&event, 0, sizeof(event));
+ event.data.fd = fd;
+ event.events = EPOLLIN;
+ if (epoll_ctl(mFd, EPOLL_CTL_ADD, fd, &event) != 0) {
+ logg->logMessage("epoll_ctl failed");
+ return false;
+ }
+
+ return true;
+}
+
+int Monitor::wait(struct epoll_event *const events, int maxevents, int timeout) {
+ int result = epoll_wait(mFd, events, maxevents, timeout);
+ if (result < 0) {
+ // Ignore if the call was interrupted as this will happen when SIGINT is received
+ if (errno == EINTR) {
+ result = 0;
+ } else {
+ logg->logMessage("epoll_wait failed");
+ }
+ }
+
+ return result;
+}
diff --git a/tools/gator/daemon/Monitor.h b/tools/gator/daemon/Monitor.h
new file mode 100644
index 0000000..55368fc
--- /dev/null
+++ b/tools/gator/daemon/Monitor.h
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef MONITOR_H
+#define MONITOR_H
+
+#include <sys/epoll.h>
+
+class Monitor {
+public:
+ Monitor();
+ ~Monitor();
+
+ void close();
+ bool init();
+ bool add(const int fd);
+ int wait(struct epoll_event *const events, int maxevents, int timeout);
+
+private:
+
+ int mFd;
+
+ // Intentionally unimplemented
+ Monitor(const Monitor &);
+ Monitor &operator=(const Monitor &);
+};
+
+#endif // MONITOR_H
diff --git a/tools/gator/daemon/NetDriver.cpp b/tools/gator/daemon/NetDriver.cpp
new file mode 100644
index 0000000..56b25e0
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+// Define to get format macros from inttypes.h
+#define __STDC_FORMAT_MACROS
+
+#include "NetDriver.h"
+
+#include <inttypes.h>
+
+#include "Logging.h"
+#include "SessionData.h"
+
+class NetCounter : public DriverCounter {
+public:
+ NetCounter(DriverCounter *next, char *const name, int64_t *const value);
+ ~NetCounter();
+
+ int64_t read();
+
+private:
+ int64_t *const mValue;
+ int64_t mPrev;
+
+ // Intentionally unimplemented
+ NetCounter(const NetCounter &);
+ NetCounter &operator=(const NetCounter &);
+};
+
+NetCounter::NetCounter(DriverCounter *next, char *const name, int64_t *const value) : DriverCounter(next, name), mValue(value), mPrev(0) {
+}
+
+NetCounter::~NetCounter() {
+}
+
+int64_t NetCounter::read() {
+ int64_t result = *mValue - mPrev;
+ mPrev = *mValue;
+ return result;
+}
+
+NetDriver::NetDriver() : mBuf(), mReceiveBytes(0), mTransmitBytes(0) {
+}
+
+NetDriver::~NetDriver() {
+}
+
+void NetDriver::readEvents(mxml_node_t *const) {
+ // Only for use with perf
+ if (!gSessionData->perf.isSetup()) {
+ return;
+ }
+
+ setCounters(new NetCounter(getCounters(), strdup("Linux_net_rx"), &mReceiveBytes));
+ setCounters(new NetCounter(getCounters(), strdup("Linux_net_tx"), &mTransmitBytes));
+}
+
+bool NetDriver::doRead() {
+ if (!countersEnabled()) {
+ return true;
+ }
+
+ if (!mBuf.read("/proc/net/dev")) {
+ return false;
+ }
+
+ // Skip the header
+ char *key;
+ if (((key = strchr(mBuf.getBuf(), '\n')) == NULL) ||
+ ((key = strchr(key + 1, '\n')) == NULL)) {
+ return false;
+ }
+ key = key + 1;
+
+ mReceiveBytes = 0;
+ mTransmitBytes = 0;
+
+ char *colon;
+ while ((colon = strchr(key, ':')) != NULL) {
+ char *end = strchr(colon + 1, '\n');
+ if (end != NULL) {
+ *end = '\0';
+ }
+ *colon = '\0';
+
+ int64_t receiveBytes;
+ int64_t transmitBytes;
+ const int count = sscanf(colon + 1, " %" SCNu64 " %*u %*u %*u %*u %*u %*u %*u %" SCNu64, &receiveBytes, &transmitBytes);
+ if (count != 2) {
+ return false;
+ }
+ mReceiveBytes += receiveBytes;
+ mTransmitBytes += transmitBytes;
+
+ if (end == NULL) {
+ break;
+ }
+ key = end + 1;
+ }
+
+ return true;
+}
+
+void NetDriver::start() {
+ if (!doRead()) {
+ logg->logError("Unable to read network stats");
+ handleException();
+ }
+ // Initialize previous values
+ for (DriverCounter *counter = getCounters(); counter != NULL; counter = counter->getNext()) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->read();
+ }
+}
+
+void NetDriver::read(Buffer *const buffer) {
+ if (!doRead()) {
+ logg->logError("Unable to read network stats");
+ handleException();
+ }
+ super::read(buffer);
+}
diff --git a/tools/gator/daemon/NetDriver.h b/tools/gator/daemon/NetDriver.h
new file mode 100644
index 0000000..5f72280
--- /dev/null
+++ b/tools/gator/daemon/NetDriver.h
@@ -0,0 +1,39 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef NETDRIVER_H
+#define NETDRIVER_H
+
+#include "Driver.h"
+#include "DynBuf.h"
+
+class NetDriver : public PolledDriver {
+private:
+ typedef PolledDriver super;
+
+public:
+ NetDriver();
+ ~NetDriver();
+
+ void readEvents(mxml_node_t *const root);
+ void start();
+ void read(Buffer *const buffer);
+
+private:
+ bool doRead();
+
+ DynBuf mBuf;
+ int64_t mReceiveBytes;
+ int64_t mTransmitBytes;
+
+ // Intentionally unimplemented
+ NetDriver(const NetDriver &);
+ NetDriver &operator=(const NetDriver &);
+};
+
+#endif // NETDRIVER_H
diff --git a/tools/gator/daemon/OlySocket.cpp b/tools/gator/daemon/OlySocket.cpp
new file mode 100644
index 0000000..078d202
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.cpp
@@ -0,0 +1,331 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlySocket.h"
+
+#include <stdio.h>
+#include <string.h>
+#ifdef WIN32
+#include <Winsock2.h>
+#include <ws2tcpip.h>
+#else
+#include <netinet/in.h>
+#include <sys/un.h>
+#include <unistd.h>
+#include <netdb.h>
+#include <fcntl.h>
+#include <stddef.h>
+#endif
+
+#include "Logging.h"
+
+#ifdef WIN32
+#define CLOSE_SOCKET(x) closesocket(x)
+#define SHUTDOWN_RX_TX SD_BOTH
+#define snprintf _snprintf
+#else
+#define CLOSE_SOCKET(x) close(x)
+#define SHUTDOWN_RX_TX SHUT_RDWR
+#endif
+
+int socket_cloexec(int domain, int type, int protocol) {
+#ifdef SOCK_CLOEXEC
+ return socket(domain, type | SOCK_CLOEXEC, protocol);
+#else
+ int sock = socket(domain, type, protocol);
+#ifdef FD_CLOEXEC
+ if (sock < 0) {
+ return -1;
+ }
+ int fdf = fcntl(sock, F_GETFD);
+ if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ close(sock);
+ return -1;
+ }
+#endif
+ return sock;
+#endif
+}
+
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen) {
+ int sock;
+#ifdef SOCK_CLOEXEC
+ sock = accept4(sockfd, addr, addrlen, SOCK_CLOEXEC);
+ if (sock >= 0) {
+ return sock;
+ }
+ // accept4 with SOCK_CLOEXEC may not work on all kernels, so fallback
+#endif
+ sock = accept(sockfd, addr, addrlen);
+#ifdef FD_CLOEXEC
+ if (sock < 0) {
+ return -1;
+ }
+ int fdf = fcntl(sock, F_GETFD);
+ if ((fdf == -1) || (fcntl(sock, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ close(sock);
+ return -1;
+ }
+#endif
+ return sock;
+}
+
+OlyServerSocket::OlyServerSocket(int port) {
+#ifdef WIN32
+ WSADATA wsaData;
+ if (WSAStartup(0x0202, &wsaData) != 0) {
+ logg->logError("Windows socket initialization failed");
+ handleException();
+ }
+#endif
+
+ createServerSocket(port);
+}
+
+OlySocket::OlySocket(int socketID) : mSocketID(socketID) {
+}
+
+#ifndef WIN32
+
+#define MIN(A, B) ({ \
+ const __typeof__(A) __a = A; \
+ const __typeof__(B) __b = B; \
+ __a > __b ? __b : __a; \
+})
+
+OlyServerSocket::OlyServerSocket(const char* path, const size_t pathSize, const bool calculateAddrlen) {
+ // Create socket
+ mFDServer = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+ if (mFDServer < 0) {
+ logg->logError("Error creating server socket");
+ handleException();
+ }
+
+ // Create sockaddr_in structure, ensuring non-populated fields are zero
+ struct sockaddr_un sockaddr;
+ memset((void*)&sockaddr, 0, sizeof(sockaddr));
+ sockaddr.sun_family = AF_UNIX;
+ memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+ sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+ // Bind the socket to an address
+ if (bind(mFDServer, (const struct sockaddr*)&sockaddr, calculateAddrlen ? offsetof(struct sockaddr_un, sun_path) + pathSize - 1 : sizeof(sockaddr)) < 0) {
+ logg->logError("Binding of server socket failed.");
+ handleException();
+ }
+
+ // Listen for connections on this socket
+ if (listen(mFDServer, 1) < 0) {
+ logg->logError("Listening of server socket failed");
+ handleException();
+ }
+}
+
+int OlySocket::connect(const char* path, const size_t pathSize, const bool calculateAddrlen) {
+ int fd = socket_cloexec(PF_UNIX, SOCK_STREAM, 0);
+ if (fd < 0) {
+ return -1;
+ }
+
+ // Create sockaddr_in structure, ensuring non-populated fields are zero
+ struct sockaddr_un sockaddr;
+ memset((void*)&sockaddr, 0, sizeof(sockaddr));
+ sockaddr.sun_family = AF_UNIX;
+ memcpy(sockaddr.sun_path, path, MIN(pathSize, sizeof(sockaddr.sun_path)));
+ sockaddr.sun_path[sizeof(sockaddr.sun_path) - 1] = '\0';
+
+ if (::connect(fd, (const struct sockaddr*)&sockaddr, calculateAddrlen ? offsetof(struct sockaddr_un, sun_path) + pathSize - 1 : sizeof(sockaddr)) < 0) {
+ close(fd);
+ return -1;
+ }
+
+ return fd;
+}
+
+#endif
+
+OlySocket::~OlySocket() {
+ if (mSocketID > 0) {
+ CLOSE_SOCKET(mSocketID);
+ }
+}
+
+OlyServerSocket::~OlyServerSocket() {
+ if (mFDServer > 0) {
+ CLOSE_SOCKET(mFDServer);
+ }
+}
+
+void OlySocket::shutdownConnection() {
+ // Shutdown is primarily used to unblock other threads that are blocking on send/receive functions
+ shutdown(mSocketID, SHUTDOWN_RX_TX);
+}
+
+void OlySocket::closeSocket() {
+ // Used for closing an accepted socket but keeping the server socket active
+ if (mSocketID > 0) {
+ CLOSE_SOCKET(mSocketID);
+ mSocketID = -1;
+ }
+}
+
+void OlyServerSocket::closeServerSocket() {
+ if (mFDServer > 0 && CLOSE_SOCKET(mFDServer) != 0) {
+ logg->logError("Failed to close server socket.");
+ handleException();
+ }
+ mFDServer = -1;
+}
+
+void OlyServerSocket::createServerSocket(int port) {
+ int family = AF_INET6;
+
+ // Create socket
+ mFDServer = socket_cloexec(PF_INET6, SOCK_STREAM, IPPROTO_TCP);
+ if (mFDServer < 0) {
+ family = AF_INET;
+ mFDServer = socket_cloexec(PF_INET, SOCK_STREAM, IPPROTO_TCP);
+ if (mFDServer < 0) {
+ logg->logError("Error creating server socket");
+ handleException();
+ }
+ }
+
+ // Enable address reuse, another solution would be to create the server socket once and only close it when the object exits
+ int on = 1;
+ if (setsockopt(mFDServer, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+ logg->logError("Setting server socket reuse option failed");
+ handleException();
+ }
+
+ // Listen on both IPv4 and IPv6
+ on = 0;
+ if (setsockopt(mFDServer, IPPROTO_IPV6, IPV6_V6ONLY, (const char*)&on, sizeof(on)) != 0) {
+ logg->logMessage("setsockopt IPV6_V6ONLY failed");
+ }
+
+ // Create sockaddr_in structure, ensuring non-populated fields are zero
+ struct sockaddr_in6 sockaddr;
+ memset((void*)&sockaddr, 0, sizeof(sockaddr));
+ sockaddr.sin6_family = family;
+ sockaddr.sin6_port = htons(port);
+ sockaddr.sin6_addr = in6addr_any;
+
+ // Bind the socket to an address
+ if (bind(mFDServer, (const struct sockaddr*)&sockaddr, sizeof(sockaddr)) < 0) {
+ logg->logError("Binding of server socket on port %i failed.\nIs an instance already running or is another application using that port?", port);
+ handleException();
+ }
+
+ // Listen for connections on this socket
+ if (listen(mFDServer, 1) < 0) {
+ logg->logError("Listening of server socket failed");
+ handleException();
+ }
+}
+
+// mSocketID is always set to the most recently accepted connection
+// The user of this class should maintain the different socket connections, e.g. by forking the process
+int OlyServerSocket::acceptConnection() {
+ int socketID;
+ if (mFDServer <= 0) {
+ logg->logError("Attempting multiple connections on a single connection server socket or attempting to accept on a client socket");
+ handleException();
+ }
+
+ // Accept a connection, note that this call blocks until a client connects
+ socketID = accept_cloexec(mFDServer, NULL, NULL);
+ if (socketID < 0) {
+ logg->logError("Socket acceptance failed");
+ handleException();
+ }
+ return socketID;
+}
+
+void OlySocket::send(const char* buffer, int size) {
+ if (size <= 0 || buffer == NULL) {
+ return;
+ }
+
+ while (size > 0) {
+ int n = ::send(mSocketID, buffer, size, 0);
+ if (n < 0) {
+ logg->logError("Socket send error");
+ handleException();
+ }
+ size -= n;
+ buffer += n;
+ }
+}
+
+// Returns the number of bytes received
+int OlySocket::receive(char* buffer, int size) {
+ if (size <= 0 || buffer == NULL) {
+ return 0;
+ }
+
+ int bytes = recv(mSocketID, buffer, size, 0);
+ if (bytes < 0) {
+ logg->logError("Socket receive error");
+ handleException();
+ } else if (bytes == 0) {
+ logg->logMessage("Socket disconnected");
+ return -1;
+ }
+ return bytes;
+}
+
+// Receive exactly size bytes of data. Note, this function will block until all bytes are received
+int OlySocket::receiveNBytes(char* buffer, int size) {
+ int bytes = 0;
+ while (size > 0 && buffer != NULL) {
+ bytes = recv(mSocketID, buffer, size, 0);
+ if (bytes < 0) {
+ logg->logError("Socket receive error");
+ handleException();
+ } else if (bytes == 0) {
+ logg->logMessage("Socket disconnected");
+ return -1;
+ }
+ buffer += bytes;
+ size -= bytes;
+ }
+ return bytes;
+}
+
+// Receive data until a carriage return, line feed, or null is encountered, or the buffer fills
+int OlySocket::receiveString(char* buffer, int size) {
+ int bytes_received = 0;
+ bool found = false;
+
+ if (buffer == 0) {
+ return 0;
+ }
+
+ while (!found && bytes_received < size) {
+ // Receive a single character
+ int bytes = recv(mSocketID, &buffer[bytes_received], 1, 0);
+ if (bytes < 0) {
+ logg->logError("Socket receive error");
+ handleException();
+ } else if (bytes == 0) {
+ logg->logMessage("Socket disconnected");
+ return -1;
+ }
+
+ // Replace carriage returns and line feeds with zero
+ if (buffer[bytes_received] == '\n' || buffer[bytes_received] == '\r' || buffer[bytes_received] == '\0') {
+ buffer[bytes_received] = '\0';
+ found = true;
+ }
+
+ bytes_received++;
+ }
+
+ return bytes_received;
+}
diff --git a/tools/gator/daemon/OlySocket.h b/tools/gator/daemon/OlySocket.h
new file mode 100644
index 0000000..757a252
--- /dev/null
+++ b/tools/gator/daemon/OlySocket.h
@@ -0,0 +1,64 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __OLY_SOCKET_H__
+#define __OLY_SOCKET_H__
+
+#include <stddef.h>
+
+#ifdef WIN32
+typedef int socklen_t;
+#else
+#include <sys/socket.h>
+#endif
+
+class OlySocket {
+public:
+#ifndef WIN32
+ static int connect(const char* path, const size_t pathSize, const bool calculateAddrlen = false);
+#endif
+
+ OlySocket(int socketID);
+ ~OlySocket();
+
+ void closeSocket();
+ void shutdownConnection();
+ void send(const char* buffer, int size);
+ int receive(char* buffer, int size);
+ int receiveNBytes(char* buffer, int size);
+ int receiveString(char* buffer, int size);
+
+ bool isValid() const { return mSocketID >= 0; }
+
+private:
+ int mSocketID;
+};
+
+class OlyServerSocket {
+public:
+ OlyServerSocket(int port);
+#ifndef WIN32
+ OlyServerSocket(const char* path, const size_t pathSize, const bool calculateAddrlen = false);
+#endif
+ ~OlyServerSocket();
+
+ int acceptConnection();
+ void closeServerSocket();
+
+ int getFd() { return mFDServer; }
+
+private:
+ int mFDServer;
+
+ void createServerSocket(int port);
+};
+
+int socket_cloexec(int domain, int type, int protocol);
+int accept_cloexec(int sockfd, struct sockaddr *addr, socklen_t *addrlen);
+
+#endif //__OLY_SOCKET_H__
diff --git a/tools/gator/daemon/OlyUtility.cpp b/tools/gator/daemon/OlyUtility.cpp
new file mode 100644
index 0000000..6f40168
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.cpp
@@ -0,0 +1,227 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "OlyUtility.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+#if defined(WIN32)
+#include <windows.h>
+#elif defined(__linux__)
+#include <unistd.h>
+#elif defined(DARWIN)
+#include <mach-o/dyld.h>
+#endif
+
+OlyUtility* util = NULL;
+
+bool OlyUtility::stringToBool(const char* string, bool defValue) {
+ char value[32];
+
+ if (string == NULL) {
+ return defValue;
+ }
+
+ strncpy(value, string, sizeof(value));
+ if (value[0] == 0) {
+ return defValue;
+ }
+ value[sizeof(value) - 1] = 0; // strncpy does not guarantee a null-terminated string
+
+ // Convert to lowercase
+ int i = 0;
+ while (value[i]) {
+ value[i] = tolower(value[i]);
+ i++;
+ }
+
+ if (strcmp(value, "true") == 0 || strcmp(value, "yes") == 0 || strcmp(value, "1") == 0 || strcmp(value, "on") == 0) {
+ return true;
+ } else if (strcmp(value, "false") == 0 || strcmp(value, "no") == 0 || strcmp(value, "0") == 0 || strcmp(value, "off") == 0) {
+ return false;
+ } else {
+ return defValue;
+ }
+}
+
+void OlyUtility::stringToLower(char* string) {
+ if (string == NULL) {
+ return;
+ }
+
+ while (*string) {
+ *string = tolower(*string);
+ string++;
+ }
+}
+
+// Modifies fullpath with the path part including the trailing path separator
+int OlyUtility::getApplicationFullPath(char* fullpath, int sizeOfPath) {
+ memset(fullpath, 0, sizeOfPath);
+#if defined(WIN32)
+ int length = GetModuleFileName(NULL, fullpath, sizeOfPath);
+#elif defined(__linux__)
+ int length = readlink("/proc/self/exe", fullpath, sizeOfPath);
+#elif defined(DARWIN)
+ uint32_t length_u = (uint32_t)sizeOfPath;
+ int length = sizeOfPath;
+ if (_NSGetExecutablePath(fullpath, &length_u) == 0) {
+ length = strlen(fullpath);
+ }
+#endif
+
+ if (length == sizeOfPath) {
+ return -1;
+ }
+
+ fullpath[length] = 0;
+ getPathPart(fullpath);
+
+ return 0;
+}
+
+char* OlyUtility::readFromDisk(const char* file, unsigned int *size, bool appendNull) {
+ // Open the file
+ FILE* pFile = fopen(file, "rb");
+ if (pFile==NULL) {
+ return NULL;
+ }
+
+ // Obtain file size
+ fseek(pFile , 0 , SEEK_END);
+ unsigned int lSize = ftell(pFile);
+ rewind(pFile);
+
+ // Allocate memory to contain the whole file
+ char* buffer = (char*)malloc(lSize + (int)appendNull);
+ if (buffer == NULL) {
+ fclose(pFile);
+ return NULL;
+ }
+
+ // Copy the file into the buffer
+ if (fread(buffer, 1, lSize, pFile) != lSize) {
+ free(buffer);
+ fclose(pFile);
+ return NULL;
+ }
+
+ // Terminate
+ fclose(pFile);
+
+ if (appendNull) {
+ buffer[lSize] = 0;
+ }
+
+ if (size) {
+ *size = lSize;
+ }
+
+ return buffer;
+}
+
+int OlyUtility::writeToDisk(const char* path, const char* data) {
+ // Open the file
+ FILE* pFile = fopen(path, "wb");
+ if (pFile == NULL) {
+ return -1;
+ }
+
+ // Write the data to disk
+ if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+ fclose(pFile);
+ return -1;
+ }
+
+ // Terminate
+ fclose(pFile);
+ return 0;
+}
+
+int OlyUtility::appendToDisk(const char* path, const char* data) {
+ // Open the file
+ FILE* pFile = fopen(path, "a");
+ if (pFile == NULL) {
+ return -1;
+ }
+
+ // Write the data to disk
+ if (fwrite(data, 1, strlen(data), pFile) != strlen(data)) {
+ fclose(pFile);
+ return -1;
+ }
+
+ // Terminate
+ fclose(pFile);
+ return 0;
+}
+
+/**
+ * Copies the srcFile into dstFile in 1kB chunks.
+ * The dstFile will be overwritten if it exists.
+ * 0 is returned on an error; otherwise 1.
+ */
+#define TRANSFER_SIZE 1024
+int OlyUtility::copyFile(const char* srcFile, const char* dstFile) {
+ char buffer[TRANSFER_SIZE];
+ FILE * f_src = fopen(srcFile,"rb");
+ if (!f_src) {
+ return 0;
+ }
+ FILE * f_dst = fopen(dstFile,"wb");
+ if (!f_dst) {
+ fclose(f_src);
+ return 0;
+ }
+ while (!feof(f_src)) {
+ int num_bytes_read = fread(buffer, 1, TRANSFER_SIZE, f_src);
+ if (num_bytes_read < TRANSFER_SIZE && !feof(f_src)) {
+ fclose(f_src);
+ fclose(f_dst);
+ return 0;
+ }
+ int num_bytes_written = fwrite(buffer, 1, num_bytes_read, f_dst);
+ if (num_bytes_written != num_bytes_read) {
+ fclose(f_src);
+ fclose(f_dst);
+ return 0;
+ }
+ }
+ fclose(f_src);
+ fclose(f_dst);
+ return 1;
+}
+
+const char* OlyUtility::getFilePart(const char* path) {
+ const char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+ // in case path is not a full path
+ if (last_sep == NULL) {
+ return path;
+ }
+
+ return last_sep++;
+}
+
+// getPathPart may modify the contents of path
+// returns the path including the trailing path separator
+char* OlyUtility::getPathPart(char* path) {
+ char* last_sep = strrchr(path, PATH_SEPARATOR);
+
+ // in case path is not a full path
+ if (last_sep == NULL) {
+ return 0;
+ }
+ last_sep++;
+ *last_sep = 0;
+
+ return (path);
+}
diff --git a/tools/gator/daemon/OlyUtility.h b/tools/gator/daemon/OlyUtility.h
new file mode 100644
index 0000000..1525081
--- /dev/null
+++ b/tools/gator/daemon/OlyUtility.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef OLY_UTILITY_H
+#define OLY_UTILITY_H
+
+#include <stddef.h>
+
+#ifdef WIN32
+#define PATH_SEPARATOR '\\'
+#define CAIMAN_PATH_MAX MAX_PATH
+#define snprintf _snprintf
+#else
+#include <limits.h>
+#define PATH_SEPARATOR '/'
+#define CAIMAN_PATH_MAX PATH_MAX
+#endif
+
+class OlyUtility {
+public:
+ OlyUtility() {};
+ ~OlyUtility() {};
+ bool stringToBool(const char* string, bool defValue);
+ void stringToLower(char* string);
+ int getApplicationFullPath(char* path, int sizeOfPath);
+ char* readFromDisk(const char* file, unsigned int *size = NULL, bool appendNull = true);
+ int writeToDisk(const char* path, const char* file);
+ int appendToDisk(const char* path, const char* file);
+ int copyFile(const char* srcFile, const char* dstFile);
+ const char* getFilePart(const char* path);
+ char* getPathPart(char* path);
+private:
+};
+
+extern OlyUtility* util;
+
+#endif // OLY_UTILITY_H
diff --git a/tools/gator/daemon/PerfBuffer.cpp b/tools/gator/daemon/PerfBuffer.cpp
new file mode 100644
index 0000000..3b9da1d
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.cpp
@@ -0,0 +1,223 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfBuffer.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+PerfBuffer::PerfBuffer() {
+ for (int cpu = 0; cpu < ARRAY_LENGTH(mBuf); ++cpu) {
+ mBuf[cpu] = MAP_FAILED;
+ mDiscard[cpu] = false;
+ mFds[cpu] = -1;
+ }
+}
+
+PerfBuffer::~PerfBuffer() {
+ for (int cpu = ARRAY_LENGTH(mBuf) - 1; cpu >= 0; --cpu) {
+ if (mBuf[cpu] != MAP_FAILED) {
+ munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+ }
+ }
+}
+
+bool PerfBuffer::useFd(const int cpu, const int fd) {
+ if (mFds[cpu] < 0) {
+ if (mBuf[cpu] != MAP_FAILED) {
+ logg->logMessage("cpu %i already online or not correctly cleaned up", cpu);
+ return false;
+ }
+
+ // The buffer isn't mapped yet
+ mBuf[cpu] = mmap(NULL, gSessionData->mPageSize + BUF_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (mBuf[cpu] == MAP_FAILED) {
+ logg->logMessage("mmap failed");
+ return false;
+ }
+ mFds[cpu] = fd;
+
+ // Check the version
+ struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+ if (pemp->compat_version != 0) {
+ logg->logMessage("Incompatible perf_event_mmap_page compat_version");
+ return false;
+ }
+ } else {
+ if (mBuf[cpu] == MAP_FAILED) {
+ logg->logMessage("cpu already online or not correctly cleaned up");
+ return false;
+ }
+
+ if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, mFds[cpu]) < 0) {
+ logg->logMessage("ioctl failed");
+ return false;
+ }
+ }
+
+ return true;
+}
+
+void PerfBuffer::discard(const int cpu) {
+ if (mBuf[cpu] != MAP_FAILED) {
+ mDiscard[cpu] = true;
+ }
+}
+
+bool PerfBuffer::isEmpty() {
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ if (mBuf[cpu] != MAP_FAILED) {
+ // Take a snapshot of the positions
+ struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+ const __u64 head = ACCESS_ONCE(pemp->data_head);
+ const __u64 tail = ACCESS_ONCE(pemp->data_tail);
+
+ if (head != tail) {
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
+bool PerfBuffer::isFull() {
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ if (mBuf[cpu] != MAP_FAILED) {
+ // Take a snapshot of the positions
+ struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+ const __u64 head = ACCESS_ONCE(pemp->data_head);
+
+ if (head + 2000 <= (unsigned int)BUF_SIZE) {
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+
+class PerfFrame {
+public:
+ PerfFrame(Sender *const sender) : mSender(sender), mWritePos(-1), mCpuSizePos(-1) {}
+
+ void add(const int cpu, const __u64 head, __u64 tail, const uint8_t *const b) {
+ cpuHeader(cpu);
+
+ while (head > tail) {
+ const int count = reinterpret_cast<const struct perf_event_header *>(b + (tail & BUF_MASK))->size/sizeof(uint64_t);
+ // Can this whole message be written as Streamline assumes events are not split between frames
+ if (sizeof(mBuf) <= mWritePos + count*Buffer::MAXSIZE_PACK64) {
+ send();
+ cpuHeader(cpu);
+ }
+ for (int i = 0; i < count; ++i) {
+ // Must account for message size
+ Buffer::packInt64(mBuf, sizeof(mBuf), mWritePos, *reinterpret_cast<const uint64_t *>(b + (tail & BUF_MASK)));
+ tail += sizeof(uint64_t);
+ }
+ }
+ }
+
+ void send() {
+ if (mWritePos > 0) {
+ writeFrameSize();
+ mSender->writeData(mBuf, mWritePos, RESPONSE_APC_DATA);
+ mWritePos = -1;
+ mCpuSizePos = -1;
+ }
+ }
+
+private:
+ void writeFrameSize() {
+ writeCpuSize();
+ const int typeLength = gSessionData->mLocalCapture ? 0 : 1;
+ Buffer::writeLEInt(reinterpret_cast<unsigned char *>(mBuf + typeLength), mWritePos - typeLength - sizeof(uint32_t));
+ }
+
+ void frameHeader() {
+ if (mWritePos < 0) {
+ mWritePos = 0;
+ mCpuSizePos = -1;
+ if (!gSessionData->mLocalCapture) {
+ mBuf[mWritePos++] = RESPONSE_APC_DATA;
+ }
+ // Reserve space for frame size
+ mWritePos += sizeof(uint32_t);
+ Buffer::packInt(mBuf, sizeof(mBuf), mWritePos, FRAME_PERF);
+ }
+ }
+
+ void writeCpuSize() {
+ if (mCpuSizePos >= 0) {
+ Buffer::writeLEInt(reinterpret_cast<unsigned char *>(mBuf + mCpuSizePos), mWritePos - mCpuSizePos - sizeof(uint32_t));
+ }
+ }
+
+ void cpuHeader(const int cpu) {
+ if (sizeof(mBuf) <= mWritePos + Buffer::MAXSIZE_PACK32 + sizeof(uint32_t)) {
+ send();
+ }
+ frameHeader();
+ writeCpuSize();
+ Buffer::packInt(mBuf, sizeof(mBuf), mWritePos, cpu);
+ mCpuSizePos = mWritePos;
+ // Reserve space for cpu size
+ mWritePos += sizeof(uint32_t);
+ }
+
+ // Pick a big size but something smaller than the chunkSize in Sender::writeData which is 100k
+ char mBuf[1<<16];
+ Sender *const mSender;
+ int mWritePos;
+ int mCpuSizePos;
+
+ // Intentionally unimplemented
+ PerfFrame(const PerfFrame &);
+ PerfFrame& operator=(const PerfFrame &);
+};
+
+bool PerfBuffer::send(Sender *const sender) {
+ PerfFrame frame(sender);
+
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ if (mBuf[cpu] == MAP_FAILED) {
+ continue;
+ }
+
+ // Take a snapshot of the positions
+ struct perf_event_mmap_page *pemp = static_cast<struct perf_event_mmap_page *>(mBuf[cpu]);
+ const __u64 head = ACCESS_ONCE(pemp->data_head);
+ const __u64 tail = ACCESS_ONCE(pemp->data_tail);
+
+ if (head > tail) {
+ const uint8_t *const b = static_cast<uint8_t *>(mBuf[cpu]) + gSessionData->mPageSize;
+ frame.add(cpu, head, tail, b);
+
+ // Update tail with the data read
+ pemp->data_tail = head;
+ }
+
+ if (mDiscard[cpu]) {
+ munmap(mBuf[cpu], gSessionData->mPageSize + BUF_SIZE);
+ mBuf[cpu] = MAP_FAILED;
+ mDiscard[cpu] = false;
+ mFds[cpu] = -1;
+ logg->logMessage("Unmaped cpu %i", cpu);
+ }
+ }
+
+ frame.send();
+
+ return true;
+}
diff --git a/tools/gator/daemon/PerfBuffer.h b/tools/gator/daemon/PerfBuffer.h
new file mode 100644
index 0000000..a2d0e9b
--- /dev/null
+++ b/tools/gator/daemon/PerfBuffer.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_BUFFER
+#define PERF_BUFFER
+
+#include "Config.h"
+
+#define BUF_SIZE (gSessionData->mTotalBufferSize * 1024 * 1024)
+#define BUF_MASK (BUF_SIZE - 1)
+
+class Sender;
+
+class PerfBuffer {
+public:
+ PerfBuffer();
+ ~PerfBuffer();
+
+ bool useFd(const int cpu, const int fd);
+ void discard(const int cpu);
+ bool isEmpty();
+ bool isFull();
+ bool send(Sender *const sender);
+
+private:
+ void *mBuf[NR_CPUS];
+ // After the buffer is flushed it should be unmaped
+ bool mDiscard[NR_CPUS];
+ // fd that corresponds to the mBuf
+ int mFds[NR_CPUS];
+
+ // Intentionally undefined
+ PerfBuffer(const PerfBuffer &);
+ PerfBuffer &operator=(const PerfBuffer &);
+};
+
+#endif // PERF_BUFFER
diff --git a/tools/gator/daemon/PerfDriver.cpp b/tools/gator/daemon/PerfDriver.cpp
new file mode 100644
index 0000000..796ee75
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.cpp
@@ -0,0 +1,409 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfDriver.h"
+
+#include <dirent.h>
+#include <sys/utsname.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Config.h"
+#include "ConfigurationXML.h"
+#include "Counter.h"
+#include "DriverSource.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfGroup.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+#define PERF_DEVICES "/sys/bus/event_source/devices"
+
+#define TYPE_DERIVED ~0U
+
+// From gator.h
+struct gator_cpu {
+ const int cpuid;
+ // Human readable name
+ const char *const core_name;
+ // gatorfs event and Perf PMU name
+ const char *const pmnc_name;
+ const int pmnc_counters;
+};
+
+// From gator_main.c
+static const struct gator_cpu gator_cpus[] = {
+ { 0x41b36, "ARM1136", "ARM_ARM11", 3 },
+ { 0x41b56, "ARM1156", "ARM_ARM11", 3 },
+ { 0x41b76, "ARM1176", "ARM_ARM11", 3 },
+ { 0x41b02, "ARM11MPCore", "ARM_ARM11MPCore", 3 },
+ { 0x41c05, "Cortex-A5", "ARMv7_Cortex_A5", 2 },
+ { 0x41c07, "Cortex-A7", "ARMv7_Cortex_A7", 4 },
+ { 0x41c08, "Cortex-A8", "ARMv7_Cortex_A8", 4 },
+ { 0x41c09, "Cortex-A9", "ARMv7_Cortex_A9", 6 },
+ { 0x41c0f, "Cortex-A15", "ARMv7_Cortex_A15", 6 },
+ { 0x41c0d, "Cortex-A17", "ARMv7_Cortex_A17", 6 },
+ { 0x41c0e, "Cortex-A17", "ARMv7_Cortex_A17", 6 },
+ { 0x5100f, "Scorpion", "Scorpion", 4 },
+ { 0x5102d, "ScorpionMP", "ScorpionMP", 4 },
+ { 0x51049, "KraitSIM", "Krait", 4 },
+ { 0x5104d, "Krait", "Krait", 4 },
+ { 0x5106f, "Krait S4 Pro", "Krait", 4 },
+ { 0x41d03, "Cortex-A53", "ARM_Cortex-A53", 6 },
+ { 0x41d07, "Cortex-A57", "ARM_Cortex-A57", 6 },
+ { 0x41d08, "Cortex-A72", "ARM_Cortex-A72", 6 },
+};
+
+static const char OLD_PMU_PREFIX[] = "ARMv7 Cortex-";
+static const char NEW_PMU_PREFIX[] = "ARMv7_Cortex_";
+
+struct uncore_counter {
+ // Perf PMU name
+ const char *const perfName;
+ // gatorfs event name
+ const char *const gatorName;
+ const int count;
+ const bool hasCyclesCounter;
+};
+
+static const struct uncore_counter uncore_counters[] = {
+ { "CCI_400", "CCI_400", 4, true },
+ { "CCI_400-r1", "CCI_400-r1", 4, true },
+ { "CCI_500", "CCI_500", 8, false },
+ { "ccn", "ARM_CCN_5XX", 8, true },
+};
+
+class PerfCounter : public DriverCounter {
+public:
+ PerfCounter(DriverCounter *next, const char *name, uint32_t type, uint64_t config, uint64_t sampleType, uint64_t flags) : DriverCounter(next, name), mType(type), mConfig(config), mSampleType(sampleType), mFlags(flags), mCount(0) {}
+
+ ~PerfCounter() {
+ }
+
+ uint32_t getType() const { return mType; }
+ int getCount() const { return mCount; }
+ void setCount(const int count) { mCount = count; }
+ uint64_t getConfig() const { return mConfig; }
+ void setConfig(const uint64_t config) { mConfig = config; }
+ uint64_t getSampleType() const { return mSampleType; }
+ uint64_t getFlags() const { return mFlags; }
+ virtual void read(Buffer *const, const int) {}
+
+private:
+ const uint32_t mType;
+ uint64_t mConfig;
+ const uint64_t mSampleType;
+ const uint64_t mFlags;
+ int mCount;
+
+ // Intentionally undefined
+ PerfCounter(const PerfCounter &);
+ PerfCounter &operator=(const PerfCounter &);
+};
+
+class CPUFreqDriver : public PerfCounter {
+public:
+ CPUFreqDriver(DriverCounter *next, uint64_t id) : PerfCounter(next, "Linux_power_cpu_freq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_RAW, PERF_GROUP_LEADER | PERF_GROUP_PER_CPU) {}
+
+ void read(Buffer *const buffer, const int cpu) {
+ char buf[64];
+
+ snprintf(buf, sizeof(buf), "/sys/devices/system/cpu/cpu%i/cpufreq/cpuinfo_cur_freq", cpu);
+ int64_t freq;
+ if (DriverSource::readInt64Driver(buf, &freq) != 0) {
+ freq = 0;
+ }
+ buffer->perfCounter(cpu, getKey(), 1000*freq);
+ }
+
+private:
+ // Intentionally undefined
+ CPUFreqDriver(const CPUFreqDriver &);
+ CPUFreqDriver &operator=(const CPUFreqDriver &);
+};
+
+PerfDriver::PerfDriver() : mIsSetup(false), mLegacySupport(false) {
+}
+
+PerfDriver::~PerfDriver() {
+}
+
+void PerfDriver::addCpuCounters(const char *const counterName, const int type, const int numCounters) {
+ int len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+ char *name = new char[len];
+ snprintf(name, len, "%s_ccnt", counterName);
+ setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU));
+
+ for (int j = 0; j < numCounters; ++j) {
+ len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+ name = new char[len];
+ snprintf(name, len, "%s_cnt%d", counterName, j);
+ setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU));
+ }
+}
+
+void PerfDriver::addUncoreCounters(const char *const counterName, const int type, const int numCounters, const bool hasCyclesCounter) {
+ int len;
+ char *name;
+
+ if (hasCyclesCounter) {
+ len = snprintf(NULL, 0, "%s_ccnt", counterName) + 1;
+ name = new char[len];
+ snprintf(name, len, "%s_ccnt", counterName);
+ setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, 0));
+ }
+
+ for (int j = 0; j < numCounters; ++j) {
+ len = snprintf(NULL, 0, "%s_cnt%d", counterName, j) + 1;
+ name = new char[len];
+ snprintf(name, len, "%s_cnt%d", counterName, j);
+ setCounters(new PerfCounter(getCounters(), name, type, -1, PERF_SAMPLE_READ, 0));
+ }
+}
+
+bool PerfDriver::setup() {
+ // Check the kernel version
+ int release[3];
+ if (!getLinuxVersion(release)) {
+ logg->logMessage("getLinuxVersion failed");
+ return false;
+ }
+
+ if (KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 4, 0)) {
+ logg->logMessage("Unsupported kernel version");
+ return false;
+ }
+ mLegacySupport = KERNEL_VERSION(release[0], release[1], release[2]) < KERNEL_VERSION(3, 12, 0);
+
+ if (access(EVENTS_PATH, R_OK) != 0) {
+ logg->logMessage(EVENTS_PATH " does not exist, is CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER enabled?");
+ return false;
+ }
+
+ // Add supported PMUs
+ bool foundCpu = false;
+ DIR *dir = opendir(PERF_DEVICES);
+ if (dir == NULL) {
+ logg->logMessage("opendir failed");
+ return false;
+ }
+
+ struct dirent *dirent;
+ while ((dirent = readdir(dir)) != NULL) {
+ for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+ const struct gator_cpu *const gator_cpu = &gator_cpus[i];
+
+ // Do the names match exactly?
+ if (strcasecmp(gator_cpu->pmnc_name, dirent->d_name) != 0 &&
+ // Do these names match but have the old vs new prefix?
+ ((strncasecmp(dirent->d_name, OLD_PMU_PREFIX, sizeof(OLD_PMU_PREFIX) - 1) != 0 ||
+ strncasecmp(gator_cpu->pmnc_name, NEW_PMU_PREFIX, sizeof(NEW_PMU_PREFIX) - 1) != 0 ||
+ strcasecmp(dirent->d_name + sizeof(OLD_PMU_PREFIX) - 1, gator_cpu->pmnc_name + sizeof(NEW_PMU_PREFIX) - 1) != 0))) {
+ continue;
+ }
+
+ int type;
+ char buf[256];
+ snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+ if (DriverSource::readIntDriver(buf, &type) != 0) {
+ continue;
+ }
+
+ foundCpu = true;
+ logg->logMessage("Adding cpu counters for %s", gator_cpu->pmnc_name);
+ addCpuCounters(gator_cpu->pmnc_name, type, gator_cpu->pmnc_counters);
+ }
+
+ for (int i = 0; i < ARRAY_LENGTH(uncore_counters); ++i) {
+ if (strcmp(dirent->d_name, uncore_counters[i].perfName) != 0) {
+ continue;
+ }
+
+ int type;
+ char buf[256];
+ snprintf(buf, sizeof(buf), PERF_DEVICES "/%s/type", dirent->d_name);
+ if (DriverSource::readIntDriver(buf, &type) != 0) {
+ continue;
+ }
+
+ logg->logMessage("Adding uncore counters for %s", uncore_counters[i].gatorName);
+ addUncoreCounters(uncore_counters[i].gatorName, type, uncore_counters[i].count, uncore_counters[i].hasCyclesCounter);
+ }
+ }
+ closedir(dir);
+
+ if (!foundCpu) {
+ // If no cpu was found based on pmu names, try by cpuid
+ for (int i = 0; i < ARRAY_LENGTH(gator_cpus); ++i) {
+ if (gSessionData->mMaxCpuId != gator_cpus[i].cpuid) {
+ continue;
+ }
+
+ foundCpu = true;
+ logg->logMessage("Adding cpu counters (based on cpuid) for %s", gator_cpus[i].pmnc_name);
+ addCpuCounters(gator_cpus[i].pmnc_name, PERF_TYPE_RAW, gator_cpus[i].pmnc_counters);
+ }
+ }
+
+ if (!foundCpu) {
+ // If all else fails, use the ARM architected counters
+ logg->logMessage("Using Other cpu");
+ addCpuCounters("Other", PERF_TYPE_RAW, 6);
+ }
+
+ // Add supported software counters
+ long long id;
+ DynBuf printb;
+
+ id = getTracepointId("irq/softirq_exit", &printb);
+ if (id >= 0) {
+ setCounters(new PerfCounter(getCounters(), "Linux_irq_softirq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU));
+ }
+
+ id = getTracepointId("irq/irq_handler_exit", &printb);
+ if (id >= 0) {
+ setCounters(new PerfCounter(getCounters(), "Linux_irq_irq", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU));
+ }
+
+ id = getTracepointId(SCHED_SWITCH, &printb);
+ if (id >= 0) {
+ setCounters(new PerfCounter(getCounters(), "Linux_sched_switch", PERF_TYPE_TRACEPOINT, id, PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU));
+ }
+
+ id = getTracepointId(CPU_FREQUENCY, &printb);
+ if (id >= 0) {
+ setCounters(new CPUFreqDriver(getCounters(), id));
+ }
+
+ setCounters(new PerfCounter(getCounters(), "Linux_cpu_wait_contention", TYPE_DERIVED, -1, 0, 0));
+
+ //Linux_cpu_wait_io
+
+ mIsSetup = true;
+ return true;
+}
+
+bool PerfDriver::summary(Buffer *const buffer) {
+ struct utsname utsname;
+ if (uname(&utsname) != 0) {
+ logg->logMessage("uname failed");
+ return false;
+ }
+
+ char buf[512];
+ snprintf(buf, sizeof(buf), "%s %s %s %s %s GNU/Linux", utsname.sysname, utsname.nodename, utsname.release, utsname.version, utsname.machine);
+
+ struct timespec ts;
+ if (clock_gettime(CLOCK_REALTIME, &ts) != 0) {
+ logg->logMessage("clock_gettime failed");
+ return false;
+ }
+ const int64_t timestamp = (int64_t)ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+ const uint64_t monotonicStarted = getTime();
+ gSessionData->mMonotonicStarted = monotonicStarted;
+ const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+ buffer->summary(currTime, timestamp, monotonicStarted, monotonicStarted, buf);
+
+ for (int i = 0; i < gSessionData->mCores; ++i) {
+ coreName(currTime, buffer, i);
+ }
+ buffer->commit(currTime);
+
+ return true;
+}
+
+void PerfDriver::coreName(const uint64_t currTime, Buffer *const buffer, const int cpu) {
+ // Don't send information on a cpu we know nothing about
+ if (gSessionData->mCpuIds[cpu] == -1) {
+ return;
+ }
+
+ int j;
+ for (j = 0; j < ARRAY_LENGTH(gator_cpus); ++j) {
+ if (gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+ break;
+ }
+ }
+ if (j < ARRAY_LENGTH(gator_cpus) && gator_cpus[j].cpuid == gSessionData->mCpuIds[cpu]) {
+ buffer->coreName(currTime, cpu, gSessionData->mCpuIds[cpu], gator_cpus[j].core_name);
+ } else {
+ char buf[32];
+ if (gSessionData->mCpuIds[cpu] == -1) {
+ snprintf(buf, sizeof(buf), "Unknown");
+ } else {
+ snprintf(buf, sizeof(buf), "Unknown (0x%.3x)", gSessionData->mCpuIds[cpu]);
+ }
+ buffer->coreName(currTime, cpu, gSessionData->mCpuIds[cpu], buf);
+ }
+}
+
+void PerfDriver::setupCounter(Counter &counter) {
+ PerfCounter *const perfCounter = static_cast<PerfCounter *>(findCounter(counter));
+ if (perfCounter == NULL) {
+ counter.setEnabled(false);
+ return;
+ }
+
+ // Don't use the config from counters XML if it's not set, ex: software counters
+ if (counter.getEvent() != -1) {
+ perfCounter->setConfig(counter.getEvent());
+ }
+ perfCounter->setCount(counter.getCount());
+ perfCounter->setEnabled(true);
+ counter.setKey(perfCounter->getKey());
+}
+
+bool PerfDriver::enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const {
+ for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+ if (counter->isEnabled() && (counter->getType() != TYPE_DERIVED)) {
+ int count = counter->getCount();
+ uint64_t sampleType = counter->getSampleType();
+ if (sampleType & PERF_SAMPLE_RAW) {
+ // If raw is enabled, every sample is needed
+ count = 1;
+ }
+ if (!group->add(currTime, buffer, counter->getKey(), counter->getType(), counter->getConfig(), count,
+ // use getCount instead of count as EBS counters need TID and IP but RAW tracepoints don't
+ (counter->getCount() > 0 ? PERF_SAMPLE_TID | PERF_SAMPLE_IP : 0) | sampleType,
+ counter->getFlags())) {
+ logg->logMessage("PerfGroup::add failed");
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
+void PerfDriver::read(Buffer *const buffer, const int cpu) {
+ for (PerfCounter *counter = static_cast<PerfCounter *>(getCounters()); counter != NULL; counter = static_cast<PerfCounter *>(counter->getNext())) {
+ if (!counter->isEnabled()) {
+ continue;
+ }
+ counter->read(buffer, cpu);
+ }
+}
+
+long long PerfDriver::getTracepointId(const char *const name, DynBuf *const printb) {
+ if (!printb->printf(EVENTS_PATH "/%s/id", name)) {
+ logg->logMessage("DynBuf::printf failed");
+ return -1;
+ }
+
+ int64_t result;
+ if (DriverSource::readInt64Driver(printb->getBuf(), &result) != 0) {
+ logg->logMessage("DriverSource::readInt64Driver failed");
+ return -1;
+ }
+
+ return result;
+}
diff --git a/tools/gator/daemon/PerfDriver.h b/tools/gator/daemon/PerfDriver.h
new file mode 100644
index 0000000..95b42bf
--- /dev/null
+++ b/tools/gator/daemon/PerfDriver.h
@@ -0,0 +1,59 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFDRIVER_H
+#define PERFDRIVER_H
+
+#include <stdint.h>
+
+#include "Driver.h"
+
+// If debugfs is not mounted at /sys/kernel/debug, update DEBUGFS_PATH
+#define DEBUGFS_PATH "/sys/kernel/debug"
+#define EVENTS_PATH DEBUGFS_PATH "/tracing/events"
+
+#define SCHED_SWITCH "sched/sched_switch"
+#define CPU_IDLE "power/cpu_idle"
+#define CPU_FREQUENCY "power/cpu_frequency"
+
+class Buffer;
+class DynBuf;
+class PerfGroup;
+
+class PerfDriver : public SimpleDriver {
+public:
+ PerfDriver();
+ ~PerfDriver();
+
+ bool getLegacySupport() const { return mLegacySupport; }
+
+ bool setup();
+ bool summary(Buffer *const buffer);
+ void coreName(const uint64_t currTime, Buffer *const buffer, const int cpu);
+ bool isSetup() const { return mIsSetup; }
+
+ void setupCounter(Counter &counter);
+
+ bool enable(const uint64_t currTime, PerfGroup *const group, Buffer *const buffer) const;
+ void read(Buffer *const buffer, const int cpu);
+
+ static long long getTracepointId(const char *const name, DynBuf *const printb);
+
+private:
+ void addCpuCounters(const char *const counterName, const int type, const int numCounters);
+ void addUncoreCounters(const char *const counterName, const int type, const int numCounters, const bool hasCyclesCounter);
+
+ bool mIsSetup;
+ bool mLegacySupport;
+
+ // Intentionally undefined
+ PerfDriver(const PerfDriver &);
+ PerfDriver &operator=(const PerfDriver &);
+};
+
+#endif // PERFDRIVER_H
diff --git a/tools/gator/daemon/PerfGroup.cpp b/tools/gator/daemon/PerfGroup.cpp
new file mode 100644
index 0000000..cfc62e4
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.cpp
@@ -0,0 +1,358 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfGroup.h"
+
+#include <errno.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "SessionData.h"
+
+static const int schedSwitchKey = getEventKey();
+static const int clockKey = getEventKey();
+
+#define DEFAULT_PEA_ARGS(pea, additionalSampleType) \
+ pea.size = sizeof(pea); \
+ /* Emit time, read_format below, group leader id, and raw tracepoint info */ \
+ pea.sample_type = (gSessionData->perf.getLegacySupport() \
+ ? PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_ID \
+ : PERF_SAMPLE_IDENTIFIER ) | PERF_SAMPLE_TIME | additionalSampleType; \
+ /* Emit emit value in group format */ \
+ pea.read_format = PERF_FORMAT_ID | PERF_FORMAT_GROUP; \
+ /* start out disabled */ \
+ pea.disabled = 1; \
+ /* have a sampling interrupt happen when we cross the wakeup_watermark boundary */ \
+ pea.watermark = 1; \
+ /* Be conservative in flush size as only one buffer set is monitored */ \
+ pea.wakeup_watermark = BUF_SIZE / 2
+
+static int sys_perf_event_open(struct perf_event_attr *const attr, const pid_t pid, const int cpu, const int group_fd, const unsigned long flags) {
+ int fd = syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+ if (fd < 0) {
+ return -1;
+ }
+ int fdf = fcntl(fd, F_GETFD);
+ if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ close(fd);
+ return -1;
+ }
+ return fd;
+}
+
+PerfGroup::PerfGroup(PerfBuffer *const pb) : mPb(pb), mSchedSwitchId(-1) {
+ memset(&mAttrs, 0, sizeof(mAttrs));
+ memset(&mFlags, 0, sizeof(mFlags));
+ memset(&mKeys, -1, sizeof(mKeys));
+ memset(&mFds, -1, sizeof(mFds));
+ memset(&mLeaders, -1, sizeof(mLeaders));
+}
+
+PerfGroup::~PerfGroup() {
+ for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+ if (mFds[pos] >= 0) {
+ close(mFds[pos]);
+ }
+ }
+}
+
+int PerfGroup::doAdd(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+ int i;
+ for (i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+ if (mKeys[i] < 0) {
+ break;
+ }
+ }
+
+ if (i >= ARRAY_LENGTH(mKeys)) {
+ logg->logMessage("Too many counters");
+ return -1;
+ }
+
+ DEFAULT_PEA_ARGS(mAttrs[i], sampleType);
+ mAttrs[i].type = type;
+ mAttrs[i].config = config;
+ mAttrs[i].sample_period = sample;
+ // always be on the CPU but only a group leader can be pinned
+ mAttrs[i].pinned = (flags & PERF_GROUP_LEADER ? 1 : 0);
+ mAttrs[i].mmap = (flags & PERF_GROUP_MMAP ? 1 : 0);
+ mAttrs[i].comm = (flags & PERF_GROUP_COMM ? 1 : 0);
+ mAttrs[i].freq = (flags & PERF_GROUP_FREQ ? 1 : 0);
+ mAttrs[i].task = (flags & PERF_GROUP_TASK ? 1 : 0);
+ mAttrs[i].sample_id_all = (flags & PERF_GROUP_SAMPLE_ID_ALL ? 1 : 0);
+ mFlags[i] = flags;
+
+ mKeys[i] = key;
+
+ buffer->marshalPea(currTime, &mAttrs[i], key);
+
+ return i;
+}
+
+/* Counters from different hardware PMUs need to be in different
+ * groups. Software counters can be in the same group as the CPU and
+ * should be marked as PERF_GROUP_CPU. The big and little clusters can
+ * be in the same group as only one or the other will be available on
+ * a given CPU.
+ */
+int PerfGroup::getEffectiveType(const int type, const int flags) {
+ const int effectiveType = flags & PERF_GROUP_CPU ? (int)PERF_TYPE_HARDWARE : type;
+ if (effectiveType >= ARRAY_LENGTH(mLeaders)) {
+ logg->logError("perf type is too large, please increase the size of PerfGroup::mLeaders");
+ handleException();
+ }
+ return effectiveType;
+}
+
+bool PerfGroup::createCpuGroup(const uint64_t currTime, Buffer *const buffer) {
+ if (mSchedSwitchId < 0) {
+ DynBuf b;
+ mSchedSwitchId = PerfDriver::getTracepointId(SCHED_SWITCH, &b);
+ if (mSchedSwitchId < 0) {
+ logg->logMessage("Unable to read sched_switch id");
+ return false;
+ }
+ }
+
+ mLeaders[PERF_TYPE_HARDWARE] = doAdd(currTime, buffer, schedSwitchKey, PERF_TYPE_TRACEPOINT, mSchedSwitchId, 1, PERF_SAMPLE_READ | PERF_SAMPLE_RAW, PERF_GROUP_MMAP | PERF_GROUP_COMM | PERF_GROUP_TASK | PERF_GROUP_SAMPLE_ID_ALL | PERF_GROUP_PER_CPU | PERF_GROUP_LEADER | PERF_GROUP_CPU);
+ if (mLeaders[PERF_TYPE_HARDWARE] < 0) {
+ return false;
+ }
+
+ if (gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS && doAdd(currTime, buffer, clockKey, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, 1000000000UL / gSessionData->mSampleRate, PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_READ, PERF_GROUP_PER_CPU | PERF_GROUP_CPU) < 0) {
+ return false;
+ }
+
+ return true;
+}
+
+bool PerfGroup::add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags) {
+ const int effectiveType = getEffectiveType(type, flags);
+
+ // Does a group exist for this already?
+ if (!(flags & PERF_GROUP_LEADER) && mLeaders[effectiveType] < 0) {
+ // Create it
+ if (effectiveType == PERF_TYPE_HARDWARE) {
+ if (!createCpuGroup(currTime, buffer)) {
+ return false;
+ }
+ } else {
+ // Non-CPU PMUs are sampled every 100ms for Sample Rate: None and EBS, otherwise they would never be sampled
+ const uint64_t timeout = gSessionData->mSampleRate > 0 && !gSessionData->mIsEBS ? 1000000000UL / gSessionData->mSampleRate : 100000000UL;
+ // PERF_SAMPLE_TID | PERF_SAMPLE_IP aren't helpful on non-CPU or 'uncore' PMUs - which CPU is the right one to sample? But removing it causes problems, remove it later.
+ mLeaders[effectiveType] = doAdd(currTime, buffer, clockKey, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK, timeout, PERF_SAMPLE_TID | PERF_SAMPLE_IP | PERF_SAMPLE_READ, PERF_GROUP_LEADER);
+ if (mLeaders[effectiveType] < 0) {
+ return false;
+ }
+ }
+ }
+
+ if (!(flags & PERF_GROUP_LEADER) && effectiveType != PERF_TYPE_HARDWARE && (flags & PERF_GROUP_PER_CPU)) {
+ logg->logError("'uncore' counters are not permitted to be per-cpu");
+ handleException();
+ }
+
+ return doAdd(currTime, buffer, key, type, config, sample, sampleType, flags) >= 0;
+}
+
+int PerfGroup::prepareCPU(const int cpu, Monitor *const monitor) {
+ logg->logMessage("Onlining cpu %i", cpu);
+
+ for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+ if (mKeys[i] < 0) {
+ continue;
+ }
+
+ if ((cpu != 0) && !(mFlags[i] & PERF_GROUP_PER_CPU)) {
+ continue;
+ }
+
+ const int offset = i * gSessionData->mCores + cpu;
+ if (mFds[offset] >= 0) {
+ logg->logMessage("cpu already online or not correctly cleaned up");
+ return PG_FAILURE;
+ }
+
+ logg->logMessage("perf_event_open cpu: %i type: %i config: %lli sample: %lli sample_type: 0x%llx pinned: %lli mmap: %lli comm: %lli freq: %lli task: %lli sample_id_all: %lli", cpu, mAttrs[i].type, mAttrs[i].config, mAttrs[i].sample_period, mAttrs[i].sample_type, mAttrs[i].pinned, mAttrs[i].mmap, mAttrs[i].comm, mAttrs[i].freq, mAttrs[i].task, mAttrs[i].sample_id_all);
+ mFds[offset] = sys_perf_event_open(&mAttrs[i], -1, cpu, mAttrs[i].pinned ? -1 : mFds[mLeaders[getEffectiveType(mAttrs[i].type, mFlags[i])] * gSessionData->mCores + cpu], mAttrs[i].pinned ? 0 : PERF_FLAG_FD_OUTPUT);
+ if (mFds[offset] < 0) {
+ logg->logMessage("failed %s", strerror(errno));
+ if (errno == ENODEV) {
+ // The core is offline
+ return PG_CPU_OFFLINE;
+ }
+#ifndef USE_STRICTER_CHECK
+ continue;
+#else
+ if (errno == ENOENT) {
+ // This event doesn't apply to this CPU but should apply to a different one, ex bL
+ continue;
+ }
+ logg->logMessage("perf_event_open failed");
+ return PG_FAILURE;
+#endif
+ }
+
+ if (!mPb->useFd(cpu, mFds[offset])) {
+ logg->logMessage("PerfBuffer::useFd failed");
+ return PG_FAILURE;
+ }
+
+
+ if (!monitor->add(mFds[offset])) {
+ logg->logMessage("Monitor::add failed");
+ return PG_FAILURE;
+ }
+ }
+
+ return PG_SUCCESS;
+}
+
+static bool readAndSend(const uint64_t currTime, Buffer *const buffer, const int fd, const int keyCount, const int *const keys) {
+ char buf[1024];
+ ssize_t bytes = read(fd, buf, sizeof(buf));
+ if (bytes < 0) {
+ logg->logMessage("read failed");
+ return false;
+ }
+ buffer->marshalKeysOld(currTime, keyCount, keys, bytes, buf);
+
+ return true;
+}
+
+int PerfGroup::onlineCPU(const uint64_t currTime, const int cpu, const bool enable, Buffer *const buffer) {
+ bool addedEvents = false;
+
+ if (!gSessionData->perf.getLegacySupport()) {
+ int idCount = 0;
+ int coreKeys[ARRAY_LENGTH(mKeys)];
+ __u64 ids[ARRAY_LENGTH(mKeys)];
+
+ for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+ const int fd = mFds[cpu + i * gSessionData->mCores];
+ if (fd < 0) {
+ continue;
+ }
+
+ coreKeys[idCount] = mKeys[i];
+ if (ioctl(fd, PERF_EVENT_IOC_ID, &ids[idCount]) != 0 &&
+ // Workaround for running 32-bit gatord on 64-bit systems, kernel patch in the works
+ ioctl(fd, (PERF_EVENT_IOC_ID & ~IOCSIZE_MASK) | (8 << _IOC_SIZESHIFT), &ids[idCount]) != 0) {
+ logg->logMessage("ioctl failed");
+ return 0;
+ }
+ ++idCount;
+ addedEvents = true;
+ }
+
+ buffer->marshalKeys(currTime, idCount, ids, coreKeys);
+ } else {
+ int idCounts[ARRAY_LENGTH(mLeaders)] = { 0 };
+ int coreKeys[ARRAY_LENGTH(mLeaders)][ARRAY_LENGTH(mKeys)];
+ for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+ const int fd = mFds[cpu + i * gSessionData->mCores];
+ if (fd < 0) {
+ continue;
+ }
+
+ const int effectiveType = getEffectiveType(mAttrs[i].type, mFlags[i]);
+ if (mAttrs[i].pinned && mLeaders[effectiveType] != i) {
+ if (!readAndSend(currTime, buffer, fd, 1, mKeys + i)) {
+ return 0;
+ }
+ } else {
+ coreKeys[effectiveType][idCounts[effectiveType]] = mKeys[i];
+ ++idCounts[effectiveType];
+ addedEvents = true;
+ }
+ }
+
+ for (int i = 0; i < ARRAY_LENGTH(mLeaders); ++i) {
+ if (idCounts[i] > 0 && !readAndSend(currTime, buffer, mFds[mLeaders[i] * gSessionData->mCores + cpu], idCounts[i], coreKeys[i])) {
+ return 0;
+ }
+ }
+ }
+
+ if (enable) {
+ for (int i = 0; i < ARRAY_LENGTH(mKeys); ++i) {
+ int offset = i * gSessionData->mCores + cpu;
+ if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ logg->logMessage("ioctl failed");
+ return 0;
+ }
+ }
+ }
+
+ if (!addedEvents) {
+ logg->logMessage("no events came online");
+ }
+
+ return 1;
+}
+
+bool PerfGroup::offlineCPU(const int cpu) {
+ logg->logMessage("Offlining cpu %i", cpu);
+
+ for (int i = ARRAY_LENGTH(mKeys) - 1; i >= 0; --i) {
+ int offset = i * gSessionData->mCores + cpu;
+ if (mFds[offset] >= 0 && ioctl(mFds[offset], PERF_EVENT_IOC_DISABLE, 0) < 0) {
+ logg->logMessage("ioctl failed");
+ return false;
+ }
+ }
+
+ // Mark the buffer so that it will be released next time it's read
+ mPb->discard(cpu);
+
+ for (int i = ARRAY_LENGTH(mKeys) - 1; i >= 0; --i) {
+ if (mKeys[i] < 0) {
+ continue;
+ }
+
+ int offset = i * gSessionData->mCores + cpu;
+ if (mFds[offset] >= 0) {
+ close(mFds[offset]);
+ mFds[offset] = -1;
+ }
+ }
+
+ return true;
+}
+
+bool PerfGroup::start() {
+ for (int pos = 0; pos < ARRAY_LENGTH(mFds); ++pos) {
+ if (mFds[pos] >= 0 && ioctl(mFds[pos], PERF_EVENT_IOC_ENABLE, 0) < 0) {
+ logg->logMessage("ioctl failed");
+ goto fail;
+ }
+ }
+
+ return true;
+
+ fail:
+ stop();
+
+ return false;
+}
+
+void PerfGroup::stop() {
+ for (int pos = ARRAY_LENGTH(mFds) - 1; pos >= 0; --pos) {
+ if (mFds[pos] >= 0) {
+ ioctl(mFds[pos], PERF_EVENT_IOC_DISABLE, 0);
+ }
+ }
+}
diff --git a/tools/gator/daemon/PerfGroup.h b/tools/gator/daemon/PerfGroup.h
new file mode 100644
index 0000000..f30d3a6
--- /dev/null
+++ b/tools/gator/daemon/PerfGroup.h
@@ -0,0 +1,74 @@
+ /**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERF_GROUP
+#define PERF_GROUP
+
+#include <stdint.h>
+
+// Use a snapshot of perf_event.h as it may be more recent than what is on the target and if not newer features won't be supported anyways
+#include "k/perf_event.h"
+
+#include "Config.h"
+
+class Buffer;
+class Monitor;
+class PerfBuffer;
+
+enum PerfGroupFlags {
+ PERF_GROUP_MMAP = 1 << 0,
+ PERF_GROUP_COMM = 1 << 1,
+ PERF_GROUP_FREQ = 1 << 2,
+ PERF_GROUP_TASK = 1 << 3,
+ PERF_GROUP_SAMPLE_ID_ALL = 1 << 4,
+ PERF_GROUP_PER_CPU = 1 << 5,
+ PERF_GROUP_LEADER = 1 << 6,
+ PERF_GROUP_CPU = 1 << 7,
+};
+
+enum {
+ PG_SUCCESS = 0,
+ PG_FAILURE,
+ PG_CPU_OFFLINE,
+};
+
+class PerfGroup {
+public:
+ PerfGroup(PerfBuffer *const pb);
+ ~PerfGroup();
+
+ bool createCpuGroup(const uint64_t currTime, Buffer *const buffer);
+ bool add(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+ // Safe to call concurrently
+ int prepareCPU(const int cpu, Monitor *const monitor);
+ // Not safe to call concurrently. Returns the number of events enabled
+ int onlineCPU(const uint64_t currTime, const int cpu, const bool enable, Buffer *const buffer);
+ bool offlineCPU(int cpu);
+ bool start();
+ void stop();
+
+private:
+ int getEffectiveType(const int type, const int flags);
+ int doAdd(const uint64_t currTime, Buffer *const buffer, const int key, const __u32 type, const __u64 config, const __u64 sample, const __u64 sampleType, const int flags);
+
+ // 2* to be conservative for sched_switch, cpu_idle, hrtimer and non-CPU groups
+ struct perf_event_attr mAttrs[2*MAX_PERFORMANCE_COUNTERS];
+ PerfBuffer *const mPb;
+ int mFlags[2*MAX_PERFORMANCE_COUNTERS];
+ int mKeys[2*MAX_PERFORMANCE_COUNTERS];
+ int mFds[NR_CPUS * (2*MAX_PERFORMANCE_COUNTERS)];
+ // Offset in mAttrs, mFlags and mKeys of the group leaders for each perf type
+ int mLeaders[16];
+ int mSchedSwitchId;
+
+ // Intentionally undefined
+ PerfGroup(const PerfGroup &);
+ PerfGroup &operator=(const PerfGroup &);
+};
+
+#endif // PERF_GROUP
diff --git a/tools/gator/daemon/PerfSource.cpp b/tools/gator/daemon/PerfSource.cpp
new file mode 100644
index 0000000..2c45de8
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.cpp
@@ -0,0 +1,447 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "PerfSource.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "PerfDriver.h"
+#include "Proc.h"
+#include "SessionData.h"
+
+#ifndef SCHED_RESET_ON_FORK
+#define SCHED_RESET_ON_FORK 0x40000000
+#endif
+
+extern Child *child;
+
+static const int cpuIdleKey = getEventKey();
+
+static bool sendTracepointFormat(const uint64_t currTime, Buffer *const buffer, const char *const name, DynBuf *const printb, DynBuf *const b) {
+ if (!printb->printf(EVENTS_PATH "/%s/format", name)) {
+ logg->logMessage("DynBuf::printf failed");
+ return false;
+ }
+ if (!b->read(printb->getBuf())) {
+ logg->logMessage("DynBuf::read failed");
+ return false;
+ }
+ buffer->marshalFormat(currTime, b->getLength(), b->getBuf());
+
+ return true;
+}
+
+static void *syncFunc(void *arg)
+{
+ struct timespec ts;
+ int64_t nextTime = gSessionData->mMonotonicStarted;
+ int err;
+ (void)arg;
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-sync", 0, 0, 0);
+
+ // Mask all signals so that this thread will not be woken up
+ {
+ sigset_t set;
+ if (sigfillset(&set) != 0) {
+ logg->logError("sigfillset failed");
+ handleException();
+ }
+ if ((err = pthread_sigmask(SIG_SETMASK, &set, NULL)) != 0) {
+ logg->logError("pthread_sigmask failed");
+ handleException();
+ }
+ }
+
+ for (;;) {
+ if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+ logg->logError("clock_gettime failed");
+ handleException();
+ }
+ const int64_t currTime = ts.tv_sec * NS_PER_S + ts.tv_nsec;
+
+ // Wake up once a second
+ nextTime += NS_PER_S;
+
+ // Always sleep more than 1 ms, hopefully things will line up better next time
+ const int64_t sleepTime = max(nextTime - currTime, (int64_t)(NS_PER_MS + 1));
+ ts.tv_sec = sleepTime/NS_PER_S;
+ ts.tv_nsec = sleepTime % NS_PER_S;
+
+ err = nanosleep(&ts, NULL);
+ if (err != 0) {
+ fprintf(stderr, "clock_nanosleep failed: %s\n", strerror(err));
+ return NULL;
+ }
+ }
+
+ return NULL;
+}
+
+static long getMaxCoreNum() {
+ DIR *dir = opendir("/sys/devices/system/cpu");
+ if (dir == NULL) {
+ logg->logError("Unable to determine the number of cores on the target, opendir failed");
+ handleException();
+ }
+
+ long maxCoreNum = -1;
+ struct dirent *dirent;
+ while ((dirent = readdir(dir)) != NULL) {
+ if (strncmp(dirent->d_name, "cpu", 3) == 0) {
+ char *endptr;
+ errno = 0;
+ long coreNum = strtol(dirent->d_name + 3, &endptr, 10);
+ if ((errno == 0) && (*endptr == '\0') && (coreNum >= maxCoreNum)) {
+ maxCoreNum = coreNum + 1;
+ }
+ }
+ }
+ closedir(dir);
+
+ if (maxCoreNum < 1) {
+ logg->logError("Unable to determine the number of cores on the target, no cpu# directories found");
+ handleException();
+ }
+
+ if (maxCoreNum >= NR_CPUS) {
+ logg->logError("Too many cores on the target, please increase NR_CPUS in Config.h");
+ handleException();
+ }
+
+ return maxCoreNum;
+}
+
+PerfSource::PerfSource(sem_t *senderSem, sem_t *startProfile) : mSummary(0, FRAME_SUMMARY, 1024, senderSem), mBuffer(NULL), mCountersBuf(), mCountersGroup(&mCountersBuf), mMonitor(), mUEvent(), mSenderSem(senderSem), mStartProfile(startProfile), mInterruptFd(-1), mIsDone(false) {
+ long l = sysconf(_SC_PAGE_SIZE);
+ if (l < 0) {
+ logg->logError("Unable to obtain the page size");
+ handleException();
+ }
+ gSessionData->mPageSize = static_cast<int>(l);
+ gSessionData->mCores = static_cast<int>(getMaxCoreNum());
+}
+
+PerfSource::~PerfSource() {
+ delete mBuffer;
+}
+
+bool PerfSource::prepare() {
+ DynBuf printb;
+ DynBuf b1;
+ long long cpuIdleId;
+
+ // MonotonicStarted has not yet been assigned!
+ const uint64_t currTime = 0;//getTime() - gSessionData->mMonotonicStarted;
+
+ mBuffer = new Buffer(0, FRAME_PERF_ATTRS, gSessionData->mTotalBufferSize*1024*1024, mSenderSem);
+
+ // Reread cpuinfo since cores may have changed since startup
+ gSessionData->readCpuInfo();
+
+ if (0
+ || !mMonitor.init()
+ || !mUEvent.init()
+ || !mMonitor.add(mUEvent.getFd())
+
+ || !sendTracepointFormat(currTime, mBuffer, SCHED_SWITCH, &printb, &b1)
+
+ || (cpuIdleId = PerfDriver::getTracepointId(CPU_IDLE, &printb)) < 0
+ || !sendTracepointFormat(currTime, mBuffer, CPU_IDLE, &printb, &b1)
+
+ || !sendTracepointFormat(currTime, mBuffer, CPU_FREQUENCY, &printb, &b1)
+
+ || !mCountersGroup.createCpuGroup(currTime, mBuffer)
+ || !mCountersGroup.add(currTime, mBuffer, cpuIdleKey, PERF_TYPE_TRACEPOINT, cpuIdleId, 1, PERF_SAMPLE_RAW, PERF_GROUP_LEADER | PERF_GROUP_PER_CPU)
+
+ || !gSessionData->perf.enable(currTime, &mCountersGroup, mBuffer)
+ || 0) {
+ logg->logMessage("perf setup failed, are you running Linux 3.4 or later?");
+ return false;
+ }
+
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ const int result = mCountersGroup.prepareCPU(cpu, &mMonitor);
+ if ((result != PG_SUCCESS) && (result != PG_CPU_OFFLINE)) {
+ logg->logError("PerfGroup::prepareCPU on mCountersGroup failed");
+ handleException();
+ }
+ }
+
+ int numEvents = 0;
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ numEvents += mCountersGroup.onlineCPU(currTime, cpu, false, mBuffer);
+ }
+ if (numEvents <= 0) {
+ logg->logMessage("PerfGroup::onlineCPU failed on all cores");
+ return false;
+ }
+
+ // Send the summary right before the start so that the monotonic delta is close to the start time
+ if (!gSessionData->perf.summary(&mSummary)) {
+ logg->logError("PerfDriver::summary failed");
+ handleException();
+ }
+
+ // Start the timer thread to used to sync perf and monotonic raw times
+ pthread_t syncThread;
+ if (pthread_create(&syncThread, NULL, syncFunc, NULL)) {
+ logg->logError("pthread_create failed");
+ handleException();
+ }
+ struct sched_param param;
+ param.sched_priority = sched_get_priority_max(SCHED_FIFO);
+ if (pthread_setschedparam(syncThread, SCHED_FIFO | SCHED_RESET_ON_FORK, ¶m) != 0) {
+ logg->logError("pthread_setschedparam failed");
+ handleException();
+ }
+
+ mBuffer->commit(currTime);
+
+ return true;
+}
+
+struct ProcThreadArgs {
+ Buffer *mBuffer;
+ uint64_t mCurrTime;
+ bool mIsDone;
+};
+
+void *procFunc(void *arg) {
+ DynBuf printb;
+ DynBuf b;
+ const ProcThreadArgs *const args = (ProcThreadArgs *)arg;
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-proc", 0, 0, 0);
+
+ // Gator runs at a high priority, reset the priority to the default
+ if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), 0) == -1) {
+ logg->logError("setpriority failed");
+ handleException();
+ }
+
+ if (!readProcMaps(args->mCurrTime, args->mBuffer, &printb, &b)) {
+ logg->logError("readProcMaps failed");
+ handleException();
+ }
+
+ if (!readKallsyms(args->mCurrTime, args->mBuffer, &args->mIsDone)) {
+ logg->logError("readKallsyms failed");
+ handleException();
+ }
+ args->mBuffer->commit(args->mCurrTime);
+
+ return NULL;
+}
+
+static const char CPU_DEVPATH[] = "/devices/system/cpu/cpu";
+
+void PerfSource::run() {
+ int pipefd[2];
+ pthread_t procThread;
+ ProcThreadArgs procThreadArgs;
+
+ if (pipe_cloexec(pipefd) != 0) {
+ logg->logError("pipe failed");
+ handleException();
+ }
+ mInterruptFd = pipefd[1];
+
+ if (!mMonitor.add(pipefd[0])) {
+ logg->logError("Monitor::add failed");
+ handleException();
+ }
+
+ {
+ DynBuf printb;
+ DynBuf b1;
+ DynBuf b2;
+
+ const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+ // Start events before reading proc to avoid race conditions
+ if (!mCountersGroup.start()) {
+ logg->logError("PerfGroup::start failed");
+ handleException();
+ }
+
+ mBuffer->perfCounterHeader(currTime);
+ for (int cpu = 0; cpu < gSessionData->mCores; ++cpu) {
+ gSessionData->perf.read(mBuffer, cpu);
+ }
+ mBuffer->perfCounterFooter(currTime);
+
+ if (!readProcComms(currTime, mBuffer, &printb, &b1, &b2)) {
+ logg->logError("readProcComms failed");
+ handleException();
+ }
+ mBuffer->commit(currTime);
+
+ // Postpone reading kallsyms as on android adb gets too backed up and data is lost
+ procThreadArgs.mBuffer = mBuffer;
+ procThreadArgs.mCurrTime = currTime;
+ procThreadArgs.mIsDone = false;
+ if (pthread_create(&procThread, NULL, procFunc, &procThreadArgs)) {
+ logg->logError("pthread_create failed");
+ handleException();
+ }
+ }
+
+ sem_post(mStartProfile);
+
+ const uint64_t NO_RATE = ~0ULL;
+ const uint64_t rate = gSessionData->mLiveRate > 0 && gSessionData->mSampleRate > 0 ? gSessionData->mLiveRate : NO_RATE;
+ uint64_t nextTime = 0;
+ int timeout = rate != NO_RATE ? 0 : -1;
+ while (gSessionData->mSessionIsActive) {
+ // +1 for uevents, +1 for pipe
+ struct epoll_event events[NR_CPUS + 2];
+ int ready = mMonitor.wait(events, ARRAY_LENGTH(events), timeout);
+ if (ready < 0) {
+ logg->logError("Monitor::wait failed");
+ handleException();
+ }
+ const uint64_t currTime = getTime() - gSessionData->mMonotonicStarted;
+
+ for (int i = 0; i < ready; ++i) {
+ if (events[i].data.fd == mUEvent.getFd()) {
+ if (!handleUEvent(currTime)) {
+ logg->logError("PerfSource::handleUEvent failed");
+ handleException();
+ }
+ break;
+ }
+ }
+
+ // send a notification that data is ready
+ sem_post(mSenderSem);
+
+ // In one shot mode, stop collection once all the buffers are filled
+ if (gSessionData->mOneShot && gSessionData->mSessionIsActive && ((mSummary.bytesAvailable() <= 0) || (mBuffer->bytesAvailable() <= 0) || mCountersBuf.isFull())) {
+ logg->logMessage("One shot (perf)");
+ child->endSession();
+ }
+
+ if (rate != NO_RATE) {
+ while (currTime > nextTime) {
+ nextTime += rate;
+ }
+ // + NS_PER_MS - 1 to ensure always rounding up
+ timeout = max(0, (int)((nextTime + NS_PER_MS - 1 - getTime() + gSessionData->mMonotonicStarted)/NS_PER_MS));
+ }
+ }
+
+ procThreadArgs.mIsDone = true;
+ pthread_join(procThread, NULL);
+ mCountersGroup.stop();
+ mBuffer->setDone();
+ mIsDone = true;
+
+ // send a notification that data is ready
+ sem_post(mSenderSem);
+
+ mInterruptFd = -1;
+ close(pipefd[0]);
+ close(pipefd[1]);
+}
+
+bool PerfSource::handleUEvent(const uint64_t currTime) {
+ UEventResult result;
+ if (!mUEvent.read(&result)) {
+ logg->logMessage("UEvent::Read failed");
+ return false;
+ }
+
+ if (strcmp(result.mSubsystem, "cpu") == 0) {
+ if (strncmp(result.mDevPath, CPU_DEVPATH, sizeof(CPU_DEVPATH) - 1) != 0) {
+ logg->logMessage("Unexpected cpu DEVPATH format");
+ return false;
+ }
+ char *endptr;
+ errno = 0;
+ int cpu = strtol(result.mDevPath + sizeof(CPU_DEVPATH) - 1, &endptr, 10);
+ if (errno != 0 || *endptr != '\0') {
+ logg->logMessage("strtol failed");
+ return false;
+ }
+
+ if (cpu >= gSessionData->mCores) {
+ logg->logError("Only %i cores are expected but core %i reports %s", gSessionData->mCores, cpu, result.mAction);
+ handleException();
+ }
+
+ if (strcmp(result.mAction, "online") == 0) {
+ mBuffer->onlineCPU(currTime, cpu);
+ // Only call onlineCPU if prepareCPU succeeded
+ bool ret = false;
+ int err = mCountersGroup.prepareCPU(cpu, &mMonitor);
+ if (err == PG_CPU_OFFLINE) {
+ ret = true;
+ } else if (err == PG_SUCCESS) {
+ if (mCountersGroup.onlineCPU(currTime, cpu, true, mBuffer) > 0) {
+ mBuffer->perfCounterHeader(currTime);
+ gSessionData->perf.read(mBuffer, cpu);
+ mBuffer->perfCounterFooter(currTime);
+ ret = true;
+ }
+ }
+ mBuffer->commit(currTime);
+
+ gSessionData->readCpuInfo();
+ gSessionData->perf.coreName(currTime, &mSummary, cpu);
+ mSummary.commit(currTime);
+ return ret;
+ } else if (strcmp(result.mAction, "offline") == 0) {
+ const bool ret = mCountersGroup.offlineCPU(cpu);
+ mBuffer->offlineCPU(currTime, cpu);
+ return ret;
+ }
+ }
+
+ return true;
+}
+
+void PerfSource::interrupt() {
+ if (mInterruptFd >= 0) {
+ int8_t c = 0;
+ // Write to the pipe to wake the monitor which will cause mSessionIsActive to be reread
+ if (::write(mInterruptFd, &c, sizeof(c)) != sizeof(c)) {
+ logg->logError("write failed");
+ handleException();
+ }
+ }
+}
+
+bool PerfSource::isDone () {
+ return mBuffer->isDone() && mIsDone && mCountersBuf.isEmpty();
+}
+
+void PerfSource::write (Sender *sender) {
+ if (!mSummary.isDone()) {
+ mSummary.write(sender);
+ gSessionData->mSentSummary = true;
+ }
+ if (!mBuffer->isDone()) {
+ mBuffer->write(sender);
+ }
+ if (!mCountersBuf.send(sender)) {
+ logg->logError("PerfBuffer::send failed");
+ handleException();
+ }
+}
diff --git a/tools/gator/daemon/PerfSource.h b/tools/gator/daemon/PerfSource.h
new file mode 100644
index 0000000..feec1c2
--- /dev/null
+++ b/tools/gator/daemon/PerfSource.h
@@ -0,0 +1,54 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PERFSOURCE_H
+#define PERFSOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Monitor.h"
+#include "PerfBuffer.h"
+#include "PerfGroup.h"
+#include "Source.h"
+#include "UEvent.h"
+
+class Sender;
+
+class PerfSource : public Source {
+public:
+ PerfSource(sem_t *senderSem, sem_t *startProfile);
+ ~PerfSource();
+
+ bool prepare();
+ void run();
+ void interrupt();
+
+ bool isDone();
+ void write(Sender *sender);
+
+private:
+ bool handleUEvent(const uint64_t currTime);
+
+ Buffer mSummary;
+ Buffer *mBuffer;
+ PerfBuffer mCountersBuf;
+ PerfGroup mCountersGroup;
+ Monitor mMonitor;
+ UEvent mUEvent;
+ sem_t *const mSenderSem;
+ sem_t *const mStartProfile;
+ int mInterruptFd;
+ bool mIsDone;
+
+ // Intentionally undefined
+ PerfSource(const PerfSource &);
+ PerfSource &operator=(const PerfSource &);
+};
+
+#endif // PERFSOURCE_H
diff --git a/tools/gator/daemon/Proc.cpp b/tools/gator/daemon/Proc.cpp
new file mode 100644
index 0000000..4ba59b6
--- /dev/null
+++ b/tools/gator/daemon/Proc.cpp
@@ -0,0 +1,312 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Proc.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+struct ProcStat {
+ // From linux-dev/include/linux/sched.h
+#define TASK_COMM_LEN 16
+ // TASK_COMM_LEN may grow, so be ready for it to get larger
+ char comm[2*TASK_COMM_LEN];
+ long numThreads;
+};
+
+static bool readProcStat(ProcStat *const ps, const char *const pathname, DynBuf *const b) {
+ if (!b->read(pathname)) {
+ logg->logMessage("DynBuf::read failed, likely because the thread exited");
+ // This is not a fatal error - the thread just doesn't exist any more
+ return true;
+ }
+
+ char *comm = strchr(b->getBuf(), '(');
+ if (comm == NULL) {
+ logg->logMessage("parsing stat failed");
+ return false;
+ }
+ ++comm;
+ char *const str = strrchr(comm, ')');
+ if (str == NULL) {
+ logg->logMessage("parsing stat failed");
+ return false;
+ }
+ *str = '\0';
+ strncpy(ps->comm, comm, sizeof(ps->comm) - 1);
+ ps->comm[sizeof(ps->comm) - 1] = '\0';
+
+ const int count = sscanf(str + 2, " %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %*s %ld", &ps->numThreads);
+ if (count != 1) {
+ logg->logMessage("sscanf failed");
+ return false;
+ }
+
+ return true;
+}
+
+static const char APP_PROCESS[] = "app_process";
+
+static const char *readProcExe(DynBuf *const printb, const int pid, const int tid, DynBuf *const b) {
+ if (tid == -1 ? !printb->printf("/proc/%i/exe", pid)
+ : !printb->printf("/proc/%i/task/%i/exe", pid, tid)) {
+ logg->logMessage("DynBuf::printf failed");
+ return NULL;
+ }
+
+ const int err = b->readlink(printb->getBuf());
+ const char *image;
+ if (err == 0) {
+ image = strrchr(b->getBuf(), '/');
+ if (image == NULL) {
+ image = b->getBuf();
+ } else {
+ ++image;
+ }
+ } else if (err == -ENOENT) {
+ // readlink /proc/[pid]/exe returns ENOENT for kernel threads
+ image = "\0";
+ } else {
+ logg->logMessage("DynBuf::readlink failed");
+ return NULL;
+ }
+
+ // Android apps are run by app_process but the cmdline is changed to reference the actual app name
+ // On 64-bit android app_process can be app_process32 or app_process64
+ if (strncmp(image, APP_PROCESS, sizeof(APP_PROCESS) - 1) != 0) {
+ return image;
+ }
+
+ if (tid == -1 ? !printb->printf("/proc/%i/cmdline", pid)
+ : !printb->printf("/proc/%i/task/%i/cmdline", pid, tid)) {
+ logg->logMessage("DynBuf::printf failed");
+ return NULL;
+ }
+
+ if (!b->read(printb->getBuf())) {
+ logg->logMessage("DynBuf::read failed, likely because the thread exited");
+ return NULL;
+ }
+
+ return b->getBuf();
+}
+
+static bool readProcTask(const uint64_t currTime, Buffer *const buffer, const int pid, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+ bool result = false;
+
+ if (!b1->printf("/proc/%i/task", pid)) {
+ logg->logMessage("DynBuf::printf failed");
+ return result;
+ }
+ DIR *task = opendir(b1->getBuf());
+ if (task == NULL) {
+ logg->logMessage("opendir failed");
+ // This is not a fatal error - the thread just doesn't exist any more
+ return true;
+ }
+
+ struct dirent *dirent;
+ while ((dirent = readdir(task)) != NULL) {
+ char *endptr;
+ const int tid = strtol(dirent->d_name, &endptr, 10);
+ if (*endptr != '\0') {
+ // Ignore task items that are not integers like ., etc...
+ continue;
+ }
+
+ if (!printb->printf("/proc/%i/task/%i/stat", pid, tid)) {
+ logg->logMessage("DynBuf::printf failed");
+ goto fail;
+ }
+ ProcStat ps;
+ if (!readProcStat(&ps, printb->getBuf(), b1)) {
+ logg->logMessage("readProcStat failed");
+ goto fail;
+ }
+
+ const char *const image = readProcExe(printb, pid, tid, b2);
+ if (image == NULL) {
+ logg->logMessage("readImage failed");
+ goto fail;
+ }
+
+ buffer->marshalComm(currTime, pid, tid, image, ps.comm);
+ }
+
+ result = true;
+
+ fail:
+ closedir(task);
+
+ return result;
+}
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2) {
+ bool result = false;
+
+ DIR *proc = opendir("/proc");
+ if (proc == NULL) {
+ logg->logMessage("opendir failed");
+ return result;
+ }
+
+ struct dirent *dirent;
+ while ((dirent = readdir(proc)) != NULL) {
+ char *endptr;
+ const int pid = strtol(dirent->d_name, &endptr, 10);
+ if (*endptr != '\0') {
+ // Ignore proc items that are not integers like ., cpuinfo, etc...
+ continue;
+ }
+
+ if (!printb->printf("/proc/%i/stat", pid)) {
+ logg->logMessage("DynBuf::printf failed");
+ goto fail;
+ }
+ ProcStat ps;
+ if (!readProcStat(&ps, printb->getBuf(), b1)) {
+ logg->logMessage("readProcStat failed");
+ goto fail;
+ }
+
+ if (ps.numThreads <= 1) {
+ const char *const image = readProcExe(printb, pid, -1, b1);
+ if (image == NULL) {
+ logg->logMessage("readImage failed");
+ goto fail;
+ }
+
+ buffer->marshalComm(currTime, pid, pid, image, ps.comm);
+ } else {
+ if (!readProcTask(currTime, buffer, pid, printb, b1, b2)) {
+ logg->logMessage("readProcTask failed");
+ goto fail;
+ }
+ }
+ }
+
+ result = true;
+
+ fail:
+ closedir(proc);
+
+ return result;
+}
+
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b) {
+ bool result = false;
+
+ DIR *proc = opendir("/proc");
+ if (proc == NULL) {
+ logg->logMessage("opendir failed");
+ return result;
+ }
+
+ struct dirent *dirent;
+ while ((dirent = readdir(proc)) != NULL) {
+ char *endptr;
+ const int pid = strtol(dirent->d_name, &endptr, 10);
+ if (*endptr != '\0') {
+ // Ignore proc items that are not integers like ., cpuinfo, etc...
+ continue;
+ }
+
+ if (!printb->printf("/proc/%i/maps", pid)) {
+ logg->logMessage("DynBuf::printf failed");
+ goto fail;
+ }
+ if (!b->read(printb->getBuf())) {
+ logg->logMessage("DynBuf::read failed, likely because the process exited");
+ // This is not a fatal error - the process just doesn't exist any more
+ continue;
+ }
+
+ buffer->marshalMaps(currTime, pid, pid, b->getBuf());
+ }
+
+ result = true;
+
+ fail:
+ closedir(proc);
+
+ return result;
+}
+
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone) {
+ int fd = ::open("/proc/kallsyms", O_RDONLY | O_CLOEXEC);
+
+ if (fd < 0) {
+ logg->logMessage("open failed");
+ return true;
+ };
+
+ char buf[1<<12];
+ ssize_t pos = 0;
+ while (gSessionData->mSessionIsActive && !ACCESS_ONCE(*isDone)) {
+ // Assert there is still space in the buffer
+ if (sizeof(buf) - pos - 1 == 0) {
+ logg->logError("no space left in buffer");
+ handleException();
+ }
+
+ {
+ // -1 to reserve space for \0
+ const ssize_t bytes = ::read(fd, buf + pos, sizeof(buf) - pos - 1);
+ if (bytes < 0) {
+ logg->logError("read failed");
+ handleException();
+ }
+ if (bytes == 0) {
+ // Assert the buffer is empty
+ if (pos != 0) {
+ logg->logError("buffer not empty on eof");
+ handleException();
+ }
+ break;
+ }
+ pos += bytes;
+ }
+
+ ssize_t newline;
+ // Find the last '\n'
+ for (newline = pos - 1; newline >= 0; --newline) {
+ if (buf[newline] == '\n') {
+ const char was = buf[newline + 1];
+ buf[newline + 1] = '\0';
+ buffer->marshalKallsyms(currTime, buf);
+ // Sleep 3 ms to avoid sending out too much data too quickly
+ usleep(3000);
+ buf[0] = was;
+ // Assert the memory regions do not overlap
+ if (pos - newline >= newline + 1) {
+ logg->logError("memcpy src and dst overlap");
+ handleException();
+ }
+ if (pos - newline - 2 > 0) {
+ memcpy(buf + 1, buf + newline + 2, pos - newline - 2);
+ }
+ pos -= newline + 1;
+ break;
+ }
+ }
+ }
+
+ close(fd);
+
+ return true;
+}
diff --git a/tools/gator/daemon/Proc.h b/tools/gator/daemon/Proc.h
new file mode 100644
index 0000000..fcc48c5
--- /dev/null
+++ b/tools/gator/daemon/Proc.h
@@ -0,0 +1,21 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef PROC_H
+#define PROC_H
+
+#include <stdint.h>
+
+class Buffer;
+class DynBuf;
+
+bool readProcComms(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b1, DynBuf *const b2);
+bool readProcMaps(const uint64_t currTime, Buffer *const buffer, DynBuf *const printb, DynBuf *const b);
+bool readKallsyms(const uint64_t currTime, Buffer *const buffer, const bool *const isDone);
+
+#endif // PROC_H
diff --git a/tools/gator/daemon/Sender.cpp b/tools/gator/daemon/Sender.cpp
new file mode 100644
index 0000000..d7ad7571
--- /dev/null
+++ b/tools/gator/daemon/Sender.cpp
@@ -0,0 +1,129 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Sender.h"
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include "Buffer.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "SessionData.h"
+
+Sender::Sender(OlySocket* socket) {
+ mDataFile = NULL;
+ mDataSocket = NULL;
+
+ // Set up the socket connection
+ if (socket) {
+ char streamline[64] = {0};
+ mDataSocket = socket;
+
+ // Receive magic sequence - can wait forever
+ // Streamline will send data prior to the magic sequence for legacy support, which should be ignored for v4+
+ while (strcmp("STREAMLINE", streamline) != 0) {
+ if (mDataSocket->receiveString(streamline, sizeof(streamline)) == -1) {
+ logg->logError("Socket disconnected");
+ handleException();
+ }
+ }
+
+ // Send magic sequence - must be done first, after which error messages can be sent
+ char magic[32];
+ snprintf(magic, 32, "GATOR %i\n", PROTOCOL_VERSION);
+ mDataSocket->send(magic, strlen(magic));
+
+ gSessionData->mWaitingOnCommand = true;
+ logg->logMessage("Completed magic sequence");
+ }
+
+ pthread_mutex_init(&mSendMutex, NULL);
+}
+
+Sender::~Sender() {
+ // Just close it as the client socket is on the stack
+ if (mDataSocket != NULL) {
+ mDataSocket->closeSocket();
+ mDataSocket = NULL;
+ }
+ if (mDataFile != NULL) {
+ fclose(mDataFile);
+ }
+}
+
+void Sender::createDataFile(char* apcDir) {
+ if (apcDir == NULL) {
+ return;
+ }
+
+ mDataFileName = (char*)malloc(strlen(apcDir) + 12);
+ sprintf(mDataFileName, "%s/0000000000", apcDir);
+ mDataFile = fopen_cloexec(mDataFileName, "wb");
+ if (!mDataFile) {
+ logg->logError("Failed to open binary file: %s", mDataFileName);
+ handleException();
+ }
+}
+
+void Sender::writeData(const char* data, int length, int type) {
+ if (length < 0 || (data == NULL && length > 0)) {
+ return;
+ }
+
+ // Multiple threads call writeData()
+ pthread_mutex_lock(&mSendMutex);
+
+ // Send data over the socket connection
+ if (mDataSocket) {
+ // Start alarm
+ const int alarmDuration = 8;
+ alarm(alarmDuration);
+
+ // Send data over the socket, sending the type and size first
+ logg->logMessage("Sending data with length %d", length);
+ if (type != RESPONSE_APC_DATA) {
+ // type and length already added by the Collector for apc data
+ unsigned char header[5];
+ header[0] = type;
+ Buffer::writeLEInt(header + 1, length);
+ mDataSocket->send((char*)&header, sizeof(header));
+ }
+
+ // 100Kbits/sec * alarmDuration sec / 8 bits/byte
+ const int chunkSize = 100*1000 * alarmDuration / 8;
+ int pos = 0;
+ while (true) {
+ mDataSocket->send((const char*)data + pos, min(length - pos, chunkSize));
+ pos += chunkSize;
+ if (pos >= length) {
+ break;
+ }
+
+ // Reset the alarm
+ alarm(alarmDuration);
+ logg->logMessage("Resetting the alarm");
+ }
+
+ // Stop alarm
+ alarm(0);
+ }
+
+ // Write data to disk as long as it is not meta data
+ if (mDataFile && type == RESPONSE_APC_DATA) {
+ logg->logMessage("Writing data with length %d", length);
+ // Send data to the data file
+ if (fwrite(data, 1, length, mDataFile) != (unsigned int)length) {
+ logg->logError("Failed writing binary file %s", mDataFileName);
+ handleException();
+ }
+ }
+
+ pthread_mutex_unlock(&mSendMutex);
+}
diff --git a/tools/gator/daemon/Sender.h b/tools/gator/daemon/Sender.h
new file mode 100644
index 0000000..8f54202
--- /dev/null
+++ b/tools/gator/daemon/Sender.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SENDER_H__
+#define __SENDER_H__
+
+#include <stdio.h>
+#include <pthread.h>
+
+class OlySocket;
+
+enum {
+ RESPONSE_XML = 1,
+ RESPONSE_APC_DATA = 3,
+ RESPONSE_ACK = 4,
+ RESPONSE_NAK = 5,
+ RESPONSE_ERROR = 0xFF
+};
+
+class Sender {
+public:
+ Sender(OlySocket* socket);
+ ~Sender();
+ void writeData(const char* data, int length, int type);
+ void createDataFile(char* apcDir);
+private:
+ OlySocket* mDataSocket;
+ FILE* mDataFile;
+ char* mDataFileName;
+ pthread_mutex_t mSendMutex;
+
+ // Intentionally unimplemented
+ Sender(const Sender &);
+ Sender &operator=(const Sender &);
+};
+
+#endif //__SENDER_H__
diff --git a/tools/gator/daemon/SessionData.cpp b/tools/gator/daemon/SessionData.cpp
new file mode 100644
index 0000000..2b661bd
--- /dev/null
+++ b/tools/gator/daemon/SessionData.cpp
@@ -0,0 +1,292 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionData.h"
+
+#include <fcntl.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "DiskIODriver.h"
+#include "FSDriver.h"
+#include "HwmonDriver.h"
+#include "Logging.h"
+#include "MemInfoDriver.h"
+#include "NetDriver.h"
+#include "SessionXML.h"
+
+#define CORE_NAME_UNKNOWN "unknown"
+
+SessionData* gSessionData = NULL;
+
+SessionData::SessionData() {
+ usDrivers[0] = new HwmonDriver();
+ usDrivers[1] = new FSDriver();
+ usDrivers[2] = new MemInfoDriver();
+ usDrivers[3] = new NetDriver();
+ usDrivers[4] = new DiskIODriver();
+ initialize();
+}
+
+SessionData::~SessionData() {
+}
+
+void SessionData::initialize() {
+ mWaitingOnCommand = false;
+ mSessionIsActive = false;
+ mLocalCapture = false;
+ mOneShot = false;
+ mSentSummary = false;
+ mAllowCommands = false;
+ const size_t cpuIdSize = sizeof(int)*NR_CPUS;
+ // Share mCpuIds across all instances of gatord
+ mCpuIds = (int *)mmap(NULL, cpuIdSize, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ if (mCpuIds == MAP_FAILED) {
+ logg->logError("Unable to mmap shared memory for cpuids");
+ handleException();
+ }
+ memset(mCpuIds, -1, cpuIdSize);
+ strcpy(mCoreName, CORE_NAME_UNKNOWN);
+ readModel();
+ readCpuInfo();
+ mImages = NULL;
+ mConfigurationXMLPath = NULL;
+ mSessionXMLPath = NULL;
+ mEventsXMLPath = NULL;
+ mEventsXMLAppend = NULL;
+ mTargetPath = NULL;
+ mAPCDir = NULL;
+ mCaptureWorkingDir = NULL;
+ mCaptureCommand = NULL;
+ mCaptureUser = NULL;
+ mSampleRate = 0;
+ mLiveRate = 0;
+ mDuration = 0;
+ mMonotonicStarted = -1;
+ mBacktraceDepth = 0;
+ mTotalBufferSize = 0;
+ // sysconf(_SC_NPROCESSORS_CONF) is unreliable on 2.6 Android, get the value from the kernel module
+ mCores = 1;
+ mPageSize = 0;
+ mAnnotateStart = -1;
+}
+
+void SessionData::parseSessionXML(char* xmlString) {
+ SessionXML session(xmlString);
+ session.parse();
+
+ // Set session data values - use prime numbers just below the desired value to reduce the chance of events firing at the same time
+ if (strcmp(session.parameters.sample_rate, "high") == 0) {
+ mSampleRate = 9973; // 10000
+ } else if (strcmp(session.parameters.sample_rate, "normal") == 0) {
+ mSampleRate = 997; // 1000
+ } else if (strcmp(session.parameters.sample_rate, "low") == 0) {
+ mSampleRate = 97; // 100
+ } else if (strcmp(session.parameters.sample_rate, "none") == 0) {
+ mSampleRate = 0;
+ } else {
+ logg->logError("Invalid sample rate (%s) in session xml.", session.parameters.sample_rate);
+ handleException();
+ }
+ mBacktraceDepth = session.parameters.call_stack_unwinding == true ? 128 : 0;
+
+ // Determine buffer size (in MB) based on buffer mode
+ mOneShot = true;
+ if (strcmp(session.parameters.buffer_mode, "streaming") == 0) {
+ mOneShot = false;
+ mTotalBufferSize = 1;
+ } else if (strcmp(session.parameters.buffer_mode, "small") == 0) {
+ mTotalBufferSize = 1;
+ } else if (strcmp(session.parameters.buffer_mode, "normal") == 0) {
+ mTotalBufferSize = 4;
+ } else if (strcmp(session.parameters.buffer_mode, "large") == 0) {
+ mTotalBufferSize = 16;
+ } else {
+ logg->logError("Invalid value for buffer mode in session xml.");
+ handleException();
+ }
+
+ // Convert milli- to nanoseconds
+ mLiveRate = session.parameters.live_rate * (int64_t)1000000;
+ if (mLiveRate > 0 && mLocalCapture) {
+ logg->logMessage("Local capture is not compatable with live, disabling live");
+ mLiveRate = 0;
+ }
+
+ if (!mAllowCommands && (mCaptureCommand != NULL)) {
+ logg->logError("Running a command during a capture is not currently allowed. Please restart gatord with the -a flag.");
+ handleException();
+ }
+}
+
+void SessionData::readModel() {
+ FILE *fh = fopen("/proc/device-tree/model", "rb");
+ if (fh == NULL) {
+ return;
+ }
+
+ char buf[256];
+ if (fgets(buf, sizeof(buf), fh) != NULL) {
+ strcpy(mCoreName, buf);
+ }
+
+ fclose(fh);
+}
+
+static void setImplementer(int &cpuId, const int implementer) {
+ if (cpuId == -1) {
+ cpuId = 0;
+ }
+ cpuId |= implementer << 12;
+}
+
+static void setPart(int &cpuId, const int part) {
+ if (cpuId == -1) {
+ cpuId = 0;
+ }
+ cpuId |= part;
+}
+
+void SessionData::readCpuInfo() {
+ char temp[256]; // arbitrarily large amount
+ mMaxCpuId = -1;
+
+ FILE *f = fopen("/proc/cpuinfo", "r");
+ if (f == NULL) {
+ logg->logMessage("Error opening /proc/cpuinfo\n"
+ "The core name in the captured xml file will be 'unknown'.");
+ return;
+ }
+
+ bool foundCoreName = (strcmp(mCoreName, CORE_NAME_UNKNOWN) != 0);
+ int processor = -1;
+ while (fgets(temp, sizeof(temp), f)) {
+ const size_t len = strlen(temp);
+
+ if (len == 1) {
+ // New section, clear the processor. Streamline will not know the cpus if the pre Linux 3.8 format of cpuinfo is encountered but also that no incorrect information will be transmitted.
+ processor = -1;
+ continue;
+ }
+
+ if (len > 0) {
+ // Replace the line feed with a null
+ temp[len - 1] = '\0';
+ }
+
+ const bool foundHardware = !foundCoreName && strstr(temp, "Hardware") != 0;
+ const bool foundCPUImplementer = strstr(temp, "CPU implementer") != 0;
+ const bool foundCPUPart = strstr(temp, "CPU part") != 0;
+ const bool foundProcessor = strstr(temp, "processor") != 0;
+ if (foundHardware || foundCPUImplementer || foundCPUPart || foundProcessor) {
+ char* position = strchr(temp, ':');
+ if (position == NULL || (unsigned int)(position - temp) + 2 >= strlen(temp)) {
+ logg->logMessage("Unknown format of /proc/cpuinfo\n"
+ "The core name in the captured xml file will be 'unknown'.");
+ return;
+ }
+ position += 2;
+
+ if (foundHardware) {
+ strncpy(mCoreName, position, sizeof(mCoreName));
+ mCoreName[sizeof(mCoreName) - 1] = 0; // strncpy does not guarantee a null-terminated string
+ foundCoreName = true;
+ }
+
+ if (foundCPUImplementer) {
+ const int implementer = strtol(position, NULL, 0);
+ if (processor >= NR_CPUS) {
+ logg->logMessage("Too many processors, please increase NR_CPUS");
+ } else if (processor >= 0) {
+ setImplementer(mCpuIds[processor], implementer);
+ } else {
+ setImplementer(mMaxCpuId, implementer);
+ }
+ }
+
+ if (foundCPUPart) {
+ const int cpuId = strtol(position, NULL, 0);
+ if (processor >= NR_CPUS) {
+ logg->logMessage("Too many processors, please increase NR_CPUS");
+ } else if (processor >= 0) {
+ setPart(mCpuIds[processor], cpuId);
+ } else {
+ setPart(mMaxCpuId, cpuId);
+ }
+ }
+
+ if (foundProcessor) {
+ processor = strtol(position, NULL, 0);
+ }
+ }
+ }
+
+ // If this does not have the full topology in /proc/cpuinfo, mCpuIds[0] may not have the 1 CPU part emitted - this guarantees it's in mMaxCpuId
+ for (int i = 0; i < NR_CPUS; ++i) {
+ if (mCpuIds[i] > mMaxCpuId) {
+ mMaxCpuId = mCpuIds[i];
+ }
+ }
+
+ if (!foundCoreName) {
+ logg->logMessage("Could not determine core name from /proc/cpuinfo\n"
+ "The core name in the captured xml file will be 'unknown'.");
+ }
+ fclose(f);
+}
+
+uint64_t getTime() {
+ struct timespec ts;
+ if (clock_gettime(CLOCK_MONOTONIC_RAW, &ts) != 0) {
+ logg->logError("Failed to get uptime");
+ handleException();
+ }
+ return (NS_PER_S*ts.tv_sec + ts.tv_nsec);
+}
+
+int getEventKey() {
+ // key 0 is reserved as a timestamp
+ // key 1 is reserved as the marker for thread specific counters
+ // key 2 is reserved as the marker for core
+ // Odd keys are assigned by the driver, even keys by the daemon
+ static int key = 4;
+
+ const int ret = key;
+ key += 2;
+ return ret;
+}
+
+int pipe_cloexec(int pipefd[2]) {
+ if (pipe(pipefd) != 0) {
+ return -1;
+ }
+
+ int fdf;
+ if (((fdf = fcntl(pipefd[0], F_GETFD)) == -1) || (fcntl(pipefd[0], F_SETFD, fdf | FD_CLOEXEC) != 0) ||
+ ((fdf = fcntl(pipefd[1], F_GETFD)) == -1) || (fcntl(pipefd[1], F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ close(pipefd[0]);
+ close(pipefd[1]);
+ return -1;
+ }
+ return 0;
+}
+
+FILE *fopen_cloexec(const char *path, const char *mode) {
+ FILE *fh = fopen(path, mode);
+ if (fh == NULL) {
+ return NULL;
+ }
+ int fd = fileno(fh);
+ int fdf = fcntl(fd, F_GETFD);
+ if ((fdf == -1) || (fcntl(fd, F_SETFD, fdf | FD_CLOEXEC) != 0)) {
+ fclose(fh);
+ return NULL;
+ }
+ return fh;
+}
diff --git a/tools/gator/daemon/SessionData.h b/tools/gator/daemon/SessionData.h
new file mode 100644
index 0000000..d0c8900
--- /dev/null
+++ b/tools/gator/daemon/SessionData.h
@@ -0,0 +1,103 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_DATA_H
+#define SESSION_DATA_H
+
+#include <stdint.h>
+
+#include "Config.h"
+#include "Counter.h"
+#include "FtraceDriver.h"
+#include "KMod.h"
+#include "MaliVideoDriver.h"
+#include "PerfDriver.h"
+
+#define PROTOCOL_VERSION 21
+// Differentiates development versions (timestamp) from release versions
+#define PROTOCOL_DEV 1000
+
+#define NS_PER_S 1000000000LL
+#define NS_PER_MS 1000000LL
+#define NS_PER_US 1000LL
+
+struct ImageLinkList {
+ char* path;
+ struct ImageLinkList *next;
+};
+
+class SessionData {
+public:
+ static const size_t MAX_STRING_LEN = 80;
+
+ SessionData();
+ ~SessionData();
+ void initialize();
+ void parseSessionXML(char* xmlString);
+ void readModel();
+ void readCpuInfo();
+
+ PolledDriver *usDrivers[5];
+ KMod kmod;
+ PerfDriver perf;
+ MaliVideoDriver maliVideo;
+ FtraceDriver ftraceDriver;
+
+ char mCoreName[MAX_STRING_LEN];
+ struct ImageLinkList *mImages;
+ char *mConfigurationXMLPath;
+ char *mSessionXMLPath;
+ char *mEventsXMLPath;
+ char *mEventsXMLAppend;
+ char *mTargetPath;
+ char *mAPCDir;
+ char *mCaptureWorkingDir;
+ char *mCaptureCommand;
+ char *mCaptureUser;
+
+ bool mWaitingOnCommand;
+ bool mSessionIsActive;
+ bool mLocalCapture;
+ // halt processing of the driver data until profiling is complete or the buffer is filled
+ bool mOneShot;
+ bool mIsEBS;
+ bool mSentSummary;
+ bool mAllowCommands;
+
+ int64_t mMonotonicStarted;
+ int mBacktraceDepth;
+ // number of MB to use for the entire collection buffer
+ int mTotalBufferSize;
+ int mSampleRate;
+ int64_t mLiveRate;
+ int mDuration;
+ int mCores;
+ int mPageSize;
+ int *mCpuIds;
+ int mMaxCpuId;
+ int mAnnotateStart;
+
+ // PMU Counters
+ int mCounterOverflow;
+ Counter mCounters[MAX_PERFORMANCE_COUNTERS];
+
+private:
+ // Intentionally unimplemented
+ SessionData(const SessionData &);
+ SessionData &operator=(const SessionData &);
+};
+
+extern SessionData* gSessionData;
+extern const char *const gSrcMd5;
+
+uint64_t getTime();
+int getEventKey();
+int pipe_cloexec(int pipefd[2]);
+FILE *fopen_cloexec(const char *path, const char *mode);
+
+#endif // SESSION_DATA_H
diff --git a/tools/gator/daemon/SessionXML.cpp b/tools/gator/daemon/SessionXML.cpp
new file mode 100644
index 0000000..c638dea
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.cpp
@@ -0,0 +1,111 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "SessionXML.h"
+
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+
+#include "Logging.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+
+static const char *TAG_SESSION = "session";
+static const char *TAG_IMAGE = "image";
+
+static const char *ATTR_VERSION = "version";
+static const char *ATTR_CALL_STACK_UNWINDING = "call_stack_unwinding";
+static const char *ATTR_BUFFER_MODE = "buffer_mode";
+static const char *ATTR_SAMPLE_RATE = "sample_rate";
+static const char *ATTR_DURATION = "duration";
+static const char *ATTR_PATH = "path";
+static const char *ATTR_LIVE_RATE = "live_rate";
+static const char *ATTR_CAPTURE_WORKING_DIR = "capture_working_dir";
+static const char *ATTR_CAPTURE_COMMAND = "capture_command";
+static const char *ATTR_CAPTURE_USER = "capture_user";
+
+SessionXML::SessionXML(const char *str) {
+ parameters.buffer_mode[0] = 0;
+ parameters.sample_rate[0] = 0;
+ parameters.call_stack_unwinding = false;
+ parameters.live_rate = 0;
+ mSessionXML = str;
+ logg->logMessage("%s", mSessionXML);
+}
+
+SessionXML::~SessionXML() {
+}
+
+void SessionXML::parse() {
+ mxml_node_t *tree;
+ mxml_node_t *node;
+
+ tree = mxmlLoadString(NULL, mSessionXML, MXML_NO_CALLBACK);
+ node = mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND);
+
+ if (node) {
+ sessionTag(tree, node);
+ mxmlDelete(tree);
+ return;
+ }
+
+ logg->logError("No session tag found in the session.xml file");
+ handleException();
+}
+
+void SessionXML::sessionTag(mxml_node_t *tree, mxml_node_t *node) {
+ int version = 0;
+ if (mxmlElementGetAttr(node, ATTR_VERSION)) version = strtol(mxmlElementGetAttr(node, ATTR_VERSION), NULL, 10);
+ if (version != 1) {
+ logg->logError("Invalid session.xml version: %d", version);
+ handleException();
+ }
+
+ // copy to pre-allocated strings
+ if (mxmlElementGetAttr(node, ATTR_BUFFER_MODE)) {
+ strncpy(parameters.buffer_mode, mxmlElementGetAttr(node, ATTR_BUFFER_MODE), sizeof(parameters.buffer_mode));
+ parameters.buffer_mode[sizeof(parameters.buffer_mode) - 1] = 0; // strncpy does not guarantee a null-terminated string
+ }
+ if (mxmlElementGetAttr(node, ATTR_SAMPLE_RATE)) {
+ strncpy(parameters.sample_rate, mxmlElementGetAttr(node, ATTR_SAMPLE_RATE), sizeof(parameters.sample_rate));
+ parameters.sample_rate[sizeof(parameters.sample_rate) - 1] = 0; // strncpy does not guarantee a null-terminated string
+ }
+ if (mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR)) gSessionData->mCaptureWorkingDir = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_WORKING_DIR));
+ if (mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND)) gSessionData->mCaptureCommand = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_COMMAND));
+ if (mxmlElementGetAttr(node, ATTR_CAPTURE_USER)) gSessionData->mCaptureUser = strdup(mxmlElementGetAttr(node, ATTR_CAPTURE_USER));
+
+ // integers/bools
+ parameters.call_stack_unwinding = util->stringToBool(mxmlElementGetAttr(node, ATTR_CALL_STACK_UNWINDING), false);
+ if (mxmlElementGetAttr(node, ATTR_DURATION)) gSessionData->mDuration = strtol(mxmlElementGetAttr(node, ATTR_DURATION), NULL, 10);
+ if (mxmlElementGetAttr(node, ATTR_LIVE_RATE)) parameters.live_rate = strtol(mxmlElementGetAttr(node, ATTR_LIVE_RATE), NULL, 10);
+
+ // parse subtags
+ node = mxmlGetFirstChild(node);
+ while (node) {
+ if (mxmlGetType(node) != MXML_ELEMENT) {
+ node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+ continue;
+ }
+ if (strcmp(TAG_IMAGE, mxmlGetElement(node)) == 0) {
+ sessionImage(node);
+ }
+ node = mxmlWalkNext(node, tree, MXML_NO_DESCEND);
+ }
+}
+
+void SessionXML::sessionImage(mxml_node_t *node) {
+ int length = strlen(mxmlElementGetAttr(node, ATTR_PATH));
+ struct ImageLinkList *image;
+
+ image = (struct ImageLinkList *)malloc(sizeof(struct ImageLinkList));
+ image->path = (char*)malloc(length + 1);
+ image->path = strdup(mxmlElementGetAttr(node, ATTR_PATH));
+ image->next = gSessionData->mImages;
+ gSessionData->mImages = image;
+}
diff --git a/tools/gator/daemon/SessionXML.h b/tools/gator/daemon/SessionXML.h
new file mode 100644
index 0000000..2ba276a
--- /dev/null
+++ b/tools/gator/daemon/SessionXML.h
@@ -0,0 +1,42 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SESSION_XML_H
+#define SESSION_XML_H
+
+#include "mxml/mxml.h"
+
+struct ImageLinkList;
+
+struct ConfigParameters {
+ // buffer mode, "streaming", "low", "normal", "high" defines oneshot and buffer size
+ char buffer_mode[64];
+ // capture mode, "high", "normal", or "low"
+ char sample_rate[64];
+ // whether stack unwinding is performed
+ bool call_stack_unwinding;
+ int live_rate;
+};
+
+class SessionXML {
+public:
+ SessionXML(const char *str);
+ ~SessionXML();
+ void parse();
+ ConfigParameters parameters;
+private:
+ const char *mSessionXML;
+ void sessionTag(mxml_node_t *tree, mxml_node_t *node);
+ void sessionImage(mxml_node_t *node);
+
+ // Intentionally unimplemented
+ SessionXML(const SessionXML &);
+ SessionXML &operator=(const SessionXML &);
+};
+
+#endif // SESSION_XML_H
diff --git a/tools/gator/daemon/Setup.cpp b/tools/gator/daemon/Setup.cpp
new file mode 100644
index 0000000..7dd83ce
--- /dev/null
+++ b/tools/gator/daemon/Setup.cpp
@@ -0,0 +1,324 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Setup.h"
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/utsname.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "Config.h"
+#include "DynBuf.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+#define GATOR_MSG "gator: "
+#define GATOR_ERROR "gator: error: "
+#define GATOR_CONFIRM "gator: confirm: "
+
+bool getLinuxVersion(int version[3]) {
+ // Check the kernel version
+ struct utsname utsname;
+ if (uname(&utsname) != 0) {
+ logg->logMessage("uname failed");
+ return false;
+ }
+
+ version[0] = 0;
+ version[1] = 0;
+ version[2] = 0;
+
+ int part = 0;
+ char *ch = utsname.release;
+ while (*ch >= '0' && *ch <= '9' && part < 3) {
+ version[part] = 10*version[part] + *ch - '0';
+
+ ++ch;
+ if (*ch == '.') {
+ ++part;
+ ++ch;
+ }
+ }
+
+ return true;
+}
+
+static int pgrep_gator(DynBuf *const printb) {
+ DynBuf b;
+
+ DIR *proc = opendir("/proc");
+ if (proc == NULL) {
+ logg->logError(GATOR_ERROR "opendir failed");
+ handleException();
+ }
+
+ int self = getpid();
+
+ struct dirent *dirent;
+ while ((dirent = readdir(proc)) != NULL) {
+ char *endptr;
+ const int pid = strtol(dirent->d_name, &endptr, 10);
+ if (*endptr != '\0' || (pid == self)) {
+ // Ignore proc items that are not integers like ., cpuinfo, etc...
+ continue;
+ }
+
+ if (!printb->printf("/proc/%i/stat", pid)) {
+ logg->logError(GATOR_ERROR "DynBuf::printf failed");
+ handleException();
+ }
+
+ if (!b.read(printb->getBuf())) {
+ // This is not a fatal error - the thread just doesn't exist any more
+ continue;
+ }
+
+ char *comm = strchr(b.getBuf(), '(');
+ if (comm == NULL) {
+ logg->logError(GATOR_ERROR "parsing stat comm begin failed");
+ handleException();
+ }
+ ++comm;
+ char *const str = strrchr(comm, ')');
+ if (str == NULL) {
+ logg->logError(GATOR_ERROR "parsing stat comm end failed");
+ handleException();
+ }
+ *str = '\0';
+
+ if (strncmp(comm, "gator", 5) != 0) {
+ continue;
+ }
+
+ char state;
+ const int count = sscanf(str + 2, " %c ", &state);
+ if (count != 1) {
+ logg->logError(GATOR_ERROR "parsing stat state failed");
+ handleException();
+ }
+
+ if (state == 'Z') {
+ // This gator is a zombie, ignore
+ continue;
+ }
+
+ // Assume there is only one gator process
+ return pid;
+ }
+
+ closedir(proc);
+
+ return -1;
+}
+
+static bool confirm(const char *const message) {
+ char buf[1<<10];
+
+ printf(GATOR_CONFIRM "%s\n", message);
+ while (fgets(buf, sizeof(buf), stdin) != NULL) {
+ if (strcmp(buf, "y\n") == 0) {
+ return true;
+ }
+ if (strcmp(buf, "n\n") == 0) {
+ return false;
+ }
+ // Ignore unrecognized input
+ }
+
+ return false;
+}
+
+void update(const char *const gatorPath) {
+ printf(GATOR_MSG "starting\n");
+
+ int version[3];
+ if (!getLinuxVersion(version)) {
+ logg->logError(GATOR_ERROR "getLinuxVersion failed");
+ handleException();
+ }
+
+ if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(2, 6, 32)) {
+ logg->logError(GATOR_ERROR "Streamline can't automatically setup gator as this kernel version is not supported. Please upgrade the kernel on your device.");
+ handleException();
+ }
+
+ if (KERNEL_VERSION(version[0], version[1], version[2]) < KERNEL_VERSION(3, 4, 0)) {
+ logg->logError(GATOR_ERROR "Streamline can't automatically setup gator as gator.ko is required for this version of Linux. Please build gator.ko and gatord and install them on your device.");
+ handleException();
+ }
+
+ if (geteuid() != 0) {
+ printf(GATOR_MSG "trying sudo\n");
+ execlp("sudo", "sudo", gatorPath, "-u", NULL);
+ // Streamline will provide the password if needed
+
+ printf(GATOR_MSG "trying su\n");
+ char buf[1<<10];
+ /*
+ * Different versions of su handle additional -c command line options differently and expect the
+ * arguments in different ways. Try both ways wrapped in a shell.
+ *
+ * Then invoke another shell after su as it avoids odd failures on some Android systems
+ */
+ snprintf(buf, sizeof(buf), "su -c \"sh -c '%s -u'\" || su -c sh -c '%s -u'", gatorPath, gatorPath);
+ execlp("sh", "sh", "-c", buf, NULL);
+ // Streamline will provide the password if needed
+
+ logg->logError(GATOR_ERROR "Streamline was unable to sudo to root on your device. Please double check passwords, ensure sudo or su work with this user or try a different username.");
+ handleException();
+ }
+ printf(GATOR_MSG "now root\n");
+
+ if (access("/sys/module/gator", F_OK) == 0) {
+ if (!confirm("Streamline has detected that the gator kernel module is loaded on your device. Click yes to switch to user space gator, click no to abort the install.")) {
+ printf("gator: cancel\n");
+ exit(-1);
+ }
+ }
+
+ // setenforce 0 not needed for userspace gator
+
+ // Kill existing gator
+ DynBuf printb;
+ int gator_main = pgrep_gator(&printb);
+ if (gator_main > 0) {
+ if (kill(gator_main, SIGTERM) != 0) {
+ logg->logError(GATOR_ERROR "kill SIGTERM failed");
+ handleException();
+ }
+ if (!printb.printf("/proc/%i/exe", gator_main)) {
+ logg->logError(GATOR_ERROR "DynBuf::printf failed");
+ handleException();
+ }
+ for (int i = 0; ; ++i) {
+ // /proc/<pid>/exe exists but will not be accessible for zombies
+ if (access(printb.getBuf(), F_OK) != 0) {
+ break;
+ }
+ if (i == 5) {
+ if (kill(gator_main, SIGKILL) != 0) {
+ logg->logError(GATOR_ERROR "kill SIGKILL failed");
+ handleException();
+ }
+ } else if (i >= 10) {
+ logg->logError(GATOR_ERROR "unable to kill running gator");
+ handleException();
+ }
+ sleep(1);
+ }
+ }
+ printf(GATOR_MSG "no gatord running\n");
+
+ umount("/dev/gator");
+ syscall(__NR_delete_module, "gator", O_NONBLOCK);
+
+ rename("gatord", "gatord.old");
+ rename("gator.ko", "gator.ko.old");
+
+ // Rename gatord.YYYYMMDDHHMMSSMMMM to gatord
+ char *newGatorPath = strdup(gatorPath);
+ char *dot = strrchr(newGatorPath, '.');
+ if (dot != NULL) {
+ *dot = '\0';
+ if (rename(gatorPath, newGatorPath) != 0) {
+ logg->logError(GATOR_ERROR "rename failed");
+ handleException();
+ }
+ }
+
+ char buf[128];
+ int pipefd[2];
+ if (pipe_cloexec(pipefd) != 0) {
+ logg->logError(GATOR_ERROR "pipe failed");
+ handleException();
+ }
+
+ // Fork and start gatord (redirect stdin, stdout and stderr so shell can close)
+ int child = fork();
+ if (child < 0) {
+ logg->logError(GATOR_ERROR "fork failed");
+ handleException();
+ } else if (child == 0) {
+ int inFd;
+ int outFd;
+ int errFd;
+ int result = -1;
+
+ buf[0] = '\0';
+ close(pipefd[0]);
+
+ inFd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ if (inFd < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "open of /dev/null failed");
+ goto fail_exit;
+ }
+ outFd = open("gatord.out", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+ if (outFd < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "open of gatord.out failed");
+ goto fail_exit;
+ }
+ errFd = open("gatord.err", O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
+ if (errFd < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "open of gatord.err failed");
+ goto fail_exit;
+ }
+ if (dup2(inFd, STDIN_FILENO) < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stdin failed");
+ goto fail_exit;
+ }
+ fflush(stdout);
+ if (dup2(outFd, STDOUT_FILENO) < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stdout failed");
+ goto fail_exit;
+ }
+ fflush(stderr);
+ if (dup2(errFd, STDERR_FILENO) < 0) {
+ snprintf(buf, sizeof(buf), GATOR_ERROR "dup2 for stderr failed");
+ goto fail_exit;
+ }
+
+ snprintf(buf, sizeof(buf), GATOR_MSG "done");
+ result = 0;
+
+ fail_exit:
+ if (buf[0] != '\0') {
+ const ssize_t bytes = write(pipefd[1], buf, sizeof(buf));
+ // Can't do anything if this fails
+ (void)bytes;
+ }
+ close(pipefd[1]);
+
+ if (result == 0) {
+ // Continue to execute gator normally
+ return;
+ }
+ exit(-1);
+ }
+
+ close(pipefd[1]);
+ const ssize_t bytes = read(pipefd[0], buf, sizeof(buf));
+ if (bytes > 0) {
+ logg->logError("%s", buf);
+ handleException();
+ }
+ close(pipefd[0]);
+
+ // Exit so parent shell can move on
+ exit(0);
+}
diff --git a/tools/gator/daemon/Setup.h b/tools/gator/daemon/Setup.h
new file mode 100644
index 0000000..427e717
--- /dev/null
+++ b/tools/gator/daemon/Setup.h
@@ -0,0 +1,18 @@
+/**
+ * Copyright (C) ARM Limited 2014-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SETUP_H
+#define SETUP_H
+
+// From include/generated/uapi/linux/version.h
+#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))
+
+bool getLinuxVersion(int version[3]);
+void update(const char *const gatorPath);
+
+#endif // SETUP_H
diff --git a/tools/gator/daemon/Source.cpp b/tools/gator/daemon/Source.cpp
new file mode 100644
index 0000000..64d6206
--- /dev/null
+++ b/tools/gator/daemon/Source.cpp
@@ -0,0 +1,33 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "Source.h"
+
+#include "Logging.h"
+
+Source::Source() : mThreadID() {
+}
+
+Source::~Source() {
+}
+
+void Source::start() {
+ if (pthread_create(&mThreadID, NULL, runStatic, this)) {
+ logg->logError("Failed to create source thread");
+ handleException();
+ }
+}
+
+void Source::join() {
+ pthread_join(mThreadID, NULL);
+}
+
+void *Source::runStatic(void *arg) {
+ static_cast<Source *>(arg)->run();
+ return NULL;
+}
diff --git a/tools/gator/daemon/Source.h b/tools/gator/daemon/Source.h
new file mode 100644
index 0000000..b9369be
--- /dev/null
+++ b/tools/gator/daemon/Source.h
@@ -0,0 +1,40 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef SOURCE_H
+#define SOURCE_H
+
+#include <pthread.h>
+
+class Sender;
+
+class Source {
+public:
+ Source();
+ virtual ~Source();
+
+ virtual bool prepare() = 0;
+ void start();
+ virtual void run() = 0;
+ virtual void interrupt() = 0;
+ void join();
+
+ virtual bool isDone() = 0;
+ virtual void write(Sender *sender) = 0;
+
+private:
+ static void *runStatic(void *arg);
+
+ pthread_t mThreadID;
+
+ // Intentionally undefined
+ Source(const Source &);
+ Source &operator=(const Source &);
+};
+
+#endif // SOURCE_H
diff --git a/tools/gator/daemon/StreamlineSetup.cpp b/tools/gator/daemon/StreamlineSetup.cpp
new file mode 100644
index 0000000..e37f271
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.cpp
@@ -0,0 +1,272 @@
+/**
+ * Copyright (C) ARM Limited 2011-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "StreamlineSetup.h"
+
+#include "Buffer.h"
+#include "CapturedXML.h"
+#include "ConfigurationXML.h"
+#include "Driver.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "Sender.h"
+#include "SessionData.h"
+
+static const char* TAG_SESSION = "session";
+static const char* TAG_REQUEST = "request";
+static const char* TAG_CONFIGURATIONS = "configurations";
+
+static const char* ATTR_TYPE = "type";
+static const char* VALUE_EVENTS = "events";
+static const char* VALUE_CONFIGURATION = "configuration";
+static const char* VALUE_COUNTERS = "counters";
+static const char* VALUE_CAPTURED = "captured";
+static const char* VALUE_DEFAULTS = "defaults";
+
+StreamlineSetup::StreamlineSetup(OlySocket* s) {
+ bool ready = false;
+ char* data = NULL;
+ int type;
+
+ mSocket = s;
+
+ // Receive commands from Streamline (master)
+ while (!ready) {
+ // receive command over socket
+ gSessionData->mWaitingOnCommand = true;
+ data = readCommand(&type);
+
+ // parse and handle data
+ switch (type) {
+ case COMMAND_REQUEST_XML:
+ handleRequest(data);
+ break;
+ case COMMAND_DELIVER_XML:
+ handleDeliver(data);
+ break;
+ case COMMAND_APC_START:
+ logg->logMessage("Received apc start request");
+ ready = true;
+ break;
+ case COMMAND_APC_STOP:
+ logg->logMessage("Received apc stop request before apc start request");
+ exit(0);
+ break;
+ case COMMAND_DISCONNECT:
+ logg->logMessage("Received disconnect command");
+ exit(0);
+ break;
+ case COMMAND_PING:
+ logg->logMessage("Received ping command");
+ sendData(NULL, 0, RESPONSE_ACK);
+ break;
+ default:
+ logg->logError("Target error: Unknown command type, %d", type);
+ handleException();
+ }
+
+ free(data);
+ }
+
+ if (gSessionData->mCounterOverflow > 0) {
+ logg->logError("Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+ handleException();
+ }
+}
+
+StreamlineSetup::~StreamlineSetup() {
+}
+
+char* StreamlineSetup::readCommand(int* command) {
+ unsigned char header[5];
+ char* data;
+ int response;
+
+ // receive type and length
+ response = mSocket->receiveNBytes((char*)&header, sizeof(header));
+
+ // After receiving a single byte, we are no longer waiting on a command
+ gSessionData->mWaitingOnCommand = false;
+
+ if (response < 0) {
+ logg->logError("Target error: Unexpected socket disconnect");
+ handleException();
+ }
+
+ const char type = header[0];
+ const int length = (header[1] << 0) | (header[2] << 8) | (header[3] << 16) | (header[4] << 24);
+
+ // add artificial limit
+ if ((length < 0) || length > 1024 * 1024) {
+ logg->logError("Target error: Invalid length received, %d", length);
+ handleException();
+ }
+
+ // allocate memory to contain the xml file, size of zero returns a zero size object
+ data = (char*)calloc(length + 1, 1);
+ if (data == NULL) {
+ logg->logError("Unable to allocate memory for xml");
+ handleException();
+ }
+
+ // receive data
+ response = mSocket->receiveNBytes(data, length);
+ if (response < 0) {
+ logg->logError("Target error: Unexpected socket disconnect");
+ handleException();
+ }
+
+ // null terminate the data for string parsing
+ if (length > 0) {
+ data[length] = 0;
+ }
+
+ *command = type;
+ return data;
+}
+
+void StreamlineSetup::handleRequest(char* xml) {
+ mxml_node_t *tree, *node;
+ const char * attr = NULL;
+
+ tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+ node = mxmlFindElement(tree, tree, TAG_REQUEST, ATTR_TYPE, NULL, MXML_DESCEND_FIRST);
+ if (node) {
+ attr = mxmlElementGetAttr(node, ATTR_TYPE);
+ }
+ if (attr && strcmp(attr, VALUE_EVENTS) == 0) {
+ sendEvents();
+ logg->logMessage("Sent events xml response");
+ } else if (attr && strcmp(attr, VALUE_CONFIGURATION) == 0) {
+ sendConfiguration();
+ logg->logMessage("Sent configuration xml response");
+ } else if (attr && strcmp(attr, VALUE_COUNTERS) == 0) {
+ sendCounters();
+ logg->logMessage("Sent counters xml response");
+ } else if (attr && strcmp(attr, VALUE_CAPTURED) == 0) {
+ CapturedXML capturedXML;
+ char* capturedText = capturedXML.getXML(false);
+ sendData(capturedText, strlen(capturedText), RESPONSE_XML);
+ free(capturedText);
+ logg->logMessage("Sent captured xml response");
+ } else if (attr && strcmp(attr, VALUE_DEFAULTS) == 0) {
+ sendDefaults();
+ logg->logMessage("Sent default configuration xml response");
+ } else {
+ char error[] = "Unknown request";
+ sendData(error, strlen(error), RESPONSE_NAK);
+ logg->logMessage("Received unknown request:\n%s", xml);
+ }
+
+ mxmlDelete(tree);
+}
+
+void StreamlineSetup::handleDeliver(char* xml) {
+ mxml_node_t *tree;
+
+ // Determine xml type
+ tree = mxmlLoadString(NULL, xml, MXML_NO_CALLBACK);
+ if (mxmlFindElement(tree, tree, TAG_SESSION, NULL, NULL, MXML_DESCEND_FIRST)) {
+ // Session XML
+ gSessionData->parseSessionXML(xml);
+ sendData(NULL, 0, RESPONSE_ACK);
+ logg->logMessage("Received session xml");
+ } else if (mxmlFindElement(tree, tree, TAG_CONFIGURATIONS, NULL, NULL, MXML_DESCEND_FIRST)) {
+ // Configuration XML
+ writeConfiguration(xml);
+ sendData(NULL, 0, RESPONSE_ACK);
+ logg->logMessage("Received configuration xml");
+ } else {
+ // Unknown XML
+ logg->logMessage("Received unknown XML delivery type");
+ sendData(NULL, 0, RESPONSE_NAK);
+ }
+
+ mxmlDelete(tree);
+}
+
+void StreamlineSetup::sendData(const char* data, uint32_t length, char type) {
+ unsigned char header[5];
+ header[0] = type;
+ Buffer::writeLEInt(header + 1, length);
+ mSocket->send((char*)&header, sizeof(header));
+ mSocket->send((const char*)data, length);
+}
+
+void StreamlineSetup::sendEvents() {
+ EventsXML eventsXML;
+ char* string = eventsXML.getXML();
+ sendString(string, RESPONSE_XML);
+ free(string);
+}
+
+void StreamlineSetup::sendConfiguration() {
+ ConfigurationXML xml;
+
+ const char* string = xml.getConfigurationXML();
+ sendData(string, strlen(string), RESPONSE_XML);
+}
+
+void StreamlineSetup::sendDefaults() {
+ // Send the config built into the binary
+ const char* xml;
+ unsigned int size;
+ ConfigurationXML::getDefaultConfigurationXml(xml, size);
+
+ // Artificial size restriction
+ if (size > 1024*1024) {
+ logg->logError("Corrupt default configuration file");
+ handleException();
+ }
+
+ sendData(xml, size, RESPONSE_XML);
+}
+
+void StreamlineSetup::sendCounters() {
+ mxml_node_t *xml;
+ mxml_node_t *counters;
+
+ xml = mxmlNewXML("1.0");
+ counters = mxmlNewElement(xml, "counters");
+ int count = 0;
+ for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+ count += driver->writeCounters(counters);
+ }
+
+ if (count == 0) {
+ logg->logError("No counters found, this could be because /dev/gator/events can not be read or because perf is not working correctly");
+ handleException();
+ }
+
+ char* string = mxmlSaveAllocString(xml, mxmlWhitespaceCB);
+ sendString(string, RESPONSE_XML);
+
+ free(string);
+ mxmlDelete(xml);
+}
+
+void StreamlineSetup::writeConfiguration(char* xml) {
+ char path[PATH_MAX];
+
+ ConfigurationXML::getPath(path);
+
+ if (util->writeToDisk(path, xml) < 0) {
+ logg->logError("Error writing %s\nPlease verify write permissions to this path.", path);
+ handleException();
+ }
+
+ // Re-populate gSessionData with the configuration, as it has now changed
+ { ConfigurationXML configuration; }
+
+ if (gSessionData->mCounterOverflow > 0) {
+ logg->logError("Only %i performance counters are permitted, %i are selected", MAX_PERFORMANCE_COUNTERS, gSessionData->mCounterOverflow);
+ handleException();
+ }
+}
diff --git a/tools/gator/daemon/StreamlineSetup.h b/tools/gator/daemon/StreamlineSetup.h
new file mode 100644
index 0000000..d8b1626
--- /dev/null
+++ b/tools/gator/daemon/StreamlineSetup.h
@@ -0,0 +1,50 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __STREAMLINE_SETUP_H__
+#define __STREAMLINE_SETUP_H__
+
+#include <stdint.h>
+#include <string.h>
+
+class OlySocket;
+
+// Commands from Streamline
+enum {
+ COMMAND_REQUEST_XML = 0,
+ COMMAND_DELIVER_XML = 1,
+ COMMAND_APC_START = 2,
+ COMMAND_APC_STOP = 3,
+ COMMAND_DISCONNECT = 4,
+ COMMAND_PING = 5
+};
+
+class StreamlineSetup {
+public:
+ StreamlineSetup(OlySocket *socket);
+ ~StreamlineSetup();
+private:
+ OlySocket* mSocket;
+
+ char* readCommand(int*);
+ void handleRequest(char* xml);
+ void handleDeliver(char* xml);
+ void sendData(const char* data, uint32_t length, char type);
+ void sendString(const char* string, int type) {sendData(string, strlen(string), type);}
+ void sendEvents();
+ void sendConfiguration();
+ void sendDefaults();
+ void sendCounters();
+ void writeConfiguration(char* xml);
+
+ // Intentionally unimplemented
+ StreamlineSetup(const StreamlineSetup &);
+ StreamlineSetup &operator=(const StreamlineSetup &);
+};
+
+#endif //__STREAMLINE_SETUP_H__
diff --git a/tools/gator/daemon/UEvent.cpp b/tools/gator/daemon/UEvent.cpp
new file mode 100644
index 0000000..6a69f5a
--- /dev/null
+++ b/tools/gator/daemon/UEvent.cpp
@@ -0,0 +1,78 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "UEvent.h"
+
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#include <linux/netlink.h>
+
+#include "Logging.h"
+#include "OlySocket.h"
+
+static const char EMPTY[] = "";
+static const char ACTION[] = "ACTION=";
+static const char DEVPATH[] = "DEVPATH=";
+static const char SUBSYSTEM[] = "SUBSYSTEM=";
+
+UEvent::UEvent() : mFd(-1) {
+}
+
+UEvent::~UEvent() {
+ if (mFd >= 0) {
+ close(mFd);
+ }
+}
+
+bool UEvent::init() {
+ mFd = socket_cloexec(PF_NETLINK, SOCK_RAW, NETLINK_KOBJECT_UEVENT);
+ if (mFd < 0) {
+ logg->logMessage("socket failed");
+ return false;
+ }
+
+ struct sockaddr_nl sockaddr;
+ memset(&sockaddr, 0, sizeof(sockaddr));
+ sockaddr.nl_family = AF_NETLINK;
+ sockaddr.nl_groups = 1; // bitmask: (1 << 0) == kernel events, (1 << 1) == udev events
+ sockaddr.nl_pid = 0;
+ if (bind(mFd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) != 0) {
+ logg->logMessage("bind failed");
+ return false;
+ }
+
+ return true;
+}
+
+bool UEvent::read(UEventResult *const result) {
+ ssize_t bytes = recv(mFd, result->mBuf, sizeof(result->mBuf), 0);
+ if (bytes <= 0) {
+ logg->logMessage("recv failed");
+ return false;
+ }
+
+ result->mAction = EMPTY;
+ result->mDevPath = EMPTY;
+ result->mSubsystem = EMPTY;
+
+ for (int pos = 0; pos < bytes; pos += strlen(result->mBuf + pos) + 1) {
+ char *const str = result->mBuf + pos;
+ logg->logMessage("uevent + %i: %s", pos, str);
+ if (strncmp(str, ACTION, sizeof(ACTION) - 1) == 0) {
+ result->mAction = str + sizeof(ACTION) - 1;
+ } else if (strncmp(str, DEVPATH, sizeof(DEVPATH) - 1) == 0) {
+ result->mDevPath = str + sizeof(DEVPATH) - 1;
+ } else if (strncmp(str, SUBSYSTEM, sizeof(SUBSYSTEM) - 1) == 0) {
+ result->mSubsystem = str + sizeof(SUBSYSTEM) - 1;
+ }
+ }
+
+ return true;
+}
diff --git a/tools/gator/daemon/UEvent.h b/tools/gator/daemon/UEvent.h
new file mode 100644
index 0000000..4c00f6c
--- /dev/null
+++ b/tools/gator/daemon/UEvent.h
@@ -0,0 +1,36 @@
+/**
+ * Copyright (C) ARM Limited 2013-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef UEVENT_H
+#define UEVENT_H
+
+struct UEventResult {
+ const char *mAction;
+ const char *mDevPath;
+ const char *mSubsystem;
+ char mBuf[1<<13];
+};
+
+class UEvent {
+public:
+ UEvent();
+ ~UEvent();
+
+ bool init();
+ bool read(UEventResult *const result);
+ int getFd() const { return mFd; }
+
+private:
+ int mFd;
+
+ // Intentionally undefined
+ UEvent(const UEvent &);
+ UEvent &operator=(const UEvent &);
+};
+
+#endif // UEVENT_H
diff --git a/tools/gator/daemon/UserSpaceSource.cpp b/tools/gator/daemon/UserSpaceSource.cpp
new file mode 100644
index 0000000..f58f828
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.cpp
@@ -0,0 +1,97 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define __STDC_FORMAT_MACROS
+
+#include "UserSpaceSource.h"
+
+#include <inttypes.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "Child.h"
+#include "DriverSource.h"
+#include "Logging.h"
+#include "SessionData.h"
+
+extern Child *child;
+
+UserSpaceSource::UserSpaceSource(sem_t *senderSem) : mBuffer(0, FRAME_BLOCK_COUNTER, gSessionData->mTotalBufferSize*1024*1024, senderSem) {
+}
+
+UserSpaceSource::~UserSpaceSource() {
+}
+
+bool UserSpaceSource::prepare() {
+ return true;
+}
+
+void UserSpaceSource::run() {
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-counters", 0, 0, 0);
+
+ for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+ gSessionData->usDrivers[i]->start();
+ }
+
+ int64_t monotonicStarted = 0;
+ while (monotonicStarted <= 0 && gSessionData->mSessionIsActive) {
+ usleep(10);
+
+ if (gSessionData->perf.isSetup()) {
+ monotonicStarted = gSessionData->mMonotonicStarted;
+ } else {
+ if (DriverSource::readInt64Driver("/dev/gator/started", &monotonicStarted) == -1) {
+ logg->logError("Error reading gator driver start time");
+ handleException();
+ }
+ gSessionData->mMonotonicStarted = monotonicStarted;
+ }
+ }
+
+ uint64_t nextTime = 0;
+ while (gSessionData->mSessionIsActive) {
+ const uint64_t currTime = getTime() - monotonicStarted;
+ // Sample ten times a second ignoring gSessionData->mSampleRate
+ nextTime += NS_PER_S/10;//gSessionData->mSampleRate;
+ if (nextTime < currTime) {
+ logg->logMessage("Too slow, currTime: %" PRIi64 " nextTime: %" PRIi64, currTime, nextTime);
+ nextTime = currTime;
+ }
+
+ if (mBuffer.eventHeader(currTime)) {
+ for (int i = 0; i < ARRAY_LENGTH(gSessionData->usDrivers); ++i) {
+ gSessionData->usDrivers[i]->read(&mBuffer);
+ }
+ // Only check after writing all counters so that time and corresponding counters appear in the same frame
+ mBuffer.check(currTime);
+ }
+
+ if (gSessionData->mOneShot && gSessionData->mSessionIsActive && (mBuffer.bytesAvailable() <= 0)) {
+ logg->logMessage("One shot (counters)");
+ child->endSession();
+ }
+
+ usleep((nextTime - currTime)/NS_PER_US);
+ }
+
+ mBuffer.setDone();
+}
+
+void UserSpaceSource::interrupt() {
+ // Do nothing
+}
+
+bool UserSpaceSource::isDone() {
+ return mBuffer.isDone();
+}
+
+void UserSpaceSource::write(Sender *sender) {
+ if (!mBuffer.isDone()) {
+ mBuffer.write(sender);
+ }
+}
diff --git a/tools/gator/daemon/UserSpaceSource.h b/tools/gator/daemon/UserSpaceSource.h
new file mode 100644
index 0000000..0038dcb
--- /dev/null
+++ b/tools/gator/daemon/UserSpaceSource.h
@@ -0,0 +1,38 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef USERSPACESOURCE_H
+#define USERSPACESOURCE_H
+
+#include <semaphore.h>
+
+#include "Buffer.h"
+#include "Source.h"
+
+// User space counters
+class UserSpaceSource : public Source {
+public:
+ UserSpaceSource(sem_t *senderSem);
+ ~UserSpaceSource();
+
+ bool prepare();
+ void run();
+ void interrupt();
+
+ bool isDone();
+ void write(Sender *sender);
+
+private:
+ Buffer mBuffer;
+
+ // Intentionally unimplemented
+ UserSpaceSource(const UserSpaceSource &);
+ UserSpaceSource &operator=(const UserSpaceSource &);
+};
+
+#endif // USERSPACESOURCE_H
diff --git a/tools/gator/daemon/c++.cpp b/tools/gator/daemon/c++.cpp
new file mode 100644
index 0000000..caf6f1e
--- /dev/null
+++ b/tools/gator/daemon/c++.cpp
@@ -0,0 +1,40 @@
+/**
+ * Minimal set of C++ functions so that libstdc++ is not required
+ *
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+void operator delete(void *ptr) {
+ if (ptr != NULL) {
+ free(ptr);
+ }
+}
+
+void operator delete[](void *ptr) {
+ operator delete(ptr);
+}
+
+void *operator new(size_t size) {
+ void *ptr = malloc(size == 0 ? 1 : size);
+ if (ptr == NULL) {
+ abort();
+ }
+ return ptr;
+}
+
+void *operator new[](size_t size) {
+ return operator new(size);
+}
+
+extern "C"
+void __cxa_pure_virtual() {
+ printf("pure virtual method called\n");
+ abort();
+}
diff --git a/tools/gator/daemon/common.mk b/tools/gator/daemon/common.mk
new file mode 100644
index 0000000..0d5a0a8
--- /dev/null
+++ b/tools/gator/daemon/common.mk
@@ -0,0 +1,55 @@
+# -g produces debugging information
+# -O3 maximum optimization
+# -O0 no optimization, used for debugging
+# -Wall enables most warnings
+# -Werror treats warnings as errors
+# -std=c++0x is the planned new c++ standard
+# -std=c++98 is the 1998 c++ standard
+CPPFLAGS += -O3 -Wall -fno-exceptions -pthread -MMD -DETCDIR=\"/etc\" -Ilibsensors
+CXXFLAGS += -fno-rtti -Wextra -Wshadow # -Weffc++
+ifeq ($(WERROR),1)
+ CPPFLAGS += -Werror
+endif
+# -s strips the binary of debug info
+LDFLAGS += -s
+LDLIBS += -lrt -lm -pthread
+TARGET = gatord
+C_SRC = $(wildcard mxml/*.c) $(wildcard libsensors/*.c)
+CXX_SRC = $(wildcard *.cpp)
+
+all: $(TARGET)
+
+events.xml: events_header.xml $(wildcard events-*.xml) events_footer.xml
+ cat $^ > $@
+
+include $(wildcard *.d)
+include $(wildcard mxml/*.d)
+
+EventsXML.cpp: events_xml.h
+ConfigurationXML.cpp: defaults_xml.h
+
+# Don't regenerate conf-lex.c or conf-parse.c
+libsensors/conf-lex.c: ;
+libsensors/conf-parse.c: ;
+
+%_xml.h: %.xml escape
+ ./escape $< > $@
+
+%.o: %.c
+ $(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+%.o: %.cpp
+ $(CXX) $(CXXFLAGS) $(CPPFLAGS) -c -o $@ $<
+
+SrcMd5.cpp: $(wildcard *.cpp *.h mxml/*.c mxml/*.h libsensors/*.c libsensors/*.h)
+ echo 'extern const char *const gSrcMd5 = "'`ls $^ | grep -Ev '^(.*_xml\.h|$@)$$' | LC_ALL=C sort | xargs cat | md5sum | cut -b 1-32`'";' > $@
+
+$(TARGET): $(CXX_SRC:%.cpp=%.o) $(C_SRC:%.c=%.o) SrcMd5.o
+ $(CC) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
+# Intentionally ignore CC as a native binary is required
+escape: escape.c
+ gcc $^ -o $@
+
+clean:
+ rm -f *.d *.o mxml/*.d mxml/*.o libsensors/*.d libsensors/*.o $(TARGET) escape events.xml events_xml.h defaults_xml.h SrcMd5.cpp
diff --git a/tools/gator/daemon/defaults.xml b/tools/gator/daemon/defaults.xml
new file mode 100644
index 0000000..31b127c
--- /dev/null
+++ b/tools/gator/daemon/defaults.xml
@@ -0,0 +1,73 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configurations revision="3">
+ <configuration counter="ARM_ARM11_ccnt" event="0xff"/>
+ <configuration counter="ARM_ARM11_cnt0" event="0x7"/>
+ <configuration counter="ARM_ARM11_cnt1" event="0xb"/>
+ <configuration counter="ARM_ARM11MPCore_ccnt" event="0xff"/>
+ <configuration counter="ARM_ARM11MPCore_cnt0" event="0x08"/>
+ <configuration counter="ARM_ARM11MPCore_cnt1" event="0x0b"/>
+ <configuration counter="ARMv7_Cortex_A5_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A5_cnt0" event="0x8"/>
+ <configuration counter="ARMv7_Cortex_A5_cnt1" event="0x1"/>
+ <configuration counter="ARMv7_Cortex_A7_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A7_cnt0" event="0x08"/>
+ <configuration counter="ARMv7_Cortex_A7_cnt1" event="0x10"/>
+ <configuration counter="ARMv7_Cortex_A7_cnt2" event="0x16"/>
+ <configuration counter="ARMv7_Cortex_A8_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A8_cnt0" event="0x8"/>
+ <configuration counter="ARMv7_Cortex_A8_cnt1" event="0x44"/>
+ <configuration counter="ARMv7_Cortex_A8_cnt2" event="0x43"/>
+ <configuration counter="ARMv7_Cortex_A8_cnt3" event="0x10"/>
+ <configuration counter="ARMv7_Cortex_A9_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A9_cnt0" event="0x68"/>
+ <configuration counter="ARMv7_Cortex_A9_cnt1" event="0x06"/>
+ <configuration counter="ARMv7_Cortex_A9_cnt2" event="0x07"/>
+ <configuration counter="ARMv7_Cortex_A9_cnt3" event="0x03"/>
+ <configuration counter="ARMv7_Cortex_A9_cnt4" event="0x04"/>
+ <configuration counter="ARMv7_Cortex_A15_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A15_cnt0" event="0x8"/>
+ <configuration counter="ARMv7_Cortex_A15_cnt1" event="0x16"/>
+ <configuration counter="ARMv7_Cortex_A15_cnt2" event="0x10"/>
+ <configuration counter="ARMv7_Cortex_A15_cnt3" event="0x19"/>
+ <configuration counter="ARMv7_Cortex_A17_ccnt" event="0xff"/>
+ <configuration counter="ARMv7_Cortex_A17_cnt0" event="0x08"/>
+ <configuration counter="ARMv7_Cortex_A17_cnt1" event="0x16"/>
+ <configuration counter="ARMv7_Cortex_A17_cnt2" event="0x10"/>
+ <configuration counter="ARMv7_Cortex_A17_cnt3" event="0x19"/>
+ <configuration counter="ARM_Cortex-A53_ccnt" event="0x11"/>
+ <configuration counter="ARM_Cortex-A53_cnt0" event="0x8"/>
+ <configuration counter="ARM_Cortex-A53_cnt1" event="0x16"/>
+ <configuration counter="ARM_Cortex-A53_cnt2" event="0x10"/>
+ <configuration counter="ARM_Cortex-A53_cnt3" event="0x19"/>
+ <configuration counter="ARM_Cortex-A57_ccnt" event="0x11"/>
+ <configuration counter="ARM_Cortex-A57_cnt0" event="0x8"/>
+ <configuration counter="ARM_Cortex-A57_cnt1" event="0x16"/>
+ <configuration counter="ARM_Cortex-A57_cnt2" event="0x10"/>
+ <configuration counter="ARM_Cortex-A57_cnt3" event="0x19"/>
+ <configuration counter="ARM_Cortex-A72_ccnt" event="0x11"/>
+ <configuration counter="ARM_Cortex-A72_cnt0" event="0x8"/>
+ <configuration counter="ARM_Cortex-A72_cnt1" event="0x16"/>
+ <configuration counter="ARM_Cortex-A72_cnt2" event="0x10"/>
+ <configuration counter="ARM_Cortex-A72_cnt3" event="0x19"/>
+ <configuration counter="Scorpion_ccnt" event="0xff"/>
+ <configuration counter="Scorpion_cnt0" event="0x08"/>
+ <configuration counter="Scorpion_cnt1" event="0x10"/>
+ <configuration counter="ScorpionMP_ccnt" event="0xff"/>
+ <configuration counter="ScorpionMP_cnt0" event="0x08"/>
+ <configuration counter="ScorpionMP_cnt1" event="0x10"/>
+ <configuration counter="Krait_ccnt" event="0xff"/>
+ <configuration counter="Krait_cnt0" event="0x08"/>
+ <configuration counter="Krait_cnt1" event="0x10"/>
+ <configuration counter="Linux_block_rq_wr"/>
+ <configuration counter="Linux_block_rq_rd"/>
+ <configuration counter="Linux_meminfo_memused"/>
+ <configuration counter="Linux_meminfo_memused2"/>
+ <configuration counter="Linux_meminfo_memfree"/>
+ <configuration counter="Linux_power_cpu_freq"/>
+ <configuration counter="ARM_Mali-4xx_fragment"/>
+ <configuration counter="ARM_Mali-4xx_vertex"/>
+ <configuration counter="ARM_Mali-Midgard_fragment" cores="1"/>
+ <configuration counter="ARM_Mali-Midgard_vertex" cores="1"/>
+ <configuration counter="ARM_Mali-Midgard_opencl" cores="1"/>
+ <configuration counter="L2C-310_cnt0" event="0x1"/>
+</configurations>
diff --git a/tools/gator/daemon/escape.c b/tools/gator/daemon/escape.c
new file mode 100644
index 0000000..99f4348
--- /dev/null
+++ b/tools/gator/daemon/escape.c
@@ -0,0 +1,75 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * The Makefile in the daemon folder builds and executes 'escape'
+ * 'escape' creates configuration_xml.h from configuration.xml and events_xml.h from events-*.xml
+ * these genereated xml files are then #included and built as part of the gatord binary
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+static void print_escaped_path(char *path) {
+ if (isdigit(*path)) {
+ printf("__");
+ }
+ for (; *path != '\0'; ++path) {
+ printf("%c", isalnum(*path) ? *path : '_');
+ }
+}
+
+int main(int argc, char *argv[]) {
+ int i;
+ char *path;
+ FILE *in = NULL;
+ int ch;
+ unsigned int len = 0;
+
+ for (i = 1; i < argc && argv[i][0] == '-'; ++i) ;
+ if (i == argc) {
+ fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
+ return EXIT_FAILURE;
+ }
+ path = argv[i];
+
+ errno = 0;
+ if ((in = fopen(path, "r")) == NULL) {
+ fprintf(stderr, "Unable to open '%s': %s\n", path, strerror(errno));
+ return EXIT_FAILURE;
+ }
+
+ printf("static const unsigned char ");
+ print_escaped_path(path);
+ printf("[] = {");
+ for (;;) {
+ ch = fgetc(in);
+ if (len != 0) {
+ printf(",");
+ }
+ if (len % 12 == 0) {
+ printf("\n ");
+ }
+ // Write out a null character after the contents of the file but do not increment len
+ printf(" 0x%.2x", (ch == EOF ? 0 : ch));
+ if (ch == EOF) {
+ break;
+ }
+ ++len;
+ }
+ printf("\n};\nstatic const unsigned int ");
+ print_escaped_path(path);
+ printf("_len = %i;\n", len);
+
+ fclose(in);
+
+ return EXIT_SUCCESS;
+}
diff --git a/tools/gator/daemon/events-ARM11.xml b/tools/gator/daemon/events-ARM11.xml
new file mode 100644
index 0000000..e481267
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11.xml
@@ -0,0 +1,39 @@
+ <counter_set name="ARM_ARM11_cnt" count="3"/>
+ <category name="ARM11" counter_set="ARM_ARM11_cnt" per_cpu="yes">
+ <event counter="ARM_ARM11_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+ <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+ <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+ <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+ <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+ <event event="0x05" title="Branch" name="Instruction executed" description="Branch instruction executed, branch might or might not have changed program flow"/>
+ <event event="0x06" title="Branch" name="Mispredicted" description="Branch mis-predicted"/>
+ <event event="0x07" title="Instruction" name="Executed" description="Instructions executed"/>
+ <event event="0x09" title="Cache" name="Data access" description="Data cache access, not including Cache operations"/>
+ <event event="0x0a" title="Cache" name="Data all access" description="Data cache access, not including Cache Operations regardless of whether or not the location is cacheable"/>
+ <event event="0x0b" title="Cache" name="Data miss" description="Data cache miss, not including Cache Operations"/>
+ <event event="0x0c" title="Cache" name="Write-back" description="Data cache write-back"/>
+ <event event="0x0d" title="Program Counter" name="SW change" description="Software changed the PC"/>
+ <event event="0x0f" title="Cache " name="TLB miss" description="Main TLB miss (unused on ARM1156)"/>
+ <event event="0x10" title="External" name="Access" description="Explicit external data or peripheral access"/>
+ <event event="0x11" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+ <event event="0x12" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of a Data Synchronization Barrier command or Strongly Ordered operation"/>
+ <event event="0x13" title="Disable Interrupts" name="FIQ" description="The number of cycles which FIQ interrupts are disabled (ARM1156 only)"/>
+ <event event="0x14" title="Disable Interrupts" name="IRQ" description="The number of cycles which IRQ interrupts are disabled (ARM1156 only)"/>
+ <event event="0x20" title="ETM" name="ETMEXTOUT[0]" description="ETMEXTOUT[0] signal was asserted for a cycle"/>
+ <event event="0x21" title="ETM" name="ETMEXTOUT[1]" description="ETMEXTOUT[1] signal was asserted for a cycle"/>
+ <event event="0x22" title="ETM" name="ETMEXTOUT[0,1]" description="ETMEXTOUT[0] or ETMEXTOUT[1] was asserted"/>
+ <event event="0x23" title="Procedure" name="Calls" description="Procedure call instruction executed"/>
+ <event event="0x24" title="Procedure" name="Returns" description="Procedure return instruction executed"/>
+ <event event="0x25" title="Procedure" name="Return and predicted" description="Procedure return instruction executed and return address predicted"/>
+ <event event="0x26" title="Procedure" name="Return and mispredicted" description="Procedure return instruction executed and return address predicted incorrectly"/>
+ <event event="0x30" title="Cache" name="Inst tag or parity error" description="Instruction cache Tag or Valid RAM parity error (ARM1156 only)"/>
+ <event event="0x31" title="Cache" name="Inst parity error" description="Instruction cache RAM parity error (ARM1156 only)"/>
+ <event event="0x32" title="Cache" name="Data tag or parity error" description="Data cache Tag or Valid RAM parity error (ARM1156 only)"/>
+ <event event="0x33" title="Cache" name="Data parity error" description="Data cache RAM parity error (ARM1156 only)"/>
+ <event event="0x34" title="ITCM" name="Error" description="ITCM error (ARM1156 only)"/>
+ <event event="0x35" title="DTCM" name="Error" description="DTCM error (ARM1156 only)"/>
+ <event event="0x36" title="Procedure" name="Return address pop" description="Procedure return address popped off the return stack (ARM1156 only)"/>
+ <event event="0x37" title="Procedure" name="Return address misprediction" description="Procedure return address popped off the return stack has been incorrectly predicted by the PFU (ARM1156 only)"/>
+ <event event="0x38" title="Cache" name="Data dirty parity error" description="Data cache Dirty RAM parity error (ARM1156 only)"/>
+ </category>
diff --git a/tools/gator/daemon/events-ARM11MPCore.xml b/tools/gator/daemon/events-ARM11MPCore.xml
new file mode 100644
index 0000000..2d5c5e1
--- /dev/null
+++ b/tools/gator/daemon/events-ARM11MPCore.xml
@@ -0,0 +1,26 @@
+ <counter_set name="ARM_ARM11MPCore_cnt" count="3"/>
+ <category name="ARM11MPCore" counter_set="ARM_ARM11MPCore_cnt" per_cpu="yes">
+ <event counter="ARM_ARM11MPCore_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Cache" name="Inst miss" description="Instruction cache miss to a cacheable location, which requires a fetch from external memory"/>
+ <event event="0x01" title="Pipeline" name="Instruction stall" description="Stall because instruction buffer cannot deliver an instruction"/>
+ <event event="0x02" title="Pipeline" name="Data stall" description="Stall because of a data dependency"/>
+ <event event="0x03" title="Cache" name="Inst micro TLB miss" description="Instruction MicroTLB miss (unused on ARM1156)"/>
+ <event event="0x04" title="Cache" name="Data micro TLB miss" description="Data MicroTLB miss (unused on ARM1156)"/>
+ <event event="0x05" title="Branch" name="Instruction executed" description="Branch instructions executed, branch might or might not have changed program flow"/>
+ <event event="0x06" title="Branch" name="Not predicted" description="Branch not predicted"/>
+ <event event="0x07" title="Branch" name="Mispredicted" description="Branch mispredicted"/>
+ <event event="0x08" title="Core" name="Instructions" description="Instructions executed"/>
+ <event event="0x09" title="Core" name="Folded Instructions" description="Folded instructions executed"/>
+ <event event="0x0a" title="Cache" name="Data read access" description="Data cache read access, not including cache operations"/>
+ <event event="0x0b" title="Cache" name="Data read miss" description="Data cache miss, not including Cache Operations"/>
+ <event event="0x0c" title="Cache" name="Data write access" description="Data cache write access"/>
+ <event event="0x0d" title="Cache" name="Data write miss" description="Data cache write miss"/>
+ <event event="0x0e" title="Cache" name="Data line eviction" description="Data cache line eviction, not including cache operations"/>
+ <event event="0x0f" title="Branch" name="PC change w/o mode change" description="Software changed the PC and there is not a mode change"/>
+ <event event="0x10" title="Cache " name="TLB miss" description="Main TLB miss"/>
+ <event event="0x11" title="External" name="External Memory request" description="External memory request (cache refill, noncachable, write-back)"/>
+ <event event="0x12" title="Cache" name="Stall" description="Stall because of Load Store Unit request queue being full"/>
+ <event event="0x13" title="Write Buffer" name="Drains" description="The number of times the Write Buffer was drained because of LSU ordering constraints or CP15 operations (Data Synchronization Barrier command) or Strongly Ordered operation"/>
+ <event event="0x14" title="Write Buffer" name="Write Merges" description="Buffered write merged in a store buffer slot"/>
+ <event event="0xFF" title="Core" name="Cycle counter" description="An increment each cycle"/>
+ </category>
diff --git a/tools/gator/daemon/events-CCI-400.xml b/tools/gator/daemon/events-CCI-400.xml
new file mode 100644
index 0000000..40d91e5
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-400.xml
@@ -0,0 +1,98 @@
+ <counter_set name="CCI_400_cnt" count="4"/>
+ <category name="CCI-400" counter_set="CCI_400_cnt" per_cpu="no">
+ <event counter="CCI_400_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+ <option_set name="Slave">
+ <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+ <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+ <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+ <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+ <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+ </option_set>
+ <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+ <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+ <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+ <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+ <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation, CleanInvalid, CleanShared, MakeInvalid"/>
+ <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+ <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+ <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+ <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+ <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+ <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+ <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+ <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+ <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+ <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+ <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+ <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+ <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+ <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+ <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+ <option_set name="Master">
+ <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+ <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+ <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+ </option_set>
+ <event event="0x14" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+ <event event="0x15" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Read request stall cycle because of an address hazard"/>
+ <event event="0x16" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of an ID hazard"/>
+ <event event="0x17" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="Read request stall cycle because the transaction tracker is full. Increase MIx_R_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+ <event event="0x18" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+ <event event="0x19" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+ <event event="0x1a" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase MIx_W_MAX to avoid this stall. See the CoreLink CCI-400 Cache Coherent Interconnect Integration Manual"/>
+ </category>
+ <counter_set name="CCI_400-r1_cnt" count="4"/>
+ <category name="CCI-400" counter_set="CCI_400-r1_cnt" per_cpu="no">
+ <event counter="CCI_400-r1_ccnt" event="0xff" title="CCI-400 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+ <option_set name="Slave">
+ <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+ <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+ <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+ <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+ <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+ </option_set>
+ <event event="0x00" option_set="Slave" title="CCI-400" name="Read: any" description="Read request handshake: any"/>
+ <event event="0x01" option_set="Slave" title="CCI-400" name="Read: transaction" description="Read request handshake: device transaction"/>
+ <event event="0x02" option_set="Slave" title="CCI-400" name="Read: normal" description="Read request handshake: normal, non-shareable or system-shareable, but not barrier or cache maintenance operation"/>
+ <event event="0x03" option_set="Slave" title="CCI-400" name="Read: shareable" description="Read request handshake: inner- or outer-shareable, but not barrier, DVM message or cache maintenance operation"/>
+ <event event="0x04" option_set="Slave" title="CCI-400" name="Read: cache" description="Read request handshake: cache maintenance operation"/>
+ <event event="0x05" option_set="Slave" title="CCI-400" name="Read: memory barrier" description="Read request handshake: memory barrier"/>
+ <event event="0x06" option_set="Slave" title="CCI-400" name="Read: sync barrier" description="Read request handshake: synchronization barrier"/>
+ <event event="0x07" option_set="Slave" title="CCI-400" name="Read: DVM message, no sync" description="Read request handshake: DVM message, not synchronization"/>
+ <event event="0x08" option_set="Slave" title="CCI-400" name="Read: DVM message, sync" description="Read request handshake: DVM message, synchronization"/>
+ <event event="0x09" option_set="Slave" title="CCI-400" name="Read: stall" description="Read request stall cycle because the transaction tracker is full. Increase SIx_R_MAX to avoid this stall"/>
+ <event event="0x0a" option_set="Slave" title="CCI-400" name="Read data last handshake" description="Read data last handshake: data returned from the snoop instead of from downstream"/>
+ <event event="0x0b" option_set="Slave" title="CCI-400" name="Read data stall cycle" description="Read data stall cycle: RVALIDS is HIGH, RREADYS is LOW"/>
+ <event event="0x0c" option_set="Slave" title="CCI-400" name="Write: any" description="Write request handshake: any"/>
+ <event event="0x0d" option_set="Slave" title="CCI-400" name="Write: transaction" description="Write request handshake: device transaction"/>
+ <event event="0x0e" option_set="Slave" title="CCI-400" name="Write: normal" description="Write request handshake: normal, non-shareable, or system-shareable, but not barrier"/>
+ <event event="0x0f" option_set="Slave" title="CCI-400" name="Write: shareable" description="Write request handshake: inner- or outer-shareable, WriteBack or WriteClean"/>
+ <event event="0x10" option_set="Slave" title="CCI-400" name="Write: WriteUnique" description="Write request handshake: WriteUnique"/>
+ <event event="0x11" option_set="Slave" title="CCI-400" name="Write: WriteLineUnique" description="Write request handshake: WriteLineUnique"/>
+ <event event="0x12" option_set="Slave" title="CCI-400" name="Write: Evict" description="Write request handshake: Evict"/>
+ <event event="0x13" option_set="Slave" title="CCI-400" name="Write stall: tracker full" description="Write request stall cycle because the transaction tracker is full. Increase SIx_W_MAX to avoid this stall"/>
+ <event event="0x14" option_set="Slave" title="CCI-400" name="Read stall: slave hazard" description="Read request stall cycle because of a slave interface ID hazard"/>
+ <option_set name="Master">
+ <option event_delta="0xa0" name="M0" description="Master interface 0"/>
+ <option event_delta="0xc0" name="M1" description="Master interface 1"/>
+ <option event_delta="0xe0" name="M2" description="Master interface 2"/>
+ </option_set>
+ <event event="0x00" option_set="Master" title="CCI-400" name="Retry fetch" description="RETRY of speculative fetch transaction"/>
+ <event event="0x01" option_set="Master" title="CCI-400" name="Read stall: address hazard" description="Stall cycle because of an address hazard. A read or write invalidation is stalled because of an outstanding transaction to an overlapping address"/>
+ <event event="0x02" option_set="Master" title="CCI-400" name="Read stall: ID hazard" description="Read request stall cycle because of a master interface ID hazard"/>
+ <event event="0x03" option_set="Master" title="CCI-400" name="Read stall: tracker full" description="A read request with a QoS value in the high priority group is stalled for a cycle because the read transaction queue is full. Increase MIx_R_MAX to avoid this stall"/>
+ <event event="0x04" option_set="Master" title="CCI-400" name="Read stall: barrier hazard" description="Read request stall cycle because of a barrier hazard"/>
+ <event event="0x05" option_set="Master" title="CCI-400" name="Write stall: barrier hazard" description="Write request stall cycle because of a barrier hazard"/>
+ <event event="0x06" option_set="Master" title="CCI-400" name="Write stall: tracker full" description="A write request is stalled for a cycle because the write transaction tracker is full. Increase MIx_W_MAX to avoid this stall"/>
+ <event event="0x07" option_set="Master" title="CCI-400" name="Read Stall: Low Priority" description="A read request with a QoS value in the low priority group is stalled for a cycle because there are no slots available in the read queue for the low priority group"/>
+ <event event="0x08" option_set="Master" title="CCI-400" name="Read Stall: Medium Priority" description="A read request with a QoS value in the medium priority group is stalled for a cycle because there are no slots available in the read queue for the medium priority group"/>
+ <event event="0x09" option_set="Master" title="CCI-400" name="Read Stall: VN0" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+ <event event="0x0a" option_set="Master" title="CCI-400" name="Read Stall: VN1" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+ <event event="0x0b" option_set="Master" title="CCI-400" name="Read Stall: VN2" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+ <event event="0x0c" option_set="Master" title="CCI-400" name="Read Stall: VN3" description="A read request is stalled for a cycle while it was waiting for a QVN token on VN3"/>
+ <event event="0x0d" option_set="Master" title="CCI-400" name="Write Stall: VN0" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN0"/>
+ <event event="0x0e" option_set="Master" title="CCI-400" name="Write Stall: VN1" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN1"/>
+ <event event="0x0f" option_set="Master" title="CCI-400" name="Write Stall: VN2" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN2"/>
+ <event event="0x10" option_set="Master" title="CCI-400" name="Write Stall: VN" description="A write request is stalled for a cycle while it was waiting for a QVN token on VN"/>
+ <event event="0x11" option_set="Master" title="CCI-400" name="WriteUnique or WriteLineUnique Stall" description="A WriteUnique or WriteLineUnique request is stalled for a cycle because of an address hazard"/>
+ </category>
diff --git a/tools/gator/daemon/events-CCI-500.xml b/tools/gator/daemon/events-CCI-500.xml
new file mode 100644
index 0000000..e7cadc4
--- /dev/null
+++ b/tools/gator/daemon/events-CCI-500.xml
@@ -0,0 +1,75 @@
+ <counter_set name="CCI_500_cnt" count="8"/>
+ <category name="CCI-500" counter_set="CCI_500_cnt" per_cpu="no">
+ <option_set name="Slave">
+ <option event_delta="0x00" name="S0" description="Slave interface 0"/>
+ <option event_delta="0x20" name="S1" description="Slave interface 1"/>
+ <option event_delta="0x40" name="S2" description="Slave interface 2"/>
+ <option event_delta="0x60" name="S3" description="Slave interface 3"/>
+ <option event_delta="0x80" name="S4" description="Slave interface 4"/>
+ <option event_delta="0xa0" name="S5" description="Slave interface 5"/>
+ <option event_delta="0xc0" name="S6" description="Slave interface 6"/>
+ </option_set>
+ <event event="0x00" option_set="Slave" title="CCI-500" name="Read ARVALID" description="Read request handshake: any ARVALID, ARREADY HIGH"/>
+ <event event="0x01" option_set="Slave" title="CCI-500" name="Read device" description="Read request: device"/>
+ <event event="0x02" option_set="Slave" title="CCI-500" name="Read non-shareable" description="Read request handshake: normal, non-shareable"/>
+ <event event="0x03" option_set="Slave" title="CCI-500" name="Read non-allocating" description="Read request handshake: normal, shareable, non-allocating, for example ReadOnce"/>
+ <event event="0x04" option_set="Slave" title="CCI-500" name="Read other" description="Read request handshake: normal, shareable allocating, for example ReadClean, ReadShared, ReadNotSharedDirty, ReadUnique"/>
+ <event event="0x05" option_set="Slave" title="CCI-500" name="Read invalidation" description="Read request handshake: invalidation, for example MakeUnique, CleanUnique"/>
+ <event event="0x06" option_set="Slave" title="CCI-500" name="Read maintenance" description="Read request handshake: cache maintenance operation, for example CleanInvalid, MakeInvalid, CleanShared"/>
+ <event event="0x07" option_set="Slave" title="CCI-500" name="Read DVM" description="Read request handshake: DVM message, any"/>
+ <event event="0x08" option_set="Slave" title="CCI-500" name="Read RVALID" description="Read data handshake: any RVALID, RREADY HIGH"/>
+ <event event="0x09" option_set="Slave" title="CCI-500" name="Read RLAST" description="Read data handshake with RLAST set, for a snoop hit"/>
+ <event event="0x0a" option_set="Slave" title="CCI-500" name="Write AWVALID" description="Write request: any AWVALID, AWREADY HIGH"/>
+ <event event="0x0b" option_set="Slave" title="CCI-500" name="Write device" description="Write request: device"/>
+ <event event="0x0c" option_set="Slave" title="CCI-500" name="Write non-shareable" description="Write request: non-shareable"/>
+ <event event="0x0d" option_set="Slave" title="CCI-500" name="Write shareable a" description="Write request handshake: shareable, for example WriteBack, WriteClean"/>
+ <event event="0x0e" option_set="Slave" title="CCI-500" name="Write shareable b" description="Write request handshake: shareable, for example WriteLineUnique"/>
+ <event event="0x0f" option_set="Slave" title="CCI-500" name="Write shareable c" description="Write request handshake: shareable, for example WriteUnique"/>
+ <event event="0x10" option_set="Slave" title="CCI-500" name="Write evict" description="Write request handshake, for example Evict"/>
+ <!--event event="0x11" option_set="Slave" title="CCI-500" name="Write evict ?" description="Write request handshake, for example WriteEvict. WriteEvict is not supported in the CCI-500, so does not fire."/-->
+ <event event="0x12" option_set="Slave" title="CCI-500" name="Write WVALID" description="Write data beat: any WVALID, WREADY HIGH"/>
+ <event event="0x13" option_set="Slave" title="CCI-500" name="Snoop ACVLID" description="Snoop request: any ACVALID, ACREADY HIGH"/>
+ <event event="0x14" option_set="Slave" title="CCI-500" name="Snoop read" description="Snoop request: read, for example ReadOnce, ReadClean, ReadNotSharedDirty, ReadShared, ReadUnique"/>
+ <event event="0x15" option_set="Slave" title="CCI-500" name="Snoop invalidate" description="Snoop request: clean or invalidate, for example MakeInvalid, CleanInvalid, CleanShared"/>
+ <event event="0x16" option_set="Slave" title="CCI-500" name="Snoop CRRESP" description="Snoop request: Data Transfer bit CRRESP[0] LOW"/>
+ <event event="0x17" option_set="Slave" title="CCI-500" name="Read request stall" description="Read request stall: ARVALID HIGH ARREADY LOW"/>
+ <event event="0x18" option_set="Slave" title="CCI-500" name="Read data stall" description="Read data stall: RVALID HIGH RREADY LOW"/>
+ <event event="0x19" option_set="Slave" title="CCI-500" name="Write request stall" description="Write request stall: AWVALID HIGH AWREADY LOW"/>
+ <event event="0x1a" option_set="Slave" title="CCI-500" name="Write data stall" description="Write data stall: WVALID HIGH WREADY LOW"/>
+ <event event="0x1b" option_set="Slave" title="CCI-500" name="Write response stall" description="Write response stall: BVALID HIGH BREADY LOW"/>
+ <event event="0x1c" option_set="Slave" title="CCI-500" name="Snoop request stall" description="Snoop request stall: ACVALID HIGH ACREADY LOW"/>
+ <event event="0x1d" option_set="Slave" title="CCI-500" name="Snoop data stall" description="Snoop data stall: CDVALID HIGH CDREADY LOW"/>
+ <event event="0x1e" option_set="Slave" title="CCI-500" name="Request stall" description="Request stall cycle because of OT transaction limit"/>
+ <event event="0x1f" option_set="Slave" title="CCI-500" name="Read stall" description="Read stall because of arbitration"/>
+ <option_set name="Master">
+ <option event_delta="0x100" name="M0" description="Master interface 0"/>
+ <option event_delta="0x120" name="M1" description="Master interface 1"/>
+ <option event_delta="0x140" name="M2" description="Master interface 2"/>
+ <option event_delta="0x160" name="M3" description="Master interface 3"/>
+ <option event_delta="0x180" name="M4" description="Master interface 4"/>
+ <option event_delta="0x1a0" name="M5" description="Master interface 5"/>
+ </option_set>
+ <event event="0x00" option_set="Master" title="CCI-500" name="Read data beat" description="Read data beat: any"/>
+ <event event="0x01" option_set="Master" title="CCI-500" name="Write data beat" description="Write data beat: any"/>
+ <event event="0x02" option_set="Master" title="CCI-500" name="Read request stall" description="Read request stall: ARVALID HIGH ARREADY LOW"/>
+ <event event="0x03" option_set="Master" title="CCI-500" name="Read data stall" description="Read data stall: RVALID HIGH RREADY LOW"/>
+ <event event="0x04" option_set="Master" title="CCI-500" name="Write request stall" description="Write request stall: AWVALID HIGH AWREADY LOW"/>
+ <event event="0x05" option_set="Master" title="CCI-500" name="Write data stall" description="Write data stall: WVALID HIGH WREADY LOW"/>
+ <event event="0x06" option_set="Master" title="CCI-500" name="Write response stall" description="Write response stall: BVALID HIGH BREADY LOW"/>
+ <event event="0x1e0" title="CCI-500" name="Snoop response 0/1" description="Access to snoop filter bank 0 or 1, any response"/>
+ <event event="0x1e1" title="CCI-500" name="Snoop response 2/3" description="Access to snoop filter bank 2 or 3, any response"/>
+ <event event="0x1e2" title="CCI-500" name="Snoop response 3/4" description="Access to snoop filter bank 4 or 5, any response"/>
+ <event event="0x1e3" title="CCI-500" name="Snoop response 6/7" description="Access to snoop filter bank 6 or 7, any response"/>
+ <event event="0x1e4" title="CCI-500" name="Snoop miss 0/1" description="Access to snoop filter bank 0 or 1, miss response"/>
+ <event event="0x1e5" title="CCI-500" name="Snoop miss 2/3" description="Access to snoop filter bank 2 or 3, miss response"/>
+ <event event="0x1e6" title="CCI-500" name="Snoop miss 4/5" description="Access to snoop filter bank 4 or 5, miss response"/>
+ <event event="0x1e7" title="CCI-500" name="Snoop miss 6/7" description="Access to snoop filter bank 6 or 7, miss response"/>
+ <event event="0x1e8" title="CCI-500" name="Snoop invalidation" description="Back invalidation from snoop filter"/>
+ <event event="0x1e9" title="CCI-500" name="Snoop small" description="Requests that allocate into a snoop filter bank might be stalled because all ways are used. The snoop filter RAM might be too small."/>
+ <event event="0x1ea" title="CCI-500" name="TT stall" description="Stall because TT full, increase TT_DEPTH parameter to avoid performance degradation"/>
+ <event event="0x1eb" title="CCI-500" name="Write request" description="CCI-generated write request"/>
+ <event event="0x1ec" title="CCI-500" name="Snoop handshake" description="CD handshake in snoop network, use this to measure snoop data bandwidth. Each event corresponds to 16 bytes of snoop data."/>
+ <event event="0x1ed" title="CCI-500" name="Address hazard" description="Request stall because of address hazard"/>
+ <event event="0x1ee" title="CCI-500" name="TT full" description="Snoop request stall because of snoop TT being full"/>
+ <event event="0x1ef" title="CCI-500" name="Snoop override" description="Snoop request type override for TZMP1 protection"/>
+ </category>
diff --git a/tools/gator/daemon/events-CCN-504.xml b/tools/gator/daemon/events-CCN-504.xml
new file mode 100644
index 0000000..6ef3e64
--- /dev/null
+++ b/tools/gator/daemon/events-CCN-504.xml
@@ -0,0 +1,113 @@
+ <counter_set name="CCN-504_cnt" count="4"/>
+ <category name="CCN-504" counter_set="CCN-504_cnt">
+ <event counter="CCN-504_ccnt" title="CCN-504 Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" description="The number of core clock cycles"/>
+ <option_set name="XP_Region">
+ <option event_delta="0x400000" name="XP 0" description="Crosspoint 0"/>
+ <option event_delta="0x410000" name="XP 1" description="Crosspoint 1"/>
+ <option event_delta="0x420000" name="XP 2" description="Crosspoint 2"/>
+ <option event_delta="0x430000" name="XP 3" description="Crosspoint 3"/>
+ <option event_delta="0x440000" name="XP 4" description="Crosspoint 4"/>
+ <option event_delta="0x450000" name="XP 5" description="Crosspoint 5"/>
+ <option event_delta="0x460000" name="XP 6" description="Crosspoint 6"/>
+ <option event_delta="0x470000" name="XP 7" description="Crosspoint 7"/>
+ <option event_delta="0x480000" name="XP 8" description="Crosspoint 8"/>
+ <option event_delta="0x490000" name="XP 9" description="Crosspoint 9"/>
+ <option event_delta="0x4A0000" name="XP 10" description="Crosspoint 10"/>
+ </option_set>
+ <event event="0x0801" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: H-bit" description="Bus 0: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x0802" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: S-bit" description="Bus 0: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x0803" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: P-Cnt" description="Bus 0: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x0804" option_set="XP_Region" title="CCN-504" name="Bus 0: REQ: TknV" description="Bus 0: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0809" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: H-bit" description="Bus 1: REQ: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x080A" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: S-bit" description="Bus 1: REQ: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x080B" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: P-Cnt" description="Bus 1: REQ: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x080C" option_set="XP_Region" title="CCN-504" name="Bus 1: REQ: TknV" description="Bus 1: REQ: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0811" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: H-bit" description="Bus 0: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x0812" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: S-bit" description="Bus 0: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x0813" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: P-Cnt" description="Bus 0: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x0814" option_set="XP_Region" title="CCN-504" name="Bus 0: RSP: TknV" description="Bus 0: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0819" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: H-bit" description="Bus 1: RSP: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x081A" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: S-bit" description="Bus 1: RSP: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x081B" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: P-Cnt" description="Bus 1: RSP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x081C" option_set="XP_Region" title="CCN-504" name="Bus 1: RSP: TknV" description="Bus 1: RSP: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0821" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: H-bit" description="Bus 0: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x0822" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: S-bit" description="Bus 0: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x0823" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: P-Cnt" description="Bus 0: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x0824" option_set="XP_Region" title="CCN-504" name="Bus 0: SNP: TknV" description="Bus 0: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0829" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: H-bit" description="Bus 1: SNP: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x082A" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: S-bit" description="Bus 1: SNP: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x082B" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: P-Cnt" description="Bus 1: SNP: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x082C" option_set="XP_Region" title="CCN-504" name="Bus 1: SNP: TknV" description="Bus 1: SNP: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0831" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: H-bit" description="Bus 0: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x0832" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: S-bit" description="Bus 0: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x0833" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: P-Cnt" description="Bus 0: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x0834" option_set="XP_Region" title="CCN-504" name="Bus 0: DAT: TknV" description="Bus 0: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0839" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: H-bit" description="Bus 1: DAT: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x083A" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: S-bit" description="Bus 1: DAT: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x083B" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: P-Cnt" description="Bus 1: DAT: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x083C" option_set="XP_Region" title="CCN-504" name="Bus 1: DAT: TknV" description="Bus 1: DAT: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0871" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: H-bit" description="Bus 0: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x0872" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: S-bit" description="Bus 0: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x0873" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: P-Cnt" description="Bus 0: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x0874" option_set="XP_Region" title="CCN-504" name="Bus 0: DATB: TknV" description="Bus 0: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+ <event event="0x0879" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: H-bit" description="Bus 1: DATB: Set H-bit, signaled when this XP sets the H-bit."/>
+ <event event="0x087A" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: S-bit" description="Bus 1: DATB: Set S-bit, signaled when this XP sets the S-bit."/>
+ <event event="0x087B" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: P-Cnt" description="Bus 1: DATB: Set P-Cnt, signaled when this XP sets the P-Cnt. This is not applicable for the SNP VC."/>
+ <event event="0x087C" option_set="XP_Region" title="CCN-504" name="Bus 1: DATB: TknV" description="Bus 1: DATB: No TknV, signaled when this XP transmits a valid packet."/>
+ <option_set name="HN-F_Region">
+ <option event_delta="0x200000" name="HN-F 3" description="Fully-coherent Home Node 3"/>
+ <option event_delta="0x210000" name="HN-F 5" description="Fully-coherent Home Node 5"/>
+ <option event_delta="0x220000" name="HN-F 7" description="Fully-coherent Home Node 7"/>
+ <option event_delta="0x230000" name="HN-F 8" description="Fully-coherent Home Node 8"/>
+ <option event_delta="0x240000" name="HN-F 13" description="Fully-coherent Home Node 13"/>
+ <option event_delta="0x250000" name="HN-F 15" description="Fully-coherent Home Node 15"/>
+ <option event_delta="0x260000" name="HN-F 17" description="Fully-coherent Home Node 17"/>
+ <option event_delta="0x270000" name="HN-F 18" description="Fully-coherent Home Node 18"/>
+ </option_set>
+ <event event="0x0401" option_set="HN-F_Region" title="CCN-504" name="Cache Miss" description="Counts the total cache misses. This is the first time lookup result, and is high priority."/>
+ <event event="0x0402" option_set="HN-F_Region" title="CCN-504" name="L3 SF Cache Access" description="Counts the number of cache accesses. This is the first time access, and is high priority."/>
+ <event event="0x0403" option_set="HN-F_Region" title="CCN-504" name="Cache Fill" description="Counts the total allocations in the HN L3 cache, and all cache line allocations to the L3 cache."/>
+ <event event="0x0404" option_set="HN-F_Region" title="CCN-504" name="POCQ Retry" description="Counts the number of requests that have been retried."/>
+ <event event="0x0405" option_set="HN-F_Region" title="CCN-504" name="POCQ Reqs Recvd" description="Counts the number of requests received by HN."/>
+ <event event="0x0406" option_set="HN-F_Region" title="CCN-504" name="SF Hit" description="Counts the number of snoop filter hits."/>
+ <event event="0x0407" option_set="HN-F_Region" title="CCN-504" name="SF Evictions" description="Counts the number of snoop filter evictions. Cache invalidations are initiated."/>
+ <event event="0x0408" option_set="HN-F_Region" title="CCN-504" name="Snoops Sent" description="Counts the number of snoops sent. Does not differentiate between broadcast or directed snoops."/>
+ <event event="0x0409" option_set="HN-F_Region" title="CCN-504" name="Snoops Broadcast" description="Counts the number of snoop broadcasts sent."/>
+ <event event="0x040A" option_set="HN-F_Region" title="CCN-504" name="L3 Eviction" description="Counts the number of L3 evictions."/>
+ <event event="0x040B" option_set="HN-F_Region" title="CCN-504" name="L3 Fill Invalid Way" description="Counts the number of L3 fills to an invalid way."/>
+ <event event="0x040C" option_set="HN-F_Region" title="CCN-504" name="MC Retries" description="Counts the number of transactions retried by the memory controller."/>
+ <event event="0x040D" option_set="HN-F_Region" title="CCN-504" name="MC Reqs" description="Counts the number of requests to the memory controller."/>
+ <event event="0x040E" option_set="HN-F_Region" title="CCN-504" name="QOS HH Retry" description="Counts the number of times a highest-priority QoS class was retried at the HN-F."/>
+ <option_set name="RN-I_Region">
+ <option event_delta="0x800000" name="RN-I 0" description="I/O-coherent Requesting Node 0"/>
+ <option event_delta="0x820000" name="RN-I 2" description="I/O-coherent Requesting Node 2"/>
+ <option event_delta="0x860000" name="RN-I 6" description="I/O-coherent Requesting Node 6"/>
+ <option event_delta="0x8C0000" name="RN-I 12" description="I/O-coherent Requesting Node 12"/>
+ <option event_delta="0x900000" name="RN-I 16" description="I/O-coherent Requesting Node 16"/>
+ <option event_delta="0x940000" name="RN-I 20" description="I/O-coherent Requesting Node 20"/>
+ </option_set>
+ <event event="0x1601" option_set="RN-I_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+ <event event="0x1602" option_set="RN-I_Region" title="CCN-504" name="S1 RDataBeats" description="S1 RDataBeats."/>
+ <event event="0x1603" option_set="RN-I_Region" title="CCN-504" name="S2 RDataBeats" description="S2 RDataBeats."/>
+ <event event="0x1604" option_set="RN-I_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+ <event event="0x1605" option_set="RN-I_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+ <event event="0x1606" option_set="RN-I_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+ <event event="0x1607" option_set="RN-I_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+ <event event="0x1608" option_set="RN-I_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+ <event event="0x1609" option_set="RN-I_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+ <event event="0x160A" option_set="RN-I_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+ <option_set name="SBAS_Region">
+ <option event_delta="0x810000" name="SBAS 1" description="ACE master to CHI protocol bridge 1"/>
+ <option event_delta="0x890000" name="SBAS 9" description="ACE master to CHI protocol bridge 9"/>
+ <option event_delta="0x8B0000" name="SBAS 11" description="ACE master to CHI protocol bridge 11"/>
+ <option event_delta="0x930000" name="SBAS 19" description="ACE master to CHI protocol bridge 19"/>
+ </option_set>
+ <event event="0x1001" option_set="SBAS_Region" title="CCN-504" name="S0 RDataBeats" description="S0 RDataBeats."/>
+ <event event="0x1004" option_set="SBAS_Region" title="CCN-504" name="RXDAT Flits received" description="RXDAT Flits received."/>
+ <event event="0x1005" option_set="SBAS_Region" title="CCN-504" name="TXDAT Flits sent" description="TXDAT Flits sent."/>
+ <event event="0x1006" option_set="SBAS_Region" title="CCN-504" name="Total TXREQ Flits sent" description="Total TXREQ Flits sent."/>
+ <event event="0x1007" option_set="SBAS_Region" title="CCN-504" name="Retried TXREQ Flits sent" description="Retried TXREQ Flits sent."/>
+ <event event="0x1008" option_set="SBAS_Region" title="CCN-504" name="RRT full" description="RRT full."/>
+ <event event="0x1009" option_set="SBAS_Region" title="CCN-504" name="WRT full" description="WRT full."/>
+ <event event="0x100A" option_set="SBAS_Region" title="CCN-504" name="Replayed TXREQ Flits" description="Replayed TXREQ Flits."/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A15.xml b/tools/gator/daemon/events-Cortex-A15.xml
new file mode 100644
index 0000000..c0ccc8a
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A15.xml
@@ -0,0 +1,70 @@
+ <counter_set name="ARMv7_Cortex_A15_cnt" count="6"/>
+ <category name="Cortex-A15" counter_set="ARMv7_Cortex_A15_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A15_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Instruction architecturally executed, condition code check pass, software increment"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed, condition code check pass, exception return"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed, condition code check pass, write to CONTEXTIDR"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache write-back"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back"/>
+ <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+ <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+ <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+ <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed, condition code check pass, write to TTBR"/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access, read"/>
+ <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access, write"/>
+ <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill, read"/>
+ <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill, write"/>
+ <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache write-back, victim"/>
+ <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache write-back, cleaning and coherency"/>
+ <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+ <event event="0x4c" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill, read"/>
+ <event event="0x4d" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill, write"/>
+ <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access, read"/>
+ <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access, write"/>
+ <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill, read"/>
+ <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill, write"/>
+ <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache write-back, victim"/>
+ <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache write-back, cleaning and coherency"/>
+ <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+ <event event="0x60" title="Bus" name="Read" description="Bus access, read"/>
+ <event event="0x61" title="Bus" name="Write" description="Bus access, write"/>
+ <event event="0x62" title="Bus" name="Cacheable normal" description="Bus access, Normal, Cacheable, Shareable"/>
+ <event event="0x63" title="Bus" name="Not normal" description="Bus access, not Normal, Cacheable, Shareable"/>
+ <event event="0x64" title="Bus" name="Access normal" description="Bus access, normal"/>
+ <event event="0x65" title="Bus" name="Peripheral" description="Bus access, peripheral"/>
+ <event event="0x66" title="Memory" name="Read" description="Data memory access, read"/>
+ <event event="0x67" title="Memory" name="Write" description="Data memory access, write"/>
+ <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access, read"/>
+ <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access, write"/>
+ <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+ <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed, LDREX"/>
+ <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed, STREX pass"/>
+ <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed, STREX fail"/>
+ <event event="0x70" title="Instruction" name="Load" description="Instruction speculatively executed, load"/>
+ <event event="0x71" title="Instruction" name="Store" description="Instruction speculatively executed, store"/>
+ <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed, load or store"/>
+ <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed, integer data processing"/>
+ <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed, Advanced SIMD Extension"/>
+ <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed, Floating-point Extension"/>
+ <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed, software change of the PC"/>
+ <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed, immediate branch"/>
+ <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed, procedure return"/>
+ <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed, indirect branch"/>
+ <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed, ISB"/>
+ <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed, DSB"/>
+ <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed, DMB"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A17.xml b/tools/gator/daemon/events-Cortex-A17.xml
new file mode 100644
index 0000000..ce1b781
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A17.xml
@@ -0,0 +1,85 @@
+ <counter_set name="ARMv7_Cortex_A17_cnt" count="6"/>
+ <category name="Cortex-A17" counter_set="ARMv7_Cortex_A17_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A17_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+ <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+ <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID register."/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x13" title="Memory" name="Memory access" description="Level 1 data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache eviction"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back. Data transfers made as a result of a coherency request from the Level 2 caches to outside of the Level 1 and Level 2 caches are not counted. Write-backs made as a result of CP15 cache maintenance operations are counted."/>
+ <event event="0x19" title="Bus" name="Access" description="Bus accesses. Single transfer bus accesses on either of the ACE read or write channels might increment twice in one cycle if both the read and write channels are active simultaneously.Operations that utilise the bus that do not explicitly transfer data, such as barrier or coherency operations are counted as bus accesses."/>
+ <event event="0x1b" title="Instruction" name="Speculative" description="Instructions speculatively executed"/>
+ <event event="0x1c" title="Memory" name="Translation table" description="Write to translation table register (TTBR0 or TTBR1)"/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+ <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+ <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+ <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+ <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache write-back - Victim"/>
+ <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache write-back - Cleaning and coherency"/>
+ <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+ <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal Cacheable"/>
+ <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not Cacheable"/>
+ <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+ <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+ <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+ <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+ <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+ <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+ <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+ <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive instruction speculatively executed - LDREX"/>
+ <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive instruction speculatively executed - STREX fail"/>
+ <event event="0x6f" title="Intrinsic" name="STREX" description="Exclusive instruction speculatively executed - STREX"/>
+ <event event="0x70" title="Instruction" name="Load" description="Load instruction speculatively executed"/>
+ <event event="0x71" title="Instruction" name="Store" description="Store instruction speculatively executed"/>
+ <event event="0x72" title="Instruction" name="Load/Store" description="Instruction speculatively executed - Load or store"/>
+ <event event="0x73" title="Instruction" name="Integer" description="Instruction speculatively executed - Data processing"/>
+ <event event="0x74" title="Instruction" name="Advanced SIMD" description="Instruction speculatively executed - Advanced SIMD"/>
+ <event event="0x75" title="Instruction" name="VFP" description="Instruction speculatively executed - VFP"/>
+ <event event="0x76" title="Instruction" name="Software change" description="Instruction speculatively executed - Software change of the PC"/>
+ <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+ <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+ <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+ <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+ <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+ <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+ <event event="0x81" title="Exception" name="Undefined" description="Exception taken - Undefined Instruction"/>
+ <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken - Hypervisor Call"/>
+ <event event="0xc0" title="Instruction" name="Stalled Linefill" description="Instruction side stalled due to a linefill"/>
+ <event event="0xc1" title="Instruction" name="Stalled Page Table Walk" description="Instruction side stalled due to a translation table walk"/>
+ <event event="0xc2" title="Cache" name="4 Ways Read" description="Number of set of 4 ways read in the instruction cache - Tag RAM"/>
+ <event event="0xc3" title="Cache" name="Ways Read" description="Number of ways read in the instruction cache - Data RAM"/>
+ <event event="0xc4" title="Cache" name="BATC Read" description="Number of ways read in the instruction BTAC RAM"/>
+ <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A17 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data."/>
+ <event event="0xd3" title="Slots" name="Load-Store Unit" description="Duration during which all slots in the Load-Store Unit are busy"/>
+ <event event="0xd8" title="Slots" name="Load-Store Issue Queue" description="Duration during which all slots in the Load-Store Issue queue are busy"/>
+ <event event="0xd9" title="Slots" name="Data Processing Issue Queue" description="Duration during which all slots in the Data Processing issue queue are busy"/>
+ <event event="0xda" title="Slots" name="Data Engine Issue Queue" description="Duration during which all slots in the Data Engine issue queue are busy"/>
+ <event event="0xdb" title="NEON" name="Flush" description="Number of NEON instruction which fail their condition code and lead to a flush of the DE pipe"/>
+ <event event="0xdc" title="Hypervisor" name="Traps" description="Number of Trap to hypervisor"/>
+ <event event="0xde" title="PTM" name="EXTOUT 0" description="PTM EXTOUT 0"/>
+ <event event="0xdf" title="PTM" name="EXTOUT 1" description="PTM EXTOUT 1"/>
+ <event event="0xe0" title="MMU" name="Table Walk" description="Duration during which the MMU handle a translation table walk"/>
+ <event event="0xe1" title="MMU" name="Stage1 Table Walk" description="Duration during which the MMU handle a Stage1 translation table walk"/>
+ <event event="0xe2" title="MMU" name="Stage2 Table Walk" description="Duration during which the MMU handle a Stage2 translation table walk"/>
+ <event event="0xe3" title="MMU" name="LSU Table Walk" description="Duration during which the MMU handle a translation table walk requested by the Load Store Unit"/>
+ <event event="0xe4" title="MMU" name="Instruction Table Walk" description="Duration during which the MMU handle a translation table walk requested by the Instruction side"/>
+ <event event="0xe5" title="MMU" name="Preload Table Walk" description="Duration during which the MMU handle a translation table walk requested by a Preload instruction or Prefetch request"/>
+ <event event="0xe6" title="MMU" name="cp15 Table Walk" description="Duration during which the MMU handle a translation table walk requested by a CP15 operation (maintenance by MVA and VA-to-PA operation)"/>
+ <event event="0xe7" title="Cache" name="L1 PLD TLB refill" description="Level 1 PLD TLB refill"/>
+ <event event="0xe8" title="Cache" name="L1 CP15 TLB refill" description="Level 1 CP15 TLB refill"/>
+ <event event="0xe9" title="Cache" name="L1 TLB flush" description="Level 1 TLB flush"/>
+ <event event="0xea" title="Cache" name="L2 TLB access" description="Level 2 TLB access"/>
+ <event event="0xeb" title="Cache" name="L2 TLB miss" description="Level 2 TLB miss"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A5.xml b/tools/gator/daemon/events-Cortex-A5.xml
new file mode 100644
index 0000000..9fd48ab
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A5.xml
@@ -0,0 +1,36 @@
+ <counter_set name="ARMv7_Cortex_A5_cnt" count="2"/>
+ <category name="Cortex-A5" counter_set="ARMv7_Cortex_A5_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A5_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+ <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+ <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Data read architecturally executed. Counts the number of data read instructions accepted by the Load Store Unit. This includes counting the speculative and aborted LDR/LDM, and the reads because of the SWP instructions."/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. Counts the number of data write instructions accepted by the Load Store Unit. This includes counting the speculative and aborted STR/STM, and the writes because of the SWP instructions."/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID Register."/>
+ <event event="0x0c" title="Branch" name="PC change" description="Software change of PC"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed (taken or not taken). This includes the branches which are flushed due to a previous load/store which aborts late."/>
+ <event event="0x0e" title="Procedure" name="Return" description="Procedure return (other than exception returns) architecturally executed"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned load-store"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted/not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="Instruction access" description="Instruction Cache access"/>
+ <event event="0x15" title="Cache" name="Data eviction" description="Data cache eviction"/>
+ <event event="0x86" title="Interrupts" name="IRQ" description="IRQ exception taken"/>
+ <event event="0x87" title="Interrupts" name="FIQ" description="FIQ exception taken"/>
+ <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+ <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+ <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+ <event event="0xc3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+ <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+ <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+ <event event="0xc7" title="ETM" name="ETM Ext Out[0]" description="ETM Ext Out[0]"/>
+ <event event="0xc8" title="ETM" name="ETM Ext Out[1]" description="ETM Ext Out[1]"/>
+ <event event="0xc9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A53.xml b/tools/gator/daemon/events-Cortex-A53.xml
new file mode 100644
index 0000000..acdfe4e
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A53.xml
@@ -0,0 +1,64 @@
+ <counter_set name="ARM_Cortex-A53_cnt" count="6"/>
+ <category name="Cortex-A53" counter_set="ARM_Cortex-A53_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARM_Cortex-A53_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x06" title="Instruction" name="Data Read" description="Instruction architecturally executed, condition check pass - load"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Instruction architecturally executed, condition check pass - store"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to Context ID retired"/>
+ <event event="0x0c" title="Branch" name="PC change" description="Instruction architecturally executed, condition check pass, software change of the PC"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Instruction architecturally executed, immediate branch"/>
+ <event event="0x0e" title="Procedure" name="Return" description="Instruction architecturally executed, condition code check pass, procedure return"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Instruction architecturally executed, condition check pass, unaligned load or store"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="L1 Instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="L1 Data cache Write-Back"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="L2 Data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="L2 Data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="L2 Data cache Write-Back"/>
+ <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+ <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x1e" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+ <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+ <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+ <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+ <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+ <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+ <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+ <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+ <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+ <event event="0xc3" title="Cache" name="Throttle" description="Instruction Cache Throttle occurred"/>
+ <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+ <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+ <event event="0xc6" title="Pre-decode" name="error" description="Pre-decode error"/>
+ <event event="0xc7" title="Memory" name="Write stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+ <event event="0xc8" title="Memory" name="Snoop" description="SCU Snooped data from another CPU for this CPU"/>
+ <event event="0xc9" title="Branch" name="Taken" description="Conditional branch executed"/>
+ <!--
+ <event event="0xca" title="Branch" name="Mispredicted a" description="Indirect branch mispredicted"/>
+ <event event="0xcb" title="Branch" name="Mispredicted b" description="Indirect branch mispredicted because of address miscompare"/>
+ <event event="0xcc" title="Branch" name="Mispredicted c" description="Conditional branch mispredicted"/>
+ -->
+ <event event="0xd0" title="Cache" name="L1 inst error" description="L1 Instruction Cache (data or tag) memory error"/>
+ <event event="0xd1" title="Cache" name="L1 data error" description="L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"/>
+ <event event="0xd2" title="Cache" name="TLB error" description="TLB memory error"/>
+ <event event="0xe0" title="Stall" name="DPU IP empty" description="Attributable Performance Impact Event. Counts every cycle that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error."/>
+ <event event="0xe1" title="Stall" name="Cache miss" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is an instruction cache miss being processed."/>
+ <event event="0xe2" title="Stall" name="TLB miss" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is an instruction micro-TLB miss being processed."/>
+ <event event="0xe3" title="Stall" name="Pre-decode error" description="Attributable Performance Impact Event. Counts every cycle the DPU IQ is empty and there is a pre-decode error being processed."/>
+ <event event="0xe4" title="Stall" name="Interlock other" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is not because of an Advanced SIMD or Floating-point instruction, and not because of a load/store instruction waiting for data to calculate the address in the AGU. Stall cycles because of a stall in Wr, typically awaiting load data, are excluded."/>
+ <event event="0xe5" title="Stall" name="Interlock address" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is because of a load/store instruction waiting for data to calculate the address in the AGU. Stall cycles because of a stall in Wr, typically awaiting load data, are excluded."/>
+ <event event="0xe6" title="Stall" name="Interlock SIMD/FPU" description="Attributable Performance Impact Event. Counts every cycle there is an interlock that is because of an Advanced SIMD or Floating-point instruction. Stall cycles because of a stall in the Wr stage, typically awaiting load data, are excluded."/>
+ <event event="0xe7" title="Stall" name="Load miss" description="Attributable Performance Impact Event. Counts every cycle there is a stall in the Wr stage because of a load miss"/>
+ <event event="0xe8" title="Stall" name="Store" description="Attributable Performance Impact Event. Counts every cycle there is a stall in the Wr stage because of a store."/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A57.xml b/tools/gator/daemon/events-Cortex-A57.xml
new file mode 100644
index 0000000..1da23e7
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A57.xml
@@ -0,0 +1,87 @@
+ <counter_set name="ARM_Cortex-A57_cnt" count="6"/>
+ <category name="Cortex-A57" counter_set="ARM_Cortex-A57_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARM_Cortex-A57_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed (condition check pass) - Exception return"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed (condition check pass) - Write to CONTEXTIDR"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+ <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+ <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+ <event event="0x1b" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+ <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x1e" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+ <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+ <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+ <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+ <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+ <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+ <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+ <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+ <event event="0x4c" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill - Read"/>
+ <event event="0x4d" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill - Write"/>
+ <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+ <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+ <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+ <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+ <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+ <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+ <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+ <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+ <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+ <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+ <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+ <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+ <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+ <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+ <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+ <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+ <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+ <event event="0x6a" title="Memory" name="Unaligned" description="Unaligned access"/>
+ <event event="0x6c" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+ <event event="0x6d" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+ <event event="0x6e" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+ <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+ <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+ <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+ <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+ <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+ <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+ <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+ <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+ <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+ <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+ <event event="0x7a" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+ <event event="0x7c" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+ <event event="0x7d" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+ <event event="0x7e" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+ <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+ <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+ <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+ <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+ <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+ <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+ <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+ <event event="0x8a" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+ <event event="0x8b" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+ <event event="0x8c" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort, or SError not taken locally"/>
+ <event event="0x8d" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+ <event event="0x8e" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+ <event event="0x8f" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+ <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load-Acquire"/>
+ <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store-Release"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A7.xml b/tools/gator/daemon/events-Cortex-A7.xml
new file mode 100644
index 0000000..22fa9b7
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A7.xml
@@ -0,0 +1,44 @@
+ <counter_set name="ARMv7_Cortex_A7_cnt" count="4"/>
+ <category name="Cortex-A7" counter_set="ARMv7_Cortex_A7_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A7_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Software increment. The register is incremented only on writes to the Software Increment Register."/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at (at least) the lowest level of instruction or unified cache. Includes the speculative linefills in the count."/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at (at least) the lowest level of TLB. Includes the speculative requests in the count."/>
+ <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at (at least) the lowest level of data or unified cache. Counts the number of allocations performed in the Data Cache because of a read or a write."/>
+ <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at (at least) the lowest level of data or unified cache. This includes speculative reads."/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at (at least) the lowest level of TLB. This does not include micro TLB misses because of PLD, PLI, CP15 Cache operation by MVA and CP15 VA to PA operations."/>
+ <event event="0x06" title="Instruction" name="Memory Read" description="Data read architecturally executed. Counts the number of data read instructions accepted by the Load Store Unit. This includes counting the speculative and aborted LDR/LDM, and the reads because of the SWP instructions."/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. Counts the number of data write instructions accepted by the Load Store Unit. This includes counting the speculative and aborted STR/STM, and the writes because of the SWP instructions."/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken. Counts the number of exceptions architecturally taken."/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Change to ContextID retired. Counts the number of instructions architecturally executed writing into the ContextID Register."/>
+ <event event="0x0c" title="Branch" name="PC change" description="Software change of PC"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed (taken or not taken). This includes the branches which are flushed due to a previous load/store which aborts late."/>
+ <event event="0x0e" title="Procedure" name="Return" description="Procedure return (other than exception returns) architecturally executed"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned load-store"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted/not predicted. Counts the number of mispredicted or not-predicted branches executed. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in program flow that could have been predicted by the branch prediction resources of the processor. This includes the branches which are flushed because of a previous load/store which aborts late."/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Instruction Cache access"/>
+ <event event="0x15" title="Cache" name="L1 data eviction" description="Data cache eviction"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back. Data transfers made as a result of a coherency request from the Level 2 caches to outside of the Level 1 and Level 2 caches are not counted. Write-backs made as a result of CP15 cache maintenance operations are counted."/>
+ <event event="0x19" title="Bus" name="Access" description="Bus accesses. Single transfer bus accesses on either of the ACE read or write channels might increment twice in one cycle if both the read and write channels are active simultaneously. Operations that utilise the bus that do not explicitly transfer data, such as barrier or coherency operations are counted as bus accesses."/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x60" title="Bus" name="Read" description="Bus access, read"/>
+ <event event="0x61" title="Bus" name="Write" description="Bus access, write"/>
+ <event event="0x86" title="Exception" name="IRQ" description="IRQ exception taken"/>
+ <event event="0x87" title="Exception" name="FIQ" description="FIQ exception taken"/>
+ <event event="0xc0" title="Memory" name="External request" description="External memory request"/>
+ <event event="0xc1" title="Memory" name="Non-cacheable ext req" description="Non-cacheable external memory request"/>
+ <event event="0xc2" title="Cache" name="Linefill" description="Linefill because of prefetch"/>
+ <event event="0xc3" title="Cache" name="Linefill dropped" description="Prefetch linefill dropped"/>
+ <event event="0xc4" title="Cache" name="Allocate mode enter" description="Entering read allocate mode"/>
+ <event event="0xc5" title="Cache" name="Allocate mode" description="Read allocate mode"/>
+ <event event="0xc7" title="ETM" name="ETM Ext Out[0]" description="ETM Ext Out[0]"/>
+ <event event="0xc8" title="ETM" name="ETM Ext Out[1]" description="ETM Ext Out[1]"/>
+ <event event="0xc9" title="Instruction" name="Pipeline stall" description="Data Write operation that stalls the pipeline because the store buffer is full"/>
+ <event event="0xca" title="Memory" name="Snoop" description="Data snooped from other processor. This event counts memory-read operations that read data from another processor within the local Cortex-A7 cluster, rather than accessing the L2 cache or issuing an external read. It increments on each transaction, rather than on each beat of data."/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A72.xml b/tools/gator/daemon/events-Cortex-A72.xml
new file mode 100644
index 0000000..31c9cf3
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A72.xml
@@ -0,0 +1,87 @@
+ <counter_set name="ARM_Cortex_A72_cnt" count="6"/>
+ <category name="Cortex-A72" counter_set="ARM_Cortex_A72_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARM_Cortex_A72_ccnt" event="0x11" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache Write-Back"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache Write-Back"/>
+ <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+ <event event="0x1A" title="Memory" name="Error" description="Local memory error"/>
+ <event event="0x1B" title="Instruction" name="Speculative" description="Operation speculatively executed"/>
+ <event event="0x1C" title="Memory" name="Translation table" description="Instruction architecturally executed (condition check pass) - Write to translation table base"/>
+ <event event="0x1D" title="Bus" name="Cycle" description="Bus cycle"/>
+ <event event="0x1E" title="Counter chain" name="Odd Performance" description="Odd performance counter chain mode"/>
+ <event event="0x40" title="Cache" name="L1 data read" description="Level 1 data cache access - Read"/>
+ <event event="0x41" title="Cache" name="L1 data access write" description="Level 1 data cache access - Write"/>
+ <event event="0x42" title="Cache" name="L1 data refill read" description="Level 1 data cache refill - Read"/>
+ <event event="0x43" title="Cache" name="L1 data refill write" description="Level 1 data cache refill - Write"/>
+ <event event="0x46" title="Cache" name="L1 data victim" description="Level 1 data cache Write-back - Victim"/>
+ <event event="0x47" title="Cache" name="L1 data clean" description="Level 1 data cache Write-back - Cleaning and coherency"/>
+ <event event="0x48" title="Cache" name="L1 data invalidate" description="Level 1 data cache invalidate"/>
+ <event event="0x4C" title="Cache" name="L1 TLB refill read" description="Level 1 data TLB refill - Read"/>
+ <event event="0x4D" title="Cache" name="L1 TLB refill write" description="Level 1 data TLB refill - Write"/>
+ <event event="0x50" title="Cache" name="L2 data read" description="Level 2 data cache access - Read"/>
+ <event event="0x51" title="Cache" name="L2 data access write" description="Level 2 data cache access - Write"/>
+ <event event="0x52" title="Cache" name="L2 data refill read" description="Level 2 data cache refill - Read"/>
+ <event event="0x53" title="Cache" name="L2 data refill write" description="Level 2 data cache refill - Write"/>
+ <event event="0x56" title="Cache" name="L2 data victim" description="Level 2 data cache Write-back - Victim"/>
+ <event event="0x57" title="Cache" name="L2 data clean" description="Level 2 data cache Write-back - Cleaning and coherency"/>
+ <event event="0x58" title="Cache" name="L2 data invalidate" description="Level 2 data cache invalidate"/>
+ <event event="0x60" title="Bus" name="Read" description="Bus access - Read"/>
+ <event event="0x61" title="Bus" name="Write" description="Bus access - Write"/>
+ <event event="0x62" title="Bus" name="Access shared" description="Bus access - Normal"/>
+ <event event="0x63" title="Bus" name="Access not shared" description="Bus access - Not normal"/>
+ <event event="0x64" title="Bus" name="Access normal" description="Bus access - Normal"/>
+ <event event="0x65" title="Bus" name="Peripheral" description="Bus access - Peripheral"/>
+ <event event="0x66" title="Memory" name="Read" description="Data memory access - Read"/>
+ <event event="0x67" title="Memory" name="Write" description="Data memory access - Write"/>
+ <event event="0x68" title="Memory" name="Unaligned Read" description="Unaligned access - Read"/>
+ <event event="0x69" title="Memory" name="Unaligned Write" description="Unaligned access - Write"/>
+ <event event="0x6A" title="Memory" name="Unaligned" description="Unaligned access"/>
+ <event event="0x6C" title="Intrinsic" name="LDREX" description="Exclusive operation speculatively executed - LDREX"/>
+ <event event="0x6D" title="Intrinsic" name="STREX pass" description="Exclusive instruction speculatively executed - STREX pass"/>
+ <event event="0x6E" title="Intrinsic" name="STREX fail" description="Exclusive operation speculatively executed - STREX fail"/>
+ <event event="0x70" title="Instruction" name="Load" description="Operation speculatively executed - Load"/>
+ <event event="0x71" title="Instruction" name="Store" description="Operation speculatively executed - Store"/>
+ <event event="0x72" title="Instruction" name="Load/Store" description="Operation speculatively executed - Load or store"/>
+ <event event="0x73" title="Instruction" name="Integer" description="Operation speculatively executed - Integer data processing"/>
+ <event event="0x74" title="Instruction" name="Advanced SIMD" description="Operation speculatively executed - Advanced SIMD"/>
+ <event event="0x75" title="Instruction" name="VFP" description="Operation speculatively executed - VFP"/>
+ <event event="0x76" title="Instruction" name="Software change" description="Operation speculatively executed - Software change of the PC"/>
+ <event event="0x77" title="Instruction" name="Crypto" description="Operation speculatively executed, crypto data processing"/>
+ <event event="0x78" title="Branch" name="Immediate" description="Branch speculatively executed - Immediate branch"/>
+ <event event="0x79" title="Procedure" name="Return" description="Branch speculatively executed - Procedure return"/>
+ <event event="0x7A" title="Branch" name="Indirect" description="Branch speculatively executed - Indirect branch"/>
+ <event event="0x7C" title="Instruction" name="ISB" description="Barrier speculatively executed - ISB"/>
+ <event event="0x7D" title="Instruction" name="DSB" description="Barrier speculatively executed - DSB"/>
+ <event event="0x7E" title="Instruction" name="DMB" description="Barrier speculatively executed - DMB"/>
+ <event event="0x81" title="Exception" name="Undefined" description="Exception taken, other synchronous"/>
+ <event event="0x82" title="Exception" name="Supervisor" description="Exception taken, Supervisor Call"/>
+ <event event="0x83" title="Exception" name="Instruction abort" description="Exception taken, Instruction Abort"/>
+ <event event="0x84" title="Exception" name="Data abort" description="Exception taken, Data Abort or SError"/>
+ <event event="0x86" title="Interrupts" name="IRQ" description="Exception taken, IRQ"/>
+ <event event="0x87" title="Interrupts" name="FIQ" description="Exception taken, FIQ"/>
+ <event event="0x88" title="Exception" name="Secure monitor call" description="Exception taken, Secure Monitor Call"/>
+ <event event="0x8A" title="Exception" name="Hypervisor call" description="Exception taken, Hypervisor Call"/>
+ <event event="0x8B" title="Exception" name="Instruction abort non-local" description="Exception taken, Instruction Abort not taken locally"/>
+ <event event="0x8C" title="Exception" name="Data abort non-local" description="Exception taken, Data Abort or SError not taken locally"/>
+ <event event="0x8D" title="Exception" name="Other non-local" description="Exception taken - Other traps not taken locally"/>
+ <event event="0x8E" title="Exception" name="IRQ non-local" description="Exception taken, IRQ not taken locally"/>
+ <event event="0x8F" title="Exception" name="FIQ non-local" description="Exception taken, FIQ not taken locally"/>
+ <event event="0x90" title="Release Consistency" name="Load" description="Release consistency instruction speculatively executed - Load Acquire"/>
+ <event event="0x91" title="Release Consistency" name="Store" description="Release consistency instruction speculatively executed - Store Release"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A8.xml b/tools/gator/daemon/events-Cortex-A8.xml
new file mode 100644
index 0000000..7056efd
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A8.xml
@@ -0,0 +1,52 @@
+ <counter_set name="ARMv7_Cortex_A8_cnt" count="4"/>
+ <category name="Cortex-A8" counter_set="ARMv7_Cortex_A8_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A8_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill at the lowest level of instruction or unified cache. Each instruction fetch from normal cacheable memory that causes a refill from outside of the cache is counted. Accesses that do not cause a new cache refill, but are satisfied from refilling data of a previous miss are not counted. Where instruction fetches consist of multiple instructions, these accesses count as single events. CP15 cache maintenance operations do not count as events. This counter increments for speculative instruction fetches and for fetches of instructions that reach execution."/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill at the lowest level of TLB. Each instruction fetch that causes a translation table walk or an access to another level of TLB caching is counted. CP15 TLB maintenance operations do not count as events. This counter increments for speculative instruction fetches and for fetches of instructions that reach execution."/>
+ <event event="0x03" title="Cache" name="Data refill" description="Data read or write operation that causes a refill at the lowest level of data or unified cache. Each data read from or write to normal cacheable memory that causes a refill from outside of the cache is counted. Accesses that do not cause a new cache refill, but are satisfied from refilling data of a previous miss are not counted. Each access to a cache line to normal cacheable memory that causes a new linefill is counted, including the multiple transaction of instructions such as LDM or STM, PUSH and POP. Write-through writes that hit in the cache do not cause a linefill and so are not counted. CP15 cache maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+ <event event="0x04" title="Cache" name="Data access" description="Data read or write operation that causes a cache access at the lowest level of data or unified cache. Each access to a cache line to normal cacheable memory is counted including the multiple transaction of instructions such as LDM or STM. CP15 cache maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Data read or write operation that causes a TLB refill at the lowest level of TLB. Each data read or write operation that causes a translation table walk or an access to another level of TLB caching is counted. CP15 TLB maintenance operations do not count as events. This counter increments for speculative data accesses and for data accesses that are explicitly made by instructions."/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Data read architecturally executed. This counter increments for every instruction that explicitly read data, including SWP. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Data write architecturally executed. The counter increments for every instruction that explicitly wrote data, including SWP. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed. This counter counts for all instructions, including conditional instructions that fail their condition codes."/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken. This counts for each exception taken."/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the Context ID Register architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x0c" title="Branch" name="PC change" description="Software change of PC, except by an exception, architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed, taken or not taken. This includes B{L}, BLX, CB{N}Z, HB{L}, and HBLP. This counter counts for all immediate branch instructions that are architecturally executed, including conditional instructions that fail their condition codes."/>
+ <event event="0x0e" title="Procedure" name="Return" description="Procedure return, other than exception returns, architecturally executed. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed. This counts each instruction that is an access to an unaligned address. This counter only increments for instructions that are unconditional or that pass their condition codes."/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted. This counts for every pipeline flush because of a misprediction from the program flow prediction resources."/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branches or other change in the program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x40" title="Cache" name="Write buffer full" description="Any write buffer full cycle"/>
+ <event event="0x41" title="Cache" name="L2 store" description="Any store that is merged in the L2 memory system"/>
+ <event event="0x42" title="Cache" name="Bufferable transaction" description="Any bufferable store transaction from load/store to L2 cache, excluding eviction or cast out data"/>
+ <event event="0x43" title="Cache" name="L2 access" description="Any accesses to the L2 cache"/>
+ <event event="0x44" title="Cache" name="L2 miss" description="Any cacheable miss in the L2 cache"/>
+ <event event="0x45" title="AXI" name="Read" description="The number of AXI read data transfers"/>
+ <event event="0x46" title="AXI" name="Write" description="The number of AXI write data transfers"/>
+ <event event="0x47" title="Memory" name="Replay event" description="Any replay event in the memory system"/>
+ <event event="0x48" title="Memory" name="Unaligned access replay" description="Any unaligned memory access that results in a replay"/>
+ <event event="0x49" title="Cache" name="L1 data hash miss" description="Any L1 data memory access that misses in the cache as a result of the hashing algorithm. The cases covered are: hash hit and physical address miss, hash hit and physical address hit in another way and hash miss and physical address hit."/>
+ <event event="0x4a" title="Cache" name="L1 inst hash miss" description="Any L1 instruction memory access that misses in the cache as a result of the hashing algorithm. The cases covered are: hash hit and physical address miss, hash hit and physical address hit in another way and hash miss and physical address hit."/>
+ <event event="0x4b" title="Cache" name="L1 page coloring" description="Any L1 data memory access in which a page coloring alias occurs. alias = virtual address [12] ! = physical address [12]. This behavior results in a data memory eviction or cast out."/>
+ <event event="0x4c" title="NEON" name="L1 cache hit" description="Any NEON access that hits in the L1 data cache"/>
+ <event event="0x4d" title="NEON" name="L1 cache access" description="Any NEON cacheable data accesses for L1 data cache"/>
+ <event event="0x4e" title="NEON" name="L2 cache access" description="Any L2 cache accesses as a result of a NEON memory access"/>
+ <event event="0x4f" title="NEON" name="L2 cache hit" description="Any NEON hit in the L2 cache"/>
+ <event event="0x50" title="Cache" name="L1 inst access" description="Any L1 instruction cache access, excluding CP15 cache accesses"/>
+ <event event="0x51" title="Branch" name="Return stack misprediction" description="Any return stack misprediction because of incorrect target address for a taken return stack pop"/>
+ <event event="0x52" title="Branch" name="Direction misprediction" description="Two forms of branch direction misprediction: branch predicted taken, but was not taken and branch predicted not taken, but was taken"/>
+ <event event="0x53" title="Branch" name="Taken prediction" description="Any predictable branch that is predicted to be taken"/>
+ <event event="0x54" title="Branch" name="Executed and taken prediction" description="Any predictable branch that is executed and taken"/>
+ <event event="0x55" title="Core" name="Operations issued" description="Number of operations issued, where an operation is either: an instruction or one operation in a sequence of operations that make up a multi-cycle instruction"/>
+ <event event="0x56" title="Core" name="No issue cycles" description="Increment for every cycle that no instructions are available for issue"/>
+ <event event="0x57" title="Core" name="Issue cycles" description="For every cycle, this event counts the number of instructions issued in that cycle. Multi-cycle instructions are only counted once."/>
+ <event event="0x58" title="NEON" name="MRC data wait" description="Number of cycles the processor stalls waiting on MRC data from NEON"/>
+ <event event="0x59" title="NEON" name="Full queue" description="Number of cycles that the processor stalls as a result of a full NEON instruction queue or NEON load queue"/>
+ <event event="0x5a" title="NEON" name="Idle" description="Number of cycles that NEON and integer processors are both not idle"/>
+ <event event="0x70" title="External" name="PMUEXTIN[0]" description="Counts any event from external input source PMUEXTIN[0]"/>
+ <event event="0x71" title="External" name="PMUEXTIN[1]" description="Counts any event from external input source PMUEXTIN[1]"/>
+ <event event="0x72" title="External" name="PMUEXTIN[0,1]" description="Counts any event from both external input sources PMUEXTIN[0] and PMUEXTIN[1]"/>
+ </category>
diff --git a/tools/gator/daemon/events-Cortex-A9.xml b/tools/gator/daemon/events-Cortex-A9.xml
new file mode 100644
index 0000000..e17c03d
--- /dev/null
+++ b/tools/gator/daemon/events-Cortex-A9.xml
@@ -0,0 +1,65 @@
+ <counter_set name="ARMv7_Cortex_A9_cnt" count="6"/>
+ <category name="Cortex-A9" counter_set="ARMv7_Cortex_A9_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ARMv7_Cortex_A9_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+ <event event="0x0c" title="Branch" name="PC change" description="Software change of the Program Counter, except by an exception, architecturally executed"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x40" title="Java" name="Bytecode execute" description="Counts the number of Java bytecodes being decoded, including speculative ones"/>
+ <event event="0x41" title="Java" name="SW bytecode execute" description="Counts the number of software Java bytecodes being decoded, including speculative ones"/>
+ <event event="0x42" title="Jazelle" name="Backward branch execute" description="Counts the number of Jazelle taken branches being executed. This includes the branches that are flushed because of a previous load/store that aborts late."/>
+ <event event="0x50" title="Cache" name="Coherency miss" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor that also miss in all the other Cortex-A9 processors. This means that the request is sent to the external memory."/>
+ <event event="0x51" title="Cache" name="Coherency hit" description="Counts the number of coherent linefill requests performed by the Cortex-A9 processor that hit in another Cortex-A9 processor. This means that the linefill data is fetched directly from the relevant Cortex-A9 cache."/>
+ <event event="0x60" title="Cache" name="Inst dependent stall" description="Counts the number of cycles where the processor: is ready to accept new instructions, does not receive a new instruction, because: the instruction side is unable to provide one or the instruction cache is performing at least one linefill"/>
+ <event event="0x61" title="Cache" name="Data dependent stall" description="Counts the number of cycles where the processor has some instructions that it cannot issue to any pipeline, and the Load Store unit has at least one pending linefill request, and no pending TLB requests"/>
+ <event event="0x62" title="Cache" name="TLB stall" description="Counts the number of cycles where the processor is stalled waiting for the completion of translation table walks from the main TLB. The processor stalls because the instruction side is not able to provide the instructions, or the data side is not able to provide the necessary data."/>
+ <event event="0x63" title="Intrinsic" name="STREX pass" description="Counts the number of STREX instructions architecturally executed and passed"/>
+ <event event="0x64" title="Intrinsic" name="STREX fail" description="Counts the number of STREX instructions architecturally executed and failed"/>
+ <event event="0x65" title="Cache" name="Data eviction" description="Counts the number of eviction requests because of a linefill in the data cache"/>
+ <event event="0x66" title="Pipeline" name="Issue stage no dispatch" description="Counts the number of cycles where the issue stage does not dispatch any instruction because it is empty or cannot dispatch any instructions"/>
+ <event event="0x67" title="Pipeline" name="Issue stage empty" description="Counts the number of cycles where the issue stage is empty"/>
+ <event event="0x68" title="Instruction" name="Executed" description="Counts the number of instructions going through the Register Renaming stage. This number is an approximate number of the total number of instructions speculatively executed, and an even more approximate number of the total number of instructions architecturally executed. The approximation depends mainly on the branch misprediction rate."/>
+ <event event="0x69" title="Cache" name="Data linefills" description="Counts the number of linefills performed on the external AXI bus. This event counts all data linefill requests, caused by: loads, including speculative ones, stores, PLD, prefetch or page table walk."/>
+ <event event="0x6a" title="Cache" name="Prefetch linefills" description="Counts the number of data linefills caused by prefetcher requests"/>
+ <event event="0x6b" title="Cache" name="Prefetch hits" description="Counts the number of cache hits in a line that belongs to a stream followed by the prefetcher. This includes: lines that have been prefetched by the automatic data prefetcher and lines already present in the cache, before the prefetcher action."/>
+ <event event="0x6e" title="Procedure" name="Return" description="Counts the number of procedure returns whose condition codes do not fail, excluding all returns from exception. This count includes procedure returns that are flushed because of a previous load/store that aborts late."/>
+ <event event="0x70" title="Instruction" name="Main execution unit" description="Counts the number of instructions being executed in the main execution pipeline of the processor, the multiply pipeline and arithmetic logic unit pipeline. The counted instructions are still speculative."/>
+ <event event="0x71" title="Instruction" name="Second execution unit" description="Counts the number of instructions being executed in the processor second execution pipeline (ALU). The counted instructions are still speculative."/>
+ <event event="0x72" title="Instruction" name="Load/Store" description="Counts the number of instructions being executed in the Load/Store unit. The counted instructions are still speculative."/>
+ <event event="0x73" title="Instruction" name="Floating point" description="Counts the number of floating-point instructions going through the Register Rename stage. Instructions are still speculative in this stage."/>
+ <event event="0x74" title="Instruction" name="NEON" description="Counts the number of NEON instructions going through the Register Rename stage. Instructions are still speculative in this stage."/>
+ <event event="0x80" title="Stalls" name="PLD" description="Counts the number of cycles where the processor is stalled because PLD slots are all full"/>
+ <event event="0x81" title="Stalls" name="Memory write" description="Counts the number of cycles when the processor is stalled. The data side is stalled also, because it is full and executes writes to the external memory."/>
+ <event event="0x82" title="Stalls" name="Inst main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the instruction side"/>
+ <event event="0x83" title="Stalls" name="Data main TLB miss" description="Counts the number of stall cycles because of main TLB misses on requests issued by the data side"/>
+ <event event="0x84" title="Stalls" name="Inst micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the instruction side. This event does not include main TLB miss stall cycles that are already counted in the corresponding main TLB event."/>
+ <event event="0x85" title="Stalls" name="Data micro TLB miss" description="Counts the number of stall cycles because of micro TLB misses on the data side. This event does not include main TLB miss stall cycles that are already counted in the corresponding main TLB event."/>
+ <event event="0x86" title="Stalls" name="DMB" description="Counts the number of stall cycles because of the execution of a DMB. This includes all DMB instructions being executed, even speculatively."/>
+ <event event="0x8a" title="Clock" name="Integer core" description="Counts the number of cycles when the integer core clock is enabled"/>
+ <event event="0x8b" title="Clock" name="Data engine" description="Counts the number of cycles when the data engine clock is enabled"/>
+ <event event="0x8c" title="Clock" name="NEON" description="Counts the number of cycles when the NEON SIMD clock is enabled"/>
+ <event event="0x8d" title="Memory" name="TLB inst allocations" description="Counts the number of TLB allocations because of Instruction requests"/>
+ <event event="0x8e" title="Memory" name="TLB data allocations" description="Counts the number of TLB allocations because of Data requests"/>
+ <event event="0x90" title="Instruction" name="ISB" description="Counts the number of ISB instructions architecturally executed"/>
+ <event event="0x91" title="Instruction" name="DSB" description="Counts the number of DSB instructions architecturally executed"/>
+ <event event="0x92" title="Instruction" name="DMB" description="Counts the number of DMB instructions speculatively executed"/>
+ <event event="0x93" title="External" name="Interrupts" description="Counts the number of external interrupts executed by the processor"/>
+ <event event="0xa0" title="PLE" name="Cache line rq completed" description="Counts the number of PLE cache line requests completed"/>
+ <event event="0xa1" title="PLE" name="Cache line rq skipped" description="Counts the number of PLE cache line requests skipped"/>
+ <event event="0xa2" title="PLE" name="FIFO flush" description="Counts the number of PLE FIFO flush requests"/>
+ <event event="0xa3" title="PLE" name="Request completed" description="Counts the number of PLE FIFO flush completed"/>
+ <event event="0xa4" title="PLE" name="FIFO overflow" description="Counts the number of PLE FIFO flush overflowed"/>
+ <event event="0xa5" title="PLE" name="Request programmed" description="Counts the number of PLE FIFO flush program requests"/>
+ </category>
diff --git a/tools/gator/daemon/events-Filesystem.xml b/tools/gator/daemon/events-Filesystem.xml
new file mode 100644
index 0000000..1fa3b3b
--- /dev/null
+++ b/tools/gator/daemon/events-Filesystem.xml
@@ -0,0 +1,10 @@
+ <category name="Filesystem">
+ <!-- counter attribute must start with filesystem_ and be unique -->
+ <!-- regex item in () is the value shown or, if the parentheses are missing, the number of times the regex matches is counted -->
+ <!--
+ <event counter="filesystem_loginuid" path="/proc/self/loginuid" title="loginuid" name="loginuid" class="absolute" description="loginuid"/>
+ <event counter="filesystem_gatord_rss" path="/proc/self/stat" title="stat" name="rss" class="absolute" regex="-?[0-9]+ \(.*\) . -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ -?[0-9]+ (-?[0-9]+)" units="pages" description="resident set size"/>
+ <event counter="filesystem_processes" path="/proc/stat" title="proc-stat" name="processes" class="absolute" regex="processes ([0-9]+)" description="Number of processes and threads created"/>
+ <event counter="filesystem_context_switches" path="/proc/stat" title="proc-stat" name="context switches" class="absolute" regex="ctxt ([0-9]+)" description="Number of processes and threads created"/>
+ -->
+ </category>
diff --git a/tools/gator/daemon/events-Krait-architected.xml b/tools/gator/daemon/events-Krait-architected.xml
new file mode 100644
index 0000000..b8d3bcb
--- /dev/null
+++ b/tools/gator/daemon/events-Krait-architected.xml
@@ -0,0 +1,22 @@
+ <counter_set name="Krait_cnt" count="4"/>
+ <category name="Krait" counter_set="Krait_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="Krait_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+ <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+ <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ </category>
diff --git a/tools/gator/daemon/events-L2C-310.xml b/tools/gator/daemon/events-L2C-310.xml
new file mode 100644
index 0000000..055847c
--- /dev/null
+++ b/tools/gator/daemon/events-L2C-310.xml
@@ -0,0 +1,18 @@
+ <counter_set name="L2C-310_cnt" count="2"/>
+ <category name="L2C-310" counter_set="L2C-310_cnt" per_cpu="no">
+ <event event="0x1" title="L2 Cache" name="CastOUT" description="Eviction, CastOUT, of a line from the L2 cache"/>
+ <event event="0x2" title="L2 Cache" name="Data Read Hit" description="Data read hit in the L2 cache"/>
+ <event event="0x3" title="L2 Cache" name="Data Read Request" description="Data read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+ <event event="0x4" title="L2 Cache" name="Data Write Hit" description="Data write hit in the L2 cache"/>
+ <event event="0x5" title="L2 Cache" name="Data Write Request" description="Data write lookup to the L2 cache. Subsequently results in a hit or miss"/>
+ <event event="0x6" title="L2 Cache" name="Data Write-Through Request" description="Data write lookup to the L2 cache with Write-Through attribute. Subsequently results in a hit or miss"/>
+ <event event="0x7" title="L2 Cache" name="Instruction Read Hit" description="Instruction read hit in the L2 cache"/>
+ <event event="0x8" title="L2 Cache" name="Instruction Read Request" description="Instruction read lookup to the L2 cache. Subsequently results in a hit or miss"/>
+ <event event="0x9" title="L2 Cache" name="Write Allocate Miss" description="Allocation into the L2 cache caused by a write, with Write-Allocate attribute, miss"/>
+ <event event="0xa" title="L2 Cache" name="Internal Prefetch Allocate" description="Allocation of a prefetch generated by L2C-310 into the L2 cache"/>
+ <event event="0xb" title="L2 Cache" name="Prefetch Hit" description="Prefetch hint hits in the L2 cache"/>
+ <event event="0xc" title="L2 Cache" name="Prefetch Allocate" description="Prefetch hint allocated into the L2 cache"/>
+ <event event="0xd" title="L2 Cache" name="Speculative Read Received" description="Speculative read received"/>
+ <event event="0xe" title="L2 Cache" name="Speculative Read Confirmed" description="Speculative read confirmed"/>
+ <event event="0xf" title="L2 Cache" name="Prefetch Hint Received" description="Prefetch hint received"/>
+ </category>
diff --git a/tools/gator/daemon/events-Linux.xml b/tools/gator/daemon/events-Linux.xml
new file mode 100644
index 0000000..0350c0c4
--- /dev/null
+++ b/tools/gator/daemon/events-Linux.xml
@@ -0,0 +1,17 @@
+ <category name="Linux">
+ <event counter="Linux_irq_softirq" title="Interrupts" name="SoftIRQ" per_cpu="yes" description="Linux SoftIRQ taken"/>
+ <event counter="Linux_irq_irq" title="Interrupts" name="IRQ" per_cpu="yes" description="Linux IRQ taken"/>
+ <event counter="Linux_block_rq_wr" title="Disk I/O" name="Write" units="B" description="Disk I/O Bytes Written"/>
+ <event counter="Linux_block_rq_rd" title="Disk I/O" name="Read" units="B" description="Disk I/O Bytes Read"/>
+ <event counter="Linux_net_rx" title="Network" name="Receive" units="B" description="Receive network traffic, including effect from Streamline"/>
+ <event counter="Linux_net_tx" title="Network" name="Transmit" units="B" description="Transmit network traffic, including effect from Streamline"/>
+ <event counter="Linux_sched_switch" title="Scheduler" name="Switch" per_cpu="yes" description="Context switch events"/>
+ <event counter="Linux_meminfo_memused" title="Memory" name="Used" class="absolute" units="B" proc="yes" description="Total used memory size. Note: a process' used memory includes shared memory that may be counted more than once (equivalent to RES from top). Kernel threads are not filterable."/>
+ <event counter="Linux_meminfo_memused2" title="Memory" name="Used" class="absolute" units="B" description="Total used memory size"/>
+ <event counter="Linux_meminfo_memfree" title="Memory" name="Free" class="absolute" display="minimum" units="B" description="Available memory size"/>
+ <event counter="Linux_meminfo_bufferram" title="Memory" name="Buffer" class="absolute" units="B" description="Memory used by OS disk buffers"/>
+ <event counter="Linux_power_cpu_freq" title="Clock" name="Frequency" per_cpu="yes" class="absolute" units="Hz" series_composition="overlay" average_cores="yes" description="Frequency setting of the CPU"/>
+ <event counter="Linux_cpu_wait_contention" title="CPU Contention" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" multiplier="0.0001" color="0x003c96fb" description="One or more threads are runnable but waiting due to CPU contention"/>
+ <event counter="Linux_cpu_wait_io" title="CPU I/O" name="Wait" per_cpu="no" class="activity" derived="yes" rendering_type="bar" average_selection="yes" percentage="yes" multiplier="0.0001" color="0x00b30000" description="One or more threads are blocked on an I/O resource"/>
+ <event counter="Linux_power_cpu" title="CPU Status" name="Activity" class="activity" activity1="Off" activity_color1="0x0000ff00" activity2="WFI" activity_color2="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="CPU Status"/>
+ </category>
diff --git a/tools/gator/daemon/events-Mali-4xx.xml b/tools/gator/daemon/events-Mali-4xx.xml
new file mode 100644
index 0000000..801dd28
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-4xx.xml
@@ -0,0 +1,245 @@
+ <counter_set name="ARM_Mali-4xx_VP_0_cnt" count="2"/>
+ <counter_set name="ARM_Mali-4xx_SW_cnt" count="0"/>
+ <category name="Mali Vertex Processor" counter_set="ARM_Mali-4xx_VP_0_cnt" per_cpu="no">
+ <event event="0x01" title="Mali-4xx VP" name="Active cycles" description="Number of cycles per frame the MaliGP2 was active."/>
+ <event event="0x02" title="Mali-4xx VP" name="Active cycles, vertex shader" description="Number of cycles per frame the vertex shader unit was active."/>
+ <event event="0x03" title="Mali-4xx VP" name="Active cycles, vertex storer" description="Number of cycles per frame the vertex storer unit was active."/>
+ <event event="0x04" title="Mali-4xx VP" name="Active cycles, vertex loader" description="Number of cycles per frame the vertex loader unit was active."/>
+ <event event="0x05" title="Mali-4xx VP" name="Cycles vertex loader waiting for vertex shader" description="Number of cycles per frame the vertex loader was idle while waiting on the vertex shader."/>
+ <event event="0x06" title="Mali-4xx VP" name="Words read, system bus" description="Total number of 64 bit words read by the GP2 from the system bus per frame."/>
+ <event event="0x07" title="Mali-4xx VP" name="Words written, system bus" description="Total number of 64 bit words written by the GP2 to the system bus per frame."/>
+ <event event="0x08" title="Mali-4xx VP" name="Read bursts, system bus" description="Number of read bursts by the GP2 from the system bus per frame."/>
+ <event event="0x09" title="Mali-4xx VP" name="Write bursts, system bus" description="Number of write bursts from the MaliGP2 to the system bus per frame."/>
+ <event event="0x0a" title="Mali-4xx VP" name="Vertices processed" description="Number of vertices processed by the MaliGP2 per frame."/>
+ <event event="0x0b" title="Mali-4xx VP" name="Vertices fetched" description="Number of vertices fetched by the MaliGP2 per frame."/>
+ <event event="0x0c" title="Mali-4xx VP" name="Primitives fetched" description="Number of graphics primitives fetched by the MaliGP2 per frame."/>
+ <event event="0x0e" title="Mali-4xx VP" name="Primitives culled" description="Number of graphics primitives discarded per frame, because they were seen from the back or were offscreen."/>
+ <event event="0x0f" title="Mali-4xx VP" name="Commands written to tiles" description="Number of commands (8 Bytes, mainly primitives) written by GP2 to the PP input data structure per frame."/>
+ <event event="0x10" title="Mali-4xx VP" name="Memory blocks allocated" description="Number of overflow data blocks needed for outputting the PP input data structure per frame ."/>
+ <event event="0x13" title="Mali-4xx VP" name="Vertex loader cache misses" description="Number of cache misses for the vertex shader's vertex input unit per frame."/>
+ <event event="0x16" title="Mali-4xx VP" name="Active cycles, vertex shader command processor" description="Number of cycles per frame the GP2 vertex shader command processor was active. This includes time waiting for semaphores."/>
+ <event event="0x17" title="Mali-4xx VP" name="Active cycles, PLBU command processor" description="Number of cycles per frame the MaliGP2 PLBU command processor was active. This includes time waiting for semaphores."/>
+ <event event="0x18" title="Mali-4xx VP" name="Active Cycles, PLBU list writer" description="Number of cycles per frame the MaliGP2 PLBU output unit was active. This includes time spent waiting on the bus."/>
+ <event event="0x19" title="Mali-4xx VP" name="Active cycles, PLBU geometry processing" description="Number of cycles per frame the MaliGP2 PLBU was active, excepting final data output. In other words: active cycles through the prepare list commands. This includes time spent waiting on the bus."/>
+ <event event="0x1b" title="Mali-4xx VP" name="Active cycles, PLBU primitive assembly" description="Number of active cycles per frame spent by the MaliGP2 PLBU doing primitive assembly. This does not include scissoring or final output. This includes time spent waiting on the bus."/>
+ <event event="0x1c" title="Mali-4xx VP" name="Active cycles, PLBU vertex fetcher" description="Number of active cycles per frame spent by the MaliGP2 PLBU fetching vertex data. This includes time spent waiting on the bus."/>
+ <event event="0x1e" title="Mali-4xx VP" name="Active cycles, Bounding-box and command generator" description="Number of active cycles per frame spent by the MaliGP2 PLBU setting up bounding boxes and commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+ <event event="0x20" title="Mali-4xx VP" name="Active cycles, Scissor tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over tiles to perform scissoring. This includes time spent waiting on the bus."/>
+ <event event="0x21" title="Mali-4xx VP" name="Active cycles, PLBU tile iterator" description="Number of active cycles per frame spent by the MaliGP2 PLBU iterating over the tiles in the bounding box generating commands (mainly graphics primitives). This includes time spent waiting on the bus."/>
+ </category>
+ <category name="Mali Fragment Processor" per_cpu="no">
+ <counter_set name="ARM_Mali-4xx_FP_0_cnt" title="Mali-4xx FP0" description="Mali GPU Fragment Processor 0" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_1_cnt" title="Mali-4xx FP1" description="Mali GPU Fragment Processor 1" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_2_cnt" title="Mali-4xx FP2" description="Mali GPU Fragment Processor 2" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_3_cnt" title="Mali-4xx FP3" description="Mali GPU Fragment Processor 3" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_4_cnt" title="Mali-4xx FP4" description="Mali GPU Fragment Processor 4" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_5_cnt" title="Mali-4xx FP5" description="Mali GPU Fragment Processor 5" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_6_cnt" title="Mali-4xx FP6" description="Mali GPU Fragment Processor 6" count="2"/>
+ <counter_set name="ARM_Mali-4xx_FP_7_cnt" title="Mali-4xx FP7" description="Mali GPU Fragment Processor 7" count="2"/>
+ <event event="0x00" title="Mali-4xx FP" name="Active clock cycles" description="Active clock cycles, between polygon start and IRQ."/>
+ <event event="0x02" title="Mali-4xx FP" name="Total bus reads" description="Total number of 64-bit words read from the bus."/>
+ <event event="0x03" title="Mali-4xx FP" name="Total bus writes" description="Total number of 64-bit words written to the bus."/>
+ <event event="0x04" title="Mali-4xx FP" name="Bus read request cycles" description="Number of cycles during which the bus read request signal was HIGH."/>
+ <event event="0x05" title="Mali-4xx FP" name="Bus write request cycles" description="Number of cycles during which the bus write request signal was HIGH."/>
+ <event event="0x06" title="Mali-4xx FP" name="Bus read transactions count" description="Number of read requests accepted by the bus."/>
+ <event event="0x07" title="Mali-4xx FP" name="Bus write transactions" description="Number of write requests accepted by the bus."/>
+ <event event="0x09" title="Mali-4xx FP" name="Tile writeback writes" description="64-bit words written to the bus by the writeback unit."/>
+ <event event="0x0a" title="Mali-4xx FP" name="Store unit writes" description="64-bit words written to the bus by the store unit."/>
+ <event event="0x0d" title="Mali-4xx FP" name="Texture cache uncompressed reads" description="Number of 64-bit words read from the bus into the uncompressed textures cache."/>
+ <event event="0x0e" title="Mali-4xx FP" name="Polygon list reads" description="Number of 64-bit words read from the bus by the polygon list reader."/>
+ <event event="0x0f" title="Mali-4xx FP" name="RSW reads" description="Number of 64-bit words read from the bus into the Render State Word register."/>
+ <event event="0x10" title="Mali-4xx FP" name="Vertex cache reads" description="Number of 64-bit words read from the bus into the vertex cache."/>
+ <event event="0x11" title="Mali-4xx FP" name="Uniform remapping reads" description="Number of 64-bit words read from the bus when reading from the uniform remapping table."/>
+ <event event="0x12" title="Mali-4xx FP" name="Program cache reads" description="Number of 64-bit words read from the bus into the fragment shader program cache."/>
+ <event event="0x13" title="Mali-4xx FP" name="Varying reads" description="Number of 64-bit words containing varyings generated by the vertex processing read from the bus."/>
+ <event event="0x14" title="Mali-4xx FP" name="Texture descriptors reads" description="Number of 64-bit words containing texture descriptors read from the bus."/>
+ <event event="0x15" title="Mali-4xx FP" name="Texture descriptor remapping reads" description="Number of 64-bit words read from the bus when reading from the texture descriptor remapping table."/>
+ <event event="0x17" title="Mali-4xx FP" name="Load unit reads" description="Number of 64-bit words read from the bus by the LOAD sub-instruction."/>
+ <event event="0x18" title="Mali-4xx FP" name="Polygon count" description="Number of triangles read from the polygon list."/>
+ <event event="0x19" title="Mali-4xx FP" name="Pixel rectangle count" description="Number of pixel rectangles read from the polygon list."/>
+ <event event="0x1a" title="Mali-4xx FP" name="Lines count" description="Number of lines read from the polygon list."/>
+ <event event="0x1b" title="Mali-4xx FP" name="Points count" description="Number of points read from the polygon list."/>
+ <event event="0x1c" title="Mali-4xx FP" name="Stall cycles PolygonListReader" description="Number of clock cycles the Polygon List Reader waited for output being collected."/>
+ <event event="0x1d" title="Mali-4xx FP" name="Stall cycles triangle setup" description="Number of clock cycles the TSC waited for input."/>
+ <event event="0x1e" title="Mali-4xx FP" name="Quad rasterized count" description="Number of 2x?2 quads output from rasterizer."/>
+ <event event="0x1f" title="Mali-4xx FP" name="Fragment rasterized count" description="Number of fragment rasterized. Fragments/(Quads*4) gives average actual fragments per quad."/>
+ <event event="0x20" title="Mali-4xx FP" name="Fragment rejected fragment-kill count" description="Number of fragments exiting the fragment shader as killed."/>
+ <event event="0x21" title="Mali-4xx FP" name="Fragment rejected fwd-fragment-kill count" description="Number of fragments killed by forward fragment kill."/>
+ <event event="0x22" title="Mali-4xx FP" name="Fragment passed z/stencil count" description="Number of fragments passing Z and stencil test."/>
+ <event event="0x23" title="Mali-4xx FP" name="Patches rejected early z/stencil count" description="Number of patches rejected by EarlyZ. A patch can be 8x8, 4x4 or 2x2 pixels."/>
+ <event event="0x24" title="Mali-4xx FP" name="Patches evaluated" description="Number of patches evaluated for EarlyZ rejection."/>
+ <event event="0x25" title="Mali-4xx FP" name="Instruction completed count" description="Number of fragment shader instruction words completed. It is a function of pixels processed and the length of the shader programs."/>
+ <event event="0x26" title="Mali-4xx FP" name="Instruction failed rendezvous count" description="Number of fragment shader instructions not completed because of failed Rendezvous."/>
+ <event event="0x27" title="Mali-4xx FP" name="Instruction failed varying-miss count" description="Number of fragment shader instructions not completed because of failed varying operation."/>
+ <event event="0x28" title="Mali-4xx FP" name="Instruction failed texture-miss count" description="Number of fragment shader instructions not completed because of failed texture operation."/>
+ <event event="0x29" title="Mali-4xx FP" name="Instruction failed load-miss count" description="Number of fragment shader instructions not completed because of failed load operation."/>
+ <event event="0x2a" title="Mali-4xx FP" name="Instruction failed tile read-miss count" description="Number of fragment shader instructions not completed because of failed read from the tilebuffer."/>
+ <event event="0x2b" title="Mali-4xx FP" name="Instruction failed store-miss count" description="Number of fragment shader instructions not completed because of failed store operation."/>
+ <event event="0x2c" title="Mali-4xx FP" name="Rendezvous breakage count" description="Number of Rendezvous breakages reported."/>
+ <event event="0x2d" title="Mali-4xx FP" name="Pipeline bubbles cycle count" description="Number of unused cycles in the fragment shader while rendering is active."/>
+ <event event="0x2e" title="Mali-4xx FP" name="Texture mapper multipass count" description="Number of texture operations looped because of more texture passes needed."/>
+ <event event="0x2f" title="Mali-4xx FP" name="Texture mapper cycle count" description="Number of texture operation cycles."/>
+ <event event="0x30" title="Mali-4xx FP" name="Vertex cache hit count" description="Number of times a requested vertex was found in the cache (Number of vertex cache hits)."/>
+ <event event="0x31" title="Mali-4xx FP" name="Vertex cache miss count" description="Number of times a requested vertex was not found in the cache (Number of vertex cache misses)."/>
+ <event event="0x32" title="Mali-4xx FP" name="Varying cache hit count" description="Number of times a requested varying was found in the cache (Number of varying cache hits)."/>
+ <event event="0x33" title="Mali-4xx FP" name="Varying cache miss count" description="Number of times a requested varying was not found in the cache (Number of varying cache misses)."/>
+ <event event="0x34" title="Mali-4xx FP" name="Varying cache conflict miss count" description="Number of times a requested varying was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+ <event event="0x35" title="Mali-4xx FP" name="Texture cache hit count" description="Number of times a requested texel was found in the texture cache (Number of texture cache hits)."/>
+ <event event="0x36" title="Mali-4xx FP" name="Texture cache miss count" description="Number of times a requested texel was not found in the texture cache (Number of texture cache misses)."/>
+ <event event="0x37" title="Mali-4xx FP" name="Texture cache conflict miss count" description="Number of times a requested texel was not in the cache and its value, retrieved from memory, must overwrite an older cache entry. This happens when an access pattern cannot be serviced by the cache."/>
+ <event event="0x38" title="Mali-4xx FP" name="Compressed texture cache hit count" description="Number of times a requested item was found in the cache."/>
+ <event event="0x39" title="Mali-4xx FP" name="Compressed texture cache miss count" description="Number of times a requested item was not found in the cache."/>
+ <event event="0x3a" title="Mali-4xx FP" name="Load/Store cache hit count" description="Number of hits in the load/store cache."/>
+ <event event="0x3b" title="Mali-4xx FP" name="Load/Store cache miss count" description="Number of misses in the load/store cache."/>
+ <event event="0x3c" title="Mali-4xx FP" name="Program cache hit count" description="Number of hits in the program cache."/>
+ <event event="0x3d" title="Mali-4xx FP" name="Program cache miss count" description="Number of misses in the program cache."/>
+ </category>
+ <counter_set name="ARM_Mali-4xx_L2_0_cnt" title="Mali-4xx L2" description="Mali GPU L2 Cache Core 0" count="2"/>
+ <category name="Mali-4xx L2" counter_set="ARM_Mali-4xx_L2_0_cnt" per_cpu="no">
+ <event event="0x01" title="Mali L2 Cache" name="Total clock cycles" description="Total clock cycles"/>
+ <event event="0x02" title="Mali L2 Cache" name="Active clock cycles" description="Active clock cycles"/>
+ <option_set name="All">
+ <option event_delta="0x08" name="Master" description="Master"/>
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <option_set name="Slaves">
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <event event="0x00" option_set="All" title="Mali L2 Cache" name="Read transactions" description="Read transactions"/>
+ <event event="0x01" option_set="All" title="Mali L2 Cache" name="Write transactions" description="Write transactions"/>
+ <event event="0x02" option_set="All" title="Mali L2 Cache" name="Words read" description="Words read"/>
+ <event event="0x03" option_set="All" title="Mali L2 Cache" name="Words written" description="Words written"/>
+ <event event="0x04" option_set="Slaves" title="Mali L2 Cache" name="Read hits" description="Read hits"/>
+ <event event="0x05" option_set="Slaves" title="Mali L2 Cache" name="Read misses" description="Read misses"/>
+ <event event="0x06" option_set="Slaves" title="Mali L2 Cache" name="Write invalidates" description="Write invalidates"/>
+ <event event="0x07" option_set="Slaves" title="Mali L2 Cache" name="Read invalidates" description="Read invalidates"/>
+ <event event="0x08" option_set="Slaves" title="Mali L2 Cache" name="Cacheable read transactions" description="Cacheable read transactions"/>
+ </category>
+ <counter_set name="ARM_Mali-4xx_L2_1_cnt" title="Mali-4xx L2 1" description="Mali GPU L2 Cache Core 1" count="2"/>
+ <category name="Mali-4xx L2_1" counter_set="ARM_Mali-4xx_L2_1_cnt" per_cpu="no">
+ <event event="0x01" title="Mali L2 Cache 1" name="Total clock cycles" description="Total clock cycles"/>
+ <event event="0x02" title="Mali L2 Cache 1" name="Active clock cycles" description="Active clock cycles"/>
+ <option_set name="All">
+ <option event_delta="0x08" name="Master" description="Master"/>
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <option_set name="Slaves">
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <event event="0x00" option_set="All" title="Mali L2 Cache 1" name="Read transactions" description="Read transactions"/>
+ <event event="0x01" option_set="All" title="Mali L2 Cache 1" name="Write transactions" description="Write transactions"/>
+ <event event="0x02" option_set="All" title="Mali L2 Cache 1" name="Words read" description="Words read"/>
+ <event event="0x03" option_set="All" title="Mali L2 Cache 1" name="Words written" description="Words written"/>
+ <event event="0x04" option_set="Slaves" title="Mali L2 Cache 1" name="Read hits" description="Read hits"/>
+ <event event="0x05" option_set="Slaves" title="Mali L2 Cache 1" name="Read misses" description="Read misses"/>
+ <event event="0x06" option_set="Slaves" title="Mali L2 Cache 1" name="Write invalidates" description="Write invalidates"/>
+ <event event="0x07" option_set="Slaves" title="Mali L2 Cache 1" name="Read invalidates" description="Read invalidates"/>
+ <event event="0x08" option_set="Slaves" title="Mali L2 Cache 1" name="Cacheable read transactions" description="Cacheable read transactions"/>
+ </category>
+ <counter_set name="ARM_Mali-4xx_L2_2_cnt" title="Mali-4xx L2 2" description="Mali GPU L2 Cache Core 2" count="2"/>
+ <category name="Mali-4xx L2_2" counter_set="ARM_Mali-4xx_L2_2_cnt" per_cpu="no">
+ <event event="0x01" title="Mali L2 Cache 2" name="Total clock cycles" description="Total clock cycles"/>
+ <event event="0x02" title="Mali L2 Cache 2" name="Active clock cycles" description="Active clock cycles"/>
+ <option_set name="All">
+ <option event_delta="0x08" name="Master" description="Master"/>
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <option_set name="Slaves">
+ <option event_delta="0x10" name="All slaves" description="All slaves"/>
+ <option event_delta="0x20" name="Slave 0" description="Slave 0"/>
+ <option event_delta="0x30" name="Slave 1" description="Slave 1"/>
+ <option event_delta="0x40" name="Slave 2" description="Slave 2"/>
+ <option event_delta="0x50" name="Slave 3" description="Slave 3"/>
+ <option event_delta="0x60" name="Slave 4" description="Slave 4"/>
+ </option_set>
+ <event event="0x00" option_set="All" title="Mali L2 Cache 2" name="Read transactions" description="Read transactions"/>
+ <event event="0x01" option_set="All" title="Mali L2 Cache 2" name="Write transactions" description="Write transactions"/>
+ <event event="0x02" option_set="All" title="Mali L2 Cache 2" name="Words read" description="Words read"/>
+ <event event="0x03" option_set="All" title="Mali L2 Cache 2" name="Words written" description="Words written"/>
+ <event event="0x04" option_set="Slaves" title="Mali L2 Cache 2" name="Read hits" description="Read hits"/>
+ <event event="0x05" option_set="Slaves" title="Mali L2 Cache 2" name="Read misses" description="Read misses"/>
+ <event event="0x06" option_set="Slaves" title="Mali L2 Cache 2" name="Write invalidates" description="Write invalidates"/>
+ <event event="0x07" option_set="Slaves" title="Mali L2 Cache 2" name="Read invalidates" description="Read invalidates"/>
+ <event event="0x08" option_set="Slaves" title="Mali L2 Cache 2" name="Cacheable read transactions" description="Cacheable read transactions"/>
+ </category>
+ <counter_set name="ARM_Mali-4xx_Filmstrip_cnt" count="1"/>
+ <category name="Mali-4xx Filmstrip" counter_set="ARM_Mali-4xx_Filmstrip_cnt" per_cpu="no">
+ <option_set name="fs">
+ <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+ <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+ <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+ </option_set>
+ <event event="0x0400" option_set="fs" title="ARM Mali-4xx" name="Filmstrip" description="Scaled framebuffer"/>
+ </category>
+ <category name="ARM_Mali-4xx_Voltage" per_cpu="no">
+ <event counter="ARM_Mali-4xx_Voltage" title="Mali GPU Voltage" name="Voltage" class="absolute" display="average" average_selection="yes" units="mV" description="GPU core voltage."/>
+ </category>
+ <category name="ARM_Mali-4xx_Frequency" per_cpu="no">
+ <event counter="ARM_Mali-4xx_Frequency" title="Mali GPU Frequency" name="Frequency" class="absolute" display="average" average_selection="yes" units="MHz" description="GPU core frequency."/>
+ </category>
+ <category name="Mali-4xx Activity" counter_set="ARM_Mali-4xx_Activity_cnt" per_cpu="yes">
+ <event counter="ARM_Mali-4xx_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" description="GPU Fragment Activity"/>
+ <event counter="ARM_Mali-4xx_vertex" title="GPU Vertex" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" description="GPU Vertex Activity"/>
+ </category>
+ <category name="Mali-4xx Software Counters" counter_set="ARM_Mali-4xx_SW_cnt" per_cpu="no">
+ <!-- EGL Counters -->
+ <event counter="ARM_Mali-4xx_SW_0" title="Mali EGL Software Counters" name="Blit Time" description="Time spent blitting the framebuffer from video memory to framebuffer."/>
+ <!-- glDrawElements Counters -->
+ <event counter="ARM_Mali-4xx_SW_1" title="glDrawElements Statistics" name="Calls to glDrawElements" description="Number of calls to glDrawElements."/>
+ <event counter="ARM_Mali-4xx_SW_2" title="glDrawElements Statistics" name="Indices to glDrawElements" description="Number of indices to glDrawElements."/>
+ <event counter="ARM_Mali-4xx_SW_3" title="glDrawElements Statistics" name="Transformed by glDrawElements" description="Number of vertices transformed by glDrawElements."/>
+ <!-- glDrawArrays Counters -->
+ <event counter="ARM_Mali-4xx_SW_4" title="glDrawArrays Statistics" name="Calls to glDrawArrays" description="Number of calls to glDrawArrays."/>
+ <event counter="ARM_Mali-4xx_SW_5" title="glDrawArrays Statistics" name="Transformed by glDrawArrays" description="Number of vertices transformed by glDrawArrays."/>
+ <!-- Draw Call Counters -->
+ <event counter="ARM_Mali-4xx_SW_6" title="Drawcall Statistics" name="Points" description="Number of calls to glDraw* with parameter GL_POINTS."/>
+ <event counter="ARM_Mali-4xx_SW_7" title="Drawcall Statistics" name="Lines" description="Number of calls to glDraw* with parameter GL_LINES."/>
+ <event counter="ARM_Mali-4xx_SW_8" title="Drawcall Statistics" name="Lineloop" description="Number of calls to glDraw* with parameter GL_LINE_LOOP."/>
+ <event counter="ARM_Mali-4xx_SW_9" title="Drawcall Statistics" name="Linestrip" description="Number of calls to glDraw* with parameter GL_LINE_STRIP."/>
+ <event counter="ARM_Mali-4xx_SW_10" title="Drawcall Statistics" name="Triangles" description="Number of calls to glDraw* with parameter GL_TRIANGLES."/>
+ <event counter="ARM_Mali-4xx_SW_11" title="Drawcall Statistics" name="Trianglestrip" description="Number of calls to glDraw* with parameter GL_TRIANGLE_STRIP."/>
+ <event counter="ARM_Mali-4xx_SW_12" title="Drawcall Statistics" name="Trianglefan" description="Number of calls to glDraw* with parameter GL_TRIANGLE_FAN."/>
+ <event counter="ARM_Mali-4xx_SW_13" title="Drawcall Statistics" name="Vertex Upload Time (us)" description="Time spent uploading vertex attributes and faceindex data not present in a VBO."/>
+ <event counter="ARM_Mali-4xx_SW_14" title="Drawcall Statistics" name="Uniform Bytes Copied (bytes)" description="Number of bytes copied to Mali memory as a result of uniforms update."/>
+ <!-- Buffer Profiling Counters -->
+ <event counter="ARM_Mali-4xx_SW_15" title="Buffer Profiling" name="Texture Upload Time (ms)" description="Time spent uploading textures."/>
+ <event counter="ARM_Mali-4xx_SW_16" title="Buffer Profiling" name="VBO Upload Time (ms)" description="Time spent uploading vertex buffer objects."/>
+ <event counter="ARM_Mali-4xx_SW_17" title="Buffer Profiling" name="FBO Flushes" description="Number of flushed on framebuffer attachment."/>
+ <!-- OpenGL ES 1.1 Emulation -->
+ <event counter="ARM_Mali-4xx_SW_18" title="Fixed-function Emulation" name="# Vertex Shaders Generated" description="Number of vertex shaders generated."/>
+ <event counter="ARM_Mali-4xx_SW_19" title="Fixed-function Emulation" name="# Fragment Shaders Generated" description="Number of fragment shaders generated."/>
+ <!-- Geometry Statistics -->
+ <event counter="ARM_Mali-4xx_SW_33" title="Geometry Statistics" name="Triangles" description="The total number of triangles passed to GLES per-frame."/>
+ <event counter="ARM_Mali-4xx_SW_34" title="Geometry Statistics" name="Independent Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLES."/>
+ <event counter="ARM_Mali-4xx_SW_35" title="Geometry Statistics" name="Strip Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_STRIP."/>
+ <event counter="ARM_Mali-4xx_SW_36" title="Geometry Statistics" name="Fan Triangles" description="Number of triangles passed to GLES using the mode GL_TRIANGLE_FAN."/>
+ <event counter="ARM_Mali-4xx_SW_37" title="Geometry Statistics" name="Lines" description="Number of lines passed to GLES per-frame."/>
+ <event counter="ARM_Mali-4xx_SW_38" title="Geometry Statistics" name="Independent Lines" description="Number of lines passed to GLES using the mode GL_LINES."/>
+ <event counter="ARM_Mali-4xx_SW_39" title="Geometry Statistics" name="Strip Lines" description="Number of lines passed to GLES using the mode GL_LINE_STRIP."/>
+ <event counter="ARM_Mali-4xx_SW_40" title="Geometry Statistics" name="Loop Lines" description="Number of lines passed to GLES using the mode GL_LINE_LOOP."/>
+ </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard.xml b/tools/gator/daemon/events-Mali-Midgard.xml
new file mode 100644
index 0000000..33c1a40
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard.xml
@@ -0,0 +1,49 @@
+ <category name="Mali-Midgard Software Counters" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_TOTAL_ALLOC_PAGES" title="Mali Total Alloc Pages" name="Total number of allocated pages" description="Mali total number of allocated pages."/>
+ </category>
+<!--
+power management is disabled during profiling so these counters are not useful as they always return zero
+ <category name="Mali-Midgard PM Shader" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_PM_SHADER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 0" description="Mali PM Shader: PM Shader Core 0."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 1" description="Mali PM Shader: PM Shader Core 1."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_2" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 2" description="Mali PM Shader: PM Shader Core 2."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_3" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 3" description="Mali PM Shader: PM Shader Core 3."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_4" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 4" description="Mali PM Shader: PM Shader Core 4."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_5" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 5" description="Mali PM Shader: PM Shader Core 5."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_6" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 6" description="Mali PM Shader: PM Shader Core 6."/>
+ <event counter="ARM_Mali-Midgard_PM_SHADER_7" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Shader" name="PM Shader Core 7" description="Mali PM Shader: PM Shader Core 7."/>
+ </category>
+ <category name="Mali-Midgard PM Tiler" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_PM_TILER_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM Tiler" name="PM Tiler Core 0" description="Mali PM Tiler: PM Tiler Core 0."/>
+ </category>
+ <category name="Mali-Midgard PM L2" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_PM_L2_0" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 0" description="Mali PM L2: PM L2 Core 0."/>
+ <event counter="ARM_Mali-Midgard_PM_L2_1" class="absolute" display="average" average_selection="yes" percentage="yes" title="Mali PM L2" name="PM L2 Core 1" description="Mali PM L2: PM L2 Core 1."/>
+ </category>
+-->
+ <category name="Mali-Midgard MMU Address Space" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_MMU_AS_0" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 0" description="Mali MMU Address Space 0 usage."/>
+ <event counter="ARM_Mali-Midgard_MMU_AS_1" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 1" description="Mali MMU Address Space 1 usage."/>
+ <event counter="ARM_Mali-Midgard_MMU_AS_2" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 2" description="Mali MMU Address Space 2 usage."/>
+ <event counter="ARM_Mali-Midgard_MMU_AS_3" average_selection="yes" percentage="yes" title="Mali MMU Address Space" name="MMU Address Space 3" description="Mali MMU Address Space 3 usage."/>
+ </category>
+ <category name="Mali-Midgard MMU Page Fault" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_0" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 0" description="Reports the number of newly allocated pages after a MMU page fault in address space 0."/>
+ <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_1" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 1" description="Reports the number of newly allocated pages after a MMU page fault in address space 1."/>
+ <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_2" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 2" description="Reports the number of newly allocated pages after a MMU page fault in address space 2."/>
+ <event counter="ARM_Mali-Midgard_MMU_PAGE_FAULT_3" title="Mali MMU Page Fault Add. Space" name="Mali MMU Page Fault Add. Space 3" description="Reports the number of newly allocated pages after a MMU page fault in address space 3."/>
+ </category>
+ <counter_set name="ARM_Mali-Midgard_Filmstrip_cnt" count="1"/>
+ <category name="Mali-Midgard Filmstrip" counter_set="ARM_Mali-Midgard_Filmstrip_cnt" per_cpu="no">
+ <option_set name="fs">
+ <option event_delta="0x3c" name="1:60" description="captures every 60th frame"/>
+ <option event_delta="0x1e" name="1:30" description="captures every 30th frame"/>
+ <option event_delta="0xa" name="1:10" description="captures every 10th frame"/>
+ </option_set>
+ <event event="0x0400" option_set="fs" title="ARM Mali-Midgard" name="Filmstrip" description="Scaled framebuffer"/>
+ </category>
+ <category name="Mali-Midgard Activity" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_fragment" title="GPU Fragment" name="Activity" class="activity" activity1="Activity" activity_color1="0x00006fcc" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 0 Activity"/>
+ <event counter="ARM_Mali-Midgard_vertex" title="GPU Vertex-Tiling-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00eda000" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 1 Activity"/>
+ <event counter="ARM_Mali-Midgard_opencl" title="GPU Vertex-Compute" name="Activity" class="activity" activity1="Activity" activity_color1="0x00ef022f" rendering_type="bar" average_selection="yes" percentage="yes" cores="1" description="GPU Job Slot 2 Activity"/>
+ </category>
diff --git a/tools/gator/daemon/events-Mali-Midgard_hw.xml b/tools/gator/daemon/events-Mali-Midgard_hw.xml
new file mode 100644
index 0000000..e8f0cb0
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-Midgard_hw.xml
@@ -0,0 +1,98 @@
+<!-- this file is valid for Midgard r4p0 and earlier and replaced with the core-specific files in r5p0 -->
+ <category name="Mali-Midgard Job Manager" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles the GPU was active"/>
+ <event counter="ARM_Mali-Midgard_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles the GPU had a pending interrupt"/>
+ <event counter="ARM_Mali-Midgard_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) was active"/>
+ <event counter="ARM_Mali-Midgard_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) was active"/>
+ <event counter="ARM_Mali-Midgard_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) was active"/>
+
+ <event counter="ARM_Mali-Midgard_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-Midgard_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-Midgard_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-Midgard_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-Midgard_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-Midgard_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+ </category>
+ <category name="Mali-Midgard Tiler" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-Midgard_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-Midgard_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-Midgard_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-Midgard_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-Midgard_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-Midgard_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-Midgard_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-Midgard_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-Midgard_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-Midgard_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-Midgard_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-Midgard_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-Midgard_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-Midgard_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-Midgard_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-Midgard_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-Midgard_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+ </category>
+ <category name="Mali-Midgard Shader Core" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles the Tripipe was active"/>
+ <event counter="ARM_Mali-Midgard_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-Midgard_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-Midgard_FRAG_CYCLE_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+ <event counter="ARM_Mali-Midgard_FRAG_THREADS" title="Mali Core Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-Midgard_FRAG_DUMMY_THREADS" title="Mali Core Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS quads" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-Midgard_FRAG_QUADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS quads" description="Number of threads killed by late ZS test"/>
+ <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_TEST" title="Mali Core Threads" name="Frag threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-Midgard_FRAG_THREADS_LZS_KILLED" title="Mali Core Threads" name="Frag threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-Midgard_COMPUTE_TASKS" title="Mali Compute Threads" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-Midgard_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads started" description="Number of compute threads started"/>
+ <event counter="ARM_Mali-Midgard_COMPUTE_CYCLES_DESC" title="Mali Compute Threads" name="Compute cycles awaiting descriptors" description="Number of compute cycles spent waiting for descriptors"/>
+
+ <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-Midgard_FRAG_PRIMATIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+ <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-Midgard_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-Midgard_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-Midgard_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-Midgard_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-Midgard_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-Midgard_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-Midgard_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-Midgard_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-Midgard_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-Midgard_TEX_THREADS" title="Mali Texture Pipe" name="T instruction issues" description="Number of instructions issused to the T-pipe, including restarts"/>
+ <event counter="ARM_Mali-Midgard_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-Midgard_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+ <event counter="ARM_Mali-Midgard_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+ </category>
+ <category name="Mali-Midgard L2 and MMU" per_cpu="no">
+ <event counter="ARM_Mali-Midgard_L2_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-Midgard_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+
+ <event counter="ARM_Mali-Midgard_L2_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-Midgard_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+
+ <event counter="ARM_Mali-Midgard_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-Midgard_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+ <event counter="ARM_Mali-Midgard_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-Midgard_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ </category>
diff --git a/tools/gator/daemon/events-Mali-T60x_hw.xml b/tools/gator/daemon/events-Mali-T60x_hw.xml
new file mode 100644
index 0000000..c35bcd1
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T60x_hw.xml
@@ -0,0 +1,116 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T60x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T60x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T60x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T60x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T60x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T60x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T60x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T60x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T60x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T60x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T60x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T60x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T60x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T60x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T60x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T60x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T60x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T60x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T60x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T60x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T60x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T60x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-T60x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-T60x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T60x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T60x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T60x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T60x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+ <event counter="ARM_Mali-T60x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T60x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T60x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T60x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T60x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T60x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T60x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T60x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T60x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T60x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T60x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-T60x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T60x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T60x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T60x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T60x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T60x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T60x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T60x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T60x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T60x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T60x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T60x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T60x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T60x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T60x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T60x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T60x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T60x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T60x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T60x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T60x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T60x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T60x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T60x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T60x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T60x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T60x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T62x_hw.xml b/tools/gator/daemon/events-Mali-T62x_hw.xml
new file mode 100644
index 0000000..4bc9306
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T62x_hw.xml
@@ -0,0 +1,116 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T62x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T62x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T62x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T62x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T62x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T62x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T62x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T62x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T62x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T62x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T62x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T62x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T62x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T62x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T62x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T62x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T62x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T62x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T62x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T62x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T62x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T62x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-T62x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-T62x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T62x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T62x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T62x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T62x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T62x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T62x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T62x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T62x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T62x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T62x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T62x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T62x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T62x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T62x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T62x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T62x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-T62x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T62x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T62x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T62x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T62x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T62x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T62x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T62x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T62x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T62x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T62x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T62x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T62x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+ <event counter="ARM_Mali-T62x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T62x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T62x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T62x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T62x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T62x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T62x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T62x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T62x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T62x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T62x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T62x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T62x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T62x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T72x_hw.xml b/tools/gator/daemon/events-Mali-T72x_hw.xml
new file mode 100644
index 0000000..fd9cb0f
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T72x_hw.xml
@@ -0,0 +1,101 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T72x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T72x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T72x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T72x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T72x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T72x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T72x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T72x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T72x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T72x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T72x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T72x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T72x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T72x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T72x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T72x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T72x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T72x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T72x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T72x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T72x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T72x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T72x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T72x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T72x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T72x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+
+ <event counter="ARM_Mali-T72x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T72x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T72x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T72x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T72x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T72x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T72x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T72x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T72x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T72x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T72x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe"/>
+
+ <event counter="ARM_Mali-T72x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T72x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T72x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T72x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+
+
+ <event counter="ARM_Mali-T72x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T72x_LSC_READ_MISSES" title="Mali Load/Store Cache Reads" name="Read misses" description="Number of read misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T72x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T72x_LSC_WRITE_MISSES" title="Mali Load/Store Cache Writes" name="Write misses" description="Number of write misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T72x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+ <event counter="ARM_Mali-T72x_LSC_ATOMIC_MISSES" title="Mali Load/Store Cache Atomics" name="Atomic misses" description="Number of atomic misses in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T72x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T72x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+ <event counter="ARM_Mali-T72x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T72x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T72x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T72x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T72x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T72x_L2_EXT_READ_BEAT" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T72x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+
+ <event counter="ARM_Mali-T72x_L2_EXT_WRITE_BEAT" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T72x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+
+ </category>
diff --git a/tools/gator/daemon/events-Mali-T76x_hw.xml b/tools/gator/daemon/events-Mali-T76x_hw.xml
new file mode 100644
index 0000000..94d059f
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T76x_hw.xml
@@ -0,0 +1,117 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T76x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T76x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T76x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T76x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T76x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T76x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T76x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T76x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T76x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T76x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T76x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T76x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T76x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T76x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T76x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T76x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T76x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T76x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T76x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T76x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T76x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T76x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-T76x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-T76x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T76x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T76x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T76x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T76x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T76x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T76x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T76x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T76x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T76x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T76x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T76x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T76x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T76x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T76x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T76x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T76x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-T76x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T76x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T76x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T76x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T76x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T76x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T76x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T76x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T76x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T76x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T76x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T76x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T76x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T76x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T76x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T76x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T76x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T76x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T76x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T76x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T76x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T76x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T76x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T76x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T76x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T76x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T76x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
\ No newline at end of file
diff --git a/tools/gator/daemon/events-Mali-T82x_hw.xml b/tools/gator/daemon/events-Mali-T82x_hw.xml
new file mode 100644
index 0000000..5caa464
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T82x_hw.xml
@@ -0,0 +1,108 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T82x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T82x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T82x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T82x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T82x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T82x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T82x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T82x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T82x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T82x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T82x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T82x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T82x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T82x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T82x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T82x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T82x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T82x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T82x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T82x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T82x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T82x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T82x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T82x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T82x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T82x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T82x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T82x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T82x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T82x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T82x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T82x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T82x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T82x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T82x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T82x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T82x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T82x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T82x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T82x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T82x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe (normalized per pipe)"/>
+
+ <event counter="ARM_Mali-T82x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T82x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T82x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T82x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T82x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T82x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T82x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T82x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T82x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T82x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T82x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T82x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T82x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T82x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T82x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T82x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T82x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T82x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T82x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T82x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T82x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T82x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T82x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T82x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T82x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T82x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T82x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
diff --git a/tools/gator/daemon/events-Mali-T83x_hw.xml b/tools/gator/daemon/events-Mali-T83x_hw.xml
new file mode 100644
index 0000000..39f7acf
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T83x_hw.xml
@@ -0,0 +1,108 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T83x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T83x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T83x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T83x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T83x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T83x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T83x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T83x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T83x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T83x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T83x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T83x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T83x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T83x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T83x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T83x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T83x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T83x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T83x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T83x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T83x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T83x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T83x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T83x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T83x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T83x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T83x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T83x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T83x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T83x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T83x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T83x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T83x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T83x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T83x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T83x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T83x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T83x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T83x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T83x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T83x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of batched instructions executed by the A-pipe (normalized per pipe)"/>
+
+ <event counter="ARM_Mali-T83x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T83x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T83x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T83x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T83x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T83x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T83x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T83x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T83x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T83x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T83x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T83x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T83x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T83x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T83x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T83x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T83x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T83x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T83x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T83x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T83x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T83x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T83x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T83x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T83x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T83x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T83x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
diff --git a/tools/gator/daemon/events-Mali-T86x_hw.xml b/tools/gator/daemon/events-Mali-T86x_hw.xml
new file mode 100644
index 0000000..6653543
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T86x_hw.xml
@@ -0,0 +1,117 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T86x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T86x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T86x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T86x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T86x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T86x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T86x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T86x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T86x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T86x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T86x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T86x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T86x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T86x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T86x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T86x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T86x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T86x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T86x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T86x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T86x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T86x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-T86x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-T86x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T86x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T86x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T86x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T86x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T86x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T86x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T86x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T86x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T86x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T86x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T86x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T86x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T86x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T86x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T86x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T86x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T86x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T86x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T86x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-T86x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T86x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T86x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T86x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T86x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T86x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T86x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T86x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T86x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T86x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T86x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T86x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T86x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T86x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T86x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T86x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T86x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T86x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T86x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T86x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T86x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T86x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T86x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T86x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T86x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T86x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T86x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
diff --git a/tools/gator/daemon/events-Mali-T88x_hw.xml b/tools/gator/daemon/events-Mali-T88x_hw.xml
new file mode 100644
index 0000000..19385d1
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-T88x_hw.xml
@@ -0,0 +1,117 @@
+
+ <category name="Mali Job Manager" per_cpu="no">
+
+ <event counter="ARM_Mali-T88x_GPU_ACTIVE" title="Mali Job Manager Cycles" name="GPU cycles" description="Number of cycles GPU active"/>
+ <event counter="ARM_Mali-T88x_IRQ_ACTIVE" title="Mali Job Manager Cycles" name="IRQ cycles" description="Number of cycles GPU interrupt pending"/>
+ <event counter="ARM_Mali-T88x_JS0_ACTIVE" title="Mali Job Manager Cycles" name="JS0 cycles" description="Number of cycles JS0 (fragment) active"/>
+ <event counter="ARM_Mali-T88x_JS1_ACTIVE" title="Mali Job Manager Cycles" name="JS1 cycles" description="Number of cycles JS1 (vertex/tiler/compute) active"/>
+ <event counter="ARM_Mali-T88x_JS2_ACTIVE" title="Mali Job Manager Cycles" name="JS2 cycles" description="Number of cycles JS2 (vertex/compute) active"/>
+
+ <event counter="ARM_Mali-T88x_JS0_JOBS" title="Mali Job Manager Jobs" name="JS0 jobs" description="Number of Jobs (fragment) completed in JS0"/>
+ <event counter="ARM_Mali-T88x_JS1_JOBS" title="Mali Job Manager Jobs" name="JS1 jobs" description="Number of Jobs (vertex/tiler/compute) completed in JS1"/>
+ <event counter="ARM_Mali-T88x_JS2_JOBS" title="Mali Job Manager Jobs" name="JS2 jobs" description="Number of Jobs (vertex/compute) completed in JS2"/>
+
+ <event counter="ARM_Mali-T88x_JS0_TASKS" title="Mali Job Manager Tasks" name="JS0 tasks" description="Number of Tasks completed in JS0"/>
+ <event counter="ARM_Mali-T88x_JS1_TASKS" title="Mali Job Manager Tasks" name="JS1 tasks" description="Number of Tasks completed in JS1"/>
+ <event counter="ARM_Mali-T88x_JS2_TASKS" title="Mali Job Manager Tasks" name="JS2 tasks" description="Number of Tasks completed in JS2"/>
+
+ </category>
+
+ <category name="Mali Tiler" per_cpu="no">
+
+ <event counter="ARM_Mali-T88x_TI_ACTIVE" title="Mali Tiler Cycles" name="Tiler cycles" description="Number of cycles Tiler active"/>
+
+ <event counter="ARM_Mali-T88x_TI_POLYGONS" title="Mali Tiler Primitives" name="Polygons" description="Number of polygons processed"/>
+ <event counter="ARM_Mali-T88x_TI_QUADS" title="Mali Tiler Primitives" name="Quads" description="Number of quads processed"/>
+ <event counter="ARM_Mali-T88x_TI_TRIANGLES" title="Mali Tiler Primitives" name="Triangles" description="Number of triangles processed"/>
+ <event counter="ARM_Mali-T88x_TI_LINES" title="Mali Tiler Primitives" name="Lines" description="Number of lines processed"/>
+ <event counter="ARM_Mali-T88x_TI_POINTS" title="Mali Tiler Primitives" name="Points" description="Number of points processed"/>
+
+ <event counter="ARM_Mali-T88x_TI_FRONT_FACING" title="Mali Tiler Culling" name="Front facing prims" description="Number of front facing primitives"/>
+ <event counter="ARM_Mali-T88x_TI_BACK_FACING" title="Mali Tiler Culling" name="Back facing prims" description="Number of back facing primitives"/>
+ <event counter="ARM_Mali-T88x_TI_PRIM_VISIBLE" title="Mali Tiler Culling" name="Visible prims" description="Number of visible primitives"/>
+ <event counter="ARM_Mali-T88x_TI_PRIM_CULLED" title="Mali Tiler Culling" name="Culled prims" description="Number of culled primitives"/>
+ <event counter="ARM_Mali-T88x_TI_PRIM_CLIPPED" title="Mali Tiler Culling" name="Clipped prims" description="Number of clipped primitives"/>
+
+ <event counter="ARM_Mali-T88x_TI_LEVEL0" title="Mali Tiler Hierarchy" name="L0 prims" description="Number of primitives in hierarchy level 0"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL1" title="Mali Tiler Hierarchy" name="L1 prims" description="Number of primitives in hierarchy level 1"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL2" title="Mali Tiler Hierarchy" name="L2 prims" description="Number of primitives in hierarchy level 2"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL3" title="Mali Tiler Hierarchy" name="L3 prims" description="Number of primitives in hierarchy level 3"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL4" title="Mali Tiler Hierarchy" name="L4 prims" description="Number of primitives in hierarchy level 4"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL5" title="Mali Tiler Hierarchy" name="L5 prims" description="Number of primitives in hierarchy level 5"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL6" title="Mali Tiler Hierarchy" name="L6 prims" description="Number of primitives in hierarchy level 6"/>
+ <event counter="ARM_Mali-T88x_TI_LEVEL7" title="Mali Tiler Hierarchy" name="L7 prims" description="Number of primitives in hierarchy level 7"/>
+
+ </category>
+
+ <category name="Mali Shader Core" per_cpu="no">
+
+ <event counter="ARM_Mali-T88x_TRIPIPE_ACTIVE" title="Mali Core Cycles" name="Tripipe cycles" description="Number of cycles tripipe was active"/>
+ <event counter="ARM_Mali-T88x_FRAG_ACTIVE" title="Mali Core Cycles" name="Fragment cycles" description="Number of cycles fragment processing was active"/>
+ <event counter="ARM_Mali-T88x_COMPUTE_ACTIVE" title="Mali Core Cycles" name="Compute cycles" description="Number of cycles vertex\compute processing was active"/>
+ <event counter="ARM_Mali-T88x_FRAG_CYCLES_NO_TILE" title="Mali Core Cycles" name="Fragment cycles waiting for tile" description="Number of cycles spent waiting for a physical tile buffer"/>
+ <event counter="ARM_Mali-T88x_FRAG_CYCLES_FPKQ_ACTIVE" title="Mali Core Cycles" name="Fragment cycles pre-pipe buffer not empty" description="Number of cycles the pre-pipe queue contains quads"/>
+
+ <event counter="ARM_Mali-T88x_FRAG_THREADS" title="Mali Fragment Threads" name="Fragment threads" description="Number of fragment threads started"/>
+ <event counter="ARM_Mali-T88x_FRAG_DUMMY_THREADS" title="Mali Fragment Threads" name="Dummy fragment threads" description="Number of dummy fragment threads started"/>
+ <event counter="ARM_Mali-T88x_FRAG_THREADS_LZS_TEST" title="Mali Fragment Threads" name="Fragment threads doing late ZS" description="Number of threads doing late ZS test"/>
+ <event counter="ARM_Mali-T88x_FRAG_THREADS_LZS_KILLED" title="Mali Fragment Threads" name="Fragment threads killed late ZS" description="Number of threads killed by late ZS test"/>
+
+ <event counter="ARM_Mali-T88x_COMPUTE_TASKS" title="Mali Compute Tasks" name="Compute tasks" description="Number of compute tasks"/>
+ <event counter="ARM_Mali-T88x_COMPUTE_THREADS" title="Mali Compute Threads" name="Compute threads" description="Number of compute threads started"/>
+
+ <event counter="ARM_Mali-T88x_FRAG_PRIMITIVES" title="Mali Fragment Primitives" name="Primitives loaded" description="Number of primitives loaded from tiler"/>
+ <event counter="ARM_Mali-T88x_FRAG_PRIMITIVES_DROPPED" title="Mali Fragment Primitives" name="Primitives dropped" description="Number of primitives dropped because out of tile"/>
+
+ <event counter="ARM_Mali-T88x_FRAG_QUADS_RAST" title="Mali Fragment Quads" name="Quads rasterized" description="Number of quads rasterized"/>
+ <event counter="ARM_Mali-T88x_FRAG_QUADS_EZS_TEST" title="Mali Fragment Quads" name="Quads doing early ZS" description="Number of quads doing early ZS test"/>
+ <event counter="ARM_Mali-T88x_FRAG_QUADS_EZS_KILLED" title="Mali Fragment Quads" name="Quads killed early Z" description="Number of quads killed by early ZS test"/>
+
+ <event counter="ARM_Mali-T88x_FRAG_NUM_TILES" title="Mali Fragment Tasks" name="Tiles rendered" description="Number of tiles rendered"/>
+ <event counter="ARM_Mali-T88x_FRAG_TRANS_ELIM" title="Mali Fragment Tasks" name="Tile writes killed by TE" description="Number of tile writes skipped by transaction elimination"/>
+
+ <event counter="ARM_Mali-T88x_ARITH_WORDS" title="Mali Arithmetic Pipe" name="A instructions" description="Number of instructions completed by the the A-pipe (normalized per pipeline)"/>
+
+ <event counter="ARM_Mali-T88x_LS_WORDS" title="Mali Load/Store Pipe" name="LS instructions" description="Number of instructions completed by the LS-pipe"/>
+ <event counter="ARM_Mali-T88x_LS_ISSUES" title="Mali Load/Store Pipe" name="LS instruction issues" description="Number of instructions issued to the LS-pipe, including restarts"/>
+
+ <event counter="ARM_Mali-T88x_TEX_WORDS" title="Mali Texture Pipe" name="T instructions" description="Number of instructions completed by the T-pipe"/>
+ <event counter="ARM_Mali-T88x_TEX_ISSUES" title="Mali Texture Pipe" name="T instruction issues" description="Number of threads through loop 2 address calculation"/>
+ <event counter="ARM_Mali-T88x_TEX_RECIRC_FMISS" title="Mali Texture Pipe" name="Cache misses" description="Number of instructions in the T-pipe, recirculated due to cache miss"/>
+
+ <event counter="ARM_Mali-T88x_LSC_READ_OP" title="Mali Load/Store Cache Reads" name="Read operations" description="Number of read operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T88x_LSC_READ_HITS" title="Mali Load/Store Cache Reads" name="Read hits" description="Number of read hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T88x_LSC_WRITE_OP" title="Mali Load/Store Cache Writes" name="Write operations" description="Number of write operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T88x_LSC_WRITE_HITS" title="Mali Load/Store Cache Writes" name="Write hits" description="Number of write hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T88x_LSC_ATOMIC_OP" title="Mali Load/Store Cache Atomics" name="Atomic operations" description="Number of atomic operations in the Load/Store cache"/>
+ <event counter="ARM_Mali-T88x_LSC_ATOMIC_HITS" title="Mali Load/Store Cache Atomics" name="Atomic hits" description="Number of atomic hits in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T88x_LSC_LINE_FETCHES" title="Mali Load/Store Cache Bus" name="Line fetches" description="Number of line fetches in the Load/Store cache"/>
+ <event counter="ARM_Mali-T88x_LSC_DIRTY_LINE" title="Mali Load/Store Cache Bus" name="Dirty line evictions" description="Number of dirty line evictions in the Load/Store cache"/>
+
+ <event counter="ARM_Mali-T88x_LSC_SNOOPS" title="Mali Load/Store Cache Bus" name="Snoops in to LSC" description="Number of coherent memory snoops in to the Load/Store cache"/>
+
+ </category>
+
+ <category name="Mali L2 Cache" per_cpu="no">
+
+ <event counter="ARM_Mali-T88x_L2_READ_LOOKUP" title="Mali L2 Cache Reads" name="L2 read lookups" description="Number of reads into the L2 cache"/>
+ <event counter="ARM_Mali-T88x_L2_READ_SNOOP" title="Mali L2 Cache Reads" name="Read snoops" description="Number of read transaction snoops"/>
+ <event counter="ARM_Mali-T88x_L2_READ_HIT" title="Mali L2 Cache Reads" name="L2 read hits" description="Number of reads hitting in the L2 cache"/>
+
+ <event counter="ARM_Mali-T88x_L2_WRITE_SNOOP" title="Mali L2 Cache Writes" name="Write snoops" description="Number of write transaction snoops"/>
+ <event counter="ARM_Mali-T88x_L2_WRITE_HIT" title="Mali L2 Cache Writes" name="L2 write hits" description="Number of writes hitting in the L2 cache"/>
+ <event counter="ARM_Mali-T88x_L2_WRITE_LOOKUP" title="Mali L2 Cache Writes" name="L2 write lookups" description="Number of writes into the L2 cache"/>
+
+ <event counter="ARM_Mali-T88x_L2_EXT_READ_BEATS" title="Mali L2 Cache Ext Reads" name="External read beats" description="Number of external bus read beats"/>
+ <event counter="ARM_Mali-T88x_L2_EXT_AR_STALL" title="Mali L2 Cache Ext Reads" name="External bus stalls (AR)" description="Number of cycles a valid read address (AR) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T88x_L2_EXT_R_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus response buffer full" description="Number of cycles a valid request is blocked by a full response buffer"/>
+ <event counter="ARM_Mali-T88x_L2_EXT_RD_BUF_FULL" title="Mali L2 Cache Ext Reads" name="External bus read data buffer full" description="Number of cycles a valid request is blocked by a full read data buffer"/>
+
+ <event counter="ARM_Mali-T88x_L2_EXT_WRITE_BEATS" title="Mali L2 Cache Ext Writes" name="External write beats" description="Number of external bus write beats"/>
+ <event counter="ARM_Mali-T88x_L2_EXT_W_STALL" title="Mali L2 Cache Ext Writes" name="External bus stalls (W)" description="Number of cycles a valid write data (W channel) is stalled by the external interconnect"/>
+ <event counter="ARM_Mali-T88x_L2_EXT_W_BUF_FULL" title="Mali L2 Cache Ext Writes" name="External bus write buffer full" description="Number of cycles a valid request is blocked by a full write buffer"/>
+
+ </category>
diff --git a/tools/gator/daemon/events-Mali-V500.xml b/tools/gator/daemon/events-Mali-V500.xml
new file mode 100644
index 0000000..89bc7f4
--- /dev/null
+++ b/tools/gator/daemon/events-Mali-V500.xml
@@ -0,0 +1,30 @@
+ <category name="Mali-V500">
+ <event counter="ARM_Mali-V500_cnt0" title="MVE-V500 Stats" name="Samples" class="absolute" description="The number of times we have taken a sample"/>
+ <event counter="ARM_Mali-V500_cnt1" title="MVE-V500 Input Totals" name="Queued input-buffers" class="absolute" description="The number of input-buffers that has been queued for consumption by the MVE"/>
+ <event counter="ARM_Mali-V500_cnt2" title="MVE-V500 Input Totals" name="Consumed input-buffers" class="absolute" description="The number of input-buffers that has been consumed by the MVE and returned to the application"/>
+ <event counter="ARM_Mali-V500_cnt3" title="MVE-V500 Output Totals" name="Queued output-buffers" class="absolute" description="The number of output-buffers that has been queued for usage by the MVE"/>
+ <event counter="ARM_Mali-V500_cnt4" title="MVE-V500 Output Totals" name="Consumed output-buffers" class="absolute" description="The number of output-buffers that has been consumed by the MVE and returned to the application"/>
+ <event counter="ARM_Mali-V500_cnt5" title="MVE-V500 Stats" name="Created Sessions" class="absolute" description="The number of created sessions throughout the lifetime of the process"/>
+ <event counter="ARM_Mali-V500_cnt6" title="MVE-V500 Sessions" name="Active Sessions" description="The number of currently existing sessions"/>
+ <event counter="ARM_Mali-V500_cnt7" title="MVE-V500 Stats" name="Processed Frames" class="absolute" description="The number of processed frames. A processed frame is one where the encode or decode is complete for that particular frame. Frames can be processed out of order so this is not the same as the number of output-buffers returned"/>
+ <event counter="ARM_Mali-V500_cnt8" title="MVE-V500 Input Totals" name="Input Flushes Requested" class="absolute" description="The number of requested flushes of the input queue"/>
+ <event counter="ARM_Mali-V500_cnt9" title="MVE-V500 Input Totals" name="Input Flushes Complete" class="absolute" description="The number of completed flushes of the input queue"/>
+ <event counter="ARM_Mali-V500_cnt10" title="MVE-V500 Output Totals" name="Output Flushes Requested" class="absolute" description="The number of requested flushes of the output queue"/>
+ <event counter="ARM_Mali-V500_cnt11" title="MVE-V500 Output Totals" name="Output Flushes Complete" class="absolute" description="The number of completed flushes of the output queue"/>
+ <event counter="ARM_Mali-V500_cnt12" title="MVE-V500 Output" name="Queued Output Buffers (current)" description="The number of output-buffers that are currently queued for usage by the MVE"/>
+ <event counter="ARM_Mali-V500_cnt13" title="MVE-V500 Input" name="Queued Input Buffers (current)" description="The number of input-buffers that are currently queued for consumption by the MVE"/>
+ <event counter="ARM_Mali-V500_cnt14" title="MVE-V500 Output" name="Output Queue Flushes" description="The number of pending flushes for the MVE output-queue"/>
+ <event counter="ARM_Mali-V500_cnt15" title="MVE-V500 Input" name="Input Queue Flushes" description="The number of pending flushes for the MVE input-queue"/>
+ <event counter="ARM_Mali-V500_cnt16" title="MVE-V500 Stats" name="Errors encountered" class="absolute" description="The number of errors encountered"/>
+ <event counter="ARM_Mali-V500_cnt17" title="MVE-V500 Bandwidth" name="Bits consumed" class="absolute" description="The number of bits consumed during decode"/>
+ <event counter="ARM_Mali-V500_cnt18" title="MVE-V500 Bandwidth" name="AFBC bandwidth" class="absolute" description="The amount of AFBC-encoded bytes read or written"/>
+ <event counter="ARM_Mali-V500_cnt19" title="MVE-V500 Bandwidth" name="Bandwidth (read)" class="absolute" description="The amount of bytes read over the AXI bus"/>
+ <event counter="ARM_Mali-V500_cnt20" title="MVE-V500 Bandwidth" name="Bandwidth (write)" class="absolute" description="The amount of bytes written over the AXI bus"/>
+ <event counter="ARM_Mali-V500_evn0" title="MVE-V500 Sessions" name="Session created" description="Generated when a session has been created"/>
+ <event counter="ARM_Mali-V500_evn1" title="MVE-V500 Sessions" name="Session destroyed" description="Generated when a session has been destroyed"/>
+ <event counter="ARM_Mali-V500_evn2" title="MVE-V500 Frames" name="Frame Processed" description="Generated when the MVE has finished processing a frame"/>
+ <event counter="ARM_Mali-V500_evn3" title="MVE-V500 Output" name="Output buffer received" description="Generated when an an output buffer is returned to us from the MVE"/>
+ <event counter="ARM_Mali-V500_evn4" title="MVE-V500 Input" name="Input buffer received" description="Generated when we an input buffer is returned to us from the MVE"/>
+ <event counter="ARM_Mali-V500_act0" title="MVE-V500 Parsed" name="Activity" class="activity" activity1="activity" activity_color1="0x000000ff" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+ <event counter="ARM_Mali-V500_act1" title="MVE-V500 Piped" name="Activity" class="activity" activity1="activity" activity_color1="0x0000ff00" rendering_type="bar" average_selection="yes" average_cores="yes" percentage="yes" cores="8" description="Mali-V500 Activity"/>
+ </category>
diff --git a/tools/gator/daemon/events-Other.xml b/tools/gator/daemon/events-Other.xml
new file mode 100644
index 0000000..8aec282
--- /dev/null
+++ b/tools/gator/daemon/events-Other.xml
@@ -0,0 +1,33 @@
+ <counter_set name="Other_cnt" count="6"/>
+ <category name="Other" counter_set="Other_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="Other_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Instruction architecturally executed, condition code check pass, software increment"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Level 1 instruction cache refill"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Level 1 instruction TLB refill"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Level 1 data cache refill"/>
+ <event event="0x04" title="Cache" name="Data access" description="Level 1 data cache access"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Level 1 data TLB refill"/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Instruction architecturally executed, condition code check pass, load"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Instruction architecturally executed, condition code check pass, store"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exception taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Instruction architecturally executed, condition code check pass, exception return"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction architecturally executed, condition code check pass, write to CONTEXTIDR"/>
+ <event event="0x0c" title="Branch" name="PC change" description="Instruction architecturally executed, condition code check pass, software change of the PC"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Instruction architecturally executed, immediate branch"/>
+ <event event="0x0e" title="Procedure" name="Return" description="Instruction architecturally executed, condition code check pass, procedure return"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Instruction architecturally executed, condition code check pass, unaligned load or store"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Mispredicted or not predicted branch speculatively executed"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Predictable branch speculatively executed"/>
+ <event event="0x13" title="Memory" name="Memory access" description="Data memory access"/>
+ <event event="0x14" title="Cache" name="L1 inst access" description="Level 1 instruction cache access"/>
+ <event event="0x15" title="Cache" name="L1 data write" description="Level 1 data cache write-back"/>
+ <event event="0x16" title="Cache" name="L2 data access" description="Level 2 data cache access"/>
+ <event event="0x17" title="Cache" name="L2 data refill" description="Level 2 data cache refill"/>
+ <event event="0x18" title="Cache" name="L2 data write" description="Level 2 data cache write-back"/>
+ <event event="0x19" title="Bus" name="Access" description="Bus access"/>
+ <event event="0x1a" title="Memory" name="Error" description="Local memory error"/>
+ <event event="0x1b" title="Instruction" name="Speculative" description="Instruction speculatively executed"/>
+ <event event="0x1c" title="Memory" name="Translation table" description="Instruction architecturally executed, condition code check pass, write to TTBR"/>
+ <event event="0x1d" title="Bus" name="Cycle" description="Bus cycle"/>
+ </category>
diff --git a/tools/gator/daemon/events-Perf-Hardware.xml b/tools/gator/daemon/events-Perf-Hardware.xml
new file mode 100644
index 0000000..423696f
--- /dev/null
+++ b/tools/gator/daemon/events-Perf-Hardware.xml
@@ -0,0 +1,12 @@
+ <counter_set name="Perf_Hardware_cnt" count="6"/>
+ <category name="Perf Hardware" counter_set="Perf_Hardware_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="Perf_Hardware_ccnt" event="0" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="1" title="Instruction" name="Executed" description="Instruction executed"/>
+ <event event="2" title="Cache" name="References" description="Cache References"/>
+ <event event="3" title="Cache" name="Misses" description="Cache Misses"/>
+ <event event="4" title="Branch" name="Instructions" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="5" title="Branch" name="Misses" description="Branch mispredicted or not predicted"/>
+ <event event="6" title="Bus" name="Cycles" description="Bus Cycles"/>
+ <event event="7" title="Instruction" name="Stalled Frontend" description="Stalled Frontend Cycles"/>
+ <event event="8" title="Instruction" name="Stalled Backend" description="Stalled Backend Cycles"/>
+ </category>
diff --git a/tools/gator/daemon/events-Scorpion.xml b/tools/gator/daemon/events-Scorpion.xml
new file mode 100644
index 0000000..fa716fd
--- /dev/null
+++ b/tools/gator/daemon/events-Scorpion.xml
@@ -0,0 +1,107 @@
+ <counter_set name="Scorpion_cnt" count="4"/>
+ <category name="Scorpion" counter_set="Scorpion_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="Scorpion_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+ <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+ <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+ <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+ <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+ <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+ <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+ <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+ <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+ <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+ <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+ <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+ <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+ <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+ <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+ <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+ <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+ <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+ <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+ <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+ <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+ <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+ <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+ <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+ <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+ <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+ <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+ <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+ <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+ <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+ <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+ <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+ <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+ <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+ <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+ <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+ <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+ <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+ <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+ <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+ <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+ <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+ <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+ <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+ <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+ <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+ <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+ <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+ <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+ <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+ <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+ <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+ <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+ <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+ <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+ <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+ <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+ <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+ <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+ <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+ <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+ <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+ <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+ <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+ <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+ <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+ <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+ <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+ <event event="0x8e" title="Scorpion" name="BANK_AB_HIT" description="L2 hit rates bank A/B hits"/>
+ <event event="0x8f" title="Scorpion" name="BANK_AB_ACCESS" description="L2 hit rates bank A/B accesses"/>
+ <event event="0x90" title="Scorpion" name="BANK_CD_HIT" description="L2 hit rates bank C/D hits"/>
+ <event event="0x91" title="Scorpion" name="BANK_CD_ACCESS" description="L2 hit rates bank C/D accesses"/>
+ <event event="0x92" title="Scorpion" name="BANK_AB_DSIDE_HIT" description="L2 hit rates bank A/B d-side hits"/>
+ <event event="0x93" title="Scorpion" name="BANK_AB_DSIDE_ACCESS" description="L2 hit rates bank A/B d-side accesses"/>
+ <event event="0x94" title="Scorpion" name="BANK_CD_DSIDE_HIT" description="L2 hit rates bank C/D d-side hits"/>
+ <event event="0x95" title="Scorpion" name="BANK_CD_DSIDE_ACCESS" description="L2 hit rates bank C/D d-side accesses"/>
+ <event event="0x96" title="Scorpion" name="BANK_AB_ISIDE_HIT" description="L2 hit rates bank A/B i-side hits"/>
+ <event event="0x97" title="Scorpion" name="BANK_AB_ISIDE_ACCESS" description="L2 hit rates bank A/B i-side accesses"/>
+ <event event="0x98" title="Scorpion" name="BANK_CD_ISIDE_HIT" description="L2 hit rates bank C/D i-side hits"/>
+ <event event="0x99" title="Scorpion" name="BANK_CD_ISIDE_ACCESS" description="L2 hit rates bank C/D i-side accesses"/>
+ <event event="0x9a" title="Scorpion" name="ISIDE_RD_WAIT" description="fills and castouts cycles that i-side RD requests wait on data from bus"/>
+ <event event="0x9b" title="Scorpion" name="DSIDE_RD_WAIT" description="fills and castouts cycles that d-side RD requests wait on data from bus"/>
+ <event event="0x9c" title="Scorpion" name="BANK_BYPASS_WRITE" description="fills and castouts bank bypass writes"/>
+ <event event="0x9d" title="Scorpion" name="BANK_AB_NON_CASTOUT" description="fills and castouts bank A/B non-castout writes to bus"/>
+ <event event="0x9e" title="Scorpion" name="BANK_AB_L2_CASTOUT" description="fills and castouts bank A/B L2 castouts (granules)"/>
+ <event event="0x9f" title="Scorpion" name="BANK_CD_NON_CASTOUT" description="fills and castouts bank C/D non-castout writes to bus"/>
+ <event event="0xa0" title="Scorpion" name="BANK_CD_L2_CASTOUT" description="fills and castouts bank C/D L2 castouts (granules)"/>
+ </category>
diff --git a/tools/gator/daemon/events-ScorpionMP.xml b/tools/gator/daemon/events-ScorpionMP.xml
new file mode 100644
index 0000000..c648cce
--- /dev/null
+++ b/tools/gator/daemon/events-ScorpionMP.xml
@@ -0,0 +1,90 @@
+ <counter_set name="ScorpionMP_cnt" count="4"/>
+ <category name="ScorpionMP" counter_set="ScorpionMP_cnt" per_cpu="yes" supports_event_based_sampling="yes">
+ <event counter="ScorpionMP_ccnt" event="0xff" title="Clock" name="Cycles" display="hertz" units="Hz" average_selection="yes" average_cores="yes" description="The number of core clock cycles"/>
+ <event event="0x00" title="Software" name="Increment" description="Incremented only on writes to the Software Increment Register"/>
+ <event event="0x01" title="Cache" name="Instruction refill" description="Instruction fetch that causes a refill of at least the level of instruction or unified cache closest to the processor"/>
+ <event event="0x02" title="Cache" name="Inst TLB refill" description="Instruction fetch that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x03" title="Cache" name="Data refill" description="Memory Read or Write operation that causes a refill of at least the level of data or unified cache closest to the processor"/>
+ <event event="0x04" title="Cache" name="Data access" description="Memory Read or Write operation that causes a cache access to at least the level of data or unified cache closest to the processor"/>
+ <event event="0x05" title="Cache" name="Data TLB refill" description="Memory Read or Write operation that causes a TLB refill of at least the level of TLB closest to the processor"/>
+ <event event="0x06" title="Instruction" name="Memory read" description="Memory-reading instruction architecturally executed"/>
+ <event event="0x07" title="Instruction" name="Memory write" description="Memory-writing instruction architecturally executed"/>
+ <event event="0x08" title="Instruction" name="Executed" description="Instruction architecturally executed"/>
+ <event event="0x09" title="Exception" name="Taken" description="Exceptions taken"/>
+ <event event="0x0a" title="Exception" name="Return" description="Exception return architecturally executed"/>
+ <event event="0x0b" title="Instruction" name="CONTEXTIDR" description="Instruction that writes to the CONTEXTIDR architecturally executed"/>
+ <event event="0x0c" title="Program Counter" name="SW change" description="Software change of PC, except by an exception, architecturally executed"/>
+ <event event="0x0d" title="Branch" name="Immediate" description="Immediate branch architecturally executed"/>
+ <event event="0x0e" title="Branch" name="Procedure Return" description="Procedure return architecturally executed (not by exceptions)"/>
+ <event event="0x0f" title="Memory" name="Unaligned access" description="Unaligned access architecturally executed"/>
+ <event event="0x10" title="Branch" name="Mispredicted" description="Branch mispredicted or not predicted"/>
+ <event event="0x12" title="Branch" name="Potential prediction" description="Branch or other change in program flow that could have been predicted by the branch prediction resources of the processor"/>
+ <event event="0x4c" title="Scorpion" name="ICACHE_EXPL_INV" description="I-cache explicit invalidates"/>
+ <event event="0x4d" title="Scorpion" name="ICACHE_MISS" description="I-cache misses"/>
+ <event event="0x4e" title="Scorpion" name="ICACHE_ACCESS" description="I-cache accesses"/>
+ <event event="0x4f" title="Scorpion" name="ICACHE_CACHEREQ_L2" description="I-cache cacheable requests to L2"/>
+ <event event="0x50" title="Scorpion" name="ICACHE_NOCACHE_L2" description="I-cache non-cacheable requests to L2"/>
+ <event event="0x51" title="Scorpion" name="HIQUP_NOPED" description="Conditional instructions HIQUPs NOPed"/>
+ <event event="0x52" title="Scorpion" name="DATA_ABORT" description="Interrupts and Exceptions Data Abort"/>
+ <event event="0x53" title="Scorpion" name="IRQ" description="Interrupts and Exceptions IRQ"/>
+ <event event="0x54" title="Scorpion" name="FIQ" description="Interrupts and Exceptions FIQ"/>
+ <event event="0x55" title="Scorpion" name="ALL_EXCPT" description="Interrupts and Exceptions All interrupts"/>
+ <event event="0x56" title="Scorpion" name="UNDEF" description="Interrupts and Exceptions Undefined"/>
+ <event event="0x57" title="Scorpion" name="SVC" description="Interrupts and Exceptions SVC"/>
+ <event event="0x58" title="Scorpion" name="SMC" description="Interrupts and Exceptions SMC"/>
+ <event event="0x59" title="Scorpion" name="PREFETCH_ABORT" description="Interrupts and Exceptions Prefetch Abort"/>
+ <event event="0x5a" title="Scorpion" name="INDEX_CHECK" description="Interrupts and Exceptions Index Check"/>
+ <event event="0x5b" title="Scorpion" name="NULL_CHECK" description="Interrupts and Exceptions Null Check"/>
+ <event event="0x5c" title="Scorpion" name="EXPL_ICIALLU" description="I-cache and BTAC Invalidates Explicit ICIALLU"/>
+ <event event="0x5d" title="Scorpion" name="IMPL_ICIALLU" description="I-cache and BTAC Invalidates Implicit ICIALLU"/>
+ <event event="0x5e" title="Scorpion" name="NONICIALLU_BTAC_INV" description="I-cache and BTAC Invalidates Non-ICIALLU BTAC Invalidate"/>
+ <event event="0x5f" title="Scorpion" name="ICIMVAU_IMPL_ICIALLU" description="I-cache and BTAC Invalidates ICIMVAU-implied ICIALLU"/>
+ <event event="0x60" title="Scorpion" name="SPIPE_ONLY_CYCLES" description="Issue S-pipe only issue cycles"/>
+ <event event="0x61" title="Scorpion" name="XPIPE_ONLY_CYCLES" description="Issue X-pipe only issue cycles"/>
+ <event event="0x62" title="Scorpion" name="DUAL_CYCLES" description="Issue dual issue cycles"/>
+ <event event="0x63" title="Scorpion" name="DISPATCH_ANY_CYCLES" description="Dispatch any dispatch cycles"/>
+ <event event="0x64" title="Scorpion" name="FIFO_FULLBLK_CMT" description="Commits Trace FIFO full Blk CMT"/>
+ <event event="0x65" title="Scorpion" name="FAIL_COND_INST" description="Conditional instructions failing conditional instrs (excluding branches)"/>
+ <event event="0x66" title="Scorpion" name="PASS_COND_INST" description="Conditional instructions passing conditional instrs (excluding branches)"/>
+ <event event="0x67" title="Scorpion" name="ALLOW_VU_CLK" description="Unit Clock Gating Allow VU Clks"/>
+ <event event="0x68" title="Scorpion" name="VU_IDLE" description="Unit Clock Gating VU Idle"/>
+ <event event="0x69" title="Scorpion" name="ALLOW_L2_CLK" description="Unit Clock Gating Allow L2 Clks"/>
+ <event event="0x6a" title="Scorpion" name="L2_IDLE" description="Unit Clock Gating L2 Idle"/>
+ <event event="0x6b" title="Scorpion" name="DTLB_IMPL_INV_SCTLR_DACR" description="DTLB implicit invalidates writes to SCTLR and DACR"/>
+ <event event="0x6c" title="Scorpion" name="DTLB_EXPL_INV" description="DTLB explicit invalidates"/>
+ <event event="0x6d" title="Scorpion" name="DTLB_MISS" description="DTLB misses"/>
+ <event event="0x6e" title="Scorpion" name="DTLB_ACCESS" description="DTLB accesses"/>
+ <event event="0x6f" title="Scorpion" name="ITLB_MISS" description="ITLB misses"/>
+ <event event="0x70" title="Scorpion" name="ITLB_IMPL_INV" description="ITLB implicit ITLB invalidates"/>
+ <event event="0x71" title="Scorpion" name="ITLB_EXPL_INV" description="ITLB explicit ITLB invalidates"/>
+ <event event="0x72" title="Scorpion" name="UTLB_D_MISS" description="UTLB d-side misses"/>
+ <event event="0x73" title="Scorpion" name="UTLB_D_ACCESS" description="UTLB d-side accesses"/>
+ <event event="0x74" title="Scorpion" name="UTLB_I_MISS" description="UTLB i-side misses"/>
+ <event event="0x75" title="Scorpion" name="UTLB_I_ACCESS" description="UTLB i-side accesses"/>
+ <event event="0x76" title="Scorpion" name="UTLB_INV_ASID" description="UTLB invalidate by ASID"/>
+ <event event="0x77" title="Scorpion" name="UTLB_INV_MVA" description="UTLB invalidate by MVA"/>
+ <event event="0x78" title="Scorpion" name="UTLB_INV_ALL" description="UTLB invalidate all"/>
+ <event event="0x79" title="Scorpion" name="S2_HOLD_RDQ_UNAVAIL" description="S2 hold RDQ unavail"/>
+ <event event="0x7a" title="Scorpion" name="S2_HOLD" description="S2 hold"/>
+ <event event="0x7b" title="Scorpion" name="S2_HOLD_DEV_OP" description="S2 hold device op"/>
+ <event event="0x7c" title="Scorpion" name="S2_HOLD_ORDER" description="S2 hold strongly ordered op"/>
+ <event event="0x7d" title="Scorpion" name="S2_HOLD_BARRIER" description="S2 hold barrier"/>
+ <event event="0x7e" title="Scorpion" name="VIU_DUAL_CYCLE" description="Scorpion VIU dual cycle"/>
+ <event event="0x7f" title="Scorpion" name="VIU_SINGLE_CYCLE" description="Scorpion VIU single cycle"/>
+ <event event="0x80" title="Scorpion" name="VX_PIPE_WAR_STALL_CYCLES" description="Scorpion VX pipe WAR cycles"/>
+ <event event="0x81" title="Scorpion" name="VX_PIPE_WAW_STALL_CYCLES" description="Scorpion VX pipe WAW cycles"/>
+ <event event="0x82" title="Scorpion" name="VX_PIPE_RAW_STALL_CYCLES" description="Scorpion VX pipe RAW cycles"/>
+ <event event="0x83" title="Scorpion" name="VX_PIPE_LOAD_USE_STALL" description="Scorpion VX pipe load use stall"/>
+ <event event="0x84" title="Scorpion" name="VS_PIPE_WAR_STALL_CYCLES" description="Scorpion VS pipe WAR stall cycles"/>
+ <event event="0x85" title="Scorpion" name="VS_PIPE_WAW_STALL_CYCLES" description="Scorpion VS pipe WAW stall cycles"/>
+ <event event="0x86" title="Scorpion" name="VS_PIPE_RAW_STALL_CYCLES" description="Scorpion VS pipe RAW stall cycles"/>
+ <event event="0x87" title="Scorpion" name="EXCEPTIONS_INV_OPERATION" description="Scorpion invalid operation exceptions"/>
+ <event event="0x88" title="Scorpion" name="EXCEPTIONS_DIV_BY_ZERO" description="Scorpion divide by zero exceptions"/>
+ <event event="0x89" title="Scorpion" name="COND_INST_FAIL_VX_PIPE" description="Scorpion conditional instruction fail VX pipe"/>
+ <event event="0x8a" title="Scorpion" name="COND_INST_FAIL_VS_PIPE" description="Scorpion conditional instruction fail VS pipe"/>
+ <event event="0x8b" title="Scorpion" name="EXCEPTIONS_OVERFLOW" description="Scorpion overflow exceptions"/>
+ <event event="0x8c" title="Scorpion" name="EXCEPTIONS_UNDERFLOW" description="Scorpion underflow exceptions"/>
+ <event event="0x8d" title="Scorpion" name="EXCEPTIONS_DENORM" description="Scorpion denorm exceptions"/>
+ <event event="0x8e" title="ScorpionMP" name="NUM_BARRIERS" description="Barriers"/>
+ <event event="0x8f" title="ScorpionMP" name="BARRIER_CYCLES" description="Barrier cycles"/>
+ </category>
diff --git a/tools/gator/daemon/events-ftrace.xml b/tools/gator/daemon/events-ftrace.xml
new file mode 100644
index 0000000..ae5529f
--- /dev/null
+++ b/tools/gator/daemon/events-ftrace.xml
@@ -0,0 +1,22 @@
+ <category name="Ftrace">
+ <!--
+ Ftrace counters require Linux 3.10 or later. If you do you see ftrace counters in counter configuration, please check your Linux version.
+ 'counter' attribute must start with ftrace_ and be unique
+ the regex item in () is the value shown or, if the parentheses are missing, the number of regex matches is counted
+ 'enable' (optional) is the ftrace event to enable associated with the gator event
+ -->
+ <!--
+ <event counter="ftrace_trace_marker_numbers" title="ftrace" name="trace_marker" regex="^tracing_mark_write: ([0-9]+)\s$" class="absolute" description="Numbers written to /sys/kernel/debug/tracing/trace_marker, ex: echo 42 > /sys/kernel/debug/tracing/trace_marker"/>
+ -->
+
+ <!-- ftrace counters -->
+ <event counter="ftrace_kmem_kmalloc" title="Kmem" name="kmalloc" regex="^kmalloc:.* bytes_alloc=([0-9]+) " enable="kmem/kmalloc" class="incident" description="Number of bytes allocated in the kernel using kmalloc"/>
+ <event counter="ftrace_ext4_ext4_da_write" title="Ext4" name="ext4_da_write" regex="^ext4_da_write_end:.* len ([0-9]+) " enable="ext4/ext4_da_write_end" class="incident" description="Number of bytes written to an ext4 filesystem"/>
+ <event counter="ftrace_f2fs_f2fs_write" title="F2FS" name="f2fs_write" regex="^f2fs_write_end:.* len ([0-9]+), " enable="f2fs/f2fs_write_end" class="incident" description="Number of bytes written to an f2fs filesystem"/>
+ <event counter="ftrace_power_clock_set_rate" title="Power" name="clock_set_rate" regex="^clock_set_rate:.* state=([0-9]+) " enable="power/clock_set_rate" class="absolute" description="Clock rate state"/>
+
+ <!-- counting ftrace counters -->
+ <event counter="ftrace_block_block_rq_complete" title="Block" name="block_rq_complete" regex="^block_rq_complete: " enable="block/block_rq_complete" class="delta" description="Number of block IO operations completed by device driver"/>
+ <event counter="ftrace_block_block_rq_issue" title="Block" name="block_rq_issue" regex="^block_rq_issue: " enable="block/block_rq_issue" class="delta" description="Number of block IO operations issued to device driver"/>
+ <event counter="ftrace_power_cpu_idle" title="Power" name="cpu_idle" regex="^cpu_idle: " enable="power/cpu_idle" class="delta" description="Number of times cpu_idle is entered or exited"/>
+ </category>
diff --git a/tools/gator/daemon/events_footer.xml b/tools/gator/daemon/events_footer.xml
new file mode 100644
index 0000000..cd2b446
--- /dev/null
+++ b/tools/gator/daemon/events_footer.xml
@@ -0,0 +1 @@
+</events>
diff --git a/tools/gator/daemon/events_header.xml b/tools/gator/daemon/events_header.xml
new file mode 100644
index 0000000..38ec4c0
--- /dev/null
+++ b/tools/gator/daemon/events_header.xml
@@ -0,0 +1,2 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<events>
diff --git a/tools/gator/daemon/k/perf_event.3.12.h b/tools/gator/daemon/k/perf_event.3.12.h
new file mode 100644
index 0000000..e886c48
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.3.12.h
@@ -0,0 +1,792 @@
+/*
+ * Performance events:
+ *
+ * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
+ * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
+ *
+ * Data type definitions, declarations, prototypes.
+ *
+ * Started by: Thomas Gleixner and Ingo Molnar
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_EVENT_H
+#define _LINUX_PERF_EVENT_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+ PERF_TYPE_HARDWARE = 0,
+ PERF_TYPE_SOFTWARE = 1,
+ PERF_TYPE_TRACEPOINT = 2,
+ PERF_TYPE_HW_CACHE = 3,
+ PERF_TYPE_RAW = 4,
+ PERF_TYPE_BREAKPOINT = 5,
+
+ PERF_TYPE_MAX, /* non-ABI */
+};
+
+/*
+ * Generalized performance event event_id types, used by the
+ * attr.event_id parameter of the sys_perf_event_open()
+ * syscall:
+ */
+enum perf_hw_id {
+ /*
+ * Common hardware events, generalized by the kernel:
+ */
+ PERF_COUNT_HW_CPU_CYCLES = 0,
+ PERF_COUNT_HW_INSTRUCTIONS = 1,
+ PERF_COUNT_HW_CACHE_REFERENCES = 2,
+ PERF_COUNT_HW_CACHE_MISSES = 3,
+ PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4,
+ PERF_COUNT_HW_BRANCH_MISSES = 5,
+ PERF_COUNT_HW_BUS_CYCLES = 6,
+ PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7,
+ PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8,
+ PERF_COUNT_HW_REF_CPU_CYCLES = 9,
+
+ PERF_COUNT_HW_MAX, /* non-ABI */
+};
+
+/*
+ * Generalized hardware cache events:
+ *
+ * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
+ * { read, write, prefetch } x
+ * { accesses, misses }
+ */
+enum perf_hw_cache_id {
+ PERF_COUNT_HW_CACHE_L1D = 0,
+ PERF_COUNT_HW_CACHE_L1I = 1,
+ PERF_COUNT_HW_CACHE_LL = 2,
+ PERF_COUNT_HW_CACHE_DTLB = 3,
+ PERF_COUNT_HW_CACHE_ITLB = 4,
+ PERF_COUNT_HW_CACHE_BPU = 5,
+ PERF_COUNT_HW_CACHE_NODE = 6,
+
+ PERF_COUNT_HW_CACHE_MAX, /* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+ PERF_COUNT_HW_CACHE_OP_READ = 0,
+ PERF_COUNT_HW_CACHE_OP_WRITE = 1,
+ PERF_COUNT_HW_CACHE_OP_PREFETCH = 2,
+
+ PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+ PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0,
+ PERF_COUNT_HW_CACHE_RESULT_MISS = 1,
+
+ PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */
+};
+
+/*
+ * Special "software" events provided by the kernel, even if the hardware
+ * does not support performance events. These events measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+ PERF_COUNT_SW_CPU_CLOCK = 0,
+ PERF_COUNT_SW_TASK_CLOCK = 1,
+ PERF_COUNT_SW_PAGE_FAULTS = 2,
+ PERF_COUNT_SW_CONTEXT_SWITCHES = 3,
+ PERF_COUNT_SW_CPU_MIGRATIONS = 4,
+ PERF_COUNT_SW_PAGE_FAULTS_MIN = 5,
+ PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6,
+ PERF_COUNT_SW_ALIGNMENT_FAULTS = 7,
+ PERF_COUNT_SW_EMULATION_FAULTS = 8,
+ PERF_COUNT_SW_DUMMY = 9,
+
+ PERF_COUNT_SW_MAX, /* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_event_sample_format {
+ PERF_SAMPLE_IP = 1U << 0,
+ PERF_SAMPLE_TID = 1U << 1,
+ PERF_SAMPLE_TIME = 1U << 2,
+ PERF_SAMPLE_ADDR = 1U << 3,
+ PERF_SAMPLE_READ = 1U << 4,
+ PERF_SAMPLE_CALLCHAIN = 1U << 5,
+ PERF_SAMPLE_ID = 1U << 6,
+ PERF_SAMPLE_CPU = 1U << 7,
+ PERF_SAMPLE_PERIOD = 1U << 8,
+ PERF_SAMPLE_STREAM_ID = 1U << 9,
+ PERF_SAMPLE_RAW = 1U << 10,
+ PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
+ PERF_SAMPLE_WEIGHT = 1U << 14,
+ PERF_SAMPLE_DATA_SRC = 1U << 15,
+ PERF_SAMPLE_IDENTIFIER = 1U << 16,
+
+ PERF_SAMPLE_MAX = 1U << 17, /* non-ABI */
+};
+
+/*
+ * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set
+ *
+ * If the user does not pass priv level information via branch_sample_type,
+ * the kernel uses the event's priv level. Branch and event priv levels do
+ * not have to match. Branch priv level is checked for permissions.
+ *
+ * The branch types can be combined, however BRANCH_ANY covers all types
+ * of branches and therefore it supersedes all the other types.
+ */
+enum perf_branch_sample_type {
+ PERF_SAMPLE_BRANCH_USER = 1U << 0, /* user branches */
+ PERF_SAMPLE_BRANCH_KERNEL = 1U << 1, /* kernel branches */
+ PERF_SAMPLE_BRANCH_HV = 1U << 2, /* hypervisor branches */
+
+ PERF_SAMPLE_BRANCH_ANY = 1U << 3, /* any branch types */
+ PERF_SAMPLE_BRANCH_ANY_CALL = 1U << 4, /* any call branch */
+ PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << 5, /* any return branch */
+ PERF_SAMPLE_BRANCH_IND_CALL = 1U << 6, /* indirect calls */
+ PERF_SAMPLE_BRANCH_ABORT_TX = 1U << 7, /* transaction aborts */
+ PERF_SAMPLE_BRANCH_IN_TX = 1U << 8, /* in transaction */
+ PERF_SAMPLE_BRANCH_NO_TX = 1U << 9, /* not in transaction */
+
+ PERF_SAMPLE_BRANCH_MAX = 1U << 10, /* non-ABI */
+};
+
+#define PERF_SAMPLE_BRANCH_PLM_ALL \
+ (PERF_SAMPLE_BRANCH_USER|\
+ PERF_SAMPLE_BRANCH_KERNEL|\
+ PERF_SAMPLE_BRANCH_HV)
+
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+ PERF_SAMPLE_REGS_ABI_NONE = 0,
+ PERF_SAMPLE_REGS_ABI_32 = 1,
+ PERF_SAMPLE_REGS_ABI_64 = 2,
+};
+
+/*
+ * The format of the data returned by read() on a perf event fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ * { u64 value;
+ * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ * { u64 id; } && PERF_FORMAT_ID
+ * } && !PERF_FORMAT_GROUP
+ *
+ * { u64 nr;
+ * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
+ * { u64 value;
+ * { u64 id; } && PERF_FORMAT_ID
+ * } cntr[nr];
+ * } && PERF_FORMAT_GROUP
+ * };
+ */
+enum perf_event_read_format {
+ PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0,
+ PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1,
+ PERF_FORMAT_ID = 1U << 2,
+ PERF_FORMAT_GROUP = 1U << 3,
+
+ PERF_FORMAT_MAX = 1U << 4, /* non-ABI */
+};
+
+#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
+#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
+#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
+ /* add: sample_stack_user */
+
+/*
+ * Hardware event_id to monitor via a performance monitoring event:
+ */
+struct perf_event_attr {
+
+ /*
+ * Major type: hardware/software/tracepoint/etc.
+ */
+ __u32 type;
+
+ /*
+ * Size of the attr structure, for fwd/bwd compat.
+ */
+ __u32 size;
+
+ /*
+ * Type specific configuration information.
+ */
+ __u64 config;
+
+ union {
+ __u64 sample_period;
+ __u64 sample_freq;
+ };
+
+ __u64 sample_type;
+ __u64 read_format;
+
+ __u64 disabled : 1, /* off by default */
+ inherit : 1, /* children inherit it */
+ pinned : 1, /* must always be on PMU */
+ exclusive : 1, /* only group on PMU */
+ exclude_user : 1, /* don't count user */
+ exclude_kernel : 1, /* ditto kernel */
+ exclude_hv : 1, /* ditto hypervisor */
+ exclude_idle : 1, /* don't count when idle */
+ mmap : 1, /* include mmap data */
+ comm : 1, /* include comm data */
+ freq : 1, /* use freq, not period */
+ inherit_stat : 1, /* per task counts */
+ enable_on_exec : 1, /* next exec enables */
+ task : 1, /* trace fork/exit */
+ watermark : 1, /* wakeup_watermark */
+ /*
+ * precise_ip:
+ *
+ * 0 - SAMPLE_IP can have arbitrary skid
+ * 1 - SAMPLE_IP must have constant skid
+ * 2 - SAMPLE_IP requested to have 0 skid
+ * 3 - SAMPLE_IP must have 0 skid
+ *
+ * See also PERF_RECORD_MISC_EXACT_IP
+ */
+ precise_ip : 2, /* skid constraint */
+ mmap_data : 1, /* non-exec mmap data */
+ sample_id_all : 1, /* sample_type all events */
+
+ exclude_host : 1, /* don't count in host */
+ exclude_guest : 1, /* don't count in guest */
+
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+ mmap2 : 1, /* include mmap with inode data */
+
+ __reserved_1 : 40;
+
+ union {
+ __u32 wakeup_events; /* wakeup every n events */
+ __u32 wakeup_watermark; /* bytes before wakeup */
+ };
+
+ __u32 bp_type;
+ union {
+ __u64 bp_addr;
+ __u64 config1; /* extension of config */
+ };
+ union {
+ __u64 bp_len;
+ __u64 config2; /* extension of config1 */
+ };
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ /* Align to u64. */
+ __u32 __reserved_2;
+};
+
+#define perf_flags(attr) (*(&(attr)->read_format + 1))
+
+/*
+ * Ioctls that can be done on a perf event fd:
+ */
+#define PERF_EVENT_IOC_ENABLE _IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE _IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH _IO ('$', 2)
+#define PERF_EVENT_IOC_RESET _IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *)
+
+enum perf_event_ioc_flags {
+ PERF_IOC_FLAG_GROUP = 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_event_mmap_page {
+ __u32 version; /* version number of this structure */
+ __u32 compat_version; /* lowest version this is compat with */
+
+ /*
+ * Bits needed to read the hw events in user-space.
+ *
+ * u32 seq, time_mult, time_shift, idx, width;
+ * u64 count, enabled, running;
+ * u64 cyc, time_offset;
+ * s64 pmc = 0;
+ *
+ * do {
+ * seq = pc->lock;
+ * barrier()
+ *
+ * enabled = pc->time_enabled;
+ * running = pc->time_running;
+ *
+ * if (pc->cap_usr_time && enabled != running) {
+ * cyc = rdtsc();
+ * time_offset = pc->time_offset;
+ * time_mult = pc->time_mult;
+ * time_shift = pc->time_shift;
+ * }
+ *
+ * idx = pc->index;
+ * count = pc->offset;
+ * if (pc->cap_usr_rdpmc && idx) {
+ * width = pc->pmc_width;
+ * pmc = rdpmc(idx - 1);
+ * }
+ *
+ * barrier();
+ * } while (pc->lock != seq);
+ *
+ * NOTE: for obvious reason this only works on self-monitoring
+ * processes.
+ */
+ __u32 lock; /* seqlock for synchronization */
+ __u32 index; /* hardware event identifier */
+ __s64 offset; /* add to hardware event value */
+ __u64 time_enabled; /* time event active */
+ __u64 time_running; /* time event on cpu */
+ union {
+ __u64 capabilities;
+ struct {
+ __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */
+ cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */
+
+ cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */
+ cap_user_time : 1, /* The time_* fields are used */
+ cap_user_time_zero : 1, /* The time_zero field is used */
+ cap_____res : 59;
+ };
+ };
+
+ /*
+ * If cap_usr_rdpmc this field provides the bit-width of the value
+ * read using the rdpmc() or equivalent instruction. This can be used
+ * to sign extend the result like:
+ *
+ * pmc <<= 64 - width;
+ * pmc >>= 64 - width; // signed shift right
+ * count += pmc;
+ */
+ __u16 pmc_width;
+
+ /*
+ * If cap_usr_time the below fields can be used to compute the time
+ * delta since time_enabled (in ns) using rdtsc or similar.
+ *
+ * u64 quot, rem;
+ * u64 delta;
+ *
+ * quot = (cyc >> time_shift);
+ * rem = cyc & ((1 << time_shift) - 1);
+ * delta = time_offset + quot * time_mult +
+ * ((rem * time_mult) >> time_shift);
+ *
+ * Where time_offset,time_mult,time_shift and cyc are read in the
+ * seqcount loop described above. This delta can then be added to
+ * enabled and possible running (if idx), improving the scaling:
+ *
+ * enabled += delta;
+ * if (idx)
+ * running += delta;
+ *
+ * quot = count / running;
+ * rem = count % running;
+ * count = quot * enabled + (rem * enabled) / running;
+ */
+ __u16 time_shift;
+ __u32 time_mult;
+ __u64 time_offset;
+ /*
+ * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+ * from sample timestamps.
+ *
+ * time = timestamp - time_zero;
+ * quot = time / time_mult;
+ * rem = time % time_mult;
+ * cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+ *
+ * And vice versa:
+ *
+ * quot = cyc >> time_shift;
+ * rem = cyc & ((1 << time_shift) - 1);
+ * timestamp = time_zero + quot * time_mult +
+ * ((rem * time_mult) >> time_shift);
+ */
+ __u64 time_zero;
+ __u32 size; /* Header size up to __reserved[] fields. */
+
+ /*
+ * Hole for extension of the self monitor capabilities
+ */
+
+ __u8 __reserved[118*8+4]; /* align to 1k. */
+
+ /*
+ * Control data for the mmap() data buffer.
+ *
+ * User-space reading the @data_head value should issue an smp_rmb(),
+ * after reading this value.
+ *
+ * When the mapping is PROT_WRITE the @data_tail value should be
+ * written by userspace to reflect the last read data, after issueing
+ * an smp_mb() to separate the data read from the ->data_tail store.
+ * In this case the kernel will not over-write unread data.
+ *
+ * See perf_output_put_handle() for the data ordering.
+ */
+ __u64 data_head; /* head in the data section */
+ __u64 data_tail; /* user-space written tail */
+};
+
+#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0)
+#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0)
+#define PERF_RECORD_MISC_KERNEL (1 << 0)
+#define PERF_RECORD_MISC_USER (2 << 0)
+#define PERF_RECORD_MISC_HYPERVISOR (3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
+
+#define PERF_RECORD_MISC_MMAP_DATA (1 << 13)
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15)
+
+struct perf_event_header {
+ __u32 type;
+ __u16 misc;
+ __u16 size;
+};
+
+enum perf_event_type {
+
+ /*
+ * If perf_event_attr.sample_id_all is set then all event types will
+ * have the sample_type selected fields related to where/when
+ * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+ * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+ * just after the perf_event_header and the fields already present for
+ * the existing fields, i.e. at the end of the payload. That way a newer
+ * perf.data file will be supported by older perf tools, with these new
+ * optional fields being ignored.
+ *
+ * struct sample_id {
+ * { u32 pid, tid; } && PERF_SAMPLE_TID
+ * { u64 time; } && PERF_SAMPLE_TIME
+ * { u64 id; } && PERF_SAMPLE_ID
+ * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
+ * { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
+ * } && perf_event_attr::sample_id_all
+ *
+ * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The
+ * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+ * relative to header.size.
+ */
+
+ /*
+ * The MMAP events record the PROT_EXEC mappings so that we can
+ * correlate userspace IPs to code. They have the following structure:
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * u64 addr;
+ * u64 len;
+ * u64 pgoff;
+ * char filename[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_MMAP = 1,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u64 id;
+ * u64 lost;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_LOST = 2,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * char comm[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_COMM = 3,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, ppid;
+ * u32 tid, ptid;
+ * u64 time;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_EXIT = 4,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u64 time;
+ * u64 id;
+ * u64 stream_id;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_THROTTLE = 5,
+ PERF_RECORD_UNTHROTTLE = 6,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, ppid;
+ * u32 tid, ptid;
+ * u64 time;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_FORK = 7,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid, tid;
+ *
+ * struct read_format values;
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_READ = 8,
+
+ /*
+ * struct {
+ * struct perf_event_header header;
+ *
+ * #
+ * # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+ * # The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+ * # is fixed relative to header.
+ * #
+ *
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
+ * { u64 ip; } && PERF_SAMPLE_IP
+ * { u32 pid, tid; } && PERF_SAMPLE_TID
+ * { u64 time; } && PERF_SAMPLE_TIME
+ * { u64 addr; } && PERF_SAMPLE_ADDR
+ * { u64 id; } && PERF_SAMPLE_ID
+ * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
+ * { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * { u64 period; } && PERF_SAMPLE_PERIOD
+ *
+ * { struct read_format values; } && PERF_SAMPLE_READ
+ *
+ * { u64 nr,
+ * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN
+ *
+ * #
+ * # The RAW record below is opaque data wrt the ABI
+ * #
+ * # That is, the ABI doesn't make any promises wrt to
+ * # the stability of its content, it may vary depending
+ * # on event, hardware, kernel version and phase of
+ * # the moon.
+ * #
+ * # In other words, PERF_SAMPLE_RAW contents are not an ABI.
+ * #
+ *
+ * { u32 size;
+ * char data[size];}&& PERF_SAMPLE_RAW
+ *
+ * { u64 nr;
+ * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
+ *
+ * { u64 weight; } && PERF_SAMPLE_WEIGHT
+ * { u64 data_src; } && PERF_SAMPLE_DATA_SRC
+ * };
+ */
+ PERF_RECORD_SAMPLE = 9,
+
+ /*
+ * The MMAP2 records are an augmented version of MMAP, they add
+ * maj, min, ino numbers to be used to uniquely identify each mapping
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * u64 addr;
+ * u64 len;
+ * u64 pgoff;
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * char filename[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_MMAP2 = 10,
+
+ PERF_RECORD_MAX, /* non-ABI */
+};
+
+#define PERF_MAX_STACK_DEPTH 127
+
+enum perf_callchain_context {
+ PERF_CONTEXT_HV = (__u64)-32,
+ PERF_CONTEXT_KERNEL = (__u64)-128,
+ PERF_CONTEXT_USER = (__u64)-512,
+
+ PERF_CONTEXT_GUEST = (__u64)-2048,
+ PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176,
+ PERF_CONTEXT_GUEST_USER = (__u64)-2560,
+
+ PERF_CONTEXT_MAX = (__u64)-4095,
+};
+
+#define PERF_FLAG_FD_NO_GROUP (1U << 0)
+#define PERF_FLAG_FD_OUTPUT (1U << 1)
+#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */
+
+union perf_mem_data_src {
+ __u64 val;
+ struct {
+ __u64 mem_op:5, /* type of opcode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_snoop:5, /* snoop mode */
+ mem_lock:2, /* lock instr */
+ mem_dtlb:7, /* tlb access */
+ mem_rsvd:31;
+ };
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA 0x01 /* not available */
+#define PERF_MEM_OP_LOAD 0x02 /* load instruction */
+#define PERF_MEM_OP_STORE 0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT 0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA 0x01 /* not available */
+#define PERF_MEM_LVL_HIT 0x02 /* hit level */
+#define PERF_MEM_LVL_MISS 0x04 /* miss level */
+#define PERF_MEM_LVL_L1 0x08 /* L1 */
+#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2 0x20 /* L2 */
+#define PERF_MEM_LVL_L3 0x40 /* L3 */
+#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT 5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA 0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT 19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA 0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT 24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA 0x01 /* not available */
+#define PERF_MEM_TLB_HIT 0x02 /* hit level */
+#define PERF_MEM_TLB_MISS 0x04 /* miss level */
+#define PERF_MEM_TLB_L1 0x08 /* L1 */
+#define PERF_MEM_TLB_L2 0x10 /* L2 */
+#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT 26
+
+#define PERF_MEM_S(a, s) \
+ (((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
+/*
+ * single taken branch record layout:
+ *
+ * from: source instruction (may not always be a branch insn)
+ * to: branch target
+ * mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ * in_tx: running in a hardware transaction
+ * abort: aborting a hardware transaction
+ */
+struct perf_branch_entry {
+ __u64 from;
+ __u64 to;
+ __u64 mispred:1, /* target mispredicted */
+ predicted:1,/* target predicted */
+ in_tx:1, /* in transaction */
+ abort:1, /* transaction abort */
+ reserved:60;
+};
+
+#endif /* _LINUX_PERF_EVENT_H */
diff --git a/tools/gator/daemon/k/perf_event.h b/tools/gator/daemon/k/perf_event.h
new file mode 120000
index 0000000..e5dff8c
--- /dev/null
+++ b/tools/gator/daemon/k/perf_event.h
@@ -0,0 +1 @@
+perf_event.3.12.h
\ No newline at end of file
diff --git a/tools/gator/daemon/libsensors/COPYING.LGPL b/tools/gator/daemon/libsensors/COPYING.LGPL
new file mode 100644
index 0000000..4362b49
--- /dev/null
+++ b/tools/gator/daemon/libsensors/COPYING.LGPL
@@ -0,0 +1,502 @@
+ GNU LESSER GENERAL PUBLIC LICENSE
+ Version 2.1, February 1999
+
+ Copyright (C) 1991, 1999 Free Software Foundation, Inc.
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+[This is the first released version of the Lesser GPL. It also counts
+ as the successor of the GNU Library Public License, version 2, hence
+ the version number 2.1.]
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+ This license, the Lesser General Public License, applies to some
+specially designated software packages--typically libraries--of the
+Free Software Foundation and other authors who decide to use it. You
+can use it too, but we suggest you first think carefully about whether
+this license or the ordinary General Public License is the better
+strategy to use in any particular case, based on the explanations below.
+
+ When we speak of free software, we are referring to freedom of use,
+not price. Our General Public Licenses are designed to make sure that
+you have the freedom to distribute copies of free software (and charge
+for this service if you wish); that you receive source code or can get
+it if you want it; that you can change the software and use pieces of
+it in new free programs; and that you are informed that you can do
+these things.
+
+ To protect your rights, we need to make restrictions that forbid
+distributors to deny you these rights or to ask you to surrender these
+rights. These restrictions translate to certain responsibilities for
+you if you distribute copies of the library or if you modify it.
+
+ For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you. You must make sure that they, too, receive or can get the source
+code. If you link other code with the library, you must provide
+complete object files to the recipients, so that they can relink them
+with the library after making changes to the library and recompiling
+it. And you must show them these terms so they know their rights.
+
+ We protect your rights with a two-step method: (1) we copyright the
+library, and (2) we offer you this license, which gives you legal
+permission to copy, distribute and/or modify the library.
+
+ To protect each distributor, we want to make it very clear that
+there is no warranty for the free library. Also, if the library is
+modified by someone else and passed on, the recipients should know
+that what they have is not the original version, so that the original
+author's reputation will not be affected by problems that might be
+introduced by others.
+
+ Finally, software patents pose a constant threat to the existence of
+any free program. We wish to make sure that a company cannot
+effectively restrict the users of a free program by obtaining a
+restrictive license from a patent holder. Therefore, we insist that
+any patent license obtained for a version of the library must be
+consistent with the full freedom of use specified in this license.
+
+ Most GNU software, including some libraries, is covered by the
+ordinary GNU General Public License. This license, the GNU Lesser
+General Public License, applies to certain designated libraries, and
+is quite different from the ordinary General Public License. We use
+this license for certain libraries in order to permit linking those
+libraries into non-free programs.
+
+ When a program is linked with a library, whether statically or using
+a shared library, the combination of the two is legally speaking a
+combined work, a derivative of the original library. The ordinary
+General Public License therefore permits such linking only if the
+entire combination fits its criteria of freedom. The Lesser General
+Public License permits more lax criteria for linking other code with
+the library.
+
+ We call this license the "Lesser" General Public License because it
+does Less to protect the user's freedom than the ordinary General
+Public License. It also provides other free software developers Less
+of an advantage over competing non-free programs. These disadvantages
+are the reason we use the ordinary General Public License for many
+libraries. However, the Lesser license provides advantages in certain
+special circumstances.
+
+ For example, on rare occasions, there may be a special need to
+encourage the widest possible use of a certain library, so that it becomes
+a de-facto standard. To achieve this, non-free programs must be
+allowed to use the library. A more frequent case is that a free
+library does the same job as widely used non-free libraries. In this
+case, there is little to gain by limiting the free library to free
+software only, so we use the Lesser General Public License.
+
+ In other cases, permission to use a particular library in non-free
+programs enables a greater number of people to use a large body of
+free software. For example, permission to use the GNU C Library in
+non-free programs enables many more people to use the whole GNU
+operating system, as well as its variant, the GNU/Linux operating
+system.
+
+ Although the Lesser General Public License is Less protective of the
+users' freedom, it does ensure that the user of a program that is
+linked with the Library has the freedom and the wherewithal to run
+that program using a modified version of the Library.
+
+ The precise terms and conditions for copying, distribution and
+modification follow. Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library". The
+former contains code derived from the library, whereas the latter must
+be combined with the library in order to run.
+
+ GNU LESSER GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License Agreement applies to any software library or other
+program which contains a notice placed by the copyright holder or
+other authorized party saying it may be distributed under the terms of
+this Lesser General Public License (also called "this License").
+Each licensee is addressed as "you".
+
+ A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+ The "Library", below, refers to any such software library or work
+which has been distributed under these terms. A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language. (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+ "Source code" for a work means the preferred form of the work for
+making modifications to it. For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+ Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it). Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+ 1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+ You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+ 2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) The modified work must itself be a software library.
+
+ b) You must cause the files modified to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ c) You must cause the whole of the work to be licensed at no
+ charge to all third parties under the terms of this License.
+
+ d) If a facility in the modified Library refers to a function or a
+ table of data to be supplied by an application program that uses
+ the facility, other than as an argument passed when the facility
+ is invoked, then you must make a good faith effort to ensure that,
+ in the event an application does not supply such function or
+ table, the facility still operates, and performs whatever part of
+ its purpose remains meaningful.
+
+ (For example, a function in a library to compute square roots has
+ a purpose that is entirely well-defined independent of the
+ application. Therefore, Subsection 2d requires that any
+ application-supplied function or table used by this function must
+ be optional: if the application does not supply it, the square
+ root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library. To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License. (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.) Do not make any other change in
+these notices.
+
+ Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+ This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+ 4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+ If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library". Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+ However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library". The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+ When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library. The
+threshold for this to be true is not precisely defined by law.
+
+ If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work. (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+ Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+ 6. As an exception to the Sections above, you may also combine or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+ You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License. You must supply a copy of this License. If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License. Also, you must do one
+of these things:
+
+ a) Accompany the work with the complete corresponding
+ machine-readable source code for the Library including whatever
+ changes were used in the work (which must be distributed under
+ Sections 1 and 2 above); and, if the work is an executable linked
+ with the Library, with the complete machine-readable "work that
+ uses the Library", as object code and/or source code, so that the
+ user can modify the Library and then relink to produce a modified
+ executable containing the modified Library. (It is understood
+ that the user who changes the contents of definitions files in the
+ Library will not necessarily be able to recompile the application
+ to use the modified definitions.)
+
+ b) Use a suitable shared library mechanism for linking with the
+ Library. A suitable mechanism is one that (1) uses at run time a
+ copy of the library already present on the user's computer system,
+ rather than copying library functions into the executable, and (2)
+ will operate properly with a modified version of the library, if
+ the user installs one, as long as the modified version is
+ interface-compatible with the version that the work was made with.
+
+ c) Accompany the work with a written offer, valid for at
+ least three years, to give the same user the materials
+ specified in Subsection 6a, above, for a charge no more
+ than the cost of performing this distribution.
+
+ d) If distribution of the work is made by offering access to copy
+ from a designated place, offer equivalent access to copy the above
+ specified materials from the same place.
+
+ e) Verify that the user has already received a copy of these
+ materials or that you have already sent this user a copy.
+
+ For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it. However, as a special exception,
+the materials to be distributed need not include anything that is
+normally distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+ It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system. Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+ 7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+ a) Accompany the combined library with a copy of the same work
+ based on the Library, uncombined with any other library
+ facilities. This must be distributed under the terms of the
+ Sections above.
+
+ b) Give prominent notice with the combined library of the fact
+ that part of it is a work based on the Library, and explaining
+ where to find the accompanying uncombined form of the same work.
+
+ 8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License. Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License. However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+ 9. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Library or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+ 10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties with
+this License.
+
+ 11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all. For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded. In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+ 13. The Free Software Foundation may publish revised and/or new
+versions of the Lesser General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation. If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+ 14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission. For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this. Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+ NO WARRANTY
+
+ 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Libraries
+
+ If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change. You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+ To apply these terms, attach the following notices to the library. It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the library's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the
+ library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+ <signature of Ty Coon>, 1 April 1990
+ Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/libsensors/access.c b/tools/gator/daemon/libsensors/access.c
new file mode 100644
index 0000000..8e227e2
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.c
@@ -0,0 +1,561 @@
+/*
+ access.c - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007-2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+#include <math.h>
+#include "access.h"
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "sysfs.h"
+
+/* We watch the recursion depth for variables only, as an easy way to
+ detect cycles. */
+#define DEPTH_MAX 8
+
+static int sensors_eval_expr(const sensors_chip_features *chip_features,
+ const sensors_expr *expr,
+ double val, int depth, double *result);
+
+/* Compare two chips name descriptions, to see whether they could match.
+ Return 0 if it does not match, return 1 if it does match. */
+static int sensors_match_chip(const sensors_chip_name *chip1,
+ const sensors_chip_name *chip2)
+{
+ if ((chip1->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+ (chip2->prefix != SENSORS_CHIP_NAME_PREFIX_ANY) &&
+ strcmp(chip1->prefix, chip2->prefix))
+ return 0;
+
+ if ((chip1->bus.type != SENSORS_BUS_TYPE_ANY) &&
+ (chip2->bus.type != SENSORS_BUS_TYPE_ANY) &&
+ (chip1->bus.type != chip2->bus.type))
+ return 0;
+
+ if ((chip1->bus.nr != SENSORS_BUS_NR_ANY) &&
+ (chip2->bus.nr != SENSORS_BUS_NR_ANY) &&
+ (chip1->bus.nr != chip2->bus.nr))
+ return 0;
+
+ if ((chip1->addr != chip2->addr) &&
+ (chip1->addr != SENSORS_CHIP_NAME_ADDR_ANY) &&
+ (chip2->addr != SENSORS_CHIP_NAME_ADDR_ANY))
+ return 0;
+
+ return 1;
+}
+
+/* Returns, one by one, a pointer to all sensor_chip structs of the
+ config file which match with the given chip name. Last should be
+ the value returned by the last call, or NULL if this is the first
+ call. Returns NULL if no more matches are found. Do not modify
+ the struct the return value points to!
+ Note that this visits the list of chips from last to first. Usually,
+ you want the match that was latest in the config file. */
+static sensors_chip *
+sensors_for_all_config_chips(const sensors_chip_name *name,
+ const sensors_chip *last)
+{
+ int nr, i;
+ sensors_chip_name_list chips;
+
+ for (nr = last ? last - sensors_config_chips - 1 :
+ sensors_config_chips_count - 1; nr >= 0; nr--) {
+
+ chips = sensors_config_chips[nr].chips;
+ for (i = 0; i < chips.fits_count; i++) {
+ if (sensors_match_chip(&chips.fits[i], name))
+ return sensors_config_chips + nr;
+ }
+ }
+ return NULL;
+}
+
+/* Look up a chip in the intern chip list, and return a pointer to it.
+ Do not modify the struct the return value points to! Returns NULL if
+ not found.*/
+static const sensors_chip_features *
+sensors_lookup_chip(const sensors_chip_name *name)
+{
+ int i;
+
+ for (i = 0; i < sensors_proc_chips_count; i++)
+ if (sensors_match_chip(&sensors_proc_chips[i].chip, name))
+ return &sensors_proc_chips[i];
+
+ return NULL;
+}
+
+/* Look up a subfeature of the given chip, and return a pointer to it.
+ Do not modify the struct the return value points to! Returns NULL if
+ not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_nr(const sensors_chip_features *chip,
+ int subfeat_nr)
+{
+ if (subfeat_nr < 0 ||
+ subfeat_nr >= chip->subfeature_count)
+ return NULL;
+ return chip->subfeature + subfeat_nr;
+}
+
+/* Look up a feature of the given chip, and return a pointer to it.
+ Do not modify the struct the return value points to! Returns NULL if
+ not found.*/
+static const sensors_feature *
+sensors_lookup_feature_nr(const sensors_chip_features *chip, int feat_nr)
+{
+ if (feat_nr < 0 ||
+ feat_nr >= chip->feature_count)
+ return NULL;
+ return chip->feature + feat_nr;
+}
+
+/* Look up a subfeature by name, and return a pointer to it.
+ Do not modify the struct the return value points to! Returns NULL if
+ not found.*/
+static const sensors_subfeature *
+sensors_lookup_subfeature_name(const sensors_chip_features *chip,
+ const char *name)
+{
+ int j;
+
+ for (j = 0; j < chip->subfeature_count; j++)
+ if (!strcmp(chip->subfeature[j].name, name))
+ return chip->subfeature + j;
+ return NULL;
+}
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+ one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+ if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip)
+{
+ if ((chip->prefix == SENSORS_CHIP_NAME_PREFIX_ANY) ||
+ (chip->bus.type == SENSORS_BUS_TYPE_ANY) ||
+ (chip->bus.nr == SENSORS_BUS_NR_ANY) ||
+ (chip->addr == SENSORS_CHIP_NAME_ADDR_ANY))
+ return 1;
+ else
+ return 0;
+}
+
+/* Look up the label for a given feature. Note that chip should not
+ contain wildcard values! The returned string is newly allocated (free it
+ yourself). On failure, NULL is returned.
+ If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+ const sensors_feature *feature)
+{
+ char *label;
+ const sensors_chip *chip;
+ char buf[PATH_MAX];
+ FILE *f;
+ int i;
+
+ if (sensors_chip_name_has_wildcards(name))
+ return NULL;
+
+ for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+ for (i = 0; i < chip->labels_count; i++)
+ if (!strcmp(feature->name, chip->labels[i].name)) {
+ label = chip->labels[i].value;
+ goto sensors_get_label_exit;
+ }
+
+ /* No user specified label, check for a _label sysfs file */
+ snprintf(buf, PATH_MAX, "%s/%s_label", name->path, feature->name);
+
+ if ((f = fopen(buf, "r"))) {
+ i = fread(buf, 1, sizeof(buf), f);
+ fclose(f);
+ if (i > 0) {
+ /* i - 1 to strip the '\n' at the end */
+ buf[i - 1] = 0;
+ label = buf;
+ goto sensors_get_label_exit;
+ }
+ }
+
+ /* No label, return the feature name instead */
+ label = feature->name;
+
+sensors_get_label_exit:
+ label = strdup(label);
+ if (!label)
+ sensors_fatal_error(__func__, "Allocating label text");
+ return label;
+}
+
+/* Looks up whether a feature should be ignored. Returns
+ 1 if it should be ignored, 0 if not. */
+static int sensors_get_ignored(const sensors_chip_name *name,
+ const sensors_feature *feature)
+{
+ const sensors_chip *chip;
+ int i;
+
+ for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+ for (i = 0; i < chip->ignores_count; i++)
+ if (!strcmp(feature->name, chip->ignores[i].name))
+ return 1;
+ return 0;
+}
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+ contain wildcard values! This function will return 0 on success, and <0
+ on failure. */
+static int __sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+ int depth, double *result)
+{
+ const sensors_chip_features *chip_features;
+ const sensors_subfeature *subfeature;
+ const sensors_expr *expr = NULL;
+ double val;
+ int res, i;
+
+ if (depth >= DEPTH_MAX)
+ return -SENSORS_ERR_RECURSION;
+ if (sensors_chip_name_has_wildcards(name))
+ return -SENSORS_ERR_WILDCARDS;
+ if (!(chip_features = sensors_lookup_chip(name)))
+ return -SENSORS_ERR_NO_ENTRY;
+ if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+ subfeat_nr)))
+ return -SENSORS_ERR_NO_ENTRY;
+ if (!(subfeature->flags & SENSORS_MODE_R))
+ return -SENSORS_ERR_ACCESS_R;
+
+ /* Apply compute statement if it exists */
+ if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+ const sensors_feature *feature;
+ const sensors_chip *chip;
+
+ feature = sensors_lookup_feature_nr(chip_features,
+ subfeature->mapping);
+
+ chip = NULL;
+ while (!expr &&
+ (chip = sensors_for_all_config_chips(name, chip)))
+ for (i = 0; i < chip->computes_count; i++) {
+ if (!strcmp(feature->name,
+ chip->computes[i].name)) {
+ expr = chip->computes[i].from_proc;
+ break;
+ }
+ }
+ }
+
+ res = sensors_read_sysfs_attr(name, subfeature, &val);
+ if (res)
+ return res;
+ if (!expr)
+ *result = val;
+ else if ((res = sensors_eval_expr(chip_features, expr, val, depth,
+ result)))
+ return res;
+ return 0;
+}
+
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+ double *result)
+{
+ return __sensors_get_value(name, subfeat_nr, 0, result);
+}
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+ contain wildcard values! This function will return 0 on success, and <0
+ on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+ double value)
+{
+ const sensors_chip_features *chip_features;
+ const sensors_subfeature *subfeature;
+ const sensors_expr *expr = NULL;
+ int i, res;
+ double to_write;
+
+ if (sensors_chip_name_has_wildcards(name))
+ return -SENSORS_ERR_WILDCARDS;
+ if (!(chip_features = sensors_lookup_chip(name)))
+ return -SENSORS_ERR_NO_ENTRY;
+ if (!(subfeature = sensors_lookup_subfeature_nr(chip_features,
+ subfeat_nr)))
+ return -SENSORS_ERR_NO_ENTRY;
+ if (!(subfeature->flags & SENSORS_MODE_W))
+ return -SENSORS_ERR_ACCESS_W;
+
+ /* Apply compute statement if it exists */
+ if (subfeature->flags & SENSORS_COMPUTE_MAPPING) {
+ const sensors_feature *feature;
+ const sensors_chip *chip;
+
+ feature = sensors_lookup_feature_nr(chip_features,
+ subfeature->mapping);
+
+ chip = NULL;
+ while (!expr &&
+ (chip = sensors_for_all_config_chips(name, chip)))
+ for (i = 0; i < chip->computes_count; i++) {
+ if (!strcmp(feature->name,
+ chip->computes[i].name)) {
+ expr = chip->computes[i].to_proc;
+ break;
+ }
+ }
+ }
+
+ to_write = value;
+ if (expr)
+ if ((res = sensors_eval_expr(chip_features, expr,
+ value, 0, &to_write)))
+ return res;
+ return sensors_write_sysfs_attr(name, subfeature, to_write);
+}
+
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+ *match, int *nr)
+{
+ const sensors_chip_name *res;
+
+ while (*nr < sensors_proc_chips_count) {
+ res = &sensors_proc_chips[(*nr)++].chip;
+ if (!match || sensors_match_chip(res, match))
+ return res;
+ }
+ return NULL;
+}
+
+const char *sensors_get_adapter_name(const sensors_bus_id *bus)
+{
+ int i;
+
+ /* bus types with a single instance */
+ switch (bus->type) {
+ case SENSORS_BUS_TYPE_ISA:
+ return "ISA adapter";
+ case SENSORS_BUS_TYPE_PCI:
+ return "PCI adapter";
+ /* SPI should not be here, but for now SPI adapters have no name
+ so we don't have any custom string to return. */
+ case SENSORS_BUS_TYPE_SPI:
+ return "SPI adapter";
+ case SENSORS_BUS_TYPE_VIRTUAL:
+ return "Virtual device";
+ case SENSORS_BUS_TYPE_ACPI:
+ return "ACPI interface";
+ /* HID should probably not be there either, but I don't know if
+ HID buses have a name nor where to find it. */
+ case SENSORS_BUS_TYPE_HID:
+ return "HID adapter";
+ }
+
+ /* bus types with several instances */
+ for (i = 0; i < sensors_proc_bus_count; i++)
+ if (sensors_proc_bus[i].bus.type == bus->type &&
+ sensors_proc_bus[i].bus.nr == bus->nr)
+ return sensors_proc_bus[i].adapter;
+ return NULL;
+}
+
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr)
+{
+ const sensors_chip_features *chip;
+
+ if (!(chip = sensors_lookup_chip(name)))
+ return NULL; /* No such chip */
+
+ while (*nr < chip->feature_count
+ && sensors_get_ignored(name, &chip->feature[*nr]))
+ (*nr)++;
+ if (*nr >= chip->feature_count)
+ return NULL;
+ return &chip->feature[(*nr)++];
+}
+
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+ const sensors_feature *feature, int *nr)
+{
+ const sensors_chip_features *chip;
+ const sensors_subfeature *subfeature;
+
+ if (!(chip = sensors_lookup_chip(name)))
+ return NULL; /* No such chip */
+
+ /* Seek directly to the first subfeature */
+ if (*nr < feature->first_subfeature)
+ *nr = feature->first_subfeature;
+
+ if (*nr >= chip->subfeature_count)
+ return NULL; /* end of list */
+ subfeature = &chip->subfeature[(*nr)++];
+ if (subfeature->mapping == feature->number)
+ return subfeature;
+ return NULL; /* end of subfeature list */
+}
+
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+ const sensors_feature *feature,
+ sensors_subfeature_type type)
+{
+ const sensors_chip_features *chip;
+ int i;
+
+ if (!(chip = sensors_lookup_chip(name)))
+ return NULL; /* No such chip */
+
+ for (i = feature->first_subfeature; i < chip->subfeature_count &&
+ chip->subfeature[i].mapping == feature->number; i++) {
+ if (chip->subfeature[i].type == type)
+ return &chip->subfeature[i];
+ }
+ return NULL; /* No such subfeature */
+}
+
+/* Evaluate an expression */
+int sensors_eval_expr(const sensors_chip_features *chip_features,
+ const sensors_expr *expr,
+ double val, int depth, double *result)
+{
+ double res1, res2;
+ int res;
+ const sensors_subfeature *subfeature;
+
+ if (expr->kind == sensors_kind_val) {
+ *result = expr->data.val;
+ return 0;
+ }
+ if (expr->kind == sensors_kind_source) {
+ *result = val;
+ return 0;
+ }
+ if (expr->kind == sensors_kind_var) {
+ if (!(subfeature = sensors_lookup_subfeature_name(chip_features,
+ expr->data.var)))
+ return -SENSORS_ERR_NO_ENTRY;
+ return __sensors_get_value(&chip_features->chip,
+ subfeature->number, depth + 1,
+ result);
+ }
+ if ((res = sensors_eval_expr(chip_features, expr->data.subexpr.sub1,
+ val, depth, &res1)))
+ return res;
+ if (expr->data.subexpr.sub2 &&
+ (res = sensors_eval_expr(chip_features, expr->data.subexpr.sub2,
+ val, depth, &res2)))
+ return res;
+ switch (expr->data.subexpr.op) {
+ case sensors_add:
+ *result = res1 + res2;
+ return 0;
+ case sensors_sub:
+ *result = res1 - res2;
+ return 0;
+ case sensors_multiply:
+ *result = res1 * res2;
+ return 0;
+ case sensors_divide:
+ if (res2 == 0.0)
+ return -SENSORS_ERR_DIV_ZERO;
+ *result = res1 / res2;
+ return 0;
+ case sensors_negate:
+ *result = -res1;
+ return 0;
+ case sensors_exp:
+ *result = exp(res1);
+ return 0;
+ case sensors_log:
+ if (res1 < 0.0)
+ return -SENSORS_ERR_DIV_ZERO;
+ *result = log(res1);
+ return 0;
+ }
+ return 0;
+}
+
+/* Execute all set statements for this particular chip. The chip may not
+ contain wildcards! This function will return 0 on success, and <0 on
+ failure. */
+static int sensors_do_this_chip_sets(const sensors_chip_name *name)
+{
+ const sensors_chip_features *chip_features;
+ sensors_chip *chip;
+ double value;
+ int i;
+ int err = 0, res;
+ const sensors_subfeature *subfeature;
+
+ chip_features = sensors_lookup_chip(name); /* Can't fail */
+
+ for (chip = NULL; (chip = sensors_for_all_config_chips(name, chip));)
+ for (i = 0; i < chip->sets_count; i++) {
+ subfeature = sensors_lookup_subfeature_name(chip_features,
+ chip->sets[i].name);
+ if (!subfeature) {
+ sensors_parse_error_wfn("Unknown feature name",
+ chip->sets[i].line.filename,
+ chip->sets[i].line.lineno);
+ err = -SENSORS_ERR_NO_ENTRY;
+ continue;
+ }
+
+ res = sensors_eval_expr(chip_features,
+ chip->sets[i].value, 0,
+ 0, &value);
+ if (res) {
+ sensors_parse_error_wfn("Error parsing expression",
+ chip->sets[i].line.filename,
+ chip->sets[i].line.lineno);
+ err = res;
+ continue;
+ }
+ if ((res = sensors_set_value(name, subfeature->number,
+ value))) {
+ sensors_parse_error_wfn("Failed to set value",
+ chip->sets[i].line.filename,
+ chip->sets[i].line.lineno);
+ err = res;
+ continue;
+ }
+ }
+ return err;
+}
+
+/* Execute all set statements for this particular chip. The chip may contain
+ wildcards! This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name)
+{
+ int nr, this_res;
+ const sensors_chip_name *found_name;
+ int res = 0;
+
+ for (nr = 0; (found_name = sensors_get_detected_chips(name, &nr));) {
+ this_res = sensors_do_this_chip_sets(found_name);
+ if (this_res)
+ res = this_res;
+ }
+ return res;
+}
diff --git a/tools/gator/daemon/libsensors/access.h b/tools/gator/daemon/libsensors/access.h
new file mode 100644
index 0000000..1d37843
--- /dev/null
+++ b/tools/gator/daemon/libsensors/access.h
@@ -0,0 +1,33 @@
+/*
+ access.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ACCESS_H
+#define LIB_SENSORS_ACCESS_H
+
+#include "sensors.h"
+#include "data.h"
+
+/* Check whether the chip name is an 'absolute' name, which can only match
+ one chip, or whether it has wildcards. Returns 0 if it is absolute, 1
+ if there are wildcards. */
+int sensors_chip_name_has_wildcards(const sensors_chip_name *chip);
+
+#endif /* def LIB_SENSORS_ACCESS_H */
diff --git a/tools/gator/daemon/libsensors/conf-lex.c b/tools/gator/daemon/libsensors/conf-lex.c
new file mode 100644
index 0000000..a54664b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.c
@@ -0,0 +1,2881 @@
+
+#line 3 "<stdout>"
+
+#define YY_INT_ALIGNED short int
+
+/* A lexical scanner generated by flex */
+
+#define yy_create_buffer sensors_yy_create_buffer
+#define yy_delete_buffer sensors_yy_delete_buffer
+#define yy_flex_debug sensors_yy_flex_debug
+#define yy_init_buffer sensors_yy_init_buffer
+#define yy_flush_buffer sensors_yy_flush_buffer
+#define yy_load_buffer_state sensors_yy_load_buffer_state
+#define yy_switch_to_buffer sensors_yy_switch_to_buffer
+#define yyin sensors_yyin
+#define yyleng sensors_yyleng
+#define yylex sensors_yylex
+#define yylineno sensors_yylineno
+#define yyout sensors_yyout
+#define yyrestart sensors_yyrestart
+#define yytext sensors_yytext
+#define yywrap sensors_yywrap
+#define yyalloc sensors_yyalloc
+#define yyrealloc sensors_yyrealloc
+#define yyfree sensors_yyfree
+
+#define FLEX_SCANNER
+#define YY_FLEX_MAJOR_VERSION 2
+#define YY_FLEX_MINOR_VERSION 5
+#define YY_FLEX_SUBMINOR_VERSION 35
+#if YY_FLEX_SUBMINOR_VERSION > 0
+#define FLEX_BETA
+#endif
+
+/* First, we deal with platform-specific or compiler-specific issues. */
+
+/* begin standard C headers. */
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <stdlib.h>
+
+/* end standard C headers. */
+
+/* flex integer type definitions */
+
+#ifndef FLEXINT_H
+#define FLEXINT_H
+
+/* C99 systems have <inttypes.h>. Non-C99 systems may or may not. */
+
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L
+
+/* C99 says to define __STDC_LIMIT_MACROS before including stdint.h,
+ * if you want the limit (max/min) macros for int types.
+ */
+#ifndef __STDC_LIMIT_MACROS
+#define __STDC_LIMIT_MACROS 1
+#endif
+
+#include <inttypes.h>
+typedef int8_t flex_int8_t;
+typedef uint8_t flex_uint8_t;
+typedef int16_t flex_int16_t;
+typedef uint16_t flex_uint16_t;
+typedef int32_t flex_int32_t;
+typedef uint32_t flex_uint32_t;
+#else
+typedef signed char flex_int8_t;
+typedef short int flex_int16_t;
+typedef int flex_int32_t;
+typedef unsigned char flex_uint8_t;
+typedef unsigned short int flex_uint16_t;
+typedef unsigned int flex_uint32_t;
+
+/* Limits of integral types. */
+#ifndef INT8_MIN
+#define INT8_MIN (-128)
+#endif
+#ifndef INT16_MIN
+#define INT16_MIN (-32767-1)
+#endif
+#ifndef INT32_MIN
+#define INT32_MIN (-2147483647-1)
+#endif
+#ifndef INT8_MAX
+#define INT8_MAX (127)
+#endif
+#ifndef INT16_MAX
+#define INT16_MAX (32767)
+#endif
+#ifndef INT32_MAX
+#define INT32_MAX (2147483647)
+#endif
+#ifndef UINT8_MAX
+#define UINT8_MAX (255U)
+#endif
+#ifndef UINT16_MAX
+#define UINT16_MAX (65535U)
+#endif
+#ifndef UINT32_MAX
+#define UINT32_MAX (4294967295U)
+#endif
+
+#endif /* ! C99 */
+
+#endif /* ! FLEXINT_H */
+
+#ifdef __cplusplus
+
+/* The "const" storage-class-modifier is valid. */
+#define YY_USE_CONST
+
+#else /* ! __cplusplus */
+
+/* C99 requires __STDC__ to be defined as 1. */
+#if defined (__STDC__)
+
+#define YY_USE_CONST
+
+#endif /* defined (__STDC__) */
+#endif /* ! __cplusplus */
+
+#ifdef YY_USE_CONST
+#define yyconst const
+#else
+#define yyconst
+#endif
+
+/* Returned upon end-of-file. */
+#define YY_NULL 0
+
+/* Promotes a possibly negative, possibly signed char to an unsigned
+ * integer for use as an array index. If the signed char is negative,
+ * we want to instead treat it as an 8-bit unsigned char, hence the
+ * double cast.
+ */
+#define YY_SC_TO_UI(c) ((unsigned int) (unsigned char) c)
+
+/* Enter a start condition. This macro really ought to take a parameter,
+ * but we do it the disgusting crufty way forced on us by the ()-less
+ * definition of BEGIN.
+ */
+#define BEGIN (yy_start) = 1 + 2 *
+
+/* Translate the current start state into a value that can be later handed
+ * to BEGIN to return to the state. The YYSTATE alias is for lex
+ * compatibility.
+ */
+#define YY_START (((yy_start) - 1) / 2)
+#define YYSTATE YY_START
+
+/* Action number for EOF rule of a given start state. */
+#define YY_STATE_EOF(state) (YY_END_OF_BUFFER + state + 1)
+
+/* Special action meaning "start processing a new file". */
+#define YY_NEW_FILE sensors_yyrestart(sensors_yyin )
+
+#define YY_END_OF_BUFFER_CHAR 0
+
+/* Size of default input buffer. */
+#ifndef YY_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k.
+ * Moreover, YY_BUF_SIZE is 2*YY_READ_BUF_SIZE in the general case.
+ * Ditto for the __ia64__ case accordingly.
+ */
+#define YY_BUF_SIZE 32768
+#else
+#define YY_BUF_SIZE 16384
+#endif /* __ia64__ */
+#endif
+
+/* The state buf must be large enough to hold one state per character in the main buffer.
+ */
+#define YY_STATE_BUF_SIZE ((YY_BUF_SIZE + 2) * sizeof(yy_state_type))
+
+#ifndef YY_TYPEDEF_YY_BUFFER_STATE
+#define YY_TYPEDEF_YY_BUFFER_STATE
+typedef struct yy_buffer_state *YY_BUFFER_STATE;
+#endif
+
+extern int sensors_yyleng;
+
+extern FILE *sensors_yyin, *sensors_yyout;
+
+#define EOB_ACT_CONTINUE_SCAN 0
+#define EOB_ACT_END_OF_FILE 1
+#define EOB_ACT_LAST_MATCH 2
+
+ #define YY_LESS_LINENO(n)
+
+/* Return all but the first "n" matched characters back to the input stream. */
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up sensors_yytext. */ \
+ int yyless_macro_arg = (n); \
+ YY_LESS_LINENO(yyless_macro_arg);\
+ *yy_cp = (yy_hold_char); \
+ YY_RESTORE_YY_MORE_OFFSET \
+ (yy_c_buf_p) = yy_cp = yy_bp + yyless_macro_arg - YY_MORE_ADJ; \
+ YY_DO_BEFORE_ACTION; /* set up sensors_yytext again */ \
+ } \
+ while ( 0 )
+
+#define unput(c) yyunput( c, (yytext_ptr) )
+
+#ifndef YY_TYPEDEF_YY_SIZE_T
+#define YY_TYPEDEF_YY_SIZE_T
+typedef size_t yy_size_t;
+#endif
+
+#ifndef YY_STRUCT_YY_BUFFER_STATE
+#define YY_STRUCT_YY_BUFFER_STATE
+struct yy_buffer_state
+ {
+ FILE *yy_input_file;
+
+ char *yy_ch_buf; /* input buffer */
+ char *yy_buf_pos; /* current position in input buffer */
+
+ /* Size of input buffer in bytes, not including room for EOB
+ * characters.
+ */
+ yy_size_t yy_buf_size;
+
+ /* Number of characters read into yy_ch_buf, not including EOB
+ * characters.
+ */
+ int yy_n_chars;
+
+ /* Whether we "own" the buffer - i.e., we know we created it,
+ * and can realloc() it to grow it, and should free() it to
+ * delete it.
+ */
+ int yy_is_our_buffer;
+
+ /* Whether this is an "interactive" input source; if so, and
+ * if we're using stdio for input, then we want to use getc()
+ * instead of fread(), to make sure we stop fetching input after
+ * each newline.
+ */
+ int yy_is_interactive;
+
+ /* Whether we're considered to be at the beginning of a line.
+ * If so, '^' rules will be active on the next match, otherwise
+ * not.
+ */
+ int yy_at_bol;
+
+ int yy_bs_lineno; /**< The line count. */
+ int yy_bs_column; /**< The column count. */
+
+ /* Whether to try to fill the input buffer when we reach the
+ * end of it.
+ */
+ int yy_fill_buffer;
+
+ int yy_buffer_status;
+
+#define YY_BUFFER_NEW 0
+#define YY_BUFFER_NORMAL 1
+ /* When an EOF's been seen but there's still some text to process
+ * then we mark the buffer as YY_EOF_PENDING, to indicate that we
+ * shouldn't try reading from the input source any more. We might
+ * still have a bunch of tokens to match, though, because of
+ * possible backing-up.
+ *
+ * When we actually see the EOF, we change the status to "new"
+ * (via sensors_yyrestart()), so that the user can continue scanning by
+ * just pointing sensors_yyin at a new input file.
+ */
+#define YY_BUFFER_EOF_PENDING 2
+
+ };
+#endif /* !YY_STRUCT_YY_BUFFER_STATE */
+
+/* Stack of input buffers. */
+static size_t yy_buffer_stack_top = 0; /**< index of top of stack. */
+static size_t yy_buffer_stack_max = 0; /**< capacity of stack. */
+static YY_BUFFER_STATE * yy_buffer_stack = 0; /**< Stack as an array. */
+
+/* We provide macros for accessing buffer states in case in the
+ * future we want to put the buffer states in a more general
+ * "scanner state".
+ *
+ * Returns the top of the stack, or NULL.
+ */
+#define YY_CURRENT_BUFFER ( (yy_buffer_stack) \
+ ? (yy_buffer_stack)[(yy_buffer_stack_top)] \
+ : NULL)
+
+/* Same as previous macro, but useful when we know that the buffer stack is not
+ * NULL or when we need an lvalue. For internal use only.
+ */
+#define YY_CURRENT_BUFFER_LVALUE (yy_buffer_stack)[(yy_buffer_stack_top)]
+
+/* yy_hold_char holds the character lost when sensors_yytext is formed. */
+static char yy_hold_char;
+static int yy_n_chars; /* number of characters read into yy_ch_buf */
+int sensors_yyleng;
+
+/* Points to current character in buffer. */
+static char *yy_c_buf_p = (char *) 0;
+static int yy_init = 0; /* whether we need to initialize */
+static int yy_start = 0; /* start state number */
+
+/* Flag which is used to allow sensors_yywrap()'s to do buffer switches
+ * instead of setting up a fresh sensors_yyin. A bit of a hack ...
+ */
+static int yy_did_buffer_switch_on_eof;
+
+void sensors_yyrestart (FILE *input_file );
+void sensors_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer );
+YY_BUFFER_STATE sensors_yy_create_buffer (FILE *file,int size );
+void sensors_yy_delete_buffer (YY_BUFFER_STATE b );
+void sensors_yy_flush_buffer (YY_BUFFER_STATE b );
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer );
+void sensors_yypop_buffer_state (void );
+
+static void sensors_yyensure_buffer_stack (void );
+static void sensors_yy_load_buffer_state (void );
+static void sensors_yy_init_buffer (YY_BUFFER_STATE b,FILE *file );
+
+#define YY_FLUSH_BUFFER sensors_yy_flush_buffer(YY_CURRENT_BUFFER )
+
+YY_BUFFER_STATE sensors_yy_scan_buffer (char *base,yy_size_t size );
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char *yy_str );
+YY_BUFFER_STATE sensors_yy_scan_bytes (yyconst char *bytes,int len );
+
+void *sensors_yyalloc (yy_size_t );
+void *sensors_yyrealloc (void *,yy_size_t );
+void sensors_yyfree (void * );
+
+#define yy_new_buffer sensors_yy_create_buffer
+
+#define yy_set_interactive(is_interactive) \
+ { \
+ if ( ! YY_CURRENT_BUFFER ){ \
+ sensors_yyensure_buffer_stack (); \
+ YY_CURRENT_BUFFER_LVALUE = \
+ sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+ } \
+ YY_CURRENT_BUFFER_LVALUE->yy_is_interactive = is_interactive; \
+ }
+
+#define yy_set_bol(at_bol) \
+ { \
+ if ( ! YY_CURRENT_BUFFER ){\
+ sensors_yyensure_buffer_stack (); \
+ YY_CURRENT_BUFFER_LVALUE = \
+ sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE ); \
+ } \
+ YY_CURRENT_BUFFER_LVALUE->yy_at_bol = at_bol; \
+ }
+
+#define YY_AT_BOL() (YY_CURRENT_BUFFER_LVALUE->yy_at_bol)
+
+/* Begin user sect3 */
+
+#define sensors_yywrap(n) 1
+#define YY_SKIP_YYWRAP
+
+typedef unsigned char YY_CHAR;
+
+FILE *sensors_yyin = (FILE *) 0, *sensors_yyout = (FILE *) 0;
+
+typedef int yy_state_type;
+
+extern int sensors_yylineno;
+
+int sensors_yylineno = 1;
+
+extern char *sensors_yytext;
+#define yytext_ptr sensors_yytext
+static yyconst flex_int16_t yy_nxt[][39] =
+ {
+ {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0
+ },
+
+ {
+ 9, 10, 11, 12, 10, 13, 10, 10, 10, 10,
+ 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
+ 14, 15, 16, 14, 14, 14, 14, 14, 17, 18,
+ 14, 14, 14, 14, 14, 19, 14, 14, 14
+ },
+
+ {
+ 9, 10, 11, 12, 10, 13, 10, 10, 10, 10,
+ 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
+
+ 14, 15, 16, 14, 14, 14, 14, 14, 17, 18,
+ 14, 14, 14, 14, 14, 19, 14, 14, 14
+ },
+
+ {
+ 9, 20, 21, 22, 23, 24, 25, 26, 27, 28,
+ 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
+ 35, 35, 35, 35, 35, 35, 35, 35, 35, 35,
+ 35, 35, 35, 35, 35, 35, 35, 35, 35
+ },
+
+ {
+ 9, 20, 21, 22, 23, 24, 25, 26, 27, 28,
+ 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
+ 35, 35, 35, 35, 35, 35, 35, 35, 35, 35,
+ 35, 35, 35, 35, 35, 35, 35, 35, 35
+
+ },
+
+ {
+ 9, 39, 39, 40, 41, 39, 39, 39, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 42, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 39, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 39, 39
+ },
+
+ {
+ 9, 39, 39, 40, 41, 39, 39, 39, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 42, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 39, 39, 39,
+ 39, 39, 39, 39, 39, 39, 39, 39, 39
+ },
+
+ {
+ 9, 43, 43, 44, 43, 43, 43, 43, 43, 43,
+ 43, 43, 43, 43, 43, 43, 43, 43, 43, 43,
+
+ 43, 43, 43, 43, 43, 43, 43, 43, 43, 43,
+ 43, 43, 43, 43, 43, 43, 43, 43, 43
+ },
+
+ {
+ 9, 43, 43, 44, 43, 43, 43, 43, 43, 43,
+ 43, 43, 43, 43, 43, 43, 43, 43, 43, 43,
+ 43, 43, 43, 43, 43, 43, 43, 43, 43, 43,
+ 43, 43, 43, 43, 43, 43, 43, 43, 43
+ },
+
+ {
+ -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
+ -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
+ -9, -9, -9, -9, -9, -9, -9, -9, -9, -9,
+ -9, -9, -9, -9, -9, -9, -9, -9, -9
+
+ },
+
+ {
+ 9, -10, -10, -10, -10, -10, -10, -10, -10, -10,
+ -10, -10, -10, -10, -10, -10, -10, -10, -10, -10,
+ -10, -10, -10, -10, -10, -10, -10, -10, -10, -10,
+ -10, -10, -10, -10, -10, -10, -10, -10, -10
+ },
+
+ {
+ 9, -11, 45, 46, -11, -11, -11, -11, -11, -11,
+ -11, -11, -11, -11, -11, -11, -11, -11, -11, -11,
+ -11, -11, -11, -11, -11, -11, -11, -11, -11, -11,
+ -11, -11, -11, -11, -11, -11, -11, -11, -11
+ },
+
+ {
+ 9, -12, -12, -12, -12, -12, -12, -12, -12, -12,
+ -12, -12, -12, -12, -12, -12, -12, -12, -12, -12,
+
+ -12, -12, -12, -12, -12, -12, -12, -12, -12, -12,
+ -12, -12, -12, -12, -12, -12, -12, -12, -12
+ },
+
+ {
+ 9, 47, 47, 48, 47, 47, 47, 47, 47, 47,
+ 47, 47, 47, 47, 47, 47, 47, 47, 47, 47,
+ 47, 47, 47, 47, 47, 47, 47, 47, 47, 47,
+ 47, 47, 47, 47, 47, 47, 47, 47, 47
+ },
+
+ {
+ 9, -14, -14, -14, -14, -14, -14, -14, -14, -14,
+ -14, -14, -14, -14, -14, -14, -14, -14, -14, -14,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -15, -15, -15, -15, -15, -15, -15, -15, -15,
+ -15, -15, -15, -15, -15, -15, -15, -15, -15, -15,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 50, 49
+ },
+
+ {
+ 9, -16, -16, -16, -16, -16, -16, -16, -16, -16,
+ -16, -16, -16, -16, -16, -16, -16, -16, -16, -16,
+ 49, 49, 49, 49, 49, 49, 49, 51, 49, 49,
+ 49, 49, 52, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -17, -17, -17, -17, -17, -17, -17, -17, -17,
+ -17, -17, -17, -17, -17, -17, -17, -17, -17, -17,
+
+ 49, 49, 49, 49, 49, 49, 53, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -18, -18, -18, -18, -18, -18, -18, -18, -18,
+ -18, -18, -18, -18, -18, -18, -18, -18, -18, -18,
+ 54, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -19, -19, -19, -19, -19, -19, -19, -19, -19,
+ -19, -19, -19, -19, -19, -19, -19, -19, -19, -19,
+ 49, 49, 49, 49, 55, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -20, -20, -20, -20, -20, -20, -20, -20, -20,
+ -20, -20, -20, -20, -20, -20, -20, -20, -20, -20,
+ -20, -20, -20, -20, -20, -20, -20, -20, -20, -20,
+ -20, -20, -20, -20, -20, -20, -20, -20, -20
+ },
+
+ {
+ 9, -21, 56, -21, -21, -21, -21, -21, -21, -21,
+ -21, -21, -21, -21, -21, -21, -21, -21, -21, -21,
+ -21, -21, -21, -21, -21, -21, -21, -21, -21, -21,
+ -21, -21, -21, -21, -21, -21, -21, -21, -21
+ },
+
+ {
+ 9, -22, -22, -22, -22, -22, -22, -22, -22, -22,
+ -22, -22, -22, -22, -22, -22, -22, -22, -22, -22,
+
+ -22, -22, -22, -22, -22, -22, -22, -22, -22, -22,
+ -22, -22, -22, -22, -22, -22, -22, -22, -22
+ },
+
+ {
+ 9, -23, -23, -23, -23, -23, -23, -23, -23, -23,
+ -23, -23, -23, -23, -23, -23, -23, -23, -23, -23,
+ -23, -23, -23, -23, -23, -23, -23, -23, -23, -23,
+ -23, -23, -23, -23, -23, -23, -23, -23, -23
+ },
+
+ {
+ 9, 57, 57, 58, 57, 57, 57, 57, 57, 57,
+ 57, 57, 57, 57, 57, 57, 57, 57, 57, 57,
+ 57, 57, 57, 57, 57, 57, 57, 57, 57, 57,
+ 57, 57, 57, 57, 57, 57, 57, 57, 57
+
+ },
+
+ {
+ 9, -25, -25, -25, -25, -25, -25, -25, -25, -25,
+ -25, -25, -25, -25, -25, -25, -25, -25, -25, -25,
+ -25, -25, -25, -25, -25, -25, -25, -25, -25, -25,
+ -25, -25, -25, -25, -25, -25, -25, -25, -25
+ },
+
+ {
+ 9, -26, -26, -26, -26, -26, -26, -26, -26, -26,
+ -26, -26, -26, -26, -26, -26, -26, -26, -26, -26,
+ -26, -26, -26, -26, -26, -26, -26, -26, -26, -26,
+ -26, -26, -26, -26, -26, -26, -26, -26, -26
+ },
+
+ {
+ 9, -27, -27, -27, -27, -27, -27, -27, -27, -27,
+ -27, -27, -27, -27, -27, -27, -27, -27, -27, -27,
+
+ -27, -27, -27, -27, -27, -27, -27, -27, -27, -27,
+ -27, -27, -27, -27, -27, -27, -27, -27, -27
+ },
+
+ {
+ 9, -28, -28, -28, -28, -28, -28, -28, -28, -28,
+ -28, -28, -28, -28, -28, -28, -28, -28, -28, -28,
+ -28, -28, -28, -28, -28, -28, -28, -28, -28, -28,
+ -28, -28, -28, -28, -28, -28, -28, -28, -28
+ },
+
+ {
+ 9, -29, -29, -29, -29, -29, -29, -29, -29, -29,
+ -29, -29, -29, -29, -29, -29, -29, -29, -29, -29,
+ -29, -29, -29, -29, -29, -29, -29, -29, -29, -29,
+ -29, -29, -29, -29, -29, -29, -29, -29, -29
+
+ },
+
+ {
+ 9, -30, -30, -30, -30, -30, -30, -30, -30, -30,
+ -30, -30, -30, -30, -30, -30, -30, -30, -30, -30,
+ -30, -30, -30, -30, -30, -30, -30, -30, -30, -30,
+ -30, -30, -30, -30, -30, -30, -30, -30, -30
+ },
+
+ {
+ 9, -31, -31, -31, -31, -31, -31, -31, -31, -31,
+ -31, -31, -31, -31, 59, -31, -31, -31, -31, -31,
+ -31, -31, -31, -31, -31, -31, -31, -31, -31, -31,
+ -31, -31, -31, -31, -31, -31, -31, -31, -31
+ },
+
+ {
+ 9, -32, -32, -32, -32, -32, -32, -32, -32, -32,
+ -32, -32, -32, -32, -32, -32, -32, -32, -32, -32,
+
+ -32, -32, -32, -32, -32, -32, -32, -32, -32, -32,
+ -32, -32, -32, -32, -32, -32, -32, -32, -32
+ },
+
+ {
+ 9, -33, -33, -33, -33, -33, -33, -33, -33, -33,
+ -33, -33, 60, -33, 61, -33, 62, -33, -33, -33,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62, 62,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62
+ },
+
+ {
+ 9, -34, -34, -34, -34, -34, -34, -34, -34, -34,
+ -34, -34, -34, -34, -34, -34, -34, -34, -34, -34,
+ -34, -34, -34, -34, -34, -34, -34, -34, -34, -34,
+ -34, -34, -34, -34, -34, -34, -34, -34, -34
+
+ },
+
+ {
+ 9, -35, -35, -35, -35, -35, -35, -35, -35, -35,
+ -35, -35, -35, -35, 62, -35, 62, -35, -35, -35,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62, 62,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62
+ },
+
+ {
+ 9, -36, 63, 64, -36, -36, -36, -36, -36, -36,
+ -36, -36, -36, -36, -36, -36, -36, -36, -36, -36,
+ -36, -36, -36, -36, -36, -36, -36, -36, -36, -36,
+ -36, -36, -36, -36, -36, -36, -36, -36, -36
+ },
+
+ {
+ 9, -37, -37, -37, -37, -37, -37, -37, -37, -37,
+ -37, -37, -37, -37, -37, -37, -37, -37, -37, -37,
+
+ -37, -37, -37, -37, -37, -37, -37, -37, -37, -37,
+ -37, -37, -37, -37, -37, -37, -37, -37, -37
+ },
+
+ {
+ 9, -38, -38, -38, -38, -38, -38, -38, -38, -38,
+ -38, -38, -38, -38, -38, -38, -38, -38, -38, -38,
+ -38, -38, -38, -38, -38, -38, -38, -38, -38, -38,
+ -38, -38, -38, -38, -38, -38, -38, -38, -38
+ },
+
+ {
+ 9, 65, 65, -39, -39, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, -39, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65
+
+ },
+
+ {
+ 9, -40, -40, -40, -40, -40, -40, -40, -40, -40,
+ -40, -40, -40, -40, -40, -40, -40, -40, -40, -40,
+ -40, -40, -40, -40, -40, -40, -40, -40, -40, -40,
+ -40, -40, -40, -40, -40, -40, -40, -40, -40
+ },
+
+ {
+ 9, -41, -41, -41, 66, -41, -41, -41, -41, -41,
+ -41, -41, -41, -41, -41, -41, -41, -41, -41, -41,
+ -41, -41, -41, -41, -41, -41, -41, -41, -41, -41,
+ -41, -41, -41, -41, -41, -41, -41, -41, -41
+ },
+
+ {
+ 9, 67, 67, 68, 67, 67, 67, 67, 67, 67,
+ 67, 67, 67, 67, 67, 67, 67, 67, 67, 67,
+
+ 69, 70, 67, 67, 67, 71, 67, 67, 67, 67,
+ 67, 72, 67, 67, 73, 67, 74, 67, 75
+ },
+
+ {
+ 9, 76, 76, -43, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76
+ },
+
+ {
+ 9, -44, -44, -44, -44, -44, -44, -44, -44, -44,
+ -44, -44, -44, -44, -44, -44, -44, -44, -44, -44,
+ -44, -44, -44, -44, -44, -44, -44, -44, -44, -44,
+ -44, -44, -44, -44, -44, -44, -44, -44, -44
+
+ },
+
+ {
+ 9, -45, 45, 46, -45, -45, -45, -45, -45, -45,
+ -45, -45, -45, -45, -45, -45, -45, -45, -45, -45,
+ -45, -45, -45, -45, -45, -45, -45, -45, -45, -45,
+ -45, -45, -45, -45, -45, -45, -45, -45, -45
+ },
+
+ {
+ 9, -46, -46, -46, -46, -46, -46, -46, -46, -46,
+ -46, -46, -46, -46, -46, -46, -46, -46, -46, -46,
+ -46, -46, -46, -46, -46, -46, -46, -46, -46, -46,
+ -46, -46, -46, -46, -46, -46, -46, -46, -46
+ },
+
+ {
+ 9, 47, 47, 48, 47, 47, 47, 47, 47, 47,
+ 47, 47, 47, 47, 47, 47, 47, 47, 47, 47,
+
+ 47, 47, 47, 47, 47, 47, 47, 47, 47, 47,
+ 47, 47, 47, 47, 47, 47, 47, 47, 47
+ },
+
+ {
+ 9, -48, -48, -48, -48, -48, -48, -48, -48, -48,
+ -48, -48, -48, -48, -48, -48, -48, -48, -48, -48,
+ -48, -48, -48, -48, -48, -48, -48, -48, -48, -48,
+ -48, -48, -48, -48, -48, -48, -48, -48, -48
+ },
+
+ {
+ 9, -49, -49, -49, -49, -49, -49, -49, -49, -49,
+ -49, -49, -49, -49, -49, -49, -49, -49, -49, -49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -50, -50, -50, -50, -50, -50, -50, -50, -50,
+ -50, -50, -50, -50, -50, -50, -50, -50, -50, -50,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 77, 49, 49, 49
+ },
+
+ {
+ 9, -51, -51, -51, -51, -51, -51, -51, -51, -51,
+ -51, -51, -51, -51, -51, -51, -51, -51, -51, -51,
+ 49, 49, 49, 49, 49, 49, 49, 49, 78, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -52, -52, -52, -52, -52, -52, -52, -52, -52,
+ -52, -52, -52, -52, -52, -52, -52, -52, -52, -52,
+
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 79, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -53, -53, -53, -53, -53, -53, -53, -53, -53,
+ -53, -53, -53, -53, -53, -53, -53, -53, -53, -53,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 80, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -54, -54, -54, -54, -54, -54, -54, -54, -54,
+ -54, -54, -54, -54, -54, -54, -54, -54, -54, -54,
+ 49, 81, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -55, -55, -55, -55, -55, -55, -55, -55, -55,
+ -55, -55, -55, -55, -55, -55, -55, -55, -55, -55,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 82, 49, 49
+ },
+
+ {
+ 9, -56, 56, -56, -56, -56, -56, -56, -56, -56,
+ -56, -56, -56, -56, -56, -56, -56, -56, -56, -56,
+ -56, -56, -56, -56, -56, -56, -56, -56, -56, -56,
+ -56, -56, -56, -56, -56, -56, -56, -56, -56
+ },
+
+ {
+ 9, 57, 57, 58, 57, 57, 57, 57, 57, 57,
+ 57, 57, 57, 57, 57, 57, 57, 57, 57, 57,
+
+ 57, 57, 57, 57, 57, 57, 57, 57, 57, 57,
+ 57, 57, 57, 57, 57, 57, 57, 57, 57
+ },
+
+ {
+ 9, -58, -58, -58, -58, -58, -58, -58, -58, -58,
+ -58, -58, -58, -58, -58, -58, -58, -58, -58, -58,
+ -58, -58, -58, -58, -58, -58, -58, -58, -58, -58,
+ -58, -58, -58, -58, -58, -58, -58, -58, -58
+ },
+
+ {
+ 9, -59, -59, -59, -59, -59, -59, -59, -59, -59,
+ -59, -59, -59, -59, 59, -59, -59, -59, -59, -59,
+ -59, -59, -59, -59, -59, -59, -59, -59, -59, -59,
+ -59, -59, -59, -59, -59, -59, -59, -59, -59
+
+ },
+
+ {
+ 9, -60, -60, -60, -60, -60, -60, -60, -60, -60,
+ -60, -60, -60, -60, 59, -60, -60, -60, -60, -60,
+ -60, -60, -60, -60, -60, -60, -60, -60, -60, -60,
+ -60, -60, -60, -60, -60, -60, -60, -60, -60
+ },
+
+ {
+ 9, -61, -61, -61, -61, -61, -61, -61, -61, -61,
+ -61, -61, 60, -61, 61, -61, 62, -61, -61, -61,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62, 62,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62
+ },
+
+ {
+ 9, -62, -62, -62, -62, -62, -62, -62, -62, -62,
+ -62, -62, -62, -62, 62, -62, 62, -62, -62, -62,
+
+ 62, 62, 62, 62, 62, 62, 62, 62, 62, 62,
+ 62, 62, 62, 62, 62, 62, 62, 62, 62
+ },
+
+ {
+ 9, -63, 63, 64, -63, -63, -63, -63, -63, -63,
+ -63, -63, -63, -63, -63, -63, -63, -63, -63, -63,
+ -63, -63, -63, -63, -63, -63, -63, -63, -63, -63,
+ -63, -63, -63, -63, -63, -63, -63, -63, -63
+ },
+
+ {
+ 9, -64, -64, -64, -64, -64, -64, -64, -64, -64,
+ -64, -64, -64, -64, -64, -64, -64, -64, -64, -64,
+ -64, -64, -64, -64, -64, -64, -64, -64, -64, -64,
+ -64, -64, -64, -64, -64, -64, -64, -64, -64
+
+ },
+
+ {
+ 9, 65, 65, -65, -65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, -65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65, 65,
+ 65, 65, 65, 65, 65, 65, 65, 65, 65
+ },
+
+ {
+ 9, -66, -66, -66, -66, -66, -66, -66, -66, -66,
+ -66, -66, -66, -66, -66, -66, -66, -66, -66, -66,
+ -66, -66, -66, -66, -66, -66, -66, -66, -66, -66,
+ -66, -66, -66, -66, -66, -66, -66, -66, -66
+ },
+
+ {
+ 9, -67, -67, -67, -67, -67, -67, -67, -67, -67,
+ -67, -67, -67, -67, -67, -67, -67, -67, -67, -67,
+
+ -67, -67, -67, -67, -67, -67, -67, -67, -67, -67,
+ -67, -67, -67, -67, -67, -67, -67, -67, -67
+ },
+
+ {
+ 9, -68, -68, -68, -68, -68, -68, -68, -68, -68,
+ -68, -68, -68, -68, -68, -68, -68, -68, -68, -68,
+ -68, -68, -68, -68, -68, -68, -68, -68, -68, -68,
+ -68, -68, -68, -68, -68, -68, -68, -68, -68
+ },
+
+ {
+ 9, -69, -69, -69, -69, -69, -69, -69, -69, -69,
+ -69, -69, -69, -69, -69, -69, -69, -69, -69, -69,
+ -69, -69, -69, -69, -69, -69, -69, -69, -69, -69,
+ -69, -69, -69, -69, -69, -69, -69, -69, -69
+
+ },
+
+ {
+ 9, -70, -70, -70, -70, -70, -70, -70, -70, -70,
+ -70, -70, -70, -70, -70, -70, -70, -70, -70, -70,
+ -70, -70, -70, -70, -70, -70, -70, -70, -70, -70,
+ -70, -70, -70, -70, -70, -70, -70, -70, -70
+ },
+
+ {
+ 9, -71, -71, -71, -71, -71, -71, -71, -71, -71,
+ -71, -71, -71, -71, -71, -71, -71, -71, -71, -71,
+ -71, -71, -71, -71, -71, -71, -71, -71, -71, -71,
+ -71, -71, -71, -71, -71, -71, -71, -71, -71
+ },
+
+ {
+ 9, -72, -72, -72, -72, -72, -72, -72, -72, -72,
+ -72, -72, -72, -72, -72, -72, -72, -72, -72, -72,
+
+ -72, -72, -72, -72, -72, -72, -72, -72, -72, -72,
+ -72, -72, -72, -72, -72, -72, -72, -72, -72
+ },
+
+ {
+ 9, -73, -73, -73, -73, -73, -73, -73, -73, -73,
+ -73, -73, -73, -73, -73, -73, -73, -73, -73, -73,
+ -73, -73, -73, -73, -73, -73, -73, -73, -73, -73,
+ -73, -73, -73, -73, -73, -73, -73, -73, -73
+ },
+
+ {
+ 9, -74, -74, -74, -74, -74, -74, -74, -74, -74,
+ -74, -74, -74, -74, -74, -74, -74, -74, -74, -74,
+ -74, -74, -74, -74, -74, -74, -74, -74, -74, -74,
+ -74, -74, -74, -74, -74, -74, -74, -74, -74
+
+ },
+
+ {
+ 9, -75, -75, -75, -75, -75, -75, -75, -75, -75,
+ -75, -75, -75, -75, -75, -75, -75, -75, -75, -75,
+ -75, -75, -75, -75, -75, -75, -75, -75, -75, -75,
+ -75, -75, -75, -75, -75, -75, -75, -75, -75
+ },
+
+ {
+ 9, 76, 76, -76, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76, 76,
+ 76, 76, 76, 76, 76, 76, 76, 76, 76
+ },
+
+ {
+ 9, -77, 83, -77, -77, -77, -77, -77, -77, -77,
+ -77, -77, -77, -77, -77, -77, -77, -77, -77, -77,
+
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -78, -78, -78, -78, -78, -78, -78, -78, -78,
+ -78, -78, -78, -78, -78, -78, -78, -78, -78, -78,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 84, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -79, -79, -79, -79, -79, -79, -79, -79, -79,
+ -79, -79, -79, -79, -79, -79, -79, -79, -79, -79,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 85, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -80, -80, -80, -80, -80, -80, -80, -80, -80,
+ -80, -80, -80, -80, -80, -80, -80, -80, -80, -80,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 86, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -81, -81, -81, -81, -81, -81, -81, -81, -81,
+ -81, -81, -81, -81, -81, -81, -81, -81, -81, -81,
+ 49, 49, 49, 49, 87, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -82, 88, -82, -82, -82, -82, -82, -82, -82,
+ -82, -82, -82, -82, -82, -82, -82, -82, -82, -82,
+
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -83, 83, -83, -83, -83, -83, -83, -83, -83,
+ -83, -83, -83, -83, -83, -83, -83, -83, -83, -83,
+ -83, -83, -83, -83, -83, -83, -83, -83, -83, -83,
+ -83, -83, -83, -83, -83, -83, -83, -83, -83
+ },
+
+ {
+ 9, -84, 89, -84, -84, -84, -84, -84, -84, -84,
+ -84, -84, -84, -84, -84, -84, -84, -84, -84, -84,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -85, -85, -85, -85, -85, -85, -85, -85, -85,
+ -85, -85, -85, -85, -85, -85, -85, -85, -85, -85,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 90, 49
+ },
+
+ {
+ 9, -86, -86, -86, -86, -86, -86, -86, -86, -86,
+ -86, -86, -86, -86, -86, -86, -86, -86, -86, -86,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 91, 49, 49, 49, 49
+ },
+
+ {
+ 9, -87, -87, -87, -87, -87, -87, -87, -87, -87,
+ -87, -87, -87, -87, -87, -87, -87, -87, -87, -87,
+
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 92,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -88, 88, -88, -88, -88, -88, -88, -88, -88,
+ -88, -88, -88, -88, -88, -88, -88, -88, -88, -88,
+ -88, -88, -88, -88, -88, -88, -88, -88, -88, -88,
+ -88, -88, -88, -88, -88, -88, -88, -88, -88
+ },
+
+ {
+ 9, -89, 89, -89, -89, -89, -89, -89, -89, -89,
+ -89, -89, -89, -89, -89, -89, -89, -89, -89, -89,
+ -89, -89, -89, -89, -89, -89, -89, -89, -89, -89,
+ -89, -89, -89, -89, -89, -89, -89, -89, -89
+
+ },
+
+ {
+ 9, -90, -90, -90, -90, -90, -90, -90, -90, -90,
+ -90, -90, -90, -90, -90, -90, -90, -90, -90, -90,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 93, 49, 49
+ },
+
+ {
+ 9, -91, -91, -91, -91, -91, -91, -91, -91, -91,
+ -91, -91, -91, -91, -91, -91, -91, -91, -91, -91,
+ 49, 49, 49, 49, 94, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -92, 95, -92, -92, -92, -92, -92, -92, -92,
+ -92, -92, -92, -92, -92, -92, -92, -92, -92, -92,
+
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -93, -93, -93, -93, -93, -93, -93, -93, -93,
+ -93, -93, -93, -93, -93, -93, -93, -93, -93, -93,
+ 49, 49, 49, 49, 96, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -94, 97, -94, -94, -94, -94, -94, -94, -94,
+ -94, -94, -94, -94, -94, -94, -94, -94, -94, -94,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+
+ },
+
+ {
+ 9, -95, 95, -95, -95, -95, -95, -95, -95, -95,
+ -95, -95, -95, -95, -95, -95, -95, -95, -95, -95,
+ -95, -95, -95, -95, -95, -95, -95, -95, -95, -95,
+ -95, -95, -95, -95, -95, -95, -95, -95, -95
+ },
+
+ {
+ 9, -96, 98, -96, -96, -96, -96, -96, -96, -96,
+ -96, -96, -96, -96, -96, -96, -96, -96, -96, -96,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49, 49,
+ 49, 49, 49, 49, 49, 49, 49, 49, 49
+ },
+
+ {
+ 9, -97, 97, -97, -97, -97, -97, -97, -97, -97,
+ -97, -97, -97, -97, -97, -97, -97, -97, -97, -97,
+
+ -97, -97, -97, -97, -97, -97, -97, -97, -97, -97,
+ -97, -97, -97, -97, -97, -97, -97, -97, -97
+ },
+
+ {
+ 9, -98, 98, -98, -98, -98, -98, -98, -98, -98,
+ -98, -98, -98, -98, -98, -98, -98, -98, -98, -98,
+ -98, -98, -98, -98, -98, -98, -98, -98, -98, -98,
+ -98, -98, -98, -98, -98, -98, -98, -98, -98
+ },
+
+ } ;
+
+static yy_state_type yy_get_previous_state (void );
+static yy_state_type yy_try_NUL_trans (yy_state_type current_state );
+static int yy_get_next_buffer (void );
+static void yy_fatal_error (yyconst char msg[] );
+
+/* Done after the current pattern has been matched and before the
+ * corresponding action - sets up sensors_yytext.
+ */
+#define YY_DO_BEFORE_ACTION \
+ (yytext_ptr) = yy_bp; \
+ sensors_yyleng = (size_t) (yy_cp - yy_bp); \
+ (yy_hold_char) = *yy_cp; \
+ *yy_cp = '\0'; \
+ (yy_c_buf_p) = yy_cp;
+
+#define YY_NUM_RULES 50
+#define YY_END_OF_BUFFER 51
+/* This struct is not used in this scanner,
+ but its presence is necessary. */
+struct yy_trans_info
+ {
+ flex_int32_t yy_verify;
+ flex_int32_t yy_nxt;
+ };
+static yyconst flex_int16_t yy_accept[99] =
+ { 0,
+ 0, 0, 0, 0, 0, 0, 13, 13, 51, 12,
+ 1, 2, 3, 11, 11, 11, 11, 11, 11, 33,
+ 15, 16, 31, 18, 25, 26, 23, 21, 27, 22,
+ 33, 24, 20, 28, 32, 33, 29, 30, 49, 36,
+ 39, 48, 13, 14, 1, 2, 3, 4, 11, 11,
+ 11, 11, 11, 11, 11, 15, 18, 19, 20, 34,
+ 20, 32, 35, 17, 49, 38, 47, 37, 40, 41,
+ 42, 43, 44, 45, 46, 13, 8, 11, 11, 11,
+ 11, 6, 8, 9, 11, 11, 11, 6, 9, 11,
+ 11, 5, 11, 10, 5, 7, 10, 7
+
+ } ;
+
+static yyconst flex_int32_t yy_ec[256] =
+ { 0,
+ 1, 1, 1, 1, 1, 1, 1, 1, 2, 3,
+ 2, 2, 2, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 2, 1, 4, 5, 1, 1, 1, 1, 6,
+ 7, 8, 9, 10, 11, 12, 13, 14, 14, 14,
+ 14, 14, 14, 14, 14, 14, 14, 1, 1, 1,
+ 1, 1, 1, 15, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 16, 16, 16, 16, 16, 16, 16, 16, 16, 16,
+ 1, 17, 1, 18, 16, 19, 20, 21, 22, 23,
+
+ 24, 25, 26, 27, 28, 23, 23, 29, 30, 31,
+ 32, 33, 23, 34, 35, 36, 37, 38, 23, 23,
+ 23, 23, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
+ 1, 1, 1, 1, 1
+ } ;
+
+extern int sensors_yy_flex_debug;
+int sensors_yy_flex_debug = 0;
+
+/* The intent behind this definition is that it'll catch
+ * any uses of REJECT which flex missed.
+ */
+#define REJECT reject_used_but_not_detected
+#define yymore() yymore_used_but_not_detected
+#define YY_MORE_ADJ 0
+#define YY_RESTORE_YY_MORE_OFFSET
+char *sensors_yytext;
+#line 1 "lib/conf-lex.l"
+#line 2 "lib/conf-lex.l"
+/*
+ conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+ &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+ &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+ &buffer_count,\
+ &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+ &buffer, \
+ &buffer_count,&buffer_max,1)
+
+/* Scanner for configuration files */
+/* All states are exclusive */
+
+
+
+/* Any whitespace-like character */
+/* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+/* Only positive whole numbers are recognized here */
+#line 1255 "<stdout>"
+
+#define INITIAL 0
+#define MIDDLE 1
+#define STRING 2
+#define ERR 3
+
+#ifndef YY_NO_UNISTD_H
+/* Special case for "unistd.h", since it is non-ANSI. We include it way
+ * down here because we want the user's section 1 to have been scanned first.
+ * The user has a chance to override it with an option.
+ */
+#include <unistd.h>
+#endif
+
+#ifndef YY_EXTRA_TYPE
+#define YY_EXTRA_TYPE void *
+#endif
+
+static int yy_init_globals (void );
+
+/* Accessor methods to globals.
+ These are made visible to non-reentrant scanners for convenience. */
+
+int sensors_yylex_destroy (void );
+
+int sensors_yyget_debug (void );
+
+void sensors_yyset_debug (int debug_flag );
+
+YY_EXTRA_TYPE sensors_yyget_extra (void );
+
+void sensors_yyset_extra (YY_EXTRA_TYPE user_defined );
+
+FILE *sensors_yyget_in (void );
+
+void sensors_yyset_in (FILE * in_str );
+
+FILE *sensors_yyget_out (void );
+
+void sensors_yyset_out (FILE * out_str );
+
+int sensors_yyget_leng (void );
+
+char *sensors_yyget_text (void );
+
+int sensors_yyget_lineno (void );
+
+void sensors_yyset_lineno (int line_number );
+
+/* Macros after this point can all be overridden by user definitions in
+ * section 1.
+ */
+
+#ifndef YY_SKIP_YYWRAP
+#ifdef __cplusplus
+extern "C" int sensors_yywrap (void );
+#else
+extern int sensors_yywrap (void );
+#endif
+#endif
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char *,yyconst char *,int );
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * );
+#endif
+
+#ifndef YY_NO_INPUT
+
+#ifdef __cplusplus
+static int yyinput (void );
+#else
+static int input (void );
+#endif
+
+#endif
+
+/* Amount of stuff to slurp up with each read. */
+#ifndef YY_READ_BUF_SIZE
+#ifdef __ia64__
+/* On IA-64, the buffer size is 16k, not 8k */
+#define YY_READ_BUF_SIZE 16384
+#else
+#define YY_READ_BUF_SIZE 8192
+#endif /* __ia64__ */
+#endif
+
+/* Copy whatever the last rule matched to the standard output. */
+#ifndef ECHO
+/* This used to be an fputs(), but since the string might contain NUL's,
+ * we now use fwrite().
+ */
+#define ECHO do { if (fwrite( sensors_yytext, sensors_yyleng, 1, sensors_yyout )) {} } while (0)
+#endif
+
+/* Gets input and stuffs it into "buf". number of characters read, or YY_NULL,
+ * is returned in "result".
+ */
+#ifndef YY_INPUT
+#define YY_INPUT(buf,result,max_size) \
+ if ( YY_CURRENT_BUFFER_LVALUE->yy_is_interactive ) \
+ { \
+ int c = '*'; \
+ size_t n; \
+ for ( n = 0; n < max_size && \
+ (c = getc( sensors_yyin )) != EOF && c != '\n'; ++n ) \
+ buf[n] = (char) c; \
+ if ( c == '\n' ) \
+ buf[n++] = (char) c; \
+ if ( c == EOF && ferror( sensors_yyin ) ) \
+ YY_FATAL_ERROR( "input in flex scanner failed" ); \
+ result = n; \
+ } \
+ else \
+ { \
+ errno=0; \
+ while ( (result = fread(buf, 1, max_size, sensors_yyin))==0 && ferror(sensors_yyin)) \
+ { \
+ if( errno != EINTR) \
+ { \
+ YY_FATAL_ERROR( "input in flex scanner failed" ); \
+ break; \
+ } \
+ errno=0; \
+ clearerr(sensors_yyin); \
+ } \
+ }\
+\
+
+#endif
+
+/* No semi-colon after return; correct usage is to write "yyterminate();" -
+ * we don't want an extra ';' after the "return" because that will cause
+ * some compilers to complain about unreachable statements.
+ */
+#ifndef yyterminate
+#define yyterminate() return YY_NULL
+#endif
+
+/* Number of entries by which start-condition stack grows. */
+#ifndef YY_START_STACK_INCR
+#define YY_START_STACK_INCR 25
+#endif
+
+/* Report a fatal error. */
+#ifndef YY_FATAL_ERROR
+#define YY_FATAL_ERROR(msg) yy_fatal_error( msg )
+#endif
+
+/* end tables serialization structures and prototypes */
+
+/* Default declaration of generated scanner - a define so the user can
+ * easily add parameters.
+ */
+#ifndef YY_DECL
+#define YY_DECL_IS_OURS 1
+
+extern int sensors_yylex (void);
+
+#define YY_DECL int sensors_yylex (void)
+#endif /* !YY_DECL */
+
+/* Code executed at the beginning of each rule, after sensors_yytext and sensors_yyleng
+ * have been set up.
+ */
+#ifndef YY_USER_ACTION
+#define YY_USER_ACTION
+#endif
+
+/* Code executed at the end of each rule. */
+#ifndef YY_BREAK
+#define YY_BREAK break;
+#endif
+
+#define YY_RULE_SETUP \
+ YY_USER_ACTION
+
+/** The main scanner function which does all the work.
+ */
+YY_DECL
+{
+ register yy_state_type yy_current_state;
+ register char *yy_cp, *yy_bp;
+ register int yy_act;
+
+#line 80 "lib/conf-lex.l"
+
+
+ /*
+ * STATE: INITIAL
+ */
+
+#line 1450 "<stdout>"
+
+ if ( !(yy_init) )
+ {
+ (yy_init) = 1;
+
+#ifdef YY_USER_INIT
+ YY_USER_INIT;
+#endif
+
+ if ( ! (yy_start) )
+ (yy_start) = 1; /* first start state */
+
+ if ( ! sensors_yyin )
+ sensors_yyin = stdin;
+
+ if ( ! sensors_yyout )
+ sensors_yyout = stdout;
+
+ if ( ! YY_CURRENT_BUFFER ) {
+ sensors_yyensure_buffer_stack ();
+ YY_CURRENT_BUFFER_LVALUE =
+ sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+ }
+
+ sensors_yy_load_buffer_state( );
+ }
+
+ while ( 1 ) /* loops until end-of-file is reached */
+ {
+ yy_cp = (yy_c_buf_p);
+
+ /* Support of sensors_yytext. */
+ *yy_cp = (yy_hold_char);
+
+ /* yy_bp points to the position in yy_ch_buf of the start of
+ * the current run.
+ */
+ yy_bp = yy_cp;
+
+ yy_current_state = (yy_start);
+yy_match:
+ while ( (yy_current_state = yy_nxt[yy_current_state][ yy_ec[YY_SC_TO_UI(*yy_cp)] ]) > 0 )
+ ++yy_cp;
+
+ yy_current_state = -yy_current_state;
+
+yy_find_action:
+ yy_act = yy_accept[yy_current_state];
+
+ YY_DO_BEFORE_ACTION;
+
+do_action: /* This label is used only to access EOF actions. */
+
+ switch ( yy_act )
+ { /* beginning of action switch */
+
+case YY_STATE_EOF(INITIAL):
+#line 88 "lib/conf-lex.l"
+{ /* EOF from this state terminates */
+ return 0;
+ }
+ YY_BREAK
+case 1:
+YY_RULE_SETUP
+#line 92 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+ YY_BREAK
+case 2:
+/* rule 2 can match eol */
+YY_RULE_SETUP
+#line 94 "lib/conf-lex.l"
+{ /* eat a bare newline (possibly preceded by blanks) */
+ sensors_yylineno++;
+ }
+ YY_BREAK
+/* comments */
+case 3:
+YY_RULE_SETUP
+#line 100 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+ YY_BREAK
+case 4:
+/* rule 4 can match eol */
+YY_RULE_SETUP
+#line 102 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+ sensors_yylineno++;
+ }
+ YY_BREAK
+/*
+ * Keywords must be followed by whitespace - eat that too.
+ * If there isn't trailing whitespace, we still need to
+ * accept it as lexically correct (even though the parser
+ * will reject it anyway.)
+ */
+case 5:
+YY_RULE_SETUP
+#line 113 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return LABEL;
+ }
+ YY_BREAK
+case 6:
+YY_RULE_SETUP
+#line 120 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return SET;
+ }
+ YY_BREAK
+case 7:
+YY_RULE_SETUP
+#line 127 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return COMPUTE;
+ }
+ YY_BREAK
+case 8:
+YY_RULE_SETUP
+#line 134 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return BUS;
+ }
+ YY_BREAK
+case 9:
+YY_RULE_SETUP
+#line 141 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return CHIP;
+ }
+ YY_BREAK
+case 10:
+YY_RULE_SETUP
+#line 148 "lib/conf-lex.l"
+{
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return IGNORE;
+ }
+ YY_BREAK
+/* Anything else at the beginning of a line is an error */
+case 11:
+#line 158 "lib/conf-lex.l"
+case 12:
+YY_RULE_SETUP
+#line 158 "lib/conf-lex.l"
+{
+ BEGIN(ERR);
+ strcpy(sensors_lex_error,"Invalid keyword");
+ return ERROR;
+ }
+ YY_BREAK
+
+/*
+ * STATE: ERROR
+ */
+
+case 13:
+YY_RULE_SETUP
+#line 171 "lib/conf-lex.l"
+; /* eat whatever is left on this line */
+ YY_BREAK
+case 14:
+/* rule 14 can match eol */
+YY_RULE_SETUP
+#line 173 "lib/conf-lex.l"
+{
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+ YY_BREAK
+
+/*
+ * STATE: MIDDLE
+ */
+
+case 15:
+YY_RULE_SETUP
+#line 186 "lib/conf-lex.l"
+; /* eat as many blanks as possible at once */
+ YY_BREAK
+case 16:
+/* rule 16 can match eol */
+YY_RULE_SETUP
+#line 188 "lib/conf-lex.l"
+{ /* newline here sends EOL token to parser */
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+ YY_BREAK
+case YY_STATE_EOF(MIDDLE):
+#line 194 "lib/conf-lex.l"
+{ /* EOF here sends EOL token to parser also */
+ BEGIN(INITIAL);
+ return EOL;
+ }
+ YY_BREAK
+case 17:
+/* rule 17 can match eol */
+YY_RULE_SETUP
+#line 199 "lib/conf-lex.l"
+{ /* eat an escaped newline with no state change */
+ sensors_yylineno++;
+ }
+ YY_BREAK
+/* comments */
+case 18:
+YY_RULE_SETUP
+#line 205 "lib/conf-lex.l"
+; /* eat the rest of the line after comment char */
+ YY_BREAK
+case 19:
+/* rule 19 can match eol */
+YY_RULE_SETUP
+#line 207 "lib/conf-lex.l"
+{ /* eat the rest of the line after comment char */
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+ YY_BREAK
+/* A number */
+case 20:
+YY_RULE_SETUP
+#line 215 "lib/conf-lex.l"
+{
+ sensors_yylval.value = atof(sensors_yytext);
+ return FLOAT;
+ }
+ YY_BREAK
+/* Some operators */
+case 21:
+YY_RULE_SETUP
+#line 222 "lib/conf-lex.l"
+return '+';
+ YY_BREAK
+case 22:
+YY_RULE_SETUP
+#line 223 "lib/conf-lex.l"
+return '-';
+ YY_BREAK
+case 23:
+YY_RULE_SETUP
+#line 224 "lib/conf-lex.l"
+return '*';
+ YY_BREAK
+case 24:
+YY_RULE_SETUP
+#line 225 "lib/conf-lex.l"
+return '/';
+ YY_BREAK
+case 25:
+YY_RULE_SETUP
+#line 226 "lib/conf-lex.l"
+return '(';
+ YY_BREAK
+case 26:
+YY_RULE_SETUP
+#line 227 "lib/conf-lex.l"
+return ')';
+ YY_BREAK
+case 27:
+YY_RULE_SETUP
+#line 228 "lib/conf-lex.l"
+return ',';
+ YY_BREAK
+case 28:
+YY_RULE_SETUP
+#line 229 "lib/conf-lex.l"
+return '@';
+ YY_BREAK
+case 29:
+YY_RULE_SETUP
+#line 230 "lib/conf-lex.l"
+return '^';
+ YY_BREAK
+case 30:
+YY_RULE_SETUP
+#line 231 "lib/conf-lex.l"
+return '`';
+ YY_BREAK
+/* Quoted string */
+case 31:
+YY_RULE_SETUP
+#line 235 "lib/conf-lex.l"
+{
+ buffer_malloc();
+ BEGIN(STRING);
+ }
+ YY_BREAK
+/* A normal, unquoted identifier */
+case 32:
+YY_RULE_SETUP
+#line 242 "lib/conf-lex.l"
+{
+ sensors_yylval.name = strdup(sensors_yytext);
+ if (! sensors_yylval.name)
+ sensors_fatal_error("conf-lex.l",
+ "Allocating a new string");
+
+ return NAME;
+ }
+ YY_BREAK
+/* anything else is bogus */
+case 33:
+#line 254 "lib/conf-lex.l"
+case 34:
+#line 255 "lib/conf-lex.l"
+case 35:
+YY_RULE_SETUP
+#line 255 "lib/conf-lex.l"
+{
+ BEGIN(ERR);
+ return ERROR;
+ }
+ YY_BREAK
+
+/*
+ * STATE: STRING
+ */
+
+/* Oops, newline or EOF while in a string is not good */
+case 36:
+/* rule 36 can match eol */
+#line 270 "lib/conf-lex.l"
+case 37:
+/* rule 37 can match eol */
+YY_RULE_SETUP
+#line 270 "lib/conf-lex.l"
+{
+ buffer_add_char("\0");
+ strcpy(sensors_lex_error,
+ "No matching double quote.");
+ buffer_free();
+ yyless(0);
+ BEGIN(ERR);
+ return ERROR;
+ }
+ YY_BREAK
+case YY_STATE_EOF(STRING):
+#line 280 "lib/conf-lex.l"
+{
+ strcpy(sensors_lex_error,
+ "Reached end-of-file without a matching double quote.");
+ buffer_free();
+ BEGIN(MIDDLE);
+ return ERROR;
+ }
+ YY_BREAK
+/* At the end */
+case 38:
+YY_RULE_SETUP
+#line 290 "lib/conf-lex.l"
+{
+ buffer_add_char("\0");
+ strcpy(sensors_lex_error,
+ "Quoted strings must be separated by whitespace.");
+ buffer_free();
+ BEGIN(ERR);
+ return ERROR;
+ }
+ YY_BREAK
+case 39:
+YY_RULE_SETUP
+#line 299 "lib/conf-lex.l"
+{
+ buffer_add_char("\0");
+ sensors_yylval.name = strdup(buffer);
+ if (! sensors_yylval.name)
+ sensors_fatal_error("conf-lex.l",
+ "Allocating a new string");
+ buffer_free();
+ BEGIN(MIDDLE);
+ return NAME;
+ }
+ YY_BREAK
+case 40:
+YY_RULE_SETUP
+#line 310 "lib/conf-lex.l"
+buffer_add_char("\a");
+ YY_BREAK
+case 41:
+YY_RULE_SETUP
+#line 311 "lib/conf-lex.l"
+buffer_add_char("\b");
+ YY_BREAK
+case 42:
+YY_RULE_SETUP
+#line 312 "lib/conf-lex.l"
+buffer_add_char("\f");
+ YY_BREAK
+case 43:
+YY_RULE_SETUP
+#line 313 "lib/conf-lex.l"
+buffer_add_char("\n");
+ YY_BREAK
+case 44:
+YY_RULE_SETUP
+#line 314 "lib/conf-lex.l"
+buffer_add_char("\r");
+ YY_BREAK
+case 45:
+YY_RULE_SETUP
+#line 315 "lib/conf-lex.l"
+buffer_add_char("\t");
+ YY_BREAK
+case 46:
+YY_RULE_SETUP
+#line 316 "lib/conf-lex.l"
+buffer_add_char("\v");
+ YY_BREAK
+/* Other escapes: just copy the character behind the slash */
+case 47:
+YY_RULE_SETUP
+#line 320 "lib/conf-lex.l"
+{
+ buffer_add_char(&sensors_yytext[1]);
+ }
+ YY_BREAK
+/* Anything else (including a bare '\' which may be followed by EOF) */
+case 48:
+#line 327 "lib/conf-lex.l"
+case 49:
+YY_RULE_SETUP
+#line 327 "lib/conf-lex.l"
+{
+ buffer_add_string(sensors_yytext);
+ }
+ YY_BREAK
+
+case 50:
+YY_RULE_SETUP
+#line 332 "lib/conf-lex.l"
+YY_FATAL_ERROR( "flex scanner jammed" );
+ YY_BREAK
+#line 1903 "<stdout>"
+ case YY_STATE_EOF(ERR):
+ yyterminate();
+
+ case YY_END_OF_BUFFER:
+ {
+ /* Amount of text matched not including the EOB char. */
+ int yy_amount_of_matched_text = (int) (yy_cp - (yytext_ptr)) - 1;
+
+ /* Undo the effects of YY_DO_BEFORE_ACTION. */
+ *yy_cp = (yy_hold_char);
+ YY_RESTORE_YY_MORE_OFFSET
+
+ if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_NEW )
+ {
+ /* We're scanning a new file or input source. It's
+ * possible that this happened because the user
+ * just pointed sensors_yyin at a new source and called
+ * sensors_yylex(). If so, then we have to assure
+ * consistency between YY_CURRENT_BUFFER and our
+ * globals. Here is the right place to do so, because
+ * this is the first action (other than possibly a
+ * back-up) that will match for the new input source.
+ */
+ (yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+ YY_CURRENT_BUFFER_LVALUE->yy_input_file = sensors_yyin;
+ YY_CURRENT_BUFFER_LVALUE->yy_buffer_status = YY_BUFFER_NORMAL;
+ }
+
+ /* Note that here we test for yy_c_buf_p "<=" to the position
+ * of the first EOB in the buffer, since yy_c_buf_p will
+ * already have been incremented past the NUL character
+ * (since all states make transitions on EOB to the
+ * end-of-buffer state). Contrast this with the test
+ * in input().
+ */
+ if ( (yy_c_buf_p) <= &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+ { /* This was really a NUL. */
+ yy_state_type yy_next_state;
+
+ (yy_c_buf_p) = (yytext_ptr) + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state( );
+
+ /* Okay, we're now positioned to make the NUL
+ * transition. We couldn't have
+ * yy_get_previous_state() go ahead and do it
+ * for us because it doesn't know how to deal
+ * with the possibility of jamming (and we don't
+ * want to build jamming into it because then it
+ * will run more slowly).
+ */
+
+ yy_next_state = yy_try_NUL_trans( yy_current_state );
+
+ yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+
+ if ( yy_next_state )
+ {
+ /* Consume the NUL. */
+ yy_cp = ++(yy_c_buf_p);
+ yy_current_state = yy_next_state;
+ goto yy_match;
+ }
+
+ else
+ {
+ yy_cp = (yy_c_buf_p);
+ goto yy_find_action;
+ }
+ }
+
+ else switch ( yy_get_next_buffer( ) )
+ {
+ case EOB_ACT_END_OF_FILE:
+ {
+ (yy_did_buffer_switch_on_eof) = 0;
+
+ if ( sensors_yywrap( ) )
+ {
+ /* Note: because we've taken care in
+ * yy_get_next_buffer() to have set up
+ * sensors_yytext, we can now set up
+ * yy_c_buf_p so that if some total
+ * hoser (like flex itself) wants to
+ * call the scanner after we return the
+ * YY_NULL, it'll still work - another
+ * YY_NULL will get returned.
+ */
+ (yy_c_buf_p) = (yytext_ptr) + YY_MORE_ADJ;
+
+ yy_act = YY_STATE_EOF(YY_START);
+ goto do_action;
+ }
+
+ else
+ {
+ if ( ! (yy_did_buffer_switch_on_eof) )
+ YY_NEW_FILE;
+ }
+ break;
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ (yy_c_buf_p) =
+ (yytext_ptr) + yy_amount_of_matched_text;
+
+ yy_current_state = yy_get_previous_state( );
+
+ yy_cp = (yy_c_buf_p);
+ yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+ goto yy_match;
+
+ case EOB_ACT_LAST_MATCH:
+ (yy_c_buf_p) =
+ &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)];
+
+ yy_current_state = yy_get_previous_state( );
+
+ yy_cp = (yy_c_buf_p);
+ yy_bp = (yytext_ptr) + YY_MORE_ADJ;
+ goto yy_find_action;
+ }
+ break;
+ }
+
+ default:
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--no action found" );
+ } /* end of action switch */
+ } /* end of scanning one token */
+} /* end of sensors_yylex */
+
+/* yy_get_next_buffer - try to read in a new buffer
+ *
+ * Returns a code representing an action:
+ * EOB_ACT_LAST_MATCH -
+ * EOB_ACT_CONTINUE_SCAN - continue scanning from current position
+ * EOB_ACT_END_OF_FILE - end of file
+ */
+static int yy_get_next_buffer (void)
+{
+ register char *dest = YY_CURRENT_BUFFER_LVALUE->yy_ch_buf;
+ register char *source = (yytext_ptr);
+ register int number_to_move, i;
+ int ret_val;
+
+ if ( (yy_c_buf_p) > &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] )
+ YY_FATAL_ERROR(
+ "fatal flex scanner internal error--end of buffer missed" );
+
+ if ( YY_CURRENT_BUFFER_LVALUE->yy_fill_buffer == 0 )
+ { /* Don't try to fill the buffer, so this is an EOF. */
+ if ( (yy_c_buf_p) - (yytext_ptr) - YY_MORE_ADJ == 1 )
+ {
+ /* We matched a single character, the EOB, so
+ * treat this as a final EOF.
+ */
+ return EOB_ACT_END_OF_FILE;
+ }
+
+ else
+ {
+ /* We matched some text prior to the EOB, first
+ * process it.
+ */
+ return EOB_ACT_LAST_MATCH;
+ }
+ }
+
+ /* Try to read more data. */
+
+ /* First move last chars to start of buffer. */
+ number_to_move = (int) ((yy_c_buf_p) - (yytext_ptr)) - 1;
+
+ for ( i = 0; i < number_to_move; ++i )
+ *(dest++) = *(source++);
+
+ if ( YY_CURRENT_BUFFER_LVALUE->yy_buffer_status == YY_BUFFER_EOF_PENDING )
+ /* don't do the read, it's not guaranteed to return an EOF,
+ * just force an EOF
+ */
+ YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars) = 0;
+
+ else
+ {
+ int num_to_read =
+ YY_CURRENT_BUFFER_LVALUE->yy_buf_size - number_to_move - 1;
+
+ while ( num_to_read <= 0 )
+ { /* Not enough room in the buffer - grow it. */
+
+ /* just a shorter name for the current buffer */
+ YY_BUFFER_STATE b = YY_CURRENT_BUFFER;
+
+ int yy_c_buf_p_offset =
+ (int) ((yy_c_buf_p) - b->yy_ch_buf);
+
+ if ( b->yy_is_our_buffer )
+ {
+ int new_size = b->yy_buf_size * 2;
+
+ if ( new_size <= 0 )
+ b->yy_buf_size += b->yy_buf_size / 8;
+ else
+ b->yy_buf_size *= 2;
+
+ b->yy_ch_buf = (char *)
+ /* Include room in for 2 EOB chars. */
+ sensors_yyrealloc((void *) b->yy_ch_buf,b->yy_buf_size + 2 );
+ }
+ else
+ /* Can't grow it, we don't own it. */
+ b->yy_ch_buf = 0;
+
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR(
+ "fatal error - scanner input buffer overflow" );
+
+ (yy_c_buf_p) = &b->yy_ch_buf[yy_c_buf_p_offset];
+
+ num_to_read = YY_CURRENT_BUFFER_LVALUE->yy_buf_size -
+ number_to_move - 1;
+
+ }
+
+ if ( num_to_read > YY_READ_BUF_SIZE )
+ num_to_read = YY_READ_BUF_SIZE;
+
+ /* Read in more data. */
+ YY_INPUT( (&YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[number_to_move]),
+ (yy_n_chars), (size_t) num_to_read );
+
+ YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+ }
+
+ if ( (yy_n_chars) == 0 )
+ {
+ if ( number_to_move == YY_MORE_ADJ )
+ {
+ ret_val = EOB_ACT_END_OF_FILE;
+ sensors_yyrestart(sensors_yyin );
+ }
+
+ else
+ {
+ ret_val = EOB_ACT_LAST_MATCH;
+ YY_CURRENT_BUFFER_LVALUE->yy_buffer_status =
+ YY_BUFFER_EOF_PENDING;
+ }
+ }
+
+ else
+ ret_val = EOB_ACT_CONTINUE_SCAN;
+
+ if ((yy_size_t) ((yy_n_chars) + number_to_move) > YY_CURRENT_BUFFER_LVALUE->yy_buf_size) {
+ /* Extend the array by 50%, plus the number we really need. */
+ yy_size_t new_size = (yy_n_chars) + number_to_move + ((yy_n_chars) >> 1);
+ YY_CURRENT_BUFFER_LVALUE->yy_ch_buf = (char *) sensors_yyrealloc((void *) YY_CURRENT_BUFFER_LVALUE->yy_ch_buf,new_size );
+ if ( ! YY_CURRENT_BUFFER_LVALUE->yy_ch_buf )
+ YY_FATAL_ERROR( "out of dynamic memory in yy_get_next_buffer()" );
+ }
+
+ (yy_n_chars) += number_to_move;
+ YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] = YY_END_OF_BUFFER_CHAR;
+ YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars) + 1] = YY_END_OF_BUFFER_CHAR;
+
+ (yytext_ptr) = &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[0];
+
+ return ret_val;
+}
+
+/* yy_get_previous_state - get the state just before the EOB char was reached */
+
+ static yy_state_type yy_get_previous_state (void)
+{
+ register yy_state_type yy_current_state;
+ register char *yy_cp;
+
+ yy_current_state = (yy_start);
+
+ for ( yy_cp = (yytext_ptr) + YY_MORE_ADJ; yy_cp < (yy_c_buf_p); ++yy_cp )
+ {
+ yy_current_state = yy_nxt[yy_current_state][(*yy_cp ? yy_ec[YY_SC_TO_UI(*yy_cp)] : 1)];
+ }
+
+ return yy_current_state;
+}
+
+/* yy_try_NUL_trans - try to make a transition on the NUL character
+ *
+ * synopsis
+ * next_state = yy_try_NUL_trans( current_state );
+ */
+ static yy_state_type yy_try_NUL_trans (yy_state_type yy_current_state )
+{
+ register int yy_is_jam;
+
+ yy_current_state = yy_nxt[yy_current_state][1];
+ yy_is_jam = (yy_current_state <= 0);
+
+ return yy_is_jam ? 0 : yy_current_state;
+}
+
+#ifndef YY_NO_INPUT
+#ifdef __cplusplus
+ static int yyinput (void)
+#else
+ static int input (void)
+#endif
+
+{
+ int c;
+
+ *(yy_c_buf_p) = (yy_hold_char);
+
+ if ( *(yy_c_buf_p) == YY_END_OF_BUFFER_CHAR )
+ {
+ /* yy_c_buf_p now points to the character we want to return.
+ * If this occurs *before* the EOB characters, then it's a
+ * valid NUL; if not, then we've hit the end of the buffer.
+ */
+ if ( (yy_c_buf_p) < &YY_CURRENT_BUFFER_LVALUE->yy_ch_buf[(yy_n_chars)] )
+ /* This was really a NUL. */
+ *(yy_c_buf_p) = '\0';
+
+ else
+ { /* need more input */
+ int offset = (yy_c_buf_p) - (yytext_ptr);
+ ++(yy_c_buf_p);
+
+ switch ( yy_get_next_buffer( ) )
+ {
+ case EOB_ACT_LAST_MATCH:
+ /* This happens because yy_g_n_b()
+ * sees that we've accumulated a
+ * token and flags that we need to
+ * try matching the token before
+ * proceeding. But for input(),
+ * there's no matching to consider.
+ * So convert the EOB_ACT_LAST_MATCH
+ * to EOB_ACT_END_OF_FILE.
+ */
+
+ /* Reset buffer status. */
+ sensors_yyrestart(sensors_yyin );
+
+ /*FALLTHROUGH*/
+
+ case EOB_ACT_END_OF_FILE:
+ {
+ if ( sensors_yywrap( ) )
+ return EOF;
+
+ if ( ! (yy_did_buffer_switch_on_eof) )
+ YY_NEW_FILE;
+#ifdef __cplusplus
+ return yyinput();
+#else
+ return input();
+#endif
+ }
+
+ case EOB_ACT_CONTINUE_SCAN:
+ (yy_c_buf_p) = (yytext_ptr) + offset;
+ break;
+ }
+ }
+ }
+
+ c = *(unsigned char *) (yy_c_buf_p); /* cast for 8-bit char's */
+ *(yy_c_buf_p) = '\0'; /* preserve sensors_yytext */
+ (yy_hold_char) = *++(yy_c_buf_p);
+
+ return c;
+}
+#endif /* ifndef YY_NO_INPUT */
+
+/** Immediately switch to a different input stream.
+ * @param input_file A readable stream.
+ *
+ * @note This function does not reset the start condition to @c INITIAL .
+ */
+ void sensors_yyrestart (FILE * input_file )
+{
+
+ if ( ! YY_CURRENT_BUFFER ){
+ sensors_yyensure_buffer_stack ();
+ YY_CURRENT_BUFFER_LVALUE =
+ sensors_yy_create_buffer(sensors_yyin,YY_BUF_SIZE );
+ }
+
+ sensors_yy_init_buffer(YY_CURRENT_BUFFER,input_file );
+ sensors_yy_load_buffer_state( );
+}
+
+/** Switch to a different input buffer.
+ * @param new_buffer The new input buffer.
+ *
+ */
+ void sensors_yy_switch_to_buffer (YY_BUFFER_STATE new_buffer )
+{
+
+ /* TODO. We should be able to replace this entire function body
+ * with
+ * sensors_yypop_buffer_state();
+ * sensors_yypush_buffer_state(new_buffer);
+ */
+ sensors_yyensure_buffer_stack ();
+ if ( YY_CURRENT_BUFFER == new_buffer )
+ return;
+
+ if ( YY_CURRENT_BUFFER )
+ {
+ /* Flush out information for old buffer. */
+ *(yy_c_buf_p) = (yy_hold_char);
+ YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+ YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+ }
+
+ YY_CURRENT_BUFFER_LVALUE = new_buffer;
+ sensors_yy_load_buffer_state( );
+
+ /* We don't actually know whether we did this switch during
+ * EOF (sensors_yywrap()) processing, but the only time this flag
+ * is looked at is after sensors_yywrap() is called, so it's safe
+ * to go ahead and always set it.
+ */
+ (yy_did_buffer_switch_on_eof) = 1;
+}
+
+static void sensors_yy_load_buffer_state (void)
+{
+ (yy_n_chars) = YY_CURRENT_BUFFER_LVALUE->yy_n_chars;
+ (yytext_ptr) = (yy_c_buf_p) = YY_CURRENT_BUFFER_LVALUE->yy_buf_pos;
+ sensors_yyin = YY_CURRENT_BUFFER_LVALUE->yy_input_file;
+ (yy_hold_char) = *(yy_c_buf_p);
+}
+
+/** Allocate and initialize an input buffer state.
+ * @param file A readable stream.
+ * @param size The character buffer size in bytes. When in doubt, use @c YY_BUF_SIZE.
+ *
+ * @return the allocated buffer state.
+ */
+ YY_BUFFER_STATE sensors_yy_create_buffer (FILE * file, int size )
+{
+ YY_BUFFER_STATE b;
+
+ b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state ) );
+ if ( ! b )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+ b->yy_buf_size = size;
+
+ /* yy_ch_buf has to be 2 characters longer than the size given because
+ * we need to put in 2 end-of-buffer characters.
+ */
+ b->yy_ch_buf = (char *) sensors_yyalloc(b->yy_buf_size + 2 );
+ if ( ! b->yy_ch_buf )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_create_buffer()" );
+
+ b->yy_is_our_buffer = 1;
+
+ sensors_yy_init_buffer(b,file );
+
+ return b;
+}
+
+/** Destroy the buffer.
+ * @param b a buffer created with sensors_yy_create_buffer()
+ *
+ */
+ void sensors_yy_delete_buffer (YY_BUFFER_STATE b )
+{
+
+ if ( ! b )
+ return;
+
+ if ( b == YY_CURRENT_BUFFER ) /* Not sure if we should pop here. */
+ YY_CURRENT_BUFFER_LVALUE = (YY_BUFFER_STATE) 0;
+
+ if ( b->yy_is_our_buffer )
+ sensors_yyfree((void *) b->yy_ch_buf );
+
+ sensors_yyfree((void *) b );
+}
+
+#ifndef __cplusplus
+extern int isatty (int );
+#endif /* __cplusplus */
+
+/* Initializes or reinitializes a buffer.
+ * This function is sometimes called more than once on the same buffer,
+ * such as during a sensors_yyrestart() or at EOF.
+ */
+ static void sensors_yy_init_buffer (YY_BUFFER_STATE b, FILE * file )
+
+{
+ int oerrno = errno;
+
+ sensors_yy_flush_buffer(b );
+
+ b->yy_input_file = file;
+ b->yy_fill_buffer = 1;
+
+ /* If b is the current buffer, then sensors_yy_init_buffer was _probably_
+ * called from sensors_yyrestart() or through yy_get_next_buffer.
+ * In that case, we don't want to reset the lineno or column.
+ */
+ if (b != YY_CURRENT_BUFFER){
+ b->yy_bs_lineno = 1;
+ b->yy_bs_column = 0;
+ }
+
+ b->yy_is_interactive = file ? (isatty( fileno(file) ) > 0) : 0;
+
+ errno = oerrno;
+}
+
+/** Discard all buffered characters. On the next scan, YY_INPUT will be called.
+ * @param b the buffer state to be flushed, usually @c YY_CURRENT_BUFFER.
+ *
+ */
+ void sensors_yy_flush_buffer (YY_BUFFER_STATE b )
+{
+ if ( ! b )
+ return;
+
+ b->yy_n_chars = 0;
+
+ /* We always need two end-of-buffer characters. The first causes
+ * a transition to the end-of-buffer state. The second causes
+ * a jam in that state.
+ */
+ b->yy_ch_buf[0] = YY_END_OF_BUFFER_CHAR;
+ b->yy_ch_buf[1] = YY_END_OF_BUFFER_CHAR;
+
+ b->yy_buf_pos = &b->yy_ch_buf[0];
+
+ b->yy_at_bol = 1;
+ b->yy_buffer_status = YY_BUFFER_NEW;
+
+ if ( b == YY_CURRENT_BUFFER )
+ sensors_yy_load_buffer_state( );
+}
+
+/** Pushes the new state onto the stack. The new state becomes
+ * the current state. This function will allocate the stack
+ * if necessary.
+ * @param new_buffer The new state.
+ *
+ */
+void sensors_yypush_buffer_state (YY_BUFFER_STATE new_buffer )
+{
+ if (new_buffer == NULL)
+ return;
+
+ sensors_yyensure_buffer_stack();
+
+ /* This block is copied from sensors_yy_switch_to_buffer. */
+ if ( YY_CURRENT_BUFFER )
+ {
+ /* Flush out information for old buffer. */
+ *(yy_c_buf_p) = (yy_hold_char);
+ YY_CURRENT_BUFFER_LVALUE->yy_buf_pos = (yy_c_buf_p);
+ YY_CURRENT_BUFFER_LVALUE->yy_n_chars = (yy_n_chars);
+ }
+
+ /* Only push if top exists. Otherwise, replace top. */
+ if (YY_CURRENT_BUFFER)
+ (yy_buffer_stack_top)++;
+ YY_CURRENT_BUFFER_LVALUE = new_buffer;
+
+ /* copied from sensors_yy_switch_to_buffer. */
+ sensors_yy_load_buffer_state( );
+ (yy_did_buffer_switch_on_eof) = 1;
+}
+
+/** Removes and deletes the top of the stack, if present.
+ * The next element becomes the new top.
+ *
+ */
+void sensors_yypop_buffer_state (void)
+{
+ if (!YY_CURRENT_BUFFER)
+ return;
+
+ sensors_yy_delete_buffer(YY_CURRENT_BUFFER );
+ YY_CURRENT_BUFFER_LVALUE = NULL;
+ if ((yy_buffer_stack_top) > 0)
+ --(yy_buffer_stack_top);
+
+ if (YY_CURRENT_BUFFER) {
+ sensors_yy_load_buffer_state( );
+ (yy_did_buffer_switch_on_eof) = 1;
+ }
+}
+
+/* Allocates the stack if it does not exist.
+ * Guarantees space for at least one push.
+ */
+static void sensors_yyensure_buffer_stack (void)
+{
+ int num_to_alloc;
+
+ if (!(yy_buffer_stack)) {
+
+ /* First allocation is just for 2 elements, since we don't know if this
+ * scanner will even need a stack. We use 2 instead of 1 to avoid an
+ * immediate realloc on the next call.
+ */
+ num_to_alloc = 1;
+ (yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyalloc
+ (num_to_alloc * sizeof(struct yy_buffer_state*)
+ );
+ if ( ! (yy_buffer_stack) )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+
+ memset((yy_buffer_stack), 0, num_to_alloc * sizeof(struct yy_buffer_state*));
+
+ (yy_buffer_stack_max) = num_to_alloc;
+ (yy_buffer_stack_top) = 0;
+ return;
+ }
+
+ if ((yy_buffer_stack_top) >= ((yy_buffer_stack_max)) - 1){
+
+ /* Increase the buffer to prepare for a possible push. */
+ int grow_size = 8 /* arbitrary grow size */;
+
+ num_to_alloc = (yy_buffer_stack_max) + grow_size;
+ (yy_buffer_stack) = (struct yy_buffer_state**)sensors_yyrealloc
+ ((yy_buffer_stack),
+ num_to_alloc * sizeof(struct yy_buffer_state*)
+ );
+ if ( ! (yy_buffer_stack) )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yyensure_buffer_stack()" );
+
+ /* zero only the new slots.*/
+ memset((yy_buffer_stack) + (yy_buffer_stack_max), 0, grow_size * sizeof(struct yy_buffer_state*));
+ (yy_buffer_stack_max) = num_to_alloc;
+ }
+}
+
+/** Setup the input buffer state to scan directly from a user-specified character buffer.
+ * @param base the character buffer
+ * @param size the size in bytes of the character buffer
+ *
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE sensors_yy_scan_buffer (char * base, yy_size_t size )
+{
+ YY_BUFFER_STATE b;
+
+ if ( size < 2 ||
+ base[size-2] != YY_END_OF_BUFFER_CHAR ||
+ base[size-1] != YY_END_OF_BUFFER_CHAR )
+ /* They forgot to leave room for the EOB's. */
+ return 0;
+
+ b = (YY_BUFFER_STATE) sensors_yyalloc(sizeof( struct yy_buffer_state ) );
+ if ( ! b )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_buffer()" );
+
+ b->yy_buf_size = size - 2; /* "- 2" to take care of EOB's */
+ b->yy_buf_pos = b->yy_ch_buf = base;
+ b->yy_is_our_buffer = 0;
+ b->yy_input_file = 0;
+ b->yy_n_chars = b->yy_buf_size;
+ b->yy_is_interactive = 0;
+ b->yy_at_bol = 1;
+ b->yy_fill_buffer = 0;
+ b->yy_buffer_status = YY_BUFFER_NEW;
+
+ sensors_yy_switch_to_buffer(b );
+
+ return b;
+}
+
+/** Setup the input buffer state to scan a string. The next call to sensors_yylex() will
+ * scan from a @e copy of @a str.
+ * @param yystr a NUL-terminated string to scan
+ *
+ * @return the newly allocated buffer state object.
+ * @note If you want to scan bytes that may contain NUL values, then use
+ * sensors_yy_scan_bytes() instead.
+ */
+YY_BUFFER_STATE sensors_yy_scan_string (yyconst char * yystr )
+{
+
+ return sensors_yy_scan_bytes(yystr,strlen(yystr) );
+}
+
+/** Setup the input buffer state to scan the given bytes. The next call to sensors_yylex() will
+ * scan from a @e copy of @a bytes.
+ * @param yybytes the byte buffer to scan
+ * @param _yybytes_len the number of bytes in the buffer pointed to by @a bytes.
+ *
+ * @return the newly allocated buffer state object.
+ */
+YY_BUFFER_STATE sensors_yy_scan_bytes (yyconst char * yybytes, int _yybytes_len )
+{
+ YY_BUFFER_STATE b;
+ char *buf;
+ yy_size_t n;
+ int i;
+
+ /* Get memory for full buffer, including space for trailing EOB's. */
+ n = _yybytes_len + 2;
+ buf = (char *) sensors_yyalloc(n );
+ if ( ! buf )
+ YY_FATAL_ERROR( "out of dynamic memory in sensors_yy_scan_bytes()" );
+
+ for ( i = 0; i < _yybytes_len; ++i )
+ buf[i] = yybytes[i];
+
+ buf[_yybytes_len] = buf[_yybytes_len+1] = YY_END_OF_BUFFER_CHAR;
+
+ b = sensors_yy_scan_buffer(buf,n );
+ if ( ! b )
+ YY_FATAL_ERROR( "bad buffer in sensors_yy_scan_bytes()" );
+
+ /* It's okay to grow etc. this buffer, and we should throw it
+ * away when we're done.
+ */
+ b->yy_is_our_buffer = 1;
+
+ return b;
+}
+
+#ifndef YY_EXIT_FAILURE
+#define YY_EXIT_FAILURE 2
+#endif
+
+static void yy_fatal_error (yyconst char* msg )
+{
+ (void) fprintf( stderr, "%s\n", msg );
+ exit( YY_EXIT_FAILURE );
+}
+
+/* Redefine yyless() so it works in section 3 code. */
+
+#undef yyless
+#define yyless(n) \
+ do \
+ { \
+ /* Undo effects of setting up sensors_yytext. */ \
+ int yyless_macro_arg = (n); \
+ YY_LESS_LINENO(yyless_macro_arg);\
+ sensors_yytext[sensors_yyleng] = (yy_hold_char); \
+ (yy_c_buf_p) = sensors_yytext + yyless_macro_arg; \
+ (yy_hold_char) = *(yy_c_buf_p); \
+ *(yy_c_buf_p) = '\0'; \
+ sensors_yyleng = yyless_macro_arg; \
+ } \
+ while ( 0 )
+
+/* Accessor methods (get/set functions) to struct members. */
+
+/** Get the current line number.
+ *
+ */
+int sensors_yyget_lineno (void)
+{
+
+ return sensors_yylineno;
+}
+
+/** Get the input stream.
+ *
+ */
+FILE *sensors_yyget_in (void)
+{
+ return sensors_yyin;
+}
+
+/** Get the output stream.
+ *
+ */
+FILE *sensors_yyget_out (void)
+{
+ return sensors_yyout;
+}
+
+/** Get the length of the current token.
+ *
+ */
+int sensors_yyget_leng (void)
+{
+ return sensors_yyleng;
+}
+
+/** Get the current token.
+ *
+ */
+
+char *sensors_yyget_text (void)
+{
+ return sensors_yytext;
+}
+
+/** Set the current line number.
+ * @param line_number
+ *
+ */
+void sensors_yyset_lineno (int line_number )
+{
+
+ sensors_yylineno = line_number;
+}
+
+/** Set the input stream. This does not discard the current
+ * input buffer.
+ * @param in_str A readable stream.
+ *
+ * @see sensors_yy_switch_to_buffer
+ */
+void sensors_yyset_in (FILE * in_str )
+{
+ sensors_yyin = in_str ;
+}
+
+void sensors_yyset_out (FILE * out_str )
+{
+ sensors_yyout = out_str ;
+}
+
+int sensors_yyget_debug (void)
+{
+ return sensors_yy_flex_debug;
+}
+
+void sensors_yyset_debug (int bdebug )
+{
+ sensors_yy_flex_debug = bdebug ;
+}
+
+static int yy_init_globals (void)
+{
+ /* Initialization is the same as for the non-reentrant scanner.
+ * This function is called from sensors_yylex_destroy(), so don't allocate here.
+ */
+
+ (yy_buffer_stack) = 0;
+ (yy_buffer_stack_top) = 0;
+ (yy_buffer_stack_max) = 0;
+ (yy_c_buf_p) = (char *) 0;
+ (yy_init) = 0;
+ (yy_start) = 0;
+
+/* Defined in main.c */
+#ifdef YY_STDINIT
+ sensors_yyin = stdin;
+ sensors_yyout = stdout;
+#else
+ sensors_yyin = (FILE *) 0;
+ sensors_yyout = (FILE *) 0;
+#endif
+
+ /* For future reference: Set errno on error, since we are called by
+ * sensors_yylex_init()
+ */
+ return 0;
+}
+
+/* sensors_yylex_destroy is for both reentrant and non-reentrant scanners. */
+int sensors_yylex_destroy (void)
+{
+
+ /* Pop the buffer stack, destroying each element. */
+ while(YY_CURRENT_BUFFER){
+ sensors_yy_delete_buffer(YY_CURRENT_BUFFER );
+ YY_CURRENT_BUFFER_LVALUE = NULL;
+ sensors_yypop_buffer_state();
+ }
+
+ /* Destroy the stack itself. */
+ sensors_yyfree((yy_buffer_stack) );
+ (yy_buffer_stack) = NULL;
+
+ /* Reset the globals. This is important in a non-reentrant scanner so the next time
+ * sensors_yylex() is called, initialization will occur. */
+ yy_init_globals( );
+
+ return 0;
+}
+
+/*
+ * Internal utility routines.
+ */
+
+#ifndef yytext_ptr
+static void yy_flex_strncpy (char* s1, yyconst char * s2, int n )
+{
+ register int i;
+ for ( i = 0; i < n; ++i )
+ s1[i] = s2[i];
+}
+#endif
+
+#ifdef YY_NEED_STRLEN
+static int yy_flex_strlen (yyconst char * s )
+{
+ register int n;
+ for ( n = 0; s[n]; ++n )
+ ;
+
+ return n;
+}
+#endif
+
+void *sensors_yyalloc (yy_size_t size )
+{
+ return (void *) malloc( size );
+}
+
+void *sensors_yyrealloc (void * ptr, yy_size_t size )
+{
+ /* The cast to (char *) in the following accommodates both
+ * implementations that use char* generic pointers, and those
+ * that use void* generic pointers. It works with the latter
+ * because both ANSI C and C++ allow castless assignment from
+ * any pointer type to void*, and deal with argument conversions
+ * as though doing an assignment.
+ */
+ return (void *) realloc( (char *) ptr, size );
+}
+
+void sensors_yyfree (void * ptr )
+{
+ free( (char *) ptr ); /* see sensors_yyrealloc() for (char *) cast */
+}
+
+#define YYTABLES_NAME "yytables"
+
+#line 332 "lib/conf-lex.l"
+
+
+
+/*
+ Do the buffer handling manually. This allows us to scan as many
+ config files as we need to, while cleaning up properly after each
+ one. The "BEGIN(0)" line ensures that we start in the default state,
+ even if e.g. the previous config file was syntactically broken.
+
+ Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+ BEGIN(0);
+ if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+ return -1;
+
+ sensors_yy_switch_to_buffer(scan_buf);
+ sensors_yyfilename = filename;
+ sensors_yylineno = 1;
+ return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+ sensors_yy_delete_buffer(scan_buf);
+ scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, sensors_yylex_destroy() must be called when done with the
+ scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+ (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+ (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+ sensors_yylex_destroy();
+#endif
+#endif
+}
+
+
diff --git a/tools/gator/daemon/libsensors/conf-lex.l b/tools/gator/daemon/libsensors/conf-lex.l
new file mode 100644
index 0000000..43ddbd8
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-lex.l
@@ -0,0 +1,372 @@
+%{
+/*
+ conf-lex.l - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "general.h"
+#include "data.h"
+#include "conf-parse.h"
+#include "error.h"
+#include "scanner.h"
+
+static int buffer_count;
+static int buffer_max;
+static char *buffer;
+
+char sensors_lex_error[100];
+
+const char *sensors_yyfilename;
+int sensors_yylineno;
+
+#define buffer_malloc() sensors_malloc_array(&buffer,&buffer_count,\
+ &buffer_max,1)
+#define buffer_free() sensors_free_array(&buffer,&buffer_count,\
+ &buffer_max)
+#define buffer_add_char(c) sensors_add_array_el(c,&buffer,\
+ &buffer_count,\
+ &buffer_max,1)
+#define buffer_add_string(s) sensors_add_array_els(s,strlen(s),\
+ &buffer, \
+ &buffer_count,&buffer_max,1)
+
+%}
+
+ /* Scanner for configuration files */
+
+%option nodefault
+%option noyywrap
+%option nounput
+
+ /* All states are exclusive */
+
+%x MIDDLE
+%x STRING
+%x ERR
+
+ /* Any whitespace-like character */
+
+BLANK [ \f\r\t\v]
+
+IDCHAR [[:alnum:]_]
+
+ /* Note: `10', `10.4' and `.4' are valid, `10.' is not */
+
+FLOAT [[:digit:]]*\.?[[:digit:]]+
+
+ /* Only positive whole numbers are recognized here */
+
+NUM 0|([1-9][[:digit:]]*)
+
+
+%%
+
+ /*
+ * STATE: INITIAL
+ */
+
+<INITIAL>{
+
+<<EOF>> { /* EOF from this state terminates */
+ return 0;
+ }
+
+{BLANK}+ ; /* eat as many blanks as possible at once */
+
+{BLANK}*\n { /* eat a bare newline (possibly preceded by blanks) */
+ sensors_yylineno++;
+ }
+
+ /* comments */
+
+#.* ; /* eat the rest of the line after comment char */
+
+#.*\n { /* eat the rest of the line after comment char */
+ sensors_yylineno++;
+ }
+
+ /*
+ * Keywords must be followed by whitespace - eat that too.
+ * If there isn't trailing whitespace, we still need to
+ * accept it as lexically correct (even though the parser
+ * will reject it anyway.)
+ */
+
+label{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return LABEL;
+ }
+
+set{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return SET;
+ }
+
+compute{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return COMPUTE;
+ }
+
+bus{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return BUS;
+ }
+
+chip{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return CHIP;
+ }
+
+ignore{BLANK}* {
+ sensors_yylval.line.filename = sensors_yyfilename;
+ sensors_yylval.line.lineno = sensors_yylineno;
+ BEGIN(MIDDLE);
+ return IGNORE;
+ }
+
+ /* Anything else at the beginning of a line is an error */
+
+[a-z]+ |
+. {
+ BEGIN(ERR);
+ strcpy(sensors_lex_error,"Invalid keyword");
+ return ERROR;
+ }
+}
+
+ /*
+ * STATE: ERROR
+ */
+
+<ERR>{
+
+.* ; /* eat whatever is left on this line */
+
+\n {
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+}
+
+ /*
+ * STATE: MIDDLE
+ */
+
+<MIDDLE>{
+
+{BLANK}+ ; /* eat as many blanks as possible at once */
+
+\n { /* newline here sends EOL token to parser */
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+
+<<EOF>> { /* EOF here sends EOL token to parser also */
+ BEGIN(INITIAL);
+ return EOL;
+ }
+
+\\{BLANK}*\n { /* eat an escaped newline with no state change */
+ sensors_yylineno++;
+ }
+
+ /* comments */
+
+#.* ; /* eat the rest of the line after comment char */
+
+#.*\n { /* eat the rest of the line after comment char */
+ BEGIN(INITIAL);
+ sensors_yylineno++;
+ return EOL;
+ }
+
+ /* A number */
+
+{FLOAT} {
+ sensors_yylval.value = atof(sensors_yytext);
+ return FLOAT;
+ }
+
+ /* Some operators */
+
+"+" return '+';
+"-" return '-';
+"*" return '*';
+"/" return '/';
+"(" return '(';
+")" return ')';
+"," return ',';
+"@" return '@';
+"^" return '^';
+"`" return '`';
+
+ /* Quoted string */
+
+\" {
+ buffer_malloc();
+ BEGIN(STRING);
+ }
+
+ /* A normal, unquoted identifier */
+
+{IDCHAR}+ {
+ sensors_yylval.name = strdup(sensors_yytext);
+ if (! sensors_yylval.name)
+ sensors_fatal_error("conf-lex.l",
+ "Allocating a new string");
+
+ return NAME;
+ }
+
+ /* anything else is bogus */
+
+. |
+[[:digit:]]*\. |
+\\{BLANK}* {
+ BEGIN(ERR);
+ return ERROR;
+ }
+}
+
+ /*
+ * STATE: STRING
+ */
+
+<STRING>{
+
+ /* Oops, newline or EOF while in a string is not good */
+
+\n |
+\\\n {
+ buffer_add_char("\0");
+ strcpy(sensors_lex_error,
+ "No matching double quote.");
+ buffer_free();
+ yyless(0);
+ BEGIN(ERR);
+ return ERROR;
+ }
+
+<<EOF>> {
+ strcpy(sensors_lex_error,
+ "Reached end-of-file without a matching double quote.");
+ buffer_free();
+ BEGIN(MIDDLE);
+ return ERROR;
+ }
+
+ /* At the end */
+
+\"\" {
+ buffer_add_char("\0");
+ strcpy(sensors_lex_error,
+ "Quoted strings must be separated by whitespace.");
+ buffer_free();
+ BEGIN(ERR);
+ return ERROR;
+ }
+
+\" {
+ buffer_add_char("\0");
+ sensors_yylval.name = strdup(buffer);
+ if (! sensors_yylval.name)
+ sensors_fatal_error("conf-lex.l",
+ "Allocating a new string");
+ buffer_free();
+ BEGIN(MIDDLE);
+ return NAME;
+ }
+
+\\a buffer_add_char("\a");
+\\b buffer_add_char("\b");
+\\f buffer_add_char("\f");
+\\n buffer_add_char("\n");
+\\r buffer_add_char("\r");
+\\t buffer_add_char("\t");
+\\v buffer_add_char("\v");
+
+ /* Other escapes: just copy the character behind the slash */
+
+\\. {
+ buffer_add_char(&sensors_yytext[1]);
+ }
+
+ /* Anything else (including a bare '\' which may be followed by EOF) */
+
+\\ |
+[^\\\n\"]+ {
+ buffer_add_string(sensors_yytext);
+ }
+}
+
+%%
+
+/*
+ Do the buffer handling manually. This allows us to scan as many
+ config files as we need to, while cleaning up properly after each
+ one. The "BEGIN(0)" line ensures that we start in the default state,
+ even if e.g. the previous config file was syntactically broken.
+
+ Returns 0 if successful, !0 otherwise.
+*/
+
+static YY_BUFFER_STATE scan_buf = (YY_BUFFER_STATE)0;
+
+int sensors_scanner_init(FILE *input, const char *filename)
+{
+ BEGIN(0);
+ if (!(scan_buf = sensors_yy_create_buffer(input, YY_BUF_SIZE)))
+ return -1;
+
+ sensors_yy_switch_to_buffer(scan_buf);
+ sensors_yyfilename = filename;
+ sensors_yylineno = 1;
+ return 0;
+}
+
+void sensors_scanner_exit(void)
+{
+ sensors_yy_delete_buffer(scan_buf);
+ scan_buf = (YY_BUFFER_STATE)0;
+
+/* As of flex 2.5.9, yylex_destroy() must be called when done with the
+ scaller, otherwise we'll leak memory. */
+#if defined(YY_FLEX_MAJOR_VERSION) && defined(YY_FLEX_MINOR_VERSION) && defined(YY_FLEX_SUBMINOR_VERSION)
+#if YY_FLEX_MAJOR_VERSION > 2 || \
+ (YY_FLEX_MAJOR_VERSION == 2 && (YY_FLEX_MINOR_VERSION > 5 || \
+ (YY_FLEX_MINOR_VERSION == 5 && YY_FLEX_SUBMINOR_VERSION >= 9)))
+ sensors_yylex_destroy();
+#endif
+#endif
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.c b/tools/gator/daemon/libsensors/conf-parse.c
new file mode 100644
index 0000000..fb77546
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.c
@@ -0,0 +1,2042 @@
+/* A Bison parser, made by GNU Bison 2.5. */
+
+/* Bison implementation for Yacc-like parsers in C
+
+ Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+/* As a special exception, you may create a larger work that contains
+ part or all of the Bison parser skeleton and distribute that work
+ under terms of your choice, so long as that work isn't itself a
+ parser generator using the skeleton or a modified version thereof
+ as a parser skeleton. Alternatively, if you modify or redistribute
+ the parser skeleton itself, you may (at your option) remove this
+ special exception, which will cause the skeleton and the resulting
+ Bison output files to be licensed under the GNU General Public
+ License without this special exception.
+
+ This special exception was added by the Free Software Foundation in
+ version 2.2 of Bison. */
+
+/* C LALR(1) parser skeleton written by Richard Stallman, by
+ simplifying the original so-called "semantic" parser. */
+
+/* All symbols defined below should begin with yy or YY, to avoid
+ infringing on user name space. This should be done even for local
+ variables, as they might otherwise be expanded by user macros.
+ There are some unavoidable exceptions within include files to
+ define necessary library symbols; they are noted "INFRINGES ON
+ USER NAME SPACE" below. */
+
+/* Identify Bison output. */
+#define YYBISON 1
+
+/* Bison version. */
+#define YYBISON_VERSION "2.5"
+
+/* Skeleton name. */
+#define YYSKELETON_NAME "yacc.c"
+
+/* Pure parsers. */
+#define YYPURE 0
+
+/* Push parsers. */
+#define YYPUSH 0
+
+/* Pull parsers. */
+#define YYPULL 1
+
+/* Using locations. */
+#define YYLSP_NEEDED 0
+
+/* Substitute the variable and function names. */
+#define yyparse sensors_yyparse
+#define yylex sensors_yylex
+#define yyerror sensors_yyerror
+#define yylval sensors_yylval
+#define yychar sensors_yychar
+#define yydebug sensors_yydebug
+#define yynerrs sensors_yynerrs
+
+
+/* Copy the first part of user declarations. */
+
+/* Line 268 of yacc.c */
+#line 1 "lib/conf-parse.y"
+
+/*
+ conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+ &sensors_config_busses,\
+ &sensors_config_busses_count,\
+ &sensors_config_busses_max,\
+ sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->labels,\
+ ¤t_chip->labels_count,\
+ ¤t_chip->labels_max,\
+ sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->sets,\
+ ¤t_chip->sets_count,\
+ ¤t_chip->sets_max,\
+ sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->computes,\
+ ¤t_chip->computes_count,\
+ ¤t_chip->computes_max,\
+ sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->ignores,\
+ ¤t_chip->ignores_count,\
+ ¤t_chip->ignores_max,\
+ sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+ &sensors_config_chips,\
+ &sensors_config_chips_count,\
+ &sensors_config_chips_max,\
+ sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+ &(list).fits,\
+ &(list).fits_count,\
+ &(list).fits_max, \
+ sizeof(sensors_chip_name));
+
+
+
+/* Line 268 of yacc.c */
+#line 158 "lib/conf-parse.c"
+
+/* Enabling traces. */
+#ifndef YYDEBUG
+# define YYDEBUG 0
+#endif
+
+/* Enabling verbose error messages. */
+#ifdef YYERROR_VERBOSE
+# undef YYERROR_VERBOSE
+# define YYERROR_VERBOSE 1
+#else
+# define YYERROR_VERBOSE 0
+#endif
+
+/* Enabling the token table. */
+#ifndef YYTOKEN_TABLE
+# define YYTOKEN_TABLE 0
+#endif
+
+
+/* Tokens. */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+ /* Put the tokens into the symbol table, so that GDB and other debuggers
+ know about them. */
+ enum yytokentype {
+ NEG = 258,
+ EOL = 259,
+ BUS = 260,
+ LABEL = 261,
+ SET = 262,
+ CHIP = 263,
+ COMPUTE = 264,
+ IGNORE = 265,
+ FLOAT = 266,
+ NAME = 267,
+ ERROR = 268
+ };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 293 of yacc.c */
+#line 79 "lib/conf-parse.y"
+
+ double value;
+ char *name;
+ void *nothing;
+ sensors_chip_name_list chips;
+ sensors_expr *expr;
+ sensors_bus_id bus;
+ sensors_chip_name chip;
+ sensors_config_line line;
+
+
+
+/* Line 293 of yacc.c */
+#line 220 "lib/conf-parse.c"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+
+/* Copy the second part of user declarations. */
+
+
+/* Line 343 of yacc.c */
+#line 232 "lib/conf-parse.c"
+
+#ifdef short
+# undef short
+#endif
+
+#ifdef YYTYPE_UINT8
+typedef YYTYPE_UINT8 yytype_uint8;
+#else
+typedef unsigned char yytype_uint8;
+#endif
+
+#ifdef YYTYPE_INT8
+typedef YYTYPE_INT8 yytype_int8;
+#elif (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+typedef signed char yytype_int8;
+#else
+typedef short int yytype_int8;
+#endif
+
+#ifdef YYTYPE_UINT16
+typedef YYTYPE_UINT16 yytype_uint16;
+#else
+typedef unsigned short int yytype_uint16;
+#endif
+
+#ifdef YYTYPE_INT16
+typedef YYTYPE_INT16 yytype_int16;
+#else
+typedef short int yytype_int16;
+#endif
+
+#ifndef YYSIZE_T
+# ifdef __SIZE_TYPE__
+# define YYSIZE_T __SIZE_TYPE__
+# elif defined size_t
+# define YYSIZE_T size_t
+# elif ! defined YYSIZE_T && (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+# include <stddef.h> /* INFRINGES ON USER NAME SPACE */
+# define YYSIZE_T size_t
+# else
+# define YYSIZE_T unsigned int
+# endif
+#endif
+
+#define YYSIZE_MAXIMUM ((YYSIZE_T) -1)
+
+#ifndef YY_
+# if defined YYENABLE_NLS && YYENABLE_NLS
+# if ENABLE_NLS
+# include <libintl.h> /* INFRINGES ON USER NAME SPACE */
+# define YY_(msgid) dgettext ("bison-runtime", msgid)
+# endif
+# endif
+# ifndef YY_
+# define YY_(msgid) msgid
+# endif
+#endif
+
+/* Suppress unused-variable warnings by "using" E. */
+#if ! defined lint || defined __GNUC__
+# define YYUSE(e) ((void) (e))
+#else
+# define YYUSE(e) /* empty */
+#endif
+
+/* Identity function, used to suppress warnings about constant conditions. */
+#ifndef lint
+# define YYID(n) (n)
+#else
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static int
+YYID (int yyi)
+#else
+static int
+YYID (yyi)
+ int yyi;
+#endif
+{
+ return yyi;
+}
+#endif
+
+#if ! defined yyoverflow || YYERROR_VERBOSE
+
+/* The parser invokes alloca or malloc; define the necessary symbols. */
+
+# ifdef YYSTACK_USE_ALLOCA
+# if YYSTACK_USE_ALLOCA
+# ifdef __GNUC__
+# define YYSTACK_ALLOC __builtin_alloca
+# elif defined __BUILTIN_VA_ARG_INCR
+# include <alloca.h> /* INFRINGES ON USER NAME SPACE */
+# elif defined _AIX
+# define YYSTACK_ALLOC __alloca
+# elif defined _MSC_VER
+# include <malloc.h> /* INFRINGES ON USER NAME SPACE */
+# define alloca _alloca
+# else
+# define YYSTACK_ALLOC alloca
+# if ! defined _ALLOCA_H && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+# include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+# ifndef EXIT_SUCCESS
+# define EXIT_SUCCESS 0
+# endif
+# endif
+# endif
+# endif
+# endif
+
+# ifdef YYSTACK_ALLOC
+ /* Pacify GCC's `empty if-body' warning. */
+# define YYSTACK_FREE(Ptr) do { /* empty */; } while (YYID (0))
+# ifndef YYSTACK_ALLOC_MAXIMUM
+ /* The OS might guarantee only one guard page at the bottom of the stack,
+ and a page size can be as small as 4096 bytes. So we cannot safely
+ invoke alloca (N) if N exceeds 4096. Use a slightly smaller number
+ to allow for a few compiler-allocated temporary stack slots. */
+# define YYSTACK_ALLOC_MAXIMUM 4032 /* reasonable circa 2006 */
+# endif
+# else
+# define YYSTACK_ALLOC YYMALLOC
+# define YYSTACK_FREE YYFREE
+# ifndef YYSTACK_ALLOC_MAXIMUM
+# define YYSTACK_ALLOC_MAXIMUM YYSIZE_MAXIMUM
+# endif
+# if (defined __cplusplus && ! defined EXIT_SUCCESS \
+ && ! ((defined YYMALLOC || defined malloc) \
+ && (defined YYFREE || defined free)))
+# include <stdlib.h> /* INFRINGES ON USER NAME SPACE */
+# ifndef EXIT_SUCCESS
+# define EXIT_SUCCESS 0
+# endif
+# endif
+# ifndef YYMALLOC
+# define YYMALLOC malloc
+# if ! defined malloc && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+void *malloc (YYSIZE_T); /* INFRINGES ON USER NAME SPACE */
+# endif
+# endif
+# ifndef YYFREE
+# define YYFREE free
+# if ! defined free && ! defined EXIT_SUCCESS && (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+void free (void *); /* INFRINGES ON USER NAME SPACE */
+# endif
+# endif
+# endif
+#endif /* ! defined yyoverflow || YYERROR_VERBOSE */
+
+
+#if (! defined yyoverflow \
+ && (! defined __cplusplus \
+ || (defined YYSTYPE_IS_TRIVIAL && YYSTYPE_IS_TRIVIAL)))
+
+/* A type that is properly aligned for any stack member. */
+union yyalloc
+{
+ yytype_int16 yyss_alloc;
+ YYSTYPE yyvs_alloc;
+};
+
+/* The size of the maximum gap between one aligned stack and the next. */
+# define YYSTACK_GAP_MAXIMUM (sizeof (union yyalloc) - 1)
+
+/* The size of an array large to enough to hold all stacks, each with
+ N elements. */
+# define YYSTACK_BYTES(N) \
+ ((N) * (sizeof (yytype_int16) + sizeof (YYSTYPE)) \
+ + YYSTACK_GAP_MAXIMUM)
+
+# define YYCOPY_NEEDED 1
+
+/* Relocate STACK from its old location to the new one. The
+ local variables YYSIZE and YYSTACKSIZE give the old and new number of
+ elements in the stack, and YYPTR gives the new location of the
+ stack. Advance YYPTR to a properly aligned location for the next
+ stack. */
+# define YYSTACK_RELOCATE(Stack_alloc, Stack) \
+ do \
+ { \
+ YYSIZE_T yynewbytes; \
+ YYCOPY (&yyptr->Stack_alloc, Stack, yysize); \
+ Stack = &yyptr->Stack_alloc; \
+ yynewbytes = yystacksize * sizeof (*Stack) + YYSTACK_GAP_MAXIMUM; \
+ yyptr += yynewbytes / sizeof (*yyptr); \
+ } \
+ while (YYID (0))
+
+#endif
+
+#if defined YYCOPY_NEEDED && YYCOPY_NEEDED
+/* Copy COUNT objects from FROM to TO. The source and destination do
+ not overlap. */
+# ifndef YYCOPY
+# if defined __GNUC__ && 1 < __GNUC__
+# define YYCOPY(To, From, Count) \
+ __builtin_memcpy (To, From, (Count) * sizeof (*(From)))
+# else
+# define YYCOPY(To, From, Count) \
+ do \
+ { \
+ YYSIZE_T yyi; \
+ for (yyi = 0; yyi < (Count); yyi++) \
+ (To)[yyi] = (From)[yyi]; \
+ } \
+ while (YYID (0))
+# endif
+# endif
+#endif /* !YYCOPY_NEEDED */
+
+/* YYFINAL -- State number of the termination state. */
+#define YYFINAL 2
+/* YYLAST -- Last index in YYTABLE. */
+#define YYLAST 58
+
+/* YYNTOKENS -- Number of terminals. */
+#define YYNTOKENS 24
+/* YYNNTS -- Number of nonterminals. */
+#define YYNNTS 16
+/* YYNRULES -- Number of rules. */
+#define YYNRULES 34
+/* YYNRULES -- Number of states. */
+#define YYNSTATES 63
+
+/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX. */
+#define YYUNDEFTOK 2
+#define YYMAXUTOK 268
+
+#define YYTRANSLATE(YYX) \
+ ((unsigned int) (YYX) <= YYMAXUTOK ? yytranslate[YYX] : YYUNDEFTOK)
+
+/* YYTRANSLATE[YYLEX] -- Bison symbol number corresponding to YYLEX. */
+static const yytype_uint8 yytranslate[] =
+{
+ 0, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 22, 23, 5, 4, 10, 3, 2, 6, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 21, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 8, 2, 9, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
+ 2, 2, 2, 2, 2, 2, 1, 2, 7, 11,
+ 12, 13, 14, 15, 16, 17, 18, 19, 20
+};
+
+#if YYDEBUG
+/* YYPRHS[YYN] -- Index of the first RHS symbol of rule number YYN in
+ YYRHS. */
+static const yytype_uint8 yyprhs[] =
+{
+ 0, 0, 3, 4, 7, 10, 13, 16, 19, 22,
+ 25, 28, 32, 36, 40, 46, 49, 52, 54, 57,
+ 59, 61, 63, 67, 71, 75, 79, 82, 86, 89,
+ 92, 94, 96, 98, 100
+};
+
+/* YYRHS -- A `-1'-separated list of the rules' RHS. */
+static const yytype_int8 yyrhs[] =
+{
+ 25, 0, -1, -1, 25, 26, -1, 27, 11, -1,
+ 28, 11, -1, 29, 11, -1, 32, 11, -1, 30,
+ 11, -1, 31, 11, -1, 1, 11, -1, 12, 35,
+ 36, -1, 13, 37, 38, -1, 14, 37, 34, -1,
+ 16, 37, 34, 10, 34, -1, 17, 37, -1, 15,
+ 33, -1, 39, -1, 33, 39, -1, 18, -1, 19,
+ -1, 21, -1, 34, 4, 34, -1, 34, 3, 34,
+ -1, 34, 5, 34, -1, 34, 6, 34, -1, 3,
+ 34, -1, 22, 34, 23, -1, 8, 34, -1, 9,
+ 34, -1, 19, -1, 19, -1, 19, -1, 19, -1,
+ 19, -1
+};
+
+/* YYRLINE[YYN] -- source line where rule number YYN was defined. */
+static const yytype_uint16 yyrline[] =
+{
+ 0, 119, 119, 120, 123, 124, 125, 126, 127, 128,
+ 129, 132, 141, 156, 171, 188, 201, 219, 225, 231,
+ 236, 241, 245, 252, 259, 266, 273, 280, 282, 289,
+ 298, 308, 312, 316, 320
+};
+#endif
+
+#if YYDEBUG || YYERROR_VERBOSE || YYTOKEN_TABLE
+/* YYTNAME[SYMBOL-NUM] -- String name of the symbol SYMBOL-NUM.
+ First, the terminals, then, starting at YYNTOKENS, nonterminals. */
+static const char *const yytname[] =
+{
+ "$end", "error", "$undefined", "'-'", "'+'", "'*'", "'/'", "NEG", "'^'",
+ "'`'", "','", "EOL", "BUS", "LABEL", "SET", "CHIP", "COMPUTE", "IGNORE",
+ "FLOAT", "NAME", "ERROR", "'@'", "'('", "')'", "$accept", "input",
+ "line", "bus_statement", "label_statement", "set_statement",
+ "compute_statement", "ignore_statement", "chip_statement",
+ "chip_name_list", "expression", "bus_id", "adapter_name",
+ "function_name", "string", "chip_name", 0
+};
+#endif
+
+# ifdef YYPRINT
+/* YYTOKNUM[YYLEX-NUM] -- Internal token number corresponding to
+ token YYLEX-NUM. */
+static const yytype_uint16 yytoknum[] =
+{
+ 0, 256, 257, 45, 43, 42, 47, 258, 94, 96,
+ 44, 259, 260, 261, 262, 263, 264, 265, 266, 267,
+ 268, 64, 40, 41
+};
+# endif
+
+/* YYR1[YYN] -- Symbol number of symbol that rule YYN derives. */
+static const yytype_uint8 yyr1[] =
+{
+ 0, 24, 25, 25, 26, 26, 26, 26, 26, 26,
+ 26, 27, 28, 29, 30, 31, 32, 33, 33, 34,
+ 34, 34, 34, 34, 34, 34, 34, 34, 34, 34,
+ 35, 36, 37, 38, 39
+};
+
+/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN. */
+static const yytype_uint8 yyr2[] =
+{
+ 0, 2, 0, 2, 2, 2, 2, 2, 2, 2,
+ 2, 3, 3, 3, 5, 2, 2, 1, 2, 1,
+ 1, 1, 3, 3, 3, 3, 2, 3, 2, 2,
+ 1, 1, 1, 1, 1
+};
+
+/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
+ Performed when YYTABLE doesn't specify something else to do. Zero
+ means the default is an error. */
+static const yytype_uint8 yydefact[] =
+{
+ 2, 0, 1, 0, 0, 0, 0, 0, 0, 0,
+ 3, 0, 0, 0, 0, 0, 0, 10, 30, 0,
+ 32, 0, 0, 34, 16, 17, 0, 15, 4, 5,
+ 6, 8, 9, 7, 31, 11, 33, 12, 0, 0,
+ 0, 19, 20, 21, 0, 13, 18, 0, 26, 28,
+ 29, 0, 0, 0, 0, 0, 0, 27, 23, 22,
+ 24, 25, 14
+};
+
+/* YYDEFGOTO[NTERM-NUM]. */
+static const yytype_int8 yydefgoto[] =
+{
+ -1, 1, 10, 11, 12, 13, 14, 15, 16, 24,
+ 45, 19, 35, 21, 37, 25
+};
+
+/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
+ STATE-NUM. */
+#define YYPACT_NINF -27
+static const yytype_int8 yypact[] =
+{
+ -27, 37, -27, -4, -3, 1, 1, 6, 1, 1,
+ -27, 8, 13, 20, 23, 32, 34, -27, -27, 29,
+ -27, 39, 14, -27, 6, -27, 14, -27, -27, -27,
+ -27, -27, -27, -27, -27, -27, -27, -27, 14, 14,
+ 14, -27, -27, -27, 14, 36, -27, 5, -27, -27,
+ -27, -2, 14, 14, 14, 14, 14, -27, 0, 0,
+ -27, -27, 36
+};
+
+/* YYPGOTO[NTERM-NUM]. */
+static const yytype_int8 yypgoto[] =
+{
+ -27, -27, -27, -27, -27, -27, -27, -27, -27, -27,
+ -26, -27, -27, 38, -27, 31
+};
+
+/* YYTABLE[YYPACT[STATE-NUM]]. What to do in state STATE-NUM. If
+ positive, shift that token. If negative, reduce the rule which
+ number is the opposite. If YYTABLE_NINF, syntax error. */
+#define YYTABLE_NINF -1
+static const yytype_uint8 yytable[] =
+{
+ 47, 52, 53, 54, 55, 54, 55, 17, 52, 53,
+ 54, 55, 48, 49, 50, 56, 18, 38, 51, 28,
+ 20, 57, 39, 40, 29, 23, 58, 59, 60, 61,
+ 62, 30, 41, 42, 31, 43, 44, 2, 3, 52,
+ 53, 54, 55, 32, 22, 33, 26, 27, 34, 4,
+ 5, 6, 7, 8, 9, 46, 0, 0, 36
+};
+
+#define yypact_value_is_default(yystate) \
+ ((yystate) == (-27))
+
+#define yytable_value_is_error(yytable_value) \
+ YYID (0)
+
+static const yytype_int8 yycheck[] =
+{
+ 26, 3, 4, 5, 6, 5, 6, 11, 3, 4,
+ 5, 6, 38, 39, 40, 10, 19, 3, 44, 11,
+ 19, 23, 8, 9, 11, 19, 52, 53, 54, 55,
+ 56, 11, 18, 19, 11, 21, 22, 0, 1, 3,
+ 4, 5, 6, 11, 6, 11, 8, 9, 19, 12,
+ 13, 14, 15, 16, 17, 24, -1, -1, 19
+};
+
+/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
+ symbol of state STATE-NUM. */
+static const yytype_uint8 yystos[] =
+{
+ 0, 25, 0, 1, 12, 13, 14, 15, 16, 17,
+ 26, 27, 28, 29, 30, 31, 32, 11, 19, 35,
+ 19, 37, 37, 19, 33, 39, 37, 37, 11, 11,
+ 11, 11, 11, 11, 19, 36, 19, 38, 3, 8,
+ 9, 18, 19, 21, 22, 34, 39, 34, 34, 34,
+ 34, 34, 3, 4, 5, 6, 10, 23, 34, 34,
+ 34, 34, 34
+};
+
+#define yyerrok (yyerrstatus = 0)
+#define yyclearin (yychar = YYEMPTY)
+#define YYEMPTY (-2)
+#define YYEOF 0
+
+#define YYACCEPT goto yyacceptlab
+#define YYABORT goto yyabortlab
+#define YYERROR goto yyerrorlab
+
+
+/* Like YYERROR except do call yyerror. This remains here temporarily
+ to ease the transition to the new meaning of YYERROR, for GCC.
+ Once GCC version 2 has supplanted version 1, this can go. However,
+ YYFAIL appears to be in use. Nevertheless, it is formally deprecated
+ in Bison 2.4.2's NEWS entry, where a plan to phase it out is
+ discussed. */
+
+#define YYFAIL goto yyerrlab
+#if defined YYFAIL
+ /* This is here to suppress warnings from the GCC cpp's
+ -Wunused-macros. Normally we don't worry about that warning, but
+ some users do, and we want to make it easy for users to remove
+ YYFAIL uses, which will produce warnings from Bison 2.5. */
+#endif
+
+#define YYRECOVERING() (!!yyerrstatus)
+
+#define YYBACKUP(Token, Value) \
+do \
+ if (yychar == YYEMPTY && yylen == 1) \
+ { \
+ yychar = (Token); \
+ yylval = (Value); \
+ YYPOPSTACK (1); \
+ goto yybackup; \
+ } \
+ else \
+ { \
+ yyerror (YY_("syntax error: cannot back up")); \
+ YYERROR; \
+ } \
+while (YYID (0))
+
+
+#define YYTERROR 1
+#define YYERRCODE 256
+
+
+/* YYLLOC_DEFAULT -- Set CURRENT to span from RHS[1] to RHS[N].
+ If N is 0, then set CURRENT to the empty location which ends
+ the previous symbol: RHS[0] (always defined). */
+
+#define YYRHSLOC(Rhs, K) ((Rhs)[K])
+#ifndef YYLLOC_DEFAULT
+# define YYLLOC_DEFAULT(Current, Rhs, N) \
+ do \
+ if (YYID (N)) \
+ { \
+ (Current).first_line = YYRHSLOC (Rhs, 1).first_line; \
+ (Current).first_column = YYRHSLOC (Rhs, 1).first_column; \
+ (Current).last_line = YYRHSLOC (Rhs, N).last_line; \
+ (Current).last_column = YYRHSLOC (Rhs, N).last_column; \
+ } \
+ else \
+ { \
+ (Current).first_line = (Current).last_line = \
+ YYRHSLOC (Rhs, 0).last_line; \
+ (Current).first_column = (Current).last_column = \
+ YYRHSLOC (Rhs, 0).last_column; \
+ } \
+ while (YYID (0))
+#endif
+
+
+/* This macro is provided for backward compatibility. */
+
+#ifndef YY_LOCATION_PRINT
+# define YY_LOCATION_PRINT(File, Loc) ((void) 0)
+#endif
+
+
+/* YYLEX -- calling `yylex' with the right arguments. */
+
+#ifdef YYLEX_PARAM
+# define YYLEX yylex (YYLEX_PARAM)
+#else
+# define YYLEX yylex ()
+#endif
+
+/* Enable debugging if requested. */
+#if YYDEBUG
+
+# ifndef YYFPRINTF
+# include <stdio.h> /* INFRINGES ON USER NAME SPACE */
+# define YYFPRINTF fprintf
+# endif
+
+# define YYDPRINTF(Args) \
+do { \
+ if (yydebug) \
+ YYFPRINTF Args; \
+} while (YYID (0))
+
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location) \
+do { \
+ if (yydebug) \
+ { \
+ YYFPRINTF (stderr, "%s ", Title); \
+ yy_symbol_print (stderr, \
+ Type, Value); \
+ YYFPRINTF (stderr, "\n"); \
+ } \
+} while (YYID (0))
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT. |
+`--------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_value_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_value_print (yyoutput, yytype, yyvaluep)
+ FILE *yyoutput;
+ int yytype;
+ YYSTYPE const * const yyvaluep;
+#endif
+{
+ if (!yyvaluep)
+ return;
+# ifdef YYPRINT
+ if (yytype < YYNTOKENS)
+ YYPRINT (yyoutput, yytoknum[yytype], *yyvaluep);
+# else
+ YYUSE (yyoutput);
+# endif
+ switch (yytype)
+ {
+ default:
+ break;
+ }
+}
+
+
+/*--------------------------------.
+| Print this symbol on YYOUTPUT. |
+`--------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static void
+yy_symbol_print (FILE *yyoutput, int yytype, YYSTYPE const * const yyvaluep)
+#else
+static void
+yy_symbol_print (yyoutput, yytype, yyvaluep)
+ FILE *yyoutput;
+ int yytype;
+ YYSTYPE const * const yyvaluep;
+#endif
+{
+ if (yytype < YYNTOKENS)
+ YYFPRINTF (yyoutput, "token %s (", yytname[yytype]);
+ else
+ YYFPRINTF (yyoutput, "nterm %s (", yytname[yytype]);
+
+ yy_symbol_value_print (yyoutput, yytype, yyvaluep);
+ YYFPRINTF (yyoutput, ")");
+}
+
+/*------------------------------------------------------------------.
+| yy_stack_print -- Print the state stack from its BOTTOM up to its |
+| TOP (included). |
+`------------------------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static void
+yy_stack_print (yytype_int16 *yybottom, yytype_int16 *yytop)
+#else
+static void
+yy_stack_print (yybottom, yytop)
+ yytype_int16 *yybottom;
+ yytype_int16 *yytop;
+#endif
+{
+ YYFPRINTF (stderr, "Stack now");
+ for (; yybottom <= yytop; yybottom++)
+ {
+ int yybot = *yybottom;
+ YYFPRINTF (stderr, " %d", yybot);
+ }
+ YYFPRINTF (stderr, "\n");
+}
+
+# define YY_STACK_PRINT(Bottom, Top) \
+do { \
+ if (yydebug) \
+ yy_stack_print ((Bottom), (Top)); \
+} while (YYID (0))
+
+
+/*------------------------------------------------.
+| Report that the YYRULE is going to be reduced. |
+`------------------------------------------------*/
+
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static void
+yy_reduce_print (YYSTYPE *yyvsp, int yyrule)
+#else
+static void
+yy_reduce_print (yyvsp, yyrule)
+ YYSTYPE *yyvsp;
+ int yyrule;
+#endif
+{
+ int yynrhs = yyr2[yyrule];
+ int yyi;
+ unsigned long int yylno = yyrline[yyrule];
+ YYFPRINTF (stderr, "Reducing stack by rule %d (line %lu):\n",
+ yyrule - 1, yylno);
+ /* The symbols being reduced. */
+ for (yyi = 0; yyi < yynrhs; yyi++)
+ {
+ YYFPRINTF (stderr, " $%d = ", yyi + 1);
+ yy_symbol_print (stderr, yyrhs[yyprhs[yyrule] + yyi],
+ &(yyvsp[(yyi + 1) - (yynrhs)])
+ );
+ YYFPRINTF (stderr, "\n");
+ }
+}
+
+# define YY_REDUCE_PRINT(Rule) \
+do { \
+ if (yydebug) \
+ yy_reduce_print (yyvsp, Rule); \
+} while (YYID (0))
+
+/* Nonzero means print parse trace. It is left uninitialized so that
+ multiple parsers can coexist. */
+int yydebug;
+#else /* !YYDEBUG */
+# define YYDPRINTF(Args)
+# define YY_SYMBOL_PRINT(Title, Type, Value, Location)
+# define YY_STACK_PRINT(Bottom, Top)
+# define YY_REDUCE_PRINT(Rule)
+#endif /* !YYDEBUG */
+
+
+/* YYINITDEPTH -- initial size of the parser's stacks. */
+#ifndef YYINITDEPTH
+# define YYINITDEPTH 200
+#endif
+
+/* YYMAXDEPTH -- maximum size the stacks can grow to (effective only
+ if the built-in stack extension method is used).
+
+ Do not make this value too large; the results are undefined if
+ YYSTACK_ALLOC_MAXIMUM < YYSTACK_BYTES (YYMAXDEPTH)
+ evaluated with infinite-precision integer arithmetic. */
+
+#ifndef YYMAXDEPTH
+# define YYMAXDEPTH 10000
+#endif
+
+
+#if YYERROR_VERBOSE
+
+# ifndef yystrlen
+# if defined __GLIBC__ && defined _STRING_H
+# define yystrlen strlen
+# else
+/* Return the length of YYSTR. */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static YYSIZE_T
+yystrlen (const char *yystr)
+#else
+static YYSIZE_T
+yystrlen (yystr)
+ const char *yystr;
+#endif
+{
+ YYSIZE_T yylen;
+ for (yylen = 0; yystr[yylen]; yylen++)
+ continue;
+ return yylen;
+}
+# endif
+# endif
+
+# ifndef yystpcpy
+# if defined __GLIBC__ && defined _STRING_H && defined _GNU_SOURCE
+# define yystpcpy stpcpy
+# else
+/* Copy YYSRC to YYDEST, returning the address of the terminating '\0' in
+ YYDEST. */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static char *
+yystpcpy (char *yydest, const char *yysrc)
+#else
+static char *
+yystpcpy (yydest, yysrc)
+ char *yydest;
+ const char *yysrc;
+#endif
+{
+ char *yyd = yydest;
+ const char *yys = yysrc;
+
+ while ((*yyd++ = *yys++) != '\0')
+ continue;
+
+ return yyd - 1;
+}
+# endif
+# endif
+
+# ifndef yytnamerr
+/* Copy to YYRES the contents of YYSTR after stripping away unnecessary
+ quotes and backslashes, so that it's suitable for yyerror. The
+ heuristic is that double-quoting is unnecessary unless the string
+ contains an apostrophe, a comma, or backslash (other than
+ backslash-backslash). YYSTR is taken from yytname. If YYRES is
+ null, do not copy; instead, return the length of what the result
+ would have been. */
+static YYSIZE_T
+yytnamerr (char *yyres, const char *yystr)
+{
+ if (*yystr == '"')
+ {
+ YYSIZE_T yyn = 0;
+ char const *yyp = yystr;
+
+ for (;;)
+ switch (*++yyp)
+ {
+ case '\'':
+ case ',':
+ goto do_not_strip_quotes;
+
+ case '\\':
+ if (*++yyp != '\\')
+ goto do_not_strip_quotes;
+ /* Fall through. */
+ default:
+ if (yyres)
+ yyres[yyn] = *yyp;
+ yyn++;
+ break;
+
+ case '"':
+ if (yyres)
+ yyres[yyn] = '\0';
+ return yyn;
+ }
+ do_not_strip_quotes: ;
+ }
+
+ if (! yyres)
+ return yystrlen (yystr);
+
+ return yystpcpy (yyres, yystr) - yyres;
+}
+# endif
+
+/* Copy into *YYMSG, which is of size *YYMSG_ALLOC, an error message
+ about the unexpected token YYTOKEN for the state stack whose top is
+ YYSSP.
+
+ Return 0 if *YYMSG was successfully written. Return 1 if *YYMSG is
+ not large enough to hold the message. In that case, also set
+ *YYMSG_ALLOC to the required number of bytes. Return 2 if the
+ required number of bytes is too large to store. */
+static int
+yysyntax_error (YYSIZE_T *yymsg_alloc, char **yymsg,
+ yytype_int16 *yyssp, int yytoken)
+{
+ YYSIZE_T yysize0 = yytnamerr (0, yytname[yytoken]);
+ YYSIZE_T yysize = yysize0;
+ YYSIZE_T yysize1;
+ enum { YYERROR_VERBOSE_ARGS_MAXIMUM = 5 };
+ /* Internationalized format string. */
+ const char *yyformat = 0;
+ /* Arguments of yyformat. */
+ char const *yyarg[YYERROR_VERBOSE_ARGS_MAXIMUM];
+ /* Number of reported tokens (one for the "unexpected", one per
+ "expected"). */
+ int yycount = 0;
+
+ /* There are many possibilities here to consider:
+ - Assume YYFAIL is not used. It's too flawed to consider. See
+ <http://lists.gnu.org/archive/html/bison-patches/2009-12/msg00024.html>
+ for details. YYERROR is fine as it does not invoke this
+ function.
+ - If this state is a consistent state with a default action, then
+ the only way this function was invoked is if the default action
+ is an error action. In that case, don't check for expected
+ tokens because there are none.
+ - The only way there can be no lookahead present (in yychar) is if
+ this state is a consistent state with a default action. Thus,
+ detecting the absence of a lookahead is sufficient to determine
+ that there is no unexpected or expected token to report. In that
+ case, just report a simple "syntax error".
+ - Don't assume there isn't a lookahead just because this state is a
+ consistent state with a default action. There might have been a
+ previous inconsistent state, consistent state with a non-default
+ action, or user semantic action that manipulated yychar.
+ - Of course, the expected token list depends on states to have
+ correct lookahead information, and it depends on the parser not
+ to perform extra reductions after fetching a lookahead from the
+ scanner and before detecting a syntax error. Thus, state merging
+ (from LALR or IELR) and default reductions corrupt the expected
+ token list. However, the list is correct for canonical LR with
+ one exception: it will still contain any token that will not be
+ accepted due to an error action in a later state.
+ */
+ if (yytoken != YYEMPTY)
+ {
+ int yyn = yypact[*yyssp];
+ yyarg[yycount++] = yytname[yytoken];
+ if (!yypact_value_is_default (yyn))
+ {
+ /* Start YYX at -YYN if negative to avoid negative indexes in
+ YYCHECK. In other words, skip the first -YYN actions for
+ this state because they are default actions. */
+ int yyxbegin = yyn < 0 ? -yyn : 0;
+ /* Stay within bounds of both yycheck and yytname. */
+ int yychecklim = YYLAST - yyn + 1;
+ int yyxend = yychecklim < YYNTOKENS ? yychecklim : YYNTOKENS;
+ int yyx;
+
+ for (yyx = yyxbegin; yyx < yyxend; ++yyx)
+ if (yycheck[yyx + yyn] == yyx && yyx != YYTERROR
+ && !yytable_value_is_error (yytable[yyx + yyn]))
+ {
+ if (yycount == YYERROR_VERBOSE_ARGS_MAXIMUM)
+ {
+ yycount = 1;
+ yysize = yysize0;
+ break;
+ }
+ yyarg[yycount++] = yytname[yyx];
+ yysize1 = yysize + yytnamerr (0, yytname[yyx]);
+ if (! (yysize <= yysize1
+ && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+ return 2;
+ yysize = yysize1;
+ }
+ }
+ }
+
+ switch (yycount)
+ {
+# define YYCASE_(N, S) \
+ case N: \
+ yyformat = S; \
+ break
+ YYCASE_(0, YY_("syntax error"));
+ YYCASE_(1, YY_("syntax error, unexpected %s"));
+ YYCASE_(2, YY_("syntax error, unexpected %s, expecting %s"));
+ YYCASE_(3, YY_("syntax error, unexpected %s, expecting %s or %s"));
+ YYCASE_(4, YY_("syntax error, unexpected %s, expecting %s or %s or %s"));
+ YYCASE_(5, YY_("syntax error, unexpected %s, expecting %s or %s or %s or %s"));
+# undef YYCASE_
+ }
+
+ yysize1 = yysize + yystrlen (yyformat);
+ if (! (yysize <= yysize1 && yysize1 <= YYSTACK_ALLOC_MAXIMUM))
+ return 2;
+ yysize = yysize1;
+
+ if (*yymsg_alloc < yysize)
+ {
+ *yymsg_alloc = 2 * yysize;
+ if (! (yysize <= *yymsg_alloc
+ && *yymsg_alloc <= YYSTACK_ALLOC_MAXIMUM))
+ *yymsg_alloc = YYSTACK_ALLOC_MAXIMUM;
+ return 1;
+ }
+
+ /* Avoid sprintf, as that infringes on the user's name space.
+ Don't have undefined behavior even if the translation
+ produced a string with the wrong number of "%s"s. */
+ {
+ char *yyp = *yymsg;
+ int yyi = 0;
+ while ((*yyp = *yyformat) != '\0')
+ if (*yyp == '%' && yyformat[1] == 's' && yyi < yycount)
+ {
+ yyp += yytnamerr (yyp, yyarg[yyi++]);
+ yyformat += 2;
+ }
+ else
+ {
+ yyp++;
+ yyformat++;
+ }
+ }
+ return 0;
+}
+#endif /* YYERROR_VERBOSE */
+
+/*-----------------------------------------------.
+| Release the memory associated to this symbol. |
+`-----------------------------------------------*/
+
+/*ARGSUSED*/
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+static void
+yydestruct (const char *yymsg, int yytype, YYSTYPE *yyvaluep)
+#else
+static void
+yydestruct (yymsg, yytype, yyvaluep)
+ const char *yymsg;
+ int yytype;
+ YYSTYPE *yyvaluep;
+#endif
+{
+ YYUSE (yyvaluep);
+
+ if (!yymsg)
+ yymsg = "Deleting";
+ YY_SYMBOL_PRINT (yymsg, yytype, yyvaluep, yylocationp);
+
+ switch (yytype)
+ {
+
+ default:
+ break;
+ }
+}
+
+
+/* Prevent warnings from -Wmissing-prototypes. */
+#ifdef YYPARSE_PARAM
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void *YYPARSE_PARAM);
+#else
+int yyparse ();
+#endif
+#else /* ! YYPARSE_PARAM */
+#if defined __STDC__ || defined __cplusplus
+int yyparse (void);
+#else
+int yyparse ();
+#endif
+#endif /* ! YYPARSE_PARAM */
+
+
+/* The lookahead symbol. */
+int yychar;
+
+/* The semantic value of the lookahead symbol. */
+YYSTYPE yylval;
+
+/* Number of syntax errors so far. */
+int yynerrs;
+
+
+/*----------.
+| yyparse. |
+`----------*/
+
+#ifdef YYPARSE_PARAM
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void *YYPARSE_PARAM)
+#else
+int
+yyparse (YYPARSE_PARAM)
+ void *YYPARSE_PARAM;
+#endif
+#else /* ! YYPARSE_PARAM */
+#if (defined __STDC__ || defined __C99__FUNC__ \
+ || defined __cplusplus || defined _MSC_VER)
+int
+yyparse (void)
+#else
+int
+yyparse ()
+
+#endif
+#endif
+{
+ int yystate;
+ /* Number of tokens to shift before error messages enabled. */
+ int yyerrstatus;
+
+ /* The stacks and their tools:
+ `yyss': related to states.
+ `yyvs': related to semantic values.
+
+ Refer to the stacks thru separate pointers, to allow yyoverflow
+ to reallocate them elsewhere. */
+
+ /* The state stack. */
+ yytype_int16 yyssa[YYINITDEPTH];
+ yytype_int16 *yyss;
+ yytype_int16 *yyssp;
+
+ /* The semantic value stack. */
+ YYSTYPE yyvsa[YYINITDEPTH];
+ YYSTYPE *yyvs;
+ YYSTYPE *yyvsp;
+
+ YYSIZE_T yystacksize;
+
+ int yyn;
+ int yyresult;
+ /* Lookahead token as an internal (translated) token number. */
+ int yytoken;
+ /* The variables used to return semantic value and location from the
+ action routines. */
+ YYSTYPE yyval;
+
+#if YYERROR_VERBOSE
+ /* Buffer for error messages, and its allocated size. */
+ char yymsgbuf[128];
+ char *yymsg = yymsgbuf;
+ YYSIZE_T yymsg_alloc = sizeof yymsgbuf;
+#endif
+
+#define YYPOPSTACK(N) (yyvsp -= (N), yyssp -= (N))
+
+ /* The number of symbols on the RHS of the reduced rule.
+ Keep to zero when no symbol should be popped. */
+ int yylen = 0;
+
+ yytoken = 0;
+ yyss = yyssa;
+ yyvs = yyvsa;
+ yystacksize = YYINITDEPTH;
+
+ YYDPRINTF ((stderr, "Starting parse\n"));
+
+ yystate = 0;
+ yyerrstatus = 0;
+ yynerrs = 0;
+ yychar = YYEMPTY; /* Cause a token to be read. */
+
+ /* Initialize stack pointers.
+ Waste one element of value and location stack
+ so that they stay on the same level as the state stack.
+ The wasted elements are never initialized. */
+ yyssp = yyss;
+ yyvsp = yyvs;
+
+ goto yysetstate;
+
+/*------------------------------------------------------------.
+| yynewstate -- Push a new state, which is found in yystate. |
+`------------------------------------------------------------*/
+ yynewstate:
+ /* In all cases, when you get here, the value and location stacks
+ have just been pushed. So pushing a state here evens the stacks. */
+ yyssp++;
+
+ yysetstate:
+ *yyssp = yystate;
+
+ if (yyss + yystacksize - 1 <= yyssp)
+ {
+ /* Get the current used size of the three stacks, in elements. */
+ YYSIZE_T yysize = yyssp - yyss + 1;
+
+#ifdef yyoverflow
+ {
+ /* Give user a chance to reallocate the stack. Use copies of
+ these so that the &'s don't force the real ones into
+ memory. */
+ YYSTYPE *yyvs1 = yyvs;
+ yytype_int16 *yyss1 = yyss;
+
+ /* Each stack pointer address is followed by the size of the
+ data in use in that stack, in bytes. This used to be a
+ conditional around just the two extra args, but that might
+ be undefined if yyoverflow is a macro. */
+ yyoverflow (YY_("memory exhausted"),
+ &yyss1, yysize * sizeof (*yyssp),
+ &yyvs1, yysize * sizeof (*yyvsp),
+ &yystacksize);
+
+ yyss = yyss1;
+ yyvs = yyvs1;
+ }
+#else /* no yyoverflow */
+# ifndef YYSTACK_RELOCATE
+ goto yyexhaustedlab;
+# else
+ /* Extend the stack our own way. */
+ if (YYMAXDEPTH <= yystacksize)
+ goto yyexhaustedlab;
+ yystacksize *= 2;
+ if (YYMAXDEPTH < yystacksize)
+ yystacksize = YYMAXDEPTH;
+
+ {
+ yytype_int16 *yyss1 = yyss;
+ union yyalloc *yyptr =
+ (union yyalloc *) YYSTACK_ALLOC (YYSTACK_BYTES (yystacksize));
+ if (! yyptr)
+ goto yyexhaustedlab;
+ YYSTACK_RELOCATE (yyss_alloc, yyss);
+ YYSTACK_RELOCATE (yyvs_alloc, yyvs);
+# undef YYSTACK_RELOCATE
+ if (yyss1 != yyssa)
+ YYSTACK_FREE (yyss1);
+ }
+# endif
+#endif /* no yyoverflow */
+
+ yyssp = yyss + yysize - 1;
+ yyvsp = yyvs + yysize - 1;
+
+ YYDPRINTF ((stderr, "Stack size increased to %lu\n",
+ (unsigned long int) yystacksize));
+
+ if (yyss + yystacksize - 1 <= yyssp)
+ YYABORT;
+ }
+
+ YYDPRINTF ((stderr, "Entering state %d\n", yystate));
+
+ if (yystate == YYFINAL)
+ YYACCEPT;
+
+ goto yybackup;
+
+/*-----------.
+| yybackup. |
+`-----------*/
+yybackup:
+
+ /* Do appropriate processing given the current state. Read a
+ lookahead token if we need one and don't already have one. */
+
+ /* First try to decide what to do without reference to lookahead token. */
+ yyn = yypact[yystate];
+ if (yypact_value_is_default (yyn))
+ goto yydefault;
+
+ /* Not known => get a lookahead token if don't already have one. */
+
+ /* YYCHAR is either YYEMPTY or YYEOF or a valid lookahead symbol. */
+ if (yychar == YYEMPTY)
+ {
+ YYDPRINTF ((stderr, "Reading a token: "));
+ yychar = YYLEX;
+ }
+
+ if (yychar <= YYEOF)
+ {
+ yychar = yytoken = YYEOF;
+ YYDPRINTF ((stderr, "Now at end of input.\n"));
+ }
+ else
+ {
+ yytoken = YYTRANSLATE (yychar);
+ YY_SYMBOL_PRINT ("Next token is", yytoken, &yylval, &yylloc);
+ }
+
+ /* If the proper action on seeing token YYTOKEN is to reduce or to
+ detect an error, take that action. */
+ yyn += yytoken;
+ if (yyn < 0 || YYLAST < yyn || yycheck[yyn] != yytoken)
+ goto yydefault;
+ yyn = yytable[yyn];
+ if (yyn <= 0)
+ {
+ if (yytable_value_is_error (yyn))
+ goto yyerrlab;
+ yyn = -yyn;
+ goto yyreduce;
+ }
+
+ /* Count tokens shifted since error; after three, turn off error
+ status. */
+ if (yyerrstatus)
+ yyerrstatus--;
+
+ /* Shift the lookahead token. */
+ YY_SYMBOL_PRINT ("Shifting", yytoken, &yylval, &yylloc);
+
+ /* Discard the shifted token. */
+ yychar = YYEMPTY;
+
+ yystate = yyn;
+ *++yyvsp = yylval;
+
+ goto yynewstate;
+
+
+/*-----------------------------------------------------------.
+| yydefault -- do the default action for the current state. |
+`-----------------------------------------------------------*/
+yydefault:
+ yyn = yydefact[yystate];
+ if (yyn == 0)
+ goto yyerrlab;
+ goto yyreduce;
+
+
+/*-----------------------------.
+| yyreduce -- Do a reduction. |
+`-----------------------------*/
+yyreduce:
+ /* yyn is the number of a rule to reduce with. */
+ yylen = yyr2[yyn];
+
+ /* If YYLEN is nonzero, implement the default value of the action:
+ `$$ = $1'.
+
+ Otherwise, the following line sets YYVAL to garbage.
+ This behavior is undocumented and Bison
+ users should not rely upon it. Assigning to YYVAL
+ unconditionally makes the parser a bit smaller, and it avoids a
+ GCC warning that YYVAL may be used uninitialized. */
+ yyval = yyvsp[1-yylen];
+
+
+ YY_REDUCE_PRINT (yyn);
+ switch (yyn)
+ {
+ case 11:
+
+/* Line 1806 of yacc.c */
+#line 133 "lib/conf-parse.y"
+ { sensors_bus new_el;
+ new_el.line = (yyvsp[(1) - (3)].line);
+ new_el.bus = (yyvsp[(2) - (3)].bus);
+ new_el.adapter = (yyvsp[(3) - (3)].name);
+ bus_add_el(&new_el);
+ }
+ break;
+
+ case 12:
+
+/* Line 1806 of yacc.c */
+#line 142 "lib/conf-parse.y"
+ { sensors_label new_el;
+ if (!current_chip) {
+ sensors_yyerror("Label statement before first chip statement");
+ free((yyvsp[(2) - (3)].name));
+ free((yyvsp[(3) - (3)].name));
+ YYERROR;
+ }
+ new_el.line = (yyvsp[(1) - (3)].line);
+ new_el.name = (yyvsp[(2) - (3)].name);
+ new_el.value = (yyvsp[(3) - (3)].name);
+ label_add_el(&new_el);
+ }
+ break;
+
+ case 13:
+
+/* Line 1806 of yacc.c */
+#line 157 "lib/conf-parse.y"
+ { sensors_set new_el;
+ if (!current_chip) {
+ sensors_yyerror("Set statement before first chip statement");
+ free((yyvsp[(2) - (3)].name));
+ sensors_free_expr((yyvsp[(3) - (3)].expr));
+ YYERROR;
+ }
+ new_el.line = (yyvsp[(1) - (3)].line);
+ new_el.name = (yyvsp[(2) - (3)].name);
+ new_el.value = (yyvsp[(3) - (3)].expr);
+ set_add_el(&new_el);
+ }
+ break;
+
+ case 14:
+
+/* Line 1806 of yacc.c */
+#line 172 "lib/conf-parse.y"
+ { sensors_compute new_el;
+ if (!current_chip) {
+ sensors_yyerror("Compute statement before first chip statement");
+ free((yyvsp[(2) - (5)].name));
+ sensors_free_expr((yyvsp[(3) - (5)].expr));
+ sensors_free_expr((yyvsp[(5) - (5)].expr));
+ YYERROR;
+ }
+ new_el.line = (yyvsp[(1) - (5)].line);
+ new_el.name = (yyvsp[(2) - (5)].name);
+ new_el.from_proc = (yyvsp[(3) - (5)].expr);
+ new_el.to_proc = (yyvsp[(5) - (5)].expr);
+ compute_add_el(&new_el);
+ }
+ break;
+
+ case 15:
+
+/* Line 1806 of yacc.c */
+#line 189 "lib/conf-parse.y"
+ { sensors_ignore new_el;
+ if (!current_chip) {
+ sensors_yyerror("Ignore statement before first chip statement");
+ free((yyvsp[(2) - (2)].name));
+ YYERROR;
+ }
+ new_el.line = (yyvsp[(1) - (2)].line);
+ new_el.name = (yyvsp[(2) - (2)].name);
+ ignore_add_el(&new_el);
+ }
+ break;
+
+ case 16:
+
+/* Line 1806 of yacc.c */
+#line 202 "lib/conf-parse.y"
+ { sensors_chip new_el;
+ new_el.line = (yyvsp[(1) - (2)].line);
+ new_el.labels = NULL;
+ new_el.sets = NULL;
+ new_el.computes = NULL;
+ new_el.ignores = NULL;
+ new_el.labels_count = new_el.labels_max = 0;
+ new_el.sets_count = new_el.sets_max = 0;
+ new_el.computes_count = new_el.computes_max = 0;
+ new_el.ignores_count = new_el.ignores_max = 0;
+ new_el.chips = (yyvsp[(2) - (2)].chips);
+ chip_add_el(&new_el);
+ current_chip = sensors_config_chips +
+ sensors_config_chips_count - 1;
+ }
+ break;
+
+ case 17:
+
+/* Line 1806 of yacc.c */
+#line 220 "lib/conf-parse.y"
+ {
+ (yyval.chips).fits = NULL;
+ (yyval.chips).fits_count = (yyval.chips).fits_max = 0;
+ fits_add_el(&(yyvsp[(1) - (1)].chip),(yyval.chips));
+ }
+ break;
+
+ case 18:
+
+/* Line 1806 of yacc.c */
+#line 226 "lib/conf-parse.y"
+ { (yyval.chips) = (yyvsp[(1) - (2)].chips);
+ fits_add_el(&(yyvsp[(2) - (2)].chip),(yyval.chips));
+ }
+ break;
+
+ case 19:
+
+/* Line 1806 of yacc.c */
+#line 232 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->data.val = (yyvsp[(1) - (1)].value);
+ (yyval.expr)->kind = sensors_kind_val;
+ }
+ break;
+
+ case 20:
+
+/* Line 1806 of yacc.c */
+#line 237 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->data.var = (yyvsp[(1) - (1)].name);
+ (yyval.expr)->kind = sensors_kind_var;
+ }
+ break;
+
+ case 21:
+
+/* Line 1806 of yacc.c */
+#line 242 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_source;
+ }
+ break;
+
+ case 22:
+
+/* Line 1806 of yacc.c */
+#line 246 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_add;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+ (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+ }
+ break;
+
+ case 23:
+
+/* Line 1806 of yacc.c */
+#line 253 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_sub;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+ (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+ }
+ break;
+
+ case 24:
+
+/* Line 1806 of yacc.c */
+#line 260 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_multiply;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+ (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+ }
+ break;
+
+ case 25:
+
+/* Line 1806 of yacc.c */
+#line 267 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_divide;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(1) - (3)].expr);
+ (yyval.expr)->data.subexpr.sub2 = (yyvsp[(3) - (3)].expr);
+ }
+ break;
+
+ case 26:
+
+/* Line 1806 of yacc.c */
+#line 274 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_negate;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+ (yyval.expr)->data.subexpr.sub2 = NULL;
+ }
+ break;
+
+ case 27:
+
+/* Line 1806 of yacc.c */
+#line 281 "lib/conf-parse.y"
+ { (yyval.expr) = (yyvsp[(2) - (3)].expr); }
+ break;
+
+ case 28:
+
+/* Line 1806 of yacc.c */
+#line 283 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_exp;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+ (yyval.expr)->data.subexpr.sub2 = NULL;
+ }
+ break;
+
+ case 29:
+
+/* Line 1806 of yacc.c */
+#line 290 "lib/conf-parse.y"
+ { (yyval.expr) = malloc_expr();
+ (yyval.expr)->kind = sensors_kind_sub;
+ (yyval.expr)->data.subexpr.op = sensors_log;
+ (yyval.expr)->data.subexpr.sub1 = (yyvsp[(2) - (2)].expr);
+ (yyval.expr)->data.subexpr.sub2 = NULL;
+ }
+ break;
+
+ case 30:
+
+/* Line 1806 of yacc.c */
+#line 299 "lib/conf-parse.y"
+ { int res = sensors_parse_bus_id((yyvsp[(1) - (1)].name),&(yyval.bus));
+ free((yyvsp[(1) - (1)].name));
+ if (res) {
+ sensors_yyerror("Parse error in bus id");
+ YYERROR;
+ }
+ }
+ break;
+
+ case 31:
+
+/* Line 1806 of yacc.c */
+#line 309 "lib/conf-parse.y"
+ { (yyval.name) = (yyvsp[(1) - (1)].name); }
+ break;
+
+ case 32:
+
+/* Line 1806 of yacc.c */
+#line 313 "lib/conf-parse.y"
+ { (yyval.name) = (yyvsp[(1) - (1)].name); }
+ break;
+
+ case 33:
+
+/* Line 1806 of yacc.c */
+#line 317 "lib/conf-parse.y"
+ { (yyval.name) = (yyvsp[(1) - (1)].name); }
+ break;
+
+ case 34:
+
+/* Line 1806 of yacc.c */
+#line 321 "lib/conf-parse.y"
+ { int res = sensors_parse_chip_name((yyvsp[(1) - (1)].name),&(yyval.chip));
+ free((yyvsp[(1) - (1)].name));
+ if (res) {
+ sensors_yyerror("Parse error in chip name");
+ YYERROR;
+ }
+ }
+ break;
+
+
+
+/* Line 1806 of yacc.c */
+#line 1793 "lib/conf-parse.c"
+ default: break;
+ }
+ /* User semantic actions sometimes alter yychar, and that requires
+ that yytoken be updated with the new translation. We take the
+ approach of translating immediately before every use of yytoken.
+ One alternative is translating here after every semantic action,
+ but that translation would be missed if the semantic action invokes
+ YYABORT, YYACCEPT, or YYERROR immediately after altering yychar or
+ if it invokes YYBACKUP. In the case of YYABORT or YYACCEPT, an
+ incorrect destructor might then be invoked immediately. In the
+ case of YYERROR or YYBACKUP, subsequent parser actions might lead
+ to an incorrect destructor call or verbose syntax error message
+ before the lookahead is translated. */
+ YY_SYMBOL_PRINT ("-> $$ =", yyr1[yyn], &yyval, &yyloc);
+
+ YYPOPSTACK (yylen);
+ yylen = 0;
+ YY_STACK_PRINT (yyss, yyssp);
+
+ *++yyvsp = yyval;
+
+ /* Now `shift' the result of the reduction. Determine what state
+ that goes to, based on the state we popped back to and the rule
+ number reduced by. */
+
+ yyn = yyr1[yyn];
+
+ yystate = yypgoto[yyn - YYNTOKENS] + *yyssp;
+ if (0 <= yystate && yystate <= YYLAST && yycheck[yystate] == *yyssp)
+ yystate = yytable[yystate];
+ else
+ yystate = yydefgoto[yyn - YYNTOKENS];
+
+ goto yynewstate;
+
+
+/*------------------------------------.
+| yyerrlab -- here on detecting error |
+`------------------------------------*/
+yyerrlab:
+ /* Make sure we have latest lookahead translation. See comments at
+ user semantic actions for why this is necessary. */
+ yytoken = yychar == YYEMPTY ? YYEMPTY : YYTRANSLATE (yychar);
+
+ /* If not already recovering from an error, report this error. */
+ if (!yyerrstatus)
+ {
+ ++yynerrs;
+#if ! YYERROR_VERBOSE
+ yyerror (YY_("syntax error"));
+#else
+# define YYSYNTAX_ERROR yysyntax_error (&yymsg_alloc, &yymsg, \
+ yyssp, yytoken)
+ {
+ char const *yymsgp = YY_("syntax error");
+ int yysyntax_error_status;
+ yysyntax_error_status = YYSYNTAX_ERROR;
+ if (yysyntax_error_status == 0)
+ yymsgp = yymsg;
+ else if (yysyntax_error_status == 1)
+ {
+ if (yymsg != yymsgbuf)
+ YYSTACK_FREE (yymsg);
+ yymsg = (char *) YYSTACK_ALLOC (yymsg_alloc);
+ if (!yymsg)
+ {
+ yymsg = yymsgbuf;
+ yymsg_alloc = sizeof yymsgbuf;
+ yysyntax_error_status = 2;
+ }
+ else
+ {
+ yysyntax_error_status = YYSYNTAX_ERROR;
+ yymsgp = yymsg;
+ }
+ }
+ yyerror (yymsgp);
+ if (yysyntax_error_status == 2)
+ goto yyexhaustedlab;
+ }
+# undef YYSYNTAX_ERROR
+#endif
+ }
+
+
+
+ if (yyerrstatus == 3)
+ {
+ /* If just tried and failed to reuse lookahead token after an
+ error, discard it. */
+
+ if (yychar <= YYEOF)
+ {
+ /* Return failure if at end of input. */
+ if (yychar == YYEOF)
+ YYABORT;
+ }
+ else
+ {
+ yydestruct ("Error: discarding",
+ yytoken, &yylval);
+ yychar = YYEMPTY;
+ }
+ }
+
+ /* Else will try to reuse lookahead token after shifting the error
+ token. */
+ goto yyerrlab1;
+
+
+/*---------------------------------------------------.
+| yyerrorlab -- error raised explicitly by YYERROR. |
+`---------------------------------------------------*/
+yyerrorlab:
+
+ /* Pacify compilers like GCC when the user code never invokes
+ YYERROR and the label yyerrorlab therefore never appears in user
+ code. */
+ if (/*CONSTCOND*/ 0)
+ goto yyerrorlab;
+
+ /* Do not reclaim the symbols of the rule which action triggered
+ this YYERROR. */
+ YYPOPSTACK (yylen);
+ yylen = 0;
+ YY_STACK_PRINT (yyss, yyssp);
+ yystate = *yyssp;
+ goto yyerrlab1;
+
+
+/*-------------------------------------------------------------.
+| yyerrlab1 -- common code for both syntax error and YYERROR. |
+`-------------------------------------------------------------*/
+yyerrlab1:
+ yyerrstatus = 3; /* Each real token shifted decrements this. */
+
+ for (;;)
+ {
+ yyn = yypact[yystate];
+ if (!yypact_value_is_default (yyn))
+ {
+ yyn += YYTERROR;
+ if (0 <= yyn && yyn <= YYLAST && yycheck[yyn] == YYTERROR)
+ {
+ yyn = yytable[yyn];
+ if (0 < yyn)
+ break;
+ }
+ }
+
+ /* Pop the current state because it cannot handle the error token. */
+ if (yyssp == yyss)
+ YYABORT;
+
+
+ yydestruct ("Error: popping",
+ yystos[yystate], yyvsp);
+ YYPOPSTACK (1);
+ yystate = *yyssp;
+ YY_STACK_PRINT (yyss, yyssp);
+ }
+
+ *++yyvsp = yylval;
+
+
+ /* Shift the error token. */
+ YY_SYMBOL_PRINT ("Shifting", yystos[yyn], yyvsp, yylsp);
+
+ yystate = yyn;
+ goto yynewstate;
+
+
+/*-------------------------------------.
+| yyacceptlab -- YYACCEPT comes here. |
+`-------------------------------------*/
+yyacceptlab:
+ yyresult = 0;
+ goto yyreturn;
+
+/*-----------------------------------.
+| yyabortlab -- YYABORT comes here. |
+`-----------------------------------*/
+yyabortlab:
+ yyresult = 1;
+ goto yyreturn;
+
+#if !defined(yyoverflow) || YYERROR_VERBOSE
+/*-------------------------------------------------.
+| yyexhaustedlab -- memory exhaustion comes here. |
+`-------------------------------------------------*/
+yyexhaustedlab:
+ yyerror (YY_("memory exhausted"));
+ yyresult = 2;
+ /* Fall through. */
+#endif
+
+yyreturn:
+ if (yychar != YYEMPTY)
+ {
+ /* Make sure we have latest lookahead translation. See comments at
+ user semantic actions for why this is necessary. */
+ yytoken = YYTRANSLATE (yychar);
+ yydestruct ("Cleanup: discarding lookahead",
+ yytoken, &yylval);
+ }
+ /* Do not reclaim the symbols of the rule which action triggered
+ this YYABORT or YYACCEPT. */
+ YYPOPSTACK (yylen);
+ YY_STACK_PRINT (yyss, yyssp);
+ while (yyssp != yyss)
+ {
+ yydestruct ("Cleanup: popping",
+ yystos[*yyssp], yyvsp);
+ YYPOPSTACK (1);
+ }
+#ifndef yyoverflow
+ if (yyss != yyssa)
+ YYSTACK_FREE (yyss);
+#endif
+#if YYERROR_VERBOSE
+ if (yymsg != yymsgbuf)
+ YYSTACK_FREE (yymsg);
+#endif
+ /* Make sure YYID is used. */
+ return YYID (yyresult);
+}
+
+
+
+/* Line 2067 of yacc.c */
+#line 330 "lib/conf-parse.y"
+
+
+void sensors_yyerror(const char *err)
+{
+ if (sensors_lex_error[0]) {
+ sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+ sensors_lex_error[0] = '\0';
+ } else
+ sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+ sensors_expr *res = malloc(sizeof(sensors_expr));
+ if (! res)
+ sensors_fatal_error(__func__, "Allocating a new expression");
+ return res;
+}
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.h b/tools/gator/daemon/libsensors/conf-parse.h
new file mode 100644
index 0000000..89c9c1a
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.h
@@ -0,0 +1,84 @@
+/* A Bison parser, made by GNU Bison 2.5. */
+
+/* Bison interface for Yacc-like parsers in C
+
+ Copyright (C) 1984, 1989-1990, 2000-2011 Free Software Foundation, Inc.
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+/* As a special exception, you may create a larger work that contains
+ part or all of the Bison parser skeleton and distribute that work
+ under terms of your choice, so long as that work isn't itself a
+ parser generator using the skeleton or a modified version thereof
+ as a parser skeleton. Alternatively, if you modify or redistribute
+ the parser skeleton itself, you may (at your option) remove this
+ special exception, which will cause the skeleton and the resulting
+ Bison output files to be licensed under the GNU General Public
+ License without this special exception.
+
+ This special exception was added by the Free Software Foundation in
+ version 2.2 of Bison. */
+
+
+/* Tokens. */
+#ifndef YYTOKENTYPE
+# define YYTOKENTYPE
+ /* Put the tokens into the symbol table, so that GDB and other debuggers
+ know about them. */
+ enum yytokentype {
+ NEG = 258,
+ EOL = 259,
+ BUS = 260,
+ LABEL = 261,
+ SET = 262,
+ CHIP = 263,
+ COMPUTE = 264,
+ IGNORE = 265,
+ FLOAT = 266,
+ NAME = 267,
+ ERROR = 268
+ };
+#endif
+
+
+
+#if ! defined YYSTYPE && ! defined YYSTYPE_IS_DECLARED
+typedef union YYSTYPE
+{
+
+/* Line 2068 of yacc.c */
+#line 79 "lib/conf-parse.y"
+
+ double value;
+ char *name;
+ void *nothing;
+ sensors_chip_name_list chips;
+ sensors_expr *expr;
+ sensors_bus_id bus;
+ sensors_chip_name chip;
+ sensors_config_line line;
+
+
+
+/* Line 2068 of yacc.c */
+#line 76 "lib/conf-parse.h"
+} YYSTYPE;
+# define YYSTYPE_IS_TRIVIAL 1
+# define yystype YYSTYPE /* obsolescent; will be withdrawn */
+# define YYSTYPE_IS_DECLARED 1
+#endif
+
+extern YYSTYPE sensors_yylval;
+
+
diff --git a/tools/gator/daemon/libsensors/conf-parse.y b/tools/gator/daemon/libsensors/conf-parse.y
new file mode 100644
index 0000000..1937f54
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf-parse.y
@@ -0,0 +1,347 @@
+%{
+/*
+ conf-parse.y - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#define YYERROR_VERBOSE
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+#include "data.h"
+#include "general.h"
+#include "error.h"
+#include "conf.h"
+#include "access.h"
+#include "init.h"
+
+static void sensors_yyerror(const char *err);
+static sensors_expr *malloc_expr(void);
+
+static sensors_chip *current_chip = NULL;
+
+#define bus_add_el(el) sensors_add_array_el(el,\
+ &sensors_config_busses,\
+ &sensors_config_busses_count,\
+ &sensors_config_busses_max,\
+ sizeof(sensors_bus))
+#define label_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->labels,\
+ ¤t_chip->labels_count,\
+ ¤t_chip->labels_max,\
+ sizeof(sensors_label));
+#define set_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->sets,\
+ ¤t_chip->sets_count,\
+ ¤t_chip->sets_max,\
+ sizeof(sensors_set));
+#define compute_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->computes,\
+ ¤t_chip->computes_count,\
+ ¤t_chip->computes_max,\
+ sizeof(sensors_compute));
+#define ignore_add_el(el) sensors_add_array_el(el,\
+ ¤t_chip->ignores,\
+ ¤t_chip->ignores_count,\
+ ¤t_chip->ignores_max,\
+ sizeof(sensors_ignore));
+#define chip_add_el(el) sensors_add_array_el(el,\
+ &sensors_config_chips,\
+ &sensors_config_chips_count,\
+ &sensors_config_chips_max,\
+ sizeof(sensors_chip));
+
+#define fits_add_el(el,list) sensors_add_array_el(el,\
+ &(list).fits,\
+ &(list).fits_count,\
+ &(list).fits_max, \
+ sizeof(sensors_chip_name));
+
+%}
+
+%union {
+ double value;
+ char *name;
+ void *nothing;
+ sensors_chip_name_list chips;
+ sensors_expr *expr;
+ sensors_bus_id bus;
+ sensors_chip_name chip;
+ sensors_config_line line;
+}
+
+%left <nothing> '-' '+'
+%left <nothing> '*' '/'
+%left <nothing> NEG
+%right <nothing> '^' '`'
+
+%token <nothing> ','
+%token <nothing> EOL
+%token <line> BUS
+%token <line> LABEL
+%token <line> SET
+%token <line> CHIP
+%token <line> COMPUTE
+%token <line> IGNORE
+%token <value> FLOAT
+%token <name> NAME
+%token <nothing> ERROR
+
+%type <chips> chip_name_list
+%type <expr> expression
+%type <bus> bus_id
+%type <name> adapter_name
+%type <name> function_name
+%type <name> string
+%type <chip> chip_name
+
+%start input
+
+%%
+
+input: /* empty */
+ | input line
+;
+
+line: bus_statement EOL
+ | label_statement EOL
+ | set_statement EOL
+ | chip_statement EOL
+ | compute_statement EOL
+ | ignore_statement EOL
+ | error EOL
+;
+
+bus_statement: BUS bus_id adapter_name
+ { sensors_bus new_el;
+ new_el.line = $1;
+ new_el.bus = $2;
+ new_el.adapter = $3;
+ bus_add_el(&new_el);
+ }
+;
+
+label_statement: LABEL function_name string
+ { sensors_label new_el;
+ if (!current_chip) {
+ sensors_yyerror("Label statement before first chip statement");
+ free($2);
+ free($3);
+ YYERROR;
+ }
+ new_el.line = $1;
+ new_el.name = $2;
+ new_el.value = $3;
+ label_add_el(&new_el);
+ }
+;
+
+set_statement: SET function_name expression
+ { sensors_set new_el;
+ if (!current_chip) {
+ sensors_yyerror("Set statement before first chip statement");
+ free($2);
+ sensors_free_expr($3);
+ YYERROR;
+ }
+ new_el.line = $1;
+ new_el.name = $2;
+ new_el.value = $3;
+ set_add_el(&new_el);
+ }
+;
+
+compute_statement: COMPUTE function_name expression ',' expression
+ { sensors_compute new_el;
+ if (!current_chip) {
+ sensors_yyerror("Compute statement before first chip statement");
+ free($2);
+ sensors_free_expr($3);
+ sensors_free_expr($5);
+ YYERROR;
+ }
+ new_el.line = $1;
+ new_el.name = $2;
+ new_el.from_proc = $3;
+ new_el.to_proc = $5;
+ compute_add_el(&new_el);
+ }
+;
+
+ignore_statement: IGNORE function_name
+ { sensors_ignore new_el;
+ if (!current_chip) {
+ sensors_yyerror("Ignore statement before first chip statement");
+ free($2);
+ YYERROR;
+ }
+ new_el.line = $1;
+ new_el.name = $2;
+ ignore_add_el(&new_el);
+ }
+;
+
+chip_statement: CHIP chip_name_list
+ { sensors_chip new_el;
+ new_el.line = $1;
+ new_el.labels = NULL;
+ new_el.sets = NULL;
+ new_el.computes = NULL;
+ new_el.ignores = NULL;
+ new_el.labels_count = new_el.labels_max = 0;
+ new_el.sets_count = new_el.sets_max = 0;
+ new_el.computes_count = new_el.computes_max = 0;
+ new_el.ignores_count = new_el.ignores_max = 0;
+ new_el.chips = $2;
+ chip_add_el(&new_el);
+ current_chip = sensors_config_chips +
+ sensors_config_chips_count - 1;
+ }
+;
+
+chip_name_list: chip_name
+ {
+ $$.fits = NULL;
+ $$.fits_count = $$.fits_max = 0;
+ fits_add_el(&$1,$$);
+ }
+ | chip_name_list chip_name
+ { $$ = $1;
+ fits_add_el(&$2,$$);
+ }
+;
+
+expression: FLOAT
+ { $$ = malloc_expr();
+ $$->data.val = $1;
+ $$->kind = sensors_kind_val;
+ }
+ | NAME
+ { $$ = malloc_expr();
+ $$->data.var = $1;
+ $$->kind = sensors_kind_var;
+ }
+ | '@'
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_source;
+ }
+ | expression '+' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_add;
+ $$->data.subexpr.sub1 = $1;
+ $$->data.subexpr.sub2 = $3;
+ }
+ | expression '-' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_sub;
+ $$->data.subexpr.sub1 = $1;
+ $$->data.subexpr.sub2 = $3;
+ }
+ | expression '*' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_multiply;
+ $$->data.subexpr.sub1 = $1;
+ $$->data.subexpr.sub2 = $3;
+ }
+ | expression '/' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_divide;
+ $$->data.subexpr.sub1 = $1;
+ $$->data.subexpr.sub2 = $3;
+ }
+ | '-' expression %prec NEG
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_negate;
+ $$->data.subexpr.sub1 = $2;
+ $$->data.subexpr.sub2 = NULL;
+ }
+ | '(' expression ')'
+ { $$ = $2; }
+ | '^' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_exp;
+ $$->data.subexpr.sub1 = $2;
+ $$->data.subexpr.sub2 = NULL;
+ }
+ | '`' expression
+ { $$ = malloc_expr();
+ $$->kind = sensors_kind_sub;
+ $$->data.subexpr.op = sensors_log;
+ $$->data.subexpr.sub1 = $2;
+ $$->data.subexpr.sub2 = NULL;
+ }
+;
+
+bus_id: NAME
+ { int res = sensors_parse_bus_id($1,&$$);
+ free($1);
+ if (res) {
+ sensors_yyerror("Parse error in bus id");
+ YYERROR;
+ }
+ }
+;
+
+adapter_name: NAME
+ { $$ = $1; }
+;
+
+function_name: NAME
+ { $$ = $1; }
+;
+
+string: NAME
+ { $$ = $1; }
+;
+
+chip_name: NAME
+ { int res = sensors_parse_chip_name($1,&$$);
+ free($1);
+ if (res) {
+ sensors_yyerror("Parse error in chip name");
+ YYERROR;
+ }
+ }
+;
+
+%%
+
+void sensors_yyerror(const char *err)
+{
+ if (sensors_lex_error[0]) {
+ sensors_parse_error_wfn(sensors_lex_error, sensors_yyfilename, sensors_yylineno);
+ sensors_lex_error[0] = '\0';
+ } else
+ sensors_parse_error_wfn(err, sensors_yyfilename, sensors_yylineno);
+}
+
+sensors_expr *malloc_expr(void)
+{
+ sensors_expr *res = malloc(sizeof(sensors_expr));
+ if (! res)
+ sensors_fatal_error(__func__, "Allocating a new expression");
+ return res;
+}
diff --git a/tools/gator/daemon/libsensors/conf.h b/tools/gator/daemon/libsensors/conf.h
new file mode 100644
index 0000000..b7ce4f7
--- /dev/null
+++ b/tools/gator/daemon/libsensors/conf.h
@@ -0,0 +1,34 @@
+/*
+ conf.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_CONF_H
+#define LIB_SENSORS_CONF_H
+
+/* This is defined in conf-lex.l */
+int sensors_yylex(void);
+extern char sensors_lex_error[];
+extern const char *sensors_yyfilename;
+extern int sensors_yylineno;
+extern FILE *sensors_yyin;
+
+/* This is defined in conf-parse.y */
+int sensors_yyparse(void);
+
+#endif /* LIB_SENSORS_CONF_H */
diff --git a/tools/gator/daemon/libsensors/data.c b/tools/gator/daemon/libsensors/data.c
new file mode 100644
index 0000000..cac9c8d
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.c
@@ -0,0 +1,278 @@
+/*
+ data.c - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007, 2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to move version.h to the current directory. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <string.h>
+
+#include "access.h"
+#include "error.h"
+#include "data.h"
+#include "sensors.h"
+#include "version.h"
+
+const char *libsensors_version = LM_VERSION;
+
+char **sensors_config_files = NULL;
+int sensors_config_files_count = 0;
+int sensors_config_files_max = 0;
+
+sensors_chip *sensors_config_chips = NULL;
+int sensors_config_chips_count = 0;
+int sensors_config_chips_subst = 0;
+int sensors_config_chips_max = 0;
+
+sensors_bus *sensors_config_busses = NULL;
+int sensors_config_busses_count = 0;
+int sensors_config_busses_max = 0;
+
+sensors_chip_features *sensors_proc_chips = NULL;
+int sensors_proc_chips_count = 0;
+int sensors_proc_chips_max = 0;
+
+sensors_bus *sensors_proc_bus = NULL;
+int sensors_proc_bus_count = 0;
+int sensors_proc_bus_max = 0;
+
+void sensors_free_chip_name(sensors_chip_name *chip)
+{
+ free(chip->prefix);
+}
+
+/*
+ Parse a chip name to the internal representation. These are valid names:
+
+ lm78-i2c-10-5e *-i2c-10-5e
+ lm78-i2c-10-* *-i2c-10-*
+ lm78-i2c-*-5e *-i2c-*-5e
+ lm78-i2c-*-* *-i2c-*-*
+ lm78-isa-10dd *-isa-10dd
+ lm78-isa-* *-isa-*
+ lm78-* *-*
+
+ Here 'lm78' can be any prefix. 'i2c' and 'isa' are
+ literal strings, just like all dashes '-' and wildcards '*'. '10' can
+ be any decimal i2c bus number. '5e' can be any hexadecimal i2c device
+ address, and '10dd' any hexadecimal isa address.
+
+ The 'prefix' part in the result is freshly allocated. All old contents
+ of res is overwritten. res itself is not allocated. In case of an error
+ return (ie. != 0), res is undefined, but all allocations are undone.
+*/
+
+int sensors_parse_chip_name(const char *name, sensors_chip_name *res)
+{
+ char *dash;
+
+ /* First, the prefix. It's either "*" or a real chip name. */
+ if (!strncmp(name, "*-", 2)) {
+ res->prefix = SENSORS_CHIP_NAME_PREFIX_ANY;
+ name += 2;
+ } else {
+ if (!(dash = strchr(name, '-')))
+ return -SENSORS_ERR_CHIP_NAME;
+ res->prefix = strndup(name, dash - name);
+ if (!res->prefix)
+ sensors_fatal_error(__func__,
+ "Allocating name prefix");
+ name = dash + 1;
+ }
+
+ /* Then we have either a sole "*" (all chips with this name) or a bus
+ type and an address. */
+ if (!strcmp(name, "*")) {
+ res->bus.type = SENSORS_BUS_TYPE_ANY;
+ res->bus.nr = SENSORS_BUS_NR_ANY;
+ res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+ return 0;
+ }
+
+ if (!(dash = strchr(name, '-')))
+ goto ERROR;
+ if (!strncmp(name, "i2c", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_I2C;
+ else if (!strncmp(name, "isa", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_ISA;
+ else if (!strncmp(name, "pci", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_PCI;
+ else if (!strncmp(name, "spi", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_SPI;
+ else if (!strncmp(name, "virtual", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+ else if (!strncmp(name, "acpi", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_ACPI;
+ else if (!strncmp(name, "hid", dash - name))
+ res->bus.type = SENSORS_BUS_TYPE_HID;
+ else
+ goto ERROR;
+ name = dash + 1;
+
+ /* Some bus types (i2c, spi) have an additional bus number.
+ For these, the next part is either a "*" (any bus of that type)
+ or a decimal number. */
+ switch (res->bus.type) {
+ case SENSORS_BUS_TYPE_I2C:
+ case SENSORS_BUS_TYPE_SPI:
+ case SENSORS_BUS_TYPE_HID:
+ if (!strncmp(name, "*-", 2)) {
+ res->bus.nr = SENSORS_BUS_NR_ANY;
+ name += 2;
+ break;
+ }
+
+ res->bus.nr = strtoul(name, &dash, 10);
+ if (*name == '\0' || *dash != '-' || res->bus.nr < 0)
+ goto ERROR;
+ name = dash + 1;
+ break;
+ default:
+ res->bus.nr = SENSORS_BUS_NR_ANY;
+ }
+
+ /* Last part is the chip address, or "*" for any address. */
+ if (!strcmp(name, "*")) {
+ res->addr = SENSORS_CHIP_NAME_ADDR_ANY;
+ } else {
+ res->addr = strtoul(name, &dash, 16);
+ if (*name == '\0' || *dash != '\0' || res->addr < 0)
+ goto ERROR;
+ }
+
+ return 0;
+
+ERROR:
+ free(res->prefix);
+ return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_snprintf_chip_name(char *str, size_t size,
+ const sensors_chip_name *chip)
+{
+ if (sensors_chip_name_has_wildcards(chip))
+ return -SENSORS_ERR_WILDCARDS;
+
+ switch (chip->bus.type) {
+ case SENSORS_BUS_TYPE_ISA:
+ return snprintf(str, size, "%s-isa-%04x", chip->prefix,
+ chip->addr);
+ case SENSORS_BUS_TYPE_PCI:
+ return snprintf(str, size, "%s-pci-%04x", chip->prefix,
+ chip->addr);
+ case SENSORS_BUS_TYPE_I2C:
+ return snprintf(str, size, "%s-i2c-%hd-%02x", chip->prefix,
+ chip->bus.nr, chip->addr);
+ case SENSORS_BUS_TYPE_SPI:
+ return snprintf(str, size, "%s-spi-%hd-%x", chip->prefix,
+ chip->bus.nr, chip->addr);
+ case SENSORS_BUS_TYPE_VIRTUAL:
+ return snprintf(str, size, "%s-virtual-%x", chip->prefix,
+ chip->addr);
+ case SENSORS_BUS_TYPE_ACPI:
+ return snprintf(str, size, "%s-acpi-%x", chip->prefix,
+ chip->addr);
+ case SENSORS_BUS_TYPE_HID:
+ return snprintf(str, size, "%s-hid-%hd-%x", chip->prefix,
+ chip->bus.nr, chip->addr);
+ }
+
+ return -SENSORS_ERR_CHIP_NAME;
+}
+
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus)
+{
+ char *endptr;
+
+ if (strncmp(name, "i2c-", 4)) {
+ return -SENSORS_ERR_BUS_NAME;
+ }
+ name += 4;
+ bus->type = SENSORS_BUS_TYPE_I2C;
+ bus->nr = strtoul(name, &endptr, 10);
+ if (*name == '\0' || *endptr != '\0' || bus->nr < 0)
+ return -SENSORS_ERR_BUS_NAME;
+ return 0;
+}
+
+static int sensors_substitute_chip(sensors_chip_name *name,
+ const char *filename, int lineno)
+{
+ int i, j;
+ for (i = 0; i < sensors_config_busses_count; i++)
+ if (sensors_config_busses[i].bus.type == name->bus.type &&
+ sensors_config_busses[i].bus.nr == name->bus.nr)
+ break;
+
+ if (i == sensors_config_busses_count) {
+ sensors_parse_error_wfn("Undeclared bus id referenced",
+ filename, lineno);
+ name->bus.nr = SENSORS_BUS_NR_IGNORE;
+ return -SENSORS_ERR_BUS_NAME;
+ }
+
+ /* Compare the adapter names */
+ for (j = 0; j < sensors_proc_bus_count; j++) {
+ if (!strcmp(sensors_config_busses[i].adapter,
+ sensors_proc_bus[j].adapter)) {
+ name->bus.nr = sensors_proc_bus[j].bus.nr;
+ return 0;
+ }
+ }
+
+ /* We did not find a matching bus name, simply ignore this chip
+ config entry. */
+ name->bus.nr = SENSORS_BUS_NR_IGNORE;
+ return 0;
+}
+
+/* Bus substitution is on a per-configuration file basis, so we keep
+ memory (in sensors_config_chips_subst) of which chip entries have been
+ already substituted. */
+int sensors_substitute_busses(void)
+{
+ int err, i, j, lineno;
+ sensors_chip_name_list *chips;
+ const char *filename;
+ int res = 0;
+
+ for (i = sensors_config_chips_subst;
+ i < sensors_config_chips_count; i++) {
+ filename = sensors_config_chips[i].line.filename;
+ lineno = sensors_config_chips[i].line.lineno;
+ chips = &sensors_config_chips[i].chips;
+ for (j = 0; j < chips->fits_count; j++) {
+ /* We can only substitute if a specific bus number
+ is given. */
+ if (chips->fits[j].bus.nr == SENSORS_BUS_NR_ANY)
+ continue;
+
+ err = sensors_substitute_chip(&chips->fits[j],
+ filename, lineno);
+ if (err)
+ res = err;
+ }
+ }
+ sensors_config_chips_subst = sensors_config_chips_count;
+ return res;
+}
diff --git a/tools/gator/daemon/libsensors/data.h b/tools/gator/daemon/libsensors/data.h
new file mode 100644
index 0000000..4a23eab
--- /dev/null
+++ b/tools/gator/daemon/libsensors/data.h
@@ -0,0 +1,184 @@
+/*
+ data.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007, 2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_DATA_H
+#define LIB_SENSORS_DATA_H
+
+#include "sensors.h"
+#include "general.h"
+
+/* This header file contains all kinds of data structures which are used
+ for the representation of the config file data and the sensors
+ data. */
+
+/* Kinds of expression operators recognized */
+typedef enum sensors_operation {
+ sensors_add, sensors_sub, sensors_multiply, sensors_divide,
+ sensors_negate, sensors_exp, sensors_log,
+} sensors_operation;
+
+/* An expression can have several forms */
+typedef enum sensors_expr_kind {
+ sensors_kind_val, sensors_kind_source, sensors_kind_var,
+ sensors_kind_sub
+} sensors_expr_kind;
+
+/* An expression. It is either a floating point value, a variable name,
+ an operation on subexpressions, or the special value 'sub' } */
+struct sensors_expr;
+
+typedef struct sensors_subexpr {
+ sensors_operation op;
+ struct sensors_expr *sub1;
+ struct sensors_expr *sub2;
+} sensors_subexpr;
+
+typedef struct sensors_expr {
+ sensors_expr_kind kind;
+ union {
+ double val;
+ char *var;
+ sensors_subexpr subexpr;
+ } data;
+} sensors_expr;
+
+/* Config file line reference */
+typedef struct sensors_config_line {
+ const char *filename;
+ int lineno;
+} sensors_config_line;
+
+/* Config file label declaration: a feature name, combined with the label
+ value */
+typedef struct sensors_label {
+ char *name;
+ char *value;
+ sensors_config_line line;
+} sensors_label;
+
+/* Config file set declaration: a subfeature name, combined with an
+ expression */
+typedef struct sensors_set {
+ char *name;
+ sensors_expr *value;
+ sensors_config_line line;
+} sensors_set;
+
+/* Config file compute declaration: a feature name, combined with two
+ expressions */
+typedef struct sensors_compute {
+ char *name;
+ sensors_expr *from_proc;
+ sensors_expr *to_proc;
+ sensors_config_line line;
+} sensors_compute;
+
+/* Config file ignore declaration: a feature name */
+typedef struct sensors_ignore {
+ char *name;
+ sensors_config_line line;
+} sensors_ignore;
+
+/* A list of chip names, used to represent a config file chips declaration */
+typedef struct sensors_chip_name_list {
+ sensors_chip_name *fits;
+ int fits_count;
+ int fits_max;
+} sensors_chip_name_list;
+
+/* A config file chip block */
+typedef struct sensors_chip {
+ sensors_chip_name_list chips;
+ sensors_label *labels;
+ int labels_count;
+ int labels_max;
+ sensors_set *sets;
+ int sets_count;
+ int sets_max;
+ sensors_compute *computes;
+ int computes_count;
+ int computes_max;
+ sensors_ignore *ignores;
+ int ignores_count;
+ int ignores_max;
+ sensors_config_line line;
+} sensors_chip;
+
+/* Config file bus declaration: the bus type and number, combined with adapter
+ name */
+typedef struct sensors_bus {
+ char *adapter;
+ sensors_bus_id bus;
+ sensors_config_line line;
+} sensors_bus;
+
+/* Internal data about all features and subfeatures of a chip */
+typedef struct sensors_chip_features {
+ struct sensors_chip_name chip;
+ struct sensors_feature *feature;
+ struct sensors_subfeature *subfeature;
+ int feature_count;
+ int subfeature_count;
+} sensors_chip_features;
+
+extern char **sensors_config_files;
+extern int sensors_config_files_count;
+extern int sensors_config_files_max;
+
+#define sensors_add_config_files(el) sensors_add_array_el( \
+ (el), &sensors_config_files, &sensors_config_files_count, \
+ &sensors_config_files_max, sizeof(char *))
+
+extern sensors_chip *sensors_config_chips;
+extern int sensors_config_chips_count;
+extern int sensors_config_chips_subst;
+extern int sensors_config_chips_max;
+
+extern sensors_bus *sensors_config_busses;
+extern int sensors_config_busses_count;
+extern int sensors_config_busses_max;
+
+extern sensors_chip_features *sensors_proc_chips;
+extern int sensors_proc_chips_count;
+extern int sensors_proc_chips_max;
+
+#define sensors_add_proc_chips(el) sensors_add_array_el( \
+ (el), &sensors_proc_chips, &sensors_proc_chips_count,\
+ &sensors_proc_chips_max, sizeof(struct sensors_chip_features))
+
+extern sensors_bus *sensors_proc_bus;
+extern int sensors_proc_bus_count;
+extern int sensors_proc_bus_max;
+
+#define sensors_add_proc_bus(el) sensors_add_array_el( \
+ (el), &sensors_proc_bus, &sensors_proc_bus_count,\
+ &sensors_proc_bus_max, sizeof(struct sensors_bus))
+
+/* Substitute configuration bus numbers with real-world bus numbers
+ in the chips lists */
+int sensors_substitute_busses(void);
+
+
+/* Parse a bus id into its components. Returns 0 on success, a value from
+ error.h on failure. */
+int sensors_parse_bus_id(const char *name, sensors_bus_id *bus);
+
+#endif /* def LIB_SENSORS_DATA_H */
diff --git a/tools/gator/daemon/libsensors/error.c b/tools/gator/daemon/libsensors/error.c
new file mode 100644
index 0000000..55bde81
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.c
@@ -0,0 +1,92 @@
+/*
+ error.c - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007-2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#include <stdlib.h>
+#include <stdio.h>
+#include "error.h"
+#include "general.h"
+
+static void sensors_default_parse_error(const char *err, int lineno);
+static void sensors_default_parse_error_wfn(const char *err,
+ const char *filename, int lineno);
+static void sensors_default_fatal_error(const char *proc, const char *err);
+
+void (*sensors_parse_error) (const char *err, int lineno) =
+ sensors_default_parse_error;
+void (*sensors_parse_error_wfn) (const char *err, const char *filename,
+ int lineno) = sensors_default_parse_error_wfn;
+void (*sensors_fatal_error) (const char *proc, const char *err) =
+ sensors_default_fatal_error;
+
+static const char *errorlist[] = {
+ /* Invalid error code */ "Unknown error",
+ /* SENSORS_ERR_WILDCARDS */ "Wildcard found in chip name",
+ /* SENSORS_ERR_NO_ENTRY */ "No such subfeature known",
+ /* SENSORS_ERR_ACCESS_R */ "Can't read",
+ /* SENSORS_ERR_KERNEL */ "Kernel interface error",
+ /* SENSORS_ERR_DIV_ZERO */ "Divide by zero",
+ /* SENSORS_ERR_CHIP_NAME */ "Can't parse chip name",
+ /* SENSORS_ERR_BUS_NAME */ "Can't parse bus name",
+ /* SENSORS_ERR_PARSE */ "General parse error",
+ /* SENSORS_ERR_ACCESS_W */ "Can't write",
+ /* SENSORS_ERR_IO */ "I/O error",
+ /* SENSORS_ERR_RECURSION */ "Evaluation recurses too deep",
+};
+
+const char *sensors_strerror(int errnum)
+{
+ if (errnum < 0)
+ errnum = -errnum;
+ if (errnum >= ARRAY_SIZE(errorlist))
+ errnum = 0;
+ return errorlist[errnum];
+}
+
+void sensors_default_parse_error(const char *err, int lineno)
+{
+ if (lineno)
+ fprintf(stderr, "Error: Line %d: %s\n", lineno, err);
+ else
+ fprintf(stderr, "Error: %s\n", err);
+}
+
+void sensors_default_parse_error_wfn(const char *err,
+ const char *filename, int lineno)
+{
+ /* If application provided a custom parse error reporting function
+ but not the variant with the filename, fall back to the original
+ variant without the filename, for backwards compatibility. */
+ if (sensors_parse_error != sensors_default_parse_error ||
+ !filename)
+ return sensors_parse_error(err, lineno);
+
+ if (lineno)
+ fprintf(stderr, "Error: File %s, line %d: %s\n", filename,
+ lineno, err);
+ else
+ fprintf(stderr, "Error: File %s: %s\n", filename, err);
+}
+
+void sensors_default_fatal_error(const char *proc, const char *err)
+{
+ fprintf(stderr, "Fatal error in `%s': %s\n", proc, err);
+ exit(1);
+}
diff --git a/tools/gator/daemon/libsensors/error.h b/tools/gator/daemon/libsensors/error.h
new file mode 100644
index 0000000..37cdc95
--- /dev/null
+++ b/tools/gator/daemon/libsensors/error.h
@@ -0,0 +1,74 @@
+/*
+ error.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007-2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_ERROR_H
+#define LIB_SENSORS_ERROR_H
+
+#define SENSORS_ERR_WILDCARDS 1 /* Wildcard found in chip name */
+#define SENSORS_ERR_NO_ENTRY 2 /* No such subfeature known */
+#define SENSORS_ERR_ACCESS_R 3 /* Can't read */
+#define SENSORS_ERR_KERNEL 4 /* Kernel interface error */
+#define SENSORS_ERR_DIV_ZERO 5 /* Divide by zero */
+#define SENSORS_ERR_CHIP_NAME 6 /* Can't parse chip name */
+#define SENSORS_ERR_BUS_NAME 7 /* Can't parse bus name */
+#define SENSORS_ERR_PARSE 8 /* General parse error */
+#define SENSORS_ERR_ACCESS_W 9 /* Can't write */
+#define SENSORS_ERR_IO 10 /* I/O error */
+#define SENSORS_ERR_RECURSION 11 /* Evaluation recurses too deep */
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+
+/* This function returns a pointer to a string which describes the error.
+ errnum may be negative (the corresponding positive error is returned).
+ You may not modify the result! */
+const char *sensors_strerror(int errnum);
+
+/* These functions are called when a parse error is detected. Give them new
+ values, and your own functions are called instead of the default (which
+ print to stderr). These functions may terminate the program, but they
+ usually output an error and return. The first function is the original
+ one, the second one was added later when support for multiple
+ configuration files was added.
+ The library code now only calls the second function. However, for
+ backwards compatibility, if an application provides a custom handling
+ function for the first function but not the second, then all parse
+ errors will be reported using the first function (that is, the filename
+ is never reported.)
+ Note that filename can be NULL (if filename isn't known) and lineno
+ can be 0 (if the error occurs before the actual parsing starts.) */
+extern void (*sensors_parse_error) (const char *err, int lineno);
+extern void (*sensors_parse_error_wfn) (const char *err,
+ const char *filename, int lineno);
+
+/* This function is called when an immediately fatal error (like no
+ memory left) is detected. Give it a new value, and your own function
+ is called instead of the default (which prints to stderr and ends
+ the program). Never let it return! */
+extern void (*sensors_fatal_error) (const char *proc, const char *err);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/general.c b/tools/gator/daemon/libsensors/general.c
new file mode 100644
index 0000000..f237e3b
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.c
@@ -0,0 +1,85 @@
+/*
+ general.c - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#include "error.h"
+#include "general.h"
+#include <errno.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+
+
+#define A_BUNCH 16
+
+void sensors_malloc_array(void *list, int *num_el, int *max_el, int el_size)
+{
+ void **my_list = (void **)list;
+
+ *my_list = malloc(el_size*A_BUNCH);
+ if (! *my_list)
+ sensors_fatal_error(__func__, "Allocating new elements");
+ *max_el = A_BUNCH;
+ *num_el = 0;
+}
+
+void sensors_free_array(void *list, int *num_el, int *max_el)
+{
+ void **my_list = (void **)list;
+
+ free(*my_list);
+ *my_list = NULL;
+ *num_el = 0;
+ *max_el = 0;
+}
+
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+ int *max_el, int el_size)
+{
+ int new_max_el;
+ void **my_list = (void *)list;
+ if (*num_el + 1 > *max_el) {
+ new_max_el = *max_el + A_BUNCH;
+ *my_list = realloc(*my_list, new_max_el * el_size);
+ if (! *my_list)
+ sensors_fatal_error(__func__,
+ "Allocating new elements");
+ *max_el = new_max_el;
+ }
+ memcpy(((char *) *my_list) + *num_el * el_size, el, el_size);
+ (*num_el) ++;
+}
+
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+ int *num_el, int *max_el, int el_size)
+{
+ int new_max_el;
+ void **my_list = (void *)list;
+ if (*num_el + nr_els > *max_el) {
+ new_max_el = (*max_el + nr_els + A_BUNCH);
+ new_max_el -= new_max_el % A_BUNCH;
+ *my_list = realloc(*my_list, new_max_el * el_size);
+ if (! *my_list)
+ sensors_fatal_error(__func__,
+ "Allocating new elements");
+ *max_el = new_max_el;
+ }
+ memcpy(((char *)*my_list) + *num_el * el_size, els, el_size * nr_els);
+ *num_el += nr_els;
+}
diff --git a/tools/gator/daemon/libsensors/general.h b/tools/gator/daemon/libsensors/general.h
new file mode 100644
index 0000000..a3971e0
--- /dev/null
+++ b/tools/gator/daemon/libsensors/general.h
@@ -0,0 +1,39 @@
+/*
+ general.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_GENERAL
+#define LIB_SENSORS_GENERAL
+
+/* These are general purpose functions. They allow you to use variable-
+ length arrays, which are extended automatically. A distinction is
+ made between the current number of elements and the maximum number.
+ You can only add elements at the end. Primitive, but very useful
+ for internal use. */
+void sensors_malloc_array(void *list, int *num_el, int *max_el,
+ int el_size);
+void sensors_free_array(void *list, int *num_el, int *max_el);
+void sensors_add_array_el(const void *el, void *list, int *num_el,
+ int *max_el, int el_size);
+void sensors_add_array_els(const void *els, int nr_els, void *list,
+ int *num_el, int *max_el, int el_size);
+
+#define ARRAY_SIZE(arr) (int)(sizeof(arr) / sizeof((arr)[0]))
+
+#endif /* LIB_SENSORS_GENERAL */
diff --git a/tools/gator/daemon/libsensors/init.c b/tools/gator/daemon/libsensors/init.c
new file mode 100644
index 0000000..558046e
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.c
@@ -0,0 +1,341 @@
+/*
+ init.c - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007, 2009 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to cast alphasort to supress a warning as it's prototype is different on android. ***/
+
+/* Needed for scandir() and alphasort() */
+#define _BSD_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <locale.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <dirent.h>
+#include <unistd.h>
+#include "sensors.h"
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "conf.h"
+#include "sysfs.h"
+#include "scanner.h"
+#include "init.h"
+
+#define DEFAULT_CONFIG_FILE ETCDIR "/sensors3.conf"
+#define ALT_CONFIG_FILE ETCDIR "/sensors.conf"
+#define DEFAULT_CONFIG_DIR ETCDIR "/sensors.d"
+
+/* Wrapper around sensors_yyparse(), which clears the locale so that
+ the decimal numbers are always parsed properly. */
+static int sensors_parse(void)
+{
+ int res;
+ char *locale;
+
+ /* Remember the current locale and clear it */
+ locale = setlocale(LC_ALL, NULL);
+ if (locale) {
+ locale = strdup(locale);
+ if (!locale)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ setlocale(LC_ALL, "C");
+ }
+
+ res = sensors_yyparse();
+
+ /* Restore the old locale */
+ if (locale) {
+ setlocale(LC_ALL, locale);
+ free(locale);
+ }
+
+ return res;
+}
+
+static void free_bus(sensors_bus *bus)
+{
+ free(bus->adapter);
+}
+
+static void free_config_busses(void)
+{
+ int i;
+
+ for (i = 0; i < sensors_config_busses_count; i++)
+ free_bus(&sensors_config_busses[i]);
+ free(sensors_config_busses);
+ sensors_config_busses = NULL;
+ sensors_config_busses_count = sensors_config_busses_max = 0;
+}
+
+static int parse_config(FILE *input, const char *name)
+{
+ int err;
+ char *name_copy;
+
+ if (name) {
+ /* Record configuration file name for error reporting */
+ name_copy = strdup(name);
+ if (!name_copy)
+ sensors_fatal_error(__func__, "Out of memory");
+ sensors_add_config_files(&name_copy);
+ } else
+ name_copy = NULL;
+
+ if (sensors_scanner_init(input, name_copy)) {
+ err = -SENSORS_ERR_PARSE;
+ goto exit_cleanup;
+ }
+ err = sensors_parse();
+ sensors_scanner_exit();
+ if (err) {
+ err = -SENSORS_ERR_PARSE;
+ goto exit_cleanup;
+ }
+
+ err = sensors_substitute_busses();
+
+exit_cleanup:
+ free_config_busses();
+ return err;
+}
+
+static int config_file_filter(const struct dirent *entry)
+{
+ return entry->d_name[0] != '.'; /* Skip hidden files */
+}
+
+static int add_config_from_dir(const char *dir)
+{
+ int count, res, i;
+ struct dirent **namelist;
+
+ count = scandir(dir, &namelist, config_file_filter, (int (*)(const struct dirent **, const struct dirent **))alphasort);
+ if (count < 0) {
+ /* Do not return an error if directory does not exist */
+ if (errno == ENOENT)
+ return 0;
+
+ sensors_parse_error_wfn(strerror(errno), NULL, 0);
+ return -SENSORS_ERR_PARSE;
+ }
+
+ for (res = 0, i = 0; !res && i < count; i++) {
+ int len;
+ char path[PATH_MAX];
+ FILE *input;
+ struct stat st;
+
+ len = snprintf(path, sizeof(path), "%s/%s", dir,
+ namelist[i]->d_name);
+ if (len < 0 || len >= (int)sizeof(path)) {
+ res = -SENSORS_ERR_PARSE;
+ continue;
+ }
+
+ /* Only accept regular files */
+ if (stat(path, &st) < 0 || !S_ISREG(st.st_mode))
+ continue;
+
+ input = fopen(path, "r");
+ if (input) {
+ res = parse_config(input, path);
+ fclose(input);
+ } else {
+ res = -SENSORS_ERR_PARSE;
+ sensors_parse_error_wfn(strerror(errno), path, 0);
+ }
+ }
+
+ /* Free memory allocated by scandir() */
+ for (i = 0; i < count; i++)
+ free(namelist[i]);
+ free(namelist);
+
+ return res;
+}
+
+int sensors_init(FILE *input)
+{
+ int res;
+
+ if (!sensors_init_sysfs())
+ return -SENSORS_ERR_KERNEL;
+ if ((res = sensors_read_sysfs_bus()) ||
+ (res = sensors_read_sysfs_chips()))
+ goto exit_cleanup;
+
+ if (input) {
+ res = parse_config(input, NULL);
+ if (res)
+ goto exit_cleanup;
+ } else {
+ const char* name;
+
+ /* No configuration provided, use default */
+ input = fopen(name = DEFAULT_CONFIG_FILE, "r");
+ if (!input && errno == ENOENT)
+ input = fopen(name = ALT_CONFIG_FILE, "r");
+ if (input) {
+ res = parse_config(input, name);
+ fclose(input);
+ if (res)
+ goto exit_cleanup;
+
+ } else if (errno != ENOENT) {
+ sensors_parse_error_wfn(strerror(errno), name, 0);
+ res = -SENSORS_ERR_PARSE;
+ goto exit_cleanup;
+ }
+
+ /* Also check for files in default directory */
+ res = add_config_from_dir(DEFAULT_CONFIG_DIR);
+ if (res)
+ goto exit_cleanup;
+ }
+
+ return 0;
+
+exit_cleanup:
+ sensors_cleanup();
+ return res;
+}
+
+static void free_chip_name(sensors_chip_name *name)
+{
+ free(name->prefix);
+ free(name->path);
+}
+
+static void free_chip_features(sensors_chip_features *features)
+{
+ int i;
+
+ for (i = 0; i < features->subfeature_count; i++)
+ free(features->subfeature[i].name);
+ free(features->subfeature);
+ for (i = 0; i < features->feature_count; i++)
+ free(features->feature[i].name);
+ free(features->feature);
+}
+
+static void free_label(sensors_label *label)
+{
+ free(label->name);
+ free(label->value);
+}
+
+void sensors_free_expr(sensors_expr *expr)
+{
+ if (expr->kind == sensors_kind_var)
+ free(expr->data.var);
+ else if (expr->kind == sensors_kind_sub) {
+ if (expr->data.subexpr.sub1)
+ sensors_free_expr(expr->data.subexpr.sub1);
+ if (expr->data.subexpr.sub2)
+ sensors_free_expr(expr->data.subexpr.sub2);
+ }
+ free(expr);
+}
+
+static void free_set(sensors_set *set)
+{
+ free(set->name);
+ sensors_free_expr(set->value);
+}
+
+static void free_compute(sensors_compute *compute)
+{
+ free(compute->name);
+ sensors_free_expr(compute->from_proc);
+ sensors_free_expr(compute->to_proc);
+}
+
+static void free_ignore(sensors_ignore *ignore)
+{
+ free(ignore->name);
+}
+
+static void free_chip(sensors_chip *chip)
+{
+ int i;
+
+ for (i = 0; i < chip->chips.fits_count; i++)
+ free_chip_name(&chip->chips.fits[i]);
+ free(chip->chips.fits);
+ chip->chips.fits_count = chip->chips.fits_max = 0;
+
+ for (i = 0; i < chip->labels_count; i++)
+ free_label(&chip->labels[i]);
+ free(chip->labels);
+ chip->labels_count = chip->labels_max = 0;
+
+ for (i = 0; i < chip->sets_count; i++)
+ free_set(&chip->sets[i]);
+ free(chip->sets);
+ chip->sets_count = chip->sets_max = 0;
+
+ for (i = 0; i < chip->computes_count; i++)
+ free_compute(&chip->computes[i]);
+ free(chip->computes);
+ chip->computes_count = chip->computes_max = 0;
+
+ for (i = 0; i < chip->ignores_count; i++)
+ free_ignore(&chip->ignores[i]);
+ free(chip->ignores);
+ chip->ignores_count = chip->ignores_max = 0;
+}
+
+void sensors_cleanup(void)
+{
+ int i;
+
+ for (i = 0; i < sensors_proc_chips_count; i++) {
+ free_chip_name(&sensors_proc_chips[i].chip);
+ free_chip_features(&sensors_proc_chips[i]);
+ }
+ free(sensors_proc_chips);
+ sensors_proc_chips = NULL;
+ sensors_proc_chips_count = sensors_proc_chips_max = 0;
+
+ for (i = 0; i < sensors_config_chips_count; i++)
+ free_chip(&sensors_config_chips[i]);
+ free(sensors_config_chips);
+ sensors_config_chips = NULL;
+ sensors_config_chips_count = sensors_config_chips_max = 0;
+ sensors_config_chips_subst = 0;
+
+ for (i = 0; i < sensors_proc_bus_count; i++)
+ free_bus(&sensors_proc_bus[i]);
+ free(sensors_proc_bus);
+ sensors_proc_bus = NULL;
+ sensors_proc_bus_count = sensors_proc_bus_max = 0;
+
+ for (i = 0; i < sensors_config_files_count; i++)
+ free(sensors_config_files[i]);
+ free(sensors_config_files);
+ sensors_config_files = NULL;
+ sensors_config_files_count = sensors_config_files_max = 0;
+}
diff --git a/tools/gator/daemon/libsensors/init.h b/tools/gator/daemon/libsensors/init.h
new file mode 100644
index 0000000..47006a6
--- /dev/null
+++ b/tools/gator/daemon/libsensors/init.h
@@ -0,0 +1,28 @@
+/*
+ init.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (C) 2007 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef LIB_SENSORS_INIT_H
+#define LIB_SENSORS_INIT_H
+
+#include "data.h"
+
+void sensors_free_expr(sensors_expr *expr);
+
+#endif /* def LIB_SENSORS_INIT_H */
diff --git a/tools/gator/daemon/libsensors/scanner.h b/tools/gator/daemon/libsensors/scanner.h
new file mode 100644
index 0000000..4c41516
--- /dev/null
+++ b/tools/gator/daemon/libsensors/scanner.h
@@ -0,0 +1,32 @@
+/*
+ scanner.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 2006 Mark M. Hoffman <mhoffman@lightlink.com>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to fix input defined but not used warning from conf-lex.c. ***/
+
+#ifndef LIB_SENSORS_SCANNER_H
+#define LIB_SENSORS_SCANNER_H
+
+int sensors_scanner_init(FILE *input, const char *filename);
+void sensors_scanner_exit(void);
+
+#define YY_NO_INPUT
+
+#endif
+
diff --git a/tools/gator/daemon/libsensors/sensors.h b/tools/gator/daemon/libsensors/sensors.h
new file mode 100644
index 0000000..7874d02
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sensors.h
@@ -0,0 +1,311 @@
+/*
+ sensors.h - Part of libsensors, a Linux library for reading sensor data.
+ Copyright (c) 1998, 1999 Frodo Looijaard <frodol@dds.nl>
+ Copyright (C) 2007, 2010 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to read non-scaled values. ***/
+
+#ifndef LIB_SENSORS_SENSORS_H
+#define LIB_SENSORS_SENSORS_H
+
+#include <stdio.h>
+#include <limits.h>
+
+/* Publicly accessible library functions */
+
+/* libsensors API version define, first digit is the major version (changed
+ when the API + ABI breaks), the third digit is incremented to track small
+ API additions like new flags / enum values. The second digit is for tracking
+ larger additions like new methods. */
+#define SENSORS_API_VERSION 0x432
+
+#define SENSORS_CHIP_NAME_PREFIX_ANY NULL
+#define SENSORS_CHIP_NAME_ADDR_ANY (-1)
+
+#define SENSORS_BUS_TYPE_ANY (-1)
+#define SENSORS_BUS_TYPE_I2C 0
+#define SENSORS_BUS_TYPE_ISA 1
+#define SENSORS_BUS_TYPE_PCI 2
+#define SENSORS_BUS_TYPE_SPI 3
+#define SENSORS_BUS_TYPE_VIRTUAL 4
+#define SENSORS_BUS_TYPE_ACPI 5
+#define SENSORS_BUS_TYPE_HID 6
+#define SENSORS_BUS_NR_ANY (-1)
+#define SENSORS_BUS_NR_IGNORE (-2)
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+extern const char *libsensors_version;
+
+extern int sensors_sysfs_no_scaling;
+
+typedef struct sensors_bus_id {
+ short type;
+ short nr;
+} sensors_bus_id;
+
+/* A chip name is encoded in this structure */
+typedef struct sensors_chip_name {
+ char *prefix;
+ sensors_bus_id bus;
+ int addr;
+ char *path;
+} sensors_chip_name;
+
+/* Load the configuration file and the detected chips list. If this
+ returns a value unequal to zero, you are in trouble; you can not
+ assume anything will be initialized properly. If you want to
+ reload the configuration file, call sensors_cleanup() below before
+ calling sensors_init() again. */
+int sensors_init(FILE *input);
+
+/* Clean-up function: You can't access anything after
+ this, until the next sensors_init() call! */
+void sensors_cleanup(void);
+
+/* Parse a chip name to the internal representation. Return 0 on success, <0
+ on error. */
+int sensors_parse_chip_name(const char *orig_name, sensors_chip_name *res);
+
+/* Free memory allocated for the internal representation of a chip name. */
+void sensors_free_chip_name(sensors_chip_name *chip);
+
+/* Print a chip name from its internal representation. Note that chip should
+ not contain wildcard values! Return the number of characters printed on
+ success (same as snprintf), <0 on error. */
+int sensors_snprintf_chip_name(char *str, size_t size,
+ const sensors_chip_name *chip);
+
+/* This function returns the adapter name of a bus,
+ as used within the sensors_chip_name structure. If it could not be found,
+ it returns NULL */
+const char *sensors_get_adapter_name(const sensors_bus_id *bus);
+
+typedef struct sensors_feature sensors_feature;
+
+/* Look up the label for a given feature. Note that chip should not
+ contain wildcard values! The returned string is newly allocated (free it
+ yourself). On failure, NULL is returned.
+ If no label exists for this feature, its name is returned itself. */
+char *sensors_get_label(const sensors_chip_name *name,
+ const sensors_feature *feature);
+
+/* Read the value of a subfeature of a certain chip. Note that chip should not
+ contain wildcard values! This function will return 0 on success, and <0
+ on failure. */
+int sensors_get_value(const sensors_chip_name *name, int subfeat_nr,
+ double *value);
+
+/* Set the value of a subfeature of a certain chip. Note that chip should not
+ contain wildcard values! This function will return 0 on success, and <0
+ on failure. */
+int sensors_set_value(const sensors_chip_name *name, int subfeat_nr,
+ double value);
+
+/* Execute all set statements for this particular chip. The chip may contain
+ wildcards! This function will return 0 on success, and <0 on failure. */
+int sensors_do_chip_sets(const sensors_chip_name *name);
+
+/* This function returns all detected chips that match a given chip name,
+ one by one. If no chip name is provided, all detected chips are returned.
+ To start at the beginning of the list, use 0 for nr; NULL is returned if
+ we are at the end of the list. Do not try to change these chip names, as
+ they point to internal structures! */
+const sensors_chip_name *sensors_get_detected_chips(const sensors_chip_name
+ *match, int *nr);
+
+/* These defines are used in the flags field of sensors_subfeature */
+#define SENSORS_MODE_R 1
+#define SENSORS_MODE_W 2
+#define SENSORS_COMPUTE_MAPPING 4
+
+typedef enum sensors_feature_type {
+ SENSORS_FEATURE_IN = 0x00,
+ SENSORS_FEATURE_FAN = 0x01,
+ SENSORS_FEATURE_TEMP = 0x02,
+ SENSORS_FEATURE_POWER = 0x03,
+ SENSORS_FEATURE_ENERGY = 0x04,
+ SENSORS_FEATURE_CURR = 0x05,
+ SENSORS_FEATURE_HUMIDITY = 0x06,
+ SENSORS_FEATURE_MAX_MAIN,
+ SENSORS_FEATURE_VID = 0x10,
+ SENSORS_FEATURE_INTRUSION = 0x11,
+ SENSORS_FEATURE_MAX_OTHER,
+ SENSORS_FEATURE_BEEP_ENABLE = 0x18,
+ SENSORS_FEATURE_UNKNOWN = INT_MAX,
+} sensors_feature_type;
+
+/* All the sensor types (in, fan, temp, vid) are a multiple of 0x100 apart,
+ and sensor subfeatures which have no compute mapping have bit 7 set. */
+typedef enum sensors_subfeature_type {
+ SENSORS_SUBFEATURE_IN_INPUT = SENSORS_FEATURE_IN << 8,
+ SENSORS_SUBFEATURE_IN_MIN,
+ SENSORS_SUBFEATURE_IN_MAX,
+ SENSORS_SUBFEATURE_IN_LCRIT,
+ SENSORS_SUBFEATURE_IN_CRIT,
+ SENSORS_SUBFEATURE_IN_AVERAGE,
+ SENSORS_SUBFEATURE_IN_LOWEST,
+ SENSORS_SUBFEATURE_IN_HIGHEST,
+ SENSORS_SUBFEATURE_IN_ALARM = (SENSORS_FEATURE_IN << 8) | 0x80,
+ SENSORS_SUBFEATURE_IN_MIN_ALARM,
+ SENSORS_SUBFEATURE_IN_MAX_ALARM,
+ SENSORS_SUBFEATURE_IN_BEEP,
+ SENSORS_SUBFEATURE_IN_LCRIT_ALARM,
+ SENSORS_SUBFEATURE_IN_CRIT_ALARM,
+
+ SENSORS_SUBFEATURE_FAN_INPUT = SENSORS_FEATURE_FAN << 8,
+ SENSORS_SUBFEATURE_FAN_MIN,
+ SENSORS_SUBFEATURE_FAN_MAX,
+ SENSORS_SUBFEATURE_FAN_ALARM = (SENSORS_FEATURE_FAN << 8) | 0x80,
+ SENSORS_SUBFEATURE_FAN_FAULT,
+ SENSORS_SUBFEATURE_FAN_DIV,
+ SENSORS_SUBFEATURE_FAN_BEEP,
+ SENSORS_SUBFEATURE_FAN_PULSES,
+ SENSORS_SUBFEATURE_FAN_MIN_ALARM,
+ SENSORS_SUBFEATURE_FAN_MAX_ALARM,
+
+ SENSORS_SUBFEATURE_TEMP_INPUT = SENSORS_FEATURE_TEMP << 8,
+ SENSORS_SUBFEATURE_TEMP_MAX,
+ SENSORS_SUBFEATURE_TEMP_MAX_HYST,
+ SENSORS_SUBFEATURE_TEMP_MIN,
+ SENSORS_SUBFEATURE_TEMP_CRIT,
+ SENSORS_SUBFEATURE_TEMP_CRIT_HYST,
+ SENSORS_SUBFEATURE_TEMP_LCRIT,
+ SENSORS_SUBFEATURE_TEMP_EMERGENCY,
+ SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST,
+ SENSORS_SUBFEATURE_TEMP_LOWEST,
+ SENSORS_SUBFEATURE_TEMP_HIGHEST,
+ SENSORS_SUBFEATURE_TEMP_ALARM = (SENSORS_FEATURE_TEMP << 8) | 0x80,
+ SENSORS_SUBFEATURE_TEMP_MAX_ALARM,
+ SENSORS_SUBFEATURE_TEMP_MIN_ALARM,
+ SENSORS_SUBFEATURE_TEMP_CRIT_ALARM,
+ SENSORS_SUBFEATURE_TEMP_FAULT,
+ SENSORS_SUBFEATURE_TEMP_TYPE,
+ SENSORS_SUBFEATURE_TEMP_OFFSET,
+ SENSORS_SUBFEATURE_TEMP_BEEP,
+ SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM,
+ SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM,
+
+ SENSORS_SUBFEATURE_POWER_AVERAGE = SENSORS_FEATURE_POWER << 8,
+ SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST,
+ SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST,
+ SENSORS_SUBFEATURE_POWER_INPUT,
+ SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST,
+ SENSORS_SUBFEATURE_POWER_INPUT_LOWEST,
+ SENSORS_SUBFEATURE_POWER_CAP,
+ SENSORS_SUBFEATURE_POWER_CAP_HYST,
+ SENSORS_SUBFEATURE_POWER_MAX,
+ SENSORS_SUBFEATURE_POWER_CRIT,
+ SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL = (SENSORS_FEATURE_POWER << 8) | 0x80,
+ SENSORS_SUBFEATURE_POWER_ALARM,
+ SENSORS_SUBFEATURE_POWER_CAP_ALARM,
+ SENSORS_SUBFEATURE_POWER_MAX_ALARM,
+ SENSORS_SUBFEATURE_POWER_CRIT_ALARM,
+
+ SENSORS_SUBFEATURE_ENERGY_INPUT = SENSORS_FEATURE_ENERGY << 8,
+
+ SENSORS_SUBFEATURE_CURR_INPUT = SENSORS_FEATURE_CURR << 8,
+ SENSORS_SUBFEATURE_CURR_MIN,
+ SENSORS_SUBFEATURE_CURR_MAX,
+ SENSORS_SUBFEATURE_CURR_LCRIT,
+ SENSORS_SUBFEATURE_CURR_CRIT,
+ SENSORS_SUBFEATURE_CURR_AVERAGE,
+ SENSORS_SUBFEATURE_CURR_LOWEST,
+ SENSORS_SUBFEATURE_CURR_HIGHEST,
+ SENSORS_SUBFEATURE_CURR_ALARM = (SENSORS_FEATURE_CURR << 8) | 0x80,
+ SENSORS_SUBFEATURE_CURR_MIN_ALARM,
+ SENSORS_SUBFEATURE_CURR_MAX_ALARM,
+ SENSORS_SUBFEATURE_CURR_BEEP,
+ SENSORS_SUBFEATURE_CURR_LCRIT_ALARM,
+ SENSORS_SUBFEATURE_CURR_CRIT_ALARM,
+
+ SENSORS_SUBFEATURE_HUMIDITY_INPUT = SENSORS_FEATURE_HUMIDITY << 8,
+
+ SENSORS_SUBFEATURE_VID = SENSORS_FEATURE_VID << 8,
+
+ SENSORS_SUBFEATURE_INTRUSION_ALARM = SENSORS_FEATURE_INTRUSION << 8,
+ SENSORS_SUBFEATURE_INTRUSION_BEEP,
+
+ SENSORS_SUBFEATURE_BEEP_ENABLE = SENSORS_FEATURE_BEEP_ENABLE << 8,
+
+ SENSORS_SUBFEATURE_UNKNOWN = INT_MAX,
+} sensors_subfeature_type;
+
+/* Data about a single chip feature (or category leader) */
+struct sensors_feature {
+ char *name;
+ int number;
+ sensors_feature_type type;
+ /* Members below are for libsensors internal use only */
+ int first_subfeature;
+ int padding1;
+};
+
+/* Data about a single chip subfeature:
+ name is the string name used to refer to this subfeature (in config files)
+ number is the internal subfeature number, used in many functions to refer
+ to this subfeature
+ type is the subfeature type
+ mapping is the number of a main feature this subfeature belongs to
+ (for example subfeatures fan1_input, fan1_min, fan1_div and fan1_alarm
+ are mapped to main feature fan1)
+ flags is a bitfield, its value is a combination of SENSORS_MODE_R (readable),
+ SENSORS_MODE_W (writable) and SENSORS_COMPUTE_MAPPING (affected by the
+ computation rules of the main feature) */
+typedef struct sensors_subfeature {
+ char *name;
+ int number;
+ sensors_subfeature_type type;
+ int mapping;
+ unsigned int flags;
+} sensors_subfeature;
+
+/* This returns all main features of a specific chip. nr is an internally
+ used variable. Set it to zero to start at the begin of the list. If no
+ more features are found NULL is returned.
+ Do not try to change the returned structure; you will corrupt internal
+ data structures. */
+const sensors_feature *
+sensors_get_features(const sensors_chip_name *name, int *nr);
+
+/* This returns all subfeatures of a given main feature. nr is an internally
+ used variable. Set it to zero to start at the begin of the list. If no
+ more features are found NULL is returned.
+ Do not try to change the returned structure; you will corrupt internal
+ data structures. */
+const sensors_subfeature *
+sensors_get_all_subfeatures(const sensors_chip_name *name,
+ const sensors_feature *feature, int *nr);
+
+/* This returns the subfeature of the given type for a given main feature,
+ if it exists, NULL otherwise.
+ Do not try to change the returned structure; you will corrupt internal
+ data structures. */
+const sensors_subfeature *
+sensors_get_subfeature(const sensors_chip_name *name,
+ const sensors_feature *feature,
+ sensors_subfeature_type type);
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#endif /* def LIB_SENSORS_ERROR_H */
diff --git a/tools/gator/daemon/libsensors/sysfs.c b/tools/gator/daemon/libsensors/sysfs.c
new file mode 100644
index 0000000..2b494c9
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.c
@@ -0,0 +1,926 @@
+/*
+ sysfs.c - Part of libsensors, a library for reading Linux sensor data
+ Copyright (c) 2005 Mark M. Hoffman <mhoffman@lightlink.com>
+ Copyright (C) 2007-2010 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+/*** This file modified by ARM on Jan 23, 2013 to improve performance by substituting calls to fread() with calls to read() and to read non-scaled values. ***/
+
+/* this define needed for strndup() */
+#define _GNU_SOURCE
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <limits.h>
+#include <errno.h>
+#include <dirent.h>
+#include <fcntl.h>
+#include "data.h"
+#include "error.h"
+#include "access.h"
+#include "general.h"
+#include "sysfs.h"
+
+
+/****************************************************************************/
+
+#define ATTR_MAX 128
+#define SYSFS_MAGIC 0x62656572
+
+int sensors_sysfs_no_scaling;
+
+/*
+ * Read an attribute from sysfs
+ * Returns a pointer to a freshly allocated string; free it yourself.
+ * If the file doesn't exist or can't be read, NULL is returned.
+ */
+static char *sysfs_read_attr(const char *device, const char *attr)
+{
+ char path[NAME_MAX];
+ char buf[ATTR_MAX], *p;
+ FILE *f;
+
+ snprintf(path, NAME_MAX, "%s/%s", device, attr);
+
+ if (!(f = fopen(path, "r")))
+ return NULL;
+ p = fgets(buf, ATTR_MAX, f);
+ fclose(f);
+ if (!p)
+ return NULL;
+
+ /* Last byte is a '\n'; chop that off */
+ p = strndup(buf, strlen(buf) - 1);
+ if (!p)
+ sensors_fatal_error(__func__, "Out of memory");
+ return p;
+}
+
+/*
+ * Call an arbitrary function for each class device of the given class
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_classdev(const char *class_name,
+ int (*func)(const char *, const char *))
+{
+ char path[NAME_MAX];
+ int path_off, ret;
+ DIR *dir;
+ struct dirent *ent;
+
+ path_off = snprintf(path, NAME_MAX, "%s/class/%s",
+ sensors_sysfs_mount, class_name);
+ if (!(dir = opendir(path)))
+ return errno;
+
+ ret = 0;
+ while (!ret && (ent = readdir(dir))) {
+ if (ent->d_name[0] == '.') /* skip hidden entries */
+ continue;
+
+ snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+ ent->d_name);
+ ret = func(path, ent->d_name);
+ }
+
+ closedir(dir);
+ return ret;
+}
+
+/*
+ * Call an arbitrary function for each device of the given bus type
+ * Returns 0 on success (all calls returned 0), a positive errno for
+ * local errors, or a negative error value if any call fails.
+ */
+static int sysfs_foreach_busdev(const char *bus_type,
+ int (*func)(const char *, const char *))
+{
+ char path[NAME_MAX];
+ int path_off, ret;
+ DIR *dir;
+ struct dirent *ent;
+
+ path_off = snprintf(path, NAME_MAX, "%s/bus/%s/devices",
+ sensors_sysfs_mount, bus_type);
+ if (!(dir = opendir(path)))
+ return errno;
+
+ ret = 0;
+ while (!ret && (ent = readdir(dir))) {
+ if (ent->d_name[0] == '.') /* skip hidden entries */
+ continue;
+
+ snprintf(path + path_off, NAME_MAX - path_off, "/%s",
+ ent->d_name);
+ ret = func(path, ent->d_name);
+ }
+
+ closedir(dir);
+ return ret;
+}
+
+/****************************************************************************/
+
+char sensors_sysfs_mount[NAME_MAX];
+
+#define MAX_MAIN_SENSOR_TYPES (SENSORS_FEATURE_MAX_MAIN - SENSORS_FEATURE_IN)
+#define MAX_OTHER_SENSOR_TYPES (SENSORS_FEATURE_MAX_OTHER - SENSORS_FEATURE_VID)
+#define MAX_SENSORS_PER_TYPE 24
+/* max_subfeatures is now computed dynamically */
+#define FEATURE_SIZE (max_subfeatures * 2)
+#define FEATURE_TYPE_SIZE (MAX_SENSORS_PER_TYPE * FEATURE_SIZE)
+
+/*
+ * Room for all 7 main types (in, fan, temp, power, energy, current, humidity)
+ * and 2 other types (VID, intrusion) with all their subfeatures + misc features
+ */
+#define SUB_OFFSET_OTHER (MAX_MAIN_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define SUB_OFFSET_MISC (SUB_OFFSET_OTHER + \
+ MAX_OTHER_SENSOR_TYPES * FEATURE_TYPE_SIZE)
+#define ALL_POSSIBLE_SUBFEATURES (SUB_OFFSET_MISC + 1)
+
+static
+int get_type_scaling(sensors_subfeature_type type)
+{
+ /* Multipliers for subfeatures */
+ switch (type & 0xFF80) {
+ case SENSORS_SUBFEATURE_IN_INPUT:
+ case SENSORS_SUBFEATURE_TEMP_INPUT:
+ case SENSORS_SUBFEATURE_CURR_INPUT:
+ case SENSORS_SUBFEATURE_HUMIDITY_INPUT:
+ return 1000;
+ case SENSORS_SUBFEATURE_FAN_INPUT:
+ return 1;
+ case SENSORS_SUBFEATURE_POWER_AVERAGE:
+ case SENSORS_SUBFEATURE_ENERGY_INPUT:
+ return 1000000;
+ }
+
+ /* Multipliers for second class subfeatures
+ that need their own multiplier */
+ switch (type) {
+ case SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL:
+ case SENSORS_SUBFEATURE_VID:
+ case SENSORS_SUBFEATURE_TEMP_OFFSET:
+ return 1000;
+ default:
+ return 1;
+ }
+}
+
+static
+char *get_feature_name(sensors_feature_type ftype, char *sfname)
+{
+ char *name, *underscore;
+
+ switch (ftype) {
+ case SENSORS_FEATURE_IN:
+ case SENSORS_FEATURE_FAN:
+ case SENSORS_FEATURE_TEMP:
+ case SENSORS_FEATURE_POWER:
+ case SENSORS_FEATURE_ENERGY:
+ case SENSORS_FEATURE_CURR:
+ case SENSORS_FEATURE_HUMIDITY:
+ case SENSORS_FEATURE_INTRUSION:
+ underscore = strchr(sfname, '_');
+ name = strndup(sfname, underscore - sfname);
+ if (!name)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ break;
+ default:
+ name = strdup(sfname);
+ if (!name)
+ sensors_fatal_error(__func__, "Out of memory");
+ }
+
+ return name;
+}
+
+/* Static mappings for use by sensors_subfeature_get_type() */
+struct subfeature_type_match
+{
+ const char *name;
+ sensors_subfeature_type type;
+};
+
+struct feature_type_match
+{
+ const char *name;
+ const struct subfeature_type_match *submatches;
+};
+
+static const struct subfeature_type_match temp_matches[] = {
+ { "input", SENSORS_SUBFEATURE_TEMP_INPUT },
+ { "max", SENSORS_SUBFEATURE_TEMP_MAX },
+ { "max_hyst", SENSORS_SUBFEATURE_TEMP_MAX_HYST },
+ { "min", SENSORS_SUBFEATURE_TEMP_MIN },
+ { "crit", SENSORS_SUBFEATURE_TEMP_CRIT },
+ { "crit_hyst", SENSORS_SUBFEATURE_TEMP_CRIT_HYST },
+ { "lcrit", SENSORS_SUBFEATURE_TEMP_LCRIT },
+ { "emergency", SENSORS_SUBFEATURE_TEMP_EMERGENCY },
+ { "emergency_hyst", SENSORS_SUBFEATURE_TEMP_EMERGENCY_HYST },
+ { "lowest", SENSORS_SUBFEATURE_TEMP_LOWEST },
+ { "highest", SENSORS_SUBFEATURE_TEMP_HIGHEST },
+ { "alarm", SENSORS_SUBFEATURE_TEMP_ALARM },
+ { "min_alarm", SENSORS_SUBFEATURE_TEMP_MIN_ALARM },
+ { "max_alarm", SENSORS_SUBFEATURE_TEMP_MAX_ALARM },
+ { "crit_alarm", SENSORS_SUBFEATURE_TEMP_CRIT_ALARM },
+ { "emergency_alarm", SENSORS_SUBFEATURE_TEMP_EMERGENCY_ALARM },
+ { "lcrit_alarm", SENSORS_SUBFEATURE_TEMP_LCRIT_ALARM },
+ { "fault", SENSORS_SUBFEATURE_TEMP_FAULT },
+ { "type", SENSORS_SUBFEATURE_TEMP_TYPE },
+ { "offset", SENSORS_SUBFEATURE_TEMP_OFFSET },
+ { "beep", SENSORS_SUBFEATURE_TEMP_BEEP },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match in_matches[] = {
+ { "input", SENSORS_SUBFEATURE_IN_INPUT },
+ { "min", SENSORS_SUBFEATURE_IN_MIN },
+ { "max", SENSORS_SUBFEATURE_IN_MAX },
+ { "lcrit", SENSORS_SUBFEATURE_IN_LCRIT },
+ { "crit", SENSORS_SUBFEATURE_IN_CRIT },
+ { "average", SENSORS_SUBFEATURE_IN_AVERAGE },
+ { "lowest", SENSORS_SUBFEATURE_IN_LOWEST },
+ { "highest", SENSORS_SUBFEATURE_IN_HIGHEST },
+ { "alarm", SENSORS_SUBFEATURE_IN_ALARM },
+ { "min_alarm", SENSORS_SUBFEATURE_IN_MIN_ALARM },
+ { "max_alarm", SENSORS_SUBFEATURE_IN_MAX_ALARM },
+ { "lcrit_alarm", SENSORS_SUBFEATURE_IN_LCRIT_ALARM },
+ { "crit_alarm", SENSORS_SUBFEATURE_IN_CRIT_ALARM },
+ { "beep", SENSORS_SUBFEATURE_IN_BEEP },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match fan_matches[] = {
+ { "input", SENSORS_SUBFEATURE_FAN_INPUT },
+ { "min", SENSORS_SUBFEATURE_FAN_MIN },
+ { "max", SENSORS_SUBFEATURE_FAN_MAX },
+ { "div", SENSORS_SUBFEATURE_FAN_DIV },
+ { "pulses", SENSORS_SUBFEATURE_FAN_PULSES },
+ { "alarm", SENSORS_SUBFEATURE_FAN_ALARM },
+ { "min_alarm", SENSORS_SUBFEATURE_FAN_MIN_ALARM },
+ { "max_alarm", SENSORS_SUBFEATURE_FAN_MAX_ALARM },
+ { "fault", SENSORS_SUBFEATURE_FAN_FAULT },
+ { "beep", SENSORS_SUBFEATURE_FAN_BEEP },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match power_matches[] = {
+ { "average", SENSORS_SUBFEATURE_POWER_AVERAGE },
+ { "average_highest", SENSORS_SUBFEATURE_POWER_AVERAGE_HIGHEST },
+ { "average_lowest", SENSORS_SUBFEATURE_POWER_AVERAGE_LOWEST },
+ { "input", SENSORS_SUBFEATURE_POWER_INPUT },
+ { "input_highest", SENSORS_SUBFEATURE_POWER_INPUT_HIGHEST },
+ { "input_lowest", SENSORS_SUBFEATURE_POWER_INPUT_LOWEST },
+ { "cap", SENSORS_SUBFEATURE_POWER_CAP },
+ { "cap_hyst", SENSORS_SUBFEATURE_POWER_CAP_HYST },
+ { "cap_alarm", SENSORS_SUBFEATURE_POWER_CAP_ALARM },
+ { "alarm", SENSORS_SUBFEATURE_POWER_ALARM },
+ { "max", SENSORS_SUBFEATURE_POWER_MAX },
+ { "max_alarm", SENSORS_SUBFEATURE_POWER_MAX_ALARM },
+ { "crit", SENSORS_SUBFEATURE_POWER_CRIT },
+ { "crit_alarm", SENSORS_SUBFEATURE_POWER_CRIT_ALARM },
+ { "average_interval", SENSORS_SUBFEATURE_POWER_AVERAGE_INTERVAL },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match energy_matches[] = {
+ { "input", SENSORS_SUBFEATURE_ENERGY_INPUT },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match curr_matches[] = {
+ { "input", SENSORS_SUBFEATURE_CURR_INPUT },
+ { "min", SENSORS_SUBFEATURE_CURR_MIN },
+ { "max", SENSORS_SUBFEATURE_CURR_MAX },
+ { "lcrit", SENSORS_SUBFEATURE_CURR_LCRIT },
+ { "crit", SENSORS_SUBFEATURE_CURR_CRIT },
+ { "average", SENSORS_SUBFEATURE_CURR_AVERAGE },
+ { "lowest", SENSORS_SUBFEATURE_CURR_LOWEST },
+ { "highest", SENSORS_SUBFEATURE_CURR_HIGHEST },
+ { "alarm", SENSORS_SUBFEATURE_CURR_ALARM },
+ { "min_alarm", SENSORS_SUBFEATURE_CURR_MIN_ALARM },
+ { "max_alarm", SENSORS_SUBFEATURE_CURR_MAX_ALARM },
+ { "lcrit_alarm", SENSORS_SUBFEATURE_CURR_LCRIT_ALARM },
+ { "crit_alarm", SENSORS_SUBFEATURE_CURR_CRIT_ALARM },
+ { "beep", SENSORS_SUBFEATURE_CURR_BEEP },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match humidity_matches[] = {
+ { "input", SENSORS_SUBFEATURE_HUMIDITY_INPUT },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match cpu_matches[] = {
+ { "vid", SENSORS_SUBFEATURE_VID },
+ { NULL, 0 }
+};
+
+static const struct subfeature_type_match intrusion_matches[] = {
+ { "alarm", SENSORS_SUBFEATURE_INTRUSION_ALARM },
+ { "beep", SENSORS_SUBFEATURE_INTRUSION_BEEP },
+ { NULL, 0 }
+};
+static struct feature_type_match matches[] = {
+ { "temp%d%c", temp_matches },
+ { "in%d%c", in_matches },
+ { "fan%d%c", fan_matches },
+ { "cpu%d%c", cpu_matches },
+ { "power%d%c", power_matches },
+ { "curr%d%c", curr_matches },
+ { "energy%d%c", energy_matches },
+ { "intrusion%d%c", intrusion_matches },
+ { "humidity%d%c", humidity_matches },
+};
+
+/* Return the subfeature type and channel number based on the subfeature
+ name */
+static
+sensors_subfeature_type sensors_subfeature_get_type(const char *name, int *nr)
+{
+ char c;
+ int i, count;
+ const struct subfeature_type_match *submatches;
+
+ /* Special case */
+ if (!strcmp(name, "beep_enable")) {
+ *nr = 0;
+ return SENSORS_SUBFEATURE_BEEP_ENABLE;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(matches); i++)
+ if ((count = sscanf(name, matches[i].name, nr, &c)))
+ break;
+
+ if (i == ARRAY_SIZE(matches) || count != 2 || c != '_')
+ return SENSORS_SUBFEATURE_UNKNOWN; /* no match */
+
+ submatches = matches[i].submatches;
+ name = strchr(name + 3, '_') + 1;
+ for (i = 0; submatches[i].name != NULL; i++)
+ if (!strcmp(name, submatches[i].name))
+ return submatches[i].type;
+
+ return SENSORS_SUBFEATURE_UNKNOWN;
+}
+
+static int sensors_compute_max(void)
+{
+ int i, j, max, offset;
+ const struct subfeature_type_match *submatches;
+ sensors_feature_type ftype;
+
+ max = 0;
+ for (i = 0; i < ARRAY_SIZE(matches); i++) {
+ submatches = matches[i].submatches;
+ for (j = 0; submatches[j].name != NULL; j++) {
+ ftype = submatches[j].type >> 8;
+
+ if (ftype < SENSORS_FEATURE_VID) {
+ offset = submatches[j].type & 0x7F;
+ if (offset >= max)
+ max = offset + 1;
+ } else {
+ offset = submatches[j].type & 0xFF;
+ if (offset >= max * 2)
+ max = ((offset + 1) + 1) / 2;
+ }
+ }
+ }
+
+ return max;
+}
+
+static int sensors_get_attr_mode(const char *device, const char *attr)
+{
+ char path[NAME_MAX];
+ struct stat st;
+ int mode = 0;
+
+ snprintf(path, NAME_MAX, "%s/%s", device, attr);
+ if (!stat(path, &st)) {
+ if (st.st_mode & S_IRUSR)
+ mode |= SENSORS_MODE_R;
+ if (st.st_mode & S_IWUSR)
+ mode |= SENSORS_MODE_W;
+ }
+ return mode;
+}
+
+static int sensors_read_dynamic_chip(sensors_chip_features *chip,
+ const char *dev_path)
+{
+ int i, fnum = 0, sfnum = 0, prev_slot;
+ static int max_subfeatures;
+ DIR *dir;
+ struct dirent *ent;
+ sensors_subfeature *all_subfeatures;
+ sensors_subfeature *dyn_subfeatures;
+ sensors_feature *dyn_features;
+ sensors_feature_type ftype;
+ sensors_subfeature_type sftype;
+
+ if (!(dir = opendir(dev_path)))
+ return -errno;
+
+ /* Dynamically figure out the max number of subfeatures */
+ if (!max_subfeatures)
+ max_subfeatures = sensors_compute_max();
+
+ /* We use a large sparse table at first to store all found
+ subfeatures, so that we can store them sorted at type and index
+ and then later create a dense sorted table. */
+ all_subfeatures = calloc(ALL_POSSIBLE_SUBFEATURES,
+ sizeof(sensors_subfeature));
+ if (!all_subfeatures)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ while ((ent = readdir(dir))) {
+ char *name;
+ int nr;
+
+ /* Skip directories and symlinks */
+ if (ent->d_type != DT_REG)
+ continue;
+
+ name = ent->d_name;
+
+ sftype = sensors_subfeature_get_type(name, &nr);
+ if (sftype == SENSORS_SUBFEATURE_UNKNOWN)
+ continue;
+ ftype = sftype >> 8;
+
+ /* Adjust the channel number */
+ switch (ftype) {
+ case SENSORS_FEATURE_FAN:
+ case SENSORS_FEATURE_TEMP:
+ case SENSORS_FEATURE_POWER:
+ case SENSORS_FEATURE_ENERGY:
+ case SENSORS_FEATURE_CURR:
+ case SENSORS_FEATURE_HUMIDITY:
+ nr--;
+ break;
+ default:
+ break;
+ }
+
+ if (nr < 0 || nr >= MAX_SENSORS_PER_TYPE) {
+ /* More sensors of one type than MAX_SENSORS_PER_TYPE,
+ we have to ignore it */
+#ifdef DEBUG
+ sensors_fatal_error(__func__,
+ "Increase MAX_SENSORS_PER_TYPE!");
+#endif
+ continue;
+ }
+
+ /* "calculate" a place to store the subfeature in our sparse,
+ sorted table */
+ switch (ftype) {
+ case SENSORS_FEATURE_VID:
+ case SENSORS_FEATURE_INTRUSION:
+ i = SUB_OFFSET_OTHER +
+ (ftype - SENSORS_FEATURE_VID) * FEATURE_TYPE_SIZE +
+ nr * FEATURE_SIZE + (sftype & 0xFF);
+ break;
+ case SENSORS_FEATURE_BEEP_ENABLE:
+ i = SUB_OFFSET_MISC +
+ (ftype - SENSORS_FEATURE_BEEP_ENABLE);
+ break;
+ default:
+ i = ftype * FEATURE_TYPE_SIZE +
+ nr * FEATURE_SIZE +
+ ((sftype & 0x80) >> 7) * max_subfeatures +
+ (sftype & 0x7F);
+ }
+
+ if (all_subfeatures[i].name) {
+#ifdef DEBUG
+ sensors_fatal_error(__func__, "Duplicate subfeature");
+#endif
+ continue;
+ }
+
+ /* fill in the subfeature members */
+ all_subfeatures[i].type = sftype;
+ all_subfeatures[i].name = strdup(name);
+ if (!all_subfeatures[i].name)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ /* Other and misc subfeatures are never scaled */
+ if (sftype < SENSORS_SUBFEATURE_VID && !(sftype & 0x80))
+ all_subfeatures[i].flags |= SENSORS_COMPUTE_MAPPING;
+ all_subfeatures[i].flags |= sensors_get_attr_mode(dev_path, name);
+
+ sfnum++;
+ }
+ closedir(dir);
+
+ if (!sfnum) { /* No subfeature */
+ chip->subfeature = NULL;
+ goto exit_free;
+ }
+
+ /* How many main features? */
+ prev_slot = -1;
+ for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+ if (!all_subfeatures[i].name)
+ continue;
+
+ if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+ fnum++;
+ prev_slot = i / FEATURE_SIZE;
+ }
+ }
+
+ dyn_subfeatures = calloc(sfnum, sizeof(sensors_subfeature));
+ dyn_features = calloc(fnum, sizeof(sensors_feature));
+ if (!dyn_subfeatures || !dyn_features)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ /* Copy from the sparse array to the compact array */
+ sfnum = 0;
+ fnum = -1;
+ prev_slot = -1;
+ for (i = 0; i < ALL_POSSIBLE_SUBFEATURES; i++) {
+ if (!all_subfeatures[i].name)
+ continue;
+
+ /* New main feature? */
+ if (i >= SUB_OFFSET_MISC || i / FEATURE_SIZE != prev_slot) {
+ ftype = all_subfeatures[i].type >> 8;
+ fnum++;
+ prev_slot = i / FEATURE_SIZE;
+
+ dyn_features[fnum].name = get_feature_name(ftype,
+ all_subfeatures[i].name);
+ dyn_features[fnum].number = fnum;
+ dyn_features[fnum].first_subfeature = sfnum;
+ dyn_features[fnum].type = ftype;
+ }
+
+ dyn_subfeatures[sfnum] = all_subfeatures[i];
+ dyn_subfeatures[sfnum].number = sfnum;
+ /* Back to the feature */
+ dyn_subfeatures[sfnum].mapping = fnum;
+
+ sfnum++;
+ }
+
+ chip->subfeature = dyn_subfeatures;
+ chip->subfeature_count = sfnum;
+ chip->feature = dyn_features;
+ chip->feature_count = ++fnum;
+
+exit_free:
+ free(all_subfeatures);
+ return 0;
+}
+
+/* returns !0 if sysfs filesystem was found, 0 otherwise */
+int sensors_init_sysfs(void)
+{
+ struct statfs statfsbuf;
+
+ snprintf(sensors_sysfs_mount, NAME_MAX, "%s", "/sys");
+ if (statfs(sensors_sysfs_mount, &statfsbuf) < 0
+ || statfsbuf.f_type != SYSFS_MAGIC)
+ return 0;
+
+ return 1;
+}
+
+/* returns: number of devices added (0 or 1) if successful, <0 otherwise */
+static int sensors_read_one_sysfs_chip(const char *dev_path,
+ const char *dev_name,
+ const char *hwmon_path)
+{
+ int domain, bus, slot, fn, vendor, product, id;
+ int err = -SENSORS_ERR_KERNEL;
+ char *bus_attr;
+ char bus_path[NAME_MAX];
+ char linkpath[NAME_MAX];
+ char subsys_path[NAME_MAX], *subsys;
+ int sub_len;
+ sensors_chip_features entry;
+
+ /* ignore any device without name attribute */
+ if (!(entry.chip.prefix = sysfs_read_attr(hwmon_path, "name")))
+ return 0;
+
+ entry.chip.path = strdup(hwmon_path);
+ if (!entry.chip.path)
+ sensors_fatal_error(__func__, "Out of memory");
+
+ if (dev_path == NULL) {
+ /* Virtual device */
+ entry.chip.bus.type = SENSORS_BUS_TYPE_VIRTUAL;
+ entry.chip.bus.nr = 0;
+ /* For now we assume that virtual devices are unique */
+ entry.chip.addr = 0;
+ goto done;
+ }
+
+ /* Find bus type */
+ snprintf(linkpath, NAME_MAX, "%s/subsystem", dev_path);
+ sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+ if (sub_len < 0 && errno == ENOENT) {
+ /* Fallback to "bus" link for kernels <= 2.6.17 */
+ snprintf(linkpath, NAME_MAX, "%s/bus", dev_path);
+ sub_len = readlink(linkpath, subsys_path, NAME_MAX - 1);
+ }
+ if (sub_len < 0) {
+ /* Older kernels (<= 2.6.11) have neither the subsystem
+ symlink nor the bus symlink */
+ if (errno == ENOENT)
+ subsys = NULL;
+ else
+ goto exit_free;
+ } else {
+ subsys_path[sub_len] = '\0';
+ subsys = strrchr(subsys_path, '/') + 1;
+ }
+
+ if ((!subsys || !strcmp(subsys, "i2c")) &&
+ sscanf(dev_name, "%hd-%x", &entry.chip.bus.nr,
+ &entry.chip.addr) == 2) {
+ /* find out if legacy ISA or not */
+ if (entry.chip.bus.nr == 9191) {
+ entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+ entry.chip.bus.nr = 0;
+ } else {
+ entry.chip.bus.type = SENSORS_BUS_TYPE_I2C;
+ snprintf(bus_path, sizeof(bus_path),
+ "%s/class/i2c-adapter/i2c-%d/device",
+ sensors_sysfs_mount, entry.chip.bus.nr);
+
+ if ((bus_attr = sysfs_read_attr(bus_path, "name"))) {
+ if (!strncmp(bus_attr, "ISA ", 4)) {
+ entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+ entry.chip.bus.nr = 0;
+ }
+
+ free(bus_attr);
+ }
+ }
+ } else
+ if ((!subsys || !strcmp(subsys, "spi")) &&
+ sscanf(dev_name, "spi%hd.%d", &entry.chip.bus.nr,
+ &entry.chip.addr) == 2) {
+ /* SPI */
+ entry.chip.bus.type = SENSORS_BUS_TYPE_SPI;
+ } else
+ if ((!subsys || !strcmp(subsys, "pci")) &&
+ sscanf(dev_name, "%x:%x:%x.%x", &domain, &bus, &slot, &fn) == 4) {
+ /* PCI */
+ entry.chip.addr = (domain << 16) + (bus << 8) + (slot << 3) + fn;
+ entry.chip.bus.type = SENSORS_BUS_TYPE_PCI;
+ entry.chip.bus.nr = 0;
+ } else
+ if ((!subsys || !strcmp(subsys, "platform") ||
+ !strcmp(subsys, "of_platform"))) {
+ /* must be new ISA (platform driver) */
+ if (sscanf(dev_name, "%*[a-z0-9_].%d", &entry.chip.addr) != 1)
+ entry.chip.addr = 0;
+ entry.chip.bus.type = SENSORS_BUS_TYPE_ISA;
+ entry.chip.bus.nr = 0;
+ } else if (subsys && !strcmp(subsys, "acpi")) {
+ entry.chip.bus.type = SENSORS_BUS_TYPE_ACPI;
+ /* For now we assume that acpi devices are unique */
+ entry.chip.bus.nr = 0;
+ entry.chip.addr = 0;
+ } else
+ if (subsys && !strcmp(subsys, "hid") &&
+ sscanf(dev_name, "%x:%x:%x.%x", &bus, &vendor, &product, &id) == 4) {
+ entry.chip.bus.type = SENSORS_BUS_TYPE_HID;
+ /* As of kernel 2.6.32, the hid device names don't look good */
+ entry.chip.bus.nr = bus;
+ entry.chip.addr = id;
+ } else {
+ /* Ignore unknown device */
+ err = 0;
+ goto exit_free;
+ }
+
+done:
+ if (sensors_read_dynamic_chip(&entry, hwmon_path) < 0)
+ goto exit_free;
+ if (!entry.subfeature) { /* No subfeature, discard chip */
+ err = 0;
+ goto exit_free;
+ }
+ sensors_add_proc_chips(&entry);
+
+ return 1;
+
+exit_free:
+ free(entry.chip.prefix);
+ free(entry.chip.path);
+ return err;
+}
+
+static int sensors_add_hwmon_device_compat(const char *path,
+ const char *dev_name)
+{
+ int err;
+
+ err = sensors_read_one_sysfs_chip(path, dev_name, path);
+ if (err < 0)
+ return err;
+ return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_read_sysfs_chips_compat(void)
+{
+ int ret;
+
+ ret = sysfs_foreach_busdev("i2c", sensors_add_hwmon_device_compat);
+ if (ret && ret != ENOENT)
+ return -SENSORS_ERR_KERNEL;
+
+ return 0;
+}
+
+static int sensors_add_hwmon_device(const char *path, const char *classdev)
+{
+ char linkpath[NAME_MAX];
+ char device[NAME_MAX], *device_p;
+ int dev_len, err;
+ (void)classdev; /* hide warning */
+
+ snprintf(linkpath, NAME_MAX, "%s/device", path);
+ dev_len = readlink(linkpath, device, NAME_MAX - 1);
+ if (dev_len < 0) {
+ /* No device link? Treat as virtual */
+ err = sensors_read_one_sysfs_chip(NULL, NULL, path);
+ } else {
+ device[dev_len] = '\0';
+ device_p = strrchr(device, '/') + 1;
+
+ /* The attributes we want might be those of the hwmon class
+ device, or those of the device itself. */
+ err = sensors_read_one_sysfs_chip(linkpath, device_p, path);
+ if (err == 0)
+ err = sensors_read_one_sysfs_chip(linkpath, device_p,
+ linkpath);
+ }
+ if (err < 0)
+ return err;
+ return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_chips(void)
+{
+ int ret;
+
+ ret = sysfs_foreach_classdev("hwmon", sensors_add_hwmon_device);
+ if (ret == ENOENT) {
+ /* compatibility function for kernel 2.6.n where n <= 13 */
+ return sensors_read_sysfs_chips_compat();
+ }
+
+ if (ret > 0)
+ ret = -SENSORS_ERR_KERNEL;
+ return ret;
+}
+
+/* returns 0 if successful, !0 otherwise */
+static int sensors_add_i2c_bus(const char *path, const char *classdev)
+{
+ sensors_bus entry;
+
+ if (sscanf(classdev, "i2c-%hd", &entry.bus.nr) != 1 ||
+ entry.bus.nr == 9191) /* legacy ISA */
+ return 0;
+ entry.bus.type = SENSORS_BUS_TYPE_I2C;
+
+ /* Get the adapter name from the classdev "name" attribute
+ * (Linux 2.6.20 and later). If it fails, fall back to
+ * the device "name" attribute (for older kernels). */
+ entry.adapter = sysfs_read_attr(path, "name");
+ if (!entry.adapter)
+ entry.adapter = sysfs_read_attr(path, "device/name");
+ if (entry.adapter)
+ sensors_add_proc_bus(&entry);
+
+ return 0;
+}
+
+/* returns 0 if successful, !0 otherwise */
+int sensors_read_sysfs_bus(void)
+{
+ int ret;
+
+ ret = sysfs_foreach_classdev("i2c-adapter", sensors_add_i2c_bus);
+ if (ret == ENOENT)
+ ret = sysfs_foreach_busdev("i2c", sensors_add_i2c_bus);
+ if (ret && ret != ENOENT)
+ return -SENSORS_ERR_KERNEL;
+
+ return 0;
+}
+
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+ const sensors_subfeature *subfeature,
+ double *value)
+{
+ char n[NAME_MAX];
+ int f;
+
+ snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+ if ((f = open(n, O_RDONLY)) != -1) {
+ int res, err = 0;
+ char buf[512];
+ int count;
+
+ errno = 0;
+ if ((count = read(f, buf, sizeof(buf) - 1)) == -1) {
+ if (errno == EIO)
+ err = -SENSORS_ERR_IO;
+ else
+ err = -SENSORS_ERR_ACCESS_R;
+ } else {
+ buf[count] = '\0';
+ errno = 0;
+ res = sscanf(buf, "%lf", value);
+ if (res == EOF && errno == EIO)
+ err = -SENSORS_ERR_IO;
+ else if (res != 1)
+ err = -SENSORS_ERR_ACCESS_R;
+ }
+ res = close(f);
+ if (err)
+ return err;
+
+ if (res != 0) {
+ if (errno == EIO)
+ return -SENSORS_ERR_IO;
+ else
+ return -SENSORS_ERR_ACCESS_R;
+ }
+ if (!sensors_sysfs_no_scaling)
+ *value /= get_type_scaling(subfeature->type);
+ } else
+ return -SENSORS_ERR_KERNEL;
+
+ return 0;
+}
+
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+ const sensors_subfeature *subfeature,
+ double value)
+{
+ char n[NAME_MAX];
+ FILE *f;
+
+ snprintf(n, NAME_MAX, "%s/%s", name->path, subfeature->name);
+ if ((f = fopen(n, "w"))) {
+ int res, err = 0;
+
+ if (!sensors_sysfs_no_scaling)
+ value *= get_type_scaling(subfeature->type);
+ res = fprintf(f, "%d", (int) value);
+ if (res == -EIO)
+ err = -SENSORS_ERR_IO;
+ else if (res < 0)
+ err = -SENSORS_ERR_ACCESS_W;
+ res = fclose(f);
+ if (err)
+ return err;
+
+ if (res == EOF) {
+ if (errno == EIO)
+ return -SENSORS_ERR_IO;
+ else
+ return -SENSORS_ERR_ACCESS_W;
+ }
+ } else
+ return -SENSORS_ERR_KERNEL;
+
+ return 0;
+}
diff --git a/tools/gator/daemon/libsensors/sysfs.h b/tools/gator/daemon/libsensors/sysfs.h
new file mode 100644
index 0000000..38584af
--- /dev/null
+++ b/tools/gator/daemon/libsensors/sysfs.h
@@ -0,0 +1,43 @@
+/*
+ sysfs.h - part of libsensors, a library for reading Linux sensor data
+ Copyright (C) Mark M. Hoffman <mhoffman@lightlink.com>
+ Copyright (C) 2007 Jean Delvare <khali@linux-fr.org>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Lesser General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ MA 02110-1301 USA.
+*/
+
+#ifndef SENSORS_LIB_SYSFS_H
+#define SENSORS_LIB_SYSFS_H
+
+extern char sensors_sysfs_mount[];
+
+int sensors_init_sysfs(void);
+
+int sensors_read_sysfs_chips(void);
+
+int sensors_read_sysfs_bus(void);
+
+/* Read a value out of a sysfs attribute file */
+int sensors_read_sysfs_attr(const sensors_chip_name *name,
+ const sensors_subfeature *subfeature,
+ double *value);
+
+/* Write a value to a sysfs attribute file */
+int sensors_write_sysfs_attr(const sensors_chip_name *name,
+ const sensors_subfeature *subfeature,
+ double value);
+
+#endif /* !SENSORS_LIB_SYSFS_H */
diff --git a/tools/gator/daemon/libsensors/version.h b/tools/gator/daemon/libsensors/version.h
new file mode 100644
index 0000000..76ceb08
--- /dev/null
+++ b/tools/gator/daemon/libsensors/version.h
@@ -0,0 +1 @@
+#define LM_VERSION "3.3.2"
diff --git a/tools/gator/daemon/main.cpp b/tools/gator/daemon/main.cpp
new file mode 100644
index 0000000..c68a892
--- /dev/null
+++ b/tools/gator/daemon/main.cpp
@@ -0,0 +1,624 @@
+/**
+ * Copyright (C) ARM Limited 2010-2015. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <arpa/inet.h>
+#include <fcntl.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "AnnotateListener.h"
+#include "CCNDriver.h"
+#include "Child.h"
+#include "EventsXML.h"
+#include "Logging.h"
+#include "Monitor.h"
+#include "OlySocket.h"
+#include "OlyUtility.h"
+#include "SessionData.h"
+#include "Setup.h"
+
+extern Child* child;
+static int shutdownFilesystem();
+static pthread_mutex_t numSessions_mutex;
+static OlyServerSocket* sock = NULL;
+static Monitor monitor;
+static int numSessions = 0;
+static bool driverRunningAtStart = false;
+static bool driverMountedAtStart = false;
+
+struct cmdline_t {
+ char *module;
+ int port;
+ bool update;
+};
+
+#define DEFAULT_PORT 8080
+
+void cleanUp() {
+ if (shutdownFilesystem() == -1) {
+ logg->logMessage("Error shutting down gator filesystem");
+ }
+ delete sock;
+ delete util;
+ delete logg;
+}
+
+// CTRL C Signal Handler
+static void handler(int signum) {
+ logg->logMessage("Received signal %d, gator daemon exiting", signum);
+
+ // Case 1: both child and parent receive the signal
+ if (numSessions > 0) {
+ // Arbitrary sleep of 1 second to give time for the child to exit;
+ // if something bad happens, continue the shutdown process regardless
+ sleep(1);
+ }
+
+ // Case 2: only the parent received the signal
+ if (numSessions > 0) {
+ // Kill child threads - the first signal exits gracefully
+ logg->logMessage("Killing process group as %d child was running when signal was received", numSessions);
+ kill(0, SIGINT);
+
+ // Give time for the child to exit
+ sleep(1);
+
+ if (numSessions > 0) {
+ // The second signal force kills the child
+ logg->logMessage("Force kill the child");
+ kill(0, SIGINT);
+ // Again, sleep for 1 second
+ sleep(1);
+
+ if (numSessions > 0) {
+ // Something bad has really happened; the child is not exiting and therefore may hold the /dev/gator resource open
+ printf("Unable to kill the gatord child process, thus gator.ko may still be loaded.\n");
+ }
+ }
+ }
+
+ cleanUp();
+ exit(0);
+}
+
+// Child exit Signal Handler
+static void child_exit(int) {
+ int status;
+ int pid = wait(&status);
+ if (pid != -1) {
+ pthread_mutex_lock(&numSessions_mutex);
+ numSessions--;
+ pthread_mutex_unlock(&numSessions_mutex);
+ logg->logMessage("Child process %d exited with status %d", pid, status);
+ }
+}
+
+static const int UDP_REQ_PORT = 30001;
+
+typedef struct {
+ char rviHeader[8];
+ uint32_t messageID;
+ uint8_t ethernetAddress[8];
+ uint32_t ethernetType;
+ uint32_t dhcp;
+ char dhcpName[40];
+ uint32_t ipAddress;
+ uint32_t defaultGateway;
+ uint32_t subnetMask;
+ uint32_t activeConnections;
+} RVIConfigureInfo;
+
+static const char DST_REQ[] = { 'D', 'S', 'T', '_', 'R', 'E', 'Q', ' ', 0, 0, 0, 0x64 };
+
+class UdpListener {
+public:
+ UdpListener() : mDstAns(), mReq(-1) {}
+
+ void setup(int port) {
+ mReq = udpPort(UDP_REQ_PORT);
+
+ // Format the answer buffer
+ memset(&mDstAns, 0, sizeof(mDstAns));
+ memcpy(mDstAns.rviHeader, "STR_ANS ", sizeof(mDstAns.rviHeader));
+ if (gethostname(mDstAns.dhcpName, sizeof(mDstAns.dhcpName) - 1) != 0) {
+ logg->logError("gethostname failed");
+ handleException();
+ }
+ // Subvert the defaultGateway field for the port number
+ if (port != DEFAULT_PORT) {
+ mDstAns.defaultGateway = port;
+ }
+ // Subvert the subnetMask field for the protocol version
+ mDstAns.subnetMask = PROTOCOL_VERSION;
+ }
+
+ int getReq() const {
+ return mReq;
+ }
+
+ void handle() {
+ char buf[128];
+ struct sockaddr_in6 sockaddr;
+ socklen_t addrlen;
+ int read;
+ addrlen = sizeof(sockaddr);
+ read = recvfrom(mReq, &buf, sizeof(buf), 0, (struct sockaddr *)&sockaddr, &addrlen);
+ if (read < 0) {
+ logg->logError("recvfrom failed");
+ handleException();
+ } else if ((read == 12) && (memcmp(buf, DST_REQ, sizeof(DST_REQ)) == 0)) {
+ // Don't care if sendto fails - gatord shouldn't exit because of it and Streamline will retry
+ sendto(mReq, &mDstAns, sizeof(mDstAns), 0, (struct sockaddr *)&sockaddr, addrlen);
+ }
+ }
+
+ void close() {
+ ::close(mReq);
+ }
+
+private:
+ int udpPort(int port) {
+ int s;
+ struct sockaddr_in6 sockaddr;
+ int on;
+ int family = AF_INET6;
+
+ s = socket_cloexec(AF_INET6, SOCK_DGRAM, IPPROTO_UDP);
+ if (s == -1) {
+ family = AF_INET;
+ s = socket_cloexec(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+ if (s == -1) {
+ logg->logError("socket failed");
+ handleException();
+ }
+ }
+
+ on = 1;
+ if (setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (const char*)&on, sizeof(on)) != 0) {
+ logg->logError("setsockopt REUSEADDR failed");
+ handleException();
+ }
+
+ // Listen on both IPv4 and IPv6
+ on = 0;
+ if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, (const char*)&on, sizeof(on)) != 0) {
+ logg->logMessage("setsockopt IPV6_V6ONLY failed");
+ }
+
+ memset((void*)&sockaddr, 0, sizeof(sockaddr));
+ sockaddr.sin6_family = family;
+ sockaddr.sin6_port = htons(port);
+ sockaddr.sin6_addr = in6addr_any;
+ if (bind(s, (struct sockaddr *)&sockaddr, sizeof(sockaddr)) < 0) {
+ logg->logError("socket failed");
+ handleException();
+ }
+
+ return s;
+ }
+
+ RVIConfigureInfo mDstAns;
+ int mReq;
+};
+
+static UdpListener udpListener;
+
+// retval: -1 = failure; 0 = was already mounted; 1 = successfully mounted
+static int mountGatorFS() {
+ // If already mounted,
+ if (access("/dev/gator/buffer", F_OK) == 0) {
+ return 0;
+ }
+
+ // else, mount the filesystem
+ mkdir("/dev/gator", S_IRWXU | S_IRWXG | S_IROTH | S_IXOTH);
+ if (mount("nodev", "/dev/gator", "gatorfs", 0, NULL) != 0) {
+ return -1;
+ } else {
+ return 1;
+ }
+}
+
+static bool init_module (const char * const location) {
+ bool ret(false);
+ const int fd = open(location, O_RDONLY | O_CLOEXEC);
+ if (fd >= 0) {
+ struct stat st;
+ if (fstat(fd, &st) == 0) {
+ void * const p = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ if (p != MAP_FAILED) {
+ if (syscall(__NR_init_module, p, (unsigned long)st.st_size, "") == 0) {
+ ret = true;
+ }
+ munmap(p, st.st_size);
+ }
+ }
+ close(fd);
+ }
+
+ return ret;
+}
+
+static bool setupFilesystem(char* module) {
+ if (module) {
+ // unmount and rmmod if the module was specified on the commandline, i.e. ensure that the specified module is indeed running
+ shutdownFilesystem();
+
+ // if still mounted
+ if (access("/dev/gator/buffer", F_OK) == 0) {
+ logg->logError("Unable to remove the running gator.ko. Manually remove the module or use the running module by not specifying one on the commandline");
+ handleException();
+ }
+ }
+
+ const int retval = mountGatorFS();
+ if (retval == 1) {
+ logg->logMessage("Driver already running at startup");
+ driverRunningAtStart = true;
+ } else if (retval == 0) {
+ logg->logMessage("Driver already mounted at startup");
+ driverRunningAtStart = driverMountedAtStart = true;
+ } else {
+ char command[256]; // arbitrarily large amount
+ char location[256]; // arbitrarily large amount
+
+ if (module) {
+ strncpy(location, module, sizeof(location));
+ } else {
+ // Is the driver co-located in the same directory?
+ if (util->getApplicationFullPath(location, sizeof(location)) != 0) { // allow some buffer space
+ logg->logMessage("Unable to determine the full path of gatord, the cwd will be used");
+ }
+ strncat(location, "gator.ko", sizeof(location) - strlen(location) - 1);
+ }
+
+ if (access(location, F_OK) == -1) {
+ if (module == NULL) {
+ // The gator kernel is not already loaded and unable to locate gator.ko in the default location
+ return false;
+ } else {
+ // gator location specified on the command line but it was not found
+ logg->logError("gator module not found at %s", location);
+ handleException();
+ }
+ }
+
+ // Load driver
+ bool success = init_module(location);
+ if (!success) {
+ logg->logMessage("init_module failed, trying insmod");
+ snprintf(command, sizeof(command), "insmod %s >/dev/null 2>&1", location);
+ if (system(command) != 0) {
+ logg->logMessage("Unable to load gator.ko driver with command: %s", command);
+ logg->logError("Unable to load (insmod) gator.ko driver:\n >>> gator.ko must be built against the current kernel version & configuration\n >>> See dmesg for more details");
+ handleException();
+ }
+ }
+
+ if (mountGatorFS() == -1) {
+ logg->logError("Unable to mount the gator filesystem needed for profiling.");
+ handleException();
+ }
+ }
+
+ return true;
+}
+
+static int shutdownFilesystem() {
+ if (driverMountedAtStart == false) {
+ umount("/dev/gator");
+ }
+ if (driverRunningAtStart == false) {
+ if (syscall(__NR_delete_module, "gator", O_NONBLOCK) != 0) {
+ logg->logMessage("delete_module failed, trying rmmod");
+ if (system("rmmod gator >/dev/null 2>&1") != 0) {
+ return -1;
+ }
+ }
+ }
+
+ return 0; // success
+}
+
+static const char OPTSTRING[] = "hvVudap:s:c:e:E:m:o:";
+
+static bool hasDebugFlag(int argc, char** argv) {
+ int c;
+
+ optind = 1;
+ while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+ if (c == 'd') {
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static struct cmdline_t parseCommandLine(int argc, char** argv) {
+ struct cmdline_t cmdline;
+ cmdline.port = DEFAULT_PORT;
+ cmdline.module = NULL;
+ cmdline.update = false;
+ char version_string[256]; // arbitrary length to hold the version information
+ int c;
+
+ // build the version string
+ if (PROTOCOL_VERSION < PROTOCOL_DEV) {
+ snprintf(version_string, sizeof(version_string), "Streamline gatord version %d (DS-5 v5.%d)", PROTOCOL_VERSION, PROTOCOL_VERSION);
+ } else {
+ snprintf(version_string, sizeof(version_string), "Streamline gatord development version %d", PROTOCOL_VERSION);
+ }
+
+ optind = 1;
+ while ((c = getopt(argc, argv, OPTSTRING)) != -1) {
+ switch (c) {
+ case 'c':
+ gSessionData->mConfigurationXMLPath = optarg;
+ break;
+ case 'd':
+ // Already handled
+ break;
+ case 'e':
+ gSessionData->mEventsXMLPath = optarg;
+ break;
+ case 'E':
+ gSessionData->mEventsXMLAppend = optarg;
+ break;
+ case 'm':
+ cmdline.module = optarg;
+ break;
+ case 'p':
+ cmdline.port = strtol(optarg, NULL, 10);
+ if ((cmdline.port == 8082) || (cmdline.port == 8083)) {
+ logg->logError("Gator can't use port %i, as it already uses ports 8082 and 8083 for annotations. Please select a different port.", cmdline.port);
+ handleException();
+ }
+ break;
+ case 's':
+ gSessionData->mSessionXMLPath = optarg;
+ break;
+ case 'o':
+ gSessionData->mTargetPath = optarg;
+ break;
+ case 'u':
+ cmdline.update = true;
+ break;
+ case 'a':
+ gSessionData->mAllowCommands = true;
+ break;
+ case 'h':
+ case '?':
+ logg->logError(
+ "%s. All parameters are optional:\n"
+ "-c config_xml path and filename of the configuration XML to use\n"
+ "-e events_xml path and filename of the events XML to use\n"
+ "-E events_xml path and filename of events XML to append\n"
+ "-h this help page\n"
+ "-m module path and filename of gator.ko\n"
+ "-p port_number port upon which the server listens; default is 8080\n"
+ "-s session_xml path and filename of a session.xml used for local capture\n"
+ "-o apc_dir path and name of the output for a local capture\n"
+ "-v version information\n"
+ "-d enable debug messages\n"
+ "-a allow the user to issue a command from Streamline"
+ , version_string);
+ handleException();
+ break;
+ case 'v':
+ logg->logError("%s", version_string);
+ handleException();
+ break;
+ case 'V':
+ logg->logError("%s\nSRC_MD5: %s", version_string, gSrcMd5);
+ handleException();
+ break;
+ }
+ }
+
+ // Error checking
+ if (cmdline.port != DEFAULT_PORT && gSessionData->mSessionXMLPath != NULL) {
+ logg->logError("Only a port or a session xml can be specified, not both");
+ handleException();
+ }
+
+ if (gSessionData->mTargetPath != NULL && gSessionData->mSessionXMLPath == NULL) {
+ logg->logError("Missing -s command line option required for a local capture.");
+ handleException();
+ }
+
+ if (optind < argc) {
+ logg->logError("Unknown argument: %s. Use '-h' for help.", argv[optind]);
+ handleException();
+ }
+
+ return cmdline;
+}
+
+static AnnotateListener annotateListener;
+
+static void handleClient() {
+ OlySocket client(sock->acceptConnection());
+
+ int pid = fork();
+ if (pid < 0) {
+ // Error
+ logg->logError("Fork process failed. Please power cycle the target device if this error persists.");
+ } else if (pid == 0) {
+ // Child
+ sock->closeServerSocket();
+ udpListener.close();
+ monitor.close();
+ annotateListener.close();
+ child = new Child(&client, numSessions + 1);
+ child->run();
+ delete child;
+ exit(0);
+ } else {
+ // Parent
+ client.closeSocket();
+
+ pthread_mutex_lock(&numSessions_mutex);
+ numSessions++;
+ pthread_mutex_unlock(&numSessions_mutex);
+
+ // Maximum number of connections is 2
+ int wait = 0;
+ while (numSessions > 1) {
+ // Throttle until one of the children exits before continuing to accept another socket connection
+ logg->logMessage("%d sessions active!", numSessions);
+ if (wait++ >= 10) { // Wait no more than 10 seconds
+ // Kill last created child
+ kill(pid, SIGALRM);
+ break;
+ }
+ sleep(1);
+ }
+ }
+}
+
+// Gator data flow: collector -> collector fifo -> sender
+int main(int argc, char** argv) {
+ // Ensure proper signal handling by making gatord the process group leader
+ // e.g. it may not be the group leader when launched as 'sudo gatord'
+ setsid();
+
+ // Set up global thread-safe logging
+ logg = new Logging(hasDebugFlag(argc, argv));
+ // Global data class
+ gSessionData = new SessionData();
+ // Set up global utility class
+ util = new OlyUtility();
+
+ // Initialize drivers
+ new CCNDriver();
+
+ prctl(PR_SET_NAME, (unsigned long)&"gatord-main", 0, 0, 0);
+ pthread_mutex_init(&numSessions_mutex, NULL);
+
+ signal(SIGINT, handler);
+ signal(SIGTERM, handler);
+ signal(SIGABRT, handler);
+
+ // Set to high priority
+ if (setpriority(PRIO_PROCESS, syscall(__NR_gettid), -19) == -1) {
+ logg->logMessage("setpriority() failed");
+ }
+
+ // Parse the command line parameters
+ struct cmdline_t cmdline = parseCommandLine(argc, argv);
+
+ if (cmdline.update) {
+ update(argv[0]);
+ cmdline.update = false;
+ gSessionData->mAllowCommands = true;
+ }
+
+ // Verify root permissions
+ uid_t euid = geteuid();
+ if (euid) {
+ logg->logError("gatord must be launched with root privileges");
+ handleException();
+ }
+
+ // Call before setting up the SIGCHLD handler, as system() spawns child processes
+ if (!setupFilesystem(cmdline.module)) {
+ logg->logMessage("Unable to set up gatorfs, trying perf");
+ if (!gSessionData->perf.setup()) {
+ logg->logError(
+ "Unable to locate gator.ko driver:\n"
+ " >>> gator.ko should be co-located with gatord in the same directory\n"
+ " >>> OR insmod gator.ko prior to launching gatord\n"
+ " >>> OR specify the location of gator.ko on the command line\n"
+ " >>> OR run Linux 3.4 or later with perf (CONFIG_PERF_EVENTS and CONFIG_HW_PERF_EVENTS) and tracing (CONFIG_TRACING and CONFIG_CONTEXT_SWITCH_TRACER) support to collect data via userspace only");
+ handleException();
+ }
+ }
+
+ {
+ EventsXML eventsXML;
+ mxml_node_t *xml = eventsXML.getTree();
+ // Initialize all drivers
+ for (Driver *driver = Driver::getHead(); driver != NULL; driver = driver->getNext()) {
+ driver->readEvents(xml);
+ }
+ mxmlDelete(xml);
+ }
+
+ // Handle child exit codes
+ signal(SIGCHLD, child_exit);
+
+ // Ignore the SIGPIPE signal so that any send to a broken socket will return an error code instead of asserting a signal
+ // Handling the error at the send function call is much easier than trying to do anything intelligent in the sig handler
+ signal(SIGPIPE, SIG_IGN);
+
+ // If the command line argument is a session xml file, no need to open a socket
+ if (gSessionData->mSessionXMLPath) {
+ child = new Child();
+ child->run();
+ delete child;
+ } else {
+ annotateListener.setup();
+ int pipefd[2];
+ if (pipe_cloexec(pipefd) != 0) {
+ logg->logError("Unable to set up annotate pipe");
+ handleException();
+ }
+ gSessionData->mAnnotateStart = pipefd[1];
+ sock = new OlyServerSocket(cmdline.port);
+ udpListener.setup(cmdline.port);
+ if (!monitor.init() ||
+ !monitor.add(sock->getFd()) ||
+ !monitor.add(udpListener.getReq()) ||
+ !monitor.add(annotateListener.getSockFd()) ||
+ !monitor.add(annotateListener.getUdsFd()) ||
+ !monitor.add(pipefd[0]) ||
+ false) {
+ logg->logError("Monitor setup failed");
+ handleException();
+ }
+ // Forever loop, can be exited via a signal or exception
+ while (1) {
+ struct epoll_event events[2];
+ logg->logMessage("Waiting on connection...");
+ int ready = monitor.wait(events, ARRAY_LENGTH(events), -1);
+ if (ready < 0) {
+ logg->logError("Monitor::wait failed");
+ handleException();
+ }
+ for (int i = 0; i < ready; ++i) {
+ if (events[i].data.fd == sock->getFd()) {
+ handleClient();
+ } else if (events[i].data.fd == udpListener.getReq()) {
+ udpListener.handle();
+ } else if (events[i].data.fd == annotateListener.getSockFd()) {
+ annotateListener.handleSock();
+ } else if (events[i].data.fd == annotateListener.getUdsFd()) {
+ annotateListener.handleUds();
+ } else if (events[i].data.fd == pipefd[0]) {
+ uint64_t val;
+ if (read(pipefd[0], &val, sizeof(val)) != sizeof(val)) {
+ logg->logMessage("Reading annotate pipe failed");
+ }
+ annotateListener.signal();
+ }
+ }
+ }
+ }
+
+ cleanUp();
+ return 0;
+}
diff --git a/tools/gator/daemon/mxml/COPYING b/tools/gator/daemon/mxml/COPYING
new file mode 100644
index 0000000..4d0aa78
--- /dev/null
+++ b/tools/gator/daemon/mxml/COPYING
@@ -0,0 +1,507 @@
+ Mini-XML License
+ September 18, 2010
+
+
+The Mini-XML library and included programs are provided under the
+terms of the GNU Library General Public License version 2 (LGPL2)
+with the following exceptions:
+
+ 1. Static linking of applications to the Mini-XML library
+does not constitute a derivative work and does not require
+the author to provide source code for the application, use
+the shared Mini-XML libraries, or link their applications
+against a user-supplied version of Mini-XML.
+
+If you link the application to a modified version of
+Mini-XML, then the changes to Mini-XML must be provided
+under the terms of the LGPL2 in sections 1, 2, and 4.
+
+ 2. You do not have to provide a copy of the Mini-XML license
+with programs that are linked to the Mini-XML library, nor
+do you have to identify the Mini-XML license in your
+program or documentation as required by section 6 of the
+LGPL2.
+
+
+ GNU LIBRARY GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1991 Free Software Foundation, Inc.
+ 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ [This is the first released version of the library GPL. It is
+ numbered 2 because it goes with version 2 of the ordinary GPL.]
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+Licenses are intended to guarantee your freedom to share and change
+free software--to make sure the software is free for all its users.
+
+ This license, the Library General Public License, applies to some
+specially designated Free Software Foundation software, and to any
+other libraries whose authors decide to use it. You can use it for
+your libraries, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if
+you distribute copies of the library, or if you modify it.
+
+ For example, if you distribute copies of the library, whether gratis
+or for a fee, you must give the recipients all the rights that we gave
+you. You must make sure that they, too, receive or can get the source
+code. If you link a program with the library, you must provide
+complete object files to the recipients so that they can relink them
+with the library, after making changes to the library and recompiling
+it. And you must show them these terms so they know their rights.
+
+ Our method of protecting your rights has two steps: (1) copyright
+the library, and (2) offer you this license which gives you legal
+permission to copy, distribute and/or modify the library.
+
+ Also, for each distributor's protection, we want to make certain
+that everyone understands that there is no warranty for this free
+library. If the library is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original
+version, so that any problems introduced by others will not reflect on
+the original authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that companies distributing free
+software will individually obtain patent licenses, thus in effect
+transforming the program into proprietary software. To prevent this,
+we have made it clear that any patent must be licensed for everyone's
+free use or not licensed at all.
+
+ Most GNU software, including some libraries, is covered by the ordinary
+GNU General Public License, which was designed for utility programs. This
+license, the GNU Library General Public License, applies to certain
+designated libraries. This license is quite different from the ordinary
+one; be sure to read it in full, and don't assume that anything in it is
+the same as in the ordinary license.
+
+ The reason we have a separate public license for some libraries is that
+they blur the distinction we usually make between modifying or adding to a
+program and simply using it. Linking a program with a library, without
+changing the library, is in some sense simply using the library, and is
+analogous to running a utility program or application program. However, in
+a textual and legal sense, the linked executable is a combined work, a
+derivative of the original library, and the ordinary General Public License
+treats it as such.
+
+ Because of this blurred distinction, using the ordinary General
+Public License for libraries did not effectively promote software
+sharing, because most developers did not use the libraries. We
+concluded that weaker conditions might promote sharing better.
+
+ However, unrestricted linking of non-free programs would deprive the
+users of those programs of all benefit from the free status of the
+libraries themselves. This Library General Public License is intended to
+permit developers of non-free programs to use free libraries, while
+preserving your freedom as a user of such programs to change the free
+libraries that are incorporated in them. (We have not seen how to achieve
+this as regards changes in header files, but we have achieved it as regards
+changes in the actual functions of the Library.) The hope is that this
+will lead to faster development of free libraries.
+
+ The precise terms and conditions for copying, distribution and
+modification follow. Pay close attention to the difference between a
+"work based on the library" and a "work that uses the library". The
+former contains code derived from the library, while the latter only
+works together with the library.
+
+ Note that it is possible for a library to be covered by the ordinary
+General Public License rather than by this special one.
+
+ GNU LIBRARY GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License Agreement applies to any software library which
+contains a notice placed by the copyright holder or other authorized
+party saying it may be distributed under the terms of this Library
+General Public License (also called "this License"). Each licensee is
+addressed as "you".
+
+ A "library" means a collection of software functions and/or data
+prepared so as to be conveniently linked with application programs
+(which use some of those functions and data) to form executables.
+
+ The "Library", below, refers to any such software library or work
+which has been distributed under these terms. A "work based on the
+Library" means either the Library or any derivative work under
+copyright law: that is to say, a work containing the Library or a
+portion of it, either verbatim or with modifications and/or translated
+straightforwardly into another language. (Hereinafter, translation is
+included without limitation in the term "modification".)
+
+ "Source code" for a work means the preferred form of the work for
+making modifications to it. For a library, complete source code means
+all the source code for all modules it contains, plus any associated
+interface definition files, plus the scripts used to control compilation
+and installation of the library.
+
+ Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running a program using the Library is not restricted, and output from
+such a program is covered only if its contents constitute a work based
+on the Library (independent of the use of the Library in a tool for
+writing it). Whether that is true depends on what the Library does
+and what the program that uses the Library does.
+
+ 1. You may copy and distribute verbatim copies of the Library's
+complete source code as you receive it, in any medium, provided that
+you conspicuously and appropriately publish on each copy an
+appropriate copyright notice and disclaimer of warranty; keep intact
+all the notices that refer to this License and to the absence of any
+warranty; and distribute a copy of this License along with the
+Library.
+
+ You may charge a fee for the physical act of transferring a copy,
+and you may at your option offer warranty protection in exchange for a
+fee.
+
+ 2. You may modify your copy or copies of the Library or any portion
+of it, thus forming a work based on the Library, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) The modified work must itself be a software library.
+
+ b) You must cause the files modified to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ c) You must cause the whole of the work to be licensed at no
+ charge to all third parties under the terms of this License.
+
+ d) If a facility in the modified Library refers to a function or a
+ table of data to be supplied by an application program that uses
+ the facility, other than as an argument passed when the facility
+ is invoked, then you must make a good faith effort to ensure that,
+ in the event an application does not supply such function or
+ table, the facility still operates, and performs whatever part of
+ its purpose remains meaningful.
+
+ (For example, a function in a library to compute square roots has
+ a purpose that is entirely well-defined independent of the
+ application. Therefore, Subsection 2d requires that any
+ application-supplied function or table used by this function must
+ be optional: if the application does not supply it, the square
+ root function must still compute square roots.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Library,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Library, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote
+it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Library.
+
+In addition, mere aggregation of another work not based on the Library
+with the Library (or with a work based on the Library) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may opt to apply the terms of the ordinary GNU General Public
+License instead of this License to a given copy of the Library. To do
+this, you must alter all the notices that refer to this License, so
+that they refer to the ordinary GNU General Public License, version 2,
+instead of to this License. (If a newer version than version 2 of the
+ordinary GNU General Public License has appeared, then you can specify
+that version instead if you wish.) Do not make any other change in
+these notices.
+
+ Once this change is made in a given copy, it is irreversible for
+that copy, so the ordinary GNU General Public License applies to all
+subsequent copies and derivative works made from that copy.
+
+ This option is useful when you wish to copy part of the code of
+the Library into a program that is not a library.
+
+ 4. You may copy and distribute the Library (or a portion or
+derivative of it, under Section 2) in object code or executable form
+under the terms of Sections 1 and 2 above provided that you accompany
+it with the complete corresponding machine-readable source code, which
+must be distributed under the terms of Sections 1 and 2 above on a
+medium customarily used for software interchange.
+
+ If distribution of object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the
+source code from the same place satisfies the requirement to
+distribute the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 5. A program that contains no derivative of any portion of the
+Library, but is designed to work with the Library by being compiled or
+linked with it, is called a "work that uses the Library". Such a
+work, in isolation, is not a derivative work of the Library, and
+therefore falls outside the scope of this License.
+
+ However, linking a "work that uses the Library" with the Library
+creates an executable that is a derivative of the Library (because it
+contains portions of the Library), rather than a "work that uses the
+library". The executable is therefore covered by this License.
+Section 6 states terms for distribution of such executables.
+
+ When a "work that uses the Library" uses material from a header file
+that is part of the Library, the object code for the work may be a
+derivative work of the Library even though the source code is not.
+Whether this is true is especially significant if the work can be
+linked without the Library, or if the work is itself a library. The
+threshold for this to be true is not precisely defined by law.
+
+ If such an object file uses only numerical parameters, data
+structure layouts and accessors, and small macros and small inline
+functions (ten lines or less in length), then the use of the object
+file is unrestricted, regardless of whether it is legally a derivative
+work. (Executables containing this object code plus portions of the
+Library will still fall under Section 6.)
+
+ Otherwise, if the work is a derivative of the Library, you may
+distribute the object code for the work under the terms of Section 6.
+Any executables containing that work also fall under Section 6,
+whether or not they are linked directly with the Library itself.
+
+ 6. As an exception to the Sections above, you may also compile or
+link a "work that uses the Library" with the Library to produce a
+work containing portions of the Library, and distribute that work
+under terms of your choice, provided that the terms permit
+modification of the work for the customer's own use and reverse
+engineering for debugging such modifications.
+
+ You must give prominent notice with each copy of the work that the
+Library is used in it and that the Library and its use are covered by
+this License. You must supply a copy of this License. If the work
+during execution displays copyright notices, you must include the
+copyright notice for the Library among them, as well as a reference
+directing the user to the copy of this License. Also, you must do one
+of these things:
+
+ a) Accompany the work with the complete corresponding
+ machine-readable source code for the Library including whatever
+ changes were used in the work (which must be distributed under
+ Sections 1 and 2 above); and, if the work is an executable linked
+ with the Library, with the complete machine-readable "work that
+ uses the Library", as object code and/or source code, so that the
+ user can modify the Library and then relink to produce a modified
+ executable containing the modified Library. (It is understood
+ that the user who changes the contents of definitions files in the
+ Library will not necessarily be able to recompile the application
+ to use the modified definitions.)
+
+ b) Accompany the work with a written offer, valid for at
+ least three years, to give the same user the materials
+ specified in Subsection 6a, above, for a charge no more
+ than the cost of performing this distribution.
+
+ c) If distribution of the work is made by offering access to copy
+ from a designated place, offer equivalent access to copy the above
+ specified materials from the same place.
+
+ d) Verify that the user has already received a copy of these
+ materials or that you have already sent this user a copy.
+
+ For an executable, the required form of the "work that uses the
+Library" must include any data and utility programs needed for
+reproducing the executable from it. However, as a special exception,
+the source code distributed need not include anything that is normally
+distributed (in either source or binary form) with the major
+components (compiler, kernel, and so on) of the operating system on
+which the executable runs, unless that component itself accompanies
+the executable.
+
+ It may happen that this requirement contradicts the license
+restrictions of other proprietary libraries that do not normally
+accompany the operating system. Such a contradiction means you cannot
+use both them and the Library together in an executable that you
+distribute.
+
+ 7. You may place library facilities that are a work based on the
+Library side-by-side in a single library together with other library
+facilities not covered by this License, and distribute such a combined
+library, provided that the separate distribution of the work based on
+the Library and of the other library facilities is otherwise
+permitted, and provided that you do these two things:
+
+ a) Accompany the combined library with a copy of the same work
+ based on the Library, uncombined with any other library
+ facilities. This must be distributed under the terms of the
+ Sections above.
+
+ b) Give prominent notice with the combined library of the fact
+ that part of it is a work based on the Library, and explaining
+ where to find the accompanying uncombined form of the same work.
+
+ 8. You may not copy, modify, sublicense, link with, or distribute
+the Library except as expressly provided under this License. Any
+attempt otherwise to copy, modify, sublicense, link with, or
+distribute the Library is void, and will automatically terminate your
+rights under this License. However, parties who have received copies,
+or rights, from you under this License will not have their licenses
+terminated so long as such parties remain in full compliance.
+
+ 9. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Library or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Library (or any work based on the
+Library), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Library or works based on it.
+
+ 10. Each time you redistribute the Library (or any work based on the
+Library), the recipient automatically receives a license from the
+original licensor to copy, distribute, link with or modify the Library
+subject to these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 11. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Library at all. For example, if a patent
+license would not permit royalty-free redistribution of the Library by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Library.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply,
+and the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 12. If the distribution and/or use of the Library is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Library under this License may add
+an explicit geographical distribution limitation excluding those countries,
+so that distribution is permitted only in or among countries not thus
+excluded. In such case, this License incorporates the limitation as if
+written in the body of this License.
+
+ 13. The Free Software Foundation may publish revised and/or new
+versions of the Library General Public License from time to time.
+Such new versions will be similar in spirit to the present version,
+but may differ in detail to address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Library
+specifies a version number of this License which applies to it and
+"any later version", you have the option of following the terms and
+conditions either of that version or of any later version published by
+the Free Software Foundation. If the Library does not specify a
+license version number, you may choose any version ever published by
+the Free Software Foundation.
+
+ 14. If you wish to incorporate parts of the Library into other free
+programs whose distribution conditions are incompatible with these,
+write to the author to ask for permission. For software which is
+copyrighted by the Free Software Foundation, write to the Free
+Software Foundation; we sometimes make exceptions for this. Our
+decision will be guided by the two goals of preserving the free status
+of all derivatives of our free software and of promoting the sharing
+and reuse of software generally.
+
+ NO WARRANTY
+
+ 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
+WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
+EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
+OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY
+KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE
+LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
+THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
+WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
+AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU
+FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR
+CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE
+LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
+RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
+SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ Appendix: How to Apply These Terms to Your New Libraries
+
+ If you develop a new library, and you want it to be of the greatest
+possible use to the public, we recommend making it free software that
+everyone can redistribute and change. You can do so by permitting
+redistribution under these terms (or, alternatively, under the terms of the
+ordinary General Public License).
+
+ To apply these terms, attach the following notices to the library. It is
+safest to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least the
+"copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the library's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Library General Public
+ License as published by the Free Software Foundation; either
+ version 2 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Library General Public License for more details.
+
+ You should have received a copy of the GNU Library General Public
+ License along with this library; if not, write to the Free
+ Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the library, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the
+ library `Frob' (a library for tweaking knobs) written by James Random Hacker.
+
+ <signature of Ty Coon>, 1 April 1990
+ Ty Coon, President of Vice
+
+That's all there is to it!
diff --git a/tools/gator/daemon/mxml/config.h b/tools/gator/daemon/mxml/config.h
new file mode 100644
index 0000000..ad6df1d
--- /dev/null
+++ b/tools/gator/daemon/mxml/config.h
@@ -0,0 +1,96 @@
+/* config.h. Generated from config.h.in by configure. */
+/*
+ * "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Configuration file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdarg.h>
+#include <ctype.h>
+
+
+/*
+ * Version number...
+ */
+
+#define MXML_VERSION "Mini-XML v2.8"
+
+
+/*
+ * Inline function support...
+ */
+
+#define inline
+
+
+/*
+ * Long long support...
+ */
+
+#define HAVE_LONG_LONG 1
+
+
+/*
+ * Do we have the snprintf() and vsnprintf() functions?
+ */
+
+#define HAVE_SNPRINTF 1
+#define HAVE_VSNPRINTF 1
+
+
+/*
+ * Do we have the strXXX() functions?
+ */
+
+#define HAVE_STRDUP 1
+
+
+/*
+ * Do we have threading support?
+ */
+
+#define HAVE_PTHREAD_H 1
+
+
+/*
+ * Define prototypes for string functions as needed...
+ */
+
+# ifndef HAVE_STRDUP
+extern char *_mxml_strdup(const char *);
+# define strdup _mxml_strdup
+# endif /* !HAVE_STRDUP */
+
+extern char *_mxml_strdupf(const char *, ...);
+extern char *_mxml_vstrdupf(const char *, va_list);
+
+# ifndef HAVE_SNPRINTF
+extern int _mxml_snprintf(char *, size_t, const char *, ...);
+# define snprintf _mxml_snprintf
+# endif /* !HAVE_SNPRINTF */
+
+# ifndef HAVE_VSNPRINTF
+extern int _mxml_vsnprintf(char *, size_t, const char *, va_list);
+# define vsnprintf _mxml_vsnprintf
+# endif /* !HAVE_VSNPRINTF */
+
+/*
+ * End of "$Id: config.h.in 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-attr.c b/tools/gator/daemon/mxml/mxml-attr.c
new file mode 100644
index 0000000..8e89cc1
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-attr.c
@@ -0,0 +1,314 @@
+/*
+ * "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Attribute support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static int mxml_set_attr(mxml_node_t *node, const char *name,
+ char *value);
+
+
+/*
+ * 'mxmlElementDeleteAttr()' - Delete an attribute.
+ *
+ * @since Mini-XML 2.4@
+ */
+
+void
+mxmlElementDeleteAttr(mxml_node_t *node,/* I - Element */
+ const char *name)/* I - Attribute name */
+{
+ int i; /* Looping var */
+ mxml_attr_t *attr; /* Cirrent attribute */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlElementDeleteAttr(node=%p, name=\"%s\")\n",
+ node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT || !name)
+ return;
+
+ /*
+ * Look for the attribute...
+ */
+
+ for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+ i > 0;
+ i --, attr ++)
+ {
+#ifdef DEBUG
+ printf(" %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+ if (!strcmp(attr->name, name))
+ {
+ /*
+ * Delete this attribute...
+ */
+
+ free(attr->name);
+ free(attr->value);
+
+ i --;
+ if (i > 0)
+ memmove(attr, attr + 1, i * sizeof(mxml_attr_t));
+
+ node->value.element.num_attrs --;
+
+ if (node->value.element.num_attrs == 0)
+ free(node->value.element.attrs);
+ return;
+ }
+ }
+}
+
+
+/*
+ * 'mxmlElementGetAttr()' - Get an attribute.
+ *
+ * This function returns NULL if the node is not an element or the
+ * named attribute does not exist.
+ */
+
+const char * /* O - Attribute value or NULL */
+mxmlElementGetAttr(mxml_node_t *node, /* I - Element node */
+ const char *name) /* I - Name of attribute */
+{
+ int i; /* Looping var */
+ mxml_attr_t *attr; /* Cirrent attribute */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlElementGetAttr(node=%p, name=\"%s\")\n",
+ node, name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT || !name)
+ return (NULL);
+
+ /*
+ * Look for the attribute...
+ */
+
+ for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+ i > 0;
+ i --, attr ++)
+ {
+#ifdef DEBUG
+ printf(" %s=\"%s\"\n", attr->name, attr->value);
+#endif /* DEBUG */
+
+ if (!strcmp(attr->name, name))
+ {
+#ifdef DEBUG
+ printf(" Returning \"%s\"!\n", attr->value);
+#endif /* DEBUG */
+ return (attr->value);
+ }
+ }
+
+ /*
+ * Didn't find attribute, so return NULL...
+ */
+
+#ifdef DEBUG
+ puts(" Returning NULL!\n");
+#endif /* DEBUG */
+
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlElementSetAttr()' - Set an attribute.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new string value. The string value is copied
+ * into the element node. This function does nothing if the node is
+ * not an element.
+ */
+
+void
+mxmlElementSetAttr(mxml_node_t *node, /* I - Element node */
+ const char *name, /* I - Name of attribute */
+ const char *value) /* I - Attribute value */
+{
+ char *valuec; /* Copy of value */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlElementSetAttr(node=%p, name=\"%s\", value=\"%s\")\n",
+ node, name ? name : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT || !name)
+ return;
+
+ if (value)
+ valuec = strdup(value);
+ else
+ valuec = NULL;
+
+ if (mxml_set_attr(node, name, valuec))
+ free(valuec);
+}
+
+
+/*
+ * 'mxmlElementSetAttrf()' - Set an attribute with a formatted value.
+ *
+ * If the named attribute already exists, the value of the attribute
+ * is replaced by the new formatted string. The formatted string value is
+ * copied into the element node. This function does nothing if the node
+ * is not an element.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlElementSetAttrf(mxml_node_t *node, /* I - Element node */
+ const char *name, /* I - Name of attribute */
+ const char *format,/* I - Printf-style attribute value */
+ ...) /* I - Additional arguments as needed */
+{
+ va_list ap; /* Argument pointer */
+ char *value; /* Value */
+
+
+#ifdef DEBUG
+ fprintf(stderr,
+ "mxmlElementSetAttrf(node=%p, name=\"%s\", format=\"%s\", ...)\n",
+ node, name ? name : "(null)", format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT || !name || !format)
+ return;
+
+ /*
+ * Format the value...
+ */
+
+ va_start(ap, format);
+ value = _mxml_vstrdupf(format, ap);
+ va_end(ap);
+
+ if (!value)
+ mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+ name, node->value.element.name);
+ else if (mxml_set_attr(node, name, value))
+ free(value);
+}
+
+
+/*
+ * 'mxml_set_attr()' - Set or add an attribute name/value pair.
+ */
+
+static int /* O - 0 on success, -1 on failure */
+mxml_set_attr(mxml_node_t *node, /* I - Element node */
+ const char *name, /* I - Attribute name */
+ char *value) /* I - Attribute value */
+{
+ int i; /* Looping var */
+ mxml_attr_t *attr; /* New attribute */
+
+
+ /*
+ * Look for the attribute...
+ */
+
+ for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+ i > 0;
+ i --, attr ++)
+ if (!strcmp(attr->name, name))
+ {
+ /*
+ * Free the old value as needed...
+ */
+
+ if (attr->value)
+ free(attr->value);
+
+ attr->value = value;
+
+ return (0);
+ }
+
+ /*
+ * Add a new attribute...
+ */
+
+ if (node->value.element.num_attrs == 0)
+ attr = malloc(sizeof(mxml_attr_t));
+ else
+ attr = realloc(node->value.element.attrs,
+ (node->value.element.num_attrs + 1) * sizeof(mxml_attr_t));
+
+ if (!attr)
+ {
+ mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+ name, node->value.element.name);
+ return (-1);
+ }
+
+ node->value.element.attrs = attr;
+ attr += node->value.element.num_attrs;
+
+ if ((attr->name = strdup(name)) == NULL)
+ {
+ mxml_error("Unable to allocate memory for attribute '%s' in element %s!",
+ name, node->value.element.name);
+ return (-1);
+ }
+
+ attr->value = value;
+
+ node->value.element.num_attrs ++;
+
+ return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-attr.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-entity.c b/tools/gator/daemon/mxml/mxml-entity.c
new file mode 100644
index 0000000..0d11df6
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-entity.c
@@ -0,0 +1,449 @@
+/*
+ * "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Character entity support code for Mini-XML, a small XML-like
+ * file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * 'mxmlEntityAddCallback()' - Add a callback to convert entities to Unicode.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlEntityAddCallback(
+ mxml_entity_cb_t cb) /* I - Callback function to add */
+{
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ if (global->num_entity_cbs < (int)(sizeof(global->entity_cbs) / sizeof(global->entity_cbs[0])))
+ {
+ global->entity_cbs[global->num_entity_cbs] = cb;
+ global->num_entity_cbs ++;
+
+ return (0);
+ }
+ else
+ {
+ mxml_error("Unable to add entity callback!");
+
+ return (-1);
+ }
+}
+
+
+/*
+ * 'mxmlEntityGetName()' - Get the name that corresponds to the character value.
+ *
+ * If val does not need to be represented by a named entity, NULL is returned.
+ */
+
+const char * /* O - Entity name or NULL */
+mxmlEntityGetName(int val) /* I - Character value */
+{
+ switch (val)
+ {
+ case '&' :
+ return ("amp");
+
+ case '<' :
+ return ("lt");
+
+ case '>' :
+ return ("gt");
+
+ case '\"' :
+ return ("quot");
+
+ default :
+ return (NULL);
+ }
+}
+
+
+/*
+ * 'mxmlEntityGetValue()' - Get the character corresponding to a named entity.
+ *
+ * The entity name can also be a numeric constant. -1 is returned if the
+ * name is not known.
+ */
+
+int /* O - Character value or -1 on error */
+mxmlEntityGetValue(const char *name) /* I - Entity name */
+{
+ int i; /* Looping var */
+ int ch; /* Character value */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ for (i = 0; i < global->num_entity_cbs; i ++)
+ if ((ch = (global->entity_cbs[i])(name)) >= 0)
+ return (ch);
+
+ return (-1);
+}
+
+
+/*
+ * 'mxmlEntityRemoveCallback()' - Remove a callback.
+ */
+
+void
+mxmlEntityRemoveCallback(
+ mxml_entity_cb_t cb) /* I - Callback function to remove */
+{
+ int i; /* Looping var */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ for (i = 0; i < global->num_entity_cbs; i ++)
+ if (cb == global->entity_cbs[i])
+ {
+ /*
+ * Remove the callback...
+ */
+
+ global->num_entity_cbs --;
+
+ if (i < global->num_entity_cbs)
+ memmove(global->entity_cbs + i, global->entity_cbs + i + 1,
+ (global->num_entity_cbs - i) * sizeof(global->entity_cbs[0]));
+
+ return;
+ }
+}
+
+
+/*
+ * '_mxml_entity_cb()' - Lookup standard (X)HTML entities.
+ */
+
+int /* O - Unicode value or -1 */
+_mxml_entity_cb(const char *name) /* I - Entity name */
+{
+ int diff, /* Difference between names */
+ current, /* Current entity in search */
+ first, /* First entity in search */
+ last; /* Last entity in search */
+ static const struct
+ {
+ const char *name; /* Entity name */
+ int val; /* Character value */
+ } entities[] =
+ {
+ { "AElig", 198 },
+ { "Aacute", 193 },
+ { "Acirc", 194 },
+ { "Agrave", 192 },
+ { "Alpha", 913 },
+ { "Aring", 197 },
+ { "Atilde", 195 },
+ { "Auml", 196 },
+ { "Beta", 914 },
+ { "Ccedil", 199 },
+ { "Chi", 935 },
+ { "Dagger", 8225 },
+ { "Delta", 916 },
+ { "Dstrok", 208 },
+ { "ETH", 208 },
+ { "Eacute", 201 },
+ { "Ecirc", 202 },
+ { "Egrave", 200 },
+ { "Epsilon", 917 },
+ { "Eta", 919 },
+ { "Euml", 203 },
+ { "Gamma", 915 },
+ { "Iacute", 205 },
+ { "Icirc", 206 },
+ { "Igrave", 204 },
+ { "Iota", 921 },
+ { "Iuml", 207 },
+ { "Kappa", 922 },
+ { "Lambda", 923 },
+ { "Mu", 924 },
+ { "Ntilde", 209 },
+ { "Nu", 925 },
+ { "OElig", 338 },
+ { "Oacute", 211 },
+ { "Ocirc", 212 },
+ { "Ograve", 210 },
+ { "Omega", 937 },
+ { "Omicron", 927 },
+ { "Oslash", 216 },
+ { "Otilde", 213 },
+ { "Ouml", 214 },
+ { "Phi", 934 },
+ { "Pi", 928 },
+ { "Prime", 8243 },
+ { "Psi", 936 },
+ { "Rho", 929 },
+ { "Scaron", 352 },
+ { "Sigma", 931 },
+ { "THORN", 222 },
+ { "Tau", 932 },
+ { "Theta", 920 },
+ { "Uacute", 218 },
+ { "Ucirc", 219 },
+ { "Ugrave", 217 },
+ { "Upsilon", 933 },
+ { "Uuml", 220 },
+ { "Xi", 926 },
+ { "Yacute", 221 },
+ { "Yuml", 376 },
+ { "Zeta", 918 },
+ { "aacute", 225 },
+ { "acirc", 226 },
+ { "acute", 180 },
+ { "aelig", 230 },
+ { "agrave", 224 },
+ { "alefsym", 8501 },
+ { "alpha", 945 },
+ { "amp", '&' },
+ { "and", 8743 },
+ { "ang", 8736 },
+ { "apos", '\'' },
+ { "aring", 229 },
+ { "asymp", 8776 },
+ { "atilde", 227 },
+ { "auml", 228 },
+ { "bdquo", 8222 },
+ { "beta", 946 },
+ { "brkbar", 166 },
+ { "brvbar", 166 },
+ { "bull", 8226 },
+ { "cap", 8745 },
+ { "ccedil", 231 },
+ { "cedil", 184 },
+ { "cent", 162 },
+ { "chi", 967 },
+ { "circ", 710 },
+ { "clubs", 9827 },
+ { "cong", 8773 },
+ { "copy", 169 },
+ { "crarr", 8629 },
+ { "cup", 8746 },
+ { "curren", 164 },
+ { "dArr", 8659 },
+ { "dagger", 8224 },
+ { "darr", 8595 },
+ { "deg", 176 },
+ { "delta", 948 },
+ { "diams", 9830 },
+ { "die", 168 },
+ { "divide", 247 },
+ { "eacute", 233 },
+ { "ecirc", 234 },
+ { "egrave", 232 },
+ { "empty", 8709 },
+ { "emsp", 8195 },
+ { "ensp", 8194 },
+ { "epsilon", 949 },
+ { "equiv", 8801 },
+ { "eta", 951 },
+ { "eth", 240 },
+ { "euml", 235 },
+ { "euro", 8364 },
+ { "exist", 8707 },
+ { "fnof", 402 },
+ { "forall", 8704 },
+ { "frac12", 189 },
+ { "frac14", 188 },
+ { "frac34", 190 },
+ { "frasl", 8260 },
+ { "gamma", 947 },
+ { "ge", 8805 },
+ { "gt", '>' },
+ { "hArr", 8660 },
+ { "harr", 8596 },
+ { "hearts", 9829 },
+ { "hellip", 8230 },
+ { "hibar", 175 },
+ { "iacute", 237 },
+ { "icirc", 238 },
+ { "iexcl", 161 },
+ { "igrave", 236 },
+ { "image", 8465 },
+ { "infin", 8734 },
+ { "int", 8747 },
+ { "iota", 953 },
+ { "iquest", 191 },
+ { "isin", 8712 },
+ { "iuml", 239 },
+ { "kappa", 954 },
+ { "lArr", 8656 },
+ { "lambda", 955 },
+ { "lang", 9001 },
+ { "laquo", 171 },
+ { "larr", 8592 },
+ { "lceil", 8968 },
+ { "ldquo", 8220 },
+ { "le", 8804 },
+ { "lfloor", 8970 },
+ { "lowast", 8727 },
+ { "loz", 9674 },
+ { "lrm", 8206 },
+ { "lsaquo", 8249 },
+ { "lsquo", 8216 },
+ { "lt", '<' },
+ { "macr", 175 },
+ { "mdash", 8212 },
+ { "micro", 181 },
+ { "middot", 183 },
+ { "minus", 8722 },
+ { "mu", 956 },
+ { "nabla", 8711 },
+ { "nbsp", 160 },
+ { "ndash", 8211 },
+ { "ne", 8800 },
+ { "ni", 8715 },
+ { "not", 172 },
+ { "notin", 8713 },
+ { "nsub", 8836 },
+ { "ntilde", 241 },
+ { "nu", 957 },
+ { "oacute", 243 },
+ { "ocirc", 244 },
+ { "oelig", 339 },
+ { "ograve", 242 },
+ { "oline", 8254 },
+ { "omega", 969 },
+ { "omicron", 959 },
+ { "oplus", 8853 },
+ { "or", 8744 },
+ { "ordf", 170 },
+ { "ordm", 186 },
+ { "oslash", 248 },
+ { "otilde", 245 },
+ { "otimes", 8855 },
+ { "ouml", 246 },
+ { "para", 182 },
+ { "part", 8706 },
+ { "permil", 8240 },
+ { "perp", 8869 },
+ { "phi", 966 },
+ { "pi", 960 },
+ { "piv", 982 },
+ { "plusmn", 177 },
+ { "pound", 163 },
+ { "prime", 8242 },
+ { "prod", 8719 },
+ { "prop", 8733 },
+ { "psi", 968 },
+ { "quot", '\"' },
+ { "rArr", 8658 },
+ { "radic", 8730 },
+ { "rang", 9002 },
+ { "raquo", 187 },
+ { "rarr", 8594 },
+ { "rceil", 8969 },
+ { "rdquo", 8221 },
+ { "real", 8476 },
+ { "reg", 174 },
+ { "rfloor", 8971 },
+ { "rho", 961 },
+ { "rlm", 8207 },
+ { "rsaquo", 8250 },
+ { "rsquo", 8217 },
+ { "sbquo", 8218 },
+ { "scaron", 353 },
+ { "sdot", 8901 },
+ { "sect", 167 },
+ { "shy", 173 },
+ { "sigma", 963 },
+ { "sigmaf", 962 },
+ { "sim", 8764 },
+ { "spades", 9824 },
+ { "sub", 8834 },
+ { "sube", 8838 },
+ { "sum", 8721 },
+ { "sup", 8835 },
+ { "sup1", 185 },
+ { "sup2", 178 },
+ { "sup3", 179 },
+ { "supe", 8839 },
+ { "szlig", 223 },
+ { "tau", 964 },
+ { "there4", 8756 },
+ { "theta", 952 },
+ { "thetasym", 977 },
+ { "thinsp", 8201 },
+ { "thorn", 254 },
+ { "tilde", 732 },
+ { "times", 215 },
+ { "trade", 8482 },
+ { "uArr", 8657 },
+ { "uacute", 250 },
+ { "uarr", 8593 },
+ { "ucirc", 251 },
+ { "ugrave", 249 },
+ { "uml", 168 },
+ { "upsih", 978 },
+ { "upsilon", 965 },
+ { "uuml", 252 },
+ { "weierp", 8472 },
+ { "xi", 958 },
+ { "yacute", 253 },
+ { "yen", 165 },
+ { "yuml", 255 },
+ { "zeta", 950 },
+ { "zwj", 8205 },
+ { "zwnj", 8204 }
+ };
+
+
+ /*
+ * Do a binary search for the named entity...
+ */
+
+ first = 0;
+ last = (int)(sizeof(entities) / sizeof(entities[0]) - 1);
+
+ while ((last - first) > 1)
+ {
+ current = (first + last) / 2;
+
+ if ((diff = strcmp(name, entities[current].name)) == 0)
+ return (entities[current].val);
+ else if (diff < 0)
+ last = current;
+ else
+ first = current;
+ }
+
+ /*
+ * If we get here, there is a small chance that there is still
+ * a match; check first and last...
+ */
+
+ if (!strcmp(name, entities[first].name))
+ return (entities[first].val);
+ else if (!strcmp(name, entities[last].name))
+ return (entities[last].val);
+ else
+ return (-1);
+}
+
+
+/*
+ * End of "$Id: mxml-entity.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-file.c b/tools/gator/daemon/mxml/mxml-file.c
new file mode 100644
index 0000000..3812c25
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-file.c
@@ -0,0 +1,3056 @@
+/*
+ * "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $"
+ *
+ * File loading code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*** This file modified by ARM on 25 Aug 2014 to avoid pointer overflow when checking if the write position is beyond the end of the buffer in mxmlSaveString and mxml_string_putc ***/
+
+/*
+ * Include necessary headers...
+ */
+
+#ifndef WIN32
+# include <unistd.h>
+#endif /* !WIN32 */
+#include "mxml-private.h"
+
+
+/*
+ * Character encoding...
+ */
+
+#define ENCODE_UTF8 0 /* UTF-8 */
+#define ENCODE_UTF16BE 1 /* UTF-16 Big-Endian */
+#define ENCODE_UTF16LE 2 /* UTF-16 Little-Endian */
+
+
+/*
+ * Macro to test for a bad XML character...
+ */
+
+#define mxml_bad_char(ch) ((ch) < ' ' && (ch) != '\n' && (ch) != '\r' && (ch) != '\t')
+
+
+/*
+ * Types and structures...
+ */
+
+typedef int (*_mxml_getc_cb_t)(void *, int *);
+typedef int (*_mxml_putc_cb_t)(int, void *);
+
+typedef struct _mxml_fdbuf_s /**** File descriptor buffer ****/
+{
+ int fd; /* File descriptor */
+ unsigned char *current, /* Current position in buffer */
+ *end, /* End of buffer */
+ buffer[8192]; /* Character buffer */
+} _mxml_fdbuf_t;
+
+
+/*
+ * Local functions...
+ */
+
+static int mxml_add_char(int ch, char **ptr, char **buffer,
+ int *bufsize);
+static int mxml_fd_getc(void *p, int *encoding);
+static int mxml_fd_putc(int ch, void *p);
+static int mxml_fd_read(_mxml_fdbuf_t *buf);
+static int mxml_fd_write(_mxml_fdbuf_t *buf);
+static int mxml_file_getc(void *p, int *encoding);
+static int mxml_file_putc(int ch, void *p);
+static int mxml_get_entity(mxml_node_t *parent, void *p,
+ int *encoding,
+ _mxml_getc_cb_t getc_cb);
+static inline int mxml_isspace(int ch)
+ {
+ return (ch == ' ' || ch == '\t' || ch == '\r' ||
+ ch == '\n');
+ }
+static mxml_node_t *mxml_load_data(mxml_node_t *top, void *p,
+ mxml_load_cb_t cb,
+ _mxml_getc_cb_t getc_cb,
+ mxml_sax_cb_t sax_cb, void *sax_data);
+static int mxml_parse_element(mxml_node_t *node, void *p,
+ int *encoding,
+ _mxml_getc_cb_t getc_cb);
+static int mxml_string_getc(void *p, int *encoding);
+static int mxml_string_putc(int ch, void *p);
+static int mxml_write_name(const char *s, void *p,
+ _mxml_putc_cb_t putc_cb);
+static int mxml_write_node(mxml_node_t *node, void *p,
+ mxml_save_cb_t cb, int col,
+ _mxml_putc_cb_t putc_cb,
+ _mxml_global_t *global);
+static int mxml_write_string(const char *s, void *p,
+ _mxml_putc_cb_t putc_cb);
+static int mxml_write_ws(mxml_node_t *node, void *p,
+ mxml_save_cb_t cb, int ws,
+ int col, _mxml_putc_cb_t putc_cb);
+
+
+/*
+ * 'mxmlLoadFd()' - Load a file descriptor into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t * /* O - First node or NULL if the file could not be read. */
+mxmlLoadFd(mxml_node_t *top, /* I - Top node */
+ int fd, /* I - File descriptor to read from */
+ mxml_load_cb_t cb) /* I - Callback function or MXML_NO_CALLBACK */
+{
+ _mxml_fdbuf_t buf; /* File descriptor buffer */
+
+
+ /*
+ * Initialize the file descriptor buffer...
+ */
+
+ buf.fd = fd;
+ buf.current = buf.buffer;
+ buf.end = buf.buffer;
+
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, &buf, cb, mxml_fd_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadFile()' - Load a file into an XML node tree.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t * /* O - First node or NULL if the file could not be read. */
+mxmlLoadFile(mxml_node_t *top, /* I - Top node */
+ FILE *fp, /* I - File to read from */
+ mxml_load_cb_t cb) /* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, fp, cb, mxml_file_getc, MXML_NO_CALLBACK, NULL));
+}
+
+
+/*
+ * 'mxmlLoadString()' - Load a string into an XML node tree.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ */
+
+mxml_node_t * /* O - First node or NULL if the string has errors. */
+mxmlLoadString(mxml_node_t *top, /* I - Top node */
+ const char *s, /* I - String to load */
+ mxml_load_cb_t cb) /* I - Callback function or MXML_NO_CALLBACK */
+{
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, MXML_NO_CALLBACK,
+ NULL));
+}
+
+
+/*
+ * 'mxmlSaveAllocString()' - Save an XML tree to an allocated string.
+ *
+ * This function returns a pointer to a string containing the textual
+ * representation of the XML node tree. The string should be freed
+ * using the free() function when you are done with it. NULL is returned
+ * if the node would produce an empty string or if the string cannot be
+ * allocated.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+char * /* O - Allocated string or NULL */
+mxmlSaveAllocString(
+ mxml_node_t *node, /* I - Node to write */
+ mxml_save_cb_t cb) /* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+ int bytes; /* Required bytes */
+ char buffer[8192]; /* Temporary buffer */
+ char *s; /* Allocated string */
+
+
+ /*
+ * Write the node to the temporary buffer...
+ */
+
+ bytes = mxmlSaveString(node, buffer, sizeof(buffer), cb);
+
+ if (bytes <= 0)
+ return (NULL);
+
+ if (bytes < (int)(sizeof(buffer) - 1))
+ {
+ /*
+ * Node fit inside the buffer, so just duplicate that string and
+ * return...
+ */
+
+ return (strdup(buffer));
+ }
+
+ /*
+ * Allocate a buffer of the required size and save the node to the
+ * new buffer...
+ */
+
+ if ((s = malloc(bytes + 1)) == NULL)
+ return (NULL);
+
+ mxmlSaveString(node, s, bytes + 1, cb);
+
+ /*
+ * Return the allocated string...
+ */
+
+ return (s);
+}
+
+
+/*
+ * 'mxmlSaveFd()' - Save an XML tree to a file descriptor.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int /* O - 0 on success, -1 on error. */
+mxmlSaveFd(mxml_node_t *node, /* I - Node to write */
+ int fd, /* I - File descriptor to write to */
+ mxml_save_cb_t cb) /* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+ int col; /* Final column */
+ _mxml_fdbuf_t buf; /* File descriptor buffer */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ /*
+ * Initialize the file descriptor buffer...
+ */
+
+ buf.fd = fd;
+ buf.current = buf.buffer;
+ buf.end = buf.buffer + sizeof(buf.buffer);
+
+ /*
+ * Write the node...
+ */
+
+ if ((col = mxml_write_node(node, &buf, cb, 0, mxml_fd_putc, global)) < 0)
+ return (-1);
+
+ if (col > 0)
+ if (mxml_fd_putc('\n', &buf) < 0)
+ return (-1);
+
+ /*
+ * Flush and return...
+ */
+
+ return (mxml_fd_write(&buf));
+}
+
+
+/*
+ * 'mxmlSaveFile()' - Save an XML tree to a file.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int /* O - 0 on success, -1 on error. */
+mxmlSaveFile(mxml_node_t *node, /* I - Node to write */
+ FILE *fp, /* I - File to write to */
+ mxml_save_cb_t cb) /* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+ int col; /* Final column */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ /*
+ * Write the node...
+ */
+
+ if ((col = mxml_write_node(node, fp, cb, 0, mxml_file_putc, global)) < 0)
+ return (-1);
+
+ if (col > 0)
+ if (putc('\n', fp) < 0)
+ return (-1);
+
+ /*
+ * Return 0 (success)...
+ */
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSaveString()' - Save an XML node tree to a string.
+ *
+ * This function returns the total number of bytes that would be
+ * required for the string but only copies (bufsize - 1) characters
+ * into the specified buffer.
+ *
+ * The callback argument specifies a function that returns a whitespace
+ * string or NULL before and after each element. If MXML_NO_CALLBACK
+ * is specified, whitespace will only be added before MXML_TEXT nodes
+ * with leading whitespace and before attribute names inside opening
+ * element tags.
+ */
+
+int /* O - Size of string */
+mxmlSaveString(mxml_node_t *node, /* I - Node to write */
+ char *buffer, /* I - String buffer */
+ int bufsize, /* I - Size of string buffer */
+ mxml_save_cb_t cb) /* I - Whitespace callback or MXML_NO_CALLBACK */
+{
+ int col; /* Final column */
+ char *ptr[3]; /* Pointers for putc_cb */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ /*
+ * Write the node...
+ */
+
+ ptr[0] = buffer;
+ ptr[1] = buffer + bufsize;
+ ptr[2] = 0;
+
+ if ((col = mxml_write_node(node, ptr, cb, 0, mxml_string_putc, global)) < 0)
+ return (-1);
+
+ if (col > 0)
+ mxml_string_putc('\n', ptr);
+
+ /*
+ * Nul-terminate the buffer...
+ */
+
+ if (ptr[2] != 0)
+ buffer[bufsize - 1] = '\0';
+ else
+ ptr[0][0] = '\0';
+
+ /*
+ * Return the number of characters...
+ */
+
+ return (ptr[0] - buffer);
+}
+
+
+/*
+ * 'mxmlSAXLoadFd()' - Load a file descriptor into an XML node tree
+ * using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t * /* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFd(mxml_node_t *top, /* I - Top node */
+ int fd, /* I - File descriptor to read from */
+ mxml_load_cb_t cb, /* I - Callback function or MXML_NO_CALLBACK */
+ mxml_sax_cb_t sax_cb, /* I - SAX callback or MXML_NO_CALLBACK */
+ void *sax_data) /* I - SAX user data */
+{
+ _mxml_fdbuf_t buf; /* File descriptor buffer */
+
+
+ /*
+ * Initialize the file descriptor buffer...
+ */
+
+ buf.fd = fd;
+ buf.current = buf.buffer;
+ buf.end = buf.buffer;
+
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, &buf, cb, mxml_fd_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadFile()' - Load a file into an XML node tree
+ * using a SAX callback.
+ *
+ * The nodes in the specified file are added to the specified top node.
+ * If no top node is provided, the XML file MUST be well-formed with a
+ * single parent node like <?xml> for the entire file. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t * /* O - First node or NULL if the file could not be read. */
+mxmlSAXLoadFile(
+ mxml_node_t *top, /* I - Top node */
+ FILE *fp, /* I - File to read from */
+ mxml_load_cb_t cb, /* I - Callback function or MXML_NO_CALLBACK */
+ mxml_sax_cb_t sax_cb, /* I - SAX callback or MXML_NO_CALLBACK */
+ void *sax_data) /* I - SAX user data */
+{
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, fp, cb, mxml_file_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSAXLoadString()' - Load a string into an XML node tree
+ * using a SAX callback.
+ *
+ * The nodes in the specified string are added to the specified top node.
+ * If no top node is provided, the XML string MUST be well-formed with a
+ * single parent node like <?xml> for the entire string. The callback
+ * function returns the value type that should be used for child nodes.
+ * If MXML_NO_CALLBACK is specified then all child nodes will be either
+ * MXML_ELEMENT or MXML_TEXT nodes.
+ *
+ * The constants MXML_INTEGER_CALLBACK, MXML_OPAQUE_CALLBACK,
+ * MXML_REAL_CALLBACK, and MXML_TEXT_CALLBACK are defined for loading
+ * child nodes of the specified type.
+ *
+ * The SAX callback must call mxmlRetain() for any nodes that need to
+ * be kept for later use. Otherwise, nodes are deleted when the parent
+ * node is closed or after each data, comment, CDATA, or directive node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t * /* O - First node or NULL if the string has errors. */
+mxmlSAXLoadString(
+ mxml_node_t *top, /* I - Top node */
+ const char *s, /* I - String to load */
+ mxml_load_cb_t cb, /* I - Callback function or MXML_NO_CALLBACK */
+ mxml_sax_cb_t sax_cb, /* I - SAX callback or MXML_NO_CALLBACK */
+ void *sax_data) /* I - SAX user data */
+{
+ /*
+ * Read the XML data...
+ */
+
+ return (mxml_load_data(top, (void *)&s, cb, mxml_string_getc, sax_cb, sax_data));
+}
+
+
+/*
+ * 'mxmlSetCustomHandlers()' - Set the handling functions for custom data.
+ *
+ * The load function accepts a node pointer and a data string and must
+ * return 0 on success and non-zero on error.
+ *
+ * The save function accepts a node pointer and must return a malloc'd
+ * string on success and NULL on error.
+ *
+ */
+
+void
+mxmlSetCustomHandlers(
+ mxml_custom_load_cb_t load, /* I - Load function */
+ mxml_custom_save_cb_t save) /* I - Save function */
+{
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ global->custom_load_cb = load;
+ global->custom_save_cb = save;
+}
+
+
+/*
+ * 'mxmlSetErrorCallback()' - Set the error message callback.
+ */
+
+void
+mxmlSetErrorCallback(mxml_error_cb_t cb)/* I - Error callback function */
+{
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ global->error_cb = cb;
+}
+
+
+/*
+ * 'mxmlSetWrapMargin()' - Set the wrap margin when saving XML data.
+ *
+ * Wrapping is disabled when "column" is 0.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+void
+mxmlSetWrapMargin(int column) /* I - Column for wrapping, 0 to disable wrapping */
+{
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ global->wrap = column;
+}
+
+
+/*
+ * 'mxml_add_char()' - Add a character to a buffer, expanding as needed.
+ */
+
+static int /* O - 0 on success, -1 on error */
+mxml_add_char(int ch, /* I - Character to add */
+ char **bufptr, /* IO - Current position in buffer */
+ char **buffer, /* IO - Current buffer */
+ int *bufsize) /* IO - Current buffer size */
+{
+ char *newbuffer; /* New buffer value */
+
+
+ if (*bufptr >= (*buffer + *bufsize - 4))
+ {
+ /*
+ * Increase the size of the buffer...
+ */
+
+ if (*bufsize < 1024)
+ (*bufsize) *= 2;
+ else
+ (*bufsize) += 1024;
+
+ if ((newbuffer = realloc(*buffer, *bufsize)) == NULL)
+ {
+ free(*buffer);
+
+ mxml_error("Unable to expand string buffer to %d bytes!", *bufsize);
+
+ return (-1);
+ }
+
+ *bufptr = newbuffer + (*bufptr - *buffer);
+ *buffer = newbuffer;
+ }
+
+ if (ch < 0x80)
+ {
+ /*
+ * Single byte ASCII...
+ */
+
+ *(*bufptr)++ = ch;
+ }
+ else if (ch < 0x800)
+ {
+ /*
+ * Two-byte UTF-8...
+ */
+
+ *(*bufptr)++ = 0xc0 | (ch >> 6);
+ *(*bufptr)++ = 0x80 | (ch & 0x3f);
+ }
+ else if (ch < 0x10000)
+ {
+ /*
+ * Three-byte UTF-8...
+ */
+
+ *(*bufptr)++ = 0xe0 | (ch >> 12);
+ *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+ *(*bufptr)++ = 0x80 | (ch & 0x3f);
+ }
+ else
+ {
+ /*
+ * Four-byte UTF-8...
+ */
+
+ *(*bufptr)++ = 0xf0 | (ch >> 18);
+ *(*bufptr)++ = 0x80 | ((ch >> 12) & 0x3f);
+ *(*bufptr)++ = 0x80 | ((ch >> 6) & 0x3f);
+ *(*bufptr)++ = 0x80 | (ch & 0x3f);
+ }
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_fd_getc()' - Read a character from a file descriptor.
+ */
+
+static int /* O - Character or EOF */
+mxml_fd_getc(void *p, /* I - File descriptor buffer */
+ int *encoding) /* IO - Encoding */
+{
+ _mxml_fdbuf_t *buf; /* File descriptor buffer */
+ int ch, /* Current character */
+ temp; /* Temporary character */
+
+
+ /*
+ * Grab the next character in the buffer...
+ */
+
+ buf = (_mxml_fdbuf_t *)p;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ ch = *(buf->current)++;
+
+ switch (*encoding)
+ {
+ case ENCODE_UTF8 :
+ /*
+ * Got a UTF-8 character; convert UTF-8 to Unicode and return...
+ */
+
+ if (!(ch & 0x80))
+ {
+#if DEBUG > 1
+ printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+
+ return (ch);
+ }
+ else if (ch == 0xfe)
+ {
+ /*
+ * UTF-16 big-endian BOM?
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ ch = *(buf->current)++;
+
+ if (ch != 0xff)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16BE;
+
+ return (mxml_fd_getc(p, encoding));
+ }
+ else if (ch == 0xff)
+ {
+ /*
+ * UTF-16 little-endian BOM?
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ ch = *(buf->current)++;
+
+ if (ch != 0xfe)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16LE;
+
+ return (mxml_fd_getc(p, encoding));
+ }
+ else if ((ch & 0xe0) == 0xc0)
+ {
+ /*
+ * Two-byte value...
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+ if (ch < 0x80)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+ }
+ else if ((ch & 0xf0) == 0xe0)
+ {
+ /*
+ * Three-byte value...
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if (ch < 0x800)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+
+ /*
+ * Ignore (strip) Byte Order Mark (BOM)...
+ */
+
+ if (ch == 0xfeff)
+ return (mxml_fd_getc(p, encoding));
+ }
+ else if ((ch & 0xf8) == 0xf0)
+ {
+ /*
+ * Four-byte value...
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ if ((temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if (ch < 0x10000)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+ }
+ else
+ return (EOF);
+ break;
+
+ case ENCODE_UTF16BE :
+ /*
+ * Read UTF-16 big-endian char...
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ ch = (ch << 8) | temp;
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ lch = *(buf->current)++;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ lch = (lch << 8) | temp;
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+ break;
+
+ case ENCODE_UTF16LE :
+ /*
+ * Read UTF-16 little-endian char...
+ */
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ ch |= (temp << 8);
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ lch = *(buf->current)++;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_read(buf) < 0)
+ return (EOF);
+
+ temp = *(buf->current)++;
+
+ lch |= (temp << 8);
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+ break;
+ }
+
+#if DEBUG > 1
+ printf("mxml_fd_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+}
+
+
+/*
+ * 'mxml_fd_putc()' - Write a character to a file descriptor.
+ */
+
+static int /* O - 0 on success, -1 on error */
+mxml_fd_putc(int ch, /* I - Character */
+ void *p) /* I - File descriptor buffer */
+{
+ _mxml_fdbuf_t *buf; /* File descriptor buffer */
+
+
+ /*
+ * Flush the write buffer as needed...
+ */
+
+ buf = (_mxml_fdbuf_t *)p;
+
+ if (buf->current >= buf->end)
+ if (mxml_fd_write(buf) < 0)
+ return (-1);
+
+ *(buf->current)++ = ch;
+
+ /*
+ * Return successfully...
+ */
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_fd_read()' - Read a buffer of data from a file descriptor.
+ */
+
+static int /* O - 0 on success, -1 on error */
+mxml_fd_read(_mxml_fdbuf_t *buf) /* I - File descriptor buffer */
+{
+ int bytes; /* Bytes read... */
+
+
+ /*
+ * Range check input...
+ */
+
+ if (!buf)
+ return (-1);
+
+ /*
+ * Read from the file descriptor...
+ */
+
+ while ((bytes = read(buf->fd, buf->buffer, sizeof(buf->buffer))) < 0)
+#ifdef EINTR
+ if (errno != EAGAIN && errno != EINTR)
+#else
+ if (errno != EAGAIN)
+#endif /* EINTR */
+ return (-1);
+
+ if (bytes == 0)
+ return (-1);
+
+ /*
+ * Update the pointers and return success...
+ */
+
+ buf->current = buf->buffer;
+ buf->end = buf->buffer + bytes;
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_fd_write()' - Write a buffer of data to a file descriptor.
+ */
+
+static int /* O - 0 on success, -1 on error */
+mxml_fd_write(_mxml_fdbuf_t *buf) /* I - File descriptor buffer */
+{
+ int bytes; /* Bytes written */
+ unsigned char *ptr; /* Pointer into buffer */
+
+
+ /*
+ * Range check...
+ */
+
+ if (!buf)
+ return (-1);
+
+ /*
+ * Return 0 if there is nothing to write...
+ */
+
+ if (buf->current == buf->buffer)
+ return (0);
+
+ /*
+ * Loop until we have written everything...
+ */
+
+ for (ptr = buf->buffer; ptr < buf->current; ptr += bytes)
+ if ((bytes = write(buf->fd, ptr, buf->current - ptr)) < 0)
+ return (-1);
+
+ /*
+ * All done, reset pointers and return success...
+ */
+
+ buf->current = buf->buffer;
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_file_getc()' - Get a character from a file.
+ */
+
+static int /* O - Character or EOF */
+mxml_file_getc(void *p, /* I - Pointer to file */
+ int *encoding) /* IO - Encoding */
+{
+ int ch, /* Character from file */
+ temp; /* Temporary character */
+ FILE *fp; /* Pointer to file */
+
+
+ /*
+ * Read a character from the file and see if it is EOF or ASCII...
+ */
+
+ fp = (FILE *)p;
+ ch = getc(fp);
+
+ if (ch == EOF)
+ return (EOF);
+
+ switch (*encoding)
+ {
+ case ENCODE_UTF8 :
+ /*
+ * Got a UTF-8 character; convert UTF-8 to Unicode and return...
+ */
+
+ if (!(ch & 0x80))
+ {
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+
+#if DEBUG > 1
+ printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+ }
+ else if (ch == 0xfe)
+ {
+ /*
+ * UTF-16 big-endian BOM?
+ */
+
+ ch = getc(fp);
+ if (ch != 0xff)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16BE;
+
+ return (mxml_file_getc(p, encoding));
+ }
+ else if (ch == 0xff)
+ {
+ /*
+ * UTF-16 little-endian BOM?
+ */
+
+ ch = getc(fp);
+ if (ch != 0xfe)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16LE;
+
+ return (mxml_file_getc(p, encoding));
+ }
+ else if ((ch & 0xe0) == 0xc0)
+ {
+ /*
+ * Two-byte value...
+ */
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x1f) << 6) | (temp & 0x3f);
+
+ if (ch < 0x80)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+ }
+ else if ((ch & 0xf0) == 0xe0)
+ {
+ /*
+ * Three-byte value...
+ */
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x0f) << 6) | (temp & 0x3f);
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if (ch < 0x800)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+
+ /*
+ * Ignore (strip) Byte Order Mark (BOM)...
+ */
+
+ if (ch == 0xfeff)
+ return (mxml_file_getc(p, encoding));
+ }
+ else if ((ch & 0xf8) == 0xf0)
+ {
+ /*
+ * Four-byte value...
+ */
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x07) << 6) | (temp & 0x3f);
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if ((temp = getc(fp)) == EOF || (temp & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = (ch << 6) | (temp & 0x3f);
+
+ if (ch < 0x10000)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+ }
+ else
+ return (EOF);
+ break;
+
+ case ENCODE_UTF16BE :
+ /*
+ * Read UTF-16 big-endian char...
+ */
+
+ ch = (ch << 8) | getc(fp);
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch = getc(fp);
+ lch = (lch << 8) | getc(fp);
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+ break;
+
+ case ENCODE_UTF16LE :
+ /*
+ * Read UTF-16 little-endian char...
+ */
+
+ ch |= (getc(fp) << 8);
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch = getc(fp);
+ lch |= (getc(fp) << 8);
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+ break;
+ }
+
+#if DEBUG > 1
+ printf("mxml_file_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+}
+
+
+/*
+ * 'mxml_file_putc()' - Write a character to a file.
+ */
+
+static int /* O - 0 on success, -1 on failure */
+mxml_file_putc(int ch, /* I - Character to write */
+ void *p) /* I - Pointer to file */
+{
+ return (putc(ch, (FILE *)p) == EOF ? -1 : 0);
+}
+
+
+/*
+ * 'mxml_get_entity()' - Get the character corresponding to an entity...
+ */
+
+static int /* O - Character value or EOF on error */
+mxml_get_entity(mxml_node_t *parent, /* I - Parent node */
+ void *p, /* I - Pointer to source */
+ int *encoding, /* IO - Character encoding */
+ int (*getc_cb)(void *, int *))
+ /* I - Get character function */
+{
+ int ch; /* Current character */
+ char entity[64], /* Entity string */
+ *entptr; /* Pointer into entity */
+
+
+ entptr = entity;
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ if (ch > 126 || (!isalnum(ch) && ch != '#'))
+ break;
+ else if (entptr < (entity + sizeof(entity) - 1))
+ *entptr++ = ch;
+ else
+ {
+ mxml_error("Entity name too long under parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ break;
+ }
+
+ *entptr = '\0';
+
+ if (ch != ';')
+ {
+ mxml_error("Character entity \"%s\" not terminated under parent <%s>!",
+ entity, parent ? parent->value.element.name : "null");
+ return (EOF);
+ }
+
+ if (entity[0] == '#')
+ {
+ if (entity[1] == 'x')
+ ch = strtol(entity + 2, NULL, 16);
+ else
+ ch = strtol(entity + 1, NULL, 10);
+ }
+ else if ((ch = mxmlEntityGetValue(entity)) < 0)
+ mxml_error("Entity name \"%s;\" not supported under parent <%s>!",
+ entity, parent ? parent->value.element.name : "null");
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x under parent <%s> not allowed by XML standard!",
+ ch, parent ? parent->value.element.name : "null");
+ return (EOF);
+ }
+
+ return (ch);
+}
+
+
+/*
+ * 'mxml_load_data()' - Load data into an XML node tree.
+ */
+
+static mxml_node_t * /* O - First node or NULL if the file could not be read. */
+mxml_load_data(
+ mxml_node_t *top, /* I - Top node */
+ void *p, /* I - Pointer to data */
+ mxml_load_cb_t cb, /* I - Callback function or MXML_NO_CALLBACK */
+ _mxml_getc_cb_t getc_cb, /* I - Read function */
+ mxml_sax_cb_t sax_cb, /* I - SAX callback or MXML_NO_CALLBACK */
+ void *sax_data) /* I - SAX user data */
+{
+ mxml_node_t *node, /* Current node */
+ *first, /* First node added */
+ *parent; /* Current parent node */
+ int ch, /* Character from file */
+ whitespace; /* Non-zero if whitespace seen */
+ char *buffer, /* String buffer */
+ *bufptr; /* Pointer into buffer */
+ int bufsize; /* Size of buffer */
+ mxml_type_t type; /* Current node type */
+ int encoding; /* Character encoding */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+ static const char * const types[] = /* Type strings... */
+ {
+ "MXML_ELEMENT", /* XML element with attributes */
+ "MXML_INTEGER", /* Integer value */
+ "MXML_OPAQUE", /* Opaque string */
+ "MXML_REAL", /* Real value */
+ "MXML_TEXT", /* Text fragment */
+ "MXML_CUSTOM" /* Custom data */
+ };
+
+
+ /*
+ * Read elements and other nodes from the file...
+ */
+
+ if ((buffer = malloc(64)) == NULL)
+ {
+ mxml_error("Unable to allocate string buffer!");
+ return (NULL);
+ }
+
+ bufsize = 64;
+ bufptr = buffer;
+ parent = top;
+ first = NULL;
+ whitespace = 0;
+ encoding = ENCODE_UTF8;
+
+ if (cb && parent)
+ type = (*cb)(parent);
+ else if (parent)
+ type = MXML_TEXT;
+ else
+ type = MXML_IGNORE;
+
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+ {
+ if ((ch == '<' ||
+ (mxml_isspace(ch) && type != MXML_OPAQUE && type != MXML_CUSTOM)) &&
+ bufptr > buffer)
+ {
+ /*
+ * Add a new value node...
+ */
+
+ *bufptr = '\0';
+
+ switch (type)
+ {
+ case MXML_INTEGER :
+ node = mxmlNewInteger(parent, strtol(buffer, &bufptr, 0));
+ break;
+
+ case MXML_OPAQUE :
+ node = mxmlNewOpaque(parent, buffer);
+ break;
+
+ case MXML_REAL :
+ node = mxmlNewReal(parent, strtod(buffer, &bufptr));
+ break;
+
+ case MXML_TEXT :
+ node = mxmlNewText(parent, whitespace, buffer);
+ break;
+
+ case MXML_CUSTOM :
+ if (global->custom_load_cb)
+ {
+ /*
+ * Use the callback to fill in the custom data...
+ */
+
+ node = mxmlNewCustom(parent, NULL, NULL);
+
+ if ((*global->custom_load_cb)(node, buffer))
+ {
+ mxml_error("Bad custom value '%s' in parent <%s>!",
+ buffer, parent ? parent->value.element.name : "null");
+ mxmlDelete(node);
+ node = NULL;
+ }
+ break;
+ }
+
+ default : /* Ignore... */
+ node = NULL;
+ break;
+ }
+
+ if (*bufptr)
+ {
+ /*
+ * Bad integer/real number value...
+ */
+
+ mxml_error("Bad %s value '%s' in parent <%s>!",
+ type == MXML_INTEGER ? "integer" : "real", buffer,
+ parent ? parent->value.element.name : "null");
+ break;
+ }
+
+ bufptr = buffer;
+ whitespace = mxml_isspace(ch) && type == MXML_TEXT;
+
+ if (!node && type != MXML_IGNORE)
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Unable to add value node of type %s to parent <%s>!",
+ types[type], parent ? parent->value.element.name : "null");
+ goto error;
+ }
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (!first && node)
+ first = node;
+ }
+ else if (mxml_isspace(ch) && type == MXML_TEXT)
+ whitespace = 1;
+
+ /*
+ * Add lone whitespace node if we have an element and existing
+ * whitespace...
+ */
+
+ if (ch == '<' && whitespace && type == MXML_TEXT)
+ {
+ if (parent)
+ {
+ node = mxmlNewText(parent, whitespace, "");
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_DATA, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (!first && node)
+ first = node;
+ }
+
+ whitespace = 0;
+ }
+
+ if (ch == '<')
+ {
+ /*
+ * Start of open/close tag...
+ */
+
+ bufptr = buffer;
+
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+ if (mxml_isspace(ch) || ch == '>' || (ch == '/' && bufptr > buffer))
+ break;
+ else if (ch == '<')
+ {
+ mxml_error("Bare < in element!");
+ goto error;
+ }
+ else if (ch == '&')
+ {
+ if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+ else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ else if (((bufptr - buffer) == 1 && buffer[0] == '?') ||
+ ((bufptr - buffer) == 3 && !strncmp(buffer, "!--", 3)) ||
+ ((bufptr - buffer) == 8 && !strncmp(buffer, "![CDATA[", 8)))
+ break;
+
+ *bufptr = '\0';
+
+ if (!strcmp(buffer, "!--"))
+ {
+ /*
+ * Gather rest of comment...
+ */
+
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+ {
+ if (ch == '>' && bufptr > (buffer + 4) &&
+ bufptr[-3] != '-' && bufptr[-2] == '-' && bufptr[-1] == '-')
+ break;
+ else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+
+ /*
+ * Error out if we didn't get the whole comment...
+ */
+
+ if (ch != '>')
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Early EOF in comment node!");
+ goto error;
+ }
+
+
+ /*
+ * Otherwise add this as an element under the current parent...
+ */
+
+ *bufptr = '\0';
+
+ if (!parent && first)
+ {
+ /*
+ * There can only be one root element!
+ */
+
+ mxml_error("<%s> cannot be a second root node after <%s>",
+ buffer, first->value.element.name);
+ goto error;
+ }
+
+ if ((node = mxmlNewElement(parent, buffer)) == NULL)
+ {
+ /*
+ * Just print error for now...
+ */
+
+ mxml_error("Unable to add comment node to parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ break;
+ }
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_COMMENT, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (node && !first)
+ first = node;
+ }
+ else if (!strcmp(buffer, "![CDATA["))
+ {
+ /*
+ * Gather CDATA section...
+ */
+
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+ {
+ if (ch == '>' && !strncmp(bufptr - 2, "]]", 2))
+ break;
+ else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+
+ /*
+ * Error out if we didn't get the whole comment...
+ */
+
+ if (ch != '>')
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Early EOF in CDATA node!");
+ goto error;
+ }
+
+
+ /*
+ * Otherwise add this as an element under the current parent...
+ */
+
+ *bufptr = '\0';
+
+ if (!parent && first)
+ {
+ /*
+ * There can only be one root element!
+ */
+
+ mxml_error("<%s> cannot be a second root node after <%s>",
+ buffer, first->value.element.name);
+ goto error;
+ }
+
+ if ((node = mxmlNewElement(parent, buffer)) == NULL)
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Unable to add CDATA node to parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ goto error;
+ }
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_CDATA, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (node && !first)
+ first = node;
+ }
+ else if (buffer[0] == '?')
+ {
+ /*
+ * Gather rest of processing instruction...
+ */
+
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF)
+ {
+ if (ch == '>' && bufptr > buffer && bufptr[-1] == '?')
+ break;
+ else if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+
+ /*
+ * Error out if we didn't get the whole processing instruction...
+ */
+
+ if (ch != '>')
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Early EOF in processing instruction node!");
+ goto error;
+ }
+
+ /*
+ * Otherwise add this as an element under the current parent...
+ */
+
+ *bufptr = '\0';
+
+ if (!parent && first)
+ {
+ /*
+ * There can only be one root element!
+ */
+
+ mxml_error("<%s> cannot be a second root node after <%s>",
+ buffer, first->value.element.name);
+ goto error;
+ }
+
+ if ((node = mxmlNewElement(parent, buffer)) == NULL)
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Unable to add processing instruction node to parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ goto error;
+ }
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (node)
+ {
+ if (!first)
+ first = node;
+
+ if (!parent)
+ {
+ parent = node;
+
+ if (cb)
+ type = (*cb)(parent);
+ }
+ }
+ }
+ else if (buffer[0] == '!')
+ {
+ /*
+ * Gather rest of declaration...
+ */
+
+ do
+ {
+ if (ch == '>')
+ break;
+ else
+ {
+ if (ch == '&')
+ if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+ }
+ while ((ch = (*getc_cb)(p, &encoding)) != EOF);
+
+ /*
+ * Error out if we didn't get the whole declaration...
+ */
+
+ if (ch != '>')
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Early EOF in declaration node!");
+ goto error;
+ }
+
+ /*
+ * Otherwise add this as an element under the current parent...
+ */
+
+ *bufptr = '\0';
+
+ if (!parent && first)
+ {
+ /*
+ * There can only be one root element!
+ */
+
+ mxml_error("<%s> cannot be a second root node after <%s>",
+ buffer, first->value.element.name);
+ goto error;
+ }
+
+ if ((node = mxmlNewElement(parent, buffer)) == NULL)
+ {
+ /*
+ * Print error and return...
+ */
+
+ mxml_error("Unable to add declaration node to parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ goto error;
+ }
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_DIRECTIVE, sax_data);
+
+ if (!mxmlRelease(node))
+ node = NULL;
+ }
+
+ if (node)
+ {
+ if (!first)
+ first = node;
+
+ if (!parent)
+ {
+ parent = node;
+
+ if (cb)
+ type = (*cb)(parent);
+ }
+ }
+ }
+ else if (buffer[0] == '/')
+ {
+ /*
+ * Handle close tag...
+ */
+
+ if (!parent || strcmp(buffer + 1, parent->value.element.name))
+ {
+ /*
+ * Close tag doesn't match tree; print an error for now...
+ */
+
+ mxml_error("Mismatched close tag <%s> under parent <%s>!",
+ buffer, parent ? parent->value.element.name : "(null)");
+ goto error;
+ }
+
+ /*
+ * Keep reading until we see >...
+ */
+
+ while (ch != '>' && ch != EOF)
+ ch = (*getc_cb)(p, &encoding);
+
+ node = parent;
+ parent = parent->parent;
+
+ if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+ if (!mxmlRelease(node) && first == node)
+ first = NULL;
+ }
+
+ /*
+ * Ascend into the parent and set the value type as needed...
+ */
+
+ if (cb && parent)
+ type = (*cb)(parent);
+ }
+ else
+ {
+ /*
+ * Handle open tag...
+ */
+
+ if (!parent && first)
+ {
+ /*
+ * There can only be one root element!
+ */
+
+ mxml_error("<%s> cannot be a second root node after <%s>",
+ buffer, first->value.element.name);
+ goto error;
+ }
+
+ if ((node = mxmlNewElement(parent, buffer)) == NULL)
+ {
+ /*
+ * Just print error for now...
+ */
+
+ mxml_error("Unable to add element node to parent <%s>!",
+ parent ? parent->value.element.name : "null");
+ goto error;
+ }
+
+ if (mxml_isspace(ch))
+ {
+ if ((ch = mxml_parse_element(node, p, &encoding, getc_cb)) == EOF)
+ goto error;
+ }
+ else if (ch == '/')
+ {
+ if ((ch = (*getc_cb)(p, &encoding)) != '>')
+ {
+ mxml_error("Expected > but got '%c' instead for element <%s/>!",
+ ch, buffer);
+ mxmlDelete(node);
+ goto error;
+ }
+
+ ch = '/';
+ }
+
+ if (sax_cb)
+ (*sax_cb)(node, MXML_SAX_ELEMENT_OPEN, sax_data);
+
+ if (!first)
+ first = node;
+
+ if (ch == EOF)
+ break;
+
+ if (ch != '/')
+ {
+ /*
+ * Descend into this node, setting the value type as needed...
+ */
+
+ parent = node;
+
+ if (cb && parent)
+ type = (*cb)(parent);
+ }
+ else if (sax_cb)
+ {
+ (*sax_cb)(node, MXML_SAX_ELEMENT_CLOSE, sax_data);
+
+ if (!mxmlRelease(node) && first == node)
+ first = NULL;
+ }
+ }
+
+ bufptr = buffer;
+ }
+ else if (ch == '&')
+ {
+ /*
+ * Add character entity to current buffer...
+ */
+
+ if ((ch = mxml_get_entity(parent, p, &encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+ else if (type == MXML_OPAQUE || type == MXML_CUSTOM || !mxml_isspace(ch))
+ {
+ /*
+ * Add character to current buffer...
+ */
+
+ if (mxml_add_char(ch, &bufptr, &buffer, &bufsize))
+ goto error;
+ }
+ }
+
+ /*
+ * Free the string buffer - we don't need it anymore...
+ */
+
+ free(buffer);
+
+ /*
+ * Find the top element and return it...
+ */
+
+ if (parent)
+ {
+ node = parent;
+
+ while (parent != top && parent->parent)
+ parent = parent->parent;
+
+ if (node != parent)
+ {
+ mxml_error("Missing close tag </%s> under parent <%s>!",
+ node->value.element.name,
+ node->parent ? node->parent->value.element.name : "(null)");
+
+ mxmlDelete(first);
+
+ return (NULL);
+ }
+ }
+
+ if (parent)
+ return (parent);
+ else
+ return (first);
+
+ /*
+ * Common error return...
+ */
+
+error:
+
+ mxmlDelete(first);
+
+ free(buffer);
+
+ return (NULL);
+}
+
+
+/*
+ * 'mxml_parse_element()' - Parse an element for any attributes...
+ */
+
+static int /* O - Terminating character */
+mxml_parse_element(
+ mxml_node_t *node, /* I - Element node */
+ void *p, /* I - Data to read from */
+ int *encoding, /* IO - Encoding */
+ _mxml_getc_cb_t getc_cb) /* I - Data callback */
+{
+ int ch, /* Current character in file */
+ quote; /* Quoting character */
+ char *name, /* Attribute name */
+ *value, /* Attribute value */
+ *ptr; /* Pointer into name/value */
+ int namesize, /* Size of name string */
+ valsize; /* Size of value string */
+
+
+ /*
+ * Initialize the name and value buffers...
+ */
+
+ if ((name = malloc(64)) == NULL)
+ {
+ mxml_error("Unable to allocate memory for name!");
+ return (EOF);
+ }
+
+ namesize = 64;
+
+ if ((value = malloc(64)) == NULL)
+ {
+ free(name);
+ mxml_error("Unable to allocate memory for value!");
+ return (EOF);
+ }
+
+ valsize = 64;
+
+ /*
+ * Loop until we hit a >, /, ?, or EOF...
+ */
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ {
+#if DEBUG > 1
+ fprintf(stderr, "parse_element: ch='%c'\n", ch);
+#endif /* DEBUG > 1 */
+
+ /*
+ * Skip leading whitespace...
+ */
+
+ if (mxml_isspace(ch))
+ continue;
+
+ /*
+ * Stop at /, ?, or >...
+ */
+
+ if (ch == '/' || ch == '?')
+ {
+ /*
+ * Grab the > character and print an error if it isn't there...
+ */
+
+ quote = (*getc_cb)(p, encoding);
+
+ if (quote != '>')
+ {
+ mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+ ch, node->value.element.name, quote);
+ goto error;
+ }
+
+ break;
+ }
+ else if (ch == '<')
+ {
+ mxml_error("Bare < in element %s!", node->value.element.name);
+ goto error;
+ }
+ else if (ch == '>')
+ break;
+
+ /*
+ * Read the attribute name...
+ */
+
+ name[0] = ch;
+ ptr = name + 1;
+
+ if (ch == '\"' || ch == '\'')
+ {
+ /*
+ * Name is in quotes, so get a quoted string...
+ */
+
+ quote = ch;
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ {
+ if (ch == '&')
+ if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &ptr, &name, &namesize))
+ goto error;
+
+ if (ch == quote)
+ break;
+ }
+ }
+ else
+ {
+ /*
+ * Grab an normal, non-quoted name...
+ */
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>' ||
+ ch == '?')
+ break;
+ else
+ {
+ if (ch == '&')
+ if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &ptr, &name, &namesize))
+ goto error;
+ }
+ }
+
+ *ptr = '\0';
+
+ if (mxmlElementGetAttr(node, name))
+ goto error;
+
+ while (ch != EOF && mxml_isspace(ch))
+ ch = (*getc_cb)(p, encoding);
+
+ if (ch == '=')
+ {
+ /*
+ * Read the attribute value...
+ */
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF && mxml_isspace(ch));
+
+ if (ch == EOF)
+ {
+ mxml_error("Missing value for attribute '%s' in element %s!",
+ name, node->value.element.name);
+ goto error;
+ }
+
+ if (ch == '\'' || ch == '\"')
+ {
+ /*
+ * Read quoted value...
+ */
+
+ quote = ch;
+ ptr = value;
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ if (ch == quote)
+ break;
+ else
+ {
+ if (ch == '&')
+ if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &ptr, &value, &valsize))
+ goto error;
+ }
+
+ *ptr = '\0';
+ }
+ else
+ {
+ /*
+ * Read unquoted value...
+ */
+
+ value[0] = ch;
+ ptr = value + 1;
+
+ while ((ch = (*getc_cb)(p, encoding)) != EOF)
+ if (mxml_isspace(ch) || ch == '=' || ch == '/' || ch == '>')
+ break;
+ else
+ {
+ if (ch == '&')
+ if ((ch = mxml_get_entity(node, p, encoding, getc_cb)) == EOF)
+ goto error;
+
+ if (mxml_add_char(ch, &ptr, &value, &valsize))
+ goto error;
+ }
+
+ *ptr = '\0';
+ }
+
+ /*
+ * Set the attribute with the given string value...
+ */
+
+ mxmlElementSetAttr(node, name, value);
+ }
+ else
+ {
+ mxml_error("Missing value for attribute '%s' in element %s!",
+ name, node->value.element.name);
+ goto error;
+ }
+
+ /*
+ * Check the end character...
+ */
+
+ if (ch == '/' || ch == '?')
+ {
+ /*
+ * Grab the > character and print an error if it isn't there...
+ */
+
+ quote = (*getc_cb)(p, encoding);
+
+ if (quote != '>')
+ {
+ mxml_error("Expected '>' after '%c' for element %s, but got '%c'!",
+ ch, node->value.element.name, quote);
+ ch = EOF;
+ }
+
+ break;
+ }
+ else if (ch == '>')
+ break;
+ }
+
+ /*
+ * Free the name and value buffers and return...
+ */
+
+ free(name);
+ free(value);
+
+ return (ch);
+
+ /*
+ * Common error return point...
+ */
+
+error:
+
+ free(name);
+ free(value);
+
+ return (EOF);
+}
+
+
+/*
+ * 'mxml_string_getc()' - Get a character from a string.
+ */
+
+static int /* O - Character or EOF */
+mxml_string_getc(void *p, /* I - Pointer to file */
+ int *encoding) /* IO - Encoding */
+{
+ int ch; /* Character */
+ const char **s; /* Pointer to string pointer */
+
+
+ s = (const char **)p;
+
+ if ((ch = (*s)[0] & 255) != 0 || *encoding == ENCODE_UTF16LE)
+ {
+ /*
+ * Got character; convert UTF-8 to integer and return...
+ */
+
+ (*s)++;
+
+ switch (*encoding)
+ {
+ case ENCODE_UTF8 :
+ if (!(ch & 0x80))
+ {
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+
+ return (ch);
+ }
+ else if (ch == 0xfe)
+ {
+ /*
+ * UTF-16 big-endian BOM?
+ */
+
+ if (((*s)[0] & 255) != 0xff)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16BE;
+ (*s)++;
+
+ return (mxml_string_getc(p, encoding));
+ }
+ else if (ch == 0xff)
+ {
+ /*
+ * UTF-16 little-endian BOM?
+ */
+
+ if (((*s)[0] & 255) != 0xfe)
+ return (EOF);
+
+ *encoding = ENCODE_UTF16LE;
+ (*s)++;
+
+ return (mxml_string_getc(p, encoding));
+ }
+ else if ((ch & 0xe0) == 0xc0)
+ {
+ /*
+ * Two-byte value...
+ */
+
+ if (((*s)[0] & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((ch & 0x1f) << 6) | ((*s)[0] & 0x3f);
+
+ (*s)++;
+
+ if (ch < 0x80)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+ }
+ else if ((ch & 0xf0) == 0xe0)
+ {
+ /*
+ * Three-byte value...
+ */
+
+ if (((*s)[0] & 0xc0) != 0x80 ||
+ ((*s)[1] & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((((ch & 0x0f) << 6) | ((*s)[0] & 0x3f)) << 6) | ((*s)[1] & 0x3f);
+
+ (*s) += 2;
+
+ if (ch < 0x800)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+
+ /*
+ * Ignore (strip) Byte Order Mark (BOM)...
+ */
+
+ if (ch == 0xfeff)
+ return (mxml_string_getc(p, encoding));
+
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+ }
+ else if ((ch & 0xf8) == 0xf0)
+ {
+ /*
+ * Four-byte value...
+ */
+
+ if (((*s)[0] & 0xc0) != 0x80 ||
+ ((*s)[1] & 0xc0) != 0x80 ||
+ ((*s)[2] & 0xc0) != 0x80)
+ return (EOF);
+
+ ch = ((((((ch & 0x07) << 6) | ((*s)[0] & 0x3f)) << 6) |
+ ((*s)[1] & 0x3f)) << 6) | ((*s)[2] & 0x3f);
+
+ (*s) += 3;
+
+ if (ch < 0x10000)
+ {
+ mxml_error("Invalid UTF-8 sequence for character 0x%04x!", ch);
+ return (EOF);
+ }
+
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+ }
+ else
+ return (EOF);
+
+ case ENCODE_UTF16BE :
+ /*
+ * Read UTF-16 big-endian char...
+ */
+
+ ch = (ch << 8) | ((*s)[0] & 255);
+ (*s) ++;
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch; /* Lower word */
+
+
+ if (!(*s)[0])
+ return (EOF);
+
+ lch = (((*s)[0] & 255) << 8) | ((*s)[1] & 255);
+ (*s) += 2;
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+
+ case ENCODE_UTF16LE :
+ /*
+ * Read UTF-16 little-endian char...
+ */
+
+ ch = ch | (((*s)[0] & 255) << 8);
+
+ if (!ch)
+ {
+ (*s) --;
+ return (EOF);
+ }
+
+ (*s) ++;
+
+ if (mxml_bad_char(ch))
+ {
+ mxml_error("Bad control character 0x%02x not allowed by XML standard!",
+ ch);
+ return (EOF);
+ }
+ else if (ch >= 0xd800 && ch <= 0xdbff)
+ {
+ /*
+ * Multi-word UTF-16 char...
+ */
+
+ int lch; /* Lower word */
+
+
+ if (!(*s)[1])
+ return (EOF);
+
+ lch = (((*s)[1] & 255) << 8) | ((*s)[0] & 255);
+ (*s) += 2;
+
+ if (lch < 0xdc00 || lch >= 0xdfff)
+ return (EOF);
+
+ ch = (((ch & 0x3ff) << 10) | (lch & 0x3ff)) + 0x10000;
+ }
+
+#if DEBUG > 1
+ printf("mxml_string_getc: %c (0x%04x)\n", ch < ' ' ? '.' : ch, ch);
+#endif /* DEBUG > 1 */
+
+ return (ch);
+ }
+ }
+
+ return (EOF);
+}
+
+
+/*
+ * 'mxml_string_putc()' - Write a character to a string.
+ */
+
+static int /* O - 0 on success, -1 on failure */
+mxml_string_putc(int ch, /* I - Character to write */
+ void *p) /* I - Pointer to string pointers */
+{
+ char **pp; /* Pointer to string pointers */
+
+
+ pp = (char **)p;
+
+ if (pp[2] == 0) {
+ if (pp[0] < pp[1])
+ pp[0][0] = ch;
+ else
+ pp[2] = (char *)1;
+ }
+
+ pp[0] ++;
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_write_name()' - Write a name string.
+ */
+
+static int /* O - 0 on success, -1 on failure */
+mxml_write_name(const char *s, /* I - Name to write */
+ void *p, /* I - Write pointer */
+ int (*putc_cb)(int, void *))
+ /* I - Write callback */
+{
+ char quote; /* Quote character */
+ const char *name; /* Entity name */
+
+
+ if (*s == '\"' || *s == '\'')
+ {
+ /*
+ * Write a quoted name string...
+ */
+
+ if ((*putc_cb)(*s, p) < 0)
+ return (-1);
+
+ quote = *s++;
+
+ while (*s && *s != quote)
+ {
+ if ((name = mxmlEntityGetName(*s)) != NULL)
+ {
+ if ((*putc_cb)('&', p) < 0)
+ return (-1);
+
+ while (*name)
+ {
+ if ((*putc_cb)(*name, p) < 0)
+ return (-1);
+
+ name ++;
+ }
+
+ if ((*putc_cb)(';', p) < 0)
+ return (-1);
+ }
+ else if ((*putc_cb)(*s, p) < 0)
+ return (-1);
+
+ s ++;
+ }
+
+ /*
+ * Write the end quote...
+ */
+
+ if ((*putc_cb)(quote, p) < 0)
+ return (-1);
+ }
+ else
+ {
+ /*
+ * Write a non-quoted name string...
+ */
+
+ while (*s)
+ {
+ if ((*putc_cb)(*s, p) < 0)
+ return (-1);
+
+ s ++;
+ }
+ }
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_write_node()' - Save an XML node to a file.
+ */
+
+static int /* O - Column or -1 on error */
+mxml_write_node(mxml_node_t *node, /* I - Node to write */
+ void *p, /* I - File to write to */
+ mxml_save_cb_t cb, /* I - Whitespace callback */
+ int col, /* I - Current column */
+ _mxml_putc_cb_t putc_cb,/* I - Output callback */
+ _mxml_global_t *global)/* I - Global data */
+{
+ int i, /* Looping var */
+ width; /* Width of attr + value */
+ mxml_attr_t *attr; /* Current attribute */
+ char s[255]; /* Temporary string */
+
+
+ /*
+ * Print the node value...
+ */
+
+ switch (node->type)
+ {
+ case MXML_ELEMENT :
+ col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_OPEN, col, putc_cb);
+
+ if ((*putc_cb)('<', p) < 0)
+ return (-1);
+ if (node->value.element.name[0] == '?' ||
+ !strncmp(node->value.element.name, "!--", 3) ||
+ !strncmp(node->value.element.name, "![CDATA[", 8))
+ {
+ /*
+ * Comments, CDATA, and processing instructions do not
+ * use character entities.
+ */
+
+ const char *ptr; /* Pointer into name */
+
+
+ for (ptr = node->value.element.name; *ptr; ptr ++)
+ if ((*putc_cb)(*ptr, p) < 0)
+ return (-1);
+ }
+ else if (mxml_write_name(node->value.element.name, p, putc_cb) < 0)
+ return (-1);
+
+ col += strlen(node->value.element.name) + 1;
+
+ for (i = node->value.element.num_attrs, attr = node->value.element.attrs;
+ i > 0;
+ i --, attr ++)
+ {
+ width = strlen(attr->name);
+
+ if (attr->value)
+ width += strlen(attr->value) + 3;
+
+ if (global->wrap > 0 && (col + width) > global->wrap)
+ {
+ if ((*putc_cb)('\n', p) < 0)
+ return (-1);
+
+ col = 0;
+ }
+ else
+ {
+ if ((*putc_cb)(' ', p) < 0)
+ return (-1);
+
+ col ++;
+ }
+
+ if (mxml_write_name(attr->name, p, putc_cb) < 0)
+ return (-1);
+
+ if (attr->value)
+ {
+ if ((*putc_cb)('=', p) < 0)
+ return (-1);
+ if ((*putc_cb)('\"', p) < 0)
+ return (-1);
+ if (mxml_write_string(attr->value, p, putc_cb) < 0)
+ return (-1);
+ if ((*putc_cb)('\"', p) < 0)
+ return (-1);
+ }
+
+ col += width;
+ }
+
+ if (node->child)
+ {
+ /*
+ * Write children...
+ */
+
+ mxml_node_t *child; /* Current child */
+
+
+ if ((*putc_cb)('>', p) < 0)
+ return (-1);
+ else
+ col ++;
+
+ col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+
+ for (child = node->child; child; child = child->next)
+ {
+ if ((col = mxml_write_node(child, p, cb, col, putc_cb, global)) < 0)
+ return (-1);
+ }
+
+ /*
+ * The ? and ! elements are special-cases and have no end tags...
+ */
+
+ if (node->value.element.name[0] != '!' &&
+ node->value.element.name[0] != '?')
+ {
+ col = mxml_write_ws(node, p, cb, MXML_WS_BEFORE_CLOSE, col, putc_cb);
+
+ if ((*putc_cb)('<', p) < 0)
+ return (-1);
+ if ((*putc_cb)('/', p) < 0)
+ return (-1);
+ if (mxml_write_string(node->value.element.name, p, putc_cb) < 0)
+ return (-1);
+ if ((*putc_cb)('>', p) < 0)
+ return (-1);
+
+ col += strlen(node->value.element.name) + 3;
+
+ col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_CLOSE, col, putc_cb);
+ }
+ }
+ else if (node->value.element.name[0] == '!' ||
+ node->value.element.name[0] == '?')
+ {
+ /*
+ * The ? and ! elements are special-cases...
+ */
+
+ if ((*putc_cb)('>', p) < 0)
+ return (-1);
+ else
+ col ++;
+
+ col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+ }
+ else
+ {
+ if ((*putc_cb)(' ', p) < 0)
+ return (-1);
+ if ((*putc_cb)('/', p) < 0)
+ return (-1);
+ if ((*putc_cb)('>', p) < 0)
+ return (-1);
+
+ col += 3;
+
+ col = mxml_write_ws(node, p, cb, MXML_WS_AFTER_OPEN, col, putc_cb);
+ }
+ break;
+
+ case MXML_INTEGER :
+ if (node->prev)
+ {
+ if (global->wrap > 0 && col > global->wrap)
+ {
+ if ((*putc_cb)('\n', p) < 0)
+ return (-1);
+
+ col = 0;
+ }
+ else if ((*putc_cb)(' ', p) < 0)
+ return (-1);
+ else
+ col ++;
+ }
+
+ sprintf(s, "%d", node->value.integer);
+ if (mxml_write_string(s, p, putc_cb) < 0)
+ return (-1);
+
+ col += strlen(s);
+ break;
+
+ case MXML_OPAQUE :
+ if (mxml_write_string(node->value.opaque, p, putc_cb) < 0)
+ return (-1);
+
+ col += strlen(node->value.opaque);
+ break;
+
+ case MXML_REAL :
+ if (node->prev)
+ {
+ if (global->wrap > 0 && col > global->wrap)
+ {
+ if ((*putc_cb)('\n', p) < 0)
+ return (-1);
+
+ col = 0;
+ }
+ else if ((*putc_cb)(' ', p) < 0)
+ return (-1);
+ else
+ col ++;
+ }
+
+ sprintf(s, "%f", node->value.real);
+ if (mxml_write_string(s, p, putc_cb) < 0)
+ return (-1);
+
+ col += strlen(s);
+ break;
+
+ case MXML_TEXT :
+ if (node->value.text.whitespace && col > 0)
+ {
+ if (global->wrap > 0 && col > global->wrap)
+ {
+ if ((*putc_cb)('\n', p) < 0)
+ return (-1);
+
+ col = 0;
+ }
+ else if ((*putc_cb)(' ', p) < 0)
+ return (-1);
+ else
+ col ++;
+ }
+
+ if (mxml_write_string(node->value.text.string, p, putc_cb) < 0)
+ return (-1);
+
+ col += strlen(node->value.text.string);
+ break;
+
+ case MXML_CUSTOM :
+ if (global->custom_save_cb)
+ {
+ char *data; /* Custom data string */
+ const char *newline; /* Last newline in string */
+
+
+ if ((data = (*global->custom_save_cb)(node)) == NULL)
+ return (-1);
+
+ if (mxml_write_string(data, p, putc_cb) < 0)
+ return (-1);
+
+ if ((newline = strrchr(data, '\n')) == NULL)
+ col += strlen(data);
+ else
+ col = strlen(newline);
+
+ free(data);
+ break;
+ }
+
+ default : /* Should never happen */
+ return (-1);
+ }
+
+ return (col);
+}
+
+
+/*
+ * 'mxml_write_string()' - Write a string, escaping & and < as needed.
+ */
+
+static int /* O - 0 on success, -1 on failure */
+mxml_write_string(
+ const char *s, /* I - String to write */
+ void *p, /* I - Write pointer */
+ _mxml_putc_cb_t putc_cb) /* I - Write callback */
+{
+ const char *name; /* Entity name, if any */
+
+
+ while (*s)
+ {
+ if ((name = mxmlEntityGetName(*s)) != NULL)
+ {
+ if ((*putc_cb)('&', p) < 0)
+ return (-1);
+
+ while (*name)
+ {
+ if ((*putc_cb)(*name, p) < 0)
+ return (-1);
+ name ++;
+ }
+
+ if ((*putc_cb)(';', p) < 0)
+ return (-1);
+ }
+ else if ((*putc_cb)(*s, p) < 0)
+ return (-1);
+
+ s ++;
+ }
+
+ return (0);
+}
+
+
+/*
+ * 'mxml_write_ws()' - Do whitespace callback...
+ */
+
+static int /* O - New column */
+mxml_write_ws(mxml_node_t *node, /* I - Current node */
+ void *p, /* I - Write pointer */
+ mxml_save_cb_t cb, /* I - Callback function */
+ int ws, /* I - Where value */
+ int col, /* I - Current column */
+ _mxml_putc_cb_t putc_cb) /* I - Write callback */
+{
+ const char *s; /* Whitespace string */
+
+
+ if (cb && (s = (*cb)(node, ws)) != NULL)
+ {
+ while (*s)
+ {
+ if ((*putc_cb)(*s, p) < 0)
+ return (-1);
+ else if (*s == '\n')
+ col = 0;
+ else if (*s == '\t')
+ {
+ col += MXML_TAB;
+ col = col - (col % MXML_TAB);
+ }
+ else
+ col ++;
+
+ s ++;
+ }
+ }
+
+ return (col);
+}
+
+
+/*
+ * End of "$Id: mxml-file.c 455 2014-01-05 03:28:03Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-get.c b/tools/gator/daemon/mxml/mxml-get.c
new file mode 100644
index 0000000..40ed3d0
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-get.c
@@ -0,0 +1,452 @@
+/*
+ * "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node get functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlGetCDATA()' - Get the value for a CDATA node.
+ *
+ * @code NULL@ is returned if the node is not a CDATA element.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char * /* O - CDATA value or NULL */
+mxmlGetCDATA(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT ||
+ strncmp(node->value.element.name, "![CDATA[", 8))
+ return (NULL);
+
+ /*
+ * Return the text following the CDATA declaration...
+ */
+
+ return (node->value.element.name + 8);
+}
+
+
+/*
+ * 'mxmlGetCustom()' - Get the value for a custom node.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a custom
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const void * /* O - Custom value or NULL */
+mxmlGetCustom(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the integer value...
+ */
+
+ if (node->type == MXML_CUSTOM)
+ return (node->value.custom.data);
+ else if (node->type == MXML_ELEMENT &&
+ node->child &&
+ node->child->type == MXML_CUSTOM)
+ return (node->child->value.custom.data);
+ else
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlGetElement()' - Get the name for an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char * /* O - Element name or NULL */
+mxmlGetElement(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT)
+ return (NULL);
+
+ /*
+ * Return the element name...
+ */
+
+ return (node->value.element.name);
+}
+
+
+/*
+ * 'mxmlGetFirstChild()' - Get the first child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t * /* O - First child or NULL */
+mxmlGetFirstChild(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT)
+ return (NULL);
+
+ /*
+ * Return the first child node...
+ */
+
+ return (node->child);
+}
+
+
+/*
+ * 'mxmlGetInteger()' - Get the integer value from the specified node or its
+ * first child.
+ *
+ * 0 is returned if the node (or its first child) is not an integer value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int /* O - Integer value or 0 */
+mxmlGetInteger(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (0);
+
+ /*
+ * Return the integer value...
+ */
+
+ if (node->type == MXML_INTEGER)
+ return (node->value.integer);
+ else if (node->type == MXML_ELEMENT &&
+ node->child &&
+ node->child->type == MXML_INTEGER)
+ return (node->child->value.integer);
+ else
+ return (0);
+}
+
+
+/*
+ * 'mxmlGetLastChild()' - Get the last child of an element node.
+ *
+ * @code NULL@ is returned if the node is not an element node or if the node
+ * has no children.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t * /* O - Last child or NULL */
+mxmlGetLastChild(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT)
+ return (NULL);
+
+ /*
+ * Return the node type...
+ */
+
+ return (node->last_child);
+}
+
+
+/*
+ * 'mxmlGetNextSibling()' - Get the next node for the current parent.
+ *
+ * @code NULL@ is returned if this is the last child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t *
+mxmlGetNextSibling(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the node type...
+ */
+
+ return (node->next);
+}
+
+
+/*
+ * 'mxmlGetOpaque()' - Get an opaque string value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not an opaque
+ * value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char * /* O - Opaque string or NULL */
+mxmlGetOpaque(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the integer value...
+ */
+
+ if (node->type == MXML_OPAQUE)
+ return (node->value.opaque);
+ else if (node->type == MXML_ELEMENT &&
+ node->child &&
+ node->child->type == MXML_OPAQUE)
+ return (node->child->value.opaque);
+ else
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlGetParent()' - Get the parent node.
+ *
+ * @code NULL@ is returned for a root node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t * /* O - Parent node or NULL */
+mxmlGetParent(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the node type...
+ */
+
+ return (node->parent);
+}
+
+
+/*
+ * 'mxmlGetPrevSibling()' - Get the previous node for the current parent.
+ *
+ * @code NULL@ is returned if this is the first child for the current parent.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t * /* O - Previous node or NULL */
+mxmlGetPrevSibling(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the node type...
+ */
+
+ return (node->prev);
+}
+
+
+/*
+ * 'mxmlGetReal()' - Get the real value for a node or its first child.
+ *
+ * 0.0 is returned if the node (or its first child) is not a real value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+double /* O - Real value or 0.0 */
+mxmlGetReal(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (0.0);
+
+ /*
+ * Return the integer value...
+ */
+
+ if (node->type == MXML_REAL)
+ return (node->value.real);
+ else if (node->type == MXML_ELEMENT &&
+ node->child &&
+ node->child->type == MXML_REAL)
+ return (node->child->value.real);
+ else
+ return (0.0);
+}
+
+
+/*
+ * 'mxmlGetText()' - Get the text value for a node or its first child.
+ *
+ * @code NULL@ is returned if the node (or its first child) is not a text node.
+ * The "whitespace" argument can be NULL.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+const char * /* O - Text string or NULL */
+mxmlGetText(mxml_node_t *node, /* I - Node to get */
+ int *whitespace) /* O - 1 if string is preceded by whitespace, 0 otherwise */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ {
+ if (whitespace)
+ *whitespace = 0;
+
+ return (NULL);
+ }
+
+ /*
+ * Return the integer value...
+ */
+
+ if (node->type == MXML_TEXT)
+ {
+ if (whitespace)
+ *whitespace = node->value.text.whitespace;
+
+ return (node->value.text.string);
+ }
+ else if (node->type == MXML_ELEMENT &&
+ node->child &&
+ node->child->type == MXML_TEXT)
+ {
+ if (whitespace)
+ *whitespace = node->child->value.text.whitespace;
+
+ return (node->child->value.text.string);
+ }
+ else
+ {
+ if (whitespace)
+ *whitespace = 0;
+
+ return (NULL);
+ }
+}
+
+
+/*
+ * 'mxmlGetType()' - Get the node type.
+ *
+ * @code MXML_IGNORE@ is returned if "node" is @code NULL@.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_type_t /* O - Type of node */
+mxmlGetType(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (MXML_IGNORE);
+
+ /*
+ * Return the node type...
+ */
+
+ return (node->type);
+}
+
+
+/*
+ * 'mxmlGetUserData()' - Get the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+void * /* O - User data pointer */
+mxmlGetUserData(mxml_node_t *node) /* I - Node to get */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Return the user data pointer...
+ */
+
+ return (node->user_data);
+}
+
+
+/*
+ * End of "$Id: mxml-get.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-index.c b/tools/gator/daemon/mxml/mxml-index.c
new file mode 100644
index 0000000..1081439
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-index.c
@@ -0,0 +1,659 @@
+/*
+ * "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Index support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Sort functions...
+ */
+
+static int index_compare(mxml_index_t *ind, mxml_node_t *first,
+ mxml_node_t *second);
+static int index_find(mxml_index_t *ind, const char *element,
+ const char *value, mxml_node_t *node);
+static void index_sort(mxml_index_t *ind, int left, int right);
+
+
+/*
+ * 'mxmlIndexDelete()' - Delete an index.
+ */
+
+void
+mxmlIndexDelete(mxml_index_t *ind) /* I - Index to delete */
+{
+ /*
+ * Range check input..
+ */
+
+ if (!ind)
+ return;
+
+ /*
+ * Free memory...
+ */
+
+ if (ind->attr)
+ free(ind->attr);
+
+ if (ind->alloc_nodes)
+ free(ind->nodes);
+
+ free(ind);
+}
+
+
+/*
+ * 'mxmlIndexEnum()' - Return the next node in the index.
+ *
+ * Nodes are returned in the sorted order of the index.
+ */
+
+mxml_node_t * /* O - Next node or NULL if there is none */
+mxmlIndexEnum(mxml_index_t *ind) /* I - Index to enumerate */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!ind)
+ return (NULL);
+
+ /*
+ * Return the next node...
+ */
+
+ if (ind->cur_node < ind->num_nodes)
+ return (ind->nodes[ind->cur_node ++]);
+ else
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexFind()' - Find the next matching node.
+ *
+ * You should call mxmlIndexReset() prior to using this function for
+ * the first time with a particular set of "element" and "value"
+ * strings. Passing NULL for both "element" and "value" is equivalent
+ * to calling mxmlIndexEnum().
+ */
+
+mxml_node_t * /* O - Node or NULL if none found */
+mxmlIndexFind(mxml_index_t *ind, /* I - Index to search */
+ const char *element, /* I - Element name to find, if any */
+ const char *value) /* I - Attribute value, if any */
+{
+ int diff, /* Difference between names */
+ current, /* Current entity in search */
+ first, /* First entity in search */
+ last; /* Last entity in search */
+
+
+#ifdef DEBUG
+ printf("mxmlIndexFind(ind=%p, element=\"%s\", value=\"%s\")\n",
+ ind, element ? element : "(null)", value ? value : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!ind || (!ind->attr && value))
+ {
+#ifdef DEBUG
+ puts(" returning NULL...");
+ printf(" ind->attr=\"%s\"\n", ind->attr ? ind->attr : "(null)");
+#endif /* DEBUG */
+
+ return (NULL);
+ }
+
+ /*
+ * If both element and value are NULL, just enumerate the nodes in the
+ * index...
+ */
+
+ if (!element && !value)
+ return (mxmlIndexEnum(ind));
+
+ /*
+ * If there are no nodes in the index, return NULL...
+ */
+
+ if (!ind->num_nodes)
+ {
+#ifdef DEBUG
+ puts(" returning NULL...");
+ puts(" no nodes!");
+#endif /* DEBUG */
+
+ return (NULL);
+ }
+
+ /*
+ * If cur_node == 0, then find the first matching node...
+ */
+
+ if (ind->cur_node == 0)
+ {
+ /*
+ * Find the first node using a modified binary search algorithm...
+ */
+
+ first = 0;
+ last = ind->num_nodes - 1;
+
+#ifdef DEBUG
+ printf(" find first time, num_nodes=%d...\n", ind->num_nodes);
+#endif /* DEBUG */
+
+ while ((last - first) > 1)
+ {
+ current = (first + last) / 2;
+
+#ifdef DEBUG
+ printf(" first=%d, last=%d, current=%d\n", first, last, current);
+#endif /* DEBUG */
+
+ if ((diff = index_find(ind, element, value, ind->nodes[current])) == 0)
+ {
+ /*
+ * Found a match, move back to find the first...
+ */
+
+#ifdef DEBUG
+ puts(" match!");
+#endif /* DEBUG */
+
+ while (current > 0 &&
+ !index_find(ind, element, value, ind->nodes[current - 1]))
+ current --;
+
+#ifdef DEBUG
+ printf(" returning first match=%d\n", current);
+#endif /* DEBUG */
+
+ /*
+ * Return the first match and save the index to the next...
+ */
+
+ ind->cur_node = current + 1;
+
+ return (ind->nodes[current]);
+ }
+ else if (diff < 0)
+ last = current;
+ else
+ first = current;
+
+#ifdef DEBUG
+ printf(" diff=%d\n", diff);
+#endif /* DEBUG */
+ }
+
+ /*
+ * If we get this far, then we found exactly 0 or 1 matches...
+ */
+
+ for (current = first; current <= last; current ++)
+ if (!index_find(ind, element, value, ind->nodes[current]))
+ {
+ /*
+ * Found exactly one (or possibly two) match...
+ */
+
+#ifdef DEBUG
+ printf(" returning only match %d...\n", current);
+#endif /* DEBUG */
+
+ ind->cur_node = current + 1;
+
+ return (ind->nodes[current]);
+ }
+
+ /*
+ * No matches...
+ */
+
+ ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+ puts(" returning NULL...");
+#endif /* DEBUG */
+
+ return (NULL);
+ }
+ else if (ind->cur_node < ind->num_nodes &&
+ !index_find(ind, element, value, ind->nodes[ind->cur_node]))
+ {
+ /*
+ * Return the next matching node...
+ */
+
+#ifdef DEBUG
+ printf(" returning next match %d...\n", ind->cur_node);
+#endif /* DEBUG */
+
+ return (ind->nodes[ind->cur_node ++]);
+ }
+
+ /*
+ * If we get this far, then we have no matches...
+ */
+
+ ind->cur_node = ind->num_nodes;
+
+#ifdef DEBUG
+ puts(" returning NULL...");
+#endif /* DEBUG */
+
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlIndexGetCount()' - Get the number of nodes in an index.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int /* I - Number of nodes in index */
+mxmlIndexGetCount(mxml_index_t *ind) /* I - Index of nodes */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!ind)
+ return (0);
+
+ /*
+ * Return the number of nodes in the index...
+ */
+
+ return (ind->num_nodes);
+}
+
+
+/*
+ * 'mxmlIndexNew()' - Create a new index.
+ *
+ * The index will contain all nodes that contain the named element and/or
+ * attribute. If both "element" and "attr" are NULL, then the index will
+ * contain a sorted list of the elements in the node tree. Nodes are
+ * sorted by element name and optionally by attribute value if the "attr"
+ * argument is not NULL.
+ */
+
+mxml_index_t * /* O - New index */
+mxmlIndexNew(mxml_node_t *node, /* I - XML node tree */
+ const char *element, /* I - Element to index or NULL for all */
+ const char *attr) /* I - Attribute to index or NULL for none */
+{
+ mxml_index_t *ind; /* New index */
+ mxml_node_t *current, /* Current node in index */
+ **temp; /* Temporary node pointer array */
+
+
+ /*
+ * Range check input...
+ */
+
+#ifdef DEBUG
+ printf("mxmlIndexNew(node=%p, element=\"%s\", attr=\"%s\")\n",
+ node, element ? element : "(null)", attr ? attr : "(null)");
+#endif /* DEBUG */
+
+ if (!node)
+ return (NULL);
+
+ /*
+ * Create a new index...
+ */
+
+ if ((ind = calloc(1, sizeof(mxml_index_t))) == NULL)
+ {
+ mxml_error("Unable to allocate %d bytes for index - %s",
+ sizeof(mxml_index_t), strerror(errno));
+ return (NULL);
+ }
+
+ if (attr)
+ ind->attr = strdup(attr);
+
+ if (!element && !attr)
+ current = node;
+ else
+ current = mxmlFindElement(node, node, element, attr, NULL, MXML_DESCEND);
+
+ while (current)
+ {
+ if (ind->num_nodes >= ind->alloc_nodes)
+ {
+ if (!ind->alloc_nodes)
+ temp = malloc(64 * sizeof(mxml_node_t *));
+ else
+ temp = realloc(ind->nodes, (ind->alloc_nodes + 64) * sizeof(mxml_node_t *));
+
+ if (!temp)
+ {
+ /*
+ * Unable to allocate memory for the index, so abort...
+ */
+
+ mxml_error("Unable to allocate %d bytes for index: %s",
+ (ind->alloc_nodes + 64) * sizeof(mxml_node_t *),
+ strerror(errno));
+
+ mxmlIndexDelete(ind);
+ return (NULL);
+ }
+
+ ind->nodes = temp;
+ ind->alloc_nodes += 64;
+ }
+
+ ind->nodes[ind->num_nodes ++] = current;
+
+ current = mxmlFindElement(current, node, element, attr, NULL, MXML_DESCEND);
+ }
+
+ /*
+ * Sort nodes based upon the search criteria...
+ */
+
+#ifdef DEBUG
+ {
+ int i; /* Looping var */
+
+
+ printf("%d node(s) in index.\n\n", ind->num_nodes);
+
+ if (attr)
+ {
+ printf("Node Address Element %s\n", attr);
+ puts("-------- -------- -------------- ------------------------------");
+
+ for (i = 0; i < ind->num_nodes; i ++)
+ printf("%8d %-8p %-14.14s %s\n", i, ind->nodes[i],
+ ind->nodes[i]->value.element.name,
+ mxmlElementGetAttr(ind->nodes[i], attr));
+ }
+ else
+ {
+ puts("Node Address Element");
+ puts("-------- -------- --------------");
+
+ for (i = 0; i < ind->num_nodes; i ++)
+ printf("%8d %-8p %s\n", i, ind->nodes[i],
+ ind->nodes[i]->value.element.name);
+ }
+
+ putchar('\n');
+ }
+#endif /* DEBUG */
+
+ if (ind->num_nodes > 1)
+ index_sort(ind, 0, ind->num_nodes - 1);
+
+#ifdef DEBUG
+ {
+ int i; /* Looping var */
+
+
+ puts("After sorting:\n");
+
+ if (attr)
+ {
+ printf("Node Address Element %s\n", attr);
+ puts("-------- -------- -------------- ------------------------------");
+
+ for (i = 0; i < ind->num_nodes; i ++)
+ printf("%8d %-8p %-14.14s %s\n", i, ind->nodes[i],
+ ind->nodes[i]->value.element.name,
+ mxmlElementGetAttr(ind->nodes[i], attr));
+ }
+ else
+ {
+ puts("Node Address Element");
+ puts("-------- -------- --------------");
+
+ for (i = 0; i < ind->num_nodes; i ++)
+ printf("%8d %-8p %s\n", i, ind->nodes[i],
+ ind->nodes[i]->value.element.name);
+ }
+
+ putchar('\n');
+ }
+#endif /* DEBUG */
+
+ /*
+ * Return the new index...
+ */
+
+ return (ind);
+}
+
+
+/*
+ * 'mxmlIndexReset()' - Reset the enumeration/find pointer in the index and
+ * return the first node in the index.
+ *
+ * This function should be called prior to using mxmlIndexEnum() or
+ * mxmlIndexFind() for the first time.
+ */
+
+mxml_node_t * /* O - First node or NULL if there is none */
+mxmlIndexReset(mxml_index_t *ind) /* I - Index to reset */
+{
+#ifdef DEBUG
+ printf("mxmlIndexReset(ind=%p)\n", ind);
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!ind)
+ return (NULL);
+
+ /*
+ * Set the index to the first element...
+ */
+
+ ind->cur_node = 0;
+
+ /*
+ * Return the first node...
+ */
+
+ if (ind->num_nodes)
+ return (ind->nodes[0]);
+ else
+ return (NULL);
+}
+
+
+/*
+ * 'index_compare()' - Compare two nodes.
+ */
+
+static int /* O - Result of comparison */
+index_compare(mxml_index_t *ind, /* I - Index */
+ mxml_node_t *first, /* I - First node */
+ mxml_node_t *second) /* I - Second node */
+{
+ int diff; /* Difference */
+
+
+ /*
+ * Check the element name...
+ */
+
+ if ((diff = strcmp(first->value.element.name,
+ second->value.element.name)) != 0)
+ return (diff);
+
+ /*
+ * Check the attribute value...
+ */
+
+ if (ind->attr)
+ {
+ if ((diff = strcmp(mxmlElementGetAttr(first, ind->attr),
+ mxmlElementGetAttr(second, ind->attr))) != 0)
+ return (diff);
+ }
+
+ /*
+ * No difference, return 0...
+ */
+
+ return (0);
+}
+
+
+/*
+ * 'index_find()' - Compare a node with index values.
+ */
+
+static int /* O - Result of comparison */
+index_find(mxml_index_t *ind, /* I - Index */
+ const char *element, /* I - Element name or NULL */
+ const char *value, /* I - Attribute value or NULL */
+ mxml_node_t *node) /* I - Node */
+{
+ int diff; /* Difference */
+
+
+ /*
+ * Check the element name...
+ */
+
+ if (element)
+ {
+ if ((diff = strcmp(element, node->value.element.name)) != 0)
+ return (diff);
+ }
+
+ /*
+ * Check the attribute value...
+ */
+
+ if (value)
+ {
+ if ((diff = strcmp(value, mxmlElementGetAttr(node, ind->attr))) != 0)
+ return (diff);
+ }
+
+ /*
+ * No difference, return 0...
+ */
+
+ return (0);
+}
+
+
+/*
+ * 'index_sort()' - Sort the nodes in the index...
+ *
+ * This function implements the classic quicksort algorithm...
+ */
+
+static void
+index_sort(mxml_index_t *ind, /* I - Index to sort */
+ int left, /* I - Left node in partition */
+ int right) /* I - Right node in partition */
+{
+ mxml_node_t *pivot, /* Pivot node */
+ *temp; /* Swap node */
+ int templ, /* Temporary left node */
+ tempr; /* Temporary right node */
+
+
+ /*
+ * Loop until we have sorted all the way to the right...
+ */
+
+ do
+ {
+ /*
+ * Sort the pivot in the current partition...
+ */
+
+ pivot = ind->nodes[left];
+
+ for (templ = left, tempr = right; templ < tempr;)
+ {
+ /*
+ * Move left while left node <= pivot node...
+ */
+
+ while ((templ < right) &&
+ index_compare(ind, ind->nodes[templ], pivot) <= 0)
+ templ ++;
+
+ /*
+ * Move right while right node > pivot node...
+ */
+
+ while ((tempr > left) &&
+ index_compare(ind, ind->nodes[tempr], pivot) > 0)
+ tempr --;
+
+ /*
+ * Swap nodes if needed...
+ */
+
+ if (templ < tempr)
+ {
+ temp = ind->nodes[templ];
+ ind->nodes[templ] = ind->nodes[tempr];
+ ind->nodes[tempr] = temp;
+ }
+ }
+
+ /*
+ * When we get here, the right (tempr) node is the new position for the
+ * pivot node...
+ */
+
+ if (index_compare(ind, pivot, ind->nodes[tempr]) > 0)
+ {
+ ind->nodes[left] = ind->nodes[tempr];
+ ind->nodes[tempr] = pivot;
+ }
+
+ /*
+ * Recursively sort the left partition as needed...
+ */
+
+ if (left < (tempr - 1))
+ index_sort(ind, left, tempr - 1);
+ }
+ while (right > (left = tempr + 1));
+}
+
+
+/*
+ * End of "$Id: mxml-index.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-node.c b/tools/gator/daemon/mxml/mxml-node.c
new file mode 100644
index 0000000..128cda1
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-node.c
@@ -0,0 +1,788 @@
+/*
+ * "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node support code for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Local functions...
+ */
+
+static mxml_node_t *mxml_new(mxml_node_t *parent, mxml_type_t type);
+
+
+/*
+ * 'mxmlAdd()' - Add a node to a tree.
+ *
+ * Adds the specified node to the parent. If the child argument is not
+ * NULL, puts the new node before or after the specified child depending
+ * on the value of the where argument. If the child argument is NULL,
+ * puts the new node at the beginning of the child list (MXML_ADD_BEFORE)
+ * or at the end of the child list (MXML_ADD_AFTER). The constant
+ * MXML_ADD_TO_PARENT can be used to specify a NULL child pointer.
+ */
+
+void
+mxmlAdd(mxml_node_t *parent, /* I - Parent node */
+ int where, /* I - Where to add, MXML_ADD_BEFORE or MXML_ADD_AFTER */
+ mxml_node_t *child, /* I - Child node for where or MXML_ADD_TO_PARENT */
+ mxml_node_t *node) /* I - Node to add */
+{
+#ifdef DEBUG
+ fprintf(stderr, "mxmlAdd(parent=%p, where=%d, child=%p, node=%p)\n", parent,
+ where, child, node);
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!parent || !node)
+ return;
+
+#if DEBUG > 1
+ fprintf(stderr, " BEFORE: node->parent=%p\n", node->parent);
+ if (parent)
+ {
+ fprintf(stderr, " BEFORE: parent->child=%p\n", parent->child);
+ fprintf(stderr, " BEFORE: parent->last_child=%p\n", parent->last_child);
+ fprintf(stderr, " BEFORE: parent->prev=%p\n", parent->prev);
+ fprintf(stderr, " BEFORE: parent->next=%p\n", parent->next);
+ }
+#endif /* DEBUG > 1 */
+
+ /*
+ * Remove the node from any existing parent...
+ */
+
+ if (node->parent)
+ mxmlRemove(node);
+
+ /*
+ * Reset pointers...
+ */
+
+ node->parent = parent;
+
+ switch (where)
+ {
+ case MXML_ADD_BEFORE :
+ if (!child || child == parent->child || child->parent != parent)
+ {
+ /*
+ * Insert as first node under parent...
+ */
+
+ node->next = parent->child;
+
+ if (parent->child)
+ parent->child->prev = node;
+ else
+ parent->last_child = node;
+
+ parent->child = node;
+ }
+ else
+ {
+ /*
+ * Insert node before this child...
+ */
+
+ node->next = child;
+ node->prev = child->prev;
+
+ if (child->prev)
+ child->prev->next = node;
+ else
+ parent->child = node;
+
+ child->prev = node;
+ }
+ break;
+
+ case MXML_ADD_AFTER :
+ if (!child || child == parent->last_child || child->parent != parent)
+ {
+ /*
+ * Insert as last node under parent...
+ */
+
+ node->parent = parent;
+ node->prev = parent->last_child;
+
+ if (parent->last_child)
+ parent->last_child->next = node;
+ else
+ parent->child = node;
+
+ parent->last_child = node;
+ }
+ else
+ {
+ /*
+ * Insert node after this child...
+ */
+
+ node->prev = child;
+ node->next = child->next;
+
+ if (child->next)
+ child->next->prev = node;
+ else
+ parent->last_child = node;
+
+ child->next = node;
+ }
+ break;
+ }
+
+#if DEBUG > 1
+ fprintf(stderr, " AFTER: node->parent=%p\n", node->parent);
+ if (parent)
+ {
+ fprintf(stderr, " AFTER: parent->child=%p\n", parent->child);
+ fprintf(stderr, " AFTER: parent->last_child=%p\n", parent->last_child);
+ fprintf(stderr, " AFTER: parent->prev=%p\n", parent->prev);
+ fprintf(stderr, " AFTER: parent->next=%p\n", parent->next);
+ }
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlDelete()' - Delete a node and all of its children.
+ *
+ * If the specified node has a parent, this function first removes the
+ * node from its parent using the mxmlRemove() function.
+ */
+
+void
+mxmlDelete(mxml_node_t *node) /* I - Node to delete */
+{
+ int i; /* Looping var */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlDelete(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return;
+
+ /*
+ * Remove the node from its parent, if any...
+ */
+
+ mxmlRemove(node);
+
+ /*
+ * Delete children...
+ */
+
+ while (node->child)
+ mxmlDelete(node->child);
+
+ /*
+ * Now delete any node data...
+ */
+
+ switch (node->type)
+ {
+ case MXML_ELEMENT :
+ if (node->value.element.name)
+ free(node->value.element.name);
+
+ if (node->value.element.num_attrs)
+ {
+ for (i = 0; i < node->value.element.num_attrs; i ++)
+ {
+ if (node->value.element.attrs[i].name)
+ free(node->value.element.attrs[i].name);
+ if (node->value.element.attrs[i].value)
+ free(node->value.element.attrs[i].value);
+ }
+
+ free(node->value.element.attrs);
+ }
+ break;
+ case MXML_INTEGER :
+ /* Nothing to do */
+ break;
+ case MXML_OPAQUE :
+ if (node->value.opaque)
+ free(node->value.opaque);
+ break;
+ case MXML_REAL :
+ /* Nothing to do */
+ break;
+ case MXML_TEXT :
+ if (node->value.text.string)
+ free(node->value.text.string);
+ break;
+ case MXML_CUSTOM :
+ if (node->value.custom.data &&
+ node->value.custom.destroy)
+ (*(node->value.custom.destroy))(node->value.custom.data);
+ break;
+ default :
+ break;
+ }
+
+ /*
+ * Free this node...
+ */
+
+ free(node);
+}
+
+
+/*
+ * 'mxmlGetRefCount()' - Get the current reference (use) count for a node.
+ *
+ * The initial reference count of new nodes is 1. Use the @link mxmlRetain@
+ * and @link mxmlRelease@ functions to increment and decrement a node's
+ * reference count.
+ *
+ * @since Mini-XML 2.7@.
+ */
+
+int /* O - Reference count */
+mxmlGetRefCount(mxml_node_t *node) /* I - Node */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (0);
+
+ /*
+ * Return the reference count...
+ */
+
+ return (node->ref_count);
+}
+
+
+/*
+ * 'mxmlNewCDATA()' - Create a new CDATA node.
+ *
+ * The new CDATA node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * CDATA node has no parent. The data string must be nul-terminated and
+ * is copied into the new node. CDATA nodes use the MXML_ELEMENT type.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewCDATA(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ const char *data) /* I - Data string */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewCDATA(parent=%p, data=\"%s\")\n",
+ parent, data ? data : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!data)
+ return (NULL);
+
+ /*
+ * Create the node and set the name value...
+ */
+
+ if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+ node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewCustom()' - Create a new custom data node.
+ *
+ * The new custom node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent. NULL can be passed when the data in the
+ * node is not dynamically allocated or is separately managed.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewCustom(
+ mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ void *data, /* I - Pointer to data */
+ mxml_custom_destroy_cb_t destroy) /* I - Function to destroy data */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewCustom(parent=%p, data=%p, destroy=%p)\n", parent,
+ data, destroy);
+#endif /* DEBUG */
+
+ /*
+ * Create the node and set the value...
+ */
+
+ if ((node = mxml_new(parent, MXML_CUSTOM)) != NULL)
+ {
+ node->value.custom.data = data;
+ node->value.custom.destroy = destroy;
+ }
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewElement()' - Create a new element node.
+ *
+ * The new element node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * element node has no parent.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewElement(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ const char *name) /* I - Name of element */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewElement(parent=%p, name=\"%s\")\n", parent,
+ name ? name : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!name)
+ return (NULL);
+
+ /*
+ * Create the node and set the element name...
+ */
+
+ if ((node = mxml_new(parent, MXML_ELEMENT)) != NULL)
+ node->value.element.name = strdup(name);
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewInteger()' - Create a new integer node.
+ *
+ * The new integer node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * integer node has no parent.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewInteger(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ int integer) /* I - Integer value */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewInteger(parent=%p, integer=%d)\n", parent, integer);
+#endif /* DEBUG */
+
+ /*
+ * Create the node and set the element name...
+ */
+
+ if ((node = mxml_new(parent, MXML_INTEGER)) != NULL)
+ node->value.integer = integer;
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewOpaque()' - Create a new opaque string.
+ *
+ * The new opaque node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * opaque node has no parent. The opaque string must be nul-terminated and
+ * is copied into the new node.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewOpaque(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ const char *opaque) /* I - Opaque string */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewOpaque(parent=%p, opaque=\"%s\")\n", parent,
+ opaque ? opaque : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!opaque)
+ return (NULL);
+
+ /*
+ * Create the node and set the element name...
+ */
+
+ if ((node = mxml_new(parent, MXML_OPAQUE)) != NULL)
+ node->value.opaque = strdup(opaque);
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewReal()' - Create a new real number node.
+ *
+ * The new real number node is added to the end of the specified parent's
+ * child list. The constant MXML_NO_PARENT can be used to specify that
+ * the new real number node has no parent.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewReal(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ double real) /* I - Real number value */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewReal(parent=%p, real=%g)\n", parent, real);
+#endif /* DEBUG */
+
+ /*
+ * Create the node and set the element name...
+ */
+
+ if ((node = mxml_new(parent, MXML_REAL)) != NULL)
+ node->value.real = real;
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewText()' - Create a new text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The text
+ * string must be nul-terminated and is copied into the new node.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewText(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ int whitespace, /* I - 1 = leading whitespace, 0 = no whitespace */
+ const char *string) /* I - String */
+{
+ mxml_node_t *node; /* New node */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewText(parent=%p, whitespace=%d, string=\"%s\")\n",
+ parent, whitespace, string ? string : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!string)
+ return (NULL);
+
+ /*
+ * Create the node and set the text value...
+ */
+
+ if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+ {
+ node->value.text.whitespace = whitespace;
+ node->value.text.string = strdup(string);
+ }
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlNewTextf()' - Create a new formatted text fragment node.
+ *
+ * The new text node is added to the end of the specified parent's child
+ * list. The constant MXML_NO_PARENT can be used to specify that the new
+ * text node has no parent. The whitespace parameter is used to specify
+ * whether leading whitespace is present before the node. The format
+ * string must be nul-terminated and is formatted into the new node.
+ */
+
+mxml_node_t * /* O - New node */
+mxmlNewTextf(mxml_node_t *parent, /* I - Parent node or MXML_NO_PARENT */
+ int whitespace, /* I - 1 = leading whitespace, 0 = no whitespace */
+ const char *format, /* I - Printf-style frmat string */
+ ...) /* I - Additional args as needed */
+{
+ mxml_node_t *node; /* New node */
+ va_list ap; /* Pointer to arguments */
+
+
+#ifdef DEBUG
+ fprintf(stderr, "mxmlNewTextf(parent=%p, whitespace=%d, format=\"%s\", ...)\n",
+ parent, whitespace, format ? format : "(null)");
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!format)
+ return (NULL);
+
+ /*
+ * Create the node and set the text value...
+ */
+
+ if ((node = mxml_new(parent, MXML_TEXT)) != NULL)
+ {
+ va_start(ap, format);
+
+ node->value.text.whitespace = whitespace;
+ node->value.text.string = _mxml_vstrdupf(format, ap);
+
+ va_end(ap);
+ }
+
+ return (node);
+}
+
+
+/*
+ * 'mxmlRemove()' - Remove a node from its parent.
+ *
+ * Does not free memory used by the node - use mxmlDelete() for that.
+ * This function does nothing if the node has no parent.
+ */
+
+void
+mxmlRemove(mxml_node_t *node) /* I - Node to remove */
+{
+#ifdef DEBUG
+ fprintf(stderr, "mxmlRemove(node=%p)\n", node);
+#endif /* DEBUG */
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || !node->parent)
+ return;
+
+ /*
+ * Remove from parent...
+ */
+
+#if DEBUG > 1
+ fprintf(stderr, " BEFORE: node->parent=%p\n", node->parent);
+ if (node->parent)
+ {
+ fprintf(stderr, " BEFORE: node->parent->child=%p\n", node->parent->child);
+ fprintf(stderr, " BEFORE: node->parent->last_child=%p\n", node->parent->last_child);
+ }
+ fprintf(stderr, " BEFORE: node->child=%p\n", node->child);
+ fprintf(stderr, " BEFORE: node->last_child=%p\n", node->last_child);
+ fprintf(stderr, " BEFORE: node->prev=%p\n", node->prev);
+ fprintf(stderr, " BEFORE: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+
+ if (node->prev)
+ node->prev->next = node->next;
+ else
+ node->parent->child = node->next;
+
+ if (node->next)
+ node->next->prev = node->prev;
+ else
+ node->parent->last_child = node->prev;
+
+ node->parent = NULL;
+ node->prev = NULL;
+ node->next = NULL;
+
+#if DEBUG > 1
+ fprintf(stderr, " AFTER: node->parent=%p\n", node->parent);
+ if (node->parent)
+ {
+ fprintf(stderr, " AFTER: node->parent->child=%p\n", node->parent->child);
+ fprintf(stderr, " AFTER: node->parent->last_child=%p\n", node->parent->last_child);
+ }
+ fprintf(stderr, " AFTER: node->child=%p\n", node->child);
+ fprintf(stderr, " AFTER: node->last_child=%p\n", node->last_child);
+ fprintf(stderr, " AFTER: node->prev=%p\n", node->prev);
+ fprintf(stderr, " AFTER: node->next=%p\n", node->next);
+#endif /* DEBUG > 1 */
+}
+
+
+/*
+ * 'mxmlNewXML()' - Create a new XML document tree.
+ *
+ * The "version" argument specifies the version number to put in the
+ * ?xml element node. If NULL, version 1.0 is assumed.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+mxml_node_t * /* O - New ?xml node */
+mxmlNewXML(const char *version) /* I - Version number to use */
+{
+ char element[1024]; /* Element text */
+
+
+ snprintf(element, sizeof(element), "?xml version=\"%s\" encoding=\"utf-8\"?",
+ version ? version : "1.0");
+
+ return (mxmlNewElement(NULL, element));
+}
+
+
+/*
+ * 'mxmlRelease()' - Release a node.
+ *
+ * When the reference count reaches zero, the node (and any children)
+ * is deleted via mxmlDelete().
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int /* O - New reference count */
+mxmlRelease(mxml_node_t *node) /* I - Node */
+{
+ if (node)
+ {
+ if ((-- node->ref_count) <= 0)
+ {
+ mxmlDelete(node);
+ return (0);
+ }
+ else
+ return (node->ref_count);
+ }
+ else
+ return (-1);
+}
+
+
+/*
+ * 'mxmlRetain()' - Retain a node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int /* O - New reference count */
+mxmlRetain(mxml_node_t *node) /* I - Node */
+{
+ if (node)
+ return (++ node->ref_count);
+ else
+ return (-1);
+}
+
+
+/*
+ * 'mxml_new()' - Create a new node.
+ */
+
+static mxml_node_t * /* O - New node */
+mxml_new(mxml_node_t *parent, /* I - Parent node */
+ mxml_type_t type) /* I - Node type */
+{
+ mxml_node_t *node; /* New node */
+
+
+#if DEBUG > 1
+ fprintf(stderr, "mxml_new(parent=%p, type=%d)\n", parent, type);
+#endif /* DEBUG > 1 */
+
+ /*
+ * Allocate memory for the node...
+ */
+
+ if ((node = calloc(1, sizeof(mxml_node_t))) == NULL)
+ {
+#if DEBUG > 1
+ fputs(" returning NULL\n", stderr);
+#endif /* DEBUG > 1 */
+
+ return (NULL);
+ }
+
+#if DEBUG > 1
+ fprintf(stderr, " returning %p\n", node);
+#endif /* DEBUG > 1 */
+
+ /*
+ * Set the node type...
+ */
+
+ node->type = type;
+ node->ref_count = 1;
+
+ /*
+ * Add to the parent if present...
+ */
+
+ if (parent)
+ mxmlAdd(parent, MXML_ADD_AFTER, MXML_ADD_TO_PARENT, node);
+
+ /*
+ * Return the new node...
+ */
+
+ return (node);
+}
+
+
+/*
+ * End of "$Id: mxml-node.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.c b/tools/gator/daemon/mxml/mxml-private.c
new file mode 100644
index 0000000..bec4bbf
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.c
@@ -0,0 +1,323 @@
+/*
+ * "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "mxml-private.h"
+
+
+/*
+ * Some crazy people think that unloading a shared object is a good or safe
+ * thing to do. Unfortunately, most objects are simply *not* safe to unload
+ * and bad things *will* happen.
+ *
+ * The following mess of conditional code allows us to provide a destructor
+ * function in Mini-XML for our thread-global storage so that it can possibly
+ * be unloaded safely, although since there is no standard way to do so I
+ * can't even provide any guarantees that you can do it safely on all platforms.
+ *
+ * This code currently supports AIX, HP-UX, Linux, Mac OS X, Solaris, and
+ * Windows. It might work on the BSDs and IRIX, but I haven't tested that.
+ */
+
+#if defined(__sun) || defined(_AIX)
+# pragma fini(_mxml_fini)
+# define _MXML_FINI _mxml_fini
+#elif defined(__hpux)
+# pragma FINI _mxml_fini
+# define _MXML_FINI _mxml_fini
+#elif defined(__GNUC__) /* Linux and Mac OS X */
+# define _MXML_FINI __attribute((destructor)) _mxml_fini
+#else
+# define _MXML_FINI _fini
+#endif /* __sun */
+
+
+/*
+ * 'mxml_error()' - Display an error message.
+ */
+
+void
+mxml_error(const char *format, /* I - Printf-style format string */
+ ...) /* I - Additional arguments as needed */
+{
+ va_list ap; /* Pointer to arguments */
+ char s[1024]; /* Message string */
+ _mxml_global_t *global = _mxml_global();
+ /* Global data */
+
+
+ /*
+ * Range check input...
+ */
+
+ if (!format)
+ return;
+
+ /*
+ * Format the error message string...
+ */
+
+ va_start(ap, format);
+
+ vsnprintf(s, sizeof(s), format, ap);
+
+ va_end(ap);
+
+ /*
+ * And then display the error message...
+ */
+
+ if (global->error_cb)
+ (*global->error_cb)(s);
+ else
+ fprintf(stderr, "mxml: %s\n", s);
+}
+
+
+/*
+ * 'mxml_ignore_cb()' - Default callback for ignored values.
+ */
+
+mxml_type_t /* O - Node type */
+mxml_ignore_cb(mxml_node_t *node) /* I - Current node */
+{
+ (void)node;
+
+ return (MXML_IGNORE);
+}
+
+
+/*
+ * 'mxml_integer_cb()' - Default callback for integer values.
+ */
+
+mxml_type_t /* O - Node type */
+mxml_integer_cb(mxml_node_t *node) /* I - Current node */
+{
+ (void)node;
+
+ return (MXML_INTEGER);
+}
+
+
+/*
+ * 'mxml_opaque_cb()' - Default callback for opaque values.
+ */
+
+mxml_type_t /* O - Node type */
+mxml_opaque_cb(mxml_node_t *node) /* I - Current node */
+{
+ (void)node;
+
+ return (MXML_OPAQUE);
+}
+
+
+/*
+ * 'mxml_real_cb()' - Default callback for real number values.
+ */
+
+mxml_type_t /* O - Node type */
+mxml_real_cb(mxml_node_t *node) /* I - Current node */
+{
+ (void)node;
+
+ return (MXML_REAL);
+}
+
+
+#ifdef HAVE_PTHREAD_H /**** POSIX threading ****/
+# include <pthread.h>
+
+static pthread_key_t _mxml_key = -1; /* Thread local storage key */
+static pthread_once_t _mxml_key_once = PTHREAD_ONCE_INIT;
+ /* One-time initialization object */
+static void _mxml_init(void);
+static void _mxml_destructor(void *g);
+
+
+/*
+ * '_mxml_destructor()' - Free memory used for globals...
+ */
+
+static void
+_mxml_destructor(void *g) /* I - Global data */
+{
+ free(g);
+}
+
+
+/*
+ * '_mxml_fini()' - Clean up when unloaded.
+ */
+
+static void
+_MXML_FINI(void)
+{
+ _mxml_global_t *global; /* Global data */
+
+
+ if (_mxml_key != -1)
+ {
+ if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) != NULL)
+ _mxml_destructor(global);
+
+ pthread_key_delete(_mxml_key);
+ _mxml_key = -1;
+ }
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t * /* O - Global data */
+_mxml_global(void)
+{
+ _mxml_global_t *global; /* Global data */
+
+
+ pthread_once(&_mxml_key_once, _mxml_init);
+
+ if ((global = (_mxml_global_t *)pthread_getspecific(_mxml_key)) == NULL)
+ {
+ global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+ pthread_setspecific(_mxml_key, global);
+
+ global->num_entity_cbs = 1;
+ global->entity_cbs[0] = _mxml_entity_cb;
+ global->wrap = 72;
+ }
+
+ return (global);
+}
+
+
+/*
+ * '_mxml_init()' - Initialize global data...
+ */
+
+static void
+_mxml_init(void)
+{
+ pthread_key_create(&_mxml_key, _mxml_destructor);
+}
+
+
+#elif defined(WIN32) && defined(MXML1_EXPORTS) /**** WIN32 threading ****/
+# include <windows.h>
+
+static DWORD _mxml_tls_index; /* Index for global storage */
+
+
+/*
+ * 'DllMain()' - Main entry for library.
+ */
+
+BOOL WINAPI /* O - Success/failure */
+DllMain(HINSTANCE hinst, /* I - DLL module handle */
+ DWORD reason, /* I - Reason */
+ LPVOID reserved) /* I - Unused */
+{
+ _mxml_global_t *global; /* Global data */
+
+
+ (void)hinst;
+ (void)reserved;
+
+ switch (reason)
+ {
+ case DLL_PROCESS_ATTACH : /* Called on library initialization */
+ if ((_mxml_tls_index = TlsAlloc()) == TLS_OUT_OF_INDEXES)
+ return (FALSE);
+ break;
+
+ case DLL_THREAD_DETACH : /* Called when a thread terminates */
+ if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+ free(global);
+ break;
+
+ case DLL_PROCESS_DETACH : /* Called when library is unloaded */
+ if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) != NULL)
+ free(global);
+
+ TlsFree(_mxml_tls_index);
+ break;
+
+ default:
+ break;
+ }
+
+ return (TRUE);
+}
+
+
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t * /* O - Global data */
+_mxml_global(void)
+{
+ _mxml_global_t *global; /* Global data */
+
+
+ if ((global = (_mxml_global_t *)TlsGetValue(_mxml_tls_index)) == NULL)
+ {
+ global = (_mxml_global_t *)calloc(1, sizeof(_mxml_global_t));
+
+ global->num_entity_cbs = 1;
+ global->entity_cbs[0] = _mxml_entity_cb;
+ global->wrap = 72;
+
+ TlsSetValue(_mxml_tls_index, (LPVOID)global);
+ }
+
+ return (global);
+}
+
+
+#else /**** No threading ****/
+/*
+ * '_mxml_global()' - Get global data.
+ */
+
+_mxml_global_t * /* O - Global data */
+_mxml_global(void)
+{
+ static _mxml_global_t global = /* Global data */
+ {
+ NULL, /* error_cb */
+ 1, /* num_entity_cbs */
+ { _mxml_entity_cb }, /* entity_cbs */
+ 72, /* wrap */
+ NULL, /* custom_load_cb */
+ NULL /* custom_save_cb */
+ };
+
+
+ return (&global);
+}
+#endif /* HAVE_PTHREAD_H */
+
+
+/*
+ * End of "$Id: mxml-private.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-private.h b/tools/gator/daemon/mxml/mxml-private.h
new file mode 100644
index 0000000..c5e4e6b
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-private.h
@@ -0,0 +1,50 @@
+/*
+ * "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Private definitions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * Global, per-thread data...
+ */
+
+typedef struct _mxml_global_s
+{
+ void (*error_cb)(const char *);
+ int num_entity_cbs;
+ int (*entity_cbs[100])(const char *name);
+ int wrap;
+ mxml_custom_load_cb_t custom_load_cb;
+ mxml_custom_save_cb_t custom_save_cb;
+} _mxml_global_t;
+
+
+/*
+ * Functions...
+ */
+
+extern _mxml_global_t *_mxml_global(void);
+extern int _mxml_entity_cb(const char *name);
+
+
+/*
+ * End of "$Id: mxml-private.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-search.c b/tools/gator/daemon/mxml/mxml-search.c
new file mode 100644
index 0000000..313a52f
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-search.c
@@ -0,0 +1,280 @@
+/*
+ * "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Search/navigation functions for Mini-XML, a small XML-like file
+ * parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlFindElement()' - Find the named element.
+ *
+ * The search is constrained by the name, attribute name, and value; any
+ * NULL names or values are treated as wildcards, so different kinds of
+ * searches can be implemented by looking for all elements of a given name
+ * or all elements with a specific attribute. The descend argument determines
+ * whether the search descends into child nodes; normally you will use
+ * MXML_DESCEND_FIRST for the initial search and MXML_NO_DESCEND to find
+ * additional direct descendents of the node. The top node argument
+ * constrains the search to a particular node's children.
+ */
+
+mxml_node_t * /* O - Element node or NULL */
+mxmlFindElement(mxml_node_t *node, /* I - Current node */
+ mxml_node_t *top, /* I - Top node */
+ const char *name, /* I - Element name or NULL for any */
+ const char *attr, /* I - Attribute name, or NULL for none */
+ const char *value, /* I - Attribute value, or NULL for any */
+ int descend) /* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+ const char *temp; /* Current attribute value */
+
+
+ /*
+ * Range check input...
+ */
+
+ if (!node || !top || (!attr && value))
+ return (NULL);
+
+ /*
+ * Start with the next node...
+ */
+
+ node = mxmlWalkNext(node, top, descend);
+
+ /*
+ * Loop until we find a matching element...
+ */
+
+ while (node != NULL)
+ {
+ /*
+ * See if this node matches...
+ */
+
+ if (node->type == MXML_ELEMENT &&
+ node->value.element.name &&
+ (!name || !strcmp(node->value.element.name, name)))
+ {
+ /*
+ * See if we need to check for an attribute...
+ */
+
+ if (!attr)
+ return (node); /* No attribute search, return it... */
+
+ /*
+ * Check for the attribute...
+ */
+
+ if ((temp = mxmlElementGetAttr(node, attr)) != NULL)
+ {
+ /*
+ * OK, we have the attribute, does it match?
+ */
+
+ if (!value || !strcmp(value, temp))
+ return (node); /* Yes, return it... */
+ }
+ }
+
+ /*
+ * No match, move on to the next node...
+ */
+
+ if (descend == MXML_DESCEND)
+ node = mxmlWalkNext(node, top, MXML_DESCEND);
+ else
+ node = node->next;
+ }
+
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlFindPath()' - Find a node with the given path.
+ *
+ * The "path" is a slash-separated list of element names. The name "*" is
+ * considered a wildcard for one or more levels of elements. For example,
+ * "foo/one/two", "bar/two/one", "*\/one", and so forth.
+ *
+ * The first child node of the found node is returned if the given node has
+ * children and the first child is a value node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+mxml_node_t * /* O - Found node or NULL */
+mxmlFindPath(mxml_node_t *top, /* I - Top node */
+ const char *path) /* I - Path to element */
+{
+ mxml_node_t *node; /* Current node */
+ char element[256]; /* Current element name */
+ const char *pathsep; /* Separator in path */
+ int descend; /* mxmlFindElement option */
+
+
+ /*
+ * Range check input...
+ */
+
+ if (!top || !path || !*path)
+ return (NULL);
+
+ /*
+ * Search each element in the path...
+ */
+
+ node = top;
+ while (*path)
+ {
+ /*
+ * Handle wildcards...
+ */
+
+ if (!strncmp(path, "*/", 2))
+ {
+ path += 2;
+ descend = MXML_DESCEND;
+ }
+ else
+ descend = MXML_DESCEND_FIRST;
+
+ /*
+ * Get the next element in the path...
+ */
+
+ if ((pathsep = strchr(path, '/')) == NULL)
+ pathsep = path + strlen(path);
+
+ if (pathsep == path || (pathsep - path) >= sizeof(element))
+ return (NULL);
+
+ memcpy(element, path, pathsep - path);
+ element[pathsep - path] = '\0';
+
+ if (*pathsep)
+ path = pathsep + 1;
+ else
+ path = pathsep;
+
+ /*
+ * Search for the element...
+ */
+
+ if ((node = mxmlFindElement(node, node, element, NULL, NULL,
+ descend)) == NULL)
+ return (NULL);
+ }
+
+ /*
+ * If we get this far, return the node or its first child...
+ */
+
+ if (node->child && node->child->type != MXML_ELEMENT)
+ return (node->child);
+ else
+ return (node);
+}
+
+
+/*
+ * 'mxmlWalkNext()' - Walk to the next logical node in the tree.
+ *
+ * The descend argument controls whether the first child is considered
+ * to be the next node. The top node argument constrains the walk to
+ * the node's children.
+ */
+
+mxml_node_t * /* O - Next node or NULL */
+mxmlWalkNext(mxml_node_t *node, /* I - Current node */
+ mxml_node_t *top, /* I - Top node */
+ int descend) /* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+ if (!node)
+ return (NULL);
+ else if (node->child && descend)
+ return (node->child);
+ else if (node == top)
+ return (NULL);
+ else if (node->next)
+ return (node->next);
+ else if (node->parent && node->parent != top)
+ {
+ node = node->parent;
+
+ while (!node->next)
+ if (node->parent == top || !node->parent)
+ return (NULL);
+ else
+ node = node->parent;
+
+ return (node->next);
+ }
+ else
+ return (NULL);
+}
+
+
+/*
+ * 'mxmlWalkPrev()' - Walk to the previous logical node in the tree.
+ *
+ * The descend argument controls whether the previous node's last child
+ * is considered to be the previous node. The top node argument constrains
+ * the walk to the node's children.
+ */
+
+mxml_node_t * /* O - Previous node or NULL */
+mxmlWalkPrev(mxml_node_t *node, /* I - Current node */
+ mxml_node_t *top, /* I - Top node */
+ int descend) /* I - Descend into tree - MXML_DESCEND, MXML_NO_DESCEND, or MXML_DESCEND_FIRST */
+{
+ if (!node || node == top)
+ return (NULL);
+ else if (node->prev)
+ {
+ if (node->prev->last_child && descend)
+ {
+ /*
+ * Find the last child under the previous node...
+ */
+
+ node = node->prev->last_child;
+
+ while (node->last_child)
+ node = node->last_child;
+
+ return (node);
+ }
+ else
+ return (node->prev);
+ }
+ else if (node->parent != top)
+ return (node->parent);
+ else
+ return (NULL);
+}
+
+
+/*
+ * End of "$Id: mxml-search.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-set.c b/tools/gator/daemon/mxml/mxml-set.c
new file mode 100644
index 0000000..16d4bf1
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-set.c
@@ -0,0 +1,337 @@
+/*
+ * "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Node set functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+#include "mxml.h"
+
+
+/*
+ * 'mxmlSetCDATA()' - Set the element name of a CDATA node.
+ *
+ * The node is not changed if it (or its first child) is not a CDATA element node.
+ *
+ * @since Mini-XML 2.3@
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetCDATA(mxml_node_t *node, /* I - Node to set */
+ const char *data) /* I - New data string */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ strncmp(node->value.element.name, "![CDATA[", 8) &&
+ node->child && node->child->type == MXML_ELEMENT &&
+ !strncmp(node->child->value.element.name, "![CDATA[", 8))
+ node = node->child;
+
+ if (!node || node->type != MXML_ELEMENT || !data ||
+ strncmp(node->value.element.name, "![CDATA[", 8))
+ return (-1);
+
+ /*
+ * Free any old element value and set the new value...
+ */
+
+ if (node->value.element.name)
+ free(node->value.element.name);
+
+ node->value.element.name = _mxml_strdupf("![CDATA[%s]]", data);
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetCustom()' - Set the data and destructor of a custom data node.
+ *
+ * The node is not changed if it (or its first child) is not a custom node.
+ *
+ * @since Mini-XML 2.1@
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetCustom(
+ mxml_node_t *node, /* I - Node to set */
+ void *data, /* I - New data pointer */
+ mxml_custom_destroy_cb_t destroy) /* I - New destructor function */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_CUSTOM)
+ node = node->child;
+
+ if (!node || node->type != MXML_CUSTOM)
+ return (-1);
+
+ /*
+ * Free any old element value and set the new value...
+ */
+
+ if (node->value.custom.data && node->value.custom.destroy)
+ (*(node->value.custom.destroy))(node->value.custom.data);
+
+ node->value.custom.data = data;
+ node->value.custom.destroy = destroy;
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetElement()' - Set the name of an element node.
+ *
+ * The node is not changed if it is not an element node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetElement(mxml_node_t *node, /* I - Node to set */
+ const char *name) /* I - New name string */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node || node->type != MXML_ELEMENT || !name)
+ return (-1);
+
+ /*
+ * Free any old element value and set the new value...
+ */
+
+ if (node->value.element.name)
+ free(node->value.element.name);
+
+ node->value.element.name = strdup(name);
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetInteger()' - Set the value of an integer node.
+ *
+ * The node is not changed if it (or its first child) is not an integer node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetInteger(mxml_node_t *node, /* I - Node to set */
+ int integer) /* I - Integer value */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_INTEGER)
+ node = node->child;
+
+ if (!node || node->type != MXML_INTEGER)
+ return (-1);
+
+ /*
+ * Set the new value and return...
+ */
+
+ node->value.integer = integer;
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetOpaque()' - Set the value of an opaque node.
+ *
+ * The node is not changed if it (or its first child) is not an opaque node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetOpaque(mxml_node_t *node, /* I - Node to set */
+ const char *opaque) /* I - Opaque string */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_OPAQUE)
+ node = node->child;
+
+ if (!node || node->type != MXML_OPAQUE || !opaque)
+ return (-1);
+
+ /*
+ * Free any old opaque value and set the new value...
+ */
+
+ if (node->value.opaque)
+ free(node->value.opaque);
+
+ node->value.opaque = strdup(opaque);
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetReal()' - Set the value of a real number node.
+ *
+ * The node is not changed if it (or its first child) is not a real number node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetReal(mxml_node_t *node, /* I - Node to set */
+ double real) /* I - Real number value */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_REAL)
+ node = node->child;
+
+ if (!node || node->type != MXML_REAL)
+ return (-1);
+
+ /*
+ * Set the new value and return...
+ */
+
+ node->value.real = real;
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetText()' - Set the value of a text node.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetText(mxml_node_t *node, /* I - Node to set */
+ int whitespace, /* I - 1 = leading whitespace, 0 = no whitespace */
+ const char *string) /* I - String */
+{
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_TEXT)
+ node = node->child;
+
+ if (!node || node->type != MXML_TEXT || !string)
+ return (-1);
+
+ /*
+ * Free any old string value and set the new value...
+ */
+
+ if (node->value.text.string)
+ free(node->value.text.string);
+
+ node->value.text.whitespace = whitespace;
+ node->value.text.string = strdup(string);
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetTextf()' - Set the value of a text node to a formatted string.
+ *
+ * The node is not changed if it (or its first child) is not a text node.
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetTextf(mxml_node_t *node, /* I - Node to set */
+ int whitespace, /* I - 1 = leading whitespace, 0 = no whitespace */
+ const char *format, /* I - Printf-style format string */
+ ...) /* I - Additional arguments as needed */
+{
+ va_list ap; /* Pointer to arguments */
+
+
+ /*
+ * Range check input...
+ */
+
+ if (node && node->type == MXML_ELEMENT &&
+ node->child && node->child->type == MXML_TEXT)
+ node = node->child;
+
+ if (!node || node->type != MXML_TEXT || !format)
+ return (-1);
+
+ /*
+ * Free any old string value and set the new value...
+ */
+
+ if (node->value.text.string)
+ free(node->value.text.string);
+
+ va_start(ap, format);
+
+ node->value.text.whitespace = whitespace;
+ node->value.text.string = _mxml_strdupf(format, ap);
+
+ va_end(ap);
+
+ return (0);
+}
+
+
+/*
+ * 'mxmlSetUserData()' - Set the user data pointer for a node.
+ *
+ * @since Mini-XML 2.7@
+ */
+
+int /* O - 0 on success, -1 on failure */
+mxmlSetUserData(mxml_node_t *node, /* I - Node to set */
+ void *data) /* I - User data pointer */
+{
+ /*
+ * Range check input...
+ */
+
+ if (!node)
+ return (-1);
+
+ /*
+ * Set the user data pointer and return...
+ */
+
+ node->user_data = data;
+ return (0);
+}
+
+
+/*
+ * End of "$Id: mxml-set.c 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml-string.c b/tools/gator/daemon/mxml/mxml-string.c
new file mode 100644
index 0000000..9d5b58e
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml-string.c
@@ -0,0 +1,469 @@
+/*
+ * "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $"
+ *
+ * String functions for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Include necessary headers...
+ */
+
+#include "config.h"
+
+
+/*
+ * The va_copy macro is part of C99, but many compilers don't implement it.
+ * Provide a "direct assignment" implmentation when va_copy isn't defined...
+ */
+
+#ifndef va_copy
+# ifdef __va_copy
+# define va_copy(dst,src) __va_copy(dst,src)
+# else
+# define va_copy(dst,src) memcpy(&dst, src, sizeof(va_list))
+# endif /* __va_copy */
+#endif /* va_copy */
+
+
+#ifndef HAVE_SNPRINTF
+/*
+ * '_mxml_snprintf()' - Format a string.
+ */
+
+int /* O - Number of bytes formatted */
+_mxml_snprintf(char *buffer, /* I - Output buffer */
+ size_t bufsize, /* I - Size of output buffer */
+ const char *format, /* I - Printf-style format string */
+ ...) /* I - Additional arguments as needed */
+{
+ va_list ap; /* Argument list */
+ int bytes; /* Number of bytes formatted */
+
+
+ va_start(ap, format);
+ bytes = vsnprintf(buffer, bufsize, format, ap);
+ va_end(ap);
+
+ return (bytes);
+}
+#endif /* !HAVE_SNPRINTF */
+
+
+/*
+ * '_mxml_strdup()' - Duplicate a string.
+ */
+
+#ifndef HAVE_STRDUP
+char * /* O - New string pointer */
+_mxml_strdup(const char *s) /* I - String to duplicate */
+{
+ char *t; /* New string pointer */
+
+
+ if (s == NULL)
+ return (NULL);
+
+ if ((t = malloc(strlen(s) + 1)) == NULL)
+ return (NULL);
+
+ return (strcpy(t, s));
+}
+#endif /* !HAVE_STRDUP */
+
+
+/*
+ * '_mxml_strdupf()' - Format and duplicate a string.
+ */
+
+char * /* O - New string pointer */
+_mxml_strdupf(const char *format, /* I - Printf-style format string */
+ ...) /* I - Additional arguments as needed */
+{
+ va_list ap; /* Pointer to additional arguments */
+ char *s; /* Pointer to formatted string */
+
+
+ /*
+ * Get a pointer to the additional arguments, format the string,
+ * and return it...
+ */
+
+ va_start(ap, format);
+ s = _mxml_vstrdupf(format, ap);
+ va_end(ap);
+
+ return (s);
+}
+
+
+#ifndef HAVE_VSNPRINTF
+/*
+ * '_mxml_vsnprintf()' - Format a string into a fixed size buffer.
+ */
+
+int /* O - Number of bytes formatted */
+_mxml_vsnprintf(char *buffer, /* O - Output buffer */
+ size_t bufsize, /* O - Size of output buffer */
+ const char *format, /* I - Printf-style format string */
+ va_list ap) /* I - Pointer to additional arguments */
+{
+ char *bufptr, /* Pointer to position in buffer */
+ *bufend, /* Pointer to end of buffer */
+ sign, /* Sign of format width */
+ size, /* Size character (h, l, L) */
+ type; /* Format type character */
+ int width, /* Width of field */
+ prec; /* Number of characters of precision */
+ char tformat[100], /* Temporary format string for sprintf() */
+ *tptr, /* Pointer into temporary format */
+ temp[1024]; /* Buffer for formatted numbers */
+ char *s; /* Pointer to string */
+ int slen; /* Length of string */
+ int bytes; /* Total number of bytes needed */
+
+
+ /*
+ * Loop through the format string, formatting as needed...
+ */
+
+ bufptr = buffer;
+ bufend = buffer + bufsize - 1;
+ bytes = 0;
+
+ while (*format)
+ {
+ if (*format == '%')
+ {
+ tptr = tformat;
+ *tptr++ = *format++;
+
+ if (*format == '%')
+ {
+ if (bufptr && bufptr < bufend)
+ *bufptr++ = *format;
+ bytes ++;
+ format ++;
+ continue;
+ }
+ else if (strchr(" -+#\'", *format))
+ {
+ *tptr++ = *format;
+ sign = *format++;
+ }
+ else
+ sign = 0;
+
+ if (*format == '*')
+ {
+ /*
+ * Get width from argument...
+ */
+
+ format ++;
+ width = va_arg(ap, int);
+
+ snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", width);
+ tptr += strlen(tptr);
+ }
+ else
+ {
+ width = 0;
+
+ while (isdigit(*format & 255))
+ {
+ if (tptr < (tformat + sizeof(tformat) - 1))
+ *tptr++ = *format;
+
+ width = width * 10 + *format++ - '0';
+ }
+ }
+
+ if (*format == '.')
+ {
+ if (tptr < (tformat + sizeof(tformat) - 1))
+ *tptr++ = *format;
+
+ format ++;
+
+ if (*format == '*')
+ {
+ /*
+ * Get precision from argument...
+ */
+
+ format ++;
+ prec = va_arg(ap, int);
+
+ snprintf(tptr, sizeof(tformat) - (tptr - tformat), "%d", prec);
+ tptr += strlen(tptr);
+ }
+ else
+ {
+ prec = 0;
+
+ while (isdigit(*format & 255))
+ {
+ if (tptr < (tformat + sizeof(tformat) - 1))
+ *tptr++ = *format;
+
+ prec = prec * 10 + *format++ - '0';
+ }
+ }
+ }
+ else
+ prec = -1;
+
+ if (*format == 'l' && format[1] == 'l')
+ {
+ size = 'L';
+
+ if (tptr < (tformat + sizeof(tformat) - 2))
+ {
+ *tptr++ = 'l';
+ *tptr++ = 'l';
+ }
+
+ format += 2;
+ }
+ else if (*format == 'h' || *format == 'l' || *format == 'L')
+ {
+ if (tptr < (tformat + sizeof(tformat) - 1))
+ *tptr++ = *format;
+
+ size = *format++;
+ }
+
+ if (!*format)
+ break;
+
+ if (tptr < (tformat + sizeof(tformat) - 1))
+ *tptr++ = *format;
+
+ type = *format++;
+ *tptr = '\0';
+
+ switch (type)
+ {
+ case 'E' : /* Floating point formats */
+ case 'G' :
+ case 'e' :
+ case 'f' :
+ case 'g' :
+ if ((width + 2) > sizeof(temp))
+ break;
+
+ sprintf(temp, tformat, va_arg(ap, double));
+
+ bytes += strlen(temp);
+
+ if (bufptr)
+ {
+ if ((bufptr + strlen(temp)) > bufend)
+ {
+ strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+ bufptr = bufend;
+ }
+ else
+ {
+ strcpy(bufptr, temp);
+ bufptr += strlen(temp);
+ }
+ }
+ break;
+
+ case 'B' : /* Integer formats */
+ case 'X' :
+ case 'b' :
+ case 'd' :
+ case 'i' :
+ case 'o' :
+ case 'u' :
+ case 'x' :
+ if ((width + 2) > sizeof(temp))
+ break;
+
+#ifdef HAVE_LONG_LONG
+ if (size == 'L')
+ sprintf(temp, tformat, va_arg(ap, long long));
+ else
+#endif /* HAVE_LONG_LONG */
+ sprintf(temp, tformat, va_arg(ap, int));
+
+ bytes += strlen(temp);
+
+ if (bufptr)
+ {
+ if ((bufptr + strlen(temp)) > bufend)
+ {
+ strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+ bufptr = bufend;
+ }
+ else
+ {
+ strcpy(bufptr, temp);
+ bufptr += strlen(temp);
+ }
+ }
+ break;
+
+ case 'p' : /* Pointer value */
+ if ((width + 2) > sizeof(temp))
+ break;
+
+ sprintf(temp, tformat, va_arg(ap, void *));
+
+ bytes += strlen(temp);
+
+ if (bufptr)
+ {
+ if ((bufptr + strlen(temp)) > bufend)
+ {
+ strncpy(bufptr, temp, (size_t)(bufend - bufptr));
+ bufptr = bufend;
+ }
+ else
+ {
+ strcpy(bufptr, temp);
+ bufptr += strlen(temp);
+ }
+ }
+ break;
+
+ case 'c' : /* Character or character array */
+ bytes += width;
+
+ if (bufptr)
+ {
+ if (width <= 1)
+ *bufptr++ = va_arg(ap, int);
+ else
+ {
+ if ((bufptr + width) > bufend)
+ width = bufend - bufptr;
+
+ memcpy(bufptr, va_arg(ap, char *), (size_t)width);
+ bufptr += width;
+ }
+ }
+ break;
+
+ case 's' : /* String */
+ if ((s = va_arg(ap, char *)) == NULL)
+ s = "(null)";
+
+ slen = strlen(s);
+ if (slen > width && prec != width)
+ width = slen;
+
+ bytes += width;
+
+ if (bufptr)
+ {
+ if ((bufptr + width) > bufend)
+ width = bufend - bufptr;
+
+ if (slen > width)
+ slen = width;
+
+ if (sign == '-')
+ {
+ strncpy(bufptr, s, (size_t)slen);
+ memset(bufptr + slen, ' ', (size_t)(width - slen));
+ }
+ else
+ {
+ memset(bufptr, ' ', (size_t)(width - slen));
+ strncpy(bufptr + width - slen, s, (size_t)slen);
+ }
+
+ bufptr += width;
+ }
+ break;
+
+ case 'n' : /* Output number of chars so far */
+ *(va_arg(ap, int *)) = bytes;
+ break;
+ }
+ }
+ else
+ {
+ bytes ++;
+
+ if (bufptr && bufptr < bufend)
+ *bufptr++ = *format;
+
+ format ++;
+ }
+ }
+
+ /*
+ * Nul-terminate the string and return the number of characters needed.
+ */
+
+ *bufptr = '\0';
+
+ return (bytes);
+}
+#endif /* !HAVE_VSNPRINTF */
+
+
+/*
+ * '_mxml_vstrdupf()' - Format and duplicate a string.
+ */
+
+char * /* O - New string pointer */
+_mxml_vstrdupf(const char *format, /* I - Printf-style format string */
+ va_list ap) /* I - Pointer to additional arguments */
+{
+ int bytes; /* Number of bytes required */
+ char *buffer, /* String buffer */
+ temp[256]; /* Small buffer for first vsnprintf */
+ va_list apcopy; /* Copy of argument list */
+
+
+ /*
+ * First format with a tiny buffer; this will tell us how many bytes are
+ * needed...
+ */
+
+ va_copy(apcopy, ap);
+ bytes = vsnprintf(temp, sizeof(temp), format, apcopy);
+
+ if (bytes < sizeof(temp))
+ {
+ /*
+ * Hey, the formatted string fits in the tiny buffer, so just dup that...
+ */
+
+ return (strdup(temp));
+ }
+
+ /*
+ * Allocate memory for the whole thing and reformat to the new, larger
+ * buffer...
+ */
+
+ if ((buffer = calloc(1, bytes + 1)) != NULL)
+ vsnprintf(buffer, bytes + 1, format, ap);
+
+ /*
+ * Return the new string...
+ */
+
+ return (buffer);
+}
+
+
+/*
+ * End of "$Id: mxml-string.c 454 2014-01-05 03:25:07Z msweet $".
+ */
diff --git a/tools/gator/daemon/mxml/mxml.h b/tools/gator/daemon/mxml/mxml.h
new file mode 100644
index 0000000..bba5fd2
--- /dev/null
+++ b/tools/gator/daemon/mxml/mxml.h
@@ -0,0 +1,332 @@
+/*
+ * "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $"
+ *
+ * Header file for Mini-XML, a small XML-like file parsing library.
+ *
+ * Copyright 2003-2014 by Michael R Sweet.
+ *
+ * These coded instructions, statements, and computer programs are the
+ * property of Michael R Sweet and are protected by Federal copyright
+ * law. Distribution and use rights are outlined in the file "COPYING"
+ * which should have been included with this file. If this file is
+ * missing or damaged, see the license at:
+ *
+ * http://www.msweet.org/projects.php/Mini-XML
+ */
+
+/*
+ * Prevent multiple inclusion...
+ */
+
+#ifndef _mxml_h_
+# define _mxml_h_
+
+/*
+ * Include necessary headers...
+ */
+
+# include <stdio.h>
+# include <stdlib.h>
+# include <string.h>
+# include <ctype.h>
+# include <errno.h>
+
+
+/*
+ * Constants...
+ */
+
+# define MXML_MAJOR_VERSION 2 /* Major version number */
+# define MXML_MINOR_VERSION 8 /* Minor version number */
+
+# define MXML_TAB 8 /* Tabs every N columns */
+
+# define MXML_NO_CALLBACK 0 /* Don't use a type callback */
+# define MXML_INTEGER_CALLBACK mxml_integer_cb
+ /* Treat all data as integers */
+# define MXML_OPAQUE_CALLBACK mxml_opaque_cb
+ /* Treat all data as opaque */
+# define MXML_REAL_CALLBACK mxml_real_cb
+ /* Treat all data as real numbers */
+# define MXML_TEXT_CALLBACK 0 /* Treat all data as text */
+# define MXML_IGNORE_CALLBACK mxml_ignore_cb
+ /* Ignore all non-element content */
+
+# define MXML_NO_PARENT 0 /* No parent for the node */
+
+# define MXML_DESCEND 1 /* Descend when finding/walking */
+# define MXML_NO_DESCEND 0 /* Don't descend when finding/walking */
+# define MXML_DESCEND_FIRST -1 /* Descend for first find */
+
+# define MXML_WS_BEFORE_OPEN 0 /* Callback for before open tag */
+# define MXML_WS_AFTER_OPEN 1 /* Callback for after open tag */
+# define MXML_WS_BEFORE_CLOSE 2 /* Callback for before close tag */
+# define MXML_WS_AFTER_CLOSE 3 /* Callback for after close tag */
+
+# define MXML_ADD_BEFORE 0 /* Add node before specified node */
+# define MXML_ADD_AFTER 1 /* Add node after specified node */
+# define MXML_ADD_TO_PARENT NULL /* Add node relative to parent */
+
+
+/*
+ * Data types...
+ */
+
+typedef enum mxml_sax_event_e /**** SAX event type. ****/
+{
+ MXML_SAX_CDATA, /* CDATA node */
+ MXML_SAX_COMMENT, /* Comment node */
+ MXML_SAX_DATA, /* Data node */
+ MXML_SAX_DIRECTIVE, /* Processing directive node */
+ MXML_SAX_ELEMENT_CLOSE, /* Element closed */
+ MXML_SAX_ELEMENT_OPEN /* Element opened */
+} mxml_sax_event_t;
+
+typedef enum mxml_type_e /**** The XML node type. ****/
+{
+ MXML_IGNORE = -1, /* Ignore/throw away node @since Mini-XML 2.3@ */
+ MXML_ELEMENT, /* XML element with attributes */
+ MXML_INTEGER, /* Integer value */
+ MXML_OPAQUE, /* Opaque string */
+ MXML_REAL, /* Real value */
+ MXML_TEXT, /* Text fragment */
+ MXML_CUSTOM /* Custom data @since Mini-XML 2.1@ */
+} mxml_type_t;
+
+typedef void (*mxml_custom_destroy_cb_t)(void *);
+ /**** Custom data destructor ****/
+
+typedef void (*mxml_error_cb_t)(const char *);
+ /**** Error callback function ****/
+
+typedef struct mxml_attr_s /**** An XML element attribute value. @private@ ****/
+{
+ char *name; /* Attribute name */
+ char *value; /* Attribute value */
+} mxml_attr_t;
+
+typedef struct mxml_element_s /**** An XML element value. @private@ ****/
+{
+ char *name; /* Name of element */
+ int num_attrs; /* Number of attributes */
+ mxml_attr_t *attrs; /* Attributes */
+} mxml_element_t;
+
+typedef struct mxml_text_s /**** An XML text value. @private@ ****/
+{
+ int whitespace; /* Leading whitespace? */
+ char *string; /* Fragment string */
+} mxml_text_t;
+
+typedef struct mxml_custom_s /**** An XML custom value. @private@ ****/
+{
+ void *data; /* Pointer to (allocated) custom data */
+ mxml_custom_destroy_cb_t destroy; /* Pointer to destructor function */
+} mxml_custom_t;
+
+typedef union mxml_value_u /**** An XML node value. @private@ ****/
+{
+ mxml_element_t element; /* Element */
+ int integer; /* Integer number */
+ char *opaque; /* Opaque string */
+ double real; /* Real number */
+ mxml_text_t text; /* Text fragment */
+ mxml_custom_t custom; /* Custom data @since Mini-XML 2.1@ */
+} mxml_value_t;
+
+struct mxml_node_s /**** An XML node. @private@ ****/
+{
+ mxml_type_t type; /* Node type */
+ struct mxml_node_s *next; /* Next node under same parent */
+ struct mxml_node_s *prev; /* Previous node under same parent */
+ struct mxml_node_s *parent; /* Parent node */
+ struct mxml_node_s *child; /* First child node */
+ struct mxml_node_s *last_child; /* Last child node */
+ mxml_value_t value; /* Node value */
+ int ref_count; /* Use count */
+ void *user_data; /* User data */
+};
+
+typedef struct mxml_node_s mxml_node_t; /**** An XML node. ****/
+
+struct mxml_index_s /**** An XML node index. @private@ ****/
+{
+ char *attr; /* Attribute used for indexing or NULL */
+ int num_nodes; /* Number of nodes in index */
+ int alloc_nodes; /* Allocated nodes in index */
+ int cur_node; /* Current node */
+ mxml_node_t **nodes; /* Node array */
+};
+
+typedef struct mxml_index_s mxml_index_t;
+ /**** An XML node index. ****/
+
+typedef int (*mxml_custom_load_cb_t)(mxml_node_t *, const char *);
+ /**** Custom data load callback function ****/
+
+typedef char *(*mxml_custom_save_cb_t)(mxml_node_t *);
+ /**** Custom data save callback function ****/
+
+typedef int (*mxml_entity_cb_t)(const char *);
+ /**** Entity callback function */
+
+typedef mxml_type_t (*mxml_load_cb_t)(mxml_node_t *);
+ /**** Load callback function ****/
+
+typedef const char *(*mxml_save_cb_t)(mxml_node_t *, int);
+ /**** Save callback function ****/
+
+typedef void (*mxml_sax_cb_t)(mxml_node_t *, mxml_sax_event_t, void *);
+ /**** SAX callback function ****/
+
+
+/*
+ * C++ support...
+ */
+
+# ifdef __cplusplus
+extern "C" {
+# endif /* __cplusplus */
+
+/*
+ * Prototypes...
+ */
+
+extern void mxmlAdd(mxml_node_t *parent, int where,
+ mxml_node_t *child, mxml_node_t *node);
+extern void mxmlDelete(mxml_node_t *node);
+extern void mxmlElementDeleteAttr(mxml_node_t *node,
+ const char *name);
+extern const char *mxmlElementGetAttr(mxml_node_t *node, const char *name);
+extern void mxmlElementSetAttr(mxml_node_t *node, const char *name,
+ const char *value);
+extern void mxmlElementSetAttrf(mxml_node_t *node, const char *name,
+ const char *format, ...)
+# ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+# endif /* __GNUC__ */
+;
+extern int mxmlEntityAddCallback(mxml_entity_cb_t cb);
+extern const char *mxmlEntityGetName(int val);
+extern int mxmlEntityGetValue(const char *name);
+extern void mxmlEntityRemoveCallback(mxml_entity_cb_t cb);
+extern mxml_node_t *mxmlFindElement(mxml_node_t *node, mxml_node_t *top,
+ const char *name, const char *attr,
+ const char *value, int descend);
+extern mxml_node_t *mxmlFindPath(mxml_node_t *node, const char *path);
+extern const char *mxmlGetCDATA(mxml_node_t *node);
+extern const void *mxmlGetCustom(mxml_node_t *node);
+extern const char *mxmlGetElement(mxml_node_t *node);
+extern mxml_node_t *mxmlGetFirstChild(mxml_node_t *node);
+extern int mxmlGetInteger(mxml_node_t *node);
+extern mxml_node_t *mxmlGetLastChild(mxml_node_t *node);
+extern mxml_node_t *mxmlGetNextSibling(mxml_node_t *node);
+extern const char *mxmlGetOpaque(mxml_node_t *node);
+extern mxml_node_t *mxmlGetParent(mxml_node_t *node);
+extern mxml_node_t *mxmlGetPrevSibling(mxml_node_t *node);
+extern double mxmlGetReal(mxml_node_t *node);
+extern int mxmlGetRefCount(mxml_node_t *node);
+extern const char *mxmlGetText(mxml_node_t *node, int *whitespace);
+extern mxml_type_t mxmlGetType(mxml_node_t *node);
+extern void *mxmlGetUserData(mxml_node_t *node);
+extern void mxmlIndexDelete(mxml_index_t *ind);
+extern mxml_node_t *mxmlIndexEnum(mxml_index_t *ind);
+extern mxml_node_t *mxmlIndexFind(mxml_index_t *ind,
+ const char *element,
+ const char *value);
+extern int mxmlIndexGetCount(mxml_index_t *ind);
+extern mxml_index_t *mxmlIndexNew(mxml_node_t *node, const char *element,
+ const char *attr);
+extern mxml_node_t *mxmlIndexReset(mxml_index_t *ind);
+extern mxml_node_t *mxmlLoadFd(mxml_node_t *top, int fd,
+ mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t *mxmlLoadFile(mxml_node_t *top, FILE *fp,
+ mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t *mxmlLoadString(mxml_node_t *top, const char *s,
+ mxml_type_t (*cb)(mxml_node_t *));
+extern mxml_node_t *mxmlNewCDATA(mxml_node_t *parent, const char *string);
+extern mxml_node_t *mxmlNewCustom(mxml_node_t *parent, void *data,
+ mxml_custom_destroy_cb_t destroy);
+extern mxml_node_t *mxmlNewElement(mxml_node_t *parent, const char *name);
+extern mxml_node_t *mxmlNewInteger(mxml_node_t *parent, int integer);
+extern mxml_node_t *mxmlNewOpaque(mxml_node_t *parent, const char *opaque);
+extern mxml_node_t *mxmlNewReal(mxml_node_t *parent, double real);
+extern mxml_node_t *mxmlNewText(mxml_node_t *parent, int whitespace,
+ const char *string);
+extern mxml_node_t *mxmlNewTextf(mxml_node_t *parent, int whitespace,
+ const char *format, ...)
+# ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+# endif /* __GNUC__ */
+;
+extern mxml_node_t *mxmlNewXML(const char *version);
+extern int mxmlRelease(mxml_node_t *node);
+extern void mxmlRemove(mxml_node_t *node);
+extern int mxmlRetain(mxml_node_t *node);
+extern char *mxmlSaveAllocString(mxml_node_t *node,
+ mxml_save_cb_t cb);
+extern int mxmlSaveFd(mxml_node_t *node, int fd,
+ mxml_save_cb_t cb);
+extern int mxmlSaveFile(mxml_node_t *node, FILE *fp,
+ mxml_save_cb_t cb);
+extern int mxmlSaveString(mxml_node_t *node, char *buffer,
+ int bufsize, mxml_save_cb_t cb);
+extern mxml_node_t *mxmlSAXLoadFd(mxml_node_t *top, int fd,
+ mxml_type_t (*cb)(mxml_node_t *),
+ mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t *mxmlSAXLoadFile(mxml_node_t *top, FILE *fp,
+ mxml_type_t (*cb)(mxml_node_t *),
+ mxml_sax_cb_t sax, void *sax_data);
+extern mxml_node_t *mxmlSAXLoadString(mxml_node_t *top, const char *s,
+ mxml_type_t (*cb)(mxml_node_t *),
+ mxml_sax_cb_t sax, void *sax_data);
+extern int mxmlSetCDATA(mxml_node_t *node, const char *data);
+extern int mxmlSetCustom(mxml_node_t *node, void *data,
+ mxml_custom_destroy_cb_t destroy);
+extern void mxmlSetCustomHandlers(mxml_custom_load_cb_t load,
+ mxml_custom_save_cb_t save);
+extern int mxmlSetElement(mxml_node_t *node, const char *name);
+extern void mxmlSetErrorCallback(mxml_error_cb_t cb);
+extern int mxmlSetInteger(mxml_node_t *node, int integer);
+extern int mxmlSetOpaque(mxml_node_t *node, const char *opaque);
+extern int mxmlSetReal(mxml_node_t *node, double real);
+extern int mxmlSetText(mxml_node_t *node, int whitespace,
+ const char *string);
+extern int mxmlSetTextf(mxml_node_t *node, int whitespace,
+ const char *format, ...)
+# ifdef __GNUC__
+__attribute__ ((__format__ (__printf__, 3, 4)))
+# endif /* __GNUC__ */
+;
+extern int mxmlSetUserData(mxml_node_t *node, void *data);
+extern void mxmlSetWrapMargin(int column);
+extern mxml_node_t *mxmlWalkNext(mxml_node_t *node, mxml_node_t *top,
+ int descend);
+extern mxml_node_t *mxmlWalkPrev(mxml_node_t *node, mxml_node_t *top,
+ int descend);
+
+
+/*
+ * Semi-private functions...
+ */
+
+extern void mxml_error(const char *format, ...);
+extern mxml_type_t mxml_ignore_cb(mxml_node_t *node);
+extern mxml_type_t mxml_integer_cb(mxml_node_t *node);
+extern mxml_type_t mxml_opaque_cb(mxml_node_t *node);
+extern mxml_type_t mxml_real_cb(mxml_node_t *node);
+
+
+/*
+ * C++ support...
+ */
+
+# ifdef __cplusplus
+}
+# endif /* __cplusplus */
+#endif /* !_mxml_h_ */
+
+
+/*
+ * End of "$Id: mxml.h 451 2014-01-04 21:50:06Z msweet $".
+ */
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index 5a1f648..274e178 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -1016,9 +1016,10 @@
if (sn_offset == 0)
strcpy(sn_str, cidr_mask);
- else
+ else {
+ strcat((char *)ip_buffer->sub_net, ";");
strcat(sn_str, cidr_mask);
- strcat((char *)ip_buffer->sub_net, ";");
+ }
sn_offset += strlen(sn_str) + 1;
}
diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
index 926cbf3..2c5a197 100644
--- a/tools/lib/lk/Makefile
+++ b/tools/lib/lk/Makefile
@@ -1,5 +1,8 @@
include ../../scripts/Makefile.include
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
# guard against environment variables
LIB_H=
LIB_OBJS=
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c
index 099e7cd..7c43479 100644
--- a/tools/lib/lk/debugfs.c
+++ b/tools/lib/lk/debugfs.c
@@ -5,7 +5,6 @@
#include <stdbool.h>
#include <sys/vfs.h>
#include <sys/mount.h>
-#include <linux/magic.h>
#include <linux/kernel.h>
#include "debugfs.h"
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 46878da..c9eac3e 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -101,7 +101,7 @@
dir1 = opendir(PATH_SYS_NODE);
if (!dir1)
- return -1;
+ return 0;
while ((dent1 = readdir(dir1)) != NULL) {
if (dent1->d_type != DT_DIR ||
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index 8ef3bd3..3e89719 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -173,7 +173,7 @@
# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
#
define get-executable-or-default
-$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2),$(1)))
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
endef
_ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
_gea_warn = $(warning The path '$(1)' is not executable.)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4bf91b0..794bb1a 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -113,7 +113,7 @@
static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) \
{ \
return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%", \
- (hpp_snprint_fn)percent_color_snprintf, true); \
+ percent_color_snprintf, true); \
}
#define __HPP_ENTRY_PERCENT_FN(_type, _field) \
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 11e46da1..66e44a5 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -318,8 +318,15 @@
return r;
}
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent)
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
{
- const char *color = get_percent_color(percent);
+ va_list args;
+ double percent;
+ const char *color;
+
+ va_start(args, fmt);
+ percent = va_arg(args, double);
+ va_end(args);
+ color = get_percent_color(percent);
return color_snprintf(bf, size, color, fmt, percent);
}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index dea082b..fced384 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,7 +39,7 @@
int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
-int percent_color_snprintf(char *bf, size_t size, const char *fmt, double percent);
+int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
const char *get_percent_color(double percent);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 07b1a3a..63b6f8c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1514,7 +1514,7 @@
switch (err) {
case EPERM:
case EACCES:
- return scnprintf(msg, size, "%s",
+ return scnprintf(msg, size,
"You may not have permission to collect %sstats.\n"
"Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
" -1 - Not paranoid at all\n"
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 14c2fe2..20764e0 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -34,6 +34,7 @@
u32 nr_invalid_chains;
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
+ u32 nr_unordered_events;
};
enum hist_column {
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6fcb9de..8bcdf9e 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -21,6 +21,7 @@
static inline int is_anon_memory(const char *filename)
{
return !strcmp(filename, "//anon") ||
+ !strcmp(filename, "/dev/zero (deleted)") ||
!strcmp(filename, "/anon_hugepage (deleted)");
}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index eacec85..b4741b0 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -282,7 +282,7 @@
event = find_cache_event(evsel);
if (!event)
- die("ug! no event found for type %" PRIu64, evsel->attr.config);
+ die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
pid = raw_field_value(event, "common_pid", data);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cf1fe01..6f593a7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -656,8 +656,7 @@
return -ETIME;
if (timestamp < s->ordered_samples.last_flush) {
- printf("Warning: Timestamp below last timeslice flush\n");
- return -EINVAL;
+ s->stats.nr_unordered_events++;
}
if (!list_empty(sc)) {
@@ -811,6 +810,7 @@
union perf_event *event)
{
const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ struct machine *machine;
if (perf_guest &&
((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
@@ -822,7 +822,11 @@
else
pid = event->ip.pid;
- return perf_session__findnew_machine(session, pid);
+ machine = perf_session__find_machine(session, pid);
+ if (!machine)
+ machine = perf_session__findnew_machine(session,
+ DEFAULT_GUEST_KERNEL_ID);
+ return machine;
}
return &session->machines.host;
@@ -1052,6 +1056,8 @@
"Do you have a KVM guest running and not using 'perf kvm'?\n",
session->stats.nr_unprocessable_samples);
}
+ if (session->stats.nr_unordered_events != 0)
+ ui__warning("%u out of order events recorded.\n", session->stats.nr_unordered_events);
}
#define session_done() (*(volatile int *)(&session_done))
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index dc4de37..bcf1d2f 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -18,9 +18,9 @@
#include "helpers/bitmask.h"
static struct option set_opts[] = {
- { .name = "perf-bias", .has_arg = optional_argument, .flag = NULL, .val = 'b'},
- { .name = "sched-mc", .has_arg = optional_argument, .flag = NULL, .val = 'm'},
- { .name = "sched-smt", .has_arg = optional_argument, .flag = NULL, .val = 's'},
+ { .name = "perf-bias", .has_arg = required_argument, .flag = NULL, .val = 'b'},
+ { .name = "sched-mc", .has_arg = required_argument, .flag = NULL, .val = 'm'},
+ { .name = "sched-smt", .has_arg = required_argument, .flag = NULL, .val = 's'},
{ },
};
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f09641d..4039854 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -1,11 +1,15 @@
CC = $(CROSS_COMPILE)gcc
-BUILD_OUTPUT := $(PWD)
+BUILD_OUTPUT := $(CURDIR)
PREFIX := /usr
DESTDIR :=
+ifeq ("$(origin O)", "command line")
+ BUILD_OUTPUT := $(O)
+endif
+
turbostat : turbostat.c
CFLAGS += -Wall
-CFLAGS += -I../../../../arch/x86/include/uapi/
+CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
%: %.c
@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index fe70207..6a7ee5f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,7 +20,7 @@
*/
#define _GNU_SOURCE
-#include <asm/msr.h>
+#include MSRHEADER
#include <stdio.h>
#include <unistd.h>
#include <sys/types.h>
@@ -35,6 +35,7 @@
#include <string.h>
#include <ctype.h>
#include <sched.h>
+#include <cpuid.h>
char *proc_stat = "/proc/stat";
unsigned int interval_sec = 5; /* set with -i interval_sec */
@@ -1894,7 +1895,7 @@
eax = ebx = ecx = edx = 0;
- asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0));
+ __get_cpuid(0, &max_level, &ebx, &ecx, &edx);
if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
genuine_intel = 1;
@@ -1903,7 +1904,7 @@
fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
(char *)&ebx, (char *)&edx, (char *)&ecx);
- asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
+ __get_cpuid(1, &fms, &ebx, &ecx, &edx);
family = (fms >> 8) & 0xf;
model = (fms >> 4) & 0xf;
stepping = fms & 0xf;
@@ -1925,7 +1926,7 @@
* This check is valid for both Intel and AMD.
*/
ebx = ecx = edx = 0;
- asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000));
+ __get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
if (max_level < 0x80000007) {
fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level);
@@ -1936,7 +1937,7 @@
* Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
* this check is valid for both Intel and AMD
*/
- asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
+ __get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
has_invariant_tsc = edx & (1 << 8);
if (!has_invariant_tsc) {
@@ -1949,7 +1950,7 @@
* this check is valid for both Intel and AMD
*/
- asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
+ __get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
has_aperf = ecx & (1 << 0);
do_dts = eax & (1 << 0);
do_ptm = eax & (1 << 6);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0a63658..2cee2b7 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -4,6 +4,7 @@
TARGETS += kcmp
TARGETS += memory-hotplug
TARGETS += mqueue
+TARGETS += mount
TARGETS += net
TARGETS += ptrace
TARGETS += vm
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
new file mode 100644
index 0000000..337d853
--- /dev/null
+++ b/tools/testing/selftests/mount/Makefile
@@ -0,0 +1,17 @@
+# Makefile for mount selftests.
+
+all: unprivileged-remount-test
+
+unprivileged-remount-test: unprivileged-remount-test.c
+ gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test
+
+# Allow specific tests to be selected.
+test_unprivileged_remount: unprivileged-remount-test
+ @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi
+
+run_tests: all test_unprivileged_remount
+
+clean:
+ rm -f unprivileged-remount-test
+
+.PHONY: all test_unprivileged_remount
diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c
new file mode 100644
index 0000000..5177850
--- /dev/null
+++ b/tools/testing/selftests/mount/unprivileged-remount-test.c
@@ -0,0 +1,370 @@
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#ifndef CLONE_NEWNS
+# define CLONE_NEWNS 0x00020000
+#endif
+#ifndef CLONE_NEWUTS
+# define CLONE_NEWUTS 0x04000000
+#endif
+#ifndef CLONE_NEWIPC
+# define CLONE_NEWIPC 0x08000000
+#endif
+#ifndef CLONE_NEWNET
+# define CLONE_NEWNET 0x40000000
+#endif
+#ifndef CLONE_NEWUSER
+# define CLONE_NEWUSER 0x10000000
+#endif
+#ifndef CLONE_NEWPID
+# define CLONE_NEWPID 0x20000000
+#endif
+
+#ifndef MS_REC
+# define MS_REC 16384
+#endif
+#ifndef MS_RELATIME
+# define MS_RELATIME (1 << 21)
+#endif
+#ifndef MS_STRICTATIME
+# define MS_STRICTATIME (1 << 24)
+#endif
+
+static void die(char *fmt, ...)
+{
+ va_list ap;
+ va_start(ap, fmt);
+ vfprintf(stderr, fmt, ap);
+ va_end(ap);
+ exit(EXIT_FAILURE);
+}
+
+static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap)
+{
+ char buf[4096];
+ int fd;
+ ssize_t written;
+ int buf_len;
+
+ buf_len = vsnprintf(buf, sizeof(buf), fmt, ap);
+ if (buf_len < 0) {
+ die("vsnprintf failed: %s\n",
+ strerror(errno));
+ }
+ if (buf_len >= sizeof(buf)) {
+ die("vsnprintf output truncated\n");
+ }
+
+ fd = open(filename, O_WRONLY);
+ if (fd < 0) {
+ if ((errno == ENOENT) && enoent_ok)
+ return;
+ die("open of %s failed: %s\n",
+ filename, strerror(errno));
+ }
+ written = write(fd, buf, buf_len);
+ if (written != buf_len) {
+ if (written >= 0) {
+ die("short write to %s\n", filename);
+ } else {
+ die("write to %s failed: %s\n",
+ filename, strerror(errno));
+ }
+ }
+ if (close(fd) != 0) {
+ die("close of %s failed: %s\n",
+ filename, strerror(errno));
+ }
+}
+
+static void maybe_write_file(char *filename, char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ vmaybe_write_file(true, filename, fmt, ap);
+ va_end(ap);
+
+}
+
+static void write_file(char *filename, char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ vmaybe_write_file(false, filename, fmt, ap);
+ va_end(ap);
+
+}
+
+static int read_mnt_flags(const char *path)
+{
+ int ret;
+ struct statvfs stat;
+ int mnt_flags;
+
+ ret = statvfs(path, &stat);
+ if (ret != 0) {
+ die("statvfs of %s failed: %s\n",
+ path, strerror(errno));
+ }
+ if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | \
+ ST_NOEXEC | ST_NOATIME | ST_NODIRATIME | ST_RELATIME | \
+ ST_SYNCHRONOUS | ST_MANDLOCK)) {
+ die("Unrecognized mount flags\n");
+ }
+ mnt_flags = 0;
+ if (stat.f_flag & ST_RDONLY)
+ mnt_flags |= MS_RDONLY;
+ if (stat.f_flag & ST_NOSUID)
+ mnt_flags |= MS_NOSUID;
+ if (stat.f_flag & ST_NODEV)
+ mnt_flags |= MS_NODEV;
+ if (stat.f_flag & ST_NOEXEC)
+ mnt_flags |= MS_NOEXEC;
+ if (stat.f_flag & ST_NOATIME)
+ mnt_flags |= MS_NOATIME;
+ if (stat.f_flag & ST_NODIRATIME)
+ mnt_flags |= MS_NODIRATIME;
+ if (stat.f_flag & ST_RELATIME)
+ mnt_flags |= MS_RELATIME;
+ if (stat.f_flag & ST_SYNCHRONOUS)
+ mnt_flags |= MS_SYNCHRONOUS;
+ if (stat.f_flag & ST_MANDLOCK)
+ mnt_flags |= ST_MANDLOCK;
+
+ return mnt_flags;
+}
+
+static void create_and_enter_userns(void)
+{
+ uid_t uid;
+ gid_t gid;
+
+ uid = getuid();
+ gid = getgid();
+
+ if (unshare(CLONE_NEWUSER) !=0) {
+ die("unshare(CLONE_NEWUSER) failed: %s\n",
+ strerror(errno));
+ }
+
+ maybe_write_file("/proc/self/setgroups", "deny");
+ write_file("/proc/self/uid_map", "0 %d 1", uid);
+ write_file("/proc/self/gid_map", "0 %d 1", gid);
+
+ if (setgid(0) != 0) {
+ die ("setgid(0) failed %s\n",
+ strerror(errno));
+ }
+ if (setuid(0) != 0) {
+ die("setuid(0) failed %s\n",
+ strerror(errno));
+ }
+}
+
+static
+bool test_unpriv_remount(const char *fstype, const char *mount_options,
+ int mount_flags, int remount_flags, int invalid_flags)
+{
+ pid_t child;
+
+ child = fork();
+ if (child == -1) {
+ die("fork failed: %s\n",
+ strerror(errno));
+ }
+ if (child != 0) { /* parent */
+ pid_t pid;
+ int status;
+ pid = waitpid(child, &status, 0);
+ if (pid == -1) {
+ die("waitpid failed: %s\n",
+ strerror(errno));
+ }
+ if (pid != child) {
+ die("waited for %d got %d\n",
+ child, pid);
+ }
+ if (!WIFEXITED(status)) {
+ die("child did not terminate cleanly\n");
+ }
+ return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+ }
+
+ create_and_enter_userns();
+ if (unshare(CLONE_NEWNS) != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("testing", "/tmp", fstype, mount_flags, mount_options) != 0) {
+ die("mount of %s with options '%s' on /tmp failed: %s\n",
+ fstype,
+ mount_options? mount_options : "",
+ strerror(errno));
+ }
+
+ create_and_enter_userns();
+
+ if (unshare(CLONE_NEWNS) != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("/tmp", "/tmp", "none",
+ MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) {
+ /* system("cat /proc/self/mounts"); */
+ die("remount of /tmp failed: %s\n",
+ strerror(errno));
+ }
+
+ if (mount("/tmp", "/tmp", "none",
+ MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) {
+ /* system("cat /proc/self/mounts"); */
+ die("remount of /tmp with invalid flags "
+ "succeeded unexpectedly\n");
+ }
+ exit(EXIT_SUCCESS);
+}
+
+static bool test_unpriv_remount_simple(int mount_flags)
+{
+ return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags, 0);
+}
+
+static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags)
+{
+ return test_unpriv_remount("ramfs", NULL, mount_flags, mount_flags,
+ invalid_flags);
+}
+
+static bool test_priv_mount_unpriv_remount(void)
+{
+ pid_t child;
+ int ret;
+ const char *orig_path = "/dev";
+ const char *dest_path = "/tmp";
+ int orig_mnt_flags, remount_mnt_flags;
+
+ child = fork();
+ if (child == -1) {
+ die("fork failed: %s\n",
+ strerror(errno));
+ }
+ if (child != 0) { /* parent */
+ pid_t pid;
+ int status;
+ pid = waitpid(child, &status, 0);
+ if (pid == -1) {
+ die("waitpid failed: %s\n",
+ strerror(errno));
+ }
+ if (pid != child) {
+ die("waited for %d got %d\n",
+ child, pid);
+ }
+ if (!WIFEXITED(status)) {
+ die("child did not terminate cleanly\n");
+ }
+ return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false;
+ }
+
+ orig_mnt_flags = read_mnt_flags(orig_path);
+
+ create_and_enter_userns();
+ ret = unshare(CLONE_NEWNS);
+ if (ret != 0) {
+ die("unshare(CLONE_NEWNS) failed: %s\n",
+ strerror(errno));
+ }
+
+ ret = mount(orig_path, dest_path, "bind", MS_BIND | MS_REC, NULL);
+ if (ret != 0) {
+ die("recursive bind mount of %s onto %s failed: %s\n",
+ orig_path, dest_path, strerror(errno));
+ }
+
+ ret = mount(dest_path, dest_path, "none",
+ MS_REMOUNT | MS_BIND | orig_mnt_flags , NULL);
+ if (ret != 0) {
+ /* system("cat /proc/self/mounts"); */
+ die("remount of /tmp failed: %s\n",
+ strerror(errno));
+ }
+
+ remount_mnt_flags = read_mnt_flags(dest_path);
+ if (orig_mnt_flags != remount_mnt_flags) {
+ die("Mount flags unexpectedly changed during remount of %s originally mounted on %s\n",
+ dest_path, orig_path);
+ }
+ exit(EXIT_SUCCESS);
+}
+
+int main(int argc, char **argv)
+{
+ if (!test_unpriv_remount_simple(MS_RDONLY)) {
+ die("MS_RDONLY malfunctions\n");
+ }
+ if (!test_unpriv_remount("devpts", "newinstance", MS_NODEV, MS_NODEV, 0)) {
+ die("MS_NODEV malfunctions\n");
+ }
+ if (!test_unpriv_remount_simple(MS_NOSUID)) {
+ die("MS_NOSUID malfunctions\n");
+ }
+ if (!test_unpriv_remount_simple(MS_NOEXEC)) {
+ die("MS_NOEXEC malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_RELATIME,
+ MS_NOATIME))
+ {
+ die("MS_RELATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_STRICTATIME,
+ MS_NOATIME))
+ {
+ die("MS_STRICTATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_NOATIME,
+ MS_STRICTATIME))
+ {
+ die("MS_NOATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME,
+ MS_NOATIME))
+ {
+ die("MS_RELATIME|MS_NODIRATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME,
+ MS_NOATIME))
+ {
+ die("MS_STRICTATIME|MS_NODIRATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME,
+ MS_STRICTATIME))
+ {
+ die("MS_NOATIME|MS_DIRATIME malfunctions\n");
+ }
+ if (!test_unpriv_remount("ramfs", NULL, MS_STRICTATIME, 0, MS_NOATIME))
+ {
+ die("Default atime malfunctions\n");
+ }
+ if (!test_priv_mount_unpriv_remount()) {
+ die("Mount flags unexpectedly changed after remount\n");
+ }
+ return EXIT_SUCCESS;
+}
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index fe1e66b..a87e99f 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -116,8 +116,8 @@
.header = {
.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
.length = cpu_to_le32(sizeof descriptors),
- .fs_count = 3,
- .hs_count = 3,
+ .fs_count = cpu_to_le32(3),
+ .hs_count = cpu_to_le32(3),
},
.fs_descs = {
.intf = {
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 779262f..fc0c5e6 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -6,6 +6,9 @@
config HAVE_KVM_IRQCHIP
bool
+config HAVE_KVM_IRQFD
+ bool
+
config HAVE_KVM_IRQ_ROUTING
bool
@@ -22,8 +25,15 @@
config KVM_ASYNC_PF
bool
+# Toggle to switch between direct notification and batch job
+config KVM_ASYNC_PF_SYNC
+ bool
+
config HAVE_KVM_MSI
bool
config HAVE_KVM_CPU_RELAX_INTERCEPT
bool
+
+config KVM_VFIO
+ bool
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
new file mode 100644
index 0000000..5081e80
--- /dev/null
+++ b/virt/kvm/arm/arch_timer.c
@@ -0,0 +1,318 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/cpu.h>
+#include <linux/of_irq.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+
+#include <clocksource/arm_arch_timer.h>
+#include <asm/arch_timer.h>
+
+#include <kvm/arm_vgic.h>
+#include <kvm/arm_arch_timer.h>
+
+static struct timecounter *timecounter;
+static struct workqueue_struct *wqueue;
+static unsigned int host_vtimer_irq;
+
+static cycle_t kvm_phys_timer_read(void)
+{
+ return timecounter->cc->read(timecounter->cc);
+}
+
+static bool timer_is_armed(struct arch_timer_cpu *timer)
+{
+ return timer->armed;
+}
+
+/* timer_arm: as in "arm the timer", not as in ARM the company */
+static void timer_arm(struct arch_timer_cpu *timer, u64 ns)
+{
+ timer->armed = true;
+ hrtimer_start(&timer->timer, ktime_add_ns(ktime_get(), ns),
+ HRTIMER_MODE_ABS);
+}
+
+static void timer_disarm(struct arch_timer_cpu *timer)
+{
+ if (timer_is_armed(timer)) {
+ hrtimer_cancel(&timer->timer);
+ cancel_work_sync(&timer->expired);
+ timer->armed = false;
+ }
+}
+
+static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
+ kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
+ timer->irq->irq,
+ timer->irq->level);
+}
+
+static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
+{
+ struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
+
+ /*
+ * We disable the timer in the world switch and let it be
+ * handled by kvm_timer_sync_hwstate(). Getting a timer
+ * interrupt at this point is a sure sign of some major
+ * breakage.
+ */
+ pr_warn("Unexpected interrupt %d on vcpu %p\n", irq, vcpu);
+ return IRQ_HANDLED;
+}
+
+static void kvm_timer_inject_irq_work(struct work_struct *work)
+{
+ struct kvm_vcpu *vcpu;
+
+ vcpu = container_of(work, struct kvm_vcpu, arch.timer_cpu.expired);
+ vcpu->arch.timer_cpu.armed = false;
+ kvm_timer_inject_irq(vcpu);
+}
+
+static enum hrtimer_restart kvm_timer_expire(struct hrtimer *hrt)
+{
+ struct arch_timer_cpu *timer;
+ timer = container_of(hrt, struct arch_timer_cpu, timer);
+ queue_work(wqueue, &timer->expired);
+ return HRTIMER_NORESTART;
+}
+
+/**
+ * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Disarm any pending soft timers, since the world-switch code will write the
+ * virtual timer state back to the physical CPU.
+ */
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ /*
+ * We're about to run this vcpu again, so there is no need to
+ * keep the background timer running, as we're about to
+ * populate the CPU timer again.
+ */
+ timer_disarm(timer);
+}
+
+/**
+ * kvm_timer_sync_hwstate - sync timer state from cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the virtual timer was armed and either schedule a corresponding
+ * soft timer or inject directly if already expired.
+ */
+void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+ cycle_t cval, now;
+ u64 ns;
+
+ if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
+ !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE))
+ return;
+
+ cval = timer->cntv_cval;
+ now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+ BUG_ON(timer_is_armed(timer));
+
+ if (cval <= now) {
+ /*
+ * Timer has already expired while we were not
+ * looking. Inject the interrupt and carry on.
+ */
+ kvm_timer_inject_irq(vcpu);
+ return;
+ }
+
+ ns = cyclecounter_cyc2ns(timecounter->cc, cval - now);
+ timer_arm(timer, ns);
+}
+
+void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
+ const struct kvm_irq_level *irq)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ /*
+ * The vcpu timer irq number cannot be determined in
+ * kvm_timer_vcpu_init() because it is called much before
+ * kvm_vcpu_set_target(). To handle this, we determine
+ * vcpu timer irq number when the vcpu is reset.
+ */
+ timer->irq = irq;
+}
+
+void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ INIT_WORK(&timer->expired, kvm_timer_inject_irq_work);
+ hrtimer_init(&timer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ timer->timer.function = kvm_timer_expire;
+}
+
+static void kvm_timer_init_interrupt(void *info)
+{
+ enable_percpu_irq(host_vtimer_irq, 0);
+}
+
+int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ switch (regid) {
+ case KVM_REG_ARM_TIMER_CTL:
+ timer->cntv_ctl = value;
+ break;
+ case KVM_REG_ARM_TIMER_CNT:
+ vcpu->kvm->arch.timer.cntvoff = kvm_phys_timer_read() - value;
+ break;
+ case KVM_REG_ARM_TIMER_CVAL:
+ timer->cntv_cval = value;
+ break;
+ default:
+ return -1;
+ }
+ return 0;
+}
+
+u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ switch (regid) {
+ case KVM_REG_ARM_TIMER_CTL:
+ return timer->cntv_ctl;
+ case KVM_REG_ARM_TIMER_CNT:
+ return kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+ case KVM_REG_ARM_TIMER_CVAL:
+ return timer->cntv_cval;
+ }
+ return (u64)-1;
+}
+
+static int kvm_timer_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *cpu)
+{
+ switch (action) {
+ case CPU_STARTING:
+ case CPU_STARTING_FROZEN:
+ kvm_timer_init_interrupt(NULL);
+ break;
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ disable_percpu_irq(host_vtimer_irq);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block kvm_timer_cpu_nb = {
+ .notifier_call = kvm_timer_cpu_notify,
+};
+
+static const struct of_device_id arch_timer_of_match[] = {
+ { .compatible = "arm,armv7-timer", },
+ { .compatible = "arm,armv8-timer", },
+ {},
+};
+
+int kvm_timer_hyp_init(void)
+{
+ struct device_node *np;
+ unsigned int ppi;
+ int err;
+
+ timecounter = arch_timer_get_timecounter();
+ if (!timecounter)
+ return -ENODEV;
+
+ np = of_find_matching_node(NULL, arch_timer_of_match);
+ if (!np) {
+ kvm_err("kvm_arch_timer: can't find DT node\n");
+ return -ENODEV;
+ }
+
+ ppi = irq_of_parse_and_map(np, 2);
+ if (!ppi) {
+ kvm_err("kvm_arch_timer: no virtual timer interrupt\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = request_percpu_irq(ppi, kvm_arch_timer_handler,
+ "kvm guest timer", kvm_get_running_vcpus());
+ if (err) {
+ kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n",
+ ppi, err);
+ goto out;
+ }
+
+ host_vtimer_irq = ppi;
+
+ err = register_cpu_notifier(&kvm_timer_cpu_nb);
+ if (err) {
+ kvm_err("Cannot register timer CPU notifier\n");
+ goto out_free;
+ }
+
+ wqueue = create_singlethread_workqueue("kvm_arch_timer");
+ if (!wqueue) {
+ err = -ENOMEM;
+ goto out_free;
+ }
+
+ kvm_info("%s IRQ%d\n", np->name, ppi);
+ on_each_cpu(kvm_timer_init_interrupt, NULL, 1);
+
+ goto out;
+out_free:
+ free_percpu_irq(ppi, kvm_get_running_vcpus());
+out:
+ of_node_put(np);
+ return err;
+}
+
+void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ timer_disarm(timer);
+}
+
+int kvm_timer_init(struct kvm *kvm)
+{
+ if (timecounter && wqueue) {
+ kvm->arch.timer.cntvoff = kvm_phys_timer_read();
+ kvm->arch.timer.enabled = 1;
+ }
+
+ return 0;
+}
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
new file mode 100644
index 0000000..01124ef
--- /dev/null
+++ b/virt/kvm/arm/vgic-v2.c
@@ -0,0 +1,265 @@
+/*
+ * Copyright (C) 2012,2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+static struct vgic_lr vgic_v2_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ struct vgic_lr lr_desc;
+ u32 val = vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr];
+
+ lr_desc.irq = val & GICH_LR_VIRTUALID;
+ if (lr_desc.irq <= 15)
+ lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+ else
+ lr_desc.source = 0;
+ lr_desc.state = 0;
+
+ if (val & GICH_LR_PENDING_BIT)
+ lr_desc.state |= LR_STATE_PENDING;
+ if (val & GICH_LR_ACTIVE_BIT)
+ lr_desc.state |= LR_STATE_ACTIVE;
+ if (val & GICH_LR_EOI)
+ lr_desc.state |= LR_EOI_INT;
+
+ return lr_desc;
+}
+
+static void vgic_v2_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ u32 lr_val = (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) | lr_desc.irq;
+
+ if (lr_desc.state & LR_STATE_PENDING)
+ lr_val |= GICH_LR_PENDING_BIT;
+ if (lr_desc.state & LR_STATE_ACTIVE)
+ lr_val |= GICH_LR_ACTIVE_BIT;
+ if (lr_desc.state & LR_EOI_INT)
+ lr_val |= GICH_LR_EOI;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
+}
+
+static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ if (!(lr_desc.state & LR_STATE_MASK))
+ set_bit(lr, (unsigned long *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr);
+}
+
+static u64 vgic_v2_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+#if BITS_PER_LONG == 64
+ val = vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[1];
+ val <<= 32;
+ val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr[0];
+#else
+ val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr;
+#endif
+ return val;
+}
+
+static u64 vgic_v2_get_eisr(const struct kvm_vcpu *vcpu)
+{
+ u64 val;
+
+#if BITS_PER_LONG == 64
+ val = vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[1];
+ val <<= 32;
+ val |= vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr[0];
+#else
+ val = *(u64 *)vcpu->arch.vgic_cpu.vgic_v2.vgic_eisr;
+#endif
+ return val;
+}
+
+static u32 vgic_v2_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+ u32 misr = vcpu->arch.vgic_cpu.vgic_v2.vgic_misr;
+ u32 ret = 0;
+
+ if (misr & GICH_MISR_EOI)
+ ret |= INT_STATUS_EOI;
+ if (misr & GICH_MISR_U)
+ ret |= INT_STATUS_UNDERFLOW;
+
+ return ret;
+}
+
+static void vgic_v2_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr |= GICH_HCR_UIE;
+}
+
+static void vgic_v2_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr &= ~GICH_HCR_UIE;
+}
+
+static void vgic_v2_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >> GICH_VMCR_CTRL_SHIFT;
+ vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >> GICH_VMCR_ALIAS_BINPOINT_SHIFT;
+ vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >> GICH_VMCR_BINPOINT_SHIFT;
+ vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >> GICH_VMCR_PRIMASK_SHIFT;
+}
+
+static void vgic_v2_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+ vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) & GICH_VMCR_ALIAS_BINPOINT_MASK;
+ vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) & GICH_VMCR_BINPOINT_MASK;
+ vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
+}
+
+static void vgic_v2_enable(struct kvm_vcpu *vcpu)
+{
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
+
+ /* Get the show on the road... */
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v2_ops = {
+ .get_lr = vgic_v2_get_lr,
+ .set_lr = vgic_v2_set_lr,
+ .sync_lr_elrsr = vgic_v2_sync_lr_elrsr,
+ .get_elrsr = vgic_v2_get_elrsr,
+ .get_eisr = vgic_v2_get_eisr,
+ .get_interrupt_status = vgic_v2_get_interrupt_status,
+ .enable_underflow = vgic_v2_enable_underflow,
+ .disable_underflow = vgic_v2_disable_underflow,
+ .get_vmcr = vgic_v2_get_vmcr,
+ .set_vmcr = vgic_v2_set_vmcr,
+ .enable = vgic_v2_enable,
+};
+
+static struct vgic_params vgic_v2_params;
+
+/**
+ * vgic_v2_probe - probe for a GICv2 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ * @ops: address of a pointer to the GICv2 operations
+ * @params: address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv2 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v2_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
+{
+ int ret;
+ struct resource vctrl_res;
+ struct resource vcpu_res;
+ struct vgic_params *vgic = &vgic_v2_params;
+
+ vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+ if (!vgic->maint_irq) {
+ kvm_err("error getting vgic maintenance irq from DT\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ret = of_address_to_resource(vgic_node, 2, &vctrl_res);
+ if (ret) {
+ kvm_err("Cannot obtain GICH resource\n");
+ goto out;
+ }
+
+ vgic->vctrl_base = of_iomap(vgic_node, 2);
+ if (!vgic->vctrl_base) {
+ kvm_err("Cannot ioremap GICH\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ vgic->nr_lr = readl_relaxed(vgic->vctrl_base + GICH_VTR);
+ vgic->nr_lr = (vgic->nr_lr & 0x3f) + 1;
+
+ ret = create_hyp_io_mappings(vgic->vctrl_base,
+ vgic->vctrl_base + resource_size(&vctrl_res),
+ vctrl_res.start);
+ if (ret) {
+ kvm_err("Cannot map VCTRL into hyp\n");
+ goto out_unmap;
+ }
+
+ if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
+ kvm_err("Cannot obtain GICV resource\n");
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ if (!PAGE_ALIGNED(vcpu_res.start)) {
+ kvm_err("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)vcpu_res.start);
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&vcpu_res),
+ PAGE_SIZE);
+ ret = -ENXIO;
+ goto out_unmap;
+ }
+
+ vgic->vcpu_base = vcpu_res.start;
+
+ kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+ vctrl_res.start, vgic->maint_irq);
+
+ vgic->type = VGIC_V2;
+ *ops = &vgic_v2_ops;
+ *params = vgic;
+ goto out;
+
+out_unmap:
+ iounmap(vgic->vctrl_base);
+out:
+ of_node_put(vgic_node);
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
new file mode 100644
index 0000000..1c2c8ee
--- /dev/null
+++ b/virt/kvm/arm/vgic-v3.c
@@ -0,0 +1,247 @@
+/*
+ * Copyright (C) 2013 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID (0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT (10)
+#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
+
+/*
+ * LRs are stored in reverse order in memory. make sure we index them
+ * correctly.
+ */
+#define LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
+
+static u32 ich_vtr_el2;
+
+static struct vgic_lr vgic_v3_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ struct vgic_lr lr_desc;
+ u64 val = vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)];
+
+ lr_desc.irq = val & GICH_LR_VIRTUALID;
+ if (lr_desc.irq <= 15)
+ lr_desc.source = (val >> GICH_LR_PHYSID_CPUID_SHIFT) & 0x7;
+ else
+ lr_desc.source = 0;
+ lr_desc.state = 0;
+
+ if (val & ICH_LR_PENDING_BIT)
+ lr_desc.state |= LR_STATE_PENDING;
+ if (val & ICH_LR_ACTIVE_BIT)
+ lr_desc.state |= LR_STATE_ACTIVE;
+ if (val & ICH_LR_EOI)
+ lr_desc.state |= LR_EOI_INT;
+
+ return lr_desc;
+}
+
+static void vgic_v3_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ u64 lr_val = (((u32)lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT) |
+ lr_desc.irq);
+
+ if (lr_desc.state & LR_STATE_PENDING)
+ lr_val |= ICH_LR_PENDING_BIT;
+ if (lr_desc.state & LR_STATE_ACTIVE)
+ lr_val |= ICH_LR_ACTIVE_BIT;
+ if (lr_desc.state & LR_EOI_INT)
+ lr_val |= ICH_LR_EOI;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val;
+}
+
+static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr lr_desc)
+{
+ if (!(lr_desc.state & LR_STATE_MASK))
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
+}
+
+static u64 vgic_v3_get_elrsr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr;
+}
+
+static u64 vgic_v3_get_eisr(const struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.vgic_cpu.vgic_v3.vgic_eisr;
+}
+
+static u32 vgic_v3_get_interrupt_status(const struct kvm_vcpu *vcpu)
+{
+ u32 misr = vcpu->arch.vgic_cpu.vgic_v3.vgic_misr;
+ u32 ret = 0;
+
+ if (misr & ICH_MISR_EOI)
+ ret |= INT_STATUS_EOI;
+ if (misr & ICH_MISR_U)
+ ret |= INT_STATUS_UNDERFLOW;
+
+ return ret;
+}
+
+static void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr = vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr;
+
+ vmcrp->ctlr = (vmcr & ICH_VMCR_CTLR_MASK) >> ICH_VMCR_CTLR_SHIFT;
+ vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
+ vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
+ vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
+}
+
+static void vgic_v3_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr |= ICH_HCR_UIE;
+}
+
+static void vgic_v3_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr &= ~ICH_HCR_UIE;
+}
+
+static void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
+{
+ u32 vmcr;
+
+ vmcr = (vmcrp->ctlr << ICH_VMCR_CTLR_SHIFT) & ICH_VMCR_CTLR_MASK;
+ vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
+ vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
+ vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
+
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = vmcr;
+}
+
+static void vgic_v3_enable(struct kvm_vcpu *vcpu)
+{
+ /*
+ * By forcing VMCR to zero, the GIC will restore the binary
+ * points to their reset values. Anything else resets to zero
+ * anyway.
+ */
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_vmcr = 0;
+
+ /* Get the show on the road... */
+ vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr = ICH_HCR_EN;
+}
+
+static const struct vgic_ops vgic_v3_ops = {
+ .get_lr = vgic_v3_get_lr,
+ .set_lr = vgic_v3_set_lr,
+ .sync_lr_elrsr = vgic_v3_sync_lr_elrsr,
+ .get_elrsr = vgic_v3_get_elrsr,
+ .get_eisr = vgic_v3_get_eisr,
+ .get_interrupt_status = vgic_v3_get_interrupt_status,
+ .enable_underflow = vgic_v3_enable_underflow,
+ .disable_underflow = vgic_v3_disable_underflow,
+ .get_vmcr = vgic_v3_get_vmcr,
+ .set_vmcr = vgic_v3_set_vmcr,
+ .enable = vgic_v3_enable,
+};
+
+static struct vgic_params vgic_v3_params;
+
+/**
+ * vgic_v3_probe - probe for a GICv3 compatible interrupt controller in DT
+ * @node: pointer to the DT node
+ * @ops: address of a pointer to the GICv3 operations
+ * @params: address of a pointer to HW-specific parameters
+ *
+ * Returns 0 if a GICv3 has been found, with the low level operations
+ * in *ops and the HW parameters in *params. Returns an error code
+ * otherwise.
+ */
+int vgic_v3_probe(struct device_node *vgic_node,
+ const struct vgic_ops **ops,
+ const struct vgic_params **params)
+{
+ int ret = 0;
+ u32 gicv_idx;
+ struct resource vcpu_res;
+ struct vgic_params *vgic = &vgic_v3_params;
+
+ vgic->maint_irq = irq_of_parse_and_map(vgic_node, 0);
+ if (!vgic->maint_irq) {
+ kvm_err("error getting vgic maintenance irq from DT\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ich_vtr_el2 = kvm_call_hyp(__vgic_v3_get_ich_vtr_el2);
+
+ /*
+ * The ListRegs field is 5 bits, but there is a architectural
+ * maximum of 16 list registers. Just ignore bit 4...
+ */
+ vgic->nr_lr = (ich_vtr_el2 & 0xf) + 1;
+
+ if (of_property_read_u32(vgic_node, "#redistributor-regions", &gicv_idx))
+ gicv_idx = 1;
+
+ gicv_idx += 3; /* Also skip GICD, GICC, GICH */
+ if (of_address_to_resource(vgic_node, gicv_idx, &vcpu_res)) {
+ kvm_err("Cannot obtain GICV region\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!PAGE_ALIGNED(vcpu_res.start)) {
+ kvm_err("GICV physical address 0x%llx not page aligned\n",
+ (unsigned long long)vcpu_res.start);
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+ kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+ (unsigned long long)resource_size(&vcpu_res),
+ PAGE_SIZE);
+ ret = -ENXIO;
+ goto out;
+ }
+
+ vgic->vcpu_base = vcpu_res.start;
+ vgic->vctrl_base = NULL;
+ vgic->type = VGIC_V3;
+
+ kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+ vcpu_res.start, vgic->maint_irq);
+
+ *ops = &vgic_v3_ops;
+ *params = vgic;
+
+out:
+ of_node_put(vgic_node);
+ return ret;
+}
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
new file mode 100644
index 0000000..8e1dc03
--- /dev/null
+++ b/virt/kvm/arm/vgic.c
@@ -0,0 +1,2464 @@
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/cpu.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/uaccess.h>
+
+#include <linux/irqchip/arm-gic.h>
+
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>
+
+/*
+ * How the whole thing works (courtesy of Christoffer Dall):
+ *
+ * - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
+ * something is pending on the CPU interface.
+ * - Interrupts that are pending on the distributor are stored on the
+ * vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
+ * ioctls and guest mmio ops, and other in-kernel peripherals such as the
+ * arch. timers).
+ * - Every time the bitmap changes, the irq_pending_on_cpu oracle is
+ * recalculated
+ * - To calculate the oracle, we need info for each cpu from
+ * compute_pending_for_cpu, which considers:
+ * - PPI: dist->irq_pending & dist->irq_enable
+ * - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
+ * - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
+ * registers, stored on each vcpu. We only keep one bit of
+ * information per interrupt, making sure that only one vcpu can
+ * accept the interrupt.
+ * - If any of the above state changes, we must recalculate the oracle.
+ * - The same is true when injecting an interrupt, except that we only
+ * consider a single interrupt at a time. The irq_spi_cpu array
+ * contains the target CPU for each SPI.
+ *
+ * The handling of level interrupts adds some extra complexity. We
+ * need to track when the interrupt has been EOIed, so we can sample
+ * the 'line' again. This is achieved as such:
+ *
+ * - When a level interrupt is moved onto a vcpu, the corresponding
+ * bit in irq_queued is set. As long as this bit is set, the line
+ * will be ignored for further interrupts. The interrupt is injected
+ * into the vcpu with the GICH_LR_EOI bit set (generate a
+ * maintenance interrupt on EOI).
+ * - When the interrupt is EOIed, the maintenance interrupt fires,
+ * and clears the corresponding bit in irq_queued. This allows the
+ * interrupt line to be sampled again.
+ * - Note that level-triggered interrupts can also be set to pending from
+ * writes to GICD_ISPENDRn and lowering the external input line does not
+ * cause the interrupt to become inactive in such a situation.
+ * Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
+ * inactive as long as the external input line is held high.
+ */
+
+#define VGIC_ADDR_UNDEF (-1)
+#define IS_VGIC_ADDR_UNDEF(_x) ((_x) == VGIC_ADDR_UNDEF)
+
+#define PRODUCT_ID_KVM 0x4b /* ASCII code K */
+#define IMPLEMENTER_ARM 0x43b
+#define GICC_ARCH_VERSION_V2 0x2
+
+#define ACCESS_READ_VALUE (1 << 0)
+#define ACCESS_READ_RAZ (0 << 0)
+#define ACCESS_READ_MASK(x) ((x) & (1 << 0))
+#define ACCESS_WRITE_IGNORED (0 << 1)
+#define ACCESS_WRITE_SETBIT (1 << 1)
+#define ACCESS_WRITE_CLEARBIT (2 << 1)
+#define ACCESS_WRITE_VALUE (3 << 1)
+#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
+
+static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
+static void vgic_update_state(struct kvm *kvm);
+static void vgic_kick_vcpus(struct kvm *kvm);
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi);
+static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
+static void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
+
+static const struct vgic_ops *vgic_ops;
+static const struct vgic_params *vgic;
+
+/*
+ * struct vgic_bitmap contains a bitmap made of unsigned longs, but
+ * extracts u32s out of them.
+ *
+ * This does not work on 64-bit BE systems, because the bitmap access
+ * will store two consecutive 32-bit words with the higher-addressed
+ * register's bits at the lower index and the lower-addressed register's
+ * bits at the higher index.
+ *
+ * Therefore, swizzle the register index when accessing the 32-bit word
+ * registers to access the right register's value.
+ */
+#if defined(CONFIG_CPU_BIG_ENDIAN) && BITS_PER_LONG == 64
+#define REG_OFFSET_SWIZZLE 1
+#else
+#define REG_OFFSET_SWIZZLE 0
+#endif
+
+static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
+{
+ int nr_longs;
+
+ nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+
+ b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
+ if (!b->private)
+ return -ENOMEM;
+
+ b->shared = b->private + nr_cpus;
+
+ return 0;
+}
+
+static void vgic_free_bitmap(struct vgic_bitmap *b)
+{
+ kfree(b->private);
+ b->private = NULL;
+ b->shared = NULL;
+}
+
+static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
+ int cpuid, u32 offset)
+{
+ offset >>= 2;
+ if (!offset)
+ return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
+ else
+ return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
+}
+
+static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
+ int cpuid, int irq)
+{
+ if (irq < VGIC_NR_PRIVATE_IRQS)
+ return test_bit(irq, x->private + cpuid);
+
+ return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
+}
+
+static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
+ int irq, int val)
+{
+ unsigned long *reg;
+
+ if (irq < VGIC_NR_PRIVATE_IRQS) {
+ reg = x->private + cpuid;
+ } else {
+ reg = x->shared;
+ irq -= VGIC_NR_PRIVATE_IRQS;
+ }
+
+ if (val)
+ set_bit(irq, reg);
+ else
+ clear_bit(irq, reg);
+}
+
+static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
+{
+ return x->private + cpuid;
+}
+
+static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
+{
+ return x->shared;
+}
+
+static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
+{
+ int size;
+
+ size = nr_cpus * VGIC_NR_PRIVATE_IRQS;
+ size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
+
+ x->private = kzalloc(size, GFP_KERNEL);
+ if (!x->private)
+ return -ENOMEM;
+
+ x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
+ return 0;
+}
+
+static void vgic_free_bytemap(struct vgic_bytemap *b)
+{
+ kfree(b->private);
+ b->private = NULL;
+ b->shared = NULL;
+}
+
+static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
+{
+ u32 *reg;
+
+ if (offset < VGIC_NR_PRIVATE_IRQS) {
+ reg = x->private;
+ offset += cpuid * VGIC_NR_PRIVATE_IRQS;
+ } else {
+ reg = x->shared;
+ offset -= VGIC_NR_PRIVATE_IRQS;
+ }
+
+ return reg + (offset / sizeof(u32));
+}
+
+#define VGIC_CFG_LEVEL 0
+#define VGIC_CFG_EDGE 1
+
+static bool vgic_irq_is_edge(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int irq_val;
+
+ irq_val = vgic_bitmap_get_irq_val(&dist->irq_cfg, vcpu->vcpu_id, irq);
+ return irq_val == VGIC_CFG_EDGE;
+}
+
+static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
+}
+
+static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
+}
+
+static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
+}
+
+static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
+{
+ if (irq < VGIC_NR_PRIVATE_IRQS)
+ set_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
+ else
+ set_bit(irq - VGIC_NR_PRIVATE_IRQS,
+ vcpu->arch.vgic_cpu.pending_shared);
+}
+
+static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
+{
+ if (irq < VGIC_NR_PRIVATE_IRQS)
+ clear_bit(irq, vcpu->arch.vgic_cpu.pending_percpu);
+ else
+ clear_bit(irq - VGIC_NR_PRIVATE_IRQS,
+ vcpu->arch.vgic_cpu.pending_shared);
+}
+
+static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
+{
+ return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
+}
+
+static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
+{
+ return le32_to_cpu(*((u32 *)mmio->data)) & mask;
+}
+
+static void mmio_data_write(struct kvm_exit_mmio *mmio, u32 mask, u32 value)
+{
+ *((u32 *)mmio->data) = cpu_to_le32(value) & mask;
+}
+
+/**
+ * vgic_reg_access - access vgic register
+ * @mmio: pointer to the data describing the mmio access
+ * @reg: pointer to the virtual backing of vgic distributor data
+ * @offset: least significant 2 bits used for word offset
+ * @mode: ACCESS_ mode (see defines above)
+ *
+ * Helper to make vgic register access easier using one of the access
+ * modes defined for vgic register access
+ * (read,raz,write-ignored,setbit,clearbit,write)
+ */
+static void vgic_reg_access(struct kvm_exit_mmio *mmio, u32 *reg,
+ phys_addr_t offset, int mode)
+{
+ int word_offset = (offset & 3) * 8;
+ u32 mask = (1UL << (mmio->len * 8)) - 1;
+ u32 regval;
+
+ /*
+ * Any alignment fault should have been delivered to the guest
+ * directly (ARM ARM B3.12.7 "Prioritization of aborts").
+ */
+
+ if (reg) {
+ regval = *reg;
+ } else {
+ BUG_ON(mode != (ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED));
+ regval = 0;
+ }
+
+ if (mmio->is_write) {
+ u32 data = mmio_data_read(mmio, mask) << word_offset;
+ switch (ACCESS_WRITE_MASK(mode)) {
+ case ACCESS_WRITE_IGNORED:
+ return;
+
+ case ACCESS_WRITE_SETBIT:
+ regval |= data;
+ break;
+
+ case ACCESS_WRITE_CLEARBIT:
+ regval &= ~data;
+ break;
+
+ case ACCESS_WRITE_VALUE:
+ regval = (regval & ~(mask << word_offset)) | data;
+ break;
+ }
+ *reg = regval;
+ } else {
+ switch (ACCESS_READ_MASK(mode)) {
+ case ACCESS_READ_RAZ:
+ regval = 0;
+ /* fall through */
+
+ case ACCESS_READ_VALUE:
+ mmio_data_write(mmio, mask, regval >> word_offset);
+ }
+ }
+}
+
+static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ u32 reg;
+ u32 word_offset = offset & 3;
+
+ switch (offset & ~3) {
+ case 0: /* GICD_CTLR */
+ reg = vcpu->kvm->arch.vgic.enabled;
+ vgic_reg_access(mmio, ®, word_offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
+ if (mmio->is_write) {
+ vcpu->kvm->arch.vgic.enabled = reg & 1;
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+ break;
+
+ case 4: /* GICD_TYPER */
+ reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
+ reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
+ vgic_reg_access(mmio, ®, word_offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
+ break;
+
+ case 8: /* GICD_IIDR */
+ reg = (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+ vgic_reg_access(mmio, ®, word_offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
+ break;
+ }
+
+ return false;
+}
+
+static bool handle_mmio_raz_wi(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ vgic_reg_access(mmio, NULL, offset,
+ ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+ return false;
+}
+
+static bool handle_mmio_set_enable_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+ if (mmio->is_write) {
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+static bool handle_mmio_clear_enable_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_enabled,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+ if (mmio->is_write) {
+ if (offset < 4) /* Force SGI enabled */
+ *reg |= 0xffff;
+ vgic_retire_disabled_irqs(vcpu);
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 *reg, orig;
+ u32 level_mask;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset);
+ level_mask = (~(*reg));
+
+ /* Mark both level and edge triggered irqs as pending */
+ reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+ orig = *reg;
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+
+ if (mmio->is_write) {
+ /* Set the soft-pending flag only for level-triggered irqs */
+ reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+ *reg &= level_mask;
+
+ /* Ignore writes to SGIs */
+ if (offset < 2) {
+ *reg &= ~0xffff;
+ *reg |= orig & 0xffff;
+ }
+
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 *level_active;
+ u32 *reg, orig;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+ orig = *reg;
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+ if (mmio->is_write) {
+ /* Re-set level triggered level-active interrupts */
+ level_active = vgic_bitmap_get_reg(&dist->irq_level,
+ vcpu->vcpu_id, offset);
+ reg = vgic_bitmap_get_reg(&dist->irq_pending,
+ vcpu->vcpu_id, offset);
+ *reg |= *level_active;
+
+ /* Ignore writes to SGIs */
+ if (offset < 2) {
+ *reg &= ~0xffff;
+ *reg |= orig & 0xffff;
+ }
+
+ /* Clear soft-pending flags */
+ reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+static bool handle_mmio_priority_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 *reg = vgic_bytemap_get_reg(&vcpu->kvm->arch.vgic.irq_priority,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
+ return false;
+}
+
+#define GICD_ITARGETSR_SIZE 32
+#define GICD_CPUTARGETS_BITS 8
+#define GICD_IRQS_PER_ITARGETSR (GICD_ITARGETSR_SIZE / GICD_CPUTARGETS_BITS)
+static u32 vgic_get_target_reg(struct kvm *kvm, int irq)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int i;
+ u32 val = 0;
+
+ irq -= VGIC_NR_PRIVATE_IRQS;
+
+ for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++)
+ val |= 1 << (dist->irq_spi_cpu[irq + i] + i * 8);
+
+ return val;
+}
+
+static void vgic_set_target_reg(struct kvm *kvm, u32 val, int irq)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int i, c;
+ unsigned long *bmap;
+ u32 target;
+
+ irq -= VGIC_NR_PRIVATE_IRQS;
+
+ /*
+ * Pick the LSB in each byte. This ensures we target exactly
+ * one vcpu per IRQ. If the byte is null, assume we target
+ * CPU0.
+ */
+ for (i = 0; i < GICD_IRQS_PER_ITARGETSR; i++) {
+ int shift = i * GICD_CPUTARGETS_BITS;
+ target = ffs((val >> shift) & 0xffU);
+ target = target ? (target - 1) : 0;
+ dist->irq_spi_cpu[irq + i] = target;
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ bmap = vgic_bitmap_get_shared_map(&dist->irq_spi_target[c]);
+ if (c == target)
+ set_bit(irq + i, bmap);
+ else
+ clear_bit(irq + i, bmap);
+ }
+ }
+}
+
+static bool handle_mmio_target_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 reg;
+
+ /* We treat the banked interrupts targets as read-only */
+ if (offset < 32) {
+ u32 roreg = 1 << vcpu->vcpu_id;
+ roreg |= roreg << 8;
+ roreg |= roreg << 16;
+
+ vgic_reg_access(mmio, &roreg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
+ return false;
+ }
+
+ reg = vgic_get_target_reg(vcpu->kvm, offset & ~3U);
+ vgic_reg_access(mmio, ®, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
+ if (mmio->is_write) {
+ vgic_set_target_reg(vcpu->kvm, reg, offset & ~3U);
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+static u32 vgic_cfg_expand(u16 val)
+{
+ u32 res = 0;
+ int i;
+
+ /*
+ * Turn a 16bit value like abcd...mnop into a 32bit word
+ * a0b0c0d0...m0n0o0p0, which is what the HW cfg register is.
+ */
+ for (i = 0; i < 16; i++)
+ res |= ((val >> i) & VGIC_CFG_EDGE) << (2 * i + 1);
+
+ return res;
+}
+
+static u16 vgic_cfg_compress(u32 val)
+{
+ u16 res = 0;
+ int i;
+
+ /*
+ * Turn a 32bit word a0b0c0d0...m0n0o0p0 into 16bit value like
+ * abcd...mnop which is what we really care about.
+ */
+ for (i = 0; i < 16; i++)
+ res |= ((val >> (i * 2 + 1)) & VGIC_CFG_EDGE) << i;
+
+ return res;
+}
+
+/*
+ * The distributor uses 2 bits per IRQ for the CFG register, but the
+ * LSB is always 0. As such, we only keep the upper bit, and use the
+ * two above functions to compress/expand the bits
+ */
+static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ u32 val;
+ u32 *reg;
+
+ reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
+ vcpu->vcpu_id, offset >> 1);
+
+ if (offset & 4)
+ val = *reg >> 16;
+ else
+ val = *reg & 0xffff;
+
+ val = vgic_cfg_expand(val);
+ vgic_reg_access(mmio, &val, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
+ if (mmio->is_write) {
+ if (offset < 8) {
+ *reg = ~0U; /* Force PPIs/SGIs to 1 */
+ return false;
+ }
+
+ val = vgic_cfg_compress(val);
+ if (offset & 4) {
+ *reg &= 0xffff;
+ *reg |= val << 16;
+ } else {
+ *reg &= 0xffff << 16;
+ *reg |= val;
+ }
+ }
+
+ return false;
+}
+
+static bool handle_mmio_sgi_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ u32 reg;
+ vgic_reg_access(mmio, ®, offset,
+ ACCESS_READ_RAZ | ACCESS_WRITE_VALUE);
+ if (mmio->is_write) {
+ vgic_dispatch_sgi(vcpu, reg);
+ vgic_update_state(vcpu->kvm);
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * vgic_unqueue_irqs - move pending IRQs from LRs to the distributor
+ * @vgic_cpu: Pointer to the vgic_cpu struct holding the LRs
+ *
+ * Move any pending IRQs that have already been assigned to LRs back to the
+ * emulated distributor state so that the complete emulated state can be read
+ * from the main emulation structures without investigating the LRs.
+ *
+ * Note that IRQs in the active state in the LRs get their pending state moved
+ * to the distributor but the active state stays in the LRs, because we don't
+ * track the active state on the distributor side.
+ */
+static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ int vcpu_id = vcpu->vcpu_id;
+ int i;
+
+ for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
+ struct vgic_lr lr = vgic_get_lr(vcpu, i);
+
+ /*
+ * There are three options for the state bits:
+ *
+ * 01: pending
+ * 10: active
+ * 11: pending and active
+ *
+ * If the LR holds only an active interrupt (not pending) then
+ * just leave it alone.
+ */
+ if ((lr.state & LR_STATE_MASK) == LR_STATE_ACTIVE)
+ continue;
+
+ /*
+ * Reestablish the pending state on the distributor and the
+ * CPU interface. It may have already been pending, but that
+ * is fine, then we are only setting a few bits that were
+ * already set.
+ */
+ vgic_dist_irq_set_pending(vcpu, lr.irq);
+ if (lr.irq < VGIC_NR_SGIS)
+ *vgic_get_sgi_sources(dist, vcpu_id, lr.irq) |= 1 << lr.source;
+ lr.state &= ~LR_STATE_PENDING;
+ vgic_set_lr(vcpu, i, lr);
+
+ /*
+ * If there's no state left on the LR (it could still be
+ * active), then the LR does not hold any useful info and can
+ * be marked as free for other use.
+ */
+ if (!(lr.state & LR_STATE_MASK)) {
+ vgic_retire_lr(i, lr.irq, vcpu);
+ vgic_irq_clear_queued(vcpu, lr.irq);
+ }
+
+ /* Finally update the VGIC state. */
+ vgic_update_state(vcpu->kvm);
+ }
+}
+
+/* Handle reads of GICD_CPENDSGIRn and GICD_SPENDSGIRn */
+static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int sgi;
+ int min_sgi = (offset & ~0x3);
+ int max_sgi = min_sgi + 3;
+ int vcpu_id = vcpu->vcpu_id;
+ u32 reg = 0;
+
+ /* Copy source SGIs from distributor side */
+ for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
+ int shift = 8 * (sgi - min_sgi);
+ reg |= ((u32)*vgic_get_sgi_sources(dist, vcpu_id, sgi)) << shift;
+ }
+
+ mmio_data_write(mmio, ~0, reg);
+ return false;
+}
+
+static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset, bool set)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int sgi;
+ int min_sgi = (offset & ~0x3);
+ int max_sgi = min_sgi + 3;
+ int vcpu_id = vcpu->vcpu_id;
+ u32 reg;
+ bool updated = false;
+
+ reg = mmio_data_read(mmio, ~0);
+
+ /* Clear pending SGIs on the distributor */
+ for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
+ u8 mask = reg >> (8 * (sgi - min_sgi));
+ u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
+ if (set) {
+ if ((*src & mask) != mask)
+ updated = true;
+ *src |= mask;
+ } else {
+ if (*src & mask)
+ updated = true;
+ *src &= ~mask;
+ }
+ }
+
+ if (updated)
+ vgic_update_state(vcpu->kvm);
+
+ return updated;
+}
+
+static bool handle_mmio_sgi_set(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ if (!mmio->is_write)
+ return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
+ else
+ return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, true);
+}
+
+static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ if (!mmio->is_write)
+ return read_set_clear_sgi_pend_reg(vcpu, mmio, offset);
+ else
+ return write_set_clear_sgi_pend_reg(vcpu, mmio, offset, false);
+}
+
+/*
+ * I would have liked to use the kvm_bus_io_*() API instead, but it
+ * cannot cope with banked registers (only the VM pointer is passed
+ * around, and we need the vcpu). One of these days, someone please
+ * fix it!
+ */
+struct mmio_range {
+ phys_addr_t base;
+ unsigned long len;
+ int bits_per_irq;
+ bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
+ phys_addr_t offset);
+};
+
+static const struct mmio_range vgic_dist_ranges[] = {
+ {
+ .base = GIC_DIST_CTRL,
+ .len = 12,
+ .bits_per_irq = 0,
+ .handle_mmio = handle_mmio_misc,
+ },
+ {
+ .base = GIC_DIST_IGROUP,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_raz_wi,
+ },
+ {
+ .base = GIC_DIST_ENABLE_SET,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_set_enable_reg,
+ },
+ {
+ .base = GIC_DIST_ENABLE_CLEAR,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_clear_enable_reg,
+ },
+ {
+ .base = GIC_DIST_PENDING_SET,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_set_pending_reg,
+ },
+ {
+ .base = GIC_DIST_PENDING_CLEAR,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_clear_pending_reg,
+ },
+ {
+ .base = GIC_DIST_ACTIVE_SET,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_raz_wi,
+ },
+ {
+ .base = GIC_DIST_ACTIVE_CLEAR,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
+ .handle_mmio = handle_mmio_raz_wi,
+ },
+ {
+ .base = GIC_DIST_PRI,
+ .len = VGIC_MAX_IRQS,
+ .bits_per_irq = 8,
+ .handle_mmio = handle_mmio_priority_reg,
+ },
+ {
+ .base = GIC_DIST_TARGET,
+ .len = VGIC_MAX_IRQS,
+ .bits_per_irq = 8,
+ .handle_mmio = handle_mmio_target_reg,
+ },
+ {
+ .base = GIC_DIST_CONFIG,
+ .len = VGIC_MAX_IRQS / 4,
+ .bits_per_irq = 2,
+ .handle_mmio = handle_mmio_cfg_reg,
+ },
+ {
+ .base = GIC_DIST_SOFTINT,
+ .len = 4,
+ .handle_mmio = handle_mmio_sgi_reg,
+ },
+ {
+ .base = GIC_DIST_SGI_PENDING_CLEAR,
+ .len = VGIC_NR_SGIS,
+ .handle_mmio = handle_mmio_sgi_clear,
+ },
+ {
+ .base = GIC_DIST_SGI_PENDING_SET,
+ .len = VGIC_NR_SGIS,
+ .handle_mmio = handle_mmio_sgi_set,
+ },
+ {}
+};
+
+static const
+struct mmio_range *find_matching_range(const struct mmio_range *ranges,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ const struct mmio_range *r = ranges;
+
+ while (r->len) {
+ if (offset >= r->base &&
+ (offset + mmio->len) <= (r->base + r->len))
+ return r;
+ r++;
+ }
+
+ return NULL;
+}
+
+static bool vgic_validate_access(const struct vgic_dist *dist,
+ const struct mmio_range *range,
+ unsigned long offset)
+{
+ int irq;
+
+ if (!range->bits_per_irq)
+ return true; /* Not an irq-based access */
+
+ irq = offset * 8 / range->bits_per_irq;
+ if (irq >= dist->nr_irqs)
+ return false;
+
+ return true;
+}
+
+/**
+ * vgic_handle_mmio - handle an in-kernel MMIO access
+ * @vcpu: pointer to the vcpu performing the access
+ * @run: pointer to the kvm_run structure
+ * @mmio: pointer to the data describing the access
+ *
+ * returns true if the MMIO access has been performed in kernel space,
+ * and false if it needs to be emulated in user space.
+ */
+bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
+ struct kvm_exit_mmio *mmio)
+{
+ const struct mmio_range *range;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ unsigned long base = dist->vgic_dist_base;
+ bool updated_state;
+ unsigned long offset;
+
+ if (!irqchip_in_kernel(vcpu->kvm) ||
+ mmio->phys_addr < base ||
+ (mmio->phys_addr + mmio->len) > (base + KVM_VGIC_V2_DIST_SIZE))
+ return false;
+
+ /* We don't support ldrd / strd or ldm / stm to the emulated vgic */
+ if (mmio->len > 4) {
+ kvm_inject_dabt(vcpu, mmio->phys_addr);
+ return true;
+ }
+
+ offset = mmio->phys_addr - base;
+ range = find_matching_range(vgic_dist_ranges, mmio, offset);
+ if (unlikely(!range || !range->handle_mmio)) {
+ pr_warn("Unhandled access %d %08llx %d\n",
+ mmio->is_write, mmio->phys_addr, mmio->len);
+ return false;
+ }
+
+ spin_lock(&vcpu->kvm->arch.vgic.lock);
+ offset = mmio->phys_addr - range->base - base;
+ if (vgic_validate_access(dist, range, offset)) {
+ updated_state = range->handle_mmio(vcpu, mmio, offset);
+ } else {
+ vgic_reg_access(mmio, NULL, offset,
+ ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+ updated_state = false;
+ }
+ spin_unlock(&vcpu->kvm->arch.vgic.lock);
+ kvm_prepare_mmio(run, mmio);
+ kvm_handle_mmio_return(vcpu, run);
+
+ if (updated_state)
+ vgic_kick_vcpus(vcpu->kvm);
+
+ return true;
+}
+
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
+{
+ return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
+}
+
+static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int nrcpus = atomic_read(&kvm->online_vcpus);
+ u8 target_cpus;
+ int sgi, mode, c, vcpu_id;
+
+ vcpu_id = vcpu->vcpu_id;
+
+ sgi = reg & 0xf;
+ target_cpus = (reg >> 16) & 0xff;
+ mode = (reg >> 24) & 3;
+
+ switch (mode) {
+ case 0:
+ if (!target_cpus)
+ return;
+ break;
+
+ case 1:
+ target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
+ break;
+
+ case 2:
+ target_cpus = 1 << vcpu_id;
+ break;
+ }
+
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ if (target_cpus & 1) {
+ /* Flag the SGI as pending */
+ vgic_dist_irq_set_pending(vcpu, sgi);
+ *vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
+ kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
+ }
+
+ target_cpus >>= 1;
+ }
+}
+
+static int vgic_nr_shared_irqs(struct vgic_dist *dist)
+{
+ return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
+}
+
+static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
+ unsigned long pending_private, pending_shared;
+ int nr_shared = vgic_nr_shared_irqs(dist);
+ int vcpu_id;
+
+ vcpu_id = vcpu->vcpu_id;
+ pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
+ pend_shared = vcpu->arch.vgic_cpu.pending_shared;
+
+ pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
+ enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
+ bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
+
+ pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
+ enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
+ bitmap_and(pend_shared, pending, enabled, nr_shared);
+ bitmap_and(pend_shared, pend_shared,
+ vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
+ nr_shared);
+
+ pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
+ pending_shared = find_first_bit(pend_shared, nr_shared);
+ return (pending_private < VGIC_NR_PRIVATE_IRQS ||
+ pending_shared < vgic_nr_shared_irqs(dist));
+}
+
+/*
+ * Update the interrupt state and determine which CPUs have pending
+ * interrupts. Must be called with distributor lock held.
+ */
+static void vgic_update_state(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int c;
+
+ if (!dist->enabled) {
+ set_bit(0, dist->irq_pending_on_cpu);
+ return;
+ }
+
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ if (compute_pending_for_cpu(vcpu)) {
+ pr_debug("CPU%d has pending interrupts\n", c);
+ set_bit(c, dist->irq_pending_on_cpu);
+ }
+ }
+}
+
+static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr)
+{
+ return vgic_ops->get_lr(vcpu, lr);
+}
+
+static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr vlr)
+{
+ vgic_ops->set_lr(vcpu, lr, vlr);
+}
+
+static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
+ struct vgic_lr vlr)
+{
+ vgic_ops->sync_lr_elrsr(vcpu, lr, vlr);
+}
+
+static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_elrsr(vcpu);
+}
+
+static inline u64 vgic_get_eisr(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_eisr(vcpu);
+}
+
+static inline u32 vgic_get_interrupt_status(struct kvm_vcpu *vcpu)
+{
+ return vgic_ops->get_interrupt_status(vcpu);
+}
+
+static inline void vgic_enable_underflow(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->enable_underflow(vcpu);
+}
+
+static inline void vgic_disable_underflow(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->disable_underflow(vcpu);
+}
+
+static inline void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ vgic_ops->get_vmcr(vcpu, vmcr);
+}
+
+static void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
+{
+ vgic_ops->set_vmcr(vcpu, vmcr);
+}
+
+static inline void vgic_enable(struct kvm_vcpu *vcpu)
+{
+ vgic_ops->enable(vcpu);
+}
+
+static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
+
+ vlr.state = 0;
+ vgic_set_lr(vcpu, lr_nr, vlr);
+ clear_bit(lr_nr, vgic_cpu->lr_used);
+ vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
+}
+
+/*
+ * An interrupt may have been disabled after being made pending on the
+ * CPU interface (the classic case is a timer running while we're
+ * rebooting the guest - the interrupt would kick as soon as the CPU
+ * interface gets enabled, with deadly consequences).
+ *
+ * The solution is to examine already active LRs, and check the
+ * interrupt is still enabled. If not, just retire it.
+ */
+static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ int lr;
+
+ for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) {
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+
+ if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
+ vgic_retire_lr(lr, vlr.irq, vcpu);
+ if (vgic_irq_is_queued(vcpu, vlr.irq))
+ vgic_irq_clear_queued(vcpu, vlr.irq);
+ }
+ }
+}
+
+/*
+ * Queue an interrupt to a CPU virtual interface. Return true on success,
+ * or false if it wasn't possible to queue it.
+ */
+static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ struct vgic_lr vlr;
+ int lr;
+
+ /* Sanitize the input... */
+ BUG_ON(sgi_source_id & ~7);
+ BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
+ BUG_ON(irq >= dist->nr_irqs);
+
+ kvm_debug("Queue IRQ%d\n", irq);
+
+ lr = vgic_cpu->vgic_irq_lr_map[irq];
+
+ /* Do we have an active interrupt for the same CPUID? */
+ if (lr != LR_EMPTY) {
+ vlr = vgic_get_lr(vcpu, lr);
+ if (vlr.source == sgi_source_id) {
+ kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
+ BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
+ vlr.state |= LR_STATE_PENDING;
+ vgic_set_lr(vcpu, lr, vlr);
+ return true;
+ }
+ }
+
+ /* Try to use another LR for this interrupt */
+ lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
+ vgic->nr_lr);
+ if (lr >= vgic->nr_lr)
+ return false;
+
+ kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
+ vgic_cpu->vgic_irq_lr_map[irq] = lr;
+ set_bit(lr, vgic_cpu->lr_used);
+
+ vlr.irq = irq;
+ vlr.source = sgi_source_id;
+ vlr.state = LR_STATE_PENDING;
+ if (!vgic_irq_is_edge(vcpu, irq))
+ vlr.state |= LR_EOI_INT;
+
+ vgic_set_lr(vcpu, lr, vlr);
+
+ return true;
+}
+
+static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ unsigned long sources;
+ int vcpu_id = vcpu->vcpu_id;
+ int c;
+
+ sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
+
+ for_each_set_bit(c, &sources, dist->nr_cpus) {
+ if (vgic_queue_irq(vcpu, c, irq))
+ clear_bit(c, &sources);
+ }
+
+ *vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
+
+ /*
+ * If the sources bitmap has been cleared it means that we
+ * could queue all the SGIs onto link registers (see the
+ * clear_bit above), and therefore we are done with them in
+ * our emulated gic and can get rid of them.
+ */
+ if (!sources) {
+ vgic_dist_irq_clear_pending(vcpu, irq);
+ vgic_cpu_irq_clear(vcpu, irq);
+ return true;
+ }
+
+ return false;
+}
+
+static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
+{
+ if (!vgic_can_sample_irq(vcpu, irq))
+ return true; /* level interrupt, already queued */
+
+ if (vgic_queue_irq(vcpu, 0, irq)) {
+ if (vgic_irq_is_edge(vcpu, irq)) {
+ vgic_dist_irq_clear_pending(vcpu, irq);
+ vgic_cpu_irq_clear(vcpu, irq);
+ } else {
+ vgic_irq_set_queued(vcpu, irq);
+ }
+
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Fill the list registers with pending interrupts before running the
+ * guest.
+ */
+static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int i, vcpu_id;
+ int overflow = 0;
+
+ vcpu_id = vcpu->vcpu_id;
+
+ /*
+ * We may not have any pending interrupt, or the interrupts
+ * may have been serviced from another vcpu. In all cases,
+ * move along.
+ */
+ if (!kvm_vgic_vcpu_pending_irq(vcpu)) {
+ pr_debug("CPU%d has no pending interrupt\n", vcpu_id);
+ goto epilog;
+ }
+
+ /* SGIs */
+ for_each_set_bit(i, vgic_cpu->pending_percpu, VGIC_NR_SGIS) {
+ if (!vgic_queue_sgi(vcpu, i))
+ overflow = 1;
+ }
+
+ /* PPIs */
+ for_each_set_bit_from(i, vgic_cpu->pending_percpu, VGIC_NR_PRIVATE_IRQS) {
+ if (!vgic_queue_hwirq(vcpu, i))
+ overflow = 1;
+ }
+
+ /* SPIs */
+ for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
+ if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
+ overflow = 1;
+ }
+
+epilog:
+ if (overflow) {
+ vgic_enable_underflow(vcpu);
+ } else {
+ vgic_disable_underflow(vcpu);
+ /*
+ * We're about to run this VCPU, and we've consumed
+ * everything the distributor had in store for
+ * us. Claim we don't have anything pending. We'll
+ * adjust that if needed while exiting.
+ */
+ clear_bit(vcpu_id, dist->irq_pending_on_cpu);
+ }
+}
+
+static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
+{
+ u32 status = vgic_get_interrupt_status(vcpu);
+ bool level_pending = false;
+
+ kvm_debug("STATUS = %08x\n", status);
+
+ if (status & INT_STATUS_EOI) {
+ /*
+ * Some level interrupts have been EOIed. Clear their
+ * active bit.
+ */
+ u64 eisr = vgic_get_eisr(vcpu);
+ unsigned long *eisr_ptr = (unsigned long *)&eisr;
+ int lr;
+
+ for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+ WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
+
+ vgic_irq_clear_queued(vcpu, vlr.irq);
+ WARN_ON(vlr.state & LR_STATE_MASK);
+ vlr.state = 0;
+ vgic_set_lr(vcpu, lr, vlr);
+
+ /*
+ * If the IRQ was EOIed it was also ACKed and we we
+ * therefore assume we can clear the soft pending
+ * state (should it had been set) for this interrupt.
+ *
+ * Note: if the IRQ soft pending state was set after
+ * the IRQ was acked, it actually shouldn't be
+ * cleared, but we have no way of knowing that unless
+ * we start trapping ACKs when the soft-pending state
+ * is set.
+ */
+ vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
+
+ /* Any additional pending interrupt? */
+ if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
+ vgic_cpu_irq_set(vcpu, vlr.irq);
+ level_pending = true;
+ } else {
+ vgic_dist_irq_clear_pending(vcpu, vlr.irq);
+ vgic_cpu_irq_clear(vcpu, vlr.irq);
+ }
+
+ /*
+ * Despite being EOIed, the LR may not have
+ * been marked as empty.
+ */
+ vgic_sync_lr_elrsr(vcpu, lr, vlr);
+ }
+ }
+
+ if (status & INT_STATUS_UNDERFLOW)
+ vgic_disable_underflow(vcpu);
+
+ return level_pending;
+}
+
+/*
+ * Sync back the VGIC state after a guest run. The distributor lock is
+ * needed so we don't get preempted in the middle of the state processing.
+ */
+static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ u64 elrsr;
+ unsigned long *elrsr_ptr;
+ int lr, pending;
+ bool level_pending;
+
+ level_pending = vgic_process_maintenance(vcpu);
+ elrsr = vgic_get_elrsr(vcpu);
+ elrsr_ptr = (unsigned long *)&elrsr;
+
+ /* Clear mappings for empty LRs */
+ for_each_set_bit(lr, elrsr_ptr, vgic->nr_lr) {
+ struct vgic_lr vlr;
+
+ if (!test_and_clear_bit(lr, vgic_cpu->lr_used))
+ continue;
+
+ vlr = vgic_get_lr(vcpu, lr);
+
+ BUG_ON(vlr.irq >= dist->nr_irqs);
+ vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
+ }
+
+ /* Check if we still have something up our sleeve... */
+ pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
+ if (level_pending || pending < vgic->nr_lr)
+ set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
+}
+
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return;
+
+ spin_lock(&dist->lock);
+ __kvm_vgic_flush_hwstate(vcpu);
+ spin_unlock(&dist->lock);
+}
+
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return;
+
+ spin_lock(&dist->lock);
+ __kvm_vgic_sync_hwstate(vcpu);
+ spin_unlock(&dist->lock);
+}
+
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 0;
+
+ return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
+}
+
+static void vgic_kick_vcpus(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int c;
+
+ /*
+ * We've injected an interrupt, time to find out who deserves
+ * a good kick...
+ */
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ if (kvm_vgic_vcpu_pending_irq(vcpu))
+ kvm_vcpu_kick(vcpu);
+ }
+}
+
+static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
+{
+ int edge_triggered = vgic_irq_is_edge(vcpu, irq);
+
+ /*
+ * Only inject an interrupt if:
+ * - edge triggered and we have a rising edge
+ * - level triggered and we change level
+ */
+ if (edge_triggered) {
+ int state = vgic_dist_irq_is_pending(vcpu, irq);
+ return level > state;
+ } else {
+ int state = vgic_dist_irq_get_level(vcpu, irq);
+ return level != state;
+ }
+}
+
+static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
+ unsigned int irq_num, bool level)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int edge_triggered, level_triggered;
+ int enabled;
+ bool ret = true;
+
+ spin_lock(&dist->lock);
+
+ vcpu = kvm_get_vcpu(kvm, cpuid);
+ edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
+ level_triggered = !edge_triggered;
+
+ if (!vgic_validate_injection(vcpu, irq_num, level)) {
+ ret = false;
+ goto out;
+ }
+
+ if (irq_num >= VGIC_NR_PRIVATE_IRQS) {
+ cpuid = dist->irq_spi_cpu[irq_num - VGIC_NR_PRIVATE_IRQS];
+ vcpu = kvm_get_vcpu(kvm, cpuid);
+ }
+
+ kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
+
+ if (level) {
+ if (level_triggered)
+ vgic_dist_irq_set_level(vcpu, irq_num);
+ vgic_dist_irq_set_pending(vcpu, irq_num);
+ } else {
+ if (level_triggered) {
+ vgic_dist_irq_clear_level(vcpu, irq_num);
+ if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
+ vgic_dist_irq_clear_pending(vcpu, irq_num);
+ } else {
+ vgic_dist_irq_clear_pending(vcpu, irq_num);
+ }
+ }
+
+ enabled = vgic_irq_is_enabled(vcpu, irq_num);
+
+ if (!enabled) {
+ ret = false;
+ goto out;
+ }
+
+ if (!vgic_can_sample_irq(vcpu, irq_num)) {
+ /*
+ * Level interrupt in progress, will be picked up
+ * when EOId.
+ */
+ ret = false;
+ goto out;
+ }
+
+ if (level) {
+ vgic_cpu_irq_set(vcpu, irq_num);
+ set_bit(cpuid, dist->irq_pending_on_cpu);
+ }
+
+out:
+ spin_unlock(&dist->lock);
+
+ return ret;
+}
+
+/**
+ * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
+ * @kvm: The VM structure pointer
+ * @cpuid: The CPU for PPIs
+ * @irq_num: The IRQ number that is assigned to the device
+ * @level: Edge-triggered: true: to trigger the interrupt
+ * false: to ignore the call
+ * Level-sensitive true: activates an interrupt
+ * false: deactivates an interrupt
+ *
+ * The GIC is not concerned with devices being active-LOW or active-HIGH for
+ * level-sensitive interrupts. You can think of the level parameter as 1
+ * being HIGH and 0 being LOW and all devices being active-HIGH.
+ */
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
+ bool level)
+{
+ if (likely(vgic_initialized(kvm)) &&
+ vgic_update_irq_pending(kvm, cpuid, irq_num, level))
+ vgic_kick_vcpus(kvm);
+
+ return 0;
+}
+
+static irqreturn_t vgic_maintenance_handler(int irq, void *data)
+{
+ /*
+ * We cannot rely on the vgic maintenance interrupt to be
+ * delivered synchronously. This means we can only use it to
+ * exit the VM, and we perform the handling of EOIed
+ * interrupts on the exit path (see vgic_process_maintenance).
+ */
+ return IRQ_HANDLED;
+}
+
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ kfree(vgic_cpu->pending_shared);
+ kfree(vgic_cpu->vgic_irq_lr_map);
+ vgic_cpu->pending_shared = NULL;
+ vgic_cpu->vgic_irq_lr_map = NULL;
+}
+
+static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+ vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
+ vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+
+ if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
+ kvm_vgic_vcpu_destroy(vcpu);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+/**
+ * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
+ * @vcpu: pointer to the vcpu struct
+ *
+ * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
+ * this vcpu and enable the VGIC for this VCPU
+ */
+static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int i;
+
+ for (i = 0; i < dist->nr_irqs; i++) {
+ if (i < VGIC_NR_PPIS)
+ vgic_bitmap_set_irq_val(&dist->irq_enabled,
+ vcpu->vcpu_id, i, 1);
+ if (i < VGIC_NR_PRIVATE_IRQS)
+ vgic_bitmap_set_irq_val(&dist->irq_cfg,
+ vcpu->vcpu_id, i, VGIC_CFG_EDGE);
+
+ vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
+ }
+
+ /*
+ * Store the number of LRs per vcpu, so we don't have to go
+ * all the way to the distributor structure to find out. Only
+ * assembly code should use this one.
+ */
+ vgic_cpu->nr_lr = vgic->nr_lr;
+
+ vgic_enable(vcpu);
+}
+
+void kvm_vgic_destroy(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_destroy(vcpu);
+
+ vgic_free_bitmap(&dist->irq_enabled);
+ vgic_free_bitmap(&dist->irq_level);
+ vgic_free_bitmap(&dist->irq_pending);
+ vgic_free_bitmap(&dist->irq_soft_pend);
+ vgic_free_bitmap(&dist->irq_queued);
+ vgic_free_bitmap(&dist->irq_cfg);
+ vgic_free_bytemap(&dist->irq_priority);
+ if (dist->irq_spi_target) {
+ for (i = 0; i < dist->nr_cpus; i++)
+ vgic_free_bitmap(&dist->irq_spi_target[i]);
+ }
+ kfree(dist->irq_sgi_sources);
+ kfree(dist->irq_spi_cpu);
+ kfree(dist->irq_spi_target);
+ kfree(dist->irq_pending_on_cpu);
+ dist->irq_sgi_sources = NULL;
+ dist->irq_spi_cpu = NULL;
+ dist->irq_spi_target = NULL;
+ dist->irq_pending_on_cpu = NULL;
+}
+
+/*
+ * Allocate and initialize the various data structures. Must be called
+ * with kvm->lock held!
+ */
+static int vgic_init_maps(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int nr_cpus, nr_irqs;
+ int ret, i;
+
+ if (dist->nr_cpus) /* Already allocated */
+ return 0;
+
+ nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
+ if (!nr_cpus) /* No vcpus? Can't be good... */
+ return -EINVAL;
+
+ /*
+ * If nobody configured the number of interrupts, use the
+ * legacy one.
+ */
+ if (!dist->nr_irqs)
+ dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
+
+ nr_irqs = dist->nr_irqs;
+
+ ret = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
+ ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
+
+ if (ret)
+ goto out;
+
+ dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
+ dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
+ dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
+ GFP_KERNEL);
+ dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
+ GFP_KERNEL);
+ if (!dist->irq_sgi_sources ||
+ !dist->irq_spi_cpu ||
+ !dist->irq_spi_target ||
+ !dist->irq_pending_on_cpu) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < nr_cpus; i++)
+ ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
+ nr_cpus, nr_irqs);
+
+ if (ret)
+ goto out;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
+ if (ret) {
+ kvm_err("VGIC: Failed to allocate vcpu memory\n");
+ break;
+ }
+ }
+
+ for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+ vgic_set_target_reg(kvm, 0, i);
+
+out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
+
+ return ret;
+}
+
+/**
+ * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * @kvm: pointer to the kvm struct
+ *
+ * Map the virtual CPU interface into the VM before running any VCPUs. We
+ * can't do this at creation time, because user space must first set the
+ * virtual CPU interface address in the guest physical address space. Also
+ * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ */
+int kvm_vgic_init(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ int ret = 0, i;
+
+ if (!irqchip_in_kernel(kvm))
+ return 0;
+
+ mutex_lock(&kvm->lock);
+
+ if (vgic_initialized(kvm))
+ goto out;
+
+ if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
+ IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_cpu_base)) {
+ kvm_err("Need to set vgic cpu and dist addresses first\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ret = vgic_init_maps(kvm);
+ if (ret) {
+ kvm_err("Unable to allocate maps\n");
+ goto out;
+ }
+
+ ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
+ vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
+ if (ret) {
+ kvm_err("Unable to remap VGIC CPU to VCPU\n");
+ goto out;
+ }
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_init(vcpu);
+
+ kvm->arch.vgic.ready = true;
+out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+int kvm_vgic_create(struct kvm *kvm)
+{
+ int i, vcpu_lock_idx = -1, ret = 0;
+ struct kvm_vcpu *vcpu;
+
+ mutex_lock(&kvm->lock);
+
+ if (kvm->arch.vgic.vctrl_base) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ /*
+ * Any time a vcpu is run, vcpu_load is called which tries to grab the
+ * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure
+ * that no other VCPUs are run while we create the vgic.
+ */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!mutex_trylock(&vcpu->mutex))
+ goto out_unlock;
+ vcpu_lock_idx = i;
+ }
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.has_run_once) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ }
+
+ spin_lock_init(&kvm->arch.vgic.lock);
+ kvm->arch.vgic.in_kernel = true;
+ kvm->arch.vgic.vctrl_base = vgic->vctrl_base;
+ kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
+ kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+
+out_unlock:
+ for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
+ vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
+ mutex_unlock(&vcpu->mutex);
+ }
+
+out:
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+static int vgic_ioaddr_overlap(struct kvm *kvm)
+{
+ phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
+ phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
+
+ if (IS_VGIC_ADDR_UNDEF(dist) || IS_VGIC_ADDR_UNDEF(cpu))
+ return 0;
+ if ((dist <= cpu && dist + KVM_VGIC_V2_DIST_SIZE > cpu) ||
+ (cpu <= dist && cpu + KVM_VGIC_V2_CPU_SIZE > dist))
+ return -EBUSY;
+ return 0;
+}
+
+static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
+ phys_addr_t addr, phys_addr_t size)
+{
+ int ret;
+
+ if (addr & ~KVM_PHYS_MASK)
+ return -E2BIG;
+
+ if (addr & (SZ_4K - 1))
+ return -EINVAL;
+
+ if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
+ return -EEXIST;
+ if (addr + size < addr)
+ return -EINVAL;
+
+ *ioaddr = addr;
+ ret = vgic_ioaddr_overlap(kvm);
+ if (ret)
+ *ioaddr = VGIC_ADDR_UNDEF;
+
+ return ret;
+}
+
+/**
+ * kvm_vgic_addr - set or get vgic VM base addresses
+ * @kvm: pointer to the vm struct
+ * @type: the VGIC addr type, one of KVM_VGIC_V2_ADDR_TYPE_XXX
+ * @addr: pointer to address value
+ * @write: if true set the address in the VM address space, if false read the
+ * address
+ *
+ * Set or get the vgic base addresses for the distributor and the virtual CPU
+ * interface in the VM physical address space. These addresses are properties
+ * of the emulated core/SoC and therefore user space initially knows this
+ * information.
+ */
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
+{
+ int r = 0;
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+
+ mutex_lock(&kvm->lock);
+ switch (type) {
+ case KVM_VGIC_V2_ADDR_TYPE_DIST:
+ if (write) {
+ r = vgic_ioaddr_assign(kvm, &vgic->vgic_dist_base,
+ *addr, KVM_VGIC_V2_DIST_SIZE);
+ } else {
+ *addr = vgic->vgic_dist_base;
+ }
+ break;
+ case KVM_VGIC_V2_ADDR_TYPE_CPU:
+ if (write) {
+ r = vgic_ioaddr_assign(kvm, &vgic->vgic_cpu_base,
+ *addr, KVM_VGIC_V2_CPU_SIZE);
+ } else {
+ *addr = vgic->vgic_cpu_base;
+ }
+ break;
+ default:
+ r = -ENODEV;
+ }
+
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static bool handle_cpu_mmio_misc(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ bool updated = false;
+ struct vgic_vmcr vmcr;
+ u32 *vmcr_field;
+ u32 reg;
+
+ vgic_get_vmcr(vcpu, &vmcr);
+
+ switch (offset & ~0x3) {
+ case GIC_CPU_CTRL:
+ vmcr_field = &vmcr.ctlr;
+ break;
+ case GIC_CPU_PRIMASK:
+ vmcr_field = &vmcr.pmr;
+ break;
+ case GIC_CPU_BINPOINT:
+ vmcr_field = &vmcr.bpr;
+ break;
+ case GIC_CPU_ALIAS_BINPOINT:
+ vmcr_field = &vmcr.abpr;
+ break;
+ default:
+ BUG();
+ }
+
+ if (!mmio->is_write) {
+ reg = *vmcr_field;
+ mmio_data_write(mmio, ~0, reg);
+ } else {
+ reg = mmio_data_read(mmio, ~0);
+ if (reg != *vmcr_field) {
+ *vmcr_field = reg;
+ vgic_set_vmcr(vcpu, &vmcr);
+ updated = true;
+ }
+ }
+ return updated;
+}
+
+static bool handle_mmio_abpr(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio, phys_addr_t offset)
+{
+ return handle_cpu_mmio_misc(vcpu, mmio, GIC_CPU_ALIAS_BINPOINT);
+}
+
+static bool handle_cpu_mmio_ident(struct kvm_vcpu *vcpu,
+ struct kvm_exit_mmio *mmio,
+ phys_addr_t offset)
+{
+ u32 reg;
+
+ if (mmio->is_write)
+ return false;
+
+ /* GICC_IIDR */
+ reg = (PRODUCT_ID_KVM << 20) |
+ (GICC_ARCH_VERSION_V2 << 16) |
+ (IMPLEMENTER_ARM << 0);
+ mmio_data_write(mmio, ~0, reg);
+ return false;
+}
+
+/*
+ * CPU Interface Register accesses - these are not accessed by the VM, but by
+ * user space for saving and restoring VGIC state.
+ */
+static const struct mmio_range vgic_cpu_ranges[] = {
+ {
+ .base = GIC_CPU_CTRL,
+ .len = 12,
+ .handle_mmio = handle_cpu_mmio_misc,
+ },
+ {
+ .base = GIC_CPU_ALIAS_BINPOINT,
+ .len = 4,
+ .handle_mmio = handle_mmio_abpr,
+ },
+ {
+ .base = GIC_CPU_ACTIVEPRIO,
+ .len = 16,
+ .handle_mmio = handle_mmio_raz_wi,
+ },
+ {
+ .base = GIC_CPU_IDENT,
+ .len = 4,
+ .handle_mmio = handle_cpu_mmio_ident,
+ },
+};
+
+static int vgic_attr_regs_access(struct kvm_device *dev,
+ struct kvm_device_attr *attr,
+ u32 *reg, bool is_write)
+{
+ const struct mmio_range *r = NULL, *ranges;
+ phys_addr_t offset;
+ int ret, cpuid, c;
+ struct kvm_vcpu *vcpu, *tmp_vcpu;
+ struct vgic_dist *vgic;
+ struct kvm_exit_mmio mmio;
+
+ offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+ cpuid = (attr->attr & KVM_DEV_ARM_VGIC_CPUID_MASK) >>
+ KVM_DEV_ARM_VGIC_CPUID_SHIFT;
+
+ mutex_lock(&dev->kvm->lock);
+
+ ret = vgic_init_maps(dev->kvm);
+ if (ret)
+ goto out;
+
+ if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ vcpu = kvm_get_vcpu(dev->kvm, cpuid);
+ vgic = &dev->kvm->arch.vgic;
+
+ mmio.len = 4;
+ mmio.is_write = is_write;
+ if (is_write)
+ mmio_data_write(&mmio, ~0, *reg);
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ mmio.phys_addr = vgic->vgic_dist_base + offset;
+ ranges = vgic_dist_ranges;
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+ mmio.phys_addr = vgic->vgic_cpu_base + offset;
+ ranges = vgic_cpu_ranges;
+ break;
+ default:
+ BUG();
+ }
+ r = find_matching_range(ranges, &mmio, offset);
+
+ if (unlikely(!r || !r->handle_mmio)) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+
+ spin_lock(&vgic->lock);
+
+ /*
+ * Ensure that no other VCPU is running by checking the vcpu->cpu
+ * field. If no other VPCUs are running we can safely access the VGIC
+ * state, because even if another VPU is run after this point, that
+ * VCPU will not touch the vgic state, because it will block on
+ * getting the vgic->lock in kvm_vgic_sync_hwstate().
+ */
+ kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm) {
+ if (unlikely(tmp_vcpu->cpu != -1)) {
+ ret = -EBUSY;
+ goto out_vgic_unlock;
+ }
+ }
+
+ /*
+ * Move all pending IRQs from the LRs on all VCPUs so the pending
+ * state can be properly represented in the register state accessible
+ * through this API.
+ */
+ kvm_for_each_vcpu(c, tmp_vcpu, dev->kvm)
+ vgic_unqueue_irqs(tmp_vcpu);
+
+ offset -= r->base;
+ r->handle_mmio(vcpu, &mmio, offset);
+
+ if (!is_write)
+ *reg = mmio_data_read(&mmio, ~0);
+
+ ret = 0;
+out_vgic_unlock:
+ spin_unlock(&vgic->lock);
+out:
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+}
+
+static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ int r;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 addr;
+ unsigned long type = (unsigned long)attr->attr;
+
+ if (copy_from_user(&addr, uaddr, sizeof(addr)))
+ return -EFAULT;
+
+ r = kvm_vgic_addr(dev->kvm, type, &addr, true);
+ return (r == -ENODEV) ? -ENXIO : r;
+ }
+
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 reg;
+
+ if (get_user(reg, uaddr))
+ return -EFAULT;
+
+ return vgic_attr_regs_access(dev, attr, ®, true);
+ }
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 val;
+ int ret = 0;
+
+ if (get_user(val, uaddr))
+ return -EFAULT;
+
+ /*
+ * We require:
+ * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
+ * - at most 1024 interrupts
+ * - a multiple of 32 interrupts
+ */
+ if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
+ val > VGIC_MAX_IRQS ||
+ (val & 31))
+ return -EINVAL;
+
+ mutex_lock(&dev->kvm->lock);
+
+ if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
+ ret = -EBUSY;
+ else
+ dev->kvm->arch.vgic.nr_irqs = val;
+
+ mutex_unlock(&dev->kvm->lock);
+
+ return ret;
+ }
+
+ }
+
+ return -ENXIO;
+}
+
+static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ int r = -ENXIO;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 addr;
+ unsigned long type = (unsigned long)attr->attr;
+
+ r = kvm_vgic_addr(dev->kvm, type, &addr, false);
+ if (r)
+ return (r == -ENODEV) ? -ENXIO : r;
+
+ if (copy_to_user(uaddr, &addr, sizeof(addr)))
+ return -EFAULT;
+ break;
+ }
+
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 reg = 0;
+
+ r = vgic_attr_regs_access(dev, attr, ®, false);
+ if (r)
+ return r;
+ r = put_user(reg, uaddr);
+ break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
+ break;
+ }
+
+ }
+
+ return r;
+}
+
+static int vgic_has_attr_regs(const struct mmio_range *ranges,
+ phys_addr_t offset)
+{
+ struct kvm_exit_mmio dev_attr_mmio;
+
+ dev_attr_mmio.len = 4;
+ if (find_matching_range(ranges, &dev_attr_mmio, offset))
+ return 0;
+ else
+ return -ENXIO;
+}
+
+static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ phys_addr_t offset;
+
+ switch (attr->group) {
+ case KVM_DEV_ARM_VGIC_GRP_ADDR:
+ switch (attr->attr) {
+ case KVM_VGIC_V2_ADDR_TYPE_DIST:
+ case KVM_VGIC_V2_ADDR_TYPE_CPU:
+ return 0;
+ }
+ break;
+ case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
+ offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+ return vgic_has_attr_regs(vgic_dist_ranges, offset);
+ case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
+ offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
+ return vgic_has_attr_regs(vgic_cpu_ranges, offset);
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+ return 0;
+ }
+ return -ENXIO;
+}
+
+static void vgic_destroy(struct kvm_device *dev)
+{
+ kfree(dev);
+}
+
+static int vgic_create(struct kvm_device *dev, u32 type)
+{
+ return kvm_vgic_create(dev->kvm);
+}
+
+static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+ .name = "kvm-arm-vgic",
+ .create = vgic_create,
+ .destroy = vgic_destroy,
+ .set_attr = vgic_set_attr,
+ .get_attr = vgic_get_attr,
+ .has_attr = vgic_has_attr,
+};
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+ enable_percpu_irq(vgic->maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *cpu)
+{
+ switch (action) {
+ case CPU_STARTING:
+ case CPU_STARTING_FROZEN:
+ vgic_init_maintenance_interrupt(NULL);
+ break;
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ disable_percpu_irq(vgic->maint_irq);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+ .notifier_call = vgic_cpu_notify,
+};
+
+static const struct of_device_id vgic_ids[] = {
+ { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+ { .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+ {},
+};
+
+int kvm_vgic_hyp_init(void)
+{
+ const struct of_device_id *matched_id;
+ int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+ const struct vgic_params **);
+ struct device_node *vgic_node;
+ int ret;
+
+ vgic_node = of_find_matching_node_and_match(NULL,
+ vgic_ids, &matched_id);
+ if (!vgic_node) {
+ kvm_err("error: no compatible GIC node found\n");
+ return -ENODEV;
+ }
+
+ vgic_probe = matched_id->data;
+ ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+ if (ret)
+ return ret;
+
+ ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
+ "vgic", kvm_get_running_vcpus());
+ if (ret) {
+ kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+ return ret;
+ }
+
+ ret = register_cpu_notifier(&vgic_cpu_nb);
+ if (ret) {
+ kvm_err("Cannot register vgic CPU notifier\n");
+ goto out_free_irq;
+ }
+
+ /* Callback into for arch code for setup */
+ vgic_arch_setup(vgic);
+
+ on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+ return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+ KVM_DEV_TYPE_ARM_VGIC_V2);
+
+out_free_irq:
+ free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
+ return ret;
+}
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index ea475cd..d6a3d09 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -28,6 +28,21 @@
#include "async_pf.h"
#include <trace/events/kvm.h>
+static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+ kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+#ifndef CONFIG_KVM_ASYNC_PF_SYNC
+ kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+
static struct kmem_cache *async_pf_cache;
int kvm_async_pf_init(void)
@@ -56,7 +71,6 @@
static void async_pf_execute(struct work_struct *work)
{
- struct page *page = NULL;
struct kvm_async_pf *apf =
container_of(work, struct kvm_async_pf, work);
struct mm_struct *mm = apf->mm;
@@ -66,16 +80,13 @@
might_sleep();
- use_mm(mm);
down_read(&mm->mmap_sem);
- get_user_pages(current, mm, addr, 1, 1, 0, &page, NULL);
+ get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
up_read(&mm->mmap_sem);
- unuse_mm(mm);
+ kvm_async_page_present_sync(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
list_add_tail(&apf->link, &vcpu->async_pf.done);
- apf->page = page;
- apf->done = true;
spin_unlock(&vcpu->async_pf.lock);
/*
@@ -83,12 +94,12 @@
* this point
*/
- trace_kvm_async_pf_completed(addr, page, gva);
+ trace_kvm_async_pf_completed(addr, gva);
if (waitqueue_active(&vcpu->wq))
wake_up_interruptible(&vcpu->wq);
- mmdrop(mm);
+ mmput(mm);
kvm_put_kvm(vcpu->kvm);
}
@@ -99,10 +110,17 @@
struct kvm_async_pf *work =
list_entry(vcpu->async_pf.queue.next,
typeof(*work), queue);
- cancel_work_sync(&work->work);
list_del(&work->queue);
- if (!work->done) /* work was canceled */
+
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+ flush_work(&work->work);
+#else
+ if (cancel_work_sync(&work->work)) {
+ mmput(work->mm);
+ kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
kmem_cache_free(async_pf_cache, work);
+ }
+#endif
}
spin_lock(&vcpu->async_pf.lock);
@@ -111,8 +129,6 @@
list_entry(vcpu->async_pf.done.next,
typeof(*work), link);
list_del(&work->link);
- if (!is_error_page(work->page))
- kvm_release_page_clean(work->page);
kmem_cache_free(async_pf_cache, work);
}
spin_unlock(&vcpu->async_pf.lock);
@@ -132,19 +148,16 @@
list_del(&work->link);
spin_unlock(&vcpu->async_pf.lock);
- if (work->page)
- kvm_arch_async_page_ready(vcpu, work);
- kvm_arch_async_page_present(vcpu, work);
+ kvm_arch_async_page_ready(vcpu, work);
+ kvm_async_page_present_async(vcpu, work);
list_del(&work->queue);
vcpu->async_pf.queued--;
- if (!is_error_page(work->page))
- kvm_release_page_clean(work->page);
kmem_cache_free(async_pf_cache, work);
}
}
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
struct kvm_arch_async_pf *arch)
{
struct kvm_async_pf *work;
@@ -162,14 +175,13 @@
if (!work)
return 0;
- work->page = NULL;
- work->done = false;
+ work->wakeup_all = false;
work->vcpu = vcpu;
work->gva = gva;
- work->addr = gfn_to_hva(vcpu->kvm, gfn);
+ work->addr = hva;
work->arch = *arch;
work->mm = current->mm;
- atomic_inc(&work->mm->mm_count);
+ atomic_inc(&work->mm->mm_users);
kvm_get_kvm(work->vcpu->kvm);
/* this can't really happen otherwise gfn_to_pfn_async
@@ -187,7 +199,7 @@
return 1;
retry_sync:
kvm_put_kvm(work->vcpu->kvm);
- mmdrop(work->mm);
+ mmput(work->mm);
kmem_cache_free(async_pf_cache, work);
return 0;
}
@@ -203,7 +215,7 @@
if (!work)
return -ENOMEM;
- work->page = KVM_ERR_PTR_BAD_PAGE;
+ work->wakeup_all = true;
INIT_LIST_HEAD(&work->queue); /* for list_del to work */
spin_lock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 88b2fe3..00d8642 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -154,17 +154,13 @@
list_add_tail(&dev->list, &kvm->coalesced_zones);
mutex_unlock(&kvm->slots_lock);
- return ret;
+ return 0;
out_free_dev:
mutex_unlock(&kvm->slots_lock);
-
kfree(dev);
- if (dev == NULL)
- return -ENXIO;
-
- return 0;
+ return ret;
}
int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 64ee720..71ed399 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -31,11 +31,14 @@
#include <linux/list.h>
#include <linux/eventfd.h>
#include <linux/kernel.h>
+#include <linux/srcu.h>
#include <linux/slab.h>
+#include <linux/seqlock.h>
+#include <trace/events/kvm.h>
#include "iodev.h"
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
/*
* --------------------------------------------------------------------
* irqfd: Allows an fd to be used to inject an interrupt to the guest
@@ -74,7 +77,8 @@
struct kvm *kvm;
wait_queue_t wait;
/* Update side is protected by irqfds.lock */
- struct kvm_kernel_irq_routing_entry __rcu *irq_entry;
+ struct kvm_kernel_irq_routing_entry irq_entry;
+ seqcount_t irq_entry_sc;
/* Used for level IRQ fast-path */
int gsi;
struct work_struct inject;
@@ -118,19 +122,22 @@
irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
{
struct _irqfd_resampler *resampler;
+ struct kvm *kvm;
struct _irqfd *irqfd;
+ int idx;
resampler = container_of(kian, struct _irqfd_resampler, notifier);
+ kvm = resampler->kvm;
- kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
resampler->notifier.gsi, 0, false);
- rcu_read_lock();
+ idx = srcu_read_lock(&kvm->irq_srcu);
list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
eventfd_signal(irqfd->resamplefd, 1);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
static void
@@ -142,7 +149,7 @@
mutex_lock(&kvm->irqfds.resampler_lock);
list_del_rcu(&irqfd->resampler_link);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
if (list_empty(&resampler->list)) {
list_del(&resampler->link);
@@ -219,19 +226,24 @@
{
struct _irqfd *irqfd = container_of(wait, struct _irqfd, wait);
unsigned long flags = (unsigned long)key;
- struct kvm_kernel_irq_routing_entry *irq;
+ struct kvm_kernel_irq_routing_entry irq;
struct kvm *kvm = irqfd->kvm;
+ unsigned seq;
+ int idx;
if (flags & POLLIN) {
- rcu_read_lock();
- irq = rcu_dereference(irqfd->irq_entry);
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ do {
+ seq = read_seqcount_begin(&irqfd->irq_entry_sc);
+ irq = irqfd->irq_entry;
+ } while (read_seqcount_retry(&irqfd->irq_entry_sc, seq));
/* An event has been signaled, inject an interrupt */
- if (irq)
- kvm_set_msi(irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
+ if (irq.type == KVM_IRQ_ROUTING_MSI)
+ kvm_set_msi(&irq, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1,
false);
else
schedule_work(&irqfd->inject);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
if (flags & POLLHUP) {
@@ -267,34 +279,37 @@
}
/* Must be called under irqfds.lock */
-static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd,
- struct kvm_irq_routing_table *irq_rt)
+static void irqfd_update(struct kvm *kvm, struct _irqfd *irqfd)
{
struct kvm_kernel_irq_routing_entry *e;
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+ int i, n_entries;
- if (irqfd->gsi >= irq_rt->nr_rt_entries) {
- rcu_assign_pointer(irqfd->irq_entry, NULL);
- return;
- }
+ n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);
- hlist_for_each_entry(e, &irq_rt->map[irqfd->gsi], link) {
+ write_seqcount_begin(&irqfd->irq_entry_sc);
+
+ irqfd->irq_entry.type = 0;
+
+ e = entries;
+ for (i = 0; i < n_entries; ++i, ++e) {
/* Only fast-path MSI. */
if (e->type == KVM_IRQ_ROUTING_MSI)
- rcu_assign_pointer(irqfd->irq_entry, e);
- else
- rcu_assign_pointer(irqfd->irq_entry, NULL);
+ irqfd->irq_entry = *e;
}
+
+ write_seqcount_end(&irqfd->irq_entry_sc);
}
static int
kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
{
- struct kvm_irq_routing_table *irq_rt;
struct _irqfd *irqfd, *tmp;
struct file *file = NULL;
struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
int ret;
unsigned int events;
+ int idx;
irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
if (!irqfd)
@@ -305,6 +320,7 @@
INIT_LIST_HEAD(&irqfd->list);
INIT_WORK(&irqfd->inject, irqfd_inject);
INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
+ seqcount_init(&irqfd->irq_entry_sc);
file = eventfd_fget(args->fd);
if (IS_ERR(file)) {
@@ -363,7 +379,7 @@
}
list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
mutex_unlock(&kvm->irqfds.resampler_lock);
}
@@ -387,9 +403,9 @@
goto fail;
}
- irq_rt = rcu_dereference_protected(kvm->irq_routing,
- lockdep_is_held(&kvm->irqfds.lock));
- irqfd_update(kvm, irqfd, irq_rt);
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ irqfd_update(kvm, irqfd);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
events = file->f_op->poll(file, &irqfd->pt);
@@ -428,12 +444,73 @@
kfree(irqfd);
return ret;
}
+
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_ack_notifier *kian;
+ int gsi, idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+ link)
+ if (kian->gsi == gsi) {
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return true;
+ }
+
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+
+void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ struct kvm_irq_ack_notifier *kian;
+ int gsi, idx;
+
+ trace_kvm_ack_irq(irqchip, pin);
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
+ link)
+ if (kian->gsi == gsi)
+ kian->irq_acked(kian);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+void kvm_register_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
+#ifdef __KVM_HAVE_IOAPIC
+ kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
+
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+ struct kvm_irq_ack_notifier *kian)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_init_rcu(&kian->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_srcu(&kvm->irq_srcu);
+#ifdef __KVM_HAVE_IOAPIC
+ kvm_vcpu_request_scan_ioapic(kvm);
+#endif
+}
#endif
void
kvm_eventfd_init(struct kvm *kvm)
{
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
spin_lock_init(&kvm->irqfds.lock);
INIT_LIST_HEAD(&kvm->irqfds.items);
INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
@@ -442,7 +519,7 @@
INIT_LIST_HEAD(&kvm->ioeventfds);
}
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+#ifdef CONFIG_HAVE_KVM_IRQFD
/*
* shutdown any irqfd's that match fd+gsi
*/
@@ -461,14 +538,14 @@
list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
/*
- * This rcu_assign_pointer is needed for when
+ * This clearing of irq_entry.type is needed for when
* another thread calls kvm_irq_routing_update before
* we flush workqueue below (we synchronize with
* kvm_irq_routing_update using irqfds.lock).
- * It is paired with synchronize_rcu done by caller
- * of that function.
*/
- rcu_assign_pointer(irqfd->irq_entry, NULL);
+ write_seqcount_begin(&irqfd->irq_entry_sc);
+ irqfd->irq_entry.type = 0;
+ write_seqcount_end(&irqfd->irq_entry_sc);
irqfd_deactivate(irqfd);
}
}
@@ -523,20 +600,17 @@
}
/*
- * Change irq_routing and irqfd.
- * Caller must invoke synchronize_rcu afterwards.
+ * Take note of a change in irq routing.
+ * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
*/
-void kvm_irq_routing_update(struct kvm *kvm,
- struct kvm_irq_routing_table *irq_rt)
+void kvm_irq_routing_update(struct kvm *kvm)
{
struct _irqfd *irqfd;
spin_lock_irq(&kvm->irqfds.lock);
- rcu_assign_pointer(kvm->irq_routing, irq_rt);
-
list_for_each_entry(irqfd, &kvm->irqfds.items, list)
- irqfd_update(kvm, irqfd, irq_rt);
+ irqfd_update(kvm, irqfd);
spin_unlock_irq(&kvm->irqfds.lock);
}
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 2d68297..b47541d 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -203,10 +203,9 @@
spin_lock(&ioapic->lock);
for (index = 0; index < IOAPIC_NUM_PINS; index++) {
e = &ioapic->redirtbl[index];
- if (!e->fields.mask &&
- (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
- kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
- index) || index == RTC_GSI)) {
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+ kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+ index == RTC_GSI) {
if (kvm_apic_match_dest(vcpu, NULL, 0,
e->fields.dest_id, e->fields.dest_mode)) {
__set_bit(e->fields.vector,
@@ -306,7 +305,7 @@
BUG_ON(ioapic->rtc_status.pending_eoi != 0);
ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
ioapic->rtc_status.dest_map);
- ioapic->rtc_status.pending_eoi = ret;
+ ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
} else
ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
@@ -520,7 +519,7 @@
return 0;
}
-void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
+static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
{
int i;
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 615d8c9..90d43e9 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -91,7 +91,6 @@
int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
int level, bool line_status);
void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
-void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq, unsigned long *dest_map);
int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 72a130b..36f4e82 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -43,13 +43,13 @@
gfn_t base_gfn, unsigned long npages);
static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
- unsigned long size)
+ unsigned long npages)
{
gfn_t end_gfn;
pfn_t pfn;
pfn = gfn_to_pfn_memslot(slot, gfn);
- end_gfn = gfn + (size >> PAGE_SHIFT);
+ end_gfn = gfn + npages;
gfn += 1;
if (is_error_noslot_pfn(pfn))
@@ -61,6 +61,14 @@
return pfn;
}
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
gfn_t gfn, end_gfn;
@@ -103,11 +111,15 @@
while ((gfn << PAGE_SHIFT) & (page_size - 1))
page_size >>= 1;
+ /* Make sure hva is aligned to the page size we want to map */
+ while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
+ page_size >>= 1;
+
/*
* Pin all pages we are about to map in memory. This is
* important because we unmap and unpin in 4kb steps later.
*/
- pfn = kvm_pin_pages(slot, gfn, page_size);
+ pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
if (is_error_noslot_pfn(pfn)) {
gfn += 1;
continue;
@@ -119,6 +131,7 @@
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%llx\n", pfn);
+ kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
goto unmap_pages;
}
@@ -130,7 +143,7 @@
return 0;
unmap_pages:
- kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
return r;
}
@@ -190,11 +203,7 @@
pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
- printk(KERN_DEBUG "assign device %x:%x:%x.%x\n",
- assigned_dev->host_segnr,
- assigned_dev->host_busnr,
- PCI_SLOT(assigned_dev->host_devfn),
- PCI_FUNC(assigned_dev->host_devfn));
+ dev_info(&pdev->dev, "kvm assign device\n");
return 0;
out_unmap:
@@ -220,11 +229,7 @@
pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
- printk(KERN_DEBUG "deassign device %x:%x:%x.%x\n",
- assigned_dev->host_segnr,
- assigned_dev->host_busnr,
- PCI_SLOT(assigned_dev->host_devfn),
- PCI_FUNC(assigned_dev->host_devfn));
+ dev_info(&pdev->dev, "kvm deassign device\n");
return 0;
}
@@ -268,14 +273,6 @@
return r;
}
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
- unsigned long i;
-
- for (i = 0; i < npages; ++i)
- kvm_release_pfn_clean(pfn + i);
-}
-
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index e2e6b44..963b899 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -160,9 +160,10 @@
*/
int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
{
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
struct kvm_kernel_irq_routing_entry *e;
int ret = -EINVAL;
- struct kvm_irq_routing_table *irq_rt;
+ int idx;
trace_kvm_set_irq(irq, level, irq_source_id);
@@ -174,17 +175,15 @@
* Since there's no easy way to do this, we only support injecting MSI
* which is limited to 1:1 GSI mapping.
*/
- rcu_read_lock();
- irq_rt = rcu_dereference(kvm->irq_routing);
- if (irq < irq_rt->nr_rt_entries)
- hlist_for_each_entry(e, &irq_rt->map[irq], link) {
- if (likely(e->type == KVM_IRQ_ROUTING_MSI))
- ret = kvm_set_msi_inatomic(e, kvm);
- else
- ret = -EWOULDBLOCK;
- break;
- }
- rcu_read_unlock();
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+ e = &entries[0];
+ if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+ ret = kvm_set_msi_inatomic(e, kvm);
+ else
+ ret = -EWOULDBLOCK;
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
return ret;
}
@@ -253,26 +252,25 @@
mutex_lock(&kvm->irq_lock);
hlist_del_rcu(&kimn->link);
mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
+ synchronize_srcu(&kvm->irq_srcu);
}
void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
bool mask)
{
struct kvm_irq_mask_notifier *kimn;
- int gsi;
+ int idx, gsi;
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
if (gsi != -1)
hlist_for_each_entry_rcu(kimn, &kvm->mask_notifier_list, link)
if (kimn->irq == gsi)
kimn->func(kimn, mask);
- rcu_read_unlock();
+ srcu_read_unlock(&kvm->irq_srcu, idx);
}
-int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
- struct kvm_kernel_irq_routing_entry *e,
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
int r = -EINVAL;
@@ -303,7 +301,6 @@
e->irqchip.pin = ue->u.irqchip.pin + delta;
if (e->irqchip.pin >= max_pin)
goto out;
- rt->chip[ue->u.irqchip.irqchip][e->irqchip.pin] = ue->gsi;
break;
case KVM_IRQ_ROUTING_MSI:
e->set = kvm_set_msi;
@@ -322,13 +319,13 @@
#define IOAPIC_ROUTING_ENTRY(irq) \
{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
+ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
#ifdef CONFIG_X86
# define PIC_ROUTING_ENTRY(irq) \
{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
+ .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
# define ROUTING_ENTRY2(irq) \
IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
#else
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 20dc9e4..7f256f3 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -26,69 +26,47 @@
#include <linux/kvm_host.h>
#include <linux/slab.h>
+#include <linux/srcu.h>
#include <linux/export.h>
#include <trace/events/kvm.h>
#include "irq.h"
-bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+struct kvm_irq_routing_table {
+ int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
+ struct kvm_kernel_irq_routing_entry *rt_entries;
+ u32 nr_rt_entries;
+ /*
+ * Array indexed by gsi. Each entry contains list of irq chips
+ * the gsi is connected to.
+ */
+ struct hlist_head map[0];
+};
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
{
- struct kvm_irq_ack_notifier *kian;
- int gsi;
+ struct kvm_irq_routing_table *irq_rt;
+ struct kvm_kernel_irq_routing_entry *e;
+ int n = 0;
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
- if (gsi != -1)
- hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
- link)
- if (kian->gsi == gsi) {
- rcu_read_unlock();
- return true;
- }
+ irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu,
+ lockdep_is_held(&kvm->irq_lock));
+ if (gsi < irq_rt->nr_rt_entries) {
+ hlist_for_each_entry(e, &irq_rt->map[gsi], link) {
+ entries[n] = *e;
+ ++n;
+ }
+ }
- rcu_read_unlock();
-
- return false;
-}
-EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
-
-void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
- struct kvm_irq_ack_notifier *kian;
- int gsi;
-
- trace_kvm_ack_irq(irqchip, pin);
-
- rcu_read_lock();
- gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
- if (gsi != -1)
- hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
- link)
- if (kian->gsi == gsi)
- kian->irq_acked(kian);
- rcu_read_unlock();
+ return n;
}
-void kvm_register_irq_ack_notifier(struct kvm *kvm,
- struct kvm_irq_ack_notifier *kian)
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
- mutex_lock(&kvm->irq_lock);
- hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
- mutex_unlock(&kvm->irq_lock);
-#ifdef __KVM_HAVE_IOAPIC
- kvm_vcpu_request_scan_ioapic(kvm);
-#endif
-}
+ struct kvm_irq_routing_table *irq_rt;
-void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
- struct kvm_irq_ack_notifier *kian)
-{
- mutex_lock(&kvm->irq_lock);
- hlist_del_init_rcu(&kian->link);
- mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
-#ifdef __KVM_HAVE_IOAPIC
- kvm_vcpu_request_scan_ioapic(kvm);
-#endif
+ irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+ return irq_rt->chip[irqchip][pin];
}
int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
@@ -114,9 +92,8 @@
int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
bool line_status)
{
- struct kvm_kernel_irq_routing_entry *e, irq_set[KVM_NR_IRQCHIPS];
- int ret = -1, i = 0;
- struct kvm_irq_routing_table *irq_rt;
+ struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS];
+ int ret = -1, i, idx;
trace_kvm_set_irq(irq, level, irq_source_id);
@@ -124,12 +101,9 @@
* IOAPIC. So set the bit in both. The guest will ignore
* writes to the unused one.
*/
- rcu_read_lock();
- irq_rt = rcu_dereference(kvm->irq_routing);
- if (irq < irq_rt->nr_rt_entries)
- hlist_for_each_entry(e, &irq_rt->map[irq], link)
- irq_set[i++] = *e;
- rcu_read_unlock();
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ i = kvm_irq_map_gsi(kvm, irq_set, irq);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
while(i--) {
int r;
@@ -170,9 +144,11 @@
e->gsi = ue->gsi;
e->type = ue->type;
- r = kvm_set_routing_entry(rt, e, ue);
+ r = kvm_set_routing_entry(e, ue);
if (r)
goto out;
+ if (e->type == KVM_IRQ_ROUTING_IRQCHIP)
+ rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi;
hlist_add_head(&e->link, &rt->map[e->gsi]);
r = 0;
@@ -223,10 +199,11 @@
mutex_lock(&kvm->irq_lock);
old = kvm->irq_routing;
- kvm_irq_routing_update(kvm, new);
+ rcu_assign_pointer(kvm->irq_routing, new);
+ kvm_irq_routing_update(kvm);
mutex_unlock(&kvm->irq_lock);
- synchronize_rcu();
+ synchronize_srcu_expedited(&kvm->irq_srcu);
new = old;
r = 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 302681c..8c56eae 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -52,6 +52,7 @@
#include <asm/processor.h>
#include <asm/io.h>
+#include <asm/ioctl.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -70,7 +71,8 @@
* kvm->lock --> kvm->slots_lock --> kvm->irq_lock
*/
-DEFINE_RAW_SPINLOCK(kvm_lock);
+DEFINE_SPINLOCK(kvm_lock);
+static DEFINE_RAW_SPINLOCK(kvm_count_lock);
LIST_HEAD(vm_list);
static cpumask_var_t cpus_hardware_enabled;
@@ -94,36 +96,22 @@
static void hardware_disable_all(void);
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
+static void update_memslots(struct kvm_memslots *slots,
+ struct kvm_memory_slot *new, u64 last_generation);
-bool kvm_rebooting;
+static void kvm_release_pfn_dirty(pfn_t pfn);
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot, gfn_t gfn);
+
+__visible bool kvm_rebooting;
EXPORT_SYMBOL_GPL(kvm_rebooting);
static bool largepages_enabled = true;
bool kvm_is_mmio_pfn(pfn_t pfn)
{
- if (pfn_valid(pfn)) {
- int reserved;
- struct page *tail = pfn_to_page(pfn);
- struct page *head = compound_trans_head(tail);
- reserved = PageReserved(head);
- if (head != tail) {
- /*
- * "head" is not a dangling pointer
- * (compound_trans_head takes care of that)
- * but the hugepage may have been splitted
- * from under us (and we may not hold a
- * reference count on the head page so it can
- * be reused before we run PageReferenced), so
- * we've to check PageTail before returning
- * what we just read.
- */
- smp_rmb();
- if (PageTail(tail))
- return reserved;
- }
- return PageReserved(tail);
- }
+ if (pfn_valid(pfn))
+ return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
return true;
}
@@ -142,7 +130,8 @@
struct pid *oldpid = vcpu->pid;
struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
rcu_assign_pointer(vcpu->pid, newpid);
- synchronize_rcu();
+ if (oldpid)
+ synchronize_rcu();
put_pid(oldpid);
}
cpu = get_cpu();
@@ -469,14 +458,16 @@
r = kvm_arch_init_vm(kvm, type);
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
r = hardware_enable_all();
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
INIT_HLIST_HEAD(&kvm->mask_notifier_list);
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif
@@ -485,10 +476,12 @@
r = -ENOMEM;
kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!kvm->memslots)
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
kvm_init_memslots_id(kvm);
if (init_srcu_struct(&kvm->srcu))
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
+ if (init_srcu_struct(&kvm->irq_srcu))
+ goto out_err_no_irq_srcu;
for (i = 0; i < KVM_NR_BUSES; i++) {
kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
GFP_KERNEL);
@@ -510,17 +503,19 @@
if (r)
goto out_err;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
return kvm;
out_err:
+ cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm->buses[i]);
kfree(kvm->memslots);
@@ -560,24 +555,24 @@
/*
* Free any memory in @free but not in @dont.
*/
-static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
+static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
kvm_destroy_dirty_bitmap(free);
- kvm_arch_free_memslot(free, dont);
+ kvm_arch_free_memslot(kvm, free, dont);
free->npages = 0;
}
-void kvm_free_physmem(struct kvm *kvm)
+static void kvm_free_physmem(struct kvm *kvm)
{
struct kvm_memslots *slots = kvm->memslots;
struct kvm_memory_slot *memslot;
kvm_for_each_memslot(memslot, slots)
- kvm_free_physmem_slot(memslot, NULL);
+ kvm_free_physmem_slot(kvm, memslot, NULL);
kfree(kvm->memslots);
}
@@ -601,9 +596,9 @@
struct mm_struct *mm = kvm->mm;
kvm_arch_sync_events(kvm);
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
kvm_free_irq_routing(kvm);
for (i = 0; i < KVM_NR_BUSES; i++)
kvm_io_bus_destroy(kvm->buses[i]);
@@ -616,6 +611,7 @@
kvm_arch_destroy_vm(kvm);
kvm_destroy_devices(kvm);
kvm_free_physmem(kvm);
+ cleanup_srcu_struct(&kvm->irq_srcu);
cleanup_srcu_struct(&kvm->srcu);
kvm_arch_free_vm(kvm);
hardware_disable_all();
@@ -693,8 +689,9 @@
slots->id_to_index[slots->memslots[i].id] = i;
}
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new,
- u64 last_generation)
+static void update_memslots(struct kvm_memslots *slots,
+ struct kvm_memory_slot *new,
+ u64 last_generation)
{
if (new) {
int id = new->id;
@@ -713,7 +710,7 @@
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
-#ifdef KVM_CAP_READONLY_MEM
+#ifdef __KVM_HAVE_READONLY_MEM
valid_flags |= KVM_MEM_READONLY;
#endif
@@ -731,7 +728,10 @@
update_memslots(slots, new, kvm->memslots->generation);
rcu_assign_pointer(kvm->memslots, slots);
synchronize_srcu_expedited(&kvm->srcu);
- return old_memslots;
+
+ kvm_arch_memslots_updated(kvm);
+
+ return old_memslots;
}
/*
@@ -779,7 +779,6 @@
base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
npages = mem->memory_size >> PAGE_SHIFT;
- r = -EINVAL;
if (npages > KVM_MEM_MAX_NR_PAGES)
goto out;
@@ -793,7 +792,6 @@
new.npages = npages;
new.flags = mem->flags;
- r = -EINVAL;
if (npages) {
if (!old.npages)
change = KVM_MR_CREATE;
@@ -838,7 +836,7 @@
if (change == KVM_MR_CREATE) {
new.userspace_addr = mem->userspace_addr;
- if (kvm_arch_create_memslot(&new, npages))
+ if (kvm_arch_create_memslot(kvm, &new, npages))
goto out_free;
}
@@ -849,7 +847,6 @@
}
if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
- r = -ENOMEM;
slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
GFP_KERNEL);
if (!slots)
@@ -889,6 +886,19 @@
goto out_free;
}
+ /* actual memory is freed via old in kvm_free_physmem_slot below */
+ if (change == KVM_MR_DELETE) {
+ new.dirty_bitmap = NULL;
+ memset(&new.arch, 0, sizeof(new.arch));
+ }
+
+ old_memslots = install_new_memslots(kvm, slots, &new);
+
+ kvm_arch_commit_memory_region(kvm, mem, &old, change);
+
+ kvm_free_physmem_slot(kvm, &old, &new);
+ kfree(old_memslots);
+
/*
* IOMMU mapping: New slots need to be mapped. Old slots need to be
* un-mapped and re-mapped if their base changes. Since base change
@@ -900,29 +910,15 @@
*/
if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
r = kvm_iommu_map_pages(kvm, &new);
- if (r)
- goto out_slots;
+ return r;
}
- /* actual memory is freed via old in kvm_free_physmem_slot below */
- if (change == KVM_MR_DELETE) {
- new.dirty_bitmap = NULL;
- memset(&new.arch, 0, sizeof(new.arch));
- }
-
- old_memslots = install_new_memslots(kvm, slots, &new);
-
- kvm_arch_commit_memory_region(kvm, mem, &old, change);
-
- kvm_free_physmem_slot(&old, &new);
- kfree(old_memslots);
-
return 0;
out_slots:
kfree(slots);
out_free:
- kvm_free_physmem_slot(&new, &old);
+ kvm_free_physmem_slot(kvm, &new, &old);
out:
return r;
}
@@ -940,8 +936,8 @@
}
EXPORT_SYMBOL_GPL(kvm_set_memory_region);
-int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem)
{
if (mem->slot >= KVM_USER_MEM_SLOTS)
return -EINVAL;
@@ -1062,7 +1058,7 @@
}
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
- gfn_t gfn)
+ gfn_t gfn)
{
return gfn_to_hva_many(slot, gfn, NULL);
}
@@ -1075,12 +1071,25 @@
EXPORT_SYMBOL_GPL(gfn_to_hva);
/*
- * The hva returned by this function is only allowed to be read.
- * It should pair with kvm_read_hva() or kvm_read_hva_atomic().
+ * If writable is set to false, the hva returned by this function is only
+ * allowed to be read.
*/
-static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn)
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
+ gfn_t gfn, bool *writable)
{
- return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false);
+ unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
+
+ if (!kvm_is_error_hva(hva) && writable)
+ *writable = !memslot_is_readonly(slot);
+
+ return hva;
+}
+
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+ return gfn_to_hva_memslot_prot(slot, gfn, writable);
}
static int kvm_read_hva(void *data, void __user *hva, int len)
@@ -1396,18 +1405,11 @@
}
EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
-void kvm_release_pfn_dirty(pfn_t pfn)
+static void kvm_release_pfn_dirty(pfn_t pfn)
{
kvm_set_pfn_dirty(pfn);
kvm_release_pfn_clean(pfn);
}
-EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
-
-void kvm_set_page_dirty(struct page *page)
-{
- kvm_set_pfn_dirty(page_to_pfn(page));
-}
-EXPORT_SYMBOL_GPL(kvm_set_page_dirty);
void kvm_set_pfn_dirty(pfn_t pfn)
{
@@ -1447,7 +1449,7 @@
int r;
unsigned long addr;
- addr = gfn_to_hva_read(kvm, gfn);
+ addr = gfn_to_hva_prot(kvm, gfn, NULL);
if (kvm_is_error_hva(addr))
return -EFAULT;
r = kvm_read_hva(data, (void __user *)addr + offset, len);
@@ -1485,7 +1487,7 @@
gfn_t gfn = gpa >> PAGE_SHIFT;
int offset = offset_in_page(gpa);
- addr = gfn_to_hva_read(kvm, gfn);
+ addr = gfn_to_hva_prot(kvm, gfn, NULL);
if (kvm_is_error_hva(addr))
return -EFAULT;
pagefault_disable();
@@ -1548,8 +1550,8 @@
ghc->generation = slots->generation;
ghc->len = len;
ghc->memslot = gfn_to_memslot(kvm, start_gfn);
- ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
- if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, NULL);
+ if (!kvm_is_error_hva(ghc->hva) && nr_pages_needed <= 1) {
ghc->hva += offset;
} else {
/*
@@ -1624,8 +1626,9 @@
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
{
- return kvm_write_guest_page(kvm, gfn, (const void *) empty_zero_page,
- offset, len);
+ const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+
+ return kvm_write_guest_page(kvm, gfn, zero_page, offset, len);
}
EXPORT_SYMBOL_GPL(kvm_clear_guest_page);
@@ -1648,8 +1651,9 @@
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);
-void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
- gfn_t gfn)
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ gfn_t gfn)
{
if (memslot && memslot->dirty_bitmap) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
@@ -1716,14 +1720,6 @@
EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
#endif /* !CONFIG_S390 */
-void kvm_resched(struct kvm_vcpu *vcpu)
-{
- if (!need_resched())
- return;
- cond_resched();
-}
-EXPORT_SYMBOL_GPL(kvm_resched);
-
bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
{
struct pid *pid;
@@ -1733,7 +1729,7 @@
rcu_read_lock();
pid = rcu_dereference(target->pid);
if (pid)
- task = get_pid_task(target->pid, PIDTYPE_PID);
+ task = get_pid_task(pid, PIDTYPE_PID);
rcu_read_unlock();
if (!task)
return ret;
@@ -1748,7 +1744,6 @@
}
EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
-#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
/*
* Helper that checks whether a VCPU is eligible for directed yield.
* Most eligible candidate to yield is decided by following heuristics:
@@ -1771,20 +1766,22 @@
* locking does not harm. It may result in trying to yield to same VCPU, fail
* and continue with next VCPU and so on.
*/
-bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
{
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
bool eligible;
eligible = !vcpu->spin_loop.in_spin_loop ||
- (vcpu->spin_loop.in_spin_loop &&
- vcpu->spin_loop.dy_eligible);
+ vcpu->spin_loop.dy_eligible;
if (vcpu->spin_loop.in_spin_loop)
kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
return eligible;
-}
+#else
+ return true;
#endif
+}
void kvm_vcpu_on_spin(struct kvm_vcpu *me)
{
@@ -1815,7 +1812,7 @@
continue;
if (vcpu == me)
continue;
- if (waitqueue_active(&vcpu->wq))
+ if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
@@ -1893,7 +1890,7 @@
*/
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
- return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR);
+ return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
/*
@@ -1904,6 +1901,9 @@
int r;
struct kvm_vcpu *vcpu, *v;
+ if (id >= KVM_MAX_VCPUS)
+ return -EINVAL;
+
vcpu = kvm_arch_vcpu_create(kvm, id);
if (IS_ERR(vcpu))
return PTR_ERR(vcpu);
@@ -1978,6 +1978,9 @@
if (vcpu->kvm->mm != current->mm)
return -EIO;
+ if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+ return -EINVAL;
+
#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
/*
* Special cases: vcpu ioctls that are asynchronous to vcpu execution,
@@ -2262,6 +2265,29 @@
return filp->private_data;
}
+static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+#ifdef CONFIG_KVM_MPIC
+ [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
+ [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
+#endif
+
+#ifdef CONFIG_KVM_XICS
+ [KVM_DEV_TYPE_XICS] = &kvm_xics_ops,
+#endif
+};
+
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+{
+ if (type >= ARRAY_SIZE(kvm_device_ops_table))
+ return -ENOSPC;
+
+ if (kvm_device_ops_table[type] != NULL)
+ return -EEXIST;
+
+ kvm_device_ops_table[type] = ops;
+ return 0;
+}
+
static int kvm_ioctl_create_device(struct kvm *kvm,
struct kvm_create_device *cd)
{
@@ -2270,21 +2296,12 @@
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
int ret;
- switch (cd->type) {
-#ifdef CONFIG_KVM_MPIC
- case KVM_DEV_TYPE_FSL_MPIC_20:
- case KVM_DEV_TYPE_FSL_MPIC_42:
- ops = &kvm_mpic_ops;
- break;
-#endif
-#ifdef CONFIG_KVM_XICS
- case KVM_DEV_TYPE_XICS:
- ops = &kvm_xics_ops;
- break;
-#endif
- default:
+ if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
- }
+
+ ops = kvm_device_ops_table[cd->type];
+ if (ops == NULL)
+ return -ENODEV;
if (test)
return 0;
@@ -2302,7 +2319,7 @@
return ret;
}
- ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR);
+ ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
if (ret < 0) {
ops->destroy(dev);
return ret;
@@ -2314,6 +2331,34 @@
return 0;
}
+static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
+{
+ switch (arg) {
+ case KVM_CAP_USER_MEMORY:
+ case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
+ case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
+#ifdef CONFIG_KVM_APIC_ARCHITECTURE
+ case KVM_CAP_SET_BOOT_CPU_ID:
+#endif
+ case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+ case KVM_CAP_SIGNAL_MSI:
+#endif
+#ifdef CONFIG_HAVE_KVM_IRQFD
+ case KVM_CAP_IRQFD_RESAMPLE:
+#endif
+ case KVM_CAP_CHECK_EXTENSION_VM:
+ return 1;
+#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
+ case KVM_CAP_IRQ_ROUTING:
+ return KVM_MAX_IRQ_ROUTES;
+#endif
+ default:
+ break;
+ }
+ return kvm_vm_ioctl_check_extension(kvm, arg);
+}
+
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2477,6 +2522,9 @@
r = 0;
break;
}
+ case KVM_CHECK_EXTENSION:
+ r = kvm_vm_ioctl_check_extension_generic(kvm, arg);
+ break;
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
if (r == -ENOTTY)
@@ -2530,44 +2578,12 @@
}
#endif
-static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- struct page *page[1];
- unsigned long addr;
- int npages;
- gfn_t gfn = vmf->pgoff;
- struct kvm *kvm = vma->vm_file->private_data;
-
- addr = gfn_to_hva(kvm, gfn);
- if (kvm_is_error_hva(addr))
- return VM_FAULT_SIGBUS;
-
- npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page,
- NULL);
- if (unlikely(npages != 1))
- return VM_FAULT_SIGBUS;
-
- vmf->page = page[0];
- return 0;
-}
-
-static const struct vm_operations_struct kvm_vm_vm_ops = {
- .fault = kvm_vm_fault,
-};
-
-static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma)
-{
- vma->vm_ops = &kvm_vm_vm_ops;
- return 0;
-}
-
static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = kvm_vm_compat_ioctl,
#endif
- .mmap = kvm_vm_mmap,
.llseek = noop_llseek,
};
@@ -2586,40 +2602,13 @@
return r;
}
#endif
- r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+ r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
if (r < 0)
kvm_put_kvm(kvm);
return r;
}
-static long kvm_dev_ioctl_check_extension_generic(long arg)
-{
- switch (arg) {
- case KVM_CAP_USER_MEMORY:
- case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
- case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS:
-#ifdef CONFIG_KVM_APIC_ARCHITECTURE
- case KVM_CAP_SET_BOOT_CPU_ID:
-#endif
- case KVM_CAP_INTERNAL_ERROR_DATA:
-#ifdef CONFIG_HAVE_KVM_MSI
- case KVM_CAP_SIGNAL_MSI:
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
- case KVM_CAP_IRQFD_RESAMPLE:
-#endif
- return 1;
-#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
- case KVM_CAP_IRQ_ROUTING:
- return KVM_MAX_IRQ_ROUTES;
-#endif
- default:
- break;
- }
- return kvm_dev_ioctl_check_extension(arg);
-}
-
static long kvm_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2627,7 +2616,6 @@
switch (ioctl) {
case KVM_GET_API_VERSION:
- r = -EINVAL;
if (arg)
goto out;
r = KVM_API_VERSION;
@@ -2636,10 +2624,9 @@
r = kvm_dev_ioctl_create_vm(arg);
break;
case KVM_CHECK_EXTENSION:
- r = kvm_dev_ioctl_check_extension_generic(arg);
+ r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
break;
case KVM_GET_VCPU_MMAP_SIZE:
- r = -EINVAL;
if (arg)
goto out;
r = PAGE_SIZE; /* struct kvm_run */
@@ -2684,7 +2671,7 @@
cpumask_set_cpu(cpu, cpus_hardware_enabled);
- r = kvm_arch_hardware_enable(NULL);
+ r = kvm_arch_hardware_enable();
if (r) {
cpumask_clear_cpu(cpu, cpus_hardware_enabled);
@@ -2694,11 +2681,12 @@
}
}
-static void hardware_enable(void *junk)
+static void hardware_enable(void)
{
- raw_spin_lock(&kvm_lock);
- hardware_enable_nolock(junk);
- raw_spin_unlock(&kvm_lock);
+ raw_spin_lock(&kvm_count_lock);
+ if (kvm_usage_count)
+ hardware_enable_nolock(NULL);
+ raw_spin_unlock(&kvm_count_lock);
}
static void hardware_disable_nolock(void *junk)
@@ -2708,14 +2696,15 @@
if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
return;
cpumask_clear_cpu(cpu, cpus_hardware_enabled);
- kvm_arch_hardware_disable(NULL);
+ kvm_arch_hardware_disable();
}
-static void hardware_disable(void *junk)
+static void hardware_disable(void)
{
- raw_spin_lock(&kvm_lock);
- hardware_disable_nolock(junk);
- raw_spin_unlock(&kvm_lock);
+ raw_spin_lock(&kvm_count_lock);
+ if (kvm_usage_count)
+ hardware_disable_nolock(NULL);
+ raw_spin_unlock(&kvm_count_lock);
}
static void hardware_disable_all_nolock(void)
@@ -2729,16 +2718,16 @@
static void hardware_disable_all(void)
{
- raw_spin_lock(&kvm_lock);
+ raw_spin_lock(&kvm_count_lock);
hardware_disable_all_nolock();
- raw_spin_unlock(&kvm_lock);
+ raw_spin_unlock(&kvm_count_lock);
}
static int hardware_enable_all(void)
{
int r = 0;
- raw_spin_lock(&kvm_lock);
+ raw_spin_lock(&kvm_count_lock);
kvm_usage_count++;
if (kvm_usage_count == 1) {
@@ -2751,7 +2740,7 @@
}
}
- raw_spin_unlock(&kvm_lock);
+ raw_spin_unlock(&kvm_count_lock);
return r;
}
@@ -2761,20 +2750,17 @@
{
int cpu = (long)v;
- if (!kvm_usage_count)
- return NOTIFY_OK;
-
val &= ~CPU_TASKS_FROZEN;
switch (val) {
case CPU_DYING:
printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
cpu);
- hardware_disable(NULL);
+ hardware_disable();
break;
case CPU_STARTING:
printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
cpu);
- hardware_enable(NULL);
+ hardware_enable();
break;
}
return NOTIFY_OK;
@@ -2987,10 +2973,10 @@
struct kvm *kvm;
*val = 0;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
*val += *(u32 *)((void *)kvm + offset);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
return 0;
}
@@ -3004,12 +2990,12 @@
int i;
*val = 0;
- raw_spin_lock(&kvm_lock);
+ spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
*val += *(u32 *)((void *)vcpu + offset);
- raw_spin_unlock(&kvm_lock);
+ spin_unlock(&kvm_lock);
return 0;
}
@@ -3022,7 +3008,7 @@
static int kvm_init_debug(void)
{
- int r = -EFAULT;
+ int r = -EEXIST;
struct kvm_stats_debugfs_item *p;
kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
@@ -3064,7 +3050,7 @@
static void kvm_resume(void)
{
if (kvm_usage_count) {
- WARN_ON(raw_spin_is_locked(&kvm_lock));
+ WARN_ON(raw_spin_is_locked(&kvm_count_lock));
hardware_enable_nolock(NULL);
}
}
@@ -3086,6 +3072,8 @@
if (vcpu->preempted)
vcpu->preempted = false;
+ kvm_arch_sched_in(vcpu, cpu);
+
kvm_arch_vcpu_load(vcpu, cpu);
}
@@ -3181,6 +3169,7 @@
out_undebugfs:
unregister_syscore_ops(&kvm_syscore_ops);
+ misc_deregister(&kvm_dev);
out_unreg:
kvm_async_pf_deinit();
out_free:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
new file mode 100644
index 0000000..475487e
--- /dev/null
+++ b/virt/kvm/vfio.c
@@ -0,0 +1,228 @@
+/*
+ * VFIO-KVM bridge pseudo device
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All rights reserved.
+ * Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+
+struct kvm_vfio_group {
+ struct list_head node;
+ struct vfio_group *vfio_group;
+};
+
+struct kvm_vfio {
+ struct list_head group_list;
+ struct mutex lock;
+};
+
+static struct vfio_group *kvm_vfio_group_get_external_user(struct file *filep)
+{
+ struct vfio_group *vfio_group;
+ struct vfio_group *(*fn)(struct file *);
+
+ fn = symbol_get(vfio_group_get_external_user);
+ if (!fn)
+ return ERR_PTR(-EINVAL);
+
+ vfio_group = fn(filep);
+
+ symbol_put(vfio_group_get_external_user);
+
+ return vfio_group;
+}
+
+static void kvm_vfio_group_put_external_user(struct vfio_group *vfio_group)
+{
+ void (*fn)(struct vfio_group *);
+
+ fn = symbol_get(vfio_group_put_external_user);
+ if (!fn)
+ return;
+
+ fn(vfio_group);
+
+ symbol_put(vfio_group_put_external_user);
+}
+
+static int kvm_vfio_set_group(struct kvm_device *dev, long attr, u64 arg)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct vfio_group *vfio_group;
+ struct kvm_vfio_group *kvg;
+ void __user *argp = (void __user *)arg;
+ struct fd f;
+ int32_t fd;
+ int ret;
+
+ switch (attr) {
+ case KVM_DEV_VFIO_GROUP_ADD:
+ if (get_user(fd, (int32_t __user *)argp))
+ return -EFAULT;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ vfio_group = kvm_vfio_group_get_external_user(f.file);
+ fdput(f);
+
+ if (IS_ERR(vfio_group))
+ return PTR_ERR(vfio_group);
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (kvg->vfio_group == vfio_group) {
+ mutex_unlock(&kv->lock);
+ kvm_vfio_group_put_external_user(vfio_group);
+ return -EEXIST;
+ }
+ }
+
+ kvg = kzalloc(sizeof(*kvg), GFP_KERNEL);
+ if (!kvg) {
+ mutex_unlock(&kv->lock);
+ kvm_vfio_group_put_external_user(vfio_group);
+ return -ENOMEM;
+ }
+
+ list_add_tail(&kvg->node, &kv->group_list);
+ kvg->vfio_group = vfio_group;
+
+ mutex_unlock(&kv->lock);
+
+ return 0;
+
+ case KVM_DEV_VFIO_GROUP_DEL:
+ if (get_user(fd, (int32_t __user *)argp))
+ return -EFAULT;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ vfio_group = kvm_vfio_group_get_external_user(f.file);
+ fdput(f);
+
+ if (IS_ERR(vfio_group))
+ return PTR_ERR(vfio_group);
+
+ ret = -ENOENT;
+
+ mutex_lock(&kv->lock);
+
+ list_for_each_entry(kvg, &kv->group_list, node) {
+ if (kvg->vfio_group != vfio_group)
+ continue;
+
+ list_del(&kvg->node);
+ kvm_vfio_group_put_external_user(kvg->vfio_group);
+ kfree(kvg);
+ ret = 0;
+ break;
+ }
+
+ mutex_unlock(&kv->lock);
+
+ kvm_vfio_group_put_external_user(vfio_group);
+
+ return ret;
+ }
+
+ return -ENXIO;
+}
+
+static int kvm_vfio_set_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_VFIO_GROUP:
+ return kvm_vfio_set_group(dev, attr->attr, attr->addr);
+ }
+
+ return -ENXIO;
+}
+
+static int kvm_vfio_has_attr(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ switch (attr->group) {
+ case KVM_DEV_VFIO_GROUP:
+ switch (attr->attr) {
+ case KVM_DEV_VFIO_GROUP_ADD:
+ case KVM_DEV_VFIO_GROUP_DEL:
+ return 0;
+ }
+
+ break;
+ }
+
+ return -ENXIO;
+}
+
+static void kvm_vfio_destroy(struct kvm_device *dev)
+{
+ struct kvm_vfio *kv = dev->private;
+ struct kvm_vfio_group *kvg, *tmp;
+
+ list_for_each_entry_safe(kvg, tmp, &kv->group_list, node) {
+ kvm_vfio_group_put_external_user(kvg->vfio_group);
+ list_del(&kvg->node);
+ kfree(kvg);
+ }
+
+ kfree(kv);
+ kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+}
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static struct kvm_device_ops kvm_vfio_ops = {
+ .name = "kvm-vfio",
+ .create = kvm_vfio_create,
+ .destroy = kvm_vfio_destroy,
+ .set_attr = kvm_vfio_set_attr,
+ .has_attr = kvm_vfio_has_attr,
+};
+
+static int kvm_vfio_create(struct kvm_device *dev, u32 type)
+{
+ struct kvm_device *tmp;
+ struct kvm_vfio *kv;
+
+ /* Only one VFIO "device" per VM */
+ list_for_each_entry(tmp, &dev->kvm->devices, vm_node)
+ if (tmp->ops == &kvm_vfio_ops)
+ return -EBUSY;
+
+ kv = kzalloc(sizeof(*kv), GFP_KERNEL);
+ if (!kv)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&kv->group_list);
+ mutex_init(&kv->lock);
+
+ dev->private = kv;
+
+ return 0;
+}
+
+static int __init kvm_vfio_ops_init(void)
+{
+ return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
+module_init(kvm_vfio_ops_init);